* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-15 13:19 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-15 13:19 UTC (permalink / raw
To: gentoo-commits
commit: 3b50392746348d310486cd36f2067df9812990a6
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Thu Aug 15 13:19:10 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Thu Aug 15 13:19:10 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=3b503927
tools lib subcmd: Fixed uninitialized use of variable in parse-options
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +++
2901_tools-lib-subcmd-compile-fix.patch | 54 +++++++++++++++++++++++++++++++++
2 files changed, 58 insertions(+)
diff --git a/0000_README b/0000_README
index 46799647..845e8cff 100644
--- a/0000_README
+++ b/0000_README
@@ -87,6 +87,10 @@ Patch: 2900_tmp513-Fix-build-issue-by-selecting-CONFIG_REG.patch
From: https://bugs.gentoo.org/710790
Desc: tmp513 requies REGMAP_I2C to build. Select it by default in Kconfig. See bug #710790. Thanks to Phil Stracchino
+Patch: 2901_tools-lib-subcmd-compile-fix.patch
+From: https://lore.kernel.org/all/20240731085217.94928-1-michael.weiss@aisec.fraunhofer.de/
+Desc: tools lib subcmd: Fixed uninitialized use of variable in parse-options
+
Patch: 2910_bfp-mark-get-entry-ip-as--maybe-unused.patch
From: https://www.spinics.net/lists/stable/msg604665.html
Desc: bpf: mark get_entry_ip as __maybe_unused
diff --git a/2901_tools-lib-subcmd-compile-fix.patch b/2901_tools-lib-subcmd-compile-fix.patch
new file mode 100644
index 00000000..bb1f7ffd
--- /dev/null
+++ b/2901_tools-lib-subcmd-compile-fix.patch
@@ -0,0 +1,54 @@
+From git@z Thu Jan 1 00:00:00 1970
+Subject: [PATCH] tools lib subcmd: Fixed uninitialized use of variable in
+ parse-options
+From: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
+Date: Wed, 31 Jul 2024 10:52:17 +0200
+Message-Id: <20240731085217.94928-1-michael.weiss@aisec.fraunhofer.de>
+MIME-Version: 1.0
+Content-Type: text/plain; charset="utf-8"
+Content-Transfer-Encoding: 8bit
+
+Since commit ea558c86248b ("tools lib subcmd: Show parent options in
+help"), our debug images fail to build.
+
+For our Yocto-based GyroidOS, we build debug images with debugging enabled
+for all binaries including the kernel. Yocto passes the corresponding gcc
+option "-Og" also to the kernel HOSTCFLAGS. This results in the following
+build error:
+
+ parse-options.c: In function ‘options__order’:
+ parse-options.c:834:9: error: ‘o’ may be used uninitialized [-Werror=maybe-uninitialized]
+ 834 | memcpy(&ordered[nr_opts], o, sizeof(*o));
+ | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+ parse-options.c:812:30: note: ‘o’ was declared here
+ 812 | const struct option *o, *p = opts;
+ | ^
+ ..
+
+Fix it by initializing 'o' instead of 'p' in the above failing line 812.
+'p' is initialized afterwards in the following for-loop anyway.
+I think that was the intention of the commit ea558c86248b ("tools lib
+subcmd: Show parent options in help") in the first place.
+
+Fixes: ea558c86248b ("tools lib subcmd: Show parent options in help")
+Signed-off-by: Michael Weiß <michael.weiss@aisec.fraunhofer.de>
+---
+ tools/lib/subcmd/parse-options.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/tools/lib/subcmd/parse-options.c b/tools/lib/subcmd/parse-options.c
+index 4b60ec03b0bb..2a3b51a690c7 100644
+--- a/tools/lib/subcmd/parse-options.c
++++ b/tools/lib/subcmd/parse-options.c
+@@ -809,7 +809,7 @@ static int option__cmp(const void *va, const void *vb)
+ static struct option *options__order(const struct option *opts)
+ {
+ int nr_opts = 0, nr_group = 0, nr_parent = 0, len;
+- const struct option *o, *p = opts;
++ const struct option *o = opts, *p;
+ struct option *opt, *ordered = NULL, *group;
+
+ /* flatten the options that have parents */
+--
+2.39.2
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-10-04 15:22 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-10-04 15:22 UTC (permalink / raw
To: gentoo-commits
commit: 78a0c5de0cf3d9086eb4023a7425f4802f64d3a6
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Fri Oct 4 15:22:11 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Fri Oct 4 15:22:11 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=78a0c5de
Linux patch 6.10.13
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1012_linux-6.10.13.patch | 28977 +++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 28981 insertions(+)
diff --git a/0000_README b/0000_README
index f735905c..fdea4bd1 100644
--- a/0000_README
+++ b/0000_README
@@ -91,6 +91,10 @@ Patch: 1011_linux-6.10.12.patch
From: https://www.kernel.org
Desc: Linux 6.10.12
+Patch: 1012_linux-6.10.13.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.13
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1012_linux-6.10.13.patch b/1012_linux-6.10.13.patch
new file mode 100644
index 00000000..0fe55b0f
--- /dev/null
+++ b/1012_linux-6.10.13.patch
@@ -0,0 +1,28977 @@
+diff --git a/.gitignore b/.gitignore
+index c59dc60ba62ef0..7acc74c54ded5b 100644
+--- a/.gitignore
++++ b/.gitignore
+@@ -136,7 +136,6 @@ GTAGS
+ # id-utils files
+ ID
+
+-*.orig
+ *~
+ \#*#
+
+diff --git a/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818 b/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818
+index 31dbb390573ff2..c431f0a13cf502 100644
+--- a/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818
++++ b/Documentation/ABI/testing/sysfs-bus-iio-filter-admv8818
+@@ -3,7 +3,7 @@ KernelVersion:
+ Contact: linux-iio@vger.kernel.org
+ Description:
+ Reading this returns the valid values that can be written to the
+- on_altvoltage0_mode attribute:
++ filter_mode attribute:
+
+ - auto -> Adjust bandpass filter to track changes in input clock rate.
+ - manual -> disable/unregister the clock rate notifier / input clock tracking.
+diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
+index 50327c05be8d1b..39c52385f11fb3 100644
+--- a/Documentation/arch/arm64/silicon-errata.rst
++++ b/Documentation/arch/arm64/silicon-errata.rst
+@@ -55,6 +55,8 @@ stable kernels.
+ +----------------+-----------------+-----------------+-----------------------------+
+ | Ampere | AmpereOne | AC03_CPU_38 | AMPERE_ERRATUM_AC03_CPU_38 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| Ampere | AmpereOne AC04 | AC04_CPU_10 | AMPERE_ERRATUM_AC03_CPU_38 |
+++----------------+-----------------+-----------------+-----------------------------+
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A510 | #2457168 | ARM64_ERRATUM_2457168 |
+ +----------------+-----------------+-----------------+-----------------------------+
+diff --git a/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml b/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml
+index 9790f75fc669ef..fe5145d3b73cf2 100644
+--- a/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml
++++ b/Documentation/devicetree/bindings/iio/magnetometer/asahi-kasei,ak8975.yaml
+@@ -23,7 +23,6 @@ properties:
+ - ak8963
+ - ak09911
+ - ak09912
+- - ak09916
+ deprecated: true
+
+ reg:
+diff --git a/Documentation/devicetree/bindings/pci/fsl,layerscape-pcie.yaml b/Documentation/devicetree/bindings/pci/fsl,layerscape-pcie.yaml
+index 793986c5af7ff3..daeab5c0758d14 100644
+--- a/Documentation/devicetree/bindings/pci/fsl,layerscape-pcie.yaml
++++ b/Documentation/devicetree/bindings/pci/fsl,layerscape-pcie.yaml
+@@ -22,18 +22,20 @@ description:
+
+ properties:
+ compatible:
+- enum:
+- - fsl,ls1021a-pcie
+- - fsl,ls2080a-pcie
+- - fsl,ls2085a-pcie
+- - fsl,ls2088a-pcie
+- - fsl,ls1088a-pcie
+- - fsl,ls1046a-pcie
+- - fsl,ls1043a-pcie
+- - fsl,ls1012a-pcie
+- - fsl,ls1028a-pcie
+- - fsl,lx2160a-pcie
+-
++ oneOf:
++ - enum:
++ - fsl,ls1012a-pcie
++ - fsl,ls1021a-pcie
++ - fsl,ls1028a-pcie
++ - fsl,ls1043a-pcie
++ - fsl,ls1046a-pcie
++ - fsl,ls1088a-pcie
++ - fsl,ls2080a-pcie
++ - fsl,ls2085a-pcie
++ - fsl,ls2088a-pcie
++ - items:
++ - const: fsl,lx2160ar2-pcie
++ - const: fsl,ls2088a-pcie
+ reg:
+ maxItems: 2
+
+diff --git a/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml b/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml
+index 4a5f41bde00f3c..902db92da83207 100644
+--- a/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml
++++ b/Documentation/devicetree/bindings/spi/spi-nxp-fspi.yaml
+@@ -21,6 +21,7 @@ properties:
+ - nxp,imx8mm-fspi
+ - nxp,imx8mp-fspi
+ - nxp,imx8qxp-fspi
++ - nxp,imx8ulp-fspi
+ - nxp,lx2160a-fspi
+ - items:
+ - enum:
+diff --git a/Documentation/driver-api/ipmi.rst b/Documentation/driver-api/ipmi.rst
+index e224e47b6b0944..dfa021eacd63c4 100644
+--- a/Documentation/driver-api/ipmi.rst
++++ b/Documentation/driver-api/ipmi.rst
+@@ -540,7 +540,7 @@ at module load time (for a module) with::
+ alerts_broken
+
+ The addresses are normal I2C addresses. The adapter is the string
+-name of the adapter, as shown in /sys/class/i2c-adapter/i2c-<n>/name.
++name of the adapter, as shown in /sys/bus/i2c/devices/i2c-<n>/name.
+ It is *NOT* i2c-<n> itself. Also, the comparison is done ignoring
+ spaces, so if the name is "This is an I2C chip" you can say
+ adapter_name=ThisisanI2cchip. This is because it's hard to pass in
+diff --git a/Documentation/filesystems/mount_api.rst b/Documentation/filesystems/mount_api.rst
+index 9aaf6ef75eb53b..317934c9e8fcac 100644
+--- a/Documentation/filesystems/mount_api.rst
++++ b/Documentation/filesystems/mount_api.rst
+@@ -645,6 +645,8 @@ The members are as follows:
+ fs_param_is_blockdev Blockdev path * Needs lookup
+ fs_param_is_path Path * Needs lookup
+ fs_param_is_fd File descriptor result->int_32
++ fs_param_is_uid User ID (u32) result->uid
++ fs_param_is_gid Group ID (u32) result->gid
+ ======================= ======================= =====================
+
+ Note that if the value is of fs_param_is_bool type, fs_parse() will try
+@@ -678,6 +680,8 @@ The members are as follows:
+ fsparam_bdev() fs_param_is_blockdev
+ fsparam_path() fs_param_is_path
+ fsparam_fd() fs_param_is_fd
++ fsparam_uid() fs_param_is_uid
++ fsparam_gid() fs_param_is_gid
+ ======================= ===============================================
+
+ all of which take two arguments, name string and option number - for
+@@ -784,8 +788,9 @@ process the parameters it is given.
+ option number (which it returns).
+
+ If successful, and if the parameter type indicates the result is a
+- boolean, integer or enum type, the value is converted by this function and
+- the result stored in result->{boolean,int_32,uint_32,uint_64}.
++ boolean, integer, enum, uid, or gid type, the value is converted by this
++ function and the result stored in
++ result->{boolean,int_32,uint_32,uint_64,uid,gid}.
+
+ If a match isn't initially made, the key is prefixed with "no" and no
+ value is present then an attempt will be made to look up the key with the
+diff --git a/Documentation/virt/kvm/locking.rst b/Documentation/virt/kvm/locking.rst
+index 02880d5552d5fa..198a5a8f26c2da 100644
+--- a/Documentation/virt/kvm/locking.rst
++++ b/Documentation/virt/kvm/locking.rst
+@@ -9,7 +9,7 @@ KVM Lock Overview
+
+ The acquisition orders for mutexes are as follows:
+
+-- cpus_read_lock() is taken outside kvm_lock
++- cpus_read_lock() is taken outside kvm_lock and kvm_usage_lock
+
+ - kvm->lock is taken outside vcpu->mutex
+
+@@ -24,6 +24,13 @@ The acquisition orders for mutexes are as follows:
+ are taken on the waiting side when modifying memslots, so MMU notifiers
+ must not take either kvm->slots_lock or kvm->slots_arch_lock.
+
++cpus_read_lock() vs kvm_lock:
++
++- Taking cpus_read_lock() outside of kvm_lock is problematic, despite that
++ being the official ordering, as it is quite easy to unknowingly trigger
++ cpus_read_lock() while holding kvm_lock. Use caution when walking vm_list,
++ e.g. avoid complex operations when possible.
++
+ For SRCU:
+
+ - ``synchronize_srcu(&kvm->srcu)`` is called inside critical sections
+@@ -227,10 +234,17 @@ time it will be set using the Dirty tracking mechanism described above.
+ :Type: mutex
+ :Arch: any
+ :Protects: - vm_list
+- - kvm_usage_count
++
++``kvm_usage_lock``
++^^^^^^^^^^^^^^^^^^
++
++:Type: mutex
++:Arch: any
++:Protects: - kvm_usage_count
+ - hardware virtualization enable/disable
+-:Comment: KVM also disables CPU hotplug via cpus_read_lock() during
+- enable/disable.
++:Comment: Exists because using kvm_lock leads to deadlock (see earlier comment
++ on cpus_read_lock() vs kvm_lock). Note, KVM also disables CPU hotplug via
++ cpus_read_lock() when enabling/disabling virtualization.
+
+ ``kvm->mn_invalidate_lock``
+ ^^^^^^^^^^^^^^^^^^^^^^^^^^^
+@@ -290,11 +304,12 @@ time it will be set using the Dirty tracking mechanism described above.
+ wakeup.
+
+ ``vendor_module_lock``
+-^^^^^^^^^^^^^^^^^^^^^^^^^^^^
++^^^^^^^^^^^^^^^^^^^^^^
+ :Type: mutex
+ :Arch: x86
+ :Protects: loading a vendor module (kvm_amd or kvm_intel)
+-:Comment: Exists because using kvm_lock leads to deadlock. cpu_hotplug_lock is
+- taken outside of kvm_lock, e.g. in KVM's CPU online/offline callbacks, and
+- many operations need to take cpu_hotplug_lock when loading a vendor module,
+- e.g. updating static calls.
++:Comment: Exists because using kvm_lock leads to deadlock. kvm_lock is taken
++ in notifiers, e.g. __kvmclock_cpufreq_notifier(), that may be invoked while
++ cpu_hotplug_lock is held, e.g. from cpufreq_boost_trigger_state(), and many
++ operations need to take cpu_hotplug_lock when loading a vendor module, e.g.
++ updating static calls.
+diff --git a/Makefile b/Makefile
+index 175d7f27ea32a4..93731d0b1a04ac 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 12
++SUBLEVEL = 13
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm/boot/dts/microchip/sam9x60.dtsi b/arch/arm/boot/dts/microchip/sam9x60.dtsi
+index 291540e5d81e76..d077afd5024db1 100644
+--- a/arch/arm/boot/dts/microchip/sam9x60.dtsi
++++ b/arch/arm/boot/dts/microchip/sam9x60.dtsi
+@@ -1312,7 +1312,7 @@ rtt: rtc@fffffe20 {
+ compatible = "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt";
+ reg = <0xfffffe20 0x20>;
+ interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+- clocks = <&clk32k 0>;
++ clocks = <&clk32k 1>;
+ };
+
+ pit: timer@fffffe40 {
+@@ -1338,7 +1338,7 @@ rtc: rtc@fffffea8 {
+ compatible = "microchip,sam9x60-rtc", "atmel,at91sam9x5-rtc";
+ reg = <0xfffffea8 0x100>;
+ interrupts = <1 IRQ_TYPE_LEVEL_HIGH 7>;
+- clocks = <&clk32k 0>;
++ clocks = <&clk32k 1>;
+ };
+
+ watchdog: watchdog@ffffff80 {
+diff --git a/arch/arm/boot/dts/microchip/sama7g5.dtsi b/arch/arm/boot/dts/microchip/sama7g5.dtsi
+index 75778be126a3d9..17bcdcf0cf4a05 100644
+--- a/arch/arm/boot/dts/microchip/sama7g5.dtsi
++++ b/arch/arm/boot/dts/microchip/sama7g5.dtsi
+@@ -272,7 +272,7 @@ rtt: rtc@e001d020 {
+ compatible = "microchip,sama7g5-rtt", "microchip,sam9x60-rtt", "atmel,at91sam9260-rtt";
+ reg = <0xe001d020 0x30>;
+ interrupts = <GIC_SPI 8 IRQ_TYPE_LEVEL_HIGH>;
+- clocks = <&clk32k 0>;
++ clocks = <&clk32k 1>;
+ };
+
+ clk32k: clock-controller@e001d050 {
+diff --git a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
+index cdbb8c435cd6aa..601d89b904cdfb 100644
+--- a/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
++++ b/arch/arm/boot/dts/nxp/imx/imx6ul-geam.dts
+@@ -365,7 +365,7 @@ MX6UL_PAD_ENET1_RX_ER__PWM8_OUT 0x110b0
+ };
+
+ pinctrl_tsc: tscgrp {
+- fsl,pin = <
++ fsl,pins = <
+ MX6UL_PAD_GPIO1_IO01__GPIO1_IO01 0xb0
+ MX6UL_PAD_GPIO1_IO02__GPIO1_IO02 0xb0
+ MX6UL_PAD_GPIO1_IO03__GPIO1_IO03 0xb0
+diff --git a/arch/arm/boot/dts/nxp/imx/imx6ull-seeed-npi-dev-board.dtsi b/arch/arm/boot/dts/nxp/imx/imx6ull-seeed-npi-dev-board.dtsi
+index 6bb12e0bbc7ec6..50654dbf62e02c 100644
+--- a/arch/arm/boot/dts/nxp/imx/imx6ull-seeed-npi-dev-board.dtsi
++++ b/arch/arm/boot/dts/nxp/imx/imx6ull-seeed-npi-dev-board.dtsi
+@@ -339,14 +339,14 @@ MX6UL_PAD_JTAG_TRST_B__SAI2_TX_DATA 0x120b0
+ };
+
+ pinctrl_uart1: uart1grp {
+- fsl,pin = <
++ fsl,pins = <
+ MX6UL_PAD_UART1_TX_DATA__UART1_DCE_TX 0x1b0b1
+ MX6UL_PAD_UART1_RX_DATA__UART1_DCE_RX 0x1b0b1
+ >;
+ };
+
+ pinctrl_uart2: uart2grp {
+- fsl,pin = <
++ fsl,pins = <
+ MX6UL_PAD_UART2_TX_DATA__UART2_DCE_TX 0x1b0b1
+ MX6UL_PAD_UART2_RX_DATA__UART2_DCE_RX 0x1b0b1
+ MX6UL_PAD_UART2_CTS_B__UART2_DCE_CTS 0x1b0b1
+@@ -355,7 +355,7 @@ MX6UL_PAD_UART2_RTS_B__UART2_DCE_RTS 0x1b0b1
+ };
+
+ pinctrl_uart3: uart3grp {
+- fsl,pin = <
++ fsl,pins = <
+ MX6UL_PAD_UART3_TX_DATA__UART3_DCE_TX 0x1b0b1
+ MX6UL_PAD_UART3_RX_DATA__UART3_DCE_RX 0x1b0b1
+ MX6UL_PAD_UART3_CTS_B__UART3_DCE_CTS 0x1b0b1
+@@ -364,21 +364,21 @@ MX6UL_PAD_UART3_RTS_B__UART3_DCE_RTS 0x1b0b1
+ };
+
+ pinctrl_uart4: uart4grp {
+- fsl,pin = <
++ fsl,pins = <
+ MX6UL_PAD_UART4_TX_DATA__UART4_DCE_TX 0x1b0b1
+ MX6UL_PAD_UART4_RX_DATA__UART4_DCE_RX 0x1b0b1
+ >;
+ };
+
+ pinctrl_uart5: uart5grp {
+- fsl,pin = <
++ fsl,pins = <
+ MX6UL_PAD_UART5_TX_DATA__UART5_DCE_TX 0x1b0b1
+ MX6UL_PAD_UART5_RX_DATA__UART5_DCE_RX 0x1b0b1
+ >;
+ };
+
+ pinctrl_usb_otg1_id: usbotg1idgrp {
+- fsl,pin = <
++ fsl,pins = <
+ MX6UL_PAD_GPIO1_IO00__ANATOP_OTG1_ID 0x17059
+ >;
+ };
+diff --git a/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts b/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts
+index 521493342fe972..8f5566027c25a2 100644
+--- a/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts
++++ b/arch/arm/boot/dts/nxp/imx/imx7d-zii-rmu2.dts
+@@ -350,7 +350,7 @@ MX7D_PAD_SD3_RESET_B__SD3_RESET_B 0x59
+
+ &iomuxc_lpsr {
+ pinctrl_enet1_phy_interrupt: enet1phyinterruptgrp {
+- fsl,phy = <
++ fsl,pins = <
+ MX7D_PAD_LPSR_GPIO1_IO02__GPIO1_IO2 0x08
+ >;
+ };
+diff --git a/arch/arm/mach-ep93xx/clock.c b/arch/arm/mach-ep93xx/clock.c
+index 85a496ddc6197e..e9f72a529b5089 100644
+--- a/arch/arm/mach-ep93xx/clock.c
++++ b/arch/arm/mach-ep93xx/clock.c
+@@ -359,7 +359,7 @@ static unsigned long ep93xx_div_recalc_rate(struct clk_hw *hw,
+ u32 val = __raw_readl(psc->reg);
+ u8 index = (val & psc->mask) >> psc->shift;
+
+- if (index > psc->num_div)
++ if (index >= psc->num_div)
+ return 0;
+
+ return DIV_ROUND_UP_ULL(parent_rate, psc->div[index]);
+diff --git a/arch/arm/mach-versatile/platsmp-realview.c b/arch/arm/mach-versatile/platsmp-realview.c
+index 6965a1de727b07..d38b2e174257e8 100644
+--- a/arch/arm/mach-versatile/platsmp-realview.c
++++ b/arch/arm/mach-versatile/platsmp-realview.c
+@@ -70,6 +70,7 @@ static void __init realview_smp_prepare_cpus(unsigned int max_cpus)
+ return;
+ }
+ map = syscon_node_to_regmap(np);
++ of_node_put(np);
+ if (IS_ERR(map)) {
+ pr_err("PLATSMP: No syscon regmap\n");
+ return;
+diff --git a/arch/arm/vfp/vfpinstr.h b/arch/arm/vfp/vfpinstr.h
+index 3c7938fd40aad6..32090b0fb250b8 100644
+--- a/arch/arm/vfp/vfpinstr.h
++++ b/arch/arm/vfp/vfpinstr.h
+@@ -64,33 +64,37 @@
+
+ #ifdef CONFIG_AS_VFP_VMRS_FPINST
+
+-#define fmrx(_vfp_) ({ \
+- u32 __v; \
+- asm(".fpu vfpv2\n" \
+- "vmrs %0, " #_vfp_ \
+- : "=r" (__v) : : "cc"); \
+- __v; \
+- })
+-
+-#define fmxr(_vfp_,_var_) \
+- asm(".fpu vfpv2\n" \
+- "vmsr " #_vfp_ ", %0" \
+- : : "r" (_var_) : "cc")
++#define fmrx(_vfp_) ({ \
++ u32 __v; \
++ asm volatile (".fpu vfpv2\n" \
++ "vmrs %0, " #_vfp_ \
++ : "=r" (__v) : : "cc"); \
++ __v; \
++})
++
++#define fmxr(_vfp_, _var_) ({ \
++ asm volatile (".fpu vfpv2\n" \
++ "vmsr " #_vfp_ ", %0" \
++ : : "r" (_var_) : "cc"); \
++})
+
+ #else
+
+ #define vfpreg(_vfp_) #_vfp_
+
+-#define fmrx(_vfp_) ({ \
+- u32 __v; \
+- asm("mrc p10, 7, %0, " vfpreg(_vfp_) ", cr0, 0 @ fmrx %0, " #_vfp_ \
+- : "=r" (__v) : : "cc"); \
+- __v; \
+- })
+-
+-#define fmxr(_vfp_,_var_) \
+- asm("mcr p10, 7, %0, " vfpreg(_vfp_) ", cr0, 0 @ fmxr " #_vfp_ ", %0" \
+- : : "r" (_var_) : "cc")
++#define fmrx(_vfp_) ({ \
++ u32 __v; \
++ asm volatile ("mrc p10, 7, %0, " vfpreg(_vfp_) "," \
++ "cr0, 0 @ fmrx %0, " #_vfp_ \
++ : "=r" (__v) : : "cc"); \
++ __v; \
++})
++
++#define fmxr(_vfp_, _var_) ({ \
++ asm volatile ("mcr p10, 7, %0, " vfpreg(_vfp_) "," \
++ "cr0, 0 @ fmxr " #_vfp_ ", %0" \
++ : : "r" (_var_) : "cc"); \
++})
+
+ #endif
+
+diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
+index 11bbdc15c6e5e2..cd9772b1fd95ee 100644
+--- a/arch/arm64/Kconfig
++++ b/arch/arm64/Kconfig
+@@ -422,7 +422,7 @@ config AMPERE_ERRATUM_AC03_CPU_38
+ default y
+ help
+ This option adds an alternative code sequence to work around Ampere
+- erratum AC03_CPU_38 on AmpereOne.
++ errata AC03_CPU_38 and AC04_CPU_10 on AmpereOne.
+
+ The affected design reports FEAT_HAFDBS as not implemented in
+ ID_AA64MMFR1_EL1.HAFDBS, but (V)TCR_ELx.{HA,HD} are not RES0
+diff --git a/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts b/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts
+index 47a389d9ff7d71..9d74fa6bfed9fb 100644
+--- a/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts
++++ b/arch/arm64/boot/dts/exynos/exynos7885-jackpotlte.dts
+@@ -32,7 +32,7 @@ memory@80000000 {
+ device_type = "memory";
+ reg = <0x0 0x80000000 0x3da00000>,
+ <0x0 0xc0000000 0x40000000>,
+- <0x8 0x80000000 0x40000000>;
++ <0x8 0x80000000 0x80000000>;
+ };
+
+ gpio-keys {
+diff --git a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
+index 1807e9d6cb0e41..0a4838b35eab6e 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8186-corsola.dtsi
+@@ -321,7 +321,8 @@ &dpi {
+ pinctrl-names = "default", "sleep";
+ pinctrl-0 = <&dpi_pins_default>;
+ pinctrl-1 = <&dpi_pins_sleep>;
+- status = "okay";
++ /* TODO Re-enable after DP to Type-C port muxing can be described */
++ status = "disabled";
+ };
+
+ &dpi_out {
+diff --git a/arch/arm64/boot/dts/mediatek/mt8186.dtsi b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
+index 4763ed5dc86cfb..d63a9defe73e17 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8186.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8186.dtsi
+@@ -731,7 +731,7 @@ opp-850000000 {
+ opp-900000000-3 {
+ opp-hz = /bits/ 64 <900000000>;
+ opp-microvolt = <850000>;
+- opp-supported-hw = <0x8>;
++ opp-supported-hw = <0xcf>;
+ };
+
+ opp-900000000-4 {
+@@ -743,13 +743,13 @@ opp-900000000-4 {
+ opp-900000000-5 {
+ opp-hz = /bits/ 64 <900000000>;
+ opp-microvolt = <825000>;
+- opp-supported-hw = <0x30>;
++ opp-supported-hw = <0x20>;
+ };
+
+ opp-950000000-3 {
+ opp-hz = /bits/ 64 <950000000>;
+ opp-microvolt = <900000>;
+- opp-supported-hw = <0x8>;
++ opp-supported-hw = <0xcf>;
+ };
+
+ opp-950000000-4 {
+@@ -761,13 +761,13 @@ opp-950000000-4 {
+ opp-950000000-5 {
+ opp-hz = /bits/ 64 <950000000>;
+ opp-microvolt = <850000>;
+- opp-supported-hw = <0x30>;
++ opp-supported-hw = <0x20>;
+ };
+
+ opp-1000000000-3 {
+ opp-hz = /bits/ 64 <1000000000>;
+ opp-microvolt = <950000>;
+- opp-supported-hw = <0x8>;
++ opp-supported-hw = <0xcf>;
+ };
+
+ opp-1000000000-4 {
+@@ -779,7 +779,7 @@ opp-1000000000-4 {
+ opp-1000000000-5 {
+ opp-hz = /bits/ 64 <1000000000>;
+ opp-microvolt = <875000>;
+- opp-supported-hw = <0x30>;
++ opp-supported-hw = <0x20>;
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+index 4a11918da37048..5a2d65edf4740f 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8195-cherry.dtsi
+@@ -1359,6 +1359,7 @@ &xhci1 {
+ rx-fifo-depth = <3072>;
+ vusb33-supply = <&mt6359_vusb_ldo_reg>;
+ vbus-supply = <&usb_vbus>;
++ mediatek,u3p-dis-msk = <1>;
+ };
+
+ &xhci2 {
+diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+index 2ee45752583c00..98c15eb68589a5 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+@@ -3251,10 +3251,10 @@ dp_intf0: dp-intf@1c015000 {
+ compatible = "mediatek,mt8195-dp-intf";
+ reg = <0 0x1c015000 0 0x1000>;
+ interrupts = <GIC_SPI 657 IRQ_TYPE_LEVEL_HIGH 0>;
+- clocks = <&vdosys0 CLK_VDO0_DP_INTF0>,
+- <&vdosys0 CLK_VDO0_DP_INTF0_DP_INTF>,
++ clocks = <&vdosys0 CLK_VDO0_DP_INTF0_DP_INTF>,
++ <&vdosys0 CLK_VDO0_DP_INTF0>,
+ <&apmixedsys CLK_APMIXED_TVDPLL1>;
+- clock-names = "engine", "pixel", "pll";
++ clock-names = "pixel", "engine", "pll";
+ status = "disabled";
+ };
+
+@@ -3521,10 +3521,10 @@ dp_intf1: dp-intf@1c113000 {
+ reg = <0 0x1c113000 0 0x1000>;
+ interrupts = <GIC_SPI 513 IRQ_TYPE_LEVEL_HIGH 0>;
+ power-domains = <&spm MT8195_POWER_DOMAIN_VDOSYS1>;
+- clocks = <&vdosys1 CLK_VDO1_DP_INTF0_MM>,
+- <&vdosys1 CLK_VDO1_DPINTF>,
++ clocks = <&vdosys1 CLK_VDO1_DPINTF>,
++ <&vdosys1 CLK_VDO1_DP_INTF0_MM>,
+ <&apmixedsys CLK_APMIXED_TVDPLL2>;
+- clock-names = "engine", "pixel", "pll";
++ clock-names = "pixel", "engine", "pll";
+ status = "disabled";
+ };
+
+diff --git a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
+index 97634cc04e659f..e2634590ca81f7 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
++++ b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
+@@ -816,6 +816,7 @@ &xhci1 {
+ usb2-lpm-disable;
+ vusb33-supply = <&mt6359_vusb_ldo_reg>;
+ vbus-supply = <&vsys>;
++ mediatek,u3p-dis-msk = <1>;
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3701-0008.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3701-0008.dtsi
+index 553fa4ba1cd48a..62c4fdad0b600b 100644
+--- a/arch/arm64/boot/dts/nvidia/tegra234-p3701-0008.dtsi
++++ b/arch/arm64/boot/dts/nvidia/tegra234-p3701-0008.dtsi
+@@ -44,39 +44,6 @@ i2c@c240000 {
+ status = "okay";
+ };
+
+- i2c@c250000 {
+- power-sensor@41 {
+- compatible = "ti,ina3221";
+- reg = <0x41>;
+- #address-cells = <1>;
+- #size-cells = <0>;
+-
+- input@0 {
+- reg = <0x0>;
+- label = "CVB_ATX_12V";
+- shunt-resistor-micro-ohms = <2000>;
+- };
+-
+- input@1 {
+- reg = <0x1>;
+- label = "CVB_ATX_3V3";
+- shunt-resistor-micro-ohms = <2000>;
+- };
+-
+- input@2 {
+- reg = <0x2>;
+- label = "CVB_ATX_5V";
+- shunt-resistor-micro-ohms = <2000>;
+- };
+- };
+-
+- power-sensor@44 {
+- compatible = "ti,ina219";
+- reg = <0x44>;
+- shunt-resistor = <2000>;
+- };
+- };
+-
+ rtc@c2a0000 {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002.dtsi b/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002.dtsi
+index 527f2f3aee3ad4..377f518bd3e57b 100644
+--- a/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002.dtsi
++++ b/arch/arm64/boot/dts/nvidia/tegra234-p3740-0002.dtsi
+@@ -183,6 +183,39 @@ usb@3610000 {
+ phy-names = "usb2-0", "usb2-1", "usb2-2", "usb2-3",
+ "usb3-0", "usb3-1", "usb3-2";
+ };
++
++ i2c@c250000 {
++ power-sensor@41 {
++ compatible = "ti,ina3221";
++ reg = <0x41>;
++ #address-cells = <1>;
++ #size-cells = <0>;
++
++ input@0 {
++ reg = <0x0>;
++ label = "CVB_ATX_12V";
++ shunt-resistor-micro-ohms = <2000>;
++ };
++
++ input@1 {
++ reg = <0x1>;
++ label = "CVB_ATX_3V3";
++ shunt-resistor-micro-ohms = <2000>;
++ };
++
++ input@2 {
++ reg = <0x2>;
++ label = "CVB_ATX_5V";
++ shunt-resistor-micro-ohms = <2000>;
++ };
++ };
++
++ power-sensor@44 {
++ compatible = "ti,ina219";
++ reg = <0x44>;
++ shunt-resistor = <2000>;
++ };
++ };
+ };
+
+ vdd_3v3_dp: regulator-vdd-3v3-dp {
+diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
+index 490e0369f52993..3a51e79af1bb6c 100644
+--- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi
++++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
+@@ -2104,6 +2104,7 @@ apps_smmu: iommu@15000000 {
+ reg = <0x0 0x15000000 0x0 0x100000>;
+ #iommu-cells = <2>;
+ #global-interrupts = <2>;
++ dma-coherent;
+
+ interrupts = <GIC_SPI 119 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 120 IRQ_TYPE_LEVEL_HIGH>,
+@@ -2242,6 +2243,7 @@ pcie_smmu: iommu@15200000 {
+ reg = <0x0 0x15200000 0x0 0x80000>;
+ #iommu-cells = <2>;
+ #global-interrupts = <2>;
++ dma-coherent;
+
+ interrupts = <GIC_SPI 920 IRQ_TYPE_LEVEL_HIGH>,
+ <GIC_SPI 921 IRQ_TYPE_LEVEL_HIGH>,
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+index 36c398e5fe5016..64d5f6e4c0b018 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi
++++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+@@ -3998,14 +3998,14 @@ mdss_dp2: displayport-controller@ae9a000 {
+
+ assigned-clocks = <&dispcc DISP_CC_MDSS_DPTX2_LINK_CLK_SRC>,
+ <&dispcc DISP_CC_MDSS_DPTX2_PIXEL0_CLK_SRC>;
+- assigned-clock-parents = <&mdss_dp2_phy 0>,
+- <&mdss_dp2_phy 1>;
++ assigned-clock-parents = <&usb_1_ss2_qmpphy QMP_USB43DP_DP_LINK_CLK>,
++ <&usb_1_ss2_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>;
+
+ operating-points-v2 = <&mdss_dp2_opp_table>;
+
+ power-domains = <&rpmhpd RPMHPD_MMCX>;
+
+- phys = <&mdss_dp2_phy>;
++ phys = <&usb_1_ss2_qmpphy QMP_USB43DP_DP_PHY>;
+ phy-names = "dp";
+
+ #sound-dai-cells = <0>;
+@@ -4189,8 +4189,8 @@ dispcc: clock-controller@af00000 {
+ <&usb_1_ss0_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>,
+ <&usb_1_ss1_qmpphy QMP_USB43DP_DP_LINK_CLK>, /* dp1 */
+ <&usb_1_ss1_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>,
+- <&mdss_dp2_phy 0>, /* dp2 */
+- <&mdss_dp2_phy 1>,
++ <&usb_1_ss2_qmpphy QMP_USB43DP_DP_LINK_CLK>, /* dp2 */
++ <&usb_1_ss2_qmpphy QMP_USB43DP_DP_VCO_DIV_CLK>,
+ <&mdss_dp3_phy 0>, /* dp3 */
+ <&mdss_dp3_phy 1>;
+ power-domains = <&rpmhpd RPMHPD_MMCX>;
+diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
+index 18ef297db93363..20fb5e41c5988c 100644
+--- a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
+@@ -210,8 +210,8 @@ gic: interrupt-controller@11900000 {
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+- reg = <0x0 0x11900000 0 0x40000>,
+- <0x0 0x11940000 0 0x60000>;
++ reg = <0x0 0x11900000 0 0x20000>,
++ <0x0 0x11940000 0 0x40000>;
+ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_LOW>;
+ };
+ };
+diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
+index 1a9891ba6c02c4..960537e401f4cf 100644
+--- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
+@@ -1043,8 +1043,8 @@ gic: interrupt-controller@11900000 {
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+- reg = <0x0 0x11900000 0 0x40000>,
+- <0x0 0x11940000 0 0x60000>;
++ reg = <0x0 0x11900000 0 0x20000>,
++ <0x0 0x11940000 0 0x40000>;
+ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_LOW>;
+ };
+
+diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
+index a2318478a66ba7..66894b676c01ec 100644
+--- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
+@@ -1051,8 +1051,8 @@ gic: interrupt-controller@11900000 {
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+- reg = <0x0 0x11900000 0 0x40000>,
+- <0x0 0x11940000 0 0x60000>;
++ reg = <0x0 0x11900000 0 0x20000>,
++ <0x0 0x11940000 0 0x40000>;
+ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_LOW>;
+ };
+
+diff --git a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
+index a2adc4e27ce979..17609d81af294f 100644
+--- a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
+@@ -269,8 +269,8 @@ gic: interrupt-controller@12400000 {
+ #interrupt-cells = <3>;
+ #address-cells = <0>;
+ interrupt-controller;
+- reg = <0x0 0x12400000 0 0x40000>,
+- <0x0 0x12440000 0 0x60000>;
++ reg = <0x0 0x12400000 0 0x20000>,
++ <0x0 0x12440000 0 0x40000>;
+ interrupts = <GIC_PPI 9 IRQ_TYPE_LEVEL_LOW>;
+ };
+
+diff --git a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
+index 294eb2de263deb..f5e124b235c83c 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3399-pinebook-pro.dts
+@@ -32,12 +32,12 @@ chosen {
+ backlight: edp-backlight {
+ compatible = "pwm-backlight";
+ power-supply = <&vcc_12v>;
+- pwms = <&pwm0 0 740740 0>;
++ pwms = <&pwm0 0 125000 0>;
+ };
+
+ bat: battery {
+ compatible = "simple-battery";
+- charge-full-design-microamp-hours = <9800000>;
++ charge-full-design-microamp-hours = <10000000>;
+ voltage-max-design-microvolt = <4350000>;
+ voltage-min-design-microvolt = <3000000>;
+ };
+diff --git a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts
+index a337f547caf538..6a02db4f073f29 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3568-odroid-m1.dts
+@@ -13,7 +13,7 @@
+
+ / {
+ model = "Hardkernel ODROID-M1";
+- compatible = "rockchip,rk3568-odroid-m1", "rockchip,rk3568";
++ compatible = "hardkernel,odroid-m1", "rockchip,rk3568";
+
+ aliases {
+ ethernet0 = &gmac0;
+diff --git a/arch/arm64/boot/dts/ti/k3-am654-idk.dtso b/arch/arm64/boot/dts/ti/k3-am654-idk.dtso
+index 8bdb87fcbde007..1674ad564be1fd 100644
+--- a/arch/arm64/boot/dts/ti/k3-am654-idk.dtso
++++ b/arch/arm64/boot/dts/ti/k3-am654-idk.dtso
+@@ -58,9 +58,7 @@ icssg0_eth: icssg0-eth {
+ <&main_udmap 0xc107>, /* egress slice 1 */
+
+ <&main_udmap 0x4100>, /* ingress slice 0 */
+- <&main_udmap 0x4101>, /* ingress slice 1 */
+- <&main_udmap 0x4102>, /* mgmnt rsp slice 0 */
+- <&main_udmap 0x4103>; /* mgmnt rsp slice 1 */
++ <&main_udmap 0x4101>; /* ingress slice 1 */
+ dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3",
+ "tx1-0", "tx1-1", "tx1-2", "tx1-3",
+ "rx0", "rx1";
+@@ -126,9 +124,7 @@ icssg1_eth: icssg1-eth {
+ <&main_udmap 0xc207>, /* egress slice 1 */
+
+ <&main_udmap 0x4200>, /* ingress slice 0 */
+- <&main_udmap 0x4201>, /* ingress slice 1 */
+- <&main_udmap 0x4202>, /* mgmnt rsp slice 0 */
+- <&main_udmap 0x4203>; /* mgmnt rsp slice 1 */
++ <&main_udmap 0x4201>; /* ingress slice 1 */
+ dma-names = "tx0-0", "tx0-1", "tx0-2", "tx0-3",
+ "tx1-0", "tx1-1", "tx1-2", "tx1-3",
+ "rx0", "rx1";
+diff --git a/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts b/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts
+index a2925555fe8180..fb899c99753ecd 100644
+--- a/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts
++++ b/arch/arm64/boot/dts/ti/k3-j721e-beagleboneai64.dts
+@@ -123,7 +123,7 @@ main_r5fss1_core1_memory_region: r5f-memory@a5100000 {
+ no-map;
+ };
+
+- c66_1_dma_memory_region: c66-dma-memory@a6000000 {
++ c66_0_dma_memory_region: c66-dma-memory@a6000000 {
+ compatible = "shared-dma-pool";
+ reg = <0x00 0xa6000000 0x00 0x100000>;
+ no-map;
+@@ -135,7 +135,7 @@ c66_0_memory_region: c66-memory@a6100000 {
+ no-map;
+ };
+
+- c66_0_dma_memory_region: c66-dma-memory@a7000000 {
++ c66_1_dma_memory_region: c66-dma-memory@a7000000 {
+ compatible = "shared-dma-pool";
+ reg = <0x00 0xa7000000 0x00 0x100000>;
+ no-map;
+diff --git a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
+index 0c4575ad8d7cb0..53156b71e47964 100644
+--- a/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
++++ b/arch/arm64/boot/dts/ti/k3-j721e-sk.dts
+@@ -119,7 +119,7 @@ main_r5fss1_core1_memory_region: r5f-memory@a5100000 {
+ no-map;
+ };
+
+- c66_1_dma_memory_region: c66-dma-memory@a6000000 {
++ c66_0_dma_memory_region: c66-dma-memory@a6000000 {
+ compatible = "shared-dma-pool";
+ reg = <0x00 0xa6000000 0x00 0x100000>;
+ no-map;
+@@ -131,7 +131,7 @@ c66_0_memory_region: c66-memory@a6100000 {
+ no-map;
+ };
+
+- c66_0_dma_memory_region: c66-dma-memory@a7000000 {
++ c66_1_dma_memory_region: c66-dma-memory@a7000000 {
+ compatible = "shared-dma-pool";
+ reg = <0x00 0xa7000000 0x00 0x100000>;
+ no-map;
+diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
+index 5fd7caea441936..5a7dfeb8e8eb55 100644
+--- a/arch/arm64/include/asm/cputype.h
++++ b/arch/arm64/include/asm/cputype.h
+@@ -143,6 +143,7 @@
+ #define APPLE_CPU_PART_M2_AVALANCHE_MAX 0x039
+
+ #define AMPERE_CPU_PART_AMPERE1 0xAC3
++#define AMPERE_CPU_PART_AMPERE1A 0xAC4
+
+ #define MICROSOFT_CPU_PART_AZURE_COBALT_100 0xD49 /* Based on r0p0 of ARM Neoverse N2 */
+
+@@ -212,6 +213,7 @@
+ #define MIDR_APPLE_M2_BLIZZARD_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_BLIZZARD_MAX)
+ #define MIDR_APPLE_M2_AVALANCHE_MAX MIDR_CPU_MODEL(ARM_CPU_IMP_APPLE, APPLE_CPU_PART_M2_AVALANCHE_MAX)
+ #define MIDR_AMPERE1 MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1)
++#define MIDR_AMPERE1A MIDR_CPU_MODEL(ARM_CPU_IMP_AMPERE, AMPERE_CPU_PART_AMPERE1A)
+ #define MIDR_MICROSOFT_AZURE_COBALT_100 MIDR_CPU_MODEL(ARM_CPU_IMP_MICROSOFT, MICROSOFT_CPU_PART_AZURE_COBALT_100)
+
+ /* Fujitsu Erratum 010001 affects A64FX 1.0 and 1.1, (v0r0 and v1r0) */
+diff --git a/arch/arm64/include/asm/esr.h b/arch/arm64/include/asm/esr.h
+index 7abf09df70331c..60f4320e44e5d3 100644
+--- a/arch/arm64/include/asm/esr.h
++++ b/arch/arm64/include/asm/esr.h
+@@ -10,63 +10,63 @@
+ #include <asm/memory.h>
+ #include <asm/sysreg.h>
+
+-#define ESR_ELx_EC_UNKNOWN (0x00)
+-#define ESR_ELx_EC_WFx (0x01)
++#define ESR_ELx_EC_UNKNOWN UL(0x00)
++#define ESR_ELx_EC_WFx UL(0x01)
+ /* Unallocated EC: 0x02 */
+-#define ESR_ELx_EC_CP15_32 (0x03)
+-#define ESR_ELx_EC_CP15_64 (0x04)
+-#define ESR_ELx_EC_CP14_MR (0x05)
+-#define ESR_ELx_EC_CP14_LS (0x06)
+-#define ESR_ELx_EC_FP_ASIMD (0x07)
+-#define ESR_ELx_EC_CP10_ID (0x08) /* EL2 only */
+-#define ESR_ELx_EC_PAC (0x09) /* EL2 and above */
++#define ESR_ELx_EC_CP15_32 UL(0x03)
++#define ESR_ELx_EC_CP15_64 UL(0x04)
++#define ESR_ELx_EC_CP14_MR UL(0x05)
++#define ESR_ELx_EC_CP14_LS UL(0x06)
++#define ESR_ELx_EC_FP_ASIMD UL(0x07)
++#define ESR_ELx_EC_CP10_ID UL(0x08) /* EL2 only */
++#define ESR_ELx_EC_PAC UL(0x09) /* EL2 and above */
+ /* Unallocated EC: 0x0A - 0x0B */
+-#define ESR_ELx_EC_CP14_64 (0x0C)
+-#define ESR_ELx_EC_BTI (0x0D)
+-#define ESR_ELx_EC_ILL (0x0E)
++#define ESR_ELx_EC_CP14_64 UL(0x0C)
++#define ESR_ELx_EC_BTI UL(0x0D)
++#define ESR_ELx_EC_ILL UL(0x0E)
+ /* Unallocated EC: 0x0F - 0x10 */
+-#define ESR_ELx_EC_SVC32 (0x11)
+-#define ESR_ELx_EC_HVC32 (0x12) /* EL2 only */
+-#define ESR_ELx_EC_SMC32 (0x13) /* EL2 and above */
++#define ESR_ELx_EC_SVC32 UL(0x11)
++#define ESR_ELx_EC_HVC32 UL(0x12) /* EL2 only */
++#define ESR_ELx_EC_SMC32 UL(0x13) /* EL2 and above */
+ /* Unallocated EC: 0x14 */
+-#define ESR_ELx_EC_SVC64 (0x15)
+-#define ESR_ELx_EC_HVC64 (0x16) /* EL2 and above */
+-#define ESR_ELx_EC_SMC64 (0x17) /* EL2 and above */
+-#define ESR_ELx_EC_SYS64 (0x18)
+-#define ESR_ELx_EC_SVE (0x19)
+-#define ESR_ELx_EC_ERET (0x1a) /* EL2 only */
++#define ESR_ELx_EC_SVC64 UL(0x15)
++#define ESR_ELx_EC_HVC64 UL(0x16) /* EL2 and above */
++#define ESR_ELx_EC_SMC64 UL(0x17) /* EL2 and above */
++#define ESR_ELx_EC_SYS64 UL(0x18)
++#define ESR_ELx_EC_SVE UL(0x19)
++#define ESR_ELx_EC_ERET UL(0x1a) /* EL2 only */
+ /* Unallocated EC: 0x1B */
+-#define ESR_ELx_EC_FPAC (0x1C) /* EL1 and above */
+-#define ESR_ELx_EC_SME (0x1D)
++#define ESR_ELx_EC_FPAC UL(0x1C) /* EL1 and above */
++#define ESR_ELx_EC_SME UL(0x1D)
+ /* Unallocated EC: 0x1E */
+-#define ESR_ELx_EC_IMP_DEF (0x1f) /* EL3 only */
+-#define ESR_ELx_EC_IABT_LOW (0x20)
+-#define ESR_ELx_EC_IABT_CUR (0x21)
+-#define ESR_ELx_EC_PC_ALIGN (0x22)
++#define ESR_ELx_EC_IMP_DEF UL(0x1f) /* EL3 only */
++#define ESR_ELx_EC_IABT_LOW UL(0x20)
++#define ESR_ELx_EC_IABT_CUR UL(0x21)
++#define ESR_ELx_EC_PC_ALIGN UL(0x22)
+ /* Unallocated EC: 0x23 */
+-#define ESR_ELx_EC_DABT_LOW (0x24)
+-#define ESR_ELx_EC_DABT_CUR (0x25)
+-#define ESR_ELx_EC_SP_ALIGN (0x26)
+-#define ESR_ELx_EC_MOPS (0x27)
+-#define ESR_ELx_EC_FP_EXC32 (0x28)
++#define ESR_ELx_EC_DABT_LOW UL(0x24)
++#define ESR_ELx_EC_DABT_CUR UL(0x25)
++#define ESR_ELx_EC_SP_ALIGN UL(0x26)
++#define ESR_ELx_EC_MOPS UL(0x27)
++#define ESR_ELx_EC_FP_EXC32 UL(0x28)
+ /* Unallocated EC: 0x29 - 0x2B */
+-#define ESR_ELx_EC_FP_EXC64 (0x2C)
++#define ESR_ELx_EC_FP_EXC64 UL(0x2C)
+ /* Unallocated EC: 0x2D - 0x2E */
+-#define ESR_ELx_EC_SERROR (0x2F)
+-#define ESR_ELx_EC_BREAKPT_LOW (0x30)
+-#define ESR_ELx_EC_BREAKPT_CUR (0x31)
+-#define ESR_ELx_EC_SOFTSTP_LOW (0x32)
+-#define ESR_ELx_EC_SOFTSTP_CUR (0x33)
+-#define ESR_ELx_EC_WATCHPT_LOW (0x34)
+-#define ESR_ELx_EC_WATCHPT_CUR (0x35)
++#define ESR_ELx_EC_SERROR UL(0x2F)
++#define ESR_ELx_EC_BREAKPT_LOW UL(0x30)
++#define ESR_ELx_EC_BREAKPT_CUR UL(0x31)
++#define ESR_ELx_EC_SOFTSTP_LOW UL(0x32)
++#define ESR_ELx_EC_SOFTSTP_CUR UL(0x33)
++#define ESR_ELx_EC_WATCHPT_LOW UL(0x34)
++#define ESR_ELx_EC_WATCHPT_CUR UL(0x35)
+ /* Unallocated EC: 0x36 - 0x37 */
+-#define ESR_ELx_EC_BKPT32 (0x38)
++#define ESR_ELx_EC_BKPT32 UL(0x38)
+ /* Unallocated EC: 0x39 */
+-#define ESR_ELx_EC_VECTOR32 (0x3A) /* EL2 only */
++#define ESR_ELx_EC_VECTOR32 UL(0x3A) /* EL2 only */
+ /* Unallocated EC: 0x3B */
+-#define ESR_ELx_EC_BRK64 (0x3C)
++#define ESR_ELx_EC_BRK64 UL(0x3C)
+ /* Unallocated EC: 0x3D - 0x3F */
+-#define ESR_ELx_EC_MAX (0x3F)
++#define ESR_ELx_EC_MAX UL(0x3F)
+
+ #define ESR_ELx_EC_SHIFT (26)
+ #define ESR_ELx_EC_WIDTH (6)
+diff --git a/arch/arm64/include/uapi/asm/sigcontext.h b/arch/arm64/include/uapi/asm/sigcontext.h
+index 8a45b7a411e045..57f76d82077ea5 100644
+--- a/arch/arm64/include/uapi/asm/sigcontext.h
++++ b/arch/arm64/include/uapi/asm/sigcontext.h
+@@ -320,10 +320,10 @@ struct zt_context {
+ ((sizeof(struct za_context) + (__SVE_VQ_BYTES - 1)) \
+ / __SVE_VQ_BYTES * __SVE_VQ_BYTES)
+
+-#define ZA_SIG_REGS_SIZE(vq) ((vq * __SVE_VQ_BYTES) * (vq * __SVE_VQ_BYTES))
++#define ZA_SIG_REGS_SIZE(vq) (((vq) * __SVE_VQ_BYTES) * ((vq) * __SVE_VQ_BYTES))
+
+ #define ZA_SIG_ZAV_OFFSET(vq, n) (ZA_SIG_REGS_OFFSET + \
+- (SVE_SIG_ZREG_SIZE(vq) * n))
++ (SVE_SIG_ZREG_SIZE(vq) * (n)))
+
+ #define ZA_SIG_CONTEXT_SIZE(vq) \
+ (ZA_SIG_REGS_OFFSET + ZA_SIG_REGS_SIZE(vq))
+@@ -334,7 +334,7 @@ struct zt_context {
+
+ #define ZT_SIG_REGS_OFFSET sizeof(struct zt_context)
+
+-#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * n)
++#define ZT_SIG_REGS_SIZE(n) (ZT_SIG_REG_BYTES * (n))
+
+ #define ZT_SIG_CONTEXT_SIZE(n) \
+ (sizeof(struct zt_context) + ZT_SIG_REGS_SIZE(n))
+diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
+index f6b6b450735715..dfefbdf4073a6a 100644
+--- a/arch/arm64/kernel/cpu_errata.c
++++ b/arch/arm64/kernel/cpu_errata.c
+@@ -456,6 +456,14 @@ static const struct midr_range erratum_spec_ssbs_list[] = {
+ };
+ #endif
+
++#ifdef CONFIG_AMPERE_ERRATUM_AC03_CPU_38
++static const struct midr_range erratum_ac03_cpu_38_list[] = {
++ MIDR_ALL_VERSIONS(MIDR_AMPERE1),
++ MIDR_ALL_VERSIONS(MIDR_AMPERE1A),
++ {},
++};
++#endif
++
+ const struct arm64_cpu_capabilities arm64_errata[] = {
+ #ifdef CONFIG_ARM64_WORKAROUND_CLEAN_CACHE
+ {
+@@ -772,7 +780,7 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
+ {
+ .desc = "AmpereOne erratum AC03_CPU_38",
+ .capability = ARM64_WORKAROUND_AMPERE_AC03_CPU_38,
+- ERRATA_MIDR_ALL_VERSIONS(MIDR_AMPERE1),
++ ERRATA_MIDR_RANGE_LIST(erratum_ac03_cpu_38_list),
+ },
+ #endif
+ {
+diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
+index 05688f6a275f10..d36b9160e9346b 100644
+--- a/arch/arm64/kernel/smp.c
++++ b/arch/arm64/kernel/smp.c
+@@ -71,7 +71,7 @@ enum ipi_msg_type {
+ IPI_RESCHEDULE,
+ IPI_CALL_FUNC,
+ IPI_CPU_STOP,
+- IPI_CPU_CRASH_STOP,
++ IPI_CPU_STOP_NMI,
+ IPI_TIMER,
+ IPI_IRQ_WORK,
+ NR_IPI,
+@@ -88,6 +88,8 @@ static int ipi_irq_base __ro_after_init;
+ static int nr_ipi __ro_after_init = NR_IPI;
+ static struct irq_desc *ipi_desc[MAX_IPI] __ro_after_init;
+
++static bool crash_stop;
++
+ static void ipi_setup(int cpu);
+
+ #ifdef CONFIG_HOTPLUG_CPU
+@@ -773,7 +775,7 @@ static const char *ipi_types[MAX_IPI] __tracepoint_string = {
+ [IPI_RESCHEDULE] = "Rescheduling interrupts",
+ [IPI_CALL_FUNC] = "Function call interrupts",
+ [IPI_CPU_STOP] = "CPU stop interrupts",
+- [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts",
++ [IPI_CPU_STOP_NMI] = "CPU stop NMIs",
+ [IPI_TIMER] = "Timer broadcast interrupts",
+ [IPI_IRQ_WORK] = "IRQ work interrupts",
+ [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts",
+@@ -817,9 +819,9 @@ void arch_irq_work_raise(void)
+ }
+ #endif
+
+-static void __noreturn local_cpu_stop(void)
++static void __noreturn local_cpu_stop(unsigned int cpu)
+ {
+- set_cpu_online(smp_processor_id(), false);
++ set_cpu_online(cpu, false);
+
+ local_daif_mask();
+ sdei_mask_local_cpu();
+@@ -833,21 +835,26 @@ static void __noreturn local_cpu_stop(void)
+ */
+ void __noreturn panic_smp_self_stop(void)
+ {
+- local_cpu_stop();
++ local_cpu_stop(smp_processor_id());
+ }
+
+-#ifdef CONFIG_KEXEC_CORE
+-static atomic_t waiting_for_crash_ipi = ATOMIC_INIT(0);
+-#endif
+-
+ static void __noreturn ipi_cpu_crash_stop(unsigned int cpu, struct pt_regs *regs)
+ {
+ #ifdef CONFIG_KEXEC_CORE
++ /*
++ * Use local_daif_mask() instead of local_irq_disable() to make sure
++ * that pseudo-NMIs are disabled. The "crash stop" code starts with
++ * an IRQ and falls back to NMI (which might be pseudo). If the IRQ
++ * finally goes through right as we're timing out then the NMI could
++ * interrupt us. It's better to prevent the NMI and let the IRQ
++ * finish since the pt_regs will be better.
++ */
++ local_daif_mask();
++
+ crash_save_cpu(regs, cpu);
+
+- atomic_dec(&waiting_for_crash_ipi);
++ set_cpu_online(cpu, false);
+
+- local_irq_disable();
+ sdei_mask_local_cpu();
+
+ if (IS_ENABLED(CONFIG_HOTPLUG_CPU))
+@@ -912,14 +919,12 @@ static void do_handle_IPI(int ipinr)
+ break;
+
+ case IPI_CPU_STOP:
+- local_cpu_stop();
+- break;
+-
+- case IPI_CPU_CRASH_STOP:
+- if (IS_ENABLED(CONFIG_KEXEC_CORE)) {
++ case IPI_CPU_STOP_NMI:
++ if (IS_ENABLED(CONFIG_KEXEC_CORE) && crash_stop) {
+ ipi_cpu_crash_stop(cpu, get_irq_regs());
+-
+ unreachable();
++ } else {
++ local_cpu_stop(cpu);
+ }
+ break;
+
+@@ -974,8 +979,7 @@ static bool ipi_should_be_nmi(enum ipi_msg_type ipi)
+ return false;
+
+ switch (ipi) {
+- case IPI_CPU_STOP:
+- case IPI_CPU_CRASH_STOP:
++ case IPI_CPU_STOP_NMI:
+ case IPI_CPU_BACKTRACE:
+ case IPI_KGDB_ROUNDUP:
+ return true;
+@@ -1088,79 +1092,109 @@ static inline unsigned int num_other_online_cpus(void)
+
+ void smp_send_stop(void)
+ {
++ static unsigned long stop_in_progress;
++ cpumask_t mask;
+ unsigned long timeout;
+
+- if (num_other_online_cpus()) {
+- cpumask_t mask;
++ /*
++ * If this cpu is the only one alive at this point in time, online or
++ * not, there are no stop messages to be sent around, so just back out.
++ */
++ if (num_other_online_cpus() == 0)
++ goto skip_ipi;
+
+- cpumask_copy(&mask, cpu_online_mask);
+- cpumask_clear_cpu(smp_processor_id(), &mask);
++ /* Only proceed if this is the first CPU to reach this code */
++ if (test_and_set_bit(0, &stop_in_progress))
++ return;
+
+- if (system_state <= SYSTEM_RUNNING)
+- pr_crit("SMP: stopping secondary CPUs\n");
+- smp_cross_call(&mask, IPI_CPU_STOP);
+- }
++ /*
++ * Send an IPI to all currently online CPUs except the CPU running
++ * this code.
++ *
++ * NOTE: we don't do anything here to prevent other CPUs from coming
++ * online after we snapshot `cpu_online_mask`. Ideally, the calling code
++ * should do something to prevent other CPUs from coming up. This code
++ * can be called in the panic path and thus it doesn't seem wise to
++ * grab the CPU hotplug mutex ourselves. Worst case:
++ * - If a CPU comes online as we're running, we'll likely notice it
++ * during the 1 second wait below and then we'll catch it when we try
++ * with an NMI (assuming NMIs are enabled) since we re-snapshot the
++ * mask before sending an NMI.
++ * - If we leave the function and see that CPUs are still online we'll
++ * at least print a warning. Especially without NMIs this function
++ * isn't foolproof anyway so calling code will just have to accept
++ * the fact that there could be cases where a CPU can't be stopped.
++ */
++ cpumask_copy(&mask, cpu_online_mask);
++ cpumask_clear_cpu(smp_processor_id(), &mask);
+
+- /* Wait up to one second for other CPUs to stop */
++ if (system_state <= SYSTEM_RUNNING)
++ pr_crit("SMP: stopping secondary CPUs\n");
++
++ /*
++ * Start with a normal IPI and wait up to one second for other CPUs to
++ * stop. We do this first because it gives other processors a chance
++ * to exit critical sections / drop locks and makes the rest of the
++ * stop process (especially console flush) more robust.
++ */
++ smp_cross_call(&mask, IPI_CPU_STOP);
+ timeout = USEC_PER_SEC;
+ while (num_other_online_cpus() && timeout--)
+ udelay(1);
+
+- if (num_other_online_cpus())
++ /*
++ * If CPUs are still online, try an NMI. There's no excuse for this to
++ * be slow, so we only give them an extra 10 ms to respond.
++ */
++ if (num_other_online_cpus() && ipi_should_be_nmi(IPI_CPU_STOP_NMI)) {
++ smp_rmb();
++ cpumask_copy(&mask, cpu_online_mask);
++ cpumask_clear_cpu(smp_processor_id(), &mask);
++
++ pr_info("SMP: retry stop with NMI for CPUs %*pbl\n",
++ cpumask_pr_args(&mask));
++
++ smp_cross_call(&mask, IPI_CPU_STOP_NMI);
++ timeout = USEC_PER_MSEC * 10;
++ while (num_other_online_cpus() && timeout--)
++ udelay(1);
++ }
++
++ if (num_other_online_cpus()) {
++ smp_rmb();
++ cpumask_copy(&mask, cpu_online_mask);
++ cpumask_clear_cpu(smp_processor_id(), &mask);
++
+ pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+- cpumask_pr_args(cpu_online_mask));
++ cpumask_pr_args(&mask));
++ }
+
++skip_ipi:
+ sdei_mask_local_cpu();
+ }
+
+ #ifdef CONFIG_KEXEC_CORE
+ void crash_smp_send_stop(void)
+ {
+- static int cpus_stopped;
+- cpumask_t mask;
+- unsigned long timeout;
+-
+ /*
+ * This function can be called twice in panic path, but obviously
+ * we execute this only once.
++ *
++ * We use this same boolean to tell whether the IPI we send was a
++ * stop or a "crash stop".
+ */
+- if (cpus_stopped)
++ if (crash_stop)
+ return;
++ crash_stop = 1;
+
+- cpus_stopped = 1;
++ smp_send_stop();
+
+- /*
+- * If this cpu is the only one alive at this point in time, online or
+- * not, there are no stop messages to be sent around, so just back out.
+- */
+- if (num_other_online_cpus() == 0)
+- goto skip_ipi;
+-
+- cpumask_copy(&mask, cpu_online_mask);
+- cpumask_clear_cpu(smp_processor_id(), &mask);
+-
+- atomic_set(&waiting_for_crash_ipi, num_other_online_cpus());
+-
+- pr_crit("SMP: stopping secondary CPUs\n");
+- smp_cross_call(&mask, IPI_CPU_CRASH_STOP);
+-
+- /* Wait up to one second for other CPUs to stop */
+- timeout = USEC_PER_SEC;
+- while ((atomic_read(&waiting_for_crash_ipi) > 0) && timeout--)
+- udelay(1);
+-
+- if (atomic_read(&waiting_for_crash_ipi) > 0)
+- pr_warn("SMP: failed to stop secondary CPUs %*pbl\n",
+- cpumask_pr_args(&mask));
+-
+-skip_ipi:
+- sdei_mask_local_cpu();
+ sdei_handler_abort();
+ }
+
+ bool smp_crash_stop_failed(void)
+ {
+- return (atomic_read(&waiting_for_crash_ipi) > 0);
++ return num_other_online_cpus() != 0;
+ }
+ #endif
+
+diff --git a/arch/arm64/kvm/hyp/nvhe/ffa.c b/arch/arm64/kvm/hyp/nvhe/ffa.c
+index efb053af331cc9..f26ae1819d1b4c 100644
+--- a/arch/arm64/kvm/hyp/nvhe/ffa.c
++++ b/arch/arm64/kvm/hyp/nvhe/ffa.c
+@@ -423,9 +423,9 @@ static void do_ffa_mem_frag_tx(struct arm_smccc_res *res,
+ return;
+ }
+
+-static __always_inline void do_ffa_mem_xfer(const u64 func_id,
+- struct arm_smccc_res *res,
+- struct kvm_cpu_context *ctxt)
++static void __do_ffa_mem_xfer(const u64 func_id,
++ struct arm_smccc_res *res,
++ struct kvm_cpu_context *ctxt)
+ {
+ DECLARE_REG(u32, len, ctxt, 1);
+ DECLARE_REG(u32, fraglen, ctxt, 2);
+@@ -437,9 +437,6 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id,
+ u32 offset, nr_ranges;
+ int ret = 0;
+
+- BUILD_BUG_ON(func_id != FFA_FN64_MEM_SHARE &&
+- func_id != FFA_FN64_MEM_LEND);
+-
+ if (addr_mbz || npages_mbz || fraglen > len ||
+ fraglen > KVM_FFA_MBOX_NR_PAGES * PAGE_SIZE) {
+ ret = FFA_RET_INVALID_PARAMETERS;
+@@ -458,6 +455,11 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id,
+ goto out_unlock;
+ }
+
++ if (len > ffa_desc_buf.len) {
++ ret = FFA_RET_NO_MEMORY;
++ goto out_unlock;
++ }
++
+ buf = hyp_buffers.tx;
+ memcpy(buf, host_buffers.tx, fraglen);
+
+@@ -509,6 +511,13 @@ static __always_inline void do_ffa_mem_xfer(const u64 func_id,
+ goto out_unlock;
+ }
+
++#define do_ffa_mem_xfer(fid, res, ctxt) \
++ do { \
++ BUILD_BUG_ON((fid) != FFA_FN64_MEM_SHARE && \
++ (fid) != FFA_FN64_MEM_LEND); \
++ __do_ffa_mem_xfer((fid), (res), (ctxt)); \
++ } while (0);
++
+ static void do_ffa_mem_reclaim(struct arm_smccc_res *res,
+ struct kvm_cpu_context *ctxt)
+ {
+diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
+index 1bf483ec971d92..c4190865f24335 100644
+--- a/arch/arm64/net/bpf_jit_comp.c
++++ b/arch/arm64/net/bpf_jit_comp.c
+@@ -26,7 +26,7 @@
+
+ #define TMP_REG_1 (MAX_BPF_JIT_REG + 0)
+ #define TMP_REG_2 (MAX_BPF_JIT_REG + 1)
+-#define TCALL_CNT (MAX_BPF_JIT_REG + 2)
++#define TCCNT_PTR (MAX_BPF_JIT_REG + 2)
+ #define TMP_REG_3 (MAX_BPF_JIT_REG + 3)
+ #define FP_BOTTOM (MAX_BPF_JIT_REG + 4)
+ #define ARENA_VM_START (MAX_BPF_JIT_REG + 5)
+@@ -63,8 +63,8 @@ static const int bpf2a64[] = {
+ [TMP_REG_1] = A64_R(10),
+ [TMP_REG_2] = A64_R(11),
+ [TMP_REG_3] = A64_R(12),
+- /* tail_call_cnt */
+- [TCALL_CNT] = A64_R(26),
++ /* tail_call_cnt_ptr */
++ [TCCNT_PTR] = A64_R(26),
+ /* temporary register for blinding constants */
+ [BPF_REG_AX] = A64_R(9),
+ [FP_BOTTOM] = A64_R(27),
+@@ -282,13 +282,35 @@ static bool is_lsi_offset(int offset, int scale)
+ * mov x29, sp
+ * stp x19, x20, [sp, #-16]!
+ * stp x21, x22, [sp, #-16]!
+- * stp x25, x26, [sp, #-16]!
++ * stp x26, x25, [sp, #-16]!
++ * stp x26, x25, [sp, #-16]!
+ * stp x27, x28, [sp, #-16]!
+ * mov x25, sp
+ * mov tcc, #0
+ * // PROLOGUE_OFFSET
+ */
+
++static void prepare_bpf_tail_call_cnt(struct jit_ctx *ctx)
++{
++ const struct bpf_prog *prog = ctx->prog;
++ const bool is_main_prog = !bpf_is_subprog(prog);
++ const u8 ptr = bpf2a64[TCCNT_PTR];
++ const u8 fp = bpf2a64[BPF_REG_FP];
++ const u8 tcc = ptr;
++
++ emit(A64_PUSH(ptr, fp, A64_SP), ctx);
++ if (is_main_prog) {
++ /* Initialize tail_call_cnt. */
++ emit(A64_MOVZ(1, tcc, 0, 0), ctx);
++ emit(A64_PUSH(tcc, fp, A64_SP), ctx);
++ emit(A64_MOV(1, ptr, A64_SP), ctx);
++ } else {
++ emit(A64_PUSH(ptr, fp, A64_SP), ctx);
++ emit(A64_NOP, ctx);
++ emit(A64_NOP, ctx);
++ }
++}
++
+ #define BTI_INSNS (IS_ENABLED(CONFIG_ARM64_BTI_KERNEL) ? 1 : 0)
+ #define PAC_INSNS (IS_ENABLED(CONFIG_ARM64_PTR_AUTH_KERNEL) ? 1 : 0)
+
+@@ -296,7 +318,7 @@ static bool is_lsi_offset(int offset, int scale)
+ #define POKE_OFFSET (BTI_INSNS + 1)
+
+ /* Tail call offset to jump into */
+-#define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 8)
++#define PROLOGUE_OFFSET (BTI_INSNS + 2 + PAC_INSNS + 10)
+
+ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
+ bool is_exception_cb, u64 arena_vm_start)
+@@ -308,7 +330,6 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
+ const u8 r8 = bpf2a64[BPF_REG_8];
+ const u8 r9 = bpf2a64[BPF_REG_9];
+ const u8 fp = bpf2a64[BPF_REG_FP];
+- const u8 tcc = bpf2a64[TCALL_CNT];
+ const u8 fpb = bpf2a64[FP_BOTTOM];
+ const u8 arena_vm_base = bpf2a64[ARENA_VM_START];
+ const int idx0 = ctx->idx;
+@@ -359,7 +380,7 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
+ /* Save callee-saved registers */
+ emit(A64_PUSH(r6, r7, A64_SP), ctx);
+ emit(A64_PUSH(r8, r9, A64_SP), ctx);
+- emit(A64_PUSH(fp, tcc, A64_SP), ctx);
++ prepare_bpf_tail_call_cnt(ctx);
+ emit(A64_PUSH(fpb, A64_R(28), A64_SP), ctx);
+ } else {
+ /*
+@@ -372,18 +393,15 @@ static int build_prologue(struct jit_ctx *ctx, bool ebpf_from_cbpf,
+ * callee-saved registers. The exception callback will not push
+ * anything and re-use the main program's stack.
+ *
+- * 10 registers are on the stack
++ * 12 registers are on the stack
+ */
+- emit(A64_SUB_I(1, A64_SP, A64_FP, 80), ctx);
++ emit(A64_SUB_I(1, A64_SP, A64_FP, 96), ctx);
+ }
+
+ /* Set up BPF prog stack base register */
+ emit(A64_MOV(1, fp, A64_SP), ctx);
+
+ if (!ebpf_from_cbpf && is_main_prog) {
+- /* Initialize tail_call_cnt */
+- emit(A64_MOVZ(1, tcc, 0, 0), ctx);
+-
+ cur_offset = ctx->idx - idx0;
+ if (cur_offset != PROLOGUE_OFFSET) {
+ pr_err_once("PROLOGUE_OFFSET = %d, expected %d!\n",
+@@ -432,7 +450,8 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
+
+ const u8 tmp = bpf2a64[TMP_REG_1];
+ const u8 prg = bpf2a64[TMP_REG_2];
+- const u8 tcc = bpf2a64[TCALL_CNT];
++ const u8 tcc = bpf2a64[TMP_REG_3];
++ const u8 ptr = bpf2a64[TCCNT_PTR];
+ const int idx0 = ctx->idx;
+ #define cur_offset (ctx->idx - idx0)
+ #define jmp_offset (out_offset - (cur_offset))
+@@ -449,11 +468,12 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
+ emit(A64_B_(A64_COND_CS, jmp_offset), ctx);
+
+ /*
+- * if (tail_call_cnt >= MAX_TAIL_CALL_CNT)
++ * if ((*tail_call_cnt_ptr) >= MAX_TAIL_CALL_CNT)
+ * goto out;
+- * tail_call_cnt++;
++ * (*tail_call_cnt_ptr)++;
+ */
+ emit_a64_mov_i64(tmp, MAX_TAIL_CALL_CNT, ctx);
++ emit(A64_LDR64I(tcc, ptr, 0), ctx);
+ emit(A64_CMP(1, tcc, tmp), ctx);
+ emit(A64_B_(A64_COND_CS, jmp_offset), ctx);
+ emit(A64_ADD_I(1, tcc, tcc, 1), ctx);
+@@ -469,6 +489,9 @@ static int emit_bpf_tail_call(struct jit_ctx *ctx)
+ emit(A64_LDR64(prg, tmp, prg), ctx);
+ emit(A64_CBZ(1, prg, jmp_offset), ctx);
+
++ /* Update tail_call_cnt if the slot is populated. */
++ emit(A64_STR64I(tcc, ptr, 0), ctx);
++
+ /* goto *(prog->bpf_func + prologue_offset); */
+ off = offsetof(struct bpf_prog, bpf_func);
+ emit_a64_mov_i64(tmp, off, ctx);
+@@ -721,6 +744,7 @@ static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb)
+ const u8 r8 = bpf2a64[BPF_REG_8];
+ const u8 r9 = bpf2a64[BPF_REG_9];
+ const u8 fp = bpf2a64[BPF_REG_FP];
++ const u8 ptr = bpf2a64[TCCNT_PTR];
+ const u8 fpb = bpf2a64[FP_BOTTOM];
+
+ /* We're done with BPF stack */
+@@ -738,7 +762,8 @@ static void build_epilogue(struct jit_ctx *ctx, bool is_exception_cb)
+ /* Restore x27 and x28 */
+ emit(A64_POP(fpb, A64_R(28), A64_SP), ctx);
+ /* Restore fs (x25) and x26 */
+- emit(A64_POP(fp, A64_R(26), A64_SP), ctx);
++ emit(A64_POP(ptr, fp, A64_SP), ctx);
++ emit(A64_POP(ptr, fp, A64_SP), ctx);
+
+ /* Restore callee-saved register */
+ emit(A64_POP(r8, r9, A64_SP), ctx);
+diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
+index d741c3e9933a51..590a92cb54165c 100644
+--- a/arch/loongarch/include/asm/kvm_vcpu.h
++++ b/arch/loongarch/include/asm/kvm_vcpu.h
+@@ -76,6 +76,7 @@ static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
+ #endif
+
+ void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
++void kvm_reset_timer(struct kvm_vcpu *vcpu);
+ void kvm_save_timer(struct kvm_vcpu *vcpu);
+ void kvm_restore_timer(struct kvm_vcpu *vcpu);
+
+diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
+index 74a4b5c272d60e..bcc6b6d063d914 100644
+--- a/arch/loongarch/kvm/timer.c
++++ b/arch/loongarch/kvm/timer.c
+@@ -188,3 +188,10 @@ void kvm_save_timer(struct kvm_vcpu *vcpu)
+ kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
+ preempt_enable();
+ }
++
++void kvm_reset_timer(struct kvm_vcpu *vcpu)
++{
++ write_gcsr_timercfg(0);
++ kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_TCFG, 0);
++ hrtimer_cancel(&vcpu->arch.swtimer);
++}
+diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
+index 0b53f4d9fddf91..9e8030d4512902 100644
+--- a/arch/loongarch/kvm/vcpu.c
++++ b/arch/loongarch/kvm/vcpu.c
+@@ -572,7 +572,7 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
+ vcpu->kvm->arch.time_offset = (signed long)(v - drdtime());
+ break;
+ case KVM_REG_LOONGARCH_VCPU_RESET:
+- vcpu->arch.st.guest_addr = 0;
++ kvm_reset_timer(vcpu);
+ memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
+ memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
+ break;
+diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
+index 2584e94e213468..fda7eac23f872d 100644
+--- a/arch/m68k/kernel/process.c
++++ b/arch/m68k/kernel/process.c
+@@ -117,7 +117,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs)
+ {
+ /* regs will be equal to current_pt_regs() */
+ struct kernel_clone_args args = {
+- .flags = regs->d1 & ~CSIGNAL,
++ .flags = (u32)(regs->d1) & ~CSIGNAL,
+ .pidfd = (int __user *)regs->d3,
+ .child_tid = (int __user *)regs->d4,
+ .parent_tid = (int __user *)regs->d3,
+diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig
+index 1e201b7ae2fc60..bd9d77b0c92ec1 100644
+--- a/arch/powerpc/crypto/Kconfig
++++ b/arch/powerpc/crypto/Kconfig
+@@ -96,6 +96,7 @@ config CRYPTO_AES_PPC_SPE
+
+ config CRYPTO_AES_GCM_P10
+ tristate "Stitched AES/GCM acceleration support on P10 or later CPU (PPC)"
++ depends on BROKEN
+ depends on PPC64 && CPU_LITTLE_ENDIAN && VSX
+ select CRYPTO_LIB_AES
+ select CRYPTO_ALGAPI
+diff --git a/arch/powerpc/include/asm/asm-compat.h b/arch/powerpc/include/asm/asm-compat.h
+index 2bc53c646ccd7d..83848b534cb171 100644
+--- a/arch/powerpc/include/asm/asm-compat.h
++++ b/arch/powerpc/include/asm/asm-compat.h
+@@ -39,6 +39,12 @@
+ #define STDX_BE stringify_in_c(stdbrx)
+ #endif
+
++#ifdef CONFIG_CC_IS_CLANG
++#define DS_FORM_CONSTRAINT "Z<>"
++#else
++#define DS_FORM_CONSTRAINT "YZ<>"
++#endif
++
+ #else /* 32-bit */
+
+ /* operations for longs and pointers */
+diff --git a/arch/powerpc/include/asm/atomic.h b/arch/powerpc/include/asm/atomic.h
+index 5bf6a4d49268c7..d1ea554c33ed7e 100644
+--- a/arch/powerpc/include/asm/atomic.h
++++ b/arch/powerpc/include/asm/atomic.h
+@@ -11,6 +11,7 @@
+ #include <asm/cmpxchg.h>
+ #include <asm/barrier.h>
+ #include <asm/asm-const.h>
++#include <asm/asm-compat.h>
+
+ /*
+ * Since *_return_relaxed and {cmp}xchg_relaxed are implemented with
+@@ -197,7 +198,7 @@ static __inline__ s64 arch_atomic64_read(const atomic64_t *v)
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
+ __asm__ __volatile__("ld %0,0(%1)" : "=r"(t) : "b"(&v->counter));
+ else
+- __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : "m<>"(v->counter));
++ __asm__ __volatile__("ld%U1%X1 %0,%1" : "=r"(t) : DS_FORM_CONSTRAINT (v->counter));
+
+ return t;
+ }
+@@ -208,7 +209,7 @@ static __inline__ void arch_atomic64_set(atomic64_t *v, s64 i)
+ if (IS_ENABLED(CONFIG_PPC_KERNEL_PREFIXED))
+ __asm__ __volatile__("std %1,0(%2)" : "=m"(v->counter) : "r"(i), "b"(&v->counter));
+ else
+- __asm__ __volatile__("std%U0%X0 %1,%0" : "=m<>"(v->counter) : "r"(i));
++ __asm__ __volatile__("std%U0%X0 %1,%0" : "=" DS_FORM_CONSTRAINT (v->counter) : "r"(i));
+ }
+
+ #define ATOMIC64_OP(op, asm_op) \
+diff --git a/arch/powerpc/include/asm/uaccess.h b/arch/powerpc/include/asm/uaccess.h
+index fd594bf6c6a9c5..4f5a46a77fa2b6 100644
+--- a/arch/powerpc/include/asm/uaccess.h
++++ b/arch/powerpc/include/asm/uaccess.h
+@@ -6,6 +6,7 @@
+ #include <asm/page.h>
+ #include <asm/extable.h>
+ #include <asm/kup.h>
++#include <asm/asm-compat.h>
+
+ #ifdef __powerpc64__
+ /* We use TASK_SIZE_USER64 as TASK_SIZE is not constant */
+@@ -92,12 +93,6 @@ __pu_failed: \
+ : label)
+ #endif
+
+-#ifdef CONFIG_CC_IS_CLANG
+-#define DS_FORM_CONSTRAINT "Z<>"
+-#else
+-#define DS_FORM_CONSTRAINT "YZ<>"
+-#endif
+-
+ #ifdef __powerpc64__
+ #ifdef CONFIG_PPC_KERNEL_PREFIXED
+ #define __put_user_asm2_goto(x, ptr, label) \
+diff --git a/arch/powerpc/kernel/head_8xx.S b/arch/powerpc/kernel/head_8xx.S
+index edc479a7c2bce3..0bd317b5647526 100644
+--- a/arch/powerpc/kernel/head_8xx.S
++++ b/arch/powerpc/kernel/head_8xx.S
+@@ -41,12 +41,12 @@
+ #include "head_32.h"
+
+ .macro compare_to_kernel_boundary scratch, addr
+-#if CONFIG_TASK_SIZE <= 0x80000000 && CONFIG_PAGE_OFFSET >= 0x80000000
++#if CONFIG_TASK_SIZE <= 0x80000000 && MODULES_VADDR >= 0x80000000
+ /* By simply checking Address >= 0x80000000, we know if its a kernel address */
+ not. \scratch, \addr
+ #else
+ rlwinm \scratch, \addr, 16, 0xfff8
+- cmpli cr0, \scratch, PAGE_OFFSET@h
++ cmpli cr0, \scratch, TASK_SIZE@h
+ #endif
+ .endm
+
+@@ -404,7 +404,7 @@ FixupDAR:/* Entry point for dcbx workaround. */
+ mfspr r10, SPRN_SRR0
+ mtspr SPRN_MD_EPN, r10
+ rlwinm r11, r10, 16, 0xfff8
+- cmpli cr1, r11, PAGE_OFFSET@h
++ cmpli cr1, r11, TASK_SIZE@h
+ mfspr r11, SPRN_M_TWB /* Get level 1 table */
+ blt+ cr1, 3f
+
+diff --git a/arch/powerpc/kernel/vdso/gettimeofday.S b/arch/powerpc/kernel/vdso/gettimeofday.S
+index 48fc6658053aa4..894cb939cd2b31 100644
+--- a/arch/powerpc/kernel/vdso/gettimeofday.S
++++ b/arch/powerpc/kernel/vdso/gettimeofday.S
+@@ -38,11 +38,7 @@
+ .else
+ addi r4, r5, VDSO_DATA_OFFSET
+ .endif
+-#ifdef __powerpc64__
+ bl CFUNC(DOTSYM(\funct))
+-#else
+- bl \funct
+-#endif
+ PPC_LL r0, PPC_MIN_STKFRM + PPC_LR_STKOFF(r1)
+ #ifdef __powerpc64__
+ PPC_LL r2, PPC_MIN_STKFRM + STK_GOT(r1)
+diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
+index d93433e26dedb8..e5cc3b3a259f9a 100644
+--- a/arch/powerpc/mm/nohash/8xx.c
++++ b/arch/powerpc/mm/nohash/8xx.c
+@@ -154,11 +154,11 @@ unsigned long __init mmu_mapin_ram(unsigned long base, unsigned long top)
+
+ mmu_mapin_immr();
+
+- mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_TEXT, true);
++ mmu_mapin_ram_chunk(0, boundary, PAGE_KERNEL_X, true);
+ if (debug_pagealloc_enabled_or_kfence()) {
+ top = boundary;
+ } else {
+- mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_TEXT, true);
++ mmu_mapin_ram_chunk(boundary, einittext8, PAGE_KERNEL_X, true);
+ mmu_mapin_ram_chunk(einittext8, top, PAGE_KERNEL, true);
+ }
+
+diff --git a/arch/riscv/include/asm/kvm_vcpu_pmu.h b/arch/riscv/include/asm/kvm_vcpu_pmu.h
+index fa0f535bbbf024..1d85b661750884 100644
+--- a/arch/riscv/include/asm/kvm_vcpu_pmu.h
++++ b/arch/riscv/include/asm/kvm_vcpu_pmu.h
+@@ -10,6 +10,7 @@
+ #define __KVM_VCPU_RISCV_PMU_H
+
+ #include <linux/perf/riscv_pmu.h>
++#include <asm/kvm_vcpu_insn.h>
+ #include <asm/sbi.h>
+
+ #ifdef CONFIG_RISCV_PMU_SBI
+@@ -64,11 +65,11 @@ struct kvm_pmu {
+
+ #if defined(CONFIG_32BIT)
+ #define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \
+-{.base = CSR_CYCLEH, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm }, \
+-{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm },
++{.base = CSR_CYCLEH, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm }, \
++{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm },
+ #else
+ #define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \
+-{.base = CSR_CYCLE, .count = 31, .func = kvm_riscv_vcpu_pmu_read_hpm },
++{.base = CSR_CYCLE, .count = 32, .func = kvm_riscv_vcpu_pmu_read_hpm },
+ #endif
+
+ int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid);
+@@ -104,8 +105,20 @@ void kvm_riscv_vcpu_pmu_reset(struct kvm_vcpu *vcpu);
+ struct kvm_pmu {
+ };
+
++static inline int kvm_riscv_vcpu_pmu_read_legacy(struct kvm_vcpu *vcpu, unsigned int csr_num,
++ unsigned long *val, unsigned long new_val,
++ unsigned long wr_mask)
++{
++ if (csr_num == CSR_CYCLE || csr_num == CSR_INSTRET) {
++ *val = 0;
++ return KVM_INSN_CONTINUE_NEXT_SEPC;
++ } else {
++ return KVM_INSN_ILLEGAL_TRAP;
++ }
++}
++
+ #define KVM_RISCV_VCPU_HPMCOUNTER_CSR_FUNCS \
+-{.base = 0, .count = 0, .func = NULL },
++{.base = CSR_CYCLE, .count = 3, .func = kvm_riscv_vcpu_pmu_read_legacy },
+
+ static inline void kvm_riscv_vcpu_pmu_init(struct kvm_vcpu *vcpu) {}
+ static inline int kvm_riscv_vcpu_pmu_incr_fw(struct kvm_vcpu *vcpu, unsigned long fid)
+diff --git a/arch/riscv/kernel/perf_callchain.c b/arch/riscv/kernel/perf_callchain.c
+index 3348a61de7d998..2932791e938821 100644
+--- a/arch/riscv/kernel/perf_callchain.c
++++ b/arch/riscv/kernel/perf_callchain.c
+@@ -62,7 +62,7 @@ void perf_callchain_user(struct perf_callchain_entry_ctx *entry,
+ perf_callchain_store(entry, regs->epc);
+
+ fp = user_backtrace(entry, fp, regs->ra);
+- while (fp && !(fp & 0x3) && entry->nr < entry->max_stack)
++ while (fp && !(fp & 0x7) && entry->nr < entry->max_stack)
+ fp = user_backtrace(entry, fp, 0);
+ }
+
+diff --git a/arch/riscv/kvm/vcpu_pmu.c b/arch/riscv/kvm/vcpu_pmu.c
+index bcf41d6e0df0e3..2707a51b082ca7 100644
+--- a/arch/riscv/kvm/vcpu_pmu.c
++++ b/arch/riscv/kvm/vcpu_pmu.c
+@@ -391,19 +391,9 @@ int kvm_riscv_vcpu_pmu_read_hpm(struct kvm_vcpu *vcpu, unsigned int csr_num,
+ static void kvm_pmu_clear_snapshot_area(struct kvm_vcpu *vcpu)
+ {
+ struct kvm_pmu *kvpmu = vcpu_to_pmu(vcpu);
+- int snapshot_area_size = sizeof(struct riscv_pmu_snapshot_data);
+
+- if (kvpmu->sdata) {
+- if (kvpmu->snapshot_addr != INVALID_GPA) {
+- memset(kvpmu->sdata, 0, snapshot_area_size);
+- kvm_vcpu_write_guest(vcpu, kvpmu->snapshot_addr,
+- kvpmu->sdata, snapshot_area_size);
+- } else {
+- pr_warn("snapshot address invalid\n");
+- }
+- kfree(kvpmu->sdata);
+- kvpmu->sdata = NULL;
+- }
++ kfree(kvpmu->sdata);
++ kvpmu->sdata = NULL;
+ kvpmu->snapshot_addr = INVALID_GPA;
+ }
+
+diff --git a/arch/riscv/kvm/vcpu_sbi.c b/arch/riscv/kvm/vcpu_sbi.c
+index 62f409d4176e41..7de128be8db9bc 100644
+--- a/arch/riscv/kvm/vcpu_sbi.c
++++ b/arch/riscv/kvm/vcpu_sbi.c
+@@ -127,8 +127,8 @@ void kvm_riscv_vcpu_sbi_forward(struct kvm_vcpu *vcpu, struct kvm_run *run)
+ run->riscv_sbi.args[3] = cp->a3;
+ run->riscv_sbi.args[4] = cp->a4;
+ run->riscv_sbi.args[5] = cp->a5;
+- run->riscv_sbi.ret[0] = cp->a0;
+- run->riscv_sbi.ret[1] = cp->a1;
++ run->riscv_sbi.ret[0] = SBI_ERR_NOT_SUPPORTED;
++ run->riscv_sbi.ret[1] = 0;
+ }
+
+ void kvm_riscv_vcpu_sbi_system_reset(struct kvm_vcpu *vcpu,
+diff --git a/arch/s390/include/asm/ftrace.h b/arch/s390/include/asm/ftrace.h
+index 77e479d44f1e37..d0cb3ecd63908a 100644
+--- a/arch/s390/include/asm/ftrace.h
++++ b/arch/s390/include/asm/ftrace.h
+@@ -7,8 +7,23 @@
+ #define MCOUNT_INSN_SIZE 6
+
+ #ifndef __ASSEMBLY__
++#include <asm/stacktrace.h>
+
+-unsigned long return_address(unsigned int n);
++static __always_inline unsigned long return_address(unsigned int n)
++{
++ struct stack_frame *sf;
++
++ if (!n)
++ return (unsigned long)__builtin_return_address(0);
++
++ sf = (struct stack_frame *)current_frame_address();
++ do {
++ sf = (struct stack_frame *)sf->back_chain;
++ if (!sf)
++ return 0;
++ } while (--n);
++ return sf->gprs[8];
++}
+ #define ftrace_return_address(n) return_address(n)
+
+ void ftrace_caller(void);
+diff --git a/arch/s390/kernel/stacktrace.c b/arch/s390/kernel/stacktrace.c
+index 640363b2a1059e..9f59837d159e0c 100644
+--- a/arch/s390/kernel/stacktrace.c
++++ b/arch/s390/kernel/stacktrace.c
+@@ -162,22 +162,3 @@ void arch_stack_walk_user(stack_trace_consume_fn consume_entry, void *cookie,
+ {
+ arch_stack_walk_user_common(consume_entry, cookie, NULL, regs, false);
+ }
+-
+-unsigned long return_address(unsigned int n)
+-{
+- struct unwind_state state;
+- unsigned long addr;
+-
+- /* Increment to skip current stack entry */
+- n++;
+-
+- unwind_for_each_frame(&state, NULL, NULL, 0) {
+- addr = unwind_get_return_address(&state);
+- if (!addr)
+- break;
+- if (!n--)
+- return addr;
+- }
+- return 0;
+-}
+-EXPORT_SYMBOL_GPL(return_address);
+diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
+index 8fe4c2b07128e7..327c45c5013fea 100644
+--- a/arch/x86/coco/tdx/tdx.c
++++ b/arch/x86/coco/tdx/tdx.c
+@@ -7,6 +7,7 @@
+ #include <linux/cpufeature.h>
+ #include <linux/export.h>
+ #include <linux/io.h>
++#include <linux/kexec.h>
+ #include <asm/coco.h>
+ #include <asm/tdx.h>
+ #include <asm/vmx.h>
+@@ -14,6 +15,8 @@
+ #include <asm/insn.h>
+ #include <asm/insn-eval.h>
+ #include <asm/pgtable.h>
++#include <asm/set_memory.h>
++#include <asm/traps.h>
+
+ /* MMIO direction */
+ #define EPT_READ 0
+@@ -38,6 +41,8 @@
+
+ #define TDREPORT_SUBTYPE_0 0
+
++static atomic_long_t nr_shared;
++
+ /* Called from __tdx_hypercall() for unrecoverable failure */
+ noinstr void __noreturn __tdx_hypercall_failed(void)
+ {
+@@ -429,6 +434,11 @@ static int handle_mmio(struct pt_regs *regs, struct ve_info *ve)
+ return -EINVAL;
+ }
+
++ if (!fault_in_kernel_space(ve->gla)) {
++ WARN_ONCE(1, "Access to userspace address is not supported");
++ return -EINVAL;
++ }
++
+ /*
+ * Reject EPT violation #VEs that split pages.
+ *
+@@ -797,28 +807,124 @@ static bool tdx_enc_status_changed(unsigned long vaddr, int numpages, bool enc)
+ return true;
+ }
+
+-static bool tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
+- bool enc)
++static int tdx_enc_status_change_prepare(unsigned long vaddr, int numpages,
++ bool enc)
+ {
+ /*
+ * Only handle shared->private conversion here.
+ * See the comment in tdx_early_init().
+ */
+- if (enc)
+- return tdx_enc_status_changed(vaddr, numpages, enc);
+- return true;
++ if (enc && !tdx_enc_status_changed(vaddr, numpages, enc))
++ return -EIO;
++
++ return 0;
+ }
+
+-static bool tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
++static int tdx_enc_status_change_finish(unsigned long vaddr, int numpages,
+ bool enc)
+ {
+ /*
+ * Only handle private->shared conversion here.
+ * See the comment in tdx_early_init().
+ */
+- if (!enc)
+- return tdx_enc_status_changed(vaddr, numpages, enc);
+- return true;
++ if (!enc && !tdx_enc_status_changed(vaddr, numpages, enc))
++ return -EIO;
++
++ if (enc)
++ atomic_long_sub(numpages, &nr_shared);
++ else
++ atomic_long_add(numpages, &nr_shared);
++
++ return 0;
++}
++
++/* Stop new private<->shared conversions */
++static void tdx_kexec_begin(void)
++{
++ if (!IS_ENABLED(CONFIG_KEXEC_CORE))
++ return;
++
++ /*
++ * Crash kernel reaches here with interrupts disabled: can't wait for
++ * conversions to finish.
++ *
++ * If race happened, just report and proceed.
++ */
++ if (!set_memory_enc_stop_conversion())
++ pr_warn("Failed to stop shared<->private conversions\n");
++}
++
++/* Walk direct mapping and convert all shared memory back to private */
++static void tdx_kexec_finish(void)
++{
++ unsigned long addr, end;
++ long found = 0, shared;
++
++ if (!IS_ENABLED(CONFIG_KEXEC_CORE))
++ return;
++
++ lockdep_assert_irqs_disabled();
++
++ addr = PAGE_OFFSET;
++ end = PAGE_OFFSET + get_max_mapped();
++
++ while (addr < end) {
++ unsigned long size;
++ unsigned int level;
++ pte_t *pte;
++
++ pte = lookup_address(addr, &level);
++ size = page_level_size(level);
++
++ if (pte && pte_decrypted(*pte)) {
++ int pages = size / PAGE_SIZE;
++
++ /*
++ * Touching memory with shared bit set triggers implicit
++ * conversion to shared.
++ *
++ * Make sure nobody touches the shared range from
++ * now on.
++ */
++ set_pte(pte, __pte(0));
++
++ /*
++ * Memory encryption state persists across kexec.
++ * If tdx_enc_status_changed() fails in the first
++ * kernel, it leaves memory in an unknown state.
++ *
++ * If that memory remains shared, accessing it in the
++ * *next* kernel through a private mapping will result
++ * in an unrecoverable guest shutdown.
++ *
++ * The kdump kernel boot is not impacted as it uses
++ * a pre-reserved memory range that is always private.
++ * However, gathering crash information could lead to
++ * a crash if it accesses unconverted memory through
++ * a private mapping which is possible when accessing
++ * that memory through /proc/vmcore, for example.
++ *
++ * In all cases, print error info in order to leave
++ * enough bread crumbs for debugging.
++ */
++ if (!tdx_enc_status_changed(addr, pages, true)) {
++ pr_err("Failed to unshare range %#lx-%#lx\n",
++ addr, addr + size);
++ }
++
++ found += pages;
++ }
++
++ addr += size;
++ }
++
++ __flush_tlb_all();
++
++ shared = atomic_long_read(&nr_shared);
++ if (shared != found) {
++ pr_err("shared page accounting is off\n");
++ pr_err("nr_shared = %ld, nr_found = %ld\n", shared, found);
++ }
+ }
+
+ void __init tdx_early_init(void)
+@@ -880,6 +986,9 @@ void __init tdx_early_init(void)
+ x86_platform.guest.enc_cache_flush_required = tdx_cache_flush_required;
+ x86_platform.guest.enc_tlb_flush_required = tdx_tlb_flush_required;
+
++ x86_platform.guest.enc_kexec_begin = tdx_kexec_begin;
++ x86_platform.guest.enc_kexec_finish = tdx_kexec_finish;
++
+ /*
+ * TDX intercepts the RDMSR to read the X2APIC ID in the parallel
+ * bringup low level code. That raises #VE which cannot be handled
+diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
+index dcac96133cb6a9..28757629d0d830 100644
+--- a/arch/x86/events/intel/core.c
++++ b/arch/x86/events/intel/core.c
+@@ -3912,8 +3912,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
+ x86_pmu.pebs_aliases(event);
+ }
+
+- if (needs_branch_stack(event) && is_sampling_event(event))
+- event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
++ if (needs_branch_stack(event)) {
++ /* Avoid branch stack setup for counting events in SAMPLE READ */
++ if (is_sampling_event(event) ||
++ !(event->attr.sample_type & PERF_SAMPLE_READ))
++ event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
++ }
+
+ if (branch_sample_counters(event)) {
+ struct perf_event *leader, *sibling;
+diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
+index b4aa8daa47738f..2959970dd10eb1 100644
+--- a/arch/x86/events/intel/pt.c
++++ b/arch/x86/events/intel/pt.c
+@@ -1606,6 +1606,7 @@ static void pt_event_stop(struct perf_event *event, int mode)
+ * see comment in intel_pt_interrupt().
+ */
+ WRITE_ONCE(pt->handle_nmi, 0);
++ barrier();
+
+ pt_config_stop(event);
+
+@@ -1657,11 +1658,10 @@ static long pt_event_snapshot_aux(struct perf_event *event,
+ return 0;
+
+ /*
+- * Here, handle_nmi tells us if the tracing is on
++ * There is no PT interrupt in this mode, so stop the trace and it will
++ * remain stopped while the buffer is copied.
+ */
+- if (READ_ONCE(pt->handle_nmi))
+- pt_config_stop(event);
+-
++ pt_config_stop(event);
+ pt_read_offset(buf);
+ pt_update_head(pt);
+
+@@ -1673,11 +1673,10 @@ static long pt_event_snapshot_aux(struct perf_event *event,
+ ret = perf_output_copy_aux(&pt->handle, handle, from, to);
+
+ /*
+- * If the tracing was on when we turned up, restart it.
+- * Compiler barrier not needed as we couldn't have been
+- * preempted by anything that touches pt->handle_nmi.
++ * Here, handle_nmi tells us if the tracing was on.
++ * If the tracing was on, restart it.
+ */
+- if (pt->handle_nmi)
++ if (READ_ONCE(pt->handle_nmi))
+ pt_config_start(event);
+
+ return ret;
+diff --git a/arch/x86/hyperv/ivm.c b/arch/x86/hyperv/ivm.c
+index 768d73de0d098a..b4a851d27c7cb8 100644
+--- a/arch/x86/hyperv/ivm.c
++++ b/arch/x86/hyperv/ivm.c
+@@ -523,9 +523,9 @@ static int hv_mark_gpa_visibility(u16 count, const u64 pfn[],
+ * transition is complete, hv_vtom_set_host_visibility() marks the pages
+ * as "present" again.
+ */
+-static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
++static int hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc)
+ {
+- return !set_memory_np(kbuffer, pagecount);
++ return set_memory_np(kbuffer, pagecount);
+ }
+
+ /*
+@@ -536,20 +536,19 @@ static bool hv_vtom_clear_present(unsigned long kbuffer, int pagecount, bool enc
+ * with host. This function works as wrap of hv_mark_gpa_visibility()
+ * with memory base and size.
+ */
+-static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc)
++static int hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bool enc)
+ {
+ enum hv_mem_host_visibility visibility = enc ?
+ VMBUS_PAGE_NOT_VISIBLE : VMBUS_PAGE_VISIBLE_READ_WRITE;
+ u64 *pfn_array;
+ phys_addr_t paddr;
++ int i, pfn, err;
+ void *vaddr;
+ int ret = 0;
+- bool result = true;
+- int i, pfn;
+
+ pfn_array = kmalloc(HV_HYP_PAGE_SIZE, GFP_KERNEL);
+ if (!pfn_array) {
+- result = false;
++ ret = -ENOMEM;
+ goto err_set_memory_p;
+ }
+
+@@ -568,10 +567,8 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
+ if (pfn == HV_MAX_MODIFY_GPA_REP_COUNT || i == pagecount - 1) {
+ ret = hv_mark_gpa_visibility(pfn, pfn_array,
+ visibility);
+- if (ret) {
+- result = false;
++ if (ret)
+ goto err_free_pfn_array;
+- }
+ pfn = 0;
+ }
+ }
+@@ -586,10 +583,11 @@ static bool hv_vtom_set_host_visibility(unsigned long kbuffer, int pagecount, bo
+ * order to avoid leaving the memory range in a "broken" state. Setting
+ * the PRESENT bits shouldn't fail, but return an error if it does.
+ */
+- if (set_memory_p(kbuffer, pagecount))
+- result = false;
++ err = set_memory_p(kbuffer, pagecount);
++ if (err && !ret)
++ ret = err;
+
+- return result;
++ return ret;
+ }
+
+ static bool hv_vtom_tlb_flush_required(bool private)
+diff --git a/arch/x86/include/asm/acpi.h b/arch/x86/include/asm/acpi.h
+index 5af926c050f094..041efa274eebd6 100644
+--- a/arch/x86/include/asm/acpi.h
++++ b/arch/x86/include/asm/acpi.h
+@@ -167,6 +167,14 @@ void acpi_generic_reduced_hw_init(void);
+ void x86_default_set_root_pointer(u64 addr);
+ u64 x86_default_get_root_pointer(void);
+
++#ifdef CONFIG_XEN_PV
++/* A Xen PV domain needs a special acpi_os_ioremap() handling. */
++extern void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys,
++ acpi_size size);
++void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size);
++#define acpi_os_ioremap acpi_os_ioremap
++#endif
++
+ #else /* !CONFIG_ACPI */
+
+ #define acpi_lapic 0
+diff --git a/arch/x86/include/asm/hardirq.h b/arch/x86/include/asm/hardirq.h
+index c67fa6ad098aae..6ffa8b75f4cd33 100644
+--- a/arch/x86/include/asm/hardirq.h
++++ b/arch/x86/include/asm/hardirq.h
+@@ -69,7 +69,11 @@ extern u64 arch_irq_stat(void);
+ #define local_softirq_pending_ref pcpu_hot.softirq_pending
+
+ #if IS_ENABLED(CONFIG_KVM_INTEL)
+-static inline void kvm_set_cpu_l1tf_flush_l1d(void)
++/*
++ * This function is called from noinstr interrupt contexts
++ * and must be inlined to not get instrumentation.
++ */
++static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void)
+ {
+ __this_cpu_write(irq_stat.kvm_cpu_l1tf_flush_l1d, 1);
+ }
+@@ -84,7 +88,7 @@ static __always_inline bool kvm_get_cpu_l1tf_flush_l1d(void)
+ return __this_cpu_read(irq_stat.kvm_cpu_l1tf_flush_l1d);
+ }
+ #else /* !IS_ENABLED(CONFIG_KVM_INTEL) */
+-static inline void kvm_set_cpu_l1tf_flush_l1d(void) { }
++static __always_inline void kvm_set_cpu_l1tf_flush_l1d(void) { }
+ #endif /* IS_ENABLED(CONFIG_KVM_INTEL) */
+
+ #endif /* _ASM_X86_HARDIRQ_H */
+diff --git a/arch/x86/include/asm/idtentry.h b/arch/x86/include/asm/idtentry.h
+index d4f24499b256c8..ad5c68f0509d4d 100644
+--- a/arch/x86/include/asm/idtentry.h
++++ b/arch/x86/include/asm/idtentry.h
+@@ -212,8 +212,8 @@ __visible noinstr void func(struct pt_regs *regs, \
+ irqentry_state_t state = irqentry_enter(regs); \
+ u32 vector = (u32)(u8)error_code; \
+ \
++ kvm_set_cpu_l1tf_flush_l1d(); \
+ instrumentation_begin(); \
+- kvm_set_cpu_l1tf_flush_l1d(); \
+ run_irq_on_irqstack_cond(__##func, regs, vector); \
+ instrumentation_end(); \
+ irqentry_exit(regs, state); \
+@@ -250,7 +250,6 @@ static void __##func(struct pt_regs *regs); \
+ \
+ static __always_inline void instr_##func(struct pt_regs *regs) \
+ { \
+- kvm_set_cpu_l1tf_flush_l1d(); \
+ run_sysvec_on_irqstack_cond(__##func, regs); \
+ } \
+ \
+@@ -258,6 +257,7 @@ __visible noinstr void func(struct pt_regs *regs) \
+ { \
+ irqentry_state_t state = irqentry_enter(regs); \
+ \
++ kvm_set_cpu_l1tf_flush_l1d(); \
+ instrumentation_begin(); \
+ instr_##func (regs); \
+ instrumentation_end(); \
+@@ -288,7 +288,6 @@ static __always_inline void __##func(struct pt_regs *regs); \
+ static __always_inline void instr_##func(struct pt_regs *regs) \
+ { \
+ __irq_enter_raw(); \
+- kvm_set_cpu_l1tf_flush_l1d(); \
+ __##func (regs); \
+ __irq_exit_raw(); \
+ } \
+@@ -297,6 +296,7 @@ __visible noinstr void func(struct pt_regs *regs) \
+ { \
+ irqentry_state_t state = irqentry_enter(regs); \
+ \
++ kvm_set_cpu_l1tf_flush_l1d(); \
+ instrumentation_begin(); \
+ instr_##func (regs); \
+ instrumentation_end(); \
+diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
+index d0274b3be2c400..e18399d08fb178 100644
+--- a/arch/x86/include/asm/kvm_host.h
++++ b/arch/x86/include/asm/kvm_host.h
+@@ -1708,7 +1708,8 @@ struct kvm_x86_ops {
+ void (*enable_nmi_window)(struct kvm_vcpu *vcpu);
+ void (*enable_irq_window)(struct kvm_vcpu *vcpu);
+ void (*update_cr8_intercept)(struct kvm_vcpu *vcpu, int tpr, int irr);
+- bool (*check_apicv_inhibit_reasons)(enum kvm_apicv_inhibit reason);
++
++ const bool x2apic_icr_is_split;
+ const unsigned long required_apicv_inhibits;
+ bool allow_apicv_in_x2apic_without_x2apic_virtualization;
+ void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
+diff --git a/arch/x86/include/asm/pgtable.h b/arch/x86/include/asm/pgtable.h
+index 65b8e5bb902cc3..e39311a89bf478 100644
+--- a/arch/x86/include/asm/pgtable.h
++++ b/arch/x86/include/asm/pgtable.h
+@@ -140,6 +140,11 @@ static inline int pte_young(pte_t pte)
+ return pte_flags(pte) & _PAGE_ACCESSED;
+ }
+
++static inline bool pte_decrypted(pte_t pte)
++{
++ return cc_mkdec(pte_val(pte)) == pte_val(pte);
++}
++
+ #define pmd_dirty pmd_dirty
+ static inline bool pmd_dirty(pmd_t pmd)
+ {
+diff --git a/arch/x86/include/asm/set_memory.h b/arch/x86/include/asm/set_memory.h
+index 9aee31862b4a8b..4b2abce2e3e7d6 100644
+--- a/arch/x86/include/asm/set_memory.h
++++ b/arch/x86/include/asm/set_memory.h
+@@ -49,8 +49,11 @@ int set_memory_wb(unsigned long addr, int numpages);
+ int set_memory_np(unsigned long addr, int numpages);
+ int set_memory_p(unsigned long addr, int numpages);
+ int set_memory_4k(unsigned long addr, int numpages);
++
++bool set_memory_enc_stop_conversion(void);
+ int set_memory_encrypted(unsigned long addr, int numpages);
+ int set_memory_decrypted(unsigned long addr, int numpages);
++
+ int set_memory_np_noalias(unsigned long addr, int numpages);
+ int set_memory_nonglobal(unsigned long addr, int numpages);
+ int set_memory_global(unsigned long addr, int numpages);
+diff --git a/arch/x86/include/asm/x86_init.h b/arch/x86/include/asm/x86_init.h
+index 6149eabe200f5b..213cf5379a5a6d 100644
+--- a/arch/x86/include/asm/x86_init.h
++++ b/arch/x86/include/asm/x86_init.h
+@@ -149,12 +149,22 @@ struct x86_init_acpi {
+ * @enc_status_change_finish Notify HV after the encryption status of a range is changed
+ * @enc_tlb_flush_required Returns true if a TLB flush is needed before changing page encryption status
+ * @enc_cache_flush_required Returns true if a cache flush is needed before changing page encryption status
++ * @enc_kexec_begin Begin the two-step process of converting shared memory back
++ * to private. It stops the new conversions from being started
++ * and waits in-flight conversions to finish, if possible.
++ * @enc_kexec_finish Finish the two-step process of converting shared memory to
++ * private. All memory is private after the call when
++ * the function returns.
++ * It is called on only one CPU while the others are shut down
++ * and with interrupts disabled.
+ */
+ struct x86_guest {
+- bool (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc);
+- bool (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc);
++ int (*enc_status_change_prepare)(unsigned long vaddr, int npages, bool enc);
++ int (*enc_status_change_finish)(unsigned long vaddr, int npages, bool enc);
+ bool (*enc_tlb_flush_required)(bool enc);
+ bool (*enc_cache_flush_required)(void);
++ void (*enc_kexec_begin)(void);
++ void (*enc_kexec_finish)(void);
+ };
+
+ /**
+diff --git a/arch/x86/kernel/acpi/boot.c b/arch/x86/kernel/acpi/boot.c
+index 4bf82dbd2a6b5a..01e929a0f6ccc1 100644
+--- a/arch/x86/kernel/acpi/boot.c
++++ b/arch/x86/kernel/acpi/boot.c
+@@ -1862,3 +1862,14 @@ u64 x86_default_get_root_pointer(void)
+ {
+ return boot_params.acpi_rsdp_addr;
+ }
++
++#ifdef CONFIG_XEN_PV
++void __iomem *x86_acpi_os_ioremap(acpi_physical_address phys, acpi_size size)
++{
++ return ioremap_cache(phys, size);
++}
++
++void __iomem * (*acpi_os_ioremap)(acpi_physical_address phys, acpi_size size) =
++ x86_acpi_os_ioremap;
++EXPORT_SYMBOL_GPL(acpi_os_ioremap);
++#endif
+diff --git a/arch/x86/kernel/cpu/sgx/main.c b/arch/x86/kernel/cpu/sgx/main.c
+index 27892e57c4ef93..6aeeb43dd3f6a8 100644
+--- a/arch/x86/kernel/cpu/sgx/main.c
++++ b/arch/x86/kernel/cpu/sgx/main.c
+@@ -475,24 +475,25 @@ struct sgx_epc_page *__sgx_alloc_epc_page(void)
+ {
+ struct sgx_epc_page *page;
+ int nid_of_current = numa_node_id();
+- int nid = nid_of_current;
++ int nid_start, nid;
+
+- if (node_isset(nid_of_current, sgx_numa_mask)) {
+- page = __sgx_alloc_epc_page_from_node(nid_of_current);
+- if (page)
+- return page;
+- }
+-
+- /* Fall back to the non-local NUMA nodes: */
+- while (true) {
+- nid = next_node_in(nid, sgx_numa_mask);
+- if (nid == nid_of_current)
+- break;
++ /*
++ * Try local node first. If it doesn't have an EPC section,
++ * fall back to the non-local NUMA nodes.
++ */
++ if (node_isset(nid_of_current, sgx_numa_mask))
++ nid_start = nid_of_current;
++ else
++ nid_start = next_node_in(nid_of_current, sgx_numa_mask);
+
++ nid = nid_start;
++ do {
+ page = __sgx_alloc_epc_page_from_node(nid);
+ if (page)
+ return page;
+- }
++
++ nid = next_node_in(nid, sgx_numa_mask);
++ } while (nid != nid_start);
+
+ return ERR_PTR(-ENOMEM);
+ }
+diff --git a/arch/x86/kernel/crash.c b/arch/x86/kernel/crash.c
+index f06501445cd981..340af815565848 100644
+--- a/arch/x86/kernel/crash.c
++++ b/arch/x86/kernel/crash.c
+@@ -128,6 +128,18 @@ void native_machine_crash_shutdown(struct pt_regs *regs)
+ #ifdef CONFIG_HPET_TIMER
+ hpet_disable();
+ #endif
++
++ /*
++ * Non-crash kexec calls enc_kexec_begin() while scheduling is still
++ * active. This allows the callback to wait until all in-flight
++ * shared<->private conversions are complete. In a crash scenario,
++ * enc_kexec_begin() gets called after all but one CPU have been shut
++ * down and interrupts have been disabled. This allows the callback to
++ * detect a race with the conversion and report it.
++ */
++ x86_platform.guest.enc_kexec_begin();
++ x86_platform.guest.enc_kexec_finish();
++
+ crash_save_cpu(regs, safe_smp_processor_id());
+ }
+
+diff --git a/arch/x86/kernel/head64.c b/arch/x86/kernel/head64.c
+index a817ed0724d1e7..4b9d4557fc94a4 100644
+--- a/arch/x86/kernel/head64.c
++++ b/arch/x86/kernel/head64.c
+@@ -559,10 +559,11 @@ void early_setup_idt(void)
+ */
+ void __head startup_64_setup_gdt_idt(void)
+ {
++ struct desc_struct *gdt = (void *)(__force unsigned long)init_per_cpu_var(gdt_page.gdt);
+ void *handler = NULL;
+
+ struct desc_ptr startup_gdt_descr = {
+- .address = (unsigned long)&RIP_REL_REF(init_per_cpu_var(gdt_page.gdt)),
++ .address = (unsigned long)&RIP_REL_REF(*gdt),
+ .size = GDT_SIZE - 1,
+ };
+
+diff --git a/arch/x86/kernel/jailhouse.c b/arch/x86/kernel/jailhouse.c
+index df337860612d84..cd8ed1edbf9ee7 100644
+--- a/arch/x86/kernel/jailhouse.c
++++ b/arch/x86/kernel/jailhouse.c
+@@ -12,6 +12,7 @@
+ #include <linux/kernel.h>
+ #include <linux/reboot.h>
+ #include <linux/serial_8250.h>
++#include <linux/acpi.h>
+ #include <asm/apic.h>
+ #include <asm/io_apic.h>
+ #include <asm/acpi.h>
+diff --git a/arch/x86/kernel/mmconf-fam10h_64.c b/arch/x86/kernel/mmconf-fam10h_64.c
+index c94dec6a18345a..1f54eedc3015e9 100644
+--- a/arch/x86/kernel/mmconf-fam10h_64.c
++++ b/arch/x86/kernel/mmconf-fam10h_64.c
+@@ -9,6 +9,7 @@
+ #include <linux/pci.h>
+ #include <linux/dmi.h>
+ #include <linux/range.h>
++#include <linux/acpi.h>
+
+ #include <asm/pci-direct.h>
+ #include <linux/sort.h>
+diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
+index 6d3d20e3e43a9b..d8d582b750d4f6 100644
+--- a/arch/x86/kernel/process_64.c
++++ b/arch/x86/kernel/process_64.c
+@@ -798,6 +798,27 @@ static long prctl_map_vdso(const struct vdso_image *image, unsigned long addr)
+
+ #define LAM_U57_BITS 6
+
++static void enable_lam_func(void *__mm)
++{
++ struct mm_struct *mm = __mm;
++
++ if (this_cpu_read(cpu_tlbstate.loaded_mm) == mm) {
++ write_cr3(__read_cr3() | mm->context.lam_cr3_mask);
++ set_tlbstate_lam_mode(mm);
++ }
++}
++
++static void mm_enable_lam(struct mm_struct *mm)
++{
++ /*
++ * Even though the process must still be single-threaded at this
++ * point, kernel threads may be using the mm. IPI those kernel
++ * threads if they exist.
++ */
++ on_each_cpu_mask(mm_cpumask(mm), enable_lam_func, mm, true);
++ set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags);
++}
++
+ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
+ {
+ if (!cpu_feature_enabled(X86_FEATURE_LAM))
+@@ -814,6 +835,10 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
+ if (mmap_write_lock_killable(mm))
+ return -EINTR;
+
++ /*
++ * MM_CONTEXT_LOCK_LAM is set on clone. Prevent LAM from
++ * being enabled unless the process is single threaded:
++ */
+ if (test_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags)) {
+ mmap_write_unlock(mm);
+ return -EBUSY;
+@@ -830,9 +855,7 @@ static int prctl_enable_tagged_addr(struct mm_struct *mm, unsigned long nr_bits)
+ return -EINVAL;
+ }
+
+- write_cr3(__read_cr3() | mm->context.lam_cr3_mask);
+- set_tlbstate_lam_mode(mm);
+- set_bit(MM_CONTEXT_LOCK_LAM, &mm->context.flags);
++ mm_enable_lam(mm);
+
+ mmap_write_unlock(mm);
+
+diff --git a/arch/x86/kernel/reboot.c b/arch/x86/kernel/reboot.c
+index f3130f762784a1..bb7a44af7efd19 100644
+--- a/arch/x86/kernel/reboot.c
++++ b/arch/x86/kernel/reboot.c
+@@ -12,6 +12,7 @@
+ #include <linux/delay.h>
+ #include <linux/objtool.h>
+ #include <linux/pgtable.h>
++#include <linux/kexec.h>
+ #include <acpi/reboot.h>
+ #include <asm/io.h>
+ #include <asm/apic.h>
+@@ -716,6 +717,14 @@ static void native_machine_emergency_restart(void)
+
+ void native_machine_shutdown(void)
+ {
++ /*
++ * Call enc_kexec_begin() while all CPUs are still active and
++ * interrupts are enabled. This will allow all in-flight memory
++ * conversions to finish cleanly.
++ */
++ if (kexec_in_progress)
++ x86_platform.guest.enc_kexec_begin();
++
+ /* Stop the cpus and apics */
+ #ifdef CONFIG_X86_IO_APIC
+ /*
+@@ -752,6 +761,9 @@ void native_machine_shutdown(void)
+ #ifdef CONFIG_X86_64
+ x86_platform.iommu_shutdown();
+ #endif
++
++ if (kexec_in_progress)
++ x86_platform.guest.enc_kexec_finish();
+ }
+
+ static void __machine_emergency_restart(int emergency)
+diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
+index 0c35207320cb4f..390e4fe7433ea3 100644
+--- a/arch/x86/kernel/smpboot.c
++++ b/arch/x86/kernel/smpboot.c
+@@ -60,6 +60,7 @@
+ #include <linux/stackprotector.h>
+ #include <linux/cpuhotplug.h>
+ #include <linux/mc146818rtc.h>
++#include <linux/acpi.h>
+
+ #include <asm/acpi.h>
+ #include <asm/cacheinfo.h>
+diff --git a/arch/x86/kernel/x86_init.c b/arch/x86/kernel/x86_init.c
+index d5dc5a92635a82..0a2bbd674a6d99 100644
+--- a/arch/x86/kernel/x86_init.c
++++ b/arch/x86/kernel/x86_init.c
+@@ -8,6 +8,7 @@
+ #include <linux/ioport.h>
+ #include <linux/export.h>
+ #include <linux/pci.h>
++#include <linux/acpi.h>
+
+ #include <asm/acpi.h>
+ #include <asm/bios_ebda.h>
+@@ -134,10 +135,12 @@ struct x86_cpuinit_ops x86_cpuinit = {
+
+ static void default_nmi_init(void) { };
+
+-static bool enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return true; }
+-static bool enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return true; }
++static int enc_status_change_prepare_noop(unsigned long vaddr, int npages, bool enc) { return 0; }
++static int enc_status_change_finish_noop(unsigned long vaddr, int npages, bool enc) { return 0; }
+ static bool enc_tlb_flush_required_noop(bool enc) { return false; }
+ static bool enc_cache_flush_required_noop(void) { return false; }
++static void enc_kexec_begin_noop(void) {}
++static void enc_kexec_finish_noop(void) {}
+ static bool is_private_mmio_noop(u64 addr) {return false; }
+
+ struct x86_platform_ops x86_platform __ro_after_init = {
+@@ -161,6 +164,8 @@ struct x86_platform_ops x86_platform __ro_after_init = {
+ .enc_status_change_finish = enc_status_change_finish_noop,
+ .enc_tlb_flush_required = enc_tlb_flush_required_noop,
+ .enc_cache_flush_required = enc_cache_flush_required_noop,
++ .enc_kexec_begin = enc_kexec_begin_noop,
++ .enc_kexec_finish = enc_kexec_finish_noop,
+ },
+ };
+
+diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c
+index acd7d48100a1d3..523d02c50562f4 100644
+--- a/arch/x86/kvm/lapic.c
++++ b/arch/x86/kvm/lapic.c
+@@ -351,10 +351,8 @@ static void kvm_recalculate_logical_map(struct kvm_apic_map *new,
+ * reversing the LDR calculation to get cluster of APICs, i.e. no
+ * additional work is required.
+ */
+- if (apic_x2apic_mode(apic)) {
+- WARN_ON_ONCE(ldr != kvm_apic_calc_x2apic_ldr(kvm_x2apic_id(apic)));
++ if (apic_x2apic_mode(apic))
+ return;
+- }
+
+ if (WARN_ON_ONCE(!kvm_apic_map_get_logical_dest(new, ldr,
+ &cluster, &mask))) {
+@@ -2453,6 +2451,43 @@ void kvm_lapic_set_eoi(struct kvm_vcpu *vcpu)
+ }
+ EXPORT_SYMBOL_GPL(kvm_lapic_set_eoi);
+
++#define X2APIC_ICR_RESERVED_BITS (GENMASK_ULL(31, 20) | GENMASK_ULL(17, 16) | BIT(13))
++
++int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data)
++{
++ if (data & X2APIC_ICR_RESERVED_BITS)
++ return 1;
++
++ /*
++ * The BUSY bit is reserved on both Intel and AMD in x2APIC mode, but
++ * only AMD requires it to be zero, Intel essentially just ignores the
++ * bit. And if IPI virtualization (Intel) or x2AVIC (AMD) is enabled,
++ * the CPU performs the reserved bits checks, i.e. the underlying CPU
++ * behavior will "win". Arbitrarily clear the BUSY bit, as there is no
++ * sane way to provide consistent behavior with respect to hardware.
++ */
++ data &= ~APIC_ICR_BUSY;
++
++ kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32));
++ if (kvm_x86_ops.x2apic_icr_is_split) {
++ kvm_lapic_set_reg(apic, APIC_ICR, data);
++ kvm_lapic_set_reg(apic, APIC_ICR2, data >> 32);
++ } else {
++ kvm_lapic_set_reg64(apic, APIC_ICR, data);
++ }
++ trace_kvm_apic_write(APIC_ICR, data);
++ return 0;
++}
++
++static u64 kvm_x2apic_icr_read(struct kvm_lapic *apic)
++{
++ if (kvm_x86_ops.x2apic_icr_is_split)
++ return (u64)kvm_lapic_get_reg(apic, APIC_ICR) |
++ (u64)kvm_lapic_get_reg(apic, APIC_ICR2) << 32;
++
++ return kvm_lapic_get_reg64(apic, APIC_ICR);
++}
++
+ /* emulate APIC access in a trap manner */
+ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
+ {
+@@ -2470,7 +2505,7 @@ void kvm_apic_write_nodecode(struct kvm_vcpu *vcpu, u32 offset)
+ * maybe-unecessary write, and both are in the noise anyways.
+ */
+ if (apic_x2apic_mode(apic) && offset == APIC_ICR)
+- kvm_x2apic_icr_write(apic, kvm_lapic_get_reg64(apic, APIC_ICR));
++ WARN_ON_ONCE(kvm_x2apic_icr_write(apic, kvm_x2apic_icr_read(apic)));
+ else
+ kvm_lapic_reg_write(apic, offset, kvm_lapic_get_reg(apic, offset));
+ }
+@@ -2964,34 +2999,48 @@ static int kvm_apic_state_fixup(struct kvm_vcpu *vcpu,
+ struct kvm_lapic_state *s, bool set)
+ {
+ if (apic_x2apic_mode(vcpu->arch.apic)) {
++ u32 x2apic_id = kvm_x2apic_id(vcpu->arch.apic);
+ u32 *id = (u32 *)(s->regs + APIC_ID);
+ u32 *ldr = (u32 *)(s->regs + APIC_LDR);
+ u64 icr;
+
+ if (vcpu->kvm->arch.x2apic_format) {
+- if (*id != vcpu->vcpu_id)
++ if (*id != x2apic_id)
+ return -EINVAL;
+ } else {
++ /*
++ * Ignore the userspace value when setting APIC state.
++ * KVM's model is that the x2APIC ID is readonly, e.g.
++ * KVM only supports delivering interrupts to KVM's
++ * version of the x2APIC ID. However, for backwards
++ * compatibility, don't reject attempts to set a
++ * mismatched ID for userspace that hasn't opted into
++ * x2apic_format.
++ */
+ if (set)
+- *id >>= 24;
++ *id = x2apic_id;
+ else
+- *id <<= 24;
++ *id = x2apic_id << 24;
+ }
+
+ /*
+ * In x2APIC mode, the LDR is fixed and based on the id. And
+- * ICR is internally a single 64-bit register, but needs to be
+- * split to ICR+ICR2 in userspace for backwards compatibility.
++ * if the ICR is _not_ split, ICR is internally a single 64-bit
++ * register, but needs to be split to ICR+ICR2 in userspace for
++ * backwards compatibility.
+ */
+- if (set) {
+- *ldr = kvm_apic_calc_x2apic_ldr(*id);
+-
+- icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
+- (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
+- __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr);
+- } else {
+- icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
+- __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
++ if (set)
++ *ldr = kvm_apic_calc_x2apic_ldr(x2apic_id);
++
++ if (!kvm_x86_ops.x2apic_icr_is_split) {
++ if (set) {
++ icr = __kvm_lapic_get_reg(s->regs, APIC_ICR) |
++ (u64)__kvm_lapic_get_reg(s->regs, APIC_ICR2) << 32;
++ __kvm_lapic_set_reg64(s->regs, APIC_ICR, icr);
++ } else {
++ icr = __kvm_lapic_get_reg64(s->regs, APIC_ICR);
++ __kvm_lapic_set_reg(s->regs, APIC_ICR2, icr >> 32);
++ }
+ }
+ }
+
+@@ -3183,22 +3232,12 @@ int kvm_lapic_set_vapic_addr(struct kvm_vcpu *vcpu, gpa_t vapic_addr)
+ return 0;
+ }
+
+-int kvm_x2apic_icr_write(struct kvm_lapic *apic, u64 data)
+-{
+- data &= ~APIC_ICR_BUSY;
+-
+- kvm_apic_send_ipi(apic, (u32)data, (u32)(data >> 32));
+- kvm_lapic_set_reg64(apic, APIC_ICR, data);
+- trace_kvm_apic_write(APIC_ICR, data);
+- return 0;
+-}
+-
+ static int kvm_lapic_msr_read(struct kvm_lapic *apic, u32 reg, u64 *data)
+ {
+ u32 low;
+
+ if (reg == APIC_ICR) {
+- *data = kvm_lapic_get_reg64(apic, APIC_ICR);
++ *data = kvm_x2apic_icr_read(apic);
+ return 0;
+ }
+
+diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
+index 0357f7af559665..6d5da700268a5b 100644
+--- a/arch/x86/kvm/svm/svm.c
++++ b/arch/x86/kvm/svm/svm.c
+@@ -5051,6 +5051,8 @@ static struct kvm_x86_ops svm_x86_ops __initdata = {
+ .enable_nmi_window = svm_enable_nmi_window,
+ .enable_irq_window = svm_enable_irq_window,
+ .update_cr8_intercept = svm_update_cr8_intercept,
++
++ .x2apic_icr_is_split = true,
+ .set_virtual_apic_mode = avic_refresh_virtual_apic_mode,
+ .refresh_apicv_exec_ctrl = avic_refresh_apicv_exec_ctrl,
+ .apicv_post_state_restore = avic_apicv_post_state_restore,
+diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
+index 547fca3709febd..35c2c004dacd2b 100644
+--- a/arch/x86/kvm/vmx/main.c
++++ b/arch/x86/kvm/vmx/main.c
+@@ -89,6 +89,8 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
+ .enable_nmi_window = vmx_enable_nmi_window,
+ .enable_irq_window = vmx_enable_irq_window,
+ .update_cr8_intercept = vmx_update_cr8_intercept,
++
++ .x2apic_icr_is_split = false,
+ .set_virtual_apic_mode = vmx_set_virtual_apic_mode,
+ .set_apic_access_page_addr = vmx_set_apic_access_page_addr,
+ .refresh_apicv_exec_ctrl = vmx_refresh_apicv_exec_ctrl,
+diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
+index d404227c164d60..e46aba18600e7a 100644
+--- a/arch/x86/kvm/vmx/x86_ops.h
++++ b/arch/x86/kvm/vmx/x86_ops.h
+@@ -46,7 +46,6 @@ bool vmx_apic_init_signal_blocked(struct kvm_vcpu *vcpu);
+ void vmx_migrate_timers(struct kvm_vcpu *vcpu);
+ void vmx_set_virtual_apic_mode(struct kvm_vcpu *vcpu);
+ void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
+-bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason);
+ void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
+ void vmx_hwapic_isr_update(int max_isr);
+ int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu);
+diff --git a/arch/x86/mm/mem_encrypt_amd.c b/arch/x86/mm/mem_encrypt_amd.c
+index 422602f6039b82..e7b67519ddb5d3 100644
+--- a/arch/x86/mm/mem_encrypt_amd.c
++++ b/arch/x86/mm/mem_encrypt_amd.c
+@@ -283,7 +283,7 @@ static void enc_dec_hypercall(unsigned long vaddr, unsigned long size, bool enc)
+ #endif
+ }
+
+-static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
++static int amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool enc)
+ {
+ /*
+ * To maintain the security guarantees of SEV-SNP guests, make sure
+@@ -292,11 +292,11 @@ static bool amd_enc_status_change_prepare(unsigned long vaddr, int npages, bool
+ if (cc_platform_has(CC_ATTR_GUEST_SEV_SNP) && !enc)
+ snp_set_memory_shared(vaddr, npages);
+
+- return true;
++ return 0;
+ }
+
+ /* Return true unconditionally: return value doesn't matter for the SEV side */
+-static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
++static int amd_enc_status_change_finish(unsigned long vaddr, int npages, bool enc)
+ {
+ /*
+ * After memory is mapped encrypted in the page table, validate it
+@@ -308,7 +308,7 @@ static bool amd_enc_status_change_finish(unsigned long vaddr, int npages, bool e
+ if (!cc_platform_has(CC_ATTR_HOST_MEM_ENCRYPT))
+ enc_dec_hypercall(vaddr, npages << PAGE_SHIFT, enc);
+
+- return true;
++ return 0;
+ }
+
+ static void __init __set_clr_pte_enc(pte_t *kpte, int level, bool enc)
+diff --git a/arch/x86/mm/pat/set_memory.c b/arch/x86/mm/pat/set_memory.c
+index 19fdfbb171ed6e..1356e25e6d1254 100644
+--- a/arch/x86/mm/pat/set_memory.c
++++ b/arch/x86/mm/pat/set_memory.c
+@@ -2196,7 +2196,8 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
+ cpa_flush(&cpa, x86_platform.guest.enc_cache_flush_required());
+
+ /* Notify hypervisor that we are about to set/clr encryption attribute. */
+- if (!x86_platform.guest.enc_status_change_prepare(addr, numpages, enc))
++ ret = x86_platform.guest.enc_status_change_prepare(addr, numpages, enc);
++ if (ret)
+ goto vmm_fail;
+
+ ret = __change_page_attr_set_clr(&cpa, 1);
+@@ -2214,24 +2215,61 @@ static int __set_memory_enc_pgtable(unsigned long addr, int numpages, bool enc)
+ return ret;
+
+ /* Notify hypervisor that we have successfully set/clr encryption attribute. */
+- if (!x86_platform.guest.enc_status_change_finish(addr, numpages, enc))
++ ret = x86_platform.guest.enc_status_change_finish(addr, numpages, enc);
++ if (ret)
+ goto vmm_fail;
+
+ return 0;
+
+ vmm_fail:
+- WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s.\n",
+- (void *)addr, numpages, enc ? "private" : "shared");
++ WARN_ONCE(1, "CPA VMM failure to convert memory (addr=%p, numpages=%d) to %s: %d\n",
++ (void *)addr, numpages, enc ? "private" : "shared", ret);
+
+- return -EIO;
++ return ret;
++}
++
++/*
++ * The lock serializes conversions between private and shared memory.
++ *
++ * It is taken for read on conversion. A write lock guarantees that no
++ * concurrent conversions are in progress.
++ */
++static DECLARE_RWSEM(mem_enc_lock);
++
++/*
++ * Stop new private<->shared conversions.
++ *
++ * Taking the exclusive mem_enc_lock waits for in-flight conversions to complete.
++ * The lock is not released to prevent new conversions from being started.
++ */
++bool set_memory_enc_stop_conversion(void)
++{
++ /*
++ * In a crash scenario, sleep is not allowed. Try to take the lock.
++ * Failure indicates that there is a race with the conversion.
++ */
++ if (oops_in_progress)
++ return down_write_trylock(&mem_enc_lock);
++
++ down_write(&mem_enc_lock);
++
++ return true;
+ }
+
+ static int __set_memory_enc_dec(unsigned long addr, int numpages, bool enc)
+ {
+- if (cc_platform_has(CC_ATTR_MEM_ENCRYPT))
+- return __set_memory_enc_pgtable(addr, numpages, enc);
++ int ret = 0;
+
+- return 0;
++ if (cc_platform_has(CC_ATTR_MEM_ENCRYPT)) {
++ if (!down_read_trylock(&mem_enc_lock))
++ return -EBUSY;
++
++ ret = __set_memory_enc_pgtable(addr, numpages, enc);
++
++ up_read(&mem_enc_lock);
++ }
++
++ return ret;
+ }
+
+ int set_memory_encrypted(unsigned long addr, int numpages)
+diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c
+index 44ac64f3a047ca..a041d2ecd83804 100644
+--- a/arch/x86/mm/tlb.c
++++ b/arch/x86/mm/tlb.c
+@@ -503,9 +503,9 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
+ {
+ struct mm_struct *prev = this_cpu_read(cpu_tlbstate.loaded_mm);
+ u16 prev_asid = this_cpu_read(cpu_tlbstate.loaded_mm_asid);
+- unsigned long new_lam = mm_lam_cr3_mask(next);
+ bool was_lazy = this_cpu_read(cpu_tlbstate_shared.is_lazy);
+ unsigned cpu = smp_processor_id();
++ unsigned long new_lam;
+ u64 next_tlb_gen;
+ bool need_flush;
+ u16 new_asid;
+@@ -619,9 +619,7 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
+ cpumask_clear_cpu(cpu, mm_cpumask(prev));
+ }
+
+- /*
+- * Start remote flushes and then read tlb_gen.
+- */
++ /* Start receiving IPIs and then read tlb_gen (and LAM below) */
+ if (next != &init_mm)
+ cpumask_set_cpu(cpu, mm_cpumask(next));
+ next_tlb_gen = atomic64_read(&next->context.tlb_gen);
+@@ -633,6 +631,7 @@ void switch_mm_irqs_off(struct mm_struct *unused, struct mm_struct *next,
+ barrier();
+ }
+
++ new_lam = mm_lam_cr3_mask(next);
+ set_tlbstate_lam_mode(next);
+ if (need_flush) {
+ this_cpu_write(cpu_tlbstate.ctxs[new_asid].ctx_id, next->context.ctx_id);
+diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c
+index 5159c7a2292294..2f28a9b34b91e4 100644
+--- a/arch/x86/net/bpf_jit_comp.c
++++ b/arch/x86/net/bpf_jit_comp.c
+@@ -273,7 +273,7 @@ struct jit_context {
+ /* Number of bytes emit_patch() needs to generate instructions */
+ #define X86_PATCH_SIZE 5
+ /* Number of bytes that will be skipped on tailcall */
+-#define X86_TAIL_CALL_OFFSET (11 + ENDBR_INSN_SIZE)
++#define X86_TAIL_CALL_OFFSET (12 + ENDBR_INSN_SIZE)
+
+ static void push_r12(u8 **pprog)
+ {
+@@ -403,6 +403,37 @@ static void emit_cfi(u8 **pprog, u32 hash)
+ *pprog = prog;
+ }
+
++static void emit_prologue_tail_call(u8 **pprog, bool is_subprog)
++{
++ u8 *prog = *pprog;
++
++ if (!is_subprog) {
++ /* cmp rax, MAX_TAIL_CALL_CNT */
++ EMIT4(0x48, 0x83, 0xF8, MAX_TAIL_CALL_CNT);
++ EMIT2(X86_JA, 6); /* ja 6 */
++ /* rax is tail_call_cnt if <= MAX_TAIL_CALL_CNT.
++ * case1: entry of main prog.
++ * case2: tail callee of main prog.
++ */
++ EMIT1(0x50); /* push rax */
++ /* Make rax as tail_call_cnt_ptr. */
++ EMIT3(0x48, 0x89, 0xE0); /* mov rax, rsp */
++ EMIT2(0xEB, 1); /* jmp 1 */
++ /* rax is tail_call_cnt_ptr if > MAX_TAIL_CALL_CNT.
++ * case: tail callee of subprog.
++ */
++ EMIT1(0x50); /* push rax */
++ /* push tail_call_cnt_ptr */
++ EMIT1(0x50); /* push rax */
++ } else { /* is_subprog */
++ /* rax is tail_call_cnt_ptr. */
++ EMIT1(0x50); /* push rax */
++ EMIT1(0x50); /* push rax */
++ }
++
++ *pprog = prog;
++}
++
+ /*
+ * Emit x86-64 prologue code for BPF program.
+ * bpf_tail_call helper will skip the first X86_TAIL_CALL_OFFSET bytes
+@@ -424,10 +455,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+ /* When it's the entry of the whole tailcall context,
+ * zeroing rax means initialising tail_call_cnt.
+ */
+- EMIT2(0x31, 0xC0); /* xor eax, eax */
++ EMIT3(0x48, 0x31, 0xC0); /* xor rax, rax */
+ else
+ /* Keep the same instruction layout. */
+- EMIT2(0x66, 0x90); /* nop2 */
++ emit_nops(&prog, 3); /* nop3 */
+ }
+ /* Exception callback receives FP as third parameter */
+ if (is_exception_cb) {
+@@ -453,7 +484,7 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf,
+ if (stack_depth)
+ EMIT3_off32(0x48, 0x81, 0xEC, round_up(stack_depth, 8));
+ if (tail_call_reachable)
+- EMIT1(0x50); /* push rax */
++ emit_prologue_tail_call(&prog, is_subprog);
+ *pprog = prog;
+ }
+
+@@ -589,13 +620,15 @@ static void emit_return(u8 **pprog, u8 *ip)
+ *pprog = prog;
+ }
+
++#define BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack) (-16 - round_up(stack, 8))
++
+ /*
+ * Generate the following code:
+ *
+ * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ...
+ * if (index >= array->map.max_entries)
+ * goto out;
+- * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT)
++ * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT)
+ * goto out;
+ * prog = array->ptrs[index];
+ * if (prog == NULL)
+@@ -608,7 +641,7 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+ u32 stack_depth, u8 *ip,
+ struct jit_context *ctx)
+ {
+- int tcc_off = -4 - round_up(stack_depth, 8);
++ int tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack_depth);
+ u8 *prog = *pprog, *start = *pprog;
+ int offset;
+
+@@ -630,16 +663,14 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+ EMIT2(X86_JBE, offset); /* jbe out */
+
+ /*
+- * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT)
++ * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT)
+ * goto out;
+ */
+- EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
+- EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
++ EMIT3_off32(0x48, 0x8B, 0x85, tcc_ptr_off); /* mov rax, qword ptr [rbp - tcc_ptr_off] */
++ EMIT4(0x48, 0x83, 0x38, MAX_TAIL_CALL_CNT); /* cmp qword ptr [rax], MAX_TAIL_CALL_CNT */
+
+ offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+ EMIT2(X86_JAE, offset); /* jae out */
+- EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
+- EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
+
+ /* prog = array->ptrs[index]; */
+ EMIT4_off32(0x48, 0x8B, 0x8C, 0xD6, /* mov rcx, [rsi + rdx * 8 + offsetof(...)] */
+@@ -654,6 +685,9 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+ offset = ctx->tail_call_indirect_label - (prog + 2 - start);
+ EMIT2(X86_JE, offset); /* je out */
+
++ /* Inc tail_call_cnt if the slot is populated. */
++ EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */
++
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+@@ -663,6 +697,11 @@ static void emit_bpf_tail_call_indirect(struct bpf_prog *bpf_prog,
+ pop_r12(&prog);
+ }
+
++ /* Pop tail_call_cnt_ptr. */
++ EMIT1(0x58); /* pop rax */
++ /* Pop tail_call_cnt, if it's main prog.
++ * Pop tail_call_cnt_ptr, if it's subprog.
++ */
+ EMIT1(0x58); /* pop rax */
+ if (stack_depth)
+ EMIT3_off32(0x48, 0x81, 0xC4, /* add rsp, sd */
+@@ -691,21 +730,19 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
+ bool *callee_regs_used, u32 stack_depth,
+ struct jit_context *ctx)
+ {
+- int tcc_off = -4 - round_up(stack_depth, 8);
++ int tcc_ptr_off = BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack_depth);
+ u8 *prog = *pprog, *start = *pprog;
+ int offset;
+
+ /*
+- * if (tail_call_cnt++ >= MAX_TAIL_CALL_CNT)
++ * if ((*tcc_ptr)++ >= MAX_TAIL_CALL_CNT)
+ * goto out;
+ */
+- EMIT2_off32(0x8B, 0x85, tcc_off); /* mov eax, dword ptr [rbp - tcc_off] */
+- EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */
++ EMIT3_off32(0x48, 0x8B, 0x85, tcc_ptr_off); /* mov rax, qword ptr [rbp - tcc_ptr_off] */
++ EMIT4(0x48, 0x83, 0x38, MAX_TAIL_CALL_CNT); /* cmp qword ptr [rax], MAX_TAIL_CALL_CNT */
+
+ offset = ctx->tail_call_direct_label - (prog + 2 - start);
+ EMIT2(X86_JAE, offset); /* jae out */
+- EMIT3(0x83, 0xC0, 0x01); /* add eax, 1 */
+- EMIT2_off32(0x89, 0x85, tcc_off); /* mov dword ptr [rbp - tcc_off], eax */
+
+ poke->tailcall_bypass = ip + (prog - start);
+ poke->adj_off = X86_TAIL_CALL_OFFSET;
+@@ -715,6 +752,9 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
+ emit_jump(&prog, (u8 *)poke->tailcall_target + X86_PATCH_SIZE,
+ poke->tailcall_bypass);
+
++ /* Inc tail_call_cnt if the slot is populated. */
++ EMIT4(0x48, 0x83, 0x00, 0x01); /* add qword ptr [rax], 1 */
++
+ if (bpf_prog->aux->exception_boundary) {
+ pop_callee_regs(&prog, all_callee_regs_used);
+ pop_r12(&prog);
+@@ -724,6 +764,11 @@ static void emit_bpf_tail_call_direct(struct bpf_prog *bpf_prog,
+ pop_r12(&prog);
+ }
+
++ /* Pop tail_call_cnt_ptr. */
++ EMIT1(0x58); /* pop rax */
++ /* Pop tail_call_cnt, if it's main prog.
++ * Pop tail_call_cnt_ptr, if it's subprog.
++ */
+ EMIT1(0x58); /* pop rax */
+ if (stack_depth)
+ EMIT3_off32(0x48, 0x81, 0xC4, round_up(stack_depth, 8));
+@@ -1313,9 +1358,11 @@ static void emit_shiftx(u8 **pprog, u32 dst_reg, u8 src_reg, bool is64, u8 op)
+
+ #define INSN_SZ_DIFF (((addrs[i] - addrs[i - 1]) - (prog - temp)))
+
+-/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
+-#define RESTORE_TAIL_CALL_CNT(stack) \
+- EMIT3_off32(0x48, 0x8B, 0x85, -round_up(stack, 8) - 8)
++#define __LOAD_TCC_PTR(off) \
++ EMIT3_off32(0x48, 0x8B, 0x85, off)
++/* mov rax, qword ptr [rbp - rounded_stack_depth - 16] */
++#define LOAD_TAIL_CALL_CNT_PTR(stack) \
++ __LOAD_TCC_PTR(BPF_TAIL_CALL_CNT_PTR_STACK_OFF(stack))
+
+ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 *rw_image,
+ int oldproglen, struct jit_context *ctx, bool jmp_padding)
+@@ -2038,7 +2085,7 @@ st: if (is_imm8(insn->off))
+
+ func = (u8 *) __bpf_call_base + imm32;
+ if (tail_call_reachable) {
+- RESTORE_TAIL_CALL_CNT(bpf_prog->aux->stack_depth);
++ LOAD_TAIL_CALL_CNT_PTR(bpf_prog->aux->stack_depth);
+ ip += 7;
+ }
+ if (!imm32)
+@@ -2713,6 +2760,10 @@ static int invoke_bpf_mod_ret(const struct btf_func_model *m, u8 **pprog,
+ return 0;
+ }
+
++/* mov rax, qword ptr [rbp - rounded_stack_depth - 8] */
++#define LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack) \
++ __LOAD_TCC_PTR(-round_up(stack, 8) - 8)
++
+ /* Example:
+ * __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev);
+ * its 'struct btf_func_model' will be nr_args=2
+@@ -2833,7 +2884,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
+ * [ ... ]
+ * [ stack_arg2 ]
+ * RBP - arg_stack_off [ stack_arg1 ]
+- * RSP [ tail_call_cnt ] BPF_TRAMP_F_TAIL_CALL_CTX
++ * RSP [ tail_call_cnt_ptr ] BPF_TRAMP_F_TAIL_CALL_CTX
+ */
+
+ /* room for return value of orig_call or fentry prog */
+@@ -2962,10 +3013,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
+ save_args(m, &prog, arg_stack_off, true);
+
+ if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
+- /* Before calling the original function, restore the
+- * tail_call_cnt from stack to rax.
++ /* Before calling the original function, load the
++ * tail_call_cnt_ptr from stack to rax.
+ */
+- RESTORE_TAIL_CALL_CNT(stack_size);
++ LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack_size);
+ }
+
+ if (flags & BPF_TRAMP_F_ORIG_STACK) {
+@@ -3024,10 +3075,10 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *rw_im
+ goto cleanup;
+ }
+ } else if (flags & BPF_TRAMP_F_TAIL_CALL_CTX) {
+- /* Before running the original function, restore the
+- * tail_call_cnt from stack to rax.
++ /* Before running the original function, load the
++ * tail_call_cnt_ptr from stack to rax.
+ */
+- RESTORE_TAIL_CALL_CNT(stack_size);
++ LOAD_TRAMP_TAIL_CALL_CNT_PTR(stack_size);
+ }
+
+ /* restore return value of orig_call or fentry prog back into RAX */
+diff --git a/arch/x86/pci/fixup.c b/arch/x86/pci/fixup.c
+index b33afb240601b0..98a9bb92d75c88 100644
+--- a/arch/x86/pci/fixup.c
++++ b/arch/x86/pci/fixup.c
+@@ -980,7 +980,7 @@ static void amd_rp_pme_suspend(struct pci_dev *dev)
+ return;
+
+ rp = pcie_find_root_port(dev);
+- if (!rp->pm_cap)
++ if (!rp || !rp->pm_cap)
+ return;
+
+ rp->pme_support &= ~((PCI_PM_CAP_PME_D3hot|PCI_PM_CAP_PME_D3cold) >>
+@@ -994,7 +994,7 @@ static void amd_rp_pme_resume(struct pci_dev *dev)
+ u16 pmc;
+
+ rp = pcie_find_root_port(dev);
+- if (!rp->pm_cap)
++ if (!rp || !rp->pm_cap)
+ return;
+
+ pci_read_config_word(rp, rp->pm_cap + PCI_PM_PMC, &pmc);
+diff --git a/arch/x86/xen/mmu_pv.c b/arch/x86/xen/mmu_pv.c
+index 54e0d311dcc94a..9e9a122c2bcfac 100644
+--- a/arch/x86/xen/mmu_pv.c
++++ b/arch/x86/xen/mmu_pv.c
+@@ -2019,10 +2019,7 @@ void __init xen_reserve_special_pages(void)
+
+ void __init xen_pt_check_e820(void)
+ {
+- if (xen_is_e820_reserved(xen_pt_base, xen_pt_size)) {
+- xen_raw_console_write("Xen hypervisor allocated page table memory conflicts with E820 map\n");
+- BUG();
+- }
++ xen_chk_is_e820_usable(xen_pt_base, xen_pt_size, "page table");
+ }
+
+ static unsigned char dummy_mapping[PAGE_SIZE] __page_aligned_bss;
+diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
+index 6bcbdf3b7999fd..d8f175ee9248f6 100644
+--- a/arch/x86/xen/p2m.c
++++ b/arch/x86/xen/p2m.c
+@@ -70,6 +70,7 @@
+ #include <linux/memblock.h>
+ #include <linux/slab.h>
+ #include <linux/vmalloc.h>
++#include <linux/acpi.h>
+
+ #include <asm/cache.h>
+ #include <asm/setup.h>
+@@ -80,6 +81,7 @@
+ #include <asm/xen/hypervisor.h>
+ #include <xen/balloon.h>
+ #include <xen/grant_table.h>
++#include <xen/hvc-console.h>
+
+ #include "multicalls.h"
+ #include "xen-ops.h"
+@@ -793,6 +795,102 @@ int clear_foreign_p2m_mapping(struct gnttab_unmap_grant_ref *unmap_ops,
+ return ret;
+ }
+
++/* Remapped non-RAM areas */
++#define NR_NONRAM_REMAP 4
++static struct nonram_remap {
++ phys_addr_t maddr;
++ phys_addr_t paddr;
++ size_t size;
++} xen_nonram_remap[NR_NONRAM_REMAP] __ro_after_init;
++static unsigned int nr_nonram_remap __ro_after_init;
++
++/*
++ * Do the real remapping of non-RAM regions as specified in the
++ * xen_nonram_remap[] array.
++ * In case of an error just crash the system.
++ */
++void __init xen_do_remap_nonram(void)
++{
++ unsigned int i;
++ unsigned int remapped = 0;
++ const struct nonram_remap *remap = xen_nonram_remap;
++ unsigned long pfn, mfn, end_pfn;
++
++ for (i = 0; i < nr_nonram_remap; i++) {
++ end_pfn = PFN_UP(remap->paddr + remap->size);
++ pfn = PFN_DOWN(remap->paddr);
++ mfn = PFN_DOWN(remap->maddr);
++ while (pfn < end_pfn) {
++ if (!set_phys_to_machine(pfn, mfn))
++ panic("Failed to set p2m mapping for pfn=%lx mfn=%lx\n",
++ pfn, mfn);
++
++ pfn++;
++ mfn++;
++ remapped++;
++ }
++
++ remap++;
++ }
++
++ pr_info("Remapped %u non-RAM page(s)\n", remapped);
++}
++
++#ifdef CONFIG_ACPI
++/*
++ * Xen variant of acpi_os_ioremap() taking potentially remapped non-RAM
++ * regions into account.
++ * Any attempt to map an area crossing a remap boundary will produce a
++ * WARN() splat.
++ * phys is related to remap->maddr on input and will be rebased to remap->paddr.
++ */
++static void __iomem *xen_acpi_os_ioremap(acpi_physical_address phys,
++ acpi_size size)
++{
++ unsigned int i;
++ const struct nonram_remap *remap = xen_nonram_remap;
++
++ for (i = 0; i < nr_nonram_remap; i++) {
++ if (phys + size > remap->maddr &&
++ phys < remap->maddr + remap->size) {
++ WARN_ON(phys < remap->maddr ||
++ phys + size > remap->maddr + remap->size);
++ phys += remap->paddr - remap->maddr;
++ break;
++ }
++ }
++
++ return x86_acpi_os_ioremap(phys, size);
++}
++#endif /* CONFIG_ACPI */
++
++/*
++ * Add a new non-RAM remap entry.
++ * In case of no free entry found, just crash the system.
++ */
++void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr,
++ unsigned long size)
++{
++ BUG_ON((maddr & ~PAGE_MASK) != (paddr & ~PAGE_MASK));
++
++ if (nr_nonram_remap == NR_NONRAM_REMAP) {
++ xen_raw_console_write("Number of required E820 entry remapping actions exceed maximum value\n");
++ BUG();
++ }
++
++#ifdef CONFIG_ACPI
++ /* Switch to the Xen acpi_os_ioremap() variant. */
++ if (nr_nonram_remap == 0)
++ acpi_os_ioremap = xen_acpi_os_ioremap;
++#endif
++
++ xen_nonram_remap[nr_nonram_remap].maddr = maddr;
++ xen_nonram_remap[nr_nonram_remap].paddr = paddr;
++ xen_nonram_remap[nr_nonram_remap].size = size;
++
++ nr_nonram_remap++;
++}
++
+ #ifdef CONFIG_XEN_DEBUG_FS
+ #include <linux/debugfs.h>
+ #include "debugfs.h"
+diff --git a/arch/x86/xen/setup.c b/arch/x86/xen/setup.c
+index 380591028cb8f4..dc822124cacb9c 100644
+--- a/arch/x86/xen/setup.c
++++ b/arch/x86/xen/setup.c
+@@ -15,12 +15,12 @@
+ #include <linux/cpuidle.h>
+ #include <linux/cpufreq.h>
+ #include <linux/memory_hotplug.h>
++#include <linux/acpi.h>
+
+ #include <asm/elf.h>
+ #include <asm/vdso.h>
+ #include <asm/e820/api.h>
+ #include <asm/setup.h>
+-#include <asm/acpi.h>
+ #include <asm/numa.h>
+ #include <asm/idtentry.h>
+ #include <asm/xen/hypervisor.h>
+@@ -47,6 +47,9 @@ bool xen_pv_pci_possible;
+ /* E820 map used during setting up memory. */
+ static struct e820_table xen_e820_table __initdata;
+
++/* Number of initially usable memory pages. */
++static unsigned long ini_nr_pages __initdata;
++
+ /*
+ * Buffer used to remap identity mapped pages. We only need the virtual space.
+ * The physical page behind this address is remapped as needed to different
+@@ -213,7 +216,7 @@ static int __init xen_free_mfn(unsigned long mfn)
+ * as a fallback if the remapping fails.
+ */
+ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
+- unsigned long end_pfn, unsigned long nr_pages)
++ unsigned long end_pfn)
+ {
+ unsigned long pfn, end;
+ int ret;
+@@ -221,7 +224,7 @@ static void __init xen_set_identity_and_release_chunk(unsigned long start_pfn,
+ WARN_ON(start_pfn > end_pfn);
+
+ /* Release pages first. */
+- end = min(end_pfn, nr_pages);
++ end = min(end_pfn, ini_nr_pages);
+ for (pfn = start_pfn; pfn < end; pfn++) {
+ unsigned long mfn = pfn_to_mfn(pfn);
+
+@@ -342,15 +345,14 @@ static void __init xen_do_set_identity_and_remap_chunk(
+ * to Xen and not remapped.
+ */
+ static unsigned long __init xen_set_identity_and_remap_chunk(
+- unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
+- unsigned long remap_pfn)
++ unsigned long start_pfn, unsigned long end_pfn, unsigned long remap_pfn)
+ {
+ unsigned long pfn;
+ unsigned long i = 0;
+ unsigned long n = end_pfn - start_pfn;
+
+ if (remap_pfn == 0)
+- remap_pfn = nr_pages;
++ remap_pfn = ini_nr_pages;
+
+ while (i < n) {
+ unsigned long cur_pfn = start_pfn + i;
+@@ -359,19 +361,19 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
+ unsigned long remap_range_size;
+
+ /* Do not remap pages beyond the current allocation */
+- if (cur_pfn >= nr_pages) {
++ if (cur_pfn >= ini_nr_pages) {
+ /* Identity map remaining pages */
+ set_phys_range_identity(cur_pfn, cur_pfn + size);
+ break;
+ }
+- if (cur_pfn + size > nr_pages)
+- size = nr_pages - cur_pfn;
++ if (cur_pfn + size > ini_nr_pages)
++ size = ini_nr_pages - cur_pfn;
+
+ remap_range_size = xen_find_pfn_range(&remap_pfn);
+ if (!remap_range_size) {
+ pr_warn("Unable to find available pfn range, not remapping identity pages\n");
+ xen_set_identity_and_release_chunk(cur_pfn,
+- cur_pfn + left, nr_pages);
++ cur_pfn + left);
+ break;
+ }
+ /* Adjust size to fit in current e820 RAM region */
+@@ -398,18 +400,18 @@ static unsigned long __init xen_set_identity_and_remap_chunk(
+ }
+
+ static unsigned long __init xen_count_remap_pages(
+- unsigned long start_pfn, unsigned long end_pfn, unsigned long nr_pages,
++ unsigned long start_pfn, unsigned long end_pfn,
+ unsigned long remap_pages)
+ {
+- if (start_pfn >= nr_pages)
++ if (start_pfn >= ini_nr_pages)
+ return remap_pages;
+
+- return remap_pages + min(end_pfn, nr_pages) - start_pfn;
++ return remap_pages + min(end_pfn, ini_nr_pages) - start_pfn;
+ }
+
+-static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
++static unsigned long __init xen_foreach_remap_area(
+ unsigned long (*func)(unsigned long start_pfn, unsigned long end_pfn,
+- unsigned long nr_pages, unsigned long last_val))
++ unsigned long last_val))
+ {
+ phys_addr_t start = 0;
+ unsigned long ret_val = 0;
+@@ -437,8 +439,7 @@ static unsigned long __init xen_foreach_remap_area(unsigned long nr_pages,
+ end_pfn = PFN_UP(entry->addr);
+
+ if (start_pfn < end_pfn)
+- ret_val = func(start_pfn, end_pfn, nr_pages,
+- ret_val);
++ ret_val = func(start_pfn, end_pfn, ret_val);
+ start = end;
+ }
+ }
+@@ -495,6 +496,8 @@ void __init xen_remap_memory(void)
+ set_pte_mfn(buf, mfn_save, PAGE_KERNEL);
+
+ pr_info("Remapped %ld page(s)\n", remapped);
++
++ xen_do_remap_nonram();
+ }
+
+ static unsigned long __init xen_get_pages_limit(void)
+@@ -568,7 +571,7 @@ static void __init xen_ignore_unusable(void)
+ }
+ }
+
+-bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
++static bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size)
+ {
+ struct e820_entry *entry;
+ unsigned mapcnt;
+@@ -625,6 +628,111 @@ phys_addr_t __init xen_find_free_area(phys_addr_t size)
+ return 0;
+ }
+
++/*
++ * Swap a non-RAM E820 map entry with RAM above ini_nr_pages.
++ * Note that the E820 map is modified accordingly, but the P2M map isn't yet.
++ * The adaption of the P2M must be deferred until page allocation is possible.
++ */
++static void __init xen_e820_swap_entry_with_ram(struct e820_entry *swap_entry)
++{
++ struct e820_entry *entry;
++ unsigned int mapcnt;
++ phys_addr_t mem_end = PFN_PHYS(ini_nr_pages);
++ phys_addr_t swap_addr, swap_size, entry_end;
++
++ swap_addr = PAGE_ALIGN_DOWN(swap_entry->addr);
++ swap_size = PAGE_ALIGN(swap_entry->addr - swap_addr + swap_entry->size);
++ entry = xen_e820_table.entries;
++
++ for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) {
++ entry_end = entry->addr + entry->size;
++ if (entry->type == E820_TYPE_RAM && entry->size >= swap_size &&
++ entry_end - swap_size >= mem_end) {
++ /* Reduce RAM entry by needed space (whole pages). */
++ entry->size -= swap_size;
++
++ /* Add new entry at the end of E820 map. */
++ entry = xen_e820_table.entries +
++ xen_e820_table.nr_entries;
++ xen_e820_table.nr_entries++;
++
++ /* Fill new entry (keep size and page offset). */
++ entry->type = swap_entry->type;
++ entry->addr = entry_end - swap_size +
++ swap_addr - swap_entry->addr;
++ entry->size = swap_entry->size;
++
++ /* Convert old entry to RAM, align to pages. */
++ swap_entry->type = E820_TYPE_RAM;
++ swap_entry->addr = swap_addr;
++ swap_entry->size = swap_size;
++
++ /* Remember PFN<->MFN relation for P2M update. */
++ xen_add_remap_nonram(swap_addr, entry_end - swap_size,
++ swap_size);
++
++ /* Order E820 table and merge entries. */
++ e820__update_table(&xen_e820_table);
++
++ return;
++ }
++
++ entry++;
++ }
++
++ xen_raw_console_write("No suitable area found for required E820 entry remapping action\n");
++ BUG();
++}
++
++/*
++ * Look for non-RAM memory types in a specific guest physical area and move
++ * those away if possible (ACPI NVS only for now).
++ */
++static void __init xen_e820_resolve_conflicts(phys_addr_t start,
++ phys_addr_t size)
++{
++ struct e820_entry *entry;
++ unsigned int mapcnt;
++ phys_addr_t end;
++
++ if (!size)
++ return;
++
++ end = start + size;
++ entry = xen_e820_table.entries;
++
++ for (mapcnt = 0; mapcnt < xen_e820_table.nr_entries; mapcnt++) {
++ if (entry->addr >= end)
++ return;
++
++ if (entry->addr + entry->size > start &&
++ entry->type == E820_TYPE_NVS)
++ xen_e820_swap_entry_with_ram(entry);
++
++ entry++;
++ }
++}
++
++/*
++ * Check for an area in physical memory to be usable for non-movable purposes.
++ * An area is considered to usable if the used E820 map lists it to be RAM or
++ * some other type which can be moved to higher PFNs while keeping the MFNs.
++ * In case the area is not usable, crash the system with an error message.
++ */
++void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size,
++ const char *component)
++{
++ xen_e820_resolve_conflicts(start, size);
++
++ if (!xen_is_e820_reserved(start, size))
++ return;
++
++ xen_raw_console_write("Xen hypervisor allocated ");
++ xen_raw_console_write(component);
++ xen_raw_console_write(" memory conflicts with E820 map\n");
++ BUG();
++}
++
+ /*
+ * Like memcpy, but with physical addresses for dest and src.
+ */
+@@ -684,20 +792,20 @@ static void __init xen_reserve_xen_mfnlist(void)
+ **/
+ char * __init xen_memory_setup(void)
+ {
+- unsigned long max_pfn, pfn_s, n_pfns;
++ unsigned long pfn_s, n_pfns;
+ phys_addr_t mem_end, addr, size, chunk_size;
+ u32 type;
+ int rc;
+ struct xen_memory_map memmap;
+ unsigned long max_pages;
+ unsigned long extra_pages = 0;
++ unsigned long maxmem_pages;
+ int i;
+ int op;
+
+ xen_parse_512gb();
+- max_pfn = xen_get_pages_limit();
+- max_pfn = min(max_pfn, xen_start_info->nr_pages);
+- mem_end = PFN_PHYS(max_pfn);
++ ini_nr_pages = min(xen_get_pages_limit(), xen_start_info->nr_pages);
++ mem_end = PFN_PHYS(ini_nr_pages);
+
+ memmap.nr_entries = ARRAY_SIZE(xen_e820_table.entries);
+ set_xen_guest_handle(memmap.buffer, xen_e820_table.entries);
+@@ -747,13 +855,35 @@ char * __init xen_memory_setup(void)
+ /* Make sure the Xen-supplied memory map is well-ordered. */
+ e820__update_table(&xen_e820_table);
+
++ /*
++ * Check whether the kernel itself conflicts with the target E820 map.
++ * Failing now is better than running into weird problems later due
++ * to relocating (and even reusing) pages with kernel text or data.
++ */
++ xen_chk_is_e820_usable(__pa_symbol(_text),
++ __pa_symbol(_end) - __pa_symbol(_text),
++ "kernel");
++
++ /*
++ * Check for a conflict of the xen_start_info memory with the target
++ * E820 map.
++ */
++ xen_chk_is_e820_usable(__pa(xen_start_info), sizeof(*xen_start_info),
++ "xen_start_info");
++
++ /*
++ * Check for a conflict of the hypervisor supplied page tables with
++ * the target E820 map.
++ */
++ xen_pt_check_e820();
++
+ max_pages = xen_get_max_pages();
+
+ /* How many extra pages do we need due to remapping? */
+- max_pages += xen_foreach_remap_area(max_pfn, xen_count_remap_pages);
++ max_pages += xen_foreach_remap_area(xen_count_remap_pages);
+
+- if (max_pages > max_pfn)
+- extra_pages += max_pages - max_pfn;
++ if (max_pages > ini_nr_pages)
++ extra_pages += max_pages - ini_nr_pages;
+
+ /*
+ * Clamp the amount of extra memory to a EXTRA_MEM_RATIO
+@@ -762,8 +892,8 @@ char * __init xen_memory_setup(void)
+ * Make sure we have no memory above max_pages, as this area
+ * isn't handled by the p2m management.
+ */
+- extra_pages = min3(EXTRA_MEM_RATIO * min(max_pfn, PFN_DOWN(MAXMEM)),
+- extra_pages, max_pages - max_pfn);
++ maxmem_pages = EXTRA_MEM_RATIO * min(ini_nr_pages, PFN_DOWN(MAXMEM));
++ extra_pages = min3(maxmem_pages, extra_pages, max_pages - ini_nr_pages);
+ i = 0;
+ addr = xen_e820_table.entries[0].addr;
+ size = xen_e820_table.entries[0].size;
+@@ -819,23 +949,6 @@ char * __init xen_memory_setup(void)
+
+ e820__update_table(e820_table);
+
+- /*
+- * Check whether the kernel itself conflicts with the target E820 map.
+- * Failing now is better than running into weird problems later due
+- * to relocating (and even reusing) pages with kernel text or data.
+- */
+- if (xen_is_e820_reserved(__pa_symbol(_text),
+- __pa_symbol(__bss_stop) - __pa_symbol(_text))) {
+- xen_raw_console_write("Xen hypervisor allocated kernel memory conflicts with E820 map\n");
+- BUG();
+- }
+-
+- /*
+- * Check for a conflict of the hypervisor supplied page tables with
+- * the target E820 map.
+- */
+- xen_pt_check_e820();
+-
+ xen_reserve_xen_mfnlist();
+
+ /* Check for a conflict of the initrd with the target E820 map. */
+@@ -863,7 +976,7 @@ char * __init xen_memory_setup(void)
+ * Set identity map on non-RAM pages and prepare remapping the
+ * underlying RAM.
+ */
+- xen_foreach_remap_area(max_pfn, xen_set_identity_and_remap_chunk);
++ xen_foreach_remap_area(xen_set_identity_and_remap_chunk);
+
+ pr_info("Released %ld page(s)\n", xen_released_pages);
+
+diff --git a/arch/x86/xen/xen-ops.h b/arch/x86/xen/xen-ops.h
+index 79cf93f2c92f1d..a6a21dd0552700 100644
+--- a/arch/x86/xen/xen-ops.h
++++ b/arch/x86/xen/xen-ops.h
+@@ -43,8 +43,12 @@ void xen_mm_unpin_all(void);
+ #ifdef CONFIG_X86_64
+ void __init xen_relocate_p2m(void);
+ #endif
++void __init xen_do_remap_nonram(void);
++void __init xen_add_remap_nonram(phys_addr_t maddr, phys_addr_t paddr,
++ unsigned long size);
+
+-bool __init xen_is_e820_reserved(phys_addr_t start, phys_addr_t size);
++void __init xen_chk_is_e820_usable(phys_addr_t start, phys_addr_t size,
++ const char *component);
+ unsigned long __ref xen_chk_extra_mem(unsigned long pfn);
+ void __init xen_inv_extra_mem(void);
+ void __init xen_remap_memory(void);
+diff --git a/block/bfq-iosched.c b/block/bfq-iosched.c
+index 4b88a54a9b76cb..05372a78cd5161 100644
+--- a/block/bfq-iosched.c
++++ b/block/bfq-iosched.c
+@@ -2911,8 +2911,12 @@ bfq_setup_cooperator(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ struct bfq_iocq_bfqq_data *bfqq_data = &bic->bfqq_data[a_idx];
+
+ /* if a merge has already been setup, then proceed with that first */
+- if (bfqq->new_bfqq)
+- return bfqq->new_bfqq;
++ new_bfqq = bfqq->new_bfqq;
++ if (new_bfqq) {
++ while (new_bfqq->new_bfqq)
++ new_bfqq = new_bfqq->new_bfqq;
++ return new_bfqq;
++ }
+
+ /*
+ * Check delayed stable merge for rotational or non-queueing
+@@ -3125,10 +3129,12 @@ void bfq_release_process_ref(struct bfq_data *bfqd, struct bfq_queue *bfqq)
+ bfq_put_queue(bfqq);
+ }
+
+-static void
+-bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+- struct bfq_queue *bfqq, struct bfq_queue *new_bfqq)
++static struct bfq_queue *bfq_merge_bfqqs(struct bfq_data *bfqd,
++ struct bfq_io_cq *bic,
++ struct bfq_queue *bfqq)
+ {
++ struct bfq_queue *new_bfqq = bfqq->new_bfqq;
++
+ bfq_log_bfqq(bfqd, bfqq, "merging with queue %lu",
+ (unsigned long)new_bfqq->pid);
+ /* Save weight raising and idle window of the merged queues */
+@@ -3222,6 +3228,8 @@ bfq_merge_bfqqs(struct bfq_data *bfqd, struct bfq_io_cq *bic,
+ bfq_reassign_last_bfqq(bfqq, new_bfqq);
+
+ bfq_release_process_ref(bfqd, bfqq);
++
++ return new_bfqq;
+ }
+
+ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+@@ -3257,14 +3265,8 @@ static bool bfq_allow_bio_merge(struct request_queue *q, struct request *rq,
+ * fulfilled, i.e., bic can be redirected to new_bfqq
+ * and bfqq can be put.
+ */
+- bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq,
+- new_bfqq);
+- /*
+- * If we get here, bio will be queued into new_queue,
+- * so use new_bfqq to decide whether bio and rq can be
+- * merged.
+- */
+- bfqq = new_bfqq;
++ while (bfqq != new_bfqq)
++ bfqq = bfq_merge_bfqqs(bfqd, bfqd->bio_bic, bfqq);
+
+ /*
+ * Change also bqfd->bio_bfqq, as
+@@ -5699,9 +5701,7 @@ bfq_do_early_stable_merge(struct bfq_data *bfqd, struct bfq_queue *bfqq,
+ * state before killing it.
+ */
+ bfqq->bic = bic;
+- bfq_merge_bfqqs(bfqd, bic, bfqq, new_bfqq);
+-
+- return new_bfqq;
++ return bfq_merge_bfqqs(bfqd, bic, bfqq);
+ }
+
+ /*
+@@ -6156,6 +6156,7 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+ bool waiting, idle_timer_disabled = false;
+
+ if (new_bfqq) {
++ struct bfq_queue *old_bfqq = bfqq;
+ /*
+ * Release the request's reference to the old bfqq
+ * and make sure one is taken to the shared queue.
+@@ -6172,18 +6173,18 @@ static bool __bfq_insert_request(struct bfq_data *bfqd, struct request *rq)
+ * new_bfqq.
+ */
+ if (bic_to_bfqq(RQ_BIC(rq), true,
+- bfq_actuator_index(bfqd, rq->bio)) == bfqq)
+- bfq_merge_bfqqs(bfqd, RQ_BIC(rq),
+- bfqq, new_bfqq);
++ bfq_actuator_index(bfqd, rq->bio)) == bfqq) {
++ while (bfqq != new_bfqq)
++ bfqq = bfq_merge_bfqqs(bfqd, RQ_BIC(rq), bfqq);
++ }
+
+- bfq_clear_bfqq_just_created(bfqq);
++ bfq_clear_bfqq_just_created(old_bfqq);
+ /*
+ * rq is about to be enqueued into new_bfqq,
+ * release rq reference on bfqq
+ */
+- bfq_put_queue(bfqq);
++ bfq_put_queue(old_bfqq);
+ rq->elv.priv[1] = new_bfqq;
+- bfqq = new_bfqq;
+ }
+
+ bfq_update_io_thinktime(bfqd, bfqq);
+@@ -6721,7 +6722,7 @@ bfq_split_bfqq(struct bfq_io_cq *bic, struct bfq_queue *bfqq)
+ {
+ bfq_log_bfqq(bfqq->bfqd, bfqq, "splitting queue");
+
+- if (bfqq_process_refs(bfqq) == 1) {
++ if (bfqq_process_refs(bfqq) == 1 && !bfqq->new_bfqq) {
+ bfqq->pid = current->pid;
+ bfq_clear_bfqq_coop(bfqq);
+ bfq_clear_bfqq_split_coop(bfqq);
+@@ -6819,6 +6820,31 @@ static void bfq_prepare_request(struct request *rq)
+ rq->elv.priv[0] = rq->elv.priv[1] = NULL;
+ }
+
++static struct bfq_queue *bfq_waker_bfqq(struct bfq_queue *bfqq)
++{
++ struct bfq_queue *new_bfqq = bfqq->new_bfqq;
++ struct bfq_queue *waker_bfqq = bfqq->waker_bfqq;
++
++ if (!waker_bfqq)
++ return NULL;
++
++ while (new_bfqq) {
++ if (new_bfqq == waker_bfqq) {
++ /*
++ * If waker_bfqq is in the merge chain, and current
++ * is the only procress.
++ */
++ if (bfqq_process_refs(waker_bfqq) == 1)
++ return NULL;
++ break;
++ }
++
++ new_bfqq = new_bfqq->new_bfqq;
++ }
++
++ return waker_bfqq;
++}
++
+ /*
+ * If needed, init rq, allocate bfq data structures associated with
+ * rq, and increment reference counters in the destination bfq_queue
+@@ -6880,7 +6906,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
+ /* If the queue was seeky for too long, break it apart. */
+ if (bfq_bfqq_coop(bfqq) && bfq_bfqq_split_coop(bfqq) &&
+ !bic->bfqq_data[a_idx].stably_merged) {
+- struct bfq_queue *old_bfqq = bfqq;
++ struct bfq_queue *waker_bfqq = bfq_waker_bfqq(bfqq);
+
+ /* Update bic before losing reference to bfqq */
+ if (bfq_bfqq_in_large_burst(bfqq))
+@@ -6900,7 +6926,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
+ bfqq_already_existing = true;
+
+ if (!bfqq_already_existing) {
+- bfqq->waker_bfqq = old_bfqq->waker_bfqq;
++ bfqq->waker_bfqq = waker_bfqq;
+ bfqq->tentative_waker_bfqq = NULL;
+
+ /*
+@@ -6910,7 +6936,7 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
+ * woken_list of the waker. See
+ * bfq_check_waker for details.
+ */
+- if (bfqq->waker_bfqq)
++ if (waker_bfqq)
+ hlist_add_head(&bfqq->woken_list_node,
+ &bfqq->waker_bfqq->woken_list);
+ }
+@@ -6932,7 +6958,8 @@ static struct bfq_queue *bfq_init_rq(struct request *rq)
+ * addition, if the queue has also just been split, we have to
+ * resume its state.
+ */
+- if (likely(bfqq != &bfqd->oom_bfqq) && bfqq_process_refs(bfqq) == 1) {
++ if (likely(bfqq != &bfqd->oom_bfqq) && !bfqq->new_bfqq &&
++ bfqq_process_refs(bfqq) == 1) {
+ bfqq->bic = bic;
+ if (split) {
+ /*
+diff --git a/block/partitions/core.c b/block/partitions/core.c
+index ab76e64f0f6c3b..5bd7a603092ea9 100644
+--- a/block/partitions/core.c
++++ b/block/partitions/core.c
+@@ -555,9 +555,11 @@ static bool blk_add_partition(struct gendisk *disk,
+
+ part = add_partition(disk, p, from, size, state->parts[p].flags,
+ &state->parts[p].info);
+- if (IS_ERR(part) && PTR_ERR(part) != -ENXIO) {
+- printk(KERN_ERR " %s: p%d could not be added: %pe\n",
+- disk->disk_name, p, part);
++ if (IS_ERR(part)) {
++ if (PTR_ERR(part) != -ENXIO) {
++ printk(KERN_ERR " %s: p%d could not be added: %pe\n",
++ disk->disk_name, p, part);
++ }
+ return true;
+ }
+
+diff --git a/crypto/asymmetric_keys/asymmetric_type.c b/crypto/asymmetric_keys/asymmetric_type.c
+index a5da8ccd353ef7..43af5fa510c09f 100644
+--- a/crypto/asymmetric_keys/asymmetric_type.c
++++ b/crypto/asymmetric_keys/asymmetric_type.c
+@@ -60,17 +60,18 @@ struct key *find_asymmetric_key(struct key *keyring,
+ char *req, *p;
+ int len;
+
+- WARN_ON(!id_0 && !id_1 && !id_2);
+-
+ if (id_0) {
+ lookup = id_0->data;
+ len = id_0->len;
+ } else if (id_1) {
+ lookup = id_1->data;
+ len = id_1->len;
+- } else {
++ } else if (id_2) {
+ lookup = id_2->data;
+ len = id_2->len;
++ } else {
++ WARN_ON(1);
++ return ERR_PTR(-EINVAL);
+ }
+
+ /* Construct an identifier "id:<keyid>". */
+diff --git a/crypto/xor.c b/crypto/xor.c
+index 8e72e5d5db0ded..56aa3169e87171 100644
+--- a/crypto/xor.c
++++ b/crypto/xor.c
+@@ -83,33 +83,30 @@ static void __init
+ do_xor_speed(struct xor_block_template *tmpl, void *b1, void *b2)
+ {
+ int speed;
+- int i, j;
+- ktime_t min, start, diff;
++ unsigned long reps;
++ ktime_t min, start, t0;
+
+ tmpl->next = template_list;
+ template_list = tmpl;
+
+ preempt_disable();
+
+- min = (ktime_t)S64_MAX;
+- for (i = 0; i < 3; i++) {
+- start = ktime_get();
+- for (j = 0; j < REPS; j++) {
+- mb(); /* prevent loop optimization */
+- tmpl->do_2(BENCH_SIZE, b1, b2);
+- mb();
+- }
+- diff = ktime_sub(ktime_get(), start);
+- if (diff < min)
+- min = diff;
+- }
++ reps = 0;
++ t0 = ktime_get();
++ /* delay start until time has advanced */
++ while ((start = ktime_get()) == t0)
++ cpu_relax();
++ do {
++ mb(); /* prevent loop optimization */
++ tmpl->do_2(BENCH_SIZE, b1, b2);
++ mb();
++ } while (reps++ < REPS || (t0 = ktime_get()) == start);
++ min = ktime_sub(t0, start);
+
+ preempt_enable();
+
+ // bytes/ns == GB/s, multiply by 1000 to get MB/s [not MiB/s]
+- if (!min)
+- min = 1;
+- speed = (1000 * REPS * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
++ speed = (1000 * reps * BENCH_SIZE) / (unsigned int)ktime_to_ns(min);
+ tmpl->speed = speed;
+
+ pr_info(" %-16s: %5d MB/sec\n", tmpl->name, speed);
+diff --git a/drivers/acpi/acpica/exsystem.c b/drivers/acpi/acpica/exsystem.c
+index f665ffd9a396cf..2c384bd52b9c4b 100644
+--- a/drivers/acpi/acpica/exsystem.c
++++ b/drivers/acpi/acpica/exsystem.c
+@@ -133,14 +133,15 @@ acpi_status acpi_ex_system_do_stall(u32 how_long_us)
+ * (ACPI specifies 100 usec as max, but this gives some slack in
+ * order to support existing BIOSs)
+ */
+- ACPI_ERROR((AE_INFO,
+- "Time parameter is too large (%u)", how_long_us));
++ ACPI_ERROR_ONCE((AE_INFO,
++ "Time parameter is too large (%u)",
++ how_long_us));
+ status = AE_AML_OPERAND_VALUE;
+ } else {
+ if (how_long_us > 100) {
+- ACPI_WARNING((AE_INFO,
+- "Time parameter %u us > 100 us violating ACPI spec, please fix the firmware.",
+- how_long_us));
++ ACPI_WARNING_ONCE((AE_INFO,
++ "Time parameter %u us > 100 us violating ACPI spec, please fix the firmware.",
++ how_long_us));
+ }
+ acpi_os_stall(how_long_us);
+ }
+diff --git a/drivers/acpi/cppc_acpi.c b/drivers/acpi/cppc_acpi.c
+index 1d857978f5f407..2a588e4ed4af44 100644
+--- a/drivers/acpi/cppc_acpi.c
++++ b/drivers/acpi/cppc_acpi.c
+@@ -170,8 +170,11 @@ show_cppc_data(cppc_get_perf_ctrs, cppc_perf_fb_ctrs, wraparound_time);
+ #define GET_BIT_WIDTH(reg) ((reg)->access_width ? (8 << ((reg)->access_width - 1)) : (reg)->bit_width)
+
+ /* Shift and apply the mask for CPC reads/writes */
+-#define MASK_VAL(reg, val) (((val) >> (reg)->bit_offset) & \
++#define MASK_VAL_READ(reg, val) (((val) >> (reg)->bit_offset) & \
+ GENMASK(((reg)->bit_width) - 1, 0))
++#define MASK_VAL_WRITE(reg, prev_val, val) \
++ ((((val) & GENMASK(((reg)->bit_width) - 1, 0)) << (reg)->bit_offset) | \
++ ((prev_val) & ~(GENMASK(((reg)->bit_width) - 1, 0) << (reg)->bit_offset))) \
+
+ static ssize_t show_feedback_ctrs(struct kobject *kobj,
+ struct kobj_attribute *attr, char *buf)
+@@ -857,6 +860,7 @@ int acpi_cppc_processor_probe(struct acpi_processor *pr)
+
+ /* Store CPU Logical ID */
+ cpc_ptr->cpu_id = pr->id;
++ spin_lock_init(&cpc_ptr->rmw_lock);
+
+ /* Parse PSD data for this CPU */
+ ret = acpi_get_psd(cpc_ptr, handle);
+@@ -1062,7 +1066,7 @@ static int cpc_read(int cpu, struct cpc_register_resource *reg_res, u64 *val)
+ }
+
+ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+- *val = MASK_VAL(reg, *val);
++ *val = MASK_VAL_READ(reg, *val);
+
+ return 0;
+ }
+@@ -1071,9 +1075,11 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
+ {
+ int ret_val = 0;
+ int size;
++ u64 prev_val;
+ void __iomem *vaddr = NULL;
+ int pcc_ss_id = per_cpu(cpu_pcc_subspace_idx, cpu);
+ struct cpc_reg *reg = ®_res->cpc_entry.reg;
++ struct cpc_desc *cpc_desc;
+
+ size = GET_BIT_WIDTH(reg);
+
+@@ -1106,8 +1112,34 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
+ return acpi_os_write_memory((acpi_physical_address)reg->address,
+ val, size);
+
+- if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
+- val = MASK_VAL(reg, val);
++ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY) {
++ cpc_desc = per_cpu(cpc_desc_ptr, cpu);
++ if (!cpc_desc) {
++ pr_debug("No CPC descriptor for CPU:%d\n", cpu);
++ return -ENODEV;
++ }
++
++ spin_lock(&cpc_desc->rmw_lock);
++ switch (size) {
++ case 8:
++ prev_val = readb_relaxed(vaddr);
++ break;
++ case 16:
++ prev_val = readw_relaxed(vaddr);
++ break;
++ case 32:
++ prev_val = readl_relaxed(vaddr);
++ break;
++ case 64:
++ prev_val = readq_relaxed(vaddr);
++ break;
++ default:
++ spin_unlock(&cpc_desc->rmw_lock);
++ return -EFAULT;
++ }
++ val = MASK_VAL_WRITE(reg, prev_val, val);
++ val |= prev_val;
++ }
+
+ switch (size) {
+ case 8:
+@@ -1134,6 +1166,9 @@ static int cpc_write(int cpu, struct cpc_register_resource *reg_res, u64 val)
+ break;
+ }
+
++ if (reg->space_id == ACPI_ADR_SPACE_SYSTEM_MEMORY)
++ spin_unlock(&cpc_desc->rmw_lock);
++
+ return ret_val;
+ }
+
+diff --git a/drivers/acpi/device_sysfs.c b/drivers/acpi/device_sysfs.c
+index 23373faa35ecd6..95a19e3569c83f 100644
+--- a/drivers/acpi/device_sysfs.c
++++ b/drivers/acpi/device_sysfs.c
+@@ -540,8 +540,9 @@ int acpi_device_setup_files(struct acpi_device *dev)
+ * If device has _STR, 'description' file is created
+ */
+ if (acpi_has_method(dev->handle, "_STR")) {
+- status = acpi_evaluate_object(dev->handle, "_STR",
+- NULL, &buffer);
++ status = acpi_evaluate_object_typed(dev->handle, "_STR",
++ NULL, &buffer,
++ ACPI_TYPE_BUFFER);
+ if (ACPI_FAILURE(status))
+ buffer.pointer = NULL;
+ dev->pnp.str_obj = buffer.pointer;
+diff --git a/drivers/acpi/pmic/tps68470_pmic.c b/drivers/acpi/pmic/tps68470_pmic.c
+index ebd03e4729555a..0d1a82eeb4b0b6 100644
+--- a/drivers/acpi/pmic/tps68470_pmic.c
++++ b/drivers/acpi/pmic/tps68470_pmic.c
+@@ -376,10 +376,8 @@ static int tps68470_pmic_opregion_probe(struct platform_device *pdev)
+ struct tps68470_pmic_opregion *opregion;
+ acpi_status status;
+
+- if (!dev || !tps68470_regmap) {
+- dev_warn(dev, "dev or regmap is NULL\n");
+- return -EINVAL;
+- }
++ if (!tps68470_regmap)
++ return dev_err_probe(dev, -EINVAL, "regmap is missing\n");
+
+ if (!handle) {
+ dev_warn(dev, "acpi handle is NULL\n");
+diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
+index df5d5a554b388b..cb2aacbb93357e 100644
+--- a/drivers/acpi/resource.c
++++ b/drivers/acpi/resource.c
+@@ -554,6 +554,12 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
+ * to have a working keyboard.
+ */
+ static const struct dmi_system_id irq1_edge_low_force_override[] = {
++ {
++ /* MECHREV Jiaolong17KS Series GM7XG0M */
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "GM7XG0M"),
++ },
++ },
+ {
+ /* XMG APEX 17 (M23) */
+ .matches = {
+@@ -572,6 +578,12 @@ static const struct dmi_system_id irq1_edge_low_force_override[] = {
+ DMI_MATCH(DMI_BOARD_NAME, "GMxXGxx"),
+ },
+ },
++ {
++ /* TongFang GMxXGxX/TUXEDO Polaris 15 Gen5 AMD */
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "GMxXGxX"),
++ },
++ },
+ {
+ /* TongFang GMxXGxx sold as Eluktronics Inc. RP-15 */
+ .matches = {
+diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
+index ff6f260433a113..75a5f559402f87 100644
+--- a/drivers/acpi/video_detect.c
++++ b/drivers/acpi/video_detect.c
+@@ -541,6 +541,22 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "iMac12,2"),
+ },
+ },
++ {
++ .callback = video_detect_force_native,
++ /* Apple MacBook Air 9,1 */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
++ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookAir9,1"),
++ },
++ },
++ {
++ .callback = video_detect_force_native,
++ /* Apple MacBook Pro 9,2 */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
++ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro9,2"),
++ },
++ },
+ {
+ /* https://bugzilla.redhat.com/show_bug.cgi?id=1217249 */
+ .callback = video_detect_force_native,
+@@ -550,6 +566,14 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro12,1"),
+ },
+ },
++ {
++ .callback = video_detect_force_native,
++ /* Apple MacBook Pro 16,2 */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "Apple Inc."),
++ DMI_MATCH(DMI_PRODUCT_NAME, "MacBookPro16,2"),
++ },
++ },
+ {
+ .callback = video_detect_force_native,
+ /* Dell Inspiron N4010 */
+diff --git a/drivers/ata/libata-eh.c b/drivers/ata/libata-eh.c
+index 214b935c2ced79..7df9ec9f924c44 100644
+--- a/drivers/ata/libata-eh.c
++++ b/drivers/ata/libata-eh.c
+@@ -630,6 +630,14 @@ void ata_scsi_cmd_error_handler(struct Scsi_Host *host, struct ata_port *ap,
+ list_for_each_entry_safe(scmd, tmp, eh_work_q, eh_entry) {
+ struct ata_queued_cmd *qc;
+
++ /*
++ * If the scmd was added to EH, via ata_qc_schedule_eh() ->
++ * scsi_timeout() -> scsi_eh_scmd_add(), scsi_timeout() will
++ * have set DID_TIME_OUT (since libata does not have an abort
++ * handler). Thus, to clear DID_TIME_OUT, clear the host byte.
++ */
++ set_host_byte(scmd, DID_OK);
++
+ ata_qc_for_each_raw(ap, qc, i) {
+ if (qc->flags & ATA_QCFLAG_ACTIVE &&
+ qc->scsicmd == scmd)
+diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
+index 4116ae08871910..0cbe331124c255 100644
+--- a/drivers/ata/libata-scsi.c
++++ b/drivers/ata/libata-scsi.c
+@@ -1693,9 +1693,6 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
+ set_status_byte(qc->scsicmd, SAM_STAT_CHECK_CONDITION);
+ } else if (is_error && !have_sense) {
+ ata_gen_ata_sense(qc);
+- } else {
+- /* Keep the SCSI ML and status byte, clear host byte. */
+- cmd->result &= 0x0000ffff;
+ }
+
+ ata_qc_done(qc);
+@@ -2361,7 +2358,7 @@ static unsigned int ata_msense_control(struct ata_device *dev, u8 *buf,
+ case ALL_SUB_MPAGES:
+ n = ata_msense_control_spg0(dev, buf, changeable);
+ n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE);
+- n += ata_msense_control_spgt2(dev, buf + n, CDL_T2A_SUB_MPAGE);
++ n += ata_msense_control_spgt2(dev, buf + n, CDL_T2B_SUB_MPAGE);
+ n += ata_msense_control_ata_feature(dev, buf + n);
+ return n;
+ default:
+diff --git a/drivers/base/core.c b/drivers/base/core.c
+index b5399262198a68..6c1a944c00d9b3 100644
+--- a/drivers/base/core.c
++++ b/drivers/base/core.c
+@@ -4515,9 +4515,11 @@ EXPORT_SYMBOL_GPL(device_destroy);
+ */
+ int device_rename(struct device *dev, const char *new_name)
+ {
++ struct subsys_private *sp = NULL;
+ struct kobject *kobj = &dev->kobj;
+ char *old_device_name = NULL;
+ int error;
++ bool is_link_renamed = false;
+
+ dev = get_device(dev);
+ if (!dev)
+@@ -4532,7 +4534,7 @@ int device_rename(struct device *dev, const char *new_name)
+ }
+
+ if (dev->class) {
+- struct subsys_private *sp = class_to_subsys(dev->class);
++ sp = class_to_subsys(dev->class);
+
+ if (!sp) {
+ error = -EINVAL;
+@@ -4541,16 +4543,19 @@ int device_rename(struct device *dev, const char *new_name)
+
+ error = sysfs_rename_link_ns(&sp->subsys.kobj, kobj, old_device_name,
+ new_name, kobject_namespace(kobj));
+- subsys_put(sp);
+ if (error)
+ goto out;
++
++ is_link_renamed = true;
+ }
+
+ error = kobject_rename(kobj, new_name);
+- if (error)
+- goto out;
+-
+ out:
++ if (error && is_link_renamed)
++ sysfs_rename_link_ns(&sp->subsys.kobj, kobj, new_name,
++ old_device_name, kobject_namespace(kobj));
++ subsys_put(sp);
++
+ put_device(dev);
+
+ kfree(old_device_name);
+diff --git a/drivers/base/firmware_loader/main.c b/drivers/base/firmware_loader/main.c
+index da8ca01d011c3f..0989a62962d33c 100644
+--- a/drivers/base/firmware_loader/main.c
++++ b/drivers/base/firmware_loader/main.c
+@@ -849,6 +849,26 @@ static void fw_log_firmware_info(const struct firmware *fw, const char *name,
+ {}
+ #endif
+
++/*
++ * Reject firmware file names with ".." path components.
++ * There are drivers that construct firmware file names from device-supplied
++ * strings, and we don't want some device to be able to tell us "I would like to
++ * be sent my firmware from ../../../etc/shadow, please".
++ *
++ * Search for ".." surrounded by either '/' or start/end of string.
++ *
++ * This intentionally only looks at the firmware name, not at the firmware base
++ * directory or at symlink contents.
++ */
++static bool name_contains_dotdot(const char *name)
++{
++ size_t name_len = strlen(name);
++
++ return strcmp(name, "..") == 0 || strncmp(name, "../", 3) == 0 ||
++ strstr(name, "/../") != NULL ||
++ (name_len >= 3 && strcmp(name+name_len-3, "/..") == 0);
++}
++
+ /* called from request_firmware() and request_firmware_work_func() */
+ static int
+ _request_firmware(const struct firmware **firmware_p, const char *name,
+@@ -869,6 +889,14 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
+ goto out;
+ }
+
++ if (name_contains_dotdot(name)) {
++ dev_warn(device,
++ "Firmware load for '%s' refused, path contains '..' component\n",
++ name);
++ ret = -EINVAL;
++ goto out;
++ }
++
+ ret = _request_firmware_prepare(&fw, name, device, buf, size,
+ offset, opt_flags);
+ if (ret <= 0) /* error or already assigned */
+@@ -946,6 +974,8 @@ _request_firmware(const struct firmware **firmware_p, const char *name,
+ * @name will be used as $FIRMWARE in the uevent environment and
+ * should be distinctive enough not to be confused with any other
+ * firmware image for this or any other device.
++ * It must not contain any ".." path components - "foo/bar..bin" is
++ * allowed, but "foo/../bar.bin" is not.
+ *
+ * Caller must hold the reference count of @device.
+ *
+diff --git a/drivers/base/module.c b/drivers/base/module.c
+index b0b79b9c189d4f..0d5c5da367f720 100644
+--- a/drivers/base/module.c
++++ b/drivers/base/module.c
+@@ -66,27 +66,31 @@ int module_add_driver(struct module *mod, struct device_driver *drv)
+ driver_name = make_driver_name(drv);
+ if (!driver_name) {
+ ret = -ENOMEM;
+- goto out;
++ goto out_remove_kobj;
+ }
+
+ module_create_drivers_dir(mk);
+ if (!mk->drivers_dir) {
+ ret = -EINVAL;
+- goto out;
++ goto out_free_driver_name;
+ }
+
+ ret = sysfs_create_link(mk->drivers_dir, &drv->p->kobj, driver_name);
+ if (ret)
+- goto out;
++ goto out_remove_drivers_dir;
+
+ kfree(driver_name);
+
+ return 0;
+-out:
+- sysfs_remove_link(&drv->p->kobj, "module");
++
++out_remove_drivers_dir:
+ sysfs_remove_link(mk->drivers_dir, driver_name);
++
++out_free_driver_name:
+ kfree(driver_name);
+
++out_remove_kobj:
++ sysfs_remove_link(&drv->p->kobj, "module");
+ return ret;
+ }
+
+diff --git a/drivers/block/drbd/drbd_main.c b/drivers/block/drbd/drbd_main.c
+index 113b441d4d3670..301843297fb788 100644
+--- a/drivers/block/drbd/drbd_main.c
++++ b/drivers/block/drbd/drbd_main.c
+@@ -3399,10 +3399,12 @@ void drbd_uuid_new_current(struct drbd_device *device) __must_hold(local)
+ void drbd_uuid_set_bm(struct drbd_device *device, u64 val) __must_hold(local)
+ {
+ unsigned long flags;
+- if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0)
++ spin_lock_irqsave(&device->ldev->md.uuid_lock, flags);
++ if (device->ldev->md.uuid[UI_BITMAP] == 0 && val == 0) {
++ spin_unlock_irqrestore(&device->ldev->md.uuid_lock, flags);
+ return;
++ }
+
+- spin_lock_irqsave(&device->ldev->md.uuid_lock, flags);
+ if (val == 0) {
+ drbd_uuid_move_history(device);
+ device->ldev->md.uuid[UI_HISTORY_START] = device->ldev->md.uuid[UI_BITMAP];
+diff --git a/drivers/block/drbd/drbd_state.c b/drivers/block/drbd/drbd_state.c
+index e858e7e0383f26..c2b6c4d9729db9 100644
+--- a/drivers/block/drbd/drbd_state.c
++++ b/drivers/block/drbd/drbd_state.c
+@@ -876,7 +876,7 @@ is_valid_state(struct drbd_device *device, union drbd_state ns)
+ ns.disk == D_OUTDATED)
+ rv = SS_CONNECTED_OUTDATES;
+
+- else if ((ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
++ else if (nc && (ns.conn == C_VERIFY_S || ns.conn == C_VERIFY_T) &&
+ (nc->verify_alg[0] == 0))
+ rv = SS_NO_VERIFY_ALG;
+
+diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
+index b87aa80a46ddaa..d4e260d3218063 100644
+--- a/drivers/block/nbd.c
++++ b/drivers/block/nbd.c
+@@ -181,6 +181,17 @@ static void nbd_requeue_cmd(struct nbd_cmd *cmd)
+ {
+ struct request *req = blk_mq_rq_from_pdu(cmd);
+
++ lockdep_assert_held(&cmd->lock);
++
++ /*
++ * Clear INFLIGHT flag so that this cmd won't be completed in
++ * normal completion path
++ *
++ * INFLIGHT flag will be set when the cmd is queued to nbd next
++ * time.
++ */
++ __clear_bit(NBD_CMD_INFLIGHT, &cmd->flags);
++
+ if (!test_and_set_bit(NBD_CMD_REQUEUED, &cmd->flags))
+ blk_mq_requeue_request(req, true);
+ }
+@@ -339,7 +350,7 @@ static int __nbd_set_size(struct nbd_device *nbd, loff_t bytesize,
+
+ lim = queue_limits_start_update(nbd->disk->queue);
+ if (nbd->config->flags & NBD_FLAG_SEND_TRIM)
+- lim.max_hw_discard_sectors = UINT_MAX;
++ lim.max_hw_discard_sectors = UINT_MAX >> SECTOR_SHIFT;
+ else
+ lim.max_hw_discard_sectors = 0;
+ lim.logical_block_size = blksize;
+@@ -480,8 +491,8 @@ static enum blk_eh_timer_return nbd_xmit_timeout(struct request *req)
+ nbd_mark_nsock_dead(nbd, nsock, 1);
+ mutex_unlock(&nsock->tx_lock);
+ }
+- mutex_unlock(&cmd->lock);
+ nbd_requeue_cmd(cmd);
++ mutex_unlock(&cmd->lock);
+ nbd_config_put(nbd);
+ return BLK_EH_DONE;
+ }
+diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
+index fc001e9f95f61a..d06c8ed29620b9 100644
+--- a/drivers/block/ublk_drv.c
++++ b/drivers/block/ublk_drv.c
+@@ -71,9 +71,6 @@ struct ublk_rq_data {
+ struct llist_node node;
+
+ struct kref ref;
+- __u64 sector;
+- __u32 operation;
+- __u32 nr_zones;
+ };
+
+ struct ublk_uring_cmd_pdu {
+@@ -214,6 +211,33 @@ static inline bool ublk_queue_is_zoned(struct ublk_queue *ubq)
+
+ #ifdef CONFIG_BLK_DEV_ZONED
+
++struct ublk_zoned_report_desc {
++ __u64 sector;
++ __u32 operation;
++ __u32 nr_zones;
++};
++
++static DEFINE_XARRAY(ublk_zoned_report_descs);
++
++static int ublk_zoned_insert_report_desc(const struct request *req,
++ struct ublk_zoned_report_desc *desc)
++{
++ return xa_insert(&ublk_zoned_report_descs, (unsigned long)req,
++ desc, GFP_KERNEL);
++}
++
++static struct ublk_zoned_report_desc *ublk_zoned_erase_report_desc(
++ const struct request *req)
++{
++ return xa_erase(&ublk_zoned_report_descs, (unsigned long)req);
++}
++
++static struct ublk_zoned_report_desc *ublk_zoned_get_report_desc(
++ const struct request *req)
++{
++ return xa_load(&ublk_zoned_report_descs, (unsigned long)req);
++}
++
+ static int ublk_get_nr_zones(const struct ublk_device *ub)
+ {
+ const struct ublk_param_basic *p = &ub->params.basic;
+@@ -310,7 +334,7 @@ static int ublk_report_zones(struct gendisk *disk, sector_t sector,
+ unsigned int zones_in_request =
+ min_t(unsigned int, remaining_zones, max_zones_per_request);
+ struct request *req;
+- struct ublk_rq_data *pdu;
++ struct ublk_zoned_report_desc desc;
+ blk_status_t status;
+
+ memset(buffer, 0, buffer_length);
+@@ -321,20 +345,23 @@ static int ublk_report_zones(struct gendisk *disk, sector_t sector,
+ goto out;
+ }
+
+- pdu = blk_mq_rq_to_pdu(req);
+- pdu->operation = UBLK_IO_OP_REPORT_ZONES;
+- pdu->sector = sector;
+- pdu->nr_zones = zones_in_request;
++ desc.operation = UBLK_IO_OP_REPORT_ZONES;
++ desc.sector = sector;
++ desc.nr_zones = zones_in_request;
++ ret = ublk_zoned_insert_report_desc(req, &desc);
++ if (ret)
++ goto free_req;
+
+ ret = blk_rq_map_kern(disk->queue, req, buffer, buffer_length,
+ GFP_KERNEL);
+- if (ret) {
+- blk_mq_free_request(req);
+- goto out;
+- }
++ if (ret)
++ goto erase_desc;
+
+ status = blk_execute_rq(req, 0);
+ ret = blk_status_to_errno(status);
++erase_desc:
++ ublk_zoned_erase_report_desc(req);
++free_req:
+ blk_mq_free_request(req);
+ if (ret)
+ goto out;
+@@ -368,7 +395,7 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
+ {
+ struct ublksrv_io_desc *iod = ublk_get_iod(ubq, req->tag);
+ struct ublk_io *io = &ubq->ios[req->tag];
+- struct ublk_rq_data *pdu = blk_mq_rq_to_pdu(req);
++ struct ublk_zoned_report_desc *desc;
+ u32 ublk_op;
+
+ switch (req_op(req)) {
+@@ -391,12 +418,15 @@ static blk_status_t ublk_setup_iod_zoned(struct ublk_queue *ubq,
+ ublk_op = UBLK_IO_OP_ZONE_RESET_ALL;
+ break;
+ case REQ_OP_DRV_IN:
+- ublk_op = pdu->operation;
++ desc = ublk_zoned_get_report_desc(req);
++ if (!desc)
++ return BLK_STS_IOERR;
++ ublk_op = desc->operation;
+ switch (ublk_op) {
+ case UBLK_IO_OP_REPORT_ZONES:
+ iod->op_flags = ublk_op | ublk_req_build_flags(req);
+- iod->nr_zones = pdu->nr_zones;
+- iod->start_sector = pdu->sector;
++ iod->nr_zones = desc->nr_zones;
++ iod->start_sector = desc->sector;
+ return BLK_STS_OK;
+ default:
+ return BLK_STS_IOERR;
+diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
+index 0927f51867c26a..c41b86608ba866 100644
+--- a/drivers/bluetooth/btusb.c
++++ b/drivers/bluetooth/btusb.c
+@@ -1393,7 +1393,10 @@ static int btusb_submit_intr_urb(struct hci_dev *hdev, gfp_t mem_flags)
+ if (!urb)
+ return -ENOMEM;
+
+- size = le16_to_cpu(data->intr_ep->wMaxPacketSize);
++ /* Use maximum HCI Event size so the USB stack handles
++ * ZPL/short-transfer automatically.
++ */
++ size = HCI_MAX_EVENT_SIZE;
+
+ buf = kmalloc(size, mem_flags);
+ if (!buf) {
+diff --git a/drivers/bus/arm-integrator-lm.c b/drivers/bus/arm-integrator-lm.c
+index b715c8ab36e8bd..a65c79b08804f4 100644
+--- a/drivers/bus/arm-integrator-lm.c
++++ b/drivers/bus/arm-integrator-lm.c
+@@ -85,6 +85,7 @@ static int integrator_ap_lm_probe(struct platform_device *pdev)
+ return -ENODEV;
+ }
+ map = syscon_node_to_regmap(syscon);
++ of_node_put(syscon);
+ if (IS_ERR(map)) {
+ dev_err(dev,
+ "could not find Integrator/AP system controller\n");
+diff --git a/drivers/bus/mhi/host/pci_generic.c b/drivers/bus/mhi/host/pci_generic.c
+index 08844ee79654ae..edb54c97992877 100644
+--- a/drivers/bus/mhi/host/pci_generic.c
++++ b/drivers/bus/mhi/host/pci_generic.c
+@@ -606,6 +606,15 @@ static const struct mhi_pci_dev_info mhi_telit_fn990_info = {
+ .mru_default = 32768,
+ };
+
++static const struct mhi_pci_dev_info mhi_telit_fe990a_info = {
++ .name = "telit-fe990a",
++ .config = &modem_telit_fn990_config,
++ .bar_num = MHI_PCI_DEFAULT_BAR_NUM,
++ .dma_data_width = 32,
++ .sideband_wake = false,
++ .mru_default = 32768,
++};
++
+ /* Keep the list sorted based on the PID. New VID should be added as the last entry */
+ static const struct pci_device_id mhi_pci_id_table[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0304),
+@@ -623,9 +632,9 @@ static const struct pci_device_id mhi_pci_id_table[] = {
+ /* Telit FN990 */
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0308, 0x1c5d, 0x2010),
+ .driver_data = (kernel_ulong_t) &mhi_telit_fn990_info },
+- /* Telit FE990 */
++ /* Telit FE990A */
+ { PCI_DEVICE_SUB(PCI_VENDOR_ID_QCOM, 0x0308, 0x1c5d, 0x2015),
+- .driver_data = (kernel_ulong_t) &mhi_telit_fn990_info },
++ .driver_data = (kernel_ulong_t) &mhi_telit_fe990a_info },
+ { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0308),
+ .driver_data = (kernel_ulong_t) &mhi_qcom_sdx65_info },
+ { PCI_DEVICE(PCI_VENDOR_ID_QCOM, 0x0309),
+diff --git a/drivers/char/hw_random/bcm2835-rng.c b/drivers/char/hw_random/bcm2835-rng.c
+index b03e8030062758..aa2b135e3ee230 100644
+--- a/drivers/char/hw_random/bcm2835-rng.c
++++ b/drivers/char/hw_random/bcm2835-rng.c
+@@ -94,8 +94,10 @@ static int bcm2835_rng_init(struct hwrng *rng)
+ return ret;
+
+ ret = reset_control_reset(priv->reset);
+- if (ret)
++ if (ret) {
++ clk_disable_unprepare(priv->clk);
+ return ret;
++ }
+
+ if (priv->mask_interrupts) {
+ /* mask the interrupt */
+diff --git a/drivers/char/hw_random/cctrng.c b/drivers/char/hw_random/cctrng.c
+index c0d2f824769f88..4c50efc464835b 100644
+--- a/drivers/char/hw_random/cctrng.c
++++ b/drivers/char/hw_random/cctrng.c
+@@ -622,6 +622,7 @@ static int __maybe_unused cctrng_resume(struct device *dev)
+ /* wait for Cryptocell reset completion */
+ if (!cctrng_wait_for_reset_completion(drvdata)) {
+ dev_err(dev, "Cryptocell reset not completed");
++ clk_disable_unprepare(drvdata->clk);
+ return -EBUSY;
+ }
+
+diff --git a/drivers/char/hw_random/mtk-rng.c b/drivers/char/hw_random/mtk-rng.c
+index aa993753ab120b..1e3048f2bb38f0 100644
+--- a/drivers/char/hw_random/mtk-rng.c
++++ b/drivers/char/hw_random/mtk-rng.c
+@@ -142,7 +142,7 @@ static int mtk_rng_probe(struct platform_device *pdev)
+ dev_set_drvdata(&pdev->dev, priv);
+ pm_runtime_set_autosuspend_delay(&pdev->dev, RNG_AUTOSUSPEND_TIMEOUT);
+ pm_runtime_use_autosuspend(&pdev->dev);
+- pm_runtime_enable(&pdev->dev);
++ devm_pm_runtime_enable(&pdev->dev);
+
+ dev_info(&pdev->dev, "registered RNG driver\n");
+
+diff --git a/drivers/char/tpm/tpm-dev-common.c b/drivers/char/tpm/tpm-dev-common.c
+index 30b4c288c1bbc3..c3fbbf4d3db79a 100644
+--- a/drivers/char/tpm/tpm-dev-common.c
++++ b/drivers/char/tpm/tpm-dev-common.c
+@@ -47,6 +47,8 @@ static ssize_t tpm_dev_transmit(struct tpm_chip *chip, struct tpm_space *space,
+
+ if (!ret)
+ ret = tpm2_commit_space(chip, space, buf, &len);
++ else
++ tpm2_flush_space(chip);
+
+ out_rc:
+ return ret ? ret : len;
+diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
+index d3521aadd43eef..44f60730cff441 100644
+--- a/drivers/char/tpm/tpm2-sessions.c
++++ b/drivers/char/tpm/tpm2-sessions.c
+@@ -1362,4 +1362,5 @@ int tpm2_sessions_init(struct tpm_chip *chip)
+
+ return rc;
+ }
++EXPORT_SYMBOL(tpm2_sessions_init);
+ #endif /* CONFIG_TCG_TPM2_HMAC */
+diff --git a/drivers/char/tpm/tpm2-space.c b/drivers/char/tpm/tpm2-space.c
+index 4892d491da8dae..25a66870c165c5 100644
+--- a/drivers/char/tpm/tpm2-space.c
++++ b/drivers/char/tpm/tpm2-space.c
+@@ -169,6 +169,9 @@ void tpm2_flush_space(struct tpm_chip *chip)
+ struct tpm_space *space = &chip->work_space;
+ int i;
+
++ if (!space)
++ return;
++
+ for (i = 0; i < ARRAY_SIZE(space->context_tbl); i++)
+ if (space->context_tbl[i] && ~space->context_tbl[i])
+ tpm2_flush_context(chip, space->context_tbl[i]);
+diff --git a/drivers/clk/at91/sama7g5.c b/drivers/clk/at91/sama7g5.c
+index 91b5c6f1481964..4e9594714b1428 100644
+--- a/drivers/clk/at91/sama7g5.c
++++ b/drivers/clk/at91/sama7g5.c
+@@ -66,6 +66,7 @@ enum pll_component_id {
+ PLL_COMPID_FRAC,
+ PLL_COMPID_DIV0,
+ PLL_COMPID_DIV1,
++ PLL_COMPID_MAX,
+ };
+
+ /*
+@@ -165,7 +166,7 @@ static struct sama7g5_pll {
+ u8 t;
+ u8 eid;
+ u8 safe_div;
+-} sama7g5_plls[][PLL_ID_MAX] = {
++} sama7g5_plls[][PLL_COMPID_MAX] = {
+ [PLL_ID_CPU] = {
+ [PLL_COMPID_FRAC] = {
+ .n = "cpupll_fracck",
+@@ -1038,7 +1039,7 @@ static void __init sama7g5_pmc_setup(struct device_node *np)
+ sama7g5_pmc->chws[PMC_MAIN] = hw;
+
+ for (i = 0; i < PLL_ID_MAX; i++) {
+- for (j = 0; j < 3; j++) {
++ for (j = 0; j < PLL_COMPID_MAX; j++) {
+ struct clk_hw *parent_hw;
+
+ if (!sama7g5_plls[i][j].n)
+diff --git a/drivers/clk/imx/clk-composite-7ulp.c b/drivers/clk/imx/clk-composite-7ulp.c
+index e208ddc511339e..db7f40b07d1abf 100644
+--- a/drivers/clk/imx/clk-composite-7ulp.c
++++ b/drivers/clk/imx/clk-composite-7ulp.c
+@@ -14,6 +14,7 @@
+ #include "../clk-fractional-divider.h"
+ #include "clk.h"
+
++#define PCG_PR_MASK BIT(31)
+ #define PCG_PCS_SHIFT 24
+ #define PCG_PCS_MASK 0x7
+ #define PCG_CGC_SHIFT 30
+@@ -78,6 +79,12 @@ static struct clk_hw *imx_ulp_clk_hw_composite(const char *name,
+ struct clk_hw *hw;
+ u32 val;
+
++ val = readl(reg);
++ if (!(val & PCG_PR_MASK)) {
++ pr_info("PCC PR is 0 for clk:%s, bypass\n", name);
++ return 0;
++ }
++
+ if (mux_present) {
+ mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+ if (!mux)
+diff --git a/drivers/clk/imx/clk-composite-8m.c b/drivers/clk/imx/clk-composite-8m.c
+index 8cc07d056a8384..f187582ba49196 100644
+--- a/drivers/clk/imx/clk-composite-8m.c
++++ b/drivers/clk/imx/clk-composite-8m.c
+@@ -204,6 +204,34 @@ static const struct clk_ops imx8m_clk_composite_mux_ops = {
+ .determine_rate = imx8m_clk_composite_mux_determine_rate,
+ };
+
++static int imx8m_clk_composite_gate_enable(struct clk_hw *hw)
++{
++ struct clk_gate *gate = to_clk_gate(hw);
++ unsigned long flags;
++ u32 val;
++
++ spin_lock_irqsave(gate->lock, flags);
++
++ val = readl(gate->reg);
++ val |= BIT(gate->bit_idx);
++ writel(val, gate->reg);
++
++ spin_unlock_irqrestore(gate->lock, flags);
++
++ return 0;
++}
++
++static void imx8m_clk_composite_gate_disable(struct clk_hw *hw)
++{
++ /* composite clk requires the disable hook */
++}
++
++static const struct clk_ops imx8m_clk_composite_gate_ops = {
++ .enable = imx8m_clk_composite_gate_enable,
++ .disable = imx8m_clk_composite_gate_disable,
++ .is_enabled = clk_gate_is_enabled,
++};
++
+ struct clk_hw *__imx8m_clk_hw_composite(const char *name,
+ const char * const *parent_names,
+ int num_parents, void __iomem *reg,
+@@ -217,6 +245,7 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name,
+ struct clk_mux *mux;
+ const struct clk_ops *divider_ops;
+ const struct clk_ops *mux_ops;
++ const struct clk_ops *gate_ops;
+
+ mux = kzalloc(sizeof(*mux), GFP_KERNEL);
+ if (!mux)
+@@ -257,20 +286,22 @@ struct clk_hw *__imx8m_clk_hw_composite(const char *name,
+ div->flags = CLK_DIVIDER_ROUND_CLOSEST;
+
+ /* skip registering the gate ops if M4 is enabled */
+- if (!mcore_booted) {
+- gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+- if (!gate)
+- goto free_div;
+-
+- gate_hw = &gate->hw;
+- gate->reg = reg;
+- gate->bit_idx = PCG_CGC_SHIFT;
+- gate->lock = &imx_ccm_lock;
+- }
++ gate = kzalloc(sizeof(*gate), GFP_KERNEL);
++ if (!gate)
++ goto free_div;
++
++ gate_hw = &gate->hw;
++ gate->reg = reg;
++ gate->bit_idx = PCG_CGC_SHIFT;
++ gate->lock = &imx_ccm_lock;
++ if (!mcore_booted)
++ gate_ops = &clk_gate_ops;
++ else
++ gate_ops = &imx8m_clk_composite_gate_ops;
+
+ hw = clk_hw_register_composite(NULL, name, parent_names, num_parents,
+ mux_hw, mux_ops, div_hw,
+- divider_ops, gate_hw, &clk_gate_ops, flags);
++ divider_ops, gate_hw, gate_ops, flags);
+ if (IS_ERR(hw))
+ goto free_gate;
+
+diff --git a/drivers/clk/imx/clk-composite-93.c b/drivers/clk/imx/clk-composite-93.c
+index 81164bdcd6cc9a..6c6c5a30f3282d 100644
+--- a/drivers/clk/imx/clk-composite-93.c
++++ b/drivers/clk/imx/clk-composite-93.c
+@@ -76,6 +76,13 @@ static int imx93_clk_composite_gate_enable(struct clk_hw *hw)
+
+ static void imx93_clk_composite_gate_disable(struct clk_hw *hw)
+ {
++ /*
++ * Skip disable the root clock gate if mcore enabled.
++ * The root clock may be used by the mcore.
++ */
++ if (mcore_booted)
++ return;
++
+ imx93_clk_composite_gate_endisable(hw, 0);
+ }
+
+@@ -222,7 +229,7 @@ struct clk_hw *imx93_clk_composite_flags(const char *name, const char * const *p
+ hw = clk_hw_register_composite(NULL, name, parent_names, num_parents,
+ mux_hw, &clk_mux_ro_ops, div_hw,
+ &clk_divider_ro_ops, NULL, NULL, flags);
+- } else if (!mcore_booted) {
++ } else {
+ gate = kzalloc(sizeof(*gate), GFP_KERNEL);
+ if (!gate)
+ goto fail;
+@@ -238,12 +245,6 @@ struct clk_hw *imx93_clk_composite_flags(const char *name, const char * const *p
+ &imx93_clk_composite_divider_ops, gate_hw,
+ &imx93_clk_composite_gate_ops,
+ flags | CLK_SET_RATE_NO_REPARENT);
+- } else {
+- hw = clk_hw_register_composite(NULL, name, parent_names, num_parents,
+- mux_hw, &imx93_clk_composite_mux_ops, div_hw,
+- &imx93_clk_composite_divider_ops, NULL,
+- &imx93_clk_composite_gate_ops,
+- flags | CLK_SET_RATE_NO_REPARENT);
+ }
+
+ if (IS_ERR(hw))
+diff --git a/drivers/clk/imx/clk-fracn-gppll.c b/drivers/clk/imx/clk-fracn-gppll.c
+index 44462ab50e513c..1becba2b62d0be 100644
+--- a/drivers/clk/imx/clk-fracn-gppll.c
++++ b/drivers/clk/imx/clk-fracn-gppll.c
+@@ -291,6 +291,10 @@ static int clk_fracn_gppll_prepare(struct clk_hw *hw)
+ if (val & POWERUP_MASK)
+ return 0;
+
++ if (pll->flags & CLK_FRACN_GPPLL_FRACN)
++ writel_relaxed(readl_relaxed(pll->base + PLL_NUMERATOR),
++ pll->base + PLL_NUMERATOR);
++
+ val |= CLKMUX_BYPASS;
+ writel_relaxed(val, pll->base + PLL_CTRL);
+
+diff --git a/drivers/clk/imx/clk-imx6ul.c b/drivers/clk/imx/clk-imx6ul.c
+index f9394e94f69d73..05c7a82b751f3c 100644
+--- a/drivers/clk/imx/clk-imx6ul.c
++++ b/drivers/clk/imx/clk-imx6ul.c
+@@ -542,8 +542,8 @@ static void __init imx6ul_clocks_init(struct device_node *ccm_node)
+
+ clk_set_parent(hws[IMX6UL_CLK_ENFC_SEL]->clk, hws[IMX6UL_CLK_PLL2_PFD2]->clk);
+
+- clk_set_parent(hws[IMX6UL_CLK_ENET1_REF_SEL]->clk, hws[IMX6UL_CLK_ENET_REF]->clk);
+- clk_set_parent(hws[IMX6UL_CLK_ENET2_REF_SEL]->clk, hws[IMX6UL_CLK_ENET2_REF]->clk);
++ clk_set_parent(hws[IMX6UL_CLK_ENET1_REF_SEL]->clk, hws[IMX6UL_CLK_ENET1_REF_125M]->clk);
++ clk_set_parent(hws[IMX6UL_CLK_ENET2_REF_SEL]->clk, hws[IMX6UL_CLK_ENET2_REF_125M]->clk);
+
+ imx_register_uart_clocks();
+ }
+diff --git a/drivers/clk/imx/clk-imx8mp-audiomix.c b/drivers/clk/imx/clk-imx8mp-audiomix.c
+index b381d6f784c890..0767d613b68b00 100644
+--- a/drivers/clk/imx/clk-imx8mp-audiomix.c
++++ b/drivers/clk/imx/clk-imx8mp-audiomix.c
+@@ -154,6 +154,15 @@ static const struct clk_parent_data clk_imx8mp_audiomix_pll_bypass_sels[] = {
+ PDM_SEL, 2, 0 \
+ }
+
++#define CLK_GATE_PARENT(gname, cname, pname) \
++ { \
++ gname"_cg", \
++ IMX8MP_CLK_AUDIOMIX_##cname, \
++ { .fw_name = pname, .name = pname }, NULL, 1, \
++ CLKEN0 + 4 * !!(IMX8MP_CLK_AUDIOMIX_##cname / 32), \
++ 1, IMX8MP_CLK_AUDIOMIX_##cname % 32 \
++ }
++
+ struct clk_imx8mp_audiomix_sel {
+ const char *name;
+ int clkid;
+@@ -171,14 +180,14 @@ static struct clk_imx8mp_audiomix_sel sels[] = {
+ CLK_GATE("earc", EARC_IPG),
+ CLK_GATE("ocrama", OCRAMA_IPG),
+ CLK_GATE("aud2htx", AUD2HTX_IPG),
+- CLK_GATE("earc_phy", EARC_PHY),
++ CLK_GATE_PARENT("earc_phy", EARC_PHY, "sai_pll_out_div2"),
+ CLK_GATE("sdma2", SDMA2_ROOT),
+ CLK_GATE("sdma3", SDMA3_ROOT),
+ CLK_GATE("spba2", SPBA2_ROOT),
+ CLK_GATE("dsp", DSP_ROOT),
+ CLK_GATE("dspdbg", DSPDBG_ROOT),
+ CLK_GATE("edma", EDMA_ROOT),
+- CLK_GATE("audpll", AUDPLL_ROOT),
++ CLK_GATE_PARENT("audpll", AUDPLL_ROOT, "osc_24m"),
+ CLK_GATE("mu2", MU2_ROOT),
+ CLK_GATE("mu3", MU3_ROOT),
+ CLK_PDM,
+diff --git a/drivers/clk/imx/clk-imx8mp.c b/drivers/clk/imx/clk-imx8mp.c
+index 670aa2bab3017e..e561ff7b135fb5 100644
+--- a/drivers/clk/imx/clk-imx8mp.c
++++ b/drivers/clk/imx/clk-imx8mp.c
+@@ -551,8 +551,8 @@ static int imx8mp_clocks_probe(struct platform_device *pdev)
+
+ hws[IMX8MP_CLK_IPG_ROOT] = imx_clk_hw_divider2("ipg_root", "ahb_root", ccm_base + 0x9080, 0, 1);
+
+- hws[IMX8MP_CLK_DRAM_ALT] = imx8m_clk_hw_composite("dram_alt", imx8mp_dram_alt_sels, ccm_base + 0xa000);
+- hws[IMX8MP_CLK_DRAM_APB] = imx8m_clk_hw_composite_critical("dram_apb", imx8mp_dram_apb_sels, ccm_base + 0xa080);
++ hws[IMX8MP_CLK_DRAM_ALT] = imx8m_clk_hw_fw_managed_composite("dram_alt", imx8mp_dram_alt_sels, ccm_base + 0xa000);
++ hws[IMX8MP_CLK_DRAM_APB] = imx8m_clk_hw_fw_managed_composite_critical("dram_apb", imx8mp_dram_apb_sels, ccm_base + 0xa080);
+ hws[IMX8MP_CLK_VPU_G1] = imx8m_clk_hw_composite("vpu_g1", imx8mp_vpu_g1_sels, ccm_base + 0xa100);
+ hws[IMX8MP_CLK_VPU_G2] = imx8m_clk_hw_composite("vpu_g2", imx8mp_vpu_g2_sels, ccm_base + 0xa180);
+ hws[IMX8MP_CLK_CAN1] = imx8m_clk_hw_composite("can1", imx8mp_can1_sels, ccm_base + 0xa200);
+diff --git a/drivers/clk/imx/clk-imx8qxp.c b/drivers/clk/imx/clk-imx8qxp.c
+index 7d8883916cacdd..83f2e8bd6d5062 100644
+--- a/drivers/clk/imx/clk-imx8qxp.c
++++ b/drivers/clk/imx/clk-imx8qxp.c
+@@ -170,8 +170,8 @@ static int imx8qxp_clk_probe(struct platform_device *pdev)
+ imx_clk_scu("pwm_clk", IMX_SC_R_LCD_0_PWM_0, IMX_SC_PM_CLK_PER);
+ imx_clk_scu("elcdif_pll", IMX_SC_R_ELCDIF_PLL, IMX_SC_PM_CLK_PLL);
+ imx_clk_scu2("lcd_clk", lcd_sels, ARRAY_SIZE(lcd_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_PER);
+- imx_clk_scu2("lcd_pxl_clk", lcd_pxl_sels, ARRAY_SIZE(lcd_pxl_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_MISC0);
+ imx_clk_scu("lcd_pxl_bypass_div_clk", IMX_SC_R_LCD_0, IMX_SC_PM_CLK_BYPASS);
++ imx_clk_scu2("lcd_pxl_clk", lcd_pxl_sels, ARRAY_SIZE(lcd_pxl_sels), IMX_SC_R_LCD_0, IMX_SC_PM_CLK_MISC0);
+
+ /* Audio SS */
+ imx_clk_scu("audio_pll0_clk", IMX_SC_R_AUDIO_PLL_0, IMX_SC_PM_CLK_PLL);
+@@ -206,18 +206,18 @@ static int imx8qxp_clk_probe(struct platform_device *pdev)
+ imx_clk_scu("usb3_lpm_div", IMX_SC_R_USB_2, IMX_SC_PM_CLK_MISC);
+
+ /* Display controller SS */
+- imx_clk_scu2("dc0_disp0_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0);
+- imx_clk_scu2("dc0_disp1_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1);
+ imx_clk_scu("dc0_pll0_clk", IMX_SC_R_DC_0_PLL_0, IMX_SC_PM_CLK_PLL);
+ imx_clk_scu("dc0_pll1_clk", IMX_SC_R_DC_0_PLL_1, IMX_SC_PM_CLK_PLL);
+ imx_clk_scu("dc0_bypass0_clk", IMX_SC_R_DC_0_VIDEO0, IMX_SC_PM_CLK_BYPASS);
++ imx_clk_scu2("dc0_disp0_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC0);
++ imx_clk_scu2("dc0_disp1_clk", dc0_sels, ARRAY_SIZE(dc0_sels), IMX_SC_R_DC_0, IMX_SC_PM_CLK_MISC1);
+ imx_clk_scu("dc0_bypass1_clk", IMX_SC_R_DC_0_VIDEO1, IMX_SC_PM_CLK_BYPASS);
+
+- imx_clk_scu2("dc1_disp0_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC0);
+- imx_clk_scu2("dc1_disp1_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC1);
+ imx_clk_scu("dc1_pll0_clk", IMX_SC_R_DC_1_PLL_0, IMX_SC_PM_CLK_PLL);
+ imx_clk_scu("dc1_pll1_clk", IMX_SC_R_DC_1_PLL_1, IMX_SC_PM_CLK_PLL);
+ imx_clk_scu("dc1_bypass0_clk", IMX_SC_R_DC_1_VIDEO0, IMX_SC_PM_CLK_BYPASS);
++ imx_clk_scu2("dc1_disp0_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC0);
++ imx_clk_scu2("dc1_disp1_clk", dc1_sels, ARRAY_SIZE(dc1_sels), IMX_SC_R_DC_1, IMX_SC_PM_CLK_MISC1);
+ imx_clk_scu("dc1_bypass1_clk", IMX_SC_R_DC_1_VIDEO1, IMX_SC_PM_CLK_BYPASS);
+
+ /* MIPI-LVDS SS */
+diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
+index 25a7b4b15c56ab..2720cbc40e0acc 100644
+--- a/drivers/clk/qcom/clk-alpha-pll.c
++++ b/drivers/clk/qcom/clk-alpha-pll.c
+@@ -1784,6 +1784,58 @@ const struct clk_ops clk_alpha_pll_agera_ops = {
+ };
+ EXPORT_SYMBOL_GPL(clk_alpha_pll_agera_ops);
+
++/**
++ * clk_lucid_5lpe_pll_configure - configure the lucid 5lpe pll
++ *
++ * @pll: clk alpha pll
++ * @regmap: register map
++ * @config: configuration to apply for pll
++ */
++void clk_lucid_5lpe_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
++ const struct alpha_pll_config *config)
++{
++ /*
++ * If the bootloader left the PLL enabled it's likely that there are
++ * RCGs that will lock up if we disable the PLL below.
++ */
++ if (trion_pll_is_enabled(pll, regmap)) {
++ pr_debug("Lucid 5LPE PLL is already enabled, skipping configuration\n");
++ return;
++ }
++
++ clk_alpha_pll_write_config(regmap, PLL_L_VAL(pll), config->l);
++ regmap_write(regmap, PLL_CAL_L_VAL(pll), TRION_PLL_CAL_VAL);
++ clk_alpha_pll_write_config(regmap, PLL_ALPHA_VAL(pll), config->alpha);
++ clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL(pll),
++ config->config_ctl_val);
++ clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U(pll),
++ config->config_ctl_hi_val);
++ clk_alpha_pll_write_config(regmap, PLL_CONFIG_CTL_U1(pll),
++ config->config_ctl_hi1_val);
++ clk_alpha_pll_write_config(regmap, PLL_USER_CTL(pll),
++ config->user_ctl_val);
++ clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U(pll),
++ config->user_ctl_hi_val);
++ clk_alpha_pll_write_config(regmap, PLL_USER_CTL_U1(pll),
++ config->user_ctl_hi1_val);
++ clk_alpha_pll_write_config(regmap, PLL_TEST_CTL(pll),
++ config->test_ctl_val);
++ clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U(pll),
++ config->test_ctl_hi_val);
++ clk_alpha_pll_write_config(regmap, PLL_TEST_CTL_U1(pll),
++ config->test_ctl_hi1_val);
++
++ /* Disable PLL output */
++ regmap_update_bits(regmap, PLL_MODE(pll), PLL_OUTCTRL, 0);
++
++ /* Set operation mode to OFF */
++ regmap_write(regmap, PLL_OPMODE(pll), PLL_STANDBY);
++
++ /* Place the PLL in STANDBY mode */
++ regmap_update_bits(regmap, PLL_MODE(pll), PLL_RESET_N, PLL_RESET_N);
++}
++EXPORT_SYMBOL_GPL(clk_lucid_5lpe_pll_configure);
++
+ static int alpha_pll_lucid_5lpe_enable(struct clk_hw *hw)
+ {
+ struct clk_alpha_pll *pll = to_clk_alpha_pll(hw);
+diff --git a/drivers/clk/qcom/clk-alpha-pll.h b/drivers/clk/qcom/clk-alpha-pll.h
+index c7055b6c42f1d5..d89ec4723e2d9c 100644
+--- a/drivers/clk/qcom/clk-alpha-pll.h
++++ b/drivers/clk/qcom/clk-alpha-pll.h
+@@ -205,6 +205,8 @@ void clk_agera_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+
+ void clk_zonda_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+ const struct alpha_pll_config *config);
++void clk_lucid_5lpe_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
++ const struct alpha_pll_config *config);
+ void clk_lucid_evo_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+ const struct alpha_pll_config *config);
+ void clk_lucid_ole_pll_configure(struct clk_alpha_pll *pll, struct regmap *regmap,
+diff --git a/drivers/clk/qcom/dispcc-sm8250.c b/drivers/clk/qcom/dispcc-sm8250.c
+index 43307c8a342cae..2103e22ca3ddee 100644
+--- a/drivers/clk/qcom/dispcc-sm8250.c
++++ b/drivers/clk/qcom/dispcc-sm8250.c
+@@ -1357,8 +1357,13 @@ static int disp_cc_sm8250_probe(struct platform_device *pdev)
+ disp_cc_sm8250_clocks[DISP_CC_MDSS_EDP_GTC_CLK_SRC] = NULL;
+ }
+
+- clk_lucid_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config);
+- clk_lucid_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config);
++ if (of_device_is_compatible(pdev->dev.of_node, "qcom,sm8350-dispcc")) {
++ clk_lucid_5lpe_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config);
++ clk_lucid_5lpe_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config);
++ } else {
++ clk_lucid_pll_configure(&disp_cc_pll0, regmap, &disp_cc_pll0_config);
++ clk_lucid_pll_configure(&disp_cc_pll1, regmap, &disp_cc_pll1_config);
++ }
+
+ /* Enable clock gating for MDP clocks */
+ regmap_update_bits(regmap, 0x8000, 0x10, 0x10);
+diff --git a/drivers/clk/qcom/dispcc-sm8550.c b/drivers/clk/qcom/dispcc-sm8550.c
+index 38ecea805503d3..1ba01bdb763b7f 100644
+--- a/drivers/clk/qcom/dispcc-sm8550.c
++++ b/drivers/clk/qcom/dispcc-sm8550.c
+@@ -196,7 +196,7 @@ static const struct clk_parent_data disp_cc_parent_data_3[] = {
+ static const struct parent_map disp_cc_parent_map_4[] = {
+ { P_BI_TCXO, 0 },
+ { P_DP0_PHY_PLL_LINK_CLK, 1 },
+- { P_DP1_PHY_PLL_VCO_DIV_CLK, 2 },
++ { P_DP0_PHY_PLL_VCO_DIV_CLK, 2 },
+ { P_DP3_PHY_PLL_VCO_DIV_CLK, 3 },
+ { P_DP1_PHY_PLL_VCO_DIV_CLK, 4 },
+ { P_DP2_PHY_PLL_VCO_DIV_CLK, 6 },
+@@ -213,7 +213,7 @@ static const struct clk_parent_data disp_cc_parent_data_4[] = {
+
+ static const struct parent_map disp_cc_parent_map_5[] = {
+ { P_BI_TCXO, 0 },
+- { P_DSI0_PHY_PLL_OUT_BYTECLK, 4 },
++ { P_DSI0_PHY_PLL_OUT_BYTECLK, 2 },
+ { P_DSI1_PHY_PLL_OUT_BYTECLK, 4 },
+ };
+
+@@ -400,7 +400,7 @@ static struct clk_rcg2 disp_cc_mdss_dptx1_aux_clk_src = {
+ .parent_data = disp_cc_parent_data_0,
+ .num_parents = ARRAY_SIZE(disp_cc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_dp_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -562,7 +562,7 @@ static struct clk_rcg2 disp_cc_mdss_esc0_clk_src = {
+ .parent_data = disp_cc_parent_data_5,
+ .num_parents = ARRAY_SIZE(disp_cc_parent_data_5),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_ops,
++ .ops = &clk_rcg2_shared_ops,
+ },
+ };
+
+@@ -577,7 +577,7 @@ static struct clk_rcg2 disp_cc_mdss_esc1_clk_src = {
+ .parent_data = disp_cc_parent_data_5,
+ .num_parents = ARRAY_SIZE(disp_cc_parent_data_5),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_ops,
++ .ops = &clk_rcg2_shared_ops,
+ },
+ };
+
+@@ -1611,7 +1611,7 @@ static struct gdsc mdss_gdsc = {
+ .name = "mdss_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
+- .flags = HW_CTRL | RETAIN_FF_ENABLE,
++ .flags = POLL_CFG_GDSCR | HW_CTRL | RETAIN_FF_ENABLE,
+ };
+
+ static struct gdsc mdss_int2_gdsc = {
+@@ -1620,7 +1620,7 @@ static struct gdsc mdss_int2_gdsc = {
+ .name = "mdss_int2_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
+- .flags = HW_CTRL | RETAIN_FF_ENABLE,
++ .flags = POLL_CFG_GDSCR | HW_CTRL | RETAIN_FF_ENABLE,
+ };
+
+ static struct clk_regmap *disp_cc_sm8550_clocks[] = {
+diff --git a/drivers/clk/qcom/gcc-ipq5332.c b/drivers/clk/qcom/gcc-ipq5332.c
+index f98591148a9767..6a4877d8882946 100644
+--- a/drivers/clk/qcom/gcc-ipq5332.c
++++ b/drivers/clk/qcom/gcc-ipq5332.c
+@@ -3388,6 +3388,7 @@ static struct clk_regmap *gcc_ipq5332_clocks[] = {
+ [GCC_QDSS_DAP_DIV_CLK_SRC] = &gcc_qdss_dap_div_clk_src.clkr,
+ [GCC_QDSS_ETR_USB_CLK] = &gcc_qdss_etr_usb_clk.clkr,
+ [GCC_QDSS_EUD_AT_CLK] = &gcc_qdss_eud_at_clk.clkr,
++ [GCC_QDSS_TSCTR_CLK_SRC] = &gcc_qdss_tsctr_clk_src.clkr,
+ [GCC_QPIC_AHB_CLK] = &gcc_qpic_ahb_clk.clkr,
+ [GCC_QPIC_CLK] = &gcc_qpic_clk.clkr,
+ [GCC_QPIC_IO_MACRO_CLK] = &gcc_qpic_io_macro_clk.clkr,
+diff --git a/drivers/clk/rockchip/clk-rk3228.c b/drivers/clk/rockchip/clk-rk3228.c
+index a24a35553e1349..7343d2d7676bca 100644
+--- a/drivers/clk/rockchip/clk-rk3228.c
++++ b/drivers/clk/rockchip/clk-rk3228.c
+@@ -409,7 +409,7 @@ static struct rockchip_clk_branch rk3228_clk_branches[] __initdata = {
+ RK2928_CLKSEL_CON(29), 0, 3, DFLAGS),
+ DIV(0, "sclk_vop_pre", "sclk_vop_src", 0,
+ RK2928_CLKSEL_CON(27), 8, 8, DFLAGS),
+- MUX(DCLK_VOP, "dclk_vop", mux_dclk_vop_p, 0,
++ MUX(DCLK_VOP, "dclk_vop", mux_dclk_vop_p, CLK_SET_RATE_PARENT | CLK_SET_RATE_NO_REPARENT,
+ RK2928_CLKSEL_CON(27), 1, 1, MFLAGS),
+
+ FACTOR(0, "xin12m", "xin24m", 0, 1, 2),
+diff --git a/drivers/clk/rockchip/clk-rk3588.c b/drivers/clk/rockchip/clk-rk3588.c
+index b30279a96dc8af..3027379f2fdd11 100644
+--- a/drivers/clk/rockchip/clk-rk3588.c
++++ b/drivers/clk/rockchip/clk-rk3588.c
+@@ -526,7 +526,7 @@ PNAME(pmu_200m_100m_p) = { "clk_pmu1_200m_src", "clk_pmu1_100m_src" };
+ PNAME(pmu_300m_24m_p) = { "clk_300m_src", "xin24m" };
+ PNAME(pmu_400m_24m_p) = { "clk_400m_src", "xin24m" };
+ PNAME(pmu_100m_50m_24m_src_p) = { "clk_pmu1_100m_src", "clk_pmu1_50m_src", "xin24m" };
+-PNAME(pmu_24m_32k_100m_src_p) = { "xin24m", "32k", "clk_pmu1_100m_src" };
++PNAME(pmu_24m_32k_100m_src_p) = { "xin24m", "xin32k", "clk_pmu1_100m_src" };
+ PNAME(hclk_pmu1_root_p) = { "clk_pmu1_200m_src", "clk_pmu1_100m_src", "clk_pmu1_50m_src", "xin24m" };
+ PNAME(hclk_pmu_cm0_root_p) = { "clk_pmu1_400m_src", "clk_pmu1_200m_src", "clk_pmu1_100m_src", "xin24m" };
+ PNAME(mclk_pdm0_p) = { "clk_pmu1_300m_src", "clk_pmu1_200m_src" };
+diff --git a/drivers/clk/starfive/clk-starfive-jh7110-vout.c b/drivers/clk/starfive/clk-starfive-jh7110-vout.c
+index 53f7af234cc23e..aabd0484ac23f6 100644
+--- a/drivers/clk/starfive/clk-starfive-jh7110-vout.c
++++ b/drivers/clk/starfive/clk-starfive-jh7110-vout.c
+@@ -145,7 +145,7 @@ static int jh7110_voutcrg_probe(struct platform_device *pdev)
+
+ /* enable power domain and clocks */
+ pm_runtime_enable(priv->dev);
+- ret = pm_runtime_get_sync(priv->dev);
++ ret = pm_runtime_resume_and_get(priv->dev);
+ if (ret < 0)
+ return dev_err_probe(priv->dev, ret, "failed to turn on power\n");
+
+diff --git a/drivers/clk/ti/clk-dra7-atl.c b/drivers/clk/ti/clk-dra7-atl.c
+index d964e3affd42ce..0eab7f3e2eab9e 100644
+--- a/drivers/clk/ti/clk-dra7-atl.c
++++ b/drivers/clk/ti/clk-dra7-atl.c
+@@ -240,6 +240,7 @@ static int of_dra7_atl_clk_probe(struct platform_device *pdev)
+ }
+
+ clk = of_clk_get_from_provider(&clkspec);
++ of_node_put(clkspec.np);
+ if (IS_ERR(clk)) {
+ pr_err("%s: failed to get atl clock %d from provider\n",
+ __func__, i);
+diff --git a/drivers/clocksource/timer-qcom.c b/drivers/clocksource/timer-qcom.c
+index b4afe3a6758351..eac4c95c6127f2 100644
+--- a/drivers/clocksource/timer-qcom.c
++++ b/drivers/clocksource/timer-qcom.c
+@@ -233,6 +233,7 @@ static int __init msm_dt_timer_init(struct device_node *np)
+ }
+
+ if (of_property_read_u32(np, "clock-frequency", &freq)) {
++ iounmap(cpu0_base);
+ pr_err("Unknown frequency\n");
+ return -EINVAL;
+ }
+@@ -243,7 +244,11 @@ static int __init msm_dt_timer_init(struct device_node *np)
+ freq /= 4;
+ writel_relaxed(DGT_CLK_CTL_DIV_4, source_base + DGT_CLK_CTL);
+
+- return msm_timer_init(freq, 32, irq, !!percpu_offset);
++ ret = msm_timer_init(freq, 32, irq, !!percpu_offset);
++ if (ret)
++ iounmap(cpu0_base);
++
++ return ret;
+ }
+ TIMER_OF_DECLARE(kpss_timer, "qcom,kpss-timer", msm_dt_timer_init);
+ TIMER_OF_DECLARE(scss_timer, "qcom,scss-timer", msm_dt_timer_init);
+diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
+index 5af85c4cbad0cc..f8e6dc3c14d359 100644
+--- a/drivers/cpufreq/ti-cpufreq.c
++++ b/drivers/cpufreq/ti-cpufreq.c
+@@ -61,6 +61,9 @@ struct ti_cpufreq_soc_data {
+ unsigned long efuse_shift;
+ unsigned long rev_offset;
+ bool multi_regulator;
++/* Backward compatibility hack: Might have missing syscon */
++#define TI_QUIRK_SYSCON_MAY_BE_MISSING 0x1
++ u8 quirks;
+ };
+
+ struct ti_cpufreq_data {
+@@ -182,6 +185,7 @@ static struct ti_cpufreq_soc_data omap34xx_soc_data = {
+ .efuse_mask = BIT(3),
+ .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE,
+ .multi_regulator = false,
++ .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING,
+ };
+
+ /*
+@@ -209,6 +213,7 @@ static struct ti_cpufreq_soc_data omap36xx_soc_data = {
+ .efuse_mask = BIT(9),
+ .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE,
+ .multi_regulator = true,
++ .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING,
+ };
+
+ /*
+@@ -223,6 +228,7 @@ static struct ti_cpufreq_soc_data am3517_soc_data = {
+ .efuse_mask = 0,
+ .rev_offset = OMAP3_CONTROL_IDCODE - OMAP3_SYSCON_BASE,
+ .multi_regulator = false,
++ .quirks = TI_QUIRK_SYSCON_MAY_BE_MISSING,
+ };
+
+ static struct ti_cpufreq_soc_data am625_soc_data = {
+@@ -250,7 +256,7 @@ static int ti_cpufreq_get_efuse(struct ti_cpufreq_data *opp_data,
+
+ ret = regmap_read(opp_data->syscon, opp_data->soc_data->efuse_offset,
+ &efuse);
+- if (ret == -EIO) {
++ if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) {
+ /* not a syscon register! */
+ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE +
+ opp_data->soc_data->efuse_offset, 4);
+@@ -291,7 +297,7 @@ static int ti_cpufreq_get_rev(struct ti_cpufreq_data *opp_data,
+
+ ret = regmap_read(opp_data->syscon, opp_data->soc_data->rev_offset,
+ &revision);
+- if (ret == -EIO) {
++ if (opp_data->soc_data->quirks & TI_QUIRK_SYSCON_MAY_BE_MISSING && ret == -EIO) {
+ /* not a syscon register! */
+ void __iomem *regs = ioremap(OMAP3_SYSCON_BASE +
+ opp_data->soc_data->rev_offset, 4);
+diff --git a/drivers/cpuidle/cpuidle-riscv-sbi.c b/drivers/cpuidle/cpuidle-riscv-sbi.c
+index a6e123dfe394d8..5bb3401220d296 100644
+--- a/drivers/cpuidle/cpuidle-riscv-sbi.c
++++ b/drivers/cpuidle/cpuidle-riscv-sbi.c
+@@ -8,6 +8,7 @@
+
+ #define pr_fmt(fmt) "cpuidle-riscv-sbi: " fmt
+
++#include <linux/cleanup.h>
+ #include <linux/cpuhotplug.h>
+ #include <linux/cpuidle.h>
+ #include <linux/cpumask.h>
+@@ -236,19 +237,16 @@ static int sbi_cpuidle_dt_init_states(struct device *dev,
+ {
+ struct sbi_cpuidle_data *data = per_cpu_ptr(&sbi_cpuidle_data, cpu);
+ struct device_node *state_node;
+- struct device_node *cpu_node;
+ u32 *states;
+ int i, ret;
+
+- cpu_node = of_cpu_device_node_get(cpu);
++ struct device_node *cpu_node __free(device_node) = of_cpu_device_node_get(cpu);
+ if (!cpu_node)
+ return -ENODEV;
+
+ states = devm_kcalloc(dev, state_count, sizeof(*states), GFP_KERNEL);
+- if (!states) {
+- ret = -ENOMEM;
+- goto fail;
+- }
++ if (!states)
++ return -ENOMEM;
+
+ /* Parse SBI specific details from state DT nodes */
+ for (i = 1; i < state_count; i++) {
+@@ -264,10 +262,8 @@ static int sbi_cpuidle_dt_init_states(struct device *dev,
+
+ pr_debug("sbi-state %#x index %d\n", states[i], i);
+ }
+- if (i != state_count) {
+- ret = -ENODEV;
+- goto fail;
+- }
++ if (i != state_count)
++ return -ENODEV;
+
+ /* Initialize optional data, used for the hierarchical topology. */
+ ret = sbi_dt_cpu_init_topology(drv, data, state_count, cpu);
+@@ -277,10 +273,7 @@ static int sbi_cpuidle_dt_init_states(struct device *dev,
+ /* Store states in the per-cpu struct. */
+ data->states = states;
+
+-fail:
+- of_node_put(cpu_node);
+-
+- return ret;
++ return 0;
+ }
+
+ static void sbi_cpuidle_deinit_cpu(int cpu)
+diff --git a/drivers/crypto/caam/caamhash.c b/drivers/crypto/caam/caamhash.c
+index fdd724228c2fa8..25c02e26725858 100644
+--- a/drivers/crypto/caam/caamhash.c
++++ b/drivers/crypto/caam/caamhash.c
+@@ -708,6 +708,7 @@ static struct ahash_edesc *ahash_edesc_alloc(struct ahash_request *req,
+ GFP_KERNEL : GFP_ATOMIC;
+ struct ahash_edesc *edesc;
+
++ sg_num = pad_sg_nents(sg_num);
+ edesc = kzalloc(struct_size(edesc, sec4_sg, sg_num), flags);
+ if (!edesc)
+ return NULL;
+diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
+index 1912bee22dd4a6..7407c9a1e844ed 100644
+--- a/drivers/crypto/ccp/sev-dev.c
++++ b/drivers/crypto/ccp/sev-dev.c
+@@ -910,7 +910,18 @@ static int __sev_do_cmd_locked(int cmd, void *data, int *psp_ret)
+
+ sev->int_rcvd = 0;
+
+- reg = FIELD_PREP(SEV_CMDRESP_CMD, cmd) | SEV_CMDRESP_IOC;
++ reg = FIELD_PREP(SEV_CMDRESP_CMD, cmd);
++
++ /*
++ * If invoked during panic handling, local interrupts are disabled so
++ * the PSP command completion interrupt can't be used.
++ * sev_wait_cmd_ioc() already checks for interrupts disabled and
++ * polls for PSP command completion. Ensure we do not request an
++ * interrupt from the PSP if irqs disabled.
++ */
++ if (!irqs_disabled())
++ reg |= SEV_CMDRESP_IOC;
++
+ iowrite32(reg, sev->io_regs + sev->vdata->cmdresp_reg);
+
+ /* wait for command completion */
+@@ -2374,6 +2385,8 @@ void sev_pci_init(void)
+ return;
+
+ err:
++ sev_dev_destroy(psp_master);
++
+ psp_master->sev_data = NULL;
+ }
+
+diff --git a/drivers/crypto/hisilicon/hpre/hpre_main.c b/drivers/crypto/hisilicon/hpre/hpre_main.c
+index 10aa4da93323f1..6b536ad2ada52a 100644
+--- a/drivers/crypto/hisilicon/hpre/hpre_main.c
++++ b/drivers/crypto/hisilicon/hpre/hpre_main.c
+@@ -13,9 +13,7 @@
+ #include <linux/uacce.h>
+ #include "hpre.h"
+
+-#define HPRE_QM_ABNML_INT_MASK 0x100004
+ #define HPRE_CTRL_CNT_CLR_CE_BIT BIT(0)
+-#define HPRE_COMM_CNT_CLR_CE 0x0
+ #define HPRE_CTRL_CNT_CLR_CE 0x301000
+ #define HPRE_FSM_MAX_CNT 0x301008
+ #define HPRE_VFG_AXQOS 0x30100c
+@@ -42,7 +40,6 @@
+ #define HPRE_HAC_INT_SET 0x301500
+ #define HPRE_RNG_TIMEOUT_NUM 0x301A34
+ #define HPRE_CORE_INT_ENABLE 0
+-#define HPRE_CORE_INT_DISABLE GENMASK(21, 0)
+ #define HPRE_RDCHN_INI_ST 0x301a00
+ #define HPRE_CLSTR_BASE 0x302000
+ #define HPRE_CORE_EN_OFFSET 0x04
+@@ -66,7 +63,6 @@
+ #define HPRE_CLSTR_ADDR_INTRVL 0x1000
+ #define HPRE_CLUSTER_INQURY 0x100
+ #define HPRE_CLSTR_ADDR_INQRY_RSLT 0x104
+-#define HPRE_TIMEOUT_ABNML_BIT 6
+ #define HPRE_PASID_EN_BIT 9
+ #define HPRE_REG_RD_INTVRL_US 10
+ #define HPRE_REG_RD_TMOUT_US 1000
+@@ -203,9 +199,9 @@ static const struct hisi_qm_cap_info hpre_basic_info[] = {
+ {HPRE_QM_RESET_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0xC37, 0x6C37},
+ {HPRE_QM_OOO_SHUTDOWN_MASK_CAP, 0x3128, 0, GENMASK(31, 0), 0x0, 0x4, 0x6C37},
+ {HPRE_QM_CE_MASK_CAP, 0x312C, 0, GENMASK(31, 0), 0x0, 0x8, 0x8},
+- {HPRE_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0x1FFFFFE},
+- {HPRE_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xBFFFFE},
+- {HPRE_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x22, 0xBFFFFE},
++ {HPRE_NFE_MASK_CAP, 0x3130, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0x1FFFC3E},
++ {HPRE_RESET_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x3FFFFE, 0xBFFC3E},
++ {HPRE_OOO_SHUTDOWN_MASK_CAP, 0x3134, 0, GENMASK(31, 0), 0x0, 0x22, 0xBFFC3E},
+ {HPRE_CE_MASK_CAP, 0x3138, 0, GENMASK(31, 0), 0x0, 0x1, 0x1},
+ {HPRE_CLUSTER_NUM_CAP, 0x313c, 20, GENMASK(3, 0), 0x0, 0x4, 0x1},
+ {HPRE_CORE_TYPE_NUM_CAP, 0x313c, 16, GENMASK(3, 0), 0x0, 0x2, 0x2},
+@@ -358,6 +354,8 @@ static struct dfx_diff_registers hpre_diff_regs[] = {
+ },
+ };
+
++static const struct hisi_qm_err_ini hpre_err_ini;
++
+ bool hpre_check_alg_support(struct hisi_qm *qm, u32 alg)
+ {
+ u32 cap_val;
+@@ -654,11 +652,6 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm)
+ writel(HPRE_QM_USR_CFG_MASK, qm->io_base + QM_AWUSER_M_CFG_ENABLE);
+ writel_relaxed(HPRE_QM_AXI_CFG_MASK, qm->io_base + QM_AXI_M_CFG);
+
+- /* HPRE need more time, we close this interrupt */
+- val = readl_relaxed(qm->io_base + HPRE_QM_ABNML_INT_MASK);
+- val |= BIT(HPRE_TIMEOUT_ABNML_BIT);
+- writel_relaxed(val, qm->io_base + HPRE_QM_ABNML_INT_MASK);
+-
+ if (qm->ver >= QM_HW_V3)
+ writel(HPRE_RSA_ENB | HPRE_ECC_ENB,
+ qm->io_base + HPRE_TYPES_ENB);
+@@ -667,9 +660,7 @@ static int hpre_set_user_domain_and_cache(struct hisi_qm *qm)
+
+ writel(HPRE_QM_VFG_AX_MASK, qm->io_base + HPRE_VFG_AXCACHE);
+ writel(0x0, qm->io_base + HPRE_BD_ENDIAN);
+- writel(0x0, qm->io_base + HPRE_INT_MASK);
+ writel(0x0, qm->io_base + HPRE_POISON_BYPASS);
+- writel(0x0, qm->io_base + HPRE_COMM_CNT_CLR_CE);
+ writel(0x0, qm->io_base + HPRE_ECC_BYPASS);
+
+ writel(HPRE_BD_USR_MASK, qm->io_base + HPRE_BD_ARUSR_CFG);
+@@ -759,7 +750,7 @@ static void hpre_hw_error_disable(struct hisi_qm *qm)
+
+ static void hpre_hw_error_enable(struct hisi_qm *qm)
+ {
+- u32 ce, nfe;
++ u32 ce, nfe, err_en;
+
+ ce = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_CE_MASK_CAP, qm->cap_ver);
+ nfe = hisi_qm_get_hw_info(qm, hpre_basic_info, HPRE_NFE_MASK_CAP, qm->cap_ver);
+@@ -776,7 +767,8 @@ static void hpre_hw_error_enable(struct hisi_qm *qm)
+ hpre_master_ooo_ctrl(qm, true);
+
+ /* enable hpre hw error interrupts */
+- writel(HPRE_CORE_INT_ENABLE, qm->io_base + HPRE_INT_MASK);
++ err_en = ce | nfe | HPRE_HAC_RAS_FE_ENABLE;
++ writel(~err_en, qm->io_base + HPRE_INT_MASK);
+ }
+
+ static inline struct hisi_qm *hpre_file_to_qm(struct hpre_debugfs_file *file)
+@@ -1161,6 +1153,7 @@ static int hpre_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
+ qm->qp_num = pf_q_num;
+ qm->debug.curr_qm_qp_num = pf_q_num;
+ qm->qm_list = &hpre_devices;
++ qm->err_ini = &hpre_err_ini;
+ if (pf_q_num_flag)
+ set_bit(QM_MODULE_PARAM, &qm->misc_ctl);
+ }
+@@ -1350,8 +1343,6 @@ static int hpre_pf_probe_init(struct hpre *hpre)
+
+ hpre_open_sva_prefetch(qm);
+
+- qm->err_ini = &hpre_err_ini;
+- qm->err_ini->err_info_init(qm);
+ hisi_qm_dev_err_init(qm);
+ ret = hpre_show_last_regs_init(qm);
+ if (ret)
+@@ -1380,6 +1371,18 @@ static int hpre_probe_init(struct hpre *hpre)
+ return 0;
+ }
+
++static void hpre_probe_uninit(struct hisi_qm *qm)
++{
++ if (qm->fun_type == QM_HW_VF)
++ return;
++
++ hpre_cnt_regs_clear(qm);
++ qm->debug.curr_qm_qp_num = 0;
++ hpre_show_last_regs_uninit(qm);
++ hpre_close_sva_prefetch(qm);
++ hisi_qm_dev_err_uninit(qm);
++}
++
+ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+ {
+ struct hisi_qm *qm;
+@@ -1405,7 +1408,7 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+
+ ret = hisi_qm_start(qm);
+ if (ret)
+- goto err_with_err_init;
++ goto err_with_probe_init;
+
+ ret = hpre_debugfs_init(qm);
+ if (ret)
+@@ -1444,9 +1447,8 @@ static int hpre_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+ hpre_debugfs_exit(qm);
+ hisi_qm_stop(qm, QM_NORMAL);
+
+-err_with_err_init:
+- hpre_show_last_regs_uninit(qm);
+- hisi_qm_dev_err_uninit(qm);
++err_with_probe_init:
++ hpre_probe_uninit(qm);
+
+ err_with_qm_init:
+ hisi_qm_uninit(qm);
+@@ -1468,13 +1470,7 @@ static void hpre_remove(struct pci_dev *pdev)
+ hpre_debugfs_exit(qm);
+ hisi_qm_stop(qm, QM_NORMAL);
+
+- if (qm->fun_type == QM_HW_PF) {
+- hpre_cnt_regs_clear(qm);
+- qm->debug.curr_qm_qp_num = 0;
+- hpre_show_last_regs_uninit(qm);
+- hisi_qm_dev_err_uninit(qm);
+- }
+-
++ hpre_probe_uninit(qm);
+ hisi_qm_uninit(qm);
+ }
+
+diff --git a/drivers/crypto/hisilicon/qm.c b/drivers/crypto/hisilicon/qm.c
+index 3dac8d8e856866..da562ceaaf277f 100644
+--- a/drivers/crypto/hisilicon/qm.c
++++ b/drivers/crypto/hisilicon/qm.c
+@@ -450,6 +450,7 @@ static struct qm_typical_qos_table shaper_cbs_s[] = {
+ };
+
+ static void qm_irqs_unregister(struct hisi_qm *qm);
++static int qm_reset_device(struct hisi_qm *qm);
+
+ static u32 qm_get_hw_error_status(struct hisi_qm *qm)
+ {
+@@ -4019,6 +4020,28 @@ static int qm_set_vf_mse(struct hisi_qm *qm, bool set)
+ return -ETIMEDOUT;
+ }
+
++static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm)
++{
++ u32 nfe_enb = 0;
++
++ /* Kunpeng930 hardware automatically close master ooo when NFE occurs */
++ if (qm->ver >= QM_HW_V3)
++ return;
++
++ if (!qm->err_status.is_dev_ecc_mbit &&
++ qm->err_status.is_qm_ecc_mbit &&
++ qm->err_ini->close_axi_master_ooo) {
++ qm->err_ini->close_axi_master_ooo(qm);
++ } else if (qm->err_status.is_dev_ecc_mbit &&
++ !qm->err_status.is_qm_ecc_mbit &&
++ !qm->err_ini->close_axi_master_ooo) {
++ nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE);
++ writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE,
++ qm->io_base + QM_RAS_NFE_ENABLE);
++ writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET);
++ }
++}
++
+ static int qm_vf_reset_prepare(struct hisi_qm *qm,
+ enum qm_stop_reason stop_reason)
+ {
+@@ -4083,6 +4106,8 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm)
+ return ret;
+ }
+
++ qm_dev_ecc_mbit_handle(qm);
++
+ /* PF obtains the information of VF by querying the register. */
+ qm_cmd_uninit(qm);
+
+@@ -4113,33 +4138,26 @@ static int qm_controller_reset_prepare(struct hisi_qm *qm)
+ return 0;
+ }
+
+-static void qm_dev_ecc_mbit_handle(struct hisi_qm *qm)
++static int qm_master_ooo_check(struct hisi_qm *qm)
+ {
+- u32 nfe_enb = 0;
++ u32 val;
++ int ret;
+
+- /* Kunpeng930 hardware automatically close master ooo when NFE occurs */
+- if (qm->ver >= QM_HW_V3)
+- return;
++ /* Check the ooo register of the device before resetting the device. */
++ writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN, qm->io_base + ACC_MASTER_GLOBAL_CTRL);
++ ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN,
++ val, (val == ACC_MASTER_TRANS_RETURN_RW),
++ POLL_PERIOD, POLL_TIMEOUT);
++ if (ret)
++ pci_warn(qm->pdev, "Bus lock! Please reset system.\n");
+
+- if (!qm->err_status.is_dev_ecc_mbit &&
+- qm->err_status.is_qm_ecc_mbit &&
+- qm->err_ini->close_axi_master_ooo) {
+- qm->err_ini->close_axi_master_ooo(qm);
+- } else if (qm->err_status.is_dev_ecc_mbit &&
+- !qm->err_status.is_qm_ecc_mbit &&
+- !qm->err_ini->close_axi_master_ooo) {
+- nfe_enb = readl(qm->io_base + QM_RAS_NFE_ENABLE);
+- writel(nfe_enb & QM_RAS_NFE_MBIT_DISABLE,
+- qm->io_base + QM_RAS_NFE_ENABLE);
+- writel(QM_ECC_MBIT, qm->io_base + QM_ABNORMAL_INT_SET);
+- }
++ return ret;
+ }
+
+-static int qm_soft_reset(struct hisi_qm *qm)
++static int qm_soft_reset_prepare(struct hisi_qm *qm)
+ {
+ struct pci_dev *pdev = qm->pdev;
+ int ret;
+- u32 val;
+
+ /* Ensure all doorbells and mailboxes received by QM */
+ ret = qm_check_req_recv(qm);
+@@ -4160,30 +4178,23 @@ static int qm_soft_reset(struct hisi_qm *qm)
+ return ret;
+ }
+
+- qm_dev_ecc_mbit_handle(qm);
+-
+- /* OOO register set and check */
+- writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN,
+- qm->io_base + ACC_MASTER_GLOBAL_CTRL);
+-
+- /* If bus lock, reset chip */
+- ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN,
+- val,
+- (val == ACC_MASTER_TRANS_RETURN_RW),
+- POLL_PERIOD, POLL_TIMEOUT);
+- if (ret) {
+- pci_emerg(pdev, "Bus lock! Please reset system.\n");
++ ret = qm_master_ooo_check(qm);
++ if (ret)
+ return ret;
+- }
+
+ if (qm->err_ini->close_sva_prefetch)
+ qm->err_ini->close_sva_prefetch(qm);
+
+ ret = qm_set_pf_mse(qm, false);
+- if (ret) {
++ if (ret)
+ pci_err(pdev, "Fails to disable pf MSE bit.\n");
+- return ret;
+- }
++
++ return ret;
++}
++
++static int qm_reset_device(struct hisi_qm *qm)
++{
++ struct pci_dev *pdev = qm->pdev;
+
+ /* The reset related sub-control registers are not in PCI BAR */
+ if (ACPI_HANDLE(&pdev->dev)) {
+@@ -4202,12 +4213,23 @@ static int qm_soft_reset(struct hisi_qm *qm)
+ pci_err(pdev, "Reset step %llu failed!\n", value);
+ return -EIO;
+ }
+- } else {
+- pci_err(pdev, "No reset method!\n");
+- return -EINVAL;
++
++ return 0;
+ }
+
+- return 0;
++ pci_err(pdev, "No reset method!\n");
++ return -EINVAL;
++}
++
++static int qm_soft_reset(struct hisi_qm *qm)
++{
++ int ret;
++
++ ret = qm_soft_reset_prepare(qm);
++ if (ret)
++ return ret;
++
++ return qm_reset_device(qm);
+ }
+
+ static int qm_vf_reset_done(struct hisi_qm *qm)
+@@ -5160,6 +5182,35 @@ static int qm_get_pci_res(struct hisi_qm *qm)
+ return ret;
+ }
+
++static int qm_clear_device(struct hisi_qm *qm)
++{
++ acpi_handle handle = ACPI_HANDLE(&qm->pdev->dev);
++ int ret;
++
++ if (qm->fun_type == QM_HW_VF)
++ return 0;
++
++ /* Device does not support reset, return */
++ if (!qm->err_ini->err_info_init)
++ return 0;
++ qm->err_ini->err_info_init(qm);
++
++ if (!handle)
++ return 0;
++
++ /* No reset method, return */
++ if (!acpi_has_method(handle, qm->err_info.acpi_rst))
++ return 0;
++
++ ret = qm_master_ooo_check(qm);
++ if (ret) {
++ writel(0x0, qm->io_base + ACC_MASTER_GLOBAL_CTRL);
++ return ret;
++ }
++
++ return qm_reset_device(qm);
++}
++
+ static int hisi_qm_pci_init(struct hisi_qm *qm)
+ {
+ struct pci_dev *pdev = qm->pdev;
+@@ -5189,8 +5240,14 @@ static int hisi_qm_pci_init(struct hisi_qm *qm)
+ goto err_get_pci_res;
+ }
+
++ ret = qm_clear_device(qm);
++ if (ret)
++ goto err_free_vectors;
++
+ return 0;
+
++err_free_vectors:
++ pci_free_irq_vectors(pdev);
+ err_get_pci_res:
+ qm_put_pci_res(qm);
+ err_disable_pcidev:
+@@ -5491,7 +5548,6 @@ static int qm_prepare_for_suspend(struct hisi_qm *qm)
+ {
+ struct pci_dev *pdev = qm->pdev;
+ int ret;
+- u32 val;
+
+ ret = qm->ops->set_msi(qm, false);
+ if (ret) {
+@@ -5499,18 +5555,9 @@ static int qm_prepare_for_suspend(struct hisi_qm *qm)
+ return ret;
+ }
+
+- /* shutdown OOO register */
+- writel(ACC_MASTER_GLOBAL_CTRL_SHUTDOWN,
+- qm->io_base + ACC_MASTER_GLOBAL_CTRL);
+-
+- ret = readl_relaxed_poll_timeout(qm->io_base + ACC_MASTER_TRANS_RETURN,
+- val,
+- (val == ACC_MASTER_TRANS_RETURN_RW),
+- POLL_PERIOD, POLL_TIMEOUT);
+- if (ret) {
+- pci_emerg(pdev, "Bus lock! Please reset system.\n");
++ ret = qm_master_ooo_check(qm);
++ if (ret)
+ return ret;
+- }
+
+ ret = qm_set_pf_mse(qm, false);
+ if (ret)
+diff --git a/drivers/crypto/hisilicon/sec2/sec_main.c b/drivers/crypto/hisilicon/sec2/sec_main.c
+index 75aad04ffe5eb9..c35533d8930b21 100644
+--- a/drivers/crypto/hisilicon/sec2/sec_main.c
++++ b/drivers/crypto/hisilicon/sec2/sec_main.c
+@@ -1065,9 +1065,6 @@ static int sec_pf_probe_init(struct sec_dev *sec)
+ struct hisi_qm *qm = &sec->qm;
+ int ret;
+
+- qm->err_ini = &sec_err_ini;
+- qm->err_ini->err_info_init(qm);
+-
+ ret = sec_set_user_domain_and_cache(qm);
+ if (ret)
+ return ret;
+@@ -1122,6 +1119,7 @@ static int sec_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
+ qm->qp_num = pf_q_num;
+ qm->debug.curr_qm_qp_num = pf_q_num;
+ qm->qm_list = &sec_devices;
++ qm->err_ini = &sec_err_ini;
+ if (pf_q_num_flag)
+ set_bit(QM_MODULE_PARAM, &qm->misc_ctl);
+ } else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) {
+@@ -1186,6 +1184,12 @@ static int sec_probe_init(struct sec_dev *sec)
+
+ static void sec_probe_uninit(struct hisi_qm *qm)
+ {
++ if (qm->fun_type == QM_HW_VF)
++ return;
++
++ sec_debug_regs_clear(qm);
++ sec_show_last_regs_uninit(qm);
++ sec_close_sva_prefetch(qm);
+ hisi_qm_dev_err_uninit(qm);
+ }
+
+@@ -1274,7 +1278,6 @@ static int sec_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+ sec_debugfs_exit(qm);
+ hisi_qm_stop(qm, QM_NORMAL);
+ err_probe_uninit:
+- sec_show_last_regs_uninit(qm);
+ sec_probe_uninit(qm);
+ err_qm_uninit:
+ sec_qm_uninit(qm);
+@@ -1296,11 +1299,6 @@ static void sec_remove(struct pci_dev *pdev)
+ sec_debugfs_exit(qm);
+
+ (void)hisi_qm_stop(qm, QM_NORMAL);
+-
+- if (qm->fun_type == QM_HW_PF)
+- sec_debug_regs_clear(qm);
+- sec_show_last_regs_uninit(qm);
+-
+ sec_probe_uninit(qm);
+
+ sec_qm_uninit(qm);
+diff --git a/drivers/crypto/hisilicon/zip/zip_main.c b/drivers/crypto/hisilicon/zip/zip_main.c
+index c94a7b20d07e6c..befef0b0e6bbe4 100644
+--- a/drivers/crypto/hisilicon/zip/zip_main.c
++++ b/drivers/crypto/hisilicon/zip/zip_main.c
+@@ -1149,8 +1149,6 @@ static int hisi_zip_pf_probe_init(struct hisi_zip *hisi_zip)
+
+ hisi_zip->ctrl = ctrl;
+ ctrl->hisi_zip = hisi_zip;
+- qm->err_ini = &hisi_zip_err_ini;
+- qm->err_ini->err_info_init(qm);
+
+ ret = hisi_zip_set_user_domain_and_cache(qm);
+ if (ret)
+@@ -1211,6 +1209,7 @@ static int hisi_zip_qm_init(struct hisi_qm *qm, struct pci_dev *pdev)
+ qm->qp_num = pf_q_num;
+ qm->debug.curr_qm_qp_num = pf_q_num;
+ qm->qm_list = &zip_devices;
++ qm->err_ini = &hisi_zip_err_ini;
+ if (pf_q_num_flag)
+ set_bit(QM_MODULE_PARAM, &qm->misc_ctl);
+ } else if (qm->fun_type == QM_HW_VF && qm->ver == QM_HW_V1) {
+@@ -1277,6 +1276,16 @@ static int hisi_zip_probe_init(struct hisi_zip *hisi_zip)
+ return 0;
+ }
+
++static void hisi_zip_probe_uninit(struct hisi_qm *qm)
++{
++ if (qm->fun_type == QM_HW_VF)
++ return;
++
++ hisi_zip_show_last_regs_uninit(qm);
++ hisi_zip_close_sva_prefetch(qm);
++ hisi_qm_dev_err_uninit(qm);
++}
++
+ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+ {
+ struct hisi_zip *hisi_zip;
+@@ -1303,7 +1312,7 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+
+ ret = hisi_qm_start(qm);
+ if (ret)
+- goto err_dev_err_uninit;
++ goto err_probe_uninit;
+
+ ret = hisi_zip_debugfs_init(qm);
+ if (ret)
+@@ -1342,9 +1351,8 @@ static int hisi_zip_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+ hisi_zip_debugfs_exit(qm);
+ hisi_qm_stop(qm, QM_NORMAL);
+
+-err_dev_err_uninit:
+- hisi_zip_show_last_regs_uninit(qm);
+- hisi_qm_dev_err_uninit(qm);
++err_probe_uninit:
++ hisi_zip_probe_uninit(qm);
+
+ err_qm_uninit:
+ hisi_zip_qm_uninit(qm);
+@@ -1366,8 +1374,7 @@ static void hisi_zip_remove(struct pci_dev *pdev)
+
+ hisi_zip_debugfs_exit(qm);
+ hisi_qm_stop(qm, QM_NORMAL);
+- hisi_zip_show_last_regs_uninit(qm);
+- hisi_qm_dev_err_uninit(qm);
++ hisi_zip_probe_uninit(qm);
+ hisi_zip_qm_uninit(qm);
+ }
+
+diff --git a/drivers/crypto/intel/iaa/iaa_crypto_main.c b/drivers/crypto/intel/iaa/iaa_crypto_main.c
+index e810d286ee8c42..237f8700007021 100644
+--- a/drivers/crypto/intel/iaa/iaa_crypto_main.c
++++ b/drivers/crypto/intel/iaa/iaa_crypto_main.c
+@@ -495,10 +495,10 @@ static void remove_device_compression_modes(struct iaa_device *iaa_device)
+ if (!device_mode)
+ continue;
+
+- free_device_compression_mode(iaa_device, device_mode);
+- iaa_device->compression_modes[i] = NULL;
+ if (iaa_compression_modes[i]->free)
+ iaa_compression_modes[i]->free(device_mode);
++ free_device_compression_mode(iaa_device, device_mode);
++ iaa_device->compression_modes[i] = NULL;
+ }
+ }
+
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
+index 8b10926cedbac2..e8c53bd76f1bd2 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
++++ b/drivers/crypto/intel/qat/qat_common/adf_gen4_hw_data.h
+@@ -83,7 +83,7 @@
+ #define ADF_WQM_CSR_RPRESETSTS(bank) (ADF_WQM_CSR_RPRESETCTL(bank) + 4)
+
+ /* Ring interrupt */
+-#define ADF_RP_INT_SRC_SEL_F_RISE_MASK BIT(2)
++#define ADF_RP_INT_SRC_SEL_F_RISE_MASK GENMASK(1, 0)
+ #define ADF_RP_INT_SRC_SEL_F_FALL_MASK GENMASK(2, 0)
+ #define ADF_RP_INT_SRC_SEL_RANGE_WIDTH 4
+ #define ADF_COALESCED_POLL_TIMEOUT_US (1 * USEC_PER_SEC)
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_init.c b/drivers/crypto/intel/qat/qat_common/adf_init.c
+index 74f0818c070348..55f1ff1e0b3225 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_init.c
++++ b/drivers/crypto/intel/qat/qat_common/adf_init.c
+@@ -323,6 +323,8 @@ static void adf_dev_stop(struct adf_accel_dev *accel_dev)
+ if (hw_data->stop_timer)
+ hw_data->stop_timer(accel_dev);
+
++ hw_data->disable_iov(accel_dev);
++
+ if (wait)
+ msleep(100);
+
+@@ -386,8 +388,6 @@ static void adf_dev_shutdown(struct adf_accel_dev *accel_dev)
+
+ adf_tl_shutdown(accel_dev);
+
+- hw_data->disable_iov(accel_dev);
+-
+ if (test_bit(ADF_STATUS_IRQ_ALLOCATED, &accel_dev->status)) {
+ hw_data->free_irq(accel_dev);
+ clear_bit(ADF_STATUS_IRQ_ALLOCATED, &accel_dev->status);
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c
+index 0e31f4b41844e0..0cee3b23dee90b 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c
++++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_pf_msg.c
+@@ -18,14 +18,17 @@ void adf_pf2vf_notify_restarting(struct adf_accel_dev *accel_dev)
+
+ dev_dbg(&GET_DEV(accel_dev), "pf2vf notify restarting\n");
+ for (i = 0, vf = accel_dev->pf.vf_info; i < num_vfs; i++, vf++) {
+- vf->restarting = false;
++ if (vf->init && vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK)
++ vf->restarting = true;
++ else
++ vf->restarting = false;
++
+ if (!vf->init)
+ continue;
++
+ if (adf_send_pf2vf_msg(accel_dev, i, msg))
+ dev_err(&GET_DEV(accel_dev),
+ "Failed to send restarting msg to VF%d\n", i);
+- else if (vf->vf_compat_ver >= ADF_PFVF_COMPAT_FALLBACK)
+- vf->restarting = true;
+ }
+ }
+
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.c b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.c
+index 1141258db4b65a..10c91e56d6be3b 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.c
++++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.c
+@@ -48,6 +48,20 @@ void adf_vf2pf_notify_shutdown(struct adf_accel_dev *accel_dev)
+ }
+ EXPORT_SYMBOL_GPL(adf_vf2pf_notify_shutdown);
+
++void adf_vf2pf_notify_restart_complete(struct adf_accel_dev *accel_dev)
++{
++ struct pfvf_message msg = { .type = ADF_VF2PF_MSGTYPE_RESTARTING_COMPLETE };
++
++ /* Check compatibility version */
++ if (accel_dev->vf.pf_compat_ver < ADF_PFVF_COMPAT_FALLBACK)
++ return;
++
++ if (adf_send_vf2pf_msg(accel_dev, msg))
++ dev_err(&GET_DEV(accel_dev),
++ "Failed to send Restarting complete event to PF\n");
++}
++EXPORT_SYMBOL_GPL(adf_vf2pf_notify_restart_complete);
++
+ int adf_vf2pf_request_version(struct adf_accel_dev *accel_dev)
+ {
+ u8 pf_version;
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.h b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.h
+index 71bc0e3f1d9335..d79340ab3134ff 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.h
++++ b/drivers/crypto/intel/qat/qat_common/adf_pfvf_vf_msg.h
+@@ -6,6 +6,7 @@
+ #if defined(CONFIG_PCI_IOV)
+ int adf_vf2pf_notify_init(struct adf_accel_dev *accel_dev);
+ void adf_vf2pf_notify_shutdown(struct adf_accel_dev *accel_dev);
++void adf_vf2pf_notify_restart_complete(struct adf_accel_dev *accel_dev);
+ int adf_vf2pf_request_version(struct adf_accel_dev *accel_dev);
+ int adf_vf2pf_get_capabilities(struct adf_accel_dev *accel_dev);
+ int adf_vf2pf_get_ring_to_svc(struct adf_accel_dev *accel_dev);
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_vf_isr.c b/drivers/crypto/intel/qat/qat_common/adf_vf_isr.c
+index cdbb2d687b1b0d..4ab9ac33151957 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_vf_isr.c
++++ b/drivers/crypto/intel/qat/qat_common/adf_vf_isr.c
+@@ -13,6 +13,7 @@
+ #include "adf_cfg.h"
+ #include "adf_cfg_strings.h"
+ #include "adf_cfg_common.h"
++#include "adf_pfvf_vf_msg.h"
+ #include "adf_transport_access_macros.h"
+ #include "adf_transport_internal.h"
+
+@@ -75,6 +76,7 @@ static void adf_dev_stop_async(struct work_struct *work)
+
+ /* Re-enable PF2VF interrupts */
+ adf_enable_pf2vf_interrupts(accel_dev);
++ adf_vf2pf_notify_restart_complete(accel_dev);
+ kfree(stop_data);
+ }
+
+diff --git a/drivers/crypto/n2_core.c b/drivers/crypto/n2_core.c
+index 59d472cb11e750..509aeffdedc69c 100644
+--- a/drivers/crypto/n2_core.c
++++ b/drivers/crypto/n2_core.c
+@@ -1357,6 +1357,7 @@ static int __n2_register_one_hmac(struct n2_ahash_alg *n2ahash)
+ ahash->setkey = n2_hmac_async_setkey;
+
+ base = &ahash->halg.base;
++ err = -EINVAL;
+ if (snprintf(base->cra_name, CRYPTO_MAX_ALG_NAME, "hmac(%s)",
+ p->child_alg) >= CRYPTO_MAX_ALG_NAME)
+ goto out_free_p;
+diff --git a/drivers/crypto/qcom-rng.c b/drivers/crypto/qcom-rng.c
+index c670d7d0c11ea8..6496b075a48d38 100644
+--- a/drivers/crypto/qcom-rng.c
++++ b/drivers/crypto/qcom-rng.c
+@@ -196,7 +196,7 @@ static int qcom_rng_probe(struct platform_device *pdev)
+ if (IS_ERR(rng->clk))
+ return PTR_ERR(rng->clk);
+
+- rng->of_data = (struct qcom_rng_of_data *)of_device_get_match_data(&pdev->dev);
++ rng->of_data = (struct qcom_rng_of_data *)device_get_match_data(&pdev->dev);
+
+ qcom_rng_dev = rng;
+ ret = crypto_register_rng(&qcom_rng_alg);
+@@ -247,7 +247,7 @@ static struct qcom_rng_of_data qcom_trng_of_data = {
+ };
+
+ static const struct acpi_device_id __maybe_unused qcom_rng_acpi_match[] = {
+- { .id = "QCOM8160", .driver_data = 1 },
++ { .id = "QCOM8160", .driver_data = (kernel_ulong_t)&qcom_prng_ee_of_data },
+ {}
+ };
+ MODULE_DEVICE_TABLE(acpi, qcom_rng_acpi_match);
+diff --git a/drivers/cxl/core/pci.c b/drivers/cxl/core/pci.c
+index 8567dd11eaac74..205085ccf12c30 100644
+--- a/drivers/cxl/core/pci.c
++++ b/drivers/cxl/core/pci.c
+@@ -390,10 +390,6 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
+
+ size |= temp & CXL_DVSEC_MEM_SIZE_LOW_MASK;
+ if (!size) {
+- info->dvsec_range[i] = (struct range) {
+- .start = 0,
+- .end = CXL_RESOURCE_NONE,
+- };
+ continue;
+ }
+
+@@ -411,12 +407,10 @@ int cxl_dvsec_rr_decode(struct device *dev, int d,
+
+ base |= temp & CXL_DVSEC_MEM_BASE_LOW_MASK;
+
+- info->dvsec_range[i] = (struct range) {
++ info->dvsec_range[ranges++] = (struct range) {
+ .start = base,
+ .end = base + size - 1
+ };
+-
+- ranges++;
+ }
+
+ info->ranges = ranges;
+diff --git a/drivers/edac/igen6_edac.c b/drivers/edac/igen6_edac.c
+index dbe9fe5f2ca6c3..594408aa934bf5 100644
+--- a/drivers/edac/igen6_edac.c
++++ b/drivers/edac/igen6_edac.c
+@@ -311,7 +311,7 @@ static u64 ehl_err_addr_to_imc_addr(u64 eaddr, int mc)
+ if (igen6_tom <= _4GB)
+ return eaddr + igen6_tolud - _4GB;
+
+- if (eaddr < _4GB)
++ if (eaddr >= igen6_tom)
+ return eaddr + igen6_tolud - igen6_tom;
+
+ return eaddr;
+diff --git a/drivers/edac/synopsys_edac.c b/drivers/edac/synopsys_edac.c
+index ea7a9a342dd30b..d7416166fd8a42 100644
+--- a/drivers/edac/synopsys_edac.c
++++ b/drivers/edac/synopsys_edac.c
+@@ -10,6 +10,7 @@
+ #include <linux/module.h>
+ #include <linux/platform_device.h>
+ #include <linux/spinlock.h>
++#include <linux/sizes.h>
+ #include <linux/interrupt.h>
+ #include <linux/of.h>
+
+@@ -337,6 +338,7 @@ struct synps_edac_priv {
+ * @get_mtype: Get mtype.
+ * @get_dtype: Get dtype.
+ * @get_ecc_state: Get ECC state.
++ * @get_mem_info: Get EDAC memory info
+ * @quirks: To differentiate IPs.
+ */
+ struct synps_platform_data {
+@@ -344,6 +346,9 @@ struct synps_platform_data {
+ enum mem_type (*get_mtype)(const void __iomem *base);
+ enum dev_type (*get_dtype)(const void __iomem *base);
+ bool (*get_ecc_state)(void __iomem *base);
++#ifdef CONFIG_EDAC_DEBUG
++ u64 (*get_mem_info)(struct synps_edac_priv *priv);
++#endif
+ int quirks;
+ };
+
+@@ -402,6 +407,25 @@ static int zynq_get_error_info(struct synps_edac_priv *priv)
+ return 0;
+ }
+
++#ifdef CONFIG_EDAC_DEBUG
++/**
++ * zynqmp_get_mem_info - Get the current memory info.
++ * @priv: DDR memory controller private instance data.
++ *
++ * Return: host interface address.
++ */
++static u64 zynqmp_get_mem_info(struct synps_edac_priv *priv)
++{
++ u64 hif_addr = 0, linear_addr;
++
++ linear_addr = priv->poison_addr;
++ if (linear_addr >= SZ_32G)
++ linear_addr = linear_addr - SZ_32G + SZ_2G;
++ hif_addr = linear_addr >> 3;
++ return hif_addr;
++}
++#endif
++
+ /**
+ * zynqmp_get_error_info - Get the current ECC error info.
+ * @priv: DDR memory controller private instance data.
+@@ -922,6 +946,9 @@ static const struct synps_platform_data zynqmp_edac_def = {
+ .get_mtype = zynqmp_get_mtype,
+ .get_dtype = zynqmp_get_dtype,
+ .get_ecc_state = zynqmp_get_ecc_state,
++#ifdef CONFIG_EDAC_DEBUG
++ .get_mem_info = zynqmp_get_mem_info,
++#endif
+ .quirks = (DDR_ECC_INTR_SUPPORT
+ #ifdef CONFIG_EDAC_DEBUG
+ | DDR_ECC_DATA_POISON_SUPPORT
+@@ -975,10 +1002,16 @@ MODULE_DEVICE_TABLE(of, synps_edac_match);
+ static void ddr_poison_setup(struct synps_edac_priv *priv)
+ {
+ int col = 0, row = 0, bank = 0, bankgrp = 0, rank = 0, regval;
++ const struct synps_platform_data *p_data;
+ int index;
+ ulong hif_addr = 0;
+
+- hif_addr = priv->poison_addr >> 3;
++ p_data = priv->p_data;
++
++ if (p_data->get_mem_info)
++ hif_addr = p_data->get_mem_info(priv);
++ else
++ hif_addr = priv->poison_addr >> 3;
+
+ for (index = 0; index < DDR_MAX_ROW_SHIFT; index++) {
+ if (priv->row_shift[index])
+diff --git a/drivers/firewire/core-cdev.c b/drivers/firewire/core-cdev.c
+index 9a7dc90330a351..a888a001bedb15 100644
+--- a/drivers/firewire/core-cdev.c
++++ b/drivers/firewire/core-cdev.c
+@@ -599,11 +599,11 @@ static void complete_transaction(struct fw_card *card, int rcode, u32 request_ts
+ queue_event(client, &e->event, rsp, sizeof(*rsp) + rsp->length, NULL, 0);
+
+ break;
++ }
+ default:
+ WARN_ON(1);
+ break;
+ }
+- }
+
+ /* Drop the idr's reference */
+ client_put(client);
+diff --git a/drivers/firmware/arm_scmi/optee.c b/drivers/firmware/arm_scmi/optee.c
+index 4e7944b91e3857..0c8908d3b1d678 100644
+--- a/drivers/firmware/arm_scmi/optee.c
++++ b/drivers/firmware/arm_scmi/optee.c
+@@ -473,6 +473,13 @@ static int scmi_optee_chan_free(int id, void *p, void *data)
+ struct scmi_chan_info *cinfo = p;
+ struct scmi_optee_channel *channel = cinfo->transport_info;
+
++ /*
++ * Different protocols might share the same chan info, so a previous
++ * call might have already freed the structure.
++ */
++ if (!channel)
++ return 0;
++
+ mutex_lock(&scmi_optee_private->mu);
+ list_del(&channel->link);
+ mutex_unlock(&scmi_optee_private->mu);
+diff --git a/drivers/firmware/efi/libstub/tpm.c b/drivers/firmware/efi/libstub/tpm.c
+index df3182f2e63a56..1fd6823248ab6e 100644
+--- a/drivers/firmware/efi/libstub/tpm.c
++++ b/drivers/firmware/efi/libstub/tpm.c
+@@ -96,7 +96,7 @@ static void efi_retrieve_tcg2_eventlog(int version, efi_physical_addr_t log_loca
+ }
+
+ /* Allocate space for the logs and copy them. */
+- status = efi_bs_call(allocate_pool, EFI_LOADER_DATA,
++ status = efi_bs_call(allocate_pool, EFI_ACPI_RECLAIM_MEMORY,
+ sizeof(*log_tbl) + log_size, (void **)&log_tbl);
+
+ if (status != EFI_SUCCESS) {
+diff --git a/drivers/firmware/qcom/qcom_scm.c b/drivers/firmware/qcom/qcom_scm.c
+index 68f4df7e6c3c7f..77dd831febf5bc 100644
+--- a/drivers/firmware/qcom/qcom_scm.c
++++ b/drivers/firmware/qcom/qcom_scm.c
+@@ -1875,14 +1875,12 @@ static int qcom_scm_probe(struct platform_device *pdev)
+ * will cause the boot stages to enter download mode, unless
+ * disabled below by a clean shutdown/reboot.
+ */
+- if (download_mode)
+- qcom_scm_set_download_mode(true);
+-
++ qcom_scm_set_download_mode(download_mode);
+
+ /*
+ * Disable SDI if indicated by DT that it is enabled by default.
+ */
+- if (of_property_read_bool(pdev->dev.of_node, "qcom,sdi-enabled"))
++ if (of_property_read_bool(pdev->dev.of_node, "qcom,sdi-enabled") || !download_mode)
+ qcom_scm_disable_sdi();
+
+ /*
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+index 0f7106066480ea..3fdbc10aebce1d 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+@@ -902,10 +902,12 @@ amdgpu_vm_tlb_flush(struct amdgpu_vm_update_params *params,
+ {
+ struct amdgpu_vm *vm = params->vm;
+
+- if (!fence || !*fence)
++ tlb_cb->vm = vm;
++ if (!fence || !*fence) {
++ amdgpu_vm_tlb_seq_cb(NULL, &tlb_cb->cb);
+ return;
++ }
+
+- tlb_cb->vm = vm;
+ if (!dma_fence_add_callback(*fence, &tlb_cb->cb,
+ amdgpu_vm_tlb_seq_cb)) {
+ dma_fence_put(vm->last_tlb_flush);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+index fb2b394bb9c555..6e9eeaeb3de1dd 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgv_sriovmsg.h
+@@ -213,7 +213,7 @@ struct amd_sriov_msg_pf2vf_info {
+ uint32_t gpu_capacity;
+ /* reserved */
+ uint32_t reserved[256 - AMD_SRIOV_MSG_PF2VF_INFO_FILLED_SIZE];
+-};
++} __packed;
+
+ struct amd_sriov_msg_vf2pf_info_header {
+ /* the total structure size in byte */
+@@ -273,7 +273,7 @@ struct amd_sriov_msg_vf2pf_info {
+ uint32_t mes_info_size;
+ /* reserved */
+ uint32_t reserved[256 - AMD_SRIOV_MSG_VF2PF_INFO_FILLED_SIZE];
+-};
++} __packed;
+
+ /* mailbox message send from guest to host */
+ enum amd_sriov_mailbox_request_message {
+diff --git a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+index 25feab188dfe69..ebf83fee43bb99 100644
+--- a/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
++++ b/drivers/gpu/drm/amd/amdgpu/atombios_encoders.c
+@@ -2065,26 +2065,29 @@ amdgpu_atombios_encoder_get_lcd_info(struct amdgpu_encoder *encoder)
+ fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record;
+ if (fake_edid_record->ucFakeEDIDLength) {
+ struct edid *edid;
+- int edid_size =
+- max((int)EDID_LENGTH, (int)fake_edid_record->ucFakeEDIDLength);
+- edid = kmalloc(edid_size, GFP_KERNEL);
++ int edid_size;
++
++ if (fake_edid_record->ucFakeEDIDLength == 128)
++ edid_size = fake_edid_record->ucFakeEDIDLength;
++ else
++ edid_size = fake_edid_record->ucFakeEDIDLength * 128;
++ edid = kmemdup(&fake_edid_record->ucFakeEDIDString[0],
++ edid_size, GFP_KERNEL);
+ if (edid) {
+- memcpy((u8 *)edid, (u8 *)&fake_edid_record->ucFakeEDIDString[0],
+- fake_edid_record->ucFakeEDIDLength);
+-
+ if (drm_edid_is_valid(edid)) {
+ adev->mode_info.bios_hardcoded_edid = edid;
+ adev->mode_info.bios_hardcoded_edid_size = edid_size;
+- } else
++ } else {
+ kfree(edid);
++ }
+ }
++ record += struct_size(fake_edid_record,
++ ucFakeEDIDString,
++ edid_size);
++ } else {
++ /* empty fake edid record must be 3 bytes long */
++ record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1;
+ }
+- record += fake_edid_record->ucFakeEDIDLength ?
+- struct_size(fake_edid_record,
+- ucFakeEDIDString,
+- fake_edid_record->ucFakeEDIDLength) :
+- /* empty fake edid record must be 3 bytes long */
+- sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1;
+ break;
+ case LCD_PANEL_RESOLUTION_RECORD_TYPE:
+ panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record;
+diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+index e1a66d585f5e99..44b277c55de4a5 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+@@ -155,7 +155,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
+ int api_status_off)
+ {
+ union MESAPI__QUERY_MES_STATUS mes_status_pkt;
+- signed long timeout = 3000000; /* 3000 ms */
++ signed long timeout = 2100000; /* 2100 ms */
+ struct amdgpu_device *adev = mes->adev;
+ struct amdgpu_ring *ring = &mes->ring;
+ struct MES_API_STATUS *api_status;
+diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+index 30e80c6f11ed68..68ac91d28ded0f 100644
+--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
++++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+@@ -1353,170 +1353,6 @@ static void vcn_v4_0_5_unified_ring_set_wptr(struct amdgpu_ring *ring)
+ }
+ }
+
+-static int vcn_v4_0_5_limit_sched(struct amdgpu_cs_parser *p,
+- struct amdgpu_job *job)
+-{
+- struct drm_gpu_scheduler **scheds;
+-
+- /* The create msg must be in the first IB submitted */
+- if (atomic_read(&job->base.entity->fence_seq))
+- return -EINVAL;
+-
+- /* if VCN0 is harvested, we can't support AV1 */
+- if (p->adev->vcn.harvest_config & AMDGPU_VCN_HARVEST_VCN0)
+- return -EINVAL;
+-
+- scheds = p->adev->gpu_sched[AMDGPU_HW_IP_VCN_ENC]
+- [AMDGPU_RING_PRIO_0].sched;
+- drm_sched_entity_modify_sched(job->base.entity, scheds, 1);
+- return 0;
+-}
+-
+-static int vcn_v4_0_5_dec_msg(struct amdgpu_cs_parser *p, struct amdgpu_job *job,
+- uint64_t addr)
+-{
+- struct ttm_operation_ctx ctx = { false, false };
+- struct amdgpu_bo_va_mapping *map;
+- uint32_t *msg, num_buffers;
+- struct amdgpu_bo *bo;
+- uint64_t start, end;
+- unsigned int i;
+- void *ptr;
+- int r;
+-
+- addr &= AMDGPU_GMC_HOLE_MASK;
+- r = amdgpu_cs_find_mapping(p, addr, &bo, &map);
+- if (r) {
+- DRM_ERROR("Can't find BO for addr 0x%08llx\n", addr);
+- return r;
+- }
+-
+- start = map->start * AMDGPU_GPU_PAGE_SIZE;
+- end = (map->last + 1) * AMDGPU_GPU_PAGE_SIZE;
+- if (addr & 0x7) {
+- DRM_ERROR("VCN messages must be 8 byte aligned!\n");
+- return -EINVAL;
+- }
+-
+- bo->flags |= AMDGPU_GEM_CREATE_CPU_ACCESS_REQUIRED;
+- amdgpu_bo_placement_from_domain(bo, bo->allowed_domains);
+- r = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+- if (r) {
+- DRM_ERROR("Failed validating the VCN message BO (%d)!\n", r);
+- return r;
+- }
+-
+- r = amdgpu_bo_kmap(bo, &ptr);
+- if (r) {
+- DRM_ERROR("Failed mapping the VCN message (%d)!\n", r);
+- return r;
+- }
+-
+- msg = ptr + addr - start;
+-
+- /* Check length */
+- if (msg[1] > end - addr) {
+- r = -EINVAL;
+- goto out;
+- }
+-
+- if (msg[3] != RDECODE_MSG_CREATE)
+- goto out;
+-
+- num_buffers = msg[2];
+- for (i = 0, msg = &msg[6]; i < num_buffers; ++i, msg += 4) {
+- uint32_t offset, size, *create;
+-
+- if (msg[0] != RDECODE_MESSAGE_CREATE)
+- continue;
+-
+- offset = msg[1];
+- size = msg[2];
+-
+- if (offset + size > end) {
+- r = -EINVAL;
+- goto out;
+- }
+-
+- create = ptr + addr + offset - start;
+-
+- /* H264, HEVC and VP9 can run on any instance */
+- if (create[0] == 0x7 || create[0] == 0x10 || create[0] == 0x11)
+- continue;
+-
+- r = vcn_v4_0_5_limit_sched(p, job);
+- if (r)
+- goto out;
+- }
+-
+-out:
+- amdgpu_bo_kunmap(bo);
+- return r;
+-}
+-
+-#define RADEON_VCN_ENGINE_TYPE_ENCODE (0x00000002)
+-#define RADEON_VCN_ENGINE_TYPE_DECODE (0x00000003)
+-
+-#define RADEON_VCN_ENGINE_INFO (0x30000001)
+-#define RADEON_VCN_ENGINE_INFO_MAX_OFFSET 16
+-
+-#define RENCODE_ENCODE_STANDARD_AV1 2
+-#define RENCODE_IB_PARAM_SESSION_INIT 0x00000003
+-#define RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET 64
+-
+-/* return the offset in ib if id is found, -1 otherwise
+- * to speed up the searching we only search upto max_offset
+- */
+-static int vcn_v4_0_5_enc_find_ib_param(struct amdgpu_ib *ib, uint32_t id, int max_offset)
+-{
+- int i;
+-
+- for (i = 0; i < ib->length_dw && i < max_offset && ib->ptr[i] >= 8; i += ib->ptr[i]/4) {
+- if (ib->ptr[i + 1] == id)
+- return i;
+- }
+- return -1;
+-}
+-
+-static int vcn_v4_0_5_ring_patch_cs_in_place(struct amdgpu_cs_parser *p,
+- struct amdgpu_job *job,
+- struct amdgpu_ib *ib)
+-{
+- struct amdgpu_ring *ring = amdgpu_job_ring(job);
+- struct amdgpu_vcn_decode_buffer *decode_buffer;
+- uint64_t addr;
+- uint32_t val;
+- int idx;
+-
+- /* The first instance can decode anything */
+- if (!ring->me)
+- return 0;
+-
+- /* RADEON_VCN_ENGINE_INFO is at the top of ib block */
+- idx = vcn_v4_0_5_enc_find_ib_param(ib, RADEON_VCN_ENGINE_INFO,
+- RADEON_VCN_ENGINE_INFO_MAX_OFFSET);
+- if (idx < 0) /* engine info is missing */
+- return 0;
+-
+- val = amdgpu_ib_get_value(ib, idx + 2); /* RADEON_VCN_ENGINE_TYPE */
+- if (val == RADEON_VCN_ENGINE_TYPE_DECODE) {
+- decode_buffer = (struct amdgpu_vcn_decode_buffer *)&ib->ptr[idx + 6];
+-
+- if (!(decode_buffer->valid_buf_flag & 0x1))
+- return 0;
+-
+- addr = ((u64)decode_buffer->msg_buffer_address_hi) << 32 |
+- decode_buffer->msg_buffer_address_lo;
+- return vcn_v4_0_5_dec_msg(p, job, addr);
+- } else if (val == RADEON_VCN_ENGINE_TYPE_ENCODE) {
+- idx = vcn_v4_0_5_enc_find_ib_param(ib, RENCODE_IB_PARAM_SESSION_INIT,
+- RENCODE_IB_PARAM_SESSION_INIT_MAX_OFFSET);
+- if (idx >= 0 && ib->ptr[idx + 2] == RENCODE_ENCODE_STANDARD_AV1)
+- return vcn_v4_0_5_limit_sched(p, job);
+- }
+- return 0;
+-}
+-
+ static const struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = {
+ .type = AMDGPU_RING_TYPE_VCN_ENC,
+ .align_mask = 0x3f,
+@@ -1524,7 +1360,6 @@ static const struct amdgpu_ring_funcs vcn_v4_0_5_unified_ring_vm_funcs = {
+ .get_rptr = vcn_v4_0_5_unified_ring_get_rptr,
+ .get_wptr = vcn_v4_0_5_unified_ring_get_wptr,
+ .set_wptr = vcn_v4_0_5_unified_ring_set_wptr,
+- .patch_cs_in_place = vcn_v4_0_5_ring_patch_cs_in_place,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 3 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 4 +
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+index 27e641f176289a..3541d154cc8d06 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+@@ -4149,6 +4149,7 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
+
+ #define AMDGPU_DM_DEFAULT_MIN_BACKLIGHT 12
+ #define AMDGPU_DM_DEFAULT_MAX_BACKLIGHT 255
++#define AMDGPU_DM_MIN_SPREAD ((AMDGPU_DM_DEFAULT_MAX_BACKLIGHT - AMDGPU_DM_DEFAULT_MIN_BACKLIGHT) / 2)
+ #define AUX_BL_DEFAULT_TRANSITION_TIME_MS 50
+
+ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm,
+@@ -4163,6 +4164,21 @@ static void amdgpu_dm_update_backlight_caps(struct amdgpu_display_manager *dm,
+ return;
+
+ amdgpu_acpi_get_backlight_caps(&caps);
++
++ /* validate the firmware value is sane */
++ if (caps.caps_valid) {
++ int spread = caps.max_input_signal - caps.min_input_signal;
++
++ if (caps.max_input_signal > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT ||
++ caps.min_input_signal < AMDGPU_DM_DEFAULT_MIN_BACKLIGHT ||
++ spread > AMDGPU_DM_DEFAULT_MAX_BACKLIGHT ||
++ spread < AMDGPU_DM_MIN_SPREAD) {
++ DRM_DEBUG_KMS("DM: Invalid backlight caps: min=%d, max=%d\n",
++ caps.min_input_signal, caps.max_input_signal);
++ caps.caps_valid = false;
++ }
++ }
++
+ if (caps.caps_valid) {
+ dm->backlight_caps[bl_idx].caps_valid = true;
+ if (caps.aux_support)
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+index b50010ed763327..9a620773141682 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+@@ -251,7 +251,7 @@ static bool validate_dsc_caps_on_connector(struct amdgpu_dm_connector *aconnecto
+ aconnector->dsc_aux = &aconnector->mst_root->dm_dp_aux.aux;
+
+ /* synaptics cascaded MST hub case */
+- if (!aconnector->dsc_aux && is_synaptics_cascaded_panamera(aconnector->dc_link, port))
++ if (is_synaptics_cascaded_panamera(aconnector->dc_link, port))
+ aconnector->dsc_aux = port->mgr->aux;
+
+ if (!aconnector->dsc_aux)
+@@ -1111,7 +1111,7 @@ static int compute_mst_dsc_configs_for_link(struct drm_atomic_state *state,
+ params[count].num_slices_v = aconnector->dsc_settings.dsc_num_slices_v;
+ params[count].bpp_overwrite = aconnector->dsc_settings.dsc_bits_per_pixel;
+ params[count].compression_possible = stream->sink->dsc_caps.dsc_dec_caps.is_dsc_supported;
+- dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy);
++ dc_dsc_get_policy_for_timing(params[count].timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link));
+ if (!dc_dsc_compute_bandwidth_range(
+ stream->sink->ctx->dc->res_pool->dscs[0],
+ stream->sink->ctx->dc->debug.dsc_min_slice_height_override,
+@@ -1264,6 +1264,9 @@ static bool is_dsc_need_re_compute(
+ }
+ }
+
++ if (new_stream_on_link_num == 0)
++ return false;
++
+ if (new_stream_on_link_num == 0)
+ return false;
+
+@@ -1583,7 +1586,7 @@ static bool is_dsc_common_config_possible(struct dc_stream_state *stream,
+ {
+ struct dc_dsc_policy dsc_policy = {0};
+
+- dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy);
++ dc_dsc_get_policy_for_timing(&stream->timing, 0, &dsc_policy, dc_link_get_highest_encoding_format(stream->link));
+ dc_dsc_compute_bandwidth_range(stream->sink->ctx->dc->res_pool->dscs[0],
+ stream->sink->ctx->dc->debug.dsc_min_slice_height_override,
+ dsc_policy.min_target_bpp * 16,
+diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+index 6c9b4e6491a5e4..985e847f958032 100644
+--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
++++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn35/dcn35_clk_mgr.c
+@@ -1149,6 +1149,12 @@ void dcn35_clk_mgr_construct(
+ ctx->dc->debug.disable_dpp_power_gate = false;
+ ctx->dc->debug.disable_hubp_power_gate = false;
+ ctx->dc->debug.disable_dsc_power_gate = false;
++
++ /* Disable dynamic IPS2 in older PMFW (93.12) for Z8 interop. */
++ if (ctx->dc->config.disable_ips == DMUB_IPS_ENABLE &&
++ ctx->dce_version == DCN_VERSION_3_5 &&
++ ((clk_mgr->base.smu_ver & 0x00FFFFFF) <= 0x005d0c00))
++ ctx->dc->config.disable_ips = DMUB_IPS_RCG_IN_ACTIVE_IPS2_IN_OFF;
+ } else {
+ /*let's reset the config control flag*/
+ ctx->dc->config.disable_ips = DMUB_IPS_DISABLE_ALL; /*pmfw not support it, disable it all*/
+diff --git a/drivers/gpu/drm/amd/display/dc/dc_dsc.h b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
+index fe3078b8789ef1..01c07545ef6b47 100644
+--- a/drivers/gpu/drm/amd/display/dc/dc_dsc.h
++++ b/drivers/gpu/drm/amd/display/dc/dc_dsc.h
+@@ -100,7 +100,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps(
+ */
+ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing,
+ uint32_t max_target_bpp_limit_override_x16,
+- struct dc_dsc_policy *policy);
++ struct dc_dsc_policy *policy,
++ const enum dc_link_encoding_format link_encoding);
+
+ void dc_dsc_policy_set_max_target_bpp_limit(uint32_t limit);
+
+diff --git a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+index 150ef23440a2c1..f8c1e1ca678bf1 100644
+--- a/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
++++ b/drivers/gpu/drm/amd/display/dc/dsc/dc_dsc.c
+@@ -883,7 +883,7 @@ static bool setup_dsc_config(
+
+ memset(dsc_cfg, 0, sizeof(struct dc_dsc_config));
+
+- dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy);
++ dc_dsc_get_policy_for_timing(timing, options->max_target_bpp_limit_override_x16, &policy, link_encoding);
+ pic_width = timing->h_addressable + timing->h_border_left + timing->h_border_right;
+ pic_height = timing->v_addressable + timing->v_border_top + timing->v_border_bottom;
+
+@@ -1156,7 +1156,8 @@ uint32_t dc_dsc_stream_bandwidth_overhead_in_kbps(
+
+ void dc_dsc_get_policy_for_timing(const struct dc_crtc_timing *timing,
+ uint32_t max_target_bpp_limit_override_x16,
+- struct dc_dsc_policy *policy)
++ struct dc_dsc_policy *policy,
++ const enum dc_link_encoding_format link_encoding)
+ {
+ uint32_t bpc = 0;
+
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+index 0d3ea291eeee18..e9e9f80a02a775 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dce110/dce110_hwseq.c
+@@ -57,6 +57,7 @@
+ #include "panel_cntl.h"
+ #include "dc_state_priv.h"
+ #include "dpcd_defs.h"
++#include "dsc.h"
+ /* include DCE11 register header files */
+ #include "dce/dce_11_0_d.h"
+ #include "dce/dce_11_0_sh_mask.h"
+@@ -1768,6 +1769,48 @@ static void get_edp_links_with_sink(
+ }
+ }
+
++static void clean_up_dsc_blocks(struct dc *dc)
++{
++ struct display_stream_compressor *dsc = NULL;
++ struct timing_generator *tg = NULL;
++ struct stream_encoder *se = NULL;
++ struct dccg *dccg = dc->res_pool->dccg;
++ struct pg_cntl *pg_cntl = dc->res_pool->pg_cntl;
++ int i;
++
++ if (dc->ctx->dce_version != DCN_VERSION_3_5 &&
++ dc->ctx->dce_version != DCN_VERSION_3_51)
++ return;
++
++ for (i = 0; i < dc->res_pool->res_cap->num_dsc; i++) {
++ struct dcn_dsc_state s = {0};
++
++ dsc = dc->res_pool->dscs[i];
++ dsc->funcs->dsc_read_state(dsc, &s);
++ if (s.dsc_fw_en) {
++ /* disable DSC in OPTC */
++ if (i < dc->res_pool->timing_generator_count) {
++ tg = dc->res_pool->timing_generators[i];
++ tg->funcs->set_dsc_config(tg, OPTC_DSC_DISABLED, 0, 0);
++ }
++ /* disable DSC in stream encoder */
++ if (i < dc->res_pool->stream_enc_count) {
++ se = dc->res_pool->stream_enc[i];
++ se->funcs->dp_set_dsc_config(se, OPTC_DSC_DISABLED, 0, 0);
++ se->funcs->dp_set_dsc_pps_info_packet(se, false, NULL, true);
++ }
++ /* disable DSC block */
++ if (dccg->funcs->set_ref_dscclk)
++ dccg->funcs->set_ref_dscclk(dccg, dsc->inst);
++ dsc->funcs->dsc_disable(dsc);
++
++ /* power down DSC */
++ if (pg_cntl != NULL)
++ pg_cntl->funcs->dsc_pg_control(pg_cntl, dsc->inst, false);
++ }
++ }
++}
++
+ /*
+ * When ASIC goes from VBIOS/VGA mode to driver/accelerated mode we need:
+ * 1. Power down all DC HW blocks
+@@ -1852,6 +1895,13 @@ void dce110_enable_accelerated_mode(struct dc *dc, struct dc_state *context)
+ clk_mgr_exit_optimized_pwr_state(dc, dc->clk_mgr);
+
+ power_down_all_hw_blocks(dc);
++
++ /* DSC could be enabled on eDP during VBIOS post.
++ * To clean up dsc blocks if eDP is in link but not active.
++ */
++ if (edp_link_with_sink && (edp_stream_num == 0))
++ clean_up_dsc_blocks(dc);
++
+ disable_vga_and_power_gate_all_controllers(dc);
+ if (edp_link_with_sink && !keep_edp_vdd_on)
+ dc->hwss.edp_power_control(edp_link_with_sink, false);
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+index 4c470615330509..05c5d4f04e1bd8 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+@@ -395,7 +395,11 @@ bool dcn30_set_output_transfer_func(struct dc *dc,
+ }
+ }
+
+- mpc->funcs->set_output_gamma(mpc, mpcc_id, params);
++ if (mpc->funcs->set_output_gamma)
++ mpc->funcs->set_output_gamma(mpc, mpcc_id, params);
++ else
++ DC_LOG_ERROR("%s: set_output_gamma function pointer is NULL.\n", __func__);
++
+ return ret;
+ }
+
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+index b8e884368dc6e5..5fc377f51f5621 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn32/dcn32_hwseq.c
+@@ -991,6 +991,20 @@ static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
+ struct dsc_config dsc_cfg;
+ struct dsc_optc_config dsc_optc_cfg = {0};
+ enum optc_dsc_mode optc_dsc_mode;
++ struct dcn_dsc_state dsc_state = {0};
++
++ if (!dsc) {
++ DC_LOG_DSC("DSC is NULL for tg instance %d:", pipe_ctx->stream_res.tg->inst);
++ return;
++ }
++
++ if (dsc->funcs->dsc_read_state) {
++ dsc->funcs->dsc_read_state(dsc, &dsc_state);
++ if (!dsc_state.dsc_fw_en) {
++ DC_LOG_DSC("DSC has been disabled for tg instance %d:", pipe_ctx->stream_res.tg->inst);
++ return;
++ }
++ }
+
+ /* Enable DSC hw block */
+ dsc_cfg.pic_width = (stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt;
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+index 4f0e9e0f701dd2..900dfc0f275373 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+@@ -375,7 +375,20 @@ static void update_dsc_on_stream(struct pipe_ctx *pipe_ctx, bool enable)
+ struct dsc_config dsc_cfg;
+ struct dsc_optc_config dsc_optc_cfg = {0};
+ enum optc_dsc_mode optc_dsc_mode;
++ struct dcn_dsc_state dsc_state = {0};
+
++ if (!dsc) {
++ DC_LOG_DSC("DSC is NULL for tg instance %d:", pipe_ctx->stream_res.tg->inst);
++ return;
++ }
++
++ if (dsc->funcs->dsc_read_state) {
++ dsc->funcs->dsc_read_state(dsc, &dsc_state);
++ if (!dsc_state.dsc_fw_en) {
++ DC_LOG_DSC("DSC has been disabled for tg instance %d:", pipe_ctx->stream_res.tg->inst);
++ return;
++ }
++ }
+ /* Enable DSC hw block */
+ dsc_cfg.pic_width = (stream->timing.h_addressable + stream->timing.h_border_left + stream->timing.h_border_right) / opp_cnt;
+ dsc_cfg.pic_height = stream->timing.v_addressable + stream->timing.v_border_top + stream->timing.v_border_bottom;
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+index 915d68cc04e9c2..66b73edda7b6dd 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+@@ -2150,6 +2150,7 @@ static bool dcn35_resource_construct(
+ dc->dml2_options.max_segments_per_hubp = 24;
+
+ dc->dml2_options.det_segment_size = DCN3_2_DET_SEG_SIZE;/*todo*/
++ dc->dml2_options.override_det_buffer_size_kbytes = true;
+
+ if (dc->config.sdpif_request_limit_words_per_umc == 0)
+ dc->config.sdpif_request_limit_words_per_umc = 16;/*todo*/
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+index b7bd0f36125a4d..987c3927b11851 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+@@ -736,7 +736,7 @@ static const struct dc_debug_options debug_defaults_drv = {
+ .hdmichar = true,
+ .dpstream = true,
+ .symclk32_se = true,
+- .symclk32_le = true,
++ .symclk32_le = false,
+ .symclk_fe = true,
+ .physymclk = true,
+ .dpiasymclk = true,
+@@ -2132,6 +2132,7 @@ static bool dcn351_resource_construct(
+
+ dc->dml2_options.max_segments_per_hubp = 24;
+ dc->dml2_options.det_segment_size = DCN3_2_DET_SEG_SIZE;/*todo*/
++ dc->dml2_options.override_det_buffer_size_kbytes = true;
+
+ if (dc->config.sdpif_request_limit_words_per_umc == 0)
+ dc->config.sdpif_request_limit_words_per_umc = 16;/*todo*/
+diff --git a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+index d09627c15b9c22..2b8d09bb0cc158 100644
+--- a/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
++++ b/drivers/gpu/drm/amd/display/modules/freesync/freesync.c
+@@ -134,7 +134,7 @@ unsigned int mod_freesync_calc_v_total_from_refresh(
+
+ v_total = div64_u64(div64_u64(((unsigned long long)(
+ frame_duration_in_ns) * (stream->timing.pix_clk_100hz / 10)),
+- stream->timing.h_total), 1000000);
++ stream->timing.h_total) + 500000, 1000000);
+
+ /* v_total cannot be less than nominal */
+ if (v_total < stream->timing.v_total) {
+diff --git a/drivers/gpu/drm/bridge/lontium-lt8912b.c b/drivers/gpu/drm/bridge/lontium-lt8912b.c
+index 1a9defa15663cf..e265ab3c8c9293 100644
+--- a/drivers/gpu/drm/bridge/lontium-lt8912b.c
++++ b/drivers/gpu/drm/bridge/lontium-lt8912b.c
+@@ -422,22 +422,6 @@ static const struct drm_connector_funcs lt8912_connector_funcs = {
+ .atomic_destroy_state = drm_atomic_helper_connector_destroy_state,
+ };
+
+-static enum drm_mode_status
+-lt8912_connector_mode_valid(struct drm_connector *connector,
+- struct drm_display_mode *mode)
+-{
+- if (mode->clock > 150000)
+- return MODE_CLOCK_HIGH;
+-
+- if (mode->hdisplay > 1920)
+- return MODE_BAD_HVALUE;
+-
+- if (mode->vdisplay > 1080)
+- return MODE_BAD_VVALUE;
+-
+- return MODE_OK;
+-}
+-
+ static int lt8912_connector_get_modes(struct drm_connector *connector)
+ {
+ const struct drm_edid *drm_edid;
+@@ -463,7 +447,6 @@ static int lt8912_connector_get_modes(struct drm_connector *connector)
+
+ static const struct drm_connector_helper_funcs lt8912_connector_helper_funcs = {
+ .get_modes = lt8912_connector_get_modes,
+- .mode_valid = lt8912_connector_mode_valid,
+ };
+
+ static void lt8912_bridge_mode_set(struct drm_bridge *bridge,
+@@ -605,6 +588,23 @@ static void lt8912_bridge_detach(struct drm_bridge *bridge)
+ drm_bridge_hpd_disable(lt->hdmi_port);
+ }
+
++static enum drm_mode_status
++lt8912_bridge_mode_valid(struct drm_bridge *bridge,
++ const struct drm_display_info *info,
++ const struct drm_display_mode *mode)
++{
++ if (mode->clock > 150000)
++ return MODE_CLOCK_HIGH;
++
++ if (mode->hdisplay > 1920)
++ return MODE_BAD_HVALUE;
++
++ if (mode->vdisplay > 1080)
++ return MODE_BAD_VVALUE;
++
++ return MODE_OK;
++}
++
+ static enum drm_connector_status
+ lt8912_bridge_detect(struct drm_bridge *bridge)
+ {
+@@ -635,6 +635,7 @@ static const struct drm_edid *lt8912_bridge_edid_read(struct drm_bridge *bridge,
+ static const struct drm_bridge_funcs lt8912_bridge_funcs = {
+ .attach = lt8912_bridge_attach,
+ .detach = lt8912_bridge_detach,
++ .mode_valid = lt8912_bridge_mode_valid,
+ .mode_set = lt8912_bridge_mode_set,
+ .enable = lt8912_bridge_enable,
+ .detect = lt8912_bridge_detect,
+diff --git a/drivers/gpu/drm/exynos/exynos_drm_gsc.c b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+index 1b111e2c33472b..752339d33f39a5 100644
+--- a/drivers/gpu/drm/exynos/exynos_drm_gsc.c
++++ b/drivers/gpu/drm/exynos/exynos_drm_gsc.c
+@@ -1174,7 +1174,7 @@ static int gsc_bind(struct device *dev, struct device *master, void *data)
+ struct exynos_drm_ipp *ipp = &ctx->ipp;
+
+ ctx->drm_dev = drm_dev;
+- ctx->drm_dev = drm_dev;
++ ipp->drm_dev = drm_dev;
+ exynos_drm_register_dma(drm_dev, dev, &ctx->dma_priv);
+
+ exynos_drm_ipp_register(dev, ipp, &ipp_funcs,
+diff --git a/drivers/gpu/drm/mediatek/mtk_crtc.c b/drivers/gpu/drm/mediatek/mtk_crtc.c
+index 6f34f573e127ec..a90504359e8d27 100644
+--- a/drivers/gpu/drm/mediatek/mtk_crtc.c
++++ b/drivers/gpu/drm/mediatek/mtk_crtc.c
+@@ -69,6 +69,8 @@ struct mtk_crtc {
+ /* lock for display hardware access */
+ struct mutex hw_lock;
+ bool config_updating;
++ /* lock for config_updating to cmd buffer */
++ spinlock_t config_lock;
+ };
+
+ struct mtk_crtc_state {
+@@ -106,11 +108,16 @@ static void mtk_crtc_finish_page_flip(struct mtk_crtc *mtk_crtc)
+
+ static void mtk_drm_finish_page_flip(struct mtk_crtc *mtk_crtc)
+ {
++ unsigned long flags;
++
+ drm_crtc_handle_vblank(&mtk_crtc->base);
++
++ spin_lock_irqsave(&mtk_crtc->config_lock, flags);
+ if (!mtk_crtc->config_updating && mtk_crtc->pending_needs_vblank) {
+ mtk_crtc_finish_page_flip(mtk_crtc);
+ mtk_crtc->pending_needs_vblank = false;
+ }
++ spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
+ }
+
+ #if IS_REACHABLE(CONFIG_MTK_CMDQ)
+@@ -308,12 +315,19 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
+ struct mtk_crtc *mtk_crtc = container_of(cmdq_cl, struct mtk_crtc, cmdq_client);
+ struct mtk_crtc_state *state;
+ unsigned int i;
++ unsigned long flags;
+
+ if (data->sta < 0)
+ return;
+
+ state = to_mtk_crtc_state(mtk_crtc->base.state);
+
++ spin_lock_irqsave(&mtk_crtc->config_lock, flags);
++ if (mtk_crtc->config_updating) {
++ spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
++ goto ddp_cmdq_cb_out;
++ }
++
+ state->pending_config = false;
+
+ if (mtk_crtc->pending_planes) {
+@@ -340,6 +354,10 @@ static void ddp_cmdq_cb(struct mbox_client *cl, void *mssg)
+ mtk_crtc->pending_async_planes = false;
+ }
+
++ spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
++
++ddp_cmdq_cb_out:
++
+ mtk_crtc->cmdq_vblank_cnt = 0;
+ wake_up(&mtk_crtc->cb_blocking_queue);
+ }
+@@ -449,6 +467,7 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_crtc *mtk_crtc)
+ {
+ struct drm_device *drm = mtk_crtc->base.dev;
+ struct drm_crtc *crtc = &mtk_crtc->base;
++ unsigned long flags;
+ int i;
+
+ for (i = 0; i < mtk_crtc->ddp_comp_nr; i++) {
+@@ -480,10 +499,10 @@ static void mtk_crtc_ddp_hw_fini(struct mtk_crtc *mtk_crtc)
+ pm_runtime_put(drm->dev);
+
+ if (crtc->state->event && !crtc->state->active) {
+- spin_lock_irq(&crtc->dev->event_lock);
++ spin_lock_irqsave(&crtc->dev->event_lock, flags);
+ drm_crtc_send_vblank_event(crtc, crtc->state->event);
+ crtc->state->event = NULL;
+- spin_unlock_irq(&crtc->dev->event_lock);
++ spin_unlock_irqrestore(&crtc->dev->event_lock, flags);
+ }
+ }
+
+@@ -569,9 +588,14 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank)
+ struct mtk_drm_private *priv = crtc->dev->dev_private;
+ unsigned int pending_planes = 0, pending_async_planes = 0;
+ int i;
++ unsigned long flags;
+
+ mutex_lock(&mtk_crtc->hw_lock);
++
++ spin_lock_irqsave(&mtk_crtc->config_lock, flags);
+ mtk_crtc->config_updating = true;
++ spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
++
+ if (needs_vblank)
+ mtk_crtc->pending_needs_vblank = true;
+
+@@ -625,7 +649,10 @@ static void mtk_crtc_update_config(struct mtk_crtc *mtk_crtc, bool needs_vblank)
+ mbox_client_txdone(mtk_crtc->cmdq_client.chan, 0);
+ }
+ #endif
++ spin_lock_irqsave(&mtk_crtc->config_lock, flags);
+ mtk_crtc->config_updating = false;
++ spin_unlock_irqrestore(&mtk_crtc->config_lock, flags);
++
+ mutex_unlock(&mtk_crtc->hw_lock);
+ }
+
+@@ -1068,6 +1095,7 @@ int mtk_crtc_create(struct drm_device *drm_dev, const unsigned int *path,
+ drm_mode_crtc_set_gamma_size(&mtk_crtc->base, gamma_lut_size);
+ drm_crtc_enable_color_mgmt(&mtk_crtc->base, 0, has_ctm, gamma_lut_size);
+ mutex_init(&mtk_crtc->hw_lock);
++ spin_lock_init(&mtk_crtc->config_lock);
+
+ #if IS_REACHABLE(CONFIG_MTK_CMDQ)
+ i = priv->mbox_index++;
+diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+index c003f970189b06..0eb3db9c3d9e61 100644
+--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
++++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.c
+@@ -65,6 +65,8 @@ void a5xx_flush(struct msm_gpu *gpu, struct msm_ringbuffer *ring,
+
+ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit)
+ {
++ struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
++ struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+ struct msm_ringbuffer *ring = submit->ring;
+ struct drm_gem_object *obj;
+ uint32_t *ptr, dwords;
+@@ -109,6 +111,7 @@ static void a5xx_submit_in_rb(struct msm_gpu *gpu, struct msm_gem_submit *submit
+ }
+ }
+
++ a5xx_gpu->last_seqno[ring->id] = submit->seqno;
+ a5xx_flush(gpu, ring, true);
+ a5xx_preempt_trigger(gpu);
+
+@@ -150,9 +153,13 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
+ OUT_PKT7(ring, CP_SET_PROTECTED_MODE, 1);
+ OUT_RING(ring, 1);
+
+- /* Enable local preemption for finegrain preemption */
++ /*
++ * Disable local preemption by default because it requires
++ * user-space to be aware of it and provide additional handling
++ * to restore rendering state or do various flushes on switch.
++ */
+ OUT_PKT7(ring, CP_PREEMPT_ENABLE_LOCAL, 1);
+- OUT_RING(ring, 0x1);
++ OUT_RING(ring, 0x0);
+
+ /* Allow CP_CONTEXT_SWITCH_YIELD packets in the IB2 */
+ OUT_PKT7(ring, CP_YIELD_ENABLE, 1);
+@@ -206,6 +213,7 @@ static void a5xx_submit(struct msm_gpu *gpu, struct msm_gem_submit *submit)
+ /* Write the fence to the scratch register */
+ OUT_PKT4(ring, REG_A5XX_CP_SCRATCH_REG(2), 1);
+ OUT_RING(ring, submit->seqno);
++ a5xx_gpu->last_seqno[ring->id] = submit->seqno;
+
+ /*
+ * Execute a CACHE_FLUSH_TS event. This will ensure that the
+diff --git a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
+index c7187bcc5e9082..9c0d701fe4b85b 100644
+--- a/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
++++ b/drivers/gpu/drm/msm/adreno/a5xx_gpu.h
+@@ -34,8 +34,10 @@ struct a5xx_gpu {
+ struct drm_gem_object *preempt_counters_bo[MSM_GPU_MAX_RINGS];
+ struct a5xx_preempt_record *preempt[MSM_GPU_MAX_RINGS];
+ uint64_t preempt_iova[MSM_GPU_MAX_RINGS];
++ uint32_t last_seqno[MSM_GPU_MAX_RINGS];
+
+ atomic_t preempt_state;
++ spinlock_t preempt_start_lock;
+ struct timer_list preempt_timer;
+
+ struct drm_gem_object *shadow_bo;
+diff --git a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+index f58dd564d122ba..0469fea5501083 100644
+--- a/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
++++ b/drivers/gpu/drm/msm/adreno/a5xx_preempt.c
+@@ -55,6 +55,8 @@ static inline void update_wptr(struct msm_gpu *gpu, struct msm_ringbuffer *ring)
+ /* Return the highest priority ringbuffer with something in it */
+ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
+ {
++ struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
++ struct a5xx_gpu *a5xx_gpu = to_a5xx_gpu(adreno_gpu);
+ unsigned long flags;
+ int i;
+
+@@ -64,6 +66,8 @@ static struct msm_ringbuffer *get_next_ring(struct msm_gpu *gpu)
+
+ spin_lock_irqsave(&ring->preempt_lock, flags);
+ empty = (get_wptr(ring) == gpu->funcs->get_rptr(gpu, ring));
++ if (!empty && ring == a5xx_gpu->cur_ring)
++ empty = ring->memptrs->fence == a5xx_gpu->last_seqno[i];
+ spin_unlock_irqrestore(&ring->preempt_lock, flags);
+
+ if (!empty)
+@@ -97,12 +101,19 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
+ if (gpu->nr_rings == 1)
+ return;
+
++ /*
++ * Serialize preemption start to ensure that we always make
++ * decision on latest state. Otherwise we can get stuck in
++ * lower priority or empty ring.
++ */
++ spin_lock_irqsave(&a5xx_gpu->preempt_start_lock, flags);
++
+ /*
+ * Try to start preemption by moving from NONE to START. If
+ * unsuccessful, a preemption is already in flight
+ */
+ if (!try_preempt_state(a5xx_gpu, PREEMPT_NONE, PREEMPT_START))
+- return;
++ goto out;
+
+ /* Get the next ring to preempt to */
+ ring = get_next_ring(gpu);
+@@ -127,9 +138,11 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
+ set_preempt_state(a5xx_gpu, PREEMPT_ABORT);
+ update_wptr(gpu, a5xx_gpu->cur_ring);
+ set_preempt_state(a5xx_gpu, PREEMPT_NONE);
+- return;
++ goto out;
+ }
+
++ spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags);
++
+ /* Make sure the wptr doesn't update while we're in motion */
+ spin_lock_irqsave(&ring->preempt_lock, flags);
+ a5xx_gpu->preempt[ring->id]->wptr = get_wptr(ring);
+@@ -152,6 +165,10 @@ void a5xx_preempt_trigger(struct msm_gpu *gpu)
+
+ /* And actually start the preemption */
+ gpu_write(gpu, REG_A5XX_CP_CONTEXT_SWITCH_CNTL, 1);
++ return;
++
++out:
++ spin_unlock_irqrestore(&a5xx_gpu->preempt_start_lock, flags);
+ }
+
+ void a5xx_preempt_irq(struct msm_gpu *gpu)
+@@ -188,6 +205,12 @@ void a5xx_preempt_irq(struct msm_gpu *gpu)
+ update_wptr(gpu, a5xx_gpu->cur_ring);
+
+ set_preempt_state(a5xx_gpu, PREEMPT_NONE);
++
++ /*
++ * Try to trigger preemption again in case there was a submit or
++ * retire during ring switch
++ */
++ a5xx_preempt_trigger(gpu);
+ }
+
+ void a5xx_preempt_hw_init(struct msm_gpu *gpu)
+@@ -204,6 +227,8 @@ void a5xx_preempt_hw_init(struct msm_gpu *gpu)
+ return;
+
+ for (i = 0; i < gpu->nr_rings; i++) {
++ a5xx_gpu->preempt[i]->data = 0;
++ a5xx_gpu->preempt[i]->info = 0;
+ a5xx_gpu->preempt[i]->wptr = 0;
+ a5xx_gpu->preempt[i]->rptr = 0;
+ a5xx_gpu->preempt[i]->rbase = gpu->rb[i]->iova;
+@@ -298,5 +323,6 @@ void a5xx_preempt_init(struct msm_gpu *gpu)
+ }
+ }
+
++ spin_lock_init(&a5xx_gpu->preempt_start_lock);
+ timer_setup(&a5xx_gpu->preempt_timer, a5xx_preempt_timer, 0);
+ }
+diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+index 789a11416f7a45..0fcae53c0b140b 100644
+--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
++++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+@@ -388,18 +388,18 @@ static void a7xx_get_debugbus_blocks(struct msm_gpu *gpu,
+ const u32 *debugbus_blocks, *gbif_debugbus_blocks;
+ int i;
+
+- if (adreno_is_a730(adreno_gpu)) {
++ if (adreno_gpu->info->family == ADRENO_7XX_GEN1) {
+ debugbus_blocks = gen7_0_0_debugbus_blocks;
+ debugbus_blocks_count = ARRAY_SIZE(gen7_0_0_debugbus_blocks);
+ gbif_debugbus_blocks = a7xx_gbif_debugbus_blocks;
+ gbif_debugbus_blocks_count = ARRAY_SIZE(a7xx_gbif_debugbus_blocks);
+- } else if (adreno_is_a740_family(adreno_gpu)) {
++ } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) {
+ debugbus_blocks = gen7_2_0_debugbus_blocks;
+ debugbus_blocks_count = ARRAY_SIZE(gen7_2_0_debugbus_blocks);
+ gbif_debugbus_blocks = a7xx_gbif_debugbus_blocks;
+ gbif_debugbus_blocks_count = ARRAY_SIZE(a7xx_gbif_debugbus_blocks);
+ } else {
+- BUG_ON(!adreno_is_a750(adreno_gpu));
++ BUG_ON(adreno_gpu->info->family != ADRENO_7XX_GEN3);
+ debugbus_blocks = gen7_9_0_debugbus_blocks;
+ debugbus_blocks_count = ARRAY_SIZE(gen7_9_0_debugbus_blocks);
+ gbif_debugbus_blocks = gen7_9_0_gbif_debugbus_blocks;
+@@ -509,7 +509,7 @@ static void a6xx_get_debugbus(struct msm_gpu *gpu,
+ const struct a6xx_debugbus_block *cx_debugbus_blocks;
+
+ if (adreno_is_a7xx(adreno_gpu)) {
+- BUG_ON(!(adreno_is_a730(adreno_gpu) || adreno_is_a740_family(adreno_gpu)));
++ BUG_ON(adreno_gpu->info->family > ADRENO_7XX_GEN3);
+ cx_debugbus_blocks = a7xx_cx_debugbus_blocks;
+ nr_cx_debugbus_blocks = ARRAY_SIZE(a7xx_cx_debugbus_blocks);
+ } else {
+@@ -660,13 +660,16 @@ static void a7xx_get_dbgahb_clusters(struct msm_gpu *gpu,
+ const struct gen7_sptp_cluster_registers *dbgahb_clusters;
+ unsigned dbgahb_clusters_size;
+
+- if (adreno_is_a730(adreno_gpu)) {
++ if (adreno_gpu->info->family == ADRENO_7XX_GEN1) {
+ dbgahb_clusters = gen7_0_0_sptp_clusters;
+ dbgahb_clusters_size = ARRAY_SIZE(gen7_0_0_sptp_clusters);
+- } else {
+- BUG_ON(!adreno_is_a740_family(adreno_gpu));
++ } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) {
+ dbgahb_clusters = gen7_2_0_sptp_clusters;
+ dbgahb_clusters_size = ARRAY_SIZE(gen7_2_0_sptp_clusters);
++ } else {
++ BUG_ON(adreno_gpu->info->family != ADRENO_7XX_GEN3);
++ dbgahb_clusters = gen7_9_0_sptp_clusters;
++ dbgahb_clusters_size = ARRAY_SIZE(gen7_9_0_sptp_clusters);
+ }
+
+ a6xx_state->dbgahb_clusters = state_kcalloc(a6xx_state,
+@@ -818,14 +821,14 @@ static void a7xx_get_clusters(struct msm_gpu *gpu,
+ const struct gen7_cluster_registers *clusters;
+ unsigned clusters_size;
+
+- if (adreno_is_a730(adreno_gpu)) {
++ if (adreno_gpu->info->family == ADRENO_7XX_GEN1) {
+ clusters = gen7_0_0_clusters;
+ clusters_size = ARRAY_SIZE(gen7_0_0_clusters);
+- } else if (adreno_is_a740_family(adreno_gpu)) {
++ } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) {
+ clusters = gen7_2_0_clusters;
+ clusters_size = ARRAY_SIZE(gen7_2_0_clusters);
+ } else {
+- BUG_ON(!adreno_is_a750(adreno_gpu));
++ BUG_ON(adreno_gpu->info->family != ADRENO_7XX_GEN3);
+ clusters = gen7_9_0_clusters;
+ clusters_size = ARRAY_SIZE(gen7_9_0_clusters);
+ }
+@@ -893,7 +896,7 @@ static void a7xx_get_shader_block(struct msm_gpu *gpu,
+ if (WARN_ON(datasize > A6XX_CD_DATA_SIZE))
+ return;
+
+- if (adreno_is_a730(adreno_gpu)) {
++ if (adreno_gpu->info->family == ADRENO_7XX_GEN1) {
+ gpu_rmw(gpu, REG_A7XX_SP_DBG_CNTL, GENMASK(1, 0), 3);
+ }
+
+@@ -923,7 +926,7 @@ static void a7xx_get_shader_block(struct msm_gpu *gpu,
+ datasize);
+
+ out:
+- if (adreno_is_a730(adreno_gpu)) {
++ if (adreno_gpu->info->family == ADRENO_7XX_GEN1) {
+ gpu_rmw(gpu, REG_A7XX_SP_DBG_CNTL, GENMASK(1, 0), 0);
+ }
+ }
+@@ -956,14 +959,14 @@ static void a7xx_get_shaders(struct msm_gpu *gpu,
+ unsigned num_shader_blocks;
+ int i;
+
+- if (adreno_is_a730(adreno_gpu)) {
++ if (adreno_gpu->info->family == ADRENO_7XX_GEN1) {
+ shader_blocks = gen7_0_0_shader_blocks;
+ num_shader_blocks = ARRAY_SIZE(gen7_0_0_shader_blocks);
+- } else if (adreno_is_a740_family(adreno_gpu)) {
++ } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) {
+ shader_blocks = gen7_2_0_shader_blocks;
+ num_shader_blocks = ARRAY_SIZE(gen7_2_0_shader_blocks);
+ } else {
+- BUG_ON(!adreno_is_a750(adreno_gpu));
++ BUG_ON(adreno_gpu->info->family != ADRENO_7XX_GEN3);
+ shader_blocks = gen7_9_0_shader_blocks;
+ num_shader_blocks = ARRAY_SIZE(gen7_9_0_shader_blocks);
+ }
+@@ -1348,14 +1351,14 @@ static void a7xx_get_registers(struct msm_gpu *gpu,
+ const u32 *pre_crashdumper_regs;
+ const struct gen7_reg_list *reglist;
+
+- if (adreno_is_a730(adreno_gpu)) {
++ if (adreno_gpu->info->family == ADRENO_7XX_GEN1) {
+ reglist = gen7_0_0_reg_list;
+ pre_crashdumper_regs = gen7_0_0_pre_crashdumper_gpu_registers;
+- } else if (adreno_is_a740_family(adreno_gpu)) {
++ } else if (adreno_gpu->info->family == ADRENO_7XX_GEN2) {
+ reglist = gen7_2_0_reg_list;
+ pre_crashdumper_regs = gen7_0_0_pre_crashdumper_gpu_registers;
+ } else {
+- BUG_ON(!adreno_is_a750(adreno_gpu));
++ BUG_ON(adreno_gpu->info->family != ADRENO_7XX_GEN3);
+ reglist = gen7_9_0_reg_list;
+ pre_crashdumper_regs = gen7_9_0_pre_crashdumper_gpu_registers;
+ }
+@@ -1405,8 +1408,7 @@ static void a7xx_get_post_crashdumper_registers(struct msm_gpu *gpu,
+ struct adreno_gpu *adreno_gpu = to_adreno_gpu(gpu);
+ const u32 *regs;
+
+- BUG_ON(!(adreno_is_a730(adreno_gpu) || adreno_is_a740_family(adreno_gpu) ||
+- adreno_is_a750(adreno_gpu)));
++ BUG_ON(adreno_gpu->info->family > ADRENO_7XX_GEN3);
+ regs = gen7_0_0_post_crashdumper_registers;
+
+ a7xx_get_ahb_gpu_registers(gpu,
+@@ -1514,11 +1516,11 @@ static void a7xx_get_indexed_registers(struct msm_gpu *gpu,
+ const struct a6xx_indexed_registers *indexed_regs;
+ int i, indexed_count, mempool_count;
+
+- if (adreno_is_a730(adreno_gpu) || adreno_is_a740_family(adreno_gpu)) {
++ if (adreno_gpu->info->family <= ADRENO_7XX_GEN2) {
+ indexed_regs = a7xx_indexed_reglist;
+ indexed_count = ARRAY_SIZE(a7xx_indexed_reglist);
+ } else {
+- BUG_ON(!adreno_is_a750(adreno_gpu));
++ BUG_ON(adreno_gpu->info->family != ADRENO_7XX_GEN3);
+ indexed_regs = gen7_9_0_cp_indexed_reg_list;
+ indexed_count = ARRAY_SIZE(gen7_9_0_cp_indexed_reg_list);
+ }
+diff --git a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
+index 260d66eccfecbf..9a327d543f27de 100644
+--- a/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
++++ b/drivers/gpu/drm/msm/adreno/adreno_gen7_9_0_snapshot.h
+@@ -1303,7 +1303,7 @@ static struct a6xx_indexed_registers gen7_9_0_cp_indexed_reg_list[] = {
+ REG_A6XX_CP_ROQ_DBG_DATA, 0x00800},
+ { "CP_UCODE_DBG_DATA", REG_A6XX_CP_SQE_UCODE_DBG_ADDR,
+ REG_A6XX_CP_SQE_UCODE_DBG_DATA, 0x08000},
+- { "CP_BV_SQE_STAT_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
++ { "CP_BV_DRAW_STATE_ADDR", REG_A7XX_CP_BV_DRAW_STATE_ADDR,
+ REG_A7XX_CP_BV_DRAW_STATE_DATA, 0x00200},
+ { "CP_BV_ROQ_DBG_ADDR", REG_A7XX_CP_BV_ROQ_DBG_ADDR,
+ REG_A7XX_CP_BV_ROQ_DBG_DATA, 0x00800},
+diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+index b93ed15f04a30e..d5d9361e11aa53 100644
+--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
++++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+@@ -475,7 +475,7 @@ adreno_request_fw(struct adreno_gpu *adreno_gpu, const char *fwname)
+ ret = request_firmware_direct(&fw, fwname, drm->dev);
+ if (!ret) {
+ DRM_DEV_INFO(drm->dev, "loaded %s from legacy location\n",
+- newname);
++ fwname);
+ adreno_gpu->fwloc = FW_LOCATION_LEGACY;
+ goto out;
+ } else if (adreno_gpu->fwloc != FW_LOCATION_UNKNOWN) {
+diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+index 3a7f7edda96b27..500b7dc895d055 100644
+--- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
++++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c
+@@ -351,7 +351,7 @@ void mdp5_smp_dump(struct mdp5_smp *smp, struct drm_printer *p,
+
+ drm_printf(p, "%s:%d\t%d\t%s\n",
+ pipe2name(pipe), j, inuse,
+- plane ? plane->name : NULL);
++ plane ? plane->name : "(null)");
+
+ total += inuse;
+ }
+diff --git a/drivers/gpu/drm/msm/dp/dp_display.c b/drivers/gpu/drm/msm/dp/dp_display.c
+index 672a7ba52edadd..9dc44ea85b7c62 100644
+--- a/drivers/gpu/drm/msm/dp/dp_display.c
++++ b/drivers/gpu/drm/msm/dp/dp_display.c
+@@ -119,7 +119,7 @@ struct msm_dp_desc {
+ };
+
+ static const struct msm_dp_desc sc7180_dp_descs[] = {
+- { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0 },
++ { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true },
+ {}
+ };
+
+@@ -130,9 +130,9 @@ static const struct msm_dp_desc sc7280_dp_descs[] = {
+ };
+
+ static const struct msm_dp_desc sc8180x_dp_descs[] = {
+- { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0 },
+- { .io_start = 0x0ae98000, .id = MSM_DP_CONTROLLER_1 },
+- { .io_start = 0x0ae9a000, .id = MSM_DP_CONTROLLER_2 },
++ { .io_start = 0x0ae90000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true },
++ { .io_start = 0x0ae98000, .id = MSM_DP_CONTROLLER_1, .wide_bus_supported = true },
++ { .io_start = 0x0ae9a000, .id = MSM_DP_CONTROLLER_2, .wide_bus_supported = true },
+ {}
+ };
+
+@@ -149,7 +149,7 @@ static const struct msm_dp_desc sc8280xp_dp_descs[] = {
+ };
+
+ static const struct msm_dp_desc sm8650_dp_descs[] = {
+- { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0 },
++ { .io_start = 0x0af54000, .id = MSM_DP_CONTROLLER_0, .wide_bus_supported = true },
+ {}
+ };
+
+diff --git a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+index 82d015aa2d634c..29aa91238bc47e 100644
+--- a/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
++++ b/drivers/gpu/drm/msm/dsi/phy/dsi_phy_7nm.c
+@@ -135,7 +135,7 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config
+ config->pll_clock_inverters = 0x00;
+ else
+ config->pll_clock_inverters = 0x40;
+- } else {
++ } else if (pll->phy->cfg->quirks & DSI_PHY_7NM_QUIRK_V4_1) {
+ if (pll_freq <= 1000000000ULL)
+ config->pll_clock_inverters = 0xa0;
+ else if (pll_freq <= 2500000000ULL)
+@@ -144,6 +144,16 @@ static void dsi_pll_calc_dec_frac(struct dsi_pll_7nm *pll, struct dsi_pll_config
+ config->pll_clock_inverters = 0x00;
+ else
+ config->pll_clock_inverters = 0x40;
++ } else {
++ /* 4.2, 4.3 */
++ if (pll_freq <= 1000000000ULL)
++ config->pll_clock_inverters = 0xa0;
++ else if (pll_freq <= 2500000000ULL)
++ config->pll_clock_inverters = 0x20;
++ else if (pll_freq <= 3500000000ULL)
++ config->pll_clock_inverters = 0x00;
++ else
++ config->pll_clock_inverters = 0x40;
+ }
+
+ config->decimal_div_start = dec;
+diff --git a/drivers/gpu/drm/radeon/evergreen_cs.c b/drivers/gpu/drm/radeon/evergreen_cs.c
+index 1fe6e0d883c79b..675a649fa7ab5d 100644
+--- a/drivers/gpu/drm/radeon/evergreen_cs.c
++++ b/drivers/gpu/drm/radeon/evergreen_cs.c
+@@ -395,7 +395,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
+ struct evergreen_cs_track *track = p->track;
+ struct eg_surface surf;
+ unsigned pitch, slice, mslice;
+- unsigned long offset;
++ u64 offset;
+ int r;
+
+ mslice = G_028C6C_SLICE_MAX(track->cb_color_view[id]) + 1;
+@@ -433,14 +433,14 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
+ return r;
+ }
+
+- offset = track->cb_color_bo_offset[id] << 8;
++ offset = (u64)track->cb_color_bo_offset[id] << 8;
+ if (offset & (surf.base_align - 1)) {
+- dev_warn(p->dev, "%s:%d cb[%d] bo base %ld not aligned with %ld\n",
++ dev_warn(p->dev, "%s:%d cb[%d] bo base %llu not aligned with %ld\n",
+ __func__, __LINE__, id, offset, surf.base_align);
+ return -EINVAL;
+ }
+
+- offset += surf.layer_size * mslice;
++ offset += (u64)surf.layer_size * mslice;
+ if (offset > radeon_bo_size(track->cb_color_bo[id])) {
+ /* old ddx are broken they allocate bo with w*h*bpp but
+ * program slice with ALIGN(h, 8), catch this and patch
+@@ -448,14 +448,14 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
+ */
+ if (!surf.mode) {
+ uint32_t *ib = p->ib.ptr;
+- unsigned long tmp, nby, bsize, size, min = 0;
++ u64 tmp, nby, bsize, size, min = 0;
+
+ /* find the height the ddx wants */
+ if (surf.nby > 8) {
+ min = surf.nby - 8;
+ }
+ bsize = radeon_bo_size(track->cb_color_bo[id]);
+- tmp = track->cb_color_bo_offset[id] << 8;
++ tmp = (u64)track->cb_color_bo_offset[id] << 8;
+ for (nby = surf.nby; nby > min; nby--) {
+ size = nby * surf.nbx * surf.bpe * surf.nsamples;
+ if ((tmp + size * mslice) <= bsize) {
+@@ -467,7 +467,7 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
+ slice = ((nby * surf.nbx) / 64) - 1;
+ if (!evergreen_surface_check(p, &surf, "cb")) {
+ /* check if this one works */
+- tmp += surf.layer_size * mslice;
++ tmp += (u64)surf.layer_size * mslice;
+ if (tmp <= bsize) {
+ ib[track->cb_color_slice_idx[id]] = slice;
+ goto old_ddx_ok;
+@@ -476,9 +476,9 @@ static int evergreen_cs_track_validate_cb(struct radeon_cs_parser *p, unsigned i
+ }
+ }
+ dev_warn(p->dev, "%s:%d cb[%d] bo too small (layer size %d, "
+- "offset %d, max layer %d, bo size %ld, slice %d)\n",
++ "offset %llu, max layer %d, bo size %ld, slice %d)\n",
+ __func__, __LINE__, id, surf.layer_size,
+- track->cb_color_bo_offset[id] << 8, mslice,
++ (u64)track->cb_color_bo_offset[id] << 8, mslice,
+ radeon_bo_size(track->cb_color_bo[id]), slice);
+ dev_warn(p->dev, "%s:%d problematic surf: (%d %d) (%d %d %d %d %d %d %d)\n",
+ __func__, __LINE__, surf.nbx, surf.nby,
+@@ -562,7 +562,7 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p)
+ struct evergreen_cs_track *track = p->track;
+ struct eg_surface surf;
+ unsigned pitch, slice, mslice;
+- unsigned long offset;
++ u64 offset;
+ int r;
+
+ mslice = G_028008_SLICE_MAX(track->db_depth_view) + 1;
+@@ -608,18 +608,18 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p)
+ return r;
+ }
+
+- offset = track->db_s_read_offset << 8;
++ offset = (u64)track->db_s_read_offset << 8;
+ if (offset & (surf.base_align - 1)) {
+- dev_warn(p->dev, "%s:%d stencil read bo base %ld not aligned with %ld\n",
++ dev_warn(p->dev, "%s:%d stencil read bo base %llu not aligned with %ld\n",
+ __func__, __LINE__, offset, surf.base_align);
+ return -EINVAL;
+ }
+- offset += surf.layer_size * mslice;
++ offset += (u64)surf.layer_size * mslice;
+ if (offset > radeon_bo_size(track->db_s_read_bo)) {
+ dev_warn(p->dev, "%s:%d stencil read bo too small (layer size %d, "
+- "offset %ld, max layer %d, bo size %ld)\n",
++ "offset %llu, max layer %d, bo size %ld)\n",
+ __func__, __LINE__, surf.layer_size,
+- (unsigned long)track->db_s_read_offset << 8, mslice,
++ (u64)track->db_s_read_offset << 8, mslice,
+ radeon_bo_size(track->db_s_read_bo));
+ dev_warn(p->dev, "%s:%d stencil invalid (0x%08x 0x%08x 0x%08x 0x%08x)\n",
+ __func__, __LINE__, track->db_depth_size,
+@@ -627,18 +627,18 @@ static int evergreen_cs_track_validate_stencil(struct radeon_cs_parser *p)
+ return -EINVAL;
+ }
+
+- offset = track->db_s_write_offset << 8;
++ offset = (u64)track->db_s_write_offset << 8;
+ if (offset & (surf.base_align - 1)) {
+- dev_warn(p->dev, "%s:%d stencil write bo base %ld not aligned with %ld\n",
++ dev_warn(p->dev, "%s:%d stencil write bo base %llu not aligned with %ld\n",
+ __func__, __LINE__, offset, surf.base_align);
+ return -EINVAL;
+ }
+- offset += surf.layer_size * mslice;
++ offset += (u64)surf.layer_size * mslice;
+ if (offset > radeon_bo_size(track->db_s_write_bo)) {
+ dev_warn(p->dev, "%s:%d stencil write bo too small (layer size %d, "
+- "offset %ld, max layer %d, bo size %ld)\n",
++ "offset %llu, max layer %d, bo size %ld)\n",
+ __func__, __LINE__, surf.layer_size,
+- (unsigned long)track->db_s_write_offset << 8, mslice,
++ (u64)track->db_s_write_offset << 8, mslice,
+ radeon_bo_size(track->db_s_write_bo));
+ return -EINVAL;
+ }
+@@ -659,7 +659,7 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p)
+ struct evergreen_cs_track *track = p->track;
+ struct eg_surface surf;
+ unsigned pitch, slice, mslice;
+- unsigned long offset;
++ u64 offset;
+ int r;
+
+ mslice = G_028008_SLICE_MAX(track->db_depth_view) + 1;
+@@ -706,34 +706,34 @@ static int evergreen_cs_track_validate_depth(struct radeon_cs_parser *p)
+ return r;
+ }
+
+- offset = track->db_z_read_offset << 8;
++ offset = (u64)track->db_z_read_offset << 8;
+ if (offset & (surf.base_align - 1)) {
+- dev_warn(p->dev, "%s:%d stencil read bo base %ld not aligned with %ld\n",
++ dev_warn(p->dev, "%s:%d stencil read bo base %llu not aligned with %ld\n",
+ __func__, __LINE__, offset, surf.base_align);
+ return -EINVAL;
+ }
+- offset += surf.layer_size * mslice;
++ offset += (u64)surf.layer_size * mslice;
+ if (offset > radeon_bo_size(track->db_z_read_bo)) {
+ dev_warn(p->dev, "%s:%d depth read bo too small (layer size %d, "
+- "offset %ld, max layer %d, bo size %ld)\n",
++ "offset %llu, max layer %d, bo size %ld)\n",
+ __func__, __LINE__, surf.layer_size,
+- (unsigned long)track->db_z_read_offset << 8, mslice,
++ (u64)track->db_z_read_offset << 8, mslice,
+ radeon_bo_size(track->db_z_read_bo));
+ return -EINVAL;
+ }
+
+- offset = track->db_z_write_offset << 8;
++ offset = (u64)track->db_z_write_offset << 8;
+ if (offset & (surf.base_align - 1)) {
+- dev_warn(p->dev, "%s:%d stencil write bo base %ld not aligned with %ld\n",
++ dev_warn(p->dev, "%s:%d stencil write bo base %llu not aligned with %ld\n",
+ __func__, __LINE__, offset, surf.base_align);
+ return -EINVAL;
+ }
+- offset += surf.layer_size * mslice;
++ offset += (u64)surf.layer_size * mslice;
+ if (offset > radeon_bo_size(track->db_z_write_bo)) {
+ dev_warn(p->dev, "%s:%d depth write bo too small (layer size %d, "
+- "offset %ld, max layer %d, bo size %ld)\n",
++ "offset %llu, max layer %d, bo size %ld)\n",
+ __func__, __LINE__, surf.layer_size,
+- (unsigned long)track->db_z_write_offset << 8, mslice,
++ (u64)track->db_z_write_offset << 8, mslice,
+ radeon_bo_size(track->db_z_write_bo));
+ return -EINVAL;
+ }
+diff --git a/drivers/gpu/drm/radeon/radeon_atombios.c b/drivers/gpu/drm/radeon/radeon_atombios.c
+index 10793a433bf586..d698a899eaf4cf 100644
+--- a/drivers/gpu/drm/radeon/radeon_atombios.c
++++ b/drivers/gpu/drm/radeon/radeon_atombios.c
+@@ -1717,26 +1717,29 @@ struct radeon_encoder_atom_dig *radeon_atombios_get_lvds_info(struct
+ fake_edid_record = (ATOM_FAKE_EDID_PATCH_RECORD *)record;
+ if (fake_edid_record->ucFakeEDIDLength) {
+ struct edid *edid;
+- int edid_size =
+- max((int)EDID_LENGTH, (int)fake_edid_record->ucFakeEDIDLength);
+- edid = kmalloc(edid_size, GFP_KERNEL);
++ int edid_size;
++
++ if (fake_edid_record->ucFakeEDIDLength == 128)
++ edid_size = fake_edid_record->ucFakeEDIDLength;
++ else
++ edid_size = fake_edid_record->ucFakeEDIDLength * 128;
++ edid = kmemdup(&fake_edid_record->ucFakeEDIDString[0],
++ edid_size, GFP_KERNEL);
+ if (edid) {
+- memcpy((u8 *)edid, (u8 *)&fake_edid_record->ucFakeEDIDString[0],
+- fake_edid_record->ucFakeEDIDLength);
+-
+ if (drm_edid_is_valid(edid)) {
+ rdev->mode_info.bios_hardcoded_edid = edid;
+ rdev->mode_info.bios_hardcoded_edid_size = edid_size;
+- } else
++ } else {
+ kfree(edid);
++ }
+ }
++ record += struct_size(fake_edid_record,
++ ucFakeEDIDString,
++ edid_size);
++ } else {
++ /* empty fake edid record must be 3 bytes long */
++ record += sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1;
+ }
+- record += fake_edid_record->ucFakeEDIDLength ?
+- struct_size(fake_edid_record,
+- ucFakeEDIDString,
+- fake_edid_record->ucFakeEDIDLength) :
+- /* empty fake edid record must be 3 bytes long */
+- sizeof(ATOM_FAKE_EDID_PATCH_RECORD) + 1;
+ break;
+ case LCD_PANEL_RESOLUTION_RECORD_TYPE:
+ panel_res_record = (ATOM_PANEL_RESOLUTION_PATCH_RECORD *)record;
+diff --git a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
+index fe33092abbe7d7..aae48e906af11b 100644
+--- a/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
++++ b/drivers/gpu/drm/rockchip/dw_hdmi-rockchip.c
+@@ -434,6 +434,8 @@ static void dw_hdmi_rk3328_setup_hpd(struct dw_hdmi *dw_hdmi, void *data)
+ HIWORD_UPDATE(RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK,
+ RK3328_HDMI_SDAIN_MSK | RK3328_HDMI_SCLIN_MSK |
+ RK3328_HDMI_HPD_IOE));
++
++ dw_hdmi_rk3328_read_hpd(dw_hdmi, data);
+ }
+
+ static const struct dw_hdmi_phy_ops rk3228_hdmi_phy_ops = {
+diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+index a13473b2d54c40..4a9c6ea7f15dc3 100644
+--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
++++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop.c
+@@ -396,8 +396,8 @@ static void scl_vop_cal_scl_fac(struct vop *vop, const struct vop_win_data *win,
+ if (info->is_yuv)
+ is_yuv = true;
+
+- if (dst_w > 3840) {
+- DRM_DEV_ERROR(vop->dev, "Maximum dst width (3840) exceeded\n");
++ if (dst_w > 4096) {
++ DRM_DEV_ERROR(vop->dev, "Maximum dst width (4096) exceeded\n");
+ return;
+ }
+
+diff --git a/drivers/gpu/drm/stm/drv.c b/drivers/gpu/drm/stm/drv.c
+index e8523abef27a50..4d2db079ad4ff3 100644
+--- a/drivers/gpu/drm/stm/drv.c
++++ b/drivers/gpu/drm/stm/drv.c
+@@ -203,12 +203,14 @@ static int stm_drm_platform_probe(struct platform_device *pdev)
+
+ ret = drm_dev_register(ddev, 0);
+ if (ret)
+- goto err_put;
++ goto err_unload;
+
+ drm_fbdev_dma_setup(ddev, 16);
+
+ return 0;
+
++err_unload:
++ drv_unload(ddev);
+ err_put:
+ drm_dev_put(ddev);
+
+diff --git a/drivers/gpu/drm/stm/ltdc.c b/drivers/gpu/drm/stm/ltdc.c
+index 5576fdae496233..5aec1e58c968c2 100644
+--- a/drivers/gpu/drm/stm/ltdc.c
++++ b/drivers/gpu/drm/stm/ltdc.c
+@@ -1580,6 +1580,8 @@ static struct drm_plane *ltdc_plane_create(struct drm_device *ddev,
+ ARRAY_SIZE(ltdc_drm_fmt_ycbcr_sp) +
+ ARRAY_SIZE(ltdc_drm_fmt_ycbcr_fp)) *
+ sizeof(*formats), GFP_KERNEL);
++ if (!formats)
++ return NULL;
+
+ for (i = 0; i < ldev->caps.pix_fmt_nb; i++) {
+ drm_fmt = ldev->caps.pix_fmt_drm[i];
+diff --git a/drivers/gpu/drm/vc4/vc4_hdmi.c b/drivers/gpu/drm/vc4/vc4_hdmi.c
+index d30f8e8e896717..c75bd5af2cefd5 100644
+--- a/drivers/gpu/drm/vc4/vc4_hdmi.c
++++ b/drivers/gpu/drm/vc4/vc4_hdmi.c
+@@ -462,6 +462,7 @@ static int vc4_hdmi_connector_detect_ctx(struct drm_connector *connector,
+ {
+ struct vc4_hdmi *vc4_hdmi = connector_to_vc4_hdmi(connector);
+ enum drm_connector_status status = connector_status_disconnected;
++ int ret;
+
+ /*
+ * NOTE: This function should really take vc4_hdmi->mutex, but
+@@ -474,7 +475,12 @@ static int vc4_hdmi_connector_detect_ctx(struct drm_connector *connector,
+ * the lock for now.
+ */
+
+- WARN_ON(pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev));
++ ret = pm_runtime_resume_and_get(&vc4_hdmi->pdev->dev);
++ if (ret) {
++ drm_err_once(connector->dev, "Failed to retain HDMI power domain: %d\n",
++ ret);
++ return connector_status_unknown;
++ }
+
+ if (vc4_hdmi->hpd_gpio) {
+ if (gpiod_get_value_cansleep(vc4_hdmi->hpd_gpio))
+diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
+index d84740be96426a..7660f62e6c1f23 100644
+--- a/drivers/hid/wacom_wac.c
++++ b/drivers/hid/wacom_wac.c
+@@ -2368,6 +2368,9 @@ static void wacom_wac_pen_usage_mapping(struct hid_device *hdev,
+ wacom_map_usage(input, usage, field, EV_KEY, BTN_STYLUS3, 0);
+ features->quirks &= ~WACOM_QUIRK_PEN_BUTTON3;
+ break;
++ case WACOM_HID_WD_SEQUENCENUMBER:
++ wacom_wac->hid_data.sequence_number = -1;
++ break;
+ }
+ }
+
+@@ -2492,9 +2495,15 @@ static void wacom_wac_pen_event(struct hid_device *hdev, struct hid_field *field
+ wacom_wac->hid_data.barrelswitch3 = value;
+ return;
+ case WACOM_HID_WD_SEQUENCENUMBER:
+- if (wacom_wac->hid_data.sequence_number != value)
+- hid_warn(hdev, "Dropped %hu packets", (unsigned short)(value - wacom_wac->hid_data.sequence_number));
++ if (wacom_wac->hid_data.sequence_number != value &&
++ wacom_wac->hid_data.sequence_number >= 0) {
++ int sequence_size = field->logical_maximum - field->logical_minimum + 1;
++ int drop_count = (value - wacom_wac->hid_data.sequence_number) % sequence_size;
++ hid_warn(hdev, "Dropped %d packets", drop_count);
++ }
+ wacom_wac->hid_data.sequence_number = value + 1;
++ if (wacom_wac->hid_data.sequence_number > field->logical_maximum)
++ wacom_wac->hid_data.sequence_number = field->logical_minimum;
+ return;
+ }
+
+diff --git a/drivers/hid/wacom_wac.h b/drivers/hid/wacom_wac.h
+index 6ec499841f7095..e6443740b462fd 100644
+--- a/drivers/hid/wacom_wac.h
++++ b/drivers/hid/wacom_wac.h
+@@ -324,7 +324,7 @@ struct hid_data {
+ int bat_connected;
+ int ps_connected;
+ bool pad_input_event_flag;
+- unsigned short sequence_number;
++ int sequence_number;
+ ktime_t time_delayed;
+ };
+
+diff --git a/drivers/hwmon/max16065.c b/drivers/hwmon/max16065.c
+index aa38c45adc09e2..0ccb5eb596fc40 100644
+--- a/drivers/hwmon/max16065.c
++++ b/drivers/hwmon/max16065.c
+@@ -79,7 +79,7 @@ static const bool max16065_have_current[] = {
+ };
+
+ struct max16065_data {
+- enum chips type;
++ enum chips chip;
+ struct i2c_client *client;
+ const struct attribute_group *groups[4];
+ struct mutex update_lock;
+@@ -114,9 +114,10 @@ static inline int LIMIT_TO_MV(int limit, int range)
+ return limit * range / 256;
+ }
+
+-static inline int MV_TO_LIMIT(int mv, int range)
++static inline int MV_TO_LIMIT(unsigned long mv, int range)
+ {
+- return clamp_val(DIV_ROUND_CLOSEST(mv * 256, range), 0, 255);
++ mv = clamp_val(mv, 0, ULONG_MAX / 256);
++ return DIV_ROUND_CLOSEST(clamp_val(mv * 256, 0, range * 255), range);
+ }
+
+ static inline int ADC_TO_CURR(int adc, int gain)
+@@ -161,10 +162,17 @@ static struct max16065_data *max16065_update_device(struct device *dev)
+ MAX16065_CURR_SENSE);
+ }
+
+- for (i = 0; i < DIV_ROUND_UP(data->num_adc, 8); i++)
++ for (i = 0; i < 2; i++)
+ data->fault[i]
+ = i2c_smbus_read_byte_data(client, MAX16065_FAULT(i));
+
++ /*
++ * MAX16067 and MAX16068 have separate undervoltage and
++ * overvoltage alarm bits. Squash them together.
++ */
++ if (data->chip == max16067 || data->chip == max16068)
++ data->fault[0] |= data->fault[1];
++
+ data->last_updated = jiffies;
+ data->valid = true;
+ }
+@@ -493,8 +501,6 @@ static const struct attribute_group max16065_max_group = {
+ .is_visible = max16065_secondary_is_visible,
+ };
+
+-static const struct i2c_device_id max16065_id[];
+-
+ static int max16065_probe(struct i2c_client *client)
+ {
+ struct i2c_adapter *adapter = client->adapter;
+@@ -505,7 +511,7 @@ static int max16065_probe(struct i2c_client *client)
+ bool have_secondary; /* true if chip has secondary limits */
+ bool secondary_is_max = false; /* secondary limits reflect max */
+ int groups = 0;
+- const struct i2c_device_id *id = i2c_match_id(max16065_id, client);
++ enum chips chip = (uintptr_t)i2c_get_match_data(client);
+
+ if (!i2c_check_functionality(adapter, I2C_FUNC_SMBUS_BYTE_DATA
+ | I2C_FUNC_SMBUS_READ_WORD_DATA))
+@@ -515,12 +521,13 @@ static int max16065_probe(struct i2c_client *client)
+ if (unlikely(!data))
+ return -ENOMEM;
+
++ data->chip = chip;
+ data->client = client;
+ mutex_init(&data->update_lock);
+
+- data->num_adc = max16065_num_adc[id->driver_data];
+- data->have_current = max16065_have_current[id->driver_data];
+- have_secondary = max16065_have_secondary[id->driver_data];
++ data->num_adc = max16065_num_adc[chip];
++ data->have_current = max16065_have_current[chip];
++ have_secondary = max16065_have_secondary[chip];
+
+ if (have_secondary) {
+ val = i2c_smbus_read_byte_data(client, MAX16065_SW_ENABLE);
+diff --git a/drivers/hwmon/ntc_thermistor.c b/drivers/hwmon/ntc_thermistor.c
+index ef75b63f5894e5..b5352900463fb9 100644
+--- a/drivers/hwmon/ntc_thermistor.c
++++ b/drivers/hwmon/ntc_thermistor.c
+@@ -62,6 +62,7 @@ static const struct platform_device_id ntc_thermistor_id[] = {
+ [NTC_SSG1404001221] = { "ssg1404_001221", TYPE_NCPXXWB473 },
+ [NTC_LAST] = { },
+ };
++MODULE_DEVICE_TABLE(platform, ntc_thermistor_id);
+
+ /*
+ * A compensation table should be sorted by the values of .ohm
+diff --git a/drivers/hwtracing/coresight/coresight-dummy.c b/drivers/hwtracing/coresight/coresight-dummy.c
+index ac70c0b491bebd..dab389a5507c11 100644
+--- a/drivers/hwtracing/coresight/coresight-dummy.c
++++ b/drivers/hwtracing/coresight/coresight-dummy.c
+@@ -23,6 +23,9 @@ DEFINE_CORESIGHT_DEVLIST(sink_devs, "dummy_sink");
+ static int dummy_source_enable(struct coresight_device *csdev,
+ struct perf_event *event, enum cs_mode mode)
+ {
++ if (!coresight_take_mode(csdev, mode))
++ return -EBUSY;
++
+ dev_dbg(csdev->dev.parent, "Dummy source enabled\n");
+
+ return 0;
+@@ -31,6 +34,7 @@ static int dummy_source_enable(struct coresight_device *csdev,
+ static void dummy_source_disable(struct coresight_device *csdev,
+ struct perf_event *event)
+ {
++ coresight_set_mode(csdev, CS_MODE_DISABLED);
+ dev_dbg(csdev->dev.parent, "Dummy source disabled\n");
+ }
+
+diff --git a/drivers/hwtracing/coresight/coresight-tmc-etr.c b/drivers/hwtracing/coresight/coresight-tmc-etr.c
+index e75428fa1592a7..610ad51cda656b 100644
+--- a/drivers/hwtracing/coresight/coresight-tmc-etr.c
++++ b/drivers/hwtracing/coresight/coresight-tmc-etr.c
+@@ -261,6 +261,7 @@ void tmc_free_sg_table(struct tmc_sg_table *sg_table)
+ {
+ tmc_free_table_pages(sg_table);
+ tmc_free_data_pages(sg_table);
++ kfree(sg_table);
+ }
+ EXPORT_SYMBOL_GPL(tmc_free_sg_table);
+
+@@ -342,7 +343,6 @@ struct tmc_sg_table *tmc_alloc_sg_table(struct device *dev,
+ rc = tmc_alloc_table_pages(sg_table);
+ if (rc) {
+ tmc_free_sg_table(sg_table);
+- kfree(sg_table);
+ return ERR_PTR(rc);
+ }
+
+diff --git a/drivers/hwtracing/coresight/coresight-tpdm.c b/drivers/hwtracing/coresight/coresight-tpdm.c
+index 0726f8842552c6..5c5a4b3fe6871c 100644
+--- a/drivers/hwtracing/coresight/coresight-tpdm.c
++++ b/drivers/hwtracing/coresight/coresight-tpdm.c
+@@ -449,6 +449,11 @@ static int tpdm_enable(struct coresight_device *csdev, struct perf_event *event,
+ return -EBUSY;
+ }
+
++ if (!coresight_take_mode(csdev, mode)) {
++ spin_unlock(&drvdata->spinlock);
++ return -EBUSY;
++ }
++
+ __tpdm_enable(drvdata);
+ drvdata->enable = true;
+ spin_unlock(&drvdata->spinlock);
+@@ -506,6 +511,7 @@ static void tpdm_disable(struct coresight_device *csdev,
+ }
+
+ __tpdm_disable(drvdata);
++ coresight_set_mode(csdev, CS_MODE_DISABLED);
+ drvdata->enable = false;
+ spin_unlock(&drvdata->spinlock);
+
+diff --git a/drivers/i2c/busses/i2c-aspeed.c b/drivers/i2c/busses/i2c-aspeed.c
+index ce8c4846b7fae4..2a03a221e2dd57 100644
+--- a/drivers/i2c/busses/i2c-aspeed.c
++++ b/drivers/i2c/busses/i2c-aspeed.c
+@@ -170,6 +170,13 @@ struct aspeed_i2c_bus {
+
+ static int aspeed_i2c_reset(struct aspeed_i2c_bus *bus);
+
++/* precondition: bus.lock has been acquired. */
++static void aspeed_i2c_do_stop(struct aspeed_i2c_bus *bus)
++{
++ bus->master_state = ASPEED_I2C_MASTER_STOP;
++ writel(ASPEED_I2CD_M_STOP_CMD, bus->base + ASPEED_I2C_CMD_REG);
++}
++
+ static int aspeed_i2c_recover_bus(struct aspeed_i2c_bus *bus)
+ {
+ unsigned long time_left, flags;
+@@ -187,7 +194,7 @@ static int aspeed_i2c_recover_bus(struct aspeed_i2c_bus *bus)
+ command);
+
+ reinit_completion(&bus->cmd_complete);
+- writel(ASPEED_I2CD_M_STOP_CMD, bus->base + ASPEED_I2C_CMD_REG);
++ aspeed_i2c_do_stop(bus);
+ spin_unlock_irqrestore(&bus->lock, flags);
+
+ time_left = wait_for_completion_timeout(
+@@ -390,13 +397,6 @@ static void aspeed_i2c_do_start(struct aspeed_i2c_bus *bus)
+ writel(command, bus->base + ASPEED_I2C_CMD_REG);
+ }
+
+-/* precondition: bus.lock has been acquired. */
+-static void aspeed_i2c_do_stop(struct aspeed_i2c_bus *bus)
+-{
+- bus->master_state = ASPEED_I2C_MASTER_STOP;
+- writel(ASPEED_I2CD_M_STOP_CMD, bus->base + ASPEED_I2C_CMD_REG);
+-}
+-
+ /* precondition: bus.lock has been acquired. */
+ static void aspeed_i2c_next_msg_or_stop(struct aspeed_i2c_bus *bus)
+ {
+diff --git a/drivers/i2c/busses/i2c-isch.c b/drivers/i2c/busses/i2c-isch.c
+index 416a9968ed2870..8b225412be5ba4 100644
+--- a/drivers/i2c/busses/i2c-isch.c
++++ b/drivers/i2c/busses/i2c-isch.c
+@@ -99,8 +99,7 @@ static int sch_transaction(void)
+ if (retries > MAX_RETRIES) {
+ dev_err(&sch_adapter.dev, "SMBus Timeout!\n");
+ result = -ETIMEDOUT;
+- }
+- if (temp & 0x04) {
++ } else if (temp & 0x04) {
+ result = -EIO;
+ dev_dbg(&sch_adapter.dev, "Bus collision! SMBus may be "
+ "locked until next hard reset. (sorry!)\n");
+diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
+index 1c08c0921ee712..4d755ffc3f4148 100644
+--- a/drivers/iio/adc/ad7606.c
++++ b/drivers/iio/adc/ad7606.c
+@@ -215,9 +215,9 @@ static int ad7606_write_os_hw(struct iio_dev *indio_dev, int val)
+ struct ad7606_state *st = iio_priv(indio_dev);
+ DECLARE_BITMAP(values, 3);
+
+- values[0] = val;
++ values[0] = val & GENMASK(2, 0);
+
+- gpiod_set_array_value(ARRAY_SIZE(values), st->gpio_os->desc,
++ gpiod_set_array_value(st->gpio_os->ndescs, st->gpio_os->desc,
+ st->gpio_os->info, values);
+
+ /* AD7616 requires a reset to update value */
+@@ -422,7 +422,7 @@ static int ad7606_request_gpios(struct ad7606_state *st)
+ return PTR_ERR(st->gpio_range);
+
+ st->gpio_standby = devm_gpiod_get_optional(dev, "standby",
+- GPIOD_OUT_HIGH);
++ GPIOD_OUT_LOW);
+ if (IS_ERR(st->gpio_standby))
+ return PTR_ERR(st->gpio_standby);
+
+@@ -665,7 +665,7 @@ static int ad7606_suspend(struct device *dev)
+
+ if (st->gpio_standby) {
+ gpiod_set_value(st->gpio_range, 1);
+- gpiod_set_value(st->gpio_standby, 0);
++ gpiod_set_value(st->gpio_standby, 1);
+ }
+
+ return 0;
+diff --git a/drivers/iio/adc/ad7606_spi.c b/drivers/iio/adc/ad7606_spi.c
+index 263a778bcf2539..287a0591533b6a 100644
+--- a/drivers/iio/adc/ad7606_spi.c
++++ b/drivers/iio/adc/ad7606_spi.c
+@@ -249,8 +249,9 @@ static int ad7616_sw_mode_config(struct iio_dev *indio_dev)
+ static int ad7606B_sw_mode_config(struct iio_dev *indio_dev)
+ {
+ struct ad7606_state *st = iio_priv(indio_dev);
+- unsigned long os[3] = {1};
++ DECLARE_BITMAP(os, 3);
+
++ bitmap_fill(os, 3);
+ /*
+ * Software mode is enabled when all three oversampling
+ * pins are set to high. If oversampling gpios are defined
+@@ -258,7 +259,7 @@ static int ad7606B_sw_mode_config(struct iio_dev *indio_dev)
+ * otherwise, they must be hardwired to VDD
+ */
+ if (st->gpio_os) {
+- gpiod_set_array_value(ARRAY_SIZE(os),
++ gpiod_set_array_value(st->gpio_os->ndescs,
+ st->gpio_os->desc, st->gpio_os->info, os);
+ }
+ /* OS of 128 and 256 are available only in software mode */
+diff --git a/drivers/iio/chemical/bme680_core.c b/drivers/iio/chemical/bme680_core.c
+index 500f56834b01f6..a6bf689833dad7 100644
+--- a/drivers/iio/chemical/bme680_core.c
++++ b/drivers/iio/chemical/bme680_core.c
+@@ -10,6 +10,7 @@
+ */
+ #include <linux/acpi.h>
+ #include <linux/bitfield.h>
++#include <linux/cleanup.h>
+ #include <linux/delay.h>
+ #include <linux/device.h>
+ #include <linux/module.h>
+@@ -52,6 +53,7 @@ struct bme680_calib {
+ struct bme680_data {
+ struct regmap *regmap;
+ struct bme680_calib bme680;
++ struct mutex lock; /* Protect multiple serial R/W ops to device. */
+ u8 oversampling_temp;
+ u8 oversampling_press;
+ u8 oversampling_humid;
+@@ -827,6 +829,8 @@ static int bme680_read_raw(struct iio_dev *indio_dev,
+ {
+ struct bme680_data *data = iio_priv(indio_dev);
+
++ guard(mutex)(&data->lock);
++
+ switch (mask) {
+ case IIO_CHAN_INFO_PROCESSED:
+ switch (chan->type) {
+@@ -871,6 +875,8 @@ static int bme680_write_raw(struct iio_dev *indio_dev,
+ {
+ struct bme680_data *data = iio_priv(indio_dev);
+
++ guard(mutex)(&data->lock);
++
+ if (val2 != 0)
+ return -EINVAL;
+
+@@ -967,6 +973,7 @@ int bme680_core_probe(struct device *dev, struct regmap *regmap,
+ name = bme680_match_acpi_device(dev);
+
+ data = iio_priv(indio_dev);
++ mutex_init(&data->lock);
+ dev_set_drvdata(dev, indio_dev);
+ data->regmap = regmap;
+ indio_dev->name = name;
+diff --git a/drivers/iio/magnetometer/ak8975.c b/drivers/iio/magnetometer/ak8975.c
+index dd466c5fa6214f..ccbebe5b66cde2 100644
+--- a/drivers/iio/magnetometer/ak8975.c
++++ b/drivers/iio/magnetometer/ak8975.c
+@@ -1081,7 +1081,6 @@ static const struct of_device_id ak8975_of_match[] = {
+ { .compatible = "asahi-kasei,ak09912", .data = &ak_def_array[AK09912] },
+ { .compatible = "ak09912", .data = &ak_def_array[AK09912] },
+ { .compatible = "asahi-kasei,ak09916", .data = &ak_def_array[AK09916] },
+- { .compatible = "ak09916", .data = &ak_def_array[AK09916] },
+ {}
+ };
+ MODULE_DEVICE_TABLE(of, ak8975_of_match);
+diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
+index 6791df64a5fe05..b7c078b7f7cfd4 100644
+--- a/drivers/infiniband/core/cache.c
++++ b/drivers/infiniband/core/cache.c
+@@ -1640,8 +1640,10 @@ int ib_cache_setup_one(struct ib_device *device)
+
+ rdma_for_each_port (device, p) {
+ err = ib_cache_update(device, p, true, true, true);
+- if (err)
++ if (err) {
++ gid_table_cleanup_one(device);
+ return err;
++ }
+ }
+
+ return 0;
+diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
+index bf3265e6786517..7d85fe41004240 100644
+--- a/drivers/infiniband/core/iwcm.c
++++ b/drivers/infiniband/core/iwcm.c
+@@ -1190,7 +1190,7 @@ static int __init iw_cm_init(void)
+ if (ret)
+ return ret;
+
+- iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", 0);
++ iwcm_wq = alloc_ordered_workqueue("iw_cm_wq", WQ_MEM_RECLAIM);
+ if (!iwcm_wq)
+ goto err_alloc;
+
+diff --git a/drivers/infiniband/hw/cxgb4/cm.c b/drivers/infiniband/hw/cxgb4/cm.c
+index 040ba2224f9ff6..b3757c6a0457a1 100644
+--- a/drivers/infiniband/hw/cxgb4/cm.c
++++ b/drivers/infiniband/hw/cxgb4/cm.c
+@@ -1222,6 +1222,8 @@ static int act_establish(struct c4iw_dev *dev, struct sk_buff *skb)
+ int ret;
+
+ ep = lookup_atid(t, atid);
++ if (!ep)
++ return -EINVAL;
+
+ pr_debug("ep %p tid %u snd_isn %u rcv_isn %u\n", ep, tid,
+ be32_to_cpu(req->snd_isn), be32_to_cpu(req->rcv_isn));
+@@ -2279,6 +2281,9 @@ static int act_open_rpl(struct c4iw_dev *dev, struct sk_buff *skb)
+ int ret = 0;
+
+ ep = lookup_atid(t, atid);
++ if (!ep)
++ return -EINVAL;
++
+ la = (struct sockaddr_in *)&ep->com.local_addr;
+ ra = (struct sockaddr_in *)&ep->com.remote_addr;
+ la6 = (struct sockaddr_in6 *)&ep->com.local_addr;
+diff --git a/drivers/infiniband/hw/erdma/erdma_verbs.c b/drivers/infiniband/hw/erdma/erdma_verbs.c
+index 40c9b6e46b82b3..3e3a3e1c241e79 100644
+--- a/drivers/infiniband/hw/erdma/erdma_verbs.c
++++ b/drivers/infiniband/hw/erdma/erdma_verbs.c
+@@ -1544,11 +1544,31 @@ int erdma_modify_qp(struct ib_qp *ibqp, struct ib_qp_attr *attr, int attr_mask,
+ return ret;
+ }
+
++static enum ib_qp_state query_qp_state(struct erdma_qp *qp)
++{
++ switch (qp->attrs.state) {
++ case ERDMA_QP_STATE_IDLE:
++ return IB_QPS_INIT;
++ case ERDMA_QP_STATE_RTR:
++ return IB_QPS_RTR;
++ case ERDMA_QP_STATE_RTS:
++ return IB_QPS_RTS;
++ case ERDMA_QP_STATE_CLOSING:
++ return IB_QPS_ERR;
++ case ERDMA_QP_STATE_TERMINATE:
++ return IB_QPS_ERR;
++ case ERDMA_QP_STATE_ERROR:
++ return IB_QPS_ERR;
++ default:
++ return IB_QPS_ERR;
++ }
++}
++
+ int erdma_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
+ int qp_attr_mask, struct ib_qp_init_attr *qp_init_attr)
+ {
+- struct erdma_qp *qp;
+ struct erdma_dev *dev;
++ struct erdma_qp *qp;
+
+ if (ibqp && qp_attr && qp_init_attr) {
+ qp = to_eqp(ibqp);
+@@ -1575,6 +1595,9 @@ int erdma_query_qp(struct ib_qp *ibqp, struct ib_qp_attr *qp_attr,
+
+ qp_init_attr->cap = qp_attr->cap;
+
++ qp_attr->qp_state = query_qp_state(qp);
++ qp_attr->cur_qp_state = query_qp_state(qp);
++
+ return 0;
+ }
+
+diff --git a/drivers/infiniband/hw/hns/hns_roce_ah.c b/drivers/infiniband/hw/hns/hns_roce_ah.c
+index 3e02c474f59fec..4fc5b9d5fea87e 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_ah.c
++++ b/drivers/infiniband/hw/hns/hns_roce_ah.c
+@@ -64,8 +64,10 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
+ u8 tc_mode = 0;
+ int ret;
+
+- if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08 && udata)
+- return -EOPNOTSUPP;
++ if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08 && udata) {
++ ret = -EOPNOTSUPP;
++ goto err_out;
++ }
+
+ ah->av.port = rdma_ah_get_port_num(ah_attr);
+ ah->av.gid_index = grh->sgid_index;
+@@ -83,7 +85,7 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
+ ret = 0;
+
+ if (ret && grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+- return ret;
++ goto err_out;
+
+ if (tc_mode == HNAE3_TC_MAP_MODE_DSCP &&
+ grh->sgid_attr->gid_type == IB_GID_TYPE_ROCE_UDP_ENCAP)
+@@ -91,8 +93,10 @@ int hns_roce_create_ah(struct ib_ah *ibah, struct rdma_ah_init_attr *init_attr,
+ else
+ ah->av.sl = rdma_ah_get_sl(ah_attr);
+
+- if (!check_sl_valid(hr_dev, ah->av.sl))
+- return -EINVAL;
++ if (!check_sl_valid(hr_dev, ah->av.sl)) {
++ ret = -EINVAL;
++ goto err_out;
++ }
+
+ memcpy(ah->av.dgid, grh->dgid.raw, HNS_ROCE_GID_SIZE);
+ memcpy(ah->av.mac, ah_attr->roce.dmac, ETH_ALEN);
+diff --git a/drivers/infiniband/hw/hns/hns_roce_hem.c b/drivers/infiniband/hw/hns/hns_roce_hem.c
+index 02baa853a76c9b..c7c167e2a04513 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_hem.c
++++ b/drivers/infiniband/hw/hns/hns_roce_hem.c
+@@ -1041,9 +1041,9 @@ static bool hem_list_is_bottom_bt(int hopnum, int bt_level)
+ * @bt_level: base address table level
+ * @unit: ba entries per bt page
+ */
+-static u32 hem_list_calc_ba_range(int hopnum, int bt_level, int unit)
++static u64 hem_list_calc_ba_range(int hopnum, int bt_level, int unit)
+ {
+- u32 step;
++ u64 step;
+ int max;
+ int i;
+
+@@ -1079,7 +1079,7 @@ int hns_roce_hem_list_calc_root_ba(const struct hns_roce_buf_region *regions,
+ {
+ struct hns_roce_buf_region *r;
+ int total = 0;
+- int step;
++ u64 step;
+ int i;
+
+ for (i = 0; i < region_cnt; i++) {
+@@ -1110,7 +1110,7 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev,
+ int ret = 0;
+ int max_ofs;
+ int level;
+- u32 step;
++ u64 step;
+ int end;
+
+ if (hopnum <= 1)
+@@ -1134,10 +1134,12 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev,
+
+ /* config L1 bt to last bt and link them to corresponding parent */
+ for (level = 1; level < hopnum; level++) {
+- cur = hem_list_search_item(&mid_bt[level], offset);
+- if (cur) {
+- hem_ptrs[level] = cur;
+- continue;
++ if (!hem_list_is_bottom_bt(hopnum, level)) {
++ cur = hem_list_search_item(&mid_bt[level], offset);
++ if (cur) {
++ hem_ptrs[level] = cur;
++ continue;
++ }
+ }
+
+ step = hem_list_calc_ba_range(hopnum, level, unit);
+@@ -1147,7 +1149,7 @@ static int hem_list_alloc_mid_bt(struct hns_roce_dev *hr_dev,
+ }
+
+ start_aligned = (distance / step) * step + r->offset;
+- end = min_t(int, start_aligned + step - 1, max_ofs);
++ end = min_t(u64, start_aligned + step - 1, max_ofs);
+ cur = hem_list_alloc_item(hr_dev, start_aligned, end, unit,
+ true);
+ if (!cur) {
+@@ -1235,7 +1237,7 @@ static int setup_middle_bt(struct hns_roce_dev *hr_dev, void *cpu_base,
+ struct hns_roce_hem_item *hem, *temp_hem;
+ int total = 0;
+ int offset;
+- int step;
++ u64 step;
+
+ step = hem_list_calc_ba_range(r->hopnum, 1, unit);
+ if (step < 1)
+diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+index 621b057fb9daa6..24e906b9d3ae13 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
++++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+@@ -1681,8 +1681,8 @@ static int hns_roce_hw_v2_query_counter(struct hns_roce_dev *hr_dev,
+
+ for (i = 0; i < HNS_ROCE_HW_CNT_TOTAL && i < *num_counters; i++) {
+ bd_idx = i / CNT_PER_DESC;
+- if (!(desc[bd_idx].flag & HNS_ROCE_CMD_FLAG_NEXT) &&
+- bd_idx != HNS_ROCE_HW_CNT_TOTAL / CNT_PER_DESC)
++ if (bd_idx != HNS_ROCE_HW_CNT_TOTAL / CNT_PER_DESC &&
++ !(desc[bd_idx].flag & cpu_to_le16(HNS_ROCE_CMD_FLAG_NEXT)))
+ break;
+
+ cnt_data = (__le64 *)&desc[bd_idx].data[0];
+@@ -2972,6 +2972,9 @@ static int hns_roce_v2_init(struct hns_roce_dev *hr_dev)
+
+ static void hns_roce_v2_exit(struct hns_roce_dev *hr_dev)
+ {
++ if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08)
++ free_mr_exit(hr_dev);
++
+ hns_roce_function_clear(hr_dev);
+
+ if (!hr_dev->is_vf)
+@@ -4423,12 +4426,14 @@ static int config_qp_rq_buf(struct hns_roce_dev *hr_dev,
+ upper_32_bits(to_hr_hw_page_addr(mtts[0])));
+ hr_reg_clear(qpc_mask, QPC_RQ_CUR_BLK_ADDR_H);
+
+- context->rq_nxt_blk_addr = cpu_to_le32(to_hr_hw_page_addr(mtts[1]));
+- qpc_mask->rq_nxt_blk_addr = 0;
+-
+- hr_reg_write(context, QPC_RQ_NXT_BLK_ADDR_H,
+- upper_32_bits(to_hr_hw_page_addr(mtts[1])));
+- hr_reg_clear(qpc_mask, QPC_RQ_NXT_BLK_ADDR_H);
++ if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08) {
++ context->rq_nxt_blk_addr =
++ cpu_to_le32(to_hr_hw_page_addr(mtts[1]));
++ qpc_mask->rq_nxt_blk_addr = 0;
++ hr_reg_write(context, QPC_RQ_NXT_BLK_ADDR_H,
++ upper_32_bits(to_hr_hw_page_addr(mtts[1])));
++ hr_reg_clear(qpc_mask, QPC_RQ_NXT_BLK_ADDR_H);
++ }
+
+ return 0;
+ }
+@@ -6193,6 +6198,7 @@ static irqreturn_t abnormal_interrupt_basic(struct hns_roce_dev *hr_dev,
+ struct pci_dev *pdev = hr_dev->pci_dev;
+ struct hnae3_ae_dev *ae_dev = pci_get_drvdata(pdev);
+ const struct hnae3_ae_ops *ops = ae_dev->ops;
++ enum hnae3_reset_type reset_type;
+ irqreturn_t int_work = IRQ_NONE;
+ u32 int_en;
+
+@@ -6204,10 +6210,12 @@ static irqreturn_t abnormal_interrupt_basic(struct hns_roce_dev *hr_dev,
+ roce_write(hr_dev, ROCEE_VF_ABN_INT_ST_REG,
+ 1 << HNS_ROCE_V2_VF_INT_ST_AEQ_OVERFLOW_S);
+
++ reset_type = hr_dev->is_vf ?
++ HNAE3_VF_FUNC_RESET : HNAE3_FUNC_RESET;
++
+ /* Set reset level for reset_event() */
+ if (ops->set_default_reset_request)
+- ops->set_default_reset_request(ae_dev,
+- HNAE3_FUNC_RESET);
++ ops->set_default_reset_request(ae_dev, reset_type);
+ if (ops->reset_event)
+ ops->reset_event(pdev, NULL);
+
+@@ -6277,7 +6285,7 @@ static u64 fmea_get_ram_res_addr(u32 res_type, __le64 *data)
+ res_type == ECC_RESOURCE_SCCC)
+ return le64_to_cpu(*data);
+
+- return le64_to_cpu(*data) << PAGE_SHIFT;
++ return le64_to_cpu(*data) << HNS_HW_PAGE_SHIFT;
+ }
+
+ static int fmea_recover_others(struct hns_roce_dev *hr_dev, u32 res_type,
+@@ -6949,9 +6957,6 @@ static void __hns_roce_hw_v2_uninit_instance(struct hnae3_handle *handle,
+ hr_dev->state = HNS_ROCE_DEVICE_STATE_UNINIT;
+ hns_roce_handle_device_err(hr_dev);
+
+- if (hr_dev->pci_dev->revision == PCI_REVISION_ID_HIP08)
+- free_mr_exit(hr_dev);
+-
+ hns_roce_exit(hr_dev);
+ kfree(hr_dev->priv);
+ ib_dealloc_device(&hr_dev->ib_dev);
+diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
+index 1de384ce4d0e15..6b03ba671ff8f3 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
++++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
+@@ -1460,19 +1460,19 @@ void hns_roce_lock_cqs(struct hns_roce_cq *send_cq, struct hns_roce_cq *recv_cq)
+ __acquire(&send_cq->lock);
+ __acquire(&recv_cq->lock);
+ } else if (unlikely(send_cq != NULL && recv_cq == NULL)) {
+- spin_lock_irq(&send_cq->lock);
++ spin_lock(&send_cq->lock);
+ __acquire(&recv_cq->lock);
+ } else if (unlikely(send_cq == NULL && recv_cq != NULL)) {
+- spin_lock_irq(&recv_cq->lock);
++ spin_lock(&recv_cq->lock);
+ __acquire(&send_cq->lock);
+ } else if (send_cq == recv_cq) {
+- spin_lock_irq(&send_cq->lock);
++ spin_lock(&send_cq->lock);
+ __acquire(&recv_cq->lock);
+ } else if (send_cq->cqn < recv_cq->cqn) {
+- spin_lock_irq(&send_cq->lock);
++ spin_lock(&send_cq->lock);
+ spin_lock_nested(&recv_cq->lock, SINGLE_DEPTH_NESTING);
+ } else {
+- spin_lock_irq(&recv_cq->lock);
++ spin_lock(&recv_cq->lock);
+ spin_lock_nested(&send_cq->lock, SINGLE_DEPTH_NESTING);
+ }
+ }
+@@ -1492,13 +1492,13 @@ void hns_roce_unlock_cqs(struct hns_roce_cq *send_cq,
+ spin_unlock(&recv_cq->lock);
+ } else if (send_cq == recv_cq) {
+ __release(&recv_cq->lock);
+- spin_unlock_irq(&send_cq->lock);
++ spin_unlock(&send_cq->lock);
+ } else if (send_cq->cqn < recv_cq->cqn) {
+ spin_unlock(&recv_cq->lock);
+- spin_unlock_irq(&send_cq->lock);
++ spin_unlock(&send_cq->lock);
+ } else {
+ spin_unlock(&send_cq->lock);
+- spin_unlock_irq(&recv_cq->lock);
++ spin_unlock(&recv_cq->lock);
+ }
+ }
+
+diff --git a/drivers/infiniband/hw/irdma/verbs.c b/drivers/infiniband/hw/irdma/verbs.c
+index 12704efb7b19a8..954450195824c3 100644
+--- a/drivers/infiniband/hw/irdma/verbs.c
++++ b/drivers/infiniband/hw/irdma/verbs.c
+@@ -1347,7 +1347,7 @@ int irdma_modify_qp_roce(struct ib_qp *ibqp, struct ib_qp_attr *attr,
+ if (attr->max_dest_rd_atomic > dev->hw_attrs.max_hw_ird) {
+ ibdev_err(&iwdev->ibdev,
+ "rd_atomic = %d, above max_hw_ird=%d\n",
+- attr->max_rd_atomic,
++ attr->max_dest_rd_atomic,
+ dev->hw_attrs.max_hw_ird);
+ return -EINVAL;
+ }
+diff --git a/drivers/infiniband/hw/mlx5/main.c b/drivers/infiniband/hw/mlx5/main.c
+index 43660c831b22cf..fdb0e62d805b9a 100644
+--- a/drivers/infiniband/hw/mlx5/main.c
++++ b/drivers/infiniband/hw/mlx5/main.c
+@@ -542,7 +542,7 @@ static int mlx5_query_port_roce(struct ib_device *device, u32 port_num,
+ if (!ndev)
+ goto out;
+
+- if (dev->lag_active) {
++ if (mlx5_lag_is_roce(mdev) || mlx5_lag_is_sriov(mdev)) {
+ rcu_read_lock();
+ upper = netdev_master_upper_dev_get_rcu(ndev);
+ if (upper) {
+diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
+index f9abdca3493aa9..0b2f18c34ee5e6 100644
+--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
++++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
+@@ -795,6 +795,7 @@ struct mlx5_cache_ent {
+ u8 is_tmp:1;
+ u8 disabled:1;
+ u8 fill_to_high_water:1;
++ u8 tmp_cleanup_scheduled:1;
+
+ /*
+ * - limit is the low water mark for stored mkeys, 2* limit is the
+@@ -826,7 +827,6 @@ struct mlx5_mkey_cache {
+ struct mutex rb_lock;
+ struct dentry *fs_root;
+ unsigned long last_add;
+- struct delayed_work remove_ent_dwork;
+ };
+
+ struct mlx5_ib_port_resources {
+diff --git a/drivers/infiniband/hw/mlx5/mr.c b/drivers/infiniband/hw/mlx5/mr.c
+index d3c1f63791a2b6..59bde614f061f5 100644
+--- a/drivers/infiniband/hw/mlx5/mr.c
++++ b/drivers/infiniband/hw/mlx5/mr.c
+@@ -48,6 +48,7 @@ enum {
+ MAX_PENDING_REG_MR = 8,
+ };
+
++#define MLX5_MR_CACHE_PERSISTENT_ENTRY_MIN_DESCS 4
+ #define MLX5_UMR_ALIGN 2048
+
+ static void
+@@ -211,9 +212,9 @@ static void create_mkey_callback(int status, struct mlx5_async_work *context)
+
+ spin_lock_irqsave(&ent->mkeys_queue.lock, flags);
+ push_mkey_locked(ent, mkey_out->mkey);
++ ent->pending--;
+ /* If we are doing fill_to_high_water then keep going. */
+ queue_adjust_cache_locked(ent);
+- ent->pending--;
+ spin_unlock_irqrestore(&ent->mkeys_queue.lock, flags);
+ kfree(mkey_out);
+ }
+@@ -527,6 +528,21 @@ static void queue_adjust_cache_locked(struct mlx5_cache_ent *ent)
+ }
+ }
+
++static void clean_keys(struct mlx5_ib_dev *dev, struct mlx5_cache_ent *ent)
++{
++ u32 mkey;
++
++ spin_lock_irq(&ent->mkeys_queue.lock);
++ while (ent->mkeys_queue.ci) {
++ mkey = pop_mkey_locked(ent);
++ spin_unlock_irq(&ent->mkeys_queue.lock);
++ mlx5_core_destroy_mkey(dev->mdev, mkey);
++ spin_lock_irq(&ent->mkeys_queue.lock);
++ }
++ ent->tmp_cleanup_scheduled = false;
++ spin_unlock_irq(&ent->mkeys_queue.lock);
++}
++
+ static void __cache_work_func(struct mlx5_cache_ent *ent)
+ {
+ struct mlx5_ib_dev *dev = ent->dev;
+@@ -598,7 +614,11 @@ static void delayed_cache_work_func(struct work_struct *work)
+ struct mlx5_cache_ent *ent;
+
+ ent = container_of(work, struct mlx5_cache_ent, dwork.work);
+- __cache_work_func(ent);
++ /* temp entries are never filled, only cleaned */
++ if (ent->is_tmp)
++ clean_keys(ent->dev, ent);
++ else
++ __cache_work_func(ent);
+ }
+
+ static int cache_ent_key_cmp(struct mlx5r_cache_rb_key key1,
+@@ -659,6 +679,7 @@ mkey_cache_ent_from_rb_key(struct mlx5_ib_dev *dev,
+ {
+ struct rb_node *node = dev->cache.rb_root.rb_node;
+ struct mlx5_cache_ent *cur, *smallest = NULL;
++ u64 ndescs_limit;
+ int cmp;
+
+ /*
+@@ -677,10 +698,18 @@ mkey_cache_ent_from_rb_key(struct mlx5_ib_dev *dev,
+ return cur;
+ }
+
++ /*
++ * Limit the usage of mkeys larger than twice the required size while
++ * also allowing the usage of smallest cache entry for small MRs.
++ */
++ ndescs_limit = max_t(u64, rb_key.ndescs * 2,
++ MLX5_MR_CACHE_PERSISTENT_ENTRY_MIN_DESCS);
++
+ return (smallest &&
+ smallest->rb_key.access_mode == rb_key.access_mode &&
+ smallest->rb_key.access_flags == rb_key.access_flags &&
+- smallest->rb_key.ats == rb_key.ats) ?
++ smallest->rb_key.ats == rb_key.ats &&
++ smallest->rb_key.ndescs <= ndescs_limit) ?
+ smallest :
+ NULL;
+ }
+@@ -765,21 +794,6 @@ struct mlx5_ib_mr *mlx5_mr_cache_alloc(struct mlx5_ib_dev *dev,
+ return _mlx5_mr_cache_alloc(dev, ent, access_flags);
+ }
+
+-static void clean_keys(struct mlx5_ib_dev *dev, struct mlx5_cache_ent *ent)
+-{
+- u32 mkey;
+-
+- cancel_delayed_work(&ent->dwork);
+- spin_lock_irq(&ent->mkeys_queue.lock);
+- while (ent->mkeys_queue.ci) {
+- mkey = pop_mkey_locked(ent);
+- spin_unlock_irq(&ent->mkeys_queue.lock);
+- mlx5_core_destroy_mkey(dev->mdev, mkey);
+- spin_lock_irq(&ent->mkeys_queue.lock);
+- }
+- spin_unlock_irq(&ent->mkeys_queue.lock);
+-}
+-
+ static void mlx5_mkey_cache_debugfs_cleanup(struct mlx5_ib_dev *dev)
+ {
+ if (!mlx5_debugfs_root || dev->is_rep)
+@@ -892,10 +906,6 @@ mlx5r_cache_create_ent_locked(struct mlx5_ib_dev *dev,
+ ent->limit = 0;
+
+ mlx5_mkey_cache_debugfs_add_ent(dev, ent);
+- } else {
+- mod_delayed_work(ent->dev->cache.wq,
+- &ent->dev->cache.remove_ent_dwork,
+- msecs_to_jiffies(30 * 1000));
+ }
+
+ return ent;
+@@ -906,35 +916,6 @@ mlx5r_cache_create_ent_locked(struct mlx5_ib_dev *dev,
+ return ERR_PTR(ret);
+ }
+
+-static void remove_ent_work_func(struct work_struct *work)
+-{
+- struct mlx5_mkey_cache *cache;
+- struct mlx5_cache_ent *ent;
+- struct rb_node *cur;
+-
+- cache = container_of(work, struct mlx5_mkey_cache,
+- remove_ent_dwork.work);
+- mutex_lock(&cache->rb_lock);
+- cur = rb_last(&cache->rb_root);
+- while (cur) {
+- ent = rb_entry(cur, struct mlx5_cache_ent, node);
+- cur = rb_prev(cur);
+- mutex_unlock(&cache->rb_lock);
+-
+- spin_lock_irq(&ent->mkeys_queue.lock);
+- if (!ent->is_tmp) {
+- spin_unlock_irq(&ent->mkeys_queue.lock);
+- mutex_lock(&cache->rb_lock);
+- continue;
+- }
+- spin_unlock_irq(&ent->mkeys_queue.lock);
+-
+- clean_keys(ent->dev, ent);
+- mutex_lock(&cache->rb_lock);
+- }
+- mutex_unlock(&cache->rb_lock);
+-}
+-
+ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
+ {
+ struct mlx5_mkey_cache *cache = &dev->cache;
+@@ -950,7 +931,6 @@ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
+ mutex_init(&dev->slow_path_mutex);
+ mutex_init(&dev->cache.rb_lock);
+ dev->cache.rb_root = RB_ROOT;
+- INIT_DELAYED_WORK(&dev->cache.remove_ent_dwork, remove_ent_work_func);
+ cache->wq = alloc_ordered_workqueue("mkey_cache", WQ_MEM_RECLAIM);
+ if (!cache->wq) {
+ mlx5_ib_warn(dev, "failed to create work queue\n");
+@@ -962,7 +942,7 @@ int mlx5_mkey_cache_init(struct mlx5_ib_dev *dev)
+ mlx5_mkey_cache_debugfs_init(dev);
+ mutex_lock(&cache->rb_lock);
+ for (i = 0; i <= mkey_cache_max_order(dev); i++) {
+- rb_key.ndescs = 1 << (i + 2);
++ rb_key.ndescs = MLX5_MR_CACHE_PERSISTENT_ENTRY_MIN_DESCS << i;
+ ent = mlx5r_cache_create_ent_locked(dev, rb_key, true);
+ if (IS_ERR(ent)) {
+ ret = PTR_ERR(ent);
+@@ -1001,7 +981,6 @@ void mlx5_mkey_cache_cleanup(struct mlx5_ib_dev *dev)
+ return;
+
+ mutex_lock(&dev->cache.rb_lock);
+- cancel_delayed_work(&dev->cache.remove_ent_dwork);
+ for (node = rb_first(root); node; node = rb_next(node)) {
+ ent = rb_entry(node, struct mlx5_cache_ent, node);
+ spin_lock_irq(&ent->mkeys_queue.lock);
+@@ -1843,8 +1822,18 @@ static int mlx5_revoke_mr(struct mlx5_ib_mr *mr)
+ struct mlx5_ib_dev *dev = to_mdev(mr->ibmr.device);
+ struct mlx5_cache_ent *ent = mr->mmkey.cache_ent;
+
+- if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr))
++ if (mr->mmkey.cacheable && !mlx5r_umr_revoke_mr(mr) && !cache_ent_find_and_store(dev, mr)) {
++ ent = mr->mmkey.cache_ent;
++ /* upon storing to a clean temp entry - schedule its cleanup */
++ spin_lock_irq(&ent->mkeys_queue.lock);
++ if (ent->is_tmp && !ent->tmp_cleanup_scheduled) {
++ mod_delayed_work(ent->dev->cache.wq, &ent->dwork,
++ msecs_to_jiffies(30 * 1000));
++ ent->tmp_cleanup_scheduled = true;
++ }
++ spin_unlock_irq(&ent->mkeys_queue.lock);
+ return 0;
++ }
+
+ if (ent) {
+ spin_lock_irq(&ent->mkeys_queue.lock);
+diff --git a/drivers/infiniband/ulp/rtrs/rtrs-clt.c b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+index 88106cf5ce550c..84d2dfcd20af6f 100644
+--- a/drivers/infiniband/ulp/rtrs/rtrs-clt.c
++++ b/drivers/infiniband/ulp/rtrs/rtrs-clt.c
+@@ -626,6 +626,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
+ */
+ if (WARN_ON(wc->wr_cqe->done != rtrs_clt_rdma_done))
+ return;
++ clt_path->s.hb_missed_cnt = 0;
+ rtrs_from_imm(be32_to_cpu(wc->ex.imm_data),
+ &imm_type, &imm_payload);
+ if (imm_type == RTRS_IO_RSP_IMM ||
+@@ -643,7 +644,6 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
+ return rtrs_clt_recv_done(con, wc);
+ } else if (imm_type == RTRS_HB_ACK_IMM) {
+ WARN_ON(con->c.cid);
+- clt_path->s.hb_missed_cnt = 0;
+ clt_path->s.hb_cur_latency =
+ ktime_sub(ktime_get(), clt_path->s.hb_last_sent);
+ if (clt_path->flags & RTRS_MSG_NEW_RKEY_F)
+@@ -670,6 +670,7 @@ static void rtrs_clt_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
+ /*
+ * Key invalidations from server side
+ */
++ clt_path->s.hb_missed_cnt = 0;
+ WARN_ON(!(wc->wc_flags & IB_WC_WITH_INVALIDATE ||
+ wc->wc_flags & IB_WC_WITH_IMM));
+ WARN_ON(wc->wr_cqe->done != rtrs_clt_rdma_done);
+@@ -2346,6 +2347,12 @@ static int init_conns(struct rtrs_clt_path *clt_path)
+ if (err)
+ goto destroy;
+ }
++
++ /*
++ * Set the cid to con_num - 1, since if we fail later, we want to stay in bounds.
++ */
++ cid = clt_path->s.con_num - 1;
++
+ err = alloc_path_reqs(clt_path);
+ if (err)
+ goto destroy;
+diff --git a/drivers/infiniband/ulp/rtrs/rtrs-srv.c b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+index 1d33efb8fb03be..94ac99a4f696e7 100644
+--- a/drivers/infiniband/ulp/rtrs/rtrs-srv.c
++++ b/drivers/infiniband/ulp/rtrs/rtrs-srv.c
+@@ -1229,6 +1229,7 @@ static void rtrs_srv_rdma_done(struct ib_cq *cq, struct ib_wc *wc)
+ */
+ if (WARN_ON(wc->wr_cqe != &io_comp_cqe))
+ return;
++ srv_path->s.hb_missed_cnt = 0;
+ err = rtrs_post_recv_empty(&con->c, &io_comp_cqe);
+ if (err) {
+ rtrs_err(s, "rtrs_post_recv(), err: %d\n", err);
+diff --git a/drivers/input/keyboard/adp5588-keys.c b/drivers/input/keyboard/adp5588-keys.c
+index 1b0279393df4bb..5acaffb7f6e11d 100644
+--- a/drivers/input/keyboard/adp5588-keys.c
++++ b/drivers/input/keyboard/adp5588-keys.c
+@@ -627,7 +627,7 @@ static int adp5588_setup(struct adp5588_kpad *kpad)
+
+ for (i = 0; i < KEYP_MAX_EVENT; i++) {
+ ret = adp5588_read(client, KEY_EVENTA);
+- if (ret)
++ if (ret < 0)
+ return ret;
+ }
+
+diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
+index bad238f69a7afd..34d1f07ea4c304 100644
+--- a/drivers/input/serio/i8042-acpipnpio.h
++++ b/drivers/input/serio/i8042-acpipnpio.h
+@@ -1120,6 +1120,43 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
+ },
+ .driver_data = (void *)(SERIO_QUIRK_NOLOOP)
+ },
++ /*
++ * Some TongFang barebones have touchpad and/or keyboard issues after
++ * suspend fixable with nomux + reset + noloop + nopnp. Luckily, none of
++ * them have an external PS/2 port so this can safely be set for all of
++ * them.
++ * TongFang barebones come with board_vendor and/or system_vendor set to
++ * a different value for each individual reseller. The only somewhat
++ * universal way to identify them is by board_name.
++ */
++ {
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "GM6XGxX"),
++ },
++ .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
++ SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
++ },
++ {
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "GMxXGxx"),
++ },
++ .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
++ SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
++ },
++ {
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "GMxXGxX"),
++ },
++ .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
++ SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
++ },
++ {
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "GMxHGxx"),
++ },
++ .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
++ SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
++ },
+ /*
+ * A lot of modern Clevo barebones have touchpad and/or keyboard issues
+ * after suspend fixable with nomux + reset + noloop + nopnp. Luckily,
+diff --git a/drivers/input/touchscreen/ilitek_ts_i2c.c b/drivers/input/touchscreen/ilitek_ts_i2c.c
+index 3eb762896345b7..5a807ad723190d 100644
+--- a/drivers/input/touchscreen/ilitek_ts_i2c.c
++++ b/drivers/input/touchscreen/ilitek_ts_i2c.c
+@@ -37,6 +37,8 @@
+ #define ILITEK_TP_CMD_GET_MCU_VER 0x61
+ #define ILITEK_TP_CMD_GET_IC_MODE 0xC0
+
++#define ILITEK_TP_I2C_REPORT_ID 0x48
++
+ #define REPORT_COUNT_ADDRESS 61
+ #define ILITEK_SUPPORT_MAX_POINT 40
+
+@@ -160,15 +162,19 @@ static int ilitek_process_and_report_v6(struct ilitek_ts_data *ts)
+ error = ilitek_i2c_write_and_read(ts, NULL, 0, 0, buf, 64);
+ if (error) {
+ dev_err(dev, "get touch info failed, err:%d\n", error);
+- goto err_sync_frame;
++ return error;
++ }
++
++ if (buf[0] != ILITEK_TP_I2C_REPORT_ID) {
++ dev_err(dev, "get touch info failed. Wrong id: 0x%02X\n", buf[0]);
++ return -EINVAL;
+ }
+
+ report_max_point = buf[REPORT_COUNT_ADDRESS];
+ if (report_max_point > ts->max_tp) {
+ dev_err(dev, "FW report max point:%d > panel info. max:%d\n",
+ report_max_point, ts->max_tp);
+- error = -EINVAL;
+- goto err_sync_frame;
++ return -EINVAL;
+ }
+
+ count = DIV_ROUND_UP(report_max_point, packet_max_point);
+@@ -178,7 +184,7 @@ static int ilitek_process_and_report_v6(struct ilitek_ts_data *ts)
+ if (error) {
+ dev_err(dev, "get touch info. failed, cnt:%d, err:%d\n",
+ count, error);
+- goto err_sync_frame;
++ return error;
+ }
+ }
+
+@@ -203,10 +209,10 @@ static int ilitek_process_and_report_v6(struct ilitek_ts_data *ts)
+ ilitek_touch_down(ts, id, x, y);
+ }
+
+-err_sync_frame:
+ input_mt_sync_frame(input);
+ input_sync(input);
+- return error;
++
++ return 0;
+ }
+
+ /* APIs of cmds for ILITEK Touch IC */
+diff --git a/drivers/interconnect/icc-clk.c b/drivers/interconnect/icc-clk.c
+index d787f2ea36d97b..a91df709cfb2f3 100644
+--- a/drivers/interconnect/icc-clk.c
++++ b/drivers/interconnect/icc-clk.c
+@@ -87,6 +87,7 @@ struct icc_provider *icc_clk_register(struct device *dev,
+ onecell = devm_kzalloc(dev, struct_size(onecell, nodes, 2 * num_clocks), GFP_KERNEL);
+ if (!onecell)
+ return ERR_PTR(-ENOMEM);
++ onecell->num_nodes = 2 * num_clocks;
+
+ qp = devm_kzalloc(dev, struct_size(qp, clocks, num_clocks), GFP_KERNEL);
+ if (!qp)
+@@ -133,8 +134,6 @@ struct icc_provider *icc_clk_register(struct device *dev,
+ onecell->nodes[j++] = node;
+ }
+
+- onecell->num_nodes = j;
+-
+ ret = icc_provider_register(provider);
+ if (ret)
+ goto err;
+diff --git a/drivers/interconnect/qcom/sm8350.c b/drivers/interconnect/qcom/sm8350.c
+index b321c3009acbac..885a9d3f92e4d1 100644
+--- a/drivers/interconnect/qcom/sm8350.c
++++ b/drivers/interconnect/qcom/sm8350.c
+@@ -1965,6 +1965,7 @@ static struct platform_driver qnoc_driver = {
+ .driver = {
+ .name = "qnoc-sm8350",
+ .of_match_table = qnoc_of_match,
++ .sync_state = icc_sync_state,
+ },
+ };
+ module_platform_driver(qnoc_driver);
+diff --git a/drivers/iommu/amd/io_pgtable.c b/drivers/iommu/amd/io_pgtable.c
+index 9d9a7fde59e75d..05aed3cb46f1bf 100644
+--- a/drivers/iommu/amd/io_pgtable.c
++++ b/drivers/iommu/amd/io_pgtable.c
+@@ -574,23 +574,27 @@ static void v1_free_pgtable(struct io_pgtable *iop)
+ pgtable->mode > PAGE_MODE_6_LEVEL);
+
+ free_sub_pt(pgtable->root, pgtable->mode, &freelist);
++ iommu_put_pages_list(&freelist);
+
+ /* Update data structure */
+ amd_iommu_domain_clr_pt_root(dom);
+
+ /* Make changes visible to IOMMUs */
+ amd_iommu_domain_update(dom);
+-
+- iommu_put_pages_list(&freelist);
+ }
+
+ static struct io_pgtable *v1_alloc_pgtable(struct io_pgtable_cfg *cfg, void *cookie)
+ {
+ struct amd_io_pgtable *pgtable = io_pgtable_cfg_to_data(cfg);
+
+- cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES,
+- cfg->ias = IOMMU_IN_ADDR_BIT_SIZE,
+- cfg->oas = IOMMU_OUT_ADDR_BIT_SIZE,
++ pgtable->root = iommu_alloc_page(GFP_KERNEL);
++ if (!pgtable->root)
++ return NULL;
++ pgtable->mode = PAGE_MODE_3_LEVEL;
++
++ cfg->pgsize_bitmap = AMD_IOMMU_PGSIZES;
++ cfg->ias = IOMMU_IN_ADDR_BIT_SIZE;
++ cfg->oas = IOMMU_OUT_ADDR_BIT_SIZE;
+ cfg->tlb = &v1_flush_ops;
+
+ pgtable->iop.ops.map_pages = iommu_v1_map_pages;
+diff --git a/drivers/iommu/amd/io_pgtable_v2.c b/drivers/iommu/amd/io_pgtable_v2.c
+index 78ac37c5ccc1e0..743f417b281d4b 100644
+--- a/drivers/iommu/amd/io_pgtable_v2.c
++++ b/drivers/iommu/amd/io_pgtable_v2.c
+@@ -51,7 +51,7 @@ static inline u64 set_pgtable_attr(u64 *page)
+ u64 prot;
+
+ prot = IOMMU_PAGE_PRESENT | IOMMU_PAGE_RW | IOMMU_PAGE_USER;
+- prot |= IOMMU_PAGE_ACCESS | IOMMU_PAGE_DIRTY;
++ prot |= IOMMU_PAGE_ACCESS;
+
+ return (iommu_virt_to_phys(page) | prot);
+ }
+@@ -362,7 +362,7 @@ static struct io_pgtable *v2_alloc_pgtable(struct io_pgtable_cfg *cfg, void *coo
+ struct protection_domain *pdom = (struct protection_domain *)cookie;
+ int ias = IOMMU_IN_ADDR_BIT_SIZE;
+
+- pgtable->pgd = iommu_alloc_page_node(pdom->nid, GFP_ATOMIC);
++ pgtable->pgd = iommu_alloc_page_node(pdom->nid, GFP_KERNEL);
+ if (!pgtable->pgd)
+ return NULL;
+
+diff --git a/drivers/iommu/amd/iommu.c b/drivers/iommu/amd/iommu.c
+index b19e8c0f48fa25..1a61f14459e4fe 100644
+--- a/drivers/iommu/amd/iommu.c
++++ b/drivers/iommu/amd/iommu.c
+@@ -52,8 +52,6 @@
+ #define HT_RANGE_START (0xfd00000000ULL)
+ #define HT_RANGE_END (0xffffffffffULL)
+
+-#define DEFAULT_PGTABLE_LEVEL PAGE_MODE_3_LEVEL
+-
+ static DEFINE_SPINLOCK(pd_bitmap_lock);
+
+ LIST_HEAD(ioapic_map);
+@@ -1552,8 +1550,8 @@ void amd_iommu_dev_flush_pasid_pages(struct iommu_dev_data *dev_data,
+ void amd_iommu_dev_flush_pasid_all(struct iommu_dev_data *dev_data,
+ ioasid_t pasid)
+ {
+- amd_iommu_dev_flush_pasid_pages(dev_data, 0,
+- CMD_INV_IOMMU_ALL_PAGES_ADDRESS, pasid);
++ amd_iommu_dev_flush_pasid_pages(dev_data, pasid, 0,
++ CMD_INV_IOMMU_ALL_PAGES_ADDRESS);
+ }
+
+ void amd_iommu_domain_flush_complete(struct protection_domain *domain)
+@@ -2185,11 +2183,12 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
+ dev_err(dev, "Failed to initialize - trying to proceed anyway\n");
+ iommu_dev = ERR_PTR(ret);
+ iommu_ignore_device(iommu, dev);
+- } else {
+- amd_iommu_set_pci_msi_domain(dev, iommu);
+- iommu_dev = &iommu->iommu;
++ goto out_err;
+ }
+
++ amd_iommu_set_pci_msi_domain(dev, iommu);
++ iommu_dev = &iommu->iommu;
++
+ /*
+ * If IOMMU and device supports PASID then it will contain max
+ * supported PASIDs, else it will be zero.
+@@ -2201,6 +2200,7 @@ static struct iommu_device *amd_iommu_probe_device(struct device *dev)
+ pci_max_pasids(to_pci_dev(dev)));
+ }
+
++out_err:
+ iommu_completion_wait(iommu);
+
+ return iommu_dev;
+@@ -2265,47 +2265,17 @@ void protection_domain_free(struct protection_domain *domain)
+ if (domain->iop.pgtbl_cfg.tlb)
+ free_io_pgtable_ops(&domain->iop.iop.ops);
+
+- if (domain->iop.root)
+- iommu_free_page(domain->iop.root);
+-
+ if (domain->id)
+ domain_id_free(domain->id);
+
+ kfree(domain);
+ }
+
+-static int protection_domain_init_v1(struct protection_domain *domain, int mode)
+-{
+- u64 *pt_root = NULL;
+-
+- BUG_ON(mode < PAGE_MODE_NONE || mode > PAGE_MODE_6_LEVEL);
+-
+- if (mode != PAGE_MODE_NONE) {
+- pt_root = iommu_alloc_page(GFP_KERNEL);
+- if (!pt_root)
+- return -ENOMEM;
+- }
+-
+- domain->pd_mode = PD_MODE_V1;
+- amd_iommu_domain_set_pgtable(domain, pt_root, mode);
+-
+- return 0;
+-}
+-
+-static int protection_domain_init_v2(struct protection_domain *pdom)
+-{
+- pdom->pd_mode = PD_MODE_V2;
+- pdom->domain.pgsize_bitmap = AMD_IOMMU_PGSIZES_V2;
+-
+- return 0;
+-}
+-
+ struct protection_domain *protection_domain_alloc(unsigned int type)
+ {
+ struct io_pgtable_ops *pgtbl_ops;
+ struct protection_domain *domain;
+ int pgtable;
+- int ret;
+
+ domain = kzalloc(sizeof(*domain), GFP_KERNEL);
+ if (!domain)
+@@ -2341,18 +2311,14 @@ struct protection_domain *protection_domain_alloc(unsigned int type)
+
+ switch (pgtable) {
+ case AMD_IOMMU_V1:
+- ret = protection_domain_init_v1(domain, DEFAULT_PGTABLE_LEVEL);
++ domain->pd_mode = PD_MODE_V1;
+ break;
+ case AMD_IOMMU_V2:
+- ret = protection_domain_init_v2(domain);
++ domain->pd_mode = PD_MODE_V2;
+ break;
+ default:
+- ret = -EINVAL;
+- break;
+- }
+-
+- if (ret)
+ goto out_err;
++ }
+
+ pgtbl_ops = alloc_io_pgtable_ops(pgtable, &domain->iop.pgtbl_cfg, domain);
+ if (!pgtbl_ops)
+@@ -2405,10 +2371,10 @@ static struct iommu_domain *do_iommu_domain_alloc(unsigned int type,
+ domain->domain.geometry.aperture_start = 0;
+ domain->domain.geometry.aperture_end = dma_max_address();
+ domain->domain.geometry.force_aperture = true;
++ domain->domain.pgsize_bitmap = domain->iop.iop.cfg.pgsize_bitmap;
+
+ if (iommu) {
+ domain->domain.type = type;
+- domain->domain.pgsize_bitmap = iommu->iommu.ops->pgsize_bitmap;
+ domain->domain.ops = iommu->iommu.ops->default_domain_ops;
+
+ if (dirty_tracking)
+@@ -2867,7 +2833,6 @@ const struct iommu_ops amd_iommu_ops = {
+ .device_group = amd_iommu_device_group,
+ .get_resv_regions = amd_iommu_get_resv_regions,
+ .is_attach_deferred = amd_iommu_is_attach_deferred,
+- .pgsize_bitmap = AMD_IOMMU_PGSIZES,
+ .def_domain_type = amd_iommu_def_domain_type,
+ .dev_enable_feat = amd_iommu_dev_enable_feature,
+ .dev_disable_feat = amd_iommu_dev_disable_feature,
+diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+index 13f3e2efb2ccbf..ccca410c948164 100644
+--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
++++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+@@ -282,6 +282,20 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
+ u32 smr;
+ int i;
+
++ /*
++ * MSM8998 LPASS SMMU reports 13 context banks, but accessing
++ * the last context bank crashes the system.
++ */
++ if (of_device_is_compatible(smmu->dev->of_node, "qcom,msm8998-smmu-v2") &&
++ smmu->num_context_banks == 13) {
++ smmu->num_context_banks = 12;
++ } else if (of_device_is_compatible(smmu->dev->of_node, "qcom,sdm630-smmu-v2")) {
++ if (smmu->num_context_banks == 21) /* SDM630 / SDM660 A2NOC SMMU */
++ smmu->num_context_banks = 7;
++ else if (smmu->num_context_banks == 14) /* SDM630 / SDM660 LPASS SMMU */
++ smmu->num_context_banks = 13;
++ }
++
+ /*
+ * Some platforms support more than the Arm SMMU architected maximum of
+ * 128 stream matching groups. For unknown reasons, the additional
+@@ -338,6 +352,19 @@ static int qcom_smmu_cfg_probe(struct arm_smmu_device *smmu)
+ return 0;
+ }
+
++static int qcom_adreno_smmuv2_cfg_probe(struct arm_smmu_device *smmu)
++{
++ /* Support for 16K pages is advertised on some SoCs, but it doesn't seem to work */
++ smmu->features &= ~ARM_SMMU_FEAT_FMT_AARCH64_16K;
++
++ /* TZ protects several last context banks, hide them from Linux */
++ if (of_device_is_compatible(smmu->dev->of_node, "qcom,sdm630-smmu-v2") &&
++ smmu->num_context_banks == 5)
++ smmu->num_context_banks = 2;
++
++ return 0;
++}
++
+ static void qcom_smmu_write_s2cr(struct arm_smmu_device *smmu, int idx)
+ {
+ struct arm_smmu_s2cr *s2cr = smmu->s2crs + idx;
+@@ -436,6 +463,7 @@ static const struct arm_smmu_impl sdm845_smmu_500_impl = {
+
+ static const struct arm_smmu_impl qcom_adreno_smmu_v2_impl = {
+ .init_context = qcom_adreno_smmu_init_context,
++ .cfg_probe = qcom_adreno_smmuv2_cfg_probe,
+ .def_domain_type = qcom_smmu_def_domain_type,
+ .alloc_context_bank = qcom_adreno_smmu_alloc_context_bank,
+ .write_sctlr = qcom_adreno_smmu_write_sctlr,
+diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
+index a9f1fe44c4c0bd..21f0d8cbd7aade 100644
+--- a/drivers/iommu/iommufd/hw_pagetable.c
++++ b/drivers/iommu/iommufd/hw_pagetable.c
+@@ -215,7 +215,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
+
+ if (flags || !user_data->len || !ops->domain_alloc_user)
+ return ERR_PTR(-EOPNOTSUPP);
+- if (parent->auto_domain || !parent->nest_parent)
++ if (parent->auto_domain || !parent->nest_parent ||
++ parent->common.domain->owner != ops)
+ return ERR_PTR(-EINVAL);
+
+ hwpt_nested = __iommufd_object_alloc(
+diff --git a/drivers/iommu/iommufd/io_pagetable.c b/drivers/iommu/iommufd/io_pagetable.c
+index 05fd9d3abf1b80..9f193c933de6ef 100644
+--- a/drivers/iommu/iommufd/io_pagetable.c
++++ b/drivers/iommu/iommufd/io_pagetable.c
+@@ -112,6 +112,7 @@ static int iopt_alloc_iova(struct io_pagetable *iopt, unsigned long *iova,
+ unsigned long page_offset = uptr % PAGE_SIZE;
+ struct interval_tree_double_span_iter used_span;
+ struct interval_tree_span_iter allowed_span;
++ unsigned long max_alignment = PAGE_SIZE;
+ unsigned long iova_alignment;
+
+ lockdep_assert_held(&iopt->iova_rwsem);
+@@ -131,6 +132,13 @@ static int iopt_alloc_iova(struct io_pagetable *iopt, unsigned long *iova,
+ roundup_pow_of_two(length),
+ 1UL << __ffs64(uptr));
+
++#ifdef CONFIG_TRANSPARENT_HUGEPAGE
++ max_alignment = HPAGE_SIZE;
++#endif
++ /* Protect against ALIGN() overflow */
++ if (iova_alignment >= max_alignment)
++ iova_alignment = max_alignment;
++
+ if (iova_alignment < iopt->iova_alignment)
+ return -EINVAL;
+
+diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
+index 654ed333909579..62bfeb7a35d850 100644
+--- a/drivers/iommu/iommufd/selftest.c
++++ b/drivers/iommu/iommufd/selftest.c
+@@ -1313,7 +1313,7 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
+ unsigned long page_size, void __user *uptr,
+ u32 flags)
+ {
+- unsigned long bitmap_size, i, max;
++ unsigned long i, max;
+ struct iommu_test_cmd *cmd = ucmd->cmd;
+ struct iommufd_hw_pagetable *hwpt;
+ struct mock_iommu_domain *mock;
+@@ -1334,15 +1334,14 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
+ }
+
+ max = length / page_size;
+- bitmap_size = DIV_ROUND_UP(max, BITS_PER_BYTE);
+-
+- tmp = kvzalloc(bitmap_size, GFP_KERNEL_ACCOUNT);
++ tmp = kvzalloc(DIV_ROUND_UP(max, BITS_PER_LONG) * sizeof(unsigned long),
++ GFP_KERNEL_ACCOUNT);
+ if (!tmp) {
+ rc = -ENOMEM;
+ goto out_put;
+ }
+
+- if (copy_from_user(tmp, uptr, bitmap_size)) {
++ if (copy_from_user(tmp, uptr,DIV_ROUND_UP(max, BITS_PER_BYTE))) {
+ rc = -EFAULT;
+ goto out_free;
+ }
+diff --git a/drivers/leds/leds-bd2606mvv.c b/drivers/leds/leds-bd2606mvv.c
+index 3fda712d2f8095..c1181a35d0f762 100644
+--- a/drivers/leds/leds-bd2606mvv.c
++++ b/drivers/leds/leds-bd2606mvv.c
+@@ -69,16 +69,14 @@ static const struct regmap_config bd2606mvv_regmap = {
+
+ static int bd2606mvv_probe(struct i2c_client *client)
+ {
+- struct fwnode_handle *np, *child;
+ struct device *dev = &client->dev;
+ struct bd2606mvv_priv *priv;
+ struct fwnode_handle *led_fwnodes[BD2606_MAX_LEDS] = { 0 };
+ int active_pairs[BD2606_MAX_LEDS / 2] = { 0 };
+ int err, reg;
+- int i;
++ int i, j;
+
+- np = dev_fwnode(dev);
+- if (!np)
++ if (!dev_fwnode(dev))
+ return -ENODEV;
+
+ priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+@@ -94,20 +92,18 @@ static int bd2606mvv_probe(struct i2c_client *client)
+
+ i2c_set_clientdata(client, priv);
+
+- fwnode_for_each_available_child_node(np, child) {
++ device_for_each_child_node_scoped(dev, child) {
+ struct bd2606mvv_led *led;
+
+ err = fwnode_property_read_u32(child, "reg", ®);
+- if (err) {
+- fwnode_handle_put(child);
++ if (err)
+ return err;
+- }
+- if (reg < 0 || reg >= BD2606_MAX_LEDS || led_fwnodes[reg]) {
+- fwnode_handle_put(child);
++
++ if (reg < 0 || reg >= BD2606_MAX_LEDS || led_fwnodes[reg])
+ return -EINVAL;
+- }
++
+ led = &priv->leds[reg];
+- led_fwnodes[reg] = child;
++ led_fwnodes[reg] = fwnode_handle_get(child);
+ active_pairs[reg / 2]++;
+ led->priv = priv;
+ led->led_no = reg;
+@@ -130,7 +126,8 @@ static int bd2606mvv_probe(struct i2c_client *client)
+ &priv->leds[i].ldev,
+ &init_data);
+ if (err < 0) {
+- fwnode_handle_put(child);
++ for (j = i; j < BD2606_MAX_LEDS; j++)
++ fwnode_handle_put(led_fwnodes[j]);
+ return dev_err_probe(dev, err,
+ "couldn't register LED %s\n",
+ priv->leds[i].ldev.name);
+diff --git a/drivers/leds/leds-gpio.c b/drivers/leds/leds-gpio.c
+index 83fcd7b6afff76..4d1612d557c841 100644
+--- a/drivers/leds/leds-gpio.c
++++ b/drivers/leds/leds-gpio.c
+@@ -150,7 +150,7 @@ static struct gpio_leds_priv *gpio_leds_create(struct device *dev)
+ {
+ struct fwnode_handle *child;
+ struct gpio_leds_priv *priv;
+- int count, ret;
++ int count, used, ret;
+
+ count = device_get_child_node_count(dev);
+ if (!count)
+@@ -159,9 +159,11 @@ static struct gpio_leds_priv *gpio_leds_create(struct device *dev)
+ priv = devm_kzalloc(dev, struct_size(priv, leds, count), GFP_KERNEL);
+ if (!priv)
+ return ERR_PTR(-ENOMEM);
++ priv->num_leds = count;
++ used = 0;
+
+ device_for_each_child_node(dev, child) {
+- struct gpio_led_data *led_dat = &priv->leds[priv->num_leds];
++ struct gpio_led_data *led_dat = &priv->leds[used];
+ struct gpio_led led = {};
+
+ /*
+@@ -197,8 +199,9 @@ static struct gpio_leds_priv *gpio_leds_create(struct device *dev)
+ /* Set gpiod label to match the corresponding LED name. */
+ gpiod_set_consumer_name(led_dat->gpiod,
+ led_dat->cdev.dev->kobj.name);
+- priv->num_leds++;
++ used++;
+ }
++ priv->num_leds = used;
+
+ return priv;
+ }
+diff --git a/drivers/leds/leds-pca995x.c b/drivers/leds/leds-pca995x.c
+index 78215dff14997c..11c7bb69573e8c 100644
+--- a/drivers/leds/leds-pca995x.c
++++ b/drivers/leds/leds-pca995x.c
+@@ -19,10 +19,6 @@
+ #define PCA995X_MODE1 0x00
+ #define PCA995X_MODE2 0x01
+ #define PCA995X_LEDOUT0 0x02
+-#define PCA9955B_PWM0 0x08
+-#define PCA9952_PWM0 0x0A
+-#define PCA9952_IREFALL 0x43
+-#define PCA9955B_IREFALL 0x45
+
+ /* Auto-increment disabled. Normal mode */
+ #define PCA995X_MODE1_CFG 0x00
+@@ -34,17 +30,38 @@
+ #define PCA995X_LDRX_MASK 0x3
+ #define PCA995X_LDRX_BITS 2
+
+-#define PCA995X_MAX_OUTPUTS 16
++#define PCA995X_MAX_OUTPUTS 24
+ #define PCA995X_OUTPUTS_PER_REG 4
+
+ #define PCA995X_IREFALL_FULL_CFG 0xFF
+ #define PCA995X_IREFALL_HALF_CFG (PCA995X_IREFALL_FULL_CFG / 2)
+
+-#define PCA995X_TYPE_NON_B 0
+-#define PCA995X_TYPE_B 1
+-
+ #define ldev_to_led(c) container_of(c, struct pca995x_led, ldev)
+
++struct pca995x_chipdef {
++ unsigned int num_leds;
++ u8 pwm_base;
++ u8 irefall;
++};
++
++static const struct pca995x_chipdef pca9952_chipdef = {
++ .num_leds = 16,
++ .pwm_base = 0x0a,
++ .irefall = 0x43,
++};
++
++static const struct pca995x_chipdef pca9955b_chipdef = {
++ .num_leds = 16,
++ .pwm_base = 0x08,
++ .irefall = 0x45,
++};
++
++static const struct pca995x_chipdef pca9956b_chipdef = {
++ .num_leds = 24,
++ .pwm_base = 0x0a,
++ .irefall = 0x40,
++};
++
+ struct pca995x_led {
+ unsigned int led_no;
+ struct led_classdev ldev;
+@@ -54,7 +71,7 @@ struct pca995x_led {
+ struct pca995x_chip {
+ struct regmap *regmap;
+ struct pca995x_led leds[PCA995X_MAX_OUTPUTS];
+- int btype;
++ const struct pca995x_chipdef *chipdef;
+ };
+
+ static int pca995x_brightness_set(struct led_classdev *led_cdev,
+@@ -62,10 +79,11 @@ static int pca995x_brightness_set(struct led_classdev *led_cdev,
+ {
+ struct pca995x_led *led = ldev_to_led(led_cdev);
+ struct pca995x_chip *chip = led->chip;
++ const struct pca995x_chipdef *chipdef = chip->chipdef;
+ u8 ledout_addr, pwmout_addr;
+ int shift, ret;
+
+- pwmout_addr = (chip->btype ? PCA9955B_PWM0 : PCA9952_PWM0) + led->led_no;
++ pwmout_addr = chipdef->pwm_base + led->led_no;
+ ledout_addr = PCA995X_LEDOUT0 + (led->led_no / PCA995X_OUTPUTS_PER_REG);
+ shift = PCA995X_LDRX_BITS * (led->led_no % PCA995X_OUTPUTS_PER_REG);
+
+@@ -102,43 +120,38 @@ static const struct regmap_config pca995x_regmap = {
+ static int pca995x_probe(struct i2c_client *client)
+ {
+ struct fwnode_handle *led_fwnodes[PCA995X_MAX_OUTPUTS] = { 0 };
+- struct fwnode_handle *np, *child;
+ struct device *dev = &client->dev;
++ const struct pca995x_chipdef *chipdef;
+ struct pca995x_chip *chip;
+ struct pca995x_led *led;
+- int i, btype, reg, ret;
++ int i, j, reg, ret;
+
+- btype = (unsigned long)device_get_match_data(&client->dev);
++ chipdef = device_get_match_data(&client->dev);
+
+- np = dev_fwnode(dev);
+- if (!np)
++ if (!dev_fwnode(dev))
+ return -ENODEV;
+
+ chip = devm_kzalloc(dev, sizeof(*chip), GFP_KERNEL);
+ if (!chip)
+ return -ENOMEM;
+
+- chip->btype = btype;
++ chip->chipdef = chipdef;
+ chip->regmap = devm_regmap_init_i2c(client, &pca995x_regmap);
+ if (IS_ERR(chip->regmap))
+ return PTR_ERR(chip->regmap);
+
+ i2c_set_clientdata(client, chip);
+
+- fwnode_for_each_available_child_node(np, child) {
++ device_for_each_child_node_scoped(dev, child) {
+ ret = fwnode_property_read_u32(child, "reg", ®);
+- if (ret) {
+- fwnode_handle_put(child);
++ if (ret)
+ return ret;
+- }
+
+- if (reg < 0 || reg >= PCA995X_MAX_OUTPUTS || led_fwnodes[reg]) {
+- fwnode_handle_put(child);
++ if (reg < 0 || reg >= PCA995X_MAX_OUTPUTS || led_fwnodes[reg])
+ return -EINVAL;
+- }
+
+ led = &chip->leds[reg];
+- led_fwnodes[reg] = child;
++ led_fwnodes[reg] = fwnode_handle_get(child);
+ led->chip = chip;
+ led->led_no = reg;
+ led->ldev.brightness_set_blocking = pca995x_brightness_set;
+@@ -157,7 +170,8 @@ static int pca995x_probe(struct i2c_client *client)
+ &chip->leds[i].ldev,
+ &init_data);
+ if (ret < 0) {
+- fwnode_handle_put(child);
++ for (j = i; j < PCA995X_MAX_OUTPUTS; j++)
++ fwnode_handle_put(led_fwnodes[j]);
+ return dev_err_probe(dev, ret,
+ "Could not register LED %s\n",
+ chip->leds[i].ldev.name);
+@@ -170,21 +184,21 @@ static int pca995x_probe(struct i2c_client *client)
+ return ret;
+
+ /* IREF Output current value for all LEDn outputs */
+- return regmap_write(chip->regmap,
+- btype ? PCA9955B_IREFALL : PCA9952_IREFALL,
+- PCA995X_IREFALL_HALF_CFG);
++ return regmap_write(chip->regmap, chipdef->irefall, PCA995X_IREFALL_HALF_CFG);
+ }
+
+ static const struct i2c_device_id pca995x_id[] = {
+- { "pca9952", .driver_data = (kernel_ulong_t)PCA995X_TYPE_NON_B },
+- { "pca9955b", .driver_data = (kernel_ulong_t)PCA995X_TYPE_B },
++ { "pca9952", .driver_data = (kernel_ulong_t)&pca9952_chipdef },
++ { "pca9955b", .driver_data = (kernel_ulong_t)&pca9955b_chipdef },
++ { "pca9956b", .driver_data = (kernel_ulong_t)&pca9956b_chipdef },
+ {}
+ };
+ MODULE_DEVICE_TABLE(i2c, pca995x_id);
+
+ static const struct of_device_id pca995x_of_match[] = {
+- { .compatible = "nxp,pca9952", .data = (void *)PCA995X_TYPE_NON_B },
+- { .compatible = "nxp,pca9955b", .data = (void *)PCA995X_TYPE_B },
++ { .compatible = "nxp,pca9952", .data = &pca9952_chipdef },
++ { .compatible = "nxp,pca9955b", . data = &pca9955b_chipdef },
++ { .compatible = "nxp,pca9956b", .data = &pca9956b_chipdef },
+ {},
+ };
+ MODULE_DEVICE_TABLE(of, pca995x_of_match);
+diff --git a/drivers/md/dm-rq.c b/drivers/md/dm-rq.c
+index f7e9a3632eb3d9..499f8cc8a39fbf 100644
+--- a/drivers/md/dm-rq.c
++++ b/drivers/md/dm-rq.c
+@@ -496,8 +496,10 @@ static blk_status_t dm_mq_queue_rq(struct blk_mq_hw_ctx *hctx,
+
+ map = dm_get_live_table(md, &srcu_idx);
+ if (unlikely(!map)) {
++ DMERR_LIMIT("%s: mapping table unavailable, erroring io",
++ dm_device_name(md));
+ dm_put_live_table(md, srcu_idx);
+- return BLK_STS_RESOURCE;
++ return BLK_STS_IOERR;
+ }
+ ti = dm_table_find_target(map, 0);
+ dm_put_live_table(md, srcu_idx);
+diff --git a/drivers/md/dm.c b/drivers/md/dm.c
+index 6e15ac4e0845cd..a0b4afba8c608e 100644
+--- a/drivers/md/dm.c
++++ b/drivers/md/dm.c
+@@ -1880,10 +1880,15 @@ static void dm_submit_bio(struct bio *bio)
+ struct dm_table *map;
+
+ map = dm_get_live_table(md, &srcu_idx);
++ if (unlikely(!map)) {
++ DMERR_LIMIT("%s: mapping table unavailable, erroring io",
++ dm_device_name(md));
++ bio_io_error(bio);
++ goto out;
++ }
+
+- /* If suspended, or map not yet available, queue this IO for later */
+- if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags)) ||
+- unlikely(!map)) {
++ /* If suspended, queue this IO for later */
++ if (unlikely(test_bit(DMF_BLOCK_IO_FOR_SUSPEND, &md->flags))) {
+ if (bio->bi_opf & REQ_NOWAIT)
+ bio_wouldblock_error(bio);
+ else if (bio->bi_opf & REQ_RAHEAD)
+diff --git a/drivers/md/md.c b/drivers/md/md.c
+index a5b5801baa9e83..e832b8b5e631f2 100644
+--- a/drivers/md/md.c
++++ b/drivers/md/md.c
+@@ -8648,7 +8648,6 @@ void md_write_start(struct mddev *mddev, struct bio *bi)
+ BUG_ON(mddev->ro == MD_RDONLY);
+ if (mddev->ro == MD_AUTO_READ) {
+ /* need to switch to read/write */
+- flush_work(&mddev->sync_work);
+ mddev->ro = MD_RDWR;
+ set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+ md_wakeup_thread(mddev->thread);
+diff --git a/drivers/media/dvb-frontends/rtl2830.c b/drivers/media/dvb-frontends/rtl2830.c
+index 30d10fe4b33e34..320aa2bf99d423 100644
+--- a/drivers/media/dvb-frontends/rtl2830.c
++++ b/drivers/media/dvb-frontends/rtl2830.c
+@@ -609,7 +609,7 @@ static int rtl2830_pid_filter(struct dvb_frontend *fe, u8 index, u16 pid, int on
+ index, pid, onoff);
+
+ /* skip invalid PIDs (0x2000) */
+- if (pid > 0x1fff || index > 32)
++ if (pid > 0x1fff || index >= 32)
+ return 0;
+
+ if (onoff)
+diff --git a/drivers/media/dvb-frontends/rtl2832.c b/drivers/media/dvb-frontends/rtl2832.c
+index 5142820b1b3d97..76c3f40443b2c9 100644
+--- a/drivers/media/dvb-frontends/rtl2832.c
++++ b/drivers/media/dvb-frontends/rtl2832.c
+@@ -983,7 +983,7 @@ static int rtl2832_pid_filter(struct dvb_frontend *fe, u8 index, u16 pid,
+ index, pid, onoff, dev->slave_ts);
+
+ /* skip invalid PIDs (0x2000) */
+- if (pid > 0x1fff || index > 32)
++ if (pid > 0x1fff || index >= 32)
+ return 0;
+
+ if (onoff)
+diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_if.c
+index 73d5cef33b2abf..1e1b32faac77bc 100644
+--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_if.c
++++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_if.c
+@@ -347,11 +347,16 @@ static int vdec_h264_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+ return vpu_dec_reset(vpu);
+
+ fb = inst->ctx->dev->vdec_pdata->get_cap_buffer(inst->ctx);
++ if (!fb) {
++ mtk_vdec_err(inst->ctx, "fb buffer is NULL");
++ return -ENOMEM;
++ }
++
+ src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer);
+ dst_buf_info = container_of(fb, struct mtk_video_dec_buf, frame_buffer);
+
+- y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0;
+- c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0;
++ y_fb_dma = fb->base_y.dma_addr;
++ c_fb_dma = fb->base_c.dma_addr;
+
+ mtk_vdec_debug(inst->ctx, "+ [%d] FB y_dma=%llx c_dma=%llx va=%p",
+ inst->num_nalu, y_fb_dma, c_fb_dma, fb);
+diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_multi_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_multi_if.c
+index 2d4611e7fa0b2f..1ed0ccec56655e 100644
+--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_multi_if.c
++++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_h264_req_multi_if.c
+@@ -724,11 +724,16 @@ static int vdec_h264_slice_single_decode(void *h_vdec, struct mtk_vcodec_mem *bs
+ return vpu_dec_reset(vpu);
+
+ fb = inst->ctx->dev->vdec_pdata->get_cap_buffer(inst->ctx);
++ if (!fb) {
++ mtk_vdec_err(inst->ctx, "fb buffer is NULL");
++ return -ENOMEM;
++ }
++
+ src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer);
+ dst_buf_info = container_of(fb, struct mtk_video_dec_buf, frame_buffer);
+
+- y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0;
+- c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0;
++ y_fb_dma = fb->base_y.dma_addr;
++ c_fb_dma = fb->base_c.dma_addr;
+ mtk_vdec_debug(inst->ctx, "[h264-dec] [%d] y_dma=%llx c_dma=%llx",
+ inst->ctx->decoded_frame_cnt, y_fb_dma, c_fb_dma);
+
+diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_req_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_req_if.c
+index e27e728f392e6c..232ef3bd246a3d 100644
+--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_req_if.c
++++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_req_if.c
+@@ -334,14 +334,18 @@ static int vdec_vp8_slice_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+ src_buf_info = container_of(bs, struct mtk_video_dec_buf, bs_buffer);
+
+ fb = inst->ctx->dev->vdec_pdata->get_cap_buffer(inst->ctx);
+- dst_buf_info = container_of(fb, struct mtk_video_dec_buf, frame_buffer);
++ if (!fb) {
++ mtk_vdec_err(inst->ctx, "fb buffer is NULL");
++ return -ENOMEM;
++ }
+
+- y_fb_dma = fb ? (u64)fb->base_y.dma_addr : 0;
++ dst_buf_info = container_of(fb, struct mtk_video_dec_buf, frame_buffer);
++ y_fb_dma = fb->base_y.dma_addr;
+ if (inst->ctx->q_data[MTK_Q_DATA_DST].fmt->num_planes == 1)
+ c_fb_dma = y_fb_dma +
+ inst->ctx->picinfo.buf_w * inst->ctx->picinfo.buf_h;
+ else
+- c_fb_dma = fb ? (u64)fb->base_c.dma_addr : 0;
++ c_fb_dma = fb->base_c.dma_addr;
+
+ inst->vsi->dec.bs_dma = (u64)bs->dma_addr;
+ inst->vsi->dec.bs_sz = bs->size;
+diff --git a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c
+index e68fcdaea207aa..c7fdee347ac8ae 100644
+--- a/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c
++++ b/drivers/media/platform/renesas/rzg2l-cru/rzg2l-csi2.c
+@@ -865,6 +865,7 @@ static const struct of_device_id rzg2l_csi2_of_table[] = {
+ { .compatible = "renesas,rzg2l-csi2", },
+ { /* sentinel */ }
+ };
++MODULE_DEVICE_TABLE(of, rzg2l_csi2_of_table);
+
+ static struct platform_driver rzg2l_csi2_pdrv = {
+ .remove_new = rzg2l_csi2_remove,
+diff --git a/drivers/media/tuners/tuner-i2c.h b/drivers/media/tuners/tuner-i2c.h
+index 07aeead0644a31..724952e001cd13 100644
+--- a/drivers/media/tuners/tuner-i2c.h
++++ b/drivers/media/tuners/tuner-i2c.h
+@@ -133,10 +133,8 @@ static inline int tuner_i2c_xfer_send_recv(struct tuner_i2c_props *props,
+ } \
+ if (0 == __ret) { \
+ state = kzalloc(sizeof(type), GFP_KERNEL); \
+- if (!state) { \
+- __ret = -ENOMEM; \
++ if (NULL == state) \
+ goto __fail; \
+- } \
+ state->i2c_props.addr = i2caddr; \
+ state->i2c_props.adap = i2cadap; \
+ state->i2c_props.name = devname; \
+diff --git a/drivers/mtd/devices/powernv_flash.c b/drivers/mtd/devices/powernv_flash.c
+index 66044f4f5bade8..10cd1d9b48859d 100644
+--- a/drivers/mtd/devices/powernv_flash.c
++++ b/drivers/mtd/devices/powernv_flash.c
+@@ -207,6 +207,9 @@ static int powernv_flash_set_driver_info(struct device *dev,
+ * get them
+ */
+ mtd->name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node);
++ if (!mtd->name)
++ return -ENOMEM;
++
+ mtd->type = MTD_NORFLASH;
+ mtd->flags = MTD_WRITEABLE;
+ mtd->size = size;
+diff --git a/drivers/mtd/devices/slram.c b/drivers/mtd/devices/slram.c
+index 28131a127d065e..8297b366a06699 100644
+--- a/drivers/mtd/devices/slram.c
++++ b/drivers/mtd/devices/slram.c
+@@ -296,10 +296,12 @@ static int __init init_slram(void)
+ T("slram: devname = %s\n", devname);
+ if ((!map) || (!(devstart = strsep(&map, ",")))) {
+ E("slram: No devicestart specified.\n");
++ break;
+ }
+ T("slram: devstart = %s\n", devstart);
+ if ((!map) || (!(devlength = strsep(&map, ",")))) {
+ E("slram: No devicelength / -end specified.\n");
++ break;
+ }
+ T("slram: devlength = %s\n", devlength);
+ if (parse_cmdline(devname, devstart, devlength) != 0) {
+diff --git a/drivers/mtd/nand/raw/mtk_nand.c b/drivers/mtd/nand/raw/mtk_nand.c
+index 17477bb2d48ff0..586868b4139f51 100644
+--- a/drivers/mtd/nand/raw/mtk_nand.c
++++ b/drivers/mtd/nand/raw/mtk_nand.c
+@@ -1429,16 +1429,32 @@ static int mtk_nfc_nand_chip_init(struct device *dev, struct mtk_nfc *nfc,
+ return 0;
+ }
+
++static void mtk_nfc_nand_chips_cleanup(struct mtk_nfc *nfc)
++{
++ struct mtk_nfc_nand_chip *mtk_chip;
++ struct nand_chip *chip;
++ int ret;
++
++ while (!list_empty(&nfc->chips)) {
++ mtk_chip = list_first_entry(&nfc->chips,
++ struct mtk_nfc_nand_chip, node);
++ chip = &mtk_chip->nand;
++ ret = mtd_device_unregister(nand_to_mtd(chip));
++ WARN_ON(ret);
++ nand_cleanup(chip);
++ list_del(&mtk_chip->node);
++ }
++}
++
+ static int mtk_nfc_nand_chips_init(struct device *dev, struct mtk_nfc *nfc)
+ {
+ struct device_node *np = dev->of_node;
+- struct device_node *nand_np;
+ int ret;
+
+- for_each_child_of_node(np, nand_np) {
++ for_each_child_of_node_scoped(np, nand_np) {
+ ret = mtk_nfc_nand_chip_init(dev, nfc, nand_np);
+ if (ret) {
+- of_node_put(nand_np);
++ mtk_nfc_nand_chips_cleanup(nfc);
+ return ret;
+ }
+ }
+@@ -1570,20 +1586,8 @@ static int mtk_nfc_probe(struct platform_device *pdev)
+ static void mtk_nfc_remove(struct platform_device *pdev)
+ {
+ struct mtk_nfc *nfc = platform_get_drvdata(pdev);
+- struct mtk_nfc_nand_chip *mtk_chip;
+- struct nand_chip *chip;
+- int ret;
+-
+- while (!list_empty(&nfc->chips)) {
+- mtk_chip = list_first_entry(&nfc->chips,
+- struct mtk_nfc_nand_chip, node);
+- chip = &mtk_chip->nand;
+- ret = mtd_device_unregister(nand_to_mtd(chip));
+- WARN_ON(ret);
+- nand_cleanup(chip);
+- list_del(&mtk_chip->node);
+- }
+
++ mtk_nfc_nand_chips_cleanup(nfc);
+ mtk_ecc_release(nfc->ecc);
+ }
+
+diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
+index 7aca0544fb29c9..e80992b4f9de9a 100644
+--- a/drivers/net/bareudp.c
++++ b/drivers/net/bareudp.c
+@@ -68,6 +68,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+ __be16 proto;
+ void *oiph;
+ int err;
++ int nh;
+
+ bareudp = rcu_dereference_sk_user_data(sk);
+ if (!bareudp)
+@@ -148,10 +149,25 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+ }
+ skb_dst_set(skb, &tun_dst->dst);
+ skb->dev = bareudp->dev;
+- oiph = skb_network_header(skb);
+- skb_reset_network_header(skb);
+ skb_reset_mac_header(skb);
+
++ /* Save offset of outer header relative to skb->head,
++ * because we are going to reset the network header to the inner header
++ * and might change skb->head.
++ */
++ nh = skb_network_header(skb) - skb->head;
++
++ skb_reset_network_header(skb);
++
++ if (!pskb_inet_may_pull(skb)) {
++ DEV_STATS_INC(bareudp->dev, rx_length_errors);
++ DEV_STATS_INC(bareudp->dev, rx_errors);
++ goto drop;
++ }
++
++ /* Get the outer header. */
++ oiph = skb->head + nh;
++
+ if (!ipv6_mod_enabled() || family == AF_INET)
+ err = IP_ECN_decapsulate(oiph, skb);
+ else
+@@ -301,6 +317,9 @@ static int bareudp_xmit_skb(struct sk_buff *skb, struct net_device *dev,
+ __be32 saddr;
+ int err;
+
++ if (!skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB)))
++ return -EINVAL;
++
+ if (!sock)
+ return -ESHUTDOWN;
+
+@@ -368,6 +387,9 @@ static int bareudp6_xmit_skb(struct sk_buff *skb, struct net_device *dev,
+ __be16 sport;
+ int err;
+
++ if (!skb_vlan_inet_prepare(skb, skb->protocol != htons(ETH_P_TEB)))
++ return -EINVAL;
++
+ if (!sock)
+ return -ESHUTDOWN;
+
+diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
+index 60db34095a2557..3c61f5fbe6b7fe 100644
+--- a/drivers/net/bonding/bond_main.c
++++ b/drivers/net/bonding/bond_main.c
+@@ -5536,9 +5536,9 @@ bond_xdp_get_xmit_slave(struct net_device *bond_dev, struct xdp_buff *xdp)
+ break;
+
+ default:
+- /* Should never happen. Mode guarded by bond_xdp_check() */
+- netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n", BOND_MODE(bond));
+- WARN_ON_ONCE(1);
++ if (net_ratelimit())
++ netdev_err(bond_dev, "Unknown bonding mode %d for xdp xmit\n",
++ BOND_MODE(bond));
+ return NULL;
+ }
+
+diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
+index ddde067f593fcf..0f9f17fdb3bb89 100644
+--- a/drivers/net/can/m_can/m_can.c
++++ b/drivers/net/can/m_can/m_can.c
+@@ -1720,11 +1720,7 @@ static int m_can_close(struct net_device *dev)
+
+ netif_stop_queue(dev);
+
+- if (!cdev->is_peripheral)
+- napi_disable(&cdev->napi);
+-
+ m_can_stop(dev);
+- m_can_clk_stop(cdev);
+ free_irq(dev->irq, dev);
+
+ m_can_clean(dev);
+@@ -1733,10 +1729,13 @@ static int m_can_close(struct net_device *dev)
+ destroy_workqueue(cdev->tx_wq);
+ cdev->tx_wq = NULL;
+ can_rx_offload_disable(&cdev->offload);
++ } else {
++ napi_disable(&cdev->napi);
+ }
+
+ close_candev(dev);
+
++ m_can_clk_stop(cdev);
+ phy_power_off(cdev->transceiver);
+
+ return 0;
+@@ -1987,6 +1986,8 @@ static int m_can_open(struct net_device *dev)
+
+ if (cdev->is_peripheral)
+ can_rx_offload_enable(&cdev->offload);
++ else
++ napi_enable(&cdev->napi);
+
+ /* register interrupt handler */
+ if (cdev->is_peripheral) {
+@@ -2020,9 +2021,6 @@ static int m_can_open(struct net_device *dev)
+ if (err)
+ goto exit_start_fail;
+
+- if (!cdev->is_peripheral)
+- napi_enable(&cdev->napi);
+-
+ netif_start_queue(dev);
+
+ return 0;
+@@ -2036,6 +2034,8 @@ static int m_can_open(struct net_device *dev)
+ out_wq_fail:
+ if (cdev->is_peripheral)
+ can_rx_offload_disable(&cdev->offload);
++ else
++ napi_disable(&cdev->napi);
+ close_candev(dev);
+ exit_disable_clks:
+ m_can_clk_stop(cdev);
+diff --git a/drivers/net/can/usb/esd_usb.c b/drivers/net/can/usb/esd_usb.c
+index 41a0e4261d15e9..03ad10b01867d8 100644
+--- a/drivers/net/can/usb/esd_usb.c
++++ b/drivers/net/can/usb/esd_usb.c
+@@ -3,7 +3,7 @@
+ * CAN driver for esd electronics gmbh CAN-USB/2, CAN-USB/3 and CAN-USB/Micro
+ *
+ * Copyright (C) 2010-2012 esd electronic system design gmbh, Matthias Fuchs <socketcan@esd.eu>
+- * Copyright (C) 2022-2023 esd electronics gmbh, Frank Jungclaus <frank.jungclaus@esd.eu>
++ * Copyright (C) 2022-2024 esd electronics gmbh, Frank Jungclaus <frank.jungclaus@esd.eu>
+ */
+
+ #include <linux/can.h>
+@@ -1116,9 +1116,6 @@ static int esd_usb_3_set_bittiming(struct net_device *netdev)
+ if (priv->can.ctrlmode & CAN_CTRLMODE_LISTENONLY)
+ flags |= ESD_USB_3_BAUDRATE_FLAG_LOM;
+
+- if (priv->can.ctrlmode & CAN_CTRLMODE_3_SAMPLES)
+- flags |= ESD_USB_3_BAUDRATE_FLAG_TRS;
+-
+ baud_x->nom.brp = cpu_to_le16(nom_bt->brp & (nom_btc->brp_max - 1));
+ baud_x->nom.sjw = cpu_to_le16(nom_bt->sjw & (nom_btc->sjw_max - 1));
+ baud_x->nom.tseg1 = cpu_to_le16((nom_bt->prop_seg + nom_bt->phase_seg1)
+@@ -1219,7 +1216,6 @@ static int esd_usb_probe_one_net(struct usb_interface *intf, int index)
+ switch (le16_to_cpu(dev->udev->descriptor.idProduct)) {
+ case ESD_USB_CANUSB3_PRODUCT_ID:
+ priv->can.clock.freq = ESD_USB_3_CAN_CLOCK;
+- priv->can.ctrlmode_supported |= CAN_CTRLMODE_3_SAMPLES;
+ priv->can.ctrlmode_supported |= CAN_CTRLMODE_FD;
+ priv->can.bittiming_const = &esd_usb_3_nom_bittiming_const;
+ priv->can.data_bittiming_const = &esd_usb_3_data_bittiming_const;
+diff --git a/drivers/net/ethernet/freescale/enetc/enetc.c b/drivers/net/ethernet/freescale/enetc/enetc.c
+index 5c45f42232d326..f04f42ea60c0f7 100644
+--- a/drivers/net/ethernet/freescale/enetc/enetc.c
++++ b/drivers/net/ethernet/freescale/enetc/enetc.c
+@@ -2305,12 +2305,11 @@ static int enetc_setup_irqs(struct enetc_ndev_priv *priv)
+
+ snprintf(v->name, sizeof(v->name), "%s-rxtx%d",
+ priv->ndev->name, i);
+- err = request_irq(irq, enetc_msix, 0, v->name, v);
++ err = request_irq(irq, enetc_msix, IRQF_NO_AUTOEN, v->name, v);
+ if (err) {
+ dev_err(priv->dev, "request_irq() failed!\n");
+ goto irq_err;
+ }
+- disable_irq(irq);
+
+ v->tbier_base = hw->reg + ENETC_BDR(TX, 0, ENETC_TBIER);
+ v->rbier = hw->reg + ENETC_BDR(RX, i, ENETC_RBIER);
+diff --git a/drivers/net/ethernet/intel/idpf/idpf.h b/drivers/net/ethernet/intel/idpf/idpf.h
+index e7a03653824659..f9e43d171f1712 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf.h
++++ b/drivers/net/ethernet/intel/idpf/idpf.h
+@@ -17,10 +17,8 @@ struct idpf_vport_max_q;
+ #include <linux/sctp.h>
+ #include <linux/ethtool_netlink.h>
+ #include <net/gro.h>
+-#include <linux/dim.h>
+
+ #include "virtchnl2.h"
+-#include "idpf_lan_txrx.h"
+ #include "idpf_txrx.h"
+ #include "idpf_controlq.h"
+
+@@ -302,7 +300,7 @@ struct idpf_vport {
+ u16 num_txq_grp;
+ struct idpf_txq_group *txq_grps;
+ u32 txq_model;
+- struct idpf_queue **txqs;
++ struct idpf_tx_queue **txqs;
+ bool crc_enable;
+
+ u16 num_rxq;
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+index 1885ba618981df..e933fed16c7ea5 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
++++ b/drivers/net/ethernet/intel/idpf/idpf_ethtool.c
+@@ -437,22 +437,24 @@ struct idpf_stats {
+ .stat_offset = offsetof(_type, _stat) \
+ }
+
+-/* Helper macro for defining some statistics related to queues */
+-#define IDPF_QUEUE_STAT(_name, _stat) \
+- IDPF_STAT(struct idpf_queue, _name, _stat)
++/* Helper macros for defining some statistics related to queues */
++#define IDPF_RX_QUEUE_STAT(_name, _stat) \
++ IDPF_STAT(struct idpf_rx_queue, _name, _stat)
++#define IDPF_TX_QUEUE_STAT(_name, _stat) \
++ IDPF_STAT(struct idpf_tx_queue, _name, _stat)
+
+ /* Stats associated with a Tx queue */
+ static const struct idpf_stats idpf_gstrings_tx_queue_stats[] = {
+- IDPF_QUEUE_STAT("pkts", q_stats.tx.packets),
+- IDPF_QUEUE_STAT("bytes", q_stats.tx.bytes),
+- IDPF_QUEUE_STAT("lso_pkts", q_stats.tx.lso_pkts),
++ IDPF_TX_QUEUE_STAT("pkts", q_stats.packets),
++ IDPF_TX_QUEUE_STAT("bytes", q_stats.bytes),
++ IDPF_TX_QUEUE_STAT("lso_pkts", q_stats.lso_pkts),
+ };
+
+ /* Stats associated with an Rx queue */
+ static const struct idpf_stats idpf_gstrings_rx_queue_stats[] = {
+- IDPF_QUEUE_STAT("pkts", q_stats.rx.packets),
+- IDPF_QUEUE_STAT("bytes", q_stats.rx.bytes),
+- IDPF_QUEUE_STAT("rx_gro_hw_pkts", q_stats.rx.rsc_pkts),
++ IDPF_RX_QUEUE_STAT("pkts", q_stats.packets),
++ IDPF_RX_QUEUE_STAT("bytes", q_stats.bytes),
++ IDPF_RX_QUEUE_STAT("rx_gro_hw_pkts", q_stats.rsc_pkts),
+ };
+
+ #define IDPF_TX_QUEUE_STATS_LEN ARRAY_SIZE(idpf_gstrings_tx_queue_stats)
+@@ -633,7 +635,7 @@ static int idpf_get_sset_count(struct net_device *netdev, int sset)
+ * Copies the stat data defined by the pointer and stat structure pair into
+ * the memory supplied as data. If the pointer is null, data will be zero'd.
+ */
+-static void idpf_add_one_ethtool_stat(u64 *data, void *pstat,
++static void idpf_add_one_ethtool_stat(u64 *data, const void *pstat,
+ const struct idpf_stats *stat)
+ {
+ char *p;
+@@ -671,6 +673,7 @@ static void idpf_add_one_ethtool_stat(u64 *data, void *pstat,
+ * idpf_add_queue_stats - copy queue statistics into supplied buffer
+ * @data: ethtool stats buffer
+ * @q: the queue to copy
++ * @type: type of the queue
+ *
+ * Queue statistics must be copied while protected by u64_stats_fetch_begin,
+ * so we can't directly use idpf_add_ethtool_stats. Assumes that queue stats
+@@ -681,19 +684,23 @@ static void idpf_add_one_ethtool_stat(u64 *data, void *pstat,
+ *
+ * This function expects to be called while under rcu_read_lock().
+ */
+-static void idpf_add_queue_stats(u64 **data, struct idpf_queue *q)
++static void idpf_add_queue_stats(u64 **data, const void *q,
++ enum virtchnl2_queue_type type)
+ {
++ const struct u64_stats_sync *stats_sync;
+ const struct idpf_stats *stats;
+ unsigned int start;
+ unsigned int size;
+ unsigned int i;
+
+- if (q->q_type == VIRTCHNL2_QUEUE_TYPE_RX) {
++ if (type == VIRTCHNL2_QUEUE_TYPE_RX) {
+ size = IDPF_RX_QUEUE_STATS_LEN;
+ stats = idpf_gstrings_rx_queue_stats;
++ stats_sync = &((const struct idpf_rx_queue *)q)->stats_sync;
+ } else {
+ size = IDPF_TX_QUEUE_STATS_LEN;
+ stats = idpf_gstrings_tx_queue_stats;
++ stats_sync = &((const struct idpf_tx_queue *)q)->stats_sync;
+ }
+
+ /* To avoid invalid statistics values, ensure that we keep retrying
+@@ -701,10 +708,10 @@ static void idpf_add_queue_stats(u64 **data, struct idpf_queue *q)
+ * u64_stats_fetch_retry.
+ */
+ do {
+- start = u64_stats_fetch_begin(&q->stats_sync);
++ start = u64_stats_fetch_begin(stats_sync);
+ for (i = 0; i < size; i++)
+ idpf_add_one_ethtool_stat(&(*data)[i], q, &stats[i]);
+- } while (u64_stats_fetch_retry(&q->stats_sync, start));
++ } while (u64_stats_fetch_retry(stats_sync, start));
+
+ /* Once we successfully copy the stats in, update the data pointer */
+ *data += size;
+@@ -793,7 +800,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
+ for (j = 0; j < num_rxq; j++) {
+ u64 hw_csum_err, hsplit, hsplit_hbo, bad_descs;
+ struct idpf_rx_queue_stats *stats;
+- struct idpf_queue *rxq;
++ struct idpf_rx_queue *rxq;
+ unsigned int start;
+
+ if (idpf_is_queue_model_split(vport->rxq_model))
+@@ -807,7 +814,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
+ do {
+ start = u64_stats_fetch_begin(&rxq->stats_sync);
+
+- stats = &rxq->q_stats.rx;
++ stats = &rxq->q_stats;
+ hw_csum_err = u64_stats_read(&stats->hw_csum_err);
+ hsplit = u64_stats_read(&stats->hsplit_pkts);
+ hsplit_hbo = u64_stats_read(&stats->hsplit_buf_ovf);
+@@ -828,7 +835,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
+
+ for (j = 0; j < txq_grp->num_txq; j++) {
+ u64 linearize, qbusy, skb_drops, dma_map_errs;
+- struct idpf_queue *txq = txq_grp->txqs[j];
++ struct idpf_tx_queue *txq = txq_grp->txqs[j];
+ struct idpf_tx_queue_stats *stats;
+ unsigned int start;
+
+@@ -838,7 +845,7 @@ static void idpf_collect_queue_stats(struct idpf_vport *vport)
+ do {
+ start = u64_stats_fetch_begin(&txq->stats_sync);
+
+- stats = &txq->q_stats.tx;
++ stats = &txq->q_stats;
+ linearize = u64_stats_read(&stats->linearize);
+ qbusy = u64_stats_read(&stats->q_busy);
+ skb_drops = u64_stats_read(&stats->skb_drops);
+@@ -896,12 +903,12 @@ static void idpf_get_ethtool_stats(struct net_device *netdev,
+ qtype = VIRTCHNL2_QUEUE_TYPE_TX;
+
+ for (j = 0; j < txq_grp->num_txq; j++, total++) {
+- struct idpf_queue *txq = txq_grp->txqs[j];
++ struct idpf_tx_queue *txq = txq_grp->txqs[j];
+
+ if (!txq)
+ idpf_add_empty_queue_stats(&data, qtype);
+ else
+- idpf_add_queue_stats(&data, txq);
++ idpf_add_queue_stats(&data, txq, qtype);
+ }
+ }
+
+@@ -929,7 +936,7 @@ static void idpf_get_ethtool_stats(struct net_device *netdev,
+ num_rxq = rxq_grp->singleq.num_rxq;
+
+ for (j = 0; j < num_rxq; j++, total++) {
+- struct idpf_queue *rxq;
++ struct idpf_rx_queue *rxq;
+
+ if (is_splitq)
+ rxq = &rxq_grp->splitq.rxq_sets[j]->rxq;
+@@ -938,7 +945,7 @@ static void idpf_get_ethtool_stats(struct net_device *netdev,
+ if (!rxq)
+ idpf_add_empty_queue_stats(&data, qtype);
+ else
+- idpf_add_queue_stats(&data, rxq);
++ idpf_add_queue_stats(&data, rxq, qtype);
+
+ /* In splitq mode, don't get page pool stats here since
+ * the pools are attached to the buffer queues
+@@ -953,7 +960,7 @@ static void idpf_get_ethtool_stats(struct net_device *netdev,
+
+ for (i = 0; i < vport->num_rxq_grp; i++) {
+ for (j = 0; j < vport->num_bufqs_per_qgrp; j++) {
+- struct idpf_queue *rxbufq =
++ struct idpf_buf_queue *rxbufq =
+ &vport->rxq_grps[i].splitq.bufq_sets[j].bufq;
+
+ page_pool_get_stats(rxbufq->pp, &pp_stats);
+@@ -971,60 +978,64 @@ static void idpf_get_ethtool_stats(struct net_device *netdev,
+ }
+
+ /**
+- * idpf_find_rxq - find rxq from q index
++ * idpf_find_rxq_vec - find rxq vector from q index
+ * @vport: virtual port associated to queue
+ * @q_num: q index used to find queue
+ *
+- * returns pointer to rx queue
++ * returns pointer to rx vector
+ */
+-static struct idpf_queue *idpf_find_rxq(struct idpf_vport *vport, int q_num)
++static struct idpf_q_vector *idpf_find_rxq_vec(const struct idpf_vport *vport,
++ int q_num)
+ {
+ int q_grp, q_idx;
+
+ if (!idpf_is_queue_model_split(vport->rxq_model))
+- return vport->rxq_grps->singleq.rxqs[q_num];
++ return vport->rxq_grps->singleq.rxqs[q_num]->q_vector;
+
+ q_grp = q_num / IDPF_DFLT_SPLITQ_RXQ_PER_GROUP;
+ q_idx = q_num % IDPF_DFLT_SPLITQ_RXQ_PER_GROUP;
+
+- return &vport->rxq_grps[q_grp].splitq.rxq_sets[q_idx]->rxq;
++ return vport->rxq_grps[q_grp].splitq.rxq_sets[q_idx]->rxq.q_vector;
+ }
+
+ /**
+- * idpf_find_txq - find txq from q index
++ * idpf_find_txq_vec - find txq vector from q index
+ * @vport: virtual port associated to queue
+ * @q_num: q index used to find queue
+ *
+- * returns pointer to tx queue
++ * returns pointer to tx vector
+ */
+-static struct idpf_queue *idpf_find_txq(struct idpf_vport *vport, int q_num)
++static struct idpf_q_vector *idpf_find_txq_vec(const struct idpf_vport *vport,
++ int q_num)
+ {
+ int q_grp;
+
+ if (!idpf_is_queue_model_split(vport->txq_model))
+- return vport->txqs[q_num];
++ return vport->txqs[q_num]->q_vector;
+
+ q_grp = q_num / IDPF_DFLT_SPLITQ_TXQ_PER_GROUP;
+
+- return vport->txq_grps[q_grp].complq;
++ return vport->txq_grps[q_grp].complq->q_vector;
+ }
+
+ /**
+ * __idpf_get_q_coalesce - get ITR values for specific queue
+ * @ec: ethtool structure to fill with driver's coalesce settings
+- * @q: quuee of Rx or Tx
++ * @q_vector: queue vector corresponding to this queue
++ * @type: queue type
+ */
+ static void __idpf_get_q_coalesce(struct ethtool_coalesce *ec,
+- struct idpf_queue *q)
++ const struct idpf_q_vector *q_vector,
++ enum virtchnl2_queue_type type)
+ {
+- if (q->q_type == VIRTCHNL2_QUEUE_TYPE_RX) {
++ if (type == VIRTCHNL2_QUEUE_TYPE_RX) {
+ ec->use_adaptive_rx_coalesce =
+- IDPF_ITR_IS_DYNAMIC(q->q_vector->rx_intr_mode);
+- ec->rx_coalesce_usecs = q->q_vector->rx_itr_value;
++ IDPF_ITR_IS_DYNAMIC(q_vector->rx_intr_mode);
++ ec->rx_coalesce_usecs = q_vector->rx_itr_value;
+ } else {
+ ec->use_adaptive_tx_coalesce =
+- IDPF_ITR_IS_DYNAMIC(q->q_vector->tx_intr_mode);
+- ec->tx_coalesce_usecs = q->q_vector->tx_itr_value;
++ IDPF_ITR_IS_DYNAMIC(q_vector->tx_intr_mode);
++ ec->tx_coalesce_usecs = q_vector->tx_itr_value;
+ }
+ }
+
+@@ -1040,8 +1051,8 @@ static int idpf_get_q_coalesce(struct net_device *netdev,
+ struct ethtool_coalesce *ec,
+ u32 q_num)
+ {
+- struct idpf_netdev_priv *np = netdev_priv(netdev);
+- struct idpf_vport *vport;
++ const struct idpf_netdev_priv *np = netdev_priv(netdev);
++ const struct idpf_vport *vport;
+ int err = 0;
+
+ idpf_vport_ctrl_lock(netdev);
+@@ -1056,10 +1067,12 @@ static int idpf_get_q_coalesce(struct net_device *netdev,
+ }
+
+ if (q_num < vport->num_rxq)
+- __idpf_get_q_coalesce(ec, idpf_find_rxq(vport, q_num));
++ __idpf_get_q_coalesce(ec, idpf_find_rxq_vec(vport, q_num),
++ VIRTCHNL2_QUEUE_TYPE_RX);
+
+ if (q_num < vport->num_txq)
+- __idpf_get_q_coalesce(ec, idpf_find_txq(vport, q_num));
++ __idpf_get_q_coalesce(ec, idpf_find_txq_vec(vport, q_num),
++ VIRTCHNL2_QUEUE_TYPE_TX);
+
+ unlock_mutex:
+ idpf_vport_ctrl_unlock(netdev);
+@@ -1103,16 +1116,15 @@ static int idpf_get_per_q_coalesce(struct net_device *netdev, u32 q_num,
+ /**
+ * __idpf_set_q_coalesce - set ITR values for specific queue
+ * @ec: ethtool structure from user to update ITR settings
+- * @q: queue for which itr values has to be set
++ * @qv: queue vector for which itr values has to be set
+ * @is_rxq: is queue type rx
+ *
+ * Returns 0 on success, negative otherwise.
+ */
+-static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec,
+- struct idpf_queue *q, bool is_rxq)
++static int __idpf_set_q_coalesce(const struct ethtool_coalesce *ec,
++ struct idpf_q_vector *qv, bool is_rxq)
+ {
+ u32 use_adaptive_coalesce, coalesce_usecs;
+- struct idpf_q_vector *qv = q->q_vector;
+ bool is_dim_ena = false;
+ u16 itr_val;
+
+@@ -1128,7 +1140,7 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec,
+ itr_val = qv->tx_itr_value;
+ }
+ if (coalesce_usecs != itr_val && use_adaptive_coalesce) {
+- netdev_err(q->vport->netdev, "Cannot set coalesce usecs if adaptive enabled\n");
++ netdev_err(qv->vport->netdev, "Cannot set coalesce usecs if adaptive enabled\n");
+
+ return -EINVAL;
+ }
+@@ -1137,7 +1149,7 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec,
+ return 0;
+
+ if (coalesce_usecs > IDPF_ITR_MAX) {
+- netdev_err(q->vport->netdev,
++ netdev_err(qv->vport->netdev,
+ "Invalid value, %d-usecs range is 0-%d\n",
+ coalesce_usecs, IDPF_ITR_MAX);
+
+@@ -1146,7 +1158,7 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec,
+
+ if (coalesce_usecs % 2) {
+ coalesce_usecs--;
+- netdev_info(q->vport->netdev,
++ netdev_info(qv->vport->netdev,
+ "HW only supports even ITR values, ITR rounded to %d\n",
+ coalesce_usecs);
+ }
+@@ -1185,15 +1197,16 @@ static int __idpf_set_q_coalesce(struct ethtool_coalesce *ec,
+ *
+ * Return 0 on success, and negative on failure
+ */
+-static int idpf_set_q_coalesce(struct idpf_vport *vport,
+- struct ethtool_coalesce *ec,
++static int idpf_set_q_coalesce(const struct idpf_vport *vport,
++ const struct ethtool_coalesce *ec,
+ int q_num, bool is_rxq)
+ {
+- struct idpf_queue *q;
++ struct idpf_q_vector *qv;
+
+- q = is_rxq ? idpf_find_rxq(vport, q_num) : idpf_find_txq(vport, q_num);
++ qv = is_rxq ? idpf_find_rxq_vec(vport, q_num) :
++ idpf_find_txq_vec(vport, q_num);
+
+- if (q && __idpf_set_q_coalesce(ec, q, is_rxq))
++ if (qv && __idpf_set_q_coalesce(ec, qv, is_rxq))
+ return -EINVAL;
+
+ return 0;
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
+index a5752dcab8887c..8c7f8ef8f1a153 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
++++ b/drivers/net/ethernet/intel/idpf/idpf_lan_txrx.h
+@@ -4,6 +4,8 @@
+ #ifndef _IDPF_LAN_TXRX_H_
+ #define _IDPF_LAN_TXRX_H_
+
++#include <linux/bits.h>
++
+ enum idpf_rss_hash {
+ IDPF_HASH_INVALID = 0,
+ /* Values 1 - 28 are reserved for future use */
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
+index 3ac9d7ab83f20f..5e336f64bc25e3 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
++++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
+@@ -4,8 +4,7 @@
+ #include "idpf.h"
+ #include "idpf_virtchnl.h"
+
+-static const struct net_device_ops idpf_netdev_ops_splitq;
+-static const struct net_device_ops idpf_netdev_ops_singleq;
++static const struct net_device_ops idpf_netdev_ops;
+
+ /**
+ * idpf_init_vector_stack - Fill the MSIX vector stack with vector index
+@@ -765,10 +764,7 @@ static int idpf_cfg_netdev(struct idpf_vport *vport)
+ }
+
+ /* assign netdev_ops */
+- if (idpf_is_queue_model_split(vport->txq_model))
+- netdev->netdev_ops = &idpf_netdev_ops_splitq;
+- else
+- netdev->netdev_ops = &idpf_netdev_ops_singleq;
++ netdev->netdev_ops = &idpf_netdev_ops;
+
+ /* setup watchdog timeout value to be 5 second */
+ netdev->watchdog_timeo = 5 * HZ;
+@@ -1318,14 +1314,14 @@ static void idpf_rx_init_buf_tail(struct idpf_vport *vport)
+
+ if (idpf_is_queue_model_split(vport->rxq_model)) {
+ for (j = 0; j < vport->num_bufqs_per_qgrp; j++) {
+- struct idpf_queue *q =
++ const struct idpf_buf_queue *q =
+ &grp->splitq.bufq_sets[j].bufq;
+
+ writel(q->next_to_alloc, q->tail);
+ }
+ } else {
+ for (j = 0; j < grp->singleq.num_rxq; j++) {
+- struct idpf_queue *q =
++ const struct idpf_rx_queue *q =
+ grp->singleq.rxqs[j];
+
+ writel(q->next_to_alloc, q->tail);
+@@ -1852,7 +1848,7 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
+ enum idpf_vport_state current_state = np->state;
+ struct idpf_adapter *adapter = vport->adapter;
+ struct idpf_vport *new_vport;
+- int err, i;
++ int err;
+
+ /* If the system is low on memory, we can end up in bad state if we
+ * free all the memory for queue resources and try to allocate them
+@@ -1923,46 +1919,6 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
+ */
+ memcpy(vport, new_vport, offsetof(struct idpf_vport, link_speed_mbps));
+
+- /* Since idpf_vport_queues_alloc was called with new_port, the queue
+- * back pointers are currently pointing to the local new_vport. Reset
+- * the backpointers to the original vport here
+- */
+- for (i = 0; i < vport->num_txq_grp; i++) {
+- struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+- int j;
+-
+- tx_qgrp->vport = vport;
+- for (j = 0; j < tx_qgrp->num_txq; j++)
+- tx_qgrp->txqs[j]->vport = vport;
+-
+- if (idpf_is_queue_model_split(vport->txq_model))
+- tx_qgrp->complq->vport = vport;
+- }
+-
+- for (i = 0; i < vport->num_rxq_grp; i++) {
+- struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+- struct idpf_queue *q;
+- u16 num_rxq;
+- int j;
+-
+- rx_qgrp->vport = vport;
+- for (j = 0; j < vport->num_bufqs_per_qgrp; j++)
+- rx_qgrp->splitq.bufq_sets[j].bufq.vport = vport;
+-
+- if (idpf_is_queue_model_split(vport->rxq_model))
+- num_rxq = rx_qgrp->splitq.num_rxq_sets;
+- else
+- num_rxq = rx_qgrp->singleq.num_rxq;
+-
+- for (j = 0; j < num_rxq; j++) {
+- if (idpf_is_queue_model_split(vport->rxq_model))
+- q = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+- else
+- q = rx_qgrp->singleq.rxqs[j];
+- q->vport = vport;
+- }
+- }
+-
+ if (reset_cause == IDPF_SR_Q_CHANGE)
+ idpf_vport_alloc_vec_indexes(vport);
+
+@@ -2393,24 +2349,10 @@ void idpf_free_dma_mem(struct idpf_hw *hw, struct idpf_dma_mem *mem)
+ mem->pa = 0;
+ }
+
+-static const struct net_device_ops idpf_netdev_ops_splitq = {
+- .ndo_open = idpf_open,
+- .ndo_stop = idpf_stop,
+- .ndo_start_xmit = idpf_tx_splitq_start,
+- .ndo_features_check = idpf_features_check,
+- .ndo_set_rx_mode = idpf_set_rx_mode,
+- .ndo_validate_addr = eth_validate_addr,
+- .ndo_set_mac_address = idpf_set_mac,
+- .ndo_change_mtu = idpf_change_mtu,
+- .ndo_get_stats64 = idpf_get_stats64,
+- .ndo_set_features = idpf_set_features,
+- .ndo_tx_timeout = idpf_tx_timeout,
+-};
+-
+-static const struct net_device_ops idpf_netdev_ops_singleq = {
++static const struct net_device_ops idpf_netdev_ops = {
+ .ndo_open = idpf_open,
+ .ndo_stop = idpf_stop,
+- .ndo_start_xmit = idpf_tx_singleq_start,
++ .ndo_start_xmit = idpf_tx_start,
+ .ndo_features_check = idpf_features_check,
+ .ndo_set_rx_mode = idpf_set_rx_mode,
+ .ndo_validate_addr = eth_validate_addr,
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+index 27b93592c4babb..5e5fa2d0aa4d18 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
++++ b/drivers/net/ethernet/intel/idpf/idpf_singleq_txrx.c
+@@ -186,7 +186,7 @@ static int idpf_tx_singleq_csum(struct sk_buff *skb,
+ * and gets a physical address for each memory location and programs
+ * it and the length into the transmit base mode descriptor.
+ */
+-static void idpf_tx_singleq_map(struct idpf_queue *tx_q,
++static void idpf_tx_singleq_map(struct idpf_tx_queue *tx_q,
+ struct idpf_tx_buf *first,
+ struct idpf_tx_offload_params *offloads)
+ {
+@@ -205,12 +205,12 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q,
+ data_len = skb->data_len;
+ size = skb_headlen(skb);
+
+- tx_desc = IDPF_BASE_TX_DESC(tx_q, i);
++ tx_desc = &tx_q->base_tx[i];
+
+ dma = dma_map_single(tx_q->dev, skb->data, size, DMA_TO_DEVICE);
+
+ /* write each descriptor with CRC bit */
+- if (tx_q->vport->crc_enable)
++ if (idpf_queue_has(CRC_EN, tx_q))
+ td_cmd |= IDPF_TX_DESC_CMD_ICRC;
+
+ for (frag = &skb_shinfo(skb)->frags[0];; frag++) {
+@@ -239,7 +239,7 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q,
+ i++;
+
+ if (i == tx_q->desc_count) {
+- tx_desc = IDPF_BASE_TX_DESC(tx_q, 0);
++ tx_desc = &tx_q->base_tx[0];
+ i = 0;
+ }
+
+@@ -259,7 +259,7 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q,
+ i++;
+
+ if (i == tx_q->desc_count) {
+- tx_desc = IDPF_BASE_TX_DESC(tx_q, 0);
++ tx_desc = &tx_q->base_tx[0];
+ i = 0;
+ }
+
+@@ -285,7 +285,7 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q,
+ /* set next_to_watch value indicating a packet is present */
+ first->next_to_watch = tx_desc;
+
+- nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx);
++ nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
+ netdev_tx_sent_queue(nq, first->bytecount);
+
+ idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more());
+@@ -299,7 +299,7 @@ static void idpf_tx_singleq_map(struct idpf_queue *tx_q,
+ * ring entry to reflect that this index is a context descriptor
+ */
+ static struct idpf_base_tx_ctx_desc *
+-idpf_tx_singleq_get_ctx_desc(struct idpf_queue *txq)
++idpf_tx_singleq_get_ctx_desc(struct idpf_tx_queue *txq)
+ {
+ struct idpf_base_tx_ctx_desc *ctx_desc;
+ int ntu = txq->next_to_use;
+@@ -307,7 +307,7 @@ idpf_tx_singleq_get_ctx_desc(struct idpf_queue *txq)
+ memset(&txq->tx_buf[ntu], 0, sizeof(struct idpf_tx_buf));
+ txq->tx_buf[ntu].ctx_entry = true;
+
+- ctx_desc = IDPF_BASE_TX_CTX_DESC(txq, ntu);
++ ctx_desc = &txq->base_ctx[ntu];
+
+ IDPF_SINGLEQ_BUMP_RING_IDX(txq, ntu);
+ txq->next_to_use = ntu;
+@@ -320,7 +320,7 @@ idpf_tx_singleq_get_ctx_desc(struct idpf_queue *txq)
+ * @txq: queue to send buffer on
+ * @offload: offload parameter structure
+ **/
+-static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq,
++static void idpf_tx_singleq_build_ctx_desc(struct idpf_tx_queue *txq,
+ struct idpf_tx_offload_params *offload)
+ {
+ struct idpf_base_tx_ctx_desc *desc = idpf_tx_singleq_get_ctx_desc(txq);
+@@ -333,7 +333,7 @@ static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq,
+ qw1 |= FIELD_PREP(IDPF_TXD_CTX_QW1_MSS_M, offload->mss);
+
+ u64_stats_update_begin(&txq->stats_sync);
+- u64_stats_inc(&txq->q_stats.tx.lso_pkts);
++ u64_stats_inc(&txq->q_stats.lso_pkts);
+ u64_stats_update_end(&txq->stats_sync);
+ }
+
+@@ -351,8 +351,8 @@ static void idpf_tx_singleq_build_ctx_desc(struct idpf_queue *txq,
+ *
+ * Returns NETDEV_TX_OK if sent, else an error code
+ */
+-static netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
+- struct idpf_queue *tx_q)
++netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
++ struct idpf_tx_queue *tx_q)
+ {
+ struct idpf_tx_offload_params offload = { };
+ struct idpf_tx_buf *first;
+@@ -369,6 +369,10 @@ static netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
+ IDPF_TX_DESCS_FOR_CTX)) {
+ idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
+
++ u64_stats_update_begin(&tx_q->stats_sync);
++ u64_stats_inc(&tx_q->q_stats.q_busy);
++ u64_stats_update_end(&tx_q->stats_sync);
++
+ return NETDEV_TX_BUSY;
+ }
+
+@@ -408,33 +412,6 @@ static netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
+ return idpf_tx_drop_skb(tx_q, skb);
+ }
+
+-/**
+- * idpf_tx_singleq_start - Selects the right Tx queue to send buffer
+- * @skb: send buffer
+- * @netdev: network interface device structure
+- *
+- * Returns NETDEV_TX_OK if sent, else an error code
+- */
+-netdev_tx_t idpf_tx_singleq_start(struct sk_buff *skb,
+- struct net_device *netdev)
+-{
+- struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
+- struct idpf_queue *tx_q;
+-
+- tx_q = vport->txqs[skb_get_queue_mapping(skb)];
+-
+- /* hardware can't handle really short frames, hardware padding works
+- * beyond this point
+- */
+- if (skb_put_padto(skb, IDPF_TX_MIN_PKT_LEN)) {
+- idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
+-
+- return NETDEV_TX_OK;
+- }
+-
+- return idpf_tx_singleq_frame(skb, tx_q);
+-}
+-
+ /**
+ * idpf_tx_singleq_clean - Reclaim resources from queue
+ * @tx_q: Tx queue to clean
+@@ -442,20 +419,19 @@ netdev_tx_t idpf_tx_singleq_start(struct sk_buff *skb,
+ * @cleaned: returns number of packets cleaned
+ *
+ */
+-static bool idpf_tx_singleq_clean(struct idpf_queue *tx_q, int napi_budget,
++static bool idpf_tx_singleq_clean(struct idpf_tx_queue *tx_q, int napi_budget,
+ int *cleaned)
+ {
+- unsigned int budget = tx_q->vport->compln_clean_budget;
+ unsigned int total_bytes = 0, total_pkts = 0;
+ struct idpf_base_tx_desc *tx_desc;
++ u32 budget = tx_q->clean_budget;
+ s16 ntc = tx_q->next_to_clean;
+ struct idpf_netdev_priv *np;
+ struct idpf_tx_buf *tx_buf;
+- struct idpf_vport *vport;
+ struct netdev_queue *nq;
+ bool dont_wake;
+
+- tx_desc = IDPF_BASE_TX_DESC(tx_q, ntc);
++ tx_desc = &tx_q->base_tx[ntc];
+ tx_buf = &tx_q->tx_buf[ntc];
+ ntc -= tx_q->desc_count;
+
+@@ -517,7 +493,7 @@ static bool idpf_tx_singleq_clean(struct idpf_queue *tx_q, int napi_budget,
+ if (unlikely(!ntc)) {
+ ntc -= tx_q->desc_count;
+ tx_buf = tx_q->tx_buf;
+- tx_desc = IDPF_BASE_TX_DESC(tx_q, 0);
++ tx_desc = &tx_q->base_tx[0];
+ }
+
+ /* unmap any remaining paged data */
+@@ -540,7 +516,7 @@ static bool idpf_tx_singleq_clean(struct idpf_queue *tx_q, int napi_budget,
+ if (unlikely(!ntc)) {
+ ntc -= tx_q->desc_count;
+ tx_buf = tx_q->tx_buf;
+- tx_desc = IDPF_BASE_TX_DESC(tx_q, 0);
++ tx_desc = &tx_q->base_tx[0];
+ }
+ } while (likely(budget));
+
+@@ -550,16 +526,15 @@ static bool idpf_tx_singleq_clean(struct idpf_queue *tx_q, int napi_budget,
+ *cleaned += total_pkts;
+
+ u64_stats_update_begin(&tx_q->stats_sync);
+- u64_stats_add(&tx_q->q_stats.tx.packets, total_pkts);
+- u64_stats_add(&tx_q->q_stats.tx.bytes, total_bytes);
++ u64_stats_add(&tx_q->q_stats.packets, total_pkts);
++ u64_stats_add(&tx_q->q_stats.bytes, total_bytes);
+ u64_stats_update_end(&tx_q->stats_sync);
+
+- vport = tx_q->vport;
+- np = netdev_priv(vport->netdev);
+- nq = netdev_get_tx_queue(vport->netdev, tx_q->idx);
++ np = netdev_priv(tx_q->netdev);
++ nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
+
+ dont_wake = np->state != __IDPF_VPORT_UP ||
+- !netif_carrier_ok(vport->netdev);
++ !netif_carrier_ok(tx_q->netdev);
+ __netif_txq_completed_wake(nq, total_pkts, total_bytes,
+ IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH,
+ dont_wake);
+@@ -584,7 +559,7 @@ static bool idpf_tx_singleq_clean_all(struct idpf_q_vector *q_vec, int budget,
+
+ budget_per_q = num_txq ? max(budget / num_txq, 1) : 0;
+ for (i = 0; i < num_txq; i++) {
+- struct idpf_queue *q;
++ struct idpf_tx_queue *q;
+
+ q = q_vec->tx[i];
+ clean_complete &= idpf_tx_singleq_clean(q, budget_per_q,
+@@ -614,14 +589,9 @@ static bool idpf_rx_singleq_test_staterr(const union virtchnl2_rx_desc *rx_desc,
+
+ /**
+ * idpf_rx_singleq_is_non_eop - process handling of non-EOP buffers
+- * @rxq: Rx ring being processed
+ * @rx_desc: Rx descriptor for current buffer
+- * @skb: Current socket buffer containing buffer in progress
+- * @ntc: next to clean
+ */
+-static bool idpf_rx_singleq_is_non_eop(struct idpf_queue *rxq,
+- union virtchnl2_rx_desc *rx_desc,
+- struct sk_buff *skb, u16 ntc)
++static bool idpf_rx_singleq_is_non_eop(const union virtchnl2_rx_desc *rx_desc)
+ {
+ /* if we are the last buffer then there is nothing else to do */
+ if (likely(idpf_rx_singleq_test_staterr(rx_desc, IDPF_RXD_EOF_SINGLEQ)))
+@@ -639,7 +609,7 @@ static bool idpf_rx_singleq_is_non_eop(struct idpf_queue *rxq,
+ *
+ * skb->protocol must be set before this function is called
+ */
+-static void idpf_rx_singleq_csum(struct idpf_queue *rxq, struct sk_buff *skb,
++static void idpf_rx_singleq_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
+ struct idpf_rx_csum_decoded *csum_bits,
+ u16 ptype)
+ {
+@@ -647,14 +617,14 @@ static void idpf_rx_singleq_csum(struct idpf_queue *rxq, struct sk_buff *skb,
+ bool ipv4, ipv6;
+
+ /* check if Rx checksum is enabled */
+- if (unlikely(!(rxq->vport->netdev->features & NETIF_F_RXCSUM)))
++ if (unlikely(!(rxq->netdev->features & NETIF_F_RXCSUM)))
+ return;
+
+ /* check if HW has decoded the packet and checksum */
+ if (unlikely(!(csum_bits->l3l4p)))
+ return;
+
+- decoded = rxq->vport->rx_ptype_lkup[ptype];
++ decoded = rxq->rx_ptype_lkup[ptype];
+ if (unlikely(!(decoded.known && decoded.outer_ip)))
+ return;
+
+@@ -707,7 +677,7 @@ static void idpf_rx_singleq_csum(struct idpf_queue *rxq, struct sk_buff *skb,
+
+ checksum_fail:
+ u64_stats_update_begin(&rxq->stats_sync);
+- u64_stats_inc(&rxq->q_stats.rx.hw_csum_err);
++ u64_stats_inc(&rxq->q_stats.hw_csum_err);
+ u64_stats_update_end(&rxq->stats_sync);
+ }
+
+@@ -721,9 +691,9 @@ static void idpf_rx_singleq_csum(struct idpf_queue *rxq, struct sk_buff *skb,
+ * This function only operates on the VIRTCHNL2_RXDID_1_32B_BASE_M base 32byte
+ * descriptor writeback format.
+ **/
+-static void idpf_rx_singleq_base_csum(struct idpf_queue *rx_q,
++static void idpf_rx_singleq_base_csum(struct idpf_rx_queue *rx_q,
+ struct sk_buff *skb,
+- union virtchnl2_rx_desc *rx_desc,
++ const union virtchnl2_rx_desc *rx_desc,
+ u16 ptype)
+ {
+ struct idpf_rx_csum_decoded csum_bits;
+@@ -761,9 +731,9 @@ static void idpf_rx_singleq_base_csum(struct idpf_queue *rx_q,
+ * This function only operates on the VIRTCHNL2_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ **/
+-static void idpf_rx_singleq_flex_csum(struct idpf_queue *rx_q,
++static void idpf_rx_singleq_flex_csum(struct idpf_rx_queue *rx_q,
+ struct sk_buff *skb,
+- union virtchnl2_rx_desc *rx_desc,
++ const union virtchnl2_rx_desc *rx_desc,
+ u16 ptype)
+ {
+ struct idpf_rx_csum_decoded csum_bits;
+@@ -801,14 +771,14 @@ static void idpf_rx_singleq_flex_csum(struct idpf_queue *rx_q,
+ * This function only operates on the VIRTCHNL2_RXDID_1_32B_BASE_M base 32byte
+ * descriptor writeback format.
+ **/
+-static void idpf_rx_singleq_base_hash(struct idpf_queue *rx_q,
++static void idpf_rx_singleq_base_hash(struct idpf_rx_queue *rx_q,
+ struct sk_buff *skb,
+- union virtchnl2_rx_desc *rx_desc,
++ const union virtchnl2_rx_desc *rx_desc,
+ struct idpf_rx_ptype_decoded *decoded)
+ {
+ u64 mask, qw1;
+
+- if (unlikely(!(rx_q->vport->netdev->features & NETIF_F_RXHASH)))
++ if (unlikely(!(rx_q->netdev->features & NETIF_F_RXHASH)))
+ return;
+
+ mask = VIRTCHNL2_RX_BASE_DESC_FLTSTAT_RSS_HASH_M;
+@@ -831,12 +801,12 @@ static void idpf_rx_singleq_base_hash(struct idpf_queue *rx_q,
+ * This function only operates on the VIRTCHNL2_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ **/
+-static void idpf_rx_singleq_flex_hash(struct idpf_queue *rx_q,
++static void idpf_rx_singleq_flex_hash(struct idpf_rx_queue *rx_q,
+ struct sk_buff *skb,
+- union virtchnl2_rx_desc *rx_desc,
++ const union virtchnl2_rx_desc *rx_desc,
+ struct idpf_rx_ptype_decoded *decoded)
+ {
+- if (unlikely(!(rx_q->vport->netdev->features & NETIF_F_RXHASH)))
++ if (unlikely(!(rx_q->netdev->features & NETIF_F_RXHASH)))
+ return;
+
+ if (FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_STATUS0_RSS_VALID_M,
+@@ -857,16 +827,16 @@ static void idpf_rx_singleq_flex_hash(struct idpf_queue *rx_q,
+ * order to populate the hash, checksum, VLAN, protocol, and
+ * other fields within the skb.
+ */
+-static void idpf_rx_singleq_process_skb_fields(struct idpf_queue *rx_q,
+- struct sk_buff *skb,
+- union virtchnl2_rx_desc *rx_desc,
+- u16 ptype)
++static void
++idpf_rx_singleq_process_skb_fields(struct idpf_rx_queue *rx_q,
++ struct sk_buff *skb,
++ const union virtchnl2_rx_desc *rx_desc,
++ u16 ptype)
+ {
+- struct idpf_rx_ptype_decoded decoded =
+- rx_q->vport->rx_ptype_lkup[ptype];
++ struct idpf_rx_ptype_decoded decoded = rx_q->rx_ptype_lkup[ptype];
+
+ /* modifies the skb - consumes the enet header */
+- skb->protocol = eth_type_trans(skb, rx_q->vport->netdev);
++ skb->protocol = eth_type_trans(skb, rx_q->netdev);
+
+ /* Check if we're using base mode descriptor IDs */
+ if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M) {
+@@ -878,6 +848,22 @@ static void idpf_rx_singleq_process_skb_fields(struct idpf_queue *rx_q,
+ }
+ }
+
++/**
++ * idpf_rx_buf_hw_update - Store the new tail and head values
++ * @rxq: queue to bump
++ * @val: new head index
++ */
++static void idpf_rx_buf_hw_update(struct idpf_rx_queue *rxq, u32 val)
++{
++ rxq->next_to_use = val;
++
++ if (unlikely(!rxq->tail))
++ return;
++
++ /* writel has an implicit memory barrier */
++ writel(val, rxq->tail);
++}
++
+ /**
+ * idpf_rx_singleq_buf_hw_alloc_all - Replace used receive buffers
+ * @rx_q: queue for which the hw buffers are allocated
+@@ -885,7 +871,7 @@ static void idpf_rx_singleq_process_skb_fields(struct idpf_queue *rx_q,
+ *
+ * Returns false if all allocations were successful, true if any fail
+ */
+-bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q,
++bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rx_q,
+ u16 cleaned_count)
+ {
+ struct virtchnl2_singleq_rx_buf_desc *desc;
+@@ -895,8 +881,8 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q,
+ if (!cleaned_count)
+ return false;
+
+- desc = IDPF_SINGLEQ_RX_BUF_DESC(rx_q, nta);
+- buf = &rx_q->rx_buf.buf[nta];
++ desc = &rx_q->single_buf[nta];
++ buf = &rx_q->rx_buf[nta];
+
+ do {
+ dma_addr_t addr;
+@@ -915,8 +901,8 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q,
+ buf++;
+ nta++;
+ if (unlikely(nta == rx_q->desc_count)) {
+- desc = IDPF_SINGLEQ_RX_BUF_DESC(rx_q, 0);
+- buf = rx_q->rx_buf.buf;
++ desc = &rx_q->single_buf[0];
++ buf = rx_q->rx_buf;
+ nta = 0;
+ }
+
+@@ -933,7 +919,6 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q,
+
+ /**
+ * idpf_rx_singleq_extract_base_fields - Extract fields from the Rx descriptor
+- * @rx_q: Rx descriptor queue
+ * @rx_desc: the descriptor to process
+ * @fields: storage for extracted values
+ *
+@@ -943,9 +928,9 @@ bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rx_q,
+ * This function only operates on the VIRTCHNL2_RXDID_1_32B_BASE_M base 32byte
+ * descriptor writeback format.
+ */
+-static void idpf_rx_singleq_extract_base_fields(struct idpf_queue *rx_q,
+- union virtchnl2_rx_desc *rx_desc,
+- struct idpf_rx_extracted *fields)
++static void
++idpf_rx_singleq_extract_base_fields(const union virtchnl2_rx_desc *rx_desc,
++ struct idpf_rx_extracted *fields)
+ {
+ u64 qword;
+
+@@ -957,7 +942,6 @@ static void idpf_rx_singleq_extract_base_fields(struct idpf_queue *rx_q,
+
+ /**
+ * idpf_rx_singleq_extract_flex_fields - Extract fields from the Rx descriptor
+- * @rx_q: Rx descriptor queue
+ * @rx_desc: the descriptor to process
+ * @fields: storage for extracted values
+ *
+@@ -967,9 +951,9 @@ static void idpf_rx_singleq_extract_base_fields(struct idpf_queue *rx_q,
+ * This function only operates on the VIRTCHNL2_RXDID_2_FLEX_SQ_NIC flexible
+ * descriptor writeback format.
+ */
+-static void idpf_rx_singleq_extract_flex_fields(struct idpf_queue *rx_q,
+- union virtchnl2_rx_desc *rx_desc,
+- struct idpf_rx_extracted *fields)
++static void
++idpf_rx_singleq_extract_flex_fields(const union virtchnl2_rx_desc *rx_desc,
++ struct idpf_rx_extracted *fields)
+ {
+ fields->size = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_PKT_LEN_M,
+ le16_to_cpu(rx_desc->flex_nic_wb.pkt_len));
+@@ -984,14 +968,15 @@ static void idpf_rx_singleq_extract_flex_fields(struct idpf_queue *rx_q,
+ * @fields: storage for extracted values
+ *
+ */
+-static void idpf_rx_singleq_extract_fields(struct idpf_queue *rx_q,
+- union virtchnl2_rx_desc *rx_desc,
+- struct idpf_rx_extracted *fields)
++static void
++idpf_rx_singleq_extract_fields(const struct idpf_rx_queue *rx_q,
++ const union virtchnl2_rx_desc *rx_desc,
++ struct idpf_rx_extracted *fields)
+ {
+ if (rx_q->rxdids == VIRTCHNL2_RXDID_1_32B_BASE_M)
+- idpf_rx_singleq_extract_base_fields(rx_q, rx_desc, fields);
++ idpf_rx_singleq_extract_base_fields(rx_desc, fields);
+ else
+- idpf_rx_singleq_extract_flex_fields(rx_q, rx_desc, fields);
++ idpf_rx_singleq_extract_flex_fields(rx_desc, fields);
+ }
+
+ /**
+@@ -1001,7 +986,7 @@ static void idpf_rx_singleq_extract_fields(struct idpf_queue *rx_q,
+ *
+ * Returns true if there's any budget left (e.g. the clean is finished)
+ */
+-static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget)
++static int idpf_rx_singleq_clean(struct idpf_rx_queue *rx_q, int budget)
+ {
+ unsigned int total_rx_bytes = 0, total_rx_pkts = 0;
+ struct sk_buff *skb = rx_q->skb;
+@@ -1016,7 +1001,7 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget)
+ struct idpf_rx_buf *rx_buf;
+
+ /* get the Rx desc from Rx queue based on 'next_to_clean' */
+- rx_desc = IDPF_RX_DESC(rx_q, ntc);
++ rx_desc = &rx_q->rx[ntc];
+
+ /* status_error_ptype_len will always be zero for unused
+ * descriptors because it's cleared in cleanup, and overlaps
+@@ -1036,7 +1021,7 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget)
+
+ idpf_rx_singleq_extract_fields(rx_q, rx_desc, &fields);
+
+- rx_buf = &rx_q->rx_buf.buf[ntc];
++ rx_buf = &rx_q->rx_buf[ntc];
+ if (!fields.size) {
+ idpf_rx_put_page(rx_buf);
+ goto skip_data;
+@@ -1058,7 +1043,7 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget)
+ cleaned_count++;
+
+ /* skip if it is non EOP desc */
+- if (idpf_rx_singleq_is_non_eop(rx_q, rx_desc, skb, ntc))
++ if (idpf_rx_singleq_is_non_eop(rx_desc))
+ continue;
+
+ #define IDPF_RXD_ERR_S FIELD_PREP(VIRTCHNL2_RX_BASE_DESC_QW1_ERROR_M, \
+@@ -1084,7 +1069,7 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget)
+ rx_desc, fields.rx_ptype);
+
+ /* send completed skb up the stack */
+- napi_gro_receive(&rx_q->q_vector->napi, skb);
++ napi_gro_receive(rx_q->pp->p.napi, skb);
+ skb = NULL;
+
+ /* update budget accounting */
+@@ -1099,8 +1084,8 @@ static int idpf_rx_singleq_clean(struct idpf_queue *rx_q, int budget)
+ failure = idpf_rx_singleq_buf_hw_alloc_all(rx_q, cleaned_count);
+
+ u64_stats_update_begin(&rx_q->stats_sync);
+- u64_stats_add(&rx_q->q_stats.rx.packets, total_rx_pkts);
+- u64_stats_add(&rx_q->q_stats.rx.bytes, total_rx_bytes);
++ u64_stats_add(&rx_q->q_stats.packets, total_rx_pkts);
++ u64_stats_add(&rx_q->q_stats.bytes, total_rx_bytes);
+ u64_stats_update_end(&rx_q->stats_sync);
+
+ /* guarantee a trip back through this routine if there was a failure */
+@@ -1127,7 +1112,7 @@ static bool idpf_rx_singleq_clean_all(struct idpf_q_vector *q_vec, int budget,
+ */
+ budget_per_q = num_rxq ? max(budget / num_rxq, 1) : 0;
+ for (i = 0; i < num_rxq; i++) {
+- struct idpf_queue *rxq = q_vec->rx[i];
++ struct idpf_rx_queue *rxq = q_vec->rx[i];
+ int pkts_cleaned_per_q;
+
+ pkts_cleaned_per_q = idpf_rx_singleq_clean(rxq, budget_per_q);
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+index 20ca04320d4bde..9b7e67d0f38be9 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
++++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+@@ -4,6 +4,9 @@
+ #include "idpf.h"
+ #include "idpf_virtchnl.h"
+
++static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
++ unsigned int count);
++
+ /**
+ * idpf_buf_lifo_push - push a buffer pointer onto stack
+ * @stack: pointer to stack struct
+@@ -60,7 +63,8 @@ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue)
+ * @tx_q: the queue that owns the buffer
+ * @tx_buf: the buffer to free
+ */
+-static void idpf_tx_buf_rel(struct idpf_queue *tx_q, struct idpf_tx_buf *tx_buf)
++static void idpf_tx_buf_rel(struct idpf_tx_queue *tx_q,
++ struct idpf_tx_buf *tx_buf)
+ {
+ if (tx_buf->skb) {
+ if (dma_unmap_len(tx_buf, len))
+@@ -86,8 +90,9 @@ static void idpf_tx_buf_rel(struct idpf_queue *tx_q, struct idpf_tx_buf *tx_buf)
+ * idpf_tx_buf_rel_all - Free any empty Tx buffers
+ * @txq: queue to be cleaned
+ */
+-static void idpf_tx_buf_rel_all(struct idpf_queue *txq)
++static void idpf_tx_buf_rel_all(struct idpf_tx_queue *txq)
+ {
++ struct idpf_buf_lifo *buf_stack;
+ u16 i;
+
+ /* Buffers already cleared, nothing to do */
+@@ -101,38 +106,57 @@ static void idpf_tx_buf_rel_all(struct idpf_queue *txq)
+ kfree(txq->tx_buf);
+ txq->tx_buf = NULL;
+
+- if (!txq->buf_stack.bufs)
++ if (!idpf_queue_has(FLOW_SCH_EN, txq))
++ return;
++
++ buf_stack = &txq->stash->buf_stack;
++ if (!buf_stack->bufs)
+ return;
+
+- for (i = 0; i < txq->buf_stack.size; i++)
+- kfree(txq->buf_stack.bufs[i]);
++ for (i = 0; i < buf_stack->size; i++)
++ kfree(buf_stack->bufs[i]);
+
+- kfree(txq->buf_stack.bufs);
+- txq->buf_stack.bufs = NULL;
++ kfree(buf_stack->bufs);
++ buf_stack->bufs = NULL;
+ }
+
+ /**
+ * idpf_tx_desc_rel - Free Tx resources per queue
+ * @txq: Tx descriptor ring for a specific queue
+- * @bufq: buffer q or completion q
+ *
+ * Free all transmit software resources
+ */
+-static void idpf_tx_desc_rel(struct idpf_queue *txq, bool bufq)
++static void idpf_tx_desc_rel(struct idpf_tx_queue *txq)
+ {
+- if (bufq)
+- idpf_tx_buf_rel_all(txq);
++ idpf_tx_buf_rel_all(txq);
+
+ if (!txq->desc_ring)
+ return;
+
+ dmam_free_coherent(txq->dev, txq->size, txq->desc_ring, txq->dma);
+ txq->desc_ring = NULL;
+- txq->next_to_alloc = 0;
+ txq->next_to_use = 0;
+ txq->next_to_clean = 0;
+ }
+
++/**
++ * idpf_compl_desc_rel - Free completion resources per queue
++ * @complq: completion queue
++ *
++ * Free all completion software resources.
++ */
++static void idpf_compl_desc_rel(struct idpf_compl_queue *complq)
++{
++ if (!complq->comp)
++ return;
++
++ dma_free_coherent(complq->netdev->dev.parent, complq->size,
++ complq->comp, complq->dma);
++ complq->comp = NULL;
++ complq->next_to_use = 0;
++ complq->next_to_clean = 0;
++}
++
+ /**
+ * idpf_tx_desc_rel_all - Free Tx Resources for All Queues
+ * @vport: virtual port structure
+@@ -150,10 +174,10 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport)
+ struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
+
+ for (j = 0; j < txq_grp->num_txq; j++)
+- idpf_tx_desc_rel(txq_grp->txqs[j], true);
++ idpf_tx_desc_rel(txq_grp->txqs[j]);
+
+ if (idpf_is_queue_model_split(vport->txq_model))
+- idpf_tx_desc_rel(txq_grp->complq, false);
++ idpf_compl_desc_rel(txq_grp->complq);
+ }
+ }
+
+@@ -163,8 +187,9 @@ static void idpf_tx_desc_rel_all(struct idpf_vport *vport)
+ *
+ * Returns 0 on success, negative on failure
+ */
+-static int idpf_tx_buf_alloc_all(struct idpf_queue *tx_q)
++static int idpf_tx_buf_alloc_all(struct idpf_tx_queue *tx_q)
+ {
++ struct idpf_buf_lifo *buf_stack;
+ int buf_size;
+ int i;
+
+@@ -180,22 +205,26 @@ static int idpf_tx_buf_alloc_all(struct idpf_queue *tx_q)
+ for (i = 0; i < tx_q->desc_count; i++)
+ tx_q->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
+
++ if (!idpf_queue_has(FLOW_SCH_EN, tx_q))
++ return 0;
++
++ buf_stack = &tx_q->stash->buf_stack;
++
+ /* Initialize tx buf stack for out-of-order completions if
+ * flow scheduling offload is enabled
+ */
+- tx_q->buf_stack.bufs =
+- kcalloc(tx_q->desc_count, sizeof(struct idpf_tx_stash *),
+- GFP_KERNEL);
+- if (!tx_q->buf_stack.bufs)
++ buf_stack->bufs = kcalloc(tx_q->desc_count, sizeof(*buf_stack->bufs),
++ GFP_KERNEL);
++ if (!buf_stack->bufs)
+ return -ENOMEM;
+
+- tx_q->buf_stack.size = tx_q->desc_count;
+- tx_q->buf_stack.top = tx_q->desc_count;
++ buf_stack->size = tx_q->desc_count;
++ buf_stack->top = tx_q->desc_count;
+
+ for (i = 0; i < tx_q->desc_count; i++) {
+- tx_q->buf_stack.bufs[i] = kzalloc(sizeof(*tx_q->buf_stack.bufs[i]),
+- GFP_KERNEL);
+- if (!tx_q->buf_stack.bufs[i])
++ buf_stack->bufs[i] = kzalloc(sizeof(*buf_stack->bufs[i]),
++ GFP_KERNEL);
++ if (!buf_stack->bufs[i])
+ return -ENOMEM;
+ }
+
+@@ -204,28 +233,22 @@ static int idpf_tx_buf_alloc_all(struct idpf_queue *tx_q)
+
+ /**
+ * idpf_tx_desc_alloc - Allocate the Tx descriptors
++ * @vport: vport to allocate resources for
+ * @tx_q: the tx ring to set up
+- * @bufq: buffer or completion queue
+ *
+ * Returns 0 on success, negative on failure
+ */
+-static int idpf_tx_desc_alloc(struct idpf_queue *tx_q, bool bufq)
++static int idpf_tx_desc_alloc(const struct idpf_vport *vport,
++ struct idpf_tx_queue *tx_q)
+ {
+ struct device *dev = tx_q->dev;
+- u32 desc_sz;
+ int err;
+
+- if (bufq) {
+- err = idpf_tx_buf_alloc_all(tx_q);
+- if (err)
+- goto err_alloc;
+-
+- desc_sz = sizeof(struct idpf_base_tx_desc);
+- } else {
+- desc_sz = sizeof(struct idpf_splitq_tx_compl_desc);
+- }
++ err = idpf_tx_buf_alloc_all(tx_q);
++ if (err)
++ goto err_alloc;
+
+- tx_q->size = tx_q->desc_count * desc_sz;
++ tx_q->size = tx_q->desc_count * sizeof(*tx_q->base_tx);
+
+ /* Allocate descriptors also round up to nearest 4K */
+ tx_q->size = ALIGN(tx_q->size, 4096);
+@@ -238,19 +261,43 @@ static int idpf_tx_desc_alloc(struct idpf_queue *tx_q, bool bufq)
+ goto err_alloc;
+ }
+
+- tx_q->next_to_alloc = 0;
+ tx_q->next_to_use = 0;
+ tx_q->next_to_clean = 0;
+- set_bit(__IDPF_Q_GEN_CHK, tx_q->flags);
++ idpf_queue_set(GEN_CHK, tx_q);
+
+ return 0;
+
+ err_alloc:
+- idpf_tx_desc_rel(tx_q, bufq);
++ idpf_tx_desc_rel(tx_q);
+
+ return err;
+ }
+
++/**
++ * idpf_compl_desc_alloc - allocate completion descriptors
++ * @vport: vport to allocate resources for
++ * @complq: completion queue to set up
++ *
++ * Return: 0 on success, -errno on failure.
++ */
++static int idpf_compl_desc_alloc(const struct idpf_vport *vport,
++ struct idpf_compl_queue *complq)
++{
++ complq->size = array_size(complq->desc_count, sizeof(*complq->comp));
++
++ complq->comp = dma_alloc_coherent(complq->netdev->dev.parent,
++ complq->size, &complq->dma,
++ GFP_KERNEL);
++ if (!complq->comp)
++ return -ENOMEM;
++
++ complq->next_to_use = 0;
++ complq->next_to_clean = 0;
++ idpf_queue_set(GEN_CHK, complq);
++
++ return 0;
++}
++
+ /**
+ * idpf_tx_desc_alloc_all - allocate all queues Tx resources
+ * @vport: virtual port private structure
+@@ -259,7 +306,6 @@ static int idpf_tx_desc_alloc(struct idpf_queue *tx_q, bool bufq)
+ */
+ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
+ {
+- struct device *dev = &vport->adapter->pdev->dev;
+ int err = 0;
+ int i, j;
+
+@@ -268,13 +314,14 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
+ */
+ for (i = 0; i < vport->num_txq_grp; i++) {
+ for (j = 0; j < vport->txq_grps[i].num_txq; j++) {
+- struct idpf_queue *txq = vport->txq_grps[i].txqs[j];
++ struct idpf_tx_queue *txq = vport->txq_grps[i].txqs[j];
+ u8 gen_bits = 0;
+ u16 bufidx_mask;
+
+- err = idpf_tx_desc_alloc(txq, true);
++ err = idpf_tx_desc_alloc(vport, txq);
+ if (err) {
+- dev_err(dev, "Allocation for Tx Queue %u failed\n",
++ pci_err(vport->adapter->pdev,
++ "Allocation for Tx Queue %u failed\n",
+ i);
+ goto err_out;
+ }
+@@ -312,9 +359,10 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
+ continue;
+
+ /* Setup completion queues */
+- err = idpf_tx_desc_alloc(vport->txq_grps[i].complq, false);
++ err = idpf_compl_desc_alloc(vport, vport->txq_grps[i].complq);
+ if (err) {
+- dev_err(dev, "Allocation for Tx Completion Queue %u failed\n",
++ pci_err(vport->adapter->pdev,
++ "Allocation for Tx Completion Queue %u failed\n",
+ i);
+ goto err_out;
+ }
+@@ -329,15 +377,14 @@ static int idpf_tx_desc_alloc_all(struct idpf_vport *vport)
+
+ /**
+ * idpf_rx_page_rel - Release an rx buffer page
+- * @rxq: the queue that owns the buffer
+ * @rx_buf: the buffer to free
+ */
+-static void idpf_rx_page_rel(struct idpf_queue *rxq, struct idpf_rx_buf *rx_buf)
++static void idpf_rx_page_rel(struct idpf_rx_buf *rx_buf)
+ {
+ if (unlikely(!rx_buf->page))
+ return;
+
+- page_pool_put_full_page(rxq->pp, rx_buf->page, false);
++ page_pool_put_full_page(rx_buf->page->pp, rx_buf->page, false);
+
+ rx_buf->page = NULL;
+ rx_buf->page_offset = 0;
+@@ -345,54 +392,72 @@ static void idpf_rx_page_rel(struct idpf_queue *rxq, struct idpf_rx_buf *rx_buf)
+
+ /**
+ * idpf_rx_hdr_buf_rel_all - Release header buffer memory
+- * @rxq: queue to use
++ * @bufq: queue to use
++ * @dev: device to free DMA memory
+ */
+-static void idpf_rx_hdr_buf_rel_all(struct idpf_queue *rxq)
++static void idpf_rx_hdr_buf_rel_all(struct idpf_buf_queue *bufq,
++ struct device *dev)
+ {
+- struct idpf_adapter *adapter = rxq->vport->adapter;
+-
+- dma_free_coherent(&adapter->pdev->dev,
+- rxq->desc_count * IDPF_HDR_BUF_SIZE,
+- rxq->rx_buf.hdr_buf_va,
+- rxq->rx_buf.hdr_buf_pa);
+- rxq->rx_buf.hdr_buf_va = NULL;
++ dma_free_coherent(dev, bufq->desc_count * IDPF_HDR_BUF_SIZE,
++ bufq->rx_buf.hdr_buf_va, bufq->rx_buf.hdr_buf_pa);
++ bufq->rx_buf.hdr_buf_va = NULL;
+ }
+
+ /**
+- * idpf_rx_buf_rel_all - Free all Rx buffer resources for a queue
+- * @rxq: queue to be cleaned
++ * idpf_rx_buf_rel_bufq - Free all Rx buffer resources for a buffer queue
++ * @bufq: queue to be cleaned
++ * @dev: device to free DMA memory
+ */
+-static void idpf_rx_buf_rel_all(struct idpf_queue *rxq)
++static void idpf_rx_buf_rel_bufq(struct idpf_buf_queue *bufq,
++ struct device *dev)
+ {
+- u16 i;
+-
+ /* queue already cleared, nothing to do */
+- if (!rxq->rx_buf.buf)
++ if (!bufq->rx_buf.buf)
+ return;
+
+ /* Free all the bufs allocated and given to hw on Rx queue */
+- for (i = 0; i < rxq->desc_count; i++)
+- idpf_rx_page_rel(rxq, &rxq->rx_buf.buf[i]);
++ for (u32 i = 0; i < bufq->desc_count; i++)
++ idpf_rx_page_rel(&bufq->rx_buf.buf[i]);
++
++ if (idpf_queue_has(HSPLIT_EN, bufq))
++ idpf_rx_hdr_buf_rel_all(bufq, dev);
+
+- if (rxq->rx_hsplit_en)
+- idpf_rx_hdr_buf_rel_all(rxq);
++ page_pool_destroy(bufq->pp);
++ bufq->pp = NULL;
++
++ kfree(bufq->rx_buf.buf);
++ bufq->rx_buf.buf = NULL;
++}
++
++/**
++ * idpf_rx_buf_rel_all - Free all Rx buffer resources for a receive queue
++ * @rxq: queue to be cleaned
++ */
++static void idpf_rx_buf_rel_all(struct idpf_rx_queue *rxq)
++{
++ if (!rxq->rx_buf)
++ return;
++
++ for (u32 i = 0; i < rxq->desc_count; i++)
++ idpf_rx_page_rel(&rxq->rx_buf[i]);
+
+ page_pool_destroy(rxq->pp);
+ rxq->pp = NULL;
+
+- kfree(rxq->rx_buf.buf);
+- rxq->rx_buf.buf = NULL;
++ kfree(rxq->rx_buf);
++ rxq->rx_buf = NULL;
+ }
+
+ /**
+ * idpf_rx_desc_rel - Free a specific Rx q resources
+ * @rxq: queue to clean the resources from
+- * @bufq: buffer q or completion q
+- * @q_model: single or split q model
++ * @dev: device to free DMA memory
++ * @model: single or split queue model
+ *
+ * Free a specific rx queue resources
+ */
+-static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model)
++static void idpf_rx_desc_rel(struct idpf_rx_queue *rxq, struct device *dev,
++ u32 model)
+ {
+ if (!rxq)
+ return;
+@@ -402,7 +467,7 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model)
+ rxq->skb = NULL;
+ }
+
+- if (bufq || !idpf_is_queue_model_split(q_model))
++ if (!idpf_is_queue_model_split(model))
+ idpf_rx_buf_rel_all(rxq);
+
+ rxq->next_to_alloc = 0;
+@@ -411,10 +476,34 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model)
+ if (!rxq->desc_ring)
+ return;
+
+- dmam_free_coherent(rxq->dev, rxq->size, rxq->desc_ring, rxq->dma);
++ dmam_free_coherent(dev, rxq->size, rxq->desc_ring, rxq->dma);
+ rxq->desc_ring = NULL;
+ }
+
++/**
++ * idpf_rx_desc_rel_bufq - free buffer queue resources
++ * @bufq: buffer queue to clean the resources from
++ * @dev: device to free DMA memory
++ */
++static void idpf_rx_desc_rel_bufq(struct idpf_buf_queue *bufq,
++ struct device *dev)
++{
++ if (!bufq)
++ return;
++
++ idpf_rx_buf_rel_bufq(bufq, dev);
++
++ bufq->next_to_alloc = 0;
++ bufq->next_to_clean = 0;
++ bufq->next_to_use = 0;
++
++ if (!bufq->split_buf)
++ return;
++
++ dma_free_coherent(dev, bufq->size, bufq->split_buf, bufq->dma);
++ bufq->split_buf = NULL;
++}
++
+ /**
+ * idpf_rx_desc_rel_all - Free Rx Resources for All Queues
+ * @vport: virtual port structure
+@@ -423,6 +512,7 @@ static void idpf_rx_desc_rel(struct idpf_queue *rxq, bool bufq, s32 q_model)
+ */
+ static void idpf_rx_desc_rel_all(struct idpf_vport *vport)
+ {
++ struct device *dev = &vport->adapter->pdev->dev;
+ struct idpf_rxq_group *rx_qgrp;
+ u16 num_rxq;
+ int i, j;
+@@ -435,15 +525,15 @@ static void idpf_rx_desc_rel_all(struct idpf_vport *vport)
+
+ if (!idpf_is_queue_model_split(vport->rxq_model)) {
+ for (j = 0; j < rx_qgrp->singleq.num_rxq; j++)
+- idpf_rx_desc_rel(rx_qgrp->singleq.rxqs[j],
+- false, vport->rxq_model);
++ idpf_rx_desc_rel(rx_qgrp->singleq.rxqs[j], dev,
++ VIRTCHNL2_QUEUE_MODEL_SINGLE);
+ continue;
+ }
+
+ num_rxq = rx_qgrp->splitq.num_rxq_sets;
+ for (j = 0; j < num_rxq; j++)
+ idpf_rx_desc_rel(&rx_qgrp->splitq.rxq_sets[j]->rxq,
+- false, vport->rxq_model);
++ dev, VIRTCHNL2_QUEUE_MODEL_SPLIT);
+
+ if (!rx_qgrp->splitq.bufq_sets)
+ continue;
+@@ -452,44 +542,40 @@ static void idpf_rx_desc_rel_all(struct idpf_vport *vport)
+ struct idpf_bufq_set *bufq_set =
+ &rx_qgrp->splitq.bufq_sets[j];
+
+- idpf_rx_desc_rel(&bufq_set->bufq, true,
+- vport->rxq_model);
++ idpf_rx_desc_rel_bufq(&bufq_set->bufq, dev);
+ }
+ }
+ }
+
+ /**
+ * idpf_rx_buf_hw_update - Store the new tail and head values
+- * @rxq: queue to bump
++ * @bufq: queue to bump
+ * @val: new head index
+ */
+-void idpf_rx_buf_hw_update(struct idpf_queue *rxq, u32 val)
++static void idpf_rx_buf_hw_update(struct idpf_buf_queue *bufq, u32 val)
+ {
+- rxq->next_to_use = val;
++ bufq->next_to_use = val;
+
+- if (unlikely(!rxq->tail))
++ if (unlikely(!bufq->tail))
+ return;
+
+ /* writel has an implicit memory barrier */
+- writel(val, rxq->tail);
++ writel(val, bufq->tail);
+ }
+
+ /**
+ * idpf_rx_hdr_buf_alloc_all - Allocate memory for header buffers
+- * @rxq: ring to use
++ * @bufq: ring to use
+ *
+ * Returns 0 on success, negative on failure.
+ */
+-static int idpf_rx_hdr_buf_alloc_all(struct idpf_queue *rxq)
++static int idpf_rx_hdr_buf_alloc_all(struct idpf_buf_queue *bufq)
+ {
+- struct idpf_adapter *adapter = rxq->vport->adapter;
+-
+- rxq->rx_buf.hdr_buf_va =
+- dma_alloc_coherent(&adapter->pdev->dev,
+- IDPF_HDR_BUF_SIZE * rxq->desc_count,
+- &rxq->rx_buf.hdr_buf_pa,
+- GFP_KERNEL);
+- if (!rxq->rx_buf.hdr_buf_va)
++ bufq->rx_buf.hdr_buf_va =
++ dma_alloc_coherent(bufq->q_vector->vport->netdev->dev.parent,
++ IDPF_HDR_BUF_SIZE * bufq->desc_count,
++ &bufq->rx_buf.hdr_buf_pa, GFP_KERNEL);
++ if (!bufq->rx_buf.hdr_buf_va)
+ return -ENOMEM;
+
+ return 0;
+@@ -502,19 +588,20 @@ static int idpf_rx_hdr_buf_alloc_all(struct idpf_queue *rxq)
+ */
+ static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
+ {
+- u16 nta = refillq->next_to_alloc;
++ u32 nta = refillq->next_to_use;
+
+ /* store the buffer ID and the SW maintained GEN bit to the refillq */
+ refillq->ring[nta] =
+ FIELD_PREP(IDPF_RX_BI_BUFID_M, buf_id) |
+ FIELD_PREP(IDPF_RX_BI_GEN_M,
+- test_bit(__IDPF_Q_GEN_CHK, refillq->flags));
++ idpf_queue_has(GEN_CHK, refillq));
+
+ if (unlikely(++nta == refillq->desc_count)) {
+ nta = 0;
+- change_bit(__IDPF_Q_GEN_CHK, refillq->flags);
++ idpf_queue_change(GEN_CHK, refillq);
+ }
+- refillq->next_to_alloc = nta;
++
++ refillq->next_to_use = nta;
+ }
+
+ /**
+@@ -524,21 +611,20 @@ static void idpf_rx_post_buf_refill(struct idpf_sw_queue *refillq, u16 buf_id)
+ *
+ * Returns false if buffer could not be allocated, true otherwise.
+ */
+-static bool idpf_rx_post_buf_desc(struct idpf_queue *bufq, u16 buf_id)
++static bool idpf_rx_post_buf_desc(struct idpf_buf_queue *bufq, u16 buf_id)
+ {
+ struct virtchnl2_splitq_rx_buf_desc *splitq_rx_desc = NULL;
+ u16 nta = bufq->next_to_alloc;
+ struct idpf_rx_buf *buf;
+ dma_addr_t addr;
+
+- splitq_rx_desc = IDPF_SPLITQ_RX_BUF_DESC(bufq, nta);
++ splitq_rx_desc = &bufq->split_buf[nta];
+ buf = &bufq->rx_buf.buf[buf_id];
+
+- if (bufq->rx_hsplit_en) {
++ if (idpf_queue_has(HSPLIT_EN, bufq))
+ splitq_rx_desc->hdr_addr =
+ cpu_to_le64(bufq->rx_buf.hdr_buf_pa +
+ (u32)buf_id * IDPF_HDR_BUF_SIZE);
+- }
+
+ addr = idpf_alloc_page(bufq->pp, buf, bufq->rx_buf_size);
+ if (unlikely(addr == DMA_MAPPING_ERROR))
+@@ -562,7 +648,8 @@ static bool idpf_rx_post_buf_desc(struct idpf_queue *bufq, u16 buf_id)
+ *
+ * Returns true if @working_set bufs were posted successfully, false otherwise.
+ */
+-static bool idpf_rx_post_init_bufs(struct idpf_queue *bufq, u16 working_set)
++static bool idpf_rx_post_init_bufs(struct idpf_buf_queue *bufq,
++ u16 working_set)
+ {
+ int i;
+
+@@ -571,26 +658,28 @@ static bool idpf_rx_post_init_bufs(struct idpf_queue *bufq, u16 working_set)
+ return false;
+ }
+
+- idpf_rx_buf_hw_update(bufq,
+- bufq->next_to_alloc & ~(bufq->rx_buf_stride - 1));
++ idpf_rx_buf_hw_update(bufq, ALIGN_DOWN(bufq->next_to_alloc,
++ IDPF_RX_BUF_STRIDE));
+
+ return true;
+ }
+
+ /**
+ * idpf_rx_create_page_pool - Create a page pool
+- * @rxbufq: RX queue to create page pool for
++ * @napi: NAPI of the associated queue vector
++ * @count: queue descriptor count
+ *
+ * Returns &page_pool on success, casted -errno on failure
+ */
+-static struct page_pool *idpf_rx_create_page_pool(struct idpf_queue *rxbufq)
++static struct page_pool *idpf_rx_create_page_pool(struct napi_struct *napi,
++ u32 count)
+ {
+ struct page_pool_params pp = {
+ .flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV,
+ .order = 0,
+- .pool_size = rxbufq->desc_count,
++ .pool_size = count,
+ .nid = NUMA_NO_NODE,
+- .dev = rxbufq->vport->netdev->dev.parent,
++ .dev = napi->dev->dev.parent,
+ .max_len = PAGE_SIZE,
+ .dma_dir = DMA_FROM_DEVICE,
+ .offset = 0,
+@@ -599,15 +688,58 @@ static struct page_pool *idpf_rx_create_page_pool(struct idpf_queue *rxbufq)
+ return page_pool_create(&pp);
+ }
+
++/**
++ * idpf_rx_buf_alloc_singleq - Allocate memory for all buffer resources
++ * @rxq: queue for which the buffers are allocated
++ *
++ * Return: 0 on success, -ENOMEM on failure.
++ */
++static int idpf_rx_buf_alloc_singleq(struct idpf_rx_queue *rxq)
++{
++ rxq->rx_buf = kcalloc(rxq->desc_count, sizeof(*rxq->rx_buf),
++ GFP_KERNEL);
++ if (!rxq->rx_buf)
++ return -ENOMEM;
++
++ if (idpf_rx_singleq_buf_hw_alloc_all(rxq, rxq->desc_count - 1))
++ goto err;
++
++ return 0;
++
++err:
++ idpf_rx_buf_rel_all(rxq);
++
++ return -ENOMEM;
++}
++
++/**
++ * idpf_rx_bufs_init_singleq - Initialize page pool and allocate Rx bufs
++ * @rxq: buffer queue to create page pool for
++ *
++ * Return: 0 on success, -errno on failure.
++ */
++static int idpf_rx_bufs_init_singleq(struct idpf_rx_queue *rxq)
++{
++ struct page_pool *pool;
++
++ pool = idpf_rx_create_page_pool(&rxq->q_vector->napi, rxq->desc_count);
++ if (IS_ERR(pool))
++ return PTR_ERR(pool);
++
++ rxq->pp = pool;
++
++ return idpf_rx_buf_alloc_singleq(rxq);
++}
++
+ /**
+ * idpf_rx_buf_alloc_all - Allocate memory for all buffer resources
+- * @rxbufq: queue for which the buffers are allocated; equivalent to
+- * rxq when operating in singleq mode
++ * @rxbufq: queue for which the buffers are allocated
+ *
+ * Returns 0 on success, negative on failure
+ */
+-static int idpf_rx_buf_alloc_all(struct idpf_queue *rxbufq)
++static int idpf_rx_buf_alloc_all(struct idpf_buf_queue *rxbufq)
+ {
++ struct device *dev = rxbufq->q_vector->vport->netdev->dev.parent;
+ int err = 0;
+
+ /* Allocate book keeping buffers */
+@@ -618,48 +750,41 @@ static int idpf_rx_buf_alloc_all(struct idpf_queue *rxbufq)
+ goto rx_buf_alloc_all_out;
+ }
+
+- if (rxbufq->rx_hsplit_en) {
++ if (idpf_queue_has(HSPLIT_EN, rxbufq)) {
+ err = idpf_rx_hdr_buf_alloc_all(rxbufq);
+ if (err)
+ goto rx_buf_alloc_all_out;
+ }
+
+ /* Allocate buffers to be given to HW. */
+- if (idpf_is_queue_model_split(rxbufq->vport->rxq_model)) {
+- int working_set = IDPF_RX_BUFQ_WORKING_SET(rxbufq);
+-
+- if (!idpf_rx_post_init_bufs(rxbufq, working_set))
+- err = -ENOMEM;
+- } else {
+- if (idpf_rx_singleq_buf_hw_alloc_all(rxbufq,
+- rxbufq->desc_count - 1))
+- err = -ENOMEM;
+- }
++ if (!idpf_rx_post_init_bufs(rxbufq, IDPF_RX_BUFQ_WORKING_SET(rxbufq)))
++ err = -ENOMEM;
+
+ rx_buf_alloc_all_out:
+ if (err)
+- idpf_rx_buf_rel_all(rxbufq);
++ idpf_rx_buf_rel_bufq(rxbufq, dev);
+
+ return err;
+ }
+
+ /**
+ * idpf_rx_bufs_init - Initialize page pool, allocate rx bufs, and post to HW
+- * @rxbufq: RX queue to create page pool for
++ * @bufq: buffer queue to create page pool for
+ *
+ * Returns 0 on success, negative on failure
+ */
+-static int idpf_rx_bufs_init(struct idpf_queue *rxbufq)
++static int idpf_rx_bufs_init(struct idpf_buf_queue *bufq)
+ {
+ struct page_pool *pool;
+
+- pool = idpf_rx_create_page_pool(rxbufq);
++ pool = idpf_rx_create_page_pool(&bufq->q_vector->napi,
++ bufq->desc_count);
+ if (IS_ERR(pool))
+ return PTR_ERR(pool);
+
+- rxbufq->pp = pool;
++ bufq->pp = pool;
+
+- return idpf_rx_buf_alloc_all(rxbufq);
++ return idpf_rx_buf_alloc_all(bufq);
+ }
+
+ /**
+@@ -671,7 +796,6 @@ static int idpf_rx_bufs_init(struct idpf_queue *rxbufq)
+ int idpf_rx_bufs_init_all(struct idpf_vport *vport)
+ {
+ struct idpf_rxq_group *rx_qgrp;
+- struct idpf_queue *q;
+ int i, j, err;
+
+ for (i = 0; i < vport->num_rxq_grp; i++) {
+@@ -682,8 +806,10 @@ int idpf_rx_bufs_init_all(struct idpf_vport *vport)
+ int num_rxq = rx_qgrp->singleq.num_rxq;
+
+ for (j = 0; j < num_rxq; j++) {
++ struct idpf_rx_queue *q;
++
+ q = rx_qgrp->singleq.rxqs[j];
+- err = idpf_rx_bufs_init(q);
++ err = idpf_rx_bufs_init_singleq(q);
+ if (err)
+ return err;
+ }
+@@ -693,6 +819,8 @@ int idpf_rx_bufs_init_all(struct idpf_vport *vport)
+
+ /* Otherwise, allocate bufs for the buffer queues */
+ for (j = 0; j < vport->num_bufqs_per_qgrp; j++) {
++ struct idpf_buf_queue *q;
++
+ q = &rx_qgrp->splitq.bufq_sets[j].bufq;
+ err = idpf_rx_bufs_init(q);
+ if (err)
+@@ -705,22 +833,17 @@ int idpf_rx_bufs_init_all(struct idpf_vport *vport)
+
+ /**
+ * idpf_rx_desc_alloc - Allocate queue Rx resources
++ * @vport: vport to allocate resources for
+ * @rxq: Rx queue for which the resources are setup
+- * @bufq: buffer or completion queue
+- * @q_model: single or split queue model
+ *
+ * Returns 0 on success, negative on failure
+ */
+-static int idpf_rx_desc_alloc(struct idpf_queue *rxq, bool bufq, s32 q_model)
++static int idpf_rx_desc_alloc(const struct idpf_vport *vport,
++ struct idpf_rx_queue *rxq)
+ {
+- struct device *dev = rxq->dev;
++ struct device *dev = &vport->adapter->pdev->dev;
+
+- if (bufq)
+- rxq->size = rxq->desc_count *
+- sizeof(struct virtchnl2_splitq_rx_buf_desc);
+- else
+- rxq->size = rxq->desc_count *
+- sizeof(union virtchnl2_rx_desc);
++ rxq->size = rxq->desc_count * sizeof(union virtchnl2_rx_desc);
+
+ /* Allocate descriptors and also round up to nearest 4K */
+ rxq->size = ALIGN(rxq->size, 4096);
+@@ -735,7 +858,35 @@ static int idpf_rx_desc_alloc(struct idpf_queue *rxq, bool bufq, s32 q_model)
+ rxq->next_to_alloc = 0;
+ rxq->next_to_clean = 0;
+ rxq->next_to_use = 0;
+- set_bit(__IDPF_Q_GEN_CHK, rxq->flags);
++ idpf_queue_set(GEN_CHK, rxq);
++
++ return 0;
++}
++
++/**
++ * idpf_bufq_desc_alloc - Allocate buffer queue descriptor ring
++ * @vport: vport to allocate resources for
++ * @bufq: buffer queue for which the resources are set up
++ *
++ * Return: 0 on success, -ENOMEM on failure.
++ */
++static int idpf_bufq_desc_alloc(const struct idpf_vport *vport,
++ struct idpf_buf_queue *bufq)
++{
++ struct device *dev = &vport->adapter->pdev->dev;
++
++ bufq->size = array_size(bufq->desc_count, sizeof(*bufq->split_buf));
++
++ bufq->split_buf = dma_alloc_coherent(dev, bufq->size, &bufq->dma,
++ GFP_KERNEL);
++ if (!bufq->split_buf)
++ return -ENOMEM;
++
++ bufq->next_to_alloc = 0;
++ bufq->next_to_clean = 0;
++ bufq->next_to_use = 0;
++
++ idpf_queue_set(GEN_CHK, bufq);
+
+ return 0;
+ }
+@@ -748,9 +899,7 @@ static int idpf_rx_desc_alloc(struct idpf_queue *rxq, bool bufq, s32 q_model)
+ */
+ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport)
+ {
+- struct device *dev = &vport->adapter->pdev->dev;
+ struct idpf_rxq_group *rx_qgrp;
+- struct idpf_queue *q;
+ int i, j, err;
+ u16 num_rxq;
+
+@@ -762,13 +911,17 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport)
+ num_rxq = rx_qgrp->singleq.num_rxq;
+
+ for (j = 0; j < num_rxq; j++) {
++ struct idpf_rx_queue *q;
++
+ if (idpf_is_queue_model_split(vport->rxq_model))
+ q = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+ else
+ q = rx_qgrp->singleq.rxqs[j];
+- err = idpf_rx_desc_alloc(q, false, vport->rxq_model);
++
++ err = idpf_rx_desc_alloc(vport, q);
+ if (err) {
+- dev_err(dev, "Memory allocation for Rx Queue %u failed\n",
++ pci_err(vport->adapter->pdev,
++ "Memory allocation for Rx Queue %u failed\n",
+ i);
+ goto err_out;
+ }
+@@ -778,10 +931,14 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport)
+ continue;
+
+ for (j = 0; j < vport->num_bufqs_per_qgrp; j++) {
++ struct idpf_buf_queue *q;
++
+ q = &rx_qgrp->splitq.bufq_sets[j].bufq;
+- err = idpf_rx_desc_alloc(q, true, vport->rxq_model);
++
++ err = idpf_bufq_desc_alloc(vport, q);
+ if (err) {
+- dev_err(dev, "Memory allocation for Rx Buffer Queue %u failed\n",
++ pci_err(vport->adapter->pdev,
++ "Memory allocation for Rx Buffer Queue %u failed\n",
+ i);
+ goto err_out;
+ }
+@@ -802,11 +959,16 @@ static int idpf_rx_desc_alloc_all(struct idpf_vport *vport)
+ */
+ static void idpf_txq_group_rel(struct idpf_vport *vport)
+ {
++ bool split, flow_sch_en;
+ int i, j;
+
+ if (!vport->txq_grps)
+ return;
+
++ split = idpf_is_queue_model_split(vport->txq_model);
++ flow_sch_en = !idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS,
++ VIRTCHNL2_CAP_SPLITQ_QSCHED);
++
+ for (i = 0; i < vport->num_txq_grp; i++) {
+ struct idpf_txq_group *txq_grp = &vport->txq_grps[i];
+
+@@ -814,8 +976,15 @@ static void idpf_txq_group_rel(struct idpf_vport *vport)
+ kfree(txq_grp->txqs[j]);
+ txq_grp->txqs[j] = NULL;
+ }
++
++ if (!split)
++ continue;
++
+ kfree(txq_grp->complq);
+ txq_grp->complq = NULL;
++
++ if (flow_sch_en)
++ kfree(txq_grp->stashes);
+ }
+ kfree(vport->txq_grps);
+ vport->txq_grps = NULL;
+@@ -919,7 +1088,7 @@ static int idpf_vport_init_fast_path_txqs(struct idpf_vport *vport)
+ {
+ int i, j, k = 0;
+
+- vport->txqs = kcalloc(vport->num_txq, sizeof(struct idpf_queue *),
++ vport->txqs = kcalloc(vport->num_txq, sizeof(*vport->txqs),
+ GFP_KERNEL);
+
+ if (!vport->txqs)
+@@ -1137,7 +1306,8 @@ static void idpf_vport_calc_numq_per_grp(struct idpf_vport *vport,
+ * @q: rx queue for which descids are set
+ *
+ */
+-static void idpf_rxq_set_descids(struct idpf_vport *vport, struct idpf_queue *q)
++static void idpf_rxq_set_descids(const struct idpf_vport *vport,
++ struct idpf_rx_queue *q)
+ {
+ if (vport->rxq_model == VIRTCHNL2_QUEUE_MODEL_SPLIT) {
+ q->rxdids = VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M;
+@@ -1158,20 +1328,22 @@ static void idpf_rxq_set_descids(struct idpf_vport *vport, struct idpf_queue *q)
+ */
+ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
+ {
+- bool flow_sch_en;
+- int err, i;
++ bool split, flow_sch_en;
++ int i;
+
+ vport->txq_grps = kcalloc(vport->num_txq_grp,
+ sizeof(*vport->txq_grps), GFP_KERNEL);
+ if (!vport->txq_grps)
+ return -ENOMEM;
+
++ split = idpf_is_queue_model_split(vport->txq_model);
+ flow_sch_en = !idpf_is_cap_ena(vport->adapter, IDPF_OTHER_CAPS,
+ VIRTCHNL2_CAP_SPLITQ_QSCHED);
+
+ for (i = 0; i < vport->num_txq_grp; i++) {
+ struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+ struct idpf_adapter *adapter = vport->adapter;
++ struct idpf_txq_stash *stashes;
+ int j;
+
+ tx_qgrp->vport = vport;
+@@ -1180,45 +1352,62 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
+ for (j = 0; j < tx_qgrp->num_txq; j++) {
+ tx_qgrp->txqs[j] = kzalloc(sizeof(*tx_qgrp->txqs[j]),
+ GFP_KERNEL);
+- if (!tx_qgrp->txqs[j]) {
+- err = -ENOMEM;
++ if (!tx_qgrp->txqs[j])
+ goto err_alloc;
+- }
++ }
++
++ if (split && flow_sch_en) {
++ stashes = kcalloc(num_txq, sizeof(*stashes),
++ GFP_KERNEL);
++ if (!stashes)
++ goto err_alloc;
++
++ tx_qgrp->stashes = stashes;
+ }
+
+ for (j = 0; j < tx_qgrp->num_txq; j++) {
+- struct idpf_queue *q = tx_qgrp->txqs[j];
++ struct idpf_tx_queue *q = tx_qgrp->txqs[j];
+
+ q->dev = &adapter->pdev->dev;
+ q->desc_count = vport->txq_desc_count;
+ q->tx_max_bufs = idpf_get_max_tx_bufs(adapter);
+ q->tx_min_pkt_len = idpf_get_min_tx_pkt_len(adapter);
+- q->vport = vport;
++ q->netdev = vport->netdev;
+ q->txq_grp = tx_qgrp;
+- hash_init(q->sched_buf_hash);
+
+- if (flow_sch_en)
+- set_bit(__IDPF_Q_FLOW_SCH_EN, q->flags);
++ if (!split) {
++ q->clean_budget = vport->compln_clean_budget;
++ idpf_queue_assign(CRC_EN, q,
++ vport->crc_enable);
++ }
++
++ if (!flow_sch_en)
++ continue;
++
++ if (split) {
++ q->stash = &stashes[j];
++ hash_init(q->stash->sched_buf_hash);
++ }
++
++ idpf_queue_set(FLOW_SCH_EN, q);
+ }
+
+- if (!idpf_is_queue_model_split(vport->txq_model))
++ if (!split)
+ continue;
+
+ tx_qgrp->complq = kcalloc(IDPF_COMPLQ_PER_GROUP,
+ sizeof(*tx_qgrp->complq),
+ GFP_KERNEL);
+- if (!tx_qgrp->complq) {
+- err = -ENOMEM;
++ if (!tx_qgrp->complq)
+ goto err_alloc;
+- }
+
+- tx_qgrp->complq->dev = &adapter->pdev->dev;
+ tx_qgrp->complq->desc_count = vport->complq_desc_count;
+- tx_qgrp->complq->vport = vport;
+ tx_qgrp->complq->txq_grp = tx_qgrp;
++ tx_qgrp->complq->netdev = vport->netdev;
++ tx_qgrp->complq->clean_budget = vport->compln_clean_budget;
+
+ if (flow_sch_en)
+- __set_bit(__IDPF_Q_FLOW_SCH_EN, tx_qgrp->complq->flags);
++ idpf_queue_set(FLOW_SCH_EN, tx_qgrp->complq);
+ }
+
+ return 0;
+@@ -1226,7 +1415,7 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
+ err_alloc:
+ idpf_txq_group_rel(vport);
+
+- return err;
++ return -ENOMEM;
+ }
+
+ /**
+@@ -1238,8 +1427,6 @@ static int idpf_txq_group_alloc(struct idpf_vport *vport, u16 num_txq)
+ */
+ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq)
+ {
+- struct idpf_adapter *adapter = vport->adapter;
+- struct idpf_queue *q;
+ int i, k, err = 0;
+ bool hs;
+
+@@ -1292,21 +1479,15 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq)
+ struct idpf_bufq_set *bufq_set =
+ &rx_qgrp->splitq.bufq_sets[j];
+ int swq_size = sizeof(struct idpf_sw_queue);
++ struct idpf_buf_queue *q;
+
+ q = &rx_qgrp->splitq.bufq_sets[j].bufq;
+- q->dev = &adapter->pdev->dev;
+ q->desc_count = vport->bufq_desc_count[j];
+- q->vport = vport;
+- q->rxq_grp = rx_qgrp;
+- q->idx = j;
+ q->rx_buf_size = vport->bufq_size[j];
+ q->rx_buffer_low_watermark = IDPF_LOW_WATERMARK;
+- q->rx_buf_stride = IDPF_RX_BUF_STRIDE;
+
+- if (hs) {
+- q->rx_hsplit_en = true;
+- q->rx_hbuf_size = IDPF_HDR_BUF_SIZE;
+- }
++ idpf_queue_assign(HSPLIT_EN, q, hs);
++ q->rx_hbuf_size = hs ? IDPF_HDR_BUF_SIZE : 0;
+
+ bufq_set->num_refillqs = num_rxq;
+ bufq_set->refillqs = kcalloc(num_rxq, swq_size,
+@@ -1319,13 +1500,12 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq)
+ struct idpf_sw_queue *refillq =
+ &bufq_set->refillqs[k];
+
+- refillq->dev = &vport->adapter->pdev->dev;
+ refillq->desc_count =
+ vport->bufq_desc_count[j];
+- set_bit(__IDPF_Q_GEN_CHK, refillq->flags);
+- set_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags);
++ idpf_queue_set(GEN_CHK, refillq);
++ idpf_queue_set(RFL_GEN_CHK, refillq);
+ refillq->ring = kcalloc(refillq->desc_count,
+- sizeof(u16),
++ sizeof(*refillq->ring),
+ GFP_KERNEL);
+ if (!refillq->ring) {
+ err = -ENOMEM;
+@@ -1336,27 +1516,27 @@ static int idpf_rxq_group_alloc(struct idpf_vport *vport, u16 num_rxq)
+
+ skip_splitq_rx_init:
+ for (j = 0; j < num_rxq; j++) {
++ struct idpf_rx_queue *q;
++
+ if (!idpf_is_queue_model_split(vport->rxq_model)) {
+ q = rx_qgrp->singleq.rxqs[j];
+ goto setup_rxq;
+ }
+ q = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+- rx_qgrp->splitq.rxq_sets[j]->refillq0 =
++ rx_qgrp->splitq.rxq_sets[j]->refillq[0] =
+ &rx_qgrp->splitq.bufq_sets[0].refillqs[j];
+ if (vport->num_bufqs_per_qgrp > IDPF_SINGLE_BUFQ_PER_RXQ_GRP)
+- rx_qgrp->splitq.rxq_sets[j]->refillq1 =
++ rx_qgrp->splitq.rxq_sets[j]->refillq[1] =
+ &rx_qgrp->splitq.bufq_sets[1].refillqs[j];
+
+- if (hs) {
+- q->rx_hsplit_en = true;
+- q->rx_hbuf_size = IDPF_HDR_BUF_SIZE;
+- }
++ idpf_queue_assign(HSPLIT_EN, q, hs);
++ q->rx_hbuf_size = hs ? IDPF_HDR_BUF_SIZE : 0;
+
+ setup_rxq:
+- q->dev = &adapter->pdev->dev;
+ q->desc_count = vport->rxq_desc_count;
+- q->vport = vport;
+- q->rxq_grp = rx_qgrp;
++ q->rx_ptype_lkup = vport->rx_ptype_lkup;
++ q->netdev = vport->netdev;
++ q->bufq_sets = rx_qgrp->splitq.bufq_sets;
+ q->idx = (i * num_rxq) + j;
+ /* In splitq mode, RXQ buffer size should be
+ * set to that of the first buffer queue
+@@ -1445,12 +1625,13 @@ int idpf_vport_queues_alloc(struct idpf_vport *vport)
+ * idpf_tx_handle_sw_marker - Handle queue marker packet
+ * @tx_q: tx queue to handle software marker
+ */
+-static void idpf_tx_handle_sw_marker(struct idpf_queue *tx_q)
++static void idpf_tx_handle_sw_marker(struct idpf_tx_queue *tx_q)
+ {
+- struct idpf_vport *vport = tx_q->vport;
++ struct idpf_netdev_priv *priv = netdev_priv(tx_q->netdev);
++ struct idpf_vport *vport = priv->vport;
+ int i;
+
+- clear_bit(__IDPF_Q_SW_MARKER, tx_q->flags);
++ idpf_queue_clear(SW_MARKER, tx_q);
+ /* Hardware must write marker packets to all queues associated with
+ * completion queues. So check if all queues received marker packets
+ */
+@@ -1458,7 +1639,7 @@ static void idpf_tx_handle_sw_marker(struct idpf_queue *tx_q)
+ /* If we're still waiting on any other TXQ marker completions,
+ * just return now since we cannot wake up the marker_wq yet.
+ */
+- if (test_bit(__IDPF_Q_SW_MARKER, vport->txqs[i]->flags))
++ if (idpf_queue_has(SW_MARKER, vport->txqs[i]))
+ return;
+
+ /* Drain complete */
+@@ -1474,7 +1655,7 @@ static void idpf_tx_handle_sw_marker(struct idpf_queue *tx_q)
+ * @cleaned: pointer to stats struct to track cleaned packets/bytes
+ * @napi_budget: Used to determine if we are in netpoll
+ */
+-static void idpf_tx_splitq_clean_hdr(struct idpf_queue *tx_q,
++static void idpf_tx_splitq_clean_hdr(struct idpf_tx_queue *tx_q,
+ struct idpf_tx_buf *tx_buf,
+ struct idpf_cleaned_stats *cleaned,
+ int napi_budget)
+@@ -1505,7 +1686,8 @@ static void idpf_tx_splitq_clean_hdr(struct idpf_queue *tx_q,
+ * @cleaned: pointer to stats struct to track cleaned packets/bytes
+ * @budget: Used to determine if we are in netpoll
+ */
+-static void idpf_tx_clean_stashed_bufs(struct idpf_queue *txq, u16 compl_tag,
++static void idpf_tx_clean_stashed_bufs(struct idpf_tx_queue *txq,
++ u16 compl_tag,
+ struct idpf_cleaned_stats *cleaned,
+ int budget)
+ {
+@@ -1513,7 +1695,7 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_queue *txq, u16 compl_tag,
+ struct hlist_node *tmp_buf;
+
+ /* Buffer completion */
+- hash_for_each_possible_safe(txq->sched_buf_hash, stash, tmp_buf,
++ hash_for_each_possible_safe(txq->stash->sched_buf_hash, stash, tmp_buf,
+ hlist, compl_tag) {
+ if (unlikely(stash->buf.compl_tag != (int)compl_tag))
+ continue;
+@@ -1530,7 +1712,7 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_queue *txq, u16 compl_tag,
+ }
+
+ /* Push shadow buf back onto stack */
+- idpf_buf_lifo_push(&txq->buf_stack, stash);
++ idpf_buf_lifo_push(&txq->stash->buf_stack, stash);
+
+ hash_del(&stash->hlist);
+ }
+@@ -1542,7 +1724,7 @@ static void idpf_tx_clean_stashed_bufs(struct idpf_queue *txq, u16 compl_tag,
+ * @txq: Tx queue to clean
+ * @tx_buf: buffer to store
+ */
+-static int idpf_stash_flow_sch_buffers(struct idpf_queue *txq,
++static int idpf_stash_flow_sch_buffers(struct idpf_tx_queue *txq,
+ struct idpf_tx_buf *tx_buf)
+ {
+ struct idpf_tx_stash *stash;
+@@ -1551,10 +1733,10 @@ static int idpf_stash_flow_sch_buffers(struct idpf_queue *txq,
+ !dma_unmap_len(tx_buf, len)))
+ return 0;
+
+- stash = idpf_buf_lifo_pop(&txq->buf_stack);
++ stash = idpf_buf_lifo_pop(&txq->stash->buf_stack);
+ if (unlikely(!stash)) {
+ net_err_ratelimited("%s: No out-of-order TX buffers left!\n",
+- txq->vport->netdev->name);
++ netdev_name(txq->netdev));
+
+ return -ENOMEM;
+ }
+@@ -1568,7 +1750,8 @@ static int idpf_stash_flow_sch_buffers(struct idpf_queue *txq,
+ stash->buf.compl_tag = tx_buf->compl_tag;
+
+ /* Add buffer to buf_hash table to be freed later */
+- hash_add(txq->sched_buf_hash, &stash->hlist, stash->buf.compl_tag);
++ hash_add(txq->stash->sched_buf_hash, &stash->hlist,
++ stash->buf.compl_tag);
+
+ memset(tx_buf, 0, sizeof(struct idpf_tx_buf));
+
+@@ -1584,7 +1767,7 @@ do { \
+ if (unlikely(!(ntc))) { \
+ ntc -= (txq)->desc_count; \
+ buf = (txq)->tx_buf; \
+- desc = IDPF_FLEX_TX_DESC(txq, 0); \
++ desc = &(txq)->flex_tx[0]; \
+ } else { \
+ (buf)++; \
+ (desc)++; \
+@@ -1607,7 +1790,7 @@ do { \
+ * and the buffers will be cleaned separately. The stats are not updated from
+ * this function when using flow-based scheduling.
+ */
+-static void idpf_tx_splitq_clean(struct idpf_queue *tx_q, u16 end,
++static void idpf_tx_splitq_clean(struct idpf_tx_queue *tx_q, u16 end,
+ int napi_budget,
+ struct idpf_cleaned_stats *cleaned,
+ bool descs_only)
+@@ -1617,8 +1800,8 @@ static void idpf_tx_splitq_clean(struct idpf_queue *tx_q, u16 end,
+ s16 ntc = tx_q->next_to_clean;
+ struct idpf_tx_buf *tx_buf;
+
+- tx_desc = IDPF_FLEX_TX_DESC(tx_q, ntc);
+- next_pending_desc = IDPF_FLEX_TX_DESC(tx_q, end);
++ tx_desc = &tx_q->flex_tx[ntc];
++ next_pending_desc = &tx_q->flex_tx[end];
+ tx_buf = &tx_q->tx_buf[ntc];
+ ntc -= tx_q->desc_count;
+
+@@ -1703,7 +1886,7 @@ do { \
+ * stashed. Returns the byte/segment count for the cleaned packet associated
+ * this completion tag.
+ */
+-static bool idpf_tx_clean_buf_ring(struct idpf_queue *txq, u16 compl_tag,
++static bool idpf_tx_clean_buf_ring(struct idpf_tx_queue *txq, u16 compl_tag,
+ struct idpf_cleaned_stats *cleaned,
+ int budget)
+ {
+@@ -1772,14 +1955,14 @@ static bool idpf_tx_clean_buf_ring(struct idpf_queue *txq, u16 compl_tag,
+ *
+ * Returns bytes/packets cleaned
+ */
+-static void idpf_tx_handle_rs_completion(struct idpf_queue *txq,
++static void idpf_tx_handle_rs_completion(struct idpf_tx_queue *txq,
+ struct idpf_splitq_tx_compl_desc *desc,
+ struct idpf_cleaned_stats *cleaned,
+ int budget)
+ {
+ u16 compl_tag;
+
+- if (!test_bit(__IDPF_Q_FLOW_SCH_EN, txq->flags)) {
++ if (!idpf_queue_has(FLOW_SCH_EN, txq)) {
+ u16 head = le16_to_cpu(desc->q_head_compl_tag.q_head);
+
+ return idpf_tx_splitq_clean(txq, head, budget, cleaned, false);
+@@ -1802,24 +1985,23 @@ static void idpf_tx_handle_rs_completion(struct idpf_queue *txq,
+ *
+ * Returns true if there's any budget left (e.g. the clean is finished)
+ */
+-static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
++static bool idpf_tx_clean_complq(struct idpf_compl_queue *complq, int budget,
+ int *cleaned)
+ {
+ struct idpf_splitq_tx_compl_desc *tx_desc;
+- struct idpf_vport *vport = complq->vport;
+ s16 ntc = complq->next_to_clean;
+ struct idpf_netdev_priv *np;
+ unsigned int complq_budget;
+ bool complq_ok = true;
+ int i;
+
+- complq_budget = vport->compln_clean_budget;
+- tx_desc = IDPF_SPLITQ_TX_COMPLQ_DESC(complq, ntc);
++ complq_budget = complq->clean_budget;
++ tx_desc = &complq->comp[ntc];
+ ntc -= complq->desc_count;
+
+ do {
+ struct idpf_cleaned_stats cleaned_stats = { };
+- struct idpf_queue *tx_q;
++ struct idpf_tx_queue *tx_q;
+ int rel_tx_qid;
+ u16 hw_head;
+ u8 ctype; /* completion type */
+@@ -1828,7 +2010,7 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
+ /* if the descriptor isn't done, no work yet to do */
+ gen = le16_get_bits(tx_desc->qid_comptype_gen,
+ IDPF_TXD_COMPLQ_GEN_M);
+- if (test_bit(__IDPF_Q_GEN_CHK, complq->flags) != gen)
++ if (idpf_queue_has(GEN_CHK, complq) != gen)
+ break;
+
+ /* Find necessary info of TX queue to clean buffers */
+@@ -1836,8 +2018,7 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
+ IDPF_TXD_COMPLQ_QID_M);
+ if (rel_tx_qid >= complq->txq_grp->num_txq ||
+ !complq->txq_grp->txqs[rel_tx_qid]) {
+- dev_err(&complq->vport->adapter->pdev->dev,
+- "TxQ not found\n");
++ netdev_err(complq->netdev, "TxQ not found\n");
+ goto fetch_next_desc;
+ }
+ tx_q = complq->txq_grp->txqs[rel_tx_qid];
+@@ -1860,15 +2041,14 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
+ idpf_tx_handle_sw_marker(tx_q);
+ break;
+ default:
+- dev_err(&tx_q->vport->adapter->pdev->dev,
+- "Unknown TX completion type: %d\n",
+- ctype);
++ netdev_err(tx_q->netdev,
++ "Unknown TX completion type: %d\n", ctype);
+ goto fetch_next_desc;
+ }
+
+ u64_stats_update_begin(&tx_q->stats_sync);
+- u64_stats_add(&tx_q->q_stats.tx.packets, cleaned_stats.packets);
+- u64_stats_add(&tx_q->q_stats.tx.bytes, cleaned_stats.bytes);
++ u64_stats_add(&tx_q->q_stats.packets, cleaned_stats.packets);
++ u64_stats_add(&tx_q->q_stats.bytes, cleaned_stats.bytes);
+ tx_q->cleaned_pkts += cleaned_stats.packets;
+ tx_q->cleaned_bytes += cleaned_stats.bytes;
+ complq->num_completions++;
+@@ -1879,8 +2059,8 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
+ ntc++;
+ if (unlikely(!ntc)) {
+ ntc -= complq->desc_count;
+- tx_desc = IDPF_SPLITQ_TX_COMPLQ_DESC(complq, 0);
+- change_bit(__IDPF_Q_GEN_CHK, complq->flags);
++ tx_desc = &complq->comp[0];
++ idpf_queue_change(GEN_CHK, complq);
+ }
+
+ prefetch(tx_desc);
+@@ -1896,9 +2076,9 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
+ IDPF_TX_COMPLQ_OVERFLOW_THRESH(complq)))
+ complq_ok = false;
+
+- np = netdev_priv(complq->vport->netdev);
++ np = netdev_priv(complq->netdev);
+ for (i = 0; i < complq->txq_grp->num_txq; ++i) {
+- struct idpf_queue *tx_q = complq->txq_grp->txqs[i];
++ struct idpf_tx_queue *tx_q = complq->txq_grp->txqs[i];
+ struct netdev_queue *nq;
+ bool dont_wake;
+
+@@ -1909,11 +2089,11 @@ static bool idpf_tx_clean_complq(struct idpf_queue *complq, int budget,
+ *cleaned += tx_q->cleaned_pkts;
+
+ /* Update BQL */
+- nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx);
++ nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
+
+ dont_wake = !complq_ok || IDPF_TX_BUF_RSV_LOW(tx_q) ||
+ np->state != __IDPF_VPORT_UP ||
+- !netif_carrier_ok(tx_q->vport->netdev);
++ !netif_carrier_ok(tx_q->netdev);
+ /* Check if the TXQ needs to and can be restarted */
+ __netif_txq_completed_wake(nq, tx_q->cleaned_pkts, tx_q->cleaned_bytes,
+ IDPF_DESC_UNUSED(tx_q), IDPF_TX_WAKE_THRESH,
+@@ -1969,29 +2149,6 @@ void idpf_tx_splitq_build_flow_desc(union idpf_tx_flex_desc *desc,
+ desc->flow.qw1.compl_tag = cpu_to_le16(params->compl_tag);
+ }
+
+-/**
+- * idpf_tx_maybe_stop_common - 1st level check for common Tx stop conditions
+- * @tx_q: the queue to be checked
+- * @size: number of descriptors we want to assure is available
+- *
+- * Returns 0 if stop is not needed
+- */
+-int idpf_tx_maybe_stop_common(struct idpf_queue *tx_q, unsigned int size)
+-{
+- struct netdev_queue *nq;
+-
+- if (likely(IDPF_DESC_UNUSED(tx_q) >= size))
+- return 0;
+-
+- u64_stats_update_begin(&tx_q->stats_sync);
+- u64_stats_inc(&tx_q->q_stats.tx.q_busy);
+- u64_stats_update_end(&tx_q->stats_sync);
+-
+- nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx);
+-
+- return netif_txq_maybe_stop(nq, IDPF_DESC_UNUSED(tx_q), size, size);
+-}
+-
+ /**
+ * idpf_tx_maybe_stop_splitq - 1st level check for Tx splitq stop conditions
+ * @tx_q: the queue to be checked
+@@ -1999,11 +2156,11 @@ int idpf_tx_maybe_stop_common(struct idpf_queue *tx_q, unsigned int size)
+ *
+ * Returns 0 if stop is not needed
+ */
+-static int idpf_tx_maybe_stop_splitq(struct idpf_queue *tx_q,
++static int idpf_tx_maybe_stop_splitq(struct idpf_tx_queue *tx_q,
+ unsigned int descs_needed)
+ {
+ if (idpf_tx_maybe_stop_common(tx_q, descs_needed))
+- goto splitq_stop;
++ goto out;
+
+ /* If there are too many outstanding completions expected on the
+ * completion queue, stop the TX queue to give the device some time to
+@@ -2022,10 +2179,12 @@ static int idpf_tx_maybe_stop_splitq(struct idpf_queue *tx_q,
+ return 0;
+
+ splitq_stop:
++ netif_stop_subqueue(tx_q->netdev, tx_q->idx);
++
++out:
+ u64_stats_update_begin(&tx_q->stats_sync);
+- u64_stats_inc(&tx_q->q_stats.tx.q_busy);
++ u64_stats_inc(&tx_q->q_stats.q_busy);
+ u64_stats_update_end(&tx_q->stats_sync);
+- netif_stop_subqueue(tx_q->vport->netdev, tx_q->idx);
+
+ return -EBUSY;
+ }
+@@ -2040,15 +2199,19 @@ static int idpf_tx_maybe_stop_splitq(struct idpf_queue *tx_q,
+ * to do a register write to update our queue status. We know this can only
+ * mean tail here as HW should be owning head for TX.
+ */
+-void idpf_tx_buf_hw_update(struct idpf_queue *tx_q, u32 val,
++void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
+ bool xmit_more)
+ {
+ struct netdev_queue *nq;
+
+- nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx);
++ nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
+ tx_q->next_to_use = val;
+
+- idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED);
++ if (idpf_tx_maybe_stop_common(tx_q, IDPF_TX_DESC_NEEDED)) {
++ u64_stats_update_begin(&tx_q->stats_sync);
++ u64_stats_inc(&tx_q->q_stats.q_busy);
++ u64_stats_update_end(&tx_q->stats_sync);
++ }
+
+ /* Force memory writes to complete before letting h/w
+ * know there are new descriptors to fetch. (Only
+@@ -2069,7 +2232,7 @@ void idpf_tx_buf_hw_update(struct idpf_queue *tx_q, u32 val,
+ *
+ * Returns number of data descriptors needed for this skb.
+ */
+-unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq,
++unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
+ struct sk_buff *skb)
+ {
+ const struct skb_shared_info *shinfo;
+@@ -2102,7 +2265,7 @@ unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq,
+
+ count = idpf_size_to_txd_count(skb->len);
+ u64_stats_update_begin(&txq->stats_sync);
+- u64_stats_inc(&txq->q_stats.tx.linearize);
++ u64_stats_inc(&txq->q_stats.linearize);
+ u64_stats_update_end(&txq->stats_sync);
+ }
+
+@@ -2116,11 +2279,11 @@ unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq,
+ * @first: original first buffer info buffer for packet
+ * @idx: starting point on ring to unwind
+ */
+-void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb,
++void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
+ struct idpf_tx_buf *first, u16 idx)
+ {
+ u64_stats_update_begin(&txq->stats_sync);
+- u64_stats_inc(&txq->q_stats.tx.dma_map_errs);
++ u64_stats_inc(&txq->q_stats.dma_map_errs);
+ u64_stats_update_end(&txq->stats_sync);
+
+ /* clear dma mappings for failed tx_buf map */
+@@ -2143,7 +2306,7 @@ void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb,
+ * used one additional descriptor for a context
+ * descriptor. Reset that here.
+ */
+- tx_desc = IDPF_FLEX_TX_DESC(txq, idx);
++ tx_desc = &txq->flex_tx[idx];
+ memset(tx_desc, 0, sizeof(struct idpf_flex_tx_ctx_desc));
+ if (idx == 0)
+ idx = txq->desc_count;
+@@ -2159,7 +2322,7 @@ void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb,
+ * @txq: the tx ring to wrap
+ * @ntu: ring index to bump
+ */
+-static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_queue *txq, u16 ntu)
++static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_tx_queue *txq, u16 ntu)
+ {
+ ntu++;
+
+@@ -2181,7 +2344,7 @@ static unsigned int idpf_tx_splitq_bump_ntu(struct idpf_queue *txq, u16 ntu)
+ * and gets a physical address for each memory location and programs
+ * it and the length into the transmit flex descriptor.
+ */
+-static void idpf_tx_splitq_map(struct idpf_queue *tx_q,
++static void idpf_tx_splitq_map(struct idpf_tx_queue *tx_q,
+ struct idpf_tx_splitq_params *params,
+ struct idpf_tx_buf *first)
+ {
+@@ -2202,7 +2365,7 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q,
+ data_len = skb->data_len;
+ size = skb_headlen(skb);
+
+- tx_desc = IDPF_FLEX_TX_DESC(tx_q, i);
++ tx_desc = &tx_q->flex_tx[i];
+
+ dma = dma_map_single(tx_q->dev, skb->data, size, DMA_TO_DEVICE);
+
+@@ -2275,7 +2438,7 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q,
+ i++;
+
+ if (i == tx_q->desc_count) {
+- tx_desc = IDPF_FLEX_TX_DESC(tx_q, 0);
++ tx_desc = &tx_q->flex_tx[0];
+ i = 0;
+ tx_q->compl_tag_cur_gen =
+ IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
+@@ -2320,7 +2483,7 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q,
+ i++;
+
+ if (i == tx_q->desc_count) {
+- tx_desc = IDPF_FLEX_TX_DESC(tx_q, 0);
++ tx_desc = &tx_q->flex_tx[0];
+ i = 0;
+ tx_q->compl_tag_cur_gen = IDPF_TX_ADJ_COMPL_TAG_GEN(tx_q);
+ }
+@@ -2348,7 +2511,7 @@ static void idpf_tx_splitq_map(struct idpf_queue *tx_q,
+ tx_q->txq_grp->num_completions_pending++;
+
+ /* record bytecount for BQL */
+- nq = netdev_get_tx_queue(tx_q->vport->netdev, tx_q->idx);
++ nq = netdev_get_tx_queue(tx_q->netdev, tx_q->idx);
+ netdev_tx_sent_queue(nq, first->bytecount);
+
+ idpf_tx_buf_hw_update(tx_q, i, netdev_xmit_more());
+@@ -2525,8 +2688,8 @@ static bool __idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs)
+ * E.g.: a packet with 7 fragments can require 9 DMA transactions; 1 for TSO
+ * header, 1 for segment payload, and then 7 for the fragments.
+ */
+-bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
+- unsigned int count)
++static bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
++ unsigned int count)
+ {
+ if (likely(count < max_bufs))
+ return false;
+@@ -2544,7 +2707,7 @@ bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
+ * ring entry to reflect that this index is a context descriptor
+ */
+ static struct idpf_flex_tx_ctx_desc *
+-idpf_tx_splitq_get_ctx_desc(struct idpf_queue *txq)
++idpf_tx_splitq_get_ctx_desc(struct idpf_tx_queue *txq)
+ {
+ struct idpf_flex_tx_ctx_desc *desc;
+ int i = txq->next_to_use;
+@@ -2553,7 +2716,7 @@ idpf_tx_splitq_get_ctx_desc(struct idpf_queue *txq)
+ txq->tx_buf[i].compl_tag = IDPF_SPLITQ_TX_INVAL_COMPL_TAG;
+
+ /* grab the next descriptor */
+- desc = IDPF_FLEX_TX_CTX_DESC(txq, i);
++ desc = &txq->flex_ctx[i];
+ txq->next_to_use = idpf_tx_splitq_bump_ntu(txq, i);
+
+ return desc;
+@@ -2564,10 +2727,10 @@ idpf_tx_splitq_get_ctx_desc(struct idpf_queue *txq)
+ * @tx_q: queue to send buffer on
+ * @skb: pointer to skb
+ */
+-netdev_tx_t idpf_tx_drop_skb(struct idpf_queue *tx_q, struct sk_buff *skb)
++netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb)
+ {
+ u64_stats_update_begin(&tx_q->stats_sync);
+- u64_stats_inc(&tx_q->q_stats.tx.skb_drops);
++ u64_stats_inc(&tx_q->q_stats.skb_drops);
+ u64_stats_update_end(&tx_q->stats_sync);
+
+ idpf_tx_buf_hw_update(tx_q, tx_q->next_to_use, false);
+@@ -2585,7 +2748,7 @@ netdev_tx_t idpf_tx_drop_skb(struct idpf_queue *tx_q, struct sk_buff *skb)
+ * Returns NETDEV_TX_OK if sent, else an error code
+ */
+ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
+- struct idpf_queue *tx_q)
++ struct idpf_tx_queue *tx_q)
+ {
+ struct idpf_tx_splitq_params tx_params = { };
+ struct idpf_tx_buf *first;
+@@ -2625,7 +2788,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
+ ctx_desc->tso.qw0.hdr_len = tx_params.offload.tso_hdr_len;
+
+ u64_stats_update_begin(&tx_q->stats_sync);
+- u64_stats_inc(&tx_q->q_stats.tx.lso_pkts);
++ u64_stats_inc(&tx_q->q_stats.lso_pkts);
+ u64_stats_update_end(&tx_q->stats_sync);
+ }
+
+@@ -2642,7 +2805,7 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
+ first->bytecount = max_t(unsigned int, skb->len, ETH_ZLEN);
+ }
+
+- if (test_bit(__IDPF_Q_FLOW_SCH_EN, tx_q->flags)) {
++ if (idpf_queue_has(FLOW_SCH_EN, tx_q)) {
+ tx_params.dtype = IDPF_TX_DESC_DTYPE_FLEX_FLOW_SCHE;
+ tx_params.eop_cmd = IDPF_TXD_FLEX_FLOW_CMD_EOP;
+ /* Set the RE bit to catch any packets that may have not been
+@@ -2672,17 +2835,16 @@ static netdev_tx_t idpf_tx_splitq_frame(struct sk_buff *skb,
+ }
+
+ /**
+- * idpf_tx_splitq_start - Selects the right Tx queue to send buffer
++ * idpf_tx_start - Selects the right Tx queue to send buffer
+ * @skb: send buffer
+ * @netdev: network interface device structure
+ *
+ * Returns NETDEV_TX_OK if sent, else an error code
+ */
+-netdev_tx_t idpf_tx_splitq_start(struct sk_buff *skb,
+- struct net_device *netdev)
++netdev_tx_t idpf_tx_start(struct sk_buff *skb, struct net_device *netdev)
+ {
+ struct idpf_vport *vport = idpf_netdev_to_vport(netdev);
+- struct idpf_queue *tx_q;
++ struct idpf_tx_queue *tx_q;
+
+ if (unlikely(skb_get_queue_mapping(skb) >= vport->num_txq)) {
+ dev_kfree_skb_any(skb);
+@@ -2701,7 +2863,10 @@ netdev_tx_t idpf_tx_splitq_start(struct sk_buff *skb,
+ return NETDEV_TX_OK;
+ }
+
+- return idpf_tx_splitq_frame(skb, tx_q);
++ if (idpf_is_queue_model_split(vport->txq_model))
++ return idpf_tx_splitq_frame(skb, tx_q);
++ else
++ return idpf_tx_singleq_frame(skb, tx_q);
+ }
+
+ /**
+@@ -2735,13 +2900,14 @@ enum pkt_hash_types idpf_ptype_to_htype(const struct idpf_rx_ptype_decoded *deco
+ * @rx_desc: Receive descriptor
+ * @decoded: Decoded Rx packet type related fields
+ */
+-static void idpf_rx_hash(struct idpf_queue *rxq, struct sk_buff *skb,
+- struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
+- struct idpf_rx_ptype_decoded *decoded)
++static void
++idpf_rx_hash(const struct idpf_rx_queue *rxq, struct sk_buff *skb,
++ const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
++ struct idpf_rx_ptype_decoded *decoded)
+ {
+ u32 hash;
+
+- if (unlikely(!idpf_is_feature_ena(rxq->vport, NETIF_F_RXHASH)))
++ if (unlikely(!(rxq->netdev->features & NETIF_F_RXHASH)))
+ return;
+
+ hash = le16_to_cpu(rx_desc->hash1) |
+@@ -2760,14 +2926,14 @@ static void idpf_rx_hash(struct idpf_queue *rxq, struct sk_buff *skb,
+ *
+ * skb->protocol must be set before this function is called
+ */
+-static void idpf_rx_csum(struct idpf_queue *rxq, struct sk_buff *skb,
++static void idpf_rx_csum(struct idpf_rx_queue *rxq, struct sk_buff *skb,
+ struct idpf_rx_csum_decoded *csum_bits,
+ struct idpf_rx_ptype_decoded *decoded)
+ {
+ bool ipv4, ipv6;
+
+ /* check if Rx checksum is enabled */
+- if (unlikely(!idpf_is_feature_ena(rxq->vport, NETIF_F_RXCSUM)))
++ if (unlikely(!(rxq->netdev->features & NETIF_F_RXCSUM)))
+ return;
+
+ /* check if HW has decoded the packet and checksum */
+@@ -2814,7 +2980,7 @@ static void idpf_rx_csum(struct idpf_queue *rxq, struct sk_buff *skb,
+
+ checksum_fail:
+ u64_stats_update_begin(&rxq->stats_sync);
+- u64_stats_inc(&rxq->q_stats.rx.hw_csum_err);
++ u64_stats_inc(&rxq->q_stats.hw_csum_err);
+ u64_stats_update_end(&rxq->stats_sync);
+ }
+
+@@ -2824,8 +2990,9 @@ static void idpf_rx_csum(struct idpf_queue *rxq, struct sk_buff *skb,
+ * @csum: structure to extract checksum fields
+ *
+ **/
+-static void idpf_rx_splitq_extract_csum_bits(struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
+- struct idpf_rx_csum_decoded *csum)
++static void
++idpf_rx_splitq_extract_csum_bits(const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
++ struct idpf_rx_csum_decoded *csum)
+ {
+ u8 qword0, qword1;
+
+@@ -2860,8 +3027,8 @@ static void idpf_rx_splitq_extract_csum_bits(struct virtchnl2_rx_flex_desc_adv_n
+ * Populate the skb fields with the total number of RSC segments, RSC payload
+ * length and packet type.
+ */
+-static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb,
+- struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
++static int idpf_rx_rsc(struct idpf_rx_queue *rxq, struct sk_buff *skb,
++ const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc,
+ struct idpf_rx_ptype_decoded *decoded)
+ {
+ u16 rsc_segments, rsc_seg_len;
+@@ -2914,7 +3081,7 @@ static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb,
+ tcp_gro_complete(skb);
+
+ u64_stats_update_begin(&rxq->stats_sync);
+- u64_stats_inc(&rxq->q_stats.rx.rsc_pkts);
++ u64_stats_inc(&rxq->q_stats.rsc_pkts);
+ u64_stats_update_end(&rxq->stats_sync);
+
+ return 0;
+@@ -2930,9 +3097,9 @@ static int idpf_rx_rsc(struct idpf_queue *rxq, struct sk_buff *skb,
+ * order to populate the hash, checksum, protocol, and
+ * other fields within the skb.
+ */
+-static int idpf_rx_process_skb_fields(struct idpf_queue *rxq,
+- struct sk_buff *skb,
+- struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
++static int
++idpf_rx_process_skb_fields(struct idpf_rx_queue *rxq, struct sk_buff *skb,
++ const struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_desc)
+ {
+ struct idpf_rx_csum_decoded csum_bits = { };
+ struct idpf_rx_ptype_decoded decoded;
+@@ -2940,19 +3107,13 @@ static int idpf_rx_process_skb_fields(struct idpf_queue *rxq,
+
+ rx_ptype = le16_get_bits(rx_desc->ptype_err_fflags0,
+ VIRTCHNL2_RX_FLEX_DESC_ADV_PTYPE_M);
+-
+- skb->protocol = eth_type_trans(skb, rxq->vport->netdev);
+-
+- decoded = rxq->vport->rx_ptype_lkup[rx_ptype];
+- /* If we don't know the ptype we can't do anything else with it. Just
+- * pass it up the stack as-is.
+- */
+- if (!decoded.known)
+- return 0;
++ decoded = rxq->rx_ptype_lkup[rx_ptype];
+
+ /* process RSS/hash */
+ idpf_rx_hash(rxq, skb, rx_desc, &decoded);
+
++ skb->protocol = eth_type_trans(skb, rxq->netdev);
++
+ if (le16_get_bits(rx_desc->hdrlen_flags,
+ VIRTCHNL2_RX_FLEX_DESC_ADV_RSC_M))
+ return idpf_rx_rsc(rxq, skb, rx_desc, &decoded);
+@@ -2992,7 +3153,7 @@ void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb,
+ * data from the current receive descriptor, taking care to set up the
+ * skb correctly.
+ */
+-struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq,
++struct sk_buff *idpf_rx_construct_skb(const struct idpf_rx_queue *rxq,
+ struct idpf_rx_buf *rx_buf,
+ unsigned int size)
+ {
+@@ -3005,7 +3166,7 @@ struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq,
+ /* prefetch first cache line of first page */
+ net_prefetch(va);
+ /* allocate a skb to store the frags */
+- skb = napi_alloc_skb(&rxq->q_vector->napi, IDPF_RX_HDR_SIZE);
++ skb = napi_alloc_skb(rxq->napi, IDPF_RX_HDR_SIZE);
+ if (unlikely(!skb)) {
+ idpf_rx_put_page(rx_buf);
+
+@@ -3052,14 +3213,14 @@ struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq,
+ * the current receive descriptor, taking care to set up the skb correctly.
+ * This specifically uses a header buffer to start building the skb.
+ */
+-static struct sk_buff *idpf_rx_hdr_construct_skb(struct idpf_queue *rxq,
+- const void *va,
+- unsigned int size)
++static struct sk_buff *
++idpf_rx_hdr_construct_skb(const struct idpf_rx_queue *rxq, const void *va,
++ unsigned int size)
+ {
+ struct sk_buff *skb;
+
+ /* allocate a skb to store the frags */
+- skb = napi_alloc_skb(&rxq->q_vector->napi, size);
++ skb = napi_alloc_skb(rxq->napi, size);
+ if (unlikely(!skb))
+ return NULL;
+
+@@ -3115,10 +3276,10 @@ static bool idpf_rx_splitq_is_eop(struct virtchnl2_rx_flex_desc_adv_nic_3 *rx_de
+ *
+ * Returns amount of work completed
+ */
+-static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
++static int idpf_rx_splitq_clean(struct idpf_rx_queue *rxq, int budget)
+ {
+ int total_rx_bytes = 0, total_rx_pkts = 0;
+- struct idpf_queue *rx_bufq = NULL;
++ struct idpf_buf_queue *rx_bufq = NULL;
+ struct sk_buff *skb = rxq->skb;
+ u16 ntc = rxq->next_to_clean;
+
+@@ -3128,7 +3289,6 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ struct idpf_sw_queue *refillq = NULL;
+ struct idpf_rxq_set *rxq_set = NULL;
+ struct idpf_rx_buf *rx_buf = NULL;
+- union virtchnl2_rx_desc *desc;
+ unsigned int pkt_len = 0;
+ unsigned int hdr_len = 0;
+ u16 gen_id, buf_id = 0;
+@@ -3138,8 +3298,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ u8 rxdid;
+
+ /* get the Rx desc from Rx queue based on 'next_to_clean' */
+- desc = IDPF_RX_DESC(rxq, ntc);
+- rx_desc = (struct virtchnl2_rx_flex_desc_adv_nic_3 *)desc;
++ rx_desc = &rxq->rx[ntc].flex_adv_nic_3_wb;
+
+ /* This memory barrier is needed to keep us from reading
+ * any other fields out of the rx_desc
+@@ -3150,7 +3309,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ gen_id = le16_get_bits(rx_desc->pktlen_gen_bufq_id,
+ VIRTCHNL2_RX_FLEX_DESC_ADV_GEN_M);
+
+- if (test_bit(__IDPF_Q_GEN_CHK, rxq->flags) != gen_id)
++ if (idpf_queue_has(GEN_CHK, rxq) != gen_id)
+ break;
+
+ rxdid = FIELD_GET(VIRTCHNL2_RX_FLEX_DESC_ADV_RXDID_M,
+@@ -3158,7 +3317,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ if (rxdid != VIRTCHNL2_RXDID_2_FLEX_SPLITQ) {
+ IDPF_RX_BUMP_NTC(rxq, ntc);
+ u64_stats_update_begin(&rxq->stats_sync);
+- u64_stats_inc(&rxq->q_stats.rx.bad_descs);
++ u64_stats_inc(&rxq->q_stats.bad_descs);
+ u64_stats_update_end(&rxq->stats_sync);
+ continue;
+ }
+@@ -3176,7 +3335,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ * data/payload buffer.
+ */
+ u64_stats_update_begin(&rxq->stats_sync);
+- u64_stats_inc(&rxq->q_stats.rx.hsplit_buf_ovf);
++ u64_stats_inc(&rxq->q_stats.hsplit_buf_ovf);
+ u64_stats_update_end(&rxq->stats_sync);
+ goto bypass_hsplit;
+ }
+@@ -3189,13 +3348,10 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ VIRTCHNL2_RX_FLEX_DESC_ADV_BUFQ_ID_M);
+
+ rxq_set = container_of(rxq, struct idpf_rxq_set, rxq);
+- if (!bufq_id)
+- refillq = rxq_set->refillq0;
+- else
+- refillq = rxq_set->refillq1;
++ refillq = rxq_set->refillq[bufq_id];
+
+ /* retrieve buffer from the rxq */
+- rx_bufq = &rxq->rxq_grp->splitq.bufq_sets[bufq_id].bufq;
++ rx_bufq = &rxq->bufq_sets[bufq_id].bufq;
+
+ buf_id = le16_to_cpu(rx_desc->buf_id);
+
+@@ -3207,7 +3363,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+
+ skb = idpf_rx_hdr_construct_skb(rxq, va, hdr_len);
+ u64_stats_update_begin(&rxq->stats_sync);
+- u64_stats_inc(&rxq->q_stats.rx.hsplit_pkts);
++ u64_stats_inc(&rxq->q_stats.hsplit_pkts);
+ u64_stats_update_end(&rxq->stats_sync);
+ }
+
+@@ -3250,7 +3406,7 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ }
+
+ /* send completed skb up the stack */
+- napi_gro_receive(&rxq->q_vector->napi, skb);
++ napi_gro_receive(rxq->napi, skb);
+ skb = NULL;
+
+ /* update budget accounting */
+@@ -3261,8 +3417,8 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+
+ rxq->skb = skb;
+ u64_stats_update_begin(&rxq->stats_sync);
+- u64_stats_add(&rxq->q_stats.rx.packets, total_rx_pkts);
+- u64_stats_add(&rxq->q_stats.rx.bytes, total_rx_bytes);
++ u64_stats_add(&rxq->q_stats.packets, total_rx_pkts);
++ u64_stats_add(&rxq->q_stats.bytes, total_rx_bytes);
+ u64_stats_update_end(&rxq->stats_sync);
+
+ /* guarantee a trip back through this routine if there was a failure */
+@@ -3272,19 +3428,16 @@ static int idpf_rx_splitq_clean(struct idpf_queue *rxq, int budget)
+ /**
+ * idpf_rx_update_bufq_desc - Update buffer queue descriptor
+ * @bufq: Pointer to the buffer queue
+- * @refill_desc: SW Refill queue descriptor containing buffer ID
++ * @buf_id: buffer ID
+ * @buf_desc: Buffer queue descriptor
+ *
+ * Return 0 on success and negative on failure.
+ */
+-static int idpf_rx_update_bufq_desc(struct idpf_queue *bufq, u16 refill_desc,
++static int idpf_rx_update_bufq_desc(struct idpf_buf_queue *bufq, u32 buf_id,
+ struct virtchnl2_splitq_rx_buf_desc *buf_desc)
+ {
+ struct idpf_rx_buf *buf;
+ dma_addr_t addr;
+- u16 buf_id;
+-
+- buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc);
+
+ buf = &bufq->rx_buf.buf[buf_id];
+
+@@ -3295,7 +3448,7 @@ static int idpf_rx_update_bufq_desc(struct idpf_queue *bufq, u16 refill_desc,
+ buf_desc->pkt_addr = cpu_to_le64(addr);
+ buf_desc->qword0.buf_id = cpu_to_le16(buf_id);
+
+- if (!bufq->rx_hsplit_en)
++ if (!idpf_queue_has(HSPLIT_EN, bufq))
+ return 0;
+
+ buf_desc->hdr_addr = cpu_to_le64(bufq->rx_buf.hdr_buf_pa +
+@@ -3311,38 +3464,37 @@ static int idpf_rx_update_bufq_desc(struct idpf_queue *bufq, u16 refill_desc,
+ *
+ * This function takes care of the buffer refill management
+ */
+-static void idpf_rx_clean_refillq(struct idpf_queue *bufq,
++static void idpf_rx_clean_refillq(struct idpf_buf_queue *bufq,
+ struct idpf_sw_queue *refillq)
+ {
+ struct virtchnl2_splitq_rx_buf_desc *buf_desc;
+ u16 bufq_nta = bufq->next_to_alloc;
+ u16 ntc = refillq->next_to_clean;
+ int cleaned = 0;
+- u16 gen;
+
+- buf_desc = IDPF_SPLITQ_RX_BUF_DESC(bufq, bufq_nta);
++ buf_desc = &bufq->split_buf[bufq_nta];
+
+ /* make sure we stop at ring wrap in the unlikely case ring is full */
+ while (likely(cleaned < refillq->desc_count)) {
+- u16 refill_desc = IDPF_SPLITQ_RX_BI_DESC(refillq, ntc);
++ u32 buf_id, refill_desc = refillq->ring[ntc];
+ bool failure;
+
+- gen = FIELD_GET(IDPF_RX_BI_GEN_M, refill_desc);
+- if (test_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags) != gen)
++ if (idpf_queue_has(RFL_GEN_CHK, refillq) !=
++ !!(refill_desc & IDPF_RX_BI_GEN_M))
+ break;
+
+- failure = idpf_rx_update_bufq_desc(bufq, refill_desc,
+- buf_desc);
++ buf_id = FIELD_GET(IDPF_RX_BI_BUFID_M, refill_desc);
++ failure = idpf_rx_update_bufq_desc(bufq, buf_id, buf_desc);
+ if (failure)
+ break;
+
+ if (unlikely(++ntc == refillq->desc_count)) {
+- change_bit(__IDPF_RFLQ_GEN_CHK, refillq->flags);
++ idpf_queue_change(RFL_GEN_CHK, refillq);
+ ntc = 0;
+ }
+
+ if (unlikely(++bufq_nta == bufq->desc_count)) {
+- buf_desc = IDPF_SPLITQ_RX_BUF_DESC(bufq, 0);
++ buf_desc = &bufq->split_buf[0];
+ bufq_nta = 0;
+ } else {
+ buf_desc++;
+@@ -3376,7 +3528,7 @@ static void idpf_rx_clean_refillq(struct idpf_queue *bufq,
+ * this vector. Returns true if clean is complete within budget, false
+ * otherwise.
+ */
+-static void idpf_rx_clean_refillq_all(struct idpf_queue *bufq)
++static void idpf_rx_clean_refillq_all(struct idpf_buf_queue *bufq)
+ {
+ struct idpf_bufq_set *bufq_set;
+ int i;
+@@ -3439,6 +3591,8 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
+ for (u32 v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
+ struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
+
++ kfree(q_vector->complq);
++ q_vector->complq = NULL;
+ kfree(q_vector->bufq);
+ q_vector->bufq = NULL;
+ kfree(q_vector->tx);
+@@ -3557,13 +3711,13 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector)
+ goto check_rx_itr;
+
+ for (i = 0, packets = 0, bytes = 0; i < q_vector->num_txq; i++) {
+- struct idpf_queue *txq = q_vector->tx[i];
++ struct idpf_tx_queue *txq = q_vector->tx[i];
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin(&txq->stats_sync);
+- packets += u64_stats_read(&txq->q_stats.tx.packets);
+- bytes += u64_stats_read(&txq->q_stats.tx.bytes);
++ packets += u64_stats_read(&txq->q_stats.packets);
++ bytes += u64_stats_read(&txq->q_stats.bytes);
+ } while (u64_stats_fetch_retry(&txq->stats_sync, start));
+ }
+
+@@ -3576,13 +3730,13 @@ static void idpf_net_dim(struct idpf_q_vector *q_vector)
+ return;
+
+ for (i = 0, packets = 0, bytes = 0; i < q_vector->num_rxq; i++) {
+- struct idpf_queue *rxq = q_vector->rx[i];
++ struct idpf_rx_queue *rxq = q_vector->rx[i];
+ unsigned int start;
+
+ do {
+ start = u64_stats_fetch_begin(&rxq->stats_sync);
+- packets += u64_stats_read(&rxq->q_stats.rx.packets);
+- bytes += u64_stats_read(&rxq->q_stats.rx.bytes);
++ packets += u64_stats_read(&rxq->q_stats.packets);
++ bytes += u64_stats_read(&rxq->q_stats.bytes);
+ } while (u64_stats_fetch_retry(&rxq->stats_sync, start));
+ }
+
+@@ -3826,16 +3980,17 @@ static void idpf_vport_intr_napi_ena_all(struct idpf_vport *vport)
+ static bool idpf_tx_splitq_clean_all(struct idpf_q_vector *q_vec,
+ int budget, int *cleaned)
+ {
+- u16 num_txq = q_vec->num_txq;
++ u16 num_complq = q_vec->num_complq;
+ bool clean_complete = true;
+ int i, budget_per_q;
+
+- if (unlikely(!num_txq))
++ if (unlikely(!num_complq))
+ return true;
+
+- budget_per_q = DIV_ROUND_UP(budget, num_txq);
+- for (i = 0; i < num_txq; i++)
+- clean_complete &= idpf_tx_clean_complq(q_vec->tx[i],
++ budget_per_q = DIV_ROUND_UP(budget, num_complq);
++
++ for (i = 0; i < num_complq; i++)
++ clean_complete &= idpf_tx_clean_complq(q_vec->complq[i],
+ budget_per_q, cleaned);
+
+ return clean_complete;
+@@ -3862,7 +4017,7 @@ static bool idpf_rx_splitq_clean_all(struct idpf_q_vector *q_vec, int budget,
+ */
+ budget_per_q = num_rxq ? max(budget / num_rxq, 1) : 0;
+ for (i = 0; i < num_rxq; i++) {
+- struct idpf_queue *rxq = q_vec->rx[i];
++ struct idpf_rx_queue *rxq = q_vec->rx[i];
+ int pkts_cleaned_per_q;
+
+ pkts_cleaned_per_q = idpf_rx_splitq_clean(rxq, budget_per_q);
+@@ -3917,8 +4072,8 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
+ * queues virtchnl message, as the interrupts will be disabled after
+ * that
+ */
+- if (unlikely(q_vector->num_txq && test_bit(__IDPF_Q_POLL_MODE,
+- q_vector->tx[0]->flags)))
++ if (unlikely(q_vector->num_txq && idpf_queue_has(POLL_MODE,
++ q_vector->tx[0])))
+ return budget;
+ else
+ return work_done;
+@@ -3932,27 +4087,28 @@ static int idpf_vport_splitq_napi_poll(struct napi_struct *napi, int budget)
+ */
+ static void idpf_vport_intr_map_vector_to_qs(struct idpf_vport *vport)
+ {
++ bool split = idpf_is_queue_model_split(vport->rxq_model);
+ u16 num_txq_grp = vport->num_txq_grp;
+- int i, j, qv_idx, bufq_vidx = 0;
+ struct idpf_rxq_group *rx_qgrp;
+ struct idpf_txq_group *tx_qgrp;
+- struct idpf_queue *q, *bufq;
+- u16 q_index;
++ u32 i, qv_idx, q_index;
+
+ for (i = 0, qv_idx = 0; i < vport->num_rxq_grp; i++) {
+ u16 num_rxq;
+
++ if (qv_idx >= vport->num_q_vectors)
++ qv_idx = 0;
++
+ rx_qgrp = &vport->rxq_grps[i];
+- if (idpf_is_queue_model_split(vport->rxq_model))
++ if (split)
+ num_rxq = rx_qgrp->splitq.num_rxq_sets;
+ else
+ num_rxq = rx_qgrp->singleq.num_rxq;
+
+- for (j = 0; j < num_rxq; j++) {
+- if (qv_idx >= vport->num_q_vectors)
+- qv_idx = 0;
++ for (u32 j = 0; j < num_rxq; j++) {
++ struct idpf_rx_queue *q;
+
+- if (idpf_is_queue_model_split(vport->rxq_model))
++ if (split)
+ q = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+ else
+ q = rx_qgrp->singleq.rxqs[j];
+@@ -3960,52 +4116,53 @@ static void idpf_vport_intr_map_vector_to_qs(struct idpf_vport *vport)
+ q_index = q->q_vector->num_rxq;
+ q->q_vector->rx[q_index] = q;
+ q->q_vector->num_rxq++;
+- qv_idx++;
++
++ if (split)
++ q->napi = &q->q_vector->napi;
+ }
+
+- if (idpf_is_queue_model_split(vport->rxq_model)) {
+- for (j = 0; j < vport->num_bufqs_per_qgrp; j++) {
++ if (split) {
++ for (u32 j = 0; j < vport->num_bufqs_per_qgrp; j++) {
++ struct idpf_buf_queue *bufq;
++
+ bufq = &rx_qgrp->splitq.bufq_sets[j].bufq;
+- bufq->q_vector = &vport->q_vectors[bufq_vidx];
++ bufq->q_vector = &vport->q_vectors[qv_idx];
+ q_index = bufq->q_vector->num_bufq;
+ bufq->q_vector->bufq[q_index] = bufq;
+ bufq->q_vector->num_bufq++;
+ }
+- if (++bufq_vidx >= vport->num_q_vectors)
+- bufq_vidx = 0;
+ }
++
++ qv_idx++;
+ }
+
++ split = idpf_is_queue_model_split(vport->txq_model);
++
+ for (i = 0, qv_idx = 0; i < num_txq_grp; i++) {
+ u16 num_txq;
+
++ if (qv_idx >= vport->num_q_vectors)
++ qv_idx = 0;
++
+ tx_qgrp = &vport->txq_grps[i];
+ num_txq = tx_qgrp->num_txq;
+
+- if (idpf_is_queue_model_split(vport->txq_model)) {
+- if (qv_idx >= vport->num_q_vectors)
+- qv_idx = 0;
++ for (u32 j = 0; j < num_txq; j++) {
++ struct idpf_tx_queue *q;
+
+- q = tx_qgrp->complq;
++ q = tx_qgrp->txqs[j];
+ q->q_vector = &vport->q_vectors[qv_idx];
+- q_index = q->q_vector->num_txq;
+- q->q_vector->tx[q_index] = q;
+- q->q_vector->num_txq++;
+- qv_idx++;
+- } else {
+- for (j = 0; j < num_txq; j++) {
+- if (qv_idx >= vport->num_q_vectors)
+- qv_idx = 0;
++ q->q_vector->tx[q->q_vector->num_txq++] = q;
++ }
+
+- q = tx_qgrp->txqs[j];
+- q->q_vector = &vport->q_vectors[qv_idx];
+- q_index = q->q_vector->num_txq;
+- q->q_vector->tx[q_index] = q;
+- q->q_vector->num_txq++;
++ if (split) {
++ struct idpf_compl_queue *q = tx_qgrp->complq;
+
+- qv_idx++;
+- }
++ q->q_vector = &vport->q_vectors[qv_idx];
++ q->q_vector->complq[q->q_vector->num_complq++] = q;
+ }
++
++ qv_idx++;
+ }
+ }
+
+@@ -4081,18 +4238,22 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
+ {
+ u16 txqs_per_vector, rxqs_per_vector, bufqs_per_vector;
+ struct idpf_q_vector *q_vector;
+- int v_idx, err;
++ u32 complqs_per_vector, v_idx;
+
+ vport->q_vectors = kcalloc(vport->num_q_vectors,
+ sizeof(struct idpf_q_vector), GFP_KERNEL);
+ if (!vport->q_vectors)
+ return -ENOMEM;
+
+- txqs_per_vector = DIV_ROUND_UP(vport->num_txq, vport->num_q_vectors);
+- rxqs_per_vector = DIV_ROUND_UP(vport->num_rxq, vport->num_q_vectors);
++ txqs_per_vector = DIV_ROUND_UP(vport->num_txq_grp,
++ vport->num_q_vectors);
++ rxqs_per_vector = DIV_ROUND_UP(vport->num_rxq_grp,
++ vport->num_q_vectors);
+ bufqs_per_vector = vport->num_bufqs_per_qgrp *
+ DIV_ROUND_UP(vport->num_rxq_grp,
+ vport->num_q_vectors);
++ complqs_per_vector = DIV_ROUND_UP(vport->num_txq_grp,
++ vport->num_q_vectors);
+
+ for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
+ q_vector = &vport->q_vectors[v_idx];
+@@ -4106,32 +4267,30 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
+ q_vector->rx_intr_mode = IDPF_ITR_DYNAMIC;
+ q_vector->rx_itr_idx = VIRTCHNL2_ITR_IDX_0;
+
+- q_vector->tx = kcalloc(txqs_per_vector,
+- sizeof(struct idpf_queue *),
++ q_vector->tx = kcalloc(txqs_per_vector, sizeof(*q_vector->tx),
+ GFP_KERNEL);
+- if (!q_vector->tx) {
+- err = -ENOMEM;
++ if (!q_vector->tx)
+ goto error;
+- }
+
+- q_vector->rx = kcalloc(rxqs_per_vector,
+- sizeof(struct idpf_queue *),
++ q_vector->rx = kcalloc(rxqs_per_vector, sizeof(*q_vector->rx),
+ GFP_KERNEL);
+- if (!q_vector->rx) {
+- err = -ENOMEM;
++ if (!q_vector->rx)
+ goto error;
+- }
+
+ if (!idpf_is_queue_model_split(vport->rxq_model))
+ continue;
+
+ q_vector->bufq = kcalloc(bufqs_per_vector,
+- sizeof(struct idpf_queue *),
++ sizeof(*q_vector->bufq),
+ GFP_KERNEL);
+- if (!q_vector->bufq) {
+- err = -ENOMEM;
++ if (!q_vector->bufq)
++ goto error;
++
++ q_vector->complq = kcalloc(complqs_per_vector,
++ sizeof(*q_vector->complq),
++ GFP_KERNEL);
++ if (!q_vector->complq)
+ goto error;
+- }
+ }
+
+ return 0;
+@@ -4139,7 +4298,7 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
+ error:
+ idpf_vport_intr_rel(vport);
+
+- return err;
++ return -ENOMEM;
+ }
+
+ /**
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.h b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+index 551391e2046470..214a24e684634a 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.h
++++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.h
+@@ -4,10 +4,13 @@
+ #ifndef _IDPF_TXRX_H_
+ #define _IDPF_TXRX_H_
+
++#include <linux/dim.h>
++
+ #include <net/page_pool/helpers.h>
+ #include <net/tcp.h>
+ #include <net/netdev_queues.h>
+
++#include "idpf_lan_txrx.h"
+ #include "virtchnl2_lan_desc.h"
+
+ #define IDPF_LARGE_MAX_Q 256
+@@ -83,7 +86,7 @@
+ do { \
+ if (unlikely(++(ntc) == (rxq)->desc_count)) { \
+ ntc = 0; \
+- change_bit(__IDPF_Q_GEN_CHK, (rxq)->flags); \
++ idpf_queue_change(GEN_CHK, rxq); \
+ } \
+ } while (0)
+
+@@ -110,36 +113,17 @@ do { \
+ */
+ #define IDPF_TX_SPLITQ_RE_MIN_GAP 64
+
+-#define IDPF_RX_BI_BUFID_S 0
+-#define IDPF_RX_BI_BUFID_M GENMASK(14, 0)
+-#define IDPF_RX_BI_GEN_S 15
+-#define IDPF_RX_BI_GEN_M BIT(IDPF_RX_BI_GEN_S)
++#define IDPF_RX_BI_GEN_M BIT(16)
++#define IDPF_RX_BI_BUFID_M GENMASK(15, 0)
++
+ #define IDPF_RXD_EOF_SPLITQ VIRTCHNL2_RX_FLEX_DESC_ADV_STATUS0_EOF_M
+ #define IDPF_RXD_EOF_SINGLEQ VIRTCHNL2_RX_BASE_DESC_STATUS_EOF_M
+
+-#define IDPF_SINGLEQ_RX_BUF_DESC(rxq, i) \
+- (&(((struct virtchnl2_singleq_rx_buf_desc *)((rxq)->desc_ring))[i]))
+-#define IDPF_SPLITQ_RX_BUF_DESC(rxq, i) \
+- (&(((struct virtchnl2_splitq_rx_buf_desc *)((rxq)->desc_ring))[i]))
+-#define IDPF_SPLITQ_RX_BI_DESC(rxq, i) ((((rxq)->ring))[i])
+-
+-#define IDPF_BASE_TX_DESC(txq, i) \
+- (&(((struct idpf_base_tx_desc *)((txq)->desc_ring))[i]))
+-#define IDPF_BASE_TX_CTX_DESC(txq, i) \
+- (&(((struct idpf_base_tx_ctx_desc *)((txq)->desc_ring))[i]))
+-#define IDPF_SPLITQ_TX_COMPLQ_DESC(txcq, i) \
+- (&(((struct idpf_splitq_tx_compl_desc *)((txcq)->desc_ring))[i]))
+-
+-#define IDPF_FLEX_TX_DESC(txq, i) \
+- (&(((union idpf_tx_flex_desc *)((txq)->desc_ring))[i]))
+-#define IDPF_FLEX_TX_CTX_DESC(txq, i) \
+- (&(((struct idpf_flex_tx_ctx_desc *)((txq)->desc_ring))[i]))
+-
+ #define IDPF_DESC_UNUSED(txq) \
+ ((((txq)->next_to_clean > (txq)->next_to_use) ? 0 : (txq)->desc_count) + \
+ (txq)->next_to_clean - (txq)->next_to_use - 1)
+
+-#define IDPF_TX_BUF_RSV_UNUSED(txq) ((txq)->buf_stack.top)
++#define IDPF_TX_BUF_RSV_UNUSED(txq) ((txq)->stash->buf_stack.top)
+ #define IDPF_TX_BUF_RSV_LOW(txq) (IDPF_TX_BUF_RSV_UNUSED(txq) < \
+ (txq)->desc_count >> 2)
+
+@@ -317,8 +301,6 @@ struct idpf_rx_extracted {
+
+ #define IDPF_RX_DMA_ATTR \
+ (DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING)
+-#define IDPF_RX_DESC(rxq, i) \
+- (&(((union virtchnl2_rx_desc *)((rxq)->desc_ring))[i]))
+
+ struct idpf_rx_buf {
+ struct page *page;
+@@ -452,23 +434,37 @@ struct idpf_rx_ptype_decoded {
+ * to 1 and knows that reading a gen bit of 1 in any
+ * descriptor on the initial pass of the ring indicates a
+ * writeback. It also flips on every ring wrap.
+- * @__IDPF_RFLQ_GEN_CHK: Refill queues are SW only, so Q_GEN acts as the HW bit
+- * and RFLGQ_GEN is the SW bit.
++ * @__IDPF_Q_RFL_GEN_CHK: Refill queues are SW only, so Q_GEN acts as the HW
++ * bit and Q_RFL_GEN is the SW bit.
+ * @__IDPF_Q_FLOW_SCH_EN: Enable flow scheduling
+ * @__IDPF_Q_SW_MARKER: Used to indicate TX queue marker completions
+ * @__IDPF_Q_POLL_MODE: Enable poll mode
++ * @__IDPF_Q_CRC_EN: enable CRC offload in singleq mode
++ * @__IDPF_Q_HSPLIT_EN: enable header split on Rx (splitq)
+ * @__IDPF_Q_FLAGS_NBITS: Must be last
+ */
+ enum idpf_queue_flags_t {
+ __IDPF_Q_GEN_CHK,
+- __IDPF_RFLQ_GEN_CHK,
++ __IDPF_Q_RFL_GEN_CHK,
+ __IDPF_Q_FLOW_SCH_EN,
+ __IDPF_Q_SW_MARKER,
+ __IDPF_Q_POLL_MODE,
++ __IDPF_Q_CRC_EN,
++ __IDPF_Q_HSPLIT_EN,
+
+ __IDPF_Q_FLAGS_NBITS,
+ };
+
++#define idpf_queue_set(f, q) __set_bit(__IDPF_Q_##f, (q)->flags)
++#define idpf_queue_clear(f, q) __clear_bit(__IDPF_Q_##f, (q)->flags)
++#define idpf_queue_change(f, q) __change_bit(__IDPF_Q_##f, (q)->flags)
++#define idpf_queue_has(f, q) test_bit(__IDPF_Q_##f, (q)->flags)
++
++#define idpf_queue_has_clear(f, q) \
++ __test_and_clear_bit(__IDPF_Q_##f, (q)->flags)
++#define idpf_queue_assign(f, q, v) \
++ __assign_bit(__IDPF_Q_##f, (q)->flags, v)
++
+ /**
+ * struct idpf_vec_regs
+ * @dyn_ctl_reg: Dynamic control interrupt register offset
+@@ -514,7 +510,9 @@ struct idpf_intr_reg {
+ * @v_idx: Vector index
+ * @intr_reg: See struct idpf_intr_reg
+ * @num_txq: Number of TX queues
++ * @num_complq: number of completion queues
+ * @tx: Array of TX queues to service
++ * @complq: array of completion queues
+ * @tx_dim: Data for TX net_dim algorithm
+ * @tx_itr_value: TX interrupt throttling rate
+ * @tx_intr_mode: Dynamic ITR or not
+@@ -538,21 +536,24 @@ struct idpf_q_vector {
+ struct idpf_intr_reg intr_reg;
+
+ u16 num_txq;
+- struct idpf_queue **tx;
++ u16 num_complq;
++ struct idpf_tx_queue **tx;
++ struct idpf_compl_queue **complq;
++
+ struct dim tx_dim;
+ u16 tx_itr_value;
+ bool tx_intr_mode;
+ u32 tx_itr_idx;
+
+ u16 num_rxq;
+- struct idpf_queue **rx;
++ struct idpf_rx_queue **rx;
+ struct dim rx_dim;
+ u16 rx_itr_value;
+ bool rx_intr_mode;
+ u32 rx_itr_idx;
+
+ u16 num_bufq;
+- struct idpf_queue **bufq;
++ struct idpf_buf_queue **bufq;
+
+ u16 total_events;
+ char *name;
+@@ -583,11 +584,6 @@ struct idpf_cleaned_stats {
+ u32 bytes;
+ };
+
+-union idpf_queue_stats {
+- struct idpf_rx_queue_stats rx;
+- struct idpf_tx_queue_stats tx;
+-};
+-
+ #define IDPF_ITR_DYNAMIC 1
+ #define IDPF_ITR_MAX 0x1FE0
+ #define IDPF_ITR_20K 0x0032
+@@ -603,39 +599,114 @@ union idpf_queue_stats {
+ #define IDPF_DIM_DEFAULT_PROFILE_IX 1
+
+ /**
+- * struct idpf_queue
+- * @dev: Device back pointer for DMA mapping
+- * @vport: Back pointer to associated vport
+- * @txq_grp: See struct idpf_txq_group
+- * @rxq_grp: See struct idpf_rxq_group
+- * @idx: For buffer queue, it is used as group id, either 0 or 1. On clean,
+- * buffer queue uses this index to determine which group of refill queues
+- * to clean.
+- * For TX queue, it is used as index to map between TX queue group and
+- * hot path TX pointers stored in vport. Used in both singleq/splitq.
+- * For RX queue, it is used to index to total RX queue across groups and
++ * struct idpf_txq_stash - Tx buffer stash for Flow-based scheduling mode
++ * @buf_stack: Stack of empty buffers to store buffer info for out of order
++ * buffer completions. See struct idpf_buf_lifo
++ * @sched_buf_hash: Hash table to store buffers
++ */
++struct idpf_txq_stash {
++ struct idpf_buf_lifo buf_stack;
++ DECLARE_HASHTABLE(sched_buf_hash, 12);
++} ____cacheline_aligned;
++
++/**
++ * struct idpf_rx_queue - software structure representing a receive queue
++ * @rx: universal receive descriptor array
++ * @single_buf: buffer descriptor array in singleq
++ * @desc_ring: virtual descriptor ring address
++ * @bufq_sets: Pointer to the array of buffer queues in splitq mode
++ * @napi: NAPI instance corresponding to this queue (splitq)
++ * @rx_buf: See struct idpf_rx_buf
++ * @pp: Page pool pointer in singleq mode
++ * @netdev: &net_device corresponding to this queue
++ * @tail: Tail offset. Used for both queue models single and split.
++ * @flags: See enum idpf_queue_flags_t
++ * @idx: For RX queue, it is used to index to total RX queue across groups and
+ * used for skb reporting.
+- * @tail: Tail offset. Used for both queue models single and split. In splitq
+- * model relevant only for TX queue and RX queue.
+- * @tx_buf: See struct idpf_tx_buf
+- * @rx_buf: Struct with RX buffer related members
+- * @rx_buf.buf: See struct idpf_rx_buf
+- * @rx_buf.hdr_buf_pa: DMA handle
+- * @rx_buf.hdr_buf_va: Virtual address
+- * @pp: Page pool pointer
++ * @desc_count: Number of descriptors
++ * @next_to_use: Next descriptor to use
++ * @next_to_clean: Next descriptor to clean
++ * @next_to_alloc: RX buffer to allocate at
++ * @rxdids: Supported RX descriptor ids
++ * @rx_ptype_lkup: LUT of Rx ptypes
+ * @skb: Pointer to the skb
+- * @q_type: Queue type (TX, RX, TX completion, RX buffer)
++ * @stats_sync: See struct u64_stats_sync
++ * @q_stats: See union idpf_rx_queue_stats
+ * @q_id: Queue id
+- * @desc_count: Number of descriptors
+- * @next_to_use: Next descriptor to use. Relevant in both split & single txq
+- * and bufq.
+- * @next_to_clean: Next descriptor to clean. In split queue model, only
+- * relevant to TX completion queue and RX queue.
+- * @next_to_alloc: RX buffer to allocate at. Used only for RX. In splitq model
+- * only relevant to RX queue.
++ * @size: Length of descriptor ring in bytes
++ * @dma: Physical address of ring
++ * @q_vector: Backreference to associated vector
++ * @rx_buffer_low_watermark: RX buffer low watermark
++ * @rx_hbuf_size: Header buffer size
++ * @rx_buf_size: Buffer size
++ * @rx_max_pkt_size: RX max packet size
++ */
++struct idpf_rx_queue {
++ union {
++ union virtchnl2_rx_desc *rx;
++ struct virtchnl2_singleq_rx_buf_desc *single_buf;
++
++ void *desc_ring;
++ };
++ union {
++ struct {
++ struct idpf_bufq_set *bufq_sets;
++ struct napi_struct *napi;
++ };
++ struct {
++ struct idpf_rx_buf *rx_buf;
++ struct page_pool *pp;
++ };
++ };
++ struct net_device *netdev;
++ void __iomem *tail;
++
++ DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
++ u16 idx;
++ u16 desc_count;
++ u16 next_to_use;
++ u16 next_to_clean;
++ u16 next_to_alloc;
++
++ u32 rxdids;
++
++ const struct idpf_rx_ptype_decoded *rx_ptype_lkup;
++ struct sk_buff *skb;
++
++ struct u64_stats_sync stats_sync;
++ struct idpf_rx_queue_stats q_stats;
++
++ /* Slowpath */
++ u32 q_id;
++ u32 size;
++ dma_addr_t dma;
++
++ struct idpf_q_vector *q_vector;
++
++ u16 rx_buffer_low_watermark;
++ u16 rx_hbuf_size;
++ u16 rx_buf_size;
++ u16 rx_max_pkt_size;
++} ____cacheline_aligned;
++
++/**
++ * struct idpf_tx_queue - software structure representing a transmit queue
++ * @base_tx: base Tx descriptor array
++ * @base_ctx: base Tx context descriptor array
++ * @flex_tx: flex Tx descriptor array
++ * @flex_ctx: flex Tx context descriptor array
++ * @desc_ring: virtual descriptor ring address
++ * @tx_buf: See struct idpf_tx_buf
++ * @txq_grp: See struct idpf_txq_group
++ * @dev: Device back pointer for DMA mapping
++ * @tail: Tail offset. Used for both queue models single and split
+ * @flags: See enum idpf_queue_flags_t
+- * @q_stats: See union idpf_queue_stats
+- * @stats_sync: See struct u64_stats_sync
++ * @idx: For TX queue, it is used as index to map between TX queue group and
++ * hot path TX pointers stored in vport. Used in both singleq/splitq.
++ * @desc_count: Number of descriptors
++ * @next_to_use: Next descriptor to use
++ * @next_to_clean: Next descriptor to clean
++ * @netdev: &net_device corresponding to this queue
+ * @cleaned_bytes: Splitq only, TXQ only: When a TX completion is received on
+ * the TX completion queue, it can be for any TXQ associated
+ * with that completion queue. This means we can clean up to
+@@ -644,26 +715,10 @@ union idpf_queue_stats {
+ * that single call to clean the completion queue. By doing so,
+ * we can update BQL with aggregate cleaned stats for each TXQ
+ * only once at the end of the cleaning routine.
++ * @clean_budget: singleq only, queue cleaning budget
+ * @cleaned_pkts: Number of packets cleaned for the above said case
+- * @rx_hsplit_en: RX headsplit enable
+- * @rx_hbuf_size: Header buffer size
+- * @rx_buf_size: Buffer size
+- * @rx_max_pkt_size: RX max packet size
+- * @rx_buf_stride: RX buffer stride
+- * @rx_buffer_low_watermark: RX buffer low watermark
+- * @rxdids: Supported RX descriptor ids
+- * @q_vector: Backreference to associated vector
+- * @size: Length of descriptor ring in bytes
+- * @dma: Physical address of ring
+- * @desc_ring: Descriptor ring memory
+ * @tx_max_bufs: Max buffers that can be transmitted with scatter-gather
+ * @tx_min_pkt_len: Min supported packet length
+- * @num_completions: Only relevant for TX completion queue. It tracks the
+- * number of completions received to compare against the
+- * number of completions pending, as accumulated by the
+- * TX queues.
+- * @buf_stack: Stack of empty buffers to store buffer info for out of order
+- * buffer completions. See struct idpf_buf_lifo.
+ * @compl_tag_bufid_m: Completion tag buffer id mask
+ * @compl_tag_gen_s: Completion tag generation bit
+ * The format of the completion tag will change based on the TXQ
+@@ -687,106 +742,188 @@ union idpf_queue_stats {
+ * This gives us 8*8160 = 65280 possible unique values.
+ * @compl_tag_cur_gen: Used to keep track of current completion tag generation
+ * @compl_tag_gen_max: To determine when compl_tag_cur_gen should be reset
+- * @sched_buf_hash: Hash table to stores buffers
++ * @stash: Tx buffer stash for Flow-based scheduling mode
++ * @stats_sync: See struct u64_stats_sync
++ * @q_stats: See union idpf_tx_queue_stats
++ * @q_id: Queue id
++ * @size: Length of descriptor ring in bytes
++ * @dma: Physical address of ring
++ * @q_vector: Backreference to associated vector
+ */
+-struct idpf_queue {
+- struct device *dev;
+- struct idpf_vport *vport;
++struct idpf_tx_queue {
+ union {
+- struct idpf_txq_group *txq_grp;
+- struct idpf_rxq_group *rxq_grp;
++ struct idpf_base_tx_desc *base_tx;
++ struct idpf_base_tx_ctx_desc *base_ctx;
++ union idpf_tx_flex_desc *flex_tx;
++ struct idpf_flex_tx_ctx_desc *flex_ctx;
++
++ void *desc_ring;
+ };
+- u16 idx;
++ struct idpf_tx_buf *tx_buf;
++ struct idpf_txq_group *txq_grp;
++ struct device *dev;
+ void __iomem *tail;
++
++ DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
++ u16 idx;
++ u16 desc_count;
++ u16 next_to_use;
++ u16 next_to_clean;
++
++ struct net_device *netdev;
++
+ union {
+- struct idpf_tx_buf *tx_buf;
+- struct {
+- struct idpf_rx_buf *buf;
+- dma_addr_t hdr_buf_pa;
+- void *hdr_buf_va;
+- } rx_buf;
++ u32 cleaned_bytes;
++ u32 clean_budget;
+ };
+- struct page_pool *pp;
+- struct sk_buff *skb;
+- u16 q_type;
++ u16 cleaned_pkts;
++
++ u16 tx_max_bufs;
++ u16 tx_min_pkt_len;
++
++ u16 compl_tag_bufid_m;
++ u16 compl_tag_gen_s;
++
++ u16 compl_tag_cur_gen;
++ u16 compl_tag_gen_max;
++
++ struct idpf_txq_stash *stash;
++
++ struct u64_stats_sync stats_sync;
++ struct idpf_tx_queue_stats q_stats;
++
++ /* Slowpath */
+ u32 q_id;
+- u16 desc_count;
++ u32 size;
++ dma_addr_t dma;
+
++ struct idpf_q_vector *q_vector;
++} ____cacheline_aligned;
++
++/**
++ * struct idpf_buf_queue - software structure representing a buffer queue
++ * @split_buf: buffer descriptor array
++ * @rx_buf: Struct with RX buffer related members
++ * @rx_buf.buf: See struct idpf_rx_buf
++ * @rx_buf.hdr_buf_pa: DMA handle
++ * @rx_buf.hdr_buf_va: Virtual address
++ * @pp: Page pool pointer
++ * @tail: Tail offset
++ * @flags: See enum idpf_queue_flags_t
++ * @desc_count: Number of descriptors
++ * @next_to_use: Next descriptor to use
++ * @next_to_clean: Next descriptor to clean
++ * @next_to_alloc: RX buffer to allocate at
++ * @q_id: Queue id
++ * @size: Length of descriptor ring in bytes
++ * @dma: Physical address of ring
++ * @q_vector: Backreference to associated vector
++ * @rx_buffer_low_watermark: RX buffer low watermark
++ * @rx_hbuf_size: Header buffer size
++ * @rx_buf_size: Buffer size
++ */
++struct idpf_buf_queue {
++ struct virtchnl2_splitq_rx_buf_desc *split_buf;
++ struct {
++ struct idpf_rx_buf *buf;
++ dma_addr_t hdr_buf_pa;
++ void *hdr_buf_va;
++ } rx_buf;
++ struct page_pool *pp;
++ void __iomem *tail;
++
++ DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
++ u16 desc_count;
+ u16 next_to_use;
+ u16 next_to_clean;
+ u16 next_to_alloc;
+- DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
+
+- union idpf_queue_stats q_stats;
+- struct u64_stats_sync stats_sync;
++ /* Slowpath */
++ u32 q_id;
++ u32 size;
++ dma_addr_t dma;
+
+- u32 cleaned_bytes;
+- u16 cleaned_pkts;
++ struct idpf_q_vector *q_vector;
+
+- bool rx_hsplit_en;
++ u16 rx_buffer_low_watermark;
+ u16 rx_hbuf_size;
+ u16 rx_buf_size;
+- u16 rx_max_pkt_size;
+- u16 rx_buf_stride;
+- u8 rx_buffer_low_watermark;
+- u64 rxdids;
+- struct idpf_q_vector *q_vector;
+- unsigned int size;
+- dma_addr_t dma;
+- void *desc_ring;
+-
+- u16 tx_max_bufs;
+- u8 tx_min_pkt_len;
++} ____cacheline_aligned;
+
+- u32 num_completions;
++/**
++ * struct idpf_compl_queue - software structure representing a completion queue
++ * @comp: completion descriptor array
++ * @txq_grp: See struct idpf_txq_group
++ * @flags: See enum idpf_queue_flags_t
++ * @desc_count: Number of descriptors
++ * @next_to_use: Next descriptor to use. Relevant in both split & single txq
++ * and bufq.
++ * @next_to_clean: Next descriptor to clean
++ * @netdev: &net_device corresponding to this queue
++ * @clean_budget: queue cleaning budget
++ * @num_completions: Only relevant for TX completion queue. It tracks the
++ * number of completions received to compare against the
++ * number of completions pending, as accumulated by the
++ * TX queues.
++ * @q_id: Queue id
++ * @size: Length of descriptor ring in bytes
++ * @dma: Physical address of ring
++ * @q_vector: Backreference to associated vector
++ */
++struct idpf_compl_queue {
++ struct idpf_splitq_tx_compl_desc *comp;
++ struct idpf_txq_group *txq_grp;
+
+- struct idpf_buf_lifo buf_stack;
++ DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
++ u16 desc_count;
++ u16 next_to_use;
++ u16 next_to_clean;
+
+- u16 compl_tag_bufid_m;
+- u16 compl_tag_gen_s;
++ struct net_device *netdev;
++ u32 clean_budget;
++ u32 num_completions;
+
+- u16 compl_tag_cur_gen;
+- u16 compl_tag_gen_max;
++ /* Slowpath */
++ u32 q_id;
++ u32 size;
++ dma_addr_t dma;
+
+- DECLARE_HASHTABLE(sched_buf_hash, 12);
+-} ____cacheline_internodealigned_in_smp;
++ struct idpf_q_vector *q_vector;
++} ____cacheline_aligned;
+
+ /**
+ * struct idpf_sw_queue
+- * @next_to_clean: Next descriptor to clean
+- * @next_to_alloc: Buffer to allocate at
+- * @flags: See enum idpf_queue_flags_t
+ * @ring: Pointer to the ring
++ * @flags: See enum idpf_queue_flags_t
+ * @desc_count: Descriptor count
+- * @dev: Device back pointer for DMA mapping
++ * @next_to_use: Buffer to allocate at
++ * @next_to_clean: Next descriptor to clean
+ *
+ * Software queues are used in splitq mode to manage buffers between rxq
+ * producer and the bufq consumer. These are required in order to maintain a
+ * lockless buffer management system and are strictly software only constructs.
+ */
+ struct idpf_sw_queue {
+- u16 next_to_clean;
+- u16 next_to_alloc;
++ u32 *ring;
++
+ DECLARE_BITMAP(flags, __IDPF_Q_FLAGS_NBITS);
+- u16 *ring;
+ u16 desc_count;
+- struct device *dev;
+-} ____cacheline_internodealigned_in_smp;
++ u16 next_to_use;
++ u16 next_to_clean;
++} ____cacheline_aligned;
+
+ /**
+ * struct idpf_rxq_set
+ * @rxq: RX queue
+- * @refillq0: Pointer to refill queue 0
+- * @refillq1: Pointer to refill queue 1
++ * @refillq: pointers to refill queues
+ *
+ * Splitq only. idpf_rxq_set associates an rxq with at an array of refillqs.
+ * Each rxq needs a refillq to return used buffers back to the respective bufq.
+ * Bufqs then clean these refillqs for buffers to give to hardware.
+ */
+ struct idpf_rxq_set {
+- struct idpf_queue rxq;
+- struct idpf_sw_queue *refillq0;
+- struct idpf_sw_queue *refillq1;
++ struct idpf_rx_queue rxq;
++ struct idpf_sw_queue *refillq[IDPF_MAX_BUFQS_PER_RXQ_GRP];
+ };
+
+ /**
+@@ -805,7 +942,7 @@ struct idpf_rxq_set {
+ * managed by at most two bufqs (depending on performance configuration).
+ */
+ struct idpf_bufq_set {
+- struct idpf_queue bufq;
++ struct idpf_buf_queue bufq;
+ int num_refillqs;
+ struct idpf_sw_queue *refillqs;
+ };
+@@ -831,7 +968,7 @@ struct idpf_rxq_group {
+ union {
+ struct {
+ u16 num_rxq;
+- struct idpf_queue *rxqs[IDPF_LARGE_MAX_Q];
++ struct idpf_rx_queue *rxqs[IDPF_LARGE_MAX_Q];
+ } singleq;
+ struct {
+ u16 num_rxq_sets;
+@@ -846,6 +983,7 @@ struct idpf_rxq_group {
+ * @vport: Vport back pointer
+ * @num_txq: Number of TX queues associated
+ * @txqs: Array of TX queue pointers
++ * @stashes: array of OOO stashes for the queues
+ * @complq: Associated completion queue pointer, split queue only
+ * @num_completions_pending: Total number of completions pending for the
+ * completion queue, acculumated for all TX queues
+@@ -859,9 +997,10 @@ struct idpf_txq_group {
+ struct idpf_vport *vport;
+
+ u16 num_txq;
+- struct idpf_queue *txqs[IDPF_LARGE_MAX_Q];
++ struct idpf_tx_queue *txqs[IDPF_LARGE_MAX_Q];
++ struct idpf_txq_stash *stashes;
+
+- struct idpf_queue *complq;
++ struct idpf_compl_queue *complq;
+
+ u32 num_completions_pending;
+ };
+@@ -998,29 +1137,31 @@ void idpf_deinit_rss(struct idpf_vport *vport);
+ int idpf_rx_bufs_init_all(struct idpf_vport *vport);
+ void idpf_rx_add_frag(struct idpf_rx_buf *rx_buf, struct sk_buff *skb,
+ unsigned int size);
+-struct sk_buff *idpf_rx_construct_skb(struct idpf_queue *rxq,
++struct sk_buff *idpf_rx_construct_skb(const struct idpf_rx_queue *rxq,
+ struct idpf_rx_buf *rx_buf,
+ unsigned int size);
+-bool idpf_init_rx_buf_hw_alloc(struct idpf_queue *rxq, struct idpf_rx_buf *buf);
+-void idpf_rx_buf_hw_update(struct idpf_queue *rxq, u32 val);
+-void idpf_tx_buf_hw_update(struct idpf_queue *tx_q, u32 val,
++void idpf_tx_buf_hw_update(struct idpf_tx_queue *tx_q, u32 val,
+ bool xmit_more);
+ unsigned int idpf_size_to_txd_count(unsigned int size);
+-netdev_tx_t idpf_tx_drop_skb(struct idpf_queue *tx_q, struct sk_buff *skb);
+-void idpf_tx_dma_map_error(struct idpf_queue *txq, struct sk_buff *skb,
++netdev_tx_t idpf_tx_drop_skb(struct idpf_tx_queue *tx_q, struct sk_buff *skb);
++void idpf_tx_dma_map_error(struct idpf_tx_queue *txq, struct sk_buff *skb,
+ struct idpf_tx_buf *first, u16 ring_idx);
+-unsigned int idpf_tx_desc_count_required(struct idpf_queue *txq,
++unsigned int idpf_tx_desc_count_required(struct idpf_tx_queue *txq,
+ struct sk_buff *skb);
+-bool idpf_chk_linearize(struct sk_buff *skb, unsigned int max_bufs,
+- unsigned int count);
+-int idpf_tx_maybe_stop_common(struct idpf_queue *tx_q, unsigned int size);
+ void idpf_tx_timeout(struct net_device *netdev, unsigned int txqueue);
+-netdev_tx_t idpf_tx_splitq_start(struct sk_buff *skb,
+- struct net_device *netdev);
+-netdev_tx_t idpf_tx_singleq_start(struct sk_buff *skb,
+- struct net_device *netdev);
+-bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_queue *rxq,
++netdev_tx_t idpf_tx_singleq_frame(struct sk_buff *skb,
++ struct idpf_tx_queue *tx_q);
++netdev_tx_t idpf_tx_start(struct sk_buff *skb, struct net_device *netdev);
++bool idpf_rx_singleq_buf_hw_alloc_all(struct idpf_rx_queue *rxq,
+ u16 cleaned_count);
+ int idpf_tso(struct sk_buff *skb, struct idpf_tx_offload_params *off);
+
++static inline bool idpf_tx_maybe_stop_common(struct idpf_tx_queue *tx_q,
++ u32 needed)
++{
++ return !netif_subqueue_maybe_stop(tx_q->netdev, tx_q->idx,
++ IDPF_DESC_UNUSED(tx_q),
++ needed, needed);
++}
++
+ #endif /* !_IDPF_TXRX_H_ */
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+index a5f9b7a5effe7b..44602b87cd4114 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
++++ b/drivers/net/ethernet/intel/idpf/idpf_virtchnl.c
+@@ -750,7 +750,7 @@ static int idpf_wait_for_marker_event(struct idpf_vport *vport)
+ int i;
+
+ for (i = 0; i < vport->num_txq; i++)
+- set_bit(__IDPF_Q_SW_MARKER, vport->txqs[i]->flags);
++ idpf_queue_set(SW_MARKER, vport->txqs[i]);
+
+ event = wait_event_timeout(vport->sw_marker_wq,
+ test_and_clear_bit(IDPF_VPORT_SW_MARKER,
+@@ -758,7 +758,7 @@ static int idpf_wait_for_marker_event(struct idpf_vport *vport)
+ msecs_to_jiffies(500));
+
+ for (i = 0; i < vport->num_txq; i++)
+- clear_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags);
++ idpf_queue_clear(POLL_MODE, vport->txqs[i]);
+
+ if (event)
+ return 0;
+@@ -1092,7 +1092,6 @@ static int __idpf_queue_reg_init(struct idpf_vport *vport, u32 *reg_vals,
+ int num_regs, u32 q_type)
+ {
+ struct idpf_adapter *adapter = vport->adapter;
+- struct idpf_queue *q;
+ int i, j, k = 0;
+
+ switch (q_type) {
+@@ -1111,6 +1110,8 @@ static int __idpf_queue_reg_init(struct idpf_vport *vport, u32 *reg_vals,
+ u16 num_rxq = rx_qgrp->singleq.num_rxq;
+
+ for (j = 0; j < num_rxq && k < num_regs; j++, k++) {
++ struct idpf_rx_queue *q;
++
+ q = rx_qgrp->singleq.rxqs[j];
+ q->tail = idpf_get_reg_addr(adapter,
+ reg_vals[k]);
+@@ -1123,6 +1124,8 @@ static int __idpf_queue_reg_init(struct idpf_vport *vport, u32 *reg_vals,
+ u8 num_bufqs = vport->num_bufqs_per_qgrp;
+
+ for (j = 0; j < num_bufqs && k < num_regs; j++, k++) {
++ struct idpf_buf_queue *q;
++
+ q = &rx_qgrp->splitq.bufq_sets[j].bufq;
+ q->tail = idpf_get_reg_addr(adapter,
+ reg_vals[k]);
+@@ -1449,19 +1452,19 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport)
+ qi[k].model =
+ cpu_to_le16(vport->txq_model);
+ qi[k].type =
+- cpu_to_le32(tx_qgrp->txqs[j]->q_type);
++ cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX);
+ qi[k].ring_len =
+ cpu_to_le16(tx_qgrp->txqs[j]->desc_count);
+ qi[k].dma_ring_addr =
+ cpu_to_le64(tx_qgrp->txqs[j]->dma);
+ if (idpf_is_queue_model_split(vport->txq_model)) {
+- struct idpf_queue *q = tx_qgrp->txqs[j];
++ struct idpf_tx_queue *q = tx_qgrp->txqs[j];
+
+ qi[k].tx_compl_queue_id =
+ cpu_to_le16(tx_qgrp->complq->q_id);
+ qi[k].relative_queue_id = cpu_to_le16(j);
+
+- if (test_bit(__IDPF_Q_FLOW_SCH_EN, q->flags))
++ if (idpf_queue_has(FLOW_SCH_EN, q))
+ qi[k].sched_mode =
+ cpu_to_le16(VIRTCHNL2_TXQ_SCHED_MODE_FLOW);
+ else
+@@ -1478,11 +1481,11 @@ static int idpf_send_config_tx_queues_msg(struct idpf_vport *vport)
+
+ qi[k].queue_id = cpu_to_le32(tx_qgrp->complq->q_id);
+ qi[k].model = cpu_to_le16(vport->txq_model);
+- qi[k].type = cpu_to_le32(tx_qgrp->complq->q_type);
++ qi[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION);
+ qi[k].ring_len = cpu_to_le16(tx_qgrp->complq->desc_count);
+ qi[k].dma_ring_addr = cpu_to_le64(tx_qgrp->complq->dma);
+
+- if (test_bit(__IDPF_Q_FLOW_SCH_EN, tx_qgrp->complq->flags))
++ if (idpf_queue_has(FLOW_SCH_EN, tx_qgrp->complq))
+ sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_FLOW;
+ else
+ sched_mode = VIRTCHNL2_TXQ_SCHED_MODE_QUEUE;
+@@ -1567,17 +1570,18 @@ static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport)
+ goto setup_rxqs;
+
+ for (j = 0; j < vport->num_bufqs_per_qgrp; j++, k++) {
+- struct idpf_queue *bufq =
++ struct idpf_buf_queue *bufq =
+ &rx_qgrp->splitq.bufq_sets[j].bufq;
+
+ qi[k].queue_id = cpu_to_le32(bufq->q_id);
+ qi[k].model = cpu_to_le16(vport->rxq_model);
+- qi[k].type = cpu_to_le32(bufq->q_type);
++ qi[k].type =
++ cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX_BUFFER);
+ qi[k].desc_ids = cpu_to_le64(VIRTCHNL2_RXDID_2_FLEX_SPLITQ_M);
+ qi[k].ring_len = cpu_to_le16(bufq->desc_count);
+ qi[k].dma_ring_addr = cpu_to_le64(bufq->dma);
+ qi[k].data_buffer_size = cpu_to_le32(bufq->rx_buf_size);
+- qi[k].buffer_notif_stride = bufq->rx_buf_stride;
++ qi[k].buffer_notif_stride = IDPF_RX_BUF_STRIDE;
+ qi[k].rx_buffer_low_watermark =
+ cpu_to_le16(bufq->rx_buffer_low_watermark);
+ if (idpf_is_feature_ena(vport, NETIF_F_GRO_HW))
+@@ -1591,7 +1595,7 @@ static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport)
+ num_rxq = rx_qgrp->singleq.num_rxq;
+
+ for (j = 0; j < num_rxq; j++, k++) {
+- struct idpf_queue *rxq;
++ struct idpf_rx_queue *rxq;
+
+ if (!idpf_is_queue_model_split(vport->rxq_model)) {
+ rxq = rx_qgrp->singleq.rxqs[j];
+@@ -1599,11 +1603,11 @@ static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport)
+ }
+ rxq = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+ qi[k].rx_bufq1_id =
+- cpu_to_le16(rxq->rxq_grp->splitq.bufq_sets[0].bufq.q_id);
++ cpu_to_le16(rxq->bufq_sets[0].bufq.q_id);
+ if (vport->num_bufqs_per_qgrp > IDPF_SINGLE_BUFQ_PER_RXQ_GRP) {
+ qi[k].bufq2_ena = IDPF_BUFQ2_ENA;
+ qi[k].rx_bufq2_id =
+- cpu_to_le16(rxq->rxq_grp->splitq.bufq_sets[1].bufq.q_id);
++ cpu_to_le16(rxq->bufq_sets[1].bufq.q_id);
+ }
+ qi[k].rx_buffer_low_watermark =
+ cpu_to_le16(rxq->rx_buffer_low_watermark);
+@@ -1611,7 +1615,7 @@ static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport)
+ qi[k].qflags |= cpu_to_le16(VIRTCHNL2_RXQ_RSC);
+
+ common_qi_fields:
+- if (rxq->rx_hsplit_en) {
++ if (idpf_queue_has(HSPLIT_EN, rxq)) {
+ qi[k].qflags |=
+ cpu_to_le16(VIRTCHNL2_RXQ_HDR_SPLIT);
+ qi[k].hdr_buffer_size =
+@@ -1619,7 +1623,7 @@ static int idpf_send_config_rx_queues_msg(struct idpf_vport *vport)
+ }
+ qi[k].queue_id = cpu_to_le32(rxq->q_id);
+ qi[k].model = cpu_to_le16(vport->rxq_model);
+- qi[k].type = cpu_to_le32(rxq->q_type);
++ qi[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
+ qi[k].ring_len = cpu_to_le16(rxq->desc_count);
+ qi[k].dma_ring_addr = cpu_to_le64(rxq->dma);
+ qi[k].max_pkt_size = cpu_to_le32(rxq->rx_max_pkt_size);
+@@ -1706,7 +1710,7 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena)
+ struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+
+ for (j = 0; j < tx_qgrp->num_txq; j++, k++) {
+- qc[k].type = cpu_to_le32(tx_qgrp->txqs[j]->q_type);
++ qc[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX);
+ qc[k].start_queue_id = cpu_to_le32(tx_qgrp->txqs[j]->q_id);
+ qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
+ }
+@@ -1720,7 +1724,7 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena)
+ for (i = 0; i < vport->num_txq_grp; i++, k++) {
+ struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+
+- qc[k].type = cpu_to_le32(tx_qgrp->complq->q_type);
++ qc[k].type = cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION);
+ qc[k].start_queue_id = cpu_to_le32(tx_qgrp->complq->q_id);
+ qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
+ }
+@@ -1741,12 +1745,12 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena)
+ qc[k].start_queue_id =
+ cpu_to_le32(rx_qgrp->splitq.rxq_sets[j]->rxq.q_id);
+ qc[k].type =
+- cpu_to_le32(rx_qgrp->splitq.rxq_sets[j]->rxq.q_type);
++ cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
+ } else {
+ qc[k].start_queue_id =
+ cpu_to_le32(rx_qgrp->singleq.rxqs[j]->q_id);
+ qc[k].type =
+- cpu_to_le32(rx_qgrp->singleq.rxqs[j]->q_type);
++ cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
+ }
+ qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
+ }
+@@ -1761,10 +1765,11 @@ static int idpf_send_ena_dis_queues_msg(struct idpf_vport *vport, bool ena)
+ struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+
+ for (j = 0; j < vport->num_bufqs_per_qgrp; j++, k++) {
+- struct idpf_queue *q;
++ const struct idpf_buf_queue *q;
+
+ q = &rx_qgrp->splitq.bufq_sets[j].bufq;
+- qc[k].type = cpu_to_le32(q->q_type);
++ qc[k].type =
++ cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX_BUFFER);
+ qc[k].start_queue_id = cpu_to_le32(q->q_id);
+ qc[k].num_queues = cpu_to_le32(IDPF_NUMQ_PER_CHUNK);
+ }
+@@ -1849,7 +1854,8 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map)
+ struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+
+ for (j = 0; j < tx_qgrp->num_txq; j++, k++) {
+- vqv[k].queue_type = cpu_to_le32(tx_qgrp->txqs[j]->q_type);
++ vqv[k].queue_type =
++ cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_TX);
+ vqv[k].queue_id = cpu_to_le32(tx_qgrp->txqs[j]->q_id);
+
+ if (idpf_is_queue_model_split(vport->txq_model)) {
+@@ -1879,14 +1885,15 @@ int idpf_send_map_unmap_queue_vector_msg(struct idpf_vport *vport, bool map)
+ num_rxq = rx_qgrp->singleq.num_rxq;
+
+ for (j = 0; j < num_rxq; j++, k++) {
+- struct idpf_queue *rxq;
++ struct idpf_rx_queue *rxq;
+
+ if (idpf_is_queue_model_split(vport->rxq_model))
+ rxq = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+ else
+ rxq = rx_qgrp->singleq.rxqs[j];
+
+- vqv[k].queue_type = cpu_to_le32(rxq->q_type);
++ vqv[k].queue_type =
++ cpu_to_le32(VIRTCHNL2_QUEUE_TYPE_RX);
+ vqv[k].queue_id = cpu_to_le32(rxq->q_id);
+ vqv[k].vector_id = cpu_to_le16(rxq->q_vector->v_idx);
+ vqv[k].itr_idx = cpu_to_le32(rxq->q_vector->rx_itr_idx);
+@@ -1975,7 +1982,7 @@ int idpf_send_disable_queues_msg(struct idpf_vport *vport)
+ * queues virtchnl message is sent
+ */
+ for (i = 0; i < vport->num_txq; i++)
+- set_bit(__IDPF_Q_POLL_MODE, vport->txqs[i]->flags);
++ idpf_queue_set(POLL_MODE, vport->txqs[i]);
+
+ /* schedule the napi to receive all the marker packets */
+ local_bh_disable();
+@@ -3242,7 +3249,6 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport,
+ int num_qids,
+ u32 q_type)
+ {
+- struct idpf_queue *q;
+ int i, j, k = 0;
+
+ switch (q_type) {
+@@ -3250,11 +3256,8 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport,
+ for (i = 0; i < vport->num_txq_grp; i++) {
+ struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+
+- for (j = 0; j < tx_qgrp->num_txq && k < num_qids; j++, k++) {
++ for (j = 0; j < tx_qgrp->num_txq && k < num_qids; j++, k++)
+ tx_qgrp->txqs[j]->q_id = qids[k];
+- tx_qgrp->txqs[j]->q_type =
+- VIRTCHNL2_QUEUE_TYPE_TX;
+- }
+ }
+ break;
+ case VIRTCHNL2_QUEUE_TYPE_RX:
+@@ -3268,12 +3271,13 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport,
+ num_rxq = rx_qgrp->singleq.num_rxq;
+
+ for (j = 0; j < num_rxq && k < num_qids; j++, k++) {
++ struct idpf_rx_queue *q;
++
+ if (idpf_is_queue_model_split(vport->rxq_model))
+ q = &rx_qgrp->splitq.rxq_sets[j]->rxq;
+ else
+ q = rx_qgrp->singleq.rxqs[j];
+ q->q_id = qids[k];
+- q->q_type = VIRTCHNL2_QUEUE_TYPE_RX;
+ }
+ }
+ break;
+@@ -3282,8 +3286,6 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport,
+ struct idpf_txq_group *tx_qgrp = &vport->txq_grps[i];
+
+ tx_qgrp->complq->q_id = qids[k];
+- tx_qgrp->complq->q_type =
+- VIRTCHNL2_QUEUE_TYPE_TX_COMPLETION;
+ }
+ break;
+ case VIRTCHNL2_QUEUE_TYPE_RX_BUFFER:
+@@ -3292,9 +3294,10 @@ static int __idpf_vport_queue_ids_init(struct idpf_vport *vport,
+ u8 num_bufqs = vport->num_bufqs_per_qgrp;
+
+ for (j = 0; j < num_bufqs && k < num_qids; j++, k++) {
++ struct idpf_buf_queue *q;
++
+ q = &rx_qgrp->splitq.bufq_sets[j].bufq;
+ q->q_id = qids[k];
+- q->q_type = VIRTCHNL2_QUEUE_TYPE_RX_BUFFER;
+ }
+ }
+ break;
+diff --git a/drivers/net/ethernet/realtek/r8169_phy_config.c b/drivers/net/ethernet/realtek/r8169_phy_config.c
+index 1f74317beb8878..e1e5d9672ae44b 100644
+--- a/drivers/net/ethernet/realtek/r8169_phy_config.c
++++ b/drivers/net/ethernet/realtek/r8169_phy_config.c
+@@ -1060,6 +1060,7 @@ static void rtl8125a_2_hw_phy_config(struct rtl8169_private *tp,
+ phy_modify_paged(phydev, 0xa86, 0x15, 0x0001, 0x0000);
+ rtl8168g_enable_gphy_10m(phydev);
+
++ rtl8168g_disable_aldps(phydev);
+ rtl8125a_config_eee_phy(phydev);
+ }
+
+@@ -1099,6 +1100,7 @@ static void rtl8125b_hw_phy_config(struct rtl8169_private *tp,
+ phy_modify_paged(phydev, 0xbf8, 0x12, 0xe000, 0xa000);
+
+ rtl8125_legacy_force_mode(phydev);
++ rtl8168g_disable_aldps(phydev);
+ rtl8125b_config_eee_phy(phydev);
+ }
+
+diff --git a/drivers/net/ethernet/renesas/ravb_main.c b/drivers/net/ethernet/renesas/ravb_main.c
+index 4d100283c30fb4..067357b2495cdc 100644
+--- a/drivers/net/ethernet/renesas/ravb_main.c
++++ b/drivers/net/ethernet/renesas/ravb_main.c
+@@ -530,8 +530,16 @@ static void ravb_emac_init_gbeth(struct net_device *ndev)
+
+ static void ravb_emac_init_rcar(struct net_device *ndev)
+ {
+- /* Receive frame limit set register */
+- ravb_write(ndev, ndev->mtu + ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN, RFLR);
++ struct ravb_private *priv = netdev_priv(ndev);
++
++ /* Set receive frame length
++ *
++ * The length set here describes the frame from the destination address
++ * up to and including the CRC data. However only the frame data,
++ * excluding the CRC, are transferred to memory. To allow for the
++ * largest frames add the CRC length to the maximum Rx descriptor size.
++ */
++ ravb_write(ndev, priv->info->rx_max_frame_size + ETH_FCS_LEN, RFLR);
+
+ /* EMAC Mode: PAUSE prohibition; Duplex; RX Checksum; TX; RX */
+ ravb_write(ndev, ECMR_ZPF | ECMR_DM |
+diff --git a/drivers/net/ethernet/seeq/ether3.c b/drivers/net/ethernet/seeq/ether3.c
+index c672f92d65e976..9319a2675e7b65 100644
+--- a/drivers/net/ethernet/seeq/ether3.c
++++ b/drivers/net/ethernet/seeq/ether3.c
+@@ -847,9 +847,11 @@ static void ether3_remove(struct expansion_card *ec)
+ {
+ struct net_device *dev = ecard_get_drvdata(ec);
+
++ ether3_outw(priv(dev)->regs.config2 |= CFG2_CTRLO, REG_CONFIG2);
+ ecard_set_drvdata(ec, NULL);
+
+ unregister_netdev(dev);
++ del_timer_sync(&priv(dev)->timer);
+ free_netdev(dev);
+ ecard_release_resources(ec);
+ }
+diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+index 9e40c28d453ab1..ee3604f58def52 100644
+--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
++++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-loongson.c
+@@ -35,6 +35,9 @@ static int loongson_default_data(struct plat_stmmacenet_data *plat)
+ /* Disable RX queues routing by default */
+ plat->rx_queues_cfg[0].pkt_route = 0x0;
+
++ plat->clk_ref_rate = 125000000;
++ plat->clk_ptp_rate = 125000000;
++
+ /* Default to phy auto-detection */
+ plat->phy_addr = -1;
+
+diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+index 33e2bd5a351cad..3b1bb6aa5b8c8c 100644
+--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+@@ -2025,7 +2025,7 @@ static int __alloc_dma_rx_desc_resources(struct stmmac_priv *priv,
+ rx_q->queue_index = queue;
+ rx_q->priv_data = priv;
+
+- pp_params.flags = PP_FLAG_DMA_MAP | PP_FLAG_DMA_SYNC_DEV;
++ pp_params.flags = PP_FLAG_DMA_MAP | (xdp_prog ? PP_FLAG_DMA_SYNC_DEV : 0);
+ pp_params.pool_size = dma_conf->dma_rx_size;
+ num_pages = DIV_ROUND_UP(dma_conf->dma_buf_sz, PAGE_SIZE);
+ pp_params.order = ilog2(num_pages);
+diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+index 88d7bc2ea71326..f1d928644b8242 100644
+--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
++++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+@@ -674,15 +674,15 @@ static int axienet_device_reset(struct net_device *ndev)
+ *
+ * Would either be called after a successful transmit operation, or after
+ * there was an error when setting up the chain.
+- * Returns the number of descriptors handled.
++ * Returns the number of packets handled.
+ */
+ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
+ int nr_bds, bool force, u32 *sizep, int budget)
+ {
+ struct axidma_bd *cur_p;
+ unsigned int status;
++ int i, packets = 0;
+ dma_addr_t phys;
+- int i;
+
+ for (i = 0; i < nr_bds; i++) {
+ cur_p = &lp->tx_bd_v[(first_bd + i) % lp->tx_bd_num];
+@@ -701,8 +701,10 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
+ (cur_p->cntrl & XAXIDMA_BD_CTRL_LENGTH_MASK),
+ DMA_TO_DEVICE);
+
+- if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK))
++ if (cur_p->skb && (status & XAXIDMA_BD_STS_COMPLETE_MASK)) {
+ napi_consume_skb(cur_p->skb, budget);
++ packets++;
++ }
+
+ cur_p->app0 = 0;
+ cur_p->app1 = 0;
+@@ -718,7 +720,13 @@ static int axienet_free_tx_chain(struct axienet_local *lp, u32 first_bd,
+ *sizep += status & XAXIDMA_BD_STS_ACTUAL_LEN_MASK;
+ }
+
+- return i;
++ if (!force) {
++ lp->tx_bd_ci += i;
++ if (lp->tx_bd_ci >= lp->tx_bd_num)
++ lp->tx_bd_ci %= lp->tx_bd_num;
++ }
++
++ return packets;
+ }
+
+ /**
+@@ -891,13 +899,10 @@ static int axienet_tx_poll(struct napi_struct *napi, int budget)
+ u32 size = 0;
+ int packets;
+
+- packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, budget, false, &size, budget);
++ packets = axienet_free_tx_chain(lp, lp->tx_bd_ci, lp->tx_bd_num, false,
++ &size, budget);
+
+ if (packets) {
+- lp->tx_bd_ci += packets;
+- if (lp->tx_bd_ci >= lp->tx_bd_num)
+- lp->tx_bd_ci %= lp->tx_bd_num;
+-
+ u64_stats_update_begin(&lp->tx_stat_sync);
+ u64_stats_add(&lp->tx_packets, packets);
+ u64_stats_add(&lp->tx_bytes, size);
+@@ -1222,9 +1227,10 @@ static irqreturn_t axienet_tx_irq(int irq, void *_ndev)
+ u32 cr = lp->tx_dma_cr;
+
+ cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
+- axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
+-
+- napi_schedule(&lp->napi_tx);
++ if (napi_schedule_prep(&lp->napi_tx)) {
++ axienet_dma_out32(lp, XAXIDMA_TX_CR_OFFSET, cr);
++ __napi_schedule(&lp->napi_tx);
++ }
+ }
+
+ return IRQ_HANDLED;
+@@ -1266,9 +1272,10 @@ static irqreturn_t axienet_rx_irq(int irq, void *_ndev)
+ u32 cr = lp->rx_dma_cr;
+
+ cr &= ~(XAXIDMA_IRQ_IOC_MASK | XAXIDMA_IRQ_DELAY_MASK);
+- axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
+-
+- napi_schedule(&lp->napi_rx);
++ if (napi_schedule_prep(&lp->napi_rx)) {
++ axienet_dma_out32(lp, XAXIDMA_RX_CR_OFFSET, cr);
++ __napi_schedule(&lp->napi_rx);
++ }
+ }
+
+ return IRQ_HANDLED;
+diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
+index 18eb5ba436df69..2506aa8c603ec0 100644
+--- a/drivers/net/usb/usbnet.c
++++ b/drivers/net/usb/usbnet.c
+@@ -464,10 +464,15 @@ static enum skb_state defer_bh(struct usbnet *dev, struct sk_buff *skb,
+ void usbnet_defer_kevent (struct usbnet *dev, int work)
+ {
+ set_bit (work, &dev->flags);
+- if (!schedule_work (&dev->kevent))
+- netdev_dbg(dev->net, "kevent %s may have been dropped\n", usbnet_event_names[work]);
+- else
+- netdev_dbg(dev->net, "kevent %s scheduled\n", usbnet_event_names[work]);
++ if (!usbnet_going_away(dev)) {
++ if (!schedule_work(&dev->kevent))
++ netdev_dbg(dev->net,
++ "kevent %s may have been dropped\n",
++ usbnet_event_names[work]);
++ else
++ netdev_dbg(dev->net,
++ "kevent %s scheduled\n", usbnet_event_names[work]);
++ }
+ }
+ EXPORT_SYMBOL_GPL(usbnet_defer_kevent);
+
+@@ -535,7 +540,8 @@ static int rx_submit (struct usbnet *dev, struct urb *urb, gfp_t flags)
+ tasklet_schedule (&dev->bh);
+ break;
+ case 0:
+- __usbnet_queue_skb(&dev->rxq, skb, rx_start);
++ if (!usbnet_going_away(dev))
++ __usbnet_queue_skb(&dev->rxq, skb, rx_start);
+ }
+ } else {
+ netif_dbg(dev, ifdown, dev->net, "rx: stopped\n");
+@@ -843,9 +849,18 @@ int usbnet_stop (struct net_device *net)
+
+ /* deferred work (timer, softirq, task) must also stop */
+ dev->flags = 0;
+- del_timer_sync (&dev->delay);
+- tasklet_kill (&dev->bh);
++ del_timer_sync(&dev->delay);
++ tasklet_kill(&dev->bh);
+ cancel_work_sync(&dev->kevent);
++
++ /* We have cyclic dependencies. Those calls are needed
++ * to break a cycle. We cannot fall into the gaps because
++ * we have a flag
++ */
++ tasklet_kill(&dev->bh);
++ del_timer_sync(&dev->delay);
++ cancel_work_sync(&dev->kevent);
++
+ if (!pm)
+ usb_autopm_put_interface(dev->intf);
+
+@@ -1171,7 +1186,8 @@ usbnet_deferred_kevent (struct work_struct *work)
+ status);
+ } else {
+ clear_bit (EVENT_RX_HALT, &dev->flags);
+- tasklet_schedule (&dev->bh);
++ if (!usbnet_going_away(dev))
++ tasklet_schedule(&dev->bh);
+ }
+ }
+
+@@ -1196,7 +1212,8 @@ usbnet_deferred_kevent (struct work_struct *work)
+ usb_autopm_put_interface(dev->intf);
+ fail_lowmem:
+ if (resched)
+- tasklet_schedule (&dev->bh);
++ if (!usbnet_going_away(dev))
++ tasklet_schedule(&dev->bh);
+ }
+ }
+
+@@ -1559,6 +1576,7 @@ static void usbnet_bh (struct timer_list *t)
+ } else if (netif_running (dev->net) &&
+ netif_device_present (dev->net) &&
+ netif_carrier_ok(dev->net) &&
++ !usbnet_going_away(dev) &&
+ !timer_pending(&dev->delay) &&
+ !test_bit(EVENT_RX_PAUSED, &dev->flags) &&
+ !test_bit(EVENT_RX_HALT, &dev->flags)) {
+@@ -1606,6 +1624,7 @@ void usbnet_disconnect (struct usb_interface *intf)
+ usb_set_intfdata(intf, NULL);
+ if (!dev)
+ return;
++ usbnet_mark_going_away(dev);
+
+ xdev = interface_to_usbdev (intf);
+
+diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
+index 21bd0c127b05ab..0b1630bb173a5e 100644
+--- a/drivers/net/virtio_net.c
++++ b/drivers/net/virtio_net.c
+@@ -1439,6 +1439,11 @@ static struct sk_buff *receive_small(struct net_device *dev,
+ struct page *page = virt_to_head_page(buf);
+ struct sk_buff *skb;
+
++ /* We passed the address of virtnet header to virtio-core,
++ * so truncate the padding.
++ */
++ buf -= VIRTNET_RX_PAD + xdp_headroom;
++
+ len -= vi->hdr_len;
+ u64_stats_add(&stats->bytes, len);
+
+@@ -2029,8 +2034,9 @@ static int add_recvbuf_small(struct virtnet_info *vi, struct receive_queue *rq,
+ if (unlikely(!buf))
+ return -ENOMEM;
+
+- virtnet_rq_init_one_sg(rq, buf + VIRTNET_RX_PAD + xdp_headroom,
+- vi->hdr_len + GOOD_PACKET_LEN);
++ buf += VIRTNET_RX_PAD + xdp_headroom;
++
++ virtnet_rq_init_one_sg(rq, buf, vi->hdr_len + GOOD_PACKET_LEN);
+
+ err = virtqueue_add_inbuf_ctx(rq->vq, rq->sg, 1, buf, ctx, gfp);
+ if (err < 0) {
+diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
+index 141ba4487cb421..9d2d3a86abf172 100644
+--- a/drivers/net/wireless/ath/ath11k/core.h
++++ b/drivers/net/wireless/ath/ath11k/core.h
+@@ -396,6 +396,7 @@ struct ath11k_vif {
+ u8 bssid[ETH_ALEN];
+ struct cfg80211_bitrate_mask bitrate_mask;
+ struct delayed_work connection_loss_work;
++ struct work_struct bcn_tx_work;
+ int num_legacy_stations;
+ int rtscts_prot_mode;
+ int txpower;
+diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
+index eaa53bc39ab2c0..74719cb78888b1 100644
+--- a/drivers/net/wireless/ath/ath11k/mac.c
++++ b/drivers/net/wireless/ath/ath11k/mac.c
+@@ -6599,6 +6599,16 @@ static int ath11k_mac_vdev_delete(struct ath11k *ar, struct ath11k_vif *arvif)
+ return ret;
+ }
+
++static void ath11k_mac_bcn_tx_work(struct work_struct *work)
++{
++ struct ath11k_vif *arvif = container_of(work, struct ath11k_vif,
++ bcn_tx_work);
++
++ mutex_lock(&arvif->ar->conf_mutex);
++ ath11k_mac_bcn_tx_event(arvif);
++ mutex_unlock(&arvif->ar->conf_mutex);
++}
++
+ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
+ struct ieee80211_vif *vif)
+ {
+@@ -6637,6 +6647,7 @@ static int ath11k_mac_op_add_interface(struct ieee80211_hw *hw,
+ arvif->vif = vif;
+
+ INIT_LIST_HEAD(&arvif->list);
++ INIT_WORK(&arvif->bcn_tx_work, ath11k_mac_bcn_tx_work);
+ INIT_DELAYED_WORK(&arvif->connection_loss_work,
+ ath11k_mac_vif_sta_connection_loss_work);
+
+@@ -6879,6 +6890,7 @@ static void ath11k_mac_op_remove_interface(struct ieee80211_hw *hw,
+ int i;
+
+ cancel_delayed_work_sync(&arvif->connection_loss_work);
++ cancel_work_sync(&arvif->bcn_tx_work);
+
+ mutex_lock(&ar->conf_mutex);
+
+diff --git a/drivers/net/wireless/ath/ath11k/wmi.c b/drivers/net/wireless/ath/ath11k/wmi.c
+index 6ff01c45f16591..f50a4c0d4b2bac 100644
+--- a/drivers/net/wireless/ath/ath11k/wmi.c
++++ b/drivers/net/wireless/ath/ath11k/wmi.c
+@@ -7404,7 +7404,9 @@ static void ath11k_bcn_tx_status_event(struct ath11k_base *ab, struct sk_buff *s
+ rcu_read_unlock();
+ return;
+ }
+- ath11k_mac_bcn_tx_event(arvif);
++
++ queue_work(ab->workqueue, &arvif->bcn_tx_work);
++
+ rcu_read_unlock();
+ }
+
+diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
+index 7037004ce97713..818ee74cf7a055 100644
+--- a/drivers/net/wireless/ath/ath12k/mac.c
++++ b/drivers/net/wireless/ath/ath12k/mac.c
+@@ -1948,9 +1948,8 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar,
+ * request, then use MAX_AMPDU_LEN_FACTOR as 16 to calculate max_ampdu
+ * length.
+ */
+- ampdu_factor = (he_cap->he_cap_elem.mac_cap_info[3] &
+- IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK) >>
+- IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK;
++ ampdu_factor = u8_get_bits(he_cap->he_cap_elem.mac_cap_info[3],
++ IEEE80211_HE_MAC_CAP3_MAX_AMPDU_LEN_EXP_MASK);
+
+ if (ampdu_factor) {
+ if (sta->deflink.vht_cap.vht_supported)
+diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
+index ef775af25093c4..55230dd00d0c7b 100644
+--- a/drivers/net/wireless/ath/ath12k/wmi.c
++++ b/drivers/net/wireless/ath/ath12k/wmi.c
+@@ -1528,6 +1528,7 @@ int ath12k_wmi_pdev_bss_chan_info_request(struct ath12k *ar,
+ cmd->tlv_header = ath12k_wmi_tlv_cmd_hdr(WMI_TAG_PDEV_BSS_CHAN_INFO_REQUEST,
+ sizeof(*cmd));
+ cmd->req_type = cpu_to_le32(type);
++ cmd->pdev_id = cpu_to_le32(ar->pdev->pdev_id);
+
+ ath12k_dbg(ar->ab, ATH12K_DBG_WMI,
+ "WMI bss chan info req type %d\n", type);
+diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
+index 742fe0b36cf20a..e947d646353c38 100644
+--- a/drivers/net/wireless/ath/ath12k/wmi.h
++++ b/drivers/net/wireless/ath/ath12k/wmi.h
+@@ -3104,6 +3104,7 @@ struct wmi_pdev_bss_chan_info_req_cmd {
+ __le32 tlv_header;
+ /* ref wmi_bss_chan_info_req_type */
+ __le32 req_type;
++ __le32 pdev_id;
+ } __packed;
+
+ struct wmi_ap_ps_peer_cmd {
+@@ -4053,7 +4054,6 @@ struct wmi_vdev_stopped_event {
+ } __packed;
+
+ struct wmi_pdev_bss_chan_info_event {
+- __le32 pdev_id;
+ __le32 freq; /* Units in MHz */
+ __le32 noise_floor; /* units are dBm */
+ /* rx clear - how often the channel was unused */
+@@ -4071,6 +4071,7 @@ struct wmi_pdev_bss_chan_info_event {
+ /*rx_cycle cnt for my bss in 64bits format */
+ __le32 rx_bss_cycle_count_low;
+ __le32 rx_bss_cycle_count_high;
++ __le32 pdev_id;
+ } __packed;
+
+ #define WMI_VDEV_INSTALL_KEY_COMPL_STATUS_SUCCESS 0
+diff --git a/drivers/net/wireless/ath/ath9k/debug.c b/drivers/net/wireless/ath/ath9k/debug.c
+index d84e3ee7b5d902..bf3da631c69fda 100644
+--- a/drivers/net/wireless/ath/ath9k/debug.c
++++ b/drivers/net/wireless/ath/ath9k/debug.c
+@@ -1380,8 +1380,6 @@ int ath9k_init_debug(struct ath_hw *ah)
+
+ sc->debug.debugfs_phy = debugfs_create_dir("ath9k",
+ sc->hw->wiphy->debugfsdir);
+- if (IS_ERR(sc->debug.debugfs_phy))
+- return -ENOMEM;
+
+ #ifdef CONFIG_ATH_DEBUG
+ debugfs_create_file("debug", 0600, sc->debug.debugfs_phy,
+diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+index f7c6d9bc931196..9437d69877cc56 100644
+--- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
++++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
+@@ -486,8 +486,6 @@ int ath9k_htc_init_debug(struct ath_hw *ah)
+
+ priv->debug.debugfs_phy = debugfs_create_dir(KBUILD_MODNAME,
+ priv->hw->wiphy->debugfsdir);
+- if (IS_ERR(priv->debug.debugfs_phy))
+- return -ENOMEM;
+
+ ath9k_cmn_spectral_init_debug(&priv->spec_priv, priv->debug.debugfs_phy);
+
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
+index 7ea2631b80692d..00794086cc7c97 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/btcoex.c
+@@ -123,7 +123,7 @@ static s32 brcmf_btcoex_params_read(struct brcmf_if *ifp, u32 addr, u32 *data)
+ {
+ *data = addr;
+
+- return brcmf_fil_iovar_int_get(ifp, "btc_params", data);
++ return brcmf_fil_iovar_int_query(ifp, "btc_params", data);
+ }
+
+ /**
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+index 826b768196e289..ccc069ae5e9d8b 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+@@ -663,8 +663,8 @@ static int brcmf_cfg80211_request_sta_if(struct brcmf_if *ifp, u8 *macaddr)
+ /* interface_create version 3+ */
+ /* get supported version from firmware side */
+ iface_create_ver = 0;
+- err = brcmf_fil_bsscfg_int_get(ifp, "interface_create",
+- &iface_create_ver);
++ err = brcmf_fil_bsscfg_int_query(ifp, "interface_create",
++ &iface_create_ver);
+ if (err) {
+ brcmf_err("fail to get supported version, err=%d\n", err);
+ return -EOPNOTSUPP;
+@@ -756,8 +756,8 @@ static int brcmf_cfg80211_request_ap_if(struct brcmf_if *ifp)
+ /* interface_create version 3+ */
+ /* get supported version from firmware side */
+ iface_create_ver = 0;
+- err = brcmf_fil_bsscfg_int_get(ifp, "interface_create",
+- &iface_create_ver);
++ err = brcmf_fil_bsscfg_int_query(ifp, "interface_create",
++ &iface_create_ver);
+ if (err) {
+ brcmf_err("fail to get supported version, err=%d\n", err);
+ return -EOPNOTSUPP;
+@@ -2101,7 +2101,8 @@ brcmf_set_key_mgmt(struct net_device *ndev, struct cfg80211_connect_params *sme)
+ if (!sme->crypto.n_akm_suites)
+ return 0;
+
+- err = brcmf_fil_bsscfg_int_get(netdev_priv(ndev), "wpa_auth", &val);
++ err = brcmf_fil_bsscfg_int_get(netdev_priv(ndev),
++ "wpa_auth", &val);
+ if (err) {
+ bphy_err(drvr, "could not get wpa_auth (%d)\n", err);
+ return err;
+@@ -2680,7 +2681,7 @@ brcmf_cfg80211_get_tx_power(struct wiphy *wiphy, struct wireless_dev *wdev,
+ struct brcmf_cfg80211_info *cfg = wiphy_to_cfg(wiphy);
+ struct brcmf_cfg80211_vif *vif = wdev_to_vif(wdev);
+ struct brcmf_pub *drvr = cfg->pub;
+- s32 qdbm = 0;
++ s32 qdbm;
+ s32 err;
+
+ brcmf_dbg(TRACE, "Enter\n");
+@@ -3067,7 +3068,7 @@ brcmf_cfg80211_get_station_ibss(struct brcmf_if *ifp,
+ struct brcmf_scb_val_le scbval;
+ struct brcmf_pktcnt_le pktcnt;
+ s32 err;
+- u32 rate = 0;
++ u32 rate;
+ u32 rssi;
+
+ /* Get the current tx rate */
+@@ -7046,8 +7047,8 @@ static int brcmf_construct_chaninfo(struct brcmf_cfg80211_info *cfg,
+ ch.bw = BRCMU_CHAN_BW_20;
+ cfg->d11inf.encchspec(&ch);
+ chaninfo = ch.chspec;
+- err = brcmf_fil_bsscfg_int_get(ifp, "per_chan_info",
+- &chaninfo);
++ err = brcmf_fil_bsscfg_int_query(ifp, "per_chan_info",
++ &chaninfo);
+ if (!err) {
+ if (chaninfo & WL_CHAN_RADAR)
+ channel->flags |=
+@@ -7081,7 +7082,7 @@ static int brcmf_enable_bw40_2g(struct brcmf_cfg80211_info *cfg)
+
+ /* verify support for bw_cap command */
+ val = WLC_BAND_5G;
+- err = brcmf_fil_iovar_int_get(ifp, "bw_cap", &val);
++ err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &val);
+
+ if (!err) {
+ /* only set 2G bandwidth using bw_cap command */
+@@ -7157,11 +7158,11 @@ static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[])
+ int err;
+
+ band = WLC_BAND_2G;
+- err = brcmf_fil_iovar_int_get(ifp, "bw_cap", &band);
++ err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &band);
+ if (!err) {
+ bw_cap[NL80211_BAND_2GHZ] = band;
+ band = WLC_BAND_5G;
+- err = brcmf_fil_iovar_int_get(ifp, "bw_cap", &band);
++ err = brcmf_fil_iovar_int_query(ifp, "bw_cap", &band);
+ if (!err) {
+ bw_cap[NL80211_BAND_5GHZ] = band;
+ return;
+@@ -7170,7 +7171,6 @@ static void brcmf_get_bwcap(struct brcmf_if *ifp, u32 bw_cap[])
+ return;
+ }
+ brcmf_dbg(INFO, "fallback to mimo_bw_cap info\n");
+- mimo_bwcap = 0;
+ err = brcmf_fil_iovar_int_get(ifp, "mimo_bw_cap", &mimo_bwcap);
+ if (err)
+ /* assume 20MHz if firmware does not give a clue */
+@@ -7266,10 +7266,10 @@ static int brcmf_setup_wiphybands(struct brcmf_cfg80211_info *cfg)
+ struct brcmf_pub *drvr = cfg->pub;
+ struct brcmf_if *ifp = brcmf_get_ifp(drvr, 0);
+ struct wiphy *wiphy = cfg_to_wiphy(cfg);
+- u32 nmode = 0;
++ u32 nmode;
+ u32 vhtmode = 0;
+ u32 bw_cap[2] = { WLC_BW_20MHZ_BIT, WLC_BW_20MHZ_BIT };
+- u32 rxchain = 0;
++ u32 rxchain;
+ u32 nchain;
+ int err;
+ s32 i;
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+index bf91b1e1368f03..df53dd1d7e748a 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/core.c
+@@ -691,7 +691,7 @@ static int brcmf_net_mon_open(struct net_device *ndev)
+ {
+ struct brcmf_if *ifp = netdev_priv(ndev);
+ struct brcmf_pub *drvr = ifp->drvr;
+- u32 monitor = 0;
++ u32 monitor;
+ int err;
+
+ brcmf_dbg(TRACE, "Enter\n");
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+index f23310a77a5d11..0d9ae197fa1ec3 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/feature.c
+@@ -184,7 +184,7 @@ static void brcmf_feat_wlc_version_overrides(struct brcmf_pub *drv)
+ static void brcmf_feat_iovar_int_get(struct brcmf_if *ifp,
+ enum brcmf_feat_id id, char *name)
+ {
+- u32 data = 0;
++ u32 data;
+ int err;
+
+ /* we need to know firmware error */
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
+index a315a7fac6a06f..31e080e4da6697 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/fwil.h
+@@ -96,15 +96,22 @@ static inline
+ s32 brcmf_fil_cmd_int_get(struct brcmf_if *ifp, u32 cmd, u32 *data)
+ {
+ s32 err;
+- __le32 data_le = cpu_to_le32(*data);
+
+- err = brcmf_fil_cmd_data_get(ifp, cmd, &data_le, sizeof(data_le));
++ err = brcmf_fil_cmd_data_get(ifp, cmd, data, sizeof(*data));
+ if (err == 0)
+- *data = le32_to_cpu(data_le);
++ *data = le32_to_cpu(*(__le32 *)data);
+ brcmf_dbg(FIL, "ifidx=%d, cmd=%d, value=%d\n", ifp->ifidx, cmd, *data);
+
+ return err;
+ }
++static inline
++s32 brcmf_fil_cmd_int_query(struct brcmf_if *ifp, u32 cmd, u32 *data)
++{
++ __le32 *data_le = (__le32 *)data;
++
++ *data_le = cpu_to_le32(*data);
++ return brcmf_fil_cmd_int_get(ifp, cmd, data);
++}
+
+ s32 brcmf_fil_iovar_data_set(struct brcmf_if *ifp, const char *name,
+ const void *data, u32 len);
+@@ -120,14 +127,21 @@ s32 brcmf_fil_iovar_int_set(struct brcmf_if *ifp, const char *name, u32 data)
+ static inline
+ s32 brcmf_fil_iovar_int_get(struct brcmf_if *ifp, const char *name, u32 *data)
+ {
+- __le32 data_le = cpu_to_le32(*data);
+ s32 err;
+
+- err = brcmf_fil_iovar_data_get(ifp, name, &data_le, sizeof(data_le));
++ err = brcmf_fil_iovar_data_get(ifp, name, data, sizeof(*data));
+ if (err == 0)
+- *data = le32_to_cpu(data_le);
++ *data = le32_to_cpu(*(__le32 *)data);
+ return err;
+ }
++static inline
++s32 brcmf_fil_iovar_int_query(struct brcmf_if *ifp, const char *name, u32 *data)
++{
++ __le32 *data_le = (__le32 *)data;
++
++ *data_le = cpu_to_le32(*data);
++ return brcmf_fil_iovar_int_get(ifp, name, data);
++}
+
+
+ s32 brcmf_fil_bsscfg_data_set(struct brcmf_if *ifp, const char *name,
+@@ -145,15 +159,21 @@ s32 brcmf_fil_bsscfg_int_set(struct brcmf_if *ifp, const char *name, u32 data)
+ static inline
+ s32 brcmf_fil_bsscfg_int_get(struct brcmf_if *ifp, const char *name, u32 *data)
+ {
+- __le32 data_le = cpu_to_le32(*data);
+ s32 err;
+
+- err = brcmf_fil_bsscfg_data_get(ifp, name, &data_le,
+- sizeof(data_le));
++ err = brcmf_fil_bsscfg_data_get(ifp, name, data, sizeof(*data));
+ if (err == 0)
+- *data = le32_to_cpu(data_le);
++ *data = le32_to_cpu(*(__le32 *)data);
+ return err;
+ }
++static inline
++s32 brcmf_fil_bsscfg_int_query(struct brcmf_if *ifp, const char *name, u32 *data)
++{
++ __le32 *data_le = (__le32 *)data;
++
++ *data_le = cpu_to_le32(*data);
++ return brcmf_fil_bsscfg_int_get(ifp, name, data);
++}
+
+ s32 brcmf_fil_xtlv_data_set(struct brcmf_if *ifp, const char *name, u16 id,
+ void *data, u32 len);
+diff --git a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+index bc98b87cf2a131..02a95bf72740b1 100644
+--- a/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
++++ b/drivers/net/wireless/intel/iwlwifi/cfg/bz.c
+@@ -148,6 +148,17 @@ const struct iwl_cfg_trans_params iwl_bz_trans_cfg = {
+ .ltr_delay = IWL_CFG_TRANS_LTR_DELAY_2500US,
+ };
+
++const struct iwl_cfg_trans_params iwl_gl_trans_cfg = {
++ .device_family = IWL_DEVICE_FAMILY_BZ,
++ .base_params = &iwl_bz_base_params,
++ .mq_rx_supported = true,
++ .rf_id = true,
++ .gen2 = true,
++ .umac_prph_offset = 0x300000,
++ .xtal_latency = 12000,
++ .low_latency_xtal = true,
++};
++
+ const char iwl_bz_name[] = "Intel(R) TBD Bz device";
+ const char iwl_fm_name[] = "Intel(R) Wi-Fi 7 BE201 320MHz";
+ const char iwl_gl_name[] = "Intel(R) Wi-Fi 7 BE200 320MHz";
+diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-config.h b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+index 732889f96ca27d..29a28b5c281142 100644
+--- a/drivers/net/wireless/intel/iwlwifi/iwl-config.h
++++ b/drivers/net/wireless/intel/iwlwifi/iwl-config.h
+@@ -503,6 +503,7 @@ extern const struct iwl_cfg_trans_params iwl_so_long_latency_trans_cfg;
+ extern const struct iwl_cfg_trans_params iwl_so_long_latency_imr_trans_cfg;
+ extern const struct iwl_cfg_trans_params iwl_ma_trans_cfg;
+ extern const struct iwl_cfg_trans_params iwl_bz_trans_cfg;
++extern const struct iwl_cfg_trans_params iwl_gl_trans_cfg;
+ extern const struct iwl_cfg_trans_params iwl_sc_trans_cfg;
+ extern const char iwl9162_name[];
+ extern const char iwl9260_name[];
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+index 3cbeaddf435865..4ff643e9db5e36 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/constants.h
+@@ -109,7 +109,7 @@
+ #define IWL_MVM_FTM_INITIATOR_SECURE_LTF false
+ #define IWL_MVM_FTM_RESP_NDP_SUPPORT true
+ #define IWL_MVM_FTM_RESP_LMR_FEEDBACK_SUPPORT true
+-#define IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR 5
++#define IWL_MVM_FTM_NON_TB_MIN_TIME_BETWEEN_MSR 7
+ #define IWL_MVM_FTM_NON_TB_MAX_TIME_BETWEEN_MSR 1000
+ #define IWL_MVM_D3_DEBUG false
+ #define IWL_MVM_USE_TWT true
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+index 9d681377cbab3f..f40d3e59d694a1 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+@@ -107,16 +107,14 @@ static void iwl_mvm_cleanup_roc(struct iwl_mvm *mvm)
+ iwl_mvm_flush_sta(mvm, mvm->aux_sta.sta_id,
+ mvm->aux_sta.tfd_queue_msk);
+
+- if (mvm->mld_api_is_used) {
+- iwl_mvm_mld_rm_aux_sta(mvm);
+- mutex_unlock(&mvm->mutex);
+- return;
+- }
+-
+ /* In newer version of this command an aux station is added only
+ * in cases of dedicated tx queue and need to be removed in end
+- * of use */
+- if (iwl_mvm_has_new_station_api(mvm->fw))
++ * of use. For the even newer mld api, use the appropriate
++ * function.
++ */
++ if (mvm->mld_api_is_used)
++ iwl_mvm_mld_rm_aux_sta(mvm);
++ else if (iwl_mvm_has_new_station_api(mvm->fw))
+ iwl_mvm_rm_aux_sta(mvm);
+ }
+
+diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+index fed2754be68029..d93eec242204f2 100644
+--- a/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
++++ b/drivers/net/wireless/intel/iwlwifi/pcie/drv.c
+@@ -500,10 +500,38 @@ VISIBLE_IF_IWLWIFI_KUNIT const struct pci_device_id iwl_hw_card_ids[] = {
+ {IWL_PCI_DEVICE(0x7E40, PCI_ANY_ID, iwl_ma_trans_cfg)},
+
+ /* Bz devices */
+- {IWL_PCI_DEVICE(0x2727, PCI_ANY_ID, iwl_bz_trans_cfg)},
+- {IWL_PCI_DEVICE(0x272D, PCI_ANY_ID, iwl_bz_trans_cfg)},
+- {IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_bz_trans_cfg)},
+- {IWL_PCI_DEVICE(0xA840, PCI_ANY_ID, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0x272b, PCI_ANY_ID, iwl_gl_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0000, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0090, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0094, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0098, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x009C, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x00C0, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x00C4, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x00E0, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x00E4, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x00E8, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x00EC, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0100, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0110, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0114, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0118, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x011C, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0310, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0314, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0510, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x0A10, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x1671, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x1672, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x1771, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x1772, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x1791, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x1792, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x4090, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x40C4, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x40E0, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x4110, iwl_bz_trans_cfg)},
++ {IWL_PCI_DEVICE(0xA840, 0x4314, iwl_bz_trans_cfg)},
+ {IWL_PCI_DEVICE(0x7740, PCI_ANY_ID, iwl_bz_trans_cfg)},
+ {IWL_PCI_DEVICE(0x4D40, PCI_ANY_ID, iwl_bz_trans_cfg)},
+
+diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
+index e8ba2e4e8484a8..b5dbcf925f9227 100644
+--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
++++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
+@@ -1524,7 +1524,7 @@ EXPORT_SYMBOL_GPL(mt76_wcid_init);
+
+ void mt76_wcid_cleanup(struct mt76_dev *dev, struct mt76_wcid *wcid)
+ {
+- struct mt76_phy *phy = dev->phys[wcid->phy_idx];
++ struct mt76_phy *phy = mt76_dev_phy(dev, wcid->phy_idx);
+ struct ieee80211_hw *hw;
+ struct sk_buff_head list;
+ struct sk_buff *skb;
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
+index 14304b06371588..e238161dfaa971 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7603/dma.c
+@@ -29,7 +29,7 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb)
+ struct ieee80211_sta *sta;
+ struct mt7603_sta *msta;
+ struct mt76_wcid *wcid;
+- u8 tid = 0, hwq = 0;
++ u8 qid, tid = 0, hwq = 0;
+ void *priv;
+ int idx;
+ u32 val;
+@@ -57,7 +57,7 @@ mt7603_rx_loopback_skb(struct mt7603_dev *dev, struct sk_buff *skb)
+ if (ieee80211_is_data_qos(hdr->frame_control)) {
+ tid = *ieee80211_get_qos_ctl(hdr) &
+ IEEE80211_QOS_CTL_TAG1D_MASK;
+- u8 qid = tid_to_ac[tid];
++ qid = tid_to_ac[tid];
+ hwq = wmm_queue_map[qid];
+ skb_set_queue_mapping(skb, qid);
+ } else if (ieee80211_is_data(hdr->frame_control)) {
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7615/init.c b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+index f7722f67db576f..0b9ebdcda221e4 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7615/init.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7615/init.c
+@@ -56,6 +56,9 @@ int mt7615_thermal_init(struct mt7615_dev *dev)
+
+ name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7615_%s",
+ wiphy_name(wiphy));
++ if (!name)
++ return -ENOMEM;
++
+ hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, dev,
+ mt7615_hwmon_groups);
+ return PTR_ERR_OR_ZERO(hwmon);
+diff --git a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+index 353e6606984093..ef003d1620a5b7 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
++++ b/drivers/net/wireless/mediatek/mt76/mt76_connac3_mac.h
+@@ -28,8 +28,6 @@ enum {
+ #define MT_RXD0_MESH BIT(18)
+ #define MT_RXD0_MHCP BIT(19)
+ #define MT_RXD0_NORMAL_ETH_TYPE_OFS GENMASK(22, 16)
+-#define MT_RXD0_NORMAL_IP_SUM BIT(23)
+-#define MT_RXD0_NORMAL_UDP_TCP_SUM BIT(24)
+
+ #define MT_RXD0_SW_PKT_TYPE_MASK GENMASK(31, 16)
+ #define MT_RXD0_SW_PKT_TYPE_MAP 0x380F
+@@ -80,6 +78,8 @@ enum {
+ #define MT_RXD3_NORMAL_BEACON_UC BIT(21)
+ #define MT_RXD3_NORMAL_CO_ANT BIT(22)
+ #define MT_RXD3_NORMAL_FCS_ERR BIT(24)
++#define MT_RXD3_NORMAL_IP_SUM BIT(26)
++#define MT_RXD3_NORMAL_UDP_TCP_SUM BIT(27)
+ #define MT_RXD3_NORMAL_VLAN2ETH BIT(31)
+
+ /* RXD DW4 */
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/init.c b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+index a978f434dc5e64..7bc3b4cd359255 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7915/init.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7915/init.c
+@@ -194,6 +194,8 @@ static int mt7915_thermal_init(struct mt7915_phy *phy)
+
+ name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7915_%s",
+ wiphy_name(wiphy));
++ if (!name)
++ return -ENOMEM;
+
+ cdev = thermal_cooling_device_register(name, phy, &mt7915_thermal_ops);
+ if (!IS_ERR(cdev)) {
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7915/main.c b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+index 2624edbb59a1a5..eea41b29f09675 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7915/main.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7915/main.c
+@@ -564,8 +564,7 @@ static void mt7915_configure_filter(struct ieee80211_hw *hw,
+
+ MT76_FILTER(CONTROL, MT_WF_RFCR_DROP_CTS |
+ MT_WF_RFCR_DROP_RTS |
+- MT_WF_RFCR_DROP_CTL_RSV |
+- MT_WF_RFCR_DROP_NDPA);
++ MT_WF_RFCR_DROP_CTL_RSV);
+
+ *total_flags = flags;
+ rxfilter = phy->rxfilter;
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/init.c b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+index ef0c721d26e332..d1d64fa7d35d02 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7921/init.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7921/init.c
+@@ -52,6 +52,8 @@ static int mt7921_thermal_init(struct mt792x_phy *phy)
+
+ name = devm_kasprintf(&wiphy->dev, GFP_KERNEL, "mt7921_%s",
+ wiphy_name(wiphy));
++ if (!name)
++ return -ENOMEM;
+
+ hwmon = devm_hwmon_device_register_with_groups(&wiphy->dev, name, phy,
+ mt7921_hwmon_groups);
+@@ -83,7 +85,7 @@ mt7921_regd_channel_update(struct wiphy *wiphy, struct mt792x_dev *dev)
+ }
+
+ /* UNII-4 */
+- if (IS_UNII_INVALID(0, 5850, 5925))
++ if (IS_UNII_INVALID(0, 5845, 5925))
+ ch->flags |= IEEE80211_CHAN_DISABLED;
+ }
+
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+index c2460ef4993db6..e9d2d0f22a5863 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7925/mac.c
+@@ -350,7 +350,7 @@ mt7925_mac_fill_rx_rate(struct mt792x_dev *dev,
+ static int
+ mt7925_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
+ {
+- u32 csum_mask = MT_RXD0_NORMAL_IP_SUM | MT_RXD0_NORMAL_UDP_TCP_SUM;
++ u32 csum_mask = MT_RXD3_NORMAL_IP_SUM | MT_RXD3_NORMAL_UDP_TCP_SUM;
+ struct mt76_rx_status *status = (struct mt76_rx_status *)skb->cb;
+ bool hdr_trans, unicast, insert_ccmp_hdr = false;
+ u8 chfreq, qos_ctl = 0, remove_pad, amsdu_info;
+@@ -360,7 +360,6 @@ mt7925_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
+ struct mt792x_phy *phy = &dev->phy;
+ struct ieee80211_supported_band *sband;
+ u32 csum_status = *(u32 *)skb->cb;
+- u32 rxd0 = le32_to_cpu(rxd[0]);
+ u32 rxd1 = le32_to_cpu(rxd[1]);
+ u32 rxd2 = le32_to_cpu(rxd[2]);
+ u32 rxd3 = le32_to_cpu(rxd[3]);
+@@ -418,7 +417,7 @@ mt7925_mac_fill_rx(struct mt792x_dev *dev, struct sk_buff *skb)
+ if (!sband->channels)
+ return -EINVAL;
+
+- if (mt76_is_mmio(&dev->mt76) && (rxd0 & csum_mask) == csum_mask &&
++ if (mt76_is_mmio(&dev->mt76) && (rxd3 & csum_mask) == csum_mask &&
+ !(csum_status & (BIT(0) | BIT(2) | BIT(3))))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+index 652a9accc43cc3..7ec6bb5bc2767f 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7925/mcu.c
+@@ -613,6 +613,9 @@ static int mt7925_load_clc(struct mt792x_dev *dev, const char *fw_name)
+ for (offset = 0; offset < len; offset += le32_to_cpu(clc->len)) {
+ clc = (const struct mt7925_clc *)(clc_base + offset);
+
++ if (clc->idx > ARRAY_SIZE(phy->clc))
++ break;
++
+ /* do not init buf again if chip reset triggered */
+ if (phy->clc[clc->idx])
+ continue;
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/init.c b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+index 283df84f1b4335..a98dcb40490bf8 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7996/init.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7996/init.c
+@@ -1011,8 +1011,6 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy,
+ return;
+
+ elem->phy_cap_info[3] |= IEEE80211_HE_PHY_CAP3_SU_BEAMFORMER;
+- if (vif == NL80211_IFTYPE_AP)
+- elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER;
+
+ c = FIELD_PREP(IEEE80211_HE_PHY_CAP5_BEAMFORMEE_NUM_SND_DIM_UNDER_80MHZ_MASK,
+ sts - 1) |
+@@ -1020,6 +1018,11 @@ mt7996_set_stream_he_txbf_caps(struct mt7996_phy *phy,
+ sts - 1);
+ elem->phy_cap_info[5] |= c;
+
++ if (vif != NL80211_IFTYPE_AP)
++ return;
++
++ elem->phy_cap_info[4] |= IEEE80211_HE_PHY_CAP4_MU_BEAMFORMER;
++
+ c = IEEE80211_HE_PHY_CAP6_TRIG_SU_BEAMFORMING_FB |
+ IEEE80211_HE_PHY_CAP6_TRIG_MU_BEAMFORMING_PARTIAL_BW_FB;
+ elem->phy_cap_info[6] |= c;
+@@ -1179,7 +1182,6 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
+ IEEE80211_EHT_MAC_CAP0_OM_CONTROL;
+
+ eht_cap_elem->phy_cap_info[0] =
+- IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ |
+ IEEE80211_EHT_PHY_CAP0_NDP_4_EHT_LFT_32_GI |
+ IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMER |
+ IEEE80211_EHT_PHY_CAP0_SU_BEAMFORMEE;
+@@ -1193,30 +1195,36 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
+ u8_encode_bits(u8_get_bits(val, GENMASK(2, 1)),
+ IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_80MHZ_MASK) |
+ u8_encode_bits(val,
+- IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK) |
+- u8_encode_bits(val,
+- IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK);
++ IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_160MHZ_MASK);
+
+ eht_cap_elem->phy_cap_info[2] =
+ u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_80MHZ_MASK) |
+- u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK) |
+- u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK);
++ u8_encode_bits(sts - 1, IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_160MHZ_MASK);
++
++ if (band == NL80211_BAND_6GHZ) {
++ eht_cap_elem->phy_cap_info[0] |=
++ IEEE80211_EHT_PHY_CAP0_320MHZ_IN_6GHZ;
++
++ eht_cap_elem->phy_cap_info[1] |=
++ u8_encode_bits(val,
++ IEEE80211_EHT_PHY_CAP1_BEAMFORMEE_SS_320MHZ_MASK);
++
++ eht_cap_elem->phy_cap_info[2] |=
++ u8_encode_bits(sts - 1,
++ IEEE80211_EHT_PHY_CAP2_SOUNDING_DIM_320MHZ_MASK);
++ }
+
+ eht_cap_elem->phy_cap_info[3] =
+ IEEE80211_EHT_PHY_CAP3_NG_16_SU_FEEDBACK |
+ IEEE80211_EHT_PHY_CAP3_NG_16_MU_FEEDBACK |
+ IEEE80211_EHT_PHY_CAP3_CODEBOOK_4_2_SU_FDBK |
+- IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK |
+- IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK |
+- IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK |
+- IEEE80211_EHT_PHY_CAP3_TRIG_CQI_FDBK;
++ IEEE80211_EHT_PHY_CAP3_CODEBOOK_7_5_MU_FDBK;
+
+ eht_cap_elem->phy_cap_info[4] =
+ u8_encode_bits(min_t(int, sts - 1, 2),
+ IEEE80211_EHT_PHY_CAP4_MAX_NC_MASK);
+
+ eht_cap_elem->phy_cap_info[5] =
+- IEEE80211_EHT_PHY_CAP5_NON_TRIG_CQI_FEEDBACK |
+ u8_encode_bits(IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_16US,
+ IEEE80211_EHT_PHY_CAP5_COMMON_NOMINAL_PKT_PAD_MASK) |
+ u8_encode_bits(u8_get_bits(0x11, GENMASK(1, 0)),
+@@ -1230,14 +1238,6 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
+ IEEE80211_EHT_PHY_CAP6_MAX_NUM_SUPP_EHT_LTF_MASK) |
+ u8_encode_bits(val, IEEE80211_EHT_PHY_CAP6_MCS15_SUPP_MASK);
+
+- eht_cap_elem->phy_cap_info[7] =
+- IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ |
+- IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ |
+- IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ |
+- IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ |
+- IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ |
+- IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ;
+-
+ val = u8_encode_bits(nss, IEEE80211_EHT_MCS_NSS_RX) |
+ u8_encode_bits(nss, IEEE80211_EHT_MCS_NSS_TX);
+ #define SET_EHT_MAX_NSS(_bw, _val) do { \
+@@ -1248,8 +1248,29 @@ mt7996_init_eht_caps(struct mt7996_phy *phy, enum nl80211_band band,
+
+ SET_EHT_MAX_NSS(80, val);
+ SET_EHT_MAX_NSS(160, val);
+- SET_EHT_MAX_NSS(320, val);
++ if (band == NL80211_BAND_6GHZ)
++ SET_EHT_MAX_NSS(320, val);
+ #undef SET_EHT_MAX_NSS
++
++ if (iftype != NL80211_IFTYPE_AP)
++ return;
++
++ eht_cap_elem->phy_cap_info[3] |=
++ IEEE80211_EHT_PHY_CAP3_TRIG_SU_BF_FDBK |
++ IEEE80211_EHT_PHY_CAP3_TRIG_MU_BF_PART_BW_FDBK;
++
++ eht_cap_elem->phy_cap_info[7] =
++ IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_80MHZ |
++ IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_160MHZ |
++ IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_80MHZ |
++ IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_160MHZ;
++
++ if (band != NL80211_BAND_6GHZ)
++ return;
++
++ eht_cap_elem->phy_cap_info[7] |=
++ IEEE80211_EHT_PHY_CAP7_NON_OFDMA_UL_MU_MIMO_320MHZ |
++ IEEE80211_EHT_PHY_CAP7_MU_BEAMFORMER_320MHZ;
+ }
+
+ static void
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+index bc7111a71f98ca..fd5fe96c32e3d1 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7996/mac.c
+@@ -435,7 +435,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
+ u32 rxd2 = le32_to_cpu(rxd[2]);
+ u32 rxd3 = le32_to_cpu(rxd[3]);
+ u32 rxd4 = le32_to_cpu(rxd[4]);
+- u32 csum_mask = MT_RXD0_NORMAL_IP_SUM | MT_RXD0_NORMAL_UDP_TCP_SUM;
++ u32 csum_mask = MT_RXD3_NORMAL_IP_SUM | MT_RXD3_NORMAL_UDP_TCP_SUM;
+ u32 csum_status = *(u32 *)skb->cb;
+ u32 mesh_mask = MT_RXD0_MESH | MT_RXD0_MHCP;
+ bool is_mesh = (rxd0 & mesh_mask) == mesh_mask;
+@@ -497,7 +497,7 @@ mt7996_mac_fill_rx(struct mt7996_dev *dev, enum mt76_rxq_id q,
+ if (!sband->channels)
+ return -EINVAL;
+
+- if ((rxd0 & csum_mask) == csum_mask &&
++ if ((rxd3 & csum_mask) == csum_mask &&
+ !(csum_status & (BIT(0) | BIT(2) | BIT(3))))
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/main.c b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+index 7c97140d8255a7..2b094b33ba31ac 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7996/main.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7996/main.c
+@@ -206,7 +206,7 @@ static int mt7996_add_interface(struct ieee80211_hw *hw,
+ mvif->mt76.omac_idx = idx;
+ mvif->phy = phy;
+ mvif->mt76.band_idx = band_idx;
+- mvif->mt76.wmm_idx = vif->type != NL80211_IFTYPE_AP;
++ mvif->mt76.wmm_idx = vif->type == NL80211_IFTYPE_AP ? 0 : 3;
+
+ ret = mt7996_mcu_add_dev_info(phy, vif, true);
+ if (ret)
+@@ -307,6 +307,10 @@ int mt7996_set_channel(struct mt7996_phy *phy)
+ if (ret)
+ goto out;
+
++ ret = mt7996_mcu_set_chan_info(phy, UNI_CHANNEL_RX_PATH);
++ if (ret)
++ goto out;
++
+ ret = mt7996_dfs_init_radar_detector(phy);
+ mt7996_mac_cca_stats_reset(phy);
+
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+index 2c857867780095..36ab59885cf2b6 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7996/mcu.c
+@@ -735,7 +735,7 @@ void mt7996_mcu_rx_event(struct mt7996_dev *dev, struct sk_buff *skb)
+ static struct tlv *
+ mt7996_mcu_add_uni_tlv(struct sk_buff *skb, u16 tag, u16 len)
+ {
+- struct tlv *ptlv = skb_put(skb, len);
++ struct tlv *ptlv = skb_put_zero(skb, len);
+
+ ptlv->tag = cpu_to_le16(tag);
+ ptlv->len = cpu_to_le16(len);
+@@ -822,7 +822,7 @@ mt7996_mcu_bss_mbssid_tlv(struct sk_buff *skb, struct ieee80211_vif *vif,
+ struct bss_info_uni_mbssid *mbssid;
+ struct tlv *tlv;
+
+- if (!vif->bss_conf.bssid_indicator)
++ if (!vif->bss_conf.bssid_indicator && enable)
+ return;
+
+ tlv = mt7996_mcu_add_uni_tlv(skb, UNI_BSS_INFO_11V_MBSSID, sizeof(*mbssid));
+@@ -1429,10 +1429,10 @@ mt7996_is_ebf_supported(struct mt7996_phy *phy, struct ieee80211_vif *vif,
+
+ if (bfee)
+ return vif->bss_conf.eht_su_beamformee &&
+- EHT_PHY(CAP0_SU_BEAMFORMEE, pe->phy_cap_info[0]);
++ EHT_PHY(CAP0_SU_BEAMFORMER, pe->phy_cap_info[0]);
+ else
+ return vif->bss_conf.eht_su_beamformer &&
+- EHT_PHY(CAP0_SU_BEAMFORMER, pe->phy_cap_info[0]);
++ EHT_PHY(CAP0_SU_BEAMFORMEE, pe->phy_cap_info[0]);
+ }
+
+ if (sta->deflink.he_cap.has_he) {
+@@ -1544,6 +1544,9 @@ mt7996_mcu_sta_bfer_he(struct ieee80211_sta *sta, struct ieee80211_vif *vif,
+ u8 nss_mcs = mt7996_mcu_get_sta_nss(mcs_map);
+ u8 snd_dim, sts;
+
++ if (!vc)
++ return;
++
+ bf->tx_mode = MT_PHY_TYPE_HE_SU;
+
+ mt7996_mcu_sta_sounding_rate(bf);
+@@ -1653,7 +1656,7 @@ mt7996_mcu_sta_bfer_tlv(struct mt7996_dev *dev, struct sk_buff *skb,
+ {
+ struct mt7996_vif *mvif = (struct mt7996_vif *)vif->drv_priv;
+ struct mt7996_phy *phy = mvif->phy;
+- int tx_ant = hweight8(phy->mt76->chainmask) - 1;
++ int tx_ant = hweight16(phy->mt76->chainmask) - 1;
+ struct sta_rec_bf *bf;
+ struct tlv *tlv;
+ static const u8 matrix[4][4] = {
+diff --git a/drivers/net/wireless/microchip/wilc1000/hif.c b/drivers/net/wireless/microchip/wilc1000/hif.c
+index 7719e4f3e2a23a..2ee8c8e365f89f 100644
+--- a/drivers/net/wireless/microchip/wilc1000/hif.c
++++ b/drivers/net/wireless/microchip/wilc1000/hif.c
+@@ -384,6 +384,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss,
+ struct wilc_join_bss_param *param;
+ u8 rates_len = 0;
+ int ies_len;
++ u64 ies_tsf;
+ int ret;
+
+ param = kzalloc(sizeof(*param), GFP_KERNEL);
+@@ -399,6 +400,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss,
+ return NULL;
+ }
+ ies_len = ies->len;
++ ies_tsf = ies->tsf;
+ rcu_read_unlock();
+
+ param->beacon_period = cpu_to_le16(bss->beacon_interval);
+@@ -454,7 +456,7 @@ wilc_parse_join_bss_param(struct cfg80211_bss *bss,
+ IEEE80211_P2P_ATTR_ABSENCE_NOTICE,
+ (u8 *)&noa_attr, sizeof(noa_attr));
+ if (ret > 0) {
+- param->tsf_lo = cpu_to_le32(ies->tsf);
++ param->tsf_lo = cpu_to_le32(ies_tsf);
+ param->noa_enabled = 1;
+ param->idx = noa_attr.index;
+ if (noa_attr.oppps_ctwindow & IEEE80211_P2P_OPPPS_ENABLE_BIT) {
+diff --git a/drivers/net/wireless/realtek/rtw88/coex.c b/drivers/net/wireless/realtek/rtw88/coex.c
+index de3332eb7a227a..a99776af56c27f 100644
+--- a/drivers/net/wireless/realtek/rtw88/coex.c
++++ b/drivers/net/wireless/realtek/rtw88/coex.c
+@@ -2194,7 +2194,6 @@ static void rtw_coex_action_bt_a2dp_pan(struct rtw_dev *rtwdev)
+ struct rtw_coex_stat *coex_stat = &coex->stat;
+ struct rtw_efuse *efuse = &rtwdev->efuse;
+ u8 table_case, tdma_case;
+- bool wl_cpt_test = false, bt_cpt_test = false;
+
+ rtw_dbg(rtwdev, RTW_DBG_COEX, "[BTCoex], %s()\n", __func__);
+
+@@ -2202,29 +2201,16 @@ static void rtw_coex_action_bt_a2dp_pan(struct rtw_dev *rtwdev)
+ rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]);
+ if (efuse->share_ant) {
+ /* Shared-Ant */
+- if (wl_cpt_test) {
+- if (coex_stat->wl_gl_busy) {
+- table_case = 20;
+- tdma_case = 17;
+- } else {
+- table_case = 10;
+- tdma_case = 15;
+- }
+- } else if (bt_cpt_test) {
+- table_case = 26;
+- tdma_case = 26;
+- } else {
+- if (coex_stat->wl_gl_busy &&
+- coex_stat->wl_noisy_level == 0)
+- table_case = 14;
+- else
+- table_case = 10;
++ if (coex_stat->wl_gl_busy &&
++ coex_stat->wl_noisy_level == 0)
++ table_case = 14;
++ else
++ table_case = 10;
+
+- if (coex_stat->wl_gl_busy)
+- tdma_case = 15;
+- else
+- tdma_case = 20;
+- }
++ if (coex_stat->wl_gl_busy)
++ tdma_case = 15;
++ else
++ tdma_case = 20;
+ } else {
+ /* Non-Shared-Ant */
+ table_case = 112;
+@@ -2235,11 +2221,7 @@ static void rtw_coex_action_bt_a2dp_pan(struct rtw_dev *rtwdev)
+ tdma_case = 120;
+ }
+
+- if (wl_cpt_test)
+- rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[1]);
+- else
+- rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]);
+-
++ rtw_coex_set_rf_para(rtwdev, chip->wl_rf_para_rx[0]);
+ rtw_coex_table(rtwdev, false, table_case);
+ rtw_coex_tdma(rtwdev, false, tdma_case);
+ }
+diff --git a/drivers/net/wireless/realtek/rtw88/fw.c b/drivers/net/wireless/realtek/rtw88/fw.c
+index ab7d414d0ba679..b9b0114e253b43 100644
+--- a/drivers/net/wireless/realtek/rtw88/fw.c
++++ b/drivers/net/wireless/realtek/rtw88/fw.c
+@@ -1468,10 +1468,12 @@ int rtw_fw_write_data_rsvd_page(struct rtw_dev *rtwdev, u16 pg_addr,
+ val |= BIT_ENSWBCN >> 8;
+ rtw_write8(rtwdev, REG_CR + 1, val);
+
+- val = rtw_read8(rtwdev, REG_FWHW_TXQ_CTRL + 2);
+- bckp[1] = val;
+- val &= ~(BIT_EN_BCNQ_DL >> 16);
+- rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, val);
++ if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE) {
++ val = rtw_read8(rtwdev, REG_FWHW_TXQ_CTRL + 2);
++ bckp[1] = val;
++ val &= ~(BIT_EN_BCNQ_DL >> 16);
++ rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, val);
++ }
+
+ ret = rtw_hci_write_data_rsvd_page(rtwdev, buf, size);
+ if (ret) {
+@@ -1496,7 +1498,8 @@ int rtw_fw_write_data_rsvd_page(struct rtw_dev *rtwdev, u16 pg_addr,
+ rsvd_pg_head = rtwdev->fifo.rsvd_boundary;
+ rtw_write16(rtwdev, REG_FIFOPAGE_CTRL_2,
+ rsvd_pg_head | BIT_BCN_VALID_V1);
+- rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, bckp[1]);
++ if (rtw_hci_type(rtwdev) == RTW_HCI_TYPE_PCIE)
++ rtw_write8(rtwdev, REG_FWHW_TXQ_CTRL + 2, bckp[1]);
+ rtw_write8(rtwdev, REG_CR + 1, bckp[0]);
+
+ return ret;
+diff --git a/drivers/net/wireless/realtek/rtw88/main.c b/drivers/net/wireless/realtek/rtw88/main.c
+index 7ab7a988b123f1..33a7577557a568 100644
+--- a/drivers/net/wireless/realtek/rtw88/main.c
++++ b/drivers/net/wireless/realtek/rtw88/main.c
+@@ -1313,20 +1313,21 @@ static int rtw_wait_firmware_completion(struct rtw_dev *rtwdev)
+ {
+ const struct rtw_chip_info *chip = rtwdev->chip;
+ struct rtw_fw_state *fw;
++ int ret = 0;
+
+ fw = &rtwdev->fw;
+ wait_for_completion(&fw->completion);
+ if (!fw->firmware)
+- return -EINVAL;
++ ret = -EINVAL;
+
+ if (chip->wow_fw_name) {
+ fw = &rtwdev->wow_fw;
+ wait_for_completion(&fw->completion);
+ if (!fw->firmware)
+- return -EINVAL;
++ ret = -EINVAL;
+ }
+
+- return 0;
++ return ret;
+ }
+
+ static enum rtw_lps_deep_mode rtw_update_lps_deep_mode(struct rtw_dev *rtwdev,
+diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
+index e2c7d9f876836a..a019f4085e7389 100644
+--- a/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
++++ b/drivers/net/wireless/realtek/rtw88/rtw8821cu.c
+@@ -31,8 +31,6 @@ static const struct usb_device_id rtw_8821cu_id_table[] = {
+ .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) },
+ { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82b, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) },
+- { USB_DEVICE_AND_INTERFACE_INFO(RTW_USB_VENDOR_ID_REALTEK, 0xc82c, 0xff, 0xff, 0xff),
+- .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) },
+ { USB_DEVICE_AND_INTERFACE_INFO(0x2001, 0x331d, 0xff, 0xff, 0xff),
+ .driver_info = (kernel_ulong_t)&(rtw8821c_hw_spec) }, /* D-Link */
+ { USB_DEVICE_AND_INTERFACE_INFO(0x7392, 0xc811, 0xff, 0xff, 0xff),
+diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+index 62376d1cca22fc..732d787652208b 100644
+--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
++++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+@@ -2611,12 +2611,14 @@ static void query_phy_status_page1(struct rtw_dev *rtwdev, u8 *phy_status,
+ else
+ rxsc = GET_PHY_STAT_P1_HT_RXSC(phy_status);
+
+- if (rxsc >= 9 && rxsc <= 12)
++ if (rxsc == 0)
++ bw = rtwdev->hal.current_band_width;
++ else if (rxsc >= 1 && rxsc <= 8)
++ bw = RTW_CHANNEL_WIDTH_20;
++ else if (rxsc >= 9 && rxsc <= 12)
+ bw = RTW_CHANNEL_WIDTH_40;
+- else if (rxsc >= 13)
+- bw = RTW_CHANNEL_WIDTH_80;
+ else
+- bw = RTW_CHANNEL_WIDTH_20;
++ bw = RTW_CHANNEL_WIDTH_80;
+
+ channel = GET_PHY_STAT_P1_CHANNEL(phy_status);
+ rtw_set_rx_freq_band(pkt_stat, channel);
+diff --git a/drivers/net/wireless/realtek/rtw88/rx.h b/drivers/net/wireless/realtek/rtw88/rx.h
+index d3668c4efc24d5..8a072dd3d73ce4 100644
+--- a/drivers/net/wireless/realtek/rtw88/rx.h
++++ b/drivers/net/wireless/realtek/rtw88/rx.h
+@@ -41,7 +41,7 @@ enum rtw_rx_desc_enc {
+ #define GET_RX_DESC_TSFL(rxdesc) \
+ le32_get_bits(*((__le32 *)(rxdesc) + 0x05), GENMASK(31, 0))
+ #define GET_RX_DESC_BW(rxdesc) \
+- (le32_get_bits(*((__le32 *)(rxdesc) + 0x04), GENMASK(31, 24)))
++ (le32_get_bits(*((__le32 *)(rxdesc) + 0x04), GENMASK(5, 4)))
+
+ void rtw_rx_stats(struct rtw_dev *rtwdev, struct ieee80211_vif *vif,
+ struct sk_buff *skb);
+diff --git a/drivers/net/wireless/realtek/rtw89/mac.h b/drivers/net/wireless/realtek/rtw89/mac.h
+index a580cb71923379..755a55c8bc20bf 100644
+--- a/drivers/net/wireless/realtek/rtw89/mac.h
++++ b/drivers/net/wireless/realtek/rtw89/mac.h
+@@ -421,7 +421,6 @@ enum rtw89_mac_c2h_mrc_func {
+
+ enum rtw89_mac_c2h_wow_func {
+ RTW89_MAC_C2H_FUNC_AOAC_REPORT,
+- RTW89_MAC_C2H_FUNC_READ_WOW_CAM,
+
+ NUM_OF_RTW89_MAC_C2H_FUNC_WOW,
+ };
+diff --git a/drivers/ntb/hw/intel/ntb_hw_gen1.c b/drivers/ntb/hw/intel/ntb_hw_gen1.c
+index 9ab836d0d4f12d..079b8cd7978573 100644
+--- a/drivers/ntb/hw/intel/ntb_hw_gen1.c
++++ b/drivers/ntb/hw/intel/ntb_hw_gen1.c
+@@ -778,7 +778,7 @@ static void ndev_init_debugfs(struct intel_ntb_dev *ndev)
+ ndev->debugfs_dir =
+ debugfs_create_dir(pci_name(ndev->ntb.pdev),
+ debugfs_dir);
+- if (!ndev->debugfs_dir)
++ if (IS_ERR(ndev->debugfs_dir))
+ ndev->debugfs_info = NULL;
+ else
+ ndev->debugfs_info =
+diff --git a/drivers/ntb/ntb_transport.c b/drivers/ntb/ntb_transport.c
+index f9e7847a378e77..c84fadfc63c52c 100644
+--- a/drivers/ntb/ntb_transport.c
++++ b/drivers/ntb/ntb_transport.c
+@@ -807,16 +807,29 @@ static void ntb_free_mw(struct ntb_transport_ctx *nt, int num_mw)
+ }
+
+ static int ntb_alloc_mw_buffer(struct ntb_transport_mw *mw,
+- struct device *dma_dev, size_t align)
++ struct device *ntb_dev, size_t align)
+ {
+ dma_addr_t dma_addr;
+ void *alloc_addr, *virt_addr;
+ int rc;
+
+- alloc_addr = dma_alloc_coherent(dma_dev, mw->alloc_size,
+- &dma_addr, GFP_KERNEL);
++ /*
++ * The buffer here is allocated against the NTB device. The reason to
++ * use dma_alloc_*() call is to allocate a large IOVA contiguous buffer
++ * backing the NTB BAR for the remote host to write to. During receive
++ * processing, the data is being copied out of the receive buffer to
++ * the kernel skbuff. When a DMA device is being used, dma_map_page()
++ * is called on the kvaddr of the receive buffer (from dma_alloc_*())
++ * and remapped against the DMA device. It appears to be a double
++ * DMA mapping of buffers, but first is mapped to the NTB device and
++ * second is to the DMA device. DMA_ATTR_FORCE_CONTIGUOUS is necessary
++ * in order for the later dma_map_page() to not fail.
++ */
++ alloc_addr = dma_alloc_attrs(ntb_dev, mw->alloc_size,
++ &dma_addr, GFP_KERNEL,
++ DMA_ATTR_FORCE_CONTIGUOUS);
+ if (!alloc_addr) {
+- dev_err(dma_dev, "Unable to alloc MW buff of size %zu\n",
++ dev_err(ntb_dev, "Unable to alloc MW buff of size %zu\n",
+ mw->alloc_size);
+ return -ENOMEM;
+ }
+@@ -845,7 +858,7 @@ static int ntb_alloc_mw_buffer(struct ntb_transport_mw *mw,
+ return 0;
+
+ err:
+- dma_free_coherent(dma_dev, mw->alloc_size, alloc_addr, dma_addr);
++ dma_free_coherent(ntb_dev, mw->alloc_size, alloc_addr, dma_addr);
+
+ return rc;
+ }
+diff --git a/drivers/ntb/test/ntb_perf.c b/drivers/ntb/test/ntb_perf.c
+index 553f1f46bc664f..72bc1d017a46ee 100644
+--- a/drivers/ntb/test/ntb_perf.c
++++ b/drivers/ntb/test/ntb_perf.c
+@@ -1227,7 +1227,7 @@ static ssize_t perf_dbgfs_read_info(struct file *filep, char __user *ubuf,
+ "\tOut buffer addr 0x%pK\n", peer->outbuf);
+
+ pos += scnprintf(buf + pos, buf_size - pos,
+- "\tOut buff phys addr %pa[p]\n", &peer->out_phys_addr);
++ "\tOut buff phys addr %pap\n", &peer->out_phys_addr);
+
+ pos += scnprintf(buf + pos, buf_size - pos,
+ "\tOut buffer size %pa\n", &peer->outbuf_size);
+diff --git a/drivers/nvdimm/namespace_devs.c b/drivers/nvdimm/namespace_devs.c
+index d6d558f94d6bb2..35d9f3cc2efabf 100644
+--- a/drivers/nvdimm/namespace_devs.c
++++ b/drivers/nvdimm/namespace_devs.c
+@@ -1937,12 +1937,16 @@ static int cmp_dpa(const void *a, const void *b)
+ static struct device **scan_labels(struct nd_region *nd_region)
+ {
+ int i, count = 0;
+- struct device *dev, **devs = NULL;
++ struct device *dev, **devs;
+ struct nd_label_ent *label_ent, *e;
+ struct nd_mapping *nd_mapping = &nd_region->mapping[0];
+ struct nvdimm_drvdata *ndd = to_ndd(nd_mapping);
+ resource_size_t map_end = nd_mapping->start + nd_mapping->size - 1;
+
++ devs = kcalloc(2, sizeof(dev), GFP_KERNEL);
++ if (!devs)
++ return NULL;
++
+ /* "safe" because create_namespace_pmem() might list_move() label_ent */
+ list_for_each_entry_safe(label_ent, e, &nd_mapping->labels, list) {
+ struct nd_namespace_label *nd_label = label_ent->label;
+@@ -1961,12 +1965,14 @@ static struct device **scan_labels(struct nd_region *nd_region)
+ goto err;
+ if (i < count)
+ continue;
+- __devs = kcalloc(count + 2, sizeof(dev), GFP_KERNEL);
+- if (!__devs)
+- goto err;
+- memcpy(__devs, devs, sizeof(dev) * count);
+- kfree(devs);
+- devs = __devs;
++ if (count) {
++ __devs = kcalloc(count + 2, sizeof(dev), GFP_KERNEL);
++ if (!__devs)
++ goto err;
++ memcpy(__devs, devs, sizeof(dev) * count);
++ kfree(devs);
++ devs = __devs;
++ }
+
+ dev = create_namespace_pmem(nd_region, nd_mapping, nd_label);
+ if (IS_ERR(dev)) {
+@@ -1993,11 +1999,6 @@ static struct device **scan_labels(struct nd_region *nd_region)
+
+ /* Publish a zero-sized namespace for userspace to configure. */
+ nd_mapping_free_labels(nd_mapping);
+-
+- devs = kcalloc(2, sizeof(dev), GFP_KERNEL);
+- if (!devs)
+- goto err;
+-
+ nspm = kzalloc(sizeof(*nspm), GFP_KERNEL);
+ if (!nspm)
+ goto err;
+@@ -2036,11 +2037,10 @@ static struct device **scan_labels(struct nd_region *nd_region)
+ return devs;
+
+ err:
+- if (devs) {
+- for (i = 0; devs[i]; i++)
+- namespace_pmem_release(devs[i]);
+- kfree(devs);
+- }
++ for (i = 0; devs[i]; i++)
++ namespace_pmem_release(devs[i]);
++ kfree(devs);
++
+ return NULL;
+ }
+
+diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
+index 03a6868f4dbc18..a47d35102b7ce7 100644
+--- a/drivers/nvme/host/multipath.c
++++ b/drivers/nvme/host/multipath.c
+@@ -587,7 +587,7 @@ static void nvme_mpath_set_live(struct nvme_ns *ns)
+ rc = device_add_disk(&head->subsys->dev, head->disk,
+ nvme_ns_attr_groups);
+ if (rc) {
+- clear_bit(NVME_NSHEAD_DISK_LIVE, &ns->flags);
++ clear_bit(NVME_NSHEAD_DISK_LIVE, &head->flags);
+ return;
+ }
+ nvme_add_ns_head_cdev(head);
+diff --git a/drivers/pci/controller/dwc/pci-dra7xx.c b/drivers/pci/controller/dwc/pci-dra7xx.c
+index d2d17d37d3e0b5..4c67fa78db2677 100644
+--- a/drivers/pci/controller/dwc/pci-dra7xx.c
++++ b/drivers/pci/controller/dwc/pci-dra7xx.c
+@@ -850,14 +850,21 @@ static int dra7xx_pcie_probe(struct platform_device *pdev)
+ dra7xx->mode = mode;
+
+ ret = devm_request_threaded_irq(dev, irq, NULL, dra7xx_pcie_irq_handler,
+- IRQF_SHARED, "dra7xx-pcie-main", dra7xx);
++ IRQF_SHARED | IRQF_ONESHOT,
++ "dra7xx-pcie-main", dra7xx);
+ if (ret) {
+ dev_err(dev, "failed to request irq\n");
+- goto err_gpio;
++ goto err_deinit;
+ }
+
+ return 0;
+
++err_deinit:
++ if (dra7xx->mode == DW_PCIE_RC_TYPE)
++ dw_pcie_host_deinit(&dra7xx->pci->pp);
++ else
++ dw_pcie_ep_deinit(&dra7xx->pci->ep);
++
+ err_gpio:
+ err_get_sync:
+ pm_runtime_put(dev);
+diff --git a/drivers/pci/controller/dwc/pci-imx6.c b/drivers/pci/controller/dwc/pci-imx6.c
+index 917c69edee1d54..dbd6d7a2748930 100644
+--- a/drivers/pci/controller/dwc/pci-imx6.c
++++ b/drivers/pci/controller/dwc/pci-imx6.c
+@@ -958,7 +958,7 @@ static int imx6_pcie_host_init(struct dw_pcie_rp *pp)
+ ret = phy_power_on(imx6_pcie->phy);
+ if (ret) {
+ dev_err(dev, "waiting for PHY ready timeout!\n");
+- goto err_phy_off;
++ goto err_phy_exit;
+ }
+ }
+
+@@ -973,8 +973,9 @@ static int imx6_pcie_host_init(struct dw_pcie_rp *pp)
+ return 0;
+
+ err_phy_off:
+- if (imx6_pcie->phy)
+- phy_exit(imx6_pcie->phy);
++ phy_power_off(imx6_pcie->phy);
++err_phy_exit:
++ phy_exit(imx6_pcie->phy);
+ err_clk_disable:
+ imx6_pcie_clk_disable(imx6_pcie);
+ err_reg_disable:
+@@ -1118,6 +1119,8 @@ static int imx6_add_pcie_ep(struct imx6_pcie *imx6_pcie,
+ if (imx6_check_flag(imx6_pcie, IMX6_PCIE_FLAG_SUPPORT_64BIT))
+ dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64));
+
++ ep->page_size = imx6_pcie->drvdata->epc_features->align;
++
+ ret = dw_pcie_ep_init(ep);
+ if (ret) {
+ dev_err(dev, "failed to initialize endpoint\n");
+@@ -1578,7 +1581,8 @@ static const struct imx6_pcie_drvdata drvdata[] = {
+ },
+ [IMX8MM_EP] = {
+ .variant = IMX8MM_EP,
+- .flags = IMX6_PCIE_FLAG_HAS_PHYDRV,
++ .flags = IMX6_PCIE_FLAG_HAS_APP_RESET |
++ IMX6_PCIE_FLAG_HAS_PHYDRV,
+ .mode = DW_PCIE_EP_TYPE,
+ .gpr = "fsl,imx8mm-iomuxc-gpr",
+ .clk_names = imx8mm_clks,
+@@ -1589,7 +1593,8 @@ static const struct imx6_pcie_drvdata drvdata[] = {
+ },
+ [IMX8MP_EP] = {
+ .variant = IMX8MP_EP,
+- .flags = IMX6_PCIE_FLAG_HAS_PHYDRV,
++ .flags = IMX6_PCIE_FLAG_HAS_APP_RESET |
++ IMX6_PCIE_FLAG_HAS_PHYDRV,
+ .mode = DW_PCIE_EP_TYPE,
+ .gpr = "fsl,imx8mp-iomuxc-gpr",
+ .clk_names = imx8mm_clks,
+diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
+index 483c9540651353..d911f0e521da04 100644
+--- a/drivers/pci/controller/dwc/pci-keystone.c
++++ b/drivers/pci/controller/dwc/pci-keystone.c
+@@ -577,7 +577,7 @@ static void ks_pcie_quirk(struct pci_dev *dev)
+ */
+ if (pci_match_id(am6_pci_devids, bridge)) {
+ bridge_dev = pci_get_host_bridge_device(dev);
+- if (!bridge_dev && !bridge_dev->parent)
++ if (!bridge_dev || !bridge_dev->parent)
+ return;
+
+ ks_pcie = dev_get_drvdata(bridge_dev->parent);
+diff --git a/drivers/pci/controller/dwc/pcie-kirin.c b/drivers/pci/controller/dwc/pcie-kirin.c
+index d5523f3021024c..deab1e653b9a39 100644
+--- a/drivers/pci/controller/dwc/pcie-kirin.c
++++ b/drivers/pci/controller/dwc/pcie-kirin.c
+@@ -412,12 +412,12 @@ static int kirin_pcie_parse_port(struct kirin_pcie *pcie,
+ if (pcie->gpio_id_reset[i] < 0)
+ continue;
+
+- pcie->num_slots++;
+- if (pcie->num_slots > MAX_PCI_SLOTS) {
++ if (pcie->num_slots + 1 >= MAX_PCI_SLOTS) {
+ dev_err(dev, "Too many PCI slots!\n");
+ ret = -EINVAL;
+ goto put_node;
+ }
++ pcie->num_slots++;
+
+ ret = of_pci_get_devfn(child);
+ if (ret < 0) {
+diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
+index 50b1635e3cbb1d..26cab226bccf4e 100644
+--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
++++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
+@@ -816,21 +816,15 @@ static int qcom_pcie_ep_probe(struct platform_device *pdev)
+ if (ret)
+ return ret;
+
+- ret = qcom_pcie_enable_resources(pcie_ep);
+- if (ret) {
+- dev_err(dev, "Failed to enable resources: %d\n", ret);
+- return ret;
+- }
+-
+ ret = dw_pcie_ep_init(&pcie_ep->pci.ep);
+ if (ret) {
+ dev_err(dev, "Failed to initialize endpoint: %d\n", ret);
+- goto err_disable_resources;
++ return ret;
+ }
+
+ ret = qcom_pcie_ep_enable_irq_resources(pdev, pcie_ep);
+ if (ret)
+- goto err_disable_resources;
++ goto err_ep_deinit;
+
+ name = devm_kasprintf(dev, GFP_KERNEL, "%pOFP", dev->of_node);
+ if (!name) {
+@@ -847,8 +841,8 @@ static int qcom_pcie_ep_probe(struct platform_device *pdev)
+ disable_irq(pcie_ep->global_irq);
+ disable_irq(pcie_ep->perst_irq);
+
+-err_disable_resources:
+- qcom_pcie_disable_resources(pcie_ep);
++err_ep_deinit:
++ dw_pcie_ep_deinit(&pcie_ep->pci.ep);
+
+ return ret;
+ }
+diff --git a/drivers/pci/controller/pcie-xilinx-nwl.c b/drivers/pci/controller/pcie-xilinx-nwl.c
+index 0408f4d612b5af..7417993f8cff76 100644
+--- a/drivers/pci/controller/pcie-xilinx-nwl.c
++++ b/drivers/pci/controller/pcie-xilinx-nwl.c
+@@ -80,8 +80,8 @@
+ #define MSGF_MISC_SR_NON_FATAL_DEV BIT(22)
+ #define MSGF_MISC_SR_FATAL_DEV BIT(23)
+ #define MSGF_MISC_SR_LINK_DOWN BIT(24)
+-#define MSGF_MSIC_SR_LINK_AUTO_BWIDTH BIT(25)
+-#define MSGF_MSIC_SR_LINK_BWIDTH BIT(26)
++#define MSGF_MISC_SR_LINK_AUTO_BWIDTH BIT(25)
++#define MSGF_MISC_SR_LINK_BWIDTH BIT(26)
+
+ #define MSGF_MISC_SR_MASKALL (MSGF_MISC_SR_RXMSG_AVAIL | \
+ MSGF_MISC_SR_RXMSG_OVER | \
+@@ -96,8 +96,8 @@
+ MSGF_MISC_SR_NON_FATAL_DEV | \
+ MSGF_MISC_SR_FATAL_DEV | \
+ MSGF_MISC_SR_LINK_DOWN | \
+- MSGF_MSIC_SR_LINK_AUTO_BWIDTH | \
+- MSGF_MSIC_SR_LINK_BWIDTH)
++ MSGF_MISC_SR_LINK_AUTO_BWIDTH | \
++ MSGF_MISC_SR_LINK_BWIDTH)
+
+ /* Legacy interrupt status mask bits */
+ #define MSGF_LEG_SR_INTA BIT(0)
+@@ -299,10 +299,10 @@ static irqreturn_t nwl_pcie_misc_handler(int irq, void *data)
+ if (misc_stat & MSGF_MISC_SR_FATAL_DEV)
+ dev_err(dev, "Fatal Error Detected\n");
+
+- if (misc_stat & MSGF_MSIC_SR_LINK_AUTO_BWIDTH)
++ if (misc_stat & MSGF_MISC_SR_LINK_AUTO_BWIDTH)
+ dev_info(dev, "Link Autonomous Bandwidth Management Status bit set\n");
+
+- if (misc_stat & MSGF_MSIC_SR_LINK_BWIDTH)
++ if (misc_stat & MSGF_MISC_SR_LINK_BWIDTH)
+ dev_info(dev, "Link Bandwidth Management Status bit set\n");
+
+ /* Clear misc interrupt status */
+@@ -371,7 +371,7 @@ static void nwl_mask_intx_irq(struct irq_data *data)
+ u32 mask;
+ u32 val;
+
+- mask = 1 << (data->hwirq - 1);
++ mask = 1 << data->hwirq;
+ raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
+ val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);
+ nwl_bridge_writel(pcie, (val & (~mask)), MSGF_LEG_MASK);
+@@ -385,7 +385,7 @@ static void nwl_unmask_intx_irq(struct irq_data *data)
+ u32 mask;
+ u32 val;
+
+- mask = 1 << (data->hwirq - 1);
++ mask = 1 << data->hwirq;
+ raw_spin_lock_irqsave(&pcie->leg_mask_lock, flags);
+ val = nwl_bridge_readl(pcie, MSGF_LEG_MASK);
+ nwl_bridge_writel(pcie, (val | mask), MSGF_LEG_MASK);
+@@ -779,6 +779,7 @@ static int nwl_pcie_probe(struct platform_device *pdev)
+ return -ENODEV;
+
+ pcie = pci_host_bridge_priv(bridge);
++ platform_set_drvdata(pdev, pcie);
+
+ pcie->dev = dev;
+
+@@ -801,13 +802,13 @@ static int nwl_pcie_probe(struct platform_device *pdev)
+ err = nwl_pcie_bridge_init(pcie);
+ if (err) {
+ dev_err(dev, "HW Initialization failed\n");
+- return err;
++ goto err_clk;
+ }
+
+ err = nwl_pcie_init_irq_domain(pcie);
+ if (err) {
+ dev_err(dev, "Failed creating IRQ Domain\n");
+- return err;
++ goto err_clk;
+ }
+
+ bridge->sysdata = pcie;
+@@ -817,11 +818,24 @@ static int nwl_pcie_probe(struct platform_device *pdev)
+ err = nwl_pcie_enable_msi(pcie);
+ if (err < 0) {
+ dev_err(dev, "failed to enable MSI support: %d\n", err);
+- return err;
++ goto err_clk;
+ }
+ }
+
+- return pci_host_probe(bridge);
++ err = pci_host_probe(bridge);
++ if (!err)
++ return 0;
++
++err_clk:
++ clk_disable_unprepare(pcie->clk);
++ return err;
++}
++
++static void nwl_pcie_remove(struct platform_device *pdev)
++{
++ struct nwl_pcie *pcie = platform_get_drvdata(pdev);
++
++ clk_disable_unprepare(pcie->clk);
+ }
+
+ static struct platform_driver nwl_pcie_driver = {
+@@ -831,5 +845,6 @@ static struct platform_driver nwl_pcie_driver = {
+ .of_match_table = nwl_pcie_of_match,
+ },
+ .probe = nwl_pcie_probe,
++ .remove_new = nwl_pcie_remove,
+ };
+ builtin_platform_driver(nwl_pcie_driver);
+diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
+index 8db214d4b1d464..4f77fe122e7d08 100644
+--- a/drivers/pci/pci.c
++++ b/drivers/pci/pci.c
+@@ -1295,7 +1295,7 @@ static int pci_dev_wait(struct pci_dev *dev, char *reset_type, int timeout)
+ if (delay > PCI_RESET_WAIT) {
+ if (retrain) {
+ retrain = false;
+- if (pcie_failed_link_retrain(bridge)) {
++ if (pcie_failed_link_retrain(bridge) == 0) {
+ delay = 1;
+ continue;
+ }
+@@ -4647,7 +4647,15 @@ int pcie_retrain_link(struct pci_dev *pdev, bool use_lt)
+ pcie_capability_clear_word(pdev, PCI_EXP_LNKCTL, PCI_EXP_LNKCTL_RL);
+ }
+
+- return pcie_wait_for_link_status(pdev, use_lt, !use_lt);
++ rc = pcie_wait_for_link_status(pdev, use_lt, !use_lt);
++
++ /*
++ * Clear LBMS after a manual retrain so that the bit can be used
++ * to track link speed or width changes made by hardware itself
++ * in attempt to correct unreliable link operation.
++ */
++ pcie_capability_write_word(pdev, PCI_EXP_LNKSTA, PCI_EXP_LNKSTA_LBMS);
++ return rc;
+ }
+
+ /**
+@@ -5598,8 +5606,10 @@ static void pci_bus_restore_locked(struct pci_bus *bus)
+
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ pci_dev_restore(dev);
+- if (dev->subordinate)
++ if (dev->subordinate) {
++ pci_bridge_wait_for_secondary_bus(dev, "bus reset");
+ pci_bus_restore_locked(dev->subordinate);
++ }
+ }
+ }
+
+@@ -5633,8 +5643,10 @@ static void pci_slot_restore_locked(struct pci_slot *slot)
+ if (!dev->slot || dev->slot != slot)
+ continue;
+ pci_dev_restore(dev);
+- if (dev->subordinate)
++ if (dev->subordinate) {
++ pci_bridge_wait_for_secondary_bus(dev, "slot reset");
+ pci_bus_restore_locked(dev->subordinate);
++ }
+ }
+ }
+
+diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h
+index fd44565c475628..55d76d6802ec88 100644
+--- a/drivers/pci/pci.h
++++ b/drivers/pci/pci.h
+@@ -541,7 +541,7 @@ void pci_acs_init(struct pci_dev *dev);
+ int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags);
+ int pci_dev_specific_enable_acs(struct pci_dev *dev);
+ int pci_dev_specific_disable_acs_redir(struct pci_dev *dev);
+-bool pcie_failed_link_retrain(struct pci_dev *dev);
++int pcie_failed_link_retrain(struct pci_dev *dev);
+ #else
+ static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev,
+ u16 acs_flags)
+@@ -556,9 +556,9 @@ static inline int pci_dev_specific_disable_acs_redir(struct pci_dev *dev)
+ {
+ return -ENOTTY;
+ }
+-static inline bool pcie_failed_link_retrain(struct pci_dev *dev)
++static inline int pcie_failed_link_retrain(struct pci_dev *dev)
+ {
+- return false;
++ return -ENOTTY;
+ }
+ #endif
+
+diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c
+index 568410e64ce64e..206b76156c051a 100644
+--- a/drivers/pci/quirks.c
++++ b/drivers/pci/quirks.c
+@@ -66,7 +66,7 @@
+ * apply this erratum workaround to any downstream ports as long as they
+ * support Link Active reporting and have the Link Control 2 register.
+ * Restrict the speed to 2.5GT/s then with the Target Link Speed field,
+- * request a retrain and wait 200ms for the data link to go up.
++ * request a retrain and check the result.
+ *
+ * If this turns out successful and we know by the Vendor:Device ID it is
+ * safe to do so, then lift the restriction, letting the devices negotiate
+@@ -74,33 +74,45 @@
+ * firmware may have already arranged and lift it with ports that already
+ * report their data link being up.
+ *
+- * Return TRUE if the link has been successfully retrained, otherwise FALSE.
++ * Otherwise revert the speed to the original setting and request a retrain
++ * again to remove any residual state, ignoring the result as it's supposed
++ * to fail anyway.
++ *
++ * Return 0 if the link has been successfully retrained. Return an error
++ * if retraining was not needed or we attempted a retrain and it failed.
+ */
+-bool pcie_failed_link_retrain(struct pci_dev *dev)
++int pcie_failed_link_retrain(struct pci_dev *dev)
+ {
+ static const struct pci_device_id ids[] = {
+ { PCI_VDEVICE(ASMEDIA, 0x2824) }, /* ASMedia ASM2824 */
+ {}
+ };
+ u16 lnksta, lnkctl2;
++ int ret = -ENOTTY;
+
+ if (!pci_is_pcie(dev) || !pcie_downstream_port(dev) ||
+ !pcie_cap_has_lnkctl2(dev) || !dev->link_active_reporting)
+- return false;
++ return ret;
+
+ pcie_capability_read_word(dev, PCI_EXP_LNKCTL2, &lnkctl2);
+ pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
+ if ((lnksta & (PCI_EXP_LNKSTA_LBMS | PCI_EXP_LNKSTA_DLLLA)) ==
+ PCI_EXP_LNKSTA_LBMS) {
++ u16 oldlnkctl2 = lnkctl2;
++
+ pci_info(dev, "broken device, retraining non-functional downstream link at 2.5GT/s\n");
+
+ lnkctl2 &= ~PCI_EXP_LNKCTL2_TLS;
+ lnkctl2 |= PCI_EXP_LNKCTL2_TLS_2_5GT;
+ pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
+
+- if (pcie_retrain_link(dev, false)) {
++ ret = pcie_retrain_link(dev, false);
++ if (ret) {
+ pci_info(dev, "retraining failed\n");
+- return false;
++ pcie_capability_write_word(dev, PCI_EXP_LNKCTL2,
++ oldlnkctl2);
++ pcie_retrain_link(dev, true);
++ return ret;
+ }
+
+ pcie_capability_read_word(dev, PCI_EXP_LNKSTA, &lnksta);
+@@ -117,13 +129,14 @@ bool pcie_failed_link_retrain(struct pci_dev *dev)
+ lnkctl2 |= lnkcap & PCI_EXP_LNKCAP_SLS;
+ pcie_capability_write_word(dev, PCI_EXP_LNKCTL2, lnkctl2);
+
+- if (pcie_retrain_link(dev, false)) {
++ ret = pcie_retrain_link(dev, false);
++ if (ret) {
+ pci_info(dev, "retraining failed\n");
+- return false;
++ return ret;
+ }
+ }
+
+- return true;
++ return ret;
+ }
+
+ static ktime_t fixup_debug_start(struct pci_dev *dev,
+diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
+index 38a2947ae8130c..c6ff1bc7d336b8 100644
+--- a/drivers/perf/alibaba_uncore_drw_pmu.c
++++ b/drivers/perf/alibaba_uncore_drw_pmu.c
+@@ -400,7 +400,7 @@ static irqreturn_t ali_drw_pmu_isr(int irq_num, void *data)
+ }
+
+ /* clear common counter intr status */
+- clr_status = FIELD_PREP(ALI_DRW_PMCOM_CNT_OV_INTR_MASK, 1);
++ clr_status = FIELD_PREP(ALI_DRW_PMCOM_CNT_OV_INTR_MASK, status);
+ writel(clr_status,
+ drw_pmu->cfg_base + ALI_DRW_PMU_OV_INTR_CLR);
+ }
+diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
+index e26ad1d3ed0bb7..058ea798b669b3 100644
+--- a/drivers/perf/arm-cmn.c
++++ b/drivers/perf/arm-cmn.c
+@@ -24,14 +24,6 @@
+ #define CMN_NI_NODE_ID GENMASK_ULL(31, 16)
+ #define CMN_NI_LOGICAL_ID GENMASK_ULL(47, 32)
+
+-#define CMN_NODEID_DEVID(reg) ((reg) & 3)
+-#define CMN_NODEID_EXT_DEVID(reg) ((reg) & 1)
+-#define CMN_NODEID_PID(reg) (((reg) >> 2) & 1)
+-#define CMN_NODEID_EXT_PID(reg) (((reg) >> 1) & 3)
+-#define CMN_NODEID_1x1_PID(reg) (((reg) >> 2) & 7)
+-#define CMN_NODEID_X(reg, bits) ((reg) >> (3 + (bits)))
+-#define CMN_NODEID_Y(reg, bits) (((reg) >> 3) & ((1U << (bits)) - 1))
+-
+ #define CMN_CHILD_INFO 0x0080
+ #define CMN_CI_CHILD_COUNT GENMASK_ULL(15, 0)
+ #define CMN_CI_CHILD_PTR_OFFSET GENMASK_ULL(31, 16)
+@@ -43,6 +35,9 @@
+ #define CMN_MAX_XPS (CMN_MAX_DIMENSION * CMN_MAX_DIMENSION)
+ #define CMN_MAX_DTMS (CMN_MAX_XPS + (CMN_MAX_DIMENSION - 1) * 4)
+
++/* Currently XPs are the node type we can have most of; others top out at 128 */
++#define CMN_MAX_NODES_PER_EVENT CMN_MAX_XPS
++
+ /* The CFG node has various info besides the discovery tree */
+ #define CMN_CFGM_PERIPH_ID_01 0x0008
+ #define CMN_CFGM_PID0_PART_0 GENMASK_ULL(7, 0)
+@@ -78,7 +73,8 @@
+ /* Technically this is 4 bits wide on DNs, but we only use 2 there anyway */
+ #define CMN__PMU_OCCUP1_ID GENMASK_ULL(34, 32)
+
+-/* HN-Ps are weird... */
++/* Some types are designed to coexist with another device in the same node */
++#define CMN_CCLA_PMU_EVENT_SEL 0x008
+ #define CMN_HNP_PMU_EVENT_SEL 0x008
+
+ /* DTMs live in the PMU space of XP registers */
+@@ -281,8 +277,11 @@ struct arm_cmn_node {
+ u16 id, logid;
+ enum cmn_node_type type;
+
++ /* XP properties really, but replicated to children for convenience */
+ u8 dtm;
+ s8 dtc;
++ u8 portid_bits:4;
++ u8 deviceid_bits:4;
+ /* DN/HN-F/CXHA */
+ struct {
+ u8 val : 4;
+@@ -358,49 +357,33 @@ struct arm_cmn {
+ static int arm_cmn_hp_state;
+
+ struct arm_cmn_nodeid {
+- u8 x;
+- u8 y;
+ u8 port;
+ u8 dev;
+ };
+
+ static int arm_cmn_xyidbits(const struct arm_cmn *cmn)
+ {
+- return fls((cmn->mesh_x - 1) | (cmn->mesh_y - 1) | 2);
++ return fls((cmn->mesh_x - 1) | (cmn->mesh_y - 1));
+ }
+
+-static struct arm_cmn_nodeid arm_cmn_nid(const struct arm_cmn *cmn, u16 id)
++static struct arm_cmn_nodeid arm_cmn_nid(const struct arm_cmn_node *dn)
+ {
+ struct arm_cmn_nodeid nid;
+
+- if (cmn->num_xps == 1) {
+- nid.x = 0;
+- nid.y = 0;
+- nid.port = CMN_NODEID_1x1_PID(id);
+- nid.dev = CMN_NODEID_DEVID(id);
+- } else {
+- int bits = arm_cmn_xyidbits(cmn);
+-
+- nid.x = CMN_NODEID_X(id, bits);
+- nid.y = CMN_NODEID_Y(id, bits);
+- if (cmn->ports_used & 0xc) {
+- nid.port = CMN_NODEID_EXT_PID(id);
+- nid.dev = CMN_NODEID_EXT_DEVID(id);
+- } else {
+- nid.port = CMN_NODEID_PID(id);
+- nid.dev = CMN_NODEID_DEVID(id);
+- }
+- }
++ nid.dev = dn->id & ((1U << dn->deviceid_bits) - 1);
++ nid.port = (dn->id >> dn->deviceid_bits) & ((1U << dn->portid_bits) - 1);
+ return nid;
+ }
+
+ static struct arm_cmn_node *arm_cmn_node_to_xp(const struct arm_cmn *cmn,
+ const struct arm_cmn_node *dn)
+ {
+- struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
+- int xp_idx = cmn->mesh_x * nid.y + nid.x;
++ int id = dn->id >> (dn->portid_bits + dn->deviceid_bits);
++ int bits = arm_cmn_xyidbits(cmn);
++ int x = id >> bits;
++ int y = id & ((1U << bits) - 1);
+
+- return cmn->xps + xp_idx;
++ return cmn->xps + cmn->mesh_x * y + x;
+ }
+ static struct arm_cmn_node *arm_cmn_node(const struct arm_cmn *cmn,
+ enum cmn_node_type type)
+@@ -486,13 +469,13 @@ static const char *arm_cmn_device_type(u8 type)
+ }
+ }
+
+-static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d)
++static void arm_cmn_show_logid(struct seq_file *s, const struct arm_cmn_node *xp, int p, int d)
+ {
+ struct arm_cmn *cmn = s->private;
+ struct arm_cmn_node *dn;
++ u16 id = xp->id | d | (p << xp->deviceid_bits);
+
+ for (dn = cmn->dns; dn->type; dn++) {
+- struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
+ int pad = dn->logid < 10;
+
+ if (dn->type == CMN_TYPE_XP)
+@@ -501,7 +484,7 @@ static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d)
+ if (dn->type < CMN_TYPE_HNI)
+ continue;
+
+- if (nid.x != x || nid.y != y || nid.port != p || nid.dev != d)
++ if (dn->id != id)
+ continue;
+
+ seq_printf(s, " %*c#%-*d |", pad + 1, ' ', 3 - pad, dn->logid);
+@@ -522,6 +505,7 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
+ y = cmn->mesh_y;
+ while (y--) {
+ int xp_base = cmn->mesh_x * y;
++ struct arm_cmn_node *xp = cmn->xps + xp_base;
+ u8 port[CMN_MAX_PORTS][CMN_MAX_DIMENSION];
+
+ for (x = 0; x < cmn->mesh_x; x++)
+@@ -529,16 +513,14 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
+
+ seq_printf(s, "\n%-2d |", y);
+ for (x = 0; x < cmn->mesh_x; x++) {
+- struct arm_cmn_node *xp = cmn->xps + xp_base + x;
+-
+ for (p = 0; p < CMN_MAX_PORTS; p++)
+- port[p][x] = arm_cmn_device_connect_info(cmn, xp, p);
++ port[p][x] = arm_cmn_device_connect_info(cmn, xp + x, p);
+ seq_printf(s, " XP #%-3d|", xp_base + x);
+ }
+
+ seq_puts(s, "\n |");
+ for (x = 0; x < cmn->mesh_x; x++) {
+- s8 dtc = cmn->xps[xp_base + x].dtc;
++ s8 dtc = xp[x].dtc;
+
+ if (dtc < 0)
+ seq_puts(s, " DTC ?? |");
+@@ -555,10 +537,10 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
+ seq_puts(s, arm_cmn_device_type(port[p][x]));
+ seq_puts(s, "\n 0|");
+ for (x = 0; x < cmn->mesh_x; x++)
+- arm_cmn_show_logid(s, x, y, p, 0);
++ arm_cmn_show_logid(s, xp + x, p, 0);
+ seq_puts(s, "\n 1|");
+ for (x = 0; x < cmn->mesh_x; x++)
+- arm_cmn_show_logid(s, x, y, p, 1);
++ arm_cmn_show_logid(s, xp + x, p, 1);
+ }
+ seq_puts(s, "\n-----+");
+ }
+@@ -586,7 +568,7 @@ static void arm_cmn_debugfs_init(struct arm_cmn *cmn, int id) {}
+
+ struct arm_cmn_hw_event {
+ struct arm_cmn_node *dn;
+- u64 dtm_idx[4];
++ u64 dtm_idx[DIV_ROUND_UP(CMN_MAX_NODES_PER_EVENT * 2, 64)];
+ s8 dtc_idx[CMN_MAX_DTCS];
+ u8 num_dns;
+ u8 dtm_offset;
+@@ -1753,10 +1735,7 @@ static int arm_cmn_event_init(struct perf_event *event)
+ }
+
+ if (!hw->num_dns) {
+- struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, nodeid);
+-
+- dev_dbg(cmn->dev, "invalid node 0x%x (%d,%d,%d,%d) type 0x%x\n",
+- nodeid, nid.x, nid.y, nid.port, nid.dev, type);
++ dev_dbg(cmn->dev, "invalid node 0x%x type 0x%x\n", nodeid, type);
+ return -EINVAL;
+ }
+
+@@ -1851,7 +1830,7 @@ static int arm_cmn_event_add(struct perf_event *event, int flags)
+ dtm->wp_event[wp_idx] = hw->dtc_idx[d];
+ writel_relaxed(cfg, dtm->base + CMN_DTM_WPn_CONFIG(wp_idx));
+ } else {
+- struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
++ struct arm_cmn_nodeid nid = arm_cmn_nid(dn);
+
+ if (cmn->multi_dtm)
+ nid.port %= 2;
+@@ -2098,10 +2077,12 @@ static int arm_cmn_init_dtcs(struct arm_cmn *cmn)
+ continue;
+
+ xp = arm_cmn_node_to_xp(cmn, dn);
++ dn->portid_bits = xp->portid_bits;
++ dn->deviceid_bits = xp->deviceid_bits;
+ dn->dtc = xp->dtc;
+ dn->dtm = xp->dtm;
+ if (cmn->multi_dtm)
+- dn->dtm += arm_cmn_nid(cmn, dn->id).port / 2;
++ dn->dtm += arm_cmn_nid(dn).port / 2;
+
+ if (dn->type == CMN_TYPE_DTC) {
+ int err = arm_cmn_init_dtc(cmn, dn, dtc_idx++);
+@@ -2271,18 +2252,27 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
+ arm_cmn_init_dtm(dtm++, xp, 0);
+ /*
+ * Keeping track of connected ports will let us filter out
+- * unnecessary XP events easily. We can also reliably infer the
+- * "extra device ports" configuration for the node ID format
+- * from this, since in that case we will see at least one XP
+- * with port 2 connected, for the HN-D.
++ * unnecessary XP events easily, and also infer the per-XP
++ * part of the node ID format.
+ */
+ for (int p = 0; p < CMN_MAX_PORTS; p++)
+ if (arm_cmn_device_connect_info(cmn, xp, p))
+ xp_ports |= BIT(p);
+
+- if (cmn->multi_dtm && (xp_ports & 0xc))
++ if (cmn->num_xps == 1) {
++ xp->portid_bits = 3;
++ xp->deviceid_bits = 2;
++ } else if (xp_ports > 0x3) {
++ xp->portid_bits = 2;
++ xp->deviceid_bits = 1;
++ } else {
++ xp->portid_bits = 1;
++ xp->deviceid_bits = 2;
++ }
++
++ if (cmn->multi_dtm && (xp_ports > 0x3))
+ arm_cmn_init_dtm(dtm++, xp, 1);
+- if (cmn->multi_dtm && (xp_ports & 0x30))
++ if (cmn->multi_dtm && (xp_ports > 0xf))
+ arm_cmn_init_dtm(dtm++, xp, 2);
+
+ cmn->ports_used |= xp_ports;
+@@ -2337,10 +2327,13 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
+ case CMN_TYPE_CXHA:
+ case CMN_TYPE_CCRA:
+ case CMN_TYPE_CCHA:
+- case CMN_TYPE_CCLA:
+ case CMN_TYPE_HNS:
+ dn++;
+ break;
++ case CMN_TYPE_CCLA:
++ dn->pmu_base += CMN_CCLA_PMU_EVENT_SEL;
++ dn++;
++ break;
+ /* Nothing to see here */
+ case CMN_TYPE_MPAM_S:
+ case CMN_TYPE_MPAM_NS:
+@@ -2358,7 +2351,7 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
+ case CMN_TYPE_HNP:
+ case CMN_TYPE_CCLA_RNI:
+ dn[1] = dn[0];
+- dn[0].pmu_base += CMN_HNP_PMU_EVENT_SEL;
++ dn[0].pmu_base += CMN_CCLA_PMU_EVENT_SEL;
+ dn[1].type = arm_cmn_subtype(dn->type);
+ dn += 2;
+ break;
+diff --git a/drivers/perf/dwc_pcie_pmu.c b/drivers/perf/dwc_pcie_pmu.c
+index c5e328f2384194..f205ecad2e4c06 100644
+--- a/drivers/perf/dwc_pcie_pmu.c
++++ b/drivers/perf/dwc_pcie_pmu.c
+@@ -556,10 +556,10 @@ static int dwc_pcie_register_dev(struct pci_dev *pdev)
+ {
+ struct platform_device *plat_dev;
+ struct dwc_pcie_dev_info *dev_info;
+- u32 bdf;
++ u32 sbdf;
+
+- bdf = PCI_DEVID(pdev->bus->number, pdev->devfn);
+- plat_dev = platform_device_register_data(NULL, "dwc_pcie_pmu", bdf,
++ sbdf = (pci_domain_nr(pdev->bus) << 16) | PCI_DEVID(pdev->bus->number, pdev->devfn);
++ plat_dev = platform_device_register_data(NULL, "dwc_pcie_pmu", sbdf,
+ pdev, sizeof(*pdev));
+
+ if (IS_ERR(plat_dev))
+@@ -611,15 +611,15 @@ static int dwc_pcie_pmu_probe(struct platform_device *plat_dev)
+ struct pci_dev *pdev = plat_dev->dev.platform_data;
+ struct dwc_pcie_pmu *pcie_pmu;
+ char *name;
+- u32 bdf, val;
++ u32 sbdf, val;
+ u16 vsec;
+ int ret;
+
+ vsec = pci_find_vsec_capability(pdev, pdev->vendor,
+ DWC_PCIE_VSEC_RAS_DES_ID);
+ pci_read_config_dword(pdev, vsec + PCI_VNDR_HEADER, &val);
+- bdf = PCI_DEVID(pdev->bus->number, pdev->devfn);
+- name = devm_kasprintf(&plat_dev->dev, GFP_KERNEL, "dwc_rootport_%x", bdf);
++ sbdf = plat_dev->id;
++ name = devm_kasprintf(&plat_dev->dev, GFP_KERNEL, "dwc_rootport_%x", sbdf);
+ if (!name)
+ return -ENOMEM;
+
+@@ -650,7 +650,7 @@ static int dwc_pcie_pmu_probe(struct platform_device *plat_dev)
+ ret = cpuhp_state_add_instance(dwc_pcie_pmu_hp_state,
+ &pcie_pmu->cpuhp_node);
+ if (ret) {
+- pci_err(pdev, "Error %d registering hotplug @%x\n", ret, bdf);
++ pci_err(pdev, "Error %d registering hotplug @%x\n", ret, sbdf);
+ return ret;
+ }
+
+@@ -663,7 +663,7 @@ static int dwc_pcie_pmu_probe(struct platform_device *plat_dev)
+
+ ret = perf_pmu_register(&pcie_pmu->pmu, name, -1);
+ if (ret) {
+- pci_err(pdev, "Error %d registering PMU @%x\n", ret, bdf);
++ pci_err(pdev, "Error %d registering PMU @%x\n", ret, sbdf);
+ return ret;
+ }
+ ret = devm_add_action_or_reset(&plat_dev->dev, dwc_pcie_unregister_pmu,
+@@ -726,7 +726,6 @@ static struct platform_driver dwc_pcie_pmu_driver = {
+ static int __init dwc_pcie_pmu_init(void)
+ {
+ struct pci_dev *pdev = NULL;
+- bool found = false;
+ int ret;
+
+ for_each_pci_dev(pdev) {
+@@ -738,11 +737,7 @@ static int __init dwc_pcie_pmu_init(void)
+ pci_dev_put(pdev);
+ return ret;
+ }
+-
+- found = true;
+ }
+- if (!found)
+- return -ENODEV;
+
+ ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN,
+ "perf/dwc_pcie_pmu:online",
+diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c
+index f06027574a241a..f7d6c59d993016 100644
+--- a/drivers/perf/hisilicon/hisi_pcie_pmu.c
++++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c
+@@ -208,7 +208,7 @@ static void hisi_pcie_pmu_writeq(struct hisi_pcie_pmu *pcie_pmu, u32 reg_offset,
+ static u64 hisi_pcie_pmu_get_event_ctrl_val(struct perf_event *event)
+ {
+ u64 port, trig_len, thr_len, len_mode;
+- u64 reg = HISI_PCIE_INIT_SET;
++ u64 reg = 0;
+
+ /* Config HISI_PCIE_EVENT_CTRL according to event. */
+ reg |= FIELD_PREP(HISI_PCIE_EVENT_M, hisi_pcie_get_real_event(event));
+@@ -452,10 +452,24 @@ static void hisi_pcie_pmu_set_period(struct perf_event *event)
+ struct hisi_pcie_pmu *pcie_pmu = to_pcie_pmu(event->pmu);
+ struct hw_perf_event *hwc = &event->hw;
+ int idx = hwc->idx;
++ u64 orig_cnt, cnt;
++
++ orig_cnt = hisi_pcie_pmu_read_counter(event);
+
+ local64_set(&hwc->prev_count, HISI_PCIE_INIT_VAL);
+ hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_CNT, idx, HISI_PCIE_INIT_VAL);
+ hisi_pcie_pmu_writeq(pcie_pmu, HISI_PCIE_EXT_CNT, idx, HISI_PCIE_INIT_VAL);
++
++ /*
++ * The counter maybe unwritable if the target event is unsupported.
++ * Check this by comparing the counts after setting the period. If
++ * the counts stay unchanged after setting the period then update
++ * the hwc->prev_count correctly. Otherwise the final counts user
++ * get maybe totally wrong.
++ */
++ cnt = hisi_pcie_pmu_read_counter(event);
++ if (orig_cnt == cnt)
++ local64_set(&hwc->prev_count, cnt);
+ }
+
+ static void hisi_pcie_pmu_enable_counter(struct hisi_pcie_pmu *pcie_pmu, struct hw_perf_event *hwc)
+diff --git a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
+index 946c01210ac8c0..3bd9b62b23dcc2 100644
+--- a/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
++++ b/drivers/phy/rockchip/phy-rockchip-samsung-hdptx.c
+@@ -15,6 +15,7 @@
+ #include <linux/of_platform.h>
+ #include <linux/phy/phy.h>
+ #include <linux/platform_device.h>
++#include <linux/pm_runtime.h>
+ #include <linux/rational.h>
+ #include <linux/regmap.h>
+ #include <linux/reset.h>
+diff --git a/drivers/pinctrl/mvebu/pinctrl-dove.c b/drivers/pinctrl/mvebu/pinctrl-dove.c
+index 1947da73e51210..dce601d993728c 100644
+--- a/drivers/pinctrl/mvebu/pinctrl-dove.c
++++ b/drivers/pinctrl/mvebu/pinctrl-dove.c
+@@ -767,7 +767,7 @@ static int dove_pinctrl_probe(struct platform_device *pdev)
+ struct resource fb_res;
+ struct mvebu_mpp_ctrl_data *mpp_data;
+ void __iomem *base;
+- int i;
++ int i, ret;
+
+ pdev->dev.platform_data = (void *)device_get_match_data(&pdev->dev);
+
+@@ -783,13 +783,17 @@ static int dove_pinctrl_probe(struct platform_device *pdev)
+ clk_prepare_enable(clk);
+
+ base = devm_platform_get_and_ioremap_resource(pdev, 0, &mpp_res);
+- if (IS_ERR(base))
+- return PTR_ERR(base);
++ if (IS_ERR(base)) {
++ ret = PTR_ERR(base);
++ goto err_probe;
++ }
+
+ mpp_data = devm_kcalloc(&pdev->dev, dove_pinctrl_info.ncontrols,
+ sizeof(*mpp_data), GFP_KERNEL);
+- if (!mpp_data)
+- return -ENOMEM;
++ if (!mpp_data) {
++ ret = -ENOMEM;
++ goto err_probe;
++ }
+
+ dove_pinctrl_info.control_data = mpp_data;
+ for (i = 0; i < ARRAY_SIZE(dove_mpp_controls); i++)
+@@ -808,8 +812,10 @@ static int dove_pinctrl_probe(struct platform_device *pdev)
+ }
+
+ mpp4_base = devm_ioremap_resource(&pdev->dev, res);
+- if (IS_ERR(mpp4_base))
+- return PTR_ERR(mpp4_base);
++ if (IS_ERR(mpp4_base)) {
++ ret = PTR_ERR(mpp4_base);
++ goto err_probe;
++ }
+
+ res = platform_get_resource(pdev, IORESOURCE_MEM, 2);
+ if (!res) {
+@@ -820,8 +826,10 @@ static int dove_pinctrl_probe(struct platform_device *pdev)
+ }
+
+ pmu_base = devm_ioremap_resource(&pdev->dev, res);
+- if (IS_ERR(pmu_base))
+- return PTR_ERR(pmu_base);
++ if (IS_ERR(pmu_base)) {
++ ret = PTR_ERR(pmu_base);
++ goto err_probe;
++ }
+
+ gconfmap = syscon_regmap_lookup_by_compatible("marvell,dove-global-config");
+ if (IS_ERR(gconfmap)) {
+@@ -831,12 +839,17 @@ static int dove_pinctrl_probe(struct platform_device *pdev)
+ adjust_resource(&fb_res,
+ (mpp_res->start & INT_REGS_MASK) + GC_REGS_OFFS, 0x14);
+ gc_base = devm_ioremap_resource(&pdev->dev, &fb_res);
+- if (IS_ERR(gc_base))
+- return PTR_ERR(gc_base);
++ if (IS_ERR(gc_base)) {
++ ret = PTR_ERR(gc_base);
++ goto err_probe;
++ }
++
+ gconfmap = devm_regmap_init_mmio(&pdev->dev,
+ gc_base, &gc_regmap_config);
+- if (IS_ERR(gconfmap))
+- return PTR_ERR(gconfmap);
++ if (IS_ERR(gconfmap)) {
++ ret = PTR_ERR(gconfmap);
++ goto err_probe;
++ }
+ }
+
+ /* Warn on any missing DT resource */
+@@ -844,6 +857,9 @@ static int dove_pinctrl_probe(struct platform_device *pdev)
+ dev_warn(&pdev->dev, FW_BUG "Missing pinctrl regs in DTB. Please update your firmware.\n");
+
+ return mvebu_pinctrl_probe(pdev);
++err_probe:
++ clk_disable_unprepare(clk);
++ return ret;
+ }
+
+ static struct platform_driver dove_pinctrl_driver = {
+diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
+index 4da3c3f422b691..2ec599e383e4b2 100644
+--- a/drivers/pinctrl/pinctrl-single.c
++++ b/drivers/pinctrl/pinctrl-single.c
+@@ -1913,7 +1913,8 @@ static int pcs_probe(struct platform_device *pdev)
+
+ dev_info(pcs->dev, "%i pins, size %u\n", pcs->desc.npins, pcs->size);
+
+- if (pinctrl_enable(pcs->pctl))
++ ret = pinctrl_enable(pcs->pctl);
++ if (ret)
+ goto free;
+
+ return 0;
+diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
+index ef97586385019a..451801acdc4038 100644
+--- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
++++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
+@@ -273,6 +273,22 @@ static int ti_iodelay_pinconf_set(struct ti_iodelay_device *iod,
+ return r;
+ }
+
++/**
++ * ti_iodelay_pinconf_deinit_dev() - deinit the iodelay device
++ * @data: IODelay device
++ *
++ * Deinitialize the IODelay device (basically just lock the region back up.
++ */
++static void ti_iodelay_pinconf_deinit_dev(void *data)
++{
++ struct ti_iodelay_device *iod = data;
++ const struct ti_iodelay_reg_data *reg = iod->reg_data;
++
++ /* lock the iodelay region back again */
++ regmap_update_bits(iod->regmap, reg->reg_global_lock_offset,
++ reg->global_lock_mask, reg->global_lock_val);
++}
++
+ /**
+ * ti_iodelay_pinconf_init_dev() - Initialize IODelay device
+ * @iod: iodelay device
+@@ -295,6 +311,11 @@ static int ti_iodelay_pinconf_init_dev(struct ti_iodelay_device *iod)
+ if (r)
+ return r;
+
++ r = devm_add_action_or_reset(iod->dev, ti_iodelay_pinconf_deinit_dev,
++ iod);
++ if (r)
++ return r;
++
+ /* Read up Recalibration sequence done by bootloader */
+ r = regmap_read(iod->regmap, reg->reg_refclk_offset, &val);
+ if (r)
+@@ -353,21 +374,6 @@ static int ti_iodelay_pinconf_init_dev(struct ti_iodelay_device *iod)
+ return 0;
+ }
+
+-/**
+- * ti_iodelay_pinconf_deinit_dev() - deinit the iodelay device
+- * @iod: IODelay device
+- *
+- * Deinitialize the IODelay device (basically just lock the region back up.
+- */
+-static void ti_iodelay_pinconf_deinit_dev(struct ti_iodelay_device *iod)
+-{
+- const struct ti_iodelay_reg_data *reg = iod->reg_data;
+-
+- /* lock the iodelay region back again */
+- regmap_update_bits(iod->regmap, reg->reg_global_lock_offset,
+- reg->global_lock_mask, reg->global_lock_val);
+-}
+-
+ /**
+ * ti_iodelay_get_pingroup() - Find the group mapped by a group selector
+ * @iod: iodelay device
+@@ -822,53 +828,48 @@ MODULE_DEVICE_TABLE(of, ti_iodelay_of_match);
+ static int ti_iodelay_probe(struct platform_device *pdev)
+ {
+ struct device *dev = &pdev->dev;
+- struct device_node *np = of_node_get(dev->of_node);
++ struct device_node *np __free(device_node) = of_node_get(dev->of_node);
+ struct resource *res;
+ struct ti_iodelay_device *iod;
+- int ret = 0;
++ int ret;
+
+ if (!np) {
+- ret = -EINVAL;
+ dev_err(dev, "No OF node\n");
+- goto exit_out;
++ return -EINVAL;
+ }
+
+ iod = devm_kzalloc(dev, sizeof(*iod), GFP_KERNEL);
+- if (!iod) {
+- ret = -ENOMEM;
+- goto exit_out;
+- }
++ if (!iod)
++ return -ENOMEM;
++
+ iod->dev = dev;
+ iod->reg_data = device_get_match_data(dev);
+ if (!iod->reg_data) {
+- ret = -EINVAL;
+ dev_err(dev, "No DATA match\n");
+- goto exit_out;
++ return -EINVAL;
+ }
+
+ /* So far We can assume there is only 1 bank of registers */
+ iod->reg_base = devm_platform_get_and_ioremap_resource(pdev, 0, &res);
+- if (IS_ERR(iod->reg_base)) {
+- ret = PTR_ERR(iod->reg_base);
+- goto exit_out;
+- }
++ if (IS_ERR(iod->reg_base))
++ return PTR_ERR(iod->reg_base);
++
+ iod->phys_base = res->start;
+
+ iod->regmap = devm_regmap_init_mmio(dev, iod->reg_base,
+ iod->reg_data->regmap_config);
+ if (IS_ERR(iod->regmap)) {
+ dev_err(dev, "Regmap MMIO init failed.\n");
+- ret = PTR_ERR(iod->regmap);
+- goto exit_out;
++ return PTR_ERR(iod->regmap);
+ }
+
+ ret = ti_iodelay_pinconf_init_dev(iod);
+ if (ret)
+- goto exit_out;
++ return ret;
+
+ ret = ti_iodelay_alloc_pins(dev, iod, res->start);
+ if (ret)
+- goto exit_out;
++ return ret;
+
+ iod->desc.pctlops = &ti_iodelay_pinctrl_ops;
+ /* no pinmux ops - we are pinconf */
+@@ -879,38 +880,14 @@ static int ti_iodelay_probe(struct platform_device *pdev)
+ ret = devm_pinctrl_register_and_init(dev, &iod->desc, iod, &iod->pctl);
+ if (ret) {
+ dev_err(dev, "Failed to register pinctrl\n");
+- goto exit_out;
++ return ret;
+ }
+
+- platform_set_drvdata(pdev, iod);
+-
+- ret = pinctrl_enable(iod->pctl);
+- if (ret)
+- goto exit_out;
+-
+- return 0;
+-
+-exit_out:
+- of_node_put(np);
+- return ret;
+-}
+-
+-/**
+- * ti_iodelay_remove() - standard remove
+- * @pdev: platform device
+- */
+-static void ti_iodelay_remove(struct platform_device *pdev)
+-{
+- struct ti_iodelay_device *iod = platform_get_drvdata(pdev);
+-
+- ti_iodelay_pinconf_deinit_dev(iod);
+-
+- /* Expect other allocations to be freed by devm */
++ return pinctrl_enable(iod->pctl);
+ }
+
+ static struct platform_driver ti_iodelay_driver = {
+ .probe = ti_iodelay_probe,
+- .remove_new = ti_iodelay_remove,
+ .driver = {
+ .name = DRIVER_NAME,
+ .of_match_table = ti_iodelay_of_match,
+diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
+index 490815917adec8..32293df50bb1cc 100644
+--- a/drivers/platform/x86/ideapad-laptop.c
++++ b/drivers/platform/x86/ideapad-laptop.c
+@@ -422,13 +422,14 @@ static ssize_t camera_power_show(struct device *dev,
+ char *buf)
+ {
+ struct ideapad_private *priv = dev_get_drvdata(dev);
+- unsigned long result;
++ unsigned long result = 0;
+ int err;
+
+- scoped_guard(mutex, &priv->vpc_mutex)
++ scoped_guard(mutex, &priv->vpc_mutex) {
+ err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result);
+- if (err)
+- return err;
++ if (err)
++ return err;
++ }
+
+ return sysfs_emit(buf, "%d\n", !!result);
+ }
+@@ -445,10 +446,11 @@ static ssize_t camera_power_store(struct device *dev,
+ if (err)
+ return err;
+
+- scoped_guard(mutex, &priv->vpc_mutex)
++ scoped_guard(mutex, &priv->vpc_mutex) {
+ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state);
+- if (err)
+- return err;
++ if (err)
++ return err;
++ }
+
+ return count;
+ }
+@@ -496,13 +498,14 @@ static ssize_t fan_mode_show(struct device *dev,
+ char *buf)
+ {
+ struct ideapad_private *priv = dev_get_drvdata(dev);
+- unsigned long result;
++ unsigned long result = 0;
+ int err;
+
+- scoped_guard(mutex, &priv->vpc_mutex)
++ scoped_guard(mutex, &priv->vpc_mutex) {
+ err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result);
+- if (err)
+- return err;
++ if (err)
++ return err;
++ }
+
+ return sysfs_emit(buf, "%lu\n", result);
+ }
+@@ -522,10 +525,11 @@ static ssize_t fan_mode_store(struct device *dev,
+ if (state > 4 || state == 3)
+ return -EINVAL;
+
+- scoped_guard(mutex, &priv->vpc_mutex)
++ scoped_guard(mutex, &priv->vpc_mutex) {
+ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state);
+- if (err)
+- return err;
++ if (err)
++ return err;
++ }
+
+ return count;
+ }
+@@ -605,13 +609,14 @@ static ssize_t touchpad_show(struct device *dev,
+ char *buf)
+ {
+ struct ideapad_private *priv = dev_get_drvdata(dev);
+- unsigned long result;
++ unsigned long result = 0;
+ int err;
+
+- scoped_guard(mutex, &priv->vpc_mutex)
++ scoped_guard(mutex, &priv->vpc_mutex) {
+ err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result);
+- if (err)
+- return err;
++ if (err)
++ return err;
++ }
+
+ priv->r_touchpad_val = result;
+
+@@ -630,10 +635,11 @@ static ssize_t touchpad_store(struct device *dev,
+ if (err)
+ return err;
+
+- scoped_guard(mutex, &priv->vpc_mutex)
++ scoped_guard(mutex, &priv->vpc_mutex) {
+ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state);
+- if (err)
+- return err;
++ if (err)
++ return err;
++ }
+
+ priv->r_touchpad_val = state;
+
+diff --git a/drivers/pmdomain/core.c b/drivers/pmdomain/core.c
+index 623d15b68707ec..0ab6008e863e82 100644
+--- a/drivers/pmdomain/core.c
++++ b/drivers/pmdomain/core.c
+@@ -3153,7 +3153,7 @@ static int genpd_summary_one(struct seq_file *s,
+ else
+ snprintf(state, sizeof(state), "%s",
+ status_lookup[genpd->status]);
+- seq_printf(s, "%-30s %-50s %u", genpd->name, state, genpd->performance_state);
++ seq_printf(s, "%-30s %-49s %u", genpd->name, state, genpd->performance_state);
+
+ /*
+ * Modifications on the list require holding locks on both
+diff --git a/drivers/power/supply/axp20x_battery.c b/drivers/power/supply/axp20x_battery.c
+index 6ac5c80cfda214..7520b599eb3d17 100644
+--- a/drivers/power/supply/axp20x_battery.c
++++ b/drivers/power/supply/axp20x_battery.c
+@@ -303,11 +303,11 @@ static int axp20x_battery_get_prop(struct power_supply *psy,
+ val->intval = reg & AXP209_FG_PERCENT;
+ break;
+
+- case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
++ case POWER_SUPPLY_PROP_VOLTAGE_MAX:
+ return axp20x_batt->data->get_max_voltage(axp20x_batt,
+ &val->intval);
+
+- case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
++ case POWER_SUPPLY_PROP_VOLTAGE_MIN:
+ ret = regmap_read(axp20x_batt->regmap, AXP20X_V_OFF, ®);
+ if (ret)
+ return ret;
+@@ -455,10 +455,10 @@ static int axp20x_battery_set_prop(struct power_supply *psy,
+ struct axp20x_batt_ps *axp20x_batt = power_supply_get_drvdata(psy);
+
+ switch (psp) {
+- case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
++ case POWER_SUPPLY_PROP_VOLTAGE_MIN:
+ return axp20x_set_voltage_min_design(axp20x_batt, val->intval);
+
+- case POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN:
++ case POWER_SUPPLY_PROP_VOLTAGE_MAX:
+ return axp20x_batt->data->set_max_voltage(axp20x_batt, val->intval);
+
+ case POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT:
+@@ -493,8 +493,8 @@ static enum power_supply_property axp20x_battery_props[] = {
+ POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT,
+ POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX,
+ POWER_SUPPLY_PROP_HEALTH,
+- POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN,
+- POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN,
++ POWER_SUPPLY_PROP_VOLTAGE_MAX,
++ POWER_SUPPLY_PROP_VOLTAGE_MIN,
+ POWER_SUPPLY_PROP_CAPACITY,
+ };
+
+@@ -502,8 +502,8 @@ static int axp20x_battery_prop_writeable(struct power_supply *psy,
+ enum power_supply_property psp)
+ {
+ return psp == POWER_SUPPLY_PROP_STATUS ||
+- psp == POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN ||
+- psp == POWER_SUPPLY_PROP_VOLTAGE_MAX_DESIGN ||
++ psp == POWER_SUPPLY_PROP_VOLTAGE_MIN ||
++ psp == POWER_SUPPLY_PROP_VOLTAGE_MAX ||
+ psp == POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT ||
+ psp == POWER_SUPPLY_PROP_CONSTANT_CHARGE_CURRENT_MAX;
+ }
+diff --git a/drivers/power/supply/max17042_battery.c b/drivers/power/supply/max17042_battery.c
+index e7d37e422c3f6e..496c3e1f2ee6d6 100644
+--- a/drivers/power/supply/max17042_battery.c
++++ b/drivers/power/supply/max17042_battery.c
+@@ -853,7 +853,10 @@ static void max17042_set_soc_threshold(struct max17042_chip *chip, u16 off)
+ /* program interrupt thresholds such that we should
+ * get interrupt for every 'off' perc change in the soc
+ */
+- regmap_read(map, MAX17042_RepSOC, &soc);
++ if (chip->pdata->enable_current_sense)
++ regmap_read(map, MAX17042_RepSOC, &soc);
++ else
++ regmap_read(map, MAX17042_VFSOC, &soc);
+ soc >>= 8;
+ soc_tr = (soc + off) << 8;
+ if (off < soc)
+diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
+index 8e7f4c0473ab94..9bf9ed9a6a54f7 100644
+--- a/drivers/powercap/intel_rapl_common.c
++++ b/drivers/powercap/intel_rapl_common.c
+@@ -740,7 +740,7 @@ static struct rapl_primitive_info *get_rpi(struct rapl_package *rp, int prim)
+ {
+ struct rapl_primitive_info *rpi = rp->priv->rpi;
+
+- if (prim < 0 || prim > NR_RAPL_PRIMITIVES || !rpi)
++ if (prim < 0 || prim >= NR_RAPL_PRIMITIVES || !rpi)
+ return NULL;
+
+ return &rpi[prim];
+diff --git a/drivers/pps/clients/pps_parport.c b/drivers/pps/clients/pps_parport.c
+index af972cdc04b53c..53e9c304ae0a7a 100644
+--- a/drivers/pps/clients/pps_parport.c
++++ b/drivers/pps/clients/pps_parport.c
+@@ -149,6 +149,9 @@ static void parport_attach(struct parport *port)
+ }
+
+ index = ida_alloc(&pps_client_index, GFP_KERNEL);
++ if (index < 0)
++ goto err_free_device;
++
+ memset(&pps_client_cb, 0, sizeof(pps_client_cb));
+ pps_client_cb.private = device;
+ pps_client_cb.irq_func = parport_irq;
+@@ -159,7 +162,7 @@ static void parport_attach(struct parport *port)
+ index);
+ if (!device->pardev) {
+ pr_err("couldn't register with %s\n", port->name);
+- goto err_free;
++ goto err_free_ida;
+ }
+
+ if (parport_claim_or_block(device->pardev) < 0) {
+@@ -187,8 +190,9 @@ static void parport_attach(struct parport *port)
+ parport_release(device->pardev);
+ err_unregister_dev:
+ parport_unregister_device(device->pardev);
+-err_free:
++err_free_ida:
+ ida_free(&pps_client_index, index);
++err_free_device:
+ kfree(device);
+ }
+
+diff --git a/drivers/regulator/of_regulator.c b/drivers/regulator/of_regulator.c
+index 03afc160fc72ce..86b680adbf01c7 100644
+--- a/drivers/regulator/of_regulator.c
++++ b/drivers/regulator/of_regulator.c
+@@ -777,7 +777,7 @@ int of_regulator_bulk_get_all(struct device *dev, struct device_node *np,
+ name[i] = '\0';
+ tmp = regulator_get(dev, name);
+ if (IS_ERR(tmp)) {
+- ret = -EINVAL;
++ ret = PTR_ERR(tmp);
+ goto error;
+ }
+ (*consumers)[n].consumer = tmp;
+diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
+index 144c8e9a642e8b..448b9a5438e0b8 100644
+--- a/drivers/remoteproc/imx_rproc.c
++++ b/drivers/remoteproc/imx_rproc.c
+@@ -210,7 +210,7 @@ static const struct imx_rproc_att imx_rproc_att_imx8mq[] = {
+ /* QSPI Code - alias */
+ { 0x08000000, 0x08000000, 0x08000000, 0 },
+ /* DDR (Code) - alias */
+- { 0x10000000, 0x80000000, 0x0FFE0000, 0 },
++ { 0x10000000, 0x40000000, 0x0FFE0000, 0 },
+ /* TCML */
+ { 0x1FFE0000, 0x007E0000, 0x00020000, ATT_OWN | ATT_IOMEM},
+ /* TCMU */
+@@ -1076,6 +1076,8 @@ static int imx_rproc_probe(struct platform_device *pdev)
+ return -ENOMEM;
+ }
+
++ INIT_WORK(&priv->rproc_work, imx_rproc_vq_work);
++
+ ret = imx_rproc_xtr_mbox_init(rproc);
+ if (ret)
+ goto err_put_wkq;
+@@ -1094,8 +1096,6 @@ static int imx_rproc_probe(struct platform_device *pdev)
+ if (ret)
+ goto err_put_scu;
+
+- INIT_WORK(&priv->rproc_work, imx_rproc_vq_work);
+-
+ if (rproc->state != RPROC_DETACHED)
+ rproc->auto_boot = of_property_read_bool(np, "fsl,auto-boot");
+
+diff --git a/drivers/reset/reset-berlin.c b/drivers/reset/reset-berlin.c
+index 2537ec05eceefd..578fe867080ce0 100644
+--- a/drivers/reset/reset-berlin.c
++++ b/drivers/reset/reset-berlin.c
+@@ -68,13 +68,14 @@ static int berlin_reset_xlate(struct reset_controller_dev *rcdev,
+
+ static int berlin2_reset_probe(struct platform_device *pdev)
+ {
+- struct device_node *parent_np = of_get_parent(pdev->dev.of_node);
++ struct device_node *parent_np;
+ struct berlin_reset_priv *priv;
+
+ priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
++ parent_np = of_get_parent(pdev->dev.of_node);
+ priv->regmap = syscon_node_to_regmap(parent_np);
+ of_node_put(parent_np);
+ if (IS_ERR(priv->regmap))
+diff --git a/drivers/reset/reset-k210.c b/drivers/reset/reset-k210.c
+index b62a2fd44e4e42..e77e4cca377dca 100644
+--- a/drivers/reset/reset-k210.c
++++ b/drivers/reset/reset-k210.c
+@@ -90,7 +90,7 @@ static const struct reset_control_ops k210_rst_ops = {
+ static int k210_rst_probe(struct platform_device *pdev)
+ {
+ struct device *dev = &pdev->dev;
+- struct device_node *parent_np = of_get_parent(dev->of_node);
++ struct device_node *parent_np;
+ struct k210_rst *ksr;
+
+ dev_info(dev, "K210 reset controller\n");
+@@ -99,6 +99,7 @@ static int k210_rst_probe(struct platform_device *pdev)
+ if (!ksr)
+ return -ENOMEM;
+
++ parent_np = of_get_parent(dev->of_node);
+ ksr->map = syscon_node_to_regmap(parent_np);
+ of_node_put(parent_np);
+ if (IS_ERR(ksr->map))
+diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
+index 99fadfb4cd9f26..09acc321d0133f 100644
+--- a/drivers/s390/crypto/ap_bus.c
++++ b/drivers/s390/crypto/ap_bus.c
+@@ -107,6 +107,7 @@ debug_info_t *ap_dbf_info;
+ static bool ap_scan_bus(void);
+ static bool ap_scan_bus_result; /* result of last ap_scan_bus() */
+ static DEFINE_MUTEX(ap_scan_bus_mutex); /* mutex ap_scan_bus() invocations */
++static struct task_struct *ap_scan_bus_task; /* thread holding the scan mutex */
+ static atomic64_t ap_scan_bus_count; /* counter ap_scan_bus() invocations */
+ static int ap_scan_bus_time = AP_CONFIG_TIME;
+ static struct timer_list ap_scan_bus_timer;
+@@ -1006,11 +1007,25 @@ bool ap_bus_force_rescan(void)
+ if (scan_counter <= 0)
+ goto out;
+
++ /*
++ * There is one unlikely but nevertheless valid scenario where the
++ * thread holding the mutex may try to send some crypto load but
++ * all cards are offline so a rescan is triggered which causes
++ * a recursive call of ap_bus_force_rescan(). A simple return if
++ * the mutex is already locked by this thread solves this.
++ */
++ if (mutex_is_locked(&ap_scan_bus_mutex)) {
++ if (ap_scan_bus_task == current)
++ goto out;
++ }
++
+ /* Try to acquire the AP scan bus mutex */
+ if (mutex_trylock(&ap_scan_bus_mutex)) {
+ /* mutex acquired, run the AP bus scan */
++ ap_scan_bus_task = current;
+ ap_scan_bus_result = ap_scan_bus();
+ rc = ap_scan_bus_result;
++ ap_scan_bus_task = NULL;
+ mutex_unlock(&ap_scan_bus_mutex);
+ goto out;
+ }
+@@ -2284,7 +2299,9 @@ static void ap_scan_bus_wq_callback(struct work_struct *unused)
+ * system_long_wq which invokes this function here again.
+ */
+ if (mutex_trylock(&ap_scan_bus_mutex)) {
++ ap_scan_bus_task = current;
+ ap_scan_bus_result = ap_scan_bus();
++ ap_scan_bus_task = NULL;
+ mutex_unlock(&ap_scan_bus_mutex);
+ }
+ }
+diff --git a/drivers/scsi/NCR5380.c b/drivers/scsi/NCR5380.c
+index cea3a79d538e4b..00e245173320c3 100644
+--- a/drivers/scsi/NCR5380.c
++++ b/drivers/scsi/NCR5380.c
+@@ -1485,6 +1485,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
+ unsigned char **data)
+ {
+ struct NCR5380_hostdata *hostdata = shost_priv(instance);
++ struct NCR5380_cmd *ncmd = NCR5380_to_ncmd(hostdata->connected);
+ int c = *count;
+ unsigned char p = *phase;
+ unsigned char *d = *data;
+@@ -1496,7 +1497,7 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
+ return -1;
+ }
+
+- NCR5380_to_ncmd(hostdata->connected)->phase = p;
++ ncmd->phase = p;
+
+ if (p & SR_IO) {
+ if (hostdata->read_overruns)
+@@ -1608,45 +1609,44 @@ static int NCR5380_transfer_dma(struct Scsi_Host *instance,
+ * request.
+ */
+
+- if (hostdata->flags & FLAG_DMA_FIXUP) {
+- if (p & SR_IO) {
+- /*
+- * The workaround was to transfer fewer bytes than we
+- * intended to with the pseudo-DMA read function, wait for
+- * the chip to latch the last byte, read it, and then disable
+- * pseudo-DMA mode.
+- *
+- * After REQ is asserted, the NCR5380 asserts DRQ and ACK.
+- * REQ is deasserted when ACK is asserted, and not reasserted
+- * until ACK goes false. Since the NCR5380 won't lower ACK
+- * until DACK is asserted, which won't happen unless we twiddle
+- * the DMA port or we take the NCR5380 out of DMA mode, we
+- * can guarantee that we won't handshake another extra
+- * byte.
+- */
+-
+- if (NCR5380_poll_politely(hostdata, BUS_AND_STATUS_REG,
+- BASR_DRQ, BASR_DRQ, 0) < 0) {
+- result = -1;
+- shost_printk(KERN_ERR, instance, "PDMA read: DRQ timeout\n");
+- }
+- if (NCR5380_poll_politely(hostdata, STATUS_REG,
+- SR_REQ, 0, 0) < 0) {
+- result = -1;
+- shost_printk(KERN_ERR, instance, "PDMA read: !REQ timeout\n");
+- }
+- d[*count - 1] = NCR5380_read(INPUT_DATA_REG);
+- } else {
+- /*
+- * Wait for the last byte to be sent. If REQ is being asserted for
+- * the byte we're interested, we'll ACK it and it will go false.
+- */
+- if (NCR5380_poll_politely2(hostdata,
+- BUS_AND_STATUS_REG, BASR_DRQ, BASR_DRQ,
+- BUS_AND_STATUS_REG, BASR_PHASE_MATCH, 0, 0) < 0) {
+- result = -1;
+- shost_printk(KERN_ERR, instance, "PDMA write: DRQ and phase timeout\n");
++ if ((hostdata->flags & FLAG_DMA_FIXUP) &&
++ (NCR5380_read(BUS_AND_STATUS_REG) & BASR_PHASE_MATCH)) {
++ /*
++ * The workaround was to transfer fewer bytes than we
++ * intended to with the pseudo-DMA receive function, wait for
++ * the chip to latch the last byte, read it, and then disable
++ * DMA mode.
++ *
++ * After REQ is asserted, the NCR5380 asserts DRQ and ACK.
++ * REQ is deasserted when ACK is asserted, and not reasserted
++ * until ACK goes false. Since the NCR5380 won't lower ACK
++ * until DACK is asserted, which won't happen unless we twiddle
++ * the DMA port or we take the NCR5380 out of DMA mode, we
++ * can guarantee that we won't handshake another extra
++ * byte.
++ *
++ * If sending, wait for the last byte to be sent. If REQ is
++ * being asserted for the byte we're interested, we'll ACK it
++ * and it will go false.
++ */
++ if (!NCR5380_poll_politely(hostdata, BUS_AND_STATUS_REG,
++ BASR_DRQ, BASR_DRQ, 0)) {
++ if ((p & SR_IO) &&
++ (NCR5380_read(BUS_AND_STATUS_REG) & BASR_PHASE_MATCH)) {
++ if (!NCR5380_poll_politely(hostdata, STATUS_REG,
++ SR_REQ, 0, 0)) {
++ d[c] = NCR5380_read(INPUT_DATA_REG);
++ --ncmd->this_residual;
++ } else {
++ result = -1;
++ scmd_printk(KERN_ERR, hostdata->connected,
++ "PDMA fixup: !REQ timeout\n");
++ }
+ }
++ } else if (NCR5380_read(BUS_AND_STATUS_REG) & BASR_PHASE_MATCH) {
++ result = -1;
++ scmd_printk(KERN_ERR, hostdata->connected,
++ "PDMA fixup: DRQ timeout\n");
+ }
+ }
+
+diff --git a/drivers/scsi/elx/libefc/efc_nport.c b/drivers/scsi/elx/libefc/efc_nport.c
+index 2e83a667901fec..1a7437f4328e87 100644
+--- a/drivers/scsi/elx/libefc/efc_nport.c
++++ b/drivers/scsi/elx/libefc/efc_nport.c
+@@ -705,9 +705,9 @@ efc_nport_vport_del(struct efc *efc, struct efc_domain *domain,
+ spin_lock_irqsave(&efc->lock, flags);
+ list_for_each_entry(nport, &domain->nport_list, list_entry) {
+ if (nport->wwpn == wwpn && nport->wwnn == wwnn) {
+- kref_put(&nport->ref, nport->release);
+ /* Shutdown this NPORT */
+ efc_sm_post_event(&nport->sm, EFC_EVT_SHUTDOWN, NULL);
++ kref_put(&nport->ref, nport->release);
+ break;
+ }
+ }
+diff --git a/drivers/scsi/lpfc/lpfc_hw4.h b/drivers/scsi/lpfc/lpfc_hw4.h
+index 500253007b1dc8..26e1313ebb21fc 100644
+--- a/drivers/scsi/lpfc/lpfc_hw4.h
++++ b/drivers/scsi/lpfc/lpfc_hw4.h
+@@ -4847,6 +4847,7 @@ struct fcp_iwrite64_wqe {
+ #define cmd_buff_len_SHIFT 16
+ #define cmd_buff_len_MASK 0x00000ffff
+ #define cmd_buff_len_WORD word3
++/* Note: payload_offset_len field depends on ASIC support */
+ #define payload_offset_len_SHIFT 0
+ #define payload_offset_len_MASK 0x0000ffff
+ #define payload_offset_len_WORD word3
+@@ -4863,6 +4864,7 @@ struct fcp_iread64_wqe {
+ #define cmd_buff_len_SHIFT 16
+ #define cmd_buff_len_MASK 0x00000ffff
+ #define cmd_buff_len_WORD word3
++/* Note: payload_offset_len field depends on ASIC support */
+ #define payload_offset_len_SHIFT 0
+ #define payload_offset_len_MASK 0x0000ffff
+ #define payload_offset_len_WORD word3
+@@ -4879,6 +4881,7 @@ struct fcp_icmnd64_wqe {
+ #define cmd_buff_len_SHIFT 16
+ #define cmd_buff_len_MASK 0x00000ffff
+ #define cmd_buff_len_WORD word3
++/* Note: payload_offset_len field depends on ASIC support */
+ #define payload_offset_len_SHIFT 0
+ #define payload_offset_len_MASK 0x0000ffff
+ #define payload_offset_len_WORD word3
+diff --git a/drivers/scsi/lpfc/lpfc_init.c b/drivers/scsi/lpfc/lpfc_init.c
+index e1dfa96c2a553a..0c1404dc5f3bdb 100644
+--- a/drivers/scsi/lpfc/lpfc_init.c
++++ b/drivers/scsi/lpfc/lpfc_init.c
+@@ -4699,6 +4699,7 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
+ uint64_t wwn;
+ bool use_no_reset_hba = false;
+ int rc;
++ u8 if_type;
+
+ if (lpfc_no_hba_reset_cnt) {
+ if (phba->sli_rev < LPFC_SLI_REV4 &&
+@@ -4773,10 +4774,24 @@ lpfc_create_port(struct lpfc_hba *phba, int instance, struct device *dev)
+ shost->max_id = LPFC_MAX_TARGET;
+ shost->max_lun = vport->cfg_max_luns;
+ shost->this_id = -1;
+- if (phba->sli_rev == LPFC_SLI_REV4)
+- shost->max_cmd_len = LPFC_FCP_CDB_LEN_32;
+- else
++
++ /* Set max_cmd_len applicable to ASIC support */
++ if (phba->sli_rev == LPFC_SLI_REV4) {
++ if_type = bf_get(lpfc_sli_intf_if_type,
++ &phba->sli4_hba.sli_intf);
++ switch (if_type) {
++ case LPFC_SLI_INTF_IF_TYPE_2:
++ fallthrough;
++ case LPFC_SLI_INTF_IF_TYPE_6:
++ shost->max_cmd_len = LPFC_FCP_CDB_LEN_32;
++ break;
++ default:
++ shost->max_cmd_len = LPFC_FCP_CDB_LEN;
++ break;
++ }
++ } else {
+ shost->max_cmd_len = LPFC_FCP_CDB_LEN;
++ }
+
+ if (phba->sli_rev == LPFC_SLI_REV4) {
+ if (!phba->cfg_fcp_mq_threshold ||
+diff --git a/drivers/scsi/lpfc/lpfc_scsi.c b/drivers/scsi/lpfc/lpfc_scsi.c
+index 98ce9d97a22570..9f0b59672e1915 100644
+--- a/drivers/scsi/lpfc/lpfc_scsi.c
++++ b/drivers/scsi/lpfc/lpfc_scsi.c
+@@ -4760,7 +4760,7 @@ static int lpfc_scsi_prep_cmnd_buf_s4(struct lpfc_vport *vport,
+
+ /* Word 3 */
+ bf_set(payload_offset_len, &wqe->fcp_icmd,
+- sizeof(struct fcp_cmnd32) + sizeof(struct fcp_rsp));
++ sizeof(struct fcp_cmnd) + sizeof(struct fcp_rsp));
+
+ /* Word 6 */
+ bf_set(wqe_ctxt_tag, &wqe->generic.wqe_com,
+diff --git a/drivers/scsi/mac_scsi.c b/drivers/scsi/mac_scsi.c
+index a402c4dc4645d3..2e9fad1e3069ec 100644
+--- a/drivers/scsi/mac_scsi.c
++++ b/drivers/scsi/mac_scsi.c
+@@ -102,11 +102,15 @@ __setup("mac5380=", mac_scsi_setup);
+ * Linux SCSI drivers lack knowledge of the timing behaviour of SCSI targets
+ * so bus errors are unavoidable.
+ *
+- * If a MOVE.B instruction faults, we assume that zero bytes were transferred
+- * and simply retry. That assumption probably depends on target behaviour but
+- * seems to hold up okay. The NOP provides synchronization: without it the
+- * fault can sometimes occur after the program counter has moved past the
+- * offending instruction. Post-increment addressing can't be used.
++ * If a MOVE.B instruction faults during a receive operation, we assume the
++ * target sent nothing and try again. That assumption probably depends on
++ * target firmware but it seems to hold up okay. If a fault happens during a
++ * send operation, the target may or may not have seen /ACK and got the byte.
++ * It's uncertain so the whole SCSI command gets retried.
++ *
++ * The NOP is needed for synchronization because the fault address in the
++ * exception stack frame may or may not be the instruction that actually
++ * caused the bus error. Post-increment addressing can't be used.
+ */
+
+ #define MOVE_BYTE(operands) \
+@@ -208,8 +212,6 @@ __setup("mac5380=", mac_scsi_setup);
+ ".previous \n" \
+ : "+a" (addr), "+r" (n), "+r" (result) : "a" (io))
+
+-#define MAC_PDMA_DELAY 32
+-
+ static inline int mac_pdma_recv(void __iomem *io, unsigned char *start, int n)
+ {
+ unsigned char *addr = start;
+@@ -245,22 +247,21 @@ static inline int mac_pdma_send(unsigned char *start, void __iomem *io, int n)
+ if (n >= 1) {
+ MOVE_BYTE("%0@,%3@");
+ if (result)
+- goto out;
++ return -1;
+ }
+ if (n >= 1 && ((unsigned long)addr & 1)) {
+ MOVE_BYTE("%0@,%3@");
+ if (result)
+- goto out;
++ return -2;
+ }
+ while (n >= 32)
+ MOVE_16_WORDS("%0@+,%3@");
+ while (n >= 2)
+ MOVE_WORD("%0@+,%3@");
+ if (result)
+- return start - addr; /* Negated to indicate uncertain length */
++ return start - addr - 1; /* Negated to indicate uncertain length */
+ if (n == 1)
+ MOVE_BYTE("%0@,%3@");
+-out:
+ return addr - start;
+ }
+
+@@ -274,25 +275,56 @@ static inline void write_ctrl_reg(struct NCR5380_hostdata *hostdata, u32 value)
+ out_be32(hostdata->io + (CTRL_REG << 4), value);
+ }
+
++static inline int macscsi_wait_for_drq(struct NCR5380_hostdata *hostdata)
++{
++ unsigned int n = 1; /* effectively multiplies NCR5380_REG_POLL_TIME */
++ unsigned char basr;
++
++again:
++ basr = NCR5380_read(BUS_AND_STATUS_REG);
++
++ if (!(basr & BASR_PHASE_MATCH))
++ return 1;
++
++ if (basr & BASR_IRQ)
++ return -1;
++
++ if (basr & BASR_DRQ)
++ return 0;
++
++ if (n-- == 0) {
++ NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
++ dsprintk(NDEBUG_PSEUDO_DMA, hostdata->host,
++ "%s: DRQ timeout\n", __func__);
++ return -1;
++ }
++
++ NCR5380_poll_politely2(hostdata,
++ BUS_AND_STATUS_REG, BASR_DRQ, BASR_DRQ,
++ BUS_AND_STATUS_REG, BASR_PHASE_MATCH, 0, 0);
++ goto again;
++}
++
+ static inline int macscsi_pread(struct NCR5380_hostdata *hostdata,
+ unsigned char *dst, int len)
+ {
+ u8 __iomem *s = hostdata->pdma_io + (INPUT_DATA_REG << 4);
+ unsigned char *d = dst;
+- int result = 0;
+
+ hostdata->pdma_residual = len;
+
+- while (!NCR5380_poll_politely(hostdata, BUS_AND_STATUS_REG,
+- BASR_DRQ | BASR_PHASE_MATCH,
+- BASR_DRQ | BASR_PHASE_MATCH, 0)) {
+- int bytes;
++ while (macscsi_wait_for_drq(hostdata) == 0) {
++ int bytes, chunk_bytes;
+
+ if (macintosh_config->ident == MAC_MODEL_IIFX)
+ write_ctrl_reg(hostdata, CTRL_HANDSHAKE_MODE |
+ CTRL_INTERRUPTS_ENABLE);
+
+- bytes = mac_pdma_recv(s, d, min(hostdata->pdma_residual, 512));
++ chunk_bytes = min(hostdata->pdma_residual, 512);
++ bytes = mac_pdma_recv(s, d, chunk_bytes);
++
++ if (macintosh_config->ident == MAC_MODEL_IIFX)
++ write_ctrl_reg(hostdata, CTRL_INTERRUPTS_ENABLE);
+
+ if (bytes > 0) {
+ d += bytes;
+@@ -300,37 +332,25 @@ static inline int macscsi_pread(struct NCR5380_hostdata *hostdata,
+ }
+
+ if (hostdata->pdma_residual == 0)
+- goto out;
++ break;
+
+- if (NCR5380_poll_politely2(hostdata, STATUS_REG, SR_REQ, SR_REQ,
+- BUS_AND_STATUS_REG, BASR_ACK,
+- BASR_ACK, 0) < 0)
+- scmd_printk(KERN_DEBUG, hostdata->connected,
+- "%s: !REQ and !ACK\n", __func__);
+- if (!(NCR5380_read(BUS_AND_STATUS_REG) & BASR_PHASE_MATCH))
+- goto out;
++ if (bytes > 0)
++ continue;
+
+- if (bytes == 0)
+- udelay(MAC_PDMA_DELAY);
++ NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
++ dsprintk(NDEBUG_PSEUDO_DMA, hostdata->host,
++ "%s: bus error [%d/%d] (%d/%d)\n",
++ __func__, d - dst, len, bytes, chunk_bytes);
+
+- if (bytes >= 0)
++ if (bytes == 0)
+ continue;
+
+- dsprintk(NDEBUG_PSEUDO_DMA, hostdata->host,
+- "%s: bus error (%d/%d)\n", __func__, d - dst, len);
+- NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
+- result = -1;
+- goto out;
++ if (macscsi_wait_for_drq(hostdata) <= 0)
++ set_host_byte(hostdata->connected, DID_ERROR);
++ break;
+ }
+
+- scmd_printk(KERN_ERR, hostdata->connected,
+- "%s: phase mismatch or !DRQ\n", __func__);
+- NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
+- result = -1;
+-out:
+- if (macintosh_config->ident == MAC_MODEL_IIFX)
+- write_ctrl_reg(hostdata, CTRL_INTERRUPTS_ENABLE);
+- return result;
++ return 0;
+ }
+
+ static inline int macscsi_pwrite(struct NCR5380_hostdata *hostdata,
+@@ -338,67 +358,47 @@ static inline int macscsi_pwrite(struct NCR5380_hostdata *hostdata,
+ {
+ unsigned char *s = src;
+ u8 __iomem *d = hostdata->pdma_io + (OUTPUT_DATA_REG << 4);
+- int result = 0;
+
+ hostdata->pdma_residual = len;
+
+- while (!NCR5380_poll_politely(hostdata, BUS_AND_STATUS_REG,
+- BASR_DRQ | BASR_PHASE_MATCH,
+- BASR_DRQ | BASR_PHASE_MATCH, 0)) {
+- int bytes;
++ while (macscsi_wait_for_drq(hostdata) == 0) {
++ int bytes, chunk_bytes;
+
+ if (macintosh_config->ident == MAC_MODEL_IIFX)
+ write_ctrl_reg(hostdata, CTRL_HANDSHAKE_MODE |
+ CTRL_INTERRUPTS_ENABLE);
+
+- bytes = mac_pdma_send(s, d, min(hostdata->pdma_residual, 512));
++ chunk_bytes = min(hostdata->pdma_residual, 512);
++ bytes = mac_pdma_send(s, d, chunk_bytes);
++
++ if (macintosh_config->ident == MAC_MODEL_IIFX)
++ write_ctrl_reg(hostdata, CTRL_INTERRUPTS_ENABLE);
+
+ if (bytes > 0) {
+ s += bytes;
+ hostdata->pdma_residual -= bytes;
+ }
+
+- if (hostdata->pdma_residual == 0) {
+- if (NCR5380_poll_politely(hostdata, TARGET_COMMAND_REG,
+- TCR_LAST_BYTE_SENT,
+- TCR_LAST_BYTE_SENT,
+- 0) < 0) {
+- scmd_printk(KERN_ERR, hostdata->connected,
+- "%s: Last Byte Sent timeout\n", __func__);
+- result = -1;
+- }
+- goto out;
+- }
++ if (hostdata->pdma_residual == 0)
++ break;
+
+- if (NCR5380_poll_politely2(hostdata, STATUS_REG, SR_REQ, SR_REQ,
+- BUS_AND_STATUS_REG, BASR_ACK,
+- BASR_ACK, 0) < 0)
+- scmd_printk(KERN_DEBUG, hostdata->connected,
+- "%s: !REQ and !ACK\n", __func__);
+- if (!(NCR5380_read(BUS_AND_STATUS_REG) & BASR_PHASE_MATCH))
+- goto out;
++ if (bytes > 0)
++ continue;
+
+- if (bytes == 0)
+- udelay(MAC_PDMA_DELAY);
++ NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
++ dsprintk(NDEBUG_PSEUDO_DMA, hostdata->host,
++ "%s: bus error [%d/%d] (%d/%d)\n",
++ __func__, s - src, len, bytes, chunk_bytes);
+
+- if (bytes >= 0)
++ if (bytes == 0)
+ continue;
+
+- dsprintk(NDEBUG_PSEUDO_DMA, hostdata->host,
+- "%s: bus error (%d/%d)\n", __func__, s - src, len);
+- NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
+- result = -1;
+- goto out;
++ if (macscsi_wait_for_drq(hostdata) <= 0)
++ set_host_byte(hostdata->connected, DID_ERROR);
++ break;
+ }
+
+- scmd_printk(KERN_ERR, hostdata->connected,
+- "%s: phase mismatch or !DRQ\n", __func__);
+- NCR5380_dprint(NDEBUG_PSEUDO_DMA, hostdata->host);
+- result = -1;
+-out:
+- if (macintosh_config->ident == MAC_MODEL_IIFX)
+- write_ctrl_reg(hostdata, CTRL_INTERRUPTS_ENABLE);
+- return result;
++ return 0;
+ }
+
+ static int macscsi_dma_xfer_len(struct NCR5380_hostdata *hostdata,
+diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
+index 7d2a294ebc3d79..5dd100175ec616 100644
+--- a/drivers/scsi/sd.c
++++ b/drivers/scsi/sd.c
+@@ -3283,7 +3283,7 @@ static void sd_read_block_characteristics(struct scsi_disk *sdkp)
+ rcu_read_lock();
+ vpd = rcu_dereference(sdkp->device->vpd_pgb1);
+
+- if (!vpd || vpd->len < 8) {
++ if (!vpd || vpd->len <= 8) {
+ rcu_read_unlock();
+ return;
+ }
+diff --git a/drivers/scsi/smartpqi/smartpqi_init.c b/drivers/scsi/smartpqi/smartpqi_init.c
+index 24c7cb285dca0f..c1524fb334eb5c 100644
+--- a/drivers/scsi/smartpqi/smartpqi_init.c
++++ b/drivers/scsi/smartpqi/smartpqi_init.c
+@@ -2354,14 +2354,6 @@ static inline void pqi_mask_device(u8 *scsi3addr)
+ scsi3addr[3] |= 0xc0;
+ }
+
+-static inline bool pqi_is_multipath_device(struct pqi_scsi_dev *device)
+-{
+- if (pqi_is_logical_device(device))
+- return false;
+-
+- return (device->path_map & (device->path_map - 1)) != 0;
+-}
+-
+ static inline bool pqi_expose_device(struct pqi_scsi_dev *device)
+ {
+ return !device->is_physical_device || !pqi_skip_device(device->scsi3addr);
+@@ -3258,14 +3250,12 @@ static void pqi_process_aio_io_error(struct pqi_io_request *io_request)
+ int residual_count;
+ int xfer_count;
+ bool device_offline;
+- struct pqi_scsi_dev *device;
+
+ scmd = io_request->scmd;
+ error_info = io_request->error_info;
+ host_byte = DID_OK;
+ sense_data_length = 0;
+ device_offline = false;
+- device = scmd->device->hostdata;
+
+ switch (error_info->service_response) {
+ case PQI_AIO_SERV_RESPONSE_COMPLETE:
+@@ -3290,14 +3280,8 @@ static void pqi_process_aio_io_error(struct pqi_io_request *io_request)
+ break;
+ case PQI_AIO_STATUS_AIO_PATH_DISABLED:
+ pqi_aio_path_disabled(io_request);
+- if (pqi_is_multipath_device(device)) {
+- pqi_device_remove_start(device);
+- host_byte = DID_NO_CONNECT;
+- scsi_status = SAM_STAT_CHECK_CONDITION;
+- } else {
+- scsi_status = SAM_STAT_GOOD;
+- io_request->status = -EAGAIN;
+- }
++ scsi_status = SAM_STAT_GOOD;
++ io_request->status = -EAGAIN;
+ break;
+ case PQI_AIO_STATUS_NO_PATH_TO_DEVICE:
+ case PQI_AIO_STATUS_INVALID_DEVICE:
+diff --git a/drivers/soc/fsl/qe/qmc.c b/drivers/soc/fsl/qe/qmc.c
+index f498db9abe35f0..04035706b96dc8 100644
+--- a/drivers/soc/fsl/qe/qmc.c
++++ b/drivers/soc/fsl/qe/qmc.c
+@@ -940,11 +940,13 @@ static int qmc_chan_start_rx(struct qmc_chan *chan)
+ goto end;
+ }
+
+- ret = qmc_setup_chan_trnsync(chan->qmc, chan);
+- if (ret) {
+- dev_err(chan->qmc->dev, "chan %u: setup TRNSYNC failed (%d)\n",
+- chan->id, ret);
+- goto end;
++ if (chan->mode == QMC_TRANSPARENT) {
++ ret = qmc_setup_chan_trnsync(chan->qmc, chan);
++ if (ret) {
++ dev_err(chan->qmc->dev, "chan %u: setup TRNSYNC failed (%d)\n",
++ chan->id, ret);
++ goto end;
++ }
+ }
+
+ /* Restart the receiver */
+@@ -982,11 +984,13 @@ static int qmc_chan_start_tx(struct qmc_chan *chan)
+ goto end;
+ }
+
+- ret = qmc_setup_chan_trnsync(chan->qmc, chan);
+- if (ret) {
+- dev_err(chan->qmc->dev, "chan %u: setup TRNSYNC failed (%d)\n",
+- chan->id, ret);
+- goto end;
++ if (chan->mode == QMC_TRANSPARENT) {
++ ret = qmc_setup_chan_trnsync(chan->qmc, chan);
++ if (ret) {
++ dev_err(chan->qmc->dev, "chan %u: setup TRNSYNC failed (%d)\n",
++ chan->id, ret);
++ goto end;
++ }
+ }
+
+ /*
+diff --git a/drivers/soc/fsl/qe/tsa.c b/drivers/soc/fsl/qe/tsa.c
+index 6c5741cf5e9d2a..53968ea84c8872 100644
+--- a/drivers/soc/fsl/qe/tsa.c
++++ b/drivers/soc/fsl/qe/tsa.c
+@@ -140,7 +140,7 @@ static inline void tsa_write32(void __iomem *addr, u32 val)
+ iowrite32be(val, addr);
+ }
+
+-static inline void tsa_write8(void __iomem *addr, u32 val)
++static inline void tsa_write8(void __iomem *addr, u8 val)
+ {
+ iowrite8(val, addr);
+ }
+diff --git a/drivers/soc/qcom/smd-rpm.c b/drivers/soc/qcom/smd-rpm.c
+index b7056aed4c7d10..9d64283d212549 100644
+--- a/drivers/soc/qcom/smd-rpm.c
++++ b/drivers/soc/qcom/smd-rpm.c
+@@ -196,9 +196,6 @@ static int qcom_smd_rpm_probe(struct rpmsg_device *rpdev)
+ {
+ struct qcom_smd_rpm *rpm;
+
+- if (!rpdev->dev.of_node)
+- return -EINVAL;
+-
+ rpm = devm_kzalloc(&rpdev->dev, sizeof(*rpm), GFP_KERNEL);
+ if (!rpm)
+ return -ENOMEM;
+@@ -218,18 +215,38 @@ static void qcom_smd_rpm_remove(struct rpmsg_device *rpdev)
+ of_platform_depopulate(&rpdev->dev);
+ }
+
+-static const struct rpmsg_device_id qcom_smd_rpm_id_table[] = {
+- { .name = "rpm_requests", },
+- { /* sentinel */ }
++static const struct of_device_id qcom_smd_rpm_of_match[] = {
++ { .compatible = "qcom,rpm-apq8084" },
++ { .compatible = "qcom,rpm-ipq6018" },
++ { .compatible = "qcom,rpm-ipq9574" },
++ { .compatible = "qcom,rpm-msm8226" },
++ { .compatible = "qcom,rpm-msm8909" },
++ { .compatible = "qcom,rpm-msm8916" },
++ { .compatible = "qcom,rpm-msm8936" },
++ { .compatible = "qcom,rpm-msm8953" },
++ { .compatible = "qcom,rpm-msm8974" },
++ { .compatible = "qcom,rpm-msm8976" },
++ { .compatible = "qcom,rpm-msm8994" },
++ { .compatible = "qcom,rpm-msm8996" },
++ { .compatible = "qcom,rpm-msm8998" },
++ { .compatible = "qcom,rpm-sdm660" },
++ { .compatible = "qcom,rpm-sm6115" },
++ { .compatible = "qcom,rpm-sm6125" },
++ { .compatible = "qcom,rpm-sm6375" },
++ { .compatible = "qcom,rpm-qcm2290" },
++ { .compatible = "qcom,rpm-qcs404" },
++ {}
+ };
+-MODULE_DEVICE_TABLE(rpmsg, qcom_smd_rpm_id_table);
++MODULE_DEVICE_TABLE(of, qcom_smd_rpm_of_match);
+
+ static struct rpmsg_driver qcom_smd_rpm_driver = {
+ .probe = qcom_smd_rpm_probe,
+ .remove = qcom_smd_rpm_remove,
+ .callback = qcom_smd_rpm_callback,
+- .id_table = qcom_smd_rpm_id_table,
+- .drv.name = "qcom_smd_rpm",
++ .drv = {
++ .name = "qcom_smd_rpm",
++ .of_match_table = qcom_smd_rpm_of_match,
++ },
+ };
+
+ static int __init qcom_smd_rpm_init(void)
+diff --git a/drivers/soc/versatile/soc-integrator.c b/drivers/soc/versatile/soc-integrator.c
+index bab4ad87aa7500..d5099a3386b4fc 100644
+--- a/drivers/soc/versatile/soc-integrator.c
++++ b/drivers/soc/versatile/soc-integrator.c
+@@ -113,6 +113,7 @@ static int __init integrator_soc_init(void)
+ return -ENODEV;
+
+ syscon_regmap = syscon_node_to_regmap(np);
++ of_node_put(np);
+ if (IS_ERR(syscon_regmap))
+ return PTR_ERR(syscon_regmap);
+
+diff --git a/drivers/soc/versatile/soc-realview.c b/drivers/soc/versatile/soc-realview.c
+index c6876d232d8fd6..cf91abe07d38d0 100644
+--- a/drivers/soc/versatile/soc-realview.c
++++ b/drivers/soc/versatile/soc-realview.c
+@@ -4,6 +4,7 @@
+ *
+ * Author: Linus Walleij <linus.walleij@linaro.org>
+ */
++#include <linux/device.h>
+ #include <linux/init.h>
+ #include <linux/io.h>
+ #include <linux/slab.h>
+@@ -81,6 +82,13 @@ static struct attribute *realview_attrs[] = {
+
+ ATTRIBUTE_GROUPS(realview);
+
++static void realview_soc_socdev_release(void *data)
++{
++ struct soc_device *soc_dev = data;
++
++ soc_device_unregister(soc_dev);
++}
++
+ static int realview_soc_probe(struct platform_device *pdev)
+ {
+ struct regmap *syscon_regmap;
+@@ -93,7 +101,7 @@ static int realview_soc_probe(struct platform_device *pdev)
+ if (IS_ERR(syscon_regmap))
+ return PTR_ERR(syscon_regmap);
+
+- soc_dev_attr = kzalloc(sizeof(*soc_dev_attr), GFP_KERNEL);
++ soc_dev_attr = devm_kzalloc(&pdev->dev, sizeof(*soc_dev_attr), GFP_KERNEL);
+ if (!soc_dev_attr)
+ return -ENOMEM;
+
+@@ -106,10 +114,14 @@ static int realview_soc_probe(struct platform_device *pdev)
+ soc_dev_attr->family = "Versatile";
+ soc_dev_attr->custom_attr_group = realview_groups[0];
+ soc_dev = soc_device_register(soc_dev_attr);
+- if (IS_ERR(soc_dev)) {
+- kfree(soc_dev_attr);
++ if (IS_ERR(soc_dev))
+ return -ENODEV;
+- }
++
++ ret = devm_add_action_or_reset(&pdev->dev, realview_soc_socdev_release,
++ soc_dev);
++ if (ret)
++ return ret;
++
+ ret = regmap_read(syscon_regmap, REALVIEW_SYS_ID_OFFSET,
+ &realview_coreid);
+ if (ret)
+diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
+index 5aaff3bee1b78f..9ea91432c11d81 100644
+--- a/drivers/spi/atmel-quadspi.c
++++ b/drivers/spi/atmel-quadspi.c
+@@ -375,9 +375,9 @@ static int atmel_qspi_set_cfg(struct atmel_qspi *aq,
+ * If the QSPI controller is set in regular SPI mode, set it in
+ * Serial Memory Mode (SMM).
+ */
+- if (aq->mr != QSPI_MR_SMM) {
+- atmel_qspi_write(QSPI_MR_SMM, aq, QSPI_MR);
+- aq->mr = QSPI_MR_SMM;
++ if (!(aq->mr & QSPI_MR_SMM)) {
++ aq->mr |= QSPI_MR_SMM;
++ atmel_qspi_write(aq->mr, aq, QSPI_MR);
+ }
+
+ /* Clear pending interrupts */
+@@ -501,7 +501,8 @@ static int atmel_qspi_setup(struct spi_device *spi)
+ if (ret < 0)
+ return ret;
+
+- aq->scr = QSPI_SCR_SCBR(scbr);
++ aq->scr &= ~QSPI_SCR_SCBR_MASK;
++ aq->scr |= QSPI_SCR_SCBR(scbr);
+ atmel_qspi_write(aq->scr, aq, QSPI_SCR);
+
+ pm_runtime_mark_last_busy(ctrl->dev.parent);
+@@ -534,6 +535,7 @@ static int atmel_qspi_set_cs_timing(struct spi_device *spi)
+ if (ret < 0)
+ return ret;
+
++ aq->scr &= ~QSPI_SCR_DLYBS_MASK;
+ aq->scr |= QSPI_SCR_DLYBS(cs_setup);
+ atmel_qspi_write(aq->scr, aq, QSPI_SCR);
+
+@@ -549,8 +551,8 @@ static void atmel_qspi_init(struct atmel_qspi *aq)
+ atmel_qspi_write(QSPI_CR_SWRST, aq, QSPI_CR);
+
+ /* Set the QSPI controller by default in Serial Memory Mode */
+- atmel_qspi_write(QSPI_MR_SMM, aq, QSPI_MR);
+- aq->mr = QSPI_MR_SMM;
++ aq->mr |= QSPI_MR_SMM;
++ atmel_qspi_write(aq->mr, aq, QSPI_MR);
+
+ /* Enable the QSPI controller */
+ atmel_qspi_write(QSPI_CR_QSPIEN, aq, QSPI_CR);
+@@ -726,6 +728,7 @@ static void atmel_qspi_remove(struct platform_device *pdev)
+ clk_unprepare(aq->pclk);
+
+ pm_runtime_disable(&pdev->dev);
++ pm_runtime_dont_use_autosuspend(&pdev->dev);
+ pm_runtime_put_noidle(&pdev->dev);
+ }
+
+diff --git a/drivers/spi/spi-airoha-snfi.c b/drivers/spi/spi-airoha-snfi.c
+index 9d97ec98881cc9..94458df53eae23 100644
+--- a/drivers/spi/spi-airoha-snfi.c
++++ b/drivers/spi/spi-airoha-snfi.c
+@@ -211,9 +211,6 @@ struct airoha_snand_dev {
+
+ u8 *txrx_buf;
+ dma_addr_t dma_addr;
+-
+- u64 cur_page_num;
+- bool data_need_update;
+ };
+
+ struct airoha_snand_ctrl {
+@@ -405,7 +402,7 @@ static int airoha_snand_write_data(struct airoha_snand_ctrl *as_ctrl, u8 cmd,
+ for (i = 0; i < len; i += data_len) {
+ int err;
+
+- data_len = min(len, SPI_MAX_TRANSFER_SIZE);
++ data_len = min(len - i, SPI_MAX_TRANSFER_SIZE);
+ err = airoha_snand_set_fifo_op(as_ctrl, cmd, data_len);
+ if (err)
+ return err;
+@@ -427,7 +424,7 @@ static int airoha_snand_read_data(struct airoha_snand_ctrl *as_ctrl, u8 *data,
+ for (i = 0; i < len; i += data_len) {
+ int err;
+
+- data_len = min(len, SPI_MAX_TRANSFER_SIZE);
++ data_len = min(len - i, SPI_MAX_TRANSFER_SIZE);
+ err = airoha_snand_set_fifo_op(as_ctrl, 0xc, data_len);
+ if (err)
+ return err;
+@@ -644,11 +641,6 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc,
+ u32 val, rd_mode;
+ int err;
+
+- if (!as_dev->data_need_update)
+- return len;
+-
+- as_dev->data_need_update = false;
+-
+ switch (op->cmd.opcode) {
+ case SPI_NAND_OP_READ_FROM_CACHE_DUAL:
+ rd_mode = 1;
+@@ -739,8 +731,13 @@ static ssize_t airoha_snand_dirmap_read(struct spi_mem_dirmap_desc *desc,
+ if (err)
+ return err;
+
+- err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_STA_CTL1,
+- SPI_NFI_READ_FROM_CACHE_DONE);
++ /*
++ * SPI_NFI_READ_FROM_CACHE_DONE bit must be written at the end
++ * of dirmap_read operation even if it is already set.
++ */
++ err = regmap_write_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_STA_CTL1,
++ SPI_NFI_READ_FROM_CACHE_DONE,
++ SPI_NFI_READ_FROM_CACHE_DONE);
+ if (err)
+ return err;
+
+@@ -870,8 +867,13 @@ static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc,
+ if (err)
+ return err;
+
+- err = regmap_set_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_STA_CTL1,
+- SPI_NFI_LOAD_TO_CACHE_DONE);
++ /*
++ * SPI_NFI_LOAD_TO_CACHE_DONE bit must be written at the end
++ * of dirmap_write operation even if it is already set.
++ */
++ err = regmap_write_bits(as_ctrl->regmap_nfi, REG_SPI_NFI_SNF_STA_CTL1,
++ SPI_NFI_LOAD_TO_CACHE_DONE,
++ SPI_NFI_LOAD_TO_CACHE_DONE);
+ if (err)
+ return err;
+
+@@ -885,23 +887,11 @@ static ssize_t airoha_snand_dirmap_write(struct spi_mem_dirmap_desc *desc,
+ static int airoha_snand_exec_op(struct spi_mem *mem,
+ const struct spi_mem_op *op)
+ {
+- struct airoha_snand_dev *as_dev = spi_get_ctldata(mem->spi);
+ u8 data[8], cmd, opcode = op->cmd.opcode;
+ struct airoha_snand_ctrl *as_ctrl;
+ int i, err;
+
+ as_ctrl = spi_controller_get_devdata(mem->spi->controller);
+- if (opcode == SPI_NAND_OP_PROGRAM_EXECUTE &&
+- op->addr.val == as_dev->cur_page_num) {
+- as_dev->data_need_update = true;
+- } else if (opcode == SPI_NAND_OP_PAGE_READ) {
+- if (!as_dev->data_need_update &&
+- op->addr.val == as_dev->cur_page_num)
+- return 0;
+-
+- as_dev->data_need_update = true;
+- as_dev->cur_page_num = op->addr.val;
+- }
+
+ /* switch to manual mode */
+ err = airoha_snand_set_mode(as_ctrl, SPI_MODE_MANUAL);
+@@ -986,7 +976,6 @@ static int airoha_snand_setup(struct spi_device *spi)
+ if (dma_mapping_error(as_ctrl->dev, as_dev->dma_addr))
+ return -ENOMEM;
+
+- as_dev->data_need_update = true;
+ spi_set_ctldata(spi, as_dev);
+
+ return 0;
+diff --git a/drivers/spi/spi-bcmbca-hsspi.c b/drivers/spi/spi-bcmbca-hsspi.c
+index 9f64afd8164ea9..4965bc86d7f52a 100644
+--- a/drivers/spi/spi-bcmbca-hsspi.c
++++ b/drivers/spi/spi-bcmbca-hsspi.c
+@@ -546,12 +546,14 @@ static int bcmbca_hsspi_probe(struct platform_device *pdev)
+ goto out_put_host;
+ }
+
+- pm_runtime_enable(&pdev->dev);
++ ret = devm_pm_runtime_enable(&pdev->dev);
++ if (ret)
++ goto out_put_host;
+
+ ret = sysfs_create_group(&pdev->dev.kobj, &bcmbca_hsspi_group);
+ if (ret) {
+ dev_err(&pdev->dev, "couldn't register sysfs group\n");
+- goto out_pm_disable;
++ goto out_put_host;
+ }
+
+ /* register and we are done */
+@@ -565,8 +567,6 @@ static int bcmbca_hsspi_probe(struct platform_device *pdev)
+
+ out_sysgroup_disable:
+ sysfs_remove_group(&pdev->dev.kobj, &bcmbca_hsspi_group);
+-out_pm_disable:
+- pm_runtime_disable(&pdev->dev);
+ out_put_host:
+ spi_controller_put(host);
+ out_disable_pll_clk:
+diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
+index d2f603e1014cf5..e235df4177f965 100644
+--- a/drivers/spi/spi-fsl-lpspi.c
++++ b/drivers/spi/spi-fsl-lpspi.c
+@@ -986,6 +986,7 @@ static void fsl_lpspi_remove(struct platform_device *pdev)
+
+ fsl_lpspi_dma_exit(controller);
+
++ pm_runtime_dont_use_autosuspend(fsl_lpspi->dev);
+ pm_runtime_disable(fsl_lpspi->dev);
+ }
+
+diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c
+index 6585b19a48662d..a961785724cdf2 100644
+--- a/drivers/spi/spi-nxp-fspi.c
++++ b/drivers/spi/spi-nxp-fspi.c
+@@ -57,13 +57,6 @@
+ #include <linux/spi/spi.h>
+ #include <linux/spi/spi-mem.h>
+
+-/*
+- * The driver only uses one single LUT entry, that is updated on
+- * each call of exec_op(). Index 0 is preset at boot with a basic
+- * read operation, so let's use the last entry (31).
+- */
+-#define SEQID_LUT 31
+-
+ /* Registers used by the driver */
+ #define FSPI_MCR0 0x00
+ #define FSPI_MCR0_AHB_TIMEOUT(x) ((x) << 24)
+@@ -263,9 +256,6 @@
+ #define FSPI_TFDR 0x180
+
+ #define FSPI_LUT_BASE 0x200
+-#define FSPI_LUT_OFFSET (SEQID_LUT * 4 * 4)
+-#define FSPI_LUT_REG(idx) \
+- (FSPI_LUT_BASE + FSPI_LUT_OFFSET + (idx) * 4)
+
+ /* register map end */
+
+@@ -341,6 +331,7 @@ struct nxp_fspi_devtype_data {
+ unsigned int txfifo;
+ unsigned int ahb_buf_size;
+ unsigned int quirks;
++ unsigned int lut_num;
+ bool little_endian;
+ };
+
+@@ -349,6 +340,7 @@ static struct nxp_fspi_devtype_data lx2160a_data = {
+ .txfifo = SZ_1K, /* (128 * 64 bits) */
+ .ahb_buf_size = SZ_2K, /* (256 * 64 bits) */
+ .quirks = 0,
++ .lut_num = 32,
+ .little_endian = true, /* little-endian */
+ };
+
+@@ -357,6 +349,7 @@ static struct nxp_fspi_devtype_data imx8mm_data = {
+ .txfifo = SZ_1K, /* (128 * 64 bits) */
+ .ahb_buf_size = SZ_2K, /* (256 * 64 bits) */
+ .quirks = 0,
++ .lut_num = 32,
+ .little_endian = true, /* little-endian */
+ };
+
+@@ -365,6 +358,7 @@ static struct nxp_fspi_devtype_data imx8qxp_data = {
+ .txfifo = SZ_1K, /* (128 * 64 bits) */
+ .ahb_buf_size = SZ_2K, /* (256 * 64 bits) */
+ .quirks = 0,
++ .lut_num = 32,
+ .little_endian = true, /* little-endian */
+ };
+
+@@ -373,6 +367,16 @@ static struct nxp_fspi_devtype_data imx8dxl_data = {
+ .txfifo = SZ_1K, /* (128 * 64 bits) */
+ .ahb_buf_size = SZ_2K, /* (256 * 64 bits) */
+ .quirks = FSPI_QUIRK_USE_IP_ONLY,
++ .lut_num = 32,
++ .little_endian = true, /* little-endian */
++};
++
++static struct nxp_fspi_devtype_data imx8ulp_data = {
++ .rxfifo = SZ_512, /* (64 * 64 bits) */
++ .txfifo = SZ_1K, /* (128 * 64 bits) */
++ .ahb_buf_size = SZ_2K, /* (256 * 64 bits) */
++ .quirks = 0,
++ .lut_num = 16,
+ .little_endian = true, /* little-endian */
+ };
+
+@@ -544,6 +548,8 @@ static void nxp_fspi_prepare_lut(struct nxp_fspi *f,
+ void __iomem *base = f->iobase;
+ u32 lutval[4] = {};
+ int lutidx = 1, i;
++ u32 lut_offset = (f->devtype_data->lut_num - 1) * 4 * 4;
++ u32 target_lut_reg;
+
+ /* cmd */
+ lutval[0] |= LUT_DEF(0, LUT_CMD, LUT_PAD(op->cmd.buswidth),
+@@ -588,8 +594,10 @@ static void nxp_fspi_prepare_lut(struct nxp_fspi *f,
+ fspi_writel(f, FSPI_LCKER_UNLOCK, f->iobase + FSPI_LCKCR);
+
+ /* fill LUT */
+- for (i = 0; i < ARRAY_SIZE(lutval); i++)
+- fspi_writel(f, lutval[i], base + FSPI_LUT_REG(i));
++ for (i = 0; i < ARRAY_SIZE(lutval); i++) {
++ target_lut_reg = FSPI_LUT_BASE + lut_offset + i * 4;
++ fspi_writel(f, lutval[i], base + target_lut_reg);
++ }
+
+ dev_dbg(f->dev, "CMD[%02x] lutval[0:%08x 1:%08x 2:%08x 3:%08x], size: 0x%08x\n",
+ op->cmd.opcode, lutval[0], lutval[1], lutval[2], lutval[3], op->data.nbytes);
+@@ -876,7 +884,7 @@ static int nxp_fspi_do_op(struct nxp_fspi *f, const struct spi_mem_op *op)
+ void __iomem *base = f->iobase;
+ int seqnum = 0;
+ int err = 0;
+- u32 reg;
++ u32 reg, seqid_lut;
+
+ reg = fspi_readl(f, base + FSPI_IPRXFCR);
+ /* invalid RXFIFO first */
+@@ -892,8 +900,9 @@ static int nxp_fspi_do_op(struct nxp_fspi *f, const struct spi_mem_op *op)
+ * the LUT at each exec_op() call. And also specify the DATA
+ * length, since it's has not been specified in the LUT.
+ */
++ seqid_lut = f->devtype_data->lut_num - 1;
+ fspi_writel(f, op->data.nbytes |
+- (SEQID_LUT << FSPI_IPCR1_SEQID_SHIFT) |
++ (seqid_lut << FSPI_IPCR1_SEQID_SHIFT) |
+ (seqnum << FSPI_IPCR1_SEQNUM_SHIFT),
+ base + FSPI_IPCR1);
+
+@@ -1017,7 +1026,7 @@ static int nxp_fspi_default_setup(struct nxp_fspi *f)
+ {
+ void __iomem *base = f->iobase;
+ int ret, i;
+- u32 reg;
++ u32 reg, seqid_lut;
+
+ /* disable and unprepare clock to avoid glitch pass to controller */
+ nxp_fspi_clk_disable_unprep(f);
+@@ -1092,11 +1101,17 @@ static int nxp_fspi_default_setup(struct nxp_fspi *f)
+ fspi_writel(f, reg, base + FSPI_FLSHB1CR1);
+ fspi_writel(f, reg, base + FSPI_FLSHB2CR1);
+
++ /*
++ * The driver only uses one single LUT entry, that is updated on
++ * each call of exec_op(). Index 0 is preset at boot with a basic
++ * read operation, so let's use the last entry.
++ */
++ seqid_lut = f->devtype_data->lut_num - 1;
+ /* AHB Read - Set lut sequence ID for all CS. */
+- fspi_writel(f, SEQID_LUT, base + FSPI_FLSHA1CR2);
+- fspi_writel(f, SEQID_LUT, base + FSPI_FLSHA2CR2);
+- fspi_writel(f, SEQID_LUT, base + FSPI_FLSHB1CR2);
+- fspi_writel(f, SEQID_LUT, base + FSPI_FLSHB2CR2);
++ fspi_writel(f, seqid_lut, base + FSPI_FLSHA1CR2);
++ fspi_writel(f, seqid_lut, base + FSPI_FLSHA2CR2);
++ fspi_writel(f, seqid_lut, base + FSPI_FLSHB1CR2);
++ fspi_writel(f, seqid_lut, base + FSPI_FLSHB2CR2);
+
+ f->selected = -1;
+
+@@ -1291,6 +1306,7 @@ static const struct of_device_id nxp_fspi_dt_ids[] = {
+ { .compatible = "nxp,imx8mp-fspi", .data = (void *)&imx8mm_data, },
+ { .compatible = "nxp,imx8qxp-fspi", .data = (void *)&imx8qxp_data, },
+ { .compatible = "nxp,imx8dxl-fspi", .data = (void *)&imx8dxl_data, },
++ { .compatible = "nxp,imx8ulp-fspi", .data = (void *)&imx8ulp_data, },
+ { /* sentinel */ }
+ };
+ MODULE_DEVICE_TABLE(of, nxp_fspi_dt_ids);
+diff --git a/drivers/spi/spi-ppc4xx.c b/drivers/spi/spi-ppc4xx.c
+index 942c3117ab3a90..8f6309f32de0b5 100644
+--- a/drivers/spi/spi-ppc4xx.c
++++ b/drivers/spi/spi-ppc4xx.c
+@@ -27,7 +27,6 @@
+ #include <linux/wait.h>
+ #include <linux/platform_device.h>
+ #include <linux/of_address.h>
+-#include <linux/of_irq.h>
+ #include <linux/of_platform.h>
+ #include <linux/interrupt.h>
+ #include <linux/delay.h>
+@@ -412,7 +411,11 @@ static int spi_ppc4xx_of_probe(struct platform_device *op)
+ }
+
+ /* Request IRQ */
+- hw->irqnum = irq_of_parse_and_map(np, 0);
++ ret = platform_get_irq(op, 0);
++ if (ret < 0)
++ goto free_host;
++ hw->irqnum = ret;
++
+ ret = request_irq(hw->irqnum, spi_ppc4xx_int,
+ 0, "spi_ppc4xx_of", (void *)hw);
+ if (ret) {
+diff --git a/drivers/staging/media/starfive/camss/stf-camss.c b/drivers/staging/media/starfive/camss/stf-camss.c
+index fecd3e67c7a1d5..b6d34145bc191e 100644
+--- a/drivers/staging/media/starfive/camss/stf-camss.c
++++ b/drivers/staging/media/starfive/camss/stf-camss.c
+@@ -358,8 +358,6 @@ static int stfcamss_probe(struct platform_device *pdev)
+ /*
+ * stfcamss_remove - Remove STFCAMSS platform device
+ * @pdev: Pointer to STFCAMSS platform device
+- *
+- * Always returns 0.
+ */
+ static void stfcamss_remove(struct platform_device *pdev)
+ {
+diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c
+index daed67d19efb81..863e7a4272e66f 100644
+--- a/drivers/thermal/gov_bang_bang.c
++++ b/drivers/thermal/gov_bang_bang.c
+@@ -92,23 +92,21 @@ static void bang_bang_manage(struct thermal_zone_device *tz)
+
+ for_each_trip_desc(tz, td) {
+ const struct thermal_trip *trip = &td->trip;
++ bool turn_on;
+
+- if (tz->temperature >= td->threshold ||
+- trip->temperature == THERMAL_TEMP_INVALID ||
++ if (trip->temperature == THERMAL_TEMP_INVALID ||
+ trip->type == THERMAL_TRIP_CRITICAL ||
+ trip->type == THERMAL_TRIP_HOT)
+ continue;
+
+ /*
+- * If the initial cooling device state is "on", but the zone
+- * temperature is not above the trip point, the core will not
+- * call bang_bang_control() until the zone temperature reaches
+- * the trip point temperature which may be never. In those
+- * cases, set the initial state of the cooling device to 0.
++ * Adjust the target states for uninitialized thermal instances
++ * to the thermal zone temperature and the trip point threshold.
+ */
++ turn_on = tz->temperature >= td->threshold;
+ list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+ if (!instance->initialized && instance->trip == trip)
+- bang_bang_set_instance_target(instance, 0);
++ bang_bang_set_instance_target(instance, turn_on);
+ }
+ }
+
+diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
+index b8d889ef4fa5e6..d0e71698b35627 100644
+--- a/drivers/thermal/thermal_core.c
++++ b/drivers/thermal/thermal_core.c
+@@ -323,11 +323,15 @@ static void thermal_zone_broken_disable(struct thermal_zone_device *tz)
+ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
+ unsigned long delay)
+ {
+- if (delay)
+- mod_delayed_work(system_freezable_power_efficient_wq,
+- &tz->poll_queue, delay);
+- else
++ if (!delay) {
+ cancel_delayed_work(&tz->poll_queue);
++ return;
++ }
++
++ if (delay > HZ)
++ delay = round_jiffies_relative(delay);
++
++ mod_delayed_work(system_freezable_power_efficient_wq, &tz->poll_queue, delay);
+ }
+
+ static void thermal_zone_recheck(struct thermal_zone_device *tz, int error)
+@@ -988,20 +992,6 @@ void print_bind_err_msg(struct thermal_zone_device *tz,
+ tz->type, cdev->type, ret);
+ }
+
+-static void bind_cdev(struct thermal_cooling_device *cdev)
+-{
+- int ret;
+- struct thermal_zone_device *pos = NULL;
+-
+- list_for_each_entry(pos, &thermal_tz_list, node) {
+- if (pos->ops.bind) {
+- ret = pos->ops.bind(pos, cdev);
+- if (ret)
+- print_bind_err_msg(pos, cdev, ret);
+- }
+- }
+-}
+-
+ /**
+ * __thermal_cooling_device_register() - register a new thermal cooling device
+ * @np: a pointer to a device tree node.
+@@ -1097,7 +1087,13 @@ __thermal_cooling_device_register(struct device_node *np,
+ list_add(&cdev->node, &thermal_cdev_list);
+
+ /* Update binding information for 'this' new cdev */
+- bind_cdev(cdev);
++ list_for_each_entry(pos, &thermal_tz_list, node) {
++ if (pos->ops.bind) {
++ ret = pos->ops.bind(pos, cdev);
++ if (ret)
++ print_bind_err_msg(pos, cdev, ret);
++ }
++ }
+
+ list_for_each_entry(pos, &thermal_tz_list, node)
+ if (atomic_cmpxchg(&pos->need_update, 1, 0))
+@@ -1335,32 +1331,6 @@ void thermal_cooling_device_unregister(struct thermal_cooling_device *cdev)
+ }
+ EXPORT_SYMBOL_GPL(thermal_cooling_device_unregister);
+
+-static void bind_tz(struct thermal_zone_device *tz)
+-{
+- int ret;
+- struct thermal_cooling_device *pos = NULL;
+-
+- if (!tz->ops.bind)
+- return;
+-
+- mutex_lock(&thermal_list_lock);
+-
+- list_for_each_entry(pos, &thermal_cdev_list, node) {
+- ret = tz->ops.bind(tz, pos);
+- if (ret)
+- print_bind_err_msg(tz, pos, ret);
+- }
+-
+- mutex_unlock(&thermal_list_lock);
+-}
+-
+-static void thermal_set_delay_jiffies(unsigned long *delay_jiffies, int delay_ms)
+-{
+- *delay_jiffies = msecs_to_jiffies(delay_ms);
+- if (delay_ms > 1000)
+- *delay_jiffies = round_jiffies(*delay_jiffies);
+-}
+-
+ int thermal_zone_get_crit_temp(struct thermal_zone_device *tz, int *temp)
+ {
+ const struct thermal_trip_desc *td;
+@@ -1497,8 +1467,8 @@ thermal_zone_device_register_with_trips(const char *type,
+ td->threshold = INT_MAX;
+ }
+
+- thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay);
+- thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay);
++ tz->polling_delay_jiffies = msecs_to_jiffies(polling_delay);
++ tz->passive_delay_jiffies = msecs_to_jiffies(passive_delay);
+ tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
+
+ /* sys I/F */
+@@ -1542,13 +1512,23 @@ thermal_zone_device_register_with_trips(const char *type,
+ }
+
+ mutex_lock(&thermal_list_lock);
++
+ mutex_lock(&tz->lock);
+ list_add_tail(&tz->node, &thermal_tz_list);
+ mutex_unlock(&tz->lock);
+- mutex_unlock(&thermal_list_lock);
+
+ /* Bind cooling devices for this zone */
+- bind_tz(tz);
++ if (tz->ops.bind) {
++ struct thermal_cooling_device *cdev;
++
++ list_for_each_entry(cdev, &thermal_cdev_list, node) {
++ result = tz->ops.bind(tz, cdev);
++ if (result)
++ print_bind_err_msg(tz, cdev, result);
++ }
++ }
++
++ mutex_unlock(&thermal_list_lock);
+
+ thermal_zone_device_init(tz);
+ /* Update the new thermal zone and mark it as already updated. */
+diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
+index afef1dd4ddf49c..fca5f25d693a72 100644
+--- a/drivers/tty/serial/8250/8250_omap.c
++++ b/drivers/tty/serial/8250/8250_omap.c
+@@ -1581,7 +1581,7 @@ static int omap8250_probe(struct platform_device *pdev)
+ ret = devm_request_irq(&pdev->dev, up.port.irq, omap8250_irq, 0,
+ dev_name(&pdev->dev), priv);
+ if (ret < 0)
+- return ret;
++ goto err;
+
+ priv->wakeirq = irq_of_parse_and_map(np, 1);
+
+diff --git a/drivers/tty/serial/qcom_geni_serial.c b/drivers/tty/serial/qcom_geni_serial.c
+index 69a632fefc41f9..f8f6e9466b400d 100644
+--- a/drivers/tty/serial/qcom_geni_serial.c
++++ b/drivers/tty/serial/qcom_geni_serial.c
+@@ -124,13 +124,14 @@ struct qcom_geni_serial_port {
+ dma_addr_t tx_dma_addr;
+ dma_addr_t rx_dma_addr;
+ bool setup;
+- unsigned int baud;
++ unsigned long poll_timeout_us;
+ unsigned long clk_rate;
+ void *rx_buf;
+ u32 loopback;
+ bool brk;
+
+ unsigned int tx_remaining;
++ unsigned int tx_queued;
+ int wakeup_irq;
+ bool rx_tx_swap;
+ bool cts_rts_swap;
+@@ -144,6 +145,8 @@ static const struct uart_ops qcom_geni_uart_pops;
+ static struct uart_driver qcom_geni_console_driver;
+ static struct uart_driver qcom_geni_uart_driver;
+
++static void qcom_geni_serial_cancel_tx_cmd(struct uart_port *uport);
++
+ static inline struct qcom_geni_serial_port *to_dev_port(struct uart_port *uport)
+ {
+ return container_of(uport, struct qcom_geni_serial_port, uport);
+@@ -265,27 +268,18 @@ static bool qcom_geni_serial_secondary_active(struct uart_port *uport)
+ return readl(uport->membase + SE_GENI_STATUS) & S_GENI_CMD_ACTIVE;
+ }
+
+-static bool qcom_geni_serial_poll_bit(struct uart_port *uport,
+- int offset, int field, bool set)
++static bool qcom_geni_serial_poll_bitfield(struct uart_port *uport,
++ unsigned int offset, u32 field, u32 val)
+ {
+ u32 reg;
+ struct qcom_geni_serial_port *port;
+- unsigned int baud;
+- unsigned int fifo_bits;
+ unsigned long timeout_us = 20000;
+ struct qcom_geni_private_data *private_data = uport->private_data;
+
+ if (private_data->drv) {
+ port = to_dev_port(uport);
+- baud = port->baud;
+- if (!baud)
+- baud = 115200;
+- fifo_bits = port->tx_fifo_depth * port->tx_fifo_width;
+- /*
+- * Total polling iterations based on FIFO worth of bytes to be
+- * sent at current baud. Add a little fluff to the wait.
+- */
+- timeout_us = ((fifo_bits * USEC_PER_SEC) / baud) + 500;
++ if (port->poll_timeout_us)
++ timeout_us = port->poll_timeout_us;
+ }
+
+ /*
+@@ -295,7 +289,7 @@ static bool qcom_geni_serial_poll_bit(struct uart_port *uport,
+ timeout_us = DIV_ROUND_UP(timeout_us, 10) * 10;
+ while (timeout_us) {
+ reg = readl(uport->membase + offset);
+- if ((bool)(reg & field) == set)
++ if ((reg & field) == val)
+ return true;
+ udelay(10);
+ timeout_us -= 10;
+@@ -303,6 +297,12 @@ static bool qcom_geni_serial_poll_bit(struct uart_port *uport,
+ return false;
+ }
+
++static bool qcom_geni_serial_poll_bit(struct uart_port *uport,
++ unsigned int offset, u32 field, bool set)
++{
++ return qcom_geni_serial_poll_bitfield(uport, offset, field, set ? field : 0);
++}
++
+ static void qcom_geni_serial_setup_tx(struct uart_port *uport, u32 xmit_size)
+ {
+ u32 m_cmd;
+@@ -315,18 +315,16 @@ static void qcom_geni_serial_setup_tx(struct uart_port *uport, u32 xmit_size)
+ static void qcom_geni_serial_poll_tx_done(struct uart_port *uport)
+ {
+ int done;
+- u32 irq_clear = M_CMD_DONE_EN;
+
+ done = qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS,
+ M_CMD_DONE_EN, true);
+ if (!done) {
+ writel(M_GENI_CMD_ABORT, uport->membase +
+ SE_GENI_M_CMD_CTRL_REG);
+- irq_clear |= M_CMD_ABORT_EN;
+ qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS,
+ M_CMD_ABORT_EN, true);
++ writel(M_CMD_ABORT_EN, uport->membase + SE_GENI_M_IRQ_CLEAR);
+ }
+- writel(irq_clear, uport->membase + SE_GENI_M_IRQ_CLEAR);
+ }
+
+ static void qcom_geni_serial_abort_rx(struct uart_port *uport)
+@@ -387,6 +385,7 @@ static void qcom_geni_serial_poll_put_char(struct uart_port *uport,
+ unsigned char c)
+ {
+ writel(DEF_TX_WM, uport->membase + SE_GENI_TX_WATERMARK_REG);
++ writel(M_CMD_DONE_EN, uport->membase + SE_GENI_M_IRQ_CLEAR);
+ qcom_geni_serial_setup_tx(uport, 1);
+ WARN_ON(!qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS,
+ M_TX_FIFO_WATERMARK_EN, true));
+@@ -397,6 +396,14 @@ static void qcom_geni_serial_poll_put_char(struct uart_port *uport,
+ #endif
+
+ #ifdef CONFIG_SERIAL_QCOM_GENI_CONSOLE
++static void qcom_geni_serial_drain_fifo(struct uart_port *uport)
++{
++ struct qcom_geni_serial_port *port = to_dev_port(uport);
++
++ qcom_geni_serial_poll_bitfield(uport, SE_GENI_M_GP_LENGTH, GP_LENGTH,
++ port->tx_queued);
++}
++
+ static void qcom_geni_serial_wr_char(struct uart_port *uport, unsigned char ch)
+ {
+ struct qcom_geni_private_data *private_data = uport->private_data;
+@@ -431,6 +438,7 @@ __qcom_geni_serial_console_write(struct uart_port *uport, const char *s,
+ }
+
+ writel(DEF_TX_WM, uport->membase + SE_GENI_TX_WATERMARK_REG);
++ writel(M_CMD_DONE_EN, uport->membase + SE_GENI_M_IRQ_CLEAR);
+ qcom_geni_serial_setup_tx(uport, bytes_to_send);
+ for (i = 0; i < count; ) {
+ size_t chars_to_write = 0;
+@@ -471,8 +479,6 @@ static void qcom_geni_serial_console_write(struct console *co, const char *s,
+ struct qcom_geni_serial_port *port;
+ bool locked = true;
+ unsigned long flags;
+- u32 geni_status;
+- u32 irq_en;
+
+ WARN_ON(co->index < 0 || co->index >= GENI_UART_CONS_PORTS);
+
+@@ -486,40 +492,20 @@ static void qcom_geni_serial_console_write(struct console *co, const char *s,
+ else
+ uart_port_lock_irqsave(uport, &flags);
+
+- geni_status = readl(uport->membase + SE_GENI_STATUS);
++ if (qcom_geni_serial_main_active(uport)) {
++ /* Wait for completion or drain FIFO */
++ if (!locked || port->tx_remaining == 0)
++ qcom_geni_serial_poll_tx_done(uport);
++ else
++ qcom_geni_serial_drain_fifo(uport);
+
+- if (!locked) {
+- /*
+- * We can only get here if an oops is in progress then we were
+- * unable to get the lock. This means we can't safely access
+- * our state variables like tx_remaining. About the best we
+- * can do is wait for the FIFO to be empty before we start our
+- * transfer, so we'll do that.
+- */
+- qcom_geni_serial_poll_bit(uport, SE_GENI_M_IRQ_STATUS,
+- M_TX_FIFO_NOT_EMPTY_EN, false);
+- } else if ((geni_status & M_GENI_CMD_ACTIVE) && !port->tx_remaining) {
+- /*
+- * It seems we can't interrupt existing transfers if all data
+- * has been sent, in which case we need to look for done first.
+- */
+- qcom_geni_serial_poll_tx_done(uport);
+-
+- if (!kfifo_is_empty(&uport->state->port.xmit_fifo)) {
+- irq_en = readl(uport->membase + SE_GENI_M_IRQ_EN);
+- writel(irq_en | M_TX_FIFO_WATERMARK_EN,
+- uport->membase + SE_GENI_M_IRQ_EN);
+- }
++ qcom_geni_serial_cancel_tx_cmd(uport);
+ }
+
+ __qcom_geni_serial_console_write(uport, s, count);
+
+-
+- if (locked) {
+- if (port->tx_remaining)
+- qcom_geni_serial_setup_tx(uport, port->tx_remaining);
++ if (locked)
+ uart_port_unlock_irqrestore(uport, flags);
+- }
+ }
+
+ static void handle_rx_console(struct uart_port *uport, u32 bytes, bool drop)
+@@ -700,6 +686,7 @@ static void qcom_geni_serial_cancel_tx_cmd(struct uart_port *uport)
+ writel(M_CMD_CANCEL_EN, uport->membase + SE_GENI_M_IRQ_CLEAR);
+
+ port->tx_remaining = 0;
++ port->tx_queued = 0;
+ }
+
+ static void qcom_geni_serial_handle_rx_fifo(struct uart_port *uport, bool drop)
+@@ -926,6 +913,7 @@ static void qcom_geni_serial_handle_tx_fifo(struct uart_port *uport,
+ if (!port->tx_remaining) {
+ qcom_geni_serial_setup_tx(uport, pending);
+ port->tx_remaining = pending;
++ port->tx_queued = 0;
+
+ irq_en = readl(uport->membase + SE_GENI_M_IRQ_EN);
+ if (!(irq_en & M_TX_FIFO_WATERMARK_EN))
+@@ -934,6 +922,7 @@ static void qcom_geni_serial_handle_tx_fifo(struct uart_port *uport,
+ }
+
+ qcom_geni_serial_send_chunk_fifo(uport, chunk);
++ port->tx_queued += chunk;
+
+ /*
+ * The tx fifo watermark is level triggered and latched. Though we had
+@@ -1244,11 +1233,11 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport,
+ unsigned long clk_rate;
+ u32 ver, sampling_rate;
+ unsigned int avg_bw_core;
++ unsigned long timeout;
+
+ qcom_geni_serial_stop_rx(uport);
+ /* baud rate */
+ baud = uart_get_baud_rate(uport, termios, old, 300, 4000000);
+- port->baud = baud;
+
+ sampling_rate = UART_OVERSAMPLING;
+ /* Sampling rate is halved for IP versions >= 2.5 */
+@@ -1326,9 +1315,21 @@ static void qcom_geni_serial_set_termios(struct uart_port *uport,
+ else
+ tx_trans_cfg |= UART_CTS_MASK;
+
+- if (baud)
++ if (baud) {
+ uart_update_timeout(uport, termios->c_cflag, baud);
+
++ /*
++ * Make sure that qcom_geni_serial_poll_bitfield() waits for
++ * the FIFO, two-word intermediate transfer register and shift
++ * register to clear.
++ *
++ * Note that uart_fifo_timeout() also adds a 20 ms margin.
++ */
++ timeout = jiffies_to_usecs(uart_fifo_timeout(uport));
++ timeout += 3 * timeout / port->tx_fifo_depth;
++ WRITE_ONCE(port->poll_timeout_us, timeout);
++ }
++
+ if (!uart_console(uport))
+ writel(port->loopback,
+ uport->membase + SE_UART_LOOPBACK_CFG);
+diff --git a/drivers/tty/serial/rp2.c b/drivers/tty/serial/rp2.c
+index 4132fcff7d4e29..8bab2aedc4991f 100644
+--- a/drivers/tty/serial/rp2.c
++++ b/drivers/tty/serial/rp2.c
+@@ -577,8 +577,8 @@ static void rp2_reset_asic(struct rp2_card *card, unsigned int asic_id)
+ u32 clk_cfg;
+
+ writew(1, base + RP2_GLOBAL_CMD);
+- readw(base + RP2_GLOBAL_CMD);
+ msleep(100);
++ readw(base + RP2_GLOBAL_CMD);
+ writel(0, base + RP2_CLK_PRESCALER);
+
+ /* TDM clock configuration */
+diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
+index 9967444eae10cb..1d0e7b8514ccc1 100644
+--- a/drivers/tty/serial/serial_core.c
++++ b/drivers/tty/serial/serial_core.c
+@@ -2696,14 +2696,13 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options)
+ int ret = 0;
+
+ tport = &state->port;
+- mutex_lock(&tport->mutex);
++
++ guard(mutex)(&tport->mutex);
+
+ port = uart_port_check(state);
+ if (!port || port->type == PORT_UNKNOWN ||
+- !(port->ops->poll_get_char && port->ops->poll_put_char)) {
+- ret = -1;
+- goto out;
+- }
++ !(port->ops->poll_get_char && port->ops->poll_put_char))
++ return -1;
+
+ pm_state = state->pm_state;
+ uart_change_pm(state, UART_PM_STATE_ON);
+@@ -2723,10 +2722,10 @@ static int uart_poll_init(struct tty_driver *driver, int line, char *options)
+ ret = uart_set_options(port, NULL, baud, parity, bits, flow);
+ console_list_unlock();
+ }
+-out:
++
+ if (ret)
+ uart_change_pm(state, pm_state);
+- mutex_unlock(&tport->mutex);
++
+ return ret;
+ }
+
+diff --git a/drivers/ufs/host/ufs-qcom.c b/drivers/ufs/host/ufs-qcom.c
+index cca190d1c577e9..92ff9706860ceb 100644
+--- a/drivers/ufs/host/ufs-qcom.c
++++ b/drivers/ufs/host/ufs-qcom.c
+@@ -93,7 +93,7 @@ static const struct __ufs_qcom_bw_table {
+ [MODE_HS_RB][UFS_HS_G3][UFS_LANE_2] = { 1492582, 204800 },
+ [MODE_HS_RB][UFS_HS_G4][UFS_LANE_2] = { 2915200, 409600 },
+ [MODE_HS_RB][UFS_HS_G5][UFS_LANE_2] = { 5836800, 819200 },
+- [MODE_MAX][0][0] = { 7643136, 307200 },
++ [MODE_MAX][0][0] = { 7643136, 819200 },
+ };
+
+ static void ufs_qcom_get_default_testbus_cfg(struct ufs_qcom_host *host);
+diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
+index dbd83d321bca01..46852529499d16 100644
+--- a/drivers/usb/cdns3/cdnsp-ring.c
++++ b/drivers/usb/cdns3/cdnsp-ring.c
+@@ -718,7 +718,8 @@ int cdnsp_remove_request(struct cdnsp_device *pdev,
+ seg = cdnsp_trb_in_td(pdev, cur_td->start_seg, cur_td->first_trb,
+ cur_td->last_trb, hw_deq);
+
+- if (seg && (pep->ep_state & EP_ENABLED))
++ if (seg && (pep->ep_state & EP_ENABLED) &&
++ !(pep->ep_state & EP_DIS_IN_RROGRESS))
+ cdnsp_find_new_dequeue_state(pdev, pep, preq->request.stream_id,
+ cur_td, &deq_state);
+ else
+@@ -736,7 +737,8 @@ int cdnsp_remove_request(struct cdnsp_device *pdev,
+ * During disconnecting all endpoint will be disabled so we don't
+ * have to worry about updating dequeue pointer.
+ */
+- if (pdev->cdnsp_state & CDNSP_STATE_DISCONNECT_PENDING) {
++ if (pdev->cdnsp_state & CDNSP_STATE_DISCONNECT_PENDING ||
++ pep->ep_state & EP_DIS_IN_RROGRESS) {
+ status = -ESHUTDOWN;
+ ret = cdnsp_cmd_set_deq(pdev, pep, &deq_state);
+ }
+diff --git a/drivers/usb/cdns3/host.c b/drivers/usb/cdns3/host.c
+index ceca4d839dfd42..7ba760ee62e331 100644
+--- a/drivers/usb/cdns3/host.c
++++ b/drivers/usb/cdns3/host.c
+@@ -62,7 +62,9 @@ static const struct xhci_plat_priv xhci_plat_cdns3_xhci = {
+ .resume_quirk = xhci_cdns3_resume_quirk,
+ };
+
+-static const struct xhci_plat_priv xhci_plat_cdnsp_xhci;
++static const struct xhci_plat_priv xhci_plat_cdnsp_xhci = {
++ .quirks = XHCI_CDNS_SCTX_QUIRK,
++};
+
+ static int __cdns_host_init(struct cdns *cdns)
+ {
+diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
+index 0c1b69d944ca45..605fea4611029b 100644
+--- a/drivers/usb/class/cdc-acm.c
++++ b/drivers/usb/class/cdc-acm.c
+@@ -962,10 +962,12 @@ static int get_serial_info(struct tty_struct *tty, struct serial_struct *ss)
+ struct acm *acm = tty->driver_data;
+
+ ss->line = acm->minor;
++ mutex_lock(&acm->port.mutex);
+ ss->close_delay = jiffies_to_msecs(acm->port.close_delay) / 10;
+ ss->closing_wait = acm->port.closing_wait == ASYNC_CLOSING_WAIT_NONE ?
+ ASYNC_CLOSING_WAIT_NONE :
+ jiffies_to_msecs(acm->port.closing_wait) / 10;
++ mutex_unlock(&acm->port.mutex);
+ return 0;
+ }
+
+diff --git a/drivers/usb/dwc2/drd.c b/drivers/usb/dwc2/drd.c
+index a8605b02115b1c..1ad8fa3f862a15 100644
+--- a/drivers/usb/dwc2/drd.c
++++ b/drivers/usb/dwc2/drd.c
+@@ -127,6 +127,15 @@ static int dwc2_drd_role_sw_set(struct usb_role_switch *sw, enum usb_role role)
+ role = USB_ROLE_DEVICE;
+ }
+
++ if ((IS_ENABLED(CONFIG_USB_DWC2_PERIPHERAL) ||
++ IS_ENABLED(CONFIG_USB_DWC2_DUAL_ROLE)) &&
++ dwc2_is_device_mode(hsotg) &&
++ hsotg->lx_state == DWC2_L2 &&
++ hsotg->params.power_down == DWC2_POWER_DOWN_PARAM_NONE &&
++ hsotg->bus_suspended &&
++ !hsotg->params.no_clock_gating)
++ dwc2_gadget_exit_clock_gating(hsotg, 0);
++
+ if (role == USB_ROLE_HOST) {
+ already = dwc2_ovr_avalid(hsotg, true);
+ } else if (role == USB_ROLE_DEVICE) {
+diff --git a/drivers/usb/gadget/udc/dummy_hcd.c b/drivers/usb/gadget/udc/dummy_hcd.c
+index f37b0d8386c1a9..ff7bee78bcc492 100644
+--- a/drivers/usb/gadget/udc/dummy_hcd.c
++++ b/drivers/usb/gadget/udc/dummy_hcd.c
+@@ -1304,7 +1304,8 @@ static int dummy_urb_enqueue(
+
+ /* kick the scheduler, it'll do the rest */
+ if (!hrtimer_active(&dum_hcd->timer))
+- hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS), HRTIMER_MODE_REL);
++ hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS),
++ HRTIMER_MODE_REL_SOFT);
+
+ done:
+ spin_unlock_irqrestore(&dum_hcd->dum->lock, flags);
+@@ -1325,7 +1326,7 @@ static int dummy_urb_dequeue(struct usb_hcd *hcd, struct urb *urb, int status)
+ rc = usb_hcd_check_unlink_urb(hcd, urb, status);
+ if (!rc && dum_hcd->rh_state != DUMMY_RH_RUNNING &&
+ !list_empty(&dum_hcd->urbp_list))
+- hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL);
++ hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL_SOFT);
+
+ spin_unlock_irqrestore(&dum_hcd->dum->lock, flags);
+ return rc;
+@@ -1995,7 +1996,8 @@ static enum hrtimer_restart dummy_timer(struct hrtimer *t)
+ dum_hcd->udev = NULL;
+ } else if (dum_hcd->rh_state == DUMMY_RH_RUNNING) {
+ /* want a 1 msec delay here */
+- hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS), HRTIMER_MODE_REL);
++ hrtimer_start(&dum_hcd->timer, ns_to_ktime(DUMMY_TIMER_INT_NSECS),
++ HRTIMER_MODE_REL_SOFT);
+ }
+
+ spin_unlock_irqrestore(&dum->lock, flags);
+@@ -2389,7 +2391,7 @@ static int dummy_bus_resume(struct usb_hcd *hcd)
+ dum_hcd->rh_state = DUMMY_RH_RUNNING;
+ set_link_state(dum_hcd);
+ if (!list_empty(&dum_hcd->urbp_list))
+- hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL);
++ hrtimer_start(&dum_hcd->timer, ns_to_ktime(0), HRTIMER_MODE_REL_SOFT);
+ hcd->state = HC_STATE_RUNNING;
+ }
+ spin_unlock_irq(&dum_hcd->dum->lock);
+@@ -2467,7 +2469,7 @@ static DEVICE_ATTR_RO(urbs);
+
+ static int dummy_start_ss(struct dummy_hcd *dum_hcd)
+ {
+- hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
++ hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+ dum_hcd->timer.function = dummy_timer;
+ dum_hcd->rh_state = DUMMY_RH_RUNNING;
+ dum_hcd->stream_en_ep = 0;
+@@ -2497,7 +2499,7 @@ static int dummy_start(struct usb_hcd *hcd)
+ return dummy_start_ss(dum_hcd);
+
+ spin_lock_init(&dum_hcd->dum->lock);
+- hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL);
++ hrtimer_init(&dum_hcd->timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_SOFT);
+ dum_hcd->timer.function = dummy_timer;
+ dum_hcd->rh_state = DUMMY_RH_RUNNING;
+
+diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
+index f591ddd086627a..fa3ee53df0ecc5 100644
+--- a/drivers/usb/host/xhci-mem.c
++++ b/drivers/usb/host/xhci-mem.c
+@@ -2325,7 +2325,10 @@ xhci_add_interrupter(struct xhci_hcd *xhci, struct xhci_interrupter *ir,
+ erst_base = xhci_read_64(xhci, &ir->ir_set->erst_base);
+ erst_base &= ERST_BASE_RSVDP;
+ erst_base |= ir->erst.erst_dma_addr & ~ERST_BASE_RSVDP;
+- xhci_write_64(xhci, erst_base, &ir->ir_set->erst_base);
++ if (xhci->quirks & XHCI_WRITE_64_HI_LO)
++ hi_lo_writeq(erst_base, &ir->ir_set->erst_base);
++ else
++ xhci_write_64(xhci, erst_base, &ir->ir_set->erst_base);
+
+ /* Set the event ring dequeue address of this interrupter */
+ xhci_set_hc_event_deq(xhci, ir);
+diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
+index dc1e345ab67ea8..994fd8b38bd015 100644
+--- a/drivers/usb/host/xhci-pci.c
++++ b/drivers/usb/host/xhci-pci.c
+@@ -55,6 +55,9 @@
+ #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed
+ #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_PCH_XHCI 0x54ed
+
++#define PCI_VENDOR_ID_PHYTIUM 0x1db7
++#define PCI_DEVICE_ID_PHYTIUM_XHCI 0xdc27
++
+ /* Thunderbolt */
+ #define PCI_DEVICE_ID_INTEL_MAPLE_RIDGE_XHCI 0x1138
+ #define PCI_DEVICE_ID_INTEL_ALPINE_RIDGE_2C_XHCI 0x15b5
+@@ -78,6 +81,9 @@
+ #define PCI_DEVICE_ID_ASMEDIA_2142_XHCI 0x2142
+ #define PCI_DEVICE_ID_ASMEDIA_3242_XHCI 0x3242
+
++#define PCI_DEVICE_ID_CADENCE 0x17CD
++#define PCI_DEVICE_ID_CADENCE_SSP 0x0200
++
+ static const char hcd_name[] = "xhci_hcd";
+
+ static struct hc_driver __read_mostly xhci_pci_hc_driver;
+@@ -416,6 +422,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
+ if (pdev->vendor == PCI_VENDOR_ID_VIA)
+ xhci->quirks |= XHCI_RESET_ON_RESUME;
+
++ if (pdev->vendor == PCI_VENDOR_ID_PHYTIUM &&
++ pdev->device == PCI_DEVICE_ID_PHYTIUM_XHCI)
++ xhci->quirks |= XHCI_RESET_ON_RESUME;
++
+ /* See https://bugzilla.kernel.org/show_bug.cgi?id=79511 */
+ if (pdev->vendor == PCI_VENDOR_ID_VIA &&
+ pdev->device == 0x3432)
+@@ -473,6 +483,10 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
+ xhci->quirks |= XHCI_ZHAOXIN_TRB_FETCH;
+ }
+
++ if (pdev->vendor == PCI_DEVICE_ID_CADENCE &&
++ pdev->device == PCI_DEVICE_ID_CADENCE_SSP)
++ xhci->quirks |= XHCI_CDNS_SCTX_QUIRK;
++
+ /* xHC spec requires PCI devices to support D3hot and D3cold */
+ if (xhci->hci_version >= 0x120)
+ xhci->quirks |= XHCI_DEFAULT_PM_RUNTIME_ALLOW;
+@@ -655,8 +669,10 @@ static int xhci_pci_probe(struct pci_dev *dev, const struct pci_device_id *id)
+ static void xhci_pci_remove(struct pci_dev *dev)
+ {
+ struct xhci_hcd *xhci;
++ bool set_power_d3;
+
+ xhci = hcd_to_xhci(pci_get_drvdata(dev));
++ set_power_d3 = xhci->quirks & XHCI_SPURIOUS_WAKEUP;
+
+ xhci->xhc_state |= XHCI_STATE_REMOVING;
+
+@@ -669,11 +685,11 @@ static void xhci_pci_remove(struct pci_dev *dev)
+ xhci->shared_hcd = NULL;
+ }
+
++ usb_hcd_pci_remove(dev);
++
+ /* Workaround for spurious wakeups at shutdown with HSW */
+- if (xhci->quirks & XHCI_SPURIOUS_WAKEUP)
++ if (set_power_d3)
+ pci_set_power_state(dev, PCI_D3hot);
+-
+- usb_hcd_pci_remove(dev);
+ }
+
+ /*
+diff --git a/drivers/usb/host/xhci-ring.c b/drivers/usb/host/xhci-ring.c
+index fd0cde3d1569c7..0fe6bef6c39800 100644
+--- a/drivers/usb/host/xhci-ring.c
++++ b/drivers/usb/host/xhci-ring.c
+@@ -1426,6 +1426,20 @@ static void xhci_handle_cmd_set_deq(struct xhci_hcd *xhci, int slot_id,
+ struct xhci_stream_ctx *ctx =
+ &ep->stream_info->stream_ctx_array[stream_id];
+ deq = le64_to_cpu(ctx->stream_ring) & SCTX_DEQ_MASK;
++
++ /*
++ * Cadence xHCI controllers store some endpoint state
++ * information within Rsvd0 fields of Stream Endpoint
++ * context. This field is not cleared during Set TR
++ * Dequeue Pointer command which causes XDMA to skip
++ * over transfer ring and leads to data loss on stream
++ * pipe.
++ * To fix this issue driver must clear Rsvd0 field.
++ */
++ if (xhci->quirks & XHCI_CDNS_SCTX_QUIRK) {
++ ctx->reserved[0] = 0;
++ ctx->reserved[1] = 0;
++ }
+ } else {
+ deq = le64_to_cpu(ep_ctx->deq) & ~EP_CTX_CYCLE_MASK;
+ }
+diff --git a/drivers/usb/host/xhci.h b/drivers/usb/host/xhci.h
+index 78d014c4d884a2..ac8da8a7df86b7 100644
+--- a/drivers/usb/host/xhci.h
++++ b/drivers/usb/host/xhci.h
+@@ -17,6 +17,7 @@
+ #include <linux/kernel.h>
+ #include <linux/usb/hcd.h>
+ #include <linux/io-64-nonatomic-lo-hi.h>
++#include <linux/io-64-nonatomic-hi-lo.h>
+
+ /* Code sharing between pci-quirks and xhci hcd */
+ #include "xhci-ext-caps.h"
+@@ -1628,6 +1629,8 @@ struct xhci_hcd {
+ #define XHCI_RESET_TO_DEFAULT BIT_ULL(44)
+ #define XHCI_ZHAOXIN_TRB_FETCH BIT_ULL(45)
+ #define XHCI_ZHAOXIN_HOST BIT_ULL(46)
++#define XHCI_WRITE_64_HI_LO BIT_ULL(47)
++#define XHCI_CDNS_SCTX_QUIRK BIT_ULL(48)
+
+ unsigned int num_active_eps;
+ unsigned int limit_active_eps;
+diff --git a/drivers/usb/misc/appledisplay.c b/drivers/usb/misc/appledisplay.c
+index c8098e9b432e13..62b5a30edc4267 100644
+--- a/drivers/usb/misc/appledisplay.c
++++ b/drivers/usb/misc/appledisplay.c
+@@ -107,7 +107,12 @@ static void appledisplay_complete(struct urb *urb)
+ case ACD_BTN_BRIGHT_UP:
+ case ACD_BTN_BRIGHT_DOWN:
+ pdata->button_pressed = 1;
+- schedule_delayed_work(&pdata->work, 0);
++ /*
++ * there is a window during which no device
++ * is registered
++ */
++ if (pdata->bd )
++ schedule_delayed_work(&pdata->work, 0);
+ break;
+ case ACD_BTN_NONE:
+ default:
+@@ -202,6 +207,7 @@ static int appledisplay_probe(struct usb_interface *iface,
+ const struct usb_device_id *id)
+ {
+ struct backlight_properties props;
++ struct backlight_device *backlight;
+ struct appledisplay *pdata;
+ struct usb_device *udev = interface_to_usbdev(iface);
+ struct usb_endpoint_descriptor *endpoint;
+@@ -272,13 +278,14 @@ static int appledisplay_probe(struct usb_interface *iface,
+ memset(&props, 0, sizeof(struct backlight_properties));
+ props.type = BACKLIGHT_RAW;
+ props.max_brightness = 0xff;
+- pdata->bd = backlight_device_register(bl_name, NULL, pdata,
++ backlight = backlight_device_register(bl_name, NULL, pdata,
+ &appledisplay_bl_data, &props);
+- if (IS_ERR(pdata->bd)) {
++ if (IS_ERR(backlight)) {
+ dev_err(&iface->dev, "Backlight registration failed\n");
+- retval = PTR_ERR(pdata->bd);
++ retval = PTR_ERR(backlight);
+ goto error;
+ }
++ pdata->bd = backlight;
+
+ /* Try to get brightness */
+ brightness = appledisplay_bl_get_brightness(pdata->bd);
+diff --git a/drivers/usb/misc/cypress_cy7c63.c b/drivers/usb/misc/cypress_cy7c63.c
+index cecd7693b7413c..75f5a740cba397 100644
+--- a/drivers/usb/misc/cypress_cy7c63.c
++++ b/drivers/usb/misc/cypress_cy7c63.c
+@@ -88,6 +88,9 @@ static int vendor_command(struct cypress *dev, unsigned char request,
+ USB_DIR_IN | USB_TYPE_VENDOR | USB_RECIP_OTHER,
+ address, data, iobuf, CYPRESS_MAX_REQSIZE,
+ USB_CTRL_GET_TIMEOUT);
++ /* we must not process garbage */
++ if (retval < 2)
++ goto err_buf;
+
+ /* store returned data (more READs to be added) */
+ switch (request) {
+@@ -107,6 +110,7 @@ static int vendor_command(struct cypress *dev, unsigned char request,
+ break;
+ }
+
++err_buf:
+ kfree(iobuf);
+ error:
+ return retval;
+diff --git a/drivers/usb/misc/yurex.c b/drivers/usb/misc/yurex.c
+index 9a0649d2369354..6adaaf66c14d7b 100644
+--- a/drivers/usb/misc/yurex.c
++++ b/drivers/usb/misc/yurex.c
+@@ -404,7 +404,6 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
+ struct usb_yurex *dev;
+ int len = 0;
+ char in_buffer[MAX_S64_STRLEN];
+- unsigned long flags;
+
+ dev = file->private_data;
+
+@@ -419,9 +418,9 @@ static ssize_t yurex_read(struct file *file, char __user *buffer, size_t count,
+ return -EIO;
+ }
+
+- spin_lock_irqsave(&dev->lock, flags);
++ spin_lock_irq(&dev->lock);
+ scnprintf(in_buffer, MAX_S64_STRLEN, "%lld\n", dev->bbu);
+- spin_unlock_irqrestore(&dev->lock, flags);
++ spin_unlock_irq(&dev->lock);
+ mutex_unlock(&dev->io_mutex);
+
+ return simple_read_from_buffer(buffer, count, ppos, in_buffer, len);
+@@ -511,8 +510,11 @@ static ssize_t yurex_write(struct file *file, const char __user *user_buffer,
+ __func__, retval);
+ goto error;
+ }
+- if (set && timeout)
++ if (set && timeout) {
++ spin_lock_irq(&dev->lock);
+ dev->bbu = c2;
++ spin_unlock_irq(&dev->lock);
++ }
+ return timeout ? count : -EIO;
+
+ error:
+diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
+index 4758914ccf8608..bf56f3d6962533 100644
+--- a/drivers/vdpa/mlx5/core/mr.c
++++ b/drivers/vdpa/mlx5/core/mr.c
+@@ -581,6 +581,9 @@ static void mlx5_vdpa_show_mr_leaks(struct mlx5_vdpa_dev *mvdev)
+
+ void mlx5_vdpa_destroy_mr_resources(struct mlx5_vdpa_dev *mvdev)
+ {
++ if (!mvdev->res.valid)
++ return;
++
+ for (int i = 0; i < MLX5_VDPA_NUM_AS; i++)
+ mlx5_vdpa_update_mr(mvdev, NULL, i);
+
+diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
+index 6b9c12acf4381a..b3d2a53f9bb77f 100644
+--- a/drivers/vhost/vdpa.c
++++ b/drivers/vhost/vdpa.c
+@@ -209,11 +209,9 @@ static void vhost_vdpa_setup_vq_irq(struct vhost_vdpa *v, u16 qid)
+ if (irq < 0)
+ return;
+
+- irq_bypass_unregister_producer(&vq->call_ctx.producer);
+ if (!vq->call_ctx.ctx)
+ return;
+
+- vq->call_ctx.producer.token = vq->call_ctx.ctx;
+ vq->call_ctx.producer.irq = irq;
+ ret = irq_bypass_register_producer(&vq->call_ctx.producer);
+ if (unlikely(ret))
+@@ -709,6 +707,14 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
+ vq->last_avail_idx = vq_state.split.avail_index;
+ }
+ break;
++ case VHOST_SET_VRING_CALL:
++ if (vq->call_ctx.ctx) {
++ if (ops->get_status(vdpa) &
++ VIRTIO_CONFIG_S_DRIVER_OK)
++ vhost_vdpa_unsetup_vq_irq(v, idx);
++ vq->call_ctx.producer.token = NULL;
++ }
++ break;
+ }
+
+ r = vhost_vring_ioctl(&v->vdev, cmd, argp);
+@@ -747,13 +753,16 @@ static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
+ cb.callback = vhost_vdpa_virtqueue_cb;
+ cb.private = vq;
+ cb.trigger = vq->call_ctx.ctx;
++ vq->call_ctx.producer.token = vq->call_ctx.ctx;
++ if (ops->get_status(vdpa) &
++ VIRTIO_CONFIG_S_DRIVER_OK)
++ vhost_vdpa_setup_vq_irq(v, idx);
+ } else {
+ cb.callback = NULL;
+ cb.private = NULL;
+ cb.trigger = NULL;
+ }
+ ops->set_vq_cb(vdpa, idx, &cb);
+- vhost_vdpa_setup_vq_irq(v, idx);
+ break;
+
+ case VHOST_SET_VRING_NUM:
+@@ -1421,6 +1430,7 @@ static int vhost_vdpa_open(struct inode *inode, struct file *filep)
+ for (i = 0; i < nvqs; i++) {
+ vqs[i] = &v->vqs[i];
+ vqs[i]->handle_kick = handle_vq_kick;
++ vqs[i]->call_ctx.ctx = NULL;
+ }
+ vhost_dev_init(dev, vqs, nvqs, 0, 0, 0, false,
+ vhost_vdpa_process_iotlb_msg);
+diff --git a/drivers/video/fbdev/hpfb.c b/drivers/video/fbdev/hpfb.c
+index 66fac8e5393e08..a1144b15098266 100644
+--- a/drivers/video/fbdev/hpfb.c
++++ b/drivers/video/fbdev/hpfb.c
+@@ -345,6 +345,7 @@ static int hpfb_dio_probe(struct dio_dev *d, const struct dio_device_id *ent)
+ if (hpfb_init_one(paddr, vaddr)) {
+ if (d->scode >= DIOII_SCBASE)
+ iounmap((void *)vaddr);
++ release_mem_region(d->resource.start, resource_size(&d->resource));
+ return -ENOMEM;
+ }
+ return 0;
+diff --git a/drivers/video/fbdev/xen-fbfront.c b/drivers/video/fbdev/xen-fbfront.c
+index 66d4628a96ae04..c90f48ebb15e3f 100644
+--- a/drivers/video/fbdev/xen-fbfront.c
++++ b/drivers/video/fbdev/xen-fbfront.c
+@@ -407,6 +407,7 @@ static int xenfb_probe(struct xenbus_device *dev,
+ /* complete the abuse: */
+ fb_info->pseudo_palette = fb_info->par;
+ fb_info->par = info;
++ fb_info->device = &dev->dev;
+
+ fb_info->screen_buffer = info->fb;
+
+diff --git a/drivers/watchdog/imx_sc_wdt.c b/drivers/watchdog/imx_sc_wdt.c
+index e51fe1b78518f4..d73076b686d8ca 100644
+--- a/drivers/watchdog/imx_sc_wdt.c
++++ b/drivers/watchdog/imx_sc_wdt.c
+@@ -216,29 +216,6 @@ static int imx_sc_wdt_probe(struct platform_device *pdev)
+ return devm_watchdog_register_device(dev, wdog);
+ }
+
+-static int __maybe_unused imx_sc_wdt_suspend(struct device *dev)
+-{
+- struct imx_sc_wdt_device *imx_sc_wdd = dev_get_drvdata(dev);
+-
+- if (watchdog_active(&imx_sc_wdd->wdd))
+- imx_sc_wdt_stop(&imx_sc_wdd->wdd);
+-
+- return 0;
+-}
+-
+-static int __maybe_unused imx_sc_wdt_resume(struct device *dev)
+-{
+- struct imx_sc_wdt_device *imx_sc_wdd = dev_get_drvdata(dev);
+-
+- if (watchdog_active(&imx_sc_wdd->wdd))
+- imx_sc_wdt_start(&imx_sc_wdd->wdd);
+-
+- return 0;
+-}
+-
+-static SIMPLE_DEV_PM_OPS(imx_sc_wdt_pm_ops,
+- imx_sc_wdt_suspend, imx_sc_wdt_resume);
+-
+ static const struct of_device_id imx_sc_wdt_dt_ids[] = {
+ { .compatible = "fsl,imx-sc-wdt", },
+ { /* sentinel */ }
+@@ -250,7 +227,6 @@ static struct platform_driver imx_sc_wdt_driver = {
+ .driver = {
+ .name = "imx-sc-wdt",
+ .of_match_table = imx_sc_wdt_dt_ids,
+- .pm = &imx_sc_wdt_pm_ops,
+ },
+ };
+ module_platform_driver(imx_sc_wdt_driver);
+diff --git a/drivers/xen/swiotlb-xen.c b/drivers/xen/swiotlb-xen.c
+index 6579ae3f6dac22..5e83d1e0bd184c 100644
+--- a/drivers/xen/swiotlb-xen.c
++++ b/drivers/xen/swiotlb-xen.c
+@@ -78,9 +78,15 @@ static inline int range_straddles_page_boundary(phys_addr_t p, size_t size)
+ {
+ unsigned long next_bfn, xen_pfn = XEN_PFN_DOWN(p);
+ unsigned int i, nr_pages = XEN_PFN_UP(xen_offset_in_page(p) + size);
++ phys_addr_t algn = 1ULL << (get_order(size) + PAGE_SHIFT);
+
+ next_bfn = pfn_to_bfn(xen_pfn);
+
++ /* If buffer is physically aligned, ensure DMA alignment. */
++ if (IS_ALIGNED(p, algn) &&
++ !IS_ALIGNED((phys_addr_t)next_bfn << XEN_PAGE_SHIFT, algn))
++ return 1;
++
+ for (i = 1; i < nr_pages; i++)
+ if (pfn_to_bfn(++xen_pfn) != ++next_bfn)
+ return 1;
+@@ -140,7 +146,7 @@ xen_swiotlb_alloc_coherent(struct device *dev, size_t size,
+ void *ret;
+
+ /* Align the allocation to the Xen page size */
+- size = 1UL << (order + XEN_PAGE_SHIFT);
++ size = ALIGN(size, XEN_PAGE_SIZE);
+
+ ret = (void *)__get_free_pages(flags, get_order(size));
+ if (!ret)
+@@ -172,7 +178,7 @@ xen_swiotlb_free_coherent(struct device *dev, size_t size, void *vaddr,
+ int order = get_order(size);
+
+ /* Convert the size to actually allocated. */
+- size = 1UL << (order + XEN_PAGE_SHIFT);
++ size = ALIGN(size, XEN_PAGE_SIZE);
+
+ if (WARN_ON_ONCE(dma_handle + size - 1 > dev->coherent_dma_mask) ||
+ WARN_ON_ONCE(range_straddles_page_boundary(phys, size)))
+diff --git a/fs/autofs/inode.c b/fs/autofs/inode.c
+index 1f5db686366316..bb404bfce036b4 100644
+--- a/fs/autofs/inode.c
++++ b/fs/autofs/inode.c
+@@ -172,8 +172,7 @@ static int autofs_parse_fd(struct fs_context *fc, struct autofs_sb_info *sbi,
+ ret = autofs_check_pipe(pipe);
+ if (ret < 0) {
+ errorf(fc, "Invalid/unusable pipe");
+- if (param->type != fs_value_is_file)
+- fput(pipe);
++ fput(pipe);
+ return -EBADF;
+ }
+
+diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
+index 6ed495ca7a311d..bc69bf0dbe93d2 100644
+--- a/fs/btrfs/btrfs_inode.h
++++ b/fs/btrfs/btrfs_inode.h
+@@ -126,6 +126,7 @@ struct btrfs_inode {
+ * logged_trans), to access/update delalloc_bytes, new_delalloc_bytes,
+ * defrag_bytes, disk_i_size, outstanding_extents, csum_bytes and to
+ * update the VFS' inode number of bytes used.
++ * Also protects setting struct file::private_data.
+ */
+ spinlock_t lock;
+
+diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
+index b2e4b30b8fae91..a4296ce1de7178 100644
+--- a/fs/btrfs/ctree.h
++++ b/fs/btrfs/ctree.h
+@@ -457,6 +457,8 @@ struct btrfs_file_private {
+ void *filldir_buf;
+ u64 last_index;
+ struct extent_state *llseek_cached_state;
++ /* Task that allocated this structure. */
++ struct task_struct *owner_task;
+ };
+
+ static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
+diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
+index 55be8a7f0bb188..79dd2d9a62d9df 100644
+--- a/fs/btrfs/extent-tree.c
++++ b/fs/btrfs/extent-tree.c
+@@ -6426,13 +6426,13 @@ int btrfs_trim_fs(struct btrfs_fs_info *fs_info, struct fstrim_range *range)
+ continue;
+
+ ret = btrfs_trim_free_extents(device, &group_trimmed);
++
++ trimmed += group_trimmed;
+ if (ret) {
+ dev_failed++;
+ dev_ret = ret;
+ break;
+ }
+-
+- trimmed += group_trimmed;
+ }
+ mutex_unlock(&fs_devices->device_list_mutex);
+
+diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
+index 66dfee87390672..0a14379a2d517d 100644
+--- a/fs/btrfs/file.c
++++ b/fs/btrfs/file.c
+@@ -3689,7 +3689,7 @@ static bool find_desired_extent_in_hole(struct btrfs_inode *inode, int whence,
+ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence)
+ {
+ struct btrfs_inode *inode = BTRFS_I(file->f_mapping->host);
+- struct btrfs_file_private *private = file->private_data;
++ struct btrfs_file_private *private;
+ struct btrfs_fs_info *fs_info = inode->root->fs_info;
+ struct extent_state *cached_state = NULL;
+ struct extent_state **delalloc_cached_state;
+@@ -3717,7 +3717,19 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence)
+ inode_get_bytes(&inode->vfs_inode) == i_size)
+ return i_size;
+
+- if (!private) {
++ spin_lock(&inode->lock);
++ private = file->private_data;
++ spin_unlock(&inode->lock);
++
++ if (private && private->owner_task != current) {
++ /*
++ * Not allocated by us, don't use it as its cached state is used
++ * by the task that allocated it and we don't want neither to
++ * mess with it nor get incorrect results because it reflects an
++ * invalid state for the current task.
++ */
++ private = NULL;
++ } else if (!private) {
+ private = kzalloc(sizeof(*private), GFP_KERNEL);
+ /*
+ * No worries if memory allocation failed.
+@@ -3725,7 +3737,23 @@ static loff_t find_desired_extent(struct file *file, loff_t offset, int whence)
+ * lseek SEEK_HOLE/DATA calls to a file when there's delalloc,
+ * so everything will still be correct.
+ */
+- file->private_data = private;
++ if (private) {
++ bool free = false;
++
++ private->owner_task = current;
++
++ spin_lock(&inode->lock);
++ if (file->private_data)
++ free = true;
++ else
++ file->private_data = private;
++ spin_unlock(&inode->lock);
++
++ if (free) {
++ kfree(private);
++ private = NULL;
++ }
++ }
+ }
+
+ if (private)
+diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
+index c1b0556e403683..4a30f34bc8300a 100644
+--- a/fs/btrfs/ioctl.c
++++ b/fs/btrfs/ioctl.c
+@@ -543,13 +543,11 @@ static noinline int btrfs_ioctl_fitrim(struct btrfs_fs_info *fs_info,
+
+ range.minlen = max(range.minlen, minlen);
+ ret = btrfs_trim_fs(fs_info, &range);
+- if (ret < 0)
+- return ret;
+
+ if (copy_to_user(arg, &range, sizeof(range)))
+ return -EFAULT;
+
+- return 0;
++ return ret;
+ }
+
+ int __pure btrfs_is_empty_uuid(u8 *uuid)
+diff --git a/fs/btrfs/subpage.c b/fs/btrfs/subpage.c
+index 54736f6238e659..831e96b607f505 100644
+--- a/fs/btrfs/subpage.c
++++ b/fs/btrfs/subpage.c
+@@ -766,8 +766,14 @@ void btrfs_folio_unlock_writer(struct btrfs_fs_info *fs_info,
+ }
+
+ #define GET_SUBPAGE_BITMAP(subpage, subpage_info, name, dst) \
+- bitmap_cut(dst, subpage->bitmaps, 0, \
+- subpage_info->name##_offset, subpage_info->bitmap_nr_bits)
++{ \
++ const int bitmap_nr_bits = subpage_info->bitmap_nr_bits; \
++ \
++ ASSERT(bitmap_nr_bits < BITS_PER_LONG); \
++ *dst = bitmap_read(subpage->bitmaps, \
++ subpage_info->name##_offset, \
++ bitmap_nr_bits); \
++}
+
+ void __cold btrfs_subpage_dump_bitmap(const struct btrfs_fs_info *fs_info,
+ struct folio *folio, u64 start, u32 len)
+diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
+index de1c063bc39dbe..42e2ec3cd1c11e 100644
+--- a/fs/btrfs/tree-checker.c
++++ b/fs/btrfs/tree-checker.c
+@@ -1499,7 +1499,7 @@ static int check_extent_item(struct extent_buffer *leaf,
+ dref_objectid > BTRFS_LAST_FREE_OBJECTID)) {
+ extent_err(leaf, slot,
+ "invalid data ref objectid value %llu",
+- dref_root);
++ dref_objectid);
+ return -EUCLEAN;
+ }
+ if (unlikely(!IS_ALIGNED(dref_offset,
+diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
+index 4dd8a993c60a8b..7c6f260a3be567 100644
+--- a/fs/cachefiles/xattr.c
++++ b/fs/cachefiles/xattr.c
+@@ -64,9 +64,15 @@ int cachefiles_set_object_xattr(struct cachefiles_object *object)
+ memcpy(buf->data, fscache_get_aux(object->cookie), len);
+
+ ret = cachefiles_inject_write_error();
+- if (ret == 0)
+- ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache,
+- buf, sizeof(struct cachefiles_xattr) + len, 0);
++ if (ret == 0) {
++ ret = mnt_want_write_file(file);
++ if (ret == 0) {
++ ret = vfs_setxattr(&nop_mnt_idmap, dentry,
++ cachefiles_xattr_cache, buf,
++ sizeof(struct cachefiles_xattr) + len, 0);
++ mnt_drop_write_file(file);
++ }
++ }
+ if (ret < 0) {
+ trace_cachefiles_vfs_error(object, file_inode(file), ret,
+ cachefiles_trace_setxattr_error);
+@@ -151,8 +157,14 @@ int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
+ int ret;
+
+ ret = cachefiles_inject_remove_error();
+- if (ret == 0)
+- ret = vfs_removexattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache);
++ if (ret == 0) {
++ ret = mnt_want_write(cache->mnt);
++ if (ret == 0) {
++ ret = vfs_removexattr(&nop_mnt_idmap, dentry,
++ cachefiles_xattr_cache);
++ mnt_drop_write(cache->mnt);
++ }
++ }
+ if (ret < 0) {
+ trace_cachefiles_vfs_error(object, d_inode(dentry), ret,
+ cachefiles_trace_remxattr_error);
+@@ -208,9 +220,15 @@ bool cachefiles_set_volume_xattr(struct cachefiles_volume *volume)
+ memcpy(buf->data, p, volume->vcookie->coherency_len);
+
+ ret = cachefiles_inject_write_error();
+- if (ret == 0)
+- ret = vfs_setxattr(&nop_mnt_idmap, dentry, cachefiles_xattr_cache,
+- buf, len, 0);
++ if (ret == 0) {
++ ret = mnt_want_write(volume->cache->mnt);
++ if (ret == 0) {
++ ret = vfs_setxattr(&nop_mnt_idmap, dentry,
++ cachefiles_xattr_cache,
++ buf, len, 0);
++ mnt_drop_write(volume->cache->mnt);
++ }
++ }
+ if (ret < 0) {
+ trace_cachefiles_vfs_error(NULL, d_inode(dentry), ret,
+ cachefiles_trace_setxattr_error);
+diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
+index 8fd928899a59e4..66d9b3b4c5881d 100644
+--- a/fs/debugfs/inode.c
++++ b/fs/debugfs/inode.c
+@@ -89,12 +89,14 @@ enum {
+ Opt_uid,
+ Opt_gid,
+ Opt_mode,
++ Opt_source,
+ };
+
+ static const struct fs_parameter_spec debugfs_param_specs[] = {
+- fsparam_u32 ("gid", Opt_gid),
++ fsparam_gid ("gid", Opt_gid),
+ fsparam_u32oct ("mode", Opt_mode),
+- fsparam_u32 ("uid", Opt_uid),
++ fsparam_uid ("uid", Opt_uid),
++ fsparam_string ("source", Opt_source),
+ {}
+ };
+
+@@ -102,8 +104,6 @@ static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param
+ {
+ struct debugfs_fs_info *opts = fc->s_fs_info;
+ struct fs_parse_result result;
+- kuid_t uid;
+- kgid_t gid;
+ int opt;
+
+ opt = fs_parse(fc, debugfs_param_specs, param, &result);
+@@ -120,20 +120,20 @@ static int debugfs_parse_param(struct fs_context *fc, struct fs_parameter *param
+
+ switch (opt) {
+ case Opt_uid:
+- uid = make_kuid(current_user_ns(), result.uint_32);
+- if (!uid_valid(uid))
+- return invalf(fc, "Unknown uid");
+- opts->uid = uid;
++ opts->uid = result.uid;
+ break;
+ case Opt_gid:
+- gid = make_kgid(current_user_ns(), result.uint_32);
+- if (!gid_valid(gid))
+- return invalf(fc, "Unknown gid");
+- opts->gid = gid;
++ opts->gid = result.gid;
+ break;
+ case Opt_mode:
+ opts->mode = result.uint_32 & S_IALLUGO;
+ break;
++ case Opt_source:
++ if (fc->source)
++ return invalfc(fc, "Multiple sources specified");
++ fc->source = param->string;
++ param->string = NULL;
++ break;
+ /*
+ * We might like to report bad mount options here;
+ * but traditionally debugfs has ignored all mount options
+diff --git a/fs/erofs/inode.c b/fs/erofs/inode.c
+index 5f6439a63af798..f2cab9e4f3bcd8 100644
+--- a/fs/erofs/inode.c
++++ b/fs/erofs/inode.c
+@@ -178,12 +178,14 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr,
+ unsigned int m_pofs)
+ {
+ struct erofs_inode *vi = EROFS_I(inode);
+- unsigned int bsz = i_blocksize(inode);
++ loff_t off;
+ char *lnk;
+
+- /* if it cannot be handled with fast symlink scheme */
+- if (vi->datalayout != EROFS_INODE_FLAT_INLINE ||
+- inode->i_size >= bsz || inode->i_size < 0) {
++ m_pofs += vi->xattr_isize;
++ /* check if it cannot be handled with fast symlink scheme */
++ if (vi->datalayout != EROFS_INODE_FLAT_INLINE || inode->i_size < 0 ||
++ check_add_overflow(m_pofs, inode->i_size, &off) ||
++ off > i_blocksize(inode)) {
+ inode->i_op = &erofs_symlink_iops;
+ return 0;
+ }
+@@ -192,16 +194,6 @@ static int erofs_fill_symlink(struct inode *inode, void *kaddr,
+ if (!lnk)
+ return -ENOMEM;
+
+- m_pofs += vi->xattr_isize;
+- /* inline symlink data shouldn't cross block boundary */
+- if (m_pofs + inode->i_size > bsz) {
+- kfree(lnk);
+- erofs_err(inode->i_sb,
+- "inline data cross block boundary @ nid %llu",
+- vi->nid);
+- DBG_BUGON(1);
+- return -EFSCORRUPTED;
+- }
+ memcpy(lnk, kaddr + m_pofs, inode->i_size);
+ lnk[inode->i_size] = '\0';
+
+diff --git a/fs/erofs/zdata.c b/fs/erofs/zdata.c
+index d6fe002a4a7194..2535479fb82dbe 100644
+--- a/fs/erofs/zdata.c
++++ b/fs/erofs/zdata.c
+@@ -19,10 +19,7 @@
+ typedef void *z_erofs_next_pcluster_t;
+
+ struct z_erofs_bvec {
+- union {
+- struct page *page;
+- struct folio *folio;
+- };
++ struct page *page;
+ int offset;
+ unsigned int end;
+ };
+@@ -617,32 +614,31 @@ static void z_erofs_bind_cache(struct z_erofs_decompress_frontend *fe)
+ fe->mode = Z_EROFS_PCLUSTER_FOLLOWED_NOINPLACE;
+ }
+
+-/* called by erofs_shrinker to get rid of all cached compressed bvecs */
++/* (erofs_shrinker) disconnect cached encoded data with pclusters */
+ int erofs_try_to_free_all_cached_folios(struct erofs_sb_info *sbi,
+ struct erofs_workgroup *grp)
+ {
+ struct z_erofs_pcluster *const pcl =
+ container_of(grp, struct z_erofs_pcluster, obj);
+ unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
++ struct folio *folio;
+ int i;
+
+ DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
+- /* There is no actice user since the pcluster is now freezed */
++ /* Each cached folio contains one page unless bs > ps is supported */
+ for (i = 0; i < pclusterpages; ++i) {
+- struct folio *folio = pcl->compressed_bvecs[i].folio;
++ if (pcl->compressed_bvecs[i].page) {
++ folio = page_folio(pcl->compressed_bvecs[i].page);
++ /* Avoid reclaiming or migrating this folio */
++ if (!folio_trylock(folio))
++ return -EBUSY;
+
+- if (!folio)
+- continue;
+-
+- /* Avoid reclaiming or migrating this folio */
+- if (!folio_trylock(folio))
+- return -EBUSY;
+-
+- if (!erofs_folio_is_managed(sbi, folio))
+- continue;
+- pcl->compressed_bvecs[i].folio = NULL;
+- folio_detach_private(folio);
+- folio_unlock(folio);
++ if (!erofs_folio_is_managed(sbi, folio))
++ continue;
++ pcl->compressed_bvecs[i].page = NULL;
++ folio_detach_private(folio);
++ folio_unlock(folio);
++ }
+ }
+ return 0;
+ }
+@@ -650,9 +646,9 @@ int erofs_try_to_free_all_cached_folios(struct erofs_sb_info *sbi,
+ static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
+ {
+ struct z_erofs_pcluster *pcl = folio_get_private(folio);
+- unsigned int pclusterpages = z_erofs_pclusterpages(pcl);
++ struct z_erofs_bvec *bvec = pcl->compressed_bvecs;
++ struct z_erofs_bvec *end = bvec + z_erofs_pclusterpages(pcl);
+ bool ret;
+- int i;
+
+ if (!folio_test_private(folio))
+ return true;
+@@ -661,9 +657,9 @@ static bool z_erofs_cache_release_folio(struct folio *folio, gfp_t gfp)
+ spin_lock(&pcl->obj.lockref.lock);
+ if (pcl->obj.lockref.count <= 0) {
+ DBG_BUGON(z_erofs_is_inline_pcluster(pcl));
+- for (i = 0; i < pclusterpages; ++i) {
+- if (pcl->compressed_bvecs[i].folio == folio) {
+- pcl->compressed_bvecs[i].folio = NULL;
++ for (; bvec < end; ++bvec) {
++ if (bvec->page && page_folio(bvec->page) == folio) {
++ bvec->page = NULL;
+ folio_detach_private(folio);
+ ret = true;
+ break;
+@@ -1066,7 +1062,7 @@ static bool z_erofs_is_sync_decompress(struct erofs_sb_info *sbi,
+
+ static bool z_erofs_page_is_invalidated(struct page *page)
+ {
+- return !page->mapping && !z_erofs_is_shortlived_page(page);
++ return !page_folio(page)->mapping && !z_erofs_is_shortlived_page(page);
+ }
+
+ struct z_erofs_decompress_backend {
+@@ -1419,6 +1415,7 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
+ bool tocache = false;
+ struct z_erofs_bvec zbv;
+ struct address_space *mapping;
++ struct folio *folio;
+ struct page *page;
+ int bs = i_blocksize(f->inode);
+
+@@ -1429,23 +1426,24 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
+ spin_lock(&pcl->obj.lockref.lock);
+ zbv = pcl->compressed_bvecs[nr];
+ spin_unlock(&pcl->obj.lockref.lock);
+- if (!zbv.folio)
++ if (!zbv.page)
+ goto out_allocfolio;
+
+- bvec->bv_page = &zbv.folio->page;
++ bvec->bv_page = zbv.page;
+ DBG_BUGON(z_erofs_is_shortlived_page(bvec->bv_page));
++
++ folio = page_folio(zbv.page);
+ /*
+ * Handle preallocated cached folios. We tried to allocate such folios
+ * without triggering direct reclaim. If allocation failed, inplace
+ * file-backed folios will be used instead.
+ */
+- if (zbv.folio->private == (void *)Z_EROFS_PREALLOCATED_PAGE) {
+- zbv.folio->private = 0;
++ if (folio->private == (void *)Z_EROFS_PREALLOCATED_PAGE) {
+ tocache = true;
+ goto out_tocache;
+ }
+
+- mapping = READ_ONCE(zbv.folio->mapping);
++ mapping = READ_ONCE(folio->mapping);
+ /*
+ * File-backed folios for inplace I/Os are all locked steady,
+ * therefore it is impossible for `mapping` to be NULL.
+@@ -1457,56 +1455,58 @@ static void z_erofs_fill_bio_vec(struct bio_vec *bvec,
+ return;
+ }
+
+- folio_lock(zbv.folio);
+- if (zbv.folio->mapping == mc) {
++ folio_lock(folio);
++ if (likely(folio->mapping == mc)) {
+ /*
+ * The cached folio is still in managed cache but without
+ * a valid `->private` pcluster hint. Let's reconnect them.
+ */
+- if (!folio_test_private(zbv.folio)) {
+- folio_attach_private(zbv.folio, pcl);
++ if (!folio_test_private(folio)) {
++ folio_attach_private(folio, pcl);
+ /* compressed_bvecs[] already takes a ref before */
+- folio_put(zbv.folio);
++ folio_put(folio);
+ }
+-
+- /* no need to submit if it is already up-to-date */
+- if (folio_test_uptodate(zbv.folio)) {
+- folio_unlock(zbv.folio);
+- bvec->bv_page = NULL;
++ if (likely(folio->private == pcl)) {
++ /* don't submit cache I/Os again if already uptodate */
++ if (folio_test_uptodate(folio)) {
++ folio_unlock(folio);
++ bvec->bv_page = NULL;
++ }
++ return;
+ }
+- return;
++ /*
++ * Already linked with another pcluster, which only appears in
++ * crafted images by fuzzers for now. But handle this anyway.
++ */
++ tocache = false; /* use temporary short-lived pages */
++ } else {
++ DBG_BUGON(1); /* referenced managed folios can't be truncated */
++ tocache = true;
+ }
+-
+- /*
+- * It has been truncated, so it's unsafe to reuse this one. Let's
+- * allocate a new page for compressed data.
+- */
+- DBG_BUGON(zbv.folio->mapping);
+- tocache = true;
+- folio_unlock(zbv.folio);
+- folio_put(zbv.folio);
++ folio_unlock(folio);
++ folio_put(folio);
+ out_allocfolio:
+ page = erofs_allocpage(&f->pagepool, gfp | __GFP_NOFAIL);
+ spin_lock(&pcl->obj.lockref.lock);
+- if (pcl->compressed_bvecs[nr].folio) {
++ if (unlikely(pcl->compressed_bvecs[nr].page != zbv.page)) {
+ erofs_pagepool_add(&f->pagepool, page);
+ spin_unlock(&pcl->obj.lockref.lock);
+ cond_resched();
+ goto repeat;
+ }
+- pcl->compressed_bvecs[nr].folio = zbv.folio = page_folio(page);
++ bvec->bv_page = pcl->compressed_bvecs[nr].page = page;
++ folio = page_folio(page);
+ spin_unlock(&pcl->obj.lockref.lock);
+- bvec->bv_page = page;
+ out_tocache:
+ if (!tocache || bs != PAGE_SIZE ||
+- filemap_add_folio(mc, zbv.folio, pcl->obj.index + nr, gfp)) {
++ filemap_add_folio(mc, folio, pcl->obj.index + nr, gfp)) {
+ /* turn into a temporary shortlived folio (1 ref) */
+- zbv.folio->private = (void *)Z_EROFS_SHORTLIVED_PAGE;
++ folio->private = (void *)Z_EROFS_SHORTLIVED_PAGE;
+ return;
+ }
+- folio_attach_private(zbv.folio, pcl);
++ folio_attach_private(folio, pcl);
+ /* drop a refcount added by allocpage (then 2 refs in total here) */
+- folio_put(zbv.folio);
++ folio_put(folio);
+ }
+
+ static struct z_erofs_decompressqueue *jobqueue_init(struct super_block *sb,
+@@ -1638,13 +1638,10 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
+ cur = mdev.m_pa;
+ end = cur + pcl->pclustersize;
+ do {
+- z_erofs_fill_bio_vec(&bvec, f, pcl, i++, mc);
+- if (!bvec.bv_page)
+- continue;
+-
++ bvec.bv_page = NULL;
+ if (bio && (cur != last_pa ||
+ bio->bi_bdev != mdev.m_bdev)) {
+-io_retry:
++drain_io:
+ if (!erofs_is_fscache_mode(sb))
+ submit_bio(bio);
+ else
+@@ -1657,6 +1654,15 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
+ bio = NULL;
+ }
+
++ if (!bvec.bv_page) {
++ z_erofs_fill_bio_vec(&bvec, f, pcl, i++, mc);
++ if (!bvec.bv_page)
++ continue;
++ if (cur + bvec.bv_len > end)
++ bvec.bv_len = end - cur;
++ DBG_BUGON(bvec.bv_len < sb->s_blocksize);
++ }
++
+ if (unlikely(PageWorkingset(bvec.bv_page)) &&
+ !memstall) {
+ psi_memstall_enter(&pflags);
+@@ -1676,13 +1682,9 @@ static void z_erofs_submit_queue(struct z_erofs_decompress_frontend *f,
+ ++nr_bios;
+ }
+
+- if (cur + bvec.bv_len > end)
+- bvec.bv_len = end - cur;
+- DBG_BUGON(bvec.bv_len < sb->s_blocksize);
+ if (!bio_add_page(bio, bvec.bv_page, bvec.bv_len,
+ bvec.bv_offset))
+- goto io_retry;
+-
++ goto drain_io;
+ last_pa = cur + bvec.bv_len;
+ bypass = false;
+ } while ((cur += bvec.bv_len) < end);
+diff --git a/fs/eventpoll.c b/fs/eventpoll.c
+index f53ca4f7fceddd..6d0e2f547ae7d1 100644
+--- a/fs/eventpoll.c
++++ b/fs/eventpoll.c
+@@ -420,7 +420,7 @@ static bool busy_loop_ep_timeout(unsigned long start_time,
+
+ static bool ep_busy_loop_on(struct eventpoll *ep)
+ {
+- return !!ep->busy_poll_usecs || net_busy_loop_on();
++ return !!READ_ONCE(ep->busy_poll_usecs) || net_busy_loop_on();
+ }
+
+ static bool ep_busy_loop_end(void *p, unsigned long start_time)
+diff --git a/fs/exfat/nls.c b/fs/exfat/nls.c
+index afdf13c34ff526..1ac011088ce76e 100644
+--- a/fs/exfat/nls.c
++++ b/fs/exfat/nls.c
+@@ -779,8 +779,11 @@ int exfat_create_upcase_table(struct super_block *sb)
+ le32_to_cpu(ep->dentry.upcase.checksum));
+
+ brelse(bh);
+- if (ret && ret != -EIO)
++ if (ret && ret != -EIO) {
++ /* free memory from exfat_load_upcase_table call */
++ exfat_free_upcase_table(sbi);
+ goto load_default;
++ }
+
+ /* load successfully */
+ return ret;
+diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
+index e9bbb1da2d0a24..5a3b4bc1241499 100644
+--- a/fs/ext4/ialloc.c
++++ b/fs/ext4/ialloc.c
+@@ -514,6 +514,8 @@ static int find_group_orlov(struct super_block *sb, struct inode *parent,
+ if (min_inodes < 1)
+ min_inodes = 1;
+ min_clusters = avefreec - EXT4_CLUSTERS_PER_GROUP(sb)*flex_size / 4;
++ if (min_clusters < 0)
++ min_clusters = 0;
+
+ /*
+ * Start looking in the flex group where we last allocated an
+@@ -755,10 +757,10 @@ int ext4_mark_inode_used(struct super_block *sb, int ino)
+ struct ext4_group_desc *gdp;
+ ext4_group_t group;
+ int bit;
+- int err = -EFSCORRUPTED;
++ int err;
+
+ if (ino < EXT4_FIRST_INO(sb) || ino > max_ino)
+- goto out;
++ return -EFSCORRUPTED;
+
+ group = (ino - 1) / EXT4_INODES_PER_GROUP(sb);
+ bit = (ino - 1) % EXT4_INODES_PER_GROUP(sb);
+@@ -860,6 +862,7 @@ int ext4_mark_inode_used(struct super_block *sb, int ino)
+ err = ext4_handle_dirty_metadata(NULL, NULL, group_desc_bh);
+ sync_dirty_buffer(group_desc_bh);
+ out:
++ brelse(inode_bitmap_bh);
+ return err;
+ }
+
+@@ -1053,12 +1056,13 @@ struct inode *__ext4_new_inode(struct mnt_idmap *idmap,
+ brelse(inode_bitmap_bh);
+ inode_bitmap_bh = ext4_read_inode_bitmap(sb, group);
+ /* Skip groups with suspicious inode tables */
+- if (((!(sbi->s_mount_state & EXT4_FC_REPLAY))
+- && EXT4_MB_GRP_IBITMAP_CORRUPT(grp)) ||
+- IS_ERR(inode_bitmap_bh)) {
++ if (IS_ERR(inode_bitmap_bh)) {
+ inode_bitmap_bh = NULL;
+ goto next_group;
+ }
++ if (!(sbi->s_mount_state & EXT4_FC_REPLAY) &&
++ EXT4_MB_GRP_IBITMAP_CORRUPT(grp))
++ goto next_group;
+
+ repeat_in_this_group:
+ ret2 = find_inode_bit(sb, group, inode_bitmap_bh, &ino);
+diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
+index e7a09a99837b96..44a5f6df59ecda 100644
+--- a/fs/ext4/inline.c
++++ b/fs/ext4/inline.c
+@@ -1664,24 +1664,36 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
+ struct ext4_dir_entry_2 **res_dir,
+ int *has_inline_data)
+ {
++ struct ext4_xattr_ibody_find is = {
++ .s = { .not_found = -ENODATA, },
++ };
++ struct ext4_xattr_info i = {
++ .name_index = EXT4_XATTR_INDEX_SYSTEM,
++ .name = EXT4_XATTR_SYSTEM_DATA,
++ };
+ int ret;
+- struct ext4_iloc iloc;
+ void *inline_start;
+ int inline_size;
+
+- if (ext4_get_inode_loc(dir, &iloc))
+- return NULL;
++ ret = ext4_get_inode_loc(dir, &is.iloc);
++ if (ret)
++ return ERR_PTR(ret);
+
+ down_read(&EXT4_I(dir)->xattr_sem);
++
++ ret = ext4_xattr_ibody_find(dir, &i, &is);
++ if (ret)
++ goto out;
++
+ if (!ext4_has_inline_data(dir)) {
+ *has_inline_data = 0;
+ goto out;
+ }
+
+- inline_start = (void *)ext4_raw_inode(&iloc)->i_block +
++ inline_start = (void *)ext4_raw_inode(&is.iloc)->i_block +
+ EXT4_INLINE_DOTDOT_SIZE;
+ inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
+- ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
++ ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size,
+ dir, fname, 0, res_dir);
+ if (ret == 1)
+ goto out_find;
+@@ -1691,20 +1703,23 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
+ if (ext4_get_inline_size(dir) == EXT4_MIN_INLINE_DATA_SIZE)
+ goto out;
+
+- inline_start = ext4_get_inline_xattr_pos(dir, &iloc);
++ inline_start = ext4_get_inline_xattr_pos(dir, &is.iloc);
+ inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
+
+- ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
++ ret = ext4_search_dir(is.iloc.bh, inline_start, inline_size,
+ dir, fname, 0, res_dir);
+ if (ret == 1)
+ goto out_find;
+
+ out:
+- brelse(iloc.bh);
+- iloc.bh = NULL;
++ brelse(is.iloc.bh);
++ if (ret < 0)
++ is.iloc.bh = ERR_PTR(ret);
++ else
++ is.iloc.bh = NULL;
+ out_find:
+ up_read(&EXT4_I(dir)->xattr_sem);
+- return iloc.bh;
++ return is.iloc.bh;
+ }
+
+ int ext4_delete_inline_entry(handle_t *handle,
+diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
+index 9dda9cd68ab2f5..dfecd25cee4eae 100644
+--- a/fs/ext4/mballoc.c
++++ b/fs/ext4/mballoc.c
+@@ -3887,11 +3887,8 @@ static void ext4_free_data_in_buddy(struct super_block *sb,
+ /*
+ * Clear the trimmed flag for the group so that the next
+ * ext4_trim_fs can trim it.
+- * If the volume is mounted with -o discard, online discard
+- * is supported and the free blocks will be trimmed online.
+ */
+- if (!test_opt(sb, DISCARD))
+- EXT4_MB_GRP_CLEAR_TRIMMED(db);
++ EXT4_MB_GRP_CLEAR_TRIMMED(db);
+
+ if (!db->bb_free_root.rb_node) {
+ /* No more items in the per group rb tree
+@@ -6515,8 +6512,9 @@ static void ext4_mb_clear_bb(handle_t *handle, struct inode *inode,
+ " group:%u block:%d count:%lu failed"
+ " with %d", block_group, bit, count,
+ err);
+- } else
+- EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
++ }
++
++ EXT4_MB_GRP_CLEAR_TRIMMED(e4b.bd_info);
+
+ ext4_lock_group(sb, block_group);
+ mb_free_blocks(inode, &e4b, bit, count_clusters);
+diff --git a/fs/ext4/super.c b/fs/ext4/super.c
+index c682fb927b64b8..edc692984404d5 100644
+--- a/fs/ext4/super.c
++++ b/fs/ext4/super.c
+@@ -5177,6 +5177,18 @@ static int ext4_block_group_meta_init(struct super_block *sb, int silent)
+ return 0;
+ }
+
++/*
++ * It's hard to get stripe aligned blocks if stripe is not aligned with
++ * cluster, just disable stripe and alert user to simplify code and avoid
++ * stripe aligned allocation which will rarely succeed.
++ */
++static bool ext4_is_stripe_incompatible(struct super_block *sb, unsigned long stripe)
++{
++ struct ext4_sb_info *sbi = EXT4_SB(sb);
++ return (stripe > 0 && sbi->s_cluster_ratio > 1 &&
++ stripe % sbi->s_cluster_ratio != 0);
++}
++
+ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
+ {
+ struct ext4_super_block *es = NULL;
+@@ -5284,13 +5296,7 @@ static int __ext4_fill_super(struct fs_context *fc, struct super_block *sb)
+ goto failed_mount3;
+
+ sbi->s_stripe = ext4_get_stripe_size(sbi);
+- /*
+- * It's hard to get stripe aligned blocks if stripe is not aligned with
+- * cluster, just disable stripe and alert user to simpfy code and avoid
+- * stripe aligned allocation which will rarely successes.
+- */
+- if (sbi->s_stripe > 0 && sbi->s_cluster_ratio > 1 &&
+- sbi->s_stripe % sbi->s_cluster_ratio != 0) {
++ if (ext4_is_stripe_incompatible(sb, sbi->s_stripe)) {
+ ext4_msg(sb, KERN_WARNING,
+ "stripe (%lu) is not aligned with cluster size (%u), "
+ "stripe is disabled",
+@@ -6453,6 +6459,15 @@ static int __ext4_remount(struct fs_context *fc, struct super_block *sb)
+
+ }
+
++ if ((ctx->spec & EXT4_SPEC_s_stripe) &&
++ ext4_is_stripe_incompatible(sb, ctx->s_stripe)) {
++ ext4_msg(sb, KERN_WARNING,
++ "stripe (%lu) is not aligned with cluster size (%u), "
++ "stripe is disabled",
++ ctx->s_stripe, sbi->s_cluster_ratio);
++ ctx->s_stripe = 0;
++ }
++
+ /*
+ * Changing the DIOREAD_NOLOCK or DELALLOC mount options may cause
+ * two calls to ext4_should_dioread_nolock() to return inconsistent
+diff --git a/fs/f2fs/compress.c b/fs/f2fs/compress.c
+index 1ef82a5463910e..b0506745adab7a 100644
+--- a/fs/f2fs/compress.c
++++ b/fs/f2fs/compress.c
+@@ -945,7 +945,7 @@ static int __f2fs_get_cluster_blocks(struct inode *inode,
+ unsigned int cluster_size = F2FS_I(inode)->i_cluster_size;
+ int count, i;
+
+- for (i = 1, count = 1; i < cluster_size; i++) {
++ for (i = 0, count = 0; i < cluster_size; i++) {
+ block_t blkaddr = data_blkaddr(dn->inode, dn->node_page,
+ dn->ofs_in_node + i);
+
+@@ -956,8 +956,8 @@ static int __f2fs_get_cluster_blocks(struct inode *inode,
+ return count;
+ }
+
+-static int __f2fs_cluster_blocks(struct inode *inode,
+- unsigned int cluster_idx, bool compr_blks)
++static int __f2fs_cluster_blocks(struct inode *inode, unsigned int cluster_idx,
++ enum cluster_check_type type)
+ {
+ struct dnode_of_data dn;
+ unsigned int start_idx = cluster_idx <<
+@@ -978,10 +978,12 @@ static int __f2fs_cluster_blocks(struct inode *inode,
+ }
+
+ if (dn.data_blkaddr == COMPRESS_ADDR) {
+- if (compr_blks)
+- ret = __f2fs_get_cluster_blocks(inode, &dn);
+- else
++ if (type == CLUSTER_COMPR_BLKS)
++ ret = 1 + __f2fs_get_cluster_blocks(inode, &dn);
++ else if (type == CLUSTER_IS_COMPR)
+ ret = 1;
++ } else if (type == CLUSTER_RAW_BLKS) {
++ ret = __f2fs_get_cluster_blocks(inode, &dn);
+ }
+ fail:
+ f2fs_put_dnode(&dn);
+@@ -991,7 +993,16 @@ static int __f2fs_cluster_blocks(struct inode *inode,
+ /* return # of compressed blocks in compressed cluster */
+ static int f2fs_compressed_blocks(struct compress_ctx *cc)
+ {
+- return __f2fs_cluster_blocks(cc->inode, cc->cluster_idx, true);
++ return __f2fs_cluster_blocks(cc->inode, cc->cluster_idx,
++ CLUSTER_COMPR_BLKS);
++}
++
++/* return # of raw blocks in non-compressed cluster */
++static int f2fs_decompressed_blocks(struct inode *inode,
++ unsigned int cluster_idx)
++{
++ return __f2fs_cluster_blocks(inode, cluster_idx,
++ CLUSTER_RAW_BLKS);
+ }
+
+ /* return whether cluster is compressed one or not */
+@@ -999,7 +1010,16 @@ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index)
+ {
+ return __f2fs_cluster_blocks(inode,
+ index >> F2FS_I(inode)->i_log_cluster_size,
+- false);
++ CLUSTER_IS_COMPR);
++}
++
++/* return whether cluster contains non raw blocks or not */
++bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index)
++{
++ unsigned int cluster_idx = index >> F2FS_I(inode)->i_log_cluster_size;
++
++ return f2fs_decompressed_blocks(inode, cluster_idx) !=
++ F2FS_I(inode)->i_cluster_size;
+ }
+
+ static bool cluster_may_compress(struct compress_ctx *cc)
+diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
+index 467f67cf2b3800..825f6bcb7fc2ee 100644
+--- a/fs/f2fs/data.c
++++ b/fs/f2fs/data.c
+@@ -2645,10 +2645,13 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
+ struct dnode_of_data dn;
+ struct node_info ni;
+ bool ipu_force = false;
++ bool atomic_commit;
+ int err = 0;
+
+ /* Use COW inode to make dnode_of_data for atomic write */
+- if (f2fs_is_atomic_file(inode))
++ atomic_commit = f2fs_is_atomic_file(inode) &&
++ page_private_atomic(fio->page);
++ if (atomic_commit)
+ set_new_dnode(&dn, F2FS_I(inode)->cow_inode, NULL, NULL, 0);
+ else
+ set_new_dnode(&dn, inode, NULL, NULL, 0);
+@@ -2747,6 +2750,8 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
+ f2fs_outplace_write_data(&dn, fio);
+ trace_f2fs_do_write_data_page(page_folio(page), OPU);
+ set_inode_flag(inode, FI_APPEND_WRITE);
++ if (atomic_commit)
++ clear_page_private_atomic(page);
+ out_writepage:
+ f2fs_put_dnode(&dn);
+ out:
+@@ -3716,6 +3721,9 @@ static int f2fs_write_end(struct file *file,
+
+ set_page_dirty(page);
+
++ if (f2fs_is_atomic_file(inode))
++ set_page_private_atomic(page);
++
+ if (pos + copied > i_size_read(inode) &&
+ !f2fs_verity_in_progress(inode)) {
+ f2fs_i_size_write(inode, pos + copied);
+diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
+index 02c9355176d3b5..5a00e010f8c112 100644
+--- a/fs/f2fs/dir.c
++++ b/fs/f2fs/dir.c
+@@ -157,7 +157,8 @@ static unsigned long dir_block_index(unsigned int level,
+ unsigned long bidx = 0;
+
+ for (i = 0; i < level; i++)
+- bidx += dir_buckets(i, dir_level) * bucket_blocks(i);
++ bidx += mul_u32_u32(dir_buckets(i, dir_level),
++ bucket_blocks(i));
+ bidx += idx * bucket_blocks(level);
+ return bidx;
+ }
+diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
+index fd1fc06359eea3..62ac440d94168a 100644
+--- a/fs/f2fs/extent_cache.c
++++ b/fs/f2fs/extent_cache.c
+@@ -366,7 +366,7 @@ static unsigned int __free_extent_tree(struct f2fs_sb_info *sbi,
+ static void __drop_largest_extent(struct extent_tree *et,
+ pgoff_t fofs, unsigned int len)
+ {
+- if (fofs < et->largest.fofs + et->largest.len &&
++ if (fofs < (pgoff_t)et->largest.fofs + et->largest.len &&
+ fofs + len > et->largest.fofs) {
+ et->largest.len = 0;
+ et->largest_updated = true;
+@@ -456,7 +456,7 @@ static bool __lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
+
+ if (type == EX_READ &&
+ et->largest.fofs <= pgofs &&
+- et->largest.fofs + et->largest.len > pgofs) {
++ (pgoff_t)et->largest.fofs + et->largest.len > pgofs) {
+ *ei = et->largest;
+ ret = true;
+ stat_inc_largest_node_hit(sbi);
+diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
+index 92fda31c68cdc3..9c8acb98f4dbf6 100644
+--- a/fs/f2fs/f2fs.h
++++ b/fs/f2fs/f2fs.h
+@@ -285,6 +285,7 @@ enum {
+ APPEND_INO, /* for append ino list */
+ UPDATE_INO, /* for update ino list */
+ TRANS_DIR_INO, /* for transactions dir ino list */
++ XATTR_DIR_INO, /* for xattr updated dir ino list */
+ FLUSH_INO, /* for multiple device flushing */
+ MAX_INO_ENTRY, /* max. list */
+ };
+@@ -784,7 +785,6 @@ enum {
+ FI_NEED_IPU, /* used for ipu per file */
+ FI_ATOMIC_FILE, /* indicate atomic file */
+ FI_DATA_EXIST, /* indicate data exists */
+- FI_INLINE_DOTS, /* indicate inline dot dentries */
+ FI_SKIP_WRITES, /* should skip data page writeback */
+ FI_OPU_WRITE, /* used for opu per file */
+ FI_DIRTY_FILE, /* indicate regular/symlink has dirty pages */
+@@ -802,6 +802,7 @@ enum {
+ FI_ALIGNED_WRITE, /* enable aligned write */
+ FI_COW_FILE, /* indicate COW file */
+ FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */
++ FI_ATOMIC_DIRTIED, /* indicate atomic file is dirtied */
+ FI_ATOMIC_REPLACE, /* indicate atomic replace */
+ FI_OPENED_FILE, /* indicate file has been opened */
+ FI_MAX, /* max flag, never be used */
+@@ -1155,6 +1156,7 @@ enum cp_reason_type {
+ CP_FASTBOOT_MODE,
+ CP_SPEC_LOG_NUM,
+ CP_RECOVER_DIR,
++ CP_XATTR_DIR,
+ };
+
+ enum iostat_type {
+@@ -1418,7 +1420,8 @@ static inline void f2fs_clear_bit(unsigned int nr, char *addr);
+ * bit 1 PAGE_PRIVATE_ONGOING_MIGRATION
+ * bit 2 PAGE_PRIVATE_INLINE_INODE
+ * bit 3 PAGE_PRIVATE_REF_RESOURCE
+- * bit 4- f2fs private data
++ * bit 4 PAGE_PRIVATE_ATOMIC_WRITE
++ * bit 5- f2fs private data
+ *
+ * Layout B: lowest bit should be 0
+ * page.private is a wrapped pointer.
+@@ -1428,6 +1431,7 @@ enum {
+ PAGE_PRIVATE_ONGOING_MIGRATION, /* data page which is on-going migrating */
+ PAGE_PRIVATE_INLINE_INODE, /* inode page contains inline data */
+ PAGE_PRIVATE_REF_RESOURCE, /* dirty page has referenced resources */
++ PAGE_PRIVATE_ATOMIC_WRITE, /* data page from atomic write path */
+ PAGE_PRIVATE_MAX
+ };
+
+@@ -2396,14 +2400,17 @@ static inline void clear_page_private_##name(struct page *page) \
+ PAGE_PRIVATE_GET_FUNC(nonpointer, NOT_POINTER);
+ PAGE_PRIVATE_GET_FUNC(inline, INLINE_INODE);
+ PAGE_PRIVATE_GET_FUNC(gcing, ONGOING_MIGRATION);
++PAGE_PRIVATE_GET_FUNC(atomic, ATOMIC_WRITE);
+
+ PAGE_PRIVATE_SET_FUNC(reference, REF_RESOURCE);
+ PAGE_PRIVATE_SET_FUNC(inline, INLINE_INODE);
+ PAGE_PRIVATE_SET_FUNC(gcing, ONGOING_MIGRATION);
++PAGE_PRIVATE_SET_FUNC(atomic, ATOMIC_WRITE);
+
+ PAGE_PRIVATE_CLEAR_FUNC(reference, REF_RESOURCE);
+ PAGE_PRIVATE_CLEAR_FUNC(inline, INLINE_INODE);
+ PAGE_PRIVATE_CLEAR_FUNC(gcing, ONGOING_MIGRATION);
++PAGE_PRIVATE_CLEAR_FUNC(atomic, ATOMIC_WRITE);
+
+ static inline unsigned long get_page_private_data(struct page *page)
+ {
+@@ -2435,6 +2442,7 @@ static inline void clear_page_private_all(struct page *page)
+ clear_page_private_reference(page);
+ clear_page_private_gcing(page);
+ clear_page_private_inline(page);
++ clear_page_private_atomic(page);
+
+ f2fs_bug_on(F2FS_P_SB(page), page_private(page));
+ }
+@@ -3038,10 +3046,8 @@ static inline void __mark_inode_dirty_flag(struct inode *inode,
+ return;
+ fallthrough;
+ case FI_DATA_EXIST:
+- case FI_INLINE_DOTS:
+ case FI_PIN_FILE:
+ case FI_COMPRESS_RELEASED:
+- case FI_ATOMIC_COMMITTED:
+ f2fs_mark_inode_dirty_sync(inode, true);
+ }
+ }
+@@ -3163,8 +3169,6 @@ static inline void get_inline_info(struct inode *inode, struct f2fs_inode *ri)
+ set_bit(FI_INLINE_DENTRY, fi->flags);
+ if (ri->i_inline & F2FS_DATA_EXIST)
+ set_bit(FI_DATA_EXIST, fi->flags);
+- if (ri->i_inline & F2FS_INLINE_DOTS)
+- set_bit(FI_INLINE_DOTS, fi->flags);
+ if (ri->i_inline & F2FS_EXTRA_ATTR)
+ set_bit(FI_EXTRA_ATTR, fi->flags);
+ if (ri->i_inline & F2FS_PIN_FILE)
+@@ -3185,8 +3189,6 @@ static inline void set_raw_inline(struct inode *inode, struct f2fs_inode *ri)
+ ri->i_inline |= F2FS_INLINE_DENTRY;
+ if (is_inode_flag_set(inode, FI_DATA_EXIST))
+ ri->i_inline |= F2FS_DATA_EXIST;
+- if (is_inode_flag_set(inode, FI_INLINE_DOTS))
+- ri->i_inline |= F2FS_INLINE_DOTS;
+ if (is_inode_flag_set(inode, FI_EXTRA_ATTR))
+ ri->i_inline |= F2FS_EXTRA_ATTR;
+ if (is_inode_flag_set(inode, FI_PIN_FILE))
+@@ -3273,11 +3275,6 @@ static inline int f2fs_exist_data(struct inode *inode)
+ return is_inode_flag_set(inode, FI_DATA_EXIST);
+ }
+
+-static inline int f2fs_has_inline_dots(struct inode *inode)
+-{
+- return is_inode_flag_set(inode, FI_INLINE_DOTS);
+-}
+-
+ static inline int f2fs_is_mmap_file(struct inode *inode)
+ {
+ return is_inode_flag_set(inode, FI_MMAP_FILE);
+@@ -3501,7 +3498,7 @@ int f2fs_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+ int f2fs_truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
+ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count);
+ int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
+- bool readonly);
++ bool readonly, bool need_lock);
+ int f2fs_precache_extents(struct inode *inode);
+ int f2fs_fileattr_get(struct dentry *dentry, struct fileattr *fa);
+ int f2fs_fileattr_set(struct mnt_idmap *idmap,
+@@ -4280,6 +4277,11 @@ static inline bool f2fs_meta_inode_gc_required(struct inode *inode)
+ * compress.c
+ */
+ #ifdef CONFIG_F2FS_FS_COMPRESSION
++enum cluster_check_type {
++ CLUSTER_IS_COMPR, /* check only if compressed cluster */
++ CLUSTER_COMPR_BLKS, /* return # of compressed blocks in a cluster */
++ CLUSTER_RAW_BLKS /* return # of raw blocks in a cluster */
++};
+ bool f2fs_is_compressed_page(struct page *page);
+ struct page *f2fs_compress_control_page(struct page *page);
+ int f2fs_prepare_compress_overwrite(struct inode *inode,
+@@ -4306,6 +4308,7 @@ int f2fs_write_multi_pages(struct compress_ctx *cc,
+ struct writeback_control *wbc,
+ enum iostat_type io_type);
+ int f2fs_is_compressed_cluster(struct inode *inode, pgoff_t index);
++bool f2fs_is_sparse_cluster(struct inode *inode, pgoff_t index);
+ void f2fs_update_read_extent_tree_range_compressed(struct inode *inode,
+ pgoff_t fofs, block_t blkaddr,
+ unsigned int llen, unsigned int c_len);
+@@ -4392,6 +4395,12 @@ static inline bool f2fs_load_compressed_page(struct f2fs_sb_info *sbi,
+ static inline void f2fs_invalidate_compress_pages(struct f2fs_sb_info *sbi,
+ nid_t ino) { }
+ #define inc_compr_inode_stat(inode) do { } while (0)
++static inline int f2fs_is_compressed_cluster(
++ struct inode *inode,
++ pgoff_t index) { return 0; }
++static inline bool f2fs_is_sparse_cluster(
++ struct inode *inode,
++ pgoff_t index) { return true; }
+ static inline void f2fs_update_read_extent_tree_range_compressed(
+ struct inode *inode,
+ pgoff_t fofs, block_t blkaddr,
+diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
+index 387ce167dda1b4..4bee980c6d1862 100644
+--- a/fs/f2fs/file.c
++++ b/fs/f2fs/file.c
+@@ -218,6 +218,9 @@ static inline enum cp_reason_type need_do_checkpoint(struct inode *inode)
+ f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
+ TRANS_DIR_INO))
+ cp_reason = CP_RECOVER_DIR;
++ else if (f2fs_exist_written_data(sbi, F2FS_I(inode)->i_pino,
++ XATTR_DIR_INO))
++ cp_reason = CP_XATTR_DIR;
+
+ return cp_reason;
+ }
+@@ -2117,10 +2120,12 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
+ struct mnt_idmap *idmap = file_mnt_idmap(filp);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+- struct inode *pinode;
+ loff_t isize;
+ int ret;
+
++ if (!(filp->f_mode & FMODE_WRITE))
++ return -EBADF;
++
+ if (!inode_owner_or_capable(idmap, inode))
+ return -EACCES;
+
+@@ -2167,15 +2172,10 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
+ /* Check if the inode already has a COW inode */
+ if (fi->cow_inode == NULL) {
+ /* Create a COW inode for atomic write */
+- pinode = f2fs_iget(inode->i_sb, fi->i_pino);
+- if (IS_ERR(pinode)) {
+- f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+- ret = PTR_ERR(pinode);
+- goto out;
+- }
++ struct dentry *dentry = file_dentry(filp);
++ struct inode *dir = d_inode(dentry->d_parent);
+
+- ret = f2fs_get_tmpfile(idmap, pinode, &fi->cow_inode);
+- iput(pinode);
++ ret = f2fs_get_tmpfile(idmap, dir, &fi->cow_inode);
+ if (ret) {
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+ goto out;
+@@ -2188,6 +2188,10 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
+ F2FS_I(fi->cow_inode)->atomic_inode = inode;
+ } else {
+ /* Reuse the already created COW inode */
++ f2fs_bug_on(sbi, get_dirty_pages(fi->cow_inode));
++
++ invalidate_mapping_pages(fi->cow_inode->i_mapping, 0, -1);
++
+ ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
+ if (ret) {
+ f2fs_up_write(&fi->i_gc_rwsem[WRITE]);
+@@ -2229,6 +2233,9 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
+ struct mnt_idmap *idmap = file_mnt_idmap(filp);
+ int ret;
+
++ if (!(filp->f_mode & FMODE_WRITE))
++ return -EBADF;
++
+ if (!inode_owner_or_capable(idmap, inode))
+ return -EACCES;
+
+@@ -2261,6 +2268,9 @@ static int f2fs_ioc_abort_atomic_write(struct file *filp)
+ struct mnt_idmap *idmap = file_mnt_idmap(filp);
+ int ret;
+
++ if (!(filp->f_mode & FMODE_WRITE))
++ return -EBADF;
++
+ if (!inode_owner_or_capable(idmap, inode))
+ return -EACCES;
+
+@@ -2280,7 +2290,7 @@ static int f2fs_ioc_abort_atomic_write(struct file *filp)
+ }
+
+ int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
+- bool readonly)
++ bool readonly, bool need_lock)
+ {
+ struct super_block *sb = sbi->sb;
+ int ret = 0;
+@@ -2327,12 +2337,19 @@ int f2fs_do_shutdown(struct f2fs_sb_info *sbi, unsigned int flag,
+ if (readonly)
+ goto out;
+
++ /* grab sb->s_umount to avoid racing w/ remount() */
++ if (need_lock)
++ down_read(&sbi->sb->s_umount);
++
+ f2fs_stop_gc_thread(sbi);
+ f2fs_stop_discard_thread(sbi);
+
+ f2fs_drop_discard_cmd(sbi);
+ clear_opt(sbi, DISCARD);
+
++ if (need_lock)
++ up_read(&sbi->sb->s_umount);
++
+ f2fs_update_time(sbi, REQ_TIME);
+ out:
+
+@@ -2369,7 +2386,7 @@ static int f2fs_ioc_shutdown(struct file *filp, unsigned long arg)
+ }
+ }
+
+- ret = f2fs_do_shutdown(sbi, in, readonly);
++ ret = f2fs_do_shutdown(sbi, in, readonly, true);
+
+ if (need_drop)
+ mnt_drop_write_file(filp);
+@@ -2687,7 +2704,8 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
+ (range->start + range->len) >> PAGE_SHIFT,
+ DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE));
+
+- if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED)) {
++ if (is_inode_flag_set(inode, FI_COMPRESS_RELEASED) ||
++ f2fs_is_atomic_file(inode)) {
+ err = -EINVAL;
+ goto unlock_out;
+ }
+@@ -2711,7 +2729,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
+ * block addresses are continuous.
+ */
+ if (f2fs_lookup_read_extent_cache(inode, pg_start, &ei)) {
+- if (ei.fofs + ei.len >= pg_end)
++ if ((pgoff_t)ei.fofs + ei.len >= pg_end)
+ goto out;
+ }
+
+@@ -2794,6 +2812,8 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
+ goto clear_out;
+ }
+
++ f2fs_wait_on_page_writeback(page, DATA, true, true);
++
+ set_page_dirty(page);
+ set_page_private_gcing(page);
+ f2fs_put_page(page, 1);
+@@ -2918,6 +2938,11 @@ static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
+ goto out_unlock;
+ }
+
++ if (f2fs_is_atomic_file(src) || f2fs_is_atomic_file(dst)) {
++ ret = -EINVAL;
++ goto out_unlock;
++ }
++
+ ret = -EINVAL;
+ if (pos_in + len > src->i_size || pos_in + len < pos_in)
+ goto out_unlock;
+@@ -3301,6 +3326,11 @@ static int f2fs_ioc_set_pin_file(struct file *filp, unsigned long arg)
+
+ inode_lock(inode);
+
++ if (f2fs_is_atomic_file(inode)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
+ if (!pin) {
+ clear_inode_flag(inode, FI_PIN_FILE);
+ f2fs_i_gc_failures_write(inode, 0);
+@@ -4187,6 +4217,8 @@ static int redirty_blocks(struct inode *inode, pgoff_t page_idx, int len)
+ /* It will never fail, when page has pinned above */
+ f2fs_bug_on(F2FS_I_SB(inode), !page);
+
++ f2fs_wait_on_page_writeback(page, DATA, true, true);
++
+ set_page_dirty(page);
+ set_page_private_gcing(page);
+ f2fs_put_page(page, 1);
+@@ -4201,9 +4233,8 @@ static int f2fs_ioc_decompress_file(struct file *filp)
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_inode_info *fi = F2FS_I(inode);
+- pgoff_t page_idx = 0, last_idx;
+- int cluster_size = fi->i_cluster_size;
+- int count, ret;
++ pgoff_t page_idx = 0, last_idx, cluster_idx;
++ int ret;
+
+ if (!f2fs_sb_has_compression(sbi) ||
+ F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
+@@ -4236,10 +4267,15 @@ static int f2fs_ioc_decompress_file(struct file *filp)
+ goto out;
+
+ last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
++ last_idx >>= fi->i_log_cluster_size;
++
++ for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) {
++ page_idx = cluster_idx << fi->i_log_cluster_size;
++
++ if (!f2fs_is_compressed_cluster(inode, page_idx))
++ continue;
+
+- count = last_idx - page_idx;
+- while (count && count >= cluster_size) {
+- ret = redirty_blocks(inode, page_idx, cluster_size);
++ ret = redirty_blocks(inode, page_idx, fi->i_cluster_size);
+ if (ret < 0)
+ break;
+
+@@ -4249,9 +4285,6 @@ static int f2fs_ioc_decompress_file(struct file *filp)
+ break;
+ }
+
+- count -= cluster_size;
+- page_idx += cluster_size;
+-
+ cond_resched();
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+@@ -4278,9 +4311,9 @@ static int f2fs_ioc_compress_file(struct file *filp)
+ {
+ struct inode *inode = file_inode(filp);
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+- pgoff_t page_idx = 0, last_idx;
+- int cluster_size = F2FS_I(inode)->i_cluster_size;
+- int count, ret;
++ struct f2fs_inode_info *fi = F2FS_I(inode);
++ pgoff_t page_idx = 0, last_idx, cluster_idx;
++ int ret;
+
+ if (!f2fs_sb_has_compression(sbi) ||
+ F2FS_OPTION(sbi).compress_mode != COMPR_MODE_USER)
+@@ -4312,10 +4345,15 @@ static int f2fs_ioc_compress_file(struct file *filp)
+ set_inode_flag(inode, FI_ENABLE_COMPRESS);
+
+ last_idx = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
++ last_idx >>= fi->i_log_cluster_size;
++
++ for (cluster_idx = 0; cluster_idx < last_idx; cluster_idx++) {
++ page_idx = cluster_idx << fi->i_log_cluster_size;
+
+- count = last_idx - page_idx;
+- while (count && count >= cluster_size) {
+- ret = redirty_blocks(inode, page_idx, cluster_size);
++ if (f2fs_is_sparse_cluster(inode, page_idx))
++ continue;
++
++ ret = redirty_blocks(inode, page_idx, fi->i_cluster_size);
+ if (ret < 0)
+ break;
+
+@@ -4325,9 +4363,6 @@ static int f2fs_ioc_compress_file(struct file *filp)
+ break;
+ }
+
+- count -= cluster_size;
+- page_idx += cluster_size;
+-
+ cond_resched();
+ if (fatal_signal_pending(current)) {
+ ret = -EINTR;
+@@ -4587,6 +4622,10 @@ static ssize_t f2fs_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
+ f2fs_trace_rw_file_path(iocb->ki_filp, iocb->ki_pos,
+ iov_iter_count(to), READ);
+
++ /* In LFS mode, if there is inflight dio, wait for its completion */
++ if (f2fs_lfs_mode(F2FS_I_SB(inode)))
++ inode_dio_wait(inode);
++
+ if (f2fs_should_use_dio(inode, iocb, to)) {
+ ret = f2fs_dio_read_iter(iocb, to);
+ } else {
+diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
+index 57da02bfa823ef..0b23a0cb438fde 100644
+--- a/fs/f2fs/inode.c
++++ b/fs/f2fs/inode.c
+@@ -35,6 +35,11 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
+ if (f2fs_inode_dirtied(inode, sync))
+ return;
+
++ if (f2fs_is_atomic_file(inode)) {
++ set_inode_flag(inode, FI_ATOMIC_DIRTIED);
++ return;
++ }
++
+ mark_inode_dirty_sync(inode);
+ }
+
+diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
+index e54f8c08bda832..a2c4091fca6fac 100644
+--- a/fs/f2fs/namei.c
++++ b/fs/f2fs/namei.c
+@@ -455,62 +455,6 @@ struct dentry *f2fs_get_parent(struct dentry *child)
+ return d_obtain_alias(f2fs_iget(child->d_sb, ino));
+ }
+
+-static int __recover_dot_dentries(struct inode *dir, nid_t pino)
+-{
+- struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
+- struct qstr dot = QSTR_INIT(".", 1);
+- struct f2fs_dir_entry *de;
+- struct page *page;
+- int err = 0;
+-
+- if (f2fs_readonly(sbi->sb)) {
+- f2fs_info(sbi, "skip recovering inline_dots inode (ino:%lu, pino:%u) in readonly mountpoint",
+- dir->i_ino, pino);
+- return 0;
+- }
+-
+- if (!S_ISDIR(dir->i_mode)) {
+- f2fs_err(sbi, "inconsistent inode status, skip recovering inline_dots inode (ino:%lu, i_mode:%u, pino:%u)",
+- dir->i_ino, dir->i_mode, pino);
+- set_sbi_flag(sbi, SBI_NEED_FSCK);
+- return -ENOTDIR;
+- }
+-
+- err = f2fs_dquot_initialize(dir);
+- if (err)
+- return err;
+-
+- f2fs_balance_fs(sbi, true);
+-
+- f2fs_lock_op(sbi);
+-
+- de = f2fs_find_entry(dir, &dot, &page);
+- if (de) {
+- f2fs_put_page(page, 0);
+- } else if (IS_ERR(page)) {
+- err = PTR_ERR(page);
+- goto out;
+- } else {
+- err = f2fs_do_add_link(dir, &dot, NULL, dir->i_ino, S_IFDIR);
+- if (err)
+- goto out;
+- }
+-
+- de = f2fs_find_entry(dir, &dotdot_name, &page);
+- if (de)
+- f2fs_put_page(page, 0);
+- else if (IS_ERR(page))
+- err = PTR_ERR(page);
+- else
+- err = f2fs_do_add_link(dir, &dotdot_name, NULL, pino, S_IFDIR);
+-out:
+- if (!err)
+- clear_inode_flag(dir, FI_INLINE_DOTS);
+-
+- f2fs_unlock_op(sbi);
+- return err;
+-}
+-
+ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
+ unsigned int flags)
+ {
+@@ -520,7 +464,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
+ struct dentry *new;
+ nid_t ino = -1;
+ int err = 0;
+- unsigned int root_ino = F2FS_ROOT_INO(F2FS_I_SB(dir));
+ struct f2fs_filename fname;
+
+ trace_f2fs_lookup_start(dir, dentry, flags);
+@@ -556,17 +499,6 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
+ goto out;
+ }
+
+- if ((dir->i_ino == root_ino) && f2fs_has_inline_dots(dir)) {
+- err = __recover_dot_dentries(dir, root_ino);
+- if (err)
+- goto out_iput;
+- }
+-
+- if (f2fs_has_inline_dots(inode)) {
+- err = __recover_dot_dentries(inode, dir->i_ino);
+- if (err)
+- goto out_iput;
+- }
+ if (IS_ENCRYPTED(dir) &&
+ (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+ !fscrypt_has_permitted_context(dir, inode)) {
+diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
+index 601825785226d2..425479d7692167 100644
+--- a/fs/f2fs/segment.c
++++ b/fs/f2fs/segment.c
+@@ -199,6 +199,10 @@ void f2fs_abort_atomic_write(struct inode *inode, bool clean)
+ clear_inode_flag(inode, FI_ATOMIC_COMMITTED);
+ clear_inode_flag(inode, FI_ATOMIC_REPLACE);
+ clear_inode_flag(inode, FI_ATOMIC_FILE);
++ if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
++ clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
++ f2fs_mark_inode_dirty_sync(inode, true);
++ }
+ stat_dec_atomic_inode(inode);
+
+ F2FS_I(inode)->atomic_write_task = NULL;
+@@ -366,6 +370,10 @@ static int __f2fs_commit_atomic_write(struct inode *inode)
+ } else {
+ sbi->committed_atomic_block += fi->atomic_write_cnt;
+ set_inode_flag(inode, FI_ATOMIC_COMMITTED);
++ if (is_inode_flag_set(inode, FI_ATOMIC_DIRTIED)) {
++ clear_inode_flag(inode, FI_ATOMIC_DIRTIED);
++ f2fs_mark_inode_dirty_sync(inode, true);
++ }
+ }
+
+ __complete_revoke_list(inode, &revoke_list, ret ? true : false);
+@@ -1282,6 +1290,13 @@ static int __submit_discard_cmd(struct f2fs_sb_info *sbi,
+ wait_list, issued);
+ return 0;
+ }
++
++ /*
++ * Issue discard for conventional zones only if the device
++ * supports discard.
++ */
++ if (!bdev_max_discard_sectors(bdev))
++ return -EOPNOTSUPP;
+ }
+ #endif
+
+diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
+index 1f1b3647a998c0..b4c8ac6c085989 100644
+--- a/fs/f2fs/super.c
++++ b/fs/f2fs/super.c
+@@ -2571,7 +2571,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
+
+ static void f2fs_shutdown(struct super_block *sb)
+ {
+- f2fs_do_shutdown(F2FS_SB(sb), F2FS_GOING_DOWN_NOSYNC, false);
++ f2fs_do_shutdown(F2FS_SB(sb), F2FS_GOING_DOWN_NOSYNC, false, false);
+ }
+
+ #ifdef CONFIG_QUOTA
+@@ -3366,9 +3366,9 @@ static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
+ u32 segment_count = le32_to_cpu(raw_super->segment_count);
+ u32 log_blocks_per_seg = le32_to_cpu(raw_super->log_blocks_per_seg);
+ u64 main_end_blkaddr = main_blkaddr +
+- (segment_count_main << log_blocks_per_seg);
++ ((u64)segment_count_main << log_blocks_per_seg);
+ u64 seg_end_blkaddr = segment0_blkaddr +
+- (segment_count << log_blocks_per_seg);
++ ((u64)segment_count << log_blocks_per_seg);
+
+ if (segment0_blkaddr != cp_blkaddr) {
+ f2fs_info(sbi, "Mismatch start address, segment0(%u) cp_blkaddr(%u)",
+@@ -4183,12 +4183,14 @@ void f2fs_handle_critical_error(struct f2fs_sb_info *sbi, unsigned char reason,
+ }
+
+ f2fs_warn(sbi, "Remounting filesystem read-only");
++
+ /*
+- * Make sure updated value of ->s_mount_flags will be visible before
+- * ->s_flags update
++ * We have already set CP_ERROR_FLAG flag to stop all updates
++ * to filesystem, so it doesn't need to set SB_RDONLY flag here
++ * because the flag should be set covered w/ sb->s_umount semaphore
++ * via remount procedure, otherwise, it will confuse code like
++ * freeze_super() which will lead to deadlocks and other problems.
+ */
+- smp_wmb();
+- sb->s_flags |= SB_RDONLY;
+ }
+
+ static void f2fs_record_error_work(struct work_struct *work)
+diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
+index f290fe9327c498..3f387494367963 100644
+--- a/fs/f2fs/xattr.c
++++ b/fs/f2fs/xattr.c
+@@ -629,6 +629,7 @@ static int __f2fs_setxattr(struct inode *inode, int index,
+ const char *name, const void *value, size_t size,
+ struct page *ipage, int flags)
+ {
++ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct f2fs_xattr_entry *here, *last;
+ void *base_addr, *last_base_addr;
+ int found, newsize;
+@@ -772,9 +773,18 @@ static int __f2fs_setxattr(struct inode *inode, int index,
+ if (index == F2FS_XATTR_INDEX_ENCRYPTION &&
+ !strcmp(name, F2FS_XATTR_NAME_ENCRYPTION_CONTEXT))
+ f2fs_set_encrypted_inode(inode);
+- if (S_ISDIR(inode->i_mode))
+- set_sbi_flag(F2FS_I_SB(inode), SBI_NEED_CP);
+
++ if (!S_ISDIR(inode->i_mode))
++ goto same;
++ /*
++ * In restrict mode, fsync() always try to trigger checkpoint for all
++ * metadata consistency, in other mode, it triggers checkpoint when
++ * parent's xattr metadata was updated.
++ */
++ if (F2FS_OPTION(sbi).fsync_mode == FSYNC_MODE_STRICT)
++ set_sbi_flag(sbi, SBI_NEED_CP);
++ else
++ f2fs_add_ino_entry(sbi, inode->i_ino, XATTR_DIR_INO);
+ same:
+ if (is_inode_flag_set(inode, FI_ACL_MODE)) {
+ inode->i_mode = F2FS_I(inode)->i_acl_mode;
+diff --git a/fs/fcntl.c b/fs/fcntl.c
+index 300e5d9ad913b5..c28dc6c005f174 100644
+--- a/fs/fcntl.c
++++ b/fs/fcntl.c
+@@ -87,8 +87,8 @@ static int setfl(int fd, struct file * filp, unsigned int arg)
+ return error;
+ }
+
+-static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
+- int force)
++void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
++ int force)
+ {
+ write_lock_irq(&filp->f_owner.lock);
+ if (force || !filp->f_owner.pid) {
+@@ -98,19 +98,13 @@ static void f_modown(struct file *filp, struct pid *pid, enum pid_type type,
+
+ if (pid) {
+ const struct cred *cred = current_cred();
++ security_file_set_fowner(filp);
+ filp->f_owner.uid = cred->uid;
+ filp->f_owner.euid = cred->euid;
+ }
+ }
+ write_unlock_irq(&filp->f_owner.lock);
+ }
+-
+-void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
+- int force)
+-{
+- security_file_set_fowner(filp);
+- f_modown(filp, pid, type, force);
+-}
+ EXPORT_SYMBOL(__f_setown);
+
+ int f_setown(struct file *filp, int who, int force)
+@@ -146,7 +140,7 @@ EXPORT_SYMBOL(f_setown);
+
+ void f_delown(struct file *filp)
+ {
+- f_modown(filp, NULL, PIDTYPE_TGID, 1);
++ __f_setown(filp, NULL, PIDTYPE_TGID, 1);
+ }
+
+ pid_t f_getown(struct file *filp)
+diff --git a/fs/fs_parser.c b/fs/fs_parser.c
+index a4d6ca0b8971e6..24727ec34e5aa4 100644
+--- a/fs/fs_parser.c
++++ b/fs/fs_parser.c
+@@ -308,6 +308,40 @@ int fs_param_is_fd(struct p_log *log, const struct fs_parameter_spec *p,
+ }
+ EXPORT_SYMBOL(fs_param_is_fd);
+
++int fs_param_is_uid(struct p_log *log, const struct fs_parameter_spec *p,
++ struct fs_parameter *param, struct fs_parse_result *result)
++{
++ kuid_t uid;
++
++ if (fs_param_is_u32(log, p, param, result) != 0)
++ return fs_param_bad_value(log, param);
++
++ uid = make_kuid(current_user_ns(), result->uint_32);
++ if (!uid_valid(uid))
++ return inval_plog(log, "Invalid uid '%s'", param->string);
++
++ result->uid = uid;
++ return 0;
++}
++EXPORT_SYMBOL(fs_param_is_uid);
++
++int fs_param_is_gid(struct p_log *log, const struct fs_parameter_spec *p,
++ struct fs_parameter *param, struct fs_parse_result *result)
++{
++ kgid_t gid;
++
++ if (fs_param_is_u32(log, p, param, result) != 0)
++ return fs_param_bad_value(log, param);
++
++ gid = make_kgid(current_user_ns(), result->uint_32);
++ if (!gid_valid(gid))
++ return inval_plog(log, "Invalid gid '%s'", param->string);
++
++ result->gid = gid;
++ return 0;
++}
++EXPORT_SYMBOL(fs_param_is_gid);
++
+ int fs_param_is_blockdev(struct p_log *log, const struct fs_parameter_spec *p,
+ struct fs_parameter *param, struct fs_parse_result *result)
+ {
+diff --git a/fs/fuse/file.c b/fs/fuse/file.c
+index ed76121f73f2e0..08f7d538ca98f4 100644
+--- a/fs/fuse/file.c
++++ b/fs/fuse/file.c
+@@ -1345,7 +1345,7 @@ static bool fuse_dio_wr_exclusive_lock(struct kiocb *iocb, struct iov_iter *from
+
+ /* shared locks are not allowed with parallel page cache IO */
+ if (test_bit(FUSE_I_CACHE_IO_MODE, &fi->state))
+- return false;
++ return true;
+
+ /* Parallel dio beyond EOF is not supported, at least for now. */
+ if (fuse_io_past_eof(iocb, from))
+diff --git a/fs/inode.c b/fs/inode.c
+index f5add7222c98ec..3df67672986aa9 100644
+--- a/fs/inode.c
++++ b/fs/inode.c
+@@ -758,6 +758,10 @@ void evict_inodes(struct super_block *sb)
+ continue;
+
+ spin_lock(&inode->i_lock);
++ if (atomic_read(&inode->i_count)) {
++ spin_unlock(&inode->i_lock);
++ continue;
++ }
+ if (inode->i_state & (I_NEW | I_FREEING | I_WILL_FREE)) {
+ spin_unlock(&inode->i_lock);
+ continue;
+diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
+index 5713994328cbcb..0625d1c0d0649a 100644
+--- a/fs/jfs/jfs_dmap.c
++++ b/fs/jfs/jfs_dmap.c
+@@ -187,7 +187,7 @@ int dbMount(struct inode *ipbmap)
+ }
+
+ bmp->db_numag = le32_to_cpu(dbmp_le->dn_numag);
+- if (!bmp->db_numag) {
++ if (!bmp->db_numag || bmp->db_numag >= MAXAG) {
+ err = -EINVAL;
+ goto err_release_metapage;
+ }
+@@ -652,7 +652,7 @@ int dbNextAG(struct inode *ipbmap)
+ * average free space.
+ */
+ for (i = 0 ; i < bmp->db_numag; i++, agpref++) {
+- if (agpref == bmp->db_numag)
++ if (agpref >= bmp->db_numag)
+ agpref = 0;
+
+ if (atomic_read(&bmp->db_active[agpref]))
+diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
+index 1407feccbc2d05..a360b24ed320c0 100644
+--- a/fs/jfs/jfs_imap.c
++++ b/fs/jfs/jfs_imap.c
+@@ -1360,7 +1360,7 @@ int diAlloc(struct inode *pip, bool dir, struct inode *ip)
+ /* get the ag number of this iag */
+ agno = BLKTOAG(JFS_IP(pip)->agstart, JFS_SBI(pip->i_sb));
+ dn_numag = JFS_SBI(pip->i_sb)->bmap->db_numag;
+- if (agno < 0 || agno > dn_numag)
++ if (agno < 0 || agno > dn_numag || agno >= MAXAG)
+ return -EIO;
+
+ if (atomic_read(&JFS_SBI(pip->i_sb)->bmap->db_active[agno])) {
+diff --git a/fs/namespace.c b/fs/namespace.c
+index e1ced589d8357f..a6675c2a238394 100644
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -2801,8 +2801,15 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *
+ if (!__mnt_is_readonly(mnt) &&
+ (!(sb->s_iflags & SB_I_TS_EXPIRY_WARNED)) &&
+ (ktime_get_real_seconds() + TIME_UPTIME_SEC_MAX > sb->s_time_max)) {
+- char *buf = (char *)__get_free_page(GFP_KERNEL);
+- char *mntpath = buf ? d_path(mountpoint, buf, PAGE_SIZE) : ERR_PTR(-ENOMEM);
++ char *buf, *mntpath;
++
++ buf = (char *)__get_free_page(GFP_KERNEL);
++ if (buf)
++ mntpath = d_path(mountpoint, buf, PAGE_SIZE);
++ else
++ mntpath = ERR_PTR(-ENOMEM);
++ if (IS_ERR(mntpath))
++ mntpath = "(unknown)";
+
+ pr_warn("%s filesystem being %s at %s supports timestamps until %ptTd (0x%llx)\n",
+ sb->s_type->name,
+@@ -2810,8 +2817,9 @@ static void mnt_warn_timestamp_expiry(struct path *mountpoint, struct vfsmount *
+ mntpath, &sb->s_time_max,
+ (unsigned long long)sb->s_time_max);
+
+- free_page((unsigned long)buf);
+ sb->s_iflags |= SB_I_TS_EXPIRY_WARNED;
++ if (buf)
++ free_page((unsigned long)buf);
+ }
+ }
+
+diff --git a/fs/netfs/main.c b/fs/netfs/main.c
+index db824c372842ad..b1d97335d7bb83 100644
+--- a/fs/netfs/main.c
++++ b/fs/netfs/main.c
+@@ -138,7 +138,7 @@ static int __init netfs_init(void)
+
+ error_fscache:
+ error_procfile:
+- remove_proc_entry("fs/netfs", NULL);
++ remove_proc_subtree("fs/netfs", NULL);
+ error_proc:
+ mempool_exit(&netfs_subrequest_pool);
+ error_subreqpool:
+@@ -155,7 +155,7 @@ fs_initcall(netfs_init);
+ static void __exit netfs_exit(void)
+ {
+ fscache_exit();
+- remove_proc_entry("fs/netfs", NULL);
++ remove_proc_subtree("fs/netfs", NULL);
+ mempool_exit(&netfs_subrequest_pool);
+ kmem_cache_destroy(netfs_subrequest_slab);
+ mempool_exit(&netfs_request_pool);
+diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
+index 5b452411e8fdf2..1153e166652bed 100644
+--- a/fs/nfs/nfs4state.c
++++ b/fs/nfs/nfs4state.c
+@@ -1956,6 +1956,7 @@ static int nfs4_do_reclaim(struct nfs_client *clp, const struct nfs4_state_recov
+ set_bit(ops->owner_flag_bit, &sp->so_flags);
+ nfs4_put_state_owner(sp);
+ status = nfs4_recovery_handle_error(clp, status);
++ nfs4_free_state_owners(&freeme);
+ return (status != 0) ? status : -EAGAIN;
+ }
+
+diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
+index f4704f5d408675..e2e248032bfd04 100644
+--- a/fs/nfsd/filecache.c
++++ b/fs/nfsd/filecache.c
+@@ -1035,8 +1035,6 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ if (likely(ret == 0))
+ goto open_file;
+
+- if (ret == -EEXIST)
+- goto retry;
+ trace_nfsd_file_insert_err(rqstp, inode, may_flags, ret);
+ status = nfserr_jukebox;
+ goto construction_err;
+@@ -1051,6 +1049,7 @@ nfsd_file_do_acquire(struct svc_rqst *rqstp, struct svc_fh *fhp,
+ status = nfserr_jukebox;
+ goto construction_err;
+ }
++ nfsd_file_put(nf);
+ open_retry = false;
+ fh_put(fhp);
+ goto retry;
+diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
+index 7a806ac13e317e..8cca1329f3485c 100644
+--- a/fs/nfsd/nfs4idmap.c
++++ b/fs/nfsd/nfs4idmap.c
+@@ -581,6 +581,7 @@ static __be32 idmap_id_to_name(struct xdr_stream *xdr,
+ .id = id,
+ .type = type,
+ };
++ __be32 status = nfs_ok;
+ __be32 *p;
+ int ret;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+@@ -593,12 +594,16 @@ static __be32 idmap_id_to_name(struct xdr_stream *xdr,
+ return nfserrno(ret);
+ ret = strlen(item->name);
+ WARN_ON_ONCE(ret > IDMAP_NAMESZ);
++
+ p = xdr_reserve_space(xdr, ret + 4);
+- if (!p)
+- return nfserr_resource;
+- p = xdr_encode_opaque(p, item->name, ret);
++ if (unlikely(!p)) {
++ status = nfserr_resource;
++ goto out_put;
++ }
++ xdr_encode_opaque(p, item->name, ret);
++out_put:
+ cache_put(&item->h, nn->idtoname_cache);
+- return 0;
++ return status;
+ }
+
+ static bool
+diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
+index 67d8673a9391c7..69a3a84e159e62 100644
+--- a/fs/nfsd/nfs4recover.c
++++ b/fs/nfsd/nfs4recover.c
+@@ -809,6 +809,10 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
+ ci = &cmsg->cm_u.cm_clntinfo;
+ if (get_user(namelen, &ci->cc_name.cn_len))
+ return -EFAULT;
++ if (!namelen) {
++ dprintk("%s: namelen should not be zero", __func__);
++ return -EINVAL;
++ }
+ name.data = memdup_user(&ci->cc_name.cn_id, namelen);
+ if (IS_ERR(name.data))
+ return PTR_ERR(name.data);
+@@ -831,6 +835,10 @@ __cld_pipe_inprogress_downcall(const struct cld_msg_v2 __user *cmsg,
+ cnm = &cmsg->cm_u.cm_name;
+ if (get_user(namelen, &cnm->cn_len))
+ return -EFAULT;
++ if (!namelen) {
++ dprintk("%s: namelen should not be zero", __func__);
++ return -EINVAL;
++ }
+ name.data = memdup_user(&cnm->cn_id, namelen);
+ if (IS_ERR(name.data))
+ return PTR_ERR(name.data);
+diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
+index a366fb1c1b9b4f..fe06779ea527a1 100644
+--- a/fs/nfsd/nfs4state.c
++++ b/fs/nfsd/nfs4state.c
+@@ -5912,6 +5912,28 @@ static void nfsd4_open_deleg_none_ext(struct nfsd4_open *open, int status)
+ }
+ }
+
++static bool
++nfs4_delegation_stat(struct nfs4_delegation *dp, struct svc_fh *currentfh,
++ struct kstat *stat)
++{
++ struct nfsd_file *nf = find_rw_file(dp->dl_stid.sc_file);
++ struct path path;
++ int rc;
++
++ if (!nf)
++ return false;
++
++ path.mnt = currentfh->fh_export->ex_path.mnt;
++ path.dentry = file_dentry(nf->nf_file);
++
++ rc = vfs_getattr(&path, stat,
++ (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
++ AT_STATX_SYNC_AS_STAT);
++
++ nfsd_file_put(nf);
++ return rc == 0;
++}
++
+ /*
+ * The Linux NFS server does not offer write delegations to NFSv4.0
+ * clients in order to avoid conflicts between write delegations and
+@@ -5947,7 +5969,6 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
+ int cb_up;
+ int status = 0;
+ struct kstat stat;
+- struct path path;
+
+ cb_up = nfsd4_cb_channel_good(oo->oo_owner.so_client);
+ open->op_recall = false;
+@@ -5983,20 +6004,16 @@ nfs4_open_delegation(struct nfsd4_open *open, struct nfs4_ol_stateid *stp,
+ memcpy(&open->op_delegate_stateid, &dp->dl_stid.sc_stateid, sizeof(dp->dl_stid.sc_stateid));
+
+ if (open->op_share_access & NFS4_SHARE_ACCESS_WRITE) {
+- open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
+- trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
+- path.mnt = currentfh->fh_export->ex_path.mnt;
+- path.dentry = currentfh->fh_dentry;
+- if (vfs_getattr(&path, &stat,
+- (STATX_SIZE | STATX_CTIME | STATX_CHANGE_COOKIE),
+- AT_STATX_SYNC_AS_STAT)) {
++ if (!nfs4_delegation_stat(dp, currentfh, &stat)) {
+ nfs4_put_stid(&dp->dl_stid);
+ destroy_delegation(dp);
+ goto out_no_deleg;
+ }
++ open->op_delegate_type = NFS4_OPEN_DELEGATE_WRITE;
+ dp->dl_cb_fattr.ncf_cur_fsize = stat.size;
+ dp->dl_cb_fattr.ncf_initial_cinfo =
+ nfsd4_change_attribute(&stat, d_inode(currentfh->fh_dentry));
++ trace_nfsd_deleg_write(&dp->dl_stid.sc_stateid);
+ } else {
+ open->op_delegate_type = NFS4_OPEN_DELEGATE_READ;
+ trace_nfsd_deleg_read(&dp->dl_stid.sc_stateid);
+@@ -8836,6 +8853,7 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
+ __be32 status;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct file_lock_context *ctx;
++ struct nfs4_delegation *dp = NULL;
+ struct file_lease *fl;
+ struct iattr attrs;
+ struct nfs4_cb_fattr *ncf;
+@@ -8845,84 +8863,76 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
+ ctx = locks_inode_context(inode);
+ if (!ctx)
+ return 0;
++
++#define NON_NFSD_LEASE ((void *)1)
++
+ spin_lock(&ctx->flc_lock);
+ for_each_file_lock(fl, &ctx->flc_lease) {
+- unsigned char type = fl->c.flc_type;
+-
+ if (fl->c.flc_flags == FL_LAYOUT)
+ continue;
+- if (fl->fl_lmops != &nfsd_lease_mng_ops) {
+- /*
+- * non-nfs lease, if it's a lease with F_RDLCK then
+- * we are done; there isn't any write delegation
+- * on this inode
+- */
+- if (type == F_RDLCK)
+- break;
+-
+- nfsd_stats_wdeleg_getattr_inc(nn);
+- spin_unlock(&ctx->flc_lock);
+-
+- status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
++ if (fl->c.flc_type == F_WRLCK) {
++ if (fl->fl_lmops == &nfsd_lease_mng_ops)
++ dp = fl->c.flc_owner;
++ else
++ dp = NON_NFSD_LEASE;
++ }
++ break;
++ }
++ if (dp == NULL || dp == NON_NFSD_LEASE ||
++ dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) {
++ spin_unlock(&ctx->flc_lock);
++ if (dp == NON_NFSD_LEASE) {
++ status = nfserrno(nfsd_open_break_lease(inode,
++ NFSD_MAY_READ));
+ if (status != nfserr_jukebox ||
+ !nfsd_wait_for_delegreturn(rqstp, inode))
+ return status;
+- return 0;
+ }
+- if (type == F_WRLCK) {
+- struct nfs4_delegation *dp = fl->c.flc_owner;
++ return 0;
++ }
+
+- if (dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) {
+- spin_unlock(&ctx->flc_lock);
+- return 0;
+- }
+- nfsd_stats_wdeleg_getattr_inc(nn);
+- dp = fl->c.flc_owner;
+- refcount_inc(&dp->dl_stid.sc_count);
+- ncf = &dp->dl_cb_fattr;
+- nfs4_cb_getattr(&dp->dl_cb_fattr);
+- spin_unlock(&ctx->flc_lock);
+- wait_on_bit_timeout(&ncf->ncf_cb_flags, CB_GETATTR_BUSY,
+- TASK_INTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT);
+- if (ncf->ncf_cb_status) {
+- /* Recall delegation only if client didn't respond */
+- status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
+- if (status != nfserr_jukebox ||
+- !nfsd_wait_for_delegreturn(rqstp, inode)) {
+- nfs4_put_stid(&dp->dl_stid);
+- return status;
+- }
+- }
+- if (!ncf->ncf_file_modified &&
+- (ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
+- ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
+- ncf->ncf_file_modified = true;
+- if (ncf->ncf_file_modified) {
+- int err;
+-
+- /*
+- * Per section 10.4.3 of RFC 8881, the server would
+- * not update the file's metadata with the client's
+- * modified size
+- */
+- attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
+- attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG;
+- inode_lock(inode);
+- err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL);
+- inode_unlock(inode);
+- if (err) {
+- nfs4_put_stid(&dp->dl_stid);
+- return nfserrno(err);
+- }
+- ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
+- *size = ncf->ncf_cur_fsize;
+- *modified = true;
+- }
+- nfs4_put_stid(&dp->dl_stid);
+- return 0;
++ nfsd_stats_wdeleg_getattr_inc(nn);
++ refcount_inc(&dp->dl_stid.sc_count);
++ ncf = &dp->dl_cb_fattr;
++ nfs4_cb_getattr(&dp->dl_cb_fattr);
++ spin_unlock(&ctx->flc_lock);
++
++ wait_on_bit_timeout(&ncf->ncf_cb_flags, CB_GETATTR_BUSY,
++ TASK_INTERRUPTIBLE, NFSD_CB_GETATTR_TIMEOUT);
++ if (ncf->ncf_cb_status) {
++ /* Recall delegation only if client didn't respond */
++ status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
++ if (status != nfserr_jukebox ||
++ !nfsd_wait_for_delegreturn(rqstp, inode))
++ goto out_status;
++ }
++ if (!ncf->ncf_file_modified &&
++ (ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
++ ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
++ ncf->ncf_file_modified = true;
++ if (ncf->ncf_file_modified) {
++ int err;
++
++ /*
++ * Per section 10.4.3 of RFC 8881, the server would
++ * not update the file's metadata with the client's
++ * modified size
++ */
++ attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
++ attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG;
++ inode_lock(inode);
++ err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL);
++ inode_unlock(inode);
++ if (err) {
++ status = nfserrno(err);
++ goto out_status;
+ }
+- break;
++ ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
++ *size = ncf->ncf_cur_fsize;
++ *modified = true;
+ }
+- spin_unlock(&ctx->flc_lock);
+- return 0;
++ status = 0;
++out_status:
++ nfs4_put_stid(&dp->dl_stid);
++ return status;
+ }
+diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
+index 862bdf23120e8a..ef5061bb56da1e 100644
+--- a/fs/nilfs2/btree.c
++++ b/fs/nilfs2/btree.c
+@@ -350,7 +350,7 @@ static int nilfs_btree_node_broken(const struct nilfs_btree_node *node,
+ if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN ||
+ level >= NILFS_BTREE_LEVEL_MAX ||
+ (flags & NILFS_BTREE_NODE_ROOT) ||
+- nchildren < 0 ||
++ nchildren <= 0 ||
+ nchildren > NILFS_BTREE_NODE_NCHILDREN_MAX(size))) {
+ nilfs_crit(inode->i_sb,
+ "bad btree node (ino=%lu, blocknr=%llu): level = %d, flags = 0x%x, nchildren = %d",
+@@ -381,7 +381,8 @@ static int nilfs_btree_root_broken(const struct nilfs_btree_node *node,
+ if (unlikely(level < NILFS_BTREE_LEVEL_NODE_MIN ||
+ level >= NILFS_BTREE_LEVEL_MAX ||
+ nchildren < 0 ||
+- nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX)) {
++ nchildren > NILFS_BTREE_ROOT_NCHILDREN_MAX ||
++ (nchildren == 0 && level > NILFS_BTREE_LEVEL_NODE_MIN))) {
+ nilfs_crit(inode->i_sb,
+ "bad btree root (ino=%lu): level = %d, flags = 0x%x, nchildren = %d",
+ inode->i_ino, level, flags, nchildren);
+@@ -1658,13 +1659,16 @@ static int nilfs_btree_check_delete(struct nilfs_bmap *btree, __u64 key)
+ int nchildren, ret;
+
+ root = nilfs_btree_get_root(btree);
++ nchildren = nilfs_btree_node_get_nchildren(root);
++ if (unlikely(nchildren == 0))
++ return 0;
++
+ switch (nilfs_btree_height(btree)) {
+ case 2:
+ bh = NULL;
+ node = root;
+ break;
+ case 3:
+- nchildren = nilfs_btree_node_get_nchildren(root);
+ if (nchildren > 1)
+ return 0;
+ ptr = nilfs_btree_node_get_ptr(root, nchildren - 1,
+@@ -1673,12 +1677,12 @@ static int nilfs_btree_check_delete(struct nilfs_bmap *btree, __u64 key)
+ if (ret < 0)
+ return ret;
+ node = (struct nilfs_btree_node *)bh->b_data;
++ nchildren = nilfs_btree_node_get_nchildren(node);
+ break;
+ default:
+ return 0;
+ }
+
+- nchildren = nilfs_btree_node_get_nchildren(node);
+ maxkey = nilfs_btree_node_get_key(node, nchildren - 1);
+ nextmaxkey = (nchildren > 1) ?
+ nilfs_btree_node_get_key(node, nchildren - 2) : 0;
+diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
+index 627eb2f72ef376..23fcf9e9d6c555 100644
+--- a/fs/quota/dquot.c
++++ b/fs/quota/dquot.c
+@@ -2408,7 +2408,7 @@ static int vfs_setup_quota_inode(struct inode *inode, int type)
+ int dquot_load_quota_sb(struct super_block *sb, int type, int format_id,
+ unsigned int flags)
+ {
+- struct quota_format_type *fmt = find_quota_format(format_id);
++ struct quota_format_type *fmt;
+ struct quota_info *dqopt = sb_dqopt(sb);
+ int error;
+
+@@ -2418,6 +2418,7 @@ int dquot_load_quota_sb(struct super_block *sb, int type, int format_id,
+ if (WARN_ON_ONCE(flags & DQUOT_SUSPENDED))
+ return -EINVAL;
+
++ fmt = find_quota_format(format_id);
+ if (!fmt)
+ return -ESRCH;
+ if (!sb->dq_op || !sb->s_qcop ||
+diff --git a/fs/smb/server/vfs.c b/fs/smb/server/vfs.c
+index 9e859ba010cf12..7cbd580120d129 100644
+--- a/fs/smb/server/vfs.c
++++ b/fs/smb/server/vfs.c
+@@ -496,7 +496,7 @@ int ksmbd_vfs_write(struct ksmbd_work *work, struct ksmbd_file *fp,
+ int err = 0;
+
+ if (work->conn->connection_type) {
+- if (!(fp->daccess & FILE_WRITE_DATA_LE)) {
++ if (!(fp->daccess & (FILE_WRITE_DATA_LE | FILE_APPEND_DATA_LE))) {
+ pr_err("no right to write(%pD)\n", fp->filp);
+ err = -EACCES;
+ goto out;
+@@ -1115,9 +1115,10 @@ static bool __dir_empty(struct dir_context *ctx, const char *name, int namlen,
+ struct ksmbd_readdir_data *buf;
+
+ buf = container_of(ctx, struct ksmbd_readdir_data, ctx);
+- buf->dirent_count++;
++ if (!is_dot_dotdot(name, namlen))
++ buf->dirent_count++;
+
+- return buf->dirent_count <= 2;
++ return !buf->dirent_count;
+ }
+
+ /**
+@@ -1137,7 +1138,7 @@ int ksmbd_vfs_empty_dir(struct ksmbd_file *fp)
+ readdir_data.dirent_count = 0;
+
+ err = iterate_dir(fp->filp, &readdir_data.ctx);
+- if (readdir_data.dirent_count > 2)
++ if (readdir_data.dirent_count)
+ err = -ENOTEMPTY;
+ else
+ err = 0;
+@@ -1166,7 +1167,7 @@ static bool __caseless_lookup(struct dir_context *ctx, const char *name,
+ if (cmp < 0)
+ cmp = strncasecmp((char *)buf->private, name, namlen);
+ if (!cmp) {
+- memcpy((char *)buf->private, name, namlen);
++ memcpy((char *)buf->private, name, buf->used);
+ buf->dirent_count = 1;
+ return false;
+ }
+@@ -1234,10 +1235,7 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name,
+ char *filepath;
+ size_t path_len, remain_len;
+
+- filepath = kstrdup(name, GFP_KERNEL);
+- if (!filepath)
+- return -ENOMEM;
+-
++ filepath = name;
+ path_len = strlen(filepath);
+ remain_len = path_len;
+
+@@ -1280,10 +1278,9 @@ int ksmbd_vfs_kern_path_locked(struct ksmbd_work *work, char *name,
+ err = -EINVAL;
+ out2:
+ path_put(parent_path);
+-out1:
+- kfree(filepath);
+ }
+
++out1:
+ if (!err) {
+ err = mnt_want_write(parent_path->mnt);
+ if (err) {
+diff --git a/include/acpi/acoutput.h b/include/acpi/acoutput.h
+index b1571dd96310af..5e0346142f983d 100644
+--- a/include/acpi/acoutput.h
++++ b/include/acpi/acoutput.h
+@@ -193,6 +193,7 @@
+ */
+ #ifndef ACPI_NO_ERROR_MESSAGES
+ #define AE_INFO _acpi_module_name, __LINE__
++#define ACPI_ONCE(_fn, _plist) { static char _done; if (!_done) { _done = 1; _fn _plist; } }
+
+ /*
+ * Error reporting. Callers module and line number are inserted by AE_INFO,
+@@ -201,8 +202,10 @@
+ */
+ #define ACPI_INFO(plist) acpi_info plist
+ #define ACPI_WARNING(plist) acpi_warning plist
++#define ACPI_WARNING_ONCE(plist) ACPI_ONCE(acpi_warning, plist)
+ #define ACPI_EXCEPTION(plist) acpi_exception plist
+ #define ACPI_ERROR(plist) acpi_error plist
++#define ACPI_ERROR_ONCE(plist) ACPI_ONCE(acpi_error, plist)
+ #define ACPI_BIOS_WARNING(plist) acpi_bios_warning plist
+ #define ACPI_BIOS_EXCEPTION(plist) acpi_bios_exception plist
+ #define ACPI_BIOS_ERROR(plist) acpi_bios_error plist
+@@ -214,8 +217,10 @@
+
+ #define ACPI_INFO(plist)
+ #define ACPI_WARNING(plist)
++#define ACPI_WARNING_ONCE(plist)
+ #define ACPI_EXCEPTION(plist)
+ #define ACPI_ERROR(plist)
++#define ACPI_ERROR_ONCE(plist)
+ #define ACPI_BIOS_WARNING(plist)
+ #define ACPI_BIOS_EXCEPTION(plist)
+ #define ACPI_BIOS_ERROR(plist)
+diff --git a/include/acpi/cppc_acpi.h b/include/acpi/cppc_acpi.h
+index 930b6afba6f4d4..e1720d93066695 100644
+--- a/include/acpi/cppc_acpi.h
++++ b/include/acpi/cppc_acpi.h
+@@ -64,6 +64,8 @@ struct cpc_desc {
+ int cpu_id;
+ int write_cmd_status;
+ int write_cmd_id;
++ /* Lock used for RMW operations in cpc_write() */
++ spinlock_t rmw_lock;
+ struct cpc_register_resource cpc_regs[MAX_CPC_REG_ENT];
+ struct acpi_psd_package domain_info;
+ struct kobject kobj;
+diff --git a/include/linux/bpf.h b/include/linux/bpf.h
+index 5e694a308081aa..5e880f0b566203 100644
+--- a/include/linux/bpf.h
++++ b/include/linux/bpf.h
+@@ -694,6 +694,11 @@ enum bpf_type_flag {
+ /* DYNPTR points to xdp_buff */
+ DYNPTR_TYPE_XDP = BIT(16 + BPF_BASE_TYPE_BITS),
+
++ /* Memory must be aligned on some architectures, used in combination with
++ * MEM_FIXED_SIZE.
++ */
++ MEM_ALIGNED = BIT(17 + BPF_BASE_TYPE_BITS),
++
+ __BPF_TYPE_FLAG_MAX,
+ __BPF_TYPE_LAST_FLAG = __BPF_TYPE_FLAG_MAX - 1,
+ };
+@@ -731,8 +736,6 @@ enum bpf_arg_type {
+ ARG_ANYTHING, /* any (initialized) argument is ok */
+ ARG_PTR_TO_SPIN_LOCK, /* pointer to bpf_spin_lock */
+ ARG_PTR_TO_SOCK_COMMON, /* pointer to sock_common */
+- ARG_PTR_TO_INT, /* pointer to int */
+- ARG_PTR_TO_LONG, /* pointer to long */
+ ARG_PTR_TO_SOCKET, /* pointer to bpf_sock (fullsock) */
+ ARG_PTR_TO_BTF_ID, /* pointer to in-kernel struct */
+ ARG_PTR_TO_RINGBUF_MEM, /* pointer to dynamically reserved ringbuf memory */
+@@ -919,6 +922,7 @@ static_assert(__BPF_REG_TYPE_MAX <= BPF_BASE_TYPE_LIMIT);
+ */
+ struct bpf_insn_access_aux {
+ enum bpf_reg_type reg_type;
++ bool is_ldsx;
+ union {
+ int ctx_field_size;
+ struct {
+@@ -927,6 +931,7 @@ struct bpf_insn_access_aux {
+ };
+ };
+ struct bpf_verifier_log *log; /* for verbose logs */
++ bool is_retval; /* is accessing function return value ? */
+ };
+
+ static inline void
+diff --git a/include/linux/bpf_lsm.h b/include/linux/bpf_lsm.h
+index 1de7ece5d36d43..aefcd656425126 100644
+--- a/include/linux/bpf_lsm.h
++++ b/include/linux/bpf_lsm.h
+@@ -9,6 +9,7 @@
+
+ #include <linux/sched.h>
+ #include <linux/bpf.h>
++#include <linux/bpf_verifier.h>
+ #include <linux/lsm_hooks.h>
+
+ #ifdef CONFIG_BPF_LSM
+@@ -45,6 +46,8 @@ void bpf_inode_storage_free(struct inode *inode);
+
+ void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog, bpf_func_t *bpf_func);
+
++int bpf_lsm_get_retval_range(const struct bpf_prog *prog,
++ struct bpf_retval_range *range);
+ #else /* !CONFIG_BPF_LSM */
+
+ static inline bool bpf_lsm_is_sleepable_hook(u32 btf_id)
+@@ -78,6 +81,11 @@ static inline void bpf_lsm_find_cgroup_shim(const struct bpf_prog *prog,
+ {
+ }
+
++static inline int bpf_lsm_get_retval_range(const struct bpf_prog *prog,
++ struct bpf_retval_range *range)
++{
++ return -EOPNOTSUPP;
++}
+ #endif /* CONFIG_BPF_LSM */
+
+ #endif /* _LINUX_BPF_LSM_H */
+diff --git a/include/linux/compiler.h b/include/linux/compiler.h
+index 8c252e073bd810..7325f88736b1cd 100644
+--- a/include/linux/compiler.h
++++ b/include/linux/compiler.h
+@@ -133,7 +133,7 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val,
+ #define annotate_unreachable() __annotate_unreachable(__COUNTER__)
+
+ /* Annotate a C jump table to allow objtool to follow the code flow */
+-#define __annotate_jump_table __section(".rodata..c_jump_table")
++#define __annotate_jump_table __section(".rodata..c_jump_table,\"a\",@progbits #")
+
+ #else /* !CONFIG_OBJTOOL */
+ #define annotate_reachable()
+diff --git a/include/linux/f2fs_fs.h b/include/linux/f2fs_fs.h
+index 41d1d71c36ff5d..eee8577bcc543c 100644
+--- a/include/linux/f2fs_fs.h
++++ b/include/linux/f2fs_fs.h
+@@ -279,7 +279,7 @@ struct node_footer {
+ #define F2FS_INLINE_DATA 0x02 /* file inline data flag */
+ #define F2FS_INLINE_DENTRY 0x04 /* file inline dentry flag */
+ #define F2FS_DATA_EXIST 0x08 /* file inline data exist flag */
+-#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries */
++#define F2FS_INLINE_DOTS 0x10 /* file having implicit dot dentries (obsolete) */
+ #define F2FS_EXTRA_ATTR 0x20 /* file having extra attribute */
+ #define F2FS_PIN_FILE 0x40 /* file should not be gced */
+ #define F2FS_COMPRESS_RELEASED 0x80 /* file released compressed blocks */
+diff --git a/include/linux/fs_parser.h b/include/linux/fs_parser.h
+index d3350979115f0a..6cf713a7e6c6fc 100644
+--- a/include/linux/fs_parser.h
++++ b/include/linux/fs_parser.h
+@@ -28,7 +28,7 @@ typedef int fs_param_type(struct p_log *,
+ */
+ fs_param_type fs_param_is_bool, fs_param_is_u32, fs_param_is_s32, fs_param_is_u64,
+ fs_param_is_enum, fs_param_is_string, fs_param_is_blob, fs_param_is_blockdev,
+- fs_param_is_path, fs_param_is_fd;
++ fs_param_is_path, fs_param_is_fd, fs_param_is_uid, fs_param_is_gid;
+
+ /*
+ * Specification of the type of value a parameter wants.
+@@ -57,6 +57,8 @@ struct fs_parse_result {
+ int int_32; /* For spec_s32/spec_enum */
+ unsigned int uint_32; /* For spec_u32{,_octal,_hex}/spec_enum */
+ u64 uint_64; /* For spec_u64 */
++ kuid_t uid;
++ kgid_t gid;
+ };
+ };
+
+@@ -131,6 +133,8 @@ static inline bool fs_validate_description(const char *name,
+ #define fsparam_bdev(NAME, OPT) __fsparam(fs_param_is_blockdev, NAME, OPT, 0, NULL)
+ #define fsparam_path(NAME, OPT) __fsparam(fs_param_is_path, NAME, OPT, 0, NULL)
+ #define fsparam_fd(NAME, OPT) __fsparam(fs_param_is_fd, NAME, OPT, 0, NULL)
++#define fsparam_uid(NAME, OPT) __fsparam(fs_param_is_uid, NAME, OPT, 0, NULL)
++#define fsparam_gid(NAME, OPT) __fsparam(fs_param_is_gid, NAME, OPT, 0, NULL)
+
+ /* String parameter that allows empty argument */
+ #define fsparam_string_empty(NAME, OPT) \
+diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
+index 855db460e08bc6..19c333fafe1138 100644
+--- a/include/linux/lsm_hook_defs.h
++++ b/include/linux/lsm_hook_defs.h
+@@ -114,6 +114,7 @@ LSM_HOOK(int, 0, path_notify, const struct path *path, u64 mask,
+ unsigned int obj_type)
+ LSM_HOOK(int, 0, inode_alloc_security, struct inode *inode)
+ LSM_HOOK(void, LSM_RET_VOID, inode_free_security, struct inode *inode)
++LSM_HOOK(void, LSM_RET_VOID, inode_free_security_rcu, void *inode_security)
+ LSM_HOOK(int, -EOPNOTSUPP, inode_init_security, struct inode *inode,
+ struct inode *dir, const struct qstr *qstr, struct xattr *xattrs,
+ int *xattr_count)
+diff --git a/include/linux/lsm_hooks.h b/include/linux/lsm_hooks.h
+index a2ade0ffe9e7d2..efd4a0655159cc 100644
+--- a/include/linux/lsm_hooks.h
++++ b/include/linux/lsm_hooks.h
+@@ -73,6 +73,7 @@ struct lsm_blob_sizes {
+ int lbs_cred;
+ int lbs_file;
+ int lbs_inode;
++ int lbs_sock;
+ int lbs_superblock;
+ int lbs_ipc;
+ int lbs_msg_msg;
+diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
+index c09cdcc99471e1..189140bf11fc40 100644
+--- a/include/linux/sbitmap.h
++++ b/include/linux/sbitmap.h
+@@ -40,7 +40,7 @@ struct sbitmap_word {
+ /**
+ * @swap_lock: serializes simultaneous updates of ->word and ->cleared
+ */
+- spinlock_t swap_lock;
++ raw_spinlock_t swap_lock;
+ } ____cacheline_aligned_in_smp;
+
+ /**
+diff --git a/include/linux/soc/qcom/geni-se.h b/include/linux/soc/qcom/geni-se.h
+index 0f038a1a033099..c3bca9c0bf2cf5 100644
+--- a/include/linux/soc/qcom/geni-se.h
++++ b/include/linux/soc/qcom/geni-se.h
+@@ -88,11 +88,15 @@ struct geni_se {
+ #define SE_GENI_M_IRQ_STATUS 0x610
+ #define SE_GENI_M_IRQ_EN 0x614
+ #define SE_GENI_M_IRQ_CLEAR 0x618
++#define SE_GENI_M_IRQ_EN_SET 0x61c
++#define SE_GENI_M_IRQ_EN_CLEAR 0x620
+ #define SE_GENI_S_CMD0 0x630
+ #define SE_GENI_S_CMD_CTRL_REG 0x634
+ #define SE_GENI_S_IRQ_STATUS 0x640
+ #define SE_GENI_S_IRQ_EN 0x644
+ #define SE_GENI_S_IRQ_CLEAR 0x648
++#define SE_GENI_S_IRQ_EN_SET 0x64c
++#define SE_GENI_S_IRQ_EN_CLEAR 0x650
+ #define SE_GENI_TX_FIFOn 0x700
+ #define SE_GENI_RX_FIFOn 0x780
+ #define SE_GENI_TX_FIFO_STATUS 0x800
+@@ -101,6 +105,8 @@ struct geni_se {
+ #define SE_GENI_RX_WATERMARK_REG 0x810
+ #define SE_GENI_RX_RFR_WATERMARK_REG 0x814
+ #define SE_GENI_IOS 0x908
++#define SE_GENI_M_GP_LENGTH 0x910
++#define SE_GENI_S_GP_LENGTH 0x914
+ #define SE_DMA_TX_IRQ_STAT 0xc40
+ #define SE_DMA_TX_IRQ_CLR 0xc44
+ #define SE_DMA_TX_FSM_RST 0xc58
+@@ -234,6 +240,9 @@ struct geni_se {
+ #define IO2_DATA_IN BIT(1)
+ #define RX_DATA_IN BIT(0)
+
++/* SE_GENI_M_GP_LENGTH and SE_GENI_S_GP_LENGTH fields */
++#define GP_LENGTH GENMASK(31, 0)
++
+ /* SE_DMA_TX_IRQ_STAT Register fields */
+ #define TX_DMA_DONE BIT(0)
+ #define TX_EOT BIT(1)
+diff --git a/include/linux/usb/usbnet.h b/include/linux/usb/usbnet.h
+index 9f08a584d70785..0b9f1e598e3a6b 100644
+--- a/include/linux/usb/usbnet.h
++++ b/include/linux/usb/usbnet.h
+@@ -76,8 +76,23 @@ struct usbnet {
+ # define EVENT_LINK_CHANGE 11
+ # define EVENT_SET_RX_MODE 12
+ # define EVENT_NO_IP_ALIGN 13
++/* This one is special, as it indicates that the device is going away
++ * there are cyclic dependencies between tasklet, timer and bh
++ * that must be broken
++ */
++# define EVENT_UNPLUG 31
+ };
+
++static inline bool usbnet_going_away(struct usbnet *ubn)
++{
++ return test_bit(EVENT_UNPLUG, &ubn->flags);
++}
++
++static inline void usbnet_mark_going_away(struct usbnet *ubn)
++{
++ set_bit(EVENT_UNPLUG, &ubn->flags);
++}
++
+ static inline struct usb_driver *driver_of(struct usb_interface *intf)
+ {
+ return to_usb_driver(intf->dev.driver);
+diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
+index ecb6824e9add83..9cfd1ce0fd36c4 100644
+--- a/include/net/bluetooth/hci_core.h
++++ b/include/net/bluetooth/hci_core.h
+@@ -2258,8 +2258,8 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ bool mgmt_connected);
+ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ u8 link_type, u8 addr_type, u8 status);
+-void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+- u8 addr_type, u8 status);
++void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn,
++ u8 status);
+ void mgmt_pin_code_request(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 secure);
+ void mgmt_pin_code_reply_complete(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ u8 status);
+diff --git a/include/net/ip.h b/include/net/ip.h
+index c5606cadb1a552..82248813619e3f 100644
+--- a/include/net/ip.h
++++ b/include/net/ip.h
+@@ -795,6 +795,8 @@ static inline void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb)
+ }
+
+ bool icmp_global_allow(void);
++void icmp_global_consume(void);
++
+ extern int sysctl_icmp_msgs_per_sec;
+ extern int sysctl_icmp_msgs_burst;
+
+diff --git a/include/net/mac80211.h b/include/net/mac80211.h
+index 45ad37adbe3287..7b3f56d862de40 100644
+--- a/include/net/mac80211.h
++++ b/include/net/mac80211.h
+@@ -953,8 +953,9 @@ enum mac80211_tx_info_flags {
+ * of their QoS TID or other priority field values.
+ * @IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX: first MLO TX, used mostly internally
+ * for sequence number assignment
+- * @IEEE80211_TX_CTRL_SCAN_TX: Indicates that this frame is transmitted
+- * due to scanning, not in normal operation on the interface.
++ * @IEEE80211_TX_CTRL_DONT_USE_RATE_MASK: Don't use rate mask for this frame
++ * which is transmitted due to scanning or offchannel TX, not in normal
++ * operation on the interface.
+ * @IEEE80211_TX_CTRL_MLO_LINK: If not @IEEE80211_LINK_UNSPECIFIED, this
+ * frame should be transmitted on the specific link. This really is
+ * only relevant for frames that do not have data present, and is
+@@ -975,7 +976,7 @@ enum mac80211_tx_control_flags {
+ IEEE80211_TX_CTRL_NO_SEQNO = BIT(7),
+ IEEE80211_TX_CTRL_DONT_REORDER = BIT(8),
+ IEEE80211_TX_CTRL_MCAST_MLO_FIRST_TX = BIT(9),
+- IEEE80211_TX_CTRL_SCAN_TX = BIT(10),
++ IEEE80211_TX_CTRL_DONT_USE_RATE_MASK = BIT(10),
+ IEEE80211_TX_CTRL_MLO_LINK = 0xf0000000,
+ };
+
+diff --git a/include/net/tcp.h b/include/net/tcp.h
+index 45bbb54e42e85e..ac647c952cf0c5 100644
+--- a/include/net/tcp.h
++++ b/include/net/tcp.h
+@@ -2437,9 +2437,26 @@ static inline s64 tcp_rto_delta_us(const struct sock *sk)
+ {
+ const struct sk_buff *skb = tcp_rtx_queue_head(sk);
+ u32 rto = inet_csk(sk)->icsk_rto;
+- u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto);
+
+- return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp;
++ if (likely(skb)) {
++ u64 rto_time_stamp_us = tcp_skb_timestamp_us(skb) + jiffies_to_usecs(rto);
++
++ return rto_time_stamp_us - tcp_sk(sk)->tcp_mstamp;
++ } else {
++ WARN_ONCE(1,
++ "rtx queue emtpy: "
++ "out:%u sacked:%u lost:%u retrans:%u "
++ "tlp_high_seq:%u sk_state:%u ca_state:%u "
++ "advmss:%u mss_cache:%u pmtu:%u\n",
++ tcp_sk(sk)->packets_out, tcp_sk(sk)->sacked_out,
++ tcp_sk(sk)->lost_out, tcp_sk(sk)->retrans_out,
++ tcp_sk(sk)->tlp_high_seq, sk->sk_state,
++ inet_csk(sk)->icsk_ca_state,
++ tcp_sk(sk)->advmss, tcp_sk(sk)->mss_cache,
++ inet_csk(sk)->icsk_pmtu_cookie);
++ return jiffies_to_usecs(rto);
++ }
++
+ }
+
+ /*
+diff --git a/include/sound/tas2781.h b/include/sound/tas2781.h
+index 99ca3e401fd1fe..6f6e3e2f652c96 100644
+--- a/include/sound/tas2781.h
++++ b/include/sound/tas2781.h
+@@ -80,11 +80,6 @@ struct tasdevice {
+ bool is_loaderr;
+ };
+
+-struct tasdevice_irqinfo {
+- int irq_gpio;
+- int irq;
+-};
+-
+ struct calidata {
+ unsigned char *data;
+ unsigned long total_sz;
+@@ -92,7 +87,6 @@ struct calidata {
+
+ struct tasdevice_priv {
+ struct tasdevice tasdevice[TASDEVICE_MAX_CHANNELS];
+- struct tasdevice_irqinfo irq_info;
+ struct tasdevice_rca rcabin;
+ struct calidata cali_data;
+ struct tasdevice_fw *fmw;
+@@ -113,6 +107,7 @@ struct tasdevice_priv {
+ unsigned int chip_id;
+ unsigned int sysclk;
+
++ int irq;
+ int cur_prog;
+ int cur_conf;
+ int fw_state;
+diff --git a/include/trace/events/f2fs.h b/include/trace/events/f2fs.h
+index ed794b5fefbe3a..2851c823095bc1 100644
+--- a/include/trace/events/f2fs.h
++++ b/include/trace/events/f2fs.h
+@@ -139,7 +139,8 @@ TRACE_DEFINE_ENUM(EX_BLOCK_AGE);
+ { CP_NODE_NEED_CP, "node needs cp" }, \
+ { CP_FASTBOOT_MODE, "fastboot mode" }, \
+ { CP_SPEC_LOG_NUM, "log type is 2" }, \
+- { CP_RECOVER_DIR, "dir needs recovery" })
++ { CP_RECOVER_DIR, "dir needs recovery" }, \
++ { CP_XATTR_DIR, "dir's xattr updated" })
+
+ #define show_shutdown_mode(type) \
+ __print_symbolic(type, \
+diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
+index 22dac5850327fc..b59a1bf844cf9d 100644
+--- a/io_uring/io-wq.c
++++ b/io_uring/io-wq.c
+@@ -13,6 +13,7 @@
+ #include <linux/slab.h>
+ #include <linux/rculist_nulls.h>
+ #include <linux/cpu.h>
++#include <linux/cpuset.h>
+ #include <linux/task_work.h>
+ #include <linux/audit.h>
+ #include <linux/mmu_context.h>
+@@ -1166,7 +1167,7 @@ struct io_wq *io_wq_create(unsigned bounded, struct io_wq_data *data)
+
+ if (!alloc_cpumask_var(&wq->cpu_mask, GFP_KERNEL))
+ goto err;
+- cpumask_copy(wq->cpu_mask, cpu_possible_mask);
++ cpuset_cpus_allowed(data->task, wq->cpu_mask);
+ wq->acct[IO_WQ_ACCT_BOUND].max_workers = bounded;
+ wq->acct[IO_WQ_ACCT_UNBOUND].max_workers =
+ task_rlimit(current, RLIMIT_NPROC);
+@@ -1321,17 +1322,29 @@ static int io_wq_cpu_offline(unsigned int cpu, struct hlist_node *node)
+
+ int io_wq_cpu_affinity(struct io_uring_task *tctx, cpumask_var_t mask)
+ {
++ cpumask_var_t allowed_mask;
++ int ret = 0;
++
+ if (!tctx || !tctx->io_wq)
+ return -EINVAL;
+
++ if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
++ return -ENOMEM;
++
+ rcu_read_lock();
+- if (mask)
+- cpumask_copy(tctx->io_wq->cpu_mask, mask);
+- else
+- cpumask_copy(tctx->io_wq->cpu_mask, cpu_possible_mask);
++ cpuset_cpus_allowed(tctx->io_wq->task, allowed_mask);
++ if (mask) {
++ if (cpumask_subset(mask, allowed_mask))
++ cpumask_copy(tctx->io_wq->cpu_mask, mask);
++ else
++ ret = -EINVAL;
++ } else {
++ cpumask_copy(tctx->io_wq->cpu_mask, allowed_mask);
++ }
+ rcu_read_unlock();
+
+- return 0;
++ free_cpumask_var(allowed_mask);
++ return ret;
+ }
+
+ /*
+diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
+index 896e707e06187f..c0d8ee0c9786df 100644
+--- a/io_uring/io_uring.c
++++ b/io_uring/io_uring.c
+@@ -2401,7 +2401,7 @@ static inline int io_cqring_wait_schedule(struct io_ring_ctx *ctx,
+ return 1;
+ if (unlikely(!llist_empty(&ctx->work_llist)))
+ return 1;
+- if (unlikely(test_thread_flag(TIF_NOTIFY_SIGNAL)))
++ if (unlikely(task_work_pending(current)))
+ return 1;
+ if (unlikely(task_sigpending(current)))
+ return -EINTR;
+@@ -2502,9 +2502,9 @@ static int io_cqring_wait(struct io_ring_ctx *ctx, int min_events,
+ * If we got woken because of task_work being processed, run it
+ * now rather than let the caller do another wait loop.
+ */
+- io_run_task_work();
+ if (!llist_empty(&ctx->work_llist))
+ io_run_local_work(ctx, nr_wait);
++ io_run_task_work();
+
+ /*
+ * Non-local task_work will be run on exit to userspace, but
+diff --git a/io_uring/rw.c b/io_uring/rw.c
+index 1a2128459cb4c8..e6b44367df67b0 100644
+--- a/io_uring/rw.c
++++ b/io_uring/rw.c
+@@ -856,6 +856,14 @@ static int __io_read(struct io_kiocb *req, unsigned int issue_flags)
+
+ ret = io_iter_do_read(rw, &io->iter);
+
++ /*
++ * Some file systems like to return -EOPNOTSUPP for an IOCB_NOWAIT
++ * issue, even though they should be returning -EAGAIN. To be safe,
++ * retry from blocking context for either.
++ */
++ if (ret == -EOPNOTSUPP && force_nonblock)
++ ret = -EAGAIN;
++
+ if (ret == -EAGAIN || (req->flags & REQ_F_REISSUE)) {
+ req->flags &= ~REQ_F_REISSUE;
+ /* If we can poll, just do that. */
+diff --git a/io_uring/sqpoll.c b/io_uring/sqpoll.c
+index b3722e5275e77e..4dcb1c586536d7 100644
+--- a/io_uring/sqpoll.c
++++ b/io_uring/sqpoll.c
+@@ -10,6 +10,7 @@
+ #include <linux/slab.h>
+ #include <linux/audit.h>
+ #include <linux/security.h>
++#include <linux/cpuset.h>
+ #include <linux/io_uring.h>
+
+ #include <uapi/linux/io_uring.h>
+@@ -460,11 +461,22 @@ __cold int io_sq_offload_create(struct io_ring_ctx *ctx,
+ return 0;
+
+ if (p->flags & IORING_SETUP_SQ_AFF) {
++ cpumask_var_t allowed_mask;
+ int cpu = p->sq_thread_cpu;
+
+ ret = -EINVAL;
+ if (cpu >= nr_cpu_ids || !cpu_online(cpu))
+ goto err_sqpoll;
++ ret = -ENOMEM;
++ if (!alloc_cpumask_var(&allowed_mask, GFP_KERNEL))
++ goto err_sqpoll;
++ ret = -EINVAL;
++ cpuset_cpus_allowed(current, allowed_mask);
++ if (!cpumask_test_cpu(cpu, allowed_mask)) {
++ free_cpumask_var(allowed_mask);
++ goto err_sqpoll;
++ }
++ free_cpumask_var(allowed_mask);
+ sqd->sq_cpu = cpu;
+ } else {
+ sqd->sq_cpu = -1;
+diff --git a/kernel/bpf/bpf_lsm.c b/kernel/bpf/bpf_lsm.c
+index 68240c3c6e7dea..7f8a66a62661b9 100644
+--- a/kernel/bpf/bpf_lsm.c
++++ b/kernel/bpf/bpf_lsm.c
+@@ -11,7 +11,6 @@
+ #include <linux/lsm_hooks.h>
+ #include <linux/bpf_lsm.h>
+ #include <linux/kallsyms.h>
+-#include <linux/bpf_verifier.h>
+ #include <net/bpf_sk_storage.h>
+ #include <linux/bpf_local_storage.h>
+ #include <linux/btf_ids.h>
+@@ -389,3 +388,36 @@ const struct bpf_verifier_ops lsm_verifier_ops = {
+ .get_func_proto = bpf_lsm_func_proto,
+ .is_valid_access = btf_ctx_access,
+ };
++
++/* hooks return 0 or 1 */
++BTF_SET_START(bool_lsm_hooks)
++#ifdef CONFIG_SECURITY_NETWORK_XFRM
++BTF_ID(func, bpf_lsm_xfrm_state_pol_flow_match)
++#endif
++#ifdef CONFIG_AUDIT
++BTF_ID(func, bpf_lsm_audit_rule_known)
++#endif
++BTF_ID(func, bpf_lsm_inode_xattr_skipcap)
++BTF_SET_END(bool_lsm_hooks)
++
++int bpf_lsm_get_retval_range(const struct bpf_prog *prog,
++ struct bpf_retval_range *retval_range)
++{
++ /* no return value range for void hooks */
++ if (!prog->aux->attach_func_proto->type)
++ return -EINVAL;
++
++ if (btf_id_set_contains(&bool_lsm_hooks, prog->aux->attach_btf_id)) {
++ retval_range->minval = 0;
++ retval_range->maxval = 1;
++ } else {
++ /* All other available LSM hooks, except task_prctl, return 0
++ * on success and negative error code on failure.
++ * To keep things simple, we only allow bpf progs to return 0
++ * or negative errno for task_prctl too.
++ */
++ retval_range->minval = -MAX_ERRNO;
++ retval_range->maxval = 0;
++ }
++ return 0;
++}
+diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
+index 2f157ffbc67cea..96e8596a76ceab 100644
+--- a/kernel/bpf/btf.c
++++ b/kernel/bpf/btf.c
+@@ -6250,8 +6250,11 @@ bool btf_ctx_access(int off, int size, enum bpf_access_type type,
+
+ if (arg == nr_args) {
+ switch (prog->expected_attach_type) {
+- case BPF_LSM_CGROUP:
+ case BPF_LSM_MAC:
++ /* mark we are accessing the return value */
++ info->is_retval = true;
++ fallthrough;
++ case BPF_LSM_CGROUP:
+ case BPF_TRACE_FEXIT:
+ /* When LSM programs are attached to void LSM hooks
+ * they use FEXIT trampolines and when attached to
+@@ -8715,6 +8718,7 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
+ struct bpf_core_cand_list cands = {};
+ struct bpf_core_relo_res targ_res;
+ struct bpf_core_spec *specs;
++ const struct btf_type *type;
+ int err;
+
+ /* ~4k of temp memory necessary to convert LLVM spec like "0:1:0:5"
+@@ -8724,6 +8728,13 @@ int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
+ if (!specs)
+ return -ENOMEM;
+
++ type = btf_type_by_id(ctx->btf, relo->type_id);
++ if (!type) {
++ bpf_log(ctx->log, "relo #%u: bad type id %u\n",
++ relo_idx, relo->type_id);
++ return -EINVAL;
++ }
++
+ if (need_cands) {
+ struct bpf_cand_cache *cc;
+ int i;
+diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
+index 7268370600f6e6..a9ae8f8e618075 100644
+--- a/kernel/bpf/helpers.c
++++ b/kernel/bpf/helpers.c
+@@ -517,11 +517,12 @@ static int __bpf_strtoll(const char *buf, size_t buf_len, u64 flags,
+ }
+
+ BPF_CALL_4(bpf_strtol, const char *, buf, size_t, buf_len, u64, flags,
+- long *, res)
++ s64 *, res)
+ {
+ long long _res;
+ int err;
+
++ *res = 0;
+ err = __bpf_strtoll(buf, buf_len, flags, &_res);
+ if (err < 0)
+ return err;
+@@ -538,16 +539,18 @@ const struct bpf_func_proto bpf_strtol_proto = {
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_ANYTHING,
+- .arg4_type = ARG_PTR_TO_LONG,
++ .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
++ .arg4_size = sizeof(s64),
+ };
+
+ BPF_CALL_4(bpf_strtoul, const char *, buf, size_t, buf_len, u64, flags,
+- unsigned long *, res)
++ u64 *, res)
+ {
+ unsigned long long _res;
+ bool is_negative;
+ int err;
+
++ *res = 0;
+ err = __bpf_strtoull(buf, buf_len, flags, &_res, &is_negative);
+ if (err < 0)
+ return err;
+@@ -566,7 +569,8 @@ const struct bpf_func_proto bpf_strtoul_proto = {
+ .arg1_type = ARG_PTR_TO_MEM | MEM_RDONLY,
+ .arg2_type = ARG_CONST_SIZE,
+ .arg3_type = ARG_ANYTHING,
+- .arg4_type = ARG_PTR_TO_LONG,
++ .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
++ .arg4_size = sizeof(u64),
+ };
+
+ BPF_CALL_3(bpf_strncmp, const char *, s1, u32, s1_sz, const char *, s2)
+diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
+index f45ed6adc092af..f6b6d297fad6ed 100644
+--- a/kernel/bpf/syscall.c
++++ b/kernel/bpf/syscall.c
+@@ -5910,6 +5910,7 @@ static const struct bpf_func_proto bpf_sys_close_proto = {
+
+ BPF_CALL_4(bpf_kallsyms_lookup_name, const char *, name, int, name_sz, int, flags, u64 *, res)
+ {
++ *res = 0;
+ if (flags)
+ return -EINVAL;
+
+@@ -5930,7 +5931,8 @@ static const struct bpf_func_proto bpf_kallsyms_lookup_name_proto = {
+ .arg1_type = ARG_PTR_TO_MEM,
+ .arg2_type = ARG_CONST_SIZE_OR_ZERO,
+ .arg3_type = ARG_ANYTHING,
+- .arg4_type = ARG_PTR_TO_LONG,
++ .arg4_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
++ .arg4_size = sizeof(u64),
+ };
+
+ static const struct bpf_func_proto *
+diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
+index 73f55f4b945eed..c821713249c81d 100644
+--- a/kernel/bpf/verifier.c
++++ b/kernel/bpf/verifier.c
+@@ -2334,6 +2334,25 @@ static void mark_reg_unknown(struct bpf_verifier_env *env,
+ __mark_reg_unknown(env, regs + regno);
+ }
+
++static int __mark_reg_s32_range(struct bpf_verifier_env *env,
++ struct bpf_reg_state *regs,
++ u32 regno,
++ s32 s32_min,
++ s32 s32_max)
++{
++ struct bpf_reg_state *reg = regs + regno;
++
++ reg->s32_min_value = max_t(s32, reg->s32_min_value, s32_min);
++ reg->s32_max_value = min_t(s32, reg->s32_max_value, s32_max);
++
++ reg->smin_value = max_t(s64, reg->smin_value, s32_min);
++ reg->smax_value = min_t(s64, reg->smax_value, s32_max);
++
++ reg_bounds_sync(reg);
++
++ return reg_bounds_sanity_check(env, reg, "s32_range");
++}
++
+ static void __mark_reg_not_init(const struct bpf_verifier_env *env,
+ struct bpf_reg_state *reg)
+ {
+@@ -5575,11 +5594,13 @@ static int check_packet_access(struct bpf_verifier_env *env, u32 regno, int off,
+ /* check access to 'struct bpf_context' fields. Supports fixed offsets only */
+ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off, int size,
+ enum bpf_access_type t, enum bpf_reg_type *reg_type,
+- struct btf **btf, u32 *btf_id)
++ struct btf **btf, u32 *btf_id, bool *is_retval, bool is_ldsx)
+ {
+ struct bpf_insn_access_aux info = {
+ .reg_type = *reg_type,
+ .log = &env->log,
++ .is_retval = false,
++ .is_ldsx = is_ldsx,
+ };
+
+ if (env->ops->is_valid_access &&
+@@ -5592,6 +5613,7 @@ static int check_ctx_access(struct bpf_verifier_env *env, int insn_idx, int off,
+ * type of narrower access.
+ */
+ *reg_type = info.reg_type;
++ *is_retval = info.is_retval;
+
+ if (base_type(*reg_type) == PTR_TO_BTF_ID) {
+ *btf = info.btf;
+@@ -6760,6 +6782,17 @@ static int check_stack_access_within_bounds(
+ return grow_stack_state(env, state, -min_off /* size */);
+ }
+
++static bool get_func_retval_range(struct bpf_prog *prog,
++ struct bpf_retval_range *range)
++{
++ if (prog->type == BPF_PROG_TYPE_LSM &&
++ prog->expected_attach_type == BPF_LSM_MAC &&
++ !bpf_lsm_get_retval_range(prog, range)) {
++ return true;
++ }
++ return false;
++}
++
+ /* check whether memory at (regno + off) is accessible for t = (read | write)
+ * if t==write, value_regno is a register which value is stored into memory
+ * if t==read, value_regno is a register which will receive the value from memory
+@@ -6864,6 +6897,8 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
+ if (!err && value_regno >= 0 && (t == BPF_READ || rdonly_mem))
+ mark_reg_unknown(env, regs, value_regno);
+ } else if (reg->type == PTR_TO_CTX) {
++ bool is_retval = false;
++ struct bpf_retval_range range;
+ enum bpf_reg_type reg_type = SCALAR_VALUE;
+ struct btf *btf = NULL;
+ u32 btf_id = 0;
+@@ -6879,7 +6914,7 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
+ return err;
+
+ err = check_ctx_access(env, insn_idx, off, size, t, ®_type, &btf,
+- &btf_id);
++ &btf_id, &is_retval, is_ldsx);
+ if (err)
+ verbose_linfo(env, insn_idx, "; ");
+ if (!err && t == BPF_READ && value_regno >= 0) {
+@@ -6888,7 +6923,14 @@ static int check_mem_access(struct bpf_verifier_env *env, int insn_idx, u32 regn
+ * case, we know the offset is zero.
+ */
+ if (reg_type == SCALAR_VALUE) {
+- mark_reg_unknown(env, regs, value_regno);
++ if (is_retval && get_func_retval_range(env->prog, &range)) {
++ err = __mark_reg_s32_range(env, regs, value_regno,
++ range.minval, range.maxval);
++ if (err)
++ return err;
++ } else {
++ mark_reg_unknown(env, regs, value_regno);
++ }
+ } else {
+ mark_reg_known_zero(env, regs,
+ value_regno);
+@@ -8116,6 +8158,12 @@ static bool arg_type_is_mem_size(enum bpf_arg_type type)
+ type == ARG_CONST_SIZE_OR_ZERO;
+ }
+
++static bool arg_type_is_raw_mem(enum bpf_arg_type type)
++{
++ return base_type(type) == ARG_PTR_TO_MEM &&
++ type & MEM_UNINIT;
++}
++
+ static bool arg_type_is_release(enum bpf_arg_type type)
+ {
+ return type & OBJ_RELEASE;
+@@ -8126,16 +8174,6 @@ static bool arg_type_is_dynptr(enum bpf_arg_type type)
+ return base_type(type) == ARG_PTR_TO_DYNPTR;
+ }
+
+-static int int_ptr_type_to_size(enum bpf_arg_type type)
+-{
+- if (type == ARG_PTR_TO_INT)
+- return sizeof(u32);
+- else if (type == ARG_PTR_TO_LONG)
+- return sizeof(u64);
+-
+- return -EINVAL;
+-}
+-
+ static int resolve_map_arg_type(struct bpf_verifier_env *env,
+ const struct bpf_call_arg_meta *meta,
+ enum bpf_arg_type *arg_type)
+@@ -8208,16 +8246,6 @@ static const struct bpf_reg_types mem_types = {
+ },
+ };
+
+-static const struct bpf_reg_types int_ptr_types = {
+- .types = {
+- PTR_TO_STACK,
+- PTR_TO_PACKET,
+- PTR_TO_PACKET_META,
+- PTR_TO_MAP_KEY,
+- PTR_TO_MAP_VALUE,
+- },
+-};
+-
+ static const struct bpf_reg_types spin_lock_types = {
+ .types = {
+ PTR_TO_MAP_VALUE,
+@@ -8273,8 +8301,6 @@ static const struct bpf_reg_types *compatible_reg_types[__BPF_ARG_TYPE_MAX] = {
+ [ARG_PTR_TO_SPIN_LOCK] = &spin_lock_types,
+ [ARG_PTR_TO_MEM] = &mem_types,
+ [ARG_PTR_TO_RINGBUF_MEM] = &ringbuf_mem_types,
+- [ARG_PTR_TO_INT] = &int_ptr_types,
+- [ARG_PTR_TO_LONG] = &int_ptr_types,
+ [ARG_PTR_TO_PERCPU_BTF_ID] = &percpu_btf_ptr_types,
+ [ARG_PTR_TO_FUNC] = &func_ptr_types,
+ [ARG_PTR_TO_STACK] = &stack_ptr_types,
+@@ -8835,9 +8861,11 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
+ */
+ meta->raw_mode = arg_type & MEM_UNINIT;
+ if (arg_type & MEM_FIXED_SIZE) {
+- err = check_helper_mem_access(env, regno,
+- fn->arg_size[arg], false,
+- meta);
++ err = check_helper_mem_access(env, regno, fn->arg_size[arg], false, meta);
++ if (err)
++ return err;
++ if (arg_type & MEM_ALIGNED)
++ err = check_ptr_alignment(env, reg, 0, fn->arg_size[arg], true);
+ }
+ break;
+ case ARG_CONST_SIZE:
+@@ -8862,17 +8890,6 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 arg,
+ if (err)
+ return err;
+ break;
+- case ARG_PTR_TO_INT:
+- case ARG_PTR_TO_LONG:
+- {
+- int size = int_ptr_type_to_size(arg_type);
+-
+- err = check_helper_mem_access(env, regno, size, false, meta);
+- if (err)
+- return err;
+- err = check_ptr_alignment(env, reg, 0, size, true);
+- break;
+- }
+ case ARG_PTR_TO_CONST_STR:
+ {
+ err = check_reg_const_str(env, reg, regno);
+@@ -9189,15 +9206,15 @@ static bool check_raw_mode_ok(const struct bpf_func_proto *fn)
+ {
+ int count = 0;
+
+- if (fn->arg1_type == ARG_PTR_TO_UNINIT_MEM)
++ if (arg_type_is_raw_mem(fn->arg1_type))
+ count++;
+- if (fn->arg2_type == ARG_PTR_TO_UNINIT_MEM)
++ if (arg_type_is_raw_mem(fn->arg2_type))
+ count++;
+- if (fn->arg3_type == ARG_PTR_TO_UNINIT_MEM)
++ if (arg_type_is_raw_mem(fn->arg3_type))
+ count++;
+- if (fn->arg4_type == ARG_PTR_TO_UNINIT_MEM)
++ if (arg_type_is_raw_mem(fn->arg4_type))
+ count++;
+- if (fn->arg5_type == ARG_PTR_TO_UNINIT_MEM)
++ if (arg_type_is_raw_mem(fn->arg5_type))
+ count++;
+
+ /* We only support one arg being in raw mode at the moment,
+@@ -9911,9 +9928,13 @@ static bool in_rbtree_lock_required_cb(struct bpf_verifier_env *env)
+ return is_rbtree_lock_required_kfunc(kfunc_btf_id);
+ }
+
+-static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg)
++static bool retval_range_within(struct bpf_retval_range range, const struct bpf_reg_state *reg,
++ bool return_32bit)
+ {
+- return range.minval <= reg->smin_value && reg->smax_value <= range.maxval;
++ if (return_32bit)
++ return range.minval <= reg->s32_min_value && reg->s32_max_value <= range.maxval;
++ else
++ return range.minval <= reg->smin_value && reg->smax_value <= range.maxval;
+ }
+
+ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
+@@ -9950,8 +9971,8 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx)
+ if (err)
+ return err;
+
+- /* enforce R0 return value range */
+- if (!retval_range_within(callee->callback_ret_range, r0)) {
++ /* enforce R0 return value range, and bpf_callback_t returns 64bit */
++ if (!retval_range_within(callee->callback_ret_range, r0, false)) {
+ verbose_invalid_scalar(env, r0, callee->callback_ret_range,
+ "At callback return", "R0");
+ return -EINVAL;
+@@ -15572,6 +15593,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char
+ int err;
+ struct bpf_func_state *frame = env->cur_state->frame[0];
+ const bool is_subprog = frame->subprogno;
++ bool return_32bit = false;
+
+ /* LSM and struct_ops func-ptr's return type could be "void" */
+ if (!is_subprog || frame->in_exception_callback_fn) {
+@@ -15677,12 +15699,14 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char
+
+ case BPF_PROG_TYPE_LSM:
+ if (env->prog->expected_attach_type != BPF_LSM_CGROUP) {
+- /* Regular BPF_PROG_TYPE_LSM programs can return
+- * any value.
+- */
+- return 0;
+- }
+- if (!env->prog->aux->attach_func_proto->type) {
++ /* no range found, any return value is allowed */
++ if (!get_func_retval_range(env->prog, &range))
++ return 0;
++ /* no restricted range, any return value is allowed */
++ if (range.minval == S32_MIN && range.maxval == S32_MAX)
++ return 0;
++ return_32bit = true;
++ } else if (!env->prog->aux->attach_func_proto->type) {
+ /* Make sure programs that attach to void
+ * hooks don't try to modify return value.
+ */
+@@ -15712,7 +15736,7 @@ static int check_return_code(struct bpf_verifier_env *env, int regno, const char
+ if (err)
+ return err;
+
+- if (!retval_range_within(range, reg)) {
++ if (!retval_range_within(range, reg, return_32bit)) {
+ verbose_invalid_scalar(env, reg, range, exit_ctx, reg_name);
+ if (!is_subprog &&
+ prog->expected_attach_type == BPF_LSM_CGROUP &&
+diff --git a/kernel/kthread.c b/kernel/kthread.c
+index f7be976ff88af7..db4ceb0f503cca 100644
+--- a/kernel/kthread.c
++++ b/kernel/kthread.c
+@@ -845,8 +845,16 @@ int kthread_worker_fn(void *worker_ptr)
+ * event only cares about the address.
+ */
+ trace_sched_kthread_work_execute_end(work, func);
+- } else if (!freezing(current))
++ } else if (!freezing(current)) {
+ schedule();
++ } else {
++ /*
++ * Handle the case where the current remains
++ * TASK_INTERRUPTIBLE. try_to_freeze() expects
++ * the current to be TASK_RUNNING.
++ */
++ __set_current_state(TASK_RUNNING);
++ }
+
+ try_to_freeze();
+ cond_resched();
+diff --git a/kernel/locking/lockdep.c b/kernel/locking/lockdep.c
+index 151bd3de59363a..3468d8230e5f75 100644
+--- a/kernel/locking/lockdep.c
++++ b/kernel/locking/lockdep.c
+@@ -6184,25 +6184,27 @@ static struct pending_free *get_pending_free(void)
+ static void free_zapped_rcu(struct rcu_head *cb);
+
+ /*
+- * Schedule an RCU callback if no RCU callback is pending. Must be called with
+- * the graph lock held.
+- */
+-static void call_rcu_zapped(struct pending_free *pf)
++* See if we need to queue an RCU callback, must called with
++* the lockdep lock held, returns false if either we don't have
++* any pending free or the callback is already scheduled.
++* Otherwise, a call_rcu() must follow this function call.
++*/
++static bool prepare_call_rcu_zapped(struct pending_free *pf)
+ {
+ WARN_ON_ONCE(inside_selftest());
+
+ if (list_empty(&pf->zapped))
+- return;
++ return false;
+
+ if (delayed_free.scheduled)
+- return;
++ return false;
+
+ delayed_free.scheduled = true;
+
+ WARN_ON_ONCE(delayed_free.pf + delayed_free.index != pf);
+ delayed_free.index ^= 1;
+
+- call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
++ return true;
+ }
+
+ /* The caller must hold the graph lock. May be called from RCU context. */
+@@ -6228,6 +6230,7 @@ static void free_zapped_rcu(struct rcu_head *ch)
+ {
+ struct pending_free *pf;
+ unsigned long flags;
++ bool need_callback;
+
+ if (WARN_ON_ONCE(ch != &delayed_free.rcu_head))
+ return;
+@@ -6239,14 +6242,18 @@ static void free_zapped_rcu(struct rcu_head *ch)
+ pf = delayed_free.pf + (delayed_free.index ^ 1);
+ __free_zapped_classes(pf);
+ delayed_free.scheduled = false;
++ need_callback =
++ prepare_call_rcu_zapped(delayed_free.pf + delayed_free.index);
++ lockdep_unlock();
++ raw_local_irq_restore(flags);
+
+ /*
+- * If there's anything on the open list, close and start a new callback.
+- */
+- call_rcu_zapped(delayed_free.pf + delayed_free.index);
++ * If there's pending free and its callback has not been scheduled,
++ * queue an RCU callback.
++ */
++ if (need_callback)
++ call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+
+- lockdep_unlock();
+- raw_local_irq_restore(flags);
+ }
+
+ /*
+@@ -6286,6 +6293,7 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
+ {
+ struct pending_free *pf;
+ unsigned long flags;
++ bool need_callback;
+
+ init_data_structures_once();
+
+@@ -6293,10 +6301,11 @@ static void lockdep_free_key_range_reg(void *start, unsigned long size)
+ lockdep_lock();
+ pf = get_pending_free();
+ __lockdep_free_key_range(pf, start, size);
+- call_rcu_zapped(pf);
++ need_callback = prepare_call_rcu_zapped(pf);
+ lockdep_unlock();
+ raw_local_irq_restore(flags);
+-
++ if (need_callback)
++ call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+ /*
+ * Wait for any possible iterators from look_up_lock_class() to pass
+ * before continuing to free the memory they refer to.
+@@ -6390,6 +6399,7 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock)
+ struct pending_free *pf;
+ unsigned long flags;
+ int locked;
++ bool need_callback = false;
+
+ raw_local_irq_save(flags);
+ locked = graph_lock();
+@@ -6398,11 +6408,13 @@ static void lockdep_reset_lock_reg(struct lockdep_map *lock)
+
+ pf = get_pending_free();
+ __lockdep_reset_lock(pf, lock);
+- call_rcu_zapped(pf);
++ need_callback = prepare_call_rcu_zapped(pf);
+
+ graph_unlock();
+ out_irq:
+ raw_local_irq_restore(flags);
++ if (need_callback)
++ call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
+ }
+
+ /*
+@@ -6446,6 +6458,7 @@ void lockdep_unregister_key(struct lock_class_key *key)
+ struct pending_free *pf;
+ unsigned long flags;
+ bool found = false;
++ bool need_callback = false;
+
+ might_sleep();
+
+@@ -6466,11 +6479,14 @@ void lockdep_unregister_key(struct lock_class_key *key)
+ if (found) {
+ pf = get_pending_free();
+ __lockdep_free_key_range(pf, key, 1);
+- call_rcu_zapped(pf);
++ need_callback = prepare_call_rcu_zapped(pf);
+ }
+ lockdep_unlock();
+ raw_local_irq_restore(flags);
+
++ if (need_callback)
++ call_rcu(&delayed_free.rcu_head, free_zapped_rcu);
++
+ /* Wait until is_dynamic_key() has finished accessing k->hash_entry. */
+ synchronize_rcu();
+ }
+diff --git a/kernel/module/Makefile b/kernel/module/Makefile
+index a10b2b9a6fdfc6..50ffcc413b5450 100644
+--- a/kernel/module/Makefile
++++ b/kernel/module/Makefile
+@@ -5,7 +5,7 @@
+
+ # These are called from save_stack_trace() on slub debug path,
+ # and produce insane amounts of uninteresting coverage.
+-KCOV_INSTRUMENT_module.o := n
++KCOV_INSTRUMENT_main.o := n
+
+ obj-y += main.o
+ obj-y += strict_rwx.o
+diff --git a/kernel/padata.c b/kernel/padata.c
+index 0fa6c289546032..d899f34558afcc 100644
+--- a/kernel/padata.c
++++ b/kernel/padata.c
+@@ -404,7 +404,8 @@ void padata_do_serial(struct padata_priv *padata)
+ /* Sort in ascending order of sequence number. */
+ list_for_each_prev(pos, &reorder->list) {
+ cur = list_entry(pos, struct padata_priv, list);
+- if (cur->seq_nr < padata->seq_nr)
++ /* Compare by difference to consider integer wrap around */
++ if ((signed int)(cur->seq_nr - padata->seq_nr) < 0)
+ break;
+ }
+ list_add(&padata->list, pos);
+@@ -512,9 +513,12 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
+ * thread function. Load balance large jobs between threads by
+ * increasing the number of chunks, guarantee at least the minimum
+ * chunk size from the caller, and honor the caller's alignment.
++ * Ensure chunk_size is at least 1 to prevent divide-by-0
++ * panic in padata_mt_helper().
+ */
+ ps.chunk_size = job->size / (ps.nworks * load_balance_factor);
+ ps.chunk_size = max(ps.chunk_size, job->min_chunk);
++ ps.chunk_size = max(ps.chunk_size, 1ul);
+ ps.chunk_size = roundup(ps.chunk_size, job->align);
+
+ /*
+diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
+index 2d9eed2bf75093..9b485f1060c017 100644
+--- a/kernel/rcu/tree_nocb.h
++++ b/kernel/rcu/tree_nocb.h
+@@ -220,7 +220,10 @@ static bool __wake_nocb_gp(struct rcu_data *rdp_gp,
+ raw_spin_unlock_irqrestore(&rdp_gp->nocb_gp_lock, flags);
+ if (needwake) {
+ trace_rcu_nocb_wake(rcu_state.name, rdp->cpu, TPS("DoWake"));
+- wake_up_process(rdp_gp->nocb_gp_kthread);
++ if (cpu_is_offline(raw_smp_processor_id()))
++ swake_up_one_online(&rdp_gp->nocb_gp_wq);
++ else
++ wake_up_process(rdp_gp->nocb_gp_kthread);
+ }
+
+ return needwake;
+diff --git a/kernel/sched/deadline.c b/kernel/sched/deadline.c
+index 9bedd148f0075c..09faca47e90fb8 100644
+--- a/kernel/sched/deadline.c
++++ b/kernel/sched/deadline.c
+@@ -1599,46 +1599,40 @@ static inline bool __dl_less(struct rb_node *a, const struct rb_node *b)
+ return dl_time_before(__node_2_dle(a)->deadline, __node_2_dle(b)->deadline);
+ }
+
+-static inline struct sched_statistics *
++static __always_inline struct sched_statistics *
+ __schedstats_from_dl_se(struct sched_dl_entity *dl_se)
+ {
++ if (!schedstat_enabled())
++ return NULL;
++
++ if (dl_server(dl_se))
++ return NULL;
++
+ return &dl_task_of(dl_se)->stats;
+ }
+
+ static inline void
+ update_stats_wait_start_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
+ {
+- struct sched_statistics *stats;
+-
+- if (!schedstat_enabled())
+- return;
+-
+- stats = __schedstats_from_dl_se(dl_se);
+- __update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
++ struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
++ if (stats)
++ __update_stats_wait_start(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+ }
+
+ static inline void
+ update_stats_wait_end_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
+ {
+- struct sched_statistics *stats;
+-
+- if (!schedstat_enabled())
+- return;
+-
+- stats = __schedstats_from_dl_se(dl_se);
+- __update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
++ struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
++ if (stats)
++ __update_stats_wait_end(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+ }
+
+ static inline void
+ update_stats_enqueue_sleeper_dl(struct dl_rq *dl_rq, struct sched_dl_entity *dl_se)
+ {
+- struct sched_statistics *stats;
+-
+- if (!schedstat_enabled())
+- return;
+-
+- stats = __schedstats_from_dl_se(dl_se);
+- __update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
++ struct sched_statistics *stats = __schedstats_from_dl_se(dl_se);
++ if (stats)
++ __update_stats_enqueue_sleeper(rq_of_dl_rq(dl_rq), dl_task_of(dl_se), stats);
+ }
+
+ static inline void
+diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
+index 483c137b9d3d7e..5e4162d02afc15 100644
+--- a/kernel/sched/fair.c
++++ b/kernel/sched/fair.c
+@@ -511,7 +511,7 @@ static int cfs_rq_is_idle(struct cfs_rq *cfs_rq)
+
+ static int se_is_idle(struct sched_entity *se)
+ {
+- return 0;
++ return task_has_idle_policy(task_of(se));
+ }
+
+ #endif /* CONFIG_FAIR_GROUP_SCHED */
+@@ -3188,6 +3188,15 @@ static bool vma_is_accessed(struct mm_struct *mm, struct vm_area_struct *vma)
+ return true;
+ }
+
++ /*
++ * This vma has not been accessed for a while, and if the number
++ * the threads in the same process is low, which means no other
++ * threads can help scan this vma, force a vma scan.
++ */
++ if (READ_ONCE(mm->numa_scan_seq) >
++ (vma->numab_state->prev_scan_seq + get_nr_threads(current)))
++ return true;
++
+ return false;
+ }
+
+@@ -8381,16 +8390,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
+ if (test_tsk_need_resched(curr))
+ return;
+
+- /* Idle tasks are by definition preempted by non-idle tasks. */
+- if (unlikely(task_has_idle_policy(curr)) &&
+- likely(!task_has_idle_policy(p)))
+- goto preempt;
+-
+- /*
+- * Batch and idle tasks do not preempt non-idle tasks (their preemption
+- * is driven by the tick):
+- */
+- if (unlikely(p->policy != SCHED_NORMAL) || !sched_feat(WAKEUP_PREEMPTION))
++ if (!sched_feat(WAKEUP_PREEMPTION))
+ return;
+
+ find_matching_se(&se, &pse);
+@@ -8400,7 +8400,7 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
+ pse_is_idle = se_is_idle(pse);
+
+ /*
+- * Preempt an idle group in favor of a non-idle group (and don't preempt
++ * Preempt an idle entity in favor of a non-idle entity (and don't preempt
+ * in the inverse case).
+ */
+ if (cse_is_idle && !pse_is_idle)
+@@ -8408,9 +8408,14 @@ static void check_preempt_wakeup_fair(struct rq *rq, struct task_struct *p, int
+ if (cse_is_idle != pse_is_idle)
+ return;
+
++ /*
++ * BATCH and IDLE tasks do not preempt others.
++ */
++ if (unlikely(p->policy != SCHED_NORMAL))
++ return;
++
+ cfs_rq = cfs_rq_of(se);
+ update_curr(cfs_rq);
+-
+ /*
+ * XXX pick_eevdf(cfs_rq) != se ?
+ */
+@@ -9360,9 +9365,10 @@ static bool __update_blocked_others(struct rq *rq, bool *done)
+
+ hw_pressure = arch_scale_hw_pressure(cpu_of(rq));
+
++ /* hw_pressure doesn't care about invariance */
+ decayed = update_rt_rq_load_avg(now, rq, curr_class == &rt_sched_class) |
+ update_dl_rq_load_avg(now, rq, curr_class == &dl_sched_class) |
+- update_hw_load_avg(now, rq, hw_pressure) |
++ update_hw_load_avg(rq_clock_task(rq), rq, hw_pressure) |
+ update_irq_load_avg(rq, 0);
+
+ if (others_have_blocked(rq))
+diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
+index d1daeab1bbc141..433be6bc8b7786 100644
+--- a/kernel/trace/bpf_trace.c
++++ b/kernel/trace/bpf_trace.c
+@@ -1226,7 +1226,8 @@ static const struct bpf_func_proto bpf_get_func_arg_proto = {
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+- .arg3_type = ARG_PTR_TO_LONG,
++ .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
++ .arg3_size = sizeof(u64),
+ };
+
+ BPF_CALL_2(get_func_ret, void *, ctx, u64 *, value)
+@@ -1242,7 +1243,8 @@ static const struct bpf_func_proto bpf_get_func_ret_proto = {
+ .func = get_func_ret,
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+- .arg2_type = ARG_PTR_TO_LONG,
++ .arg2_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
++ .arg2_size = sizeof(u64),
+ };
+
+ BPF_CALL_1(get_func_arg_cnt, void *, ctx)
+@@ -3482,17 +3484,20 @@ int bpf_uprobe_multi_link_attach(const union bpf_attr *attr, struct bpf_prog *pr
+ uprobes[i].ref_ctr_offset,
+ &uprobes[i].consumer);
+ if (err) {
+- bpf_uprobe_unregister(&path, uprobes, i);
+- goto error_free;
++ link->cnt = i;
++ goto error_unregister;
+ }
+ }
+
+ err = bpf_link_prime(&link->link, &link_primer);
+ if (err)
+- goto error_free;
++ goto error_unregister;
+
+ return bpf_link_settle(&link_primer);
+
++error_unregister:
++ bpf_uprobe_unregister(&path, uprobes, link->cnt);
++
+ error_free:
+ kvfree(uprobes);
+ kfree(link);
+diff --git a/lib/debugobjects.c b/lib/debugobjects.c
+index 7cea91e193a8f0..1ea8af72849cdb 100644
+--- a/lib/debugobjects.c
++++ b/lib/debugobjects.c
+@@ -142,13 +142,14 @@ static void fill_pool(void)
+ * READ_ONCE()s pair with the WRITE_ONCE()s in pool_lock critical
+ * sections.
+ */
+- while (READ_ONCE(obj_nr_tofree) && (READ_ONCE(obj_pool_free) < obj_pool_min_free)) {
++ while (READ_ONCE(obj_nr_tofree) &&
++ READ_ONCE(obj_pool_free) < debug_objects_pool_min_level) {
+ raw_spin_lock_irqsave(&pool_lock, flags);
+ /*
+ * Recheck with the lock held as the worker thread might have
+ * won the race and freed the global free list already.
+ */
+- while (obj_nr_tofree && (obj_pool_free < obj_pool_min_free)) {
++ while (obj_nr_tofree && (obj_pool_free < debug_objects_pool_min_level)) {
+ obj = hlist_entry(obj_to_free.first, typeof(*obj), node);
+ hlist_del(&obj->node);
+ WRITE_ONCE(obj_nr_tofree, obj_nr_tofree - 1);
+diff --git a/lib/sbitmap.c b/lib/sbitmap.c
+index 5e2e93307f0d05..d3412984170c03 100644
+--- a/lib/sbitmap.c
++++ b/lib/sbitmap.c
+@@ -65,7 +65,7 @@ static inline bool sbitmap_deferred_clear(struct sbitmap_word *map,
+ {
+ unsigned long mask, word_mask;
+
+- guard(spinlock_irqsave)(&map->swap_lock);
++ guard(raw_spinlock_irqsave)(&map->swap_lock);
+
+ if (!map->cleared) {
+ if (depth == 0)
+@@ -136,7 +136,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
+ }
+
+ for (i = 0; i < sb->map_nr; i++)
+- spin_lock_init(&sb->map[i].swap_lock);
++ raw_spin_lock_init(&sb->map[i].swap_lock);
+
+ return 0;
+ }
+diff --git a/lib/xz/xz_crc32.c b/lib/xz/xz_crc32.c
+index 88a2c35e1b5971..5627b00fca296e 100644
+--- a/lib/xz/xz_crc32.c
++++ b/lib/xz/xz_crc32.c
+@@ -29,7 +29,7 @@ STATIC_RW_DATA uint32_t xz_crc32_table[256];
+
+ XZ_EXTERN void xz_crc32_init(void)
+ {
+- const uint32_t poly = CRC32_POLY_LE;
++ const uint32_t poly = 0xEDB88320;
+
+ uint32_t i;
+ uint32_t j;
+diff --git a/lib/xz/xz_private.h b/lib/xz/xz_private.h
+index bf1e94ec7873cf..d9fd49b45fd758 100644
+--- a/lib/xz/xz_private.h
++++ b/lib/xz/xz_private.h
+@@ -105,10 +105,6 @@
+ # endif
+ #endif
+
+-#ifndef CRC32_POLY_LE
+-#define CRC32_POLY_LE 0xedb88320
+-#endif
+-
+ /*
+ * Allocate memory for LZMA2 decoder. xz_dec_lzma2_reset() must be used
+ * before calling xz_dec_lzma2_run().
+diff --git a/mm/damon/vaddr.c b/mm/damon/vaddr.c
+index 381559e4a1faba..26877b290de63a 100644
+--- a/mm/damon/vaddr.c
++++ b/mm/damon/vaddr.c
+@@ -126,6 +126,7 @@ static int __damon_va_three_regions(struct mm_struct *mm,
+ * If this is too slow, it can be optimised to examine the maple
+ * tree gaps.
+ */
++ rcu_read_lock();
+ for_each_vma(vmi, vma) {
+ unsigned long gap;
+
+@@ -146,6 +147,7 @@ static int __damon_va_three_regions(struct mm_struct *mm,
+ next:
+ prev = vma;
+ }
++ rcu_read_unlock();
+
+ if (!sz_range(&second_gap) || !sz_range(&first_gap))
+ return -EINVAL;
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 4d9c1277e5e4d1..cedc93028894c6 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -214,6 +214,8 @@ static bool get_huge_zero_page(void)
+ count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED);
+ return false;
+ }
++ /* Ensure zero folio won't have large_rmappable flag set. */
++ folio_clear_large_rmappable(zero_folio);
+ preempt_disable();
+ if (cmpxchg(&huge_zero_folio, NULL, zero_folio)) {
+ preempt_enable();
+diff --git a/mm/hugetlb.c b/mm/hugetlb.c
+index 92a2e8dcb79655..423d20453b90c9 100644
+--- a/mm/hugetlb.c
++++ b/mm/hugetlb.c
+@@ -3919,100 +3919,124 @@ static int set_max_huge_pages(struct hstate *h, unsigned long count, int nid,
+ return 0;
+ }
+
+-static int demote_free_hugetlb_folio(struct hstate *h, struct folio *folio)
++static long demote_free_hugetlb_folios(struct hstate *src, struct hstate *dst,
++ struct list_head *src_list)
+ {
+- int i, nid = folio_nid(folio);
+- struct hstate *target_hstate;
+- struct page *subpage;
+- struct folio *inner_folio;
+- int rc = 0;
+-
+- target_hstate = size_to_hstate(PAGE_SIZE << h->demote_order);
++ long rc;
++ struct folio *folio, *next;
++ LIST_HEAD(dst_list);
++ LIST_HEAD(ret_list);
+
+- remove_hugetlb_folio(h, folio, false);
+- spin_unlock_irq(&hugetlb_lock);
+-
+- /*
+- * If vmemmap already existed for folio, the remove routine above would
+- * have cleared the hugetlb folio flag. Hence the folio is technically
+- * no longer a hugetlb folio. hugetlb_vmemmap_restore_folio can only be
+- * passed hugetlb folios and will BUG otherwise.
+- */
+- if (folio_test_hugetlb(folio)) {
+- rc = hugetlb_vmemmap_restore_folio(h, folio);
+- if (rc) {
+- /* Allocation of vmemmmap failed, we can not demote folio */
+- spin_lock_irq(&hugetlb_lock);
+- add_hugetlb_folio(h, folio, false);
+- return rc;
+- }
+- }
+-
+- /*
+- * Use destroy_compound_hugetlb_folio_for_demote for all huge page
+- * sizes as it will not ref count folios.
+- */
+- destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(h));
++ rc = hugetlb_vmemmap_restore_folios(src, src_list, &ret_list);
++ list_splice_init(&ret_list, src_list);
+
+ /*
+ * Taking target hstate mutex synchronizes with set_max_huge_pages.
+ * Without the mutex, pages added to target hstate could be marked
+ * as surplus.
+ *
+- * Note that we already hold h->resize_lock. To prevent deadlock,
++ * Note that we already hold src->resize_lock. To prevent deadlock,
+ * use the convention of always taking larger size hstate mutex first.
+ */
+- mutex_lock(&target_hstate->resize_lock);
+- for (i = 0; i < pages_per_huge_page(h);
+- i += pages_per_huge_page(target_hstate)) {
+- subpage = folio_page(folio, i);
+- inner_folio = page_folio(subpage);
+- if (hstate_is_gigantic(target_hstate))
+- prep_compound_gigantic_folio_for_demote(inner_folio,
+- target_hstate->order);
+- else
+- prep_compound_page(subpage, target_hstate->order);
+- folio_change_private(inner_folio, NULL);
+- prep_new_hugetlb_folio(target_hstate, inner_folio, nid);
+- free_huge_folio(inner_folio);
++ mutex_lock(&dst->resize_lock);
++
++ list_for_each_entry_safe(folio, next, src_list, lru) {
++ int i;
++
++ if (folio_test_hugetlb_vmemmap_optimized(folio))
++ continue;
++
++ list_del(&folio->lru);
++ /*
++ * Use destroy_compound_hugetlb_folio_for_demote for all huge page
++ * sizes as it will not ref count folios.
++ */
++ destroy_compound_hugetlb_folio_for_demote(folio, huge_page_order(src));
++
++ for (i = 0; i < pages_per_huge_page(src); i += pages_per_huge_page(dst)) {
++ struct page *page = folio_page(folio, i);
++
++ if (hstate_is_gigantic(dst))
++ prep_compound_gigantic_folio_for_demote(page_folio(page),
++ dst->order);
++ else
++ prep_compound_page(page, dst->order);
++ set_page_private(page, 0);
++
++ init_new_hugetlb_folio(dst, page_folio(page));
++ list_add(&page->lru, &dst_list);
++ }
+ }
+- mutex_unlock(&target_hstate->resize_lock);
+
+- spin_lock_irq(&hugetlb_lock);
++ prep_and_add_allocated_folios(dst, &dst_list);
+
+- /*
+- * Not absolutely necessary, but for consistency update max_huge_pages
+- * based on pool changes for the demoted page.
+- */
+- h->max_huge_pages--;
+- target_hstate->max_huge_pages +=
+- pages_per_huge_page(h) / pages_per_huge_page(target_hstate);
++ mutex_unlock(&dst->resize_lock);
+
+ return rc;
+ }
+
+-static int demote_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed)
++static long demote_pool_huge_page(struct hstate *src, nodemask_t *nodes_allowed,
++ unsigned long nr_to_demote)
+ __must_hold(&hugetlb_lock)
+ {
+ int nr_nodes, node;
+- struct folio *folio;
++ struct hstate *dst;
++ long rc = 0;
++ long nr_demoted = 0;
+
+ lockdep_assert_held(&hugetlb_lock);
+
+ /* We should never get here if no demote order */
+- if (!h->demote_order) {
++ if (!src->demote_order) {
+ pr_warn("HugeTLB: NULL demote order passed to demote_pool_huge_page.\n");
+ return -EINVAL; /* internal error */
+ }
++ dst = size_to_hstate(PAGE_SIZE << src->demote_order);
+
+- for_each_node_mask_to_free(h, nr_nodes, node, nodes_allowed) {
+- list_for_each_entry(folio, &h->hugepage_freelists[node], lru) {
++ for_each_node_mask_to_free(src, nr_nodes, node, nodes_allowed) {
++ LIST_HEAD(list);
++ struct folio *folio, *next;
++
++ list_for_each_entry_safe(folio, next, &src->hugepage_freelists[node], lru) {
+ if (folio_test_hwpoison(folio))
+ continue;
+- return demote_free_hugetlb_folio(h, folio);
++
++ remove_hugetlb_folio(src, folio, false);
++ list_add(&folio->lru, &list);
++
++ if (++nr_demoted == nr_to_demote)
++ break;
+ }
++
++ spin_unlock_irq(&hugetlb_lock);
++
++ rc = demote_free_hugetlb_folios(src, dst, &list);
++
++ spin_lock_irq(&hugetlb_lock);
++
++ list_for_each_entry_safe(folio, next, &list, lru) {
++ list_del(&folio->lru);
++ add_hugetlb_folio(src, folio, false);
++
++ nr_demoted--;
++ }
++
++ if (rc < 0 || nr_demoted == nr_to_demote)
++ break;
+ }
+
++ /*
++ * Not absolutely necessary, but for consistency update max_huge_pages
++ * based on pool changes for the demoted page.
++ */
++ src->max_huge_pages -= nr_demoted;
++ dst->max_huge_pages += nr_demoted << (huge_page_order(src) - huge_page_order(dst));
++
++ if (rc < 0)
++ return rc;
++
++ if (nr_demoted)
++ return nr_demoted;
+ /*
+ * Only way to get here is if all pages on free lists are poisoned.
+ * Return -EBUSY so that caller will not retry.
+@@ -4247,6 +4271,8 @@ static ssize_t demote_store(struct kobject *kobj,
+ spin_lock_irq(&hugetlb_lock);
+
+ while (nr_demote) {
++ long rc;
++
+ /*
+ * Check for available pages to demote each time thorough the
+ * loop as demote_pool_huge_page will drop hugetlb_lock.
+@@ -4259,11 +4285,13 @@ static ssize_t demote_store(struct kobject *kobj,
+ if (!nr_available)
+ break;
+
+- err = demote_pool_huge_page(h, n_mask);
+- if (err)
++ rc = demote_pool_huge_page(h, n_mask, nr_demote);
++ if (rc < 0) {
++ err = rc;
+ break;
++ }
+
+- nr_demote--;
++ nr_demote -= rc;
+ }
+
+ spin_unlock_irq(&hugetlb_lock);
+@@ -6047,7 +6075,7 @@ static vm_fault_t hugetlb_wp(struct folio *pagecache_folio,
+ * When the original hugepage is shared one, it does not have
+ * anon_vma prepared.
+ */
+- ret = vmf_anon_prepare(vmf);
++ ret = __vmf_anon_prepare(vmf);
+ if (unlikely(ret))
+ goto out_release_all;
+
+@@ -6246,7 +6274,7 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping,
+ }
+
+ if (!(vma->vm_flags & VM_MAYSHARE)) {
+- ret = vmf_anon_prepare(vmf);
++ ret = __vmf_anon_prepare(vmf);
+ if (unlikely(ret))
+ goto out;
+ }
+@@ -6378,6 +6406,14 @@ static vm_fault_t hugetlb_no_page(struct address_space *mapping,
+ folio_unlock(folio);
+ out:
+ hugetlb_vma_unlock_read(vma);
++
++ /*
++ * We must check to release the per-VMA lock. __vmf_anon_prepare() is
++ * the only way ret can be set to VM_FAULT_RETRY.
++ */
++ if (unlikely(ret & VM_FAULT_RETRY))
++ vma_end_read(vma);
++
+ mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ return ret;
+
+@@ -6599,6 +6635,14 @@ vm_fault_t hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma,
+ }
+ out_mutex:
+ hugetlb_vma_unlock_read(vma);
++
++ /*
++ * We must check to release the per-VMA lock. __vmf_anon_prepare() in
++ * hugetlb_wp() is the only way ret can be set to VM_FAULT_RETRY.
++ */
++ if (unlikely(ret & VM_FAULT_RETRY))
++ vma_end_read(vma);
++
+ mutex_unlock(&hugetlb_fault_mutex_table[hash]);
+ /*
+ * Generally it's safe to hold refcount during waiting page lock. But
+diff --git a/mm/internal.h b/mm/internal.h
+index cc2c5e07fad3ba..6ef5eecabfc4f9 100644
+--- a/mm/internal.h
++++ b/mm/internal.h
+@@ -293,7 +293,16 @@ static inline void wake_throttle_isolated(pg_data_t *pgdat)
+ wake_up(wqh);
+ }
+
+-vm_fault_t vmf_anon_prepare(struct vm_fault *vmf);
++vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf);
++static inline vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
++{
++ vm_fault_t ret = __vmf_anon_prepare(vmf);
++
++ if (unlikely(ret & VM_FAULT_RETRY))
++ vma_end_read(vmf->vma);
++ return ret;
++}
++
+ vm_fault_t do_swap_page(struct vm_fault *vmf);
+ void folio_rotate_reclaimable(struct folio *folio);
+ bool __folio_end_writeback(struct folio *folio);
+diff --git a/mm/memory.c b/mm/memory.c
+index 7a898b85788dd9..cfc4df9fe99544 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -3226,7 +3226,7 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf)
+ }
+
+ /**
+- * vmf_anon_prepare - Prepare to handle an anonymous fault.
++ * __vmf_anon_prepare - Prepare to handle an anonymous fault.
+ * @vmf: The vm_fault descriptor passed from the fault handler.
+ *
+ * When preparing to insert an anonymous page into a VMA from a
+@@ -3240,7 +3240,7 @@ static inline vm_fault_t vmf_can_call_fault(const struct vm_fault *vmf)
+ * Return: 0 if fault handling can proceed. Any other value should be
+ * returned to the caller.
+ */
+-vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
++vm_fault_t __vmf_anon_prepare(struct vm_fault *vmf)
+ {
+ struct vm_area_struct *vma = vmf->vma;
+ vm_fault_t ret = 0;
+@@ -3248,10 +3248,8 @@ vm_fault_t vmf_anon_prepare(struct vm_fault *vmf)
+ if (likely(vma->anon_vma))
+ return 0;
+ if (vmf->flags & FAULT_FLAG_VMA_LOCK) {
+- if (!mmap_read_trylock(vma->vm_mm)) {
+- vma_end_read(vma);
++ if (!mmap_read_trylock(vma->vm_mm))
+ return VM_FAULT_RETRY;
+- }
+ }
+ if (__anon_vma_prepare(vma))
+ ret = VM_FAULT_OOM;
+diff --git a/mm/migrate.c b/mm/migrate.c
+index 9dabeb90f772d8..817019be893653 100644
+--- a/mm/migrate.c
++++ b/mm/migrate.c
+@@ -1129,7 +1129,7 @@ static int migrate_folio_unmap(new_folio_t get_new_folio,
+ int rc = -EAGAIN;
+ int old_page_state = 0;
+ struct anon_vma *anon_vma = NULL;
+- bool is_lru = !__folio_test_movable(src);
++ bool is_lru = data_race(!__folio_test_movable(src));
+ bool locked = false;
+ bool dst_locked = false;
+
+diff --git a/mm/mmap.c b/mm/mmap.c
+index 83b4682ec85cfa..47bd6f65f44139 100644
+--- a/mm/mmap.c
++++ b/mm/mmap.c
+@@ -3127,8 +3127,12 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size,
+ flags |= MAP_LOCKED;
+
+ file = get_file(vma->vm_file);
++ ret = security_mmap_file(vma->vm_file, prot, flags);
++ if (ret)
++ goto out_fput;
+ ret = do_mmap(vma->vm_file, start, size,
+ prot, flags, 0, pgoff, &populate, NULL);
++out_fput:
+ fput(file);
+ out:
+ mmap_write_unlock(mm);
+diff --git a/mm/util.c b/mm/util.c
+index fe723241b66f73..37a5d75f8adf05 100644
+--- a/mm/util.c
++++ b/mm/util.c
+@@ -451,7 +451,7 @@ static unsigned long mmap_base(unsigned long rnd, struct rlimit *rlim_stack)
+ if (gap + pad > gap)
+ gap += pad;
+
+- if (gap < MIN_GAP)
++ if (gap < MIN_GAP && MIN_GAP < MAX_GAP)
+ gap = MIN_GAP;
+ else if (gap > MAX_GAP)
+ gap = MAX_GAP;
+diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
+index 3c74d171085deb..bfa773730f3bd7 100644
+--- a/net/bluetooth/hci_conn.c
++++ b/net/bluetooth/hci_conn.c
+@@ -107,8 +107,7 @@ void hci_connect_le_scan_cleanup(struct hci_conn *conn, u8 status)
+ * where a timeout + cancel does indicate an actual failure.
+ */
+ if (status && status != HCI_ERROR_UNKNOWN_CONN_ID)
+- mgmt_connect_failed(hdev, &conn->dst, conn->type,
+- conn->dst_type, status);
++ mgmt_connect_failed(hdev, conn, status);
+
+ /* The connection attempt was doing scan for new RPA, and is
+ * in scan phase. If params are not associated with any other
+@@ -1251,8 +1250,7 @@ void hci_conn_failed(struct hci_conn *conn, u8 status)
+ hci_le_conn_failed(conn, status);
+ break;
+ case ACL_LINK:
+- mgmt_connect_failed(hdev, &conn->dst, conn->type,
+- conn->dst_type, status);
++ mgmt_connect_failed(hdev, conn, status);
+ break;
+ }
+
+diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
+index f4a54dbc07f19a..86fee9d6c14248 100644
+--- a/net/bluetooth/hci_sync.c
++++ b/net/bluetooth/hci_sync.c
+@@ -5331,7 +5331,10 @@ int hci_stop_discovery_sync(struct hci_dev *hdev)
+ if (!e)
+ return 0;
+
+- return hci_remote_name_cancel_sync(hdev, &e->data.bdaddr);
++ /* Ignore cancel errors since it should interfere with stopping
++ * of the discovery.
++ */
++ hci_remote_name_cancel_sync(hdev, &e->data.bdaddr);
+ }
+
+ return 0;
+diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
+index ba28907afb3fa6..c383eb44d516bc 100644
+--- a/net/bluetooth/mgmt.c
++++ b/net/bluetooth/mgmt.c
+@@ -9734,13 +9734,18 @@ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ mgmt_pending_remove(cmd);
+ }
+
+-void mgmt_connect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr, u8 link_type,
+- u8 addr_type, u8 status)
++void mgmt_connect_failed(struct hci_dev *hdev, struct hci_conn *conn, u8 status)
+ {
+ struct mgmt_ev_connect_failed ev;
+
+- bacpy(&ev.addr.bdaddr, bdaddr);
+- ev.addr.type = link_to_bdaddr(link_type, addr_type);
++ if (test_and_clear_bit(HCI_CONN_MGMT_CONNECTED, &conn->flags)) {
++ mgmt_device_disconnected(hdev, &conn->dst, conn->type,
++ conn->dst_type, status, true);
++ return;
++ }
++
++ bacpy(&ev.addr.bdaddr, &conn->dst);
++ ev.addr.type = link_to_bdaddr(conn->type, conn->dst_type);
+ ev.status = mgmt_status(status);
+
+ mgmt_event(MGMT_EV_CONNECT_FAILED, hdev, &ev, sizeof(ev), NULL);
+diff --git a/net/can/bcm.c b/net/can/bcm.c
+index 46d3ec3aa44b4a..217049fa496e9d 100644
+--- a/net/can/bcm.c
++++ b/net/can/bcm.c
+@@ -1471,8 +1471,10 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
+ /* remove device reference, if this is our bound device */
+ if (bo->bound && bo->ifindex == dev->ifindex) {
+ #if IS_ENABLED(CONFIG_PROC_FS)
+- if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read)
++ if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read) {
+ remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir);
++ bo->bcm_proc_read = NULL;
++ }
+ #endif
+ bo->bound = 0;
+ bo->ifindex = 0;
+diff --git a/net/can/j1939/transport.c b/net/can/j1939/transport.c
+index 4be73de5033cb7..319f47df33300c 100644
+--- a/net/can/j1939/transport.c
++++ b/net/can/j1939/transport.c
+@@ -1179,10 +1179,10 @@ static enum hrtimer_restart j1939_tp_txtimer(struct hrtimer *hrtimer)
+ break;
+ case -ENETDOWN:
+ /* In this case we should get a netdev_event(), all active
+- * sessions will be cleared by
+- * j1939_cancel_all_active_sessions(). So handle this as an
+- * error, but let j1939_cancel_all_active_sessions() do the
+- * cleanup including propagation of the error to user space.
++ * sessions will be cleared by j1939_cancel_active_session().
++ * So handle this as an error, but let
++ * j1939_cancel_active_session() do the cleanup including
++ * propagation of the error to user space.
+ */
+ break;
+ case -EOVERFLOW:
+diff --git a/net/core/filter.c b/net/core/filter.c
+index 55b1d9de2334db..61da5512cd4d2a 100644
+--- a/net/core/filter.c
++++ b/net/core/filter.c
+@@ -6258,20 +6258,25 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
+ int ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+ struct net_device *dev = skb->dev;
+ int skb_len, dev_len;
+- int mtu;
++ int mtu = 0;
+
+- if (unlikely(flags & ~(BPF_MTU_CHK_SEGS)))
+- return -EINVAL;
++ if (unlikely(flags & ~(BPF_MTU_CHK_SEGS))) {
++ ret = -EINVAL;
++ goto out;
++ }
+
+- if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len)))
+- return -EINVAL;
++ if (unlikely(flags & BPF_MTU_CHK_SEGS && (len_diff || *mtu_len))) {
++ ret = -EINVAL;
++ goto out;
++ }
+
+ dev = __dev_via_ifindex(dev, ifindex);
+- if (unlikely(!dev))
+- return -ENODEV;
++ if (unlikely(!dev)) {
++ ret = -ENODEV;
++ goto out;
++ }
+
+ mtu = READ_ONCE(dev->mtu);
+-
+ dev_len = mtu + dev->hard_header_len;
+
+ /* If set use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+@@ -6289,15 +6294,12 @@ BPF_CALL_5(bpf_skb_check_mtu, struct sk_buff *, skb,
+ */
+ if (skb_is_gso(skb)) {
+ ret = BPF_MTU_CHK_RET_SUCCESS;
+-
+ if (flags & BPF_MTU_CHK_SEGS &&
+ !skb_gso_validate_network_len(skb, mtu))
+ ret = BPF_MTU_CHK_RET_SEGS_TOOBIG;
+ }
+ out:
+- /* BPF verifier guarantees valid pointer */
+ *mtu_len = mtu;
+-
+ return ret;
+ }
+
+@@ -6307,19 +6309,21 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
+ struct net_device *dev = xdp->rxq->dev;
+ int xdp_len = xdp->data_end - xdp->data;
+ int ret = BPF_MTU_CHK_RET_SUCCESS;
+- int mtu, dev_len;
++ int mtu = 0, dev_len;
+
+ /* XDP variant doesn't support multi-buffer segment check (yet) */
+- if (unlikely(flags))
+- return -EINVAL;
++ if (unlikely(flags)) {
++ ret = -EINVAL;
++ goto out;
++ }
+
+ dev = __dev_via_ifindex(dev, ifindex);
+- if (unlikely(!dev))
+- return -ENODEV;
++ if (unlikely(!dev)) {
++ ret = -ENODEV;
++ goto out;
++ }
+
+ mtu = READ_ONCE(dev->mtu);
+-
+- /* Add L2-header as dev MTU is L3 size */
+ dev_len = mtu + dev->hard_header_len;
+
+ /* Use *mtu_len as input, L3 as iph->tot_len (like fib_lookup) */
+@@ -6329,10 +6333,8 @@ BPF_CALL_5(bpf_xdp_check_mtu, struct xdp_buff *, xdp,
+ xdp_len += len_diff; /* minus result pass check */
+ if (xdp_len > dev_len)
+ ret = BPF_MTU_CHK_RET_FRAG_NEEDED;
+-
+- /* BPF verifier guarantees valid pointer */
++out:
+ *mtu_len = mtu;
+-
+ return ret;
+ }
+
+@@ -6342,7 +6344,8 @@ static const struct bpf_func_proto bpf_skb_check_mtu_proto = {
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+- .arg3_type = ARG_PTR_TO_INT,
++ .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
++ .arg3_size = sizeof(u32),
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+ };
+@@ -6353,7 +6356,8 @@ static const struct bpf_func_proto bpf_xdp_check_mtu_proto = {
+ .ret_type = RET_INTEGER,
+ .arg1_type = ARG_PTR_TO_CTX,
+ .arg2_type = ARG_ANYTHING,
+- .arg3_type = ARG_PTR_TO_INT,
++ .arg3_type = ARG_PTR_TO_FIXED_SIZE_MEM | MEM_UNINIT | MEM_ALIGNED,
++ .arg3_size = sizeof(u32),
+ .arg4_type = ARG_ANYTHING,
+ .arg5_type = ARG_ANYTHING,
+ };
+@@ -8568,13 +8572,16 @@ static bool bpf_skb_is_valid_access(int off, int size, enum bpf_access_type type
+ if (off + size > offsetofend(struct __sk_buff, cb[4]))
+ return false;
+ break;
++ case bpf_ctx_range(struct __sk_buff, data):
++ case bpf_ctx_range(struct __sk_buff, data_meta):
++ case bpf_ctx_range(struct __sk_buff, data_end):
++ if (info->is_ldsx || size != size_default)
++ return false;
++ break;
+ case bpf_ctx_range_till(struct __sk_buff, remote_ip6[0], remote_ip6[3]):
+ case bpf_ctx_range_till(struct __sk_buff, local_ip6[0], local_ip6[3]):
+ case bpf_ctx_range_till(struct __sk_buff, remote_ip4, remote_ip4):
+ case bpf_ctx_range_till(struct __sk_buff, local_ip4, local_ip4):
+- case bpf_ctx_range(struct __sk_buff, data):
+- case bpf_ctx_range(struct __sk_buff, data_meta):
+- case bpf_ctx_range(struct __sk_buff, data_end):
+ if (size != size_default)
+ return false;
+ break;
+@@ -9018,6 +9025,14 @@ static bool xdp_is_valid_access(int off, int size,
+ }
+ }
+ return false;
++ } else {
++ switch (off) {
++ case offsetof(struct xdp_md, data_meta):
++ case offsetof(struct xdp_md, data):
++ case offsetof(struct xdp_md, data_end):
++ if (info->is_ldsx)
++ return false;
++ }
+ }
+
+ switch (off) {
+@@ -9343,12 +9358,12 @@ static bool flow_dissector_is_valid_access(int off, int size,
+
+ switch (off) {
+ case bpf_ctx_range(struct __sk_buff, data):
+- if (size != size_default)
++ if (info->is_ldsx || size != size_default)
+ return false;
+ info->reg_type = PTR_TO_PACKET;
+ return true;
+ case bpf_ctx_range(struct __sk_buff, data_end):
+- if (size != size_default)
++ if (info->is_ldsx || size != size_default)
+ return false;
+ info->reg_type = PTR_TO_PACKET_END;
+ return true;
+diff --git a/net/core/sock_map.c b/net/core/sock_map.c
+index d3dbb92153f2fe..724b6856fcc3e9 100644
+--- a/net/core/sock_map.c
++++ b/net/core/sock_map.c
+@@ -1183,6 +1183,7 @@ static void sock_hash_free(struct bpf_map *map)
+ sock_put(elem->sk);
+ sock_hash_free_elem(htab, elem);
+ }
++ cond_resched();
+ }
+
+ /* wait for psock readers accessing its map link */
+diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c
+index af6cf64a00e081..464f683e016dbb 100644
+--- a/net/hsr/hsr_slave.c
++++ b/net/hsr/hsr_slave.c
+@@ -67,7 +67,16 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb)
+ skb_set_network_header(skb, ETH_HLEN + HSR_HLEN);
+ skb_reset_mac_len(skb);
+
+- hsr_forward_skb(skb, port);
++ /* Only the frames received over the interlink port will assign a
++ * sequence number and require synchronisation vs other sender.
++ */
++ if (port->type == HSR_PT_INTERLINK) {
++ spin_lock_bh(&hsr->seqnr_lock);
++ hsr_forward_skb(skb, port);
++ spin_unlock_bh(&hsr->seqnr_lock);
++ } else {
++ hsr_forward_skb(skb, port);
++ }
+
+ finish_consume:
+ return RX_HANDLER_CONSUMED;
+diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c
+index ab6d0d98dbc34c..336518e623b280 100644
+--- a/net/ipv4/icmp.c
++++ b/net/ipv4/icmp.c
+@@ -224,57 +224,59 @@ int sysctl_icmp_msgs_per_sec __read_mostly = 1000;
+ int sysctl_icmp_msgs_burst __read_mostly = 50;
+
+ static struct {
+- spinlock_t lock;
+- u32 credit;
++ atomic_t credit;
+ u32 stamp;
+-} icmp_global = {
+- .lock = __SPIN_LOCK_UNLOCKED(icmp_global.lock),
+-};
++} icmp_global;
+
+ /**
+ * icmp_global_allow - Are we allowed to send one more ICMP message ?
+ *
+ * Uses a token bucket to limit our ICMP messages to ~sysctl_icmp_msgs_per_sec.
+ * Returns false if we reached the limit and can not send another packet.
+- * Note: called with BH disabled
++ * Works in tandem with icmp_global_consume().
+ */
+ bool icmp_global_allow(void)
+ {
+- u32 credit, delta, incr = 0, now = (u32)jiffies;
+- bool rc = false;
++ u32 delta, now, oldstamp;
++ int incr, new, old;
+
+- /* Check if token bucket is empty and cannot be refilled
+- * without taking the spinlock. The READ_ONCE() are paired
+- * with the following WRITE_ONCE() in this same function.
++ /* Note: many cpus could find this condition true.
++ * Then later icmp_global_consume() could consume more credits,
++ * this is an acceptable race.
+ */
+- if (!READ_ONCE(icmp_global.credit)) {
+- delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ);
+- if (delta < HZ / 50)
+- return false;
+- }
++ if (atomic_read(&icmp_global.credit) > 0)
++ return true;
+
+- spin_lock(&icmp_global.lock);
+- delta = min_t(u32, now - icmp_global.stamp, HZ);
+- if (delta >= HZ / 50) {
+- incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
+- if (incr)
+- WRITE_ONCE(icmp_global.stamp, now);
+- }
+- credit = min_t(u32, icmp_global.credit + incr,
+- READ_ONCE(sysctl_icmp_msgs_burst));
+- if (credit) {
+- /* We want to use a credit of one in average, but need to randomize
+- * it for security reasons.
+- */
+- credit = max_t(int, credit - get_random_u32_below(3), 0);
+- rc = true;
++ now = jiffies;
++ oldstamp = READ_ONCE(icmp_global.stamp);
++ delta = min_t(u32, now - oldstamp, HZ);
++ if (delta < HZ / 50)
++ return false;
++
++ incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ;
++ if (!incr)
++ return false;
++
++ if (cmpxchg(&icmp_global.stamp, oldstamp, now) == oldstamp) {
++ old = atomic_read(&icmp_global.credit);
++ do {
++ new = min(old + incr, READ_ONCE(sysctl_icmp_msgs_burst));
++ } while (!atomic_try_cmpxchg(&icmp_global.credit, &old, new));
+ }
+- WRITE_ONCE(icmp_global.credit, credit);
+- spin_unlock(&icmp_global.lock);
+- return rc;
++ return true;
+ }
+ EXPORT_SYMBOL(icmp_global_allow);
+
++void icmp_global_consume(void)
++{
++ int credits = get_random_u32_below(3);
++
++ /* Note: this might make icmp_global.credit negative. */
++ if (credits)
++ atomic_sub(credits, &icmp_global.credit);
++}
++EXPORT_SYMBOL(icmp_global_consume);
++
+ static bool icmpv4_mask_allow(struct net *net, int type, int code)
+ {
+ if (type > NR_ICMP_TYPES)
+@@ -291,14 +293,16 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code)
+ return false;
+ }
+
+-static bool icmpv4_global_allow(struct net *net, int type, int code)
++static bool icmpv4_global_allow(struct net *net, int type, int code,
++ bool *apply_ratelimit)
+ {
+ if (icmpv4_mask_allow(net, type, code))
+ return true;
+
+- if (icmp_global_allow())
++ if (icmp_global_allow()) {
++ *apply_ratelimit = true;
+ return true;
+-
++ }
+ __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
+ return false;
+ }
+@@ -308,15 +312,16 @@ static bool icmpv4_global_allow(struct net *net, int type, int code)
+ */
+
+ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
+- struct flowi4 *fl4, int type, int code)
++ struct flowi4 *fl4, int type, int code,
++ bool apply_ratelimit)
+ {
+ struct dst_entry *dst = &rt->dst;
+ struct inet_peer *peer;
+ bool rc = true;
+ int vif;
+
+- if (icmpv4_mask_allow(net, type, code))
+- goto out;
++ if (!apply_ratelimit)
++ return true;
+
+ /* No rate limit on loopback */
+ if (dst->dev && (dst->dev->flags&IFF_LOOPBACK))
+@@ -331,6 +336,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt,
+ out:
+ if (!rc)
+ __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITHOST);
++ else
++ icmp_global_consume();
+ return rc;
+ }
+
+@@ -402,6 +409,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
+ struct ipcm_cookie ipc;
+ struct rtable *rt = skb_rtable(skb);
+ struct net *net = dev_net(rt->dst.dev);
++ bool apply_ratelimit = false;
+ struct flowi4 fl4;
+ struct sock *sk;
+ struct inet_sock *inet;
+@@ -413,11 +421,11 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
+ if (ip_options_echo(net, &icmp_param->replyopts.opt.opt, skb))
+ return;
+
+- /* Needed by both icmp_global_allow and icmp_xmit_lock */
++ /* Needed by both icmpv4_global_allow and icmp_xmit_lock */
+ local_bh_disable();
+
+- /* global icmp_msgs_per_sec */
+- if (!icmpv4_global_allow(net, type, code))
++ /* is global icmp_msgs_per_sec exhausted ? */
++ if (!icmpv4_global_allow(net, type, code, &apply_ratelimit))
+ goto out_bh_enable;
+
+ sk = icmp_xmit_lock(net);
+@@ -450,7 +458,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb)
+ rt = ip_route_output_key(net, &fl4);
+ if (IS_ERR(rt))
+ goto out_unlock;
+- if (icmpv4_xrlim_allow(net, rt, &fl4, type, code))
++ if (icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit))
+ icmp_push_reply(sk, icmp_param, &fl4, &ipc, &rt);
+ ip_rt_put(rt);
+ out_unlock:
+@@ -596,6 +604,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+ int room;
+ struct icmp_bxm icmp_param;
+ struct rtable *rt = skb_rtable(skb_in);
++ bool apply_ratelimit = false;
+ struct ipcm_cookie ipc;
+ struct flowi4 fl4;
+ __be32 saddr;
+@@ -677,7 +686,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+ }
+ }
+
+- /* Needed by both icmp_global_allow and icmp_xmit_lock */
++ /* Needed by both icmpv4_global_allow and icmp_xmit_lock */
+ local_bh_disable();
+
+ /* Check global sysctl_icmp_msgs_per_sec ratelimit, unless
+@@ -685,7 +694,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+ * loopback, then peer ratelimit still work (in icmpv4_xrlim_allow)
+ */
+ if (!(skb_in->dev && (skb_in->dev->flags&IFF_LOOPBACK)) &&
+- !icmpv4_global_allow(net, type, code))
++ !icmpv4_global_allow(net, type, code, &apply_ratelimit))
+ goto out_bh_enable;
+
+ sk = icmp_xmit_lock(net);
+@@ -744,7 +753,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info,
+ goto out_unlock;
+
+ /* peer icmp_ratelimit */
+- if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code))
++ if (!icmpv4_xrlim_allow(net, rt, &fl4, type, code, apply_ratelimit))
+ goto ende;
+
+ /* RFC says return as much as we can without exceeding 576 bytes. */
+diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
+index 08d4b7132d4c45..1c9c686d9522f7 100644
+--- a/net/ipv6/Kconfig
++++ b/net/ipv6/Kconfig
+@@ -323,6 +323,7 @@ config IPV6_RPL_LWTUNNEL
+ bool "IPv6: RPL Source Routing Header support"
+ depends on IPV6
+ select LWTUNNEL
++ select DST_CACHE
+ help
+ Support for RFC6554 RPL Source Routing Header using the lightweight
+ tunnels mechanism.
+diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c
+index 7b31674644efc3..46f70e4a835139 100644
+--- a/net/ipv6/icmp.c
++++ b/net/ipv6/icmp.c
+@@ -175,14 +175,16 @@ static bool icmpv6_mask_allow(struct net *net, int type)
+ return false;
+ }
+
+-static bool icmpv6_global_allow(struct net *net, int type)
++static bool icmpv6_global_allow(struct net *net, int type,
++ bool *apply_ratelimit)
+ {
+ if (icmpv6_mask_allow(net, type))
+ return true;
+
+- if (icmp_global_allow())
++ if (icmp_global_allow()) {
++ *apply_ratelimit = true;
+ return true;
+-
++ }
+ __ICMP_INC_STATS(net, ICMP_MIB_RATELIMITGLOBAL);
+ return false;
+ }
+@@ -191,13 +193,13 @@ static bool icmpv6_global_allow(struct net *net, int type)
+ * Check the ICMP output rate limit
+ */
+ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
+- struct flowi6 *fl6)
++ struct flowi6 *fl6, bool apply_ratelimit)
+ {
+ struct net *net = sock_net(sk);
+ struct dst_entry *dst;
+ bool res = false;
+
+- if (icmpv6_mask_allow(net, type))
++ if (!apply_ratelimit)
+ return true;
+
+ /*
+@@ -228,6 +230,8 @@ static bool icmpv6_xrlim_allow(struct sock *sk, u8 type,
+ if (!res)
+ __ICMP6_INC_STATS(net, ip6_dst_idev(dst),
+ ICMP6_MIB_RATELIMITHOST);
++ else
++ icmp_global_consume();
+ dst_release(dst);
+ return res;
+ }
+@@ -452,6 +456,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+ struct net *net;
+ struct ipv6_pinfo *np;
+ const struct in6_addr *saddr = NULL;
++ bool apply_ratelimit = false;
+ struct dst_entry *dst;
+ struct icmp6hdr tmp_hdr;
+ struct flowi6 fl6;
+@@ -533,11 +538,12 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+ return;
+ }
+
+- /* Needed by both icmp_global_allow and icmpv6_xmit_lock */
++ /* Needed by both icmpv6_global_allow and icmpv6_xmit_lock */
+ local_bh_disable();
+
+ /* Check global sysctl_icmp_msgs_per_sec ratelimit */
+- if (!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, type))
++ if (!(skb->dev->flags & IFF_LOOPBACK) &&
++ !icmpv6_global_allow(net, type, &apply_ratelimit))
+ goto out_bh_enable;
+
+ mip6_addr_swap(skb, parm);
+@@ -575,7 +581,7 @@ void icmp6_send(struct sk_buff *skb, u8 type, u8 code, __u32 info,
+
+ np = inet6_sk(sk);
+
+- if (!icmpv6_xrlim_allow(sk, type, &fl6))
++ if (!icmpv6_xrlim_allow(sk, type, &fl6, apply_ratelimit))
+ goto out;
+
+ tmp_hdr.icmp6_type = type;
+@@ -717,6 +723,7 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
+ struct ipv6_pinfo *np;
+ const struct in6_addr *saddr = NULL;
+ struct icmp6hdr *icmph = icmp6_hdr(skb);
++ bool apply_ratelimit = false;
+ struct icmp6hdr tmp_hdr;
+ struct flowi6 fl6;
+ struct icmpv6_msg msg;
+@@ -781,8 +788,9 @@ static enum skb_drop_reason icmpv6_echo_reply(struct sk_buff *skb)
+ goto out;
+
+ /* Check the ratelimit */
+- if ((!(skb->dev->flags & IFF_LOOPBACK) && !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY)) ||
+- !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6))
++ if ((!(skb->dev->flags & IFF_LOOPBACK) &&
++ !icmpv6_global_allow(net, ICMPV6_ECHO_REPLY, &apply_ratelimit)) ||
++ !icmpv6_xrlim_allow(sk, ICMPV6_ECHO_REPLY, &fl6, apply_ratelimit))
+ goto out_dst_release;
+
+ idev = __in6_dev_get(skb->dev);
+diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c
+index dedee264b8f6c8..b9457473c176df 100644
+--- a/net/ipv6/netfilter/nf_reject_ipv6.c
++++ b/net/ipv6/netfilter/nf_reject_ipv6.c
+@@ -223,33 +223,23 @@ void nf_reject_ip6_tcphdr_put(struct sk_buff *nskb,
+ const struct tcphdr *oth, unsigned int otcplen)
+ {
+ struct tcphdr *tcph;
+- int needs_ack;
+
+ skb_reset_transport_header(nskb);
+- tcph = skb_put(nskb, sizeof(struct tcphdr));
++ tcph = skb_put_zero(nskb, sizeof(struct tcphdr));
+ /* Truncate to length (no data) */
+ tcph->doff = sizeof(struct tcphdr)/4;
+ tcph->source = oth->dest;
+ tcph->dest = oth->source;
+
+ if (oth->ack) {
+- needs_ack = 0;
+ tcph->seq = oth->ack_seq;
+- tcph->ack_seq = 0;
+ } else {
+- needs_ack = 1;
+ tcph->ack_seq = htonl(ntohl(oth->seq) + oth->syn + oth->fin +
+ otcplen - (oth->doff<<2));
+- tcph->seq = 0;
++ tcph->ack = 1;
+ }
+
+- /* Reset flags */
+- ((u_int8_t *)tcph)[13] = 0;
+ tcph->rst = 1;
+- tcph->ack = needs_ack;
+- tcph->window = 0;
+- tcph->urg_ptr = 0;
+- tcph->check = 0;
+
+ /* Adjust TCP checksum */
+ tcph->check = csum_ipv6_magic(&ipv6_hdr(nskb)->saddr,
+diff --git a/net/ipv6/route.c b/net/ipv6/route.c
+index a9644a8edb9609..1febd95822c9a7 100644
+--- a/net/ipv6/route.c
++++ b/net/ipv6/route.c
+@@ -175,7 +175,7 @@ static void rt6_uncached_list_flush_dev(struct net_device *dev)
+ struct net_device *rt_dev = rt->dst.dev;
+ bool handled = false;
+
+- if (rt_idev->dev == dev) {
++ if (rt_idev && rt_idev->dev == dev) {
+ rt->rt6i_idev = in6_dev_get(blackhole_netdev);
+ in6_dev_put(rt_idev);
+ handled = true;
+diff --git a/net/ipv6/rpl_iptunnel.c b/net/ipv6/rpl_iptunnel.c
+index 2c83b7586422dd..db3c19a42e1ca7 100644
+--- a/net/ipv6/rpl_iptunnel.c
++++ b/net/ipv6/rpl_iptunnel.c
+@@ -263,10 +263,8 @@ static int rpl_input(struct sk_buff *skb)
+ rlwt = rpl_lwt_lwtunnel(orig_dst->lwtstate);
+
+ err = rpl_do_srh(skb, rlwt);
+- if (unlikely(err)) {
+- kfree_skb(skb);
+- return err;
+- }
++ if (unlikely(err))
++ goto drop;
+
+ local_bh_disable();
+ dst = dst_cache_get(&rlwt->cache);
+@@ -286,9 +284,13 @@ static int rpl_input(struct sk_buff *skb)
+
+ err = skb_cow_head(skb, LL_RESERVED_SPACE(dst->dev));
+ if (unlikely(err))
+- return err;
++ goto drop;
+
+ return dst_input(skb);
++
++drop:
++ kfree_skb(skb);
++ return err;
+ }
+
+ static int nla_put_rpl_srh(struct sk_buff *skb, int attrtype,
+diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c
+index b935bb5d8ed1f7..3e3814076006e6 100644
+--- a/net/mac80211/iface.c
++++ b/net/mac80211/iface.c
+@@ -462,6 +462,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
+ {
+ struct ieee80211_local *local = sdata->local;
+ unsigned long flags;
++ struct sk_buff_head freeq;
+ struct sk_buff *skb, *tmp;
+ u32 hw_reconf_flags = 0;
+ int i, flushed;
+@@ -641,18 +642,32 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do
+ skb_queue_purge(&sdata->status_queue);
+ }
+
++ /*
++ * Since ieee80211_free_txskb() may issue __dev_queue_xmit()
++ * which should be called with interrupts enabled, reclamation
++ * is done in two phases:
++ */
++ __skb_queue_head_init(&freeq);
++
++ /* unlink from local queues... */
+ spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
+ for (i = 0; i < IEEE80211_MAX_QUEUES; i++) {
+ skb_queue_walk_safe(&local->pending[i], skb, tmp) {
+ struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
+ if (info->control.vif == &sdata->vif) {
+ __skb_unlink(skb, &local->pending[i]);
+- ieee80211_free_txskb(&local->hw, skb);
++ __skb_queue_tail(&freeq, skb);
+ }
+ }
+ }
+ spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
+
++ /* ... and perform actual reclamation with interrupts enabled. */
++ skb_queue_walk_safe(&freeq, skb, tmp) {
++ __skb_unlink(skb, &freeq);
++ ieee80211_free_txskb(&local->hw, skb);
++ }
++
+ if (sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ ieee80211_txq_remove_vlan(local, sdata);
+
+diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
+index ad2ce9c92ba8a2..1faf4d7c115f08 100644
+--- a/net/mac80211/mlme.c
++++ b/net/mac80211/mlme.c
+@@ -4317,7 +4317,7 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
+ ((assoc_data->wmm && !elems->wmm_param) ||
+ (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_HT &&
+ (!elems->ht_cap_elem || !elems->ht_operation)) ||
+- (link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT &&
++ (is_5ghz && link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT &&
+ (!elems->vht_cap_elem || !elems->vht_operation)))) {
+ const struct cfg80211_bss_ies *ies;
+ struct ieee802_11_elems *bss_elems;
+@@ -4365,19 +4365,22 @@ static bool ieee80211_assoc_config_link(struct ieee80211_link_data *link,
+ sdata_info(sdata,
+ "AP bug: HT operation missing from AssocResp\n");
+ }
+- if (!elems->vht_cap_elem && bss_elems->vht_cap_elem &&
+- link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
+- elems->vht_cap_elem = bss_elems->vht_cap_elem;
+- sdata_info(sdata,
+- "AP bug: VHT capa missing from AssocResp\n");
+- }
+- if (!elems->vht_operation && bss_elems->vht_operation &&
+- link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
+- elems->vht_operation = bss_elems->vht_operation;
+- sdata_info(sdata,
+- "AP bug: VHT operation missing from AssocResp\n");
+- }
+
++ if (is_5ghz) {
++ if (!elems->vht_cap_elem && bss_elems->vht_cap_elem &&
++ link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
++ elems->vht_cap_elem = bss_elems->vht_cap_elem;
++ sdata_info(sdata,
++ "AP bug: VHT capa missing from AssocResp\n");
++ }
++
++ if (!elems->vht_operation && bss_elems->vht_operation &&
++ link->u.mgd.conn.mode >= IEEE80211_CONN_MODE_VHT) {
++ elems->vht_operation = bss_elems->vht_operation;
++ sdata_info(sdata,
++ "AP bug: VHT operation missing from AssocResp\n");
++ }
++ }
+ kfree(bss_elems);
+ }
+
+@@ -7121,6 +7124,7 @@ static int ieee80211_do_assoc(struct ieee80211_sub_if_data *sdata)
+ lockdep_assert_wiphy(sdata->local->hw.wiphy);
+
+ assoc_data->tries++;
++ assoc_data->comeback = false;
+ if (assoc_data->tries > IEEE80211_ASSOC_MAX_TRIES) {
+ sdata_info(sdata, "association with %pM timed out\n",
+ assoc_data->ap_addr);
+diff --git a/net/mac80211/offchannel.c b/net/mac80211/offchannel.c
+index 65e1e9e971fd69..5810d938edc44c 100644
+--- a/net/mac80211/offchannel.c
++++ b/net/mac80211/offchannel.c
+@@ -964,6 +964,7 @@ int ieee80211_mgmt_tx(struct wiphy *wiphy, struct wireless_dev *wdev,
+ }
+
+ IEEE80211_SKB_CB(skb)->flags = flags;
++ IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK;
+
+ skb->dev = sdata->dev;
+
+diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c
+index 4dc1def6954865..3dc9752188d58f 100644
+--- a/net/mac80211/rate.c
++++ b/net/mac80211/rate.c
+@@ -890,7 +890,7 @@ void ieee80211_get_tx_rates(struct ieee80211_vif *vif,
+ if (ieee80211_is_tx_data(skb))
+ rate_control_apply_mask(sdata, sta, sband, dest, max_rates);
+
+- if (!(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX))
++ if (!(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK))
+ mask = sdata->rc_rateidx_mask[info->band];
+
+ if (dest[0].idx < 0)
+diff --git a/net/mac80211/scan.c b/net/mac80211/scan.c
+index b5f2df61c7f671..1c5d99975ad04d 100644
+--- a/net/mac80211/scan.c
++++ b/net/mac80211/scan.c
+@@ -649,7 +649,7 @@ static void ieee80211_send_scan_probe_req(struct ieee80211_sub_if_data *sdata,
+ cpu_to_le16(IEEE80211_SN_TO_SEQ(sn));
+ }
+ IEEE80211_SKB_CB(skb)->flags |= tx_flags;
+- IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_SCAN_TX;
++ IEEE80211_SKB_CB(skb)->control.flags |= IEEE80211_TX_CTRL_DONT_USE_RATE_MASK;
+ ieee80211_tx_skb_tid_band(sdata, skb, 7, channel->band);
+ }
+ }
+diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
+index bca7b341dd772d..a9ee8698225929 100644
+--- a/net/mac80211/tx.c
++++ b/net/mac80211/tx.c
+@@ -699,7 +699,7 @@ ieee80211_tx_h_rate_ctrl(struct ieee80211_tx_data *tx)
+ txrc.skb = tx->skb;
+ txrc.reported_rate.idx = -1;
+
+- if (unlikely(info->control.flags & IEEE80211_TX_CTRL_SCAN_TX)) {
++ if (unlikely(info->control.flags & IEEE80211_TX_CTRL_DONT_USE_RATE_MASK)) {
+ txrc.rate_idx_mask = ~0;
+ } else {
+ txrc.rate_idx_mask = tx->sdata->rc_rateidx_mask[info->band];
+diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
+index 4cbf71d0786b0d..c55cf5bc36b2f2 100644
+--- a/net/netfilter/nf_conntrack_netlink.c
++++ b/net/netfilter/nf_conntrack_netlink.c
+@@ -382,7 +382,7 @@ static int ctnetlink_dump_secctx(struct sk_buff *skb, const struct nf_conn *ct)
+ #define ctnetlink_dump_secctx(a, b) (0)
+ #endif
+
+-#ifdef CONFIG_NF_CONNTRACK_LABELS
++#ifdef CONFIG_NF_CONNTRACK_EVENTS
+ static inline int ctnetlink_label_size(const struct nf_conn *ct)
+ {
+ struct nf_conn_labels *labels = nf_ct_labels_find(ct);
+@@ -391,6 +391,7 @@ static inline int ctnetlink_label_size(const struct nf_conn *ct)
+ return 0;
+ return nla_total_size(sizeof(labels->bits));
+ }
++#endif
+
+ static int
+ ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct)
+@@ -411,10 +412,6 @@ ctnetlink_dump_labels(struct sk_buff *skb, const struct nf_conn *ct)
+
+ return 0;
+ }
+-#else
+-#define ctnetlink_dump_labels(a, b) (0)
+-#define ctnetlink_label_size(a) (0)
+-#endif
+
+ #define master_tuple(ct) &(ct->master->tuplehash[IP_CT_DIR_ORIGINAL].tuple)
+
+diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
+index 41d7faeb101cfc..465cc43c75e30e 100644
+--- a/net/netfilter/nf_tables_api.c
++++ b/net/netfilter/nf_tables_api.c
+@@ -1795,7 +1795,7 @@ static int nft_dump_basechain_hook(struct sk_buff *skb, int family,
+ if (!hook_list)
+ hook_list = &basechain->hook_list;
+
+- list_for_each_entry(hook, hook_list, list) {
++ list_for_each_entry_rcu(hook, hook_list, list) {
+ if (!first)
+ first = hook;
+
+@@ -4544,7 +4544,7 @@ int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result)
+ return -ERANGE;
+
+ ms *= NSEC_PER_MSEC;
+- *result = nsecs_to_jiffies64(ms);
++ *result = nsecs_to_jiffies64(ms) ? : !!ms;
+ return 0;
+ }
+
+@@ -6631,7 +6631,7 @@ static int nft_setelem_catchall_insert(const struct net *net,
+ }
+ }
+
+- catchall = kmalloc(sizeof(*catchall), GFP_KERNEL);
++ catchall = kmalloc(sizeof(*catchall), GFP_KERNEL_ACCOUNT);
+ if (!catchall)
+ return -ENOMEM;
+
+@@ -6867,17 +6867,23 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
+ return err;
+ } else if (set->flags & NFT_SET_TIMEOUT &&
+ !(flags & NFT_SET_ELEM_INTERVAL_END)) {
+- timeout = READ_ONCE(set->timeout);
++ timeout = set->timeout;
+ }
+
+ expiration = 0;
+ if (nla[NFTA_SET_ELEM_EXPIRATION] != NULL) {
+ if (!(set->flags & NFT_SET_TIMEOUT))
+ return -EINVAL;
++ if (timeout == 0)
++ return -EOPNOTSUPP;
++
+ err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_EXPIRATION],
+ &expiration);
+ if (err)
+ return err;
++
++ if (expiration > timeout)
++ return -ERANGE;
+ }
+
+ if (nla[NFTA_SET_ELEM_EXPR]) {
+@@ -6968,7 +6974,7 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set,
+ if (err < 0)
+ goto err_parse_key_end;
+
+- if (timeout != READ_ONCE(set->timeout)) {
++ if (timeout != set->timeout) {
+ err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT);
+ if (err < 0)
+ goto err_parse_key_end;
+@@ -9131,7 +9137,7 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable)
+ flowtable->data.type->setup(&flowtable->data, hook->ops.dev,
+ FLOW_BLOCK_UNBIND);
+ list_del_rcu(&hook->list);
+- kfree(hook);
++ kfree_rcu(hook, rcu);
+ }
+ kfree(flowtable->name);
+ module_put(flowtable->data.type->owner);
+diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c
+index d3d11dede54507..85450f60114263 100644
+--- a/net/netfilter/nft_compat.c
++++ b/net/netfilter/nft_compat.c
+@@ -536,7 +536,7 @@ nft_match_large_init(const struct nft_ctx *ctx, const struct nft_expr *expr,
+ struct xt_match *m = expr->ops->data;
+ int ret;
+
+- priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL);
++ priv->info = kmalloc(XT_ALIGN(m->matchsize), GFP_KERNEL_ACCOUNT);
+ if (!priv->info)
+ return -ENOMEM;
+
+@@ -810,7 +810,7 @@ nft_match_select_ops(const struct nft_ctx *ctx,
+ goto err;
+ }
+
+- ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
++ ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT);
+ if (!ops) {
+ err = -ENOMEM;
+ goto err;
+@@ -900,7 +900,7 @@ nft_target_select_ops(const struct nft_ctx *ctx,
+ goto err;
+ }
+
+- ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL);
++ ops = kzalloc(sizeof(struct nft_expr_ops), GFP_KERNEL_ACCOUNT);
+ if (!ops) {
+ err = -ENOMEM;
+ goto err;
+diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c
+index b4ada3ab21679b..489a9b34f1ecc1 100644
+--- a/net/netfilter/nft_dynset.c
++++ b/net/netfilter/nft_dynset.c
+@@ -56,7 +56,7 @@ static struct nft_elem_priv *nft_dynset_new(struct nft_set *set,
+ if (!atomic_add_unless(&set->nelems, 1, set->size))
+ return NULL;
+
+- timeout = priv->timeout ? : set->timeout;
++ timeout = priv->timeout ? : READ_ONCE(set->timeout);
+ elem_priv = nft_set_elem_init(set, &priv->tmpl,
+ ®s->data[priv->sreg_key], NULL,
+ ®s->data[priv->sreg_data],
+@@ -95,7 +95,7 @@ void nft_dynset_eval(const struct nft_expr *expr,
+ expr, regs, &ext)) {
+ if (priv->op == NFT_DYNSET_OP_UPDATE &&
+ nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) {
+- timeout = priv->timeout ? : set->timeout;
++ timeout = priv->timeout ? : READ_ONCE(set->timeout);
+ *nft_set_ext_expiration(ext) = get_jiffies_64() + timeout;
+ }
+
+@@ -313,7 +313,7 @@ static int nft_dynset_init(const struct nft_ctx *ctx,
+ nft_dynset_ext_add_expr(priv);
+
+ if (set->flags & NFT_SET_TIMEOUT) {
+- if (timeout || set->timeout) {
++ if (timeout || READ_ONCE(set->timeout)) {
+ nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_TIMEOUT);
+ nft_set_ext_add(&priv->tmpl, NFT_SET_EXT_EXPIRATION);
+ }
+diff --git a/net/netfilter/nft_log.c b/net/netfilter/nft_log.c
+index 5defe6e4fd9820..e3558813799579 100644
+--- a/net/netfilter/nft_log.c
++++ b/net/netfilter/nft_log.c
+@@ -163,7 +163,7 @@ static int nft_log_init(const struct nft_ctx *ctx,
+
+ nla = tb[NFTA_LOG_PREFIX];
+ if (nla != NULL) {
+- priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL);
++ priv->prefix = kmalloc(nla_len(nla) + 1, GFP_KERNEL_ACCOUNT);
+ if (priv->prefix == NULL)
+ return -ENOMEM;
+ nla_strscpy(priv->prefix, nla, nla_len(nla) + 1);
+diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c
+index 9139ce38ea7b9a..f23faf565b6873 100644
+--- a/net/netfilter/nft_meta.c
++++ b/net/netfilter/nft_meta.c
+@@ -954,7 +954,7 @@ static int nft_secmark_obj_init(const struct nft_ctx *ctx,
+ if (tb[NFTA_SECMARK_CTX] == NULL)
+ return -EINVAL;
+
+- priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL);
++ priv->ctx = nla_strdup(tb[NFTA_SECMARK_CTX], GFP_KERNEL_ACCOUNT);
+ if (!priv->ctx)
+ return -ENOMEM;
+
+diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c
+index 7d29db7c2ac0f0..bd058babfc820c 100644
+--- a/net/netfilter/nft_numgen.c
++++ b/net/netfilter/nft_numgen.c
+@@ -66,7 +66,7 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx,
+ if (priv->offset + priv->modulus - 1 < priv->offset)
+ return -EOVERFLOW;
+
+- priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL);
++ priv->counter = kmalloc(sizeof(*priv->counter), GFP_KERNEL_ACCOUNT);
+ if (!priv->counter)
+ return -ENOMEM;
+
+diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
+index eb4c4a4ac7acea..7be342b495f5f7 100644
+--- a/net/netfilter/nft_set_pipapo.c
++++ b/net/netfilter/nft_set_pipapo.c
+@@ -663,7 +663,7 @@ static int pipapo_realloc_mt(struct nft_pipapo_field *f,
+ check_add_overflow(rules, extra, &rules_alloc))
+ return -EOVERFLOW;
+
+- new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL);
++ new_mt = kvmalloc_array(rules_alloc, sizeof(*new_mt), GFP_KERNEL_ACCOUNT);
+ if (!new_mt)
+ return -ENOMEM;
+
+@@ -936,7 +936,7 @@ static void pipapo_lt_bits_adjust(struct nft_pipapo_field *f)
+ return;
+ }
+
+- new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL);
++ new_lt = kvzalloc(lt_size + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL_ACCOUNT);
+ if (!new_lt)
+ return;
+
+@@ -1212,7 +1212,7 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone,
+ scratch = kzalloc_node(struct_size(scratch, map,
+ bsize_max * 2) +
+ NFT_PIPAPO_ALIGN_HEADROOM,
+- GFP_KERNEL, cpu_to_node(i));
++ GFP_KERNEL_ACCOUNT, cpu_to_node(i));
+ if (!scratch) {
+ /* On failure, there's no need to undo previous
+ * allocations: this means that some scratch maps have
+@@ -1427,7 +1427,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
+ struct nft_pipapo_match *new;
+ int i;
+
+- new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL);
++ new = kmalloc(struct_size(new, f, old->field_count), GFP_KERNEL_ACCOUNT);
+ if (!new)
+ return NULL;
+
+@@ -1457,7 +1457,7 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
+ new_lt = kvzalloc(src->groups * NFT_PIPAPO_BUCKETS(src->bb) *
+ src->bsize * sizeof(*dst->lt) +
+ NFT_PIPAPO_ALIGN_HEADROOM,
+- GFP_KERNEL);
++ GFP_KERNEL_ACCOUNT);
+ if (!new_lt)
+ goto out_lt;
+
+@@ -1470,7 +1470,8 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old)
+
+ if (src->rules > 0) {
+ dst->mt = kvmalloc_array(src->rules_alloc,
+- sizeof(*src->mt), GFP_KERNEL);
++ sizeof(*src->mt),
++ GFP_KERNEL_ACCOUNT);
+ if (!dst->mt)
+ goto out_mt;
+
+diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c
+index 60a76e6e348e7b..5c6ed68cc6e058 100644
+--- a/net/netfilter/nft_tunnel.c
++++ b/net/netfilter/nft_tunnel.c
+@@ -509,13 +509,14 @@ static int nft_tunnel_obj_init(const struct nft_ctx *ctx,
+ return err;
+ }
+
+- md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL, GFP_KERNEL);
++ md = metadata_dst_alloc(priv->opts.len, METADATA_IP_TUNNEL,
++ GFP_KERNEL_ACCOUNT);
+ if (!md)
+ return -ENOMEM;
+
+ memcpy(&md->u.tun_info, &info, sizeof(info));
+ #ifdef CONFIG_DST_CACHE
+- err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL);
++ err = dst_cache_init(&md->u.tun_info.dst_cache, GFP_KERNEL_ACCOUNT);
+ if (err < 0) {
+ metadata_dst_free(md);
+ return err;
+diff --git a/net/qrtr/af_qrtr.c b/net/qrtr/af_qrtr.c
+index 41ece61eb57ab7..00c51cf693f3d0 100644
+--- a/net/qrtr/af_qrtr.c
++++ b/net/qrtr/af_qrtr.c
+@@ -884,7 +884,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb,
+
+ mutex_lock(&qrtr_node_lock);
+ list_for_each_entry(node, &qrtr_all_nodes, item) {
+- skbn = skb_clone(skb, GFP_KERNEL);
++ skbn = pskb_copy(skb, GFP_KERNEL);
+ if (!skbn)
+ break;
+ skb_set_owner_w(skbn, skb->sk);
+diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c
+index 593846d252143c..114fef65f92eab 100644
+--- a/net/tipc/bcast.c
++++ b/net/tipc/bcast.c
+@@ -320,8 +320,8 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb,
+ {
+ struct tipc_msg *hdr, *_hdr;
+ struct sk_buff_head tmpq;
++ u16 cong_link_cnt = 0;
+ struct sk_buff *_skb;
+- u16 cong_link_cnt;
+ int rc = 0;
+
+ /* Is a cluster supporting with new capabilities ? */
+diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
+index 967bc4935b4ed9..e3bf14e489c5de 100644
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -9658,7 +9658,8 @@ nl80211_parse_sched_scan(struct wiphy *wiphy, struct wireless_dev *wdev,
+ return ERR_PTR(-ENOMEM);
+
+ if (n_ssids)
+- request->ssids = (void *)&request->channels[n_channels];
++ request->ssids = (void *)request +
++ struct_size(request, channels, n_channels);
+ request->n_ssids = n_ssids;
+ if (ie_len) {
+ if (n_ssids)
+diff --git a/net/wireless/scan.c b/net/wireless/scan.c
+index 64c779788a6466..44c93b9a9751c1 100644
+--- a/net/wireless/scan.c
++++ b/net/wireless/scan.c
+@@ -3452,8 +3452,8 @@ int cfg80211_wext_siwscan(struct net_device *dev,
+ n_channels = ieee80211_get_num_supported_channels(wiphy);
+ }
+
+- creq = kzalloc(sizeof(*creq) + sizeof(struct cfg80211_ssid) +
+- n_channels * sizeof(void *),
++ creq = kzalloc(struct_size(creq, channels, n_channels) +
++ sizeof(struct cfg80211_ssid),
+ GFP_ATOMIC);
+ if (!creq)
+ return -ENOMEM;
+@@ -3461,7 +3461,7 @@ int cfg80211_wext_siwscan(struct net_device *dev,
+ creq->wiphy = wiphy;
+ creq->wdev = dev->ieee80211_ptr;
+ /* SSIDs come after channels */
+- creq->ssids = (void *)&creq->channels[n_channels];
++ creq->ssids = (void *)creq + struct_size(creq, channels, n_channels);
+ creq->n_channels = n_channels;
+ creq->n_ssids = 1;
+ creq->scan_start = jiffies;
+diff --git a/net/wireless/sme.c b/net/wireless/sme.c
+index 1cfe673bc52f37..4b80af0edbe976 100644
+--- a/net/wireless/sme.c
++++ b/net/wireless/sme.c
+@@ -115,7 +115,8 @@ static int cfg80211_conn_scan(struct wireless_dev *wdev)
+ n_channels = i;
+ }
+ request->n_channels = n_channels;
+- request->ssids = (void *)&request->channels[n_channels];
++ request->ssids = (void *)request +
++ struct_size(request, channels, n_channels);
+ request->n_ssids = 1;
+
+ memcpy(request->ssids[0].ssid, wdev->conn->params.ssid,
+diff --git a/net/wireless/util.c b/net/wireless/util.c
+index af6ec719567fc1..f1193aca79bae8 100644
+--- a/net/wireless/util.c
++++ b/net/wireless/util.c
+@@ -998,10 +998,10 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
+ * Diffserv Service Classes no update is needed:
+ * - Standard: DF
+ * - Low Priority Data: CS1
+- * - Multimedia Streaming: AF31, AF32, AF33
+ * - Multimedia Conferencing: AF41, AF42, AF43
+ * - Network Control Traffic: CS7
+ * - Real-Time Interactive: CS4
++ * - Signaling: CS5
+ */
+ switch (dscp >> 2) {
+ case 10:
+@@ -1026,9 +1026,11 @@ unsigned int cfg80211_classify8021d(struct sk_buff *skb,
+ /* Broadcasting video: CS3 */
+ ret = 4;
+ break;
+- case 40:
+- /* Signaling: CS5 */
+- ret = 5;
++ case 26:
++ case 28:
++ case 30:
++ /* Multimedia Streaming: AF31, AF32, AF33 */
++ ret = 4;
+ break;
+ case 44:
+ /* Voice Admit: VA */
+diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c
+index c0e0204b963045..b0f24ebd05f0ba 100644
+--- a/net/xdp/xsk_buff_pool.c
++++ b/net/xdp/xsk_buff_pool.c
+@@ -623,20 +623,31 @@ static u32 xp_alloc_reused(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u3
+ return nb_entries;
+ }
+
+-u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
++static u32 xp_alloc_slow(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
++ u32 max)
+ {
+- u32 nb_entries1 = 0, nb_entries2;
++ int i;
+
+- if (unlikely(pool->dev && dma_dev_need_sync(pool->dev))) {
++ for (i = 0; i < max; i++) {
+ struct xdp_buff *buff;
+
+- /* Slow path */
+ buff = xp_alloc(pool);
+- if (buff)
+- *xdp = buff;
+- return !!buff;
++ if (unlikely(!buff))
++ return i;
++ *xdp = buff;
++ xdp++;
+ }
+
++ return max;
++}
++
++u32 xp_alloc_batch(struct xsk_buff_pool *pool, struct xdp_buff **xdp, u32 max)
++{
++ u32 nb_entries1 = 0, nb_entries2;
++
++ if (unlikely(pool->dev && dma_dev_need_sync(pool->dev)))
++ return xp_alloc_slow(pool, xdp, max);
++
+ if (unlikely(pool->free_list_cnt)) {
+ nb_entries1 = xp_alloc_reused(pool, xdp, max);
+ if (nb_entries1 == max)
+diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile
+index 3e003dd6bea09c..dca56aa360ff32 100644
+--- a/samples/bpf/Makefile
++++ b/samples/bpf/Makefile
+@@ -169,6 +169,10 @@ BPF_EXTRA_CFLAGS += -I$(srctree)/arch/mips/include/asm/mach-generic
+ endif
+ endif
+
++ifeq ($(ARCH), x86)
++BPF_EXTRA_CFLAGS += -fcf-protection
++endif
++
+ TPROGS_CFLAGS += -Wall -O2
+ TPROGS_CFLAGS += -Wmissing-prototypes
+ TPROGS_CFLAGS += -Wstrict-prototypes
+@@ -405,7 +409,7 @@ $(obj)/%.o: $(src)/%.c
+ -Wno-gnu-variable-sized-type-not-at-end \
+ -Wno-address-of-packed-member -Wno-tautological-compare \
+ -Wno-unknown-warning-option $(CLANG_ARCH_ARGS) \
+- -fno-asynchronous-unwind-tables -fcf-protection \
++ -fno-asynchronous-unwind-tables \
+ -I$(srctree)/samples/bpf/ -include asm_goto_workaround.h \
+ -O2 -emit-llvm -Xclang -disable-llvm-passes -c $< -o - | \
+ $(OPT) -O2 -mtriple=bpf-pc-linux | $(LLVM_DIS) | \
+diff --git a/security/apparmor/include/net.h b/security/apparmor/include/net.h
+index 67bf888c3bd6b9..c42ed8a73f1cef 100644
+--- a/security/apparmor/include/net.h
++++ b/security/apparmor/include/net.h
+@@ -51,10 +51,9 @@ struct aa_sk_ctx {
+ struct aa_label *peer;
+ };
+
+-#define SK_CTX(X) ((X)->sk_security)
+ static inline struct aa_sk_ctx *aa_sock(const struct sock *sk)
+ {
+- return sk->sk_security;
++ return sk->sk_security + apparmor_blob_sizes.lbs_sock;
+ }
+
+ #define DEFINE_AUDIT_NET(NAME, OP, SK, F, T, P) \
+diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
+index 4373b914acf204..b8366fca98d23e 100644
+--- a/security/apparmor/lsm.c
++++ b/security/apparmor/lsm.c
+@@ -1057,27 +1057,12 @@ static int apparmor_userns_create(const struct cred *cred)
+ return error;
+ }
+
+-static int apparmor_sk_alloc_security(struct sock *sk, int family, gfp_t flags)
+-{
+- struct aa_sk_ctx *ctx;
+-
+- ctx = kzalloc(sizeof(*ctx), flags);
+- if (!ctx)
+- return -ENOMEM;
+-
+- sk->sk_security = ctx;
+-
+- return 0;
+-}
+-
+ static void apparmor_sk_free_security(struct sock *sk)
+ {
+ struct aa_sk_ctx *ctx = aa_sock(sk);
+
+- sk->sk_security = NULL;
+ aa_put_label(ctx->label);
+ aa_put_label(ctx->peer);
+- kfree(ctx);
+ }
+
+ /**
+@@ -1432,6 +1417,7 @@ struct lsm_blob_sizes apparmor_blob_sizes __ro_after_init = {
+ .lbs_cred = sizeof(struct aa_label *),
+ .lbs_file = sizeof(struct aa_file_ctx),
+ .lbs_task = sizeof(struct aa_task_ctx),
++ .lbs_sock = sizeof(struct aa_sk_ctx),
+ };
+
+ static const struct lsm_id apparmor_lsmid = {
+@@ -1477,7 +1463,6 @@ static struct security_hook_list apparmor_hooks[] __ro_after_init = {
+ LSM_HOOK_INIT(getprocattr, apparmor_getprocattr),
+ LSM_HOOK_INIT(setprocattr, apparmor_setprocattr),
+
+- LSM_HOOK_INIT(sk_alloc_security, apparmor_sk_alloc_security),
+ LSM_HOOK_INIT(sk_free_security, apparmor_sk_free_security),
+ LSM_HOOK_INIT(sk_clone_security, apparmor_sk_clone_security),
+
+diff --git a/security/apparmor/net.c b/security/apparmor/net.c
+index 87e934b2b54887..77413a5191179a 100644
+--- a/security/apparmor/net.c
++++ b/security/apparmor/net.c
+@@ -151,7 +151,7 @@ static int aa_label_sk_perm(const struct cred *subj_cred,
+ const char *op, u32 request,
+ struct sock *sk)
+ {
+- struct aa_sk_ctx *ctx = SK_CTX(sk);
++ struct aa_sk_ctx *ctx = aa_sock(sk);
+ int error = 0;
+
+ AA_BUG(!label);
+diff --git a/security/bpf/hooks.c b/security/bpf/hooks.c
+index 57b9ffd53c98ae..3663aec7bcbd21 100644
+--- a/security/bpf/hooks.c
++++ b/security/bpf/hooks.c
+@@ -31,7 +31,6 @@ static int __init bpf_lsm_init(void)
+
+ struct lsm_blob_sizes bpf_lsm_blob_sizes __ro_after_init = {
+ .lbs_inode = sizeof(struct bpf_storage_blob),
+- .lbs_task = sizeof(struct bpf_storage_blob),
+ };
+
+ DEFINE_LSM(bpf) = {
+diff --git a/security/integrity/ima/ima.h b/security/integrity/ima/ima.h
+index c51e24d24d1e9e..3c323ca213d42c 100644
+--- a/security/integrity/ima/ima.h
++++ b/security/integrity/ima/ima.h
+@@ -223,7 +223,7 @@ static inline void ima_inode_set_iint(const struct inode *inode,
+
+ struct ima_iint_cache *ima_iint_find(struct inode *inode);
+ struct ima_iint_cache *ima_inode_get(struct inode *inode);
+-void ima_inode_free(struct inode *inode);
++void ima_inode_free_rcu(void *inode_security);
+ void __init ima_iintcache_init(void);
+
+ extern const int read_idmap[];
+diff --git a/security/integrity/ima/ima_iint.c b/security/integrity/ima/ima_iint.c
+index e23412a2c56b09..00b249101f98d3 100644
+--- a/security/integrity/ima/ima_iint.c
++++ b/security/integrity/ima/ima_iint.c
+@@ -109,22 +109,18 @@ struct ima_iint_cache *ima_inode_get(struct inode *inode)
+ }
+
+ /**
+- * ima_inode_free - Called on inode free
+- * @inode: Pointer to the inode
++ * ima_inode_free_rcu - Called to free an inode via a RCU callback
++ * @inode_security: The inode->i_security pointer
+ *
+- * Free the iint associated with an inode.
++ * Free the IMA data associated with an inode.
+ */
+-void ima_inode_free(struct inode *inode)
++void ima_inode_free_rcu(void *inode_security)
+ {
+- struct ima_iint_cache *iint;
+-
+- if (!IS_IMA(inode))
+- return;
+-
+- iint = ima_iint_find(inode);
+- ima_inode_set_iint(inode, NULL);
++ struct ima_iint_cache **iint_p = inode_security + ima_blob_sizes.lbs_inode;
+
+- ima_iint_free(iint);
++ /* *iint_p should be NULL if !IS_IMA(inode) */
++ if (*iint_p)
++ ima_iint_free(*iint_p);
+ }
+
+ static void ima_iint_init_once(void *foo)
+diff --git a/security/integrity/ima/ima_main.c b/security/integrity/ima/ima_main.c
+index f04f43af651c8e..5b3394864b218e 100644
+--- a/security/integrity/ima/ima_main.c
++++ b/security/integrity/ima/ima_main.c
+@@ -1193,7 +1193,7 @@ static struct security_hook_list ima_hooks[] __ro_after_init = {
+ #ifdef CONFIG_INTEGRITY_ASYMMETRIC_KEYS
+ LSM_HOOK_INIT(kernel_module_request, ima_kernel_module_request),
+ #endif
+- LSM_HOOK_INIT(inode_free_security, ima_inode_free),
++ LSM_HOOK_INIT(inode_free_security_rcu, ima_inode_free_rcu),
+ };
+
+ static const struct lsm_id ima_lsmid = {
+diff --git a/security/landlock/fs.c b/security/landlock/fs.c
+index 7877a64cc6b87c..0804f76a67be2e 100644
+--- a/security/landlock/fs.c
++++ b/security/landlock/fs.c
+@@ -1207,13 +1207,16 @@ static int current_check_refer_path(struct dentry *const old_dentry,
+
+ /* Inode hooks */
+
+-static void hook_inode_free_security(struct inode *const inode)
++static void hook_inode_free_security_rcu(void *inode_security)
+ {
++ struct landlock_inode_security *inode_sec;
++
+ /*
+ * All inodes must already have been untied from their object by
+ * release_inode() or hook_sb_delete().
+ */
+- WARN_ON_ONCE(landlock_inode(inode)->object);
++ inode_sec = inode_security + landlock_blob_sizes.lbs_inode;
++ WARN_ON_ONCE(inode_sec->object);
+ }
+
+ /* Super-block hooks */
+@@ -1637,7 +1640,7 @@ static int hook_file_ioctl_compat(struct file *file, unsigned int cmd,
+ }
+
+ static struct security_hook_list landlock_hooks[] __ro_after_init = {
+- LSM_HOOK_INIT(inode_free_security, hook_inode_free_security),
++ LSM_HOOK_INIT(inode_free_security_rcu, hook_inode_free_security_rcu),
+
+ LSM_HOOK_INIT(sb_delete, hook_sb_delete),
+ LSM_HOOK_INIT(sb_mount, hook_sb_mount),
+diff --git a/security/security.c b/security/security.c
+index 8cee5b6c6e6d53..43166e341526c0 100644
+--- a/security/security.c
++++ b/security/security.c
+@@ -29,6 +29,7 @@
+ #include <linux/msg.h>
+ #include <linux/overflow.h>
+ #include <net/flow.h>
++#include <net/sock.h>
+
+ /* How many LSMs were built into the kernel? */
+ #define LSM_COUNT (__end_lsm_info - __start_lsm_info)
+@@ -227,6 +228,7 @@ static void __init lsm_set_blob_sizes(struct lsm_blob_sizes *needed)
+ lsm_set_blob_size(&needed->lbs_inode, &blob_sizes.lbs_inode);
+ lsm_set_blob_size(&needed->lbs_ipc, &blob_sizes.lbs_ipc);
+ lsm_set_blob_size(&needed->lbs_msg_msg, &blob_sizes.lbs_msg_msg);
++ lsm_set_blob_size(&needed->lbs_sock, &blob_sizes.lbs_sock);
+ lsm_set_blob_size(&needed->lbs_superblock, &blob_sizes.lbs_superblock);
+ lsm_set_blob_size(&needed->lbs_task, &blob_sizes.lbs_task);
+ lsm_set_blob_size(&needed->lbs_xattr_count,
+@@ -401,6 +403,7 @@ static void __init ordered_lsm_init(void)
+ init_debug("inode blob size = %d\n", blob_sizes.lbs_inode);
+ init_debug("ipc blob size = %d\n", blob_sizes.lbs_ipc);
+ init_debug("msg_msg blob size = %d\n", blob_sizes.lbs_msg_msg);
++ init_debug("sock blob size = %d\n", blob_sizes.lbs_sock);
+ init_debug("superblock blob size = %d\n", blob_sizes.lbs_superblock);
+ init_debug("task blob size = %d\n", blob_sizes.lbs_task);
+ init_debug("xattr slots = %d\n", blob_sizes.lbs_xattr_count);
+@@ -1596,9 +1599,8 @@ int security_inode_alloc(struct inode *inode)
+
+ static void inode_free_by_rcu(struct rcu_head *head)
+ {
+- /*
+- * The rcu head is at the start of the inode blob
+- */
++ /* The rcu head is at the start of the inode blob */
++ call_void_hook(inode_free_security_rcu, head);
+ kmem_cache_free(lsm_inode_cache, head);
+ }
+
+@@ -1606,23 +1608,24 @@ static void inode_free_by_rcu(struct rcu_head *head)
+ * security_inode_free() - Free an inode's LSM blob
+ * @inode: the inode
+ *
+- * Deallocate the inode security structure and set @inode->i_security to NULL.
++ * Release any LSM resources associated with @inode, although due to the
++ * inode's RCU protections it is possible that the resources will not be
++ * fully released until after the current RCU grace period has elapsed.
++ *
++ * It is important for LSMs to note that despite being present in a call to
++ * security_inode_free(), @inode may still be referenced in a VFS path walk
++ * and calls to security_inode_permission() may be made during, or after,
++ * a call to security_inode_free(). For this reason the inode->i_security
++ * field is released via a call_rcu() callback and any LSMs which need to
++ * retain inode state for use in security_inode_permission() should only
++ * release that state in the inode_free_security_rcu() LSM hook callback.
+ */
+ void security_inode_free(struct inode *inode)
+ {
+ call_void_hook(inode_free_security, inode);
+- /*
+- * The inode may still be referenced in a path walk and
+- * a call to security_inode_permission() can be made
+- * after inode_free_security() is called. Ideally, the VFS
+- * wouldn't do this, but fixing that is a much harder
+- * job. For now, simply free the i_security via RCU, and
+- * leave the current inode->i_security pointer intact.
+- * The inode will be freed after the RCU grace period too.
+- */
+- if (inode->i_security)
+- call_rcu((struct rcu_head *)inode->i_security,
+- inode_free_by_rcu);
++ if (!inode->i_security)
++ return;
++ call_rcu((struct rcu_head *)inode->i_security, inode_free_by_rcu);
+ }
+
+ /**
+@@ -4673,6 +4676,28 @@ int security_socket_getpeersec_dgram(struct socket *sock,
+ }
+ EXPORT_SYMBOL(security_socket_getpeersec_dgram);
+
++/**
++ * lsm_sock_alloc - allocate a composite sock blob
++ * @sock: the sock that needs a blob
++ * @priority: allocation mode
++ *
++ * Allocate the sock blob for all the modules
++ *
++ * Returns 0, or -ENOMEM if memory can't be allocated.
++ */
++static int lsm_sock_alloc(struct sock *sock, gfp_t priority)
++{
++ if (blob_sizes.lbs_sock == 0) {
++ sock->sk_security = NULL;
++ return 0;
++ }
++
++ sock->sk_security = kzalloc(blob_sizes.lbs_sock, priority);
++ if (sock->sk_security == NULL)
++ return -ENOMEM;
++ return 0;
++}
++
+ /**
+ * security_sk_alloc() - Allocate and initialize a sock's LSM blob
+ * @sk: sock
+@@ -4686,7 +4711,14 @@ EXPORT_SYMBOL(security_socket_getpeersec_dgram);
+ */
+ int security_sk_alloc(struct sock *sk, int family, gfp_t priority)
+ {
+- return call_int_hook(sk_alloc_security, sk, family, priority);
++ int rc = lsm_sock_alloc(sk, priority);
++
++ if (unlikely(rc))
++ return rc;
++ rc = call_int_hook(sk_alloc_security, sk, family, priority);
++ if (unlikely(rc))
++ security_sk_free(sk);
++ return rc;
+ }
+
+ /**
+@@ -4698,6 +4730,8 @@ int security_sk_alloc(struct sock *sk, int family, gfp_t priority)
+ void security_sk_free(struct sock *sk)
+ {
+ call_void_hook(sk_free_security, sk);
++ kfree(sk->sk_security);
++ sk->sk_security = NULL;
+ }
+
+ /**
+diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
+index 400eca4ad0fb6c..c11303d662d809 100644
+--- a/security/selinux/hooks.c
++++ b/security/selinux/hooks.c
+@@ -4594,7 +4594,7 @@ static int socket_sockcreate_sid(const struct task_security_struct *tsec,
+
+ static int sock_has_perm(struct sock *sk, u32 perms)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ struct common_audit_data ad;
+ struct lsm_network_audit net;
+
+@@ -4662,7 +4662,7 @@ static int selinux_socket_post_create(struct socket *sock, int family,
+ isec->initialized = LABEL_INITIALIZED;
+
+ if (sock->sk) {
+- sksec = sock->sk->sk_security;
++ sksec = selinux_sock(sock->sk);
+ sksec->sclass = sclass;
+ sksec->sid = sid;
+ /* Allows detection of the first association on this socket */
+@@ -4678,8 +4678,8 @@ static int selinux_socket_post_create(struct socket *sock, int family,
+ static int selinux_socket_socketpair(struct socket *socka,
+ struct socket *sockb)
+ {
+- struct sk_security_struct *sksec_a = socka->sk->sk_security;
+- struct sk_security_struct *sksec_b = sockb->sk->sk_security;
++ struct sk_security_struct *sksec_a = selinux_sock(socka->sk);
++ struct sk_security_struct *sksec_b = selinux_sock(sockb->sk);
+
+ sksec_a->peer_sid = sksec_b->sid;
+ sksec_b->peer_sid = sksec_a->sid;
+@@ -4694,7 +4694,7 @@ static int selinux_socket_socketpair(struct socket *socka,
+ static int selinux_socket_bind(struct socket *sock, struct sockaddr *address, int addrlen)
+ {
+ struct sock *sk = sock->sk;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ u16 family;
+ int err;
+
+@@ -4834,7 +4834,7 @@ static int selinux_socket_connect_helper(struct socket *sock,
+ struct sockaddr *address, int addrlen)
+ {
+ struct sock *sk = sock->sk;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ int err;
+
+ err = sock_has_perm(sk, SOCKET__CONNECT);
+@@ -5012,9 +5012,9 @@ static int selinux_socket_unix_stream_connect(struct sock *sock,
+ struct sock *other,
+ struct sock *newsk)
+ {
+- struct sk_security_struct *sksec_sock = sock->sk_security;
+- struct sk_security_struct *sksec_other = other->sk_security;
+- struct sk_security_struct *sksec_new = newsk->sk_security;
++ struct sk_security_struct *sksec_sock = selinux_sock(sock);
++ struct sk_security_struct *sksec_other = selinux_sock(other);
++ struct sk_security_struct *sksec_new = selinux_sock(newsk);
+ struct common_audit_data ad;
+ struct lsm_network_audit net;
+ int err;
+@@ -5043,8 +5043,8 @@ static int selinux_socket_unix_stream_connect(struct sock *sock,
+ static int selinux_socket_unix_may_send(struct socket *sock,
+ struct socket *other)
+ {
+- struct sk_security_struct *ssec = sock->sk->sk_security;
+- struct sk_security_struct *osec = other->sk->sk_security;
++ struct sk_security_struct *ssec = selinux_sock(sock->sk);
++ struct sk_security_struct *osec = selinux_sock(other->sk);
+ struct common_audit_data ad;
+ struct lsm_network_audit net;
+
+@@ -5081,7 +5081,7 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb,
+ u16 family)
+ {
+ int err = 0;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ u32 sk_sid = sksec->sid;
+ struct common_audit_data ad;
+ struct lsm_network_audit net;
+@@ -5110,7 +5110,7 @@ static int selinux_sock_rcv_skb_compat(struct sock *sk, struct sk_buff *skb,
+ static int selinux_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+ {
+ int err, peerlbl_active, secmark_active;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ u16 family = sk->sk_family;
+ u32 sk_sid = sksec->sid;
+ struct common_audit_data ad;
+@@ -5178,7 +5178,7 @@ static int selinux_socket_getpeersec_stream(struct socket *sock,
+ int err = 0;
+ char *scontext = NULL;
+ u32 scontext_len;
+- struct sk_security_struct *sksec = sock->sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sock->sk);
+ u32 peer_sid = SECSID_NULL;
+
+ if (sksec->sclass == SECCLASS_UNIX_STREAM_SOCKET ||
+@@ -5238,34 +5238,27 @@ static int selinux_socket_getpeersec_dgram(struct socket *sock,
+
+ static int selinux_sk_alloc_security(struct sock *sk, int family, gfp_t priority)
+ {
+- struct sk_security_struct *sksec;
+-
+- sksec = kzalloc(sizeof(*sksec), priority);
+- if (!sksec)
+- return -ENOMEM;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ sksec->peer_sid = SECINITSID_UNLABELED;
+ sksec->sid = SECINITSID_UNLABELED;
+ sksec->sclass = SECCLASS_SOCKET;
+ selinux_netlbl_sk_security_reset(sksec);
+- sk->sk_security = sksec;
+
+ return 0;
+ }
+
+ static void selinux_sk_free_security(struct sock *sk)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+- sk->sk_security = NULL;
+ selinux_netlbl_sk_security_free(sksec);
+- kfree(sksec);
+ }
+
+ static void selinux_sk_clone_security(const struct sock *sk, struct sock *newsk)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
+- struct sk_security_struct *newsksec = newsk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
++ struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+ newsksec->sid = sksec->sid;
+ newsksec->peer_sid = sksec->peer_sid;
+@@ -5279,7 +5272,7 @@ static void selinux_sk_getsecid(const struct sock *sk, u32 *secid)
+ if (!sk)
+ *secid = SECINITSID_ANY_SOCKET;
+ else {
+- const struct sk_security_struct *sksec = sk->sk_security;
++ const struct sk_security_struct *sksec = selinux_sock(sk);
+
+ *secid = sksec->sid;
+ }
+@@ -5289,7 +5282,7 @@ static void selinux_sock_graft(struct sock *sk, struct socket *parent)
+ {
+ struct inode_security_struct *isec =
+ inode_security_novalidate(SOCK_INODE(parent));
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ if (sk->sk_family == PF_INET || sk->sk_family == PF_INET6 ||
+ sk->sk_family == PF_UNIX)
+@@ -5306,7 +5299,7 @@ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc,
+ {
+ struct sock *sk = asoc->base.sk;
+ u16 family = sk->sk_family;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ struct common_audit_data ad;
+ struct lsm_network_audit net;
+ int err;
+@@ -5361,7 +5354,7 @@ static int selinux_sctp_process_new_assoc(struct sctp_association *asoc,
+ static int selinux_sctp_assoc_request(struct sctp_association *asoc,
+ struct sk_buff *skb)
+ {
+- struct sk_security_struct *sksec = asoc->base.sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(asoc->base.sk);
+ u32 conn_sid;
+ int err;
+
+@@ -5394,7 +5387,7 @@ static int selinux_sctp_assoc_request(struct sctp_association *asoc,
+ static int selinux_sctp_assoc_established(struct sctp_association *asoc,
+ struct sk_buff *skb)
+ {
+- struct sk_security_struct *sksec = asoc->base.sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(asoc->base.sk);
+
+ if (!selinux_policycap_extsockclass())
+ return 0;
+@@ -5493,8 +5486,8 @@ static int selinux_sctp_bind_connect(struct sock *sk, int optname,
+ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk,
+ struct sock *newsk)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
+- struct sk_security_struct *newsksec = newsk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
++ struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+ /* If policy does not support SECCLASS_SCTP_SOCKET then call
+ * the non-sctp clone version.
+@@ -5510,8 +5503,8 @@ static void selinux_sctp_sk_clone(struct sctp_association *asoc, struct sock *sk
+
+ static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
+ {
+- struct sk_security_struct *ssksec = ssk->sk_security;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *ssksec = selinux_sock(ssk);
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ ssksec->sclass = sksec->sclass;
+ ssksec->sid = sksec->sid;
+@@ -5526,7 +5519,7 @@ static int selinux_mptcp_add_subflow(struct sock *sk, struct sock *ssk)
+ static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+ struct request_sock *req)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ int err;
+ u16 family = req->rsk_ops->family;
+ u32 connsid;
+@@ -5547,7 +5540,7 @@ static int selinux_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+ static void selinux_inet_csk_clone(struct sock *newsk,
+ const struct request_sock *req)
+ {
+- struct sk_security_struct *newsksec = newsk->sk_security;
++ struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+ newsksec->sid = req->secid;
+ newsksec->peer_sid = req->peer_secid;
+@@ -5564,7 +5557,7 @@ static void selinux_inet_csk_clone(struct sock *newsk,
+ static void selinux_inet_conn_established(struct sock *sk, struct sk_buff *skb)
+ {
+ u16 family = sk->sk_family;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ /* handle mapped IPv4 packets arriving via IPv6 sockets */
+ if (family == PF_INET6 && skb->protocol == htons(ETH_P_IP))
+@@ -5639,7 +5632,7 @@ static int selinux_tun_dev_attach_queue(void *security)
+ static int selinux_tun_dev_attach(struct sock *sk, void *security)
+ {
+ struct tun_security_struct *tunsec = security;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ /* we don't currently perform any NetLabel based labeling here and it
+ * isn't clear that we would want to do so anyway; while we could apply
+@@ -5762,7 +5755,7 @@ static unsigned int selinux_ip_output(void *priv, struct sk_buff *skb,
+ return NF_ACCEPT;
+
+ /* standard practice, label using the parent socket */
+- sksec = sk->sk_security;
++ sksec = selinux_sock(sk);
+ sid = sksec->sid;
+ } else
+ sid = SECINITSID_KERNEL;
+@@ -5785,7 +5778,7 @@ static unsigned int selinux_ip_postroute_compat(struct sk_buff *skb,
+ sk = skb_to_full_sk(skb);
+ if (sk == NULL)
+ return NF_ACCEPT;
+- sksec = sk->sk_security;
++ sksec = selinux_sock(sk);
+
+ ad_net_init_from_iif(&ad, &net, state->out->ifindex, state->pf);
+ if (selinux_parse_skb(skb, &ad, NULL, 0, &proto))
+@@ -5874,7 +5867,7 @@ static unsigned int selinux_ip_postroute(void *priv,
+ u32 skb_sid;
+ struct sk_security_struct *sksec;
+
+- sksec = sk->sk_security;
++ sksec = selinux_sock(sk);
+ if (selinux_skb_peerlbl_sid(skb, family, &skb_sid))
+ return NF_DROP;
+ /* At this point, if the returned skb peerlbl is SECSID_NULL
+@@ -5903,7 +5896,7 @@ static unsigned int selinux_ip_postroute(void *priv,
+ } else {
+ /* Locally generated packet, fetch the security label from the
+ * associated socket. */
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ peer_sid = sksec->sid;
+ secmark_perm = PACKET__SEND;
+ }
+@@ -5946,7 +5939,7 @@ static int selinux_netlink_send(struct sock *sk, struct sk_buff *skb)
+ unsigned int data_len = skb->len;
+ unsigned char *data = skb->data;
+ struct nlmsghdr *nlh;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ u16 sclass = sksec->sclass;
+ u32 perm;
+
+@@ -7004,6 +6997,7 @@ struct lsm_blob_sizes selinux_blob_sizes __ro_after_init = {
+ .lbs_inode = sizeof(struct inode_security_struct),
+ .lbs_ipc = sizeof(struct ipc_security_struct),
+ .lbs_msg_msg = sizeof(struct msg_security_struct),
++ .lbs_sock = sizeof(struct sk_security_struct),
+ .lbs_superblock = sizeof(struct superblock_security_struct),
+ .lbs_xattr_count = SELINUX_INODE_INIT_XATTRS,
+ };
+diff --git a/security/selinux/include/objsec.h b/security/selinux/include/objsec.h
+index dea1d6f3ed2d3b..b074099acbaf79 100644
+--- a/security/selinux/include/objsec.h
++++ b/security/selinux/include/objsec.h
+@@ -195,4 +195,9 @@ selinux_superblock(const struct super_block *superblock)
+ return superblock->s_security + selinux_blob_sizes.lbs_superblock;
+ }
+
++static inline struct sk_security_struct *selinux_sock(const struct sock *sock)
++{
++ return sock->sk_security + selinux_blob_sizes.lbs_sock;
++}
++
+ #endif /* _SELINUX_OBJSEC_H_ */
+diff --git a/security/selinux/netlabel.c b/security/selinux/netlabel.c
+index 55885634e8804a..fbe5f8c29f8137 100644
+--- a/security/selinux/netlabel.c
++++ b/security/selinux/netlabel.c
+@@ -17,6 +17,7 @@
+ #include <linux/gfp.h>
+ #include <linux/ip.h>
+ #include <linux/ipv6.h>
++#include <linux/lsm_hooks.h>
+ #include <net/sock.h>
+ #include <net/netlabel.h>
+ #include <net/ip.h>
+@@ -68,7 +69,7 @@ static int selinux_netlbl_sidlookup_cached(struct sk_buff *skb,
+ static struct netlbl_lsm_secattr *selinux_netlbl_sock_genattr(struct sock *sk)
+ {
+ int rc;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ struct netlbl_lsm_secattr *secattr;
+
+ if (sksec->nlbl_secattr != NULL)
+@@ -100,7 +101,7 @@ static struct netlbl_lsm_secattr *selinux_netlbl_sock_getattr(
+ const struct sock *sk,
+ u32 sid)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ struct netlbl_lsm_secattr *secattr = sksec->nlbl_secattr;
+
+ if (secattr == NULL)
+@@ -240,7 +241,7 @@ int selinux_netlbl_skbuff_setsid(struct sk_buff *skb,
+ * being labeled by it's parent socket, if it is just exit */
+ sk = skb_to_full_sk(skb);
+ if (sk != NULL) {
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ if (sksec->nlbl_state != NLBL_REQSKB)
+ return 0;
+@@ -277,7 +278,7 @@ int selinux_netlbl_sctp_assoc_request(struct sctp_association *asoc,
+ {
+ int rc;
+ struct netlbl_lsm_secattr secattr;
+- struct sk_security_struct *sksec = asoc->base.sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(asoc->base.sk);
+ struct sockaddr_in addr4;
+ struct sockaddr_in6 addr6;
+
+@@ -356,7 +357,7 @@ int selinux_netlbl_inet_conn_request(struct request_sock *req, u16 family)
+ */
+ void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ if (family == PF_INET)
+ sksec->nlbl_state = NLBL_LABELED;
+@@ -374,8 +375,8 @@ void selinux_netlbl_inet_csk_clone(struct sock *sk, u16 family)
+ */
+ void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
+- struct sk_security_struct *newsksec = newsk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
++ struct sk_security_struct *newsksec = selinux_sock(newsk);
+
+ newsksec->nlbl_state = sksec->nlbl_state;
+ }
+@@ -393,7 +394,7 @@ void selinux_netlbl_sctp_sk_clone(struct sock *sk, struct sock *newsk)
+ int selinux_netlbl_socket_post_create(struct sock *sk, u16 family)
+ {
+ int rc;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ struct netlbl_lsm_secattr *secattr;
+
+ if (family != PF_INET && family != PF_INET6)
+@@ -510,7 +511,7 @@ int selinux_netlbl_socket_setsockopt(struct socket *sock,
+ {
+ int rc = 0;
+ struct sock *sk = sock->sk;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ struct netlbl_lsm_secattr secattr;
+
+ if (selinux_netlbl_option(level, optname) &&
+@@ -548,7 +549,7 @@ static int selinux_netlbl_socket_connect_helper(struct sock *sk,
+ struct sockaddr *addr)
+ {
+ int rc;
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+ struct netlbl_lsm_secattr *secattr;
+
+ /* connected sockets are allowed to disconnect when the address family
+@@ -587,7 +588,7 @@ static int selinux_netlbl_socket_connect_helper(struct sock *sk,
+ int selinux_netlbl_socket_connect_locked(struct sock *sk,
+ struct sockaddr *addr)
+ {
+- struct sk_security_struct *sksec = sk->sk_security;
++ struct sk_security_struct *sksec = selinux_sock(sk);
+
+ if (sksec->nlbl_state != NLBL_REQSKB &&
+ sksec->nlbl_state != NLBL_CONNLABELED)
+diff --git a/security/smack/smack.h b/security/smack/smack.h
+index 041688e5a77a3e..297f21446f4568 100644
+--- a/security/smack/smack.h
++++ b/security/smack/smack.h
+@@ -355,6 +355,11 @@ static inline struct superblock_smack *smack_superblock(
+ return superblock->s_security + smack_blob_sizes.lbs_superblock;
+ }
+
++static inline struct socket_smack *smack_sock(const struct sock *sock)
++{
++ return sock->sk_security + smack_blob_sizes.lbs_sock;
++}
++
+ /*
+ * Is the directory transmuting?
+ */
+diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
+index 002a1b9ed83a56..6ec9a40f3ec592 100644
+--- a/security/smack/smack_lsm.c
++++ b/security/smack/smack_lsm.c
+@@ -1606,7 +1606,7 @@ static int smack_inode_getsecurity(struct mnt_idmap *idmap,
+ if (sock == NULL || sock->sk == NULL)
+ return -EOPNOTSUPP;
+
+- ssp = sock->sk->sk_security;
++ ssp = smack_sock(sock->sk);
+
+ if (strcmp(name, XATTR_SMACK_IPIN) == 0)
+ isp = ssp->smk_in;
+@@ -1994,7 +1994,7 @@ static int smack_file_receive(struct file *file)
+
+ if (inode->i_sb->s_magic == SOCKFS_MAGIC) {
+ sock = SOCKET_I(inode);
+- ssp = sock->sk->sk_security;
++ ssp = smack_sock(sock->sk);
+ tsp = smack_cred(current_cred());
+ /*
+ * If the receiving process can't write to the
+@@ -2409,11 +2409,7 @@ static void smack_task_to_inode(struct task_struct *p, struct inode *inode)
+ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags)
+ {
+ struct smack_known *skp = smk_of_current();
+- struct socket_smack *ssp;
+-
+- ssp = kzalloc(sizeof(struct socket_smack), gfp_flags);
+- if (ssp == NULL)
+- return -ENOMEM;
++ struct socket_smack *ssp = smack_sock(sk);
+
+ /*
+ * Sockets created by kernel threads receive web label.
+@@ -2427,11 +2423,10 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags)
+ }
+ ssp->smk_packet = NULL;
+
+- sk->sk_security = ssp;
+-
+ return 0;
+ }
+
++#ifdef SMACK_IPV6_PORT_LABELING
+ /**
+ * smack_sk_free_security - Free a socket blob
+ * @sk: the socket
+@@ -2440,7 +2435,6 @@ static int smack_sk_alloc_security(struct sock *sk, int family, gfp_t gfp_flags)
+ */
+ static void smack_sk_free_security(struct sock *sk)
+ {
+-#ifdef SMACK_IPV6_PORT_LABELING
+ struct smk_port_label *spp;
+
+ if (sk->sk_family == PF_INET6) {
+@@ -2453,9 +2447,8 @@ static void smack_sk_free_security(struct sock *sk)
+ }
+ rcu_read_unlock();
+ }
+-#endif
+- kfree(sk->sk_security);
+ }
++#endif
+
+ /**
+ * smack_sk_clone_security - Copy security context
+@@ -2466,8 +2459,8 @@ static void smack_sk_free_security(struct sock *sk)
+ */
+ static void smack_sk_clone_security(const struct sock *sk, struct sock *newsk)
+ {
+- struct socket_smack *ssp_old = sk->sk_security;
+- struct socket_smack *ssp_new = newsk->sk_security;
++ struct socket_smack *ssp_old = smack_sock(sk);
++ struct socket_smack *ssp_new = smack_sock(newsk);
+
+ *ssp_new = *ssp_old;
+ }
+@@ -2583,7 +2576,7 @@ static struct smack_known *smack_ipv6host_label(struct sockaddr_in6 *sip)
+ */
+ static int smack_netlbl_add(struct sock *sk)
+ {
+- struct socket_smack *ssp = sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sk);
+ struct smack_known *skp = ssp->smk_out;
+ int rc;
+
+@@ -2616,7 +2609,7 @@ static int smack_netlbl_add(struct sock *sk)
+ */
+ static void smack_netlbl_delete(struct sock *sk)
+ {
+- struct socket_smack *ssp = sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sk);
+
+ /*
+ * Take the label off the socket if one is set.
+@@ -2648,7 +2641,7 @@ static int smk_ipv4_check(struct sock *sk, struct sockaddr_in *sap)
+ struct smack_known *skp;
+ int rc = 0;
+ struct smack_known *hkp;
+- struct socket_smack *ssp = sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sk);
+ struct smk_audit_info ad;
+
+ rcu_read_lock();
+@@ -2721,7 +2714,7 @@ static void smk_ipv6_port_label(struct socket *sock, struct sockaddr *address)
+ {
+ struct sock *sk = sock->sk;
+ struct sockaddr_in6 *addr6;
+- struct socket_smack *ssp = sock->sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sock->sk);
+ struct smk_port_label *spp;
+ unsigned short port = 0;
+
+@@ -2809,7 +2802,7 @@ static int smk_ipv6_port_check(struct sock *sk, struct sockaddr_in6 *address,
+ int act)
+ {
+ struct smk_port_label *spp;
+- struct socket_smack *ssp = sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sk);
+ struct smack_known *skp = NULL;
+ unsigned short port;
+ struct smack_known *object;
+@@ -2912,7 +2905,7 @@ static int smack_inode_setsecurity(struct inode *inode, const char *name,
+ if (sock == NULL || sock->sk == NULL)
+ return -EOPNOTSUPP;
+
+- ssp = sock->sk->sk_security;
++ ssp = smack_sock(sock->sk);
+
+ if (strcmp(name, XATTR_SMACK_IPIN) == 0)
+ ssp->smk_in = skp;
+@@ -2960,7 +2953,7 @@ static int smack_socket_post_create(struct socket *sock, int family,
+ * Sockets created by kernel threads receive web label.
+ */
+ if (unlikely(current->flags & PF_KTHREAD)) {
+- ssp = sock->sk->sk_security;
++ ssp = smack_sock(sock->sk);
+ ssp->smk_in = &smack_known_web;
+ ssp->smk_out = &smack_known_web;
+ }
+@@ -2985,8 +2978,8 @@ static int smack_socket_post_create(struct socket *sock, int family,
+ static int smack_socket_socketpair(struct socket *socka,
+ struct socket *sockb)
+ {
+- struct socket_smack *asp = socka->sk->sk_security;
+- struct socket_smack *bsp = sockb->sk->sk_security;
++ struct socket_smack *asp = smack_sock(socka->sk);
++ struct socket_smack *bsp = smack_sock(sockb->sk);
+
+ asp->smk_packet = bsp->smk_out;
+ bsp->smk_packet = asp->smk_out;
+@@ -3049,7 +3042,7 @@ static int smack_socket_connect(struct socket *sock, struct sockaddr *sap,
+ if (__is_defined(SMACK_IPV6_SECMARK_LABELING))
+ rsp = smack_ipv6host_label(sip);
+ if (rsp != NULL) {
+- struct socket_smack *ssp = sock->sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sock->sk);
+
+ rc = smk_ipv6_check(ssp->smk_out, rsp, sip,
+ SMK_CONNECTING);
+@@ -3844,9 +3837,9 @@ static int smack_unix_stream_connect(struct sock *sock,
+ {
+ struct smack_known *skp;
+ struct smack_known *okp;
+- struct socket_smack *ssp = sock->sk_security;
+- struct socket_smack *osp = other->sk_security;
+- struct socket_smack *nsp = newsk->sk_security;
++ struct socket_smack *ssp = smack_sock(sock);
++ struct socket_smack *osp = smack_sock(other);
++ struct socket_smack *nsp = smack_sock(newsk);
+ struct smk_audit_info ad;
+ int rc = 0;
+ #ifdef CONFIG_AUDIT
+@@ -3898,8 +3891,8 @@ static int smack_unix_stream_connect(struct sock *sock,
+ */
+ static int smack_unix_may_send(struct socket *sock, struct socket *other)
+ {
+- struct socket_smack *ssp = sock->sk->sk_security;
+- struct socket_smack *osp = other->sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sock->sk);
++ struct socket_smack *osp = smack_sock(other->sk);
+ struct smk_audit_info ad;
+ int rc;
+
+@@ -3936,7 +3929,7 @@ static int smack_socket_sendmsg(struct socket *sock, struct msghdr *msg,
+ struct sockaddr_in6 *sap = (struct sockaddr_in6 *) msg->msg_name;
+ #endif
+ #ifdef SMACK_IPV6_SECMARK_LABELING
+- struct socket_smack *ssp = sock->sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sock->sk);
+ struct smack_known *rsp;
+ #endif
+ int rc = 0;
+@@ -4148,7 +4141,7 @@ static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family,
+ netlbl_secattr_init(&secattr);
+
+ if (sk)
+- ssp = sk->sk_security;
++ ssp = smack_sock(sk);
+
+ if (netlbl_skbuff_getattr(skb, family, &secattr) == 0) {
+ skp = smack_from_secattr(&secattr, ssp);
+@@ -4170,7 +4163,7 @@ static struct smack_known *smack_from_netlbl(const struct sock *sk, u16 family,
+ */
+ static int smack_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+ {
+- struct socket_smack *ssp = sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sk);
+ struct smack_known *skp = NULL;
+ int rc = 0;
+ struct smk_audit_info ad;
+@@ -4274,7 +4267,7 @@ static int smack_socket_getpeersec_stream(struct socket *sock,
+ u32 slen = 1;
+ int rc = 0;
+
+- ssp = sock->sk->sk_security;
++ ssp = smack_sock(sock->sk);
+ if (ssp->smk_packet != NULL) {
+ rcp = ssp->smk_packet->smk_known;
+ slen = strlen(rcp) + 1;
+@@ -4324,7 +4317,7 @@ static int smack_socket_getpeersec_dgram(struct socket *sock,
+
+ switch (family) {
+ case PF_UNIX:
+- ssp = sock->sk->sk_security;
++ ssp = smack_sock(sock->sk);
+ s = ssp->smk_out->smk_secid;
+ break;
+ case PF_INET:
+@@ -4373,7 +4366,7 @@ static void smack_sock_graft(struct sock *sk, struct socket *parent)
+ (sk->sk_family != PF_INET && sk->sk_family != PF_INET6))
+ return;
+
+- ssp = sk->sk_security;
++ ssp = smack_sock(sk);
+ ssp->smk_in = skp;
+ ssp->smk_out = skp;
+ /* cssp->smk_packet is already set in smack_inet_csk_clone() */
+@@ -4393,7 +4386,7 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+ {
+ u16 family = sk->sk_family;
+ struct smack_known *skp;
+- struct socket_smack *ssp = sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sk);
+ struct sockaddr_in addr;
+ struct iphdr *hdr;
+ struct smack_known *hskp;
+@@ -4479,7 +4472,7 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+ static void smack_inet_csk_clone(struct sock *sk,
+ const struct request_sock *req)
+ {
+- struct socket_smack *ssp = sk->sk_security;
++ struct socket_smack *ssp = smack_sock(sk);
+ struct smack_known *skp;
+
+ if (req->peer_secid != 0) {
+@@ -5049,6 +5042,7 @@ struct lsm_blob_sizes smack_blob_sizes __ro_after_init = {
+ .lbs_inode = sizeof(struct inode_smack),
+ .lbs_ipc = sizeof(struct smack_known *),
+ .lbs_msg_msg = sizeof(struct smack_known *),
++ .lbs_sock = sizeof(struct socket_smack),
+ .lbs_superblock = sizeof(struct superblock_smack),
+ .lbs_xattr_count = SMACK_INODE_INIT_XATTRS,
+ };
+@@ -5173,7 +5167,9 @@ static struct security_hook_list smack_hooks[] __ro_after_init = {
+ LSM_HOOK_INIT(socket_getpeersec_stream, smack_socket_getpeersec_stream),
+ LSM_HOOK_INIT(socket_getpeersec_dgram, smack_socket_getpeersec_dgram),
+ LSM_HOOK_INIT(sk_alloc_security, smack_sk_alloc_security),
++#ifdef SMACK_IPV6_PORT_LABELING
+ LSM_HOOK_INIT(sk_free_security, smack_sk_free_security),
++#endif
+ LSM_HOOK_INIT(sk_clone_security, smack_sk_clone_security),
+ LSM_HOOK_INIT(sock_graft, smack_sock_graft),
+ LSM_HOOK_INIT(inet_conn_request, smack_inet_conn_request),
+diff --git a/security/smack/smack_netfilter.c b/security/smack/smack_netfilter.c
+index b945c1d3a7431a..bad71b7e648da7 100644
+--- a/security/smack/smack_netfilter.c
++++ b/security/smack/smack_netfilter.c
+@@ -26,8 +26,8 @@ static unsigned int smack_ip_output(void *priv,
+ struct socket_smack *ssp;
+ struct smack_known *skp;
+
+- if (sk && sk->sk_security) {
+- ssp = sk->sk_security;
++ if (sk) {
++ ssp = smack_sock(sk);
+ skp = ssp->smk_out;
+ skb->secmark = skp->smk_secid;
+ }
+diff --git a/security/smack/smackfs.c b/security/smack/smackfs.c
+index e22aad7604e8ac..5dd1e164f9b13d 100644
+--- a/security/smack/smackfs.c
++++ b/security/smack/smackfs.c
+@@ -932,7 +932,7 @@ static ssize_t smk_set_cipso(struct file *file, const char __user *buf,
+ }
+ if (rc >= 0) {
+ old_cat = skp->smk_netlabel.attr.mls.cat;
+- skp->smk_netlabel.attr.mls.cat = ncats.attr.mls.cat;
++ rcu_assign_pointer(skp->smk_netlabel.attr.mls.cat, ncats.attr.mls.cat);
+ skp->smk_netlabel.attr.mls.lvl = ncats.attr.mls.lvl;
+ synchronize_rcu();
+ netlbl_catmap_free(old_cat);
+diff --git a/sound/pci/hda/cs35l41_hda_spi.c b/sound/pci/hda/cs35l41_hda_spi.c
+index b76c0dfd5fefc4..f8c356ad0d340f 100644
+--- a/sound/pci/hda/cs35l41_hda_spi.c
++++ b/sound/pci/hda/cs35l41_hda_spi.c
+@@ -38,6 +38,7 @@ static const struct spi_device_id cs35l41_hda_spi_id[] = {
+ { "cs35l41-hda", 0 },
+ {}
+ };
++MODULE_DEVICE_TABLE(spi, cs35l41_hda_spi_id);
+
+ static const struct acpi_device_id cs35l41_acpi_hda_match[] = {
+ { "CSC3551", 0 },
+diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
+index 9e88d39eac1e22..0676b416056607 100644
+--- a/sound/pci/hda/tas2781_hda_i2c.c
++++ b/sound/pci/hda/tas2781_hda_i2c.c
+@@ -822,7 +822,7 @@ static int tas2781_hda_i2c_probe(struct i2c_client *clt)
+ } else
+ return -ENODEV;
+
+- tas_hda->priv->irq_info.irq = clt->irq;
++ tas_hda->priv->irq = clt->irq;
+ ret = tas2781_read_acpi(tas_hda->priv, device_name);
+ if (ret)
+ return dev_err_probe(tas_hda->dev, ret,
+diff --git a/sound/soc/codecs/rt5682.c b/sound/soc/codecs/rt5682.c
+index e3aca9c785a079..aa163ec4086223 100644
+--- a/sound/soc/codecs/rt5682.c
++++ b/sound/soc/codecs/rt5682.c
+@@ -2903,8 +2903,10 @@ int rt5682_register_dai_clks(struct rt5682_priv *rt5682)
+ }
+
+ if (dev->of_node) {
+- devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
++ ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get,
+ dai_clk_hw);
++ if (ret)
++ return ret;
+ } else {
+ ret = devm_clk_hw_register_clkdev(dev, dai_clk_hw,
+ init.name,
+diff --git a/sound/soc/codecs/rt5682s.c b/sound/soc/codecs/rt5682s.c
+index f50f196d700d72..ce2e88e066f3e5 100644
+--- a/sound/soc/codecs/rt5682s.c
++++ b/sound/soc/codecs/rt5682s.c
+@@ -2828,7 +2828,9 @@ static int rt5682s_register_dai_clks(struct snd_soc_component *component)
+ }
+
+ if (dev->of_node) {
+- devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, dai_clk_hw);
++ ret = devm_of_clk_add_hw_provider(dev, of_clk_hw_simple_get, dai_clk_hw);
++ if (ret)
++ return ret;
+ } else {
+ ret = devm_clk_hw_register_clkdev(dev, dai_clk_hw,
+ init.name, dev_name(dev));
+diff --git a/sound/soc/codecs/tas2781-comlib.c b/sound/soc/codecs/tas2781-comlib.c
+index 3aa81514dad76f..0444cf90c5119f 100644
+--- a/sound/soc/codecs/tas2781-comlib.c
++++ b/sound/soc/codecs/tas2781-comlib.c
+@@ -14,7 +14,6 @@
+ #include <linux/interrupt.h>
+ #include <linux/module.h>
+ #include <linux/of.h>
+-#include <linux/of_gpio.h>
+ #include <linux/of_irq.h>
+ #include <linux/regmap.h>
+ #include <linux/slab.h>
+@@ -406,8 +405,6 @@ EXPORT_SYMBOL_GPL(tasdevice_dsp_remove);
+
+ void tasdevice_remove(struct tasdevice_priv *tas_priv)
+ {
+- if (gpio_is_valid(tas_priv->irq_info.irq_gpio))
+- gpio_free(tas_priv->irq_info.irq_gpio);
+ mutex_destroy(&tas_priv->codec_lock);
+ }
+ EXPORT_SYMBOL_GPL(tasdevice_remove);
+diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
+index 8f9a3ae7153e94..f3a7605f071043 100644
+--- a/sound/soc/codecs/tas2781-fmwlib.c
++++ b/sound/soc/codecs/tas2781-fmwlib.c
+@@ -13,7 +13,6 @@
+ #include <linux/interrupt.h>
+ #include <linux/module.h>
+ #include <linux/of.h>
+-#include <linux/of_gpio.h>
+ #include <linux/of_irq.h>
+ #include <linux/regmap.h>
+ #include <linux/slab.h>
+diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
+index c64d458e524e2c..edd1ad3062c886 100644
+--- a/sound/soc/codecs/tas2781-i2c.c
++++ b/sound/soc/codecs/tas2781-i2c.c
+@@ -21,7 +21,7 @@
+ #include <linux/interrupt.h>
+ #include <linux/module.h>
+ #include <linux/of.h>
+-#include <linux/of_gpio.h>
++#include <linux/of_address.h>
+ #include <linux/of_irq.h>
+ #include <linux/regmap.h>
+ #include <linux/slab.h>
+@@ -618,7 +618,7 @@ static void tasdevice_parse_dt(struct tasdevice_priv *tas_priv)
+ {
+ struct i2c_client *client = (struct i2c_client *)tas_priv->client;
+ unsigned int dev_addrs[TASDEVICE_MAX_CHANNELS];
+- int rc, i, ndev = 0;
++ int i, ndev = 0;
+
+ if (tas_priv->isacpi) {
+ ndev = device_property_read_u32_array(&client->dev,
+@@ -633,64 +633,34 @@ static void tasdevice_parse_dt(struct tasdevice_priv *tas_priv)
+ "ti,audio-slots", dev_addrs, ndev);
+ }
+
+- tas_priv->irq_info.irq_gpio =
++ tas_priv->irq =
+ acpi_dev_gpio_irq_get(ACPI_COMPANION(&client->dev), 0);
+- } else {
++ } else if (IS_ENABLED(CONFIG_OF)) {
+ struct device_node *np = tas_priv->dev->of_node;
+-#ifdef CONFIG_OF
+- const __be32 *reg, *reg_end;
+- int len, sw, aw;
+-
+- aw = of_n_addr_cells(np);
+- sw = of_n_size_cells(np);
+- if (sw == 0) {
+- reg = (const __be32 *)of_get_property(np,
+- "reg", &len);
+- reg_end = reg + len/sizeof(*reg);
+- ndev = 0;
+- do {
+- dev_addrs[ndev] = of_read_number(reg, aw);
+- reg += aw;
+- ndev++;
+- } while (reg < reg_end);
+- } else {
+- ndev = 1;
+- dev_addrs[0] = client->addr;
++ u64 addr;
++
++ for (i = 0; i < TASDEVICE_MAX_CHANNELS; i++) {
++ if (of_property_read_reg(np, i, &addr, NULL))
++ break;
++ dev_addrs[ndev++] = addr;
+ }
+-#else
++
++ tas_priv->irq = of_irq_get(np, 0);
++ } else {
+ ndev = 1;
+ dev_addrs[0] = client->addr;
+-#endif
+- tas_priv->irq_info.irq_gpio = of_irq_get(np, 0);
+ }
+ tas_priv->ndev = ndev;
+ for (i = 0; i < ndev; i++)
+ tas_priv->tasdevice[i].dev_addr = dev_addrs[i];
+
+ tas_priv->reset = devm_gpiod_get_optional(&client->dev,
+- "reset-gpios", GPIOD_OUT_HIGH);
++ "reset", GPIOD_OUT_HIGH);
+ if (IS_ERR(tas_priv->reset))
+ dev_err(tas_priv->dev, "%s Can't get reset GPIO\n",
+ __func__);
+
+ strcpy(tas_priv->dev_name, tasdevice_id[tas_priv->chip_id].name);
+-
+- if (gpio_is_valid(tas_priv->irq_info.irq_gpio)) {
+- rc = gpio_request(tas_priv->irq_info.irq_gpio,
+- "AUDEV-IRQ");
+- if (!rc) {
+- gpio_direction_input(
+- tas_priv->irq_info.irq_gpio);
+-
+- tas_priv->irq_info.irq =
+- gpio_to_irq(tas_priv->irq_info.irq_gpio);
+- } else
+- dev_err(tas_priv->dev, "%s: GPIO %d request error\n",
+- __func__, tas_priv->irq_info.irq_gpio);
+- } else
+- dev_err(tas_priv->dev,
+- "Looking up irq-gpio property failed %d\n",
+- tas_priv->irq_info.irq_gpio);
+ }
+
+ static int tasdevice_i2c_probe(struct i2c_client *i2c)
+diff --git a/sound/soc/loongson/loongson_card.c b/sound/soc/loongson/loongson_card.c
+index fae5e9312bf08c..2c8dbdba27c5f8 100644
+--- a/sound/soc/loongson/loongson_card.c
++++ b/sound/soc/loongson/loongson_card.c
+@@ -127,8 +127,8 @@ static int loongson_card_parse_of(struct loongson_card_data *data)
+ codec = of_get_child_by_name(dev->of_node, "codec");
+ if (!codec) {
+ dev_err(dev, "audio-codec property missing or invalid\n");
+- ret = -EINVAL;
+- goto err;
++ of_node_put(cpu);
++ return -EINVAL;
+ }
+
+ for (i = 0; i < card->num_links; i++) {
+diff --git a/tools/bpf/runqslower/Makefile b/tools/bpf/runqslower/Makefile
+index d8288936c9120f..c4f1f1735af659 100644
+--- a/tools/bpf/runqslower/Makefile
++++ b/tools/bpf/runqslower/Makefile
+@@ -15,6 +15,7 @@ INCLUDES := -I$(OUTPUT) -I$(BPF_INCLUDE) -I$(abspath ../../include/uapi)
+ CFLAGS := -g -Wall $(CLANG_CROSS_FLAGS)
+ CFLAGS += $(EXTRA_CFLAGS)
+ LDFLAGS += $(EXTRA_LDFLAGS)
++LDLIBS += -lelf -lz
+
+ # Try to detect best kernel BTF source
+ KERNEL_REL := $(shell uname -r)
+@@ -51,7 +52,7 @@ clean:
+ libbpf_hdrs: $(BPFOBJ)
+
+ $(OUTPUT)/runqslower: $(OUTPUT)/runqslower.o $(BPFOBJ)
+- $(QUIET_LINK)$(CC) $(CFLAGS) $^ -lelf -lz -o $@
++ $(QUIET_LINK)$(CC) $(CFLAGS) $(LDFLAGS) $^ $(LDLIBS) -o $@
+
+ $(OUTPUT)/runqslower.o: runqslower.h $(OUTPUT)/runqslower.skel.h \
+ $(OUTPUT)/runqslower.bpf.o | libbpf_hdrs
+diff --git a/tools/build/feature/test-all.c b/tools/build/feature/test-all.c
+index dd0a18c2ef8fc0..6f4bf386a3b5c4 100644
+--- a/tools/build/feature/test-all.c
++++ b/tools/build/feature/test-all.c
+@@ -134,10 +134,6 @@
+ #undef main
+ #endif
+
+-#define main main_test_libcapstone
+-# include "test-libcapstone.c"
+-#undef main
+-
+ #define main main_test_lzma
+ # include "test-lzma.c"
+ #undef main
+diff --git a/tools/include/nolibc/string.h b/tools/include/nolibc/string.h
+index f9ab28421e6dcd..9ec9c24f38c092 100644
+--- a/tools/include/nolibc/string.h
++++ b/tools/include/nolibc/string.h
+@@ -7,6 +7,7 @@
+ #ifndef _NOLIBC_STRING_H
+ #define _NOLIBC_STRING_H
+
++#include "arch.h"
+ #include "std.h"
+
+ static void *malloc(size_t len);
+diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
+index 5edb717647847b..3ecb33188336f6 100644
+--- a/tools/lib/bpf/libbpf.c
++++ b/tools/lib/bpf/libbpf.c
+@@ -473,8 +473,6 @@ struct bpf_program {
+ };
+
+ struct bpf_struct_ops {
+- const char *tname;
+- const struct btf_type *type;
+ struct bpf_program **progs;
+ __u32 *kern_func_off;
+ /* e.g. struct tcp_congestion_ops in bpf_prog's btf format */
+@@ -1059,11 +1057,14 @@ static int bpf_object_adjust_struct_ops_autoload(struct bpf_object *obj)
+ continue;
+
+ for (j = 0; j < obj->nr_maps; ++j) {
++ const struct btf_type *type;
++
+ map = &obj->maps[j];
+ if (!bpf_map__is_struct_ops(map))
+ continue;
+
+- vlen = btf_vlen(map->st_ops->type);
++ type = btf__type_by_id(obj->btf, map->st_ops->type_id);
++ vlen = btf_vlen(type);
+ for (k = 0; k < vlen; ++k) {
+ slot_prog = map->st_ops->progs[k];
+ if (prog != slot_prog)
+@@ -1097,8 +1098,8 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
+ int err;
+
+ st_ops = map->st_ops;
+- type = st_ops->type;
+- tname = st_ops->tname;
++ type = btf__type_by_id(btf, st_ops->type_id);
++ tname = btf__name_by_offset(btf, type->name_off);
+ err = find_struct_ops_kern_types(obj, tname, &mod_btf,
+ &kern_type, &kern_type_id,
+ &kern_vtype, &kern_vtype_id,
+@@ -1398,8 +1399,6 @@ static int init_struct_ops_maps(struct bpf_object *obj, const char *sec_name,
+ memcpy(st_ops->data,
+ data->d_buf + vsi->offset,
+ type->size);
+- st_ops->tname = tname;
+- st_ops->type = type;
+ st_ops->type_id = type_id;
+
+ pr_debug("struct_ops init: struct %s(type_id=%u) %s found at offset %u\n",
+@@ -7867,16 +7866,19 @@ static int bpf_object_init_progs(struct bpf_object *obj, const struct bpf_object
+ }
+
+ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf, size_t obj_buf_sz,
++ const char *obj_name,
+ const struct bpf_object_open_opts *opts)
+ {
+- const char *obj_name, *kconfig, *btf_tmp_path, *token_path;
++ const char *kconfig, *btf_tmp_path, *token_path;
+ struct bpf_object *obj;
+- char tmp_name[64];
+ int err;
+ char *log_buf;
+ size_t log_size;
+ __u32 log_level;
+
++ if (obj_buf && !obj_name)
++ return ERR_PTR(-EINVAL);
++
+ if (elf_version(EV_CURRENT) == EV_NONE) {
+ pr_warn("failed to init libelf for %s\n",
+ path ? : "(mem buf)");
+@@ -7886,16 +7888,12 @@ static struct bpf_object *bpf_object_open(const char *path, const void *obj_buf,
+ if (!OPTS_VALID(opts, bpf_object_open_opts))
+ return ERR_PTR(-EINVAL);
+
+- obj_name = OPTS_GET(opts, object_name, NULL);
++ obj_name = OPTS_GET(opts, object_name, NULL) ?: obj_name;
+ if (obj_buf) {
+- if (!obj_name) {
+- snprintf(tmp_name, sizeof(tmp_name), "%lx-%lx",
+- (unsigned long)obj_buf,
+- (unsigned long)obj_buf_sz);
+- obj_name = tmp_name;
+- }
+ path = obj_name;
+ pr_debug("loading object '%s' from buffer\n", obj_name);
++ } else {
++ pr_debug("loading object from %s\n", path);
+ }
+
+ log_buf = OPTS_GET(opts, kernel_log_buf, NULL);
+@@ -7979,9 +7977,7 @@ bpf_object__open_file(const char *path, const struct bpf_object_open_opts *opts)
+ if (!path)
+ return libbpf_err_ptr(-EINVAL);
+
+- pr_debug("loading %s\n", path);
+-
+- return libbpf_ptr(bpf_object_open(path, NULL, 0, opts));
++ return libbpf_ptr(bpf_object_open(path, NULL, 0, NULL, opts));
+ }
+
+ struct bpf_object *bpf_object__open(const char *path)
+@@ -7993,10 +7989,15 @@ struct bpf_object *
+ bpf_object__open_mem(const void *obj_buf, size_t obj_buf_sz,
+ const struct bpf_object_open_opts *opts)
+ {
++ char tmp_name[64];
++
+ if (!obj_buf || obj_buf_sz == 0)
+ return libbpf_err_ptr(-EINVAL);
+
+- return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, opts));
++ /* create a (quite useless) default "name" for this memory buffer object */
++ snprintf(tmp_name, sizeof(tmp_name), "%lx-%zx", (unsigned long)obj_buf, obj_buf_sz);
++
++ return libbpf_ptr(bpf_object_open(NULL, obj_buf, obj_buf_sz, tmp_name, opts));
+ }
+
+ static int bpf_object_unload(struct bpf_object *obj)
+@@ -8406,11 +8407,13 @@ static int bpf_object__resolve_externs(struct bpf_object *obj,
+
+ static void bpf_map_prepare_vdata(const struct bpf_map *map)
+ {
++ const struct btf_type *type;
+ struct bpf_struct_ops *st_ops;
+ __u32 i;
+
+ st_ops = map->st_ops;
+- for (i = 0; i < btf_vlen(st_ops->type); i++) {
++ type = btf__type_by_id(map->obj->btf, st_ops->type_id);
++ for (i = 0; i < btf_vlen(type); i++) {
+ struct bpf_program *prog = st_ops->progs[i];
+ void *kern_data;
+ int prog_fd;
+@@ -9673,6 +9676,7 @@ static struct bpf_map *find_struct_ops_map_by_offset(struct bpf_object *obj,
+ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
+ Elf64_Shdr *shdr, Elf_Data *data)
+ {
++ const struct btf_type *type;
+ const struct btf_member *member;
+ struct bpf_struct_ops *st_ops;
+ struct bpf_program *prog;
+@@ -9732,13 +9736,14 @@ static int bpf_object__collect_st_ops_relos(struct bpf_object *obj,
+ }
+ insn_idx = sym->st_value / BPF_INSN_SZ;
+
+- member = find_member_by_offset(st_ops->type, moff * 8);
++ type = btf__type_by_id(btf, st_ops->type_id);
++ member = find_member_by_offset(type, moff * 8);
+ if (!member) {
+ pr_warn("struct_ops reloc %s: cannot find member at moff %u\n",
+ map->name, moff);
+ return -EINVAL;
+ }
+- member_idx = member - btf_members(st_ops->type);
++ member_idx = member - btf_members(type);
+ name = btf__name_by_offset(btf, member->name_off);
+
+ if (!resolve_func_ptr(btf, member->type, NULL)) {
+@@ -13715,29 +13720,13 @@ static int populate_skeleton_progs(const struct bpf_object *obj,
+ int bpf_object__open_skeleton(struct bpf_object_skeleton *s,
+ const struct bpf_object_open_opts *opts)
+ {
+- DECLARE_LIBBPF_OPTS(bpf_object_open_opts, skel_opts,
+- .object_name = s->name,
+- );
+ struct bpf_object *obj;
+ int err;
+
+- /* Attempt to preserve opts->object_name, unless overriden by user
+- * explicitly. Overwriting object name for skeletons is discouraged,
+- * as it breaks global data maps, because they contain object name
+- * prefix as their own map name prefix. When skeleton is generated,
+- * bpftool is making an assumption that this name will stay the same.
+- */
+- if (opts) {
+- memcpy(&skel_opts, opts, sizeof(*opts));
+- if (!opts->object_name)
+- skel_opts.object_name = s->name;
+- }
+-
+- obj = bpf_object__open_mem(s->data, s->data_sz, &skel_opts);
+- err = libbpf_get_error(obj);
+- if (err) {
+- pr_warn("failed to initialize skeleton BPF object '%s': %d\n",
+- s->name, err);
++ obj = bpf_object_open(NULL, s->data, s->data_sz, s->name, opts);
++ if (IS_ERR(obj)) {
++ err = PTR_ERR(obj);
++ pr_warn("failed to initialize skeleton BPF object '%s': %d\n", s->name, err);
+ return libbpf_err(err);
+ }
+
+diff --git a/tools/objtool/arch/loongarch/decode.c b/tools/objtool/arch/loongarch/decode.c
+index aee479d2191c21..69b66994f2a155 100644
+--- a/tools/objtool/arch/loongarch/decode.c
++++ b/tools/objtool/arch/loongarch/decode.c
+@@ -122,7 +122,7 @@ static bool decode_insn_reg2i12_fomat(union loongarch_instruction inst,
+ switch (inst.reg2i12_format.opcode) {
+ case addid_op:
+ if ((inst.reg2i12_format.rd == CFI_SP) || (inst.reg2i12_format.rj == CFI_SP)) {
+- /* addi.d sp,sp,si12 or addi.d fp,sp,si12 */
++ /* addi.d sp,sp,si12 or addi.d fp,sp,si12 or addi.d sp,fp,si12 */
+ insn->immediate = sign_extend64(inst.reg2i12_format.immediate, 11);
+ ADD_OP(op) {
+ op->src.type = OP_SRC_ADD;
+@@ -132,6 +132,15 @@ static bool decode_insn_reg2i12_fomat(union loongarch_instruction inst,
+ op->dest.reg = inst.reg2i12_format.rd;
+ }
+ }
++ if ((inst.reg2i12_format.rd == CFI_SP) && (inst.reg2i12_format.rj == CFI_FP)) {
++ /* addi.d sp,fp,si12 */
++ struct symbol *func = find_func_containing(insn->sec, insn->offset);
++
++ if (!func)
++ return false;
++
++ func->frame_pointer = true;
++ }
+ break;
+ case ldd_op:
+ if (inst.reg2i12_format.rj == CFI_SP) {
+diff --git a/tools/objtool/check.c b/tools/objtool/check.c
+index 0a33d9195b7a91..60680b2bec96c0 100644
+--- a/tools/objtool/check.c
++++ b/tools/objtool/check.c
+@@ -2991,10 +2991,27 @@ static int update_cfi_state(struct instruction *insn,
+ break;
+ }
+
+- if (op->dest.reg == CFI_SP && op->src.reg == CFI_BP) {
++ if (op->dest.reg == CFI_BP && op->src.reg == CFI_SP &&
++ insn->sym->frame_pointer) {
++ /* addi.d fp,sp,imm on LoongArch */
++ if (cfa->base == CFI_SP && cfa->offset == op->src.offset) {
++ cfa->base = CFI_BP;
++ cfa->offset = 0;
++ }
++ break;
++ }
+
+- /* lea disp(%rbp), %rsp */
+- cfi->stack_size = -(op->src.offset + regs[CFI_BP].offset);
++ if (op->dest.reg == CFI_SP && op->src.reg == CFI_BP) {
++ /* addi.d sp,fp,imm on LoongArch */
++ if (cfa->base == CFI_BP && cfa->offset == 0) {
++ if (insn->sym->frame_pointer) {
++ cfa->base = CFI_SP;
++ cfa->offset = -op->src.offset;
++ }
++ } else {
++ /* lea disp(%rbp), %rsp */
++ cfi->stack_size = -(op->src.offset + regs[CFI_BP].offset);
++ }
+ break;
+ }
+
+diff --git a/tools/objtool/include/objtool/elf.h b/tools/objtool/include/objtool/elf.h
+index 2b8a69de4db871..d7e815c2fd1567 100644
+--- a/tools/objtool/include/objtool/elf.h
++++ b/tools/objtool/include/objtool/elf.h
+@@ -68,6 +68,7 @@ struct symbol {
+ u8 warned : 1;
+ u8 embedded_insn : 1;
+ u8 local_label : 1;
++ u8 frame_pointer : 1;
+ struct list_head pv_target;
+ struct reloc *relocs;
+ };
+diff --git a/tools/perf/builtin-c2c.c b/tools/perf/builtin-c2c.c
+index c157bd31f2e5a4..7298f360706220 100644
+--- a/tools/perf/builtin-c2c.c
++++ b/tools/perf/builtin-c2c.c
+@@ -3266,7 +3266,7 @@ static int perf_c2c__record(int argc, const char **argv)
+ return -1;
+ }
+
+- if (perf_pmu__mem_events_init(pmu)) {
++ if (perf_pmu__mem_events_init()) {
+ pr_err("failed: memory events not supported\n");
+ return -1;
+ }
+@@ -3290,19 +3290,15 @@ static int perf_c2c__record(int argc, const char **argv)
+ * PERF_MEM_EVENTS__LOAD_STORE if it is supported.
+ */
+ if (e->tag) {
+- e->record = true;
++ perf_mem_record[PERF_MEM_EVENTS__LOAD_STORE] = true;
+ rec_argv[i++] = "-W";
+ } else {
+- e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
+- e->record = true;
+-
+- e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__STORE);
+- e->record = true;
++ perf_mem_record[PERF_MEM_EVENTS__LOAD] = true;
++ perf_mem_record[PERF_MEM_EVENTS__STORE] = true;
+ }
+ }
+
+- e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
+- if (e->record)
++ if (perf_mem_record[PERF_MEM_EVENTS__LOAD])
+ rec_argv[i++] = "-W";
+
+ rec_argv[i++] = "-d";
+diff --git a/tools/perf/builtin-inject.c b/tools/perf/builtin-inject.c
+index a212678d47beb1..c80fb0f60e611f 100644
+--- a/tools/perf/builtin-inject.c
++++ b/tools/perf/builtin-inject.c
+@@ -2204,6 +2204,7 @@ int cmd_inject(int argc, const char **argv)
+ .finished_init = perf_event__repipe_op2_synth,
+ .compressed = perf_event__repipe_op4_synth,
+ .auxtrace = perf_event__repipe_auxtrace,
++ .dont_split_sample_group = true,
+ },
+ .input_name = "-",
+ .samples = LIST_HEAD_INIT(inject.samples),
+diff --git a/tools/perf/builtin-mem.c b/tools/perf/builtin-mem.c
+index 863fcd735daee9..08724fa508e14c 100644
+--- a/tools/perf/builtin-mem.c
++++ b/tools/perf/builtin-mem.c
+@@ -97,7 +97,7 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
+ return -1;
+ }
+
+- if (perf_pmu__mem_events_init(pmu)) {
++ if (perf_pmu__mem_events_init()) {
+ pr_err("failed: memory events not supported\n");
+ return -1;
+ }
+@@ -126,22 +126,17 @@ static int __cmd_record(int argc, const char **argv, struct perf_mem *mem)
+ if (e->tag &&
+ (mem->operation & MEM_OPERATION_LOAD) &&
+ (mem->operation & MEM_OPERATION_STORE)) {
+- e->record = true;
++ perf_mem_record[PERF_MEM_EVENTS__LOAD_STORE] = true;
+ rec_argv[i++] = "-W";
+ } else {
+- if (mem->operation & MEM_OPERATION_LOAD) {
+- e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
+- e->record = true;
+- }
++ if (mem->operation & MEM_OPERATION_LOAD)
++ perf_mem_record[PERF_MEM_EVENTS__LOAD] = true;
+
+- if (mem->operation & MEM_OPERATION_STORE) {
+- e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__STORE);
+- e->record = true;
+- }
++ if (mem->operation & MEM_OPERATION_STORE)
++ perf_mem_record[PERF_MEM_EVENTS__STORE] = true;
+ }
+
+- e = perf_pmu__mem_events_ptr(pmu, PERF_MEM_EVENTS__LOAD);
+- if (e->record)
++ if (perf_mem_record[PERF_MEM_EVENTS__LOAD])
+ rec_argv[i++] = "-W";
+
+ rec_argv[i++] = "-d";
+@@ -372,6 +367,7 @@ static int report_events(int argc, const char **argv, struct perf_mem *mem)
+ rep_argv[i] = argv[j];
+
+ ret = cmd_report(i, rep_argv);
++ free(new_sort_order);
+ free(rep_argv);
+ return ret;
+ }
+diff --git a/tools/perf/builtin-report.c b/tools/perf/builtin-report.c
+index 69618fb0110b64..8bebaba56bc3f5 100644
+--- a/tools/perf/builtin-report.c
++++ b/tools/perf/builtin-report.c
+@@ -565,6 +565,7 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c
+ struct hists *hists = evsel__hists(pos);
+ const char *evname = evsel__name(pos);
+
++ i++;
+ if (symbol_conf.event_group && !evsel__is_group_leader(pos))
+ continue;
+
+@@ -574,7 +575,7 @@ static int evlist__tty_browse_hists(struct evlist *evlist, struct report *rep, c
+ hists__fprintf_nr_sample_events(hists, rep, evname, stdout);
+
+ if (rep->total_cycles_mode) {
+- report__browse_block_hists(&rep->block_reports[i++].hist,
++ report__browse_block_hists(&rep->block_reports[i - 1].hist,
+ rep->min_percent, pos, NULL);
+ continue;
+ }
+diff --git a/tools/perf/builtin-sched.c b/tools/perf/builtin-sched.c
+index 5977c49ae2c76b..ed11a20bc14935 100644
+--- a/tools/perf/builtin-sched.c
++++ b/tools/perf/builtin-sched.c
+@@ -2596,9 +2596,12 @@ static int timehist_sched_change_event(struct perf_tool *tool,
+ * - previous sched event is out of window - we are done
+ * - sample time is beyond window user cares about - reset it
+ * to close out stats for time window interest
++ * - If tprev is 0, that is, sched_in event for current task is
++ * not recorded, cannot determine whether sched_in event is
++ * within time window interest - ignore it
+ */
+ if (ptime->end) {
+- if (tprev > ptime->end)
++ if (!tprev || tprev > ptime->end)
+ goto out;
+
+ if (t > ptime->end)
+@@ -3031,7 +3034,8 @@ static int perf_sched__timehist(struct perf_sched *sched)
+
+ if (perf_time__parse_str(&sched->ptime, sched->time_str) != 0) {
+ pr_err("Invalid time string\n");
+- return -EINVAL;
++ err = -EINVAL;
++ goto out;
+ }
+
+ if (timehist_check_attr(sched, evlist) != 0)
+diff --git a/tools/perf/scripts/python/arm-cs-trace-disasm.py b/tools/perf/scripts/python/arm-cs-trace-disasm.py
+index d973c2baed1c85..7aff02d84ffb3b 100755
+--- a/tools/perf/scripts/python/arm-cs-trace-disasm.py
++++ b/tools/perf/scripts/python/arm-cs-trace-disasm.py
+@@ -192,17 +192,16 @@ def process_event(param_dict):
+ ip = sample["ip"]
+ addr = sample["addr"]
+
++ if (options.verbose == True):
++ print("Event type: %s" % name)
++ print_sample(sample)
++
+ # Initialize CPU data if it's empty, and directly return back
+ # if this is the first tracing event for this CPU.
+ if (cpu_data.get(str(cpu) + 'addr') == None):
+ cpu_data[str(cpu) + 'addr'] = addr
+ return
+
+-
+- if (options.verbose == True):
+- print("Event type: %s" % name)
+- print_sample(sample)
+-
+ # If cannot find dso so cannot dump assembler, bail out
+ if (dso == '[unknown]'):
+ return
+diff --git a/tools/perf/util/annotate-data.c b/tools/perf/util/annotate-data.c
+index 965da6c0b5427e..79c1f2ae7affdc 100644
+--- a/tools/perf/util/annotate-data.c
++++ b/tools/perf/util/annotate-data.c
+@@ -104,7 +104,7 @@ static void pr_debug_location(Dwarf_Die *die, u64 pc, int reg)
+ return;
+
+ while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+- if (reg != DWARF_REG_PC && end < pc)
++ if (reg != DWARF_REG_PC && end <= pc)
+ continue;
+ if (reg != DWARF_REG_PC && start > pc)
+ break;
+diff --git a/tools/perf/util/bpf_skel/lock_data.h b/tools/perf/util/bpf_skel/lock_data.h
+index 36af11faad03c1..de12892f992f8d 100644
+--- a/tools/perf/util/bpf_skel/lock_data.h
++++ b/tools/perf/util/bpf_skel/lock_data.h
+@@ -7,11 +7,11 @@ struct tstamp_data {
+ u64 timestamp;
+ u64 lock;
+ u32 flags;
+- u32 stack_id;
++ s32 stack_id;
+ };
+
+ struct contention_key {
+- u32 stack_id;
++ s32 stack_id;
+ u32 pid;
+ u64 lock_addr_or_cgroup;
+ };
+diff --git a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
+index e9028235d7717b..d818e30c545713 100644
+--- a/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
++++ b/tools/perf/util/bpf_skel/vmlinux/vmlinux.h
+@@ -15,6 +15,7 @@
+
+ typedef __u8 u8;
+ typedef __u32 u32;
++typedef __s32 s32;
+ typedef __u64 u64;
+ typedef __s64 s64;
+
+diff --git a/tools/perf/util/dwarf-aux.c b/tools/perf/util/dwarf-aux.c
+index 44ef968a7ad331..1b0e59f4d8e936 100644
+--- a/tools/perf/util/dwarf-aux.c
++++ b/tools/perf/util/dwarf-aux.c
+@@ -1444,7 +1444,7 @@ static int __die_find_var_reg_cb(Dwarf_Die *die_mem, void *arg)
+
+ while ((off = dwarf_getlocations(&attr, off, &base, &start, &end, &ops, &nops)) > 0) {
+ /* Assuming the location list is sorted by address */
+- if (end < data->pc)
++ if (end <= data->pc)
+ continue;
+ if (start > data->pc)
+ break;
+@@ -1598,6 +1598,9 @@ static int __die_collect_vars_cb(Dwarf_Die *die_mem, void *arg)
+ if (dwarf_getlocations(&attr, 0, &base, &start, &end, &ops, &nops) <= 0)
+ return DIE_FIND_CB_SIBLING;
+
++ if (!check_allowed_ops(ops, nops))
++ return DIE_FIND_CB_SIBLING;
++
+ if (die_get_real_type(die_mem, &type_die) == NULL)
+ return DIE_FIND_CB_SIBLING;
+
+@@ -1974,8 +1977,15 @@ static int __die_find_member_offset_cb(Dwarf_Die *die_mem, void *arg)
+ return DIE_FIND_CB_SIBLING;
+
+ /* Unions might not have location */
+- if (die_get_data_member_location(die_mem, &loc) < 0)
+- loc = 0;
++ if (die_get_data_member_location(die_mem, &loc) < 0) {
++ Dwarf_Attribute attr;
++
++ if (dwarf_attr_integrate(die_mem, DW_AT_data_bit_offset, &attr) &&
++ dwarf_formudata(&attr, &loc) == 0)
++ loc /= 8;
++ else
++ loc = 0;
++ }
+
+ if (offset == loc)
+ return DIE_FIND_CB_END;
+diff --git a/tools/perf/util/mem-events.c b/tools/perf/util/mem-events.c
+index 6dda47bb774faa..1f1e1063efe378 100644
+--- a/tools/perf/util/mem-events.c
++++ b/tools/perf/util/mem-events.c
+@@ -28,6 +28,8 @@ struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX] = {
+ };
+ #undef E
+
++bool perf_mem_record[PERF_MEM_EVENTS__MAX] = { 0 };
++
+ static char mem_loads_name[100];
+ static char mem_stores_name[100];
+
+@@ -162,7 +164,7 @@ int perf_pmu__mem_events_parse(struct perf_pmu *pmu, const char *str)
+ continue;
+
+ if (strstr(e->tag, tok))
+- e->record = found = true;
++ perf_mem_record[j] = found = true;
+ }
+
+ tok = strtok_r(NULL, ",", &saveptr);
+@@ -191,7 +193,7 @@ static bool perf_pmu__mem_events_supported(const char *mnt, struct perf_pmu *pmu
+ return !stat(path, &st);
+ }
+
+-int perf_pmu__mem_events_init(struct perf_pmu *pmu)
++static int __perf_pmu__mem_events_init(struct perf_pmu *pmu)
+ {
+ const char *mnt = sysfs__mount();
+ bool found = false;
+@@ -218,6 +220,18 @@ int perf_pmu__mem_events_init(struct perf_pmu *pmu)
+ return found ? 0 : -ENOENT;
+ }
+
++int perf_pmu__mem_events_init(void)
++{
++ struct perf_pmu *pmu = NULL;
++
++ while ((pmu = perf_pmus__scan_mem(pmu)) != NULL) {
++ if (__perf_pmu__mem_events_init(pmu))
++ return -ENOENT;
++ }
++
++ return 0;
++}
++
+ void perf_pmu__mem_events_list(struct perf_pmu *pmu)
+ {
+ int j;
+@@ -247,7 +261,7 @@ int perf_mem_events__record_args(const char **rec_argv, int *argv_nr)
+ for (int j = 0; j < PERF_MEM_EVENTS__MAX; j++) {
+ e = perf_pmu__mem_events_ptr(pmu, j);
+
+- if (!e->record)
++ if (!perf_mem_record[j])
+ continue;
+
+ if (!e->supported) {
+diff --git a/tools/perf/util/mem-events.h b/tools/perf/util/mem-events.h
+index ca31014d7934f4..8dc27db9fd52f4 100644
+--- a/tools/perf/util/mem-events.h
++++ b/tools/perf/util/mem-events.h
+@@ -6,7 +6,6 @@
+ #include <linux/types.h>
+
+ struct perf_mem_event {
+- bool record;
+ bool supported;
+ bool ldlat;
+ u32 aux_event;
+@@ -28,9 +27,10 @@ struct perf_pmu;
+
+ extern unsigned int perf_mem_events__loads_ldlat;
+ extern struct perf_mem_event perf_mem_events[PERF_MEM_EVENTS__MAX];
++extern bool perf_mem_record[PERF_MEM_EVENTS__MAX];
+
+ int perf_pmu__mem_events_parse(struct perf_pmu *pmu, const char *str);
+-int perf_pmu__mem_events_init(struct perf_pmu *pmu);
++int perf_pmu__mem_events_init(void);
+
+ struct perf_mem_event *perf_pmu__mem_events_ptr(struct perf_pmu *pmu, int i);
+ struct perf_pmu *perf_mem_events_find_pmu(void);
+diff --git a/tools/perf/util/session.c b/tools/perf/util/session.c
+index a10343b9dcd419..1457cd5288abc8 100644
+--- a/tools/perf/util/session.c
++++ b/tools/perf/util/session.c
+@@ -1511,6 +1511,9 @@ static int deliver_sample_group(struct evlist *evlist,
+ int ret = -EINVAL;
+ struct sample_read_value *v = sample->read.group.values;
+
++ if (tool->dont_split_sample_group)
++ return deliver_sample_value(evlist, tool, event, sample, v, machine);
++
+ sample_read_group__for_each(v, sample->read.group.nr, read_format) {
+ ret = deliver_sample_value(evlist, tool, event, sample, v,
+ machine);
+diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
+index 186305fd2d0efa..ac79ac4ccbe022 100644
+--- a/tools/perf/util/stat-display.c
++++ b/tools/perf/util/stat-display.c
+@@ -1226,7 +1226,8 @@ static void print_metric_headers(struct perf_stat_config *config,
+
+ /* Print metrics headers only */
+ evlist__for_each_entry(evlist, counter) {
+- if (config->aggr_mode != AGGR_NONE && counter->metric_leader != counter)
++ if (!config->iostat_run &&
++ config->aggr_mode != AGGR_NONE && counter->metric_leader != counter)
+ continue;
+
+ os.evsel = counter;
+diff --git a/tools/perf/util/time-utils.c b/tools/perf/util/time-utils.c
+index 30244392168163..1b91ccd4d52348 100644
+--- a/tools/perf/util/time-utils.c
++++ b/tools/perf/util/time-utils.c
+@@ -20,7 +20,7 @@ int parse_nsec_time(const char *str, u64 *ptime)
+ u64 time_sec, time_nsec;
+ char *end;
+
+- time_sec = strtoul(str, &end, 10);
++ time_sec = strtoull(str, &end, 10);
+ if (*end != '.' && *end != '\0')
+ return -1;
+
+@@ -38,7 +38,7 @@ int parse_nsec_time(const char *str, u64 *ptime)
+ for (i = strlen(nsec_buf); i < 9; i++)
+ nsec_buf[i] = '0';
+
+- time_nsec = strtoul(nsec_buf, &end, 10);
++ time_nsec = strtoull(nsec_buf, &end, 10);
+ if (*end != '\0')
+ return -1;
+ } else
+diff --git a/tools/perf/util/tool.h b/tools/perf/util/tool.h
+index c957fb849ac633..62bbc9cec151bb 100644
+--- a/tools/perf/util/tool.h
++++ b/tools/perf/util/tool.h
+@@ -85,6 +85,7 @@ struct perf_tool {
+ bool namespace_events;
+ bool cgroup_events;
+ bool no_warn;
++ bool dont_split_sample_group;
+ enum show_feature_header show_feat_hdr;
+ };
+
+diff --git a/tools/power/cpupower/lib/powercap.c b/tools/power/cpupower/lib/powercap.c
+index a7a59c6bacda81..94a0c69e55ef5e 100644
+--- a/tools/power/cpupower/lib/powercap.c
++++ b/tools/power/cpupower/lib/powercap.c
+@@ -77,6 +77,14 @@ int powercap_get_enabled(int *mode)
+ return sysfs_get_enabled(path, mode);
+ }
+
++/*
++ * TODO: implement function. Returns dummy 0 for now.
++ */
++int powercap_set_enabled(int mode)
++{
++ return 0;
++}
++
+ /*
+ * Hardcoded, because rapl is the only powercap implementation
+ - * this needs to get more generic if more powercap implementations
+diff --git a/tools/testing/selftests/arm64/signal/Makefile b/tools/testing/selftests/arm64/signal/Makefile
+index 8f5febaf1a9a25..edb3613513b8a8 100644
+--- a/tools/testing/selftests/arm64/signal/Makefile
++++ b/tools/testing/selftests/arm64/signal/Makefile
+@@ -23,7 +23,7 @@ $(TEST_GEN_PROGS): $(PROGS)
+ # Common test-unit targets to build common-layout test-cases executables
+ # Needs secondary expansion to properly include the testcase c-file in pre-reqs
+ COMMON_SOURCES := test_signals.c test_signals_utils.c testcases/testcases.c \
+- signals.S
++ signals.S sve_helpers.c
+ COMMON_HEADERS := test_signals.h test_signals_utils.h testcases/testcases.h
+
+ .SECONDEXPANSION:
+diff --git a/tools/testing/selftests/arm64/signal/sve_helpers.c b/tools/testing/selftests/arm64/signal/sve_helpers.c
+new file mode 100644
+index 00000000000000..0acc121af3062a
+--- /dev/null
++++ b/tools/testing/selftests/arm64/signal/sve_helpers.c
+@@ -0,0 +1,56 @@
++// SPDX-License-Identifier: GPL-2.0
++/*
++ * Copyright (C) 2024 ARM Limited
++ *
++ * Common helper functions for SVE and SME functionality.
++ */
++
++#include <stdbool.h>
++#include <kselftest.h>
++#include <asm/sigcontext.h>
++#include <sys/prctl.h>
++
++unsigned int vls[SVE_VQ_MAX];
++unsigned int nvls;
++
++int sve_fill_vls(bool use_sme, int min_vls)
++{
++ int vq, vl;
++ int pr_set_vl = use_sme ? PR_SME_SET_VL : PR_SVE_SET_VL;
++ int len_mask = use_sme ? PR_SME_VL_LEN_MASK : PR_SVE_VL_LEN_MASK;
++
++ /*
++ * Enumerate up to SVE_VQ_MAX vector lengths
++ */
++ for (vq = SVE_VQ_MAX; vq > 0; --vq) {
++ vl = prctl(pr_set_vl, vq * 16);
++ if (vl == -1)
++ return KSFT_FAIL;
++
++ vl &= len_mask;
++
++ /*
++ * Unlike SVE, SME does not require the minimum vector length
++ * to be implemented, or the VLs to be consecutive, so any call
++ * to the prctl might return the single implemented VL, which
++ * might be larger than 16. So to avoid this loop never
++ * terminating, bail out here when we find a higher VL than
++ * we asked for.
++ * See the ARM ARM, DDI 0487K.a, B1.4.2: I_QQRNR and I_NWYBP.
++ */
++ if (vq < sve_vq_from_vl(vl))
++ break;
++
++ /* Skip missing VLs */
++ vq = sve_vq_from_vl(vl);
++
++ vls[nvls++] = vl;
++ }
++
++ if (nvls < min_vls) {
++ fprintf(stderr, "Only %d VL supported\n", nvls);
++ return KSFT_SKIP;
++ }
++
++ return KSFT_PASS;
++}
+diff --git a/tools/testing/selftests/arm64/signal/sve_helpers.h b/tools/testing/selftests/arm64/signal/sve_helpers.h
+new file mode 100644
+index 00000000000000..50948ce471cc62
+--- /dev/null
++++ b/tools/testing/selftests/arm64/signal/sve_helpers.h
+@@ -0,0 +1,21 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * Copyright (C) 2024 ARM Limited
++ *
++ * Common helper functions for SVE and SME functionality.
++ */
++
++#ifndef __SVE_HELPERS_H__
++#define __SVE_HELPERS_H__
++
++#include <stdbool.h>
++
++#define VLS_USE_SVE false
++#define VLS_USE_SME true
++
++extern unsigned int vls[];
++extern unsigned int nvls;
++
++int sve_fill_vls(bool use_sme, int min_vls);
++
++#endif
+diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
+index ebd5815b54bbaa..dfd6a2badf9fb3 100644
+--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
++++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sme_change_vl.c
+@@ -6,44 +6,28 @@
+ * handler, this is not supported and is expected to segfault.
+ */
+
++#include <kselftest.h>
+ #include <signal.h>
+ #include <ucontext.h>
+ #include <sys/prctl.h>
+
+ #include "test_signals_utils.h"
++#include "sve_helpers.h"
+ #include "testcases.h"
+
+ struct fake_sigframe sf;
+-static unsigned int vls[SVE_VQ_MAX];
+-unsigned int nvls = 0;
+
+ static bool sme_get_vls(struct tdescr *td)
+ {
+- int vq, vl;
++ int res = sve_fill_vls(VLS_USE_SME, 2);
+
+- /*
+- * Enumerate up to SVE_VQ_MAX vector lengths
+- */
+- for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+- vl = prctl(PR_SVE_SET_VL, vq * 16);
+- if (vl == -1)
+- return false;
++ if (!res)
++ return true;
+
+- vl &= PR_SME_VL_LEN_MASK;
++ if (res == KSFT_SKIP)
++ td->result = KSFT_SKIP;
+
+- /* Skip missing VLs */
+- vq = sve_vq_from_vl(vl);
+-
+- vls[nvls++] = vl;
+- }
+-
+- /* We need at least two VLs */
+- if (nvls < 2) {
+- fprintf(stderr, "Only %d VL supported\n", nvls);
+- return false;
+- }
+-
+- return true;
++ return false;
+ }
+
+ static int fake_sigreturn_ssve_change_vl(struct tdescr *td,
+@@ -51,30 +35,30 @@ static int fake_sigreturn_ssve_change_vl(struct tdescr *td,
+ {
+ size_t resv_sz, offset;
+ struct _aarch64_ctx *head = GET_SF_RESV_HEAD(sf);
+- struct sve_context *sve;
++ struct za_context *za;
+
+ /* Get a signal context with a SME ZA frame in it */
+ if (!get_current_context(td, &sf.uc, sizeof(sf.uc)))
+ return 1;
+
+ resv_sz = GET_SF_RESV_SIZE(sf);
+- head = get_header(head, SVE_MAGIC, resv_sz, &offset);
++ head = get_header(head, ZA_MAGIC, resv_sz, &offset);
+ if (!head) {
+- fprintf(stderr, "No SVE context\n");
++ fprintf(stderr, "No ZA context\n");
+ return 1;
+ }
+
+- if (head->size != sizeof(struct sve_context)) {
++ if (head->size != sizeof(struct za_context)) {
+ fprintf(stderr, "Register data present, aborting\n");
+ return 1;
+ }
+
+- sve = (struct sve_context *)head;
++ za = (struct za_context *)head;
+
+ /* No changes are supported; init left us at minimum VL so go to max */
+ fprintf(stderr, "Attempting to change VL from %d to %d\n",
+- sve->vl, vls[0]);
+- sve->vl = vls[0];
++ za->vl, vls[0]);
++ za->vl = vls[0];
+
+ fake_sigreturn(&sf, sizeof(sf), 0);
+
+diff --git a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
+index e2a452190511ff..e1ccf8f85a70c8 100644
+--- a/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
++++ b/tools/testing/selftests/arm64/signal/testcases/fake_sigreturn_sve_change_vl.c
+@@ -12,40 +12,22 @@
+ #include <sys/prctl.h>
+
+ #include "test_signals_utils.h"
++#include "sve_helpers.h"
+ #include "testcases.h"
+
+ struct fake_sigframe sf;
+-static unsigned int vls[SVE_VQ_MAX];
+-unsigned int nvls = 0;
+
+ static bool sve_get_vls(struct tdescr *td)
+ {
+- int vq, vl;
++ int res = sve_fill_vls(VLS_USE_SVE, 2);
+
+- /*
+- * Enumerate up to SVE_VQ_MAX vector lengths
+- */
+- for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+- vl = prctl(PR_SVE_SET_VL, vq * 16);
+- if (vl == -1)
+- return false;
++ if (!res)
++ return true;
+
+- vl &= PR_SVE_VL_LEN_MASK;
+-
+- /* Skip missing VLs */
+- vq = sve_vq_from_vl(vl);
+-
+- vls[nvls++] = vl;
+- }
+-
+- /* We need at least two VLs */
+- if (nvls < 2) {
+- fprintf(stderr, "Only %d VL supported\n", nvls);
++ if (res == KSFT_SKIP)
+ td->result = KSFT_SKIP;
+- return false;
+- }
+
+- return true;
++ return false;
+ }
+
+ static int fake_sigreturn_sve_change_vl(struct tdescr *td,
+diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
+index 3d37daafcff513..6dbe48cf8b09ed 100644
+--- a/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
++++ b/tools/testing/selftests/arm64/signal/testcases/ssve_regs.c
+@@ -6,51 +6,31 @@
+ * set up as expected.
+ */
+
++#include <kselftest.h>
+ #include <signal.h>
+ #include <ucontext.h>
+ #include <sys/prctl.h>
+
+ #include "test_signals_utils.h"
++#include "sve_helpers.h"
+ #include "testcases.h"
+
+ static union {
+ ucontext_t uc;
+ char buf[1024 * 64];
+ } context;
+-static unsigned int vls[SVE_VQ_MAX];
+-unsigned int nvls = 0;
+
+ static bool sme_get_vls(struct tdescr *td)
+ {
+- int vq, vl;
++ int res = sve_fill_vls(VLS_USE_SME, 1);
+
+- /*
+- * Enumerate up to SVE_VQ_MAX vector lengths
+- */
+- for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+- vl = prctl(PR_SME_SET_VL, vq * 16);
+- if (vl == -1)
+- return false;
+-
+- vl &= PR_SME_VL_LEN_MASK;
+-
+- /* Did we find the lowest supported VL? */
+- if (vq < sve_vq_from_vl(vl))
+- break;
++ if (!res)
++ return true;
+
+- /* Skip missing VLs */
+- vq = sve_vq_from_vl(vl);
+-
+- vls[nvls++] = vl;
+- }
+-
+- /* We need at least one VL */
+- if (nvls < 1) {
+- fprintf(stderr, "Only %d VL supported\n", nvls);
+- return false;
+- }
++ if (res == KSFT_SKIP)
++ td->result = KSFT_SKIP;
+
+- return true;
++ return false;
+ }
+
+ static void setup_ssve_regs(void)
+diff --git a/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c
+index 9dc5f128bbc0d5..5557e116e97363 100644
+--- a/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c
++++ b/tools/testing/selftests/arm64/signal/testcases/ssve_za_regs.c
+@@ -6,51 +6,31 @@
+ * signal frames is set up as expected when enabled simultaneously.
+ */
+
++#include <kselftest.h>
+ #include <signal.h>
+ #include <ucontext.h>
+ #include <sys/prctl.h>
+
+ #include "test_signals_utils.h"
++#include "sve_helpers.h"
+ #include "testcases.h"
+
+ static union {
+ ucontext_t uc;
+ char buf[1024 * 128];
+ } context;
+-static unsigned int vls[SVE_VQ_MAX];
+-unsigned int nvls = 0;
+
+ static bool sme_get_vls(struct tdescr *td)
+ {
+- int vq, vl;
++ int res = sve_fill_vls(VLS_USE_SME, 1);
+
+- /*
+- * Enumerate up to SVE_VQ_MAX vector lengths
+- */
+- for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+- vl = prctl(PR_SME_SET_VL, vq * 16);
+- if (vl == -1)
+- return false;
+-
+- vl &= PR_SME_VL_LEN_MASK;
+-
+- /* Did we find the lowest supported VL? */
+- if (vq < sve_vq_from_vl(vl))
+- break;
++ if (!res)
++ return true;
+
+- /* Skip missing VLs */
+- vq = sve_vq_from_vl(vl);
+-
+- vls[nvls++] = vl;
+- }
+-
+- /* We need at least one VL */
+- if (nvls < 1) {
+- fprintf(stderr, "Only %d VL supported\n", nvls);
+- return false;
+- }
++ if (res == KSFT_SKIP)
++ td->result = KSFT_SKIP;
+
+- return true;
++ return false;
+ }
+
+ static void setup_regs(void)
+diff --git a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
+index 8b16eabbb7697e..8143eb1c58c187 100644
+--- a/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
++++ b/tools/testing/selftests/arm64/signal/testcases/sve_regs.c
+@@ -6,47 +6,31 @@
+ * expected.
+ */
+
++#include <kselftest.h>
+ #include <signal.h>
+ #include <ucontext.h>
+ #include <sys/prctl.h>
+
+ #include "test_signals_utils.h"
++#include "sve_helpers.h"
+ #include "testcases.h"
+
+ static union {
+ ucontext_t uc;
+ char buf[1024 * 64];
+ } context;
+-static unsigned int vls[SVE_VQ_MAX];
+-unsigned int nvls = 0;
+
+ static bool sve_get_vls(struct tdescr *td)
+ {
+- int vq, vl;
++ int res = sve_fill_vls(VLS_USE_SVE, 1);
+
+- /*
+- * Enumerate up to SVE_VQ_MAX vector lengths
+- */
+- for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+- vl = prctl(PR_SVE_SET_VL, vq * 16);
+- if (vl == -1)
+- return false;
+-
+- vl &= PR_SVE_VL_LEN_MASK;
+-
+- /* Skip missing VLs */
+- vq = sve_vq_from_vl(vl);
++ if (!res)
++ return true;
+
+- vls[nvls++] = vl;
+- }
+-
+- /* We need at least one VL */
+- if (nvls < 1) {
+- fprintf(stderr, "Only %d VL supported\n", nvls);
+- return false;
+- }
++ if (res == KSFT_SKIP)
++ td->result = KSFT_SKIP;
+
+- return true;
++ return false;
+ }
+
+ static void setup_sve_regs(void)
+diff --git a/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
+index 4d6f94b6178f36..ce26e9c2fa5e34 100644
+--- a/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
++++ b/tools/testing/selftests/arm64/signal/testcases/za_no_regs.c
+@@ -6,47 +6,31 @@
+ * expected.
+ */
+
++#include <kselftest.h>
+ #include <signal.h>
+ #include <ucontext.h>
+ #include <sys/prctl.h>
+
+ #include "test_signals_utils.h"
++#include "sve_helpers.h"
+ #include "testcases.h"
+
+ static union {
+ ucontext_t uc;
+ char buf[1024 * 128];
+ } context;
+-static unsigned int vls[SVE_VQ_MAX];
+-unsigned int nvls = 0;
+
+ static bool sme_get_vls(struct tdescr *td)
+ {
+- int vq, vl;
++ int res = sve_fill_vls(VLS_USE_SME, 1);
+
+- /*
+- * Enumerate up to SME_VQ_MAX vector lengths
+- */
+- for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+- vl = prctl(PR_SME_SET_VL, vq * 16);
+- if (vl == -1)
+- return false;
+-
+- vl &= PR_SME_VL_LEN_MASK;
+-
+- /* Skip missing VLs */
+- vq = sve_vq_from_vl(vl);
++ if (!res)
++ return true;
+
+- vls[nvls++] = vl;
+- }
+-
+- /* We need at least one VL */
+- if (nvls < 1) {
+- fprintf(stderr, "Only %d VL supported\n", nvls);
+- return false;
+- }
++ if (res == KSFT_SKIP)
++ td->result = KSFT_SKIP;
+
+- return true;
++ return false;
+ }
+
+ static int do_one_sme_vl(struct tdescr *td, siginfo_t *si, ucontext_t *uc,
+diff --git a/tools/testing/selftests/arm64/signal/testcases/za_regs.c b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
+index 174ad665669647..b9e13f27f1f9aa 100644
+--- a/tools/testing/selftests/arm64/signal/testcases/za_regs.c
++++ b/tools/testing/selftests/arm64/signal/testcases/za_regs.c
+@@ -6,51 +6,31 @@
+ * expected.
+ */
+
++#include <kselftest.h>
+ #include <signal.h>
+ #include <ucontext.h>
+ #include <sys/prctl.h>
+
+ #include "test_signals_utils.h"
++#include "sve_helpers.h"
+ #include "testcases.h"
+
+ static union {
+ ucontext_t uc;
+ char buf[1024 * 128];
+ } context;
+-static unsigned int vls[SVE_VQ_MAX];
+-unsigned int nvls = 0;
+
+ static bool sme_get_vls(struct tdescr *td)
+ {
+- int vq, vl;
++ int res = sve_fill_vls(VLS_USE_SME, 1);
+
+- /*
+- * Enumerate up to SME_VQ_MAX vector lengths
+- */
+- for (vq = SVE_VQ_MAX; vq > 0; --vq) {
+- vl = prctl(PR_SME_SET_VL, vq * 16);
+- if (vl == -1)
+- return false;
+-
+- vl &= PR_SME_VL_LEN_MASK;
+-
+- /* Did we find the lowest supported VL? */
+- if (vq < sve_vq_from_vl(vl))
+- break;
++ if (!res)
++ return true;
+
+- /* Skip missing VLs */
+- vq = sve_vq_from_vl(vl);
+-
+- vls[nvls++] = vl;
+- }
+-
+- /* We need at least one VL */
+- if (nvls < 1) {
+- fprintf(stderr, "Only %d VL supported\n", nvls);
+- return false;
+- }
++ if (res == KSFT_SKIP)
++ td->result = KSFT_SKIP;
+
+- return true;
++ return false;
+ }
+
+ static void setup_za_regs(void)
+diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile
+index dd49c1d23a604c..88e8a316e7686a 100644
+--- a/tools/testing/selftests/bpf/Makefile
++++ b/tools/testing/selftests/bpf/Makefile
+@@ -427,23 +427,24 @@ $(OUTPUT)/cgroup_getset_retval_hooks.o: cgroup_getset_retval_hooks.h
+ # $1 - input .c file
+ # $2 - output .o file
+ # $3 - CFLAGS
++# $4 - binary name
+ define CLANG_BPF_BUILD_RULE
+- $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
++ $(call msg,CLNG-BPF,$4,$2)
+ $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v3 -o $2
+ endef
+ # Similar to CLANG_BPF_BUILD_RULE, but with disabled alu32
+ define CLANG_NOALU32_BPF_BUILD_RULE
+- $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
++ $(call msg,CLNG-BPF,$4,$2)
+ $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v2 -o $2
+ endef
+ # Similar to CLANG_BPF_BUILD_RULE, but with cpu-v4
+ define CLANG_CPUV4_BPF_BUILD_RULE
+- $(call msg,CLNG-BPF,$(TRUNNER_BINARY),$2)
++ $(call msg,CLNG-BPF,$4,$2)
+ $(Q)$(CLANG) $3 -O2 --target=bpf -c $1 -mcpu=v4 -o $2
+ endef
+ # Build BPF object using GCC
+ define GCC_BPF_BUILD_RULE
+- $(call msg,GCC-BPF,$(TRUNNER_BINARY),$2)
++ $(call msg,GCC-BPF,$4,$2)
+ $(Q)$(BPF_GCC) $3 -DBPF_NO_PRESERVE_ACCESS_INDEX -Wno-attributes -O2 -c $1 -o $2
+ endef
+
+@@ -535,7 +536,7 @@ $(TRUNNER_BPF_OBJS): $(TRUNNER_OUTPUT)/%.bpf.o: \
+ $$(call $(TRUNNER_BPF_BUILD_RULE),$$<,$$@, \
+ $(TRUNNER_BPF_CFLAGS) \
+ $$($$<-CFLAGS) \
+- $$($$<-$2-CFLAGS))
++ $$($$<-$2-CFLAGS),$(TRUNNER_BINARY))
+
+ $(TRUNNER_BPF_SKELS): %.skel.h: %.bpf.o $(BPFTOOL) | $(TRUNNER_OUTPUT)
+ $$(call msg,GEN-SKEL,$(TRUNNER_BINARY),$$@)
+@@ -762,6 +763,8 @@ $(OUTPUT)/veristat: $(OUTPUT)/veristat.o
+ $(call msg,BINARY,,$@)
+ $(Q)$(CC) $(CFLAGS) $(LDFLAGS) $(filter %.a %.o,$^) $(LDLIBS) -o $@
+
++# Linking uprobe_multi can fail due to relocation overflows on mips.
++$(OUTPUT)/uprobe_multi: CFLAGS += $(if $(filter mips, $(ARCH)),-mxgot)
+ $(OUTPUT)/uprobe_multi: uprobe_multi.c
+ $(call msg,BINARY,,$@)
+ $(Q)$(CC) $(CFLAGS) -O0 $(LDFLAGS) $^ $(LDLIBS) -o $@
+diff --git a/tools/testing/selftests/bpf/bench.c b/tools/testing/selftests/bpf/bench.c
+index 627b74ae041b52..90dc3aca32bd8f 100644
+--- a/tools/testing/selftests/bpf/bench.c
++++ b/tools/testing/selftests/bpf/bench.c
+@@ -10,6 +10,7 @@
+ #include <sys/sysinfo.h>
+ #include <signal.h>
+ #include "bench.h"
++#include "bpf_util.h"
+ #include "testing_helpers.h"
+
+ struct env env = {
+diff --git a/tools/testing/selftests/bpf/bench.h b/tools/testing/selftests/bpf/bench.h
+index 68180d8f8558ec..005c401b3e2275 100644
+--- a/tools/testing/selftests/bpf/bench.h
++++ b/tools/testing/selftests/bpf/bench.h
+@@ -10,6 +10,7 @@
+ #include <math.h>
+ #include <time.h>
+ #include <sys/syscall.h>
++#include <limits.h>
+
+ struct cpu_set {
+ bool *cpus;
+diff --git a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
+index 18405c3b7cee9a..af10c309359a77 100644
+--- a/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
++++ b/tools/testing/selftests/bpf/map_tests/sk_storage_map.c
+@@ -412,7 +412,7 @@ static void test_sk_storage_map_stress_free(void)
+ rlim_new.rlim_max = rlim_new.rlim_cur + 128;
+ err = setrlimit(RLIMIT_NOFILE, &rlim_new);
+ CHECK(err, "setrlimit(RLIMIT_NOFILE)", "rlim_new:%lu errno:%d",
+- rlim_new.rlim_cur, errno);
++ (unsigned long) rlim_new.rlim_cur, errno);
+ }
+
+ err = do_sk_storage_map_stress_free();
+diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
+index b52ff8ce34db82..16bed9dd8e6a30 100644
+--- a/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
++++ b/tools/testing/selftests/bpf/prog_tests/bpf_iter_setsockopt.c
+@@ -95,7 +95,7 @@ static unsigned short get_local_port(int fd)
+ struct sockaddr_in6 addr;
+ socklen_t addrlen = sizeof(addr);
+
+- if (!getsockname(fd, &addr, &addrlen))
++ if (!getsockname(fd, (struct sockaddr *)&addr, &addrlen))
+ return ntohs(addr.sin6_port);
+
+ return 0;
+diff --git a/tools/testing/selftests/bpf/prog_tests/core_reloc.c b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+index 47f42e6801056b..26019313e1fc20 100644
+--- a/tools/testing/selftests/bpf/prog_tests/core_reloc.c
++++ b/tools/testing/selftests/bpf/prog_tests/core_reloc.c
+@@ -1,4 +1,5 @@
+ // SPDX-License-Identifier: GPL-2.0
++#define _GNU_SOURCE
+ #include <test_progs.h>
+ #include "progs/core_reloc_types.h"
+ #include "bpf_testmod/bpf_testmod.h"
+diff --git a/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c b/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
+index b1a3a49a822a7b..42bd07f7218dc3 100644
+--- a/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
++++ b/tools/testing/selftests/bpf/prog_tests/crypto_sanity.c
+@@ -4,7 +4,6 @@
+ #include <sys/types.h>
+ #include <sys/socket.h>
+ #include <net/if.h>
+-#include <linux/in6.h>
+ #include <linux/if_alg.h>
+
+ #include "test_progs.h"
+diff --git a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
+index dcb9e5070cc3d9..d79f398ec6b7c1 100644
+--- a/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
++++ b/tools/testing/selftests/bpf/prog_tests/decap_sanity.c
+@@ -4,7 +4,6 @@
+ #include <sys/types.h>
+ #include <sys/socket.h>
+ #include <net/if.h>
+-#include <linux/in6.h>
+
+ #include "test_progs.h"
+ #include "network_helpers.h"
+diff --git a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+index 9e5f38739104bf..3171047414a7dc 100644
+--- a/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
++++ b/tools/testing/selftests/bpf/prog_tests/flow_dissector.c
+@@ -1,7 +1,7 @@
+ // SPDX-License-Identifier: GPL-2.0
++#define _GNU_SOURCE
+ #include <test_progs.h>
+ #include <network_helpers.h>
+-#include <error.h>
+ #include <linux/if_tun.h>
+ #include <sys/uio.h>
+
+diff --git a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+index c07991544a789e..34f8822fd2219c 100644
+--- a/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
++++ b/tools/testing/selftests/bpf/prog_tests/kfree_skb.c
+@@ -1,4 +1,5 @@
+ // SPDX-License-Identifier: GPL-2.0
++#define _GNU_SOURCE
+ #include <test_progs.h>
+ #include <network_helpers.h>
+ #include "kfree_skb.skel.h"
+diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
+index 835a1d756c1662..b6e8d822e8e95f 100644
+--- a/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
++++ b/tools/testing/selftests/bpf/prog_tests/lwt_redirect.c
+@@ -47,7 +47,6 @@
+ #include <linux/if_ether.h>
+ #include <linux/if_packet.h>
+ #include <linux/if_tun.h>
+-#include <linux/icmp.h>
+ #include <arpa/inet.h>
+ #include <unistd.h>
+ #include <errno.h>
+diff --git a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
+index 03825d2b45a8b7..6c50c0f63f4365 100644
+--- a/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
++++ b/tools/testing/selftests/bpf/prog_tests/lwt_reroute.c
+@@ -49,6 +49,7 @@
+ * is not crashed, it is considered successful.
+ */
+ #define NETNS "ns_lwt_reroute"
++#include <netinet/in.h>
+ #include "lwt_helpers.h"
+ #include "network_helpers.h"
+ #include <linux/net_tstamp.h>
+diff --git a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+index e72d75d6baa71e..c29787e092d66a 100644
+--- a/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
++++ b/tools/testing/selftests/bpf/prog_tests/ns_current_pid_tgid.c
+@@ -11,7 +11,7 @@
+ #include <sched.h>
+ #include <sys/wait.h>
+ #include <sys/mount.h>
+-#include <sys/fcntl.h>
++#include <fcntl.h>
+ #include "network_helpers.h"
+
+ #define STACK_SIZE (1024 * 1024)
+diff --git a/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c b/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
+index daa952711d8fdf..e9c07d561ded6d 100644
+--- a/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
++++ b/tools/testing/selftests/bpf/prog_tests/parse_tcp_hdr_opt.c
+@@ -1,5 +1,6 @@
+ // SPDX-License-Identifier: GPL-2.0
+
++#define _GNU_SOURCE
+ #include <test_progs.h>
+ #include <network_helpers.h>
+ #include "test_parse_tcp_hdr_opt.skel.h"
+diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+index de2466547efe0f..a1ab0af004549b 100644
+--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
++++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+@@ -18,7 +18,6 @@
+ #include <arpa/inet.h>
+ #include <assert.h>
+ #include <errno.h>
+-#include <error.h>
+ #include <fcntl.h>
+ #include <sched.h>
+ #include <stdio.h>
+diff --git a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+index b1073d36d77ac2..a80a83e0440e3f 100644
+--- a/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
++++ b/tools/testing/selftests/bpf/prog_tests/tc_redirect.c
+@@ -471,7 +471,7 @@ static int set_forwarding(bool enable)
+
+ static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp)
+ {
+- struct __kernel_timespec pkt_ts = {};
++ struct timespec pkt_ts = {};
+ char ctl[CMSG_SPACE(sizeof(pkt_ts))];
+ struct timespec now_ts;
+ struct msghdr msg = {};
+@@ -495,7 +495,7 @@ static int __rcv_tstamp(int fd, const char *expected, size_t s, __u64 *tstamp)
+
+ cmsg = CMSG_FIRSTHDR(&msg);
+ if (cmsg && cmsg->cmsg_level == SOL_SOCKET &&
+- cmsg->cmsg_type == SO_TIMESTAMPNS_NEW)
++ cmsg->cmsg_type == SO_TIMESTAMPNS)
+ memcpy(&pkt_ts, CMSG_DATA(cmsg), sizeof(pkt_ts));
+
+ pkt_ns = pkt_ts.tv_sec * NSEC_PER_SEC + pkt_ts.tv_nsec;
+@@ -537,9 +537,9 @@ static int wait_netstamp_needed_key(void)
+ if (!ASSERT_GE(srv_fd, 0, "start_server"))
+ goto done;
+
+- err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
++ err = setsockopt(srv_fd, SOL_SOCKET, SO_TIMESTAMPNS,
+ &opt, sizeof(opt));
+- if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)"))
++ if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS)"))
+ goto done;
+
+ cli_fd = connect_to_fd(srv_fd, TIMEOUT_MILLIS);
+@@ -621,9 +621,9 @@ static void test_inet_dtime(int family, int type, const char *addr, __u16 port)
+ return;
+
+ /* Ensure the kernel puts the (rcv) timestamp for all skb */
+- err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS_NEW,
++ err = setsockopt(listen_fd, SOL_SOCKET, SO_TIMESTAMPNS,
+ &opt, sizeof(opt));
+- if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS_NEW)"))
++ if (!ASSERT_OK(err, "setsockopt(SO_TIMESTAMPNS)"))
+ goto done;
+
+ if (type == SOCK_STREAM) {
+diff --git a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+index f2b99d95d91607..c38784c1c066e6 100644
+--- a/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
++++ b/tools/testing/selftests/bpf/prog_tests/tcp_rtt.c
+@@ -1,4 +1,5 @@
+ // SPDX-License-Identifier: GPL-2.0
++#define _GNU_SOURCE
+ #include <test_progs.h>
+ #include "cgroup_helpers.h"
+ #include "network_helpers.h"
+diff --git a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
+index e51721df14fc19..dfff6feac12c3c 100644
+--- a/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
++++ b/tools/testing/selftests/bpf/prog_tests/user_ringbuf.c
+@@ -4,6 +4,7 @@
+ #define _GNU_SOURCE
+ #include <linux/compiler.h>
+ #include <linux/ring_buffer.h>
++#include <linux/build_bug.h>
+ #include <pthread.h>
+ #include <stdio.h>
+ #include <stdlib.h>
+diff --git a/tools/testing/selftests/bpf/progs/bpf_misc.h b/tools/testing/selftests/bpf/progs/bpf_misc.h
+index fb2f5513e29e1c..20541a7cd8070d 100644
+--- a/tools/testing/selftests/bpf/progs/bpf_misc.h
++++ b/tools/testing/selftests/bpf/progs/bpf_misc.h
+@@ -2,14 +2,17 @@
+ #ifndef __BPF_MISC_H__
+ #define __BPF_MISC_H__
+
++#define XSTR(s) STR(s)
++#define STR(s) #s
++
+ /* This set of attributes controls behavior of the
+ * test_loader.c:test_loader__run_subtests().
+ *
+ * The test_loader sequentially loads each program in a skeleton.
+ * Programs could be loaded in privileged and unprivileged modes.
+- * - __success, __failure, __msg imply privileged mode;
+- * - __success_unpriv, __failure_unpriv, __msg_unpriv imply
+- * unprivileged mode.
++ * - __success, __failure, __msg, __regex imply privileged mode;
++ * - __success_unpriv, __failure_unpriv, __msg_unpriv, __regex_unpriv
++ * imply unprivileged mode.
+ * If combination of privileged and unprivileged attributes is present
+ * both modes are used. If none are present privileged mode is implied.
+ *
+@@ -24,6 +27,12 @@
+ * Multiple __msg attributes could be specified.
+ * __msg_unpriv Same as __msg but for unprivileged mode.
+ *
++ * __regex Same as __msg, but using a regular expression.
++ * __regex_unpriv Same as __msg_unpriv but using a regular expression.
++ * __xlated Expect a line in a disassembly log after verifier applies rewrites.
++ * Multiple __xlated attributes could be specified.
++ * __xlated_unpriv Same as __xlated but for unprivileged mode.
++ *
+ * __success Expect program load success in privileged mode.
+ * __success_unpriv Expect program load success in unprivileged mode.
+ *
+@@ -57,12 +66,20 @@
+ * __auxiliary Annotated program is not a separate test, but used as auxiliary
+ * for some other test cases and should always be loaded.
+ * __auxiliary_unpriv Same, but load program in unprivileged mode.
++ *
++ * __arch_* Specify on which architecture the test case should be tested.
++ * Several __arch_* annotations could be specified at once.
++ * When test case is not run on current arch it is marked as skipped.
+ */
+-#define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" msg)))
++#define __msg(msg) __attribute__((btf_decl_tag("comment:test_expect_msg=" XSTR(__COUNTER__) "=" msg)))
++#define __regex(regex) __attribute__((btf_decl_tag("comment:test_expect_regex=" XSTR(__COUNTER__) "=" regex)))
++#define __xlated(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated=" XSTR(__COUNTER__) "=" msg)))
+ #define __failure __attribute__((btf_decl_tag("comment:test_expect_failure")))
+ #define __success __attribute__((btf_decl_tag("comment:test_expect_success")))
+ #define __description(desc) __attribute__((btf_decl_tag("comment:test_description=" desc)))
+-#define __msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" msg)))
++#define __msg_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_msg_unpriv=" XSTR(__COUNTER__) "=" msg)))
++#define __regex_unpriv(regex) __attribute__((btf_decl_tag("comment:test_expect_regex_unpriv=" XSTR(__COUNTER__) "=" regex)))
++#define __xlated_unpriv(msg) __attribute__((btf_decl_tag("comment:test_expect_xlated_unpriv=" XSTR(__COUNTER__) "=" msg)))
+ #define __failure_unpriv __attribute__((btf_decl_tag("comment:test_expect_failure_unpriv")))
+ #define __success_unpriv __attribute__((btf_decl_tag("comment:test_expect_success_unpriv")))
+ #define __log_level(lvl) __attribute__((btf_decl_tag("comment:test_log_level="#lvl)))
+@@ -72,6 +89,10 @@
+ #define __auxiliary __attribute__((btf_decl_tag("comment:test_auxiliary")))
+ #define __auxiliary_unpriv __attribute__((btf_decl_tag("comment:test_auxiliary_unpriv")))
+ #define __btf_path(path) __attribute__((btf_decl_tag("comment:test_btf_path=" path)))
++#define __arch(arch) __attribute__((btf_decl_tag("comment:test_arch=" arch)))
++#define __arch_x86_64 __arch("X86_64")
++#define __arch_arm64 __arch("ARM64")
++#define __arch_riscv64 __arch("RISCV64")
+
+ /* Convenience macro for use with 'asm volatile' blocks */
+ #define __naked __attribute__((naked))
+diff --git a/tools/testing/selftests/bpf/progs/cg_storage_multi.h b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
+index a0778fe7857a14..41d59f0ee606c7 100644
+--- a/tools/testing/selftests/bpf/progs/cg_storage_multi.h
++++ b/tools/testing/selftests/bpf/progs/cg_storage_multi.h
+@@ -3,8 +3,6 @@
+ #ifndef __PROGS_CG_STORAGE_MULTI_H
+ #define __PROGS_CG_STORAGE_MULTI_H
+
+-#include <asm/types.h>
+-
+ struct cgroup_value {
+ __u32 egress_pkts;
+ __u32 ingress_pkts;
+diff --git a/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
+index f5ac5f3e89196f..568816307f7125 100644
+--- a/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
++++ b/tools/testing/selftests/bpf/progs/test_libbpf_get_fd_by_id_opts.c
+@@ -31,6 +31,7 @@ int BPF_PROG(check_access, struct bpf_map *map, fmode_t fmode)
+
+ if (fmode & FMODE_WRITE)
+ return -EACCES;
++ barrier();
+
+ return 0;
+ }
+diff --git a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+index 85e48069c9e616..d4b99c3b4719b2 100644
+--- a/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
++++ b/tools/testing/selftests/bpf/progs/verifier_spill_fill.c
+@@ -1213,10 +1213,10 @@ __success __log_level(2)
+ * - once for path entry - label 2;
+ * - once for path entry - label 1 - label 2.
+ */
+-__msg("r1 = *(u64 *)(r10 -8)")
+-__msg("exit")
+-__msg("r1 = *(u64 *)(r10 -8)")
+-__msg("exit")
++__msg("8: (79) r1 = *(u64 *)(r10 -8)")
++__msg("9: (95) exit")
++__msg("from 2 to 7")
++__msg("8: safe")
+ __msg("processed 11 insns")
+ __flag(BPF_F_TEST_STATE_FREQ)
+ __naked void old_stack_misc_vs_cur_ctx_ptr(void)
+diff --git a/tools/testing/selftests/bpf/test_cpp.cpp b/tools/testing/selftests/bpf/test_cpp.cpp
+index dde0bb16e782e9..abc2a56ab26164 100644
+--- a/tools/testing/selftests/bpf/test_cpp.cpp
++++ b/tools/testing/selftests/bpf/test_cpp.cpp
+@@ -6,6 +6,10 @@
+ #include <bpf/libbpf.h>
+ #include <bpf/bpf.h>
+ #include <bpf/btf.h>
++
++#ifndef _Bool
++#define _Bool bool
++#endif
+ #include "test_core_extern.skel.h"
+ #include "struct_ops_module.skel.h"
+
+diff --git a/tools/testing/selftests/bpf/test_loader.c b/tools/testing/selftests/bpf/test_loader.c
+index 524c38e9cde48f..2150e9c9b53fb1 100644
+--- a/tools/testing/selftests/bpf/test_loader.c
++++ b/tools/testing/selftests/bpf/test_loader.c
+@@ -2,10 +2,12 @@
+ /* Copyright (c) 2022 Meta Platforms, Inc. and affiliates. */
+ #include <linux/capability.h>
+ #include <stdlib.h>
++#include <regex.h>
+ #include <test_progs.h>
+ #include <bpf/btf.h>
+
+ #include "autoconf_helper.h"
++#include "disasm_helpers.h"
+ #include "unpriv_helpers.h"
+ #include "cap_helpers.h"
+
+@@ -17,9 +19,13 @@
+ #define TEST_TAG_EXPECT_FAILURE "comment:test_expect_failure"
+ #define TEST_TAG_EXPECT_SUCCESS "comment:test_expect_success"
+ #define TEST_TAG_EXPECT_MSG_PFX "comment:test_expect_msg="
++#define TEST_TAG_EXPECT_REGEX_PFX "comment:test_expect_regex="
++#define TEST_TAG_EXPECT_XLATED_PFX "comment:test_expect_xlated="
+ #define TEST_TAG_EXPECT_FAILURE_UNPRIV "comment:test_expect_failure_unpriv"
+ #define TEST_TAG_EXPECT_SUCCESS_UNPRIV "comment:test_expect_success_unpriv"
+ #define TEST_TAG_EXPECT_MSG_PFX_UNPRIV "comment:test_expect_msg_unpriv="
++#define TEST_TAG_EXPECT_REGEX_PFX_UNPRIV "comment:test_expect_regex_unpriv="
++#define TEST_TAG_EXPECT_XLATED_PFX_UNPRIV "comment:test_expect_xlated_unpriv="
+ #define TEST_TAG_LOG_LEVEL_PFX "comment:test_log_level="
+ #define TEST_TAG_PROG_FLAGS_PFX "comment:test_prog_flags="
+ #define TEST_TAG_DESCRIPTION_PFX "comment:test_description="
+@@ -28,6 +34,7 @@
+ #define TEST_TAG_AUXILIARY "comment:test_auxiliary"
+ #define TEST_TAG_AUXILIARY_UNPRIV "comment:test_auxiliary_unpriv"
+ #define TEST_BTF_PATH "comment:test_btf_path="
++#define TEST_TAG_ARCH "comment:test_arch="
+
+ /* Warning: duplicated in bpf_misc.h */
+ #define POINTER_VALUE 0xcafe4all
+@@ -46,11 +53,22 @@ enum mode {
+ UNPRIV = 2
+ };
+
++struct expect_msg {
++ const char *substr; /* substring match */
++ const char *regex_str; /* regex-based match */
++ regex_t regex;
++};
++
++struct expected_msgs {
++ struct expect_msg *patterns;
++ size_t cnt;
++};
++
+ struct test_subspec {
+ char *name;
+ bool expect_failure;
+- const char **expect_msgs;
+- size_t expect_msg_cnt;
++ struct expected_msgs expect_msgs;
++ struct expected_msgs expect_xlated;
+ int retval;
+ bool execute;
+ };
+@@ -63,6 +81,7 @@ struct test_spec {
+ int log_level;
+ int prog_flags;
+ int mode_mask;
++ int arch_mask;
+ bool auxiliary;
+ bool valid;
+ };
+@@ -87,31 +106,64 @@ void test_loader_fini(struct test_loader *tester)
+ free(tester->log_buf);
+ }
+
++static void free_msgs(struct expected_msgs *msgs)
++{
++ int i;
++
++ for (i = 0; i < msgs->cnt; i++)
++ if (msgs->patterns[i].regex_str)
++ regfree(&msgs->patterns[i].regex);
++ free(msgs->patterns);
++ msgs->patterns = NULL;
++ msgs->cnt = 0;
++}
++
+ static void free_test_spec(struct test_spec *spec)
+ {
++ /* Deallocate expect_msgs arrays. */
++ free_msgs(&spec->priv.expect_msgs);
++ free_msgs(&spec->unpriv.expect_msgs);
++ free_msgs(&spec->priv.expect_xlated);
++ free_msgs(&spec->unpriv.expect_xlated);
++
+ free(spec->priv.name);
+ free(spec->unpriv.name);
+- free(spec->priv.expect_msgs);
+- free(spec->unpriv.expect_msgs);
+-
+ spec->priv.name = NULL;
+ spec->unpriv.name = NULL;
+- spec->priv.expect_msgs = NULL;
+- spec->unpriv.expect_msgs = NULL;
+ }
+
+-static int push_msg(const char *msg, struct test_subspec *subspec)
++static int push_msg(const char *substr, const char *regex_str, struct expected_msgs *msgs)
+ {
+ void *tmp;
++ int regcomp_res;
++ char error_msg[100];
++ struct expect_msg *msg;
+
+- tmp = realloc(subspec->expect_msgs, (1 + subspec->expect_msg_cnt) * sizeof(void *));
++ tmp = realloc(msgs->patterns,
++ (1 + msgs->cnt) * sizeof(struct expect_msg));
+ if (!tmp) {
+ ASSERT_FAIL("failed to realloc memory for messages\n");
+ return -ENOMEM;
+ }
+- subspec->expect_msgs = tmp;
+- subspec->expect_msgs[subspec->expect_msg_cnt++] = msg;
++ msgs->patterns = tmp;
++ msg = &msgs->patterns[msgs->cnt];
++
++ if (substr) {
++ msg->substr = substr;
++ msg->regex_str = NULL;
++ } else {
++ msg->regex_str = regex_str;
++ msg->substr = NULL;
++ regcomp_res = regcomp(&msg->regex, regex_str, REG_EXTENDED|REG_NEWLINE);
++ if (regcomp_res != 0) {
++ regerror(regcomp_res, &msg->regex, error_msg, sizeof(error_msg));
++ PRINT_FAIL("Regexp compilation error in '%s': '%s'\n",
++ regex_str, error_msg);
++ return -EINVAL;
++ }
++ }
+
++ msgs->cnt += 1;
+ return 0;
+ }
+
+@@ -163,6 +215,41 @@ static void update_flags(int *flags, int flag, bool clear)
+ *flags |= flag;
+ }
+
++/* Matches a string of form '<pfx>[^=]=.*' and returns it's suffix.
++ * Used to parse btf_decl_tag values.
++ * Such values require unique prefix because compiler does not add
++ * same __attribute__((btf_decl_tag(...))) twice.
++ * Test suite uses two-component tags for such cases:
++ *
++ * <pfx> __COUNTER__ '='
++ *
++ * For example, two consecutive __msg tags '__msg("foo") __msg("foo")'
++ * would be encoded as:
++ *
++ * [18] DECL_TAG 'comment:test_expect_msg=0=foo' type_id=15 component_idx=-1
++ * [19] DECL_TAG 'comment:test_expect_msg=1=foo' type_id=15 component_idx=-1
++ *
++ * And the purpose of this function is to extract 'foo' from the above.
++ */
++static const char *skip_dynamic_pfx(const char *s, const char *pfx)
++{
++ const char *msg;
++
++ if (strncmp(s, pfx, strlen(pfx)) != 0)
++ return NULL;
++ msg = s + strlen(pfx);
++ msg = strchr(msg, '=');
++ if (!msg)
++ return NULL;
++ return msg + 1;
++}
++
++enum arch {
++ ARCH_X86_64 = 0x1,
++ ARCH_ARM64 = 0x2,
++ ARCH_RISCV64 = 0x4,
++};
++
+ /* Uses btf_decl_tag attributes to describe the expected test
+ * behavior, see bpf_misc.h for detailed description of each attribute
+ * and attribute combinations.
+@@ -176,6 +263,7 @@ static int parse_test_spec(struct test_loader *tester,
+ bool has_unpriv_result = false;
+ bool has_unpriv_retval = false;
+ int func_id, i, err = 0;
++ u32 arch_mask = 0;
+ struct btf *btf;
+
+ memset(spec, 0, sizeof(*spec));
+@@ -231,15 +319,33 @@ static int parse_test_spec(struct test_loader *tester,
+ } else if (strcmp(s, TEST_TAG_AUXILIARY_UNPRIV) == 0) {
+ spec->auxiliary = true;
+ spec->mode_mask |= UNPRIV;
+- } else if (str_has_pfx(s, TEST_TAG_EXPECT_MSG_PFX)) {
+- msg = s + sizeof(TEST_TAG_EXPECT_MSG_PFX) - 1;
+- err = push_msg(msg, &spec->priv);
++ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX))) {
++ err = push_msg(msg, NULL, &spec->priv.expect_msgs);
++ if (err)
++ goto cleanup;
++ spec->mode_mask |= PRIV;
++ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV))) {
++ err = push_msg(msg, NULL, &spec->unpriv.expect_msgs);
++ if (err)
++ goto cleanup;
++ spec->mode_mask |= UNPRIV;
++ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_REGEX_PFX))) {
++ err = push_msg(NULL, msg, &spec->priv.expect_msgs);
++ if (err)
++ goto cleanup;
++ spec->mode_mask |= PRIV;
++ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_REGEX_PFX_UNPRIV))) {
++ err = push_msg(NULL, msg, &spec->unpriv.expect_msgs);
++ if (err)
++ goto cleanup;
++ spec->mode_mask |= UNPRIV;
++ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_XLATED_PFX))) {
++ err = push_msg(msg, NULL, &spec->priv.expect_xlated);
+ if (err)
+ goto cleanup;
+ spec->mode_mask |= PRIV;
+- } else if (str_has_pfx(s, TEST_TAG_EXPECT_MSG_PFX_UNPRIV)) {
+- msg = s + sizeof(TEST_TAG_EXPECT_MSG_PFX_UNPRIV) - 1;
+- err = push_msg(msg, &spec->unpriv);
++ } else if ((msg = skip_dynamic_pfx(s, TEST_TAG_EXPECT_XLATED_PFX_UNPRIV))) {
++ err = push_msg(msg, NULL, &spec->unpriv.expect_xlated);
+ if (err)
+ goto cleanup;
+ spec->mode_mask |= UNPRIV;
+@@ -290,11 +396,26 @@ static int parse_test_spec(struct test_loader *tester,
+ goto cleanup;
+ update_flags(&spec->prog_flags, flags, clear);
+ }
++ } else if (str_has_pfx(s, TEST_TAG_ARCH)) {
++ val = s + sizeof(TEST_TAG_ARCH) - 1;
++ if (strcmp(val, "X86_64") == 0) {
++ arch_mask |= ARCH_X86_64;
++ } else if (strcmp(val, "ARM64") == 0) {
++ arch_mask |= ARCH_ARM64;
++ } else if (strcmp(val, "RISCV64") == 0) {
++ arch_mask |= ARCH_RISCV64;
++ } else {
++ PRINT_FAIL("bad arch spec: '%s'", val);
++ err = -EINVAL;
++ goto cleanup;
++ }
+ } else if (str_has_pfx(s, TEST_BTF_PATH)) {
+ spec->btf_custom_path = s + sizeof(TEST_BTF_PATH) - 1;
+ }
+ }
+
++ spec->arch_mask = arch_mask;
++
+ if (spec->mode_mask == 0)
+ spec->mode_mask = PRIV;
+
+@@ -336,17 +457,25 @@ static int parse_test_spec(struct test_loader *tester,
+ spec->unpriv.execute = spec->priv.execute;
+ }
+
+- if (!spec->unpriv.expect_msgs) {
+- size_t sz = spec->priv.expect_msg_cnt * sizeof(void *);
++ if (spec->unpriv.expect_msgs.cnt == 0) {
++ for (i = 0; i < spec->priv.expect_msgs.cnt; i++) {
++ struct expect_msg *msg = &spec->priv.expect_msgs.patterns[i];
+
+- spec->unpriv.expect_msgs = malloc(sz);
+- if (!spec->unpriv.expect_msgs) {
+- PRINT_FAIL("failed to allocate memory for unpriv.expect_msgs\n");
+- err = -ENOMEM;
+- goto cleanup;
++ err = push_msg(msg->substr, msg->regex_str,
++ &spec->unpriv.expect_msgs);
++ if (err)
++ goto cleanup;
++ }
++ }
++ if (spec->unpriv.expect_xlated.cnt == 0) {
++ for (i = 0; i < spec->priv.expect_xlated.cnt; i++) {
++ struct expect_msg *msg = &spec->priv.expect_xlated.patterns[i];
++
++ err = push_msg(msg->substr, msg->regex_str,
++ &spec->unpriv.expect_xlated);
++ if (err)
++ goto cleanup;
+ }
+- memcpy(spec->unpriv.expect_msgs, spec->priv.expect_msgs, sz);
+- spec->unpriv.expect_msg_cnt = spec->priv.expect_msg_cnt;
+ }
+ }
+
+@@ -386,7 +515,6 @@ static void prepare_case(struct test_loader *tester,
+ bpf_program__set_flags(prog, prog_flags | spec->prog_flags);
+
+ tester->log_buf[0] = '\0';
+- tester->next_match_pos = 0;
+ }
+
+ static void emit_verifier_log(const char *log_buf, bool force)
+@@ -396,33 +524,48 @@ static void emit_verifier_log(const char *log_buf, bool force)
+ fprintf(stdout, "VERIFIER LOG:\n=============\n%s=============\n", log_buf);
+ }
+
+-static void validate_case(struct test_loader *tester,
+- struct test_subspec *subspec,
+- struct bpf_object *obj,
+- struct bpf_program *prog,
+- int load_err)
++static void emit_xlated(const char *xlated, bool force)
+ {
+- int i, j;
+-
+- for (i = 0; i < subspec->expect_msg_cnt; i++) {
+- char *match;
+- const char *expect_msg;
++ if (!force && env.verbosity == VERBOSE_NONE)
++ return;
++ fprintf(stdout, "XLATED:\n=============\n%s=============\n", xlated);
++}
+
+- expect_msg = subspec->expect_msgs[i];
++static void validate_msgs(char *log_buf, struct expected_msgs *msgs,
++ void (*emit_fn)(const char *buf, bool force))
++{
++ regmatch_t reg_match[1];
++ const char *log = log_buf;
++ int i, j, err;
++
++ for (i = 0; i < msgs->cnt; i++) {
++ struct expect_msg *msg = &msgs->patterns[i];
++ const char *match = NULL;
++
++ if (msg->substr) {
++ match = strstr(log, msg->substr);
++ if (match)
++ log = match + strlen(msg->substr);
++ } else {
++ err = regexec(&msg->regex, log, 1, reg_match, 0);
++ if (err == 0) {
++ match = log + reg_match[0].rm_so;
++ log += reg_match[0].rm_eo;
++ }
++ }
+
+- match = strstr(tester->log_buf + tester->next_match_pos, expect_msg);
+ if (!ASSERT_OK_PTR(match, "expect_msg")) {
+- /* if we are in verbose mode, we've already emitted log */
+ if (env.verbosity == VERBOSE_NONE)
+- emit_verifier_log(tester->log_buf, true /*force*/);
+- for (j = 0; j < i; j++)
+- fprintf(stderr,
+- "MATCHED MSG: '%s'\n", subspec->expect_msgs[j]);
+- fprintf(stderr, "EXPECTED MSG: '%s'\n", expect_msg);
++ emit_fn(log_buf, true /*force*/);
++ for (j = 0; j <= i; j++) {
++ msg = &msgs->patterns[j];
++ fprintf(stderr, "%s %s: '%s'\n",
++ j < i ? "MATCHED " : "EXPECTED",
++ msg->substr ? "SUBSTR" : " REGEX",
++ msg->substr ?: msg->regex_str);
++ }
+ return;
+ }
+-
+- tester->next_match_pos = match - tester->log_buf + strlen(expect_msg);
+ }
+ }
+
+@@ -550,6 +693,51 @@ static bool should_do_test_run(struct test_spec *spec, struct test_subspec *subs
+ return true;
+ }
+
++/* Get a disassembly of BPF program after verifier applies all rewrites */
++static int get_xlated_program_text(int prog_fd, char *text, size_t text_sz)
++{
++ struct bpf_insn *insn_start = NULL, *insn, *insn_end;
++ __u32 insns_cnt = 0, i;
++ char buf[64];
++ FILE *out = NULL;
++ int err;
++
++ err = get_xlated_program(prog_fd, &insn_start, &insns_cnt);
++ if (!ASSERT_OK(err, "get_xlated_program"))
++ goto out;
++ out = fmemopen(text, text_sz, "w");
++ if (!ASSERT_OK_PTR(out, "open_memstream"))
++ goto out;
++ insn_end = insn_start + insns_cnt;
++ insn = insn_start;
++ while (insn < insn_end) {
++ i = insn - insn_start;
++ insn = disasm_insn(insn, buf, sizeof(buf));
++ fprintf(out, "%d: %s\n", i, buf);
++ }
++ fflush(out);
++
++out:
++ free(insn_start);
++ if (out)
++ fclose(out);
++ return err;
++}
++
++static bool run_on_current_arch(int arch_mask)
++{
++ if (arch_mask == 0)
++ return true;
++#if defined(__x86_64__)
++ return arch_mask & ARCH_X86_64;
++#elif defined(__aarch64__)
++ return arch_mask & ARCH_ARM64;
++#elif defined(__riscv) && __riscv_xlen == 64
++ return arch_mask & ARCH_RISCV64;
++#endif
++ return false;
++}
++
+ /* this function is forced noinline and has short generic name to look better
+ * in test_progs output (in case of a failure)
+ */
+@@ -574,6 +762,11 @@ void run_subtest(struct test_loader *tester,
+ if (!test__start_subtest(subspec->name))
+ return;
+
++ if (!run_on_current_arch(spec->arch_mask)) {
++ test__skip();
++ return;
++ }
++
+ if (unpriv) {
+ if (!can_execute_unpriv(tester, spec)) {
+ test__skip();
+@@ -634,9 +827,17 @@ void run_subtest(struct test_loader *tester,
+ goto tobj_cleanup;
+ }
+ }
+-
+ emit_verifier_log(tester->log_buf, false /*force*/);
+- validate_case(tester, subspec, tobj, tprog, err);
++ validate_msgs(tester->log_buf, &subspec->expect_msgs, emit_verifier_log);
++
++ if (subspec->expect_xlated.cnt) {
++ err = get_xlated_program_text(bpf_program__fd(tprog),
++ tester->log_buf, tester->log_buf_sz);
++ if (err)
++ goto tobj_cleanup;
++ emit_xlated(tester->log_buf, false /*force*/);
++ validate_msgs(tester->log_buf, &subspec->expect_xlated, emit_xlated);
++ }
+
+ if (should_do_test_run(spec, subspec)) {
+ /* For some reason test_verifier executes programs
+diff --git a/tools/testing/selftests/bpf/test_lru_map.c b/tools/testing/selftests/bpf/test_lru_map.c
+index 4d0650cfb5cd8b..fda7589c50236c 100644
+--- a/tools/testing/selftests/bpf/test_lru_map.c
++++ b/tools/testing/selftests/bpf/test_lru_map.c
+@@ -126,7 +126,8 @@ static int sched_next_online(int pid, int *next_to_try)
+
+ while (next < nr_cpus) {
+ CPU_ZERO(&cpuset);
+- CPU_SET(next++, &cpuset);
++ CPU_SET(next, &cpuset);
++ next++;
+ if (!sched_setaffinity(pid, sizeof(cpuset), &cpuset)) {
+ ret = 0;
+ break;
+diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c
+index 89ff704e9dad5e..d5d0cb4eb1975b 100644
+--- a/tools/testing/selftests/bpf/test_progs.c
++++ b/tools/testing/selftests/bpf/test_progs.c
+@@ -10,7 +10,6 @@
+ #include <sched.h>
+ #include <signal.h>
+ #include <string.h>
+-#include <execinfo.h> /* backtrace */
+ #include <sys/sysinfo.h> /* get_nprocs */
+ #include <netinet/in.h>
+ #include <sys/select.h>
+@@ -19,6 +18,21 @@
+ #include <bpf/btf.h>
+ #include "json_writer.h"
+
++#ifdef __GLIBC__
++#include <execinfo.h> /* backtrace */
++#endif
++
++/* Default backtrace funcs if missing at link */
++__weak int backtrace(void **buffer, int size)
++{
++ return 0;
++}
++
++__weak void backtrace_symbols_fd(void *const *buffer, int size, int fd)
++{
++ dprintf(fd, "<backtrace not supported>\n");
++}
++
+ static bool verbose(void)
+ {
+ return env.verbosity > VERBOSE_NONE;
+@@ -1731,7 +1745,7 @@ int main(int argc, char **argv)
+ /* launch workers if requested */
+ env.worker_id = -1; /* main process */
+ if (env.workers) {
+- env.worker_pids = calloc(sizeof(__pid_t), env.workers);
++ env.worker_pids = calloc(sizeof(pid_t), env.workers);
+ env.worker_socks = calloc(sizeof(int), env.workers);
+ if (env.debug)
+ fprintf(stdout, "Launching %d workers.\n", env.workers);
+diff --git a/tools/testing/selftests/bpf/test_progs.h b/tools/testing/selftests/bpf/test_progs.h
+index 0ba5a20b19ba8e..8e997de596db05 100644
+--- a/tools/testing/selftests/bpf/test_progs.h
++++ b/tools/testing/selftests/bpf/test_progs.h
+@@ -438,7 +438,6 @@ typedef int (*pre_execution_cb)(struct bpf_object *obj);
+ struct test_loader {
+ char *log_buf;
+ size_t log_buf_sz;
+- size_t next_match_pos;
+ pre_execution_cb pre_execution_cb;
+
+ struct bpf_object *obj;
+diff --git a/tools/testing/selftests/bpf/testing_helpers.c b/tools/testing/selftests/bpf/testing_helpers.c
+index d5379a0e6da804..680e452583a78b 100644
+--- a/tools/testing/selftests/bpf/testing_helpers.c
++++ b/tools/testing/selftests/bpf/testing_helpers.c
+@@ -220,13 +220,13 @@ int parse_test_list(const char *s,
+ bool is_glob_pattern)
+ {
+ char *input, *state = NULL, *test_spec;
+- int err = 0;
++ int err = 0, cnt = 0;
+
+ input = strdup(s);
+ if (!input)
+ return -ENOMEM;
+
+- while ((test_spec = strtok_r(state ? NULL : input, ",", &state))) {
++ while ((test_spec = strtok_r(cnt++ ? NULL : input, ",", &state))) {
+ err = insert_test(set, test_spec, is_glob_pattern);
+ if (err)
+ break;
+@@ -451,7 +451,7 @@ int get_xlated_program(int fd_prog, struct bpf_insn **buf, __u32 *cnt)
+
+ *cnt = xlated_prog_len / buf_element_size;
+ *buf = calloc(*cnt, buf_element_size);
+- if (!buf) {
++ if (!*buf) {
+ perror("can't allocate xlated program buffer");
+ return -ENOMEM;
+ }
+diff --git a/tools/testing/selftests/bpf/unpriv_helpers.c b/tools/testing/selftests/bpf/unpriv_helpers.c
+index b6d016461fb023..220f6a96381345 100644
+--- a/tools/testing/selftests/bpf/unpriv_helpers.c
++++ b/tools/testing/selftests/bpf/unpriv_helpers.c
+@@ -2,7 +2,6 @@
+
+ #include <stdbool.h>
+ #include <stdlib.h>
+-#include <error.h>
+ #include <stdio.h>
+ #include <string.h>
+ #include <unistd.h>
+diff --git a/tools/testing/selftests/bpf/veristat.c b/tools/testing/selftests/bpf/veristat.c
+index b2854238d4a0eb..fd9780082ff48a 100644
+--- a/tools/testing/selftests/bpf/veristat.c
++++ b/tools/testing/selftests/bpf/veristat.c
+@@ -784,13 +784,13 @@ static int parse_stat(const char *stat_name, struct stat_specs *specs)
+ static int parse_stats(const char *stats_str, struct stat_specs *specs)
+ {
+ char *input, *state = NULL, *next;
+- int err;
++ int err, cnt = 0;
+
+ input = strdup(stats_str);
+ if (!input)
+ return -ENOMEM;
+
+- while ((next = strtok_r(state ? NULL : input, ",", &state))) {
++ while ((next = strtok_r(cnt++ ? NULL : input, ",", &state))) {
+ err = parse_stat(next, specs);
+ if (err) {
+ free(input);
+@@ -1493,7 +1493,7 @@ static int parse_stats_csv(const char *filename, struct stat_specs *specs,
+ while (fgets(line, sizeof(line), f)) {
+ char *input = line, *state = NULL, *next;
+ struct verif_stats *st = NULL;
+- int col = 0;
++ int col = 0, cnt = 0;
+
+ if (!header) {
+ void *tmp;
+@@ -1511,7 +1511,7 @@ static int parse_stats_csv(const char *filename, struct stat_specs *specs,
+ *stat_cntp += 1;
+ }
+
+- while ((next = strtok_r(state ? NULL : input, ",\n", &state))) {
++ while ((next = strtok_r(cnt++ ? NULL : input, ",\n", &state))) {
+ if (header) {
+ /* for the first line, set up spec stats */
+ err = parse_stat(next, specs);
+diff --git a/tools/testing/selftests/dt/test_unprobed_devices.sh b/tools/testing/selftests/dt/test_unprobed_devices.sh
+index 2d7e70c5ad2d36..5e3f42ef249eec 100755
+--- a/tools/testing/selftests/dt/test_unprobed_devices.sh
++++ b/tools/testing/selftests/dt/test_unprobed_devices.sh
+@@ -34,8 +34,21 @@ nodes_compatible=$(
+ # Check if node is available
+ if [[ -e "${node}"/status ]]; then
+ status=$(tr -d '\000' < "${node}"/status)
+- [[ "${status}" != "okay" && "${status}" != "ok" ]] && continue
++ if [[ "${status}" != "okay" && "${status}" != "ok" ]]; then
++ if [ -n "${disabled_nodes_regex}" ]; then
++ disabled_nodes_regex="${disabled_nodes_regex}|${node}"
++ else
++ disabled_nodes_regex="${node}"
++ fi
++ continue
++ fi
+ fi
++
++ # Ignore this node if one of its ancestors was disabled
++ if [ -n "${disabled_nodes_regex}" ]; then
++ echo "${node}" | grep -q -E "${disabled_nodes_regex}" && continue
++ fi
++
+ echo "${node}" | sed -e 's|\/proc\/device-tree||'
+ done | sort
+ )
+diff --git a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
+index c45094d1e1d2db..803efd7b56c77d 100644
+--- a/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
++++ b/tools/testing/selftests/ftrace/test.d/00basic/test_ownership.tc
+@@ -6,6 +6,18 @@ original_group=`stat -c "%g" .`
+ original_owner=`stat -c "%u" .`
+
+ mount_point=`stat -c '%m' .`
++
++# If stat -c '%m' does not work (e.g. busybox) or failed, try to use the
++# current working directory (which should be a tracefs) as the mount point.
++if [ ! -d "$mount_point" ]; then
++ if mount | grep -qw $PWD ; then
++ mount_point=$PWD
++ else
++ # If PWD doesn't work, that is an environmental problem.
++ exit_unresolved
++ fi
++fi
++
+ mount_options=`mount | grep "$mount_point" | sed -e 's/.*(\(.*\)).*/\1/'`
+
+ # find another owner and group that is not the original
+diff --git a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+index 073a748b9380a1..263f6b798c853e 100644
+--- a/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
++++ b/tools/testing/selftests/ftrace/test.d/ftrace/func_set_ftrace_file.tc
+@@ -19,7 +19,14 @@ fail() { # mesg
+
+ FILTER=set_ftrace_filter
+ FUNC1="schedule"
+-FUNC2="sched_tick"
++if grep '^sched_tick\b' available_filter_functions; then
++ FUNC2="sched_tick"
++elif grep '^scheduler_tick\b' available_filter_functions; then
++ FUNC2="scheduler_tick"
++else
++ exit_unresolved
++fi
++
+
+ ALL_FUNCS="#### all functions enabled ####"
+
+diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc
+index e21c9c27ece476..77f4c07cdcb899 100644
+--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc
++++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_char.tc
+@@ -1,7 +1,7 @@
+ #!/bin/sh
+ # SPDX-License-Identifier: GPL-2.0
+ # description: Kprobe event char type argument
+-# requires: kprobe_events
++# requires: kprobe_events available_filter_functions
+
+ case `uname -m` in
+ x86_64)
+diff --git a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
+index 93217d4595563f..39001073f7ed5d 100644
+--- a/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
++++ b/tools/testing/selftests/ftrace/test.d/kprobe/kprobe_args_string.tc
+@@ -1,7 +1,7 @@
+ #!/bin/sh
+ # SPDX-License-Identifier: GPL-2.0
+ # description: Kprobe event string type argument
+-# requires: kprobe_events
++# requires: kprobe_events available_filter_functions
+
+ case `uname -m` in
+ x86_64)
+diff --git a/tools/testing/selftests/kselftest.h b/tools/testing/selftests/kselftest.h
+index 76c2a6945d3e83..f9214e7cdd1345 100644
+--- a/tools/testing/selftests/kselftest.h
++++ b/tools/testing/selftests/kselftest.h
+@@ -61,6 +61,7 @@
+ #define ARRAY_SIZE(arr) (sizeof(arr) / sizeof((arr)[0]))
+ #endif
+
++#if defined(__i386__) || defined(__x86_64__) /* arch */
+ /*
+ * gcc cpuid.h provides __cpuid_count() since v4.4.
+ * Clang/LLVM cpuid.h provides __cpuid_count() since v3.4.0.
+@@ -75,6 +76,7 @@
+ : "=a" (a), "=b" (b), "=c" (c), "=d" (d) \
+ : "0" (level), "2" (count))
+ #endif
++#endif /* end arch */
+
+ /* define kselftest exit codes */
+ #define KSFT_PASS 0
+diff --git a/tools/testing/selftests/net/netfilter/ipvs.sh b/tools/testing/selftests/net/netfilter/ipvs.sh
+index 4ceee9fb39495b..d3edb16cd4b3f6 100755
+--- a/tools/testing/selftests/net/netfilter/ipvs.sh
++++ b/tools/testing/selftests/net/netfilter/ipvs.sh
+@@ -97,7 +97,7 @@ cleanup() {
+ }
+
+ server_listen() {
+- ip netns exec "$ns2" socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
++ ip netns exec "$ns2" timeout 5 socat -u -4 TCP-LISTEN:8080,reuseaddr STDOUT > "${outfile}" &
+ server_pid=$!
+ sleep 0.2
+ }
+diff --git a/tools/testing/selftests/resctrl/cat_test.c b/tools/testing/selftests/resctrl/cat_test.c
+index 55315ed695f47e..18565f02163e72 100644
+--- a/tools/testing/selftests/resctrl/cat_test.c
++++ b/tools/testing/selftests/resctrl/cat_test.c
+@@ -293,12 +293,12 @@ static int cat_run_test(const struct resctrl_test *test, const struct user_param
+
+ static bool arch_supports_noncont_cat(const struct resctrl_test *test)
+ {
+- unsigned int eax, ebx, ecx, edx;
+-
+ /* AMD always supports non-contiguous CBM. */
+ if (get_vendor() == ARCH_AMD)
+ return true;
+
++#if defined(__i386__) || defined(__x86_64__) /* arch */
++ unsigned int eax, ebx, ecx, edx;
+ /* Intel support for non-contiguous CBM needs to be discovered. */
+ if (!strcmp(test->resource, "L3"))
+ __cpuid_count(0x10, 1, eax, ebx, ecx, edx);
+@@ -308,6 +308,9 @@ static bool arch_supports_noncont_cat(const struct resctrl_test *test)
+ return false;
+
+ return ((ecx >> 3) & 1);
++#endif /* end arch */
++
++ return false;
+ }
+
+ static int noncont_cat_run_test(const struct resctrl_test *test,
+diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c
+index 1192942aef911d..3163bcf8148a64 100644
+--- a/virt/kvm/kvm_main.c
++++ b/virt/kvm/kvm_main.c
+@@ -5500,6 +5500,7 @@ __visible bool kvm_rebooting;
+ EXPORT_SYMBOL_GPL(kvm_rebooting);
+
+ static DEFINE_PER_CPU(bool, hardware_enabled);
++static DEFINE_MUTEX(kvm_usage_lock);
+ static int kvm_usage_count;
+
+ static int __hardware_enable_nolock(void)
+@@ -5532,10 +5533,10 @@ static int kvm_online_cpu(unsigned int cpu)
+ * be enabled. Otherwise running VMs would encounter unrecoverable
+ * errors when scheduled to this CPU.
+ */
+- mutex_lock(&kvm_lock);
++ mutex_lock(&kvm_usage_lock);
+ if (kvm_usage_count)
+ ret = __hardware_enable_nolock();
+- mutex_unlock(&kvm_lock);
++ mutex_unlock(&kvm_usage_lock);
+ return ret;
+ }
+
+@@ -5555,10 +5556,10 @@ static void hardware_disable_nolock(void *junk)
+
+ static int kvm_offline_cpu(unsigned int cpu)
+ {
+- mutex_lock(&kvm_lock);
++ mutex_lock(&kvm_usage_lock);
+ if (kvm_usage_count)
+ hardware_disable_nolock(NULL);
+- mutex_unlock(&kvm_lock);
++ mutex_unlock(&kvm_usage_lock);
+ return 0;
+ }
+
+@@ -5574,9 +5575,9 @@ static void hardware_disable_all_nolock(void)
+ static void hardware_disable_all(void)
+ {
+ cpus_read_lock();
+- mutex_lock(&kvm_lock);
++ mutex_lock(&kvm_usage_lock);
+ hardware_disable_all_nolock();
+- mutex_unlock(&kvm_lock);
++ mutex_unlock(&kvm_usage_lock);
+ cpus_read_unlock();
+ }
+
+@@ -5607,7 +5608,7 @@ static int hardware_enable_all(void)
+ * enable hardware multiple times.
+ */
+ cpus_read_lock();
+- mutex_lock(&kvm_lock);
++ mutex_lock(&kvm_usage_lock);
+
+ r = 0;
+
+@@ -5621,7 +5622,7 @@ static int hardware_enable_all(void)
+ }
+ }
+
+- mutex_unlock(&kvm_lock);
++ mutex_unlock(&kvm_usage_lock);
+ cpus_read_unlock();
+
+ return r;
+@@ -5649,13 +5650,13 @@ static int kvm_suspend(void)
+ {
+ /*
+ * Secondary CPUs and CPU hotplug are disabled across the suspend/resume
+- * callbacks, i.e. no need to acquire kvm_lock to ensure the usage count
+- * is stable. Assert that kvm_lock is not held to ensure the system
+- * isn't suspended while KVM is enabling hardware. Hardware enabling
+- * can be preempted, but the task cannot be frozen until it has dropped
+- * all locks (userspace tasks are frozen via a fake signal).
++ * callbacks, i.e. no need to acquire kvm_usage_lock to ensure the usage
++ * count is stable. Assert that kvm_usage_lock is not held to ensure
++ * the system isn't suspended while KVM is enabling hardware. Hardware
++ * enabling can be preempted, but the task cannot be frozen until it has
++ * dropped all locks (userspace tasks are frozen via a fake signal).
+ */
+- lockdep_assert_not_held(&kvm_lock);
++ lockdep_assert_not_held(&kvm_usage_lock);
+ lockdep_assert_irqs_disabled();
+
+ if (kvm_usage_count)
+@@ -5665,7 +5666,7 @@ static int kvm_suspend(void)
+
+ static void kvm_resume(void)
+ {
+- lockdep_assert_not_held(&kvm_lock);
++ lockdep_assert_not_held(&kvm_usage_lock);
+ lockdep_assert_irqs_disabled();
+
+ if (kvm_usage_count)
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-30 16:11 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-30 16:11 UTC (permalink / raw
To: gentoo-commits
commit: 13d4521ec8233c1a6e250857c77d1c62a7fcb1e0
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Mon Sep 30 16:11:22 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Mon Sep 30 16:11:22 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=13d4521e
Remove older dtrace patch
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
2995_dtrace-6.10_p3.patch | 2352 ---------------------------------------------
1 file changed, 2352 deletions(-)
diff --git a/2995_dtrace-6.10_p3.patch b/2995_dtrace-6.10_p3.patch
deleted file mode 100644
index 775a7868..00000000
--- a/2995_dtrace-6.10_p3.patch
+++ /dev/null
@@ -1,2352 +0,0 @@
-diff --git a/Documentation/dontdiff b/Documentation/dontdiff
-index 3c399f132e2db..75b9655e57914 100644
---- a/Documentation/dontdiff
-+++ b/Documentation/dontdiff
-@@ -179,7 +179,7 @@ mkutf8data
- modpost
- modules-only.symvers
- modules.builtin
--modules.builtin.modinfo
-+modules.builtin.*
- modules.nsdeps
- modules.order
- modversions.h*
-diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst
-index 9c8d1d046ea56..79e104ffee715 100644
---- a/Documentation/kbuild/kbuild.rst
-+++ b/Documentation/kbuild/kbuild.rst
-@@ -17,6 +17,11 @@ modules.builtin
- This file lists all modules that are built into the kernel. This is used
- by modprobe to not fail when trying to load something builtin.
-
-+modules.builtin.objs
-+-----------------------
-+This file contains object mapping of modules that are built into the kernel
-+to their corresponding object files used to build the module.
-+
- modules.builtin.modinfo
- -----------------------
- This file contains modinfo from all modules that are built into the kernel.
-diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
-index 5685d7bfe4d0f..8db62fe4dadff 100644
---- a/Documentation/process/changes.rst
-+++ b/Documentation/process/changes.rst
-@@ -63,9 +63,13 @@ cpio any cpio --version
- GNU tar 1.28 tar --version
- gtags (optional) 6.6.5 gtags --version
- mkimage (optional) 2017.01 mkimage --version
-+GNU AWK (optional) 5.1.0 gawk --version
-+GNU C\ [#f2]_ 12.0 gcc --version
-+binutils\ [#f2]_ 2.36 ld -v
- ====================== =============== ========================================
-
- .. [#f1] Sphinx is needed only to build the Kernel documentation
-+.. [#f2] These are needed at build-time when CONFIG_CTF is enabled
-
- Kernel compilation
- ******************
-@@ -198,6 +202,12 @@ platforms. The tool is available via the ``u-boot-tools`` package or can be
- built from the U-Boot source code. See the instructions at
- https://docs.u-boot.org/en/latest/build/tools.html#building-tools-for-linux
-
-+GNU AWK
-+-------
-+
-+GNU AWK is needed if you want kernel builds to generate address range data for
-+builtin modules (CONFIG_BUILTIN_MODULE_RANGES).
-+
- System utilities
- ****************
-
-diff --git a/Makefile b/Makefile
-index 2e5ac6ab3d476..635896f269f1f 100644
---- a/Makefile
-+++ b/Makefile
-@@ -1024,6 +1024,7 @@ include-$(CONFIG_UBSAN) += scripts/Makefile.ubsan
- include-$(CONFIG_KCOV) += scripts/Makefile.kcov
- include-$(CONFIG_RANDSTRUCT) += scripts/Makefile.randstruct
- include-$(CONFIG_GCC_PLUGINS) += scripts/Makefile.gcc-plugins
-+include-$(CONFIG_CTF) += scripts/Makefile.ctfa-toplevel
-
- include $(addprefix $(srctree)/, $(include-y))
-
-@@ -1151,7 +1152,11 @@ PHONY += vmlinux_o
- vmlinux_o: vmlinux.a $(KBUILD_VMLINUX_LIBS)
- $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux_o
-
--vmlinux.o modules.builtin.modinfo modules.builtin: vmlinux_o
-+MODULES_BUILTIN := modules.builtin.modinfo
-+MODULES_BUILTIN += modules.builtin
-+MODULES_BUILTIN += modules.builtin.objs
-+
-+vmlinux.o $(MODULES_BUILTIN): vmlinux_o
- @:
-
- PHONY += vmlinux
-@@ -1490,9 +1495,10 @@ endif # CONFIG_MODULES
-
- # Directories & files removed with 'make clean'
- CLEAN_FILES += vmlinux.symvers modules-only.symvers \
-- modules.builtin modules.builtin.modinfo modules.nsdeps \
-+ modules.builtin modules.builtin.* modules.nsdeps \
- compile_commands.json rust/test \
-- rust-project.json .vmlinux.objs .vmlinux.export.c
-+ rust-project.json .vmlinux.objs .vmlinux.export.c \
-+ vmlinux.ctfa
-
- # Directories & files removed with 'make mrproper'
- MRPROPER_FILES += include/config include/generated \
-@@ -1586,6 +1592,8 @@ help:
- @echo ' (requires a recent binutils and recent build (System.map))'
- @echo ' dir/file.ko - Build module including final link'
- @echo ' modules_prepare - Set up for building external modules'
-+ @echo ' ctf - Generate CTF type information, installed by make ctf_install'
-+ @echo ' ctf_install - Install CTF to INSTALL_MOD_PATH (default: /)'
- @echo ' tags/TAGS - Generate tags file for editors'
- @echo ' cscope - Generate cscope index'
- @echo ' gtags - Generate GNU GLOBAL index'
-@@ -1942,7 +1950,7 @@ clean: $(clean-dirs)
- $(call cmd,rmfiles)
- @find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \
- \( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \
-- -o -name '*.ko.*' \
-+ -o -name '*.ko.*' -o -name '*.ctf' \
- -o -name '*.dtb' -o -name '*.dtbo' \
- -o -name '*.dtb.S' -o -name '*.dtbo.S' \
- -o -name '*.dt.yaml' -o -name 'dtbs-list' \
-diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
-index 01067a2bc43b7..d2193b8dfad83 100644
---- a/arch/arm/vdso/Makefile
-+++ b/arch/arm/vdso/Makefile
-@@ -14,6 +14,10 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
- ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
- ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO32
-
-+# CTF in the vDSO would introduce a new section, which would
-+# expand the vDSO to more than a page.
-+ccflags-y += $(call cc-option,-gctf0)
-+
- ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8
- ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
- -z max-page-size=4096 -shared $(ldflags-y) \
-diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
-index d63930c828397..6e84d3822cfe3 100644
---- a/arch/arm64/kernel/vdso/Makefile
-+++ b/arch/arm64/kernel/vdso/Makefile
-@@ -33,6 +33,10 @@ ldflags-y += -T
- ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
- ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-
-+# CTF in the vDSO would introduce a new section, which would
-+# expand the vDSO to more than a page.
-+ccflags-y += $(call cc-option,-gctf0)
-+
- # -Wmissing-prototypes and -Wmissing-declarations are removed from
- # the CFLAGS of vgettimeofday.c to make possible to build the
- # kernel with CONFIG_WERROR enabled.
-diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
-index d724d46b07c84..fbedb95223ae1 100644
---- a/arch/loongarch/vdso/Makefile
-+++ b/arch/loongarch/vdso/Makefile
-@@ -21,7 +21,8 @@ cflags-vdso := $(ccflags-vdso) \
- -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
- -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
- $(call cc-option, -fno-asynchronous-unwind-tables) \
-- $(call cc-option, -fno-stack-protector)
-+ $(call cc-option, -fno-stack-protector) \
-+ $(call cc-option,-gctf0)
- aflags-vdso := $(ccflags-vdso) \
- -D__ASSEMBLY__ -Wa,-gdwarf-2
-
-diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
-index b289b2c1b2946..6c8d777525f9b 100644
---- a/arch/mips/vdso/Makefile
-+++ b/arch/mips/vdso/Makefile
-@@ -30,7 +30,8 @@ cflags-vdso := $(ccflags-vdso) \
- -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
- -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \
- -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
-- $(call cc-option, -fno-asynchronous-unwind-tables)
-+ $(call cc-option, -fno-asynchronous-unwind-tables) \
-+ $(call cc-option,-gctf0)
- aflags-vdso := $(ccflags-vdso) \
- -D__ASSEMBLY__ -Wa,-gdwarf-2
-
-diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
-index 243dbfc4609d8..e4f3e47074e9d 100644
---- a/arch/sparc/vdso/Makefile
-+++ b/arch/sparc/vdso/Makefile
-@@ -44,7 +44,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
- CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 \
- $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
- -fno-omit-frame-pointer -foptimize-sibling-calls \
-- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-+ $(call cc-option,-gctf0) -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-
- SPARC_REG_CFLAGS = -ffixed-g4 -ffixed-g5 -fcall-used-g5 -fcall-used-g7
-
-diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
-index 215a1b202a918..2fa1613a06275 100644
---- a/arch/x86/entry/vdso/Makefile
-+++ b/arch/x86/entry/vdso/Makefile
-@@ -54,6 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
- CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
- $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
- -fno-omit-frame-pointer -foptimize-sibling-calls \
-+ $(call cc-option,-gctf0) \
- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-
- ifdef CONFIG_MITIGATION_RETPOLINE
-@@ -131,6 +132,7 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
- KBUILD_CFLAGS_32 += -fno-stack-protector
- KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
- KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
-+KBUILD_CFLAGS_32 += $(call cc-option,-gctf0)
- KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-
- ifdef CONFIG_MITIGATION_RETPOLINE
-diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
-index 6a77ea6434ffd..6db233b5edd75 100644
---- a/arch/x86/um/vdso/Makefile
-+++ b/arch/x86/um/vdso/Makefile
-@@ -40,7 +40,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
- #
- CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
- $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
-- -fno-omit-frame-pointer -foptimize-sibling-calls
-+ -fno-omit-frame-pointer -foptimize-sibling-calls $(call cc-option,-gctf0)
-
- $(vobjs): KBUILD_CFLAGS += $(CFL)
-
-diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
-index f00a8e18f389f..2e307c0824574 100644
---- a/include/asm-generic/vmlinux.lds.h
-+++ b/include/asm-generic/vmlinux.lds.h
-@@ -1014,6 +1014,7 @@
- *(.discard.*) \
- *(.export_symbol) \
- *(.modinfo) \
-+ *(.ctf) \
- /* ld.bfd warns about .gnu.version* even when not emitted */ \
- *(.gnu.version*) \
-
-diff --git a/include/linux/module.h b/include/linux/module.h
-index 330ffb59efe51..2d9fcca542d13 100644
---- a/include/linux/module.h
-+++ b/include/linux/module.h
-@@ -180,7 +180,13 @@ extern void cleanup_module(void);
- #ifdef MODULE
- #define MODULE_FILE
- #else
--#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
-+#ifdef CONFIG_CTF
-+#define MODULE_FILE \
-+ MODULE_INFO(file, KBUILD_MODFILE); \
-+ MODULE_INFO(objs, KBUILD_MODOBJS);
-+#else
-+#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
-+#endif
- #endif
-
- /*
-diff --git a/init/Kconfig b/init/Kconfig
-index 9684e5d2b81c6..c1b00b2e4a43d 100644
---- a/init/Kconfig
-+++ b/init/Kconfig
-@@ -111,6 +111,12 @@ config PAHOLE_VERSION
- int
- default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
-
-+config HAVE_CTF_TOOLCHAIN
-+ def_bool $(cc-option,-gctf) && $(ld-option,-lbfd -liberty -lctf -lbfd -liberty -lz -ldl -lc -o /dev/null)
-+ depends on CC_IS_GCC
-+ help
-+ GCC and binutils support CTF generation.
-+
- config CONSTRUCTORS
- bool
-
-diff --git a/lib/Kconfig b/lib/Kconfig
-index b0a76dff5c182..61d0be30b3562 100644
---- a/lib/Kconfig
-+++ b/lib/Kconfig
-@@ -633,6 +633,16 @@ config DIMLIB
- #
- config LIBFDT
- bool
-+#
-+# CTF support is select'ed if needed
-+#
-+config CTF
-+ bool "Compact Type Format generation"
-+ depends on HAVE_CTF_TOOLCHAIN
-+ help
-+ Emit a compact, compressed description of the kernel's datatypes and
-+ global variables into the vmlinux.ctfa archive (for in-tree modules)
-+ or into .ctf sections in kernel modules (for out-of-tree modules).
-
- config OID_REGISTRY
- tristate
-diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
-index 59b6765d86b8f..dab7e6983eace 100644
---- a/lib/Kconfig.debug
-+++ b/lib/Kconfig.debug
-@@ -571,6 +571,21 @@ config VMLINUX_MAP
- pieces of code get eliminated with
- CONFIG_LD_DEAD_CODE_DATA_ELIMINATION.
-
-+config BUILTIN_MODULE_RANGES
-+ bool "Generate address range information for builtin modules"
-+ depends on !LTO
-+ depends on VMLINUX_MAP
-+ help
-+ When modules are built into the kernel, there will be no module name
-+ associated with its symbols in /proc/kallsyms. Tracers may want to
-+ identify symbols by module name and symbol name regardless of whether
-+ the module is configured as loadable or not.
-+
-+ This option generates modules.builtin.ranges in the build tree with
-+ offset ranges (per ELF section) for the module(s) they belong to.
-+ It also records an anchor symbol to determine the load address of the
-+ section.
-+
- config DEBUG_FORCE_WEAK_PER_CPU
- bool "Force weak per-cpu definitions"
- depends on DEBUG_KERNEL
-+y!/Makefile.ctf
-diff --git a/scripts/Makefile b/scripts/Makefile
-index fe56eeef09dd4..8e7eb174d3154 100644
---- a/scripts/Makefile
-+++ b/scripts/Makefile
-@@ -54,6 +54,7 @@ targets += module.lds
-
- subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
- subdir-$(CONFIG_MODVERSIONS) += genksyms
-+subdir-$(CONFIG_CTF) += ctf
- subdir-$(CONFIG_SECURITY_SELINUX) += selinux
-
- # Let clean descend into subdirs
-diff --git a/scripts/Makefile.ctfa b/scripts/Makefile.ctfa
-new file mode 100644
-index 0000000000000..b65d9d391c29c
---- /dev/null
-+++ b/scripts/Makefile.ctfa
-@@ -0,0 +1,92 @@
-+# SPDX-License-Identifier: GPL-2.0-only
-+# ===========================================================================
-+# Module CTF/CTFA generation
-+# ===========================================================================
-+
-+include include/config/auto.conf
-+include $(srctree)/scripts/Kbuild.include
-+
-+# CTF is already present in every object file if CONFIG_CTF is enabled.
-+# vmlinux.lds.h strips it out of the finished kernel, but if nothing is done
-+# it will be deduplicated into module .ko's. For out-of-tree module builds,
-+# this is what we want, but for in-tree modules we can save substantial
-+# space by deduplicating it against all the core kernel types as well. So
-+# split the CTF out of in-tree module .ko's into separate .ctf files so that
-+# it doesn't take up space in the modules on disk, and let the specialized
-+# ctfarchive tool consume it and all the CTF in the vmlinux.o files when
-+# 'make ctf' is invoked, and use the same machinery that the linker uses to
-+# do CTF deduplication to emit vmlinux.ctfa containing the deduplicated CTF.
-+
-+# Nothing special needs to be done if CTF is turned off or if a standalone
-+# module is being built.
-+module-ctf-postlink = mv $(1).tmp $(1)
-+
-+ifdef CONFIG_CTF
-+
-+# This is quite tricky. The CTF machinery needs to be told about all the
-+# built-in objects as well as all the external modules -- but Makefile.modfinal
-+# only knows about the latter. So the toplevel makefile emits the names of the
-+# built-in objects into a temporary file, which is then catted and its contents
-+# used as prerequisites by this rule.
-+#
-+# We write the names of the object files to be scanned for CTF content into a
-+# file, then use that, to avoid hitting command-line length limits.
-+
-+ifeq ($(KBUILD_EXTMOD),)
-+ctf-modules := $(shell find . -name '*.ko.ctf' -print)
-+quiet_cmd_ctfa_raw = CTFARAW
-+ cmd_ctfa_raw = scripts/ctf/ctfarchive $@ .tmp_objects.builtin modules.builtin.objs $(ctf-filelist)
-+ctf-builtins := .tmp_objects.builtin
-+ctf-filelist := .tmp_ctf.filelist
-+ctf-filelist-raw := .tmp_ctf.filelist.raw
-+
-+define module-ctf-postlink =
-+ $(OBJCOPY) --only-section=.ctf $(1).tmp $(1).ctf && \
-+ $(OBJCOPY) --remove-section=.ctf $(1).tmp $(1) && rm -f $(1).tmp
-+endef
-+
-+# Split a list up like shell xargs does.
-+define xargs =
-+$(1) $(wordlist 1,1024,$(2))
-+$(if $(word 1025,$(2)),$(call xargs,$(1),$(wordlist 1025,$(words $(2)),$(2))))
-+endef
-+
-+$(ctf-filelist-raw): $(ctf-builtins) $(ctf-modules)
-+ @rm -f $(ctf-filelist-raw);
-+ $(call xargs,@printf "%s\n" >> $(ctf-filelist-raw),$^)
-+ @touch $(ctf-filelist-raw)
-+
-+$(ctf-filelist): $(ctf-filelist-raw)
-+ @rm -f $(ctf-filelist);
-+ @cat $(ctf-filelist-raw) | while read -r obj; do \
-+ case $$obj in \
-+ $(ctf-builtins)) cat $$obj >> $(ctf-filelist);; \
-+ *.a) $(AR) t $$obj > $(ctf-filelist);; \
-+ *.builtin) cat $$obj >> $(ctf-filelist);; \
-+ *) echo "$$obj" >> $(ctf-filelist);; \
-+ esac; \
-+ done
-+ @touch $(ctf-filelist)
-+
-+# The raw CTF depends on the output CTF file list, and that depends
-+# on the .ko files for the modules.
-+.tmp_vmlinux.ctfa.raw: $(ctf-filelist) FORCE
-+ $(call if_changed,ctfa_raw)
-+
-+quiet_cmd_ctfa = CTFA
-+ cmd_ctfa = { echo 'int main () { return 0; } ' | \
-+ $(CC) -x c -c -o $<.stub -; \
-+ $(OBJCOPY) '--remove-section=.*' --add-section=.ctf=$< \
-+ $<.stub $@; }
-+
-+# The CTF itself is an ELF executable with one section: the CTF. This lets
-+# objdump work on it, at minimal size cost.
-+vmlinux.ctfa: .tmp_vmlinux.ctfa.raw FORCE
-+ $(call if_changed,ctfa)
-+
-+targets += vmlinux.ctfa
-+
-+endif # KBUILD_EXTMOD
-+
-+endif # !CONFIG_CTF
-+
-diff --git a/scripts/Makefile.ctfa-toplevel b/scripts/Makefile.ctfa-toplevel
-new file mode 100644
-index 0000000000000..210bef3854e9b
---- /dev/null
-+++ b/scripts/Makefile.ctfa-toplevel
-@@ -0,0 +1,54 @@
-+# SPDX-License-Identifier: GPL-2.0-only
-+# ===========================================================================
-+# CTF rules for the top-level makefile only
-+# ===========================================================================
-+
-+KBUILD_CFLAGS += $(call cc-option,-gctf)
-+KBUILD_LDFLAGS += $(call ld-option, --ctf-variables)
-+
-+ifeq ($(KBUILD_EXTMOD),)
-+
-+# CTF generation for in-tree code (modules, built-in and not, and core kernel)
-+
-+# This contains all the object files that are built directly into the
-+# kernel (including built-in modules), for consumption by ctfarchive in
-+# Makefile.modfinal.
-+# This is made doubly annoying by the presence of '.o' files which are actually
-+# thin ar archives, and the need to support file(1) versions too old to
-+# recognize them as archives at all. (So we assume that everything that is notr
-+# an ELF object is an archive.)
-+ifeq ($(SRCARCH),x86)
-+.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),bzImage) FORCE
-+else
-+ifeq ($(SRCARCH),arm64)
-+.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),Image) FORCE
-+else
-+.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) FORCE
-+endif
-+endif
-+ @echo $(KBUILD_VMLINUX_OBJS) | \
-+ tr " " "\n" | grep "\.o$$" | xargs -r file | \
-+ grep ELF | cut -d: -f1 > .tmp_objects.builtin
-+ @for archive in $$(echo $(KBUILD_VMLINUX_OBJS) |\
-+ tr " " "\n" | xargs -r file | grep -v ELF | cut -d: -f1); do \
-+ $(AR) t "$$archive" >> .tmp_objects.builtin; \
-+ done
-+
-+ctf: vmlinux.ctfa
-+PHONY += ctf ctf_install
-+
-+# Making CTF needs the builtin files. We need to force everything to be
-+# built if not already done, since we need the .o files for the machinery
-+# above to work.
-+vmlinux.ctfa: KBUILD_BUILTIN := 1
-+vmlinux.ctfa: modules.builtin.objs .tmp_objects.builtin
-+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal vmlinux.ctfa
-+
-+ctf_install:
-+ $(Q)mkdir -p $(MODLIB)/kernel
-+ @ln -sf $(abspath $(srctree)) $(MODLIB)/source
-+ $(Q)cp -f $(objtree)/vmlinux.ctfa $(MODLIB)/kernel
-+
-+CLEAN_FILES += vmlinux.ctfa
-+
-+endif
-diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
-index 7f8ec77bf35c9..8e67961ba2ec9 100644
---- a/scripts/Makefile.lib
-+++ b/scripts/Makefile.lib
-@@ -118,6 +118,8 @@ modname-multi = $(sort $(foreach m,$(multi-obj-ym),\
- __modname = $(or $(modname-multi),$(basetarget))
-
- modname = $(subst $(space),:,$(__modname))
-+modname-objs = $($(modname)-objs) $($(modname)-y) $($(modname)-Y)
-+modname-objs-prefixed = $(sort $(strip $(addprefix $(obj)/, $(modname-objs))))
- modfile = $(addprefix $(obj)/,$(__modname))
-
- # target with $(obj)/ and its suffix stripped
-@@ -133,6 +135,10 @@ modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
- -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
- modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
-
-+ifdef CONFIG_CTF
-+modfile_flags += -DKBUILD_MODOBJS=$(call stringify,$(modfile).o:$(subst $(space),|,$(modname-objs-prefixed)))
-+endif
-+
- _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
- $(filter-out $(ccflags-remove-y), \
- $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(ccflags-y)) \
-@@ -238,7 +244,7 @@ modkern_rustflags = \
-
- modkern_aflags = $(if $(part-of-module), \
- $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE), \
-- $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL))
-+ $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) $(modfile_flags))
-
- c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
- -include $(srctree)/include/linux/compiler_types.h \
-@@ -248,7 +254,7 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
- rust_flags = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg
-
- a_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
-- $(_a_flags) $(modkern_aflags)
-+ $(_a_flags) $(modkern_aflags) $(modname_flags)
-
- cpp_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
- $(_cpp_flags)
-diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
-index 3bec9043e4f38..06807e403d162 100644
---- a/scripts/Makefile.modfinal
-+++ b/scripts/Makefile.modfinal
-@@ -30,11 +30,16 @@ quiet_cmd_cc_o_c = CC [M] $@
- %.mod.o: %.mod.c FORCE
- $(call if_changed_dep,cc_o_c)
-
-+# for module-ctf-postlink
-+include $(srctree)/scripts/Makefile.ctfa
-+
- quiet_cmd_ld_ko_o = LD [M] $@
- cmd_ld_ko_o += \
- $(LD) -r $(KBUILD_LDFLAGS) \
- $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
-- -T scripts/module.lds -o $@ $(filter %.o, $^)
-+ -T scripts/module.lds $(LDFLAGS_$(modname)) -o $@.tmp \
-+ $(filter %.o, $^) && \
-+ $(call module-ctf-postlink,$@) \
-
- quiet_cmd_btf_ko = BTF [M] $@
- cmd_btf_ko = \
-diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
-index 0afd75472679f..e668469ce098c 100644
---- a/scripts/Makefile.modinst
-+++ b/scripts/Makefile.modinst
-@@ -30,10 +30,12 @@ $(MODLIB)/modules.order: modules.order FORCE
- quiet_cmd_install_modorder = INSTALL $@
- cmd_install_modorder = sed 's:^\(.*\)\.o$$:kernel/\1.ko:' $< > $@
-
--# Install modules.builtin(.modinfo) even when CONFIG_MODULES is disabled.
--install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo)
-+# Install modules.builtin(.modinfo,.ranges,.objs) even when CONFIG_MODULES is disabled.
-+install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.objs)
-
--$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo): $(MODLIB)/%: % FORCE
-+install-$(CONFIG_BUILTIN_MODULE_RANGES) += $(MODLIB)/modules.builtin.ranges
-+
-+$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.ranges modules.builtin.objs): $(MODLIB)/%: % FORCE
- $(call cmd,install)
-
- endif
-diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
-index 49946cb968440..7e8b703799c85 100644
---- a/scripts/Makefile.vmlinux
-+++ b/scripts/Makefile.vmlinux
-@@ -33,6 +33,24 @@ targets += vmlinux
- vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE
- +$(call if_changed_dep,link_vmlinux)
-
-+# module.builtin.ranges
-+# ---------------------------------------------------------------------------
-+ifdef CONFIG_BUILTIN_MODULE_RANGES
-+__default: modules.builtin.ranges
-+
-+quiet_cmd_modules_builtin_ranges = GEN $@
-+ cmd_modules_builtin_ranges = $(real-prereqs) > $@
-+
-+targets += modules.builtin.ranges
-+modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \
-+ modules.builtin vmlinux.map vmlinux.o.map FORCE
-+ $(call if_changed,modules_builtin_ranges)
-+
-+vmlinux.map: vmlinux
-+ @:
-+
-+endif
-+
- # Add FORCE to the prequisites of a target to force it to be always rebuilt.
- # ---------------------------------------------------------------------------
-
-diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
-index 6de297916ce68..86d6f8887313f 100644
---- a/scripts/Makefile.vmlinux_o
-+++ b/scripts/Makefile.vmlinux_o
-@@ -1,7 +1,7 @@
- # SPDX-License-Identifier: GPL-2.0-only
-
- PHONY := __default
--__default: vmlinux.o modules.builtin.modinfo modules.builtin
-+__default: vmlinux.o modules.builtin.modinfo modules.builtin modules.builtin.objs
-
- include include/config/auto.conf
- include $(srctree)/scripts/Kbuild.include
-@@ -27,6 +27,18 @@ ifdef CONFIG_LTO_CLANG
- initcalls-lds := .tmp_initcalls.lds
- endif
-
-+# Generate a linker script to delete CTF sections
-+# -----------------------------------------------
-+
-+quiet_cmd_gen_remove_ctf.lds = GEN $@
-+ cmd_gen_remove_ctf.lds = \
-+ $(LD) $(KBUILD_LDFLAGS) -r --verbose | awk -f $(real-prereqs) > $@
-+
-+.tmp_remove-ctf.lds: $(srctree)/scripts/remove-ctf-lds.awk FORCE
-+ $(call if_changed,gen_remove_ctf.lds)
-+
-+targets := .tmp_remove-ctf.lds
-+
- # objtool for vmlinux.o
- # ---------------------------------------------------------------------------
- #
-@@ -42,13 +54,18 @@ vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \
-
- objtool-args = $(vmlinux-objtool-args-y) --link
-
--# Link of vmlinux.o used for section mismatch analysis
-+# Link of vmlinux.o used for section mismatch analysis: we also strip the CTF
-+# section out at this stage, since ctfarchive gets it from the underlying object
-+# files and linking it further is a waste of time.
- # ---------------------------------------------------------------------------
-
-+vmlinux-o-ld-args-$(CONFIG_BUILTIN_MODULE_RANGES) += -Map=$@.map
-+
- quiet_cmd_ld_vmlinux.o = LD $@
- cmd_ld_vmlinux.o = \
- $(LD) ${KBUILD_LDFLAGS} -r -o $@ \
-- $(addprefix -T , $(initcalls-lds)) \
-+ $(vmlinux-o-ld-args-y) \
-+ $(addprefix -T , $(initcalls-lds)) -T .tmp_remove-ctf.lds \
- --whole-archive vmlinux.a --no-whole-archive \
- --start-group $(KBUILD_VMLINUX_LIBS) --end-group \
- $(cmd_objtool)
-@@ -58,7 +75,7 @@ define rule_ld_vmlinux.o
- $(call cmd,gen_objtooldep)
- endef
-
--vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
-+vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) .tmp_remove-ctf.lds FORCE
- $(call if_changed_rule,ld_vmlinux.o)
-
- targets += vmlinux.o
-@@ -87,6 +104,19 @@ targets += modules.builtin
- modules.builtin: modules.builtin.modinfo FORCE
- $(call if_changed,modules_builtin)
-
-+# module.builtin.objs
-+# ---------------------------------------------------------------------------
-+quiet_cmd_modules_builtin_objs = GEN $@
-+ cmd_modules_builtin_objs = \
-+ tr '\0' '\n' < $< | \
-+ sed -n 's/^[[:alnum:]:_]*\.objs=//p' | \
-+ tr ' ' '\n' | uniq | sed -e 's|:|: |' -e 's:|: :g' | \
-+ tr -s ' ' > $@
-+
-+targets += modules.builtin.objs
-+modules.builtin.objs: modules.builtin.modinfo FORCE
-+ $(call if_changed,modules_builtin_objs)
-+
- # Add FORCE to the prequisites of a target to force it to be always rebuilt.
- # ---------------------------------------------------------------------------
-
-diff --git a/scripts/ctf/.gitignore b/scripts/ctf/.gitignore
-new file mode 100644
-index 0000000000000..6a0eb1c3ceeab
---- /dev/null
-+++ b/scripts/ctf/.gitignore
-@@ -0,0 +1 @@
-+ctfarchive
-diff --git a/scripts/ctf/Makefile b/scripts/ctf/Makefile
-new file mode 100644
-index 0000000000000..3b83f93bb9f9a
---- /dev/null
-+++ b/scripts/ctf/Makefile
-@@ -0,0 +1,5 @@
-+ifdef CONFIG_CTF
-+hostprogs-always-y := ctfarchive
-+ctfarchive-objs := ctfarchive.o modules_builtin.o
-+HOSTLDLIBS_ctfarchive := -lctf
-+endif
-diff --git a/scripts/ctf/ctfarchive.c b/scripts/ctf/ctfarchive.c
-new file mode 100644
-index 0000000000000..92cc4912ed0ee
---- /dev/null
-+++ b/scripts/ctf/ctfarchive.c
-@@ -0,0 +1,413 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * ctfmerge.c: Read in CTF extracted from generated object files from a
-+ * specified directory and generate a CTF archive whose members are the
-+ * deduplicated CTF derived from those object files, split up by kernel
-+ * module.
-+ *
-+ * Copyright (c) 2019, 2023, Oracle and/or its affiliates.
-+ *
-+ * This program is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ */
-+
-+#define _GNU_SOURCE 1
-+#include <errno.h>
-+#include <stdio.h>
-+#include <stdlib.h>
-+#include <string.h>
-+#include <ctf-api.h>
-+#include "modules_builtin.h"
-+
-+static ctf_file_t *output;
-+
-+static int private_ctf_link_add_ctf(ctf_file_t *fp,
-+ const char *name)
-+{
-+#if !defined (CTF_LINK_FINAL)
-+ return ctf_link_add_ctf(fp, NULL, name);
-+#else
-+ /* Non-upstreamed, erroneously-broken API. */
-+ return ctf_link_add_ctf(fp, NULL, name, NULL, 0);
-+#endif
-+}
-+
-+/*
-+ * Add a file to the link.
-+ */
-+static void add_to_link(const char *fn)
-+{
-+ if (private_ctf_link_add_ctf(output, fn) < 0)
-+ {
-+ fprintf(stderr, "Cannot add CTF file %s: %s\n", fn,
-+ ctf_errmsg(ctf_errno(output)));
-+ exit(1);
-+ }
-+}
-+
-+struct from_to
-+{
-+ char *from;
-+ char *to;
-+};
-+
-+/*
-+ * The world's stupidest hash table of FROM -> TO.
-+ */
-+static struct from_to **from_tos[256];
-+static size_t alloc_from_tos[256];
-+static size_t num_from_tos[256];
-+
-+static unsigned char from_to_hash(const char *from)
-+{
-+ unsigned char hval = 0;
-+
-+ const char *p;
-+ for (p = from; *p; p++)
-+ hval += *p;
-+
-+ return hval;
-+}
-+
-+/*
-+ * Note that we will need to add a CU mapping later on.
-+ *
-+ * Present purely to work around a binutils bug that stops
-+ * ctf_link_add_cu_mapping() working right when called repeatedly
-+ * with the same FROM.
-+ */
-+static int add_cu_mapping(const char *from, const char *to)
-+{
-+ ssize_t i, j;
-+
-+ i = from_to_hash(from);
-+
-+ for (j = 0; j < num_from_tos[i]; j++)
-+ if (strcmp(from, from_tos[i][j]->from) == 0) {
-+ char *tmp;
-+
-+ free(from_tos[i][j]->to);
-+ tmp = strdup(to);
-+ if (!tmp)
-+ goto oom;
-+ from_tos[i][j]->to = tmp;
-+ return 0;
-+ }
-+
-+ if (num_from_tos[i] >= alloc_from_tos[i]) {
-+ struct from_to **tmp;
-+ if (alloc_from_tos[i] < 16)
-+ alloc_from_tos[i] = 16;
-+ else
-+ alloc_from_tos[i] *= 2;
-+
-+ tmp = realloc(from_tos[i], alloc_from_tos[i] * sizeof(struct from_to *));
-+ if (!tmp)
-+ goto oom;
-+
-+ from_tos[i] = tmp;
-+ }
-+
-+ j = num_from_tos[i];
-+ from_tos[i][j] = malloc(sizeof(struct from_to));
-+ if (from_tos[i][j] == NULL)
-+ goto oom;
-+ from_tos[i][j]->from = strdup(from);
-+ from_tos[i][j]->to = strdup(to);
-+ if (!from_tos[i][j]->from || !from_tos[i][j]->to)
-+ goto oom;
-+ num_from_tos[i]++;
-+
-+ return 0;
-+ oom:
-+ fprintf(stderr,
-+ "out of memory in add_cu_mapping\n");
-+ exit(1);
-+}
-+
-+/*
-+ * Finally tell binutils to add all the CU mappings, with duplicate FROMs
-+ * replaced with the most recent one.
-+ */
-+static void commit_cu_mappings(void)
-+{
-+ ssize_t i, j;
-+
-+ for (i = 0; i < 256; i++)
-+ for (j = 0; j < num_from_tos[i]; j++)
-+ ctf_link_add_cu_mapping(output, from_tos[i][j]->from,
-+ from_tos[i][j]->to);
-+}
-+
-+/*
-+ * Add a CU mapping to the link.
-+ *
-+ * CU mappings for built-in modules are added by suck_in_modules, below: here,
-+ * we only want to add mappings for names ending in '.ko.ctf', i.e. external
-+ * modules, which appear only in the filelist (since they are not built-in).
-+ * The pathnames are stripped off because modules don't have any, and hyphens
-+ * are translated into underscores.
-+ */
-+static void add_cu_mappings(const char *fn)
-+{
-+ const char *last_slash;
-+ const char *modname = fn;
-+ char *dynmodname = NULL;
-+ char *dash;
-+ size_t n;
-+
-+ last_slash = strrchr(modname, '/');
-+ if (last_slash)
-+ last_slash++;
-+ else
-+ last_slash = modname;
-+ modname = last_slash;
-+ if (strchr(modname, '-') != NULL)
-+ {
-+ dynmodname = strdup(last_slash);
-+ dash = dynmodname;
-+ while (dash != NULL) {
-+ dash = strchr(dash, '-');
-+ if (dash != NULL)
-+ *dash = '_';
-+ }
-+ modname = dynmodname;
-+ }
-+
-+ n = strlen(modname);
-+ if (strcmp(modname + n - strlen(".ko.ctf"), ".ko.ctf") == 0) {
-+ char *mod;
-+
-+ n -= strlen(".ko.ctf");
-+ mod = strndup(modname, n);
-+ add_cu_mapping(fn, mod);
-+ free(mod);
-+ }
-+ free(dynmodname);
-+}
-+
-+/*
-+ * Add the passed names as mappings to "vmlinux".
-+ */
-+static void add_builtins(const char *fn)
-+{
-+ if (add_cu_mapping(fn, "vmlinux") < 0)
-+ {
-+ fprintf(stderr, "Cannot add CTF CU mapping from %s to \"vmlinux\"\n",
-+ ctf_errmsg(ctf_errno(output)));
-+ exit(1);
-+ }
-+}
-+
-+/*
-+ * Do something with a file, line by line.
-+ */
-+static void suck_in_lines(const char *filename, void (*func)(const char *line))
-+{
-+ FILE *f;
-+ char *line = NULL;
-+ size_t line_size = 0;
-+
-+ f = fopen(filename, "r");
-+ if (f == NULL) {
-+ fprintf(stderr, "Cannot open %s: %s\n", filename,
-+ strerror(errno));
-+ exit(1);
-+ }
-+
-+ while (getline(&line, &line_size, f) >= 0) {
-+ size_t len = strlen(line);
-+
-+ if (len == 0)
-+ continue;
-+
-+ if (line[len-1] == '\n')
-+ line[len-1] = '\0';
-+
-+ func(line);
-+ }
-+ free(line);
-+
-+ if (ferror(f)) {
-+ fprintf(stderr, "Error reading from %s: %s\n", filename,
-+ strerror(errno));
-+ exit(1);
-+ }
-+
-+ fclose(f);
-+}
-+
-+/*
-+ * Pull in modules.builtin.objs and turn it into CU mappings.
-+ */
-+static void suck_in_modules(const char *modules_builtin_name)
-+{
-+ struct modules_builtin_iter *i;
-+ char *module_name = NULL;
-+ char **paths;
-+
-+ i = modules_builtin_iter_new(modules_builtin_name);
-+ if (i == NULL) {
-+ fprintf(stderr, "Cannot iterate over builtin module file.\n");
-+ exit(1);
-+ }
-+
-+ while ((paths = modules_builtin_iter_next(i, &module_name)) != NULL) {
-+ size_t j;
-+
-+ for (j = 0; paths[j] != NULL; j++) {
-+ char *alloc = NULL;
-+ char *path = paths[j];
-+ /*
-+ * If the name doesn't start in ./, add it, to match the names
-+ * passed to add_builtins.
-+ */
-+ if (strncmp(paths[j], "./", 2) != 0) {
-+ char *p;
-+ if ((alloc = malloc(strlen(paths[j]) + 3)) == NULL) {
-+ fprintf(stderr, "Cannot allocate memory for "
-+ "builtin module object name %s.\n",
-+ paths[j]);
-+ exit(1);
-+ }
-+ p = alloc;
-+ p = stpcpy(p, "./");
-+ p = stpcpy(p, paths[j]);
-+ path = alloc;
-+ }
-+ if (add_cu_mapping(path, module_name) < 0) {
-+ fprintf(stderr, "Cannot add path -> module mapping for "
-+ "%s -> %s: %s\n", path, module_name,
-+ ctf_errmsg(ctf_errno(output)));
-+ exit(1);
-+ }
-+ free (alloc);
-+ }
-+ free(paths);
-+ }
-+ free(module_name);
-+ modules_builtin_iter_free(i);
-+}
-+
-+/*
-+ * Strip the leading .ctf. off all the module names: transform the default name
-+ * from _CTF_SECTION into shared_ctf, and chop any trailing .ctf off (since that
-+ * derives from the intermediate file used to keep the CTF out of the final
-+ * module).
-+ */
-+static char *transform_module_names(ctf_file_t *fp __attribute__((__unused__)),
-+ const char *name,
-+ void *arg __attribute__((__unused__)))
-+{
-+ if (strcmp(name, ".ctf") == 0)
-+ return strdup("shared_ctf");
-+
-+ if (strncmp(name, ".ctf", 4) == 0) {
-+ size_t n = strlen (name);
-+ if (strcmp(name + n - 4, ".ctf") == 0)
-+ n -= 4;
-+ return strndup(name + 4, n - 4);
-+ }
-+ return NULL;
-+}
-+
-+int main(int argc, char *argv[])
-+{
-+ int err;
-+ const char *output_file;
-+ unsigned char *file_data = NULL;
-+ size_t file_size;
-+ FILE *fp;
-+
-+ if (argc != 5) {
-+ fprintf(stderr, "Syntax: ctfarchive output-file objects.builtin modules.builtin\n");
-+ fprintf(stderr, " filelist\n");
-+ exit(1);
-+ }
-+
-+ output_file = argv[1];
-+
-+ /*
-+ * First pull in the input files and add them to the link.
-+ */
-+
-+ output = ctf_create(&err);
-+ if (!output) {
-+ fprintf(stderr, "Cannot create output CTF archive: %s\n",
-+ ctf_errmsg(err));
-+ return 1;
-+ }
-+
-+ suck_in_lines(argv[4], add_to_link);
-+
-+ /*
-+ * Make sure that, even if all their types are shared, all modules have
-+ * a ctf member that can be used as a child of the shared CTF.
-+ */
-+ suck_in_lines(argv[4], add_cu_mappings);
-+
-+ /*
-+ * Then pull in the builtin objects list and add them as
-+ * mappings to "vmlinux".
-+ */
-+
-+ suck_in_lines(argv[2], add_builtins);
-+
-+ /*
-+ * Finally, pull in the object -> module mapping and add it
-+ * as appropriate mappings.
-+ */
-+ suck_in_modules(argv[3]);
-+
-+ /*
-+ * Commit the added CU mappings.
-+ */
-+ commit_cu_mappings();
-+
-+ /*
-+ * Arrange to fix up the module names.
-+ */
-+ ctf_link_set_memb_name_changer(output, transform_module_names, NULL);
-+
-+ /*
-+ * Do the link.
-+ */
-+ if (ctf_link(output, CTF_LINK_SHARE_DUPLICATED |
-+ CTF_LINK_EMPTY_CU_MAPPINGS) < 0)
-+ goto ctf_err;
-+
-+ /*
-+ * Write the output.
-+ */
-+
-+ file_data = ctf_link_write(output, &file_size, 4096);
-+ if (!file_data)
-+ goto ctf_err;
-+
-+ fp = fopen(output_file, "w");
-+ if (!fp)
-+ goto err;
-+
-+ while ((err = fwrite(file_data, file_size, 1, fp)) == 0);
-+ if (ferror(fp)) {
-+ errno = ferror(fp);
-+ goto err;
-+ }
-+ if (fclose(fp) < 0)
-+ goto err;
-+ free(file_data);
-+ ctf_file_close(output);
-+
-+ return 0;
-+err:
-+ free(file_data);
-+ fprintf(stderr, "Cannot create output CTF archive: %s\n",
-+ strerror(errno));
-+ return 1;
-+ctf_err:
-+ fprintf(stderr, "Cannot create output CTF archive: %s\n",
-+ ctf_errmsg(ctf_errno(output)));
-+ return 1;
-+}
-diff --git a/scripts/ctf/modules_builtin.c b/scripts/ctf/modules_builtin.c
-new file mode 100644
-index 0000000000000..10af2bbc80e0c
---- /dev/null
-+++ b/scripts/ctf/modules_builtin.c
-@@ -0,0 +1,2 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+#include "../modules_builtin.c"
-diff --git a/scripts/ctf/modules_builtin.h b/scripts/ctf/modules_builtin.h
-new file mode 100644
-index 0000000000000..5e0299e5600c2
---- /dev/null
-+++ b/scripts/ctf/modules_builtin.h
-@@ -0,0 +1,2 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+#include "../modules_builtin.h"
-diff --git a/scripts/generate_builtin_ranges.awk b/scripts/generate_builtin_ranges.awk
-new file mode 100755
-index 0000000000000..51ae0458ffbdd
---- /dev/null
-+++ b/scripts/generate_builtin_ranges.awk
-@@ -0,0 +1,516 @@
-+#!/usr/bin/gawk -f
-+# SPDX-License-Identifier: GPL-2.0
-+# generate_builtin_ranges.awk: Generate address range data for builtin modules
-+# Written by Kris Van Hees <kris.van.hees@oracle.com>
-+#
-+# Usage: generate_builtin_ranges.awk modules.builtin vmlinux.map \
-+# vmlinux.o.map [ <build-dir> ] > modules.builtin.ranges
-+#
-+
-+# Return the module name(s) (if any) associated with the given object.
-+#
-+# If we have seen this object before, return information from the cache.
-+# Otherwise, retrieve it from the corresponding .cmd file.
-+#
-+function get_module_info(fn, mod, obj, s) {
-+ if (fn in omod)
-+ return omod[fn];
-+
-+ if (match(fn, /\/[^/]+$/) == 0)
-+ return "";
-+
-+ obj = fn;
-+ mod = "";
-+ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
-+ if (getline s <fn == 1) {
-+ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
-+ mod = substr(s, RSTART + 16, RLENGTH - 16);
-+ gsub(/['"]/, "", mod);
-+ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
-+ mod = substr(s, RSTART + 13, RLENGTH - 13);
-+ }
-+ close(fn);
-+
-+ # A single module (common case) also reflects objects that are not part
-+ # of a module. Some of those objects have names that are also a module
-+ # name (e.g. core). We check the associated module file name, and if
-+ # they do not match, the object is not part of a module.
-+ if (mod !~ / /) {
-+ if (!(mod in mods))
-+ mod = "";
-+ }
-+
-+ gsub(/([^/ ]*\/)+/, "", mod);
-+ gsub(/-/, "_", mod);
-+
-+ # At this point, mod is a single (valid) module name, or a list of
-+ # module names (that do not need validation).
-+ omod[obj] = mod;
-+
-+ return mod;
-+}
-+
-+# Update the ranges entry for the given module 'mod' in section 'osect'.
-+#
-+# We use a modified absolute start address (soff + base) as index because we
-+# may need to insert an anchor record later that must be at the start of the
-+# section data, and the first module may very well start at the same address.
-+# So, we use (addr << 1) + 1 to allow a possible anchor record to be placed at
-+# (addr << 1). This is safe because the index is only used to sort the entries
-+# before writing them out.
-+#
-+function update_entry(osect, mod, soff, eoff, sect, idx) {
-+ sect = sect_in[osect];
-+ idx = (soff + sect_base[osect]) * 2 + 1;
-+ entries[idx] = sprintf("%s %08x-%08x %s", sect, soff, eoff, mod);
-+ count[sect]++;
-+}
-+
-+# Determine the kernel build directory to use (default is .).
-+#
-+BEGIN {
-+ if (ARGC > 4) {
-+ kdir = ARGV[ARGC - 1];
-+ ARGV[ARGC - 1] = "";
-+ } else
-+ kdir = ".";
-+}
-+
-+# (1) Build a lookup map of built-in module names.
-+#
-+# The first file argument is used as input (modules.builtin).
-+#
-+# Lines will be like:
-+# kernel/crypto/lzo-rle.ko
-+# and we record the object name "crypto/lzo-rle".
-+#
-+ARGIND == 1 {
-+ sub(/kernel\//, ""); # strip off "kernel/" prefix
-+ sub(/\.ko$/, ""); # strip off .ko suffix
-+
-+ mods[$1] = 1;
-+ next;
-+}
-+
-+# (2) Collect address information for each section.
-+#
-+# The second file argument is used as input (vmlinux.map).
-+#
-+# We collect the base address of the section in order to convert all addresses
-+# in the section into offset values.
-+#
-+# We collect the address of the anchor (or first symbol in the section if there
-+# is no explicit anchor) to allow users of the range data to calculate address
-+# ranges based on the actual load address of the section in the running kernel.
-+#
-+# We collect the start address of any sub-section (section included in the top
-+# level section being processed). This is needed when the final linking was
-+# done using vmlinux.a because then the list of objects contained in each
-+# section is to be obtained from vmlinux.o.map. The offset of the sub-section
-+# is recorded here, to be used as an addend when processing vmlinux.o.map
-+# later.
-+#
-+
-+# Both GNU ld and LLVM lld linker map format are supported by converting LLVM
-+# lld linker map records into equivalent GNU ld linker map records.
-+#
-+# The first record of the vmlinux.map file provides enough information to know
-+# which format we are dealing with.
-+#
-+ARGIND == 2 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
-+ map_is_lld = 1;
-+ if (dbg)
-+ printf "NOTE: %s uses LLVM lld linker map format\n", FILENAME >"/dev/stderr";
-+ next;
-+}
-+
-+# (LLD) Convert a section record fronm lld format to ld format.
-+#
-+# lld: ffffffff82c00000 2c00000 2493c0 8192 .data
-+# ->
-+# ld: .data 0xffffffff82c00000 0x2493c0 load address 0x0000000002c00000
-+#
-+ARGIND == 2 && map_is_lld && NF == 5 && /[0-9] [^ ]+$/ {
-+ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
-+}
-+
-+# (LLD) Convert an anchor record from lld format to ld format.
-+#
-+# lld: ffffffff81000000 1000000 0 1 _text = .
-+# ->
-+# ld: 0xffffffff81000000 _text = .
-+#
-+ARGIND == 2 && map_is_lld && !anchor && NF == 7 && raw_addr == "0x"$1 && $6 == "=" && $7 == "." {
-+ $0 = " 0x"$1 " " $5 " = .";
-+}
-+
-+# (LLD) Convert an object record from lld format to ld format.
-+#
-+# lld: 11480 11480 1f07 16 vmlinux.a(arch/x86/events/amd/uncore.o):(.text)
-+# ->
-+# ld: .text 0x0000000000011480 0x1f07 arch/x86/events/amd/uncore.o
-+#
-+ARGIND == 2 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
-+ gsub(/\)/, "");
-+ sub(/ vmlinux\.a\(/, " ");
-+ sub(/:\(/, " ");
-+ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
-+}
-+
-+# (LLD) Convert a symbol record from lld format to ld format.
-+#
-+# We only care about these while processing a section for which no anchor has
-+# been determined yet.
-+#
-+# lld: ffffffff82a859a4 2a859a4 0 1 btf_ksym_iter_id
-+# ->
-+# ld: 0xffffffff82a859a4 btf_ksym_iter_id
-+#
-+ARGIND == 2 && map_is_lld && sect && !anchor && NF == 5 && $5 ~ /^[_A-Za-z][_A-Za-z0-9]*$/ {
-+ $0 = " 0x"$1 " " $5;
-+}
-+
-+# (LLD) We do not need any other ldd linker map records.
-+#
-+ARGIND == 2 && map_is_lld && /^[0-9a-f]{16} / {
-+ next;
-+}
-+
-+# (LD) Section records with just the section name at the start of the line
-+# need to have the next line pulled in to determine whether it is a
-+# loadable section. If it is, the next line will contains a hex value
-+# as first and second items.
-+#
-+ARGIND == 2 && !map_is_lld && NF == 1 && /^[^ ]/ {
-+ s = $0;
-+ getline;
-+ if ($1 !~ /^0x/ || $2 !~ /^0x/)
-+ next;
-+
-+ $0 = s " " $0;
-+}
-+
-+# (LD) Object records with just the section name denote records with a long
-+# section name for which the remainder of the record can be found on the
-+# next line.
-+#
-+# (This is also needed for vmlinux.o.map, when used.)
-+#
-+ARGIND >= 2 && !map_is_lld && NF == 1 && /^ [^ \*]/ {
-+ s = $0;
-+ getline;
-+ $0 = s " " $0;
-+}
-+
-+# Beginning a new section - done with the previous one (if any).
-+#
-+ARGIND == 2 && /^[^ ]/ {
-+ sect = 0;
-+}
-+
-+# Process a loadable section (we only care about .-sections).
-+#
-+# Record the section name and its base address.
-+# We also record the raw (non-stripped) address of the section because it can
-+# be used to identify an anchor record.
-+#
-+# Note:
-+# Since some AWK implementations cannot handle large integers, we strip off the
-+# first 4 hex digits from the address. This is safe because the kernel space
-+# is not large enough for addresses to extend into those digits. The portion
-+# to strip off is stored in addr_prefix as a regexp, so further clauses can
-+# perform a simple substitution to do the address stripping.
-+#
-+ARGIND == 2 && /^\./ {
-+ # Explicitly ignore a few sections that are not relevant here.
-+ if ($1 ~ /^\.orc_/ || $1 ~ /_sites$/ || $1 ~ /\.percpu/)
-+ next;
-+
-+ # Sections with a 0-address can be ignored as well.
-+ if ($2 ~ /^0x0+$/)
-+ next;
-+
-+ raw_addr = $2;
-+ addr_prefix = "^" substr($2, 1, 6);
-+ base = $2;
-+ sub(addr_prefix, "0x", base);
-+ base = strtonum(base);
-+ sect = $1;
-+ anchor = 0;
-+ sect_base[sect] = base;
-+ sect_size[sect] = strtonum($3);
-+
-+ if (dbg)
-+ printf "[%s] BASE %016x\n", sect, base >"/dev/stderr";
-+
-+ next;
-+}
-+
-+# If we are not in a section we care about, we ignore the record.
-+#
-+ARGIND == 2 && !sect {
-+ next;
-+}
-+
-+# Record the first anchor symbol for the current section.
-+#
-+# An anchor record for the section bears the same raw address as the section
-+# record.
-+#
-+ARGIND == 2 && !anchor && NF == 4 && raw_addr == $1 && $3 == "=" && $4 == "." {
-+ anchor = sprintf("%s %08x-%08x = %s", sect, 0, 0, $2);
-+ sect_anchor[sect] = anchor;
-+
-+ if (dbg)
-+ printf "[%s] ANCHOR %016x = %s (.)\n", sect, 0, $2 >"/dev/stderr";
-+
-+ next;
-+}
-+
-+# If no anchor record was found for the current section, use the first symbol
-+# in the section as anchor.
-+#
-+ARGIND == 2 && !anchor && NF == 2 && $1 ~ /^0x/ && $2 !~ /^0x/ {
-+ addr = $1;
-+ sub(addr_prefix, "0x", addr);
-+ addr = strtonum(addr) - base;
-+ anchor = sprintf("%s %08x-%08x = %s", sect, addr, addr, $2);
-+ sect_anchor[sect] = anchor;
-+
-+ if (dbg)
-+ printf "[%s] ANCHOR %016x = %s\n", sect, addr, $2 >"/dev/stderr";
-+
-+ next;
-+}
-+
-+# The first occurrence of a section name in an object record establishes the
-+# addend (often 0) for that section. This information is needed to handle
-+# sections that get combined in the final linking of vmlinux (e.g. .head.text
-+# getting included at the start of .text).
-+#
-+# If the section does not have a base yet, use the base of the encapsulating
-+# section.
-+#
-+ARGIND == 2 && sect && NF == 4 && /^ [^ \*]/ && !($1 in sect_addend) {
-+ if (!($1 in sect_base)) {
-+ sect_base[$1] = base;
-+
-+ if (dbg)
-+ printf "[%s] BASE %016x\n", $1, base >"/dev/stderr";
-+ }
-+
-+ addr = $2;
-+ sub(addr_prefix, "0x", addr);
-+ addr = strtonum(addr);
-+ sect_addend[$1] = addr - sect_base[$1];
-+ sect_in[$1] = sect;
-+
-+ if (dbg)
-+ printf "[%s] ADDEND %016x - %016x = %016x\n", $1, addr, base, sect_addend[$1] >"/dev/stderr";
-+
-+ # If the object is vmlinux.o then we will need vmlinux.o.map to get the
-+ # actual offsets of objects.
-+ if ($4 == "vmlinux.o")
-+ need_o_map = 1;
-+}
-+
-+# (3) Collect offset ranges (relative to the section base address) for built-in
-+# modules.
-+#
-+# If the final link was done using the actual objects, vmlinux.map contains all
-+# the information we need (see section (3a)).
-+# If linking was done using vmlinux.a as intermediary, we will need to process
-+# vmlinux.o.map (see section (3b)).
-+
-+# (3a) Determine offset range info using vmlinux.map.
-+#
-+# Since we are already processing vmlinux.map, the top level section that is
-+# being processed is already known. If we do not have a base address for it,
-+# we do not need to process records for it.
-+#
-+# Given the object name, we determine the module(s) (if any) that the current
-+# object is associated with.
-+#
-+# If we were already processing objects for a (list of) module(s):
-+# - If the current object belongs to the same module(s), update the range data
-+# to include the current object.
-+# - Otherwise, ensure that the end offset of the range is valid.
-+#
-+# If the current object does not belong to a built-in module, ignore it.
-+#
-+# If it does, we add a new built-in module offset range record.
-+#
-+ARGIND == 2 && !need_o_map && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
-+ if (!(sect in sect_base))
-+ next;
-+
-+ # Turn the address into an offset from the section base.
-+ soff = $2;
-+ sub(addr_prefix, "0x", soff);
-+ soff = strtonum(soff) - sect_base[sect];
-+ eoff = soff + strtonum($3);
-+
-+ # Determine which (if any) built-in modules the object belongs to.
-+ mod = get_module_info($4);
-+
-+ # If we are processing a built-in module:
-+ # - If the current object is within the same module, we update its
-+ # entry by extending the range and move on
-+ # - Otherwise:
-+ # + If we are still processing within the same main section, we
-+ # validate the end offset against the start offset of the
-+ # current object (e.g. .rodata.str1.[18] objects are often
-+ # listed with an incorrect size in the linker map)
-+ # + Otherwise, we validate the end offset against the section
-+ # size
-+ if (mod_name) {
-+ if (mod == mod_name) {
-+ mod_eoff = eoff;
-+ update_entry(mod_sect, mod_name, mod_soff, eoff);
-+
-+ next;
-+ } else if (sect == sect_in[mod_sect]) {
-+ if (mod_eoff > soff)
-+ update_entry(mod_sect, mod_name, mod_soff, soff);
-+ } else {
-+ v = sect_size[sect_in[mod_sect]];
-+ if (mod_eoff > v)
-+ update_entry(mod_sect, mod_name, mod_soff, v);
-+ }
-+ }
-+
-+ mod_name = mod;
-+
-+ # If we encountered an object that is not part of a built-in module, we
-+ # do not need to record any data.
-+ if (!mod)
-+ next;
-+
-+ # At this point, we encountered the start of a new built-in module.
-+ mod_name = mod;
-+ mod_soff = soff;
-+ mod_eoff = eoff;
-+ mod_sect = $1;
-+ update_entry($1, mod, soff, mod_eoff);
-+
-+ next;
-+}
-+
-+# If we do not need to parse the vmlinux.o.map file, we are done.
-+#
-+ARGIND == 3 && !need_o_map {
-+ if (dbg)
-+ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
-+ exit;
-+}
-+
-+# (3) Collect offset ranges (relative to the section base address) for built-in
-+# modules.
-+#
-+
-+# (LLD) Convert an object record from lld format to ld format.
-+#
-+ARGIND == 3 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
-+ gsub(/\)/, "");
-+ sub(/:\(/, " ");
-+
-+ sect = $6;
-+ if (!(sect in sect_addend))
-+ next;
-+
-+ sub(/ vmlinux\.a\(/, " ");
-+ $0 = " "sect " 0x"$1 " 0x"$3 " " $5;
-+}
-+
-+# (3b) Determine offset range info using vmlinux.o.map.
-+#
-+# If we do not know an addend for the object's section, we are interested in
-+# anything within that section.
-+#
-+# Determine the top-level section that the object's section was included in
-+# during the final link. This is the section name offset range data will be
-+# associated with for this object.
-+#
-+# The remainder of the processing of the current object record follows the
-+# procedure outlined in (3a).
-+#
-+ARGIND == 3 && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
-+ osect = $1;
-+ if (!(osect in sect_addend))
-+ next;
-+
-+ # We need to work with the main section.
-+ sect = sect_in[osect];
-+
-+ # Turn the address into an offset from the section base.
-+ soff = $2;
-+ sub(addr_prefix, "0x", soff);
-+ soff = strtonum(soff) + sect_addend[osect];
-+ eoff = soff + strtonum($3);
-+
-+ # Determine which (if any) built-in modules the object belongs to.
-+ mod = get_module_info($4);
-+
-+ # If we are processing a built-in module:
-+ # - If the current object is within the same module, we update its
-+ # entry by extending the range and move on
-+ # - Otherwise:
-+ # + If we are still processing within the same main section, we
-+ # validate the end offset against the start offset of the
-+ # current object (e.g. .rodata.str1.[18] objects are often
-+ # listed with an incorrect size in the linker map)
-+ # + Otherwise, we validate the end offset against the section
-+ # size
-+ if (mod_name) {
-+ if (mod == mod_name) {
-+ mod_eoff = eoff;
-+ update_entry(mod_sect, mod_name, mod_soff, eoff);
-+
-+ next;
-+ } else if (sect == sect_in[mod_sect]) {
-+ if (mod_eoff > soff)
-+ update_entry(mod_sect, mod_name, mod_soff, soff);
-+ } else {
-+ v = sect_size[sect_in[mod_sect]];
-+ if (mod_eoff > v)
-+ update_entry(mod_sect, mod_name, mod_soff, v);
-+ }
-+ }
-+
-+ mod_name = mod;
-+
-+ # If we encountered an object that is not part of a built-in module, we
-+ # do not need to record any data.
-+ if (!mod)
-+ next;
-+
-+ # At this point, we encountered the start of a new built-in module.
-+ mod_name = mod;
-+ mod_soff = soff;
-+ mod_eoff = eoff;
-+ mod_sect = osect;
-+ update_entry(osect, mod, soff, mod_eoff);
-+
-+ next;
-+}
-+
-+# (4) Generate the output.
-+#
-+# Anchor records are added for each section that contains offset range data
-+# records. They are added at an adjusted section base address (base << 1) to
-+# ensure they come first in the second records (see update_entry() above for
-+# more information).
-+#
-+# All entries are sorted by (adjusted) address to ensure that the output can be
-+# parsed in strict ascending address order.
-+#
-+END {
-+ for (sect in count) {
-+ if (sect in sect_anchor)
-+ entries[sect_base[sect] * 2] = sect_anchor[sect];
-+ }
-+
-+ n = asorti(entries, indices);
-+ for (i = 1; i <= n; i++)
-+ print entries[indices[i]];
-+}
-diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
-index f48d72d22dc2a..d7e6cd7781256 100644
---- a/scripts/mod/modpost.c
-+++ b/scripts/mod/modpost.c
-@@ -733,6 +733,7 @@ static const char *const section_white_list[] =
- ".comment*",
- ".debug*",
- ".zdebug*", /* Compressed debug sections. */
-+ ".ctf", /* Type info */
- ".GCC.command.line", /* record-gcc-switches */
- ".mdebug*", /* alpha, score, mips etc. */
- ".pdr", /* alpha, score, mips etc. */
-diff --git a/scripts/modules_builtin.c b/scripts/modules_builtin.c
-new file mode 100644
-index 0000000000000..df52932a4417b
---- /dev/null
-+++ b/scripts/modules_builtin.c
-@@ -0,0 +1,200 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * A simple modules_builtin reader.
-+ *
-+ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
-+ *
-+ * This program is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ */
-+
-+#include <errno.h>
-+#include <stdio.h>
-+#include <stdlib.h>
-+#include <string.h>
-+
-+#include "modules_builtin.h"
-+
-+/*
-+ * Read a modules.builtin.objs file and translate it into a stream of
-+ * name / module-name pairs.
-+ */
-+
-+/*
-+ * Construct a modules.builtin.objs iterator.
-+ */
-+struct modules_builtin_iter *
-+modules_builtin_iter_new(const char *modules_builtin_file)
-+{
-+ struct modules_builtin_iter *i;
-+
-+ i = calloc(1, sizeof(struct modules_builtin_iter));
-+ if (i == NULL)
-+ return NULL;
-+
-+ i->f = fopen(modules_builtin_file, "r");
-+
-+ if (i->f == NULL) {
-+ fprintf(stderr, "Cannot open builtin module file %s: %s\n",
-+ modules_builtin_file, strerror(errno));
-+ return NULL;
-+ }
-+
-+ return i;
-+}
-+
-+/*
-+ * Iterate, returning a new null-terminated array of object file names, and a
-+ * new dynamically-allocated module name. (The module name passed in is freed.)
-+ *
-+ * The array of object file names should be freed by the caller: the strings it
-+ * points to are owned by the iterator, and should not be freed.
-+ */
-+
-+char ** __attribute__((__nonnull__))
-+modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name)
-+{
-+ size_t npaths = 1;
-+ char **module_paths;
-+ char *last_slash;
-+ char *last_dot;
-+ char *trailing_linefeed;
-+ char *object_name = i->line;
-+ char *dash;
-+ int composite = 0;
-+
-+ /*
-+ * Read in all module entries, computing the suffixless, pathless name
-+ * of the module and building the next arrayful of object file names for
-+ * return.
-+ *
-+ * Modules can consist of multiple files: in this case, the portion
-+ * before the colon is the path to the module (as before): the portion
-+ * after the colon is a space-separated list of files that should be
-+ * considered part of this module. In this case, the portion before the
-+ * name is an "object file" that does not actually exist: it is merged
-+ * into built-in.a without ever being written out.
-+ *
-+ * All module names have - translated to _, to match what is done to the
-+ * names of the same things when built as modules.
-+ */
-+
-+ /*
-+ * Reinvocation of exhausted iterator. Return NULL, once.
-+ */
-+retry:
-+ if (getline(&i->line, &i->line_size, i->f) < 0) {
-+ if (ferror(i->f)) {
-+ fprintf(stderr, "Error reading from modules_builtin file:"
-+ " %s\n", strerror(errno));
-+ exit(1);
-+ }
-+ rewind(i->f);
-+ return NULL;
-+ }
-+
-+ if (i->line[0] == '\0')
-+ goto retry;
-+
-+ trailing_linefeed = strchr(i->line, '\n');
-+ if (trailing_linefeed != NULL)
-+ *trailing_linefeed = '\0';
-+
-+ /*
-+ * Slice the line in two at the colon, if any. If there is anything
-+ * past the ': ', this is a composite module. (We allow for no colon
-+ * for robustness, even though one should always be present.)
-+ */
-+ if (strchr(i->line, ':') != NULL) {
-+ char *name_start;
-+
-+ object_name = strchr(i->line, ':');
-+ *object_name = '\0';
-+ object_name++;
-+ name_start = object_name + strspn(object_name, " \n");
-+ if (*name_start != '\0') {
-+ composite = 1;
-+ object_name = name_start;
-+ }
-+ }
-+
-+ /*
-+ * Figure out the module name.
-+ */
-+ last_slash = strrchr(i->line, '/');
-+ last_slash = (!last_slash) ? i->line :
-+ last_slash + 1;
-+ free(*module_name);
-+ *module_name = strdup(last_slash);
-+ dash = *module_name;
-+
-+ while (dash != NULL) {
-+ dash = strchr(dash, '-');
-+ if (dash != NULL)
-+ *dash = '_';
-+ }
-+
-+ last_dot = strrchr(*module_name, '.');
-+ if (last_dot != NULL)
-+ *last_dot = '\0';
-+
-+ /*
-+ * Multifile separator? Object file names explicitly stated:
-+ * slice them up and shuffle them in.
-+ *
-+ * The array size may be an overestimate if any object file
-+ * names start or end with spaces (very unlikely) but cannot be
-+ * an underestimate. (Check for it anyway.)
-+ */
-+ if (composite) {
-+ char *one_object;
-+
-+ for (npaths = 0, one_object = object_name;
-+ one_object != NULL;
-+ npaths++, one_object = strchr(one_object + 1, ' '));
-+ }
-+
-+ module_paths = malloc((npaths + 1) * sizeof(char *));
-+ if (!module_paths) {
-+ fprintf(stderr, "%s: out of memory on module %s\n", __func__,
-+ *module_name);
-+ exit(1);
-+ }
-+
-+ if (composite) {
-+ char *one_object;
-+ size_t i = 0;
-+
-+ while ((one_object = strsep(&object_name, " ")) != NULL) {
-+ if (i >= npaths) {
-+ fprintf(stderr, "%s: num_objs overflow on module "
-+ "%s: this is a bug.\n", __func__,
-+ *module_name);
-+ exit(1);
-+ }
-+
-+ module_paths[i++] = one_object;
-+ }
-+ } else
-+ module_paths[0] = i->line; /* untransformed module name */
-+
-+ module_paths[npaths] = NULL;
-+
-+ return module_paths;
-+}
-+
-+/*
-+ * Free an iterator. Can be called while iteration is underway, so even
-+ * state that is freed at the end of iteration must be freed here too.
-+ */
-+void
-+modules_builtin_iter_free(struct modules_builtin_iter *i)
-+{
-+ if (i == NULL)
-+ return;
-+ fclose(i->f);
-+ free(i->line);
-+ free(i);
-+}
-diff --git a/scripts/modules_builtin.h b/scripts/modules_builtin.h
-new file mode 100644
-index 0000000000000..5138792b42ef0
---- /dev/null
-+++ b/scripts/modules_builtin.h
-@@ -0,0 +1,48 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * A simple modules.builtin.objs reader.
-+ *
-+ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
-+ *
-+ * This program is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ */
-+
-+#ifndef _LINUX_MODULES_BUILTIN_H
-+#define _LINUX_MODULES_BUILTIN_H
-+
-+#include <stdio.h>
-+#include <stddef.h>
-+
-+/*
-+ * modules.builtin.objs iteration state.
-+ */
-+struct modules_builtin_iter {
-+ FILE *f;
-+ char *line;
-+ size_t line_size;
-+};
-+
-+/*
-+ * Construct a modules_builtin.objs iterator.
-+ */
-+struct modules_builtin_iter *
-+modules_builtin_iter_new(const char *modules_builtin_file);
-+
-+/*
-+ * Iterate, returning a new null-terminated array of object file names, and a
-+ * new dynamically-allocated module name. (The module name passed in is freed.)
-+ *
-+ * The array of object file names should be freed by the caller: the strings it
-+ * points to are owned by the iterator, and should not be freed.
-+ */
-+
-+char ** __attribute__((__nonnull__))
-+modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name);
-+
-+void
-+modules_builtin_iter_free(struct modules_builtin_iter *i);
-+
-+#endif
-diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
-index c52d517b93647..8f75906a96314 100644
---- a/scripts/package/kernel.spec
-+++ b/scripts/package/kernel.spec
-@@ -53,12 +53,18 @@ patch -p1 < %{SOURCE2}
-
- %build
- %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
-+%if %{with_ctf}
-+%{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release} ctf
-+%endif
-
- %install
- mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
- cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
- # DEPMOD=true makes depmod no-op. We do not package depmod-generated files.
- %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} DEPMOD=true modules_install
-+%if %{with_ctf}
-+%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} ctf_install
-+%endif
- %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
- cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
- cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
-diff --git a/scripts/package/mkspec b/scripts/package/mkspec
-index ce201bfa8377c..aeb43c7ab1229 100755
---- a/scripts/package/mkspec
-+++ b/scripts/package/mkspec
-@@ -21,10 +21,16 @@ else
- echo '%define with_devel 0'
- fi
-
-+if grep -q CONFIG_CTF=y include/config/auto.conf; then
-+echo '%define with_ctf %{?_without_ctf: 0} %{?!_without_ctf: 1}'
-+else
-+echo '%define with_ctf 0'
-+fi
- cat<<EOF
- %define ARCH ${ARCH}
- %define KERNELRELEASE ${KERNELRELEASE}
- %define pkg_release $("${srctree}/init/build-version")
-+
- EOF
-
- cat "${srctree}/scripts/package/kernel.spec"
-diff --git a/scripts/remove-ctf-lds.awk b/scripts/remove-ctf-lds.awk
-new file mode 100644
-index 0000000000000..5d94d6ee99227
---- /dev/null
-+++ b/scripts/remove-ctf-lds.awk
-@@ -0,0 +1,12 @@
-+# SPDX-License-Identifier: GPL-2.0
-+# See Makefile.vmlinux_o
-+
-+BEGIN {
-+ discards = 0; p = 0
-+}
-+
-+/^====/ { p = 1; next; }
-+p && /\.ctf/ { next; }
-+p && !discards && /DISCARD/ { sub(/\} *$/, " *(.ctf) }"); discards = 1 }
-+p && /^\}/ && !discards { print " /DISCARD/ : { *(.ctf) }"; }
-+p { print $0; }
-diff --git a/scripts/verify_builtin_ranges.awk b/scripts/verify_builtin_ranges.awk
-new file mode 100755
-index 0000000000000..f513841da83e1
---- /dev/null
-+++ b/scripts/verify_builtin_ranges.awk
-@@ -0,0 +1,356 @@
-+#!/usr/bin/gawk -f
-+# SPDX-License-Identifier: GPL-2.0
-+# verify_builtin_ranges.awk: Verify address range data for builtin modules
-+# Written by Kris Van Hees <kris.van.hees@oracle.com>
-+#
-+# Usage: verify_builtin_ranges.awk modules.builtin.ranges System.map \
-+# modules.builtin vmlinux.map vmlinux.o.map \
-+# [ <build-dir> ]
-+#
-+
-+# Return the module name(s) (if any) associated with the given object.
-+#
-+# If we have seen this object before, return information from the cache.
-+# Otherwise, retrieve it from the corresponding .cmd file.
-+#
-+function get_module_info(fn, mod, obj, s) {
-+ if (fn in omod)
-+ return omod[fn];
-+
-+ if (match(fn, /\/[^/]+$/) == 0)
-+ return "";
-+
-+ obj = fn;
-+ mod = "";
-+ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
-+ if (getline s <fn == 1) {
-+ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
-+ mod = substr(s, RSTART + 16, RLENGTH - 16);
-+ gsub(/['"]/, "", mod);
-+ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
-+ mod = substr(s, RSTART + 13, RLENGTH - 13);
-+ } else {
-+ print "ERROR: Failed to read: " fn "\n\n" \
-+ " Invalid kernel build directory (" kdir ")\n" \
-+ " or its content does not match " ARGV[1] >"/dev/stderr";
-+ close(fn);
-+ total = 0;
-+ exit(1);
-+ }
-+ close(fn);
-+
-+ # A single module (common case) also reflects objects that are not part
-+ # of a module. Some of those objects have names that are also a module
-+ # name (e.g. core). We check the associated module file name, and if
-+ # they do not match, the object is not part of a module.
-+ if (mod !~ / /) {
-+ if (!(mod in mods))
-+ mod = "";
-+ }
-+
-+ gsub(/([^/ ]*\/)+/, "", mod);
-+ gsub(/-/, "_", mod);
-+
-+ # At this point, mod is a single (valid) module name, or a list of
-+ # module names (that do not need validation).
-+ omod[obj] = mod;
-+
-+ return mod;
-+}
-+
-+# Return a representative integer value for a given hexadecimal address.
-+#
-+# Since all kernel addresses fall within the same memory region, we can safely
-+# strip off the first 6 hex digits before performing the hex-to-dec conversion,
-+# thereby avoiding integer overflows.
-+#
-+function addr2val(val) {
-+ sub(/^0x/, "", val);
-+ if (length(val) == 16)
-+ val = substr(val, 5);
-+ return strtonum("0x" val);
-+}
-+
-+# Determine the kernel build directory to use (default is .).
-+#
-+BEGIN {
-+ if (ARGC > 6) {
-+ kdir = ARGV[ARGC - 1];
-+ ARGV[ARGC - 1] = "";
-+ } else
-+ kdir = ".";
-+}
-+
-+# (1) Load the built-in module address range data.
-+#
-+ARGIND == 1 {
-+ ranges[FNR] = $0;
-+ rcnt++;
-+ next;
-+}
-+
-+# (2) Annotate System.map symbols with module names.
-+#
-+ARGIND == 2 {
-+ addr = addr2val($1);
-+ name = $3;
-+
-+ while (addr >= mod_eaddr) {
-+ if (sect_symb) {
-+ if (sect_symb != name)
-+ next;
-+
-+ sect_base = addr - sect_off;
-+ if (dbg)
-+ printf "[%s] BASE (%s) %016x - %016x = %016x\n", sect_name, sect_symb, addr, sect_off, sect_base >"/dev/stderr";
-+ sect_symb = 0;
-+ }
-+
-+ if (++ridx > rcnt)
-+ break;
-+
-+ $0 = ranges[ridx];
-+ sub(/-/, " ");
-+ if ($4 != "=") {
-+ sub(/-/, " ");
-+ mod_saddr = strtonum("0x" $2) + sect_base;
-+ mod_eaddr = strtonum("0x" $3) + sect_base;
-+ $1 = $2 = $3 = "";
-+ sub(/^ +/, "");
-+ mod_name = $0;
-+
-+ if (dbg)
-+ printf "[%s] %s from %016x to %016x\n", sect_name, mod_name, mod_saddr, mod_eaddr >"/dev/stderr";
-+ } else {
-+ sect_name = $1;
-+ sect_off = strtonum("0x" $2);
-+ sect_symb = $5;
-+ }
-+ }
-+
-+ idx = addr"-"name;
-+ if (addr >= mod_saddr && addr < mod_eaddr)
-+ sym2mod[idx] = mod_name;
-+
-+ next;
-+}
-+
-+# Once we are done annotating the System.map, we no longer need the ranges data.
-+#
-+FNR == 1 && ARGIND == 3 {
-+ delete ranges;
-+}
-+
-+# (3) Build a lookup map of built-in module names.
-+#
-+# Lines from modules.builtin will be like:
-+# kernel/crypto/lzo-rle.ko
-+# and we record the object name "crypto/lzo-rle".
-+#
-+ARGIND == 3 {
-+ sub(/kernel\//, ""); # strip off "kernel/" prefix
-+ sub(/\.ko$/, ""); # strip off .ko suffix
-+
-+ mods[$1] = 1;
-+ next;
-+}
-+
-+# (4) Get a list of symbols (per object).
-+#
-+# Symbols by object are read from vmlinux.map, with fallback to vmlinux.o.map
-+# if vmlinux is found to have inked in vmlinux.o.
-+#
-+
-+# If we were able to get the data we need from vmlinux.map, there is no need to
-+# process vmlinux.o.map.
-+#
-+FNR == 1 && ARGIND == 5 && total > 0 {
-+ if (dbg)
-+ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
-+ exit;
-+}
-+
-+# First determine whether we are dealing with a GNU ld or LLVM lld linker map.
-+#
-+ARGIND >= 4 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
-+ map_is_lld = 1;
-+ next;
-+}
-+
-+# (LLD) Convert a section record fronm lld format to ld format.
-+#
-+ARGIND >= 4 && map_is_lld && NF == 5 && /[0-9] [^ ]/ {
-+ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
-+}
-+
-+# (LLD) Convert an object record from lld format to ld format.
-+#
-+ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /:\(\./ {
-+ gsub(/\)/, "");
-+ sub(/:\(/, " ");
-+ sub(/ vmlinux\.a\(/, " ");
-+ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
-+}
-+
-+# (LLD) Convert a symbol record from lld format to ld format.
-+#
-+ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /^[A-Za-z_][A-Za-z0-9_]*$/ {
-+ $0 = " 0x" $1 " " $5;
-+}
-+
-+# (LLD) We do not need any other ldd linker map records.
-+#
-+ARGIND >= 4 && map_is_lld && /^[0-9a-f]{16} / {
-+ next;
-+}
-+
-+# Handle section records with long section names (spilling onto a 2nd line).
-+#
-+ARGIND >= 4 && !map_is_lld && NF == 1 && /^[^ ]/ {
-+ s = $0;
-+ getline;
-+ $0 = s " " $0;
-+}
-+
-+# Next section - previous one is done.
-+#
-+ARGIND >= 4 && /^[^ ]/ {
-+ sect = 0;
-+}
-+
-+# Get the (top level) section name.
-+#
-+ARGIND >= 4 && /^[^ ]/ && $2 ~ /^0x/ && $3 ~ /^0x/ {
-+ # Empty section or per-CPU section - ignore.
-+ if (NF < 3 || $1 ~ /\.percpu/) {
-+ sect = 0;
-+ next;
-+ }
-+
-+ sect = $1;
-+
-+ next;
-+}
-+
-+# If we are not currently in a section we care about, ignore records.
-+#
-+!sect {
-+ next;
-+}
-+
-+# Handle object records with long section names (spilling onto a 2nd line).
-+#
-+ARGIND >= 4 && /^ [^ \*]/ && NF == 1 {
-+ # If the section name is long, the remainder of the entry is found on
-+ # the next line.
-+ s = $0;
-+ getline;
-+ $0 = s " " $0;
-+}
-+
-+# If the object is vmlinux.o, we need to consult vmlinux.o.map for per-object
-+# symbol information
-+#
-+ARGIND == 4 && /^ [^ ]/ && NF == 4 {
-+ idx = sect":"$1;
-+ if (!(idx in sect_addend)) {
-+ sect_addend[idx] = addr2val($2);
-+ if (dbg)
-+ printf "ADDEND %s = %016x\n", idx, sect_addend[idx] >"/dev/stderr";
-+ }
-+ if ($4 == "vmlinux.o") {
-+ need_o_map = 1;
-+ next;
-+ }
-+}
-+
-+# If data from vmlinux.o.map is needed, we only process section and object
-+# records from vmlinux.map to determine which section we need to pay attention
-+# to in vmlinux.o.map. So skip everything else from vmlinux.map.
-+#
-+ARGIND == 4 && need_o_map {
-+ next;
-+}
-+
-+# Get module information for the current object.
-+#
-+ARGIND >= 4 && /^ [^ ]/ && NF == 4 {
-+ msect = $1;
-+ mod_name = get_module_info($4);
-+ mod_eaddr = addr2val($2) + addr2val($3);
-+
-+ next;
-+}
-+
-+# Process a symbol record.
-+#
-+# Evaluate the module information obtained from vmlinux.map (or vmlinux.o.map)
-+# as follows:
-+# - For all symbols in a given object:
-+# - If the symbol is annotated with the same module name(s) that the object
-+# belongs to, count it as a match.
-+# - Otherwise:
-+# - If the symbol is known to have duplicates of which at least one is
-+# in a built-in module, disregard it.
-+# - If the symbol us not annotated with any module name(s) AND the
-+# object belongs to built-in modules, count it as missing.
-+# - Otherwise, count it as a mismatch.
-+#
-+ARGIND >= 4 && /^ / && NF == 2 && $1 ~ /^0x/ {
-+ idx = sect":"msect;
-+ if (!(idx in sect_addend))
-+ next;
-+
-+ addr = addr2val($1);
-+
-+ # Handle the rare but annoying case where a 0-size symbol is placed at
-+ # the byte *after* the module range. Based on vmlinux.map it will be
-+ # considered part of the current object, but it falls just beyond the
-+ # module address range. Unfortunately, its address could be at the
-+ # start of another built-in module, so the only safe thing to do is to
-+ # ignore it.
-+ if (mod_name && addr == mod_eaddr)
-+ next;
-+
-+ # If we are processing vmlinux.o.map, we need to apply the base address
-+ # of the section to the relative address on the record.
-+ #
-+ if (ARGIND == 5)
-+ addr += sect_addend[idx];
-+
-+ idx = addr"-"$2;
-+ mod = "";
-+ if (idx in sym2mod) {
-+ mod = sym2mod[idx];
-+ if (sym2mod[idx] == mod_name) {
-+ mod_matches++;
-+ matches++;
-+ } else if (mod_name == "") {
-+ print $2 " in " sym2mod[idx] " (should NOT be)";
-+ mismatches++;
-+ } else {
-+ print $2 " in " sym2mod[idx] " (should be " mod_name ")";
-+ mismatches++;
-+ }
-+ } else if (mod_name != "") {
-+ print $2 " should be in " mod_name;
-+ missing++;
-+ } else
-+ matches++;
-+
-+ total++;
-+
-+ next;
-+}
-+
-+# Issue the comparison report.
-+#
-+END {
-+ if (total) {
-+ printf "Verification of %s:\n", ARGV[1];
-+ printf " Correct matches: %6d (%d%% of total)\n", matches, 100 * matches / total;
-+ printf " Module matches: %6d (%d%% of matches)\n", mod_matches, 100 * mod_matches / matches;
-+ printf " Mismatches: %6d (%d%% of total)\n", mismatches, 100 * mismatches / total;
-+ printf " Missing: %6d (%d%% of total)\n", missing, 100 * missing / total;
-+ }
-+}
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-30 16:03 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-30 16:03 UTC (permalink / raw
To: gentoo-commits
commit: 214d41397bbe150fe75f123d504ba3b7f6d0f1f4
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Mon Sep 30 16:02:51 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Mon Sep 30 16:02:51 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=214d4139
Linux patch 6.10.12
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1011_linux-6.10.12.patch | 2389 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 2393 insertions(+)
diff --git a/0000_README b/0000_README
index 23b2116a..f735905c 100644
--- a/0000_README
+++ b/0000_README
@@ -87,6 +87,10 @@ Patch: 1010_linux-6.10.11.patch
From: https://www.kernel.org
Desc: Linux 6.10.11
+Patch: 1011_linux-6.10.12.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.12
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1011_linux-6.10.12.patch b/1011_linux-6.10.12.patch
new file mode 100644
index 00000000..d6d1ff01
--- /dev/null
+++ b/1011_linux-6.10.12.patch
@@ -0,0 +1,2389 @@
+diff --git a/Makefile b/Makefile
+index 447856c43b3275..175d7f27ea32a4 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 11
++SUBLEVEL = 12
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/loongarch/include/asm/hw_irq.h b/arch/loongarch/include/asm/hw_irq.h
+index af4f4e8fbd858f..8156ffb6741591 100644
+--- a/arch/loongarch/include/asm/hw_irq.h
++++ b/arch/loongarch/include/asm/hw_irq.h
+@@ -9,6 +9,8 @@
+
+ extern atomic_t irq_err_count;
+
++#define ARCH_IRQ_INIT_FLAGS IRQ_NOPROBE
++
+ /*
+ * interrupt-retrigger: NOP for now. This may not be appropriate for all
+ * machines, we'll see ...
+diff --git a/arch/loongarch/include/asm/kvm_vcpu.h b/arch/loongarch/include/asm/kvm_vcpu.h
+index 590a92cb54165c..d741c3e9933a51 100644
+--- a/arch/loongarch/include/asm/kvm_vcpu.h
++++ b/arch/loongarch/include/asm/kvm_vcpu.h
+@@ -76,7 +76,6 @@ static inline void kvm_restore_lasx(struct loongarch_fpu *fpu) { }
+ #endif
+
+ void kvm_init_timer(struct kvm_vcpu *vcpu, unsigned long hz);
+-void kvm_reset_timer(struct kvm_vcpu *vcpu);
+ void kvm_save_timer(struct kvm_vcpu *vcpu);
+ void kvm_restore_timer(struct kvm_vcpu *vcpu);
+
+diff --git a/arch/loongarch/kernel/irq.c b/arch/loongarch/kernel/irq.c
+index f4991c03514f48..adac8fcbb2aca4 100644
+--- a/arch/loongarch/kernel/irq.c
++++ b/arch/loongarch/kernel/irq.c
+@@ -102,9 +102,6 @@ void __init init_IRQ(void)
+ mp_ops.init_ipi();
+ #endif
+
+- for (i = 0; i < NR_IRQS; i++)
+- irq_set_noprobe(i);
+-
+ for_each_possible_cpu(i) {
+ page = alloc_pages_node(cpu_to_node(i), GFP_KERNEL, order);
+
+diff --git a/arch/loongarch/kvm/timer.c b/arch/loongarch/kvm/timer.c
+index bcc6b6d063d914..74a4b5c272d60e 100644
+--- a/arch/loongarch/kvm/timer.c
++++ b/arch/loongarch/kvm/timer.c
+@@ -188,10 +188,3 @@ void kvm_save_timer(struct kvm_vcpu *vcpu)
+ kvm_save_hw_gcsr(csr, LOONGARCH_CSR_ESTAT);
+ preempt_enable();
+ }
+-
+-void kvm_reset_timer(struct kvm_vcpu *vcpu)
+-{
+- write_gcsr_timercfg(0);
+- kvm_write_sw_gcsr(vcpu->arch.csr, LOONGARCH_CSR_TCFG, 0);
+- hrtimer_cancel(&vcpu->arch.swtimer);
+-}
+diff --git a/arch/loongarch/kvm/vcpu.c b/arch/loongarch/kvm/vcpu.c
+index 9e8030d4512902..0b53f4d9fddf91 100644
+--- a/arch/loongarch/kvm/vcpu.c
++++ b/arch/loongarch/kvm/vcpu.c
+@@ -572,7 +572,7 @@ static int kvm_set_one_reg(struct kvm_vcpu *vcpu,
+ vcpu->kvm->arch.time_offset = (signed long)(v - drdtime());
+ break;
+ case KVM_REG_LOONGARCH_VCPU_RESET:
+- kvm_reset_timer(vcpu);
++ vcpu->arch.st.guest_addr = 0;
+ memset(&vcpu->arch.irq_pending, 0, sizeof(vcpu->arch.irq_pending));
+ memset(&vcpu->arch.irq_clear, 0, sizeof(vcpu->arch.irq_clear));
+ break;
+diff --git a/arch/microblaze/mm/init.c b/arch/microblaze/mm/init.c
+index 3827dc76edd823..4520c57415797f 100644
+--- a/arch/microblaze/mm/init.c
++++ b/arch/microblaze/mm/init.c
+@@ -193,11 +193,6 @@ asmlinkage void __init mmu_init(void)
+ {
+ unsigned int kstart, ksize;
+
+- if (!memblock.reserved.cnt) {
+- pr_emerg("Error memory count\n");
+- machine_restart(NULL);
+- }
+-
+ if ((u32) memblock.memory.regions[0].size < 0x400000) {
+ pr_emerg("Memory must be greater than 4MB\n");
+ machine_restart(NULL);
+diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
+index 41632fb57796de..ead967479fa634 100644
+--- a/arch/x86/kernel/cpu/mshyperv.c
++++ b/arch/x86/kernel/cpu/mshyperv.c
+@@ -424,6 +424,7 @@ static void __init ms_hyperv_init_platform(void)
+ ms_hyperv.misc_features & HV_FEATURE_FREQUENCY_MSRS_AVAILABLE) {
+ x86_platform.calibrate_tsc = hv_get_tsc_khz;
+ x86_platform.calibrate_cpu = hv_get_tsc_khz;
++ setup_force_cpu_cap(X86_FEATURE_TSC_KNOWN_FREQ);
+ }
+
+ if (ms_hyperv.priv_high & HV_ISOLATION) {
+diff --git a/drivers/accel/drm_accel.c b/drivers/accel/drm_accel.c
+index 16c3edb8c46ee1..aa826033b0ceb9 100644
+--- a/drivers/accel/drm_accel.c
++++ b/drivers/accel/drm_accel.c
+@@ -8,7 +8,7 @@
+
+ #include <linux/debugfs.h>
+ #include <linux/device.h>
+-#include <linux/idr.h>
++#include <linux/xarray.h>
+
+ #include <drm/drm_accel.h>
+ #include <drm/drm_auth.h>
+@@ -18,8 +18,7 @@
+ #include <drm/drm_ioctl.h>
+ #include <drm/drm_print.h>
+
+-static DEFINE_SPINLOCK(accel_minor_lock);
+-static struct idr accel_minors_idr;
++DEFINE_XARRAY_ALLOC(accel_minors_xa);
+
+ static struct dentry *accel_debugfs_root;
+
+@@ -117,99 +116,6 @@ void accel_set_device_instance_params(struct device *kdev, int index)
+ kdev->type = &accel_sysfs_device_minor;
+ }
+
+-/**
+- * accel_minor_alloc() - Allocates a new accel minor
+- *
+- * This function access the accel minors idr and allocates from it
+- * a new id to represent a new accel minor
+- *
+- * Return: A new id on success or error code in case idr_alloc failed
+- */
+-int accel_minor_alloc(void)
+-{
+- unsigned long flags;
+- int r;
+-
+- spin_lock_irqsave(&accel_minor_lock, flags);
+- r = idr_alloc(&accel_minors_idr, NULL, 0, ACCEL_MAX_MINORS, GFP_NOWAIT);
+- spin_unlock_irqrestore(&accel_minor_lock, flags);
+-
+- return r;
+-}
+-
+-/**
+- * accel_minor_remove() - Remove an accel minor
+- * @index: The minor id to remove.
+- *
+- * This function access the accel minors idr and removes from
+- * it the member with the id that is passed to this function.
+- */
+-void accel_minor_remove(int index)
+-{
+- unsigned long flags;
+-
+- spin_lock_irqsave(&accel_minor_lock, flags);
+- idr_remove(&accel_minors_idr, index);
+- spin_unlock_irqrestore(&accel_minor_lock, flags);
+-}
+-
+-/**
+- * accel_minor_replace() - Replace minor pointer in accel minors idr.
+- * @minor: Pointer to the new minor.
+- * @index: The minor id to replace.
+- *
+- * This function access the accel minors idr structure and replaces the pointer
+- * that is associated with an existing id. Because the minor pointer can be
+- * NULL, we need to explicitly pass the index.
+- *
+- * Return: 0 for success, negative value for error
+- */
+-void accel_minor_replace(struct drm_minor *minor, int index)
+-{
+- unsigned long flags;
+-
+- spin_lock_irqsave(&accel_minor_lock, flags);
+- idr_replace(&accel_minors_idr, minor, index);
+- spin_unlock_irqrestore(&accel_minor_lock, flags);
+-}
+-
+-/*
+- * Looks up the given minor-ID and returns the respective DRM-minor object. The
+- * refence-count of the underlying device is increased so you must release this
+- * object with accel_minor_release().
+- *
+- * The object can be only a drm_minor that represents an accel device.
+- *
+- * As long as you hold this minor, it is guaranteed that the object and the
+- * minor->dev pointer will stay valid! However, the device may get unplugged and
+- * unregistered while you hold the minor.
+- */
+-static struct drm_minor *accel_minor_acquire(unsigned int minor_id)
+-{
+- struct drm_minor *minor;
+- unsigned long flags;
+-
+- spin_lock_irqsave(&accel_minor_lock, flags);
+- minor = idr_find(&accel_minors_idr, minor_id);
+- if (minor)
+- drm_dev_get(minor->dev);
+- spin_unlock_irqrestore(&accel_minor_lock, flags);
+-
+- if (!minor) {
+- return ERR_PTR(-ENODEV);
+- } else if (drm_dev_is_unplugged(minor->dev)) {
+- drm_dev_put(minor->dev);
+- return ERR_PTR(-ENODEV);
+- }
+-
+- return minor;
+-}
+-
+-static void accel_minor_release(struct drm_minor *minor)
+-{
+- drm_dev_put(minor->dev);
+-}
+-
+ /**
+ * accel_open - open method for ACCEL file
+ * @inode: device inode
+@@ -227,7 +133,7 @@ int accel_open(struct inode *inode, struct file *filp)
+ struct drm_minor *minor;
+ int retcode;
+
+- minor = accel_minor_acquire(iminor(inode));
++ minor = drm_minor_acquire(&accel_minors_xa, iminor(inode));
+ if (IS_ERR(minor))
+ return PTR_ERR(minor);
+
+@@ -246,7 +152,7 @@ int accel_open(struct inode *inode, struct file *filp)
+
+ err_undo:
+ atomic_dec(&dev->open_count);
+- accel_minor_release(minor);
++ drm_minor_release(minor);
+ return retcode;
+ }
+ EXPORT_SYMBOL_GPL(accel_open);
+@@ -257,7 +163,7 @@ static int accel_stub_open(struct inode *inode, struct file *filp)
+ struct drm_minor *minor;
+ int err;
+
+- minor = accel_minor_acquire(iminor(inode));
++ minor = drm_minor_acquire(&accel_minors_xa, iminor(inode));
+ if (IS_ERR(minor))
+ return PTR_ERR(minor);
+
+@@ -274,7 +180,7 @@ static int accel_stub_open(struct inode *inode, struct file *filp)
+ err = 0;
+
+ out:
+- accel_minor_release(minor);
++ drm_minor_release(minor);
+
+ return err;
+ }
+@@ -290,15 +196,13 @@ void accel_core_exit(void)
+ unregister_chrdev(ACCEL_MAJOR, "accel");
+ debugfs_remove(accel_debugfs_root);
+ accel_sysfs_destroy();
+- idr_destroy(&accel_minors_idr);
++ WARN_ON(!xa_empty(&accel_minors_xa));
+ }
+
+ int __init accel_core_init(void)
+ {
+ int ret;
+
+- idr_init(&accel_minors_idr);
+-
+ ret = accel_sysfs_init();
+ if (ret < 0) {
+ DRM_ERROR("Cannot create ACCEL class: %d\n", ret);
+diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
+index 1fd3b7073ab90d..b5bfe12a97e1bc 100644
+--- a/drivers/bluetooth/btintel_pcie.c
++++ b/drivers/bluetooth/btintel_pcie.c
+@@ -1208,7 +1208,7 @@ static int btintel_pcie_setup_hdev(struct btintel_pcie_data *data)
+ int err;
+ struct hci_dev *hdev;
+
+- hdev = hci_alloc_dev();
++ hdev = hci_alloc_dev_priv(sizeof(struct btintel_data));
+ if (!hdev)
+ return -ENOMEM;
+
+diff --git a/drivers/clk/qcom/gcc-sm8650.c b/drivers/clk/qcom/gcc-sm8650.c
+index 9d1cbdf860fb3b..10834c3141d07f 100644
+--- a/drivers/clk/qcom/gcc-sm8650.c
++++ b/drivers/clk/qcom/gcc-sm8650.c
+@@ -713,7 +713,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s0_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -728,7 +728,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s1_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -743,7 +743,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s2_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -758,7 +758,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s3_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -773,7 +773,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s4_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -788,7 +788,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s5_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -803,7 +803,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s6_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -818,7 +818,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s7_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -833,7 +833,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s8_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -848,7 +848,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s9_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -863,7 +863,7 @@ static struct clk_init_data gcc_qupv3_wrap1_qspi_ref_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_qspi_ref_clk_src = {
+@@ -899,7 +899,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = {
+@@ -916,7 +916,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = {
+@@ -948,7 +948,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = {
+@@ -980,7 +980,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = {
+@@ -997,7 +997,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = {
+@@ -1014,7 +1014,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s6_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s6_clk_src = {
+@@ -1031,7 +1031,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s7_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s7_clk_src = {
+@@ -1059,7 +1059,7 @@ static struct clk_rcg2 gcc_qupv3_wrap2_ibi_ctrl_0_clk_src = {
+ .parent_data = gcc_parent_data_2,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_2),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -1068,7 +1068,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s0_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s0_clk_src = {
+@@ -1085,7 +1085,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s1_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s1_clk_src = {
+@@ -1102,7 +1102,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s2_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s2_clk_src = {
+@@ -1119,7 +1119,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s3_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s3_clk_src = {
+@@ -1136,7 +1136,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s4_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s4_clk_src = {
+@@ -1153,7 +1153,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s5_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s5_clk_src = {
+@@ -1186,7 +1186,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s6_clk_src_init = {
+ .parent_data = gcc_parent_data_10,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_10),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s6_clk_src = {
+@@ -1203,7 +1203,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s7_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s7_clk_src = {
+@@ -1226,7 +1226,7 @@ static struct clk_init_data gcc_qupv3_wrap3_qspi_ref_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap3_qspi_ref_clk_src = {
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+index 06b65159f7b4a8..33c7740dd50a70 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+@@ -672,6 +672,9 @@ static int smu_v14_0_2_set_default_dpm_table(struct smu_context *smu)
+ pcie_table->clk_freq[pcie_table->num_of_link_levels] =
+ skutable->LclkFreq[link_level];
+ pcie_table->num_of_link_levels++;
++
++ if (link_level == 0)
++ link_level++;
+ }
+
+ return 0;
+diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+index fe46b0ebefea37..e5eb5d672bcd7d 100644
+--- a/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
++++ b/drivers/gpu/drm/arm/display/komeda/komeda_kms.c
+@@ -160,6 +160,7 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc,
+ struct drm_plane *plane;
+ struct list_head zorder_list;
+ int order = 0, err;
++ u32 slave_zpos = 0;
+
+ DRM_DEBUG_ATOMIC("[CRTC:%d:%s] calculating normalized zpos values\n",
+ crtc->base.id, crtc->name);
+@@ -199,10 +200,13 @@ static int komeda_crtc_normalize_zpos(struct drm_crtc *crtc,
+ plane_st->zpos, plane_st->normalized_zpos);
+
+ /* calculate max slave zorder */
+- if (has_bit(drm_plane_index(plane), kcrtc->slave_planes))
++ if (has_bit(drm_plane_index(plane), kcrtc->slave_planes)) {
++ slave_zpos = plane_st->normalized_zpos;
++ if (to_kplane_st(plane_st)->layer_split)
++ slave_zpos++;
+ kcrtc_st->max_slave_zorder =
+- max(plane_st->normalized_zpos,
+- kcrtc_st->max_slave_zorder);
++ max(slave_zpos, kcrtc_st->max_slave_zorder);
++ }
+ }
+
+ crtc_st->zpos_changed = true;
+diff --git a/drivers/gpu/drm/drm_drv.c b/drivers/gpu/drm/drm_drv.c
+index 535b624d4c9da9..928824b9194568 100644
+--- a/drivers/gpu/drm/drm_drv.c
++++ b/drivers/gpu/drm/drm_drv.c
+@@ -34,6 +34,7 @@
+ #include <linux/pseudo_fs.h>
+ #include <linux/slab.h>
+ #include <linux/srcu.h>
++#include <linux/xarray.h>
+
+ #include <drm/drm_accel.h>
+ #include <drm/drm_cache.h>
+@@ -54,8 +55,7 @@ MODULE_AUTHOR("Gareth Hughes, Leif Delgass, José Fonseca, Jon Smirl");
+ MODULE_DESCRIPTION("DRM shared core routines");
+ MODULE_LICENSE("GPL and additional rights");
+
+-static DEFINE_SPINLOCK(drm_minor_lock);
+-static struct idr drm_minors_idr;
++DEFINE_XARRAY_ALLOC(drm_minors_xa);
+
+ /*
+ * If the drm core fails to init for whatever reason,
+@@ -83,6 +83,18 @@ DEFINE_STATIC_SRCU(drm_unplug_srcu);
+ * registered and unregistered dynamically according to device-state.
+ */
+
++static struct xarray *drm_minor_get_xa(enum drm_minor_type type)
++{
++ if (type == DRM_MINOR_PRIMARY || type == DRM_MINOR_RENDER)
++ return &drm_minors_xa;
++#if IS_ENABLED(CONFIG_DRM_ACCEL)
++ else if (type == DRM_MINOR_ACCEL)
++ return &accel_minors_xa;
++#endif
++ else
++ return ERR_PTR(-EOPNOTSUPP);
++}
++
+ static struct drm_minor **drm_minor_get_slot(struct drm_device *dev,
+ enum drm_minor_type type)
+ {
+@@ -101,25 +113,31 @@ static struct drm_minor **drm_minor_get_slot(struct drm_device *dev,
+ static void drm_minor_alloc_release(struct drm_device *dev, void *data)
+ {
+ struct drm_minor *minor = data;
+- unsigned long flags;
+
+ WARN_ON(dev != minor->dev);
+
+ put_device(minor->kdev);
+
+- if (minor->type == DRM_MINOR_ACCEL) {
+- accel_minor_remove(minor->index);
+- } else {
+- spin_lock_irqsave(&drm_minor_lock, flags);
+- idr_remove(&drm_minors_idr, minor->index);
+- spin_unlock_irqrestore(&drm_minor_lock, flags);
+- }
++ xa_erase(drm_minor_get_xa(minor->type), minor->index);
+ }
+
++/*
++ * DRM used to support 64 devices, for backwards compatibility we need to maintain the
++ * minor allocation scheme where minors 0-63 are primary nodes, 64-127 are control nodes,
++ * and 128-191 are render nodes.
++ * After reaching the limit, we're allocating minors dynamically - first-come, first-serve.
++ * Accel nodes are using a distinct major, so the minors are allocated in continuous 0-MAX
++ * range.
++ */
++#define DRM_MINOR_LIMIT(t) ({ \
++ typeof(t) _t = (t); \
++ _t == DRM_MINOR_ACCEL ? XA_LIMIT(0, ACCEL_MAX_MINORS) : XA_LIMIT(64 * _t, 64 * _t + 63); \
++})
++#define DRM_EXTENDED_MINOR_LIMIT XA_LIMIT(192, (1 << MINORBITS) - 1)
++
+ static int drm_minor_alloc(struct drm_device *dev, enum drm_minor_type type)
+ {
+ struct drm_minor *minor;
+- unsigned long flags;
+ int r;
+
+ minor = drmm_kzalloc(dev, sizeof(*minor), GFP_KERNEL);
+@@ -129,25 +147,14 @@ static int drm_minor_alloc(struct drm_device *dev, enum drm_minor_type type)
+ minor->type = type;
+ minor->dev = dev;
+
+- idr_preload(GFP_KERNEL);
+- if (type == DRM_MINOR_ACCEL) {
+- r = accel_minor_alloc();
+- } else {
+- spin_lock_irqsave(&drm_minor_lock, flags);
+- r = idr_alloc(&drm_minors_idr,
+- NULL,
+- 64 * type,
+- 64 * (type + 1),
+- GFP_NOWAIT);
+- spin_unlock_irqrestore(&drm_minor_lock, flags);
+- }
+- idr_preload_end();
+-
++ r = xa_alloc(drm_minor_get_xa(type), &minor->index,
++ NULL, DRM_MINOR_LIMIT(type), GFP_KERNEL);
++ if (r == -EBUSY && (type == DRM_MINOR_PRIMARY || type == DRM_MINOR_RENDER))
++ r = xa_alloc(&drm_minors_xa, &minor->index,
++ NULL, DRM_EXTENDED_MINOR_LIMIT, GFP_KERNEL);
+ if (r < 0)
+ return r;
+
+- minor->index = r;
+-
+ r = drmm_add_action_or_reset(dev, drm_minor_alloc_release, minor);
+ if (r)
+ return r;
+@@ -163,7 +170,7 @@ static int drm_minor_alloc(struct drm_device *dev, enum drm_minor_type type)
+ static int drm_minor_register(struct drm_device *dev, enum drm_minor_type type)
+ {
+ struct drm_minor *minor;
+- unsigned long flags;
++ void *entry;
+ int ret;
+
+ DRM_DEBUG("\n");
+@@ -186,13 +193,12 @@ static int drm_minor_register(struct drm_device *dev, enum drm_minor_type type)
+ goto err_debugfs;
+
+ /* replace NULL with @minor so lookups will succeed from now on */
+- if (minor->type == DRM_MINOR_ACCEL) {
+- accel_minor_replace(minor, minor->index);
+- } else {
+- spin_lock_irqsave(&drm_minor_lock, flags);
+- idr_replace(&drm_minors_idr, minor, minor->index);
+- spin_unlock_irqrestore(&drm_minor_lock, flags);
++ entry = xa_store(drm_minor_get_xa(type), minor->index, minor, GFP_KERNEL);
++ if (xa_is_err(entry)) {
++ ret = xa_err(entry);
++ goto err_debugfs;
+ }
++ WARN_ON(entry);
+
+ DRM_DEBUG("new minor registered %d\n", minor->index);
+ return 0;
+@@ -205,20 +211,13 @@ static int drm_minor_register(struct drm_device *dev, enum drm_minor_type type)
+ static void drm_minor_unregister(struct drm_device *dev, enum drm_minor_type type)
+ {
+ struct drm_minor *minor;
+- unsigned long flags;
+
+ minor = *drm_minor_get_slot(dev, type);
+ if (!minor || !device_is_registered(minor->kdev))
+ return;
+
+ /* replace @minor with NULL so lookups will fail from now on */
+- if (minor->type == DRM_MINOR_ACCEL) {
+- accel_minor_replace(NULL, minor->index);
+- } else {
+- spin_lock_irqsave(&drm_minor_lock, flags);
+- idr_replace(&drm_minors_idr, NULL, minor->index);
+- spin_unlock_irqrestore(&drm_minor_lock, flags);
+- }
++ xa_store(drm_minor_get_xa(type), minor->index, NULL, GFP_KERNEL);
+
+ device_del(minor->kdev);
+ dev_set_drvdata(minor->kdev, NULL); /* safety belt */
+@@ -234,16 +233,15 @@ static void drm_minor_unregister(struct drm_device *dev, enum drm_minor_type typ
+ * minor->dev pointer will stay valid! However, the device may get unplugged and
+ * unregistered while you hold the minor.
+ */
+-struct drm_minor *drm_minor_acquire(unsigned int minor_id)
++struct drm_minor *drm_minor_acquire(struct xarray *minor_xa, unsigned int minor_id)
+ {
+ struct drm_minor *minor;
+- unsigned long flags;
+
+- spin_lock_irqsave(&drm_minor_lock, flags);
+- minor = idr_find(&drm_minors_idr, minor_id);
++ xa_lock(minor_xa);
++ minor = xa_load(minor_xa, minor_id);
+ if (minor)
+ drm_dev_get(minor->dev);
+- spin_unlock_irqrestore(&drm_minor_lock, flags);
++ xa_unlock(minor_xa);
+
+ if (!minor) {
+ return ERR_PTR(-ENODEV);
+@@ -1036,7 +1034,7 @@ static int drm_stub_open(struct inode *inode, struct file *filp)
+
+ DRM_DEBUG("\n");
+
+- minor = drm_minor_acquire(iminor(inode));
++ minor = drm_minor_acquire(&drm_minors_xa, iminor(inode));
+ if (IS_ERR(minor))
+ return PTR_ERR(minor);
+
+@@ -1071,7 +1069,7 @@ static void drm_core_exit(void)
+ unregister_chrdev(DRM_MAJOR, "drm");
+ debugfs_remove(drm_debugfs_root);
+ drm_sysfs_destroy();
+- idr_destroy(&drm_minors_idr);
++ WARN_ON(!xa_empty(&drm_minors_xa));
+ drm_connector_ida_destroy();
+ }
+
+@@ -1080,7 +1078,6 @@ static int __init drm_core_init(void)
+ int ret;
+
+ drm_connector_ida_init();
+- idr_init(&drm_minors_idr);
+ drm_memcpy_init_early();
+
+ ret = drm_sysfs_init();
+diff --git a/drivers/gpu/drm/drm_file.c b/drivers/gpu/drm/drm_file.c
+index 714e42b0510800..f917b259b33421 100644
+--- a/drivers/gpu/drm/drm_file.c
++++ b/drivers/gpu/drm/drm_file.c
+@@ -364,7 +364,7 @@ int drm_open(struct inode *inode, struct file *filp)
+ struct drm_minor *minor;
+ int retcode;
+
+- minor = drm_minor_acquire(iminor(inode));
++ minor = drm_minor_acquire(&drm_minors_xa, iminor(inode));
+ if (IS_ERR(minor))
+ return PTR_ERR(minor);
+
+diff --git a/drivers/gpu/drm/drm_internal.h b/drivers/gpu/drm/drm_internal.h
+index 690505a1f7a5db..12acf44c4e2400 100644
+--- a/drivers/gpu/drm/drm_internal.h
++++ b/drivers/gpu/drm/drm_internal.h
+@@ -81,10 +81,6 @@ void drm_prime_destroy_file_private(struct drm_prime_file_private *prime_fpriv);
+ void drm_prime_remove_buf_handle(struct drm_prime_file_private *prime_fpriv,
+ uint32_t handle);
+
+-/* drm_drv.c */
+-struct drm_minor *drm_minor_acquire(unsigned int minor_id);
+-void drm_minor_release(struct drm_minor *minor);
+-
+ /* drm_managed.c */
+ void drm_managed_release(struct drm_device *dev);
+ void drmm_add_final_kfree(struct drm_device *dev, void *container);
+diff --git a/drivers/hwmon/asus-ec-sensors.c b/drivers/hwmon/asus-ec-sensors.c
+index 36f9e38000d5ef..3b3b8beed83a51 100644
+--- a/drivers/hwmon/asus-ec-sensors.c
++++ b/drivers/hwmon/asus-ec-sensors.c
+@@ -412,7 +412,7 @@ static const struct ec_board_info board_info_strix_b550_i_gaming = {
+
+ static const struct ec_board_info board_info_strix_x570_e_gaming = {
+ .sensors = SENSOR_SET_TEMP_CHIPSET_CPU_MB |
+- SENSOR_TEMP_T_SENSOR | SENSOR_TEMP_VRM |
++ SENSOR_TEMP_T_SENSOR |
+ SENSOR_FAN_CHIPSET | SENSOR_CURR_CPU |
+ SENSOR_IN_CPU_CORE,
+ .mutex_path = ASUS_HW_ACCESS_MUTEX_ASMX,
+diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
+index e4f0a382c21652..ddde067f593fcf 100644
+--- a/drivers/net/can/m_can/m_can.c
++++ b/drivers/net/can/m_can/m_can.c
+@@ -2141,7 +2141,7 @@ static int m_can_set_coalesce(struct net_device *dev,
+ return 0;
+ }
+
+-static const struct ethtool_ops m_can_ethtool_ops = {
++static const struct ethtool_ops m_can_ethtool_ops_coalescing = {
+ .supported_coalesce_params = ETHTOOL_COALESCE_RX_USECS_IRQ |
+ ETHTOOL_COALESCE_RX_MAX_FRAMES_IRQ |
+ ETHTOOL_COALESCE_TX_USECS_IRQ |
+@@ -2152,18 +2152,20 @@ static const struct ethtool_ops m_can_ethtool_ops = {
+ .set_coalesce = m_can_set_coalesce,
+ };
+
+-static const struct ethtool_ops m_can_ethtool_ops_polling = {
++static const struct ethtool_ops m_can_ethtool_ops = {
+ .get_ts_info = ethtool_op_get_ts_info,
+ };
+
+-static int register_m_can_dev(struct net_device *dev)
++static int register_m_can_dev(struct m_can_classdev *cdev)
+ {
++ struct net_device *dev = cdev->net;
++
+ dev->flags |= IFF_ECHO; /* we support local echo */
+ dev->netdev_ops = &m_can_netdev_ops;
+- if (dev->irq)
+- dev->ethtool_ops = &m_can_ethtool_ops;
++ if (dev->irq && cdev->is_peripheral)
++ dev->ethtool_ops = &m_can_ethtool_ops_coalescing;
+ else
+- dev->ethtool_ops = &m_can_ethtool_ops_polling;
++ dev->ethtool_ops = &m_can_ethtool_ops;
+
+ return register_candev(dev);
+ }
+@@ -2349,7 +2351,7 @@ int m_can_class_register(struct m_can_classdev *cdev)
+ if (ret)
+ goto rx_offload_del;
+
+- ret = register_m_can_dev(cdev->net);
++ ret = register_m_can_dev(cdev);
+ if (ret) {
+ dev_err(cdev->dev, "registering %s failed (err=%d)\n",
+ cdev->net->name, ret);
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+index f1e6007b74cec7..262c6c7002860c 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+@@ -744,6 +744,7 @@ static void mcp251xfd_chip_stop(struct mcp251xfd_priv *priv,
+
+ mcp251xfd_chip_interrupts_disable(priv);
+ mcp251xfd_chip_rx_int_disable(priv);
++ mcp251xfd_timestamp_stop(priv);
+ mcp251xfd_chip_sleep(priv);
+ }
+
+@@ -763,6 +764,8 @@ static int mcp251xfd_chip_start(struct mcp251xfd_priv *priv)
+ if (err)
+ goto out_chip_stop;
+
++ mcp251xfd_timestamp_start(priv);
++
+ err = mcp251xfd_set_bittiming(priv);
+ if (err)
+ goto out_chip_stop;
+@@ -791,7 +794,7 @@ static int mcp251xfd_chip_start(struct mcp251xfd_priv *priv)
+
+ return 0;
+
+- out_chip_stop:
++out_chip_stop:
+ mcp251xfd_dump(priv);
+ mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
+
+@@ -1576,7 +1579,7 @@ static irqreturn_t mcp251xfd_irq(int irq, void *dev_id)
+ handled = IRQ_HANDLED;
+ } while (1);
+
+- out_fail:
++out_fail:
+ can_rx_offload_threaded_irq_finish(&priv->offload);
+
+ netdev_err(priv->ndev, "IRQ handler returned %d (intf=0x%08x).\n",
+@@ -1610,11 +1613,12 @@ static int mcp251xfd_open(struct net_device *ndev)
+ if (err)
+ goto out_mcp251xfd_ring_free;
+
++ mcp251xfd_timestamp_init(priv);
++
+ err = mcp251xfd_chip_start(priv);
+ if (err)
+ goto out_transceiver_disable;
+
+- mcp251xfd_timestamp_init(priv);
+ clear_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
+ can_rx_offload_enable(&priv->offload);
+
+@@ -1641,22 +1645,21 @@ static int mcp251xfd_open(struct net_device *ndev)
+
+ return 0;
+
+- out_free_irq:
++out_free_irq:
+ free_irq(spi->irq, priv);
+- out_destroy_workqueue:
++out_destroy_workqueue:
+ destroy_workqueue(priv->wq);
+- out_can_rx_offload_disable:
++out_can_rx_offload_disable:
+ can_rx_offload_disable(&priv->offload);
+ set_bit(MCP251XFD_FLAGS_DOWN, priv->flags);
+- mcp251xfd_timestamp_stop(priv);
+- out_transceiver_disable:
++out_transceiver_disable:
+ mcp251xfd_transceiver_disable(priv);
+- out_mcp251xfd_ring_free:
++out_mcp251xfd_ring_free:
+ mcp251xfd_ring_free(priv);
+- out_pm_runtime_put:
++out_pm_runtime_put:
+ mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
+ pm_runtime_put(ndev->dev.parent);
+- out_close_candev:
++out_close_candev:
+ close_candev(ndev);
+
+ return err;
+@@ -1674,7 +1677,6 @@ static int mcp251xfd_stop(struct net_device *ndev)
+ free_irq(ndev->irq, priv);
+ destroy_workqueue(priv->wq);
+ can_rx_offload_disable(&priv->offload);
+- mcp251xfd_timestamp_stop(priv);
+ mcp251xfd_chip_stop(priv, CAN_STATE_STOPPED);
+ mcp251xfd_transceiver_disable(priv);
+ mcp251xfd_ring_free(priv);
+@@ -1820,9 +1822,9 @@ mcp251xfd_register_get_dev_id(const struct mcp251xfd_priv *priv, u32 *dev_id,
+ *effective_speed_hz_slow = xfer[0].effective_speed_hz;
+ *effective_speed_hz_fast = xfer[1].effective_speed_hz;
+
+- out_kfree_buf_tx:
++out_kfree_buf_tx:
+ kfree(buf_tx);
+- out_kfree_buf_rx:
++out_kfree_buf_rx:
+ kfree(buf_rx);
+
+ return err;
+@@ -1936,13 +1938,13 @@ static int mcp251xfd_register(struct mcp251xfd_priv *priv)
+
+ return 0;
+
+- out_unregister_candev:
++out_unregister_candev:
+ unregister_candev(ndev);
+- out_chip_sleep:
++out_chip_sleep:
+ mcp251xfd_chip_sleep(priv);
+- out_runtime_disable:
++out_runtime_disable:
+ pm_runtime_disable(ndev->dev.parent);
+- out_runtime_put_noidle:
++out_runtime_put_noidle:
+ pm_runtime_put_noidle(ndev->dev.parent);
+ mcp251xfd_clks_and_vdd_disable(priv);
+
+@@ -2162,9 +2164,9 @@ static int mcp251xfd_probe(struct spi_device *spi)
+
+ return 0;
+
+- out_can_rx_offload_del:
++out_can_rx_offload_del:
+ can_rx_offload_del(&priv->offload);
+- out_free_candev:
++out_free_candev:
+ spi->max_speed_hz = priv->spi_max_speed_hz_orig;
+
+ free_candev(ndev);
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-dump.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-dump.c
+index 004eaf96262bfd..050321345304be 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-dump.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-dump.c
+@@ -94,7 +94,7 @@ static void mcp251xfd_dump_registers(const struct mcp251xfd_priv *priv,
+ kfree(buf);
+ }
+
+- out:
++out:
+ mcp251xfd_dump_header(iter, MCP251XFD_DUMP_OBJECT_TYPE_REG, reg);
+ }
+
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
+index 92b7bc7f14b9eb..65150e76200720 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-regmap.c
+@@ -397,7 +397,7 @@ mcp251xfd_regmap_crc_read(void *context,
+
+ return err;
+ }
+- out:
++out:
+ memcpy(val_buf, buf_rx->data, val_len);
+
+ return 0;
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+index f72582d4d3e8e2..83c18035b2a24d 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+@@ -290,7 +290,7 @@ int mcp251xfd_ring_init(struct mcp251xfd_priv *priv)
+ const struct mcp251xfd_rx_ring *rx_ring;
+ u16 base = 0, ram_used;
+ u8 fifo_nr = 1;
+- int i;
++ int err = 0, i;
+
+ netdev_reset_queue(priv->ndev);
+
+@@ -386,10 +386,18 @@ int mcp251xfd_ring_init(struct mcp251xfd_priv *priv)
+ netdev_err(priv->ndev,
+ "Error during ring configuration, using more RAM (%u bytes) than available (%u bytes).\n",
+ ram_used, MCP251XFD_RAM_SIZE);
+- return -ENOMEM;
++ err = -ENOMEM;
+ }
+
+- return 0;
++ if (priv->tx_obj_num_coalesce_irq &&
++ priv->tx_obj_num_coalesce_irq * 2 != priv->tx->obj_num) {
++ netdev_err(priv->ndev,
++ "Error during ring configuration, number of TEF coalescing buffers (%u) must be half of TEF buffers (%u).\n",
++ priv->tx_obj_num_coalesce_irq, priv->tx->obj_num);
++ err = -EINVAL;
++ }
++
++ return err;
+ }
+
+ void mcp251xfd_ring_free(struct mcp251xfd_priv *priv)
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+index 3886476a8f8efb..f732556d233a7b 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+@@ -219,7 +219,7 @@ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
+ total_frame_len += frame_len;
+ }
+
+- out_netif_wake_queue:
++out_netif_wake_queue:
+ len = i; /* number of handled goods TEFs */
+ if (len) {
+ struct mcp251xfd_tef_ring *ring = priv->tef;
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
+index 1db99aabe85c56..202ca0d24d03b9 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
+@@ -48,9 +48,12 @@ void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv)
+ cc->shift = 1;
+ cc->mult = clocksource_hz2mult(priv->can.clock.freq, cc->shift);
+
+- timecounter_init(&priv->tc, &priv->cc, ktime_get_real_ns());
+-
+ INIT_DELAYED_WORK(&priv->timestamp, mcp251xfd_timestamp_work);
++}
++
++void mcp251xfd_timestamp_start(struct mcp251xfd_priv *priv)
++{
++ timecounter_init(&priv->tc, &priv->cc, ktime_get_real_ns());
+ schedule_delayed_work(&priv->timestamp,
+ MCP251XFD_TIMESTAMP_WORK_DELAY_SEC * HZ);
+ }
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+index 991662fbba42e8..dcbbd2b2fae827 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+@@ -957,6 +957,7 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv);
+ int mcp251xfd_handle_rxif(struct mcp251xfd_priv *priv);
+ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv);
+ void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv);
++void mcp251xfd_timestamp_start(struct mcp251xfd_priv *priv);
+ void mcp251xfd_timestamp_stop(struct mcp251xfd_priv *priv);
+
+ void mcp251xfd_tx_obj_write_sync(struct work_struct *work);
+diff --git a/drivers/net/ethernet/faraday/ftgmac100.c b/drivers/net/ethernet/faraday/ftgmac100.c
+index fddfd1dd50709f..4c546c3aef0fec 100644
+--- a/drivers/net/ethernet/faraday/ftgmac100.c
++++ b/drivers/net/ethernet/faraday/ftgmac100.c
+@@ -572,7 +572,7 @@ static bool ftgmac100_rx_packet(struct ftgmac100 *priv, int *processed)
+ (*processed)++;
+ return true;
+
+- drop:
++drop:
+ /* Clean rxdes0 (which resets own bit) */
+ rxdes->rxdes0 = cpu_to_le32(status & priv->rxdes0_edorr_mask);
+ priv->rx_pointer = ftgmac100_next_rx_pointer(priv, pointer);
+@@ -656,6 +656,11 @@ static bool ftgmac100_tx_complete_packet(struct ftgmac100 *priv)
+ ftgmac100_free_tx_packet(priv, pointer, skb, txdes, ctl_stat);
+ txdes->txdes0 = cpu_to_le32(ctl_stat & priv->txdes0_edotr_mask);
+
++ /* Ensure the descriptor config is visible before setting the tx
++ * pointer.
++ */
++ smp_wmb();
++
+ priv->tx_clean_pointer = ftgmac100_next_tx_pointer(priv, pointer);
+
+ return true;
+@@ -809,6 +814,11 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
+ dma_wmb();
+ first->txdes0 = cpu_to_le32(f_ctl_stat);
+
++ /* Ensure the descriptor config is visible before setting the tx
++ * pointer.
++ */
++ smp_wmb();
++
+ /* Update next TX pointer */
+ priv->tx_pointer = pointer;
+
+@@ -829,7 +839,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
+
+ return NETDEV_TX_OK;
+
+- dma_err:
++dma_err:
+ if (net_ratelimit())
+ netdev_err(netdev, "map tx fragment failed\n");
+
+@@ -851,7 +861,7 @@ static netdev_tx_t ftgmac100_hard_start_xmit(struct sk_buff *skb,
+ * last fragment, so we know ftgmac100_free_tx_packet()
+ * hasn't freed the skb yet.
+ */
+- drop:
++drop:
+ /* Drop the packet */
+ dev_kfree_skb_any(skb);
+ netdev->stats.tx_dropped++;
+@@ -1344,7 +1354,7 @@ static void ftgmac100_reset(struct ftgmac100 *priv)
+ ftgmac100_init_all(priv, true);
+
+ netdev_dbg(netdev, "Reset done !\n");
+- bail:
++bail:
+ if (priv->mii_bus)
+ mutex_unlock(&priv->mii_bus->mdio_lock);
+ if (netdev->phydev)
+@@ -1543,15 +1553,15 @@ static int ftgmac100_open(struct net_device *netdev)
+
+ return 0;
+
+- err_ncsi:
++err_ncsi:
+ napi_disable(&priv->napi);
+ netif_stop_queue(netdev);
+- err_alloc:
++err_alloc:
+ ftgmac100_free_buffers(priv);
+ free_irq(netdev->irq, netdev);
+- err_irq:
++err_irq:
+ netif_napi_del(&priv->napi);
+- err_hw:
++err_hw:
+ iowrite32(0, priv->base + FTGMAC100_OFFSET_IER);
+ ftgmac100_free_rings(priv);
+ return err;
+diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
+index c2ba586593475c..a3ee7697edb562 100644
+--- a/drivers/net/ethernet/intel/ice/ice_lib.c
++++ b/drivers/net/ethernet/intel/ice/ice_lib.c
+@@ -2419,7 +2419,7 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
+ dev_err(ice_pf_to_dev(pf), "Failed to remove RDMA scheduler config for VSI %u, err %d\n",
+ vsi->vsi_num, err);
+
+- if (ice_is_xdp_ena_vsi(vsi))
++ if (vsi->xdp_rings)
+ /* return value check can be skipped here, it always returns
+ * 0 if reset is in progress
+ */
+@@ -2521,7 +2521,7 @@ static void ice_vsi_release_msix(struct ice_vsi *vsi)
+ for (q = 0; q < q_vector->num_ring_tx; q++) {
+ ice_write_itr(&q_vector->tx, 0);
+ wr32(hw, QINT_TQCTL(vsi->txq_map[txq]), 0);
+- if (ice_is_xdp_ena_vsi(vsi)) {
++ if (vsi->xdp_rings) {
+ u32 xdp_txq = txq + vsi->num_xdp_txq;
+
+ wr32(hw, QINT_TQCTL(vsi->txq_map[xdp_txq]), 0);
+diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
+index 766f9a466bc350..c82715eb5b93cf 100644
+--- a/drivers/net/ethernet/intel/ice/ice_main.c
++++ b/drivers/net/ethernet/intel/ice/ice_main.c
+@@ -7253,7 +7253,7 @@ int ice_down(struct ice_vsi *vsi)
+ if (tx_err)
+ netdev_err(vsi->netdev, "Failed stop Tx rings, VSI %d error %d\n",
+ vsi->vsi_num, tx_err);
+- if (!tx_err && ice_is_xdp_ena_vsi(vsi)) {
++ if (!tx_err && vsi->xdp_rings) {
+ tx_err = ice_vsi_stop_xdp_tx_rings(vsi);
+ if (tx_err)
+ netdev_err(vsi->netdev, "Failed stop XDP rings, VSI %d error %d\n",
+@@ -7270,7 +7270,7 @@ int ice_down(struct ice_vsi *vsi)
+ ice_for_each_txq(vsi, i)
+ ice_clean_tx_ring(vsi->tx_rings[i]);
+
+- if (ice_is_xdp_ena_vsi(vsi))
++ if (vsi->xdp_rings)
+ ice_for_each_xdp_txq(vsi, i)
+ ice_clean_tx_ring(vsi->xdp_rings[i]);
+
+diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
+index 87a5427570d762..5dee829bfc47c5 100644
+--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
++++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
+@@ -39,7 +39,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
+ sizeof(vsi_stat->rx_ring_stats[q_idx]->rx_stats));
+ memset(&vsi_stat->tx_ring_stats[q_idx]->stats, 0,
+ sizeof(vsi_stat->tx_ring_stats[q_idx]->stats));
+- if (ice_is_xdp_ena_vsi(vsi))
++ if (vsi->xdp_rings)
+ memset(&vsi->xdp_rings[q_idx]->ring_stats->stats, 0,
+ sizeof(vsi->xdp_rings[q_idx]->ring_stats->stats));
+ }
+@@ -52,7 +52,7 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
+ static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
+ {
+ ice_clean_tx_ring(vsi->tx_rings[q_idx]);
+- if (ice_is_xdp_ena_vsi(vsi))
++ if (vsi->xdp_rings)
+ ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
+ ice_clean_rx_ring(vsi->rx_rings[q_idx]);
+ }
+@@ -186,7 +186,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+ err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
+ if (!fail)
+ fail = err;
+- if (ice_is_xdp_ena_vsi(vsi)) {
++ if (vsi->xdp_rings) {
+ struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
+
+ memset(&txq_meta, 0, sizeof(txq_meta));
+diff --git a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+index 945ffc083d25c4..79fffa82cfd928 100644
+--- a/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
++++ b/drivers/net/wireless/intel/iwlwifi/fw/dbg.c
+@@ -3352,7 +3352,7 @@ void iwl_fw_dbg_stop_restart_recording(struct iwl_fw_runtime *fwrt,
+ {
+ int ret __maybe_unused = 0;
+
+- if (test_bit(STATUS_FW_ERROR, &fwrt->trans->status))
++ if (!iwl_trans_fw_running(fwrt->trans))
+ return;
+
+ if (fw_has_capa(&fwrt->fw->ucode_capa,
+diff --git a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+index b93cef7b233018..4c56dccb18a9b3 100644
+--- a/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
++++ b/drivers/net/wireless/intel/iwlwifi/iwl-trans.h
+@@ -1579,8 +1579,8 @@ static inline void iwl_trans_fw_error(struct iwl_trans *trans, bool sync)
+
+ /* prevent double restarts due to the same erroneous FW */
+ if (!test_and_set_bit(STATUS_FW_ERROR, &trans->status)) {
+- iwl_op_mode_nic_error(trans->op_mode, sync);
+ trans->state = IWL_TRANS_NO_FW;
++ iwl_op_mode_nic_error(trans->op_mode, sync);
+ }
+ }
+
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+index 259afecd1a98da..83551d962a46c4 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+@@ -5819,6 +5819,10 @@ static void iwl_mvm_flush_no_vif(struct iwl_mvm *mvm, u32 queues, bool drop)
+ int i;
+
+ if (!iwl_mvm_has_new_tx_api(mvm)) {
++ /* we can't ask the firmware anything if it is dead */
++ if (test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
++ &mvm->status))
++ return;
+ if (drop) {
+ mutex_lock(&mvm->mutex);
+ iwl_mvm_flush_tx_path(mvm,
+@@ -5914,8 +5918,11 @@ void iwl_mvm_mac_flush(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+
+ /* this can take a while, and we may need/want other operations
+ * to succeed while doing this, so do it without the mutex held
++ * If the firmware is dead, this can't work...
+ */
+- if (!drop && !iwl_mvm_has_new_tx_api(mvm))
++ if (!drop && !iwl_mvm_has_new_tx_api(mvm) &&
++ !test_bit(IWL_MVM_STATUS_HW_RESTART_REQUESTED,
++ &mvm->status))
+ iwl_trans_wait_tx_queues_empty(mvm->trans, msk);
+ }
+
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+index 498afbe4ee6beb..6375cc3c48f3c9 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+@@ -1521,6 +1521,8 @@ void iwl_mvm_stop_device(struct iwl_mvm *mvm)
+
+ clear_bit(IWL_MVM_STATUS_FIRMWARE_RUNNING, &mvm->status);
+
++ iwl_mvm_pause_tcm(mvm, false);
++
+ iwl_fw_dbg_stop_sync(&mvm->fwrt);
+ iwl_trans_stop_device(mvm->trans);
+ iwl_free_fw_paging(&mvm->fwrt);
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+index 7615c91a55c623..d7c276237c74ea 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+@@ -48,6 +48,8 @@
+ /* Number of iterations on the channel for mei filtered scan */
+ #define IWL_MEI_SCAN_NUM_ITER 5U
+
++#define WFA_TPC_IE_LEN 9
++
+ struct iwl_mvm_scan_timing_params {
+ u32 suspend_time;
+ u32 max_out_time;
+@@ -303,8 +305,8 @@ static int iwl_mvm_max_scan_ie_fw_cmd_room(struct iwl_mvm *mvm)
+
+ max_probe_len = SCAN_OFFLOAD_PROBE_REQ_SIZE;
+
+- /* we create the 802.11 header and SSID element */
+- max_probe_len -= 24 + 2;
++ /* we create the 802.11 header SSID element and WFA TPC element */
++ max_probe_len -= 24 + 2 + WFA_TPC_IE_LEN;
+
+ /* DS parameter set element is added on 2.4GHZ band if required */
+ if (iwl_mvm_rrm_scan_needed(mvm))
+@@ -731,8 +733,6 @@ static u8 *iwl_mvm_copy_and_insert_ds_elem(struct iwl_mvm *mvm, const u8 *ies,
+ return newpos;
+ }
+
+-#define WFA_TPC_IE_LEN 9
+-
+ static void iwl_mvm_add_tpc_report_ie(u8 *pos)
+ {
+ pos[0] = WLAN_EID_VENDOR_SPECIFIC;
+@@ -837,8 +837,8 @@ static inline bool iwl_mvm_scan_fits(struct iwl_mvm *mvm, int n_ssids,
+ return ((n_ssids <= PROBE_OPTION_MAX) &&
+ (n_channels <= mvm->fw->ucode_capa.n_scan_channels) &
+ (ies->common_ie_len +
+- ies->len[NL80211_BAND_2GHZ] +
+- ies->len[NL80211_BAND_5GHZ] <=
++ ies->len[NL80211_BAND_2GHZ] + ies->len[NL80211_BAND_5GHZ] +
++ ies->len[NL80211_BAND_6GHZ] <=
+ iwl_mvm_max_scan_ie_fw_cmd_room(mvm)));
+ }
+
+@@ -3179,18 +3179,16 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
+ params.n_channels = j;
+ }
+
+- if (non_psc_included &&
+- !iwl_mvm_scan_fits(mvm, req->n_ssids, ies, params.n_channels)) {
+- kfree(params.channels);
+- return -ENOBUFS;
++ if (!iwl_mvm_scan_fits(mvm, req->n_ssids, ies, params.n_channels)) {
++ ret = -ENOBUFS;
++ goto out;
+ }
+
+ uid = iwl_mvm_build_scan_cmd(mvm, vif, &hcmd, ¶ms, type);
+-
+- if (non_psc_included)
+- kfree(params.channels);
+- if (uid < 0)
+- return uid;
++ if (uid < 0) {
++ ret = uid;
++ goto out;
++ }
+
+ ret = iwl_mvm_send_cmd(mvm, &hcmd);
+ if (!ret) {
+@@ -3208,6 +3206,9 @@ int iwl_mvm_sched_scan_start(struct iwl_mvm *mvm,
+ mvm->sched_scan_pass_all = SCHED_SCAN_PASS_ALL_DISABLED;
+ }
+
++out:
++ if (non_psc_included)
++ kfree(params.channels);
+ return ret;
+ }
+
+diff --git a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+index ebf11f276b20a1..37f0bc9e0d9639 100644
+--- a/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
++++ b/drivers/net/wireless/intel/iwlwifi/pcie/ctxt-info-gen3.c
+@@ -89,7 +89,8 @@ iwl_pcie_ctxt_info_dbg_enable(struct iwl_trans *trans,
+ }
+ break;
+ default:
+- IWL_ERR(trans, "WRT: Invalid buffer destination\n");
++ IWL_DEBUG_FW(trans, "WRT: Invalid buffer destination (%d)\n",
++ le32_to_cpu(fw_mon_cfg->buf_location));
+ }
+ out:
+ if (dbg_flags)
+diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
+index 5e66bcb34d530c..ff1769172778be 100644
+--- a/drivers/nvme/host/nvme.h
++++ b/drivers/nvme/host/nvme.h
+@@ -89,6 +89,11 @@ enum nvme_quirks {
+ */
+ NVME_QUIRK_NO_DEEPEST_PS = (1 << 5),
+
++ /*
++ * Problems seen with concurrent commands
++ */
++ NVME_QUIRK_QDEPTH_ONE = (1 << 6),
++
+ /*
+ * Set MEDIUM priority on SQ creation
+ */
+diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
+index 18d85575cdb482..fde4073fa418ed 100644
+--- a/drivers/nvme/host/pci.c
++++ b/drivers/nvme/host/pci.c
+@@ -2528,15 +2528,8 @@ static int nvme_pci_enable(struct nvme_dev *dev)
+ else
+ dev->io_sqes = NVME_NVM_IOSQES;
+
+- /*
+- * Temporary fix for the Apple controller found in the MacBook8,1 and
+- * some MacBook7,1 to avoid controller resets and data loss.
+- */
+- if (pdev->vendor == PCI_VENDOR_ID_APPLE && pdev->device == 0x2001) {
++ if (dev->ctrl.quirks & NVME_QUIRK_QDEPTH_ONE) {
+ dev->q_depth = 2;
+- dev_warn(dev->ctrl.device, "detected Apple NVMe controller, "
+- "set queue depth=%u to work around controller resets\n",
+- dev->q_depth);
+ } else if (pdev->vendor == PCI_VENDOR_ID_SAMSUNG &&
+ (pdev->device == 0xa821 || pdev->device == 0xa822) &&
+ NVME_CAP_MQES(dev->ctrl.cap) == 0) {
+@@ -3401,6 +3394,8 @@ static const struct pci_device_id nvme_id_table[] = {
+ NVME_QUIRK_BOGUS_NID, },
+ { PCI_VDEVICE(REDHAT, 0x0010), /* Qemu emulated controller */
+ .driver_data = NVME_QUIRK_BOGUS_NID, },
++ { PCI_DEVICE(0x1217, 0x8760), /* O2 Micro 64GB Steam Deck */
++ .driver_data = NVME_QUIRK_QDEPTH_ONE },
+ { PCI_DEVICE(0x126f, 0x2262), /* Silicon Motion generic */
+ .driver_data = NVME_QUIRK_NO_DEEPEST_PS |
+ NVME_QUIRK_BOGUS_NID, },
+@@ -3535,7 +3530,12 @@ static const struct pci_device_id nvme_id_table[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMAZON, 0xcd02),
+ .driver_data = NVME_QUIRK_DMA_ADDRESS_BITS_48, },
+ { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2001),
+- .driver_data = NVME_QUIRK_SINGLE_VECTOR },
++ /*
++ * Fix for the Apple controller found in the MacBook8,1 and
++ * some MacBook7,1 to avoid controller resets and data loss.
++ */
++ .driver_data = NVME_QUIRK_SINGLE_VECTOR |
++ NVME_QUIRK_QDEPTH_ONE },
+ { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2003) },
+ { PCI_DEVICE(PCI_VENDOR_ID_APPLE, 0x2005),
+ .driver_data = NVME_QUIRK_SINGLE_VECTOR |
+diff --git a/drivers/pinctrl/pinctrl-at91.c b/drivers/pinctrl/pinctrl-at91.c
+index 5aa9d5c533c6a9..d7b66928a4e50d 100644
+--- a/drivers/pinctrl/pinctrl-at91.c
++++ b/drivers/pinctrl/pinctrl-at91.c
+@@ -1409,8 +1409,11 @@ static int at91_pinctrl_probe(struct platform_device *pdev)
+
+ /* We will handle a range of GPIO pins */
+ for (i = 0; i < gpio_banks; i++)
+- if (gpio_chips[i])
++ if (gpio_chips[i]) {
+ pinctrl_add_gpio_range(info->pctl, &gpio_chips[i]->range);
++ gpiochip_add_pin_range(&gpio_chips[i]->chip, dev_name(info->pctl->dev), 0,
++ gpio_chips[i]->range.pin_base, gpio_chips[i]->range.npins);
++ }
+
+ dev_info(dev, "initialized AT91 pinctrl driver\n");
+
+diff --git a/drivers/platform/x86/amd/pmf/pmf-quirks.c b/drivers/platform/x86/amd/pmf/pmf-quirks.c
+index 460444cda1b295..48870ca52b4139 100644
+--- a/drivers/platform/x86/amd/pmf/pmf-quirks.c
++++ b/drivers/platform/x86/amd/pmf/pmf-quirks.c
+@@ -25,7 +25,7 @@ static const struct dmi_system_id fwbug_list[] = {
+ .ident = "ROG Zephyrus G14",
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
+- DMI_MATCH(DMI_PRODUCT_NAME, "GA403UV"),
++ DMI_MATCH(DMI_PRODUCT_NAME, "GA403U"),
+ },
+ .driver_data = &quirk_no_sps_bug,
+ },
+diff --git a/drivers/platform/x86/asus-nb-wmi.c b/drivers/platform/x86/asus-nb-wmi.c
+index fceffe2082ec58..ed3633c5955d9f 100644
+--- a/drivers/platform/x86/asus-nb-wmi.c
++++ b/drivers/platform/x86/asus-nb-wmi.c
+@@ -145,6 +145,10 @@ static struct quirk_entry quirk_asus_ignore_fan = {
+ .wmi_ignore_fan = true,
+ };
+
++static struct quirk_entry quirk_asus_zenbook_duo_kbd = {
++ .ignore_key_wlan = true,
++};
++
+ static int dmi_matched(const struct dmi_system_id *dmi)
+ {
+ pr_info("Identified laptop model '%s'\n", dmi->ident);
+@@ -516,6 +520,15 @@ static const struct dmi_system_id asus_quirks[] = {
+ },
+ .driver_data = &quirk_asus_ignore_fan,
+ },
++ {
++ .callback = dmi_matched,
++ .ident = "ASUS Zenbook Duo UX8406MA",
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
++ DMI_MATCH(DMI_PRODUCT_NAME, "UX8406MA"),
++ },
++ .driver_data = &quirk_asus_zenbook_duo_kbd,
++ },
+ {},
+ };
+
+@@ -630,7 +643,12 @@ static void asus_nb_wmi_key_filter(struct asus_wmi_driver *asus_wmi, int *code,
+ case 0x32: /* Volume Mute */
+ if (atkbd_reports_vol_keys)
+ *code = ASUS_WMI_KEY_IGNORE;
+-
++ break;
++ case 0x5D: /* Wireless console Toggle */
++ case 0x5E: /* Wireless console Enable */
++ case 0x5F: /* Wireless console Disable */
++ if (quirks->ignore_key_wlan)
++ *code = ASUS_WMI_KEY_IGNORE;
+ break;
+ }
+ }
+diff --git a/drivers/platform/x86/asus-wmi.h b/drivers/platform/x86/asus-wmi.h
+index cc30f185384723..d02f15fd3482fa 100644
+--- a/drivers/platform/x86/asus-wmi.h
++++ b/drivers/platform/x86/asus-wmi.h
+@@ -40,6 +40,7 @@ struct quirk_entry {
+ bool wmi_force_als_set;
+ bool wmi_ignore_fan;
+ bool filter_i8042_e1_extended_codes;
++ bool ignore_key_wlan;
+ enum asus_wmi_tablet_switch_mode tablet_switch_mode;
+ int wapf;
+ /*
+diff --git a/drivers/platform/x86/x86-android-tablets/dmi.c b/drivers/platform/x86/x86-android-tablets/dmi.c
+index 141a2d25e83be6..387dd092c4dd01 100644
+--- a/drivers/platform/x86/x86-android-tablets/dmi.c
++++ b/drivers/platform/x86/x86-android-tablets/dmi.c
+@@ -140,7 +140,6 @@ const struct dmi_system_id x86_android_tablet_ids[] __initconst = {
+ /* Lenovo Yoga Tab 3 Pro YT3-X90F */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+- DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
+ },
+ .driver_data = (void *)&lenovo_yt3_info,
+diff --git a/drivers/powercap/intel_rapl_common.c b/drivers/powercap/intel_rapl_common.c
+index aac0744011a3aa..8e7f4c0473ab94 100644
+--- a/drivers/powercap/intel_rapl_common.c
++++ b/drivers/powercap/intel_rapl_common.c
+@@ -1285,6 +1285,7 @@ static const struct x86_cpu_id rapl_ids[] __initconst = {
+
+ X86_MATCH_VENDOR_FAM(AMD, 0x17, &rapl_defaults_amd),
+ X86_MATCH_VENDOR_FAM(AMD, 0x19, &rapl_defaults_amd),
++ X86_MATCH_VENDOR_FAM(AMD, 0x1A, &rapl_defaults_amd),
+ X86_MATCH_VENDOR_FAM(HYGON, 0x18, &rapl_defaults_amd),
+ {}
+ };
+@@ -2128,6 +2129,21 @@ void rapl_remove_package(struct rapl_package *rp)
+ }
+ EXPORT_SYMBOL_GPL(rapl_remove_package);
+
++/*
++ * RAPL Package energy counter scope:
++ * 1. AMD/HYGON platforms use per-PKG package energy counter
++ * 2. For Intel platforms
++ * 2.1 CLX-AP platform has per-DIE package energy counter
++ * 2.2 Other platforms that uses MSR RAPL are single die systems so the
++ * package energy counter can be considered as per-PKG/per-DIE,
++ * here it is considered as per-DIE.
++ * 2.3 New platforms that use TPMI RAPL doesn't care about the
++ * scope because they are not MSR/CPU based.
++ */
++#define rapl_msrs_are_pkg_scope() \
++ (boot_cpu_data.x86_vendor == X86_VENDOR_AMD || \
++ boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
++
+ /* caller to ensure CPU hotplug lock is held */
+ struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_priv *priv,
+ bool id_is_cpu)
+@@ -2135,8 +2151,14 @@ struct rapl_package *rapl_find_package_domain_cpuslocked(int id, struct rapl_if_
+ struct rapl_package *rp;
+ int uid;
+
+- if (id_is_cpu)
+- uid = topology_logical_die_id(id);
++ if (id_is_cpu) {
++ uid = rapl_msrs_are_pkg_scope() ?
++ topology_physical_package_id(id) : topology_logical_die_id(id);
++ if (uid < 0) {
++ pr_err("topology_logical_(package/die)_id() returned a negative value");
++ return NULL;
++ }
++ }
+ else
+ uid = id;
+
+@@ -2168,9 +2190,14 @@ struct rapl_package *rapl_add_package_cpuslocked(int id, struct rapl_if_priv *pr
+ return ERR_PTR(-ENOMEM);
+
+ if (id_is_cpu) {
+- rp->id = topology_logical_die_id(id);
++ rp->id = rapl_msrs_are_pkg_scope() ?
++ topology_physical_package_id(id) : topology_logical_die_id(id);
++ if ((int)(rp->id) < 0) {
++ pr_err("topology_logical_(package/die)_id() returned a negative value");
++ return ERR_PTR(-EINVAL);
++ }
+ rp->lead_cpu = id;
+- if (topology_max_dies_per_package() > 1)
++ if (!rapl_msrs_are_pkg_scope() && topology_max_dies_per_package() > 1)
+ snprintf(rp->name, PACKAGE_DOMAIN_NAME_LENGTH, "package-%d-die-%d",
+ topology_physical_package_id(id), topology_die_id(id));
+ else
+diff --git a/drivers/scsi/lpfc/lpfc_bsg.c b/drivers/scsi/lpfc/lpfc_bsg.c
+index 4156419c52c78a..4756a3f825310c 100644
+--- a/drivers/scsi/lpfc/lpfc_bsg.c
++++ b/drivers/scsi/lpfc/lpfc_bsg.c
+@@ -5410,7 +5410,7 @@ lpfc_get_cgnbuf_info(struct bsg_job *job)
+ struct get_cgnbuf_info_req *cgnbuf_req;
+ struct lpfc_cgn_info *cp;
+ uint8_t *cgn_buff;
+- int size, cinfosz;
++ size_t size, cinfosz;
+ int rc = 0;
+
+ if (job->request_len < sizeof(struct fc_bsg_request) +
+diff --git a/drivers/spi/spi-bcm63xx.c b/drivers/spi/spi-bcm63xx.c
+index aac41bd05f98f8..2fb8d4e55c7773 100644
+--- a/drivers/spi/spi-bcm63xx.c
++++ b/drivers/spi/spi-bcm63xx.c
+@@ -472,6 +472,7 @@ static const struct of_device_id bcm63xx_spi_of_match[] = {
+ { .compatible = "brcm,bcm6358-spi", .data = &bcm6358_spi_reg_offsets },
+ { },
+ };
++MODULE_DEVICE_TABLE(of, bcm63xx_spi_of_match);
+
+ static int bcm63xx_spi_probe(struct platform_device *pdev)
+ {
+diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
+index 5304728c68c20d..face93a9cf2035 100644
+--- a/drivers/spi/spidev.c
++++ b/drivers/spi/spidev.c
+@@ -702,6 +702,7 @@ static const struct class spidev_class = {
+ static const struct spi_device_id spidev_spi_ids[] = {
+ { .name = "bh2228fv" },
+ { .name = "dh2228fv" },
++ { .name = "jg10309-01" },
+ { .name = "ltc2488" },
+ { .name = "sx1301" },
+ { .name = "bk4" },
+@@ -731,6 +732,7 @@ static int spidev_of_check(struct device *dev)
+ static const struct of_device_id spidev_dt_ids[] = {
+ { .compatible = "cisco,spi-petra", .data = &spidev_of_check },
+ { .compatible = "dh,dhcom-board", .data = &spidev_of_check },
++ { .compatible = "elgin,jg10309-01", .data = &spidev_of_check },
+ { .compatible = "lineartechnology,ltc2488", .data = &spidev_of_check },
+ { .compatible = "lwn,bk4", .data = &spidev_of_check },
+ { .compatible = "menlo,m53cpld", .data = &spidev_of_check },
+diff --git a/drivers/usb/class/usbtmc.c b/drivers/usb/class/usbtmc.c
+index 311007b1d90465..c2e666e82857c1 100644
+--- a/drivers/usb/class/usbtmc.c
++++ b/drivers/usb/class/usbtmc.c
+@@ -754,7 +754,7 @@ static struct urb *usbtmc_create_urb(void)
+ if (!urb)
+ return NULL;
+
+- dmabuf = kmalloc(bufsize, GFP_KERNEL);
++ dmabuf = kzalloc(bufsize, GFP_KERNEL);
+ if (!dmabuf) {
+ usb_free_urb(urb);
+ return NULL;
+diff --git a/drivers/usb/serial/pl2303.c b/drivers/usb/serial/pl2303.c
+index d93f5d58455782..8e327fcb222f73 100644
+--- a/drivers/usb/serial/pl2303.c
++++ b/drivers/usb/serial/pl2303.c
+@@ -118,6 +118,7 @@ static const struct usb_device_id id_table[] = {
+ { USB_DEVICE(SMART_VENDOR_ID, SMART_PRODUCT_ID) },
+ { USB_DEVICE(AT_VENDOR_ID, AT_VTKIT3_PRODUCT_ID) },
+ { USB_DEVICE(IBM_VENDOR_ID, IBM_PRODUCT_ID) },
++ { USB_DEVICE(MACROSILICON_VENDOR_ID, MACROSILICON_MS3020_PRODUCT_ID) },
+ { } /* Terminating entry */
+ };
+
+diff --git a/drivers/usb/serial/pl2303.h b/drivers/usb/serial/pl2303.h
+index 732f9b13ad5d59..d60eda7f6edaf8 100644
+--- a/drivers/usb/serial/pl2303.h
++++ b/drivers/usb/serial/pl2303.h
+@@ -171,3 +171,7 @@
+ /* Allied Telesis VT-Kit3 */
+ #define AT_VENDOR_ID 0x0caa
+ #define AT_VTKIT3_PRODUCT_ID 0x3001
++
++/* Macrosilicon MS3020 */
++#define MACROSILICON_VENDOR_ID 0x345f
++#define MACROSILICON_MS3020_PRODUCT_ID 0x3020
+diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
+index 3b81213ed7b85b..35c0cc2a51af82 100644
+--- a/fs/ocfs2/xattr.c
++++ b/fs/ocfs2/xattr.c
+@@ -1062,13 +1062,13 @@ ssize_t ocfs2_listxattr(struct dentry *dentry,
+ return i_ret + b_ret;
+ }
+
+-static int ocfs2_xattr_find_entry(int name_index,
++static int ocfs2_xattr_find_entry(struct inode *inode, int name_index,
+ const char *name,
+ struct ocfs2_xattr_search *xs)
+ {
+ struct ocfs2_xattr_entry *entry;
+ size_t name_len;
+- int i, cmp = 1;
++ int i, name_offset, cmp = 1;
+
+ if (name == NULL)
+ return -EINVAL;
+@@ -1076,13 +1076,22 @@ static int ocfs2_xattr_find_entry(int name_index,
+ name_len = strlen(name);
+ entry = xs->here;
+ for (i = 0; i < le16_to_cpu(xs->header->xh_count); i++) {
++ if ((void *)entry >= xs->end) {
++ ocfs2_error(inode->i_sb, "corrupted xattr entries");
++ return -EFSCORRUPTED;
++ }
+ cmp = name_index - ocfs2_xattr_get_type(entry);
+ if (!cmp)
+ cmp = name_len - entry->xe_name_len;
+- if (!cmp)
+- cmp = memcmp(name, (xs->base +
+- le16_to_cpu(entry->xe_name_offset)),
+- name_len);
++ if (!cmp) {
++ name_offset = le16_to_cpu(entry->xe_name_offset);
++ if ((xs->base + name_offset + name_len) > xs->end) {
++ ocfs2_error(inode->i_sb,
++ "corrupted xattr entries");
++ return -EFSCORRUPTED;
++ }
++ cmp = memcmp(name, (xs->base + name_offset), name_len);
++ }
+ if (cmp == 0)
+ break;
+ entry += 1;
+@@ -1166,7 +1175,7 @@ static int ocfs2_xattr_ibody_get(struct inode *inode,
+ xs->base = (void *)xs->header;
+ xs->here = xs->header->xh_entries;
+
+- ret = ocfs2_xattr_find_entry(name_index, name, xs);
++ ret = ocfs2_xattr_find_entry(inode, name_index, name, xs);
+ if (ret)
+ return ret;
+ size = le64_to_cpu(xs->here->xe_value_size);
+@@ -2698,7 +2707,7 @@ static int ocfs2_xattr_ibody_find(struct inode *inode,
+
+ /* Find the named attribute. */
+ if (oi->ip_dyn_features & OCFS2_INLINE_XATTR_FL) {
+- ret = ocfs2_xattr_find_entry(name_index, name, xs);
++ ret = ocfs2_xattr_find_entry(inode, name_index, name, xs);
+ if (ret && ret != -ENODATA)
+ return ret;
+ xs->not_found = ret;
+@@ -2833,7 +2842,7 @@ static int ocfs2_xattr_block_find(struct inode *inode,
+ xs->end = (void *)(blk_bh->b_data) + blk_bh->b_size;
+ xs->here = xs->header->xh_entries;
+
+- ret = ocfs2_xattr_find_entry(name_index, name, xs);
++ ret = ocfs2_xattr_find_entry(inode, name_index, name, xs);
+ } else
+ ret = ocfs2_xattr_index_block_find(inode, blk_bh,
+ name_index,
+diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
+index d2307162a2de15..e325e06357ffb7 100644
+--- a/fs/smb/client/connect.c
++++ b/fs/smb/client/connect.c
+@@ -656,6 +656,19 @@ allocate_buffers(struct TCP_Server_Info *server)
+ static bool
+ server_unresponsive(struct TCP_Server_Info *server)
+ {
++ /*
++ * If we're in the process of mounting a share or reconnecting a session
++ * and the server abruptly shut down (e.g. socket wasn't closed, packet
++ * had been ACK'ed but no SMB response), don't wait longer than 20s to
++ * negotiate protocol.
++ */
++ spin_lock(&server->srv_lock);
++ if (server->tcpStatus == CifsInNegotiate &&
++ time_after(jiffies, server->lstrp + 20 * HZ)) {
++ spin_unlock(&server->srv_lock);
++ cifs_reconnect(server, false);
++ return true;
++ }
+ /*
+ * We need to wait 3 echo intervals to make sure we handle such
+ * situations right:
+@@ -667,7 +680,6 @@ server_unresponsive(struct TCP_Server_Info *server)
+ * 65s kernel_recvmsg times out, and we see that we haven't gotten
+ * a response in >60s.
+ */
+- spin_lock(&server->srv_lock);
+ if ((server->tcpStatus == CifsGood ||
+ server->tcpStatus == CifsNeedNegotiate) &&
+ (!server->ops->can_echo || server->ops->can_echo(server)) &&
+diff --git a/include/drm/drm_accel.h b/include/drm/drm_accel.h
+index f4d3784b1dce05..8867ce0be94cdd 100644
+--- a/include/drm/drm_accel.h
++++ b/include/drm/drm_accel.h
+@@ -51,11 +51,10 @@
+
+ #if IS_ENABLED(CONFIG_DRM_ACCEL)
+
++extern struct xarray accel_minors_xa;
++
+ void accel_core_exit(void);
+ int accel_core_init(void);
+-void accel_minor_remove(int index);
+-int accel_minor_alloc(void);
+-void accel_minor_replace(struct drm_minor *minor, int index);
+ void accel_set_device_instance_params(struct device *kdev, int index);
+ int accel_open(struct inode *inode, struct file *filp);
+ void accel_debugfs_init(struct drm_device *dev);
+@@ -73,19 +72,6 @@ static inline int __init accel_core_init(void)
+ return 0;
+ }
+
+-static inline void accel_minor_remove(int index)
+-{
+-}
+-
+-static inline int accel_minor_alloc(void)
+-{
+- return -EOPNOTSUPP;
+-}
+-
+-static inline void accel_minor_replace(struct drm_minor *minor, int index)
+-{
+-}
+-
+ static inline void accel_set_device_instance_params(struct device *kdev, int index)
+ {
+ }
+diff --git a/include/drm/drm_file.h b/include/drm/drm_file.h
+index ab230d3af138db..8c0030c7730816 100644
+--- a/include/drm/drm_file.h
++++ b/include/drm/drm_file.h
+@@ -45,6 +45,8 @@ struct drm_printer;
+ struct device;
+ struct file;
+
++extern struct xarray drm_minors_xa;
++
+ /*
+ * FIXME: Not sure we want to have drm_minor here in the end, but to avoid
+ * header include loops we need it here for now.
+@@ -434,6 +436,9 @@ static inline bool drm_is_accel_client(const struct drm_file *file_priv)
+
+ void drm_file_update_pid(struct drm_file *);
+
++struct drm_minor *drm_minor_acquire(struct xarray *minors_xa, unsigned int minor_id);
++void drm_minor_release(struct drm_minor *minor);
++
+ int drm_open(struct inode *inode, struct file *filp);
+ int drm_open_helper(struct file *filp, struct drm_minor *minor);
+ ssize_t drm_read(struct file *filp, char __user *buffer,
+diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
+index edba4a31844fb6..bca7b341dd772d 100644
+--- a/net/mac80211/tx.c
++++ b/net/mac80211/tx.c
+@@ -5348,8 +5348,10 @@ ieee80211_beacon_get_ap(struct ieee80211_hw *hw,
+ if (beacon->tail)
+ skb_put_data(skb, beacon->tail, beacon->tail_len);
+
+- if (ieee80211_beacon_protect(skb, local, sdata, link) < 0)
++ if (ieee80211_beacon_protect(skb, local, sdata, link) < 0) {
++ dev_kfree_skb(skb);
+ return NULL;
++ }
+
+ ieee80211_beacon_get_finish(hw, vif, link, offs, beacon, skb,
+ chanctx_conf, csa_off_base);
+diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
+index 765ffd6e06bc41..0a8883a93e8369 100644
+--- a/net/netfilter/nft_socket.c
++++ b/net/netfilter/nft_socket.c
+@@ -9,7 +9,8 @@
+
+ struct nft_socket {
+ enum nft_socket_keys key:8;
+- u8 level;
++ u8 level; /* cgroupv2 level to extract */
++ u8 level_user; /* cgroupv2 level provided by userspace */
+ u8 len;
+ union {
+ u8 dreg;
+@@ -53,6 +54,28 @@ nft_sock_get_eval_cgroupv2(u32 *dest, struct sock *sk, const struct nft_pktinfo
+ memcpy(dest, &cgid, sizeof(u64));
+ return true;
+ }
++
++/* process context only, uses current->nsproxy. */
++static noinline int nft_socket_cgroup_subtree_level(void)
++{
++ struct cgroup *cgrp = cgroup_get_from_path("/");
++ int level;
++
++ if (IS_ERR(cgrp))
++ return PTR_ERR(cgrp);
++
++ level = cgrp->level;
++
++ cgroup_put(cgrp);
++
++ if (WARN_ON_ONCE(level > 255))
++ return -ERANGE;
++
++ if (WARN_ON_ONCE(level < 0))
++ return -EINVAL;
++
++ return level;
++}
+ #endif
+
+ static struct sock *nft_socket_do_lookup(const struct nft_pktinfo *pkt)
+@@ -174,9 +197,10 @@ static int nft_socket_init(const struct nft_ctx *ctx,
+ case NFT_SOCKET_MARK:
+ len = sizeof(u32);
+ break;
+-#ifdef CONFIG_CGROUPS
++#ifdef CONFIG_SOCK_CGROUP_DATA
+ case NFT_SOCKET_CGROUPV2: {
+ unsigned int level;
++ int err;
+
+ if (!tb[NFTA_SOCKET_LEVEL])
+ return -EINVAL;
+@@ -185,6 +209,17 @@ static int nft_socket_init(const struct nft_ctx *ctx,
+ if (level > 255)
+ return -EOPNOTSUPP;
+
++ err = nft_socket_cgroup_subtree_level();
++ if (err < 0)
++ return err;
++
++ priv->level_user = level;
++
++ level += err;
++ /* Implies a giant cgroup tree */
++ if (WARN_ON_ONCE(level > 255))
++ return -EOPNOTSUPP;
++
+ priv->level = level;
+ len = sizeof(u64);
+ break;
+@@ -209,7 +244,7 @@ static int nft_socket_dump(struct sk_buff *skb,
+ if (nft_dump_register(skb, NFTA_SOCKET_DREG, priv->dreg))
+ return -1;
+ if (priv->key == NFT_SOCKET_CGROUPV2 &&
+- nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level)))
++ nla_put_be32(skb, NFTA_SOCKET_LEVEL, htonl(priv->level_user)))
+ return -1;
+ return 0;
+ }
+diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
+index 78042ac2b71f21..643e0496b09362 100644
+--- a/sound/pci/hda/patch_hdmi.c
++++ b/sound/pci/hda/patch_hdmi.c
+@@ -4639,6 +4639,7 @@ HDA_CODEC_ENTRY(0x8086281d, "Meteor Lake HDMI", patch_i915_adlp_hdmi),
+ HDA_CODEC_ENTRY(0x8086281e, "Battlemage HDMI", patch_i915_adlp_hdmi),
+ HDA_CODEC_ENTRY(0x8086281f, "Raptor Lake P HDMI", patch_i915_adlp_hdmi),
+ HDA_CODEC_ENTRY(0x80862820, "Lunar Lake HDMI", patch_i915_adlp_hdmi),
++HDA_CODEC_ENTRY(0x80862822, "Panther Lake HDMI", patch_i915_adlp_hdmi),
+ HDA_CODEC_ENTRY(0x80862880, "CedarTrail HDMI", patch_generic_hdmi),
+ HDA_CODEC_ENTRY(0x80862882, "Valleyview2 HDMI", patch_i915_byt_hdmi),
+ HDA_CODEC_ENTRY(0x80862883, "Braswell HDMI", patch_i915_byt_hdmi),
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index 0cde024d1d33cd..2b674691ce4b64 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -4925,6 +4925,30 @@ static void alc269_fixup_hp_line1_mic1_led(struct hda_codec *codec,
+ }
+ }
+
++static void alc_hp_mute_disable(struct hda_codec *codec, unsigned int delay)
++{
++ if (delay <= 0)
++ delay = 75;
++ snd_hda_codec_write(codec, 0x21, 0,
++ AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
++ msleep(delay);
++ snd_hda_codec_write(codec, 0x21, 0,
++ AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
++ msleep(delay);
++}
++
++static void alc_hp_enable_unmute(struct hda_codec *codec, unsigned int delay)
++{
++ if (delay <= 0)
++ delay = 75;
++ snd_hda_codec_write(codec, 0x21, 0,
++ AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
++ msleep(delay);
++ snd_hda_codec_write(codec, 0x21, 0,
++ AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
++ msleep(delay);
++}
++
+ static const struct coef_fw alc225_pre_hsmode[] = {
+ UPDATE_COEF(0x4a, 1<<8, 0),
+ UPDATE_COEFEX(0x57, 0x05, 1<<14, 0),
+@@ -5026,6 +5050,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
+ case 0x10ec0236:
+ case 0x10ec0256:
+ case 0x19e58326:
++ alc_hp_mute_disable(codec, 75);
+ alc_process_coef_fw(codec, coef0256);
+ break;
+ case 0x10ec0234:
+@@ -5060,6 +5085,7 @@ static void alc_headset_mode_unplugged(struct hda_codec *codec)
+ case 0x10ec0295:
+ case 0x10ec0289:
+ case 0x10ec0299:
++ alc_hp_mute_disable(codec, 75);
+ alc_process_coef_fw(codec, alc225_pre_hsmode);
+ alc_process_coef_fw(codec, coef0225);
+ break;
+@@ -5285,6 +5311,7 @@ static void alc_headset_mode_default(struct hda_codec *codec)
+ case 0x10ec0299:
+ alc_process_coef_fw(codec, alc225_pre_hsmode);
+ alc_process_coef_fw(codec, coef0225);
++ alc_hp_enable_unmute(codec, 75);
+ break;
+ case 0x10ec0255:
+ alc_process_coef_fw(codec, coef0255);
+@@ -5297,6 +5324,7 @@ static void alc_headset_mode_default(struct hda_codec *codec)
+ alc_write_coef_idx(codec, 0x45, 0xc089);
+ msleep(50);
+ alc_process_coef_fw(codec, coef0256);
++ alc_hp_enable_unmute(codec, 75);
+ break;
+ case 0x10ec0234:
+ case 0x10ec0274:
+@@ -5394,6 +5422,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
+ case 0x10ec0256:
+ case 0x19e58326:
+ alc_process_coef_fw(codec, coef0256);
++ alc_hp_enable_unmute(codec, 75);
+ break;
+ case 0x10ec0234:
+ case 0x10ec0274:
+@@ -5442,6 +5471,7 @@ static void alc_headset_mode_ctia(struct hda_codec *codec)
+ alc_process_coef_fw(codec, coef0225_2);
+ else
+ alc_process_coef_fw(codec, coef0225_1);
++ alc_hp_enable_unmute(codec, 75);
+ break;
+ case 0x10ec0867:
+ alc_update_coefex_idx(codec, 0x57, 0x5, 1<<14, 0);
+@@ -5509,6 +5539,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
+ case 0x10ec0256:
+ case 0x19e58326:
+ alc_process_coef_fw(codec, coef0256);
++ alc_hp_enable_unmute(codec, 75);
+ break;
+ case 0x10ec0234:
+ case 0x10ec0274:
+@@ -5546,6 +5577,7 @@ static void alc_headset_mode_omtp(struct hda_codec *codec)
+ case 0x10ec0289:
+ case 0x10ec0299:
+ alc_process_coef_fw(codec, coef0225);
++ alc_hp_enable_unmute(codec, 75);
+ break;
+ }
+ codec_dbg(codec, "Headset jack set to Nokia-style headset mode.\n");
+@@ -5614,25 +5646,21 @@ static void alc_determine_headset_type(struct hda_codec *codec)
+ alc_write_coef_idx(codec, 0x06, 0x6104);
+ alc_write_coefex_idx(codec, 0x57, 0x3, 0x09a3);
+
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+- msleep(80);
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+-
+ alc_process_coef_fw(codec, coef0255);
+ msleep(300);
+ val = alc_read_coef_idx(codec, 0x46);
+ is_ctia = (val & 0x0070) == 0x0070;
+-
++ if (!is_ctia) {
++ alc_write_coef_idx(codec, 0x45, 0xe089);
++ msleep(100);
++ val = alc_read_coef_idx(codec, 0x46);
++ if ((val & 0x0070) == 0x0070)
++ is_ctia = false;
++ else
++ is_ctia = true;
++ }
+ alc_write_coefex_idx(codec, 0x57, 0x3, 0x0da3);
+ alc_update_coefex_idx(codec, 0x57, 0x5, 1<<14, 0);
+-
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+- msleep(80);
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+ break;
+ case 0x10ec0234:
+ case 0x10ec0274:
+@@ -5709,12 +5737,6 @@ static void alc_determine_headset_type(struct hda_codec *codec)
+ case 0x10ec0295:
+ case 0x10ec0289:
+ case 0x10ec0299:
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+- msleep(80);
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_PIN_WIDGET_CONTROL, 0x0);
+-
+ alc_process_coef_fw(codec, alc225_pre_hsmode);
+ alc_update_coef_idx(codec, 0x67, 0xf000, 0x1000);
+ val = alc_read_coef_idx(codec, 0x45);
+@@ -5731,15 +5753,19 @@ static void alc_determine_headset_type(struct hda_codec *codec)
+ val = alc_read_coef_idx(codec, 0x46);
+ is_ctia = (val & 0x00f0) == 0x00f0;
+ }
++ if (!is_ctia) {
++ alc_update_coef_idx(codec, 0x45, 0x3f<<10, 0x38<<10);
++ alc_update_coef_idx(codec, 0x49, 3<<8, 1<<8);
++ msleep(100);
++ val = alc_read_coef_idx(codec, 0x46);
++ if ((val & 0x00f0) == 0x00f0)
++ is_ctia = false;
++ else
++ is_ctia = true;
++ }
+ alc_update_coef_idx(codec, 0x4a, 7<<6, 7<<6);
+ alc_update_coef_idx(codec, 0x4a, 3<<4, 3<<4);
+ alc_update_coef_idx(codec, 0x67, 0xf000, 0x3000);
+-
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+- msleep(80);
+- snd_hda_codec_write(codec, 0x21, 0,
+- AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+ break;
+ case 0x10ec0867:
+ is_ctia = true;
+diff --git a/sound/soc/amd/acp/acp-sof-mach.c b/sound/soc/amd/acp/acp-sof-mach.c
+index fc59ea34e687ad..b3a702dcd9911a 100644
+--- a/sound/soc/amd/acp/acp-sof-mach.c
++++ b/sound/soc/amd/acp/acp-sof-mach.c
+@@ -158,6 +158,8 @@ static const struct platform_device_id board_ids[] = {
+ },
+ { }
+ };
++MODULE_DEVICE_TABLE(platform, board_ids);
++
+ static struct platform_driver acp_asoc_audio = {
+ .driver = {
+ .name = "sof_mach",
+diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
+index f6c1dbd0ebcf57..248e3bcbf386b0 100644
+--- a/sound/soc/amd/yc/acp6x-mach.c
++++ b/sound/soc/amd/yc/acp6x-mach.c
+@@ -353,6 +353,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 15 C7VF"),
+ }
+ },
++ {
++ .driver_data = &acp6x_card,
++ .matches = {
++ DMI_MATCH(DMI_BOARD_VENDOR, "Micro-Star International Co., Ltd."),
++ DMI_MATCH(DMI_PRODUCT_NAME, "Bravo 17 D7VEK"),
++ }
++ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+diff --git a/sound/soc/au1x/db1200.c b/sound/soc/au1x/db1200.c
+index 83a75a38705b4e..81abe2e184024e 100644
+--- a/sound/soc/au1x/db1200.c
++++ b/sound/soc/au1x/db1200.c
+@@ -44,6 +44,7 @@ static const struct platform_device_id db1200_pids[] = {
+ },
+ {},
+ };
++MODULE_DEVICE_TABLE(platform, db1200_pids);
+
+ /*------------------------- AC97 PART ---------------------------*/
+
+diff --git a/sound/soc/codecs/chv3-codec.c b/sound/soc/codecs/chv3-codec.c
+index ab99effa68748d..40020500b1fe89 100644
+--- a/sound/soc/codecs/chv3-codec.c
++++ b/sound/soc/codecs/chv3-codec.c
+@@ -26,6 +26,7 @@ static const struct of_device_id chv3_codec_of_match[] = {
+ { .compatible = "google,chv3-codec", },
+ { }
+ };
++MODULE_DEVICE_TABLE(of, chv3_codec_of_match);
+
+ static struct platform_driver chv3_codec_platform_driver = {
+ .driver = {
+diff --git a/sound/soc/codecs/tda7419.c b/sound/soc/codecs/tda7419.c
+index 386b99c8023bdc..7d6fcba9986ea4 100644
+--- a/sound/soc/codecs/tda7419.c
++++ b/sound/soc/codecs/tda7419.c
+@@ -623,6 +623,7 @@ static const struct of_device_id tda7419_of_match[] = {
+ { .compatible = "st,tda7419" },
+ { },
+ };
++MODULE_DEVICE_TABLE(of, tda7419_of_match);
+
+ static struct i2c_driver tda7419_driver = {
+ .driver = {
+diff --git a/sound/soc/google/chv3-i2s.c b/sound/soc/google/chv3-i2s.c
+index 08e558f24af865..0ff24653d49f47 100644
+--- a/sound/soc/google/chv3-i2s.c
++++ b/sound/soc/google/chv3-i2s.c
+@@ -322,6 +322,7 @@ static const struct of_device_id chv3_i2s_of_match[] = {
+ { .compatible = "google,chv3-i2s" },
+ {},
+ };
++MODULE_DEVICE_TABLE(of, chv3_i2s_of_match);
+
+ static struct platform_driver chv3_i2s_driver = {
+ .probe = chv3_i2s_probe,
+diff --git a/sound/soc/intel/common/soc-acpi-intel-cht-match.c b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
+index 5e2ec60e2954b2..e4c3492a0c2824 100644
+--- a/sound/soc/intel/common/soc-acpi-intel-cht-match.c
++++ b/sound/soc/intel/common/soc-acpi-intel-cht-match.c
+@@ -84,7 +84,6 @@ static const struct dmi_system_id lenovo_yoga_tab3_x90[] = {
+ /* Lenovo Yoga Tab 3 Pro YT3-X90, codec missing from DSDT */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+- DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
+ },
+ },
+diff --git a/sound/soc/intel/keembay/kmb_platform.c b/sound/soc/intel/keembay/kmb_platform.c
+index 37ea2e1d2e9220..aa5de167e7909d 100644
+--- a/sound/soc/intel/keembay/kmb_platform.c
++++ b/sound/soc/intel/keembay/kmb_platform.c
+@@ -814,6 +814,7 @@ static const struct of_device_id kmb_plat_of_match[] = {
+ { .compatible = "intel,keembay-tdm", .data = &intel_kmb_tdm_dai},
+ {}
+ };
++MODULE_DEVICE_TABLE(of, kmb_plat_of_match);
+
+ static int kmb_plat_dai_probe(struct platform_device *pdev)
+ {
+diff --git a/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c b/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c
+index ccb6c1f3adc7d9..73e5c63aeec878 100644
+--- a/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c
++++ b/sound/soc/mediatek/mt8188/mt8188-afe-pcm.c
+@@ -2748,6 +2748,7 @@ static bool mt8188_is_volatile_reg(struct device *dev, unsigned int reg)
+ case AFE_ASRC12_NEW_CON9:
+ case AFE_LRCK_CNT:
+ case AFE_DAC_MON0:
++ case AFE_DAC_CON0:
+ case AFE_DL2_CUR:
+ case AFE_DL3_CUR:
+ case AFE_DL6_CUR:
+diff --git a/sound/soc/mediatek/mt8188/mt8188-mt6359.c b/sound/soc/mediatek/mt8188/mt8188-mt6359.c
+index eba6f4c445ffbf..08ae962afeb929 100644
+--- a/sound/soc/mediatek/mt8188/mt8188-mt6359.c
++++ b/sound/soc/mediatek/mt8188/mt8188-mt6359.c
+@@ -734,6 +734,7 @@ static int mt8188_headset_codec_init(struct snd_soc_pcm_runtime *rtd)
+ struct mtk_soc_card_data *soc_card_data = snd_soc_card_get_drvdata(rtd->card);
+ struct snd_soc_jack *jack = &soc_card_data->card_data->jacks[MT8188_JACK_HEADSET];
+ struct snd_soc_component *component = snd_soc_rtd_to_codec(rtd, 0)->component;
++ struct mtk_platform_card_data *card_data = soc_card_data->card_data;
+ int ret;
+
+ ret = snd_soc_dapm_new_controls(&card->dapm, mt8188_nau8825_widgets,
+@@ -762,10 +763,18 @@ static int mt8188_headset_codec_init(struct snd_soc_pcm_runtime *rtd)
+ return ret;
+ }
+
+- snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
+- snd_jack_set_key(jack->jack, SND_JACK_BTN_1, KEY_VOICECOMMAND);
+- snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEUP);
+- snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOLUMEDOWN);
++ if (card_data->flags & ES8326_HS_PRESENT) {
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_1, KEY_VOLUMEUP);
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEDOWN);
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOICECOMMAND);
++ } else {
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_0, KEY_PLAYPAUSE);
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_1, KEY_VOICECOMMAND);
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_2, KEY_VOLUMEUP);
++ snd_jack_set_key(jack->jack, SND_JACK_BTN_3, KEY_VOLUMEDOWN);
++ }
++
+ ret = snd_soc_component_set_jack(component, jack, NULL);
+
+ if (ret) {
+diff --git a/sound/soc/sof/mediatek/mt8195/mt8195.c b/sound/soc/sof/mediatek/mt8195/mt8195.c
+index 8d3fc167cd8103..b9d4508bbb85dd 100644
+--- a/sound/soc/sof/mediatek/mt8195/mt8195.c
++++ b/sound/soc/sof/mediatek/mt8195/mt8195.c
+@@ -574,6 +574,9 @@ static struct snd_sof_of_mach sof_mt8195_machs[] = {
+ {
+ .compatible = "google,tomato",
+ .sof_tplg_filename = "sof-mt8195-mt6359-rt1019-rt5682.tplg"
++ }, {
++ .compatible = "google,dojo",
++ .sof_tplg_filename = "sof-mt8195-mt6359-max98390-rt5682.tplg"
+ }, {
+ .compatible = "mediatek,mt8195",
+ .sof_tplg_filename = "sof-mt8195.tplg"
+diff --git a/tools/hv/Makefile b/tools/hv/Makefile
+index 2e60e2c212cd9e..34ffcec264ab0f 100644
+--- a/tools/hv/Makefile
++++ b/tools/hv/Makefile
+@@ -52,7 +52,7 @@ $(OUTPUT)hv_fcopy_uio_daemon: $(HV_FCOPY_UIO_DAEMON_IN)
+
+ clean:
+ rm -f $(ALL_PROGRAMS)
+- find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete
++ find $(or $(OUTPUT),.) -name '*.o' -delete -o -name '\.*.d' -delete -o -name '\.*.cmd' -delete
+
+ install: $(ALL_PROGRAMS)
+ install -d -m 755 $(DESTDIR)$(sbindir); \
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-24 18:52 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-24 18:52 UTC (permalink / raw
To: gentoo-commits
commit: bd01035c68fd9cf21dcfa87e5de209e0aa0f2950
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Tue Sep 24 18:51:40 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Tue Sep 24 18:51:40 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=bd01035c
dtrace patch for 6.10.X (CTF, modules.builtin.objs) p4
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 2 +-
2995_dtrace-6.10_p4.patch | 2373 +++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 2374 insertions(+), 1 deletion(-)
diff --git a/0000_README b/0000_README
index f48df58b..23b2116a 100644
--- a/0000_README
+++ b/0000_README
@@ -127,7 +127,7 @@ Patch: 2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
From: https://lore.kernel.org/bpf/
Desc: libbpf: workaround -Wmaybe-uninitialized false positive
-Patch: 2995_dtrace-6.10_p3.patch
+Patch: 2995_dtrace-6.10_p4.patch
From: https://github.com/thesamesam/linux/tree/dtrace-sam/v2/6.10
Desc: dtrace patch for 6.10.X (CTF, modules.builtin.objs)
diff --git a/2995_dtrace-6.10_p4.patch b/2995_dtrace-6.10_p4.patch
new file mode 100644
index 00000000..be81fda1
--- /dev/null
+++ b/2995_dtrace-6.10_p4.patch
@@ -0,0 +1,2373 @@
+diff --git a/Documentation/dontdiff b/Documentation/dontdiff
+index 3c399f132e2db..75b9655e57914 100644
+--- a/Documentation/dontdiff
++++ b/Documentation/dontdiff
+@@ -179,7 +179,7 @@ mkutf8data
+ modpost
+ modules-only.symvers
+ modules.builtin
+-modules.builtin.modinfo
++modules.builtin.*
+ modules.nsdeps
+ modules.order
+ modversions.h*
+diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst
+index 9c8d1d046ea56..4e2d666f167aa 100644
+--- a/Documentation/kbuild/kbuild.rst
++++ b/Documentation/kbuild/kbuild.rst
+@@ -17,11 +17,21 @@ modules.builtin
+ This file lists all modules that are built into the kernel. This is used
+ by modprobe to not fail when trying to load something builtin.
+
++modules.builtin.objs
++-----------------------
++This file contains object mapping of modules that are built into the kernel
++to their corresponding object files used to build the module.
++
+ modules.builtin.modinfo
+ -----------------------
+ This file contains modinfo from all modules that are built into the kernel.
+ Unlike modinfo of a separate module, all fields are prefixed with module name.
+
++modules.builtin.ranges
++----------------------
++This file contains address offset ranges (per ELF section) for all modules
++that are built into the kernel. Together with System.map, it can be used
++to associate module names with symbols.
+
+ Environment variables
+ =====================
+diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
+index 5685d7bfe4d0f..68fd086ac6538 100644
+--- a/Documentation/process/changes.rst
++++ b/Documentation/process/changes.rst
+@@ -63,9 +63,14 @@ cpio any cpio --version
+ GNU tar 1.28 tar --version
+ gtags (optional) 6.6.5 gtags --version
+ mkimage (optional) 2017.01 mkimage --version
++Python (optional) 3.5.x python3 --version
++GNU AWK (optional) 5.1.0 gawk --version
++GNU C\ [#f2]_ 12.0 gcc --version
++binutils\ [#f2]_ 2.36 ld -v
+ ====================== =============== ========================================
+
+ .. [#f1] Sphinx is needed only to build the Kernel documentation
++.. [#f2] These are needed at build-time when CONFIG_CTF is enabled
+
+ Kernel compilation
+ ******************
+@@ -198,6 +203,12 @@ platforms. The tool is available via the ``u-boot-tools`` package or can be
+ built from the U-Boot source code. See the instructions at
+ https://docs.u-boot.org/en/latest/build/tools.html#building-tools-for-linux
+
++GNU AWK
++-------
++
++GNU AWK is needed if you want kernel builds to generate address range data for
++builtin modules (CONFIG_BUILTIN_MODULE_RANGES).
++
+ System utilities
+ ****************
+
+diff --git a/Makefile b/Makefile
+index 447856c43b327..9977b007ad898 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1024,6 +1024,7 @@ include-$(CONFIG_UBSAN) += scripts/Makefile.ubsan
+ include-$(CONFIG_KCOV) += scripts/Makefile.kcov
+ include-$(CONFIG_RANDSTRUCT) += scripts/Makefile.randstruct
+ include-$(CONFIG_GCC_PLUGINS) += scripts/Makefile.gcc-plugins
++include-$(CONFIG_CTF) += scripts/Makefile.ctfa-toplevel
+
+ include $(addprefix $(srctree)/, $(include-y))
+
+@@ -1151,7 +1152,11 @@ PHONY += vmlinux_o
+ vmlinux_o: vmlinux.a $(KBUILD_VMLINUX_LIBS)
+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux_o
+
+-vmlinux.o modules.builtin.modinfo modules.builtin: vmlinux_o
++MODULES_BUILTIN := modules.builtin.modinfo
++MODULES_BUILTIN += modules.builtin
++MODULES_BUILTIN += modules.builtin.objs
++
++vmlinux.o $(MODULES_BUILTIN): vmlinux_o
+ @:
+
+ PHONY += vmlinux
+@@ -1490,9 +1495,10 @@ endif # CONFIG_MODULES
+
+ # Directories & files removed with 'make clean'
+ CLEAN_FILES += vmlinux.symvers modules-only.symvers \
+- modules.builtin modules.builtin.modinfo modules.nsdeps \
++ modules.builtin modules.builtin.* modules.nsdeps vmlinux.o.map \
+ compile_commands.json rust/test \
+- rust-project.json .vmlinux.objs .vmlinux.export.c
++ rust-project.json .vmlinux.objs .vmlinux.export.c \
++ vmlinux.ctfa
+
+ # Directories & files removed with 'make mrproper'
+ MRPROPER_FILES += include/config include/generated \
+@@ -1586,6 +1592,8 @@ help:
+ @echo ' (requires a recent binutils and recent build (System.map))'
+ @echo ' dir/file.ko - Build module including final link'
+ @echo ' modules_prepare - Set up for building external modules'
++ @echo ' ctf - Generate CTF type information, installed by make ctf_install'
++ @echo ' ctf_install - Install CTF to INSTALL_MOD_PATH (default: /)'
+ @echo ' tags/TAGS - Generate tags file for editors'
+ @echo ' cscope - Generate cscope index'
+ @echo ' gtags - Generate GNU GLOBAL index'
+@@ -1942,7 +1950,7 @@ clean: $(clean-dirs)
+ $(call cmd,rmfiles)
+ @find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \
+ \( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \
+- -o -name '*.ko.*' \
++ -o -name '*.ko.*' -o -name '*.ctf' \
+ -o -name '*.dtb' -o -name '*.dtbo' \
+ -o -name '*.dtb.S' -o -name '*.dtbo.S' \
+ -o -name '*.dt.yaml' -o -name 'dtbs-list' \
+diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
+index 01067a2bc43b7..d2193b8dfad83 100644
+--- a/arch/arm/vdso/Makefile
++++ b/arch/arm/vdso/Makefile
+@@ -14,6 +14,10 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+ ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
+ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO32
+
++# CTF in the vDSO would introduce a new section, which would
++# expand the vDSO to more than a page.
++ccflags-y += $(call cc-option,-gctf0)
++
+ ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8
+ ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
+ -z max-page-size=4096 -shared $(ldflags-y) \
+diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
+index d63930c828397..6e84d3822cfe3 100644
+--- a/arch/arm64/kernel/vdso/Makefile
++++ b/arch/arm64/kernel/vdso/Makefile
+@@ -33,6 +33,10 @@ ldflags-y += -T
+ ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
+ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
++# CTF in the vDSO would introduce a new section, which would
++# expand the vDSO to more than a page.
++ccflags-y += $(call cc-option,-gctf0)
++
+ # -Wmissing-prototypes and -Wmissing-declarations are removed from
+ # the CFLAGS of vgettimeofday.c to make possible to build the
+ # kernel with CONFIG_WERROR enabled.
+diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
+index d724d46b07c84..fbedb95223ae1 100644
+--- a/arch/loongarch/vdso/Makefile
++++ b/arch/loongarch/vdso/Makefile
+@@ -21,7 +21,8 @@ cflags-vdso := $(ccflags-vdso) \
+ -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
+ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
+ $(call cc-option, -fno-asynchronous-unwind-tables) \
+- $(call cc-option, -fno-stack-protector)
++ $(call cc-option, -fno-stack-protector) \
++ $(call cc-option,-gctf0)
+ aflags-vdso := $(ccflags-vdso) \
+ -D__ASSEMBLY__ -Wa,-gdwarf-2
+
+diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
+index b289b2c1b2946..6c8d777525f9b 100644
+--- a/arch/mips/vdso/Makefile
++++ b/arch/mips/vdso/Makefile
+@@ -30,7 +30,8 @@ cflags-vdso := $(ccflags-vdso) \
+ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+ -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \
+ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
+- $(call cc-option, -fno-asynchronous-unwind-tables)
++ $(call cc-option, -fno-asynchronous-unwind-tables) \
++ $(call cc-option,-gctf0)
+ aflags-vdso := $(ccflags-vdso) \
+ -D__ASSEMBLY__ -Wa,-gdwarf-2
+
+diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
+index 243dbfc4609d8..e4f3e47074e9d 100644
+--- a/arch/sparc/vdso/Makefile
++++ b/arch/sparc/vdso/Makefile
+@@ -44,7 +44,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
+- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
++ $(call cc-option,-gctf0) -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ SPARC_REG_CFLAGS = -ffixed-g4 -ffixed-g5 -fcall-used-g5 -fcall-used-g7
+
+diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
+index 215a1b202a918..2fa1613a06275 100644
+--- a/arch/x86/entry/vdso/Makefile
++++ b/arch/x86/entry/vdso/Makefile
+@@ -54,6 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
++ $(call cc-option,-gctf0) \
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ ifdef CONFIG_MITIGATION_RETPOLINE
+@@ -131,6 +132,7 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
+ KBUILD_CFLAGS_32 += -fno-stack-protector
+ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
+ KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
++KBUILD_CFLAGS_32 += $(call cc-option,-gctf0)
+ KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+
+ ifdef CONFIG_MITIGATION_RETPOLINE
+diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
+index 6a77ea6434ffd..6db233b5edd75 100644
+--- a/arch/x86/um/vdso/Makefile
++++ b/arch/x86/um/vdso/Makefile
+@@ -40,7 +40,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
+ #
+ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+- -fno-omit-frame-pointer -foptimize-sibling-calls
++ -fno-omit-frame-pointer -foptimize-sibling-calls $(call cc-option,-gctf0)
+
+ $(vobjs): KBUILD_CFLAGS += $(CFL)
+
+diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
+index f00a8e18f389f..2e307c0824574 100644
+--- a/include/asm-generic/vmlinux.lds.h
++++ b/include/asm-generic/vmlinux.lds.h
+@@ -1014,6 +1014,7 @@
+ *(.discard.*) \
+ *(.export_symbol) \
+ *(.modinfo) \
++ *(.ctf) \
+ /* ld.bfd warns about .gnu.version* even when not emitted */ \
+ *(.gnu.version*) \
+
+diff --git a/include/linux/module.h b/include/linux/module.h
+index 330ffb59efe51..2d9fcca542d13 100644
+--- a/include/linux/module.h
++++ b/include/linux/module.h
+@@ -180,7 +180,13 @@ extern void cleanup_module(void);
+ #ifdef MODULE
+ #define MODULE_FILE
+ #else
+-#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
++#ifdef CONFIG_CTF
++#define MODULE_FILE \
++ MODULE_INFO(file, KBUILD_MODFILE); \
++ MODULE_INFO(objs, KBUILD_MODOBJS);
++#else
++#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
++#endif
+ #endif
+
+ /*
+diff --git a/init/Kconfig b/init/Kconfig
+index 9684e5d2b81c6..c1b00b2e4a43d 100644
+--- a/init/Kconfig
++++ b/init/Kconfig
+@@ -111,6 +111,12 @@ config PAHOLE_VERSION
+ int
+ default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
+
++config HAVE_CTF_TOOLCHAIN
++ def_bool $(cc-option,-gctf) && $(ld-option,-lbfd -liberty -lctf -lbfd -liberty -lz -ldl -lc -o /dev/null)
++ depends on CC_IS_GCC
++ help
++ GCC and binutils support CTF generation.
++
+ config CONSTRUCTORS
+ bool
+
+diff --git a/lib/Kconfig b/lib/Kconfig
+index b0a76dff5c182..61d0be30b3562 100644
+--- a/lib/Kconfig
++++ b/lib/Kconfig
+@@ -633,6 +633,16 @@ config DIMLIB
+ #
+ config LIBFDT
+ bool
++#
++# CTF support is select'ed if needed
++#
++config CTF
++ bool "Compact Type Format generation"
++ depends on HAVE_CTF_TOOLCHAIN
++ help
++ Emit a compact, compressed description of the kernel's datatypes and
++ global variables into the vmlinux.ctfa archive (for in-tree modules)
++ or into .ctf sections in kernel modules (for out-of-tree modules).
+
+ config OID_REGISTRY
+ tristate
+diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
+index 59b6765d86b8f..dab7e6983eace 100644
+--- a/lib/Kconfig.debug
++++ b/lib/Kconfig.debug
+@@ -571,6 +571,21 @@ config VMLINUX_MAP
+ pieces of code get eliminated with
+ CONFIG_LD_DEAD_CODE_DATA_ELIMINATION.
+
++config BUILTIN_MODULE_RANGES
++ bool "Generate address range information for builtin modules"
++ depends on !LTO
++ depends on VMLINUX_MAP
++ help
++ When modules are built into the kernel, there will be no module name
++ associated with its symbols in /proc/kallsyms. Tracers may want to
++ identify symbols by module name and symbol name regardless of whether
++ the module is configured as loadable or not.
++
++ This option generates modules.builtin.ranges in the build tree with
++ offset ranges (per ELF section) for the module(s) they belong to.
++ It also records an anchor symbol to determine the load address of the
++ section.
++
+ config DEBUG_FORCE_WEAK_PER_CPU
+ bool "Force weak per-cpu definitions"
+ depends on DEBUG_KERNEL
+diff --git a/scripts/Makefile b/scripts/Makefile
+index fe56eeef09dd4..8e7eb174d3154 100644
+--- a/scripts/Makefile
++++ b/scripts/Makefile
+@@ -54,6 +54,7 @@ targets += module.lds
+
+ subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
+ subdir-$(CONFIG_MODVERSIONS) += genksyms
++subdir-$(CONFIG_CTF) += ctf
+ subdir-$(CONFIG_SECURITY_SELINUX) += selinux
+
+ # Let clean descend into subdirs
+diff --git a/scripts/Makefile.ctfa b/scripts/Makefile.ctfa
+new file mode 100644
+index 0000000000000..b65d9d391c29c
+--- /dev/null
++++ b/scripts/Makefile.ctfa
+@@ -0,0 +1,92 @@
++# SPDX-License-Identifier: GPL-2.0-only
++# ===========================================================================
++# Module CTF/CTFA generation
++# ===========================================================================
++
++include include/config/auto.conf
++include $(srctree)/scripts/Kbuild.include
++
++# CTF is already present in every object file if CONFIG_CTF is enabled.
++# vmlinux.lds.h strips it out of the finished kernel, but if nothing is done
++# it will be deduplicated into module .ko's. For out-of-tree module builds,
++# this is what we want, but for in-tree modules we can save substantial
++# space by deduplicating it against all the core kernel types as well. So
++# split the CTF out of in-tree module .ko's into separate .ctf files so that
++# it doesn't take up space in the modules on disk, and let the specialized
++# ctfarchive tool consume it and all the CTF in the vmlinux.o files when
++# 'make ctf' is invoked, and use the same machinery that the linker uses to
++# do CTF deduplication to emit vmlinux.ctfa containing the deduplicated CTF.
++
++# Nothing special needs to be done if CTF is turned off or if a standalone
++# module is being built.
++module-ctf-postlink = mv $(1).tmp $(1)
++
++ifdef CONFIG_CTF
++
++# This is quite tricky. The CTF machinery needs to be told about all the
++# built-in objects as well as all the external modules -- but Makefile.modfinal
++# only knows about the latter. So the toplevel makefile emits the names of the
++# built-in objects into a temporary file, which is then catted and its contents
++# used as prerequisites by this rule.
++#
++# We write the names of the object files to be scanned for CTF content into a
++# file, then use that, to avoid hitting command-line length limits.
++
++ifeq ($(KBUILD_EXTMOD),)
++ctf-modules := $(shell find . -name '*.ko.ctf' -print)
++quiet_cmd_ctfa_raw = CTFARAW
++ cmd_ctfa_raw = scripts/ctf/ctfarchive $@ .tmp_objects.builtin modules.builtin.objs $(ctf-filelist)
++ctf-builtins := .tmp_objects.builtin
++ctf-filelist := .tmp_ctf.filelist
++ctf-filelist-raw := .tmp_ctf.filelist.raw
++
++define module-ctf-postlink =
++ $(OBJCOPY) --only-section=.ctf $(1).tmp $(1).ctf && \
++ $(OBJCOPY) --remove-section=.ctf $(1).tmp $(1) && rm -f $(1).tmp
++endef
++
++# Split a list up like shell xargs does.
++define xargs =
++$(1) $(wordlist 1,1024,$(2))
++$(if $(word 1025,$(2)),$(call xargs,$(1),$(wordlist 1025,$(words $(2)),$(2))))
++endef
++
++$(ctf-filelist-raw): $(ctf-builtins) $(ctf-modules)
++ @rm -f $(ctf-filelist-raw);
++ $(call xargs,@printf "%s\n" >> $(ctf-filelist-raw),$^)
++ @touch $(ctf-filelist-raw)
++
++$(ctf-filelist): $(ctf-filelist-raw)
++ @rm -f $(ctf-filelist);
++ @cat $(ctf-filelist-raw) | while read -r obj; do \
++ case $$obj in \
++ $(ctf-builtins)) cat $$obj >> $(ctf-filelist);; \
++ *.a) $(AR) t $$obj > $(ctf-filelist);; \
++ *.builtin) cat $$obj >> $(ctf-filelist);; \
++ *) echo "$$obj" >> $(ctf-filelist);; \
++ esac; \
++ done
++ @touch $(ctf-filelist)
++
++# The raw CTF depends on the output CTF file list, and that depends
++# on the .ko files for the modules.
++.tmp_vmlinux.ctfa.raw: $(ctf-filelist) FORCE
++ $(call if_changed,ctfa_raw)
++
++quiet_cmd_ctfa = CTFA
++ cmd_ctfa = { echo 'int main () { return 0; } ' | \
++ $(CC) -x c -c -o $<.stub -; \
++ $(OBJCOPY) '--remove-section=.*' --add-section=.ctf=$< \
++ $<.stub $@; }
++
++# The CTF itself is an ELF executable with one section: the CTF. This lets
++# objdump work on it, at minimal size cost.
++vmlinux.ctfa: .tmp_vmlinux.ctfa.raw FORCE
++ $(call if_changed,ctfa)
++
++targets += vmlinux.ctfa
++
++endif # KBUILD_EXTMOD
++
++endif # !CONFIG_CTF
++
+diff --git a/scripts/Makefile.ctfa-toplevel b/scripts/Makefile.ctfa-toplevel
+new file mode 100644
+index 0000000000000..210bef3854e9b
+--- /dev/null
++++ b/scripts/Makefile.ctfa-toplevel
+@@ -0,0 +1,54 @@
++# SPDX-License-Identifier: GPL-2.0-only
++# ===========================================================================
++# CTF rules for the top-level makefile only
++# ===========================================================================
++
++KBUILD_CFLAGS += $(call cc-option,-gctf)
++KBUILD_LDFLAGS += $(call ld-option, --ctf-variables)
++
++ifeq ($(KBUILD_EXTMOD),)
++
++# CTF generation for in-tree code (modules, built-in and not, and core kernel)
++
++# This contains all the object files that are built directly into the
++# kernel (including built-in modules), for consumption by ctfarchive in
++# Makefile.modfinal.
++# This is made doubly annoying by the presence of '.o' files which are actually
++# thin ar archives, and the need to support file(1) versions too old to
++# recognize them as archives at all. (So we assume that everything that is notr
++# an ELF object is an archive.)
++ifeq ($(SRCARCH),x86)
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),bzImage) FORCE
++else
++ifeq ($(SRCARCH),arm64)
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),Image) FORCE
++else
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) FORCE
++endif
++endif
++ @echo $(KBUILD_VMLINUX_OBJS) | \
++ tr " " "\n" | grep "\.o$$" | xargs -r file | \
++ grep ELF | cut -d: -f1 > .tmp_objects.builtin
++ @for archive in $$(echo $(KBUILD_VMLINUX_OBJS) |\
++ tr " " "\n" | xargs -r file | grep -v ELF | cut -d: -f1); do \
++ $(AR) t "$$archive" >> .tmp_objects.builtin; \
++ done
++
++ctf: vmlinux.ctfa
++PHONY += ctf ctf_install
++
++# Making CTF needs the builtin files. We need to force everything to be
++# built if not already done, since we need the .o files for the machinery
++# above to work.
++vmlinux.ctfa: KBUILD_BUILTIN := 1
++vmlinux.ctfa: modules.builtin.objs .tmp_objects.builtin
++ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal vmlinux.ctfa
++
++ctf_install:
++ $(Q)mkdir -p $(MODLIB)/kernel
++ @ln -sf $(abspath $(srctree)) $(MODLIB)/source
++ $(Q)cp -f $(objtree)/vmlinux.ctfa $(MODLIB)/kernel
++
++CLEAN_FILES += vmlinux.ctfa
++
++endif
+diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
+index 7f8ec77bf35c9..8e67961ba2ec9 100644
+--- a/scripts/Makefile.lib
++++ b/scripts/Makefile.lib
+@@ -118,6 +118,8 @@ modname-multi = $(sort $(foreach m,$(multi-obj-ym),\
+ __modname = $(or $(modname-multi),$(basetarget))
+
+ modname = $(subst $(space),:,$(__modname))
++modname-objs = $($(modname)-objs) $($(modname)-y) $($(modname)-Y)
++modname-objs-prefixed = $(sort $(strip $(addprefix $(obj)/, $(modname-objs))))
+ modfile = $(addprefix $(obj)/,$(__modname))
+
+ # target with $(obj)/ and its suffix stripped
+@@ -133,6 +135,10 @@ modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
+ -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
+ modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
+
++ifdef CONFIG_CTF
++modfile_flags += -DKBUILD_MODOBJS=$(call stringify,$(modfile).o:$(subst $(space),|,$(modname-objs-prefixed)))
++endif
++
+ _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
+ $(filter-out $(ccflags-remove-y), \
+ $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(ccflags-y)) \
+@@ -238,7 +244,7 @@ modkern_rustflags = \
+
+ modkern_aflags = $(if $(part-of-module), \
+ $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE), \
+- $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL))
++ $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) $(modfile_flags))
+
+ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ -include $(srctree)/include/linux/compiler_types.h \
+@@ -248,7 +254,7 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ rust_flags = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg
+
+ a_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+- $(_a_flags) $(modkern_aflags)
++ $(_a_flags) $(modkern_aflags) $(modname_flags)
+
+ cpp_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ $(_cpp_flags)
+diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
+index 3bec9043e4f38..06807e403d162 100644
+--- a/scripts/Makefile.modfinal
++++ b/scripts/Makefile.modfinal
+@@ -30,11 +30,16 @@ quiet_cmd_cc_o_c = CC [M] $@
+ %.mod.o: %.mod.c FORCE
+ $(call if_changed_dep,cc_o_c)
+
++# for module-ctf-postlink
++include $(srctree)/scripts/Makefile.ctfa
++
+ quiet_cmd_ld_ko_o = LD [M] $@
+ cmd_ld_ko_o += \
+ $(LD) -r $(KBUILD_LDFLAGS) \
+ $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
+- -T scripts/module.lds -o $@ $(filter %.o, $^)
++ -T scripts/module.lds $(LDFLAGS_$(modname)) -o $@.tmp \
++ $(filter %.o, $^) && \
++ $(call module-ctf-postlink,$@) \
+
+ quiet_cmd_btf_ko = BTF [M] $@
+ cmd_btf_ko = \
+diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
+index 0afd75472679f..e668469ce098c 100644
+--- a/scripts/Makefile.modinst
++++ b/scripts/Makefile.modinst
+@@ -30,10 +30,12 @@ $(MODLIB)/modules.order: modules.order FORCE
+ quiet_cmd_install_modorder = INSTALL $@
+ cmd_install_modorder = sed 's:^\(.*\)\.o$$:kernel/\1.ko:' $< > $@
+
+-# Install modules.builtin(.modinfo) even when CONFIG_MODULES is disabled.
+-install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo)
++# Install modules.builtin(.modinfo,.ranges,.objs) even when CONFIG_MODULES is disabled.
++install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.objs)
+
+-$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo): $(MODLIB)/%: % FORCE
++install-$(CONFIG_BUILTIN_MODULE_RANGES) += $(MODLIB)/modules.builtin.ranges
++
++$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.ranges modules.builtin.objs): $(MODLIB)/%: % FORCE
+ $(call cmd,install)
+
+ endif
+diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
+index 49946cb968440..2524c8e2edbdb 100644
+--- a/scripts/Makefile.vmlinux
++++ b/scripts/Makefile.vmlinux
+@@ -33,7 +33,25 @@ targets += vmlinux
+ vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE
+ +$(call if_changed_dep,link_vmlinux)
+
+-# Add FORCE to the prequisites of a target to force it to be always rebuilt.
++# ---------------------------------------------------------------------------
++ifdef CONFIG_BUILTIN_MODULE_RANGES
++__default: modules.builtin.ranges
++
++quiet_cmd_modules_builtin_ranges = GEN $@
++ cmd_modules_builtin_ranges = gawk -f $(real-prereqs) > $@
++
++targets += modules.builtin.ranges
++modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \
++ modules.builtin vmlinux.map vmlinux.o.map FORCE
++ $(call if_changed,modules_builtin_ranges)
++
++vmlinux.map: vmlinux
++ @:
++
++endif
++
++# Add FORCE to the prerequisites of a target to force it to be always rebuilt.
++
+ # ---------------------------------------------------------------------------
+
+ PHONY += FORCE
+diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
+index 6de297916ce68..e8d5c98173d74 100644
+--- a/scripts/Makefile.vmlinux_o
++++ b/scripts/Makefile.vmlinux_o
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0-only
+
+ PHONY := __default
+-__default: vmlinux.o modules.builtin.modinfo modules.builtin
++__default: vmlinux.o modules.builtin.modinfo modules.builtin modules.builtin.objs
+
+ include include/config/auto.conf
+ include $(srctree)/scripts/Kbuild.include
+@@ -27,6 +27,20 @@ ifdef CONFIG_LTO_CLANG
+ initcalls-lds := .tmp_initcalls.lds
+ endif
+
++# Generate a linker script to delete CTF sections
++# -----------------------------------------------
++
++quiet_cmd_gen_remove_ctf.lds = GEN $@
++ cmd_gen_remove_ctf.lds = \
++ $(LD) $(KBUILD_LDFLAGS) -r --verbose | awk -f $(real-prereqs) > $@
++
++.tmp_remove-ctf.lds: $(srctree)/scripts/remove-ctf-lds.awk FORCE
++ $(call if_changed,gen_remove_ctf.lds)
++
++ifdef CONFIG_CTF
++targets := .tmp_remove-ctf.lds
++endif
++
+ # objtool for vmlinux.o
+ # ---------------------------------------------------------------------------
+ #
+@@ -42,13 +56,26 @@ vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \
+
+ objtool-args = $(vmlinux-objtool-args-y) --link
+
+-# Link of vmlinux.o used for section mismatch analysis
++# Link of vmlinux.o used for section mismatch analysis: we also strip the CTF
++# section out at this stage, since ctfarchive gets it from the underlying object
++# files and linking it further is a waste of time.
+ # ---------------------------------------------------------------------------
+
++vmlinux-o-ld-args-$(CONFIG_BUILTIN_MODULE_RANGES) += -Map=$@.map
++
++ifdef CONFIG_CTF
++ctf_strip_script_arg = -T .tmp_remove-ctf.lds
++ctf_target = .tmp_remove-ctf.lds
++else
++ctf_strip_script_arg =
++ctf_target =
++endif
++
+ quiet_cmd_ld_vmlinux.o = LD $@
+ cmd_ld_vmlinux.o = \
+ $(LD) ${KBUILD_LDFLAGS} -r -o $@ \
+- $(addprefix -T , $(initcalls-lds)) \
++ $(vmlinux-o-ld-args-y) \
++ $(addprefix -T , $(initcalls-lds)) $(ctf_strip_script_arg) \
+ --whole-archive vmlinux.a --no-whole-archive \
+ --start-group $(KBUILD_VMLINUX_LIBS) --end-group \
+ $(cmd_objtool)
+@@ -58,7 +85,7 @@ define rule_ld_vmlinux.o
+ $(call cmd,gen_objtooldep)
+ endef
+
+-vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
++vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) $(ctf_target) FORCE
+ $(call if_changed_rule,ld_vmlinux.o)
+
+ targets += vmlinux.o
+@@ -87,6 +114,19 @@ targets += modules.builtin
+ modules.builtin: modules.builtin.modinfo FORCE
+ $(call if_changed,modules_builtin)
+
++# module.builtin.objs
++# ---------------------------------------------------------------------------
++quiet_cmd_modules_builtin_objs = GEN $@
++ cmd_modules_builtin_objs = \
++ tr '\0' '\n' < $< | \
++ sed -n 's/^[[:alnum:]:_]*\.objs=//p' | \
++ tr ' ' '\n' | uniq | sed -e 's|:|: |' -e 's:|: :g' | \
++ tr -s ' ' > $@
++
++targets += modules.builtin.objs
++modules.builtin.objs: modules.builtin.modinfo FORCE
++ $(call if_changed,modules_builtin_objs)
++
+ # Add FORCE to the prequisites of a target to force it to be always rebuilt.
+ # ---------------------------------------------------------------------------
+
+diff --git a/scripts/ctf/Makefile b/scripts/ctf/Makefile
+new file mode 100644
+index 0000000000000..3b83f93bb9f9a
+--- /dev/null
++++ b/scripts/ctf/Makefile
+@@ -0,0 +1,5 @@
++ifdef CONFIG_CTF
++hostprogs-always-y := ctfarchive
++ctfarchive-objs := ctfarchive.o modules_builtin.o
++HOSTLDLIBS_ctfarchive := -lctf
++endif
+diff --git a/scripts/ctf/ctfarchive.c b/scripts/ctf/ctfarchive.c
+new file mode 100644
+index 0000000000000..92cc4912ed0ee
+--- /dev/null
++++ b/scripts/ctf/ctfarchive.c
+@@ -0,0 +1,413 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * ctfmerge.c: Read in CTF extracted from generated object files from a
++ * specified directory and generate a CTF archive whose members are the
++ * deduplicated CTF derived from those object files, split up by kernel
++ * module.
++ *
++ * Copyright (c) 2019, 2023, Oracle and/or its affiliates.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#define _GNU_SOURCE 1
++#include <errno.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <string.h>
++#include <ctf-api.h>
++#include "modules_builtin.h"
++
++static ctf_file_t *output;
++
++static int private_ctf_link_add_ctf(ctf_file_t *fp,
++ const char *name)
++{
++#if !defined (CTF_LINK_FINAL)
++ return ctf_link_add_ctf(fp, NULL, name);
++#else
++ /* Non-upstreamed, erroneously-broken API. */
++ return ctf_link_add_ctf(fp, NULL, name, NULL, 0);
++#endif
++}
++
++/*
++ * Add a file to the link.
++ */
++static void add_to_link(const char *fn)
++{
++ if (private_ctf_link_add_ctf(output, fn) < 0)
++ {
++ fprintf(stderr, "Cannot add CTF file %s: %s\n", fn,
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++}
++
++struct from_to
++{
++ char *from;
++ char *to;
++};
++
++/*
++ * The world's stupidest hash table of FROM -> TO.
++ */
++static struct from_to **from_tos[256];
++static size_t alloc_from_tos[256];
++static size_t num_from_tos[256];
++
++static unsigned char from_to_hash(const char *from)
++{
++ unsigned char hval = 0;
++
++ const char *p;
++ for (p = from; *p; p++)
++ hval += *p;
++
++ return hval;
++}
++
++/*
++ * Note that we will need to add a CU mapping later on.
++ *
++ * Present purely to work around a binutils bug that stops
++ * ctf_link_add_cu_mapping() working right when called repeatedly
++ * with the same FROM.
++ */
++static int add_cu_mapping(const char *from, const char *to)
++{
++ ssize_t i, j;
++
++ i = from_to_hash(from);
++
++ for (j = 0; j < num_from_tos[i]; j++)
++ if (strcmp(from, from_tos[i][j]->from) == 0) {
++ char *tmp;
++
++ free(from_tos[i][j]->to);
++ tmp = strdup(to);
++ if (!tmp)
++ goto oom;
++ from_tos[i][j]->to = tmp;
++ return 0;
++ }
++
++ if (num_from_tos[i] >= alloc_from_tos[i]) {
++ struct from_to **tmp;
++ if (alloc_from_tos[i] < 16)
++ alloc_from_tos[i] = 16;
++ else
++ alloc_from_tos[i] *= 2;
++
++ tmp = realloc(from_tos[i], alloc_from_tos[i] * sizeof(struct from_to *));
++ if (!tmp)
++ goto oom;
++
++ from_tos[i] = tmp;
++ }
++
++ j = num_from_tos[i];
++ from_tos[i][j] = malloc(sizeof(struct from_to));
++ if (from_tos[i][j] == NULL)
++ goto oom;
++ from_tos[i][j]->from = strdup(from);
++ from_tos[i][j]->to = strdup(to);
++ if (!from_tos[i][j]->from || !from_tos[i][j]->to)
++ goto oom;
++ num_from_tos[i]++;
++
++ return 0;
++ oom:
++ fprintf(stderr,
++ "out of memory in add_cu_mapping\n");
++ exit(1);
++}
++
++/*
++ * Finally tell binutils to add all the CU mappings, with duplicate FROMs
++ * replaced with the most recent one.
++ */
++static void commit_cu_mappings(void)
++{
++ ssize_t i, j;
++
++ for (i = 0; i < 256; i++)
++ for (j = 0; j < num_from_tos[i]; j++)
++ ctf_link_add_cu_mapping(output, from_tos[i][j]->from,
++ from_tos[i][j]->to);
++}
++
++/*
++ * Add a CU mapping to the link.
++ *
++ * CU mappings for built-in modules are added by suck_in_modules, below: here,
++ * we only want to add mappings for names ending in '.ko.ctf', i.e. external
++ * modules, which appear only in the filelist (since they are not built-in).
++ * The pathnames are stripped off because modules don't have any, and hyphens
++ * are translated into underscores.
++ */
++static void add_cu_mappings(const char *fn)
++{
++ const char *last_slash;
++ const char *modname = fn;
++ char *dynmodname = NULL;
++ char *dash;
++ size_t n;
++
++ last_slash = strrchr(modname, '/');
++ if (last_slash)
++ last_slash++;
++ else
++ last_slash = modname;
++ modname = last_slash;
++ if (strchr(modname, '-') != NULL)
++ {
++ dynmodname = strdup(last_slash);
++ dash = dynmodname;
++ while (dash != NULL) {
++ dash = strchr(dash, '-');
++ if (dash != NULL)
++ *dash = '_';
++ }
++ modname = dynmodname;
++ }
++
++ n = strlen(modname);
++ if (strcmp(modname + n - strlen(".ko.ctf"), ".ko.ctf") == 0) {
++ char *mod;
++
++ n -= strlen(".ko.ctf");
++ mod = strndup(modname, n);
++ add_cu_mapping(fn, mod);
++ free(mod);
++ }
++ free(dynmodname);
++}
++
++/*
++ * Add the passed names as mappings to "vmlinux".
++ */
++static void add_builtins(const char *fn)
++{
++ if (add_cu_mapping(fn, "vmlinux") < 0)
++ {
++ fprintf(stderr, "Cannot add CTF CU mapping from %s to \"vmlinux\"\n",
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++}
++
++/*
++ * Do something with a file, line by line.
++ */
++static void suck_in_lines(const char *filename, void (*func)(const char *line))
++{
++ FILE *f;
++ char *line = NULL;
++ size_t line_size = 0;
++
++ f = fopen(filename, "r");
++ if (f == NULL) {
++ fprintf(stderr, "Cannot open %s: %s\n", filename,
++ strerror(errno));
++ exit(1);
++ }
++
++ while (getline(&line, &line_size, f) >= 0) {
++ size_t len = strlen(line);
++
++ if (len == 0)
++ continue;
++
++ if (line[len-1] == '\n')
++ line[len-1] = '\0';
++
++ func(line);
++ }
++ free(line);
++
++ if (ferror(f)) {
++ fprintf(stderr, "Error reading from %s: %s\n", filename,
++ strerror(errno));
++ exit(1);
++ }
++
++ fclose(f);
++}
++
++/*
++ * Pull in modules.builtin.objs and turn it into CU mappings.
++ */
++static void suck_in_modules(const char *modules_builtin_name)
++{
++ struct modules_builtin_iter *i;
++ char *module_name = NULL;
++ char **paths;
++
++ i = modules_builtin_iter_new(modules_builtin_name);
++ if (i == NULL) {
++ fprintf(stderr, "Cannot iterate over builtin module file.\n");
++ exit(1);
++ }
++
++ while ((paths = modules_builtin_iter_next(i, &module_name)) != NULL) {
++ size_t j;
++
++ for (j = 0; paths[j] != NULL; j++) {
++ char *alloc = NULL;
++ char *path = paths[j];
++ /*
++ * If the name doesn't start in ./, add it, to match the names
++ * passed to add_builtins.
++ */
++ if (strncmp(paths[j], "./", 2) != 0) {
++ char *p;
++ if ((alloc = malloc(strlen(paths[j]) + 3)) == NULL) {
++ fprintf(stderr, "Cannot allocate memory for "
++ "builtin module object name %s.\n",
++ paths[j]);
++ exit(1);
++ }
++ p = alloc;
++ p = stpcpy(p, "./");
++ p = stpcpy(p, paths[j]);
++ path = alloc;
++ }
++ if (add_cu_mapping(path, module_name) < 0) {
++ fprintf(stderr, "Cannot add path -> module mapping for "
++ "%s -> %s: %s\n", path, module_name,
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++ free (alloc);
++ }
++ free(paths);
++ }
++ free(module_name);
++ modules_builtin_iter_free(i);
++}
++
++/*
++ * Strip the leading .ctf. off all the module names: transform the default name
++ * from _CTF_SECTION into shared_ctf, and chop any trailing .ctf off (since that
++ * derives from the intermediate file used to keep the CTF out of the final
++ * module).
++ */
++static char *transform_module_names(ctf_file_t *fp __attribute__((__unused__)),
++ const char *name,
++ void *arg __attribute__((__unused__)))
++{
++ if (strcmp(name, ".ctf") == 0)
++ return strdup("shared_ctf");
++
++ if (strncmp(name, ".ctf", 4) == 0) {
++ size_t n = strlen (name);
++ if (strcmp(name + n - 4, ".ctf") == 0)
++ n -= 4;
++ return strndup(name + 4, n - 4);
++ }
++ return NULL;
++}
++
++int main(int argc, char *argv[])
++{
++ int err;
++ const char *output_file;
++ unsigned char *file_data = NULL;
++ size_t file_size;
++ FILE *fp;
++
++ if (argc != 5) {
++ fprintf(stderr, "Syntax: ctfarchive output-file objects.builtin modules.builtin\n");
++ fprintf(stderr, " filelist\n");
++ exit(1);
++ }
++
++ output_file = argv[1];
++
++ /*
++ * First pull in the input files and add them to the link.
++ */
++
++ output = ctf_create(&err);
++ if (!output) {
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ ctf_errmsg(err));
++ return 1;
++ }
++
++ suck_in_lines(argv[4], add_to_link);
++
++ /*
++ * Make sure that, even if all their types are shared, all modules have
++ * a ctf member that can be used as a child of the shared CTF.
++ */
++ suck_in_lines(argv[4], add_cu_mappings);
++
++ /*
++ * Then pull in the builtin objects list and add them as
++ * mappings to "vmlinux".
++ */
++
++ suck_in_lines(argv[2], add_builtins);
++
++ /*
++ * Finally, pull in the object -> module mapping and add it
++ * as appropriate mappings.
++ */
++ suck_in_modules(argv[3]);
++
++ /*
++ * Commit the added CU mappings.
++ */
++ commit_cu_mappings();
++
++ /*
++ * Arrange to fix up the module names.
++ */
++ ctf_link_set_memb_name_changer(output, transform_module_names, NULL);
++
++ /*
++ * Do the link.
++ */
++ if (ctf_link(output, CTF_LINK_SHARE_DUPLICATED |
++ CTF_LINK_EMPTY_CU_MAPPINGS) < 0)
++ goto ctf_err;
++
++ /*
++ * Write the output.
++ */
++
++ file_data = ctf_link_write(output, &file_size, 4096);
++ if (!file_data)
++ goto ctf_err;
++
++ fp = fopen(output_file, "w");
++ if (!fp)
++ goto err;
++
++ while ((err = fwrite(file_data, file_size, 1, fp)) == 0);
++ if (ferror(fp)) {
++ errno = ferror(fp);
++ goto err;
++ }
++ if (fclose(fp) < 0)
++ goto err;
++ free(file_data);
++ ctf_file_close(output);
++
++ return 0;
++err:
++ free(file_data);
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ strerror(errno));
++ return 1;
++ctf_err:
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ ctf_errmsg(ctf_errno(output)));
++ return 1;
++}
+diff --git a/scripts/ctf/modules_builtin.c b/scripts/ctf/modules_builtin.c
+new file mode 100644
+index 0000000000000..10af2bbc80e0c
+--- /dev/null
++++ b/scripts/ctf/modules_builtin.c
+@@ -0,0 +1,2 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++#include "../modules_builtin.c"
+diff --git a/scripts/ctf/modules_builtin.h b/scripts/ctf/modules_builtin.h
+new file mode 100644
+index 0000000000000..5e0299e5600c2
+--- /dev/null
++++ b/scripts/ctf/modules_builtin.h
+@@ -0,0 +1,2 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++#include "../modules_builtin.h"
+diff --git a/scripts/generate_builtin_ranges.awk b/scripts/generate_builtin_ranges.awk
+new file mode 100755
+index 0000000000000..b9ec761b3befc
+--- /dev/null
++++ b/scripts/generate_builtin_ranges.awk
+@@ -0,0 +1,508 @@
++#!/usr/bin/gawk -f
++# SPDX-License-Identifier: GPL-2.0
++# generate_builtin_ranges.awk: Generate address range data for builtin modules
++# Written by Kris Van Hees <kris.van.hees@oracle.com>
++#
++# Usage: generate_builtin_ranges.awk modules.builtin vmlinux.map \
++# vmlinux.o.map > modules.builtin.ranges
++#
++
++# Return the module name(s) (if any) associated with the given object.
++#
++# If we have seen this object before, return information from the cache.
++# Otherwise, retrieve it from the corresponding .cmd file.
++#
++function get_module_info(fn, mod, obj, s) {
++ if (fn in omod)
++ return omod[fn];
++
++ if (match(fn, /\/[^/]+$/) == 0)
++ return "";
++
++ obj = fn;
++ mod = "";
++ fn = substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
++ if (getline s <fn == 1) {
++ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
++ mod = substr(s, RSTART + 16, RLENGTH - 16);
++ gsub(/['"]/, "", mod);
++ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
++ mod = substr(s, RSTART + 13, RLENGTH - 13);
++ }
++ close(fn);
++
++ # A single module (common case) also reflects objects that are not part
++ # of a module. Some of those objects have names that are also a module
++ # name (e.g. core). We check the associated module file name, and if
++ # they do not match, the object is not part of a module.
++ if (mod !~ / /) {
++ if (!(mod in mods))
++ mod = "";
++ }
++
++ gsub(/([^/ ]*\/)+/, "", mod);
++ gsub(/-/, "_", mod);
++
++ # At this point, mod is a single (valid) module name, or a list of
++ # module names (that do not need validation).
++ omod[obj] = mod;
++
++ return mod;
++}
++
++# Update the ranges entry for the given module 'mod' in section 'osect'.
++#
++# We use a modified absolute start address (soff + base) as index because we
++# may need to insert an anchor record later that must be at the start of the
++# section data, and the first module may very well start at the same address.
++# So, we use (addr << 1) + 1 to allow a possible anchor record to be placed at
++# (addr << 1). This is safe because the index is only used to sort the entries
++# before writing them out.
++#
++function update_entry(osect, mod, soff, eoff, sect, idx) {
++ sect = sect_in[osect];
++ idx = sprintf("%016x", (soff + sect_base[osect]) * 2 + 1);
++ entries[idx] = sprintf("%s %08x-%08x %s", sect, soff, eoff, mod);
++ count[sect]++;
++}
++
++# (1) Build a lookup map of built-in module names.
++#
++# The first file argument is used as input (modules.builtin).
++#
++# Lines will be like:
++# kernel/crypto/lzo-rle.ko
++# and we record the object name "crypto/lzo-rle".
++#
++ARGIND == 1 {
++ sub(/kernel\//, ""); # strip off "kernel/" prefix
++ sub(/\.ko$/, ""); # strip off .ko suffix
++
++ mods[$1] = 1;
++ next;
++}
++
++# (2) Collect address information for each section.
++#
++# The second file argument is used as input (vmlinux.map).
++#
++# We collect the base address of the section in order to convert all addresses
++# in the section into offset values.
++#
++# We collect the address of the anchor (or first symbol in the section if there
++# is no explicit anchor) to allow users of the range data to calculate address
++# ranges based on the actual load address of the section in the running kernel.
++#
++# We collect the start address of any sub-section (section included in the top
++# level section being processed). This is needed when the final linking was
++# done using vmlinux.a because then the list of objects contained in each
++# section is to be obtained from vmlinux.o.map. The offset of the sub-section
++# is recorded here, to be used as an addend when processing vmlinux.o.map
++# later.
++#
++
++# Both GNU ld and LLVM lld linker map format are supported by converting LLVM
++# lld linker map records into equivalent GNU ld linker map records.
++#
++# The first record of the vmlinux.map file provides enough information to know
++# which format we are dealing with.
++#
++ARGIND == 2 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
++ map_is_lld = 1;
++ if (dbg)
++ printf "NOTE: %s uses LLVM lld linker map format\n", FILENAME >"/dev/stderr";
++ next;
++}
++
++# (LLD) Convert a section record fronm lld format to ld format.
++#
++# lld: ffffffff82c00000 2c00000 2493c0 8192 .data
++# ->
++# ld: .data 0xffffffff82c00000 0x2493c0 load address 0x0000000002c00000
++#
++ARGIND == 2 && map_is_lld && NF == 5 && /[0-9] [^ ]+$/ {
++ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
++}
++
++# (LLD) Convert an anchor record from lld format to ld format.
++#
++# lld: ffffffff81000000 1000000 0 1 _text = .
++# ->
++# ld: 0xffffffff81000000 _text = .
++#
++ARGIND == 2 && map_is_lld && !anchor && NF == 7 && raw_addr == "0x"$1 && $6 == "=" && $7 == "." {
++ $0 = " 0x"$1 " " $5 " = .";
++}
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++# lld: 11480 11480 1f07 16 vmlinux.a(arch/x86/events/amd/uncore.o):(.text)
++# ->
++# ld: .text 0x0000000000011480 0x1f07 arch/x86/events/amd/uncore.o
++#
++ARGIND == 2 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
++ gsub(/\)/, "");
++ sub(/ vmlinux\.a\(/, " ");
++ sub(/:\(/, " ");
++ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (LLD) Convert a symbol record from lld format to ld format.
++#
++# We only care about these while processing a section for which no anchor has
++# been determined yet.
++#
++# lld: ffffffff82a859a4 2a859a4 0 1 btf_ksym_iter_id
++# ->
++# ld: 0xffffffff82a859a4 btf_ksym_iter_id
++#
++ARGIND == 2 && map_is_lld && sect && !anchor && NF == 5 && $5 ~ /^[_A-Za-z][_A-Za-z0-9]*$/ {
++ $0 = " 0x"$1 " " $5;
++}
++
++# (LLD) We do not need any other ldd linker map records.
++#
++ARGIND == 2 && map_is_lld && /^[0-9a-f]{16} / {
++ next;
++}
++
++# (LD) Section records with just the section name at the start of the line
++# need to have the next line pulled in to determine whether it is a
++# loadable section. If it is, the next line will contains a hex value
++# as first and second items.
++#
++ARGIND == 2 && !map_is_lld && NF == 1 && /^[^ ]/ {
++ s = $0;
++ getline;
++ if ($1 !~ /^0x/ || $2 !~ /^0x/)
++ next;
++
++ $0 = s " " $0;
++}
++
++# (LD) Object records with just the section name denote records with a long
++# section name for which the remainder of the record can be found on the
++# next line.
++#
++# (This is also needed for vmlinux.o.map, when used.)
++#
++ARGIND >= 2 && !map_is_lld && NF == 1 && /^ [^ \*]/ {
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# Beginning a new section - done with the previous one (if any).
++#
++ARGIND == 2 && /^[^ ]/ {
++ sect = 0;
++}
++
++# Process a loadable section (we only care about .-sections).
++#
++# Record the section name and its base address.
++# We also record the raw (non-stripped) address of the section because it can
++# be used to identify an anchor record.
++#
++# Note:
++# Since some AWK implementations cannot handle large integers, we strip off the
++# first 4 hex digits from the address. This is safe because the kernel space
++# is not large enough for addresses to extend into those digits. The portion
++# to strip off is stored in addr_prefix as a regexp, so further clauses can
++# perform a simple substitution to do the address stripping.
++#
++ARGIND == 2 && /^\./ {
++ # Explicitly ignore a few sections that are not relevant here.
++ if ($1 ~ /^\.orc_/ || $1 ~ /_sites$/ || $1 ~ /\.percpu/)
++ next;
++
++ # Sections with a 0-address can be ignored as well.
++ if ($2 ~ /^0x0+$/)
++ next;
++
++ raw_addr = $2;
++ addr_prefix = "^" substr($2, 1, 6);
++ base = $2;
++ sub(addr_prefix, "0x", base);
++ base = strtonum(base);
++ sect = $1;
++ anchor = 0;
++ sect_base[sect] = base;
++ sect_size[sect] = strtonum($3);
++
++ if (dbg)
++ printf "[%s] BASE %016x\n", sect, base >"/dev/stderr";
++
++ next;
++}
++
++# If we are not in a section we care about, we ignore the record.
++#
++ARGIND == 2 && !sect {
++ next;
++}
++
++# Record the first anchor symbol for the current section.
++#
++# An anchor record for the section bears the same raw address as the section
++# record.
++#
++ARGIND == 2 && !anchor && NF == 4 && raw_addr == $1 && $3 == "=" && $4 == "." {
++ anchor = sprintf("%s %08x-%08x = %s", sect, 0, 0, $2);
++ sect_anchor[sect] = anchor;
++
++ if (dbg)
++ printf "[%s] ANCHOR %016x = %s (.)\n", sect, 0, $2 >"/dev/stderr";
++
++ next;
++}
++
++# If no anchor record was found for the current section, use the first symbol
++# in the section as anchor.
++#
++ARGIND == 2 && !anchor && NF == 2 && $1 ~ /^0x/ && $2 !~ /^0x/ {
++ addr = $1;
++ sub(addr_prefix, "0x", addr);
++ addr = strtonum(addr) - base;
++ anchor = sprintf("%s %08x-%08x = %s", sect, addr, addr, $2);
++ sect_anchor[sect] = anchor;
++
++ if (dbg)
++ printf "[%s] ANCHOR %016x = %s\n", sect, addr, $2 >"/dev/stderr";
++
++ next;
++}
++
++# The first occurrence of a section name in an object record establishes the
++# addend (often 0) for that section. This information is needed to handle
++# sections that get combined in the final linking of vmlinux (e.g. .head.text
++# getting included at the start of .text).
++#
++# If the section does not have a base yet, use the base of the encapsulating
++# section.
++#
++ARGIND == 2 && sect && NF == 4 && /^ [^ \*]/ && !($1 in sect_addend) {
++ if (!($1 in sect_base)) {
++ sect_base[$1] = base;
++
++ if (dbg)
++ printf "[%s] BASE %016x\n", $1, base >"/dev/stderr";
++ }
++
++ addr = $2;
++ sub(addr_prefix, "0x", addr);
++ addr = strtonum(addr);
++ sect_addend[$1] = addr - sect_base[$1];
++ sect_in[$1] = sect;
++
++ if (dbg)
++ printf "[%s] ADDEND %016x - %016x = %016x\n", $1, addr, base, sect_addend[$1] >"/dev/stderr";
++
++ # If the object is vmlinux.o then we will need vmlinux.o.map to get the
++ # actual offsets of objects.
++ if ($4 == "vmlinux.o")
++ need_o_map = 1;
++}
++
++# (3) Collect offset ranges (relative to the section base address) for built-in
++# modules.
++#
++# If the final link was done using the actual objects, vmlinux.map contains all
++# the information we need (see section (3a)).
++# If linking was done using vmlinux.a as intermediary, we will need to process
++# vmlinux.o.map (see section (3b)).
++
++# (3a) Determine offset range info using vmlinux.map.
++#
++# Since we are already processing vmlinux.map, the top level section that is
++# being processed is already known. If we do not have a base address for it,
++# we do not need to process records for it.
++#
++# Given the object name, we determine the module(s) (if any) that the current
++# object is associated with.
++#
++# If we were already processing objects for a (list of) module(s):
++# - If the current object belongs to the same module(s), update the range data
++# to include the current object.
++# - Otherwise, ensure that the end offset of the range is valid.
++#
++# If the current object does not belong to a built-in module, ignore it.
++#
++# If it does, we add a new built-in module offset range record.
++#
++ARGIND == 2 && !need_o_map && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
++ if (!(sect in sect_base))
++ next;
++
++ # Turn the address into an offset from the section base.
++ soff = $2;
++ sub(addr_prefix, "0x", soff);
++ soff = strtonum(soff) - sect_base[sect];
++ eoff = soff + strtonum($3);
++
++ # Determine which (if any) built-in modules the object belongs to.
++ mod = get_module_info($4);
++
++ # If we are processing a built-in module:
++ # - If the current object is within the same module, we update its
++ # entry by extending the range and move on
++ # - Otherwise:
++ # + If we are still processing within the same main section, we
++ # validate the end offset against the start offset of the
++ # current object (e.g. .rodata.str1.[18] objects are often
++ # listed with an incorrect size in the linker map)
++ # + Otherwise, we validate the end offset against the section
++ # size
++ if (mod_name) {
++ if (mod == mod_name) {
++ mod_eoff = eoff;
++ update_entry(mod_sect, mod_name, mod_soff, eoff);
++
++ next;
++ } else if (sect == sect_in[mod_sect]) {
++ if (mod_eoff > soff)
++ update_entry(mod_sect, mod_name, mod_soff, soff);
++ } else {
++ v = sect_size[sect_in[mod_sect]];
++ if (mod_eoff > v)
++ update_entry(mod_sect, mod_name, mod_soff, v);
++ }
++ }
++
++ mod_name = mod;
++
++ # If we encountered an object that is not part of a built-in module, we
++ # do not need to record any data.
++ if (!mod)
++ next;
++
++ # At this point, we encountered the start of a new built-in module.
++ mod_name = mod;
++ mod_soff = soff;
++ mod_eoff = eoff;
++ mod_sect = $1;
++ update_entry($1, mod, soff, mod_eoff);
++
++ next;
++}
++
++# If we do not need to parse the vmlinux.o.map file, we are done.
++#
++ARGIND == 3 && !need_o_map {
++ if (dbg)
++ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
++ exit;
++}
++
++# (3) Collect offset ranges (relative to the section base address) for built-in
++# modules.
++#
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++ARGIND == 3 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
++ gsub(/\)/, "");
++ sub(/:\(/, " ");
++
++ sect = $6;
++ if (!(sect in sect_addend))
++ next;
++
++ sub(/ vmlinux\.a\(/, " ");
++ $0 = " "sect " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (3b) Determine offset range info using vmlinux.o.map.
++#
++# If we do not know an addend for the object's section, we are interested in
++# anything within that section.
++#
++# Determine the top-level section that the object's section was included in
++# during the final link. This is the section name offset range data will be
++# associated with for this object.
++#
++# The remainder of the processing of the current object record follows the
++# procedure outlined in (3a).
++#
++ARGIND == 3 && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
++ osect = $1;
++ if (!(osect in sect_addend))
++ next;
++
++ # We need to work with the main section.
++ sect = sect_in[osect];
++
++ # Turn the address into an offset from the section base.
++ soff = $2;
++ sub(addr_prefix, "0x", soff);
++ soff = strtonum(soff) + sect_addend[osect];
++ eoff = soff + strtonum($3);
++
++ # Determine which (if any) built-in modules the object belongs to.
++ mod = get_module_info($4);
++
++ # If we are processing a built-in module:
++ # - If the current object is within the same module, we update its
++ # entry by extending the range and move on
++ # - Otherwise:
++ # + If we are still processing within the same main section, we
++ # validate the end offset against the start offset of the
++ # current object (e.g. .rodata.str1.[18] objects are often
++ # listed with an incorrect size in the linker map)
++ # + Otherwise, we validate the end offset against the section
++ # size
++ if (mod_name) {
++ if (mod == mod_name) {
++ mod_eoff = eoff;
++ update_entry(mod_sect, mod_name, mod_soff, eoff);
++
++ next;
++ } else if (sect == sect_in[mod_sect]) {
++ if (mod_eoff > soff)
++ update_entry(mod_sect, mod_name, mod_soff, soff);
++ } else {
++ v = sect_size[sect_in[mod_sect]];
++ if (mod_eoff > v)
++ update_entry(mod_sect, mod_name, mod_soff, v);
++ }
++ }
++
++ mod_name = mod;
++
++ # If we encountered an object that is not part of a built-in module, we
++ # do not need to record any data.
++ if (!mod)
++ next;
++
++ # At this point, we encountered the start of a new built-in module.
++ mod_name = mod;
++ mod_soff = soff;
++ mod_eoff = eoff;
++ mod_sect = osect;
++ update_entry(osect, mod, soff, mod_eoff);
++
++ next;
++}
++
++# (4) Generate the output.
++#
++# Anchor records are added for each section that contains offset range data
++# records. They are added at an adjusted section base address (base << 1) to
++# ensure they come first in the second records (see update_entry() above for
++# more information).
++#
++# All entries are sorted by (adjusted) address to ensure that the output can be
++# parsed in strict ascending address order.
++#
++END {
++ for (sect in count) {
++ if (sect in sect_anchor) {
++ idx = sprintf("%016x", sect_base[sect] * 2);
++ entries[idx] = sect_anchor[sect];
++ }
++ }
++
++ n = asorti(entries, indices);
++ for (i = 1; i <= n; i++)
++ print entries[indices[i]];
++}
+diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
+index f48d72d22dc2a..d7e6cd7781256 100644
+--- a/scripts/mod/modpost.c
++++ b/scripts/mod/modpost.c
+@@ -733,6 +733,7 @@ static const char *const section_white_list[] =
+ ".comment*",
+ ".debug*",
+ ".zdebug*", /* Compressed debug sections. */
++ ".ctf", /* Type info */
+ ".GCC.command.line", /* record-gcc-switches */
+ ".mdebug*", /* alpha, score, mips etc. */
+ ".pdr", /* alpha, score, mips etc. */
+diff --git a/scripts/modules_builtin.c b/scripts/modules_builtin.c
+new file mode 100644
+index 0000000000000..df52932a4417b
+--- /dev/null
++++ b/scripts/modules_builtin.c
+@@ -0,0 +1,200 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * A simple modules_builtin reader.
++ *
++ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#include <errno.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <string.h>
++
++#include "modules_builtin.h"
++
++/*
++ * Read a modules.builtin.objs file and translate it into a stream of
++ * name / module-name pairs.
++ */
++
++/*
++ * Construct a modules.builtin.objs iterator.
++ */
++struct modules_builtin_iter *
++modules_builtin_iter_new(const char *modules_builtin_file)
++{
++ struct modules_builtin_iter *i;
++
++ i = calloc(1, sizeof(struct modules_builtin_iter));
++ if (i == NULL)
++ return NULL;
++
++ i->f = fopen(modules_builtin_file, "r");
++
++ if (i->f == NULL) {
++ fprintf(stderr, "Cannot open builtin module file %s: %s\n",
++ modules_builtin_file, strerror(errno));
++ return NULL;
++ }
++
++ return i;
++}
++
++/*
++ * Iterate, returning a new null-terminated array of object file names, and a
++ * new dynamically-allocated module name. (The module name passed in is freed.)
++ *
++ * The array of object file names should be freed by the caller: the strings it
++ * points to are owned by the iterator, and should not be freed.
++ */
++
++char ** __attribute__((__nonnull__))
++modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name)
++{
++ size_t npaths = 1;
++ char **module_paths;
++ char *last_slash;
++ char *last_dot;
++ char *trailing_linefeed;
++ char *object_name = i->line;
++ char *dash;
++ int composite = 0;
++
++ /*
++ * Read in all module entries, computing the suffixless, pathless name
++ * of the module and building the next arrayful of object file names for
++ * return.
++ *
++ * Modules can consist of multiple files: in this case, the portion
++ * before the colon is the path to the module (as before): the portion
++ * after the colon is a space-separated list of files that should be
++ * considered part of this module. In this case, the portion before the
++ * name is an "object file" that does not actually exist: it is merged
++ * into built-in.a without ever being written out.
++ *
++ * All module names have - translated to _, to match what is done to the
++ * names of the same things when built as modules.
++ */
++
++ /*
++ * Reinvocation of exhausted iterator. Return NULL, once.
++ */
++retry:
++ if (getline(&i->line, &i->line_size, i->f) < 0) {
++ if (ferror(i->f)) {
++ fprintf(stderr, "Error reading from modules_builtin file:"
++ " %s\n", strerror(errno));
++ exit(1);
++ }
++ rewind(i->f);
++ return NULL;
++ }
++
++ if (i->line[0] == '\0')
++ goto retry;
++
++ trailing_linefeed = strchr(i->line, '\n');
++ if (trailing_linefeed != NULL)
++ *trailing_linefeed = '\0';
++
++ /*
++ * Slice the line in two at the colon, if any. If there is anything
++ * past the ': ', this is a composite module. (We allow for no colon
++ * for robustness, even though one should always be present.)
++ */
++ if (strchr(i->line, ':') != NULL) {
++ char *name_start;
++
++ object_name = strchr(i->line, ':');
++ *object_name = '\0';
++ object_name++;
++ name_start = object_name + strspn(object_name, " \n");
++ if (*name_start != '\0') {
++ composite = 1;
++ object_name = name_start;
++ }
++ }
++
++ /*
++ * Figure out the module name.
++ */
++ last_slash = strrchr(i->line, '/');
++ last_slash = (!last_slash) ? i->line :
++ last_slash + 1;
++ free(*module_name);
++ *module_name = strdup(last_slash);
++ dash = *module_name;
++
++ while (dash != NULL) {
++ dash = strchr(dash, '-');
++ if (dash != NULL)
++ *dash = '_';
++ }
++
++ last_dot = strrchr(*module_name, '.');
++ if (last_dot != NULL)
++ *last_dot = '\0';
++
++ /*
++ * Multifile separator? Object file names explicitly stated:
++ * slice them up and shuffle them in.
++ *
++ * The array size may be an overestimate if any object file
++ * names start or end with spaces (very unlikely) but cannot be
++ * an underestimate. (Check for it anyway.)
++ */
++ if (composite) {
++ char *one_object;
++
++ for (npaths = 0, one_object = object_name;
++ one_object != NULL;
++ npaths++, one_object = strchr(one_object + 1, ' '));
++ }
++
++ module_paths = malloc((npaths + 1) * sizeof(char *));
++ if (!module_paths) {
++ fprintf(stderr, "%s: out of memory on module %s\n", __func__,
++ *module_name);
++ exit(1);
++ }
++
++ if (composite) {
++ char *one_object;
++ size_t i = 0;
++
++ while ((one_object = strsep(&object_name, " ")) != NULL) {
++ if (i >= npaths) {
++ fprintf(stderr, "%s: num_objs overflow on module "
++ "%s: this is a bug.\n", __func__,
++ *module_name);
++ exit(1);
++ }
++
++ module_paths[i++] = one_object;
++ }
++ } else
++ module_paths[0] = i->line; /* untransformed module name */
++
++ module_paths[npaths] = NULL;
++
++ return module_paths;
++}
++
++/*
++ * Free an iterator. Can be called while iteration is underway, so even
++ * state that is freed at the end of iteration must be freed here too.
++ */
++void
++modules_builtin_iter_free(struct modules_builtin_iter *i)
++{
++ if (i == NULL)
++ return;
++ fclose(i->f);
++ free(i->line);
++ free(i);
++}
+diff --git a/scripts/modules_builtin.h b/scripts/modules_builtin.h
+new file mode 100644
+index 0000000000000..5138792b42ef0
+--- /dev/null
++++ b/scripts/modules_builtin.h
+@@ -0,0 +1,48 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * A simple modules.builtin.objs reader.
++ *
++ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#ifndef _LINUX_MODULES_BUILTIN_H
++#define _LINUX_MODULES_BUILTIN_H
++
++#include <stdio.h>
++#include <stddef.h>
++
++/*
++ * modules.builtin.objs iteration state.
++ */
++struct modules_builtin_iter {
++ FILE *f;
++ char *line;
++ size_t line_size;
++};
++
++/*
++ * Construct a modules_builtin.objs iterator.
++ */
++struct modules_builtin_iter *
++modules_builtin_iter_new(const char *modules_builtin_file);
++
++/*
++ * Iterate, returning a new null-terminated array of object file names, and a
++ * new dynamically-allocated module name. (The module name passed in is freed.)
++ *
++ * The array of object file names should be freed by the caller: the strings it
++ * points to are owned by the iterator, and should not be freed.
++ */
++
++char ** __attribute__((__nonnull__))
++modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name);
++
++void
++modules_builtin_iter_free(struct modules_builtin_iter *i);
++
++#endif
+diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
+index c52d517b93647..8f75906a96314 100644
+--- a/scripts/package/kernel.spec
++++ b/scripts/package/kernel.spec
+@@ -53,12 +53,18 @@ patch -p1 < %{SOURCE2}
+
+ %build
+ %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
++%if %{with_ctf}
++%{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release} ctf
++%endif
+
+ %install
+ mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
+ cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
+ # DEPMOD=true makes depmod no-op. We do not package depmod-generated files.
+ %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} DEPMOD=true modules_install
++%if %{with_ctf}
++%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} ctf_install
++%endif
+ %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
+ cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
+ cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
+diff --git a/scripts/package/mkspec b/scripts/package/mkspec
+index ce201bfa8377c..aeb43c7ab1229 100755
+--- a/scripts/package/mkspec
++++ b/scripts/package/mkspec
+@@ -21,10 +21,16 @@ else
+ echo '%define with_devel 0'
+ fi
+
++if grep -q CONFIG_CTF=y include/config/auto.conf; then
++echo '%define with_ctf %{?_without_ctf: 0} %{?!_without_ctf: 1}'
++else
++echo '%define with_ctf 0'
++fi
+ cat<<EOF
+ %define ARCH ${ARCH}
+ %define KERNELRELEASE ${KERNELRELEASE}
+ %define pkg_release $("${srctree}/init/build-version")
++
+ EOF
+
+ cat "${srctree}/scripts/package/kernel.spec"
+diff --git a/scripts/remove-ctf-lds.awk b/scripts/remove-ctf-lds.awk
+new file mode 100644
+index 0000000000000..5d94d6ee99227
+--- /dev/null
++++ b/scripts/remove-ctf-lds.awk
+@@ -0,0 +1,12 @@
++# SPDX-License-Identifier: GPL-2.0
++# See Makefile.vmlinux_o
++
++BEGIN {
++ discards = 0; p = 0
++}
++
++/^====/ { p = 1; next; }
++p && /\.ctf/ { next; }
++p && !discards && /DISCARD/ { sub(/\} *$/, " *(.ctf) }"); discards = 1 }
++p && /^\}/ && !discards { print " /DISCARD/ : { *(.ctf) }"; }
++p { print $0; }
+diff --git a/scripts/verify_builtin_ranges.awk b/scripts/verify_builtin_ranges.awk
+new file mode 100755
+index 0000000000000..0de7ed5216011
+--- /dev/null
++++ b/scripts/verify_builtin_ranges.awk
+@@ -0,0 +1,370 @@
++#!/usr/bin/gawk -f
++# SPDX-License-Identifier: GPL-2.0
++# verify_builtin_ranges.awk: Verify address range data for builtin modules
++# Written by Kris Van Hees <kris.van.hees@oracle.com>
++#
++# Usage: verify_builtin_ranges.awk modules.builtin.ranges System.map \
++# modules.builtin vmlinux.map vmlinux.o.map
++#
++
++# Return the module name(s) (if any) associated with the given object.
++#
++# If we have seen this object before, return information from the cache.
++# Otherwise, retrieve it from the corresponding .cmd file.
++#
++function get_module_info(fn, mod, obj, s) {
++ if (fn in omod)
++ return omod[fn];
++
++ if (match(fn, /\/[^/]+$/) == 0)
++ return "";
++
++ obj = fn;
++ mod = "";
++ fn = substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
++ if (getline s <fn == 1) {
++ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
++ mod = substr(s, RSTART + 16, RLENGTH - 16);
++ gsub(/['"]/, "", mod);
++ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
++ mod = substr(s, RSTART + 13, RLENGTH - 13);
++ } else {
++ print "ERROR: Failed to read: " fn "\n\n" \
++ " For kernels built with O=<objdir>, cd to <objdir>\n" \
++ " and execute this script as ./source/scripts/..." \
++ >"/dev/stderr";
++ close(fn);
++ total = 0;
++ exit(1);
++ }
++ close(fn);
++
++ # A single module (common case) also reflects objects that are not part
++ # of a module. Some of those objects have names that are also a module
++ # name (e.g. core). We check the associated module file name, and if
++ # they do not match, the object is not part of a module.
++ if (mod !~ / /) {
++ if (!(mod in mods))
++ mod = "";
++ }
++
++ gsub(/([^/ ]*\/)+/, "", mod);
++ gsub(/-/, "_", mod);
++
++ # At this point, mod is a single (valid) module name, or a list of
++ # module names (that do not need validation).
++ omod[obj] = mod;
++
++ return mod;
++}
++
++# Return a representative integer value for a given hexadecimal address.
++#
++# Since all kernel addresses fall within the same memory region, we can safely
++# strip off the first 6 hex digits before performing the hex-to-dec conversion,
++# thereby avoiding integer overflows.
++#
++function addr2val(val) {
++ sub(/^0x/, "", val);
++ if (length(val) == 16)
++ val = substr(val, 5);
++ return strtonum("0x" val);
++}
++
++# Determine the kernel build directory to use (default is .).
++#
++BEGIN {
++ if (ARGC < 6) {
++ print "Syntax: verify_builtin_ranges.awk <ranges-file> <system-map>\n" \
++ " <builtin-file> <vmlinux-map> <vmlinux-o-map>\n" \
++ >"/dev/stderr";
++ total = 0;
++ exit(1);
++ }
++}
++
++# (1) Load the built-in module address range data.
++#
++ARGIND == 1 {
++ ranges[FNR] = $0;
++ rcnt++;
++ next;
++}
++
++# (2) Annotate System.map symbols with module names.
++#
++ARGIND == 2 {
++ addr = addr2val($1);
++ name = $3;
++
++ while (addr >= mod_eaddr) {
++ if (sect_symb) {
++ if (sect_symb != name)
++ next;
++
++ sect_base = addr - sect_off;
++ if (dbg)
++ printf "[%s] BASE (%s) %016x - %016x = %016x\n", sect_name, sect_symb, addr, sect_off, sect_base >"/dev/stderr";
++ sect_symb = 0;
++ }
++
++ if (++ridx > rcnt)
++ break;
++
++ $0 = ranges[ridx];
++ sub(/-/, " ");
++ if ($4 != "=") {
++ sub(/-/, " ");
++ mod_saddr = strtonum("0x" $2) + sect_base;
++ mod_eaddr = strtonum("0x" $3) + sect_base;
++ $1 = $2 = $3 = "";
++ sub(/^ +/, "");
++ mod_name = $0;
++
++ if (dbg)
++ printf "[%s] %s from %016x to %016x\n", sect_name, mod_name, mod_saddr, mod_eaddr >"/dev/stderr";
++ } else {
++ sect_name = $1;
++ sect_off = strtonum("0x" $2);
++ sect_symb = $5;
++ }
++ }
++
++ idx = addr"-"name;
++ if (addr >= mod_saddr && addr < mod_eaddr)
++ sym2mod[idx] = mod_name;
++
++ next;
++}
++
++# Once we are done annotating the System.map, we no longer need the ranges data.
++#
++FNR == 1 && ARGIND == 3 {
++ delete ranges;
++}
++
++# (3) Build a lookup map of built-in module names.
++#
++# Lines from modules.builtin will be like:
++# kernel/crypto/lzo-rle.ko
++# and we record the object name "crypto/lzo-rle".
++#
++ARGIND == 3 {
++ sub(/kernel\//, ""); # strip off "kernel/" prefix
++ sub(/\.ko$/, ""); # strip off .ko suffix
++
++ mods[$1] = 1;
++ next;
++}
++
++# (4) Get a list of symbols (per object).
++#
++# Symbols by object are read from vmlinux.map, with fallback to vmlinux.o.map
++# if vmlinux is found to have inked in vmlinux.o.
++#
++
++# If we were able to get the data we need from vmlinux.map, there is no need to
++# process vmlinux.o.map.
++#
++FNR == 1 && ARGIND == 5 && total > 0 {
++ if (dbg)
++ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
++ exit;
++}
++
++# First determine whether we are dealing with a GNU ld or LLVM lld linker map.
++#
++ARGIND >= 4 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
++ map_is_lld = 1;
++ next;
++}
++
++# (LLD) Convert a section record fronm lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && /[0-9] [^ ]+$/ {
++ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
++}
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
++ if (/\.a\(/ && !/ vmlinux\.a\(/)
++ next;
++
++ gsub(/\)/, "");
++ sub(/:\(/, " ");
++ sub(/ vmlinux\.a\(/, " ");
++ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (LLD) Convert a symbol record from lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /^[A-Za-z_][A-Za-z0-9_]*$/ {
++ $0 = " 0x" $1 " " $5;
++}
++
++# (LLD) We do not need any other ldd linker map records.
++#
++ARGIND >= 4 && map_is_lld && /^[0-9a-f]{16} / {
++ next;
++}
++
++# Handle section records with long section names (spilling onto a 2nd line).
++#
++ARGIND >= 4 && !map_is_lld && NF == 1 && /^[^ ]/ {
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# Next section - previous one is done.
++#
++ARGIND >= 4 && /^[^ ]/ {
++ sect = 0;
++}
++
++# Get the (top level) section name.
++#
++ARGIND >= 4 && /^\./ {
++ # Explicitly ignore a few sections that are not relevant here.
++ if ($1 ~ /^\.orc_/ || $1 ~ /_sites$/ || $1 ~ /\.percpu/)
++ next;
++
++ # Sections with a 0-address can be ignored as well (in vmlinux.map).
++ if (ARGIND == 4 && $2 ~ /^0x0+$/)
++ next;
++
++ sect = $1;
++
++ next;
++}
++
++# If we are not currently in a section we care about, ignore records.
++#
++!sect {
++ next;
++}
++
++# Handle object records with long section names (spilling onto a 2nd line).
++#
++ARGIND >= 4 && /^ [^ \*]/ && NF == 1 {
++ # If the section name is long, the remainder of the entry is found on
++ # the next line.
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# Objects linked in from static libraries are ignored.
++# If the object is vmlinux.o, we need to consult vmlinux.o.map for per-object
++# symbol information
++#
++ARGIND == 4 && /^ [^ ]/ && NF == 4 {
++ if ($4 ~ /\.a\(/)
++ next;
++
++ idx = sect":"$1;
++ if (!(idx in sect_addend)) {
++ sect_addend[idx] = addr2val($2);
++ if (dbg)
++ printf "ADDEND %s = %016x\n", idx, sect_addend[idx] >"/dev/stderr";
++ }
++ if ($4 == "vmlinux.o") {
++ need_o_map = 1;
++ next;
++ }
++}
++
++# If data from vmlinux.o.map is needed, we only process section and object
++# records from vmlinux.map to determine which section we need to pay attention
++# to in vmlinux.o.map. So skip everything else from vmlinux.map.
++#
++ARGIND == 4 && need_o_map {
++ next;
++}
++
++# Get module information for the current object.
++#
++ARGIND >= 4 && /^ [^ ]/ && NF == 4 {
++ msect = $1;
++ mod_name = get_module_info($4);
++ mod_eaddr = addr2val($2) + addr2val($3);
++
++ next;
++}
++
++# Process a symbol record.
++#
++# Evaluate the module information obtained from vmlinux.map (or vmlinux.o.map)
++# as follows:
++# - For all symbols in a given object:
++# - If the symbol is annotated with the same module name(s) that the object
++# belongs to, count it as a match.
++# - Otherwise:
++# - If the symbol is known to have duplicates of which at least one is
++# in a built-in module, disregard it.
++# - If the symbol us not annotated with any module name(s) AND the
++# object belongs to built-in modules, count it as missing.
++# - Otherwise, count it as a mismatch.
++#
++ARGIND >= 4 && /^ / && NF == 2 && $1 ~ /^0x/ {
++ idx = sect":"msect;
++ if (!(idx in sect_addend))
++ next;
++
++ addr = addr2val($1);
++
++ # Handle the rare but annoying case where a 0-size symbol is placed at
++ # the byte *after* the module range. Based on vmlinux.map it will be
++ # considered part of the current object, but it falls just beyond the
++ # module address range. Unfortunately, its address could be at the
++ # start of another built-in module, so the only safe thing to do is to
++ # ignore it.
++ if (mod_name && addr == mod_eaddr)
++ next;
++
++ # If we are processing vmlinux.o.map, we need to apply the base address
++ # of the section to the relative address on the record.
++ #
++ if (ARGIND == 5)
++ addr += sect_addend[idx];
++
++ idx = addr"-"$2;
++ mod = "";
++ if (idx in sym2mod) {
++ mod = sym2mod[idx];
++ if (sym2mod[idx] == mod_name) {
++ mod_matches++;
++ matches++;
++ } else if (mod_name == "") {
++ print $2 " in " mod " (should NOT be)";
++ mismatches++;
++ } else {
++ print $2 " in " mod " (should be " mod_name ")";
++ mismatches++;
++ }
++ } else if (mod_name != "") {
++ print $2 " should be in " mod_name;
++ missing++;
++ } else
++ matches++;
++
++ total++;
++
++ next;
++}
++
++# Issue the comparison report.
++#
++END {
++ if (total) {
++ printf "Verification of %s:\n", ARGV[1];
++ printf " Correct matches: %6d (%d%% of total)\n", matches, 100 * matches / total;
++ printf " Module matches: %6d (%d%% of matches)\n", mod_matches, 100 * mod_matches / matches;
++ printf " Mismatches: %6d (%d%% of total)\n", mismatches, 100 * mismatches / total;
++ printf " Missing: %6d (%d%% of total)\n", missing, 100 * missing / total;
++
++ if (mismatches || missing)
++ exit(1);
++ }
++}
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-18 18:01 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-18 18:01 UTC (permalink / raw
To: gentoo-commits
commit: a8b69318d24bf26247b03424e6663c02a7d0b5c5
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Sep 18 18:01:30 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Sep 18 18:01:30 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=a8b69318
Linux patch 6.10.11
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1010_linux-6.10.11.patch | 4668 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 4672 insertions(+)
diff --git a/0000_README b/0000_README
index fbbb6719..f48df58b 100644
--- a/0000_README
+++ b/0000_README
@@ -83,6 +83,10 @@ Patch: 1009_linux-6.10.10.patch
From: https://www.kernel.org
Desc: Linux 6.10.10
+Patch: 1010_linux-6.10.11.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.11
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1010_linux-6.10.11.patch b/1010_linux-6.10.11.patch
new file mode 100644
index 00000000..76b166b4
--- /dev/null
+++ b/1010_linux-6.10.11.patch
@@ -0,0 +1,4668 @@
+diff --git a/Documentation/netlink/specs/mptcp_pm.yaml b/Documentation/netlink/specs/mptcp_pm.yaml
+index af525ed2979234..30d8342cacc870 100644
+--- a/Documentation/netlink/specs/mptcp_pm.yaml
++++ b/Documentation/netlink/specs/mptcp_pm.yaml
+@@ -109,7 +109,6 @@ attribute-sets:
+ -
+ name: port
+ type: u16
+- byte-order: big-endian
+ -
+ name: flags
+ type: u32
+diff --git a/Makefile b/Makefile
+index 9b4614c0fcbb68..447856c43b3275 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 10
++SUBLEVEL = 11
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
+index a608a219543e59..3e08e2fd0a7828 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3328-rock-pi-e.dts
+@@ -387,7 +387,7 @@ led_pin: led-pin {
+
+ pmic {
+ pmic_int_l: pmic-int-l {
+- rockchip,pins = <2 RK_PA6 RK_FUNC_GPIO &pcfg_pull_up>;
++ rockchip,pins = <0 RK_PA2 RK_FUNC_GPIO &pcfg_pull_up>;
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+index ccbe3a7a1d2c2f..d24444cdf54afa 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
++++ b/arch/arm64/boot/dts/rockchip/rk3399-puma.dtsi
+@@ -154,6 +154,22 @@ bios-disable-hog {
+ };
+ };
+
++&gpio3 {
++ /*
++ * The Qseven BIOS_DISABLE signal on the RK3399-Q7 keeps the on-module
++ * eMMC and SPI flash powered-down initially (in fact it keeps the
++ * reset signal asserted). BIOS_DISABLE_OVERRIDE pin allows to override
++ * that signal so that eMMC and SPI can be used regardless of the state
++ * of the signal.
++ */
++ bios-disable-override-hog {
++ gpios = <RK_PD5 GPIO_ACTIVE_LOW>;
++ gpio-hog;
++ line-name = "bios_disable_override";
++ output-high;
++ };
++};
++
+ &gmac {
+ assigned-clocks = <&cru SCLK_RMII_SRC>;
+ assigned-clock-parents = <&clkin_gmac>;
+@@ -409,6 +425,7 @@ vdd_cpu_b: regulator@60 {
+
+ &i2s0 {
+ pinctrl-0 = <&i2s0_2ch_bus>;
++ pinctrl-1 = <&i2s0_2ch_bus_bclk_off>;
+ rockchip,playback-channels = <2>;
+ rockchip,capture-channels = <2>;
+ status = "okay";
+@@ -417,8 +434,8 @@ &i2s0 {
+ /*
+ * As Q7 does not specify neither a global nor a RX clock for I2S these
+ * signals are not used. Furthermore I2S0_LRCK_RX is used as GPIO.
+- * Therefore we have to redefine the i2s0_2ch_bus definition to prevent
+- * conflicts.
++ * Therefore we have to redefine the i2s0_2ch_bus and i2s0_2ch_bus_bclk_off
++ * definitions to prevent conflicts.
+ */
+ &i2s0_2ch_bus {
+ rockchip,pins =
+@@ -428,6 +445,14 @@ &i2s0_2ch_bus {
+ <3 RK_PD7 1 &pcfg_pull_none>;
+ };
+
++&i2s0_2ch_bus_bclk_off {
++ rockchip,pins =
++ <3 RK_PD0 RK_FUNC_GPIO &pcfg_pull_none>,
++ <3 RK_PD2 1 &pcfg_pull_none>,
++ <3 RK_PD3 1 &pcfg_pull_none>,
++ <3 RK_PD7 1 &pcfg_pull_none>;
++};
++
+ &io_domains {
+ status = "okay";
+ bt656-supply = <&vcc_1v8>;
+@@ -449,9 +474,14 @@ &pcie_clkreqn_cpm {
+
+ &pinctrl {
+ pinctrl-names = "default";
+- pinctrl-0 = <&q7_thermal_pin>;
++ pinctrl-0 = <&q7_thermal_pin &bios_disable_override_hog_pin>;
+
+ gpios {
++ bios_disable_override_hog_pin: bios-disable-override-hog-pin {
++ rockchip,pins =
++ <3 RK_PD5 RK_FUNC_GPIO &pcfg_pull_down>;
++ };
++
+ q7_thermal_pin: q7-thermal-pin {
+ rockchip,pins =
+ <0 RK_PA3 RK_FUNC_GPIO &pcfg_pull_up>;
+diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c
+index 4bd2f87616baa9..943430077375a4 100644
+--- a/arch/powerpc/kernel/setup-common.c
++++ b/arch/powerpc/kernel/setup-common.c
+@@ -959,6 +959,7 @@ void __init setup_arch(char **cmdline_p)
+ mem_topology_setup();
+ /* Set max_mapnr before paging_init() */
+ set_max_mapnr(max_pfn);
++ high_memory = (void *)__va(max_low_pfn * PAGE_SIZE);
+
+ /*
+ * Release secondary cpus out of their spinloops at 0x60 now that
+diff --git a/arch/powerpc/mm/mem.c b/arch/powerpc/mm/mem.c
+index d325217ab20121..da21cb018984eb 100644
+--- a/arch/powerpc/mm/mem.c
++++ b/arch/powerpc/mm/mem.c
+@@ -290,8 +290,6 @@ void __init mem_init(void)
+ swiotlb_init(ppc_swiotlb_enable, ppc_swiotlb_flags);
+ #endif
+
+- high_memory = (void *) __va(max_low_pfn * PAGE_SIZE);
+-
+ kasan_late_init();
+
+ memblock_free_all();
+diff --git a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi
+index 68d16717db8cdb..51d85f44762669 100644
+--- a/arch/riscv/boot/dts/starfive/jh7110-common.dtsi
++++ b/arch/riscv/boot/dts/starfive/jh7110-common.dtsi
+@@ -354,6 +354,12 @@ spi_dev0: spi@0 {
+ };
+ };
+
++&syscrg {
++ assigned-clocks = <&syscrg JH7110_SYSCLK_CPU_CORE>,
++ <&pllclk JH7110_PLLCLK_PLL0_OUT>;
++ assigned-clock-rates = <500000000>, <1500000000>;
++};
++
+ &sysgpio {
+ i2c0_pins: i2c0-0 {
+ i2c-pins {
+diff --git a/arch/riscv/mm/cacheflush.c b/arch/riscv/mm/cacheflush.c
+index a03c994eed3b6b..b8167272988723 100644
+--- a/arch/riscv/mm/cacheflush.c
++++ b/arch/riscv/mm/cacheflush.c
+@@ -158,6 +158,7 @@ void __init riscv_init_cbo_blocksizes(void)
+ #ifdef CONFIG_SMP
+ static void set_icache_stale_mask(void)
+ {
++ int cpu = get_cpu();
+ cpumask_t *mask;
+ bool stale_cpu;
+
+@@ -168,10 +169,11 @@ static void set_icache_stale_mask(void)
+ * concurrently on different harts.
+ */
+ mask = ¤t->mm->context.icache_stale_mask;
+- stale_cpu = cpumask_test_cpu(smp_processor_id(), mask);
++ stale_cpu = cpumask_test_cpu(cpu, mask);
+
+ cpumask_setall(mask);
+- cpumask_assign_cpu(smp_processor_id(), mask, stale_cpu);
++ cpumask_assign_cpu(cpu, mask, stale_cpu);
++ put_cpu();
+ }
+ #endif
+
+@@ -239,14 +241,12 @@ int riscv_set_icache_flush_ctx(unsigned long ctx, unsigned long scope)
+ case PR_RISCV_CTX_SW_FENCEI_OFF:
+ switch (scope) {
+ case PR_RISCV_SCOPE_PER_PROCESS:
+- current->mm->context.force_icache_flush = false;
+-
+ set_icache_stale_mask();
++ current->mm->context.force_icache_flush = false;
+ break;
+ case PR_RISCV_SCOPE_PER_THREAD:
+- current->thread.force_icache_flush = false;
+-
+ set_icache_stale_mask();
++ current->thread.force_icache_flush = false;
+ break;
+ default:
+ return -EINVAL;
+diff --git a/arch/s390/Kconfig b/arch/s390/Kconfig
+index c59d2b54df4940..4f7ed0cd12ccb2 100644
+--- a/arch/s390/Kconfig
++++ b/arch/s390/Kconfig
+@@ -602,6 +602,19 @@ config RANDOMIZE_BASE
+ as a security feature that deters exploit attempts relying on
+ knowledge of the location of kernel internals.
+
++config RANDOMIZE_IDENTITY_BASE
++ bool "Randomize the address of the identity mapping base"
++ depends on RANDOMIZE_BASE
++ default DEBUG_VM
++ help
++ The identity mapping base address is pinned to zero by default.
++ Allow randomization of that base to expose otherwise missed
++ notion of physical and virtual addresses of data structures.
++ That does not have any impact on the base address at which the
++ kernel image is loaded.
++
++ If unsure, say N
++
+ config KERNEL_IMAGE_BASE
+ hex "Kernel image base address"
+ range 0x100000 0x1FFFFFE0000000 if !KASAN
+diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
+index 66ee97ac803de3..90c51368f93341 100644
+--- a/arch/s390/boot/startup.c
++++ b/arch/s390/boot/startup.c
+@@ -333,7 +333,8 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
+ BUILD_BUG_ON(MAX_DCSS_ADDR > (1UL << MAX_PHYSMEM_BITS));
+ max_mappable = max(ident_map_size, MAX_DCSS_ADDR);
+ max_mappable = min(max_mappable, vmemmap_start);
+- __identity_base = round_down(vmemmap_start - max_mappable, rte_size);
++ if (IS_ENABLED(CONFIG_RANDOMIZE_IDENTITY_BASE))
++ __identity_base = round_down(vmemmap_start - max_mappable, rte_size);
+
+ return asce_limit;
+ }
+diff --git a/arch/x86/hyperv/hv_init.c b/arch/x86/hyperv/hv_init.c
+index 17a71e92a343e1..95eada2994e150 100644
+--- a/arch/x86/hyperv/hv_init.c
++++ b/arch/x86/hyperv/hv_init.c
+@@ -35,7 +35,6 @@
+ #include <clocksource/hyperv_timer.h>
+ #include <linux/highmem.h>
+
+-int hyperv_init_cpuhp;
+ u64 hv_current_partition_id = ~0ull;
+ EXPORT_SYMBOL_GPL(hv_current_partition_id);
+
+@@ -607,8 +606,6 @@ void __init hyperv_init(void)
+
+ register_syscore_ops(&hv_syscore_ops);
+
+- hyperv_init_cpuhp = cpuhp;
+-
+ if (cpuid_ebx(HYPERV_CPUID_FEATURES) & HV_ACCESS_PARTITION_ID)
+ hv_get_partition_id();
+
+@@ -637,7 +634,7 @@ void __init hyperv_init(void)
+ clean_guest_os_id:
+ wrmsrl(HV_X64_MSR_GUEST_OS_ID, 0);
+ hv_ivm_msr_write(HV_X64_MSR_GUEST_OS_ID, 0);
+- cpuhp_remove_state(cpuhp);
++ cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
+ free_ghcb_page:
+ free_percpu(hv_ghcb_pg);
+ free_vp_assist_page:
+diff --git a/arch/x86/include/asm/mshyperv.h b/arch/x86/include/asm/mshyperv.h
+index 390c4d13956d0c..5f0bc6a6d02556 100644
+--- a/arch/x86/include/asm/mshyperv.h
++++ b/arch/x86/include/asm/mshyperv.h
+@@ -40,7 +40,6 @@ static inline unsigned char hv_get_nmi_reason(void)
+ }
+
+ #if IS_ENABLED(CONFIG_HYPERV)
+-extern int hyperv_init_cpuhp;
+ extern bool hyperv_paravisor_present;
+
+ extern void *hv_hypercall_pg;
+diff --git a/arch/x86/kernel/cpu/mshyperv.c b/arch/x86/kernel/cpu/mshyperv.c
+index e0fd57a8ba8404..41632fb57796de 100644
+--- a/arch/x86/kernel/cpu/mshyperv.c
++++ b/arch/x86/kernel/cpu/mshyperv.c
+@@ -199,8 +199,8 @@ static void hv_machine_shutdown(void)
+ * Call hv_cpu_die() on all the CPUs, otherwise later the hypervisor
+ * corrupts the old VP Assist Pages and can crash the kexec kernel.
+ */
+- if (kexec_in_progress && hyperv_init_cpuhp > 0)
+- cpuhp_remove_state(hyperv_init_cpuhp);
++ if (kexec_in_progress)
++ cpuhp_remove_state(CPUHP_AP_HYPERV_ONLINE);
+
+ /* The function calls stop_other_cpus(). */
+ native_machine_shutdown();
+@@ -449,9 +449,23 @@ static void __init ms_hyperv_init_platform(void)
+ ms_hyperv.hints &= ~HV_X64_APIC_ACCESS_RECOMMENDED;
+
+ if (!ms_hyperv.paravisor_present) {
+- /* To be supported: more work is required. */
++ /*
++ * Mark the Hyper-V TSC page feature as disabled
++ * in a TDX VM without paravisor so that the
++ * Invariant TSC, which is a better clocksource
++ * anyway, is used instead.
++ */
+ ms_hyperv.features &= ~HV_MSR_REFERENCE_TSC_AVAILABLE;
+
++ /*
++ * The Invariant TSC is expected to be available
++ * in a TDX VM without paravisor, but if not,
++ * print a warning message. The slower Hyper-V MSR-based
++ * Ref Counter should end up being the clocksource.
++ */
++ if (!(ms_hyperv.features & HV_ACCESS_TSC_INVARIANT))
++ pr_warn("Hyper-V: Invariant TSC is unavailable\n");
++
+ /* HV_MSR_CRASH_CTL is unsupported. */
+ ms_hyperv.misc_features &= ~HV_FEATURE_GUEST_CRASH_MSR_AVAILABLE;
+
+diff --git a/drivers/clk/sophgo/clk-cv18xx-ip.c b/drivers/clk/sophgo/clk-cv18xx-ip.c
+index 805f561725ae15..b186e64d4813e2 100644
+--- a/drivers/clk/sophgo/clk-cv18xx-ip.c
++++ b/drivers/clk/sophgo/clk-cv18xx-ip.c
+@@ -613,7 +613,7 @@ static u8 mmux_get_parent_id(struct cv1800_clk_mmux *mmux)
+ return i;
+ }
+
+- unreachable();
++ BUG();
+ }
+
+ static int mmux_enable(struct clk_hw *hw)
+diff --git a/drivers/clocksource/hyperv_timer.c b/drivers/clocksource/hyperv_timer.c
+index b2a080647e4132..99177835cadec4 100644
+--- a/drivers/clocksource/hyperv_timer.c
++++ b/drivers/clocksource/hyperv_timer.c
+@@ -137,7 +137,21 @@ static int hv_stimer_init(unsigned int cpu)
+ ce->name = "Hyper-V clockevent";
+ ce->features = CLOCK_EVT_FEAT_ONESHOT;
+ ce->cpumask = cpumask_of(cpu);
+- ce->rating = 1000;
++
++ /*
++ * Lower the rating of the Hyper-V timer in a TDX VM without paravisor,
++ * so the local APIC timer (lapic_clockevent) is the default timer in
++ * such a VM. The Hyper-V timer is not preferred in such a VM because
++ * it depends on the slow VM Reference Counter MSR (the Hyper-V TSC
++ * page is not enbled in such a VM because the VM uses Invariant TSC
++ * as a better clocksource and it's challenging to mark the Hyper-V
++ * TSC page shared in very early boot).
++ */
++ if (!ms_hyperv.paravisor_present && hv_isolation_type_tdx())
++ ce->rating = 90;
++ else
++ ce->rating = 1000;
++
+ ce->set_state_shutdown = hv_ce_shutdown;
+ ce->set_state_oneshot = hv_ce_set_oneshot;
+ ce->set_next_event = hv_ce_set_next_event;
+diff --git a/drivers/cxl/acpi.c b/drivers/cxl/acpi.c
+index 571069863c6294..6b6ae9c81368ea 100644
+--- a/drivers/cxl/acpi.c
++++ b/drivers/cxl/acpi.c
+@@ -74,6 +74,43 @@ static struct cxl_dport *cxl_hb_xor(struct cxl_root_decoder *cxlrd, int pos)
+ return cxlrd->cxlsd.target[n];
+ }
+
++static u64 cxl_xor_hpa_to_spa(struct cxl_root_decoder *cxlrd, u64 hpa)
++{
++ struct cxl_cxims_data *cximsd = cxlrd->platform_data;
++ int hbiw = cxlrd->cxlsd.nr_targets;
++ u64 val;
++ int pos;
++
++ /* No xormaps for host bridge interleave ways of 1 or 3 */
++ if (hbiw == 1 || hbiw == 3)
++ return hpa;
++
++ /*
++ * For root decoders using xormaps (hbiw: 2,4,6,8,12,16) restore
++ * the position bit to its value before the xormap was applied at
++ * HPA->DPA translation.
++ *
++ * pos is the lowest set bit in an XORMAP
++ * val is the XORALLBITS(HPA & XORMAP)
++ *
++ * XORALLBITS: The CXL spec (3.1 Table 9-22) defines XORALLBITS
++ * as an operation that outputs a single bit by XORing all the
++ * bits in the input (hpa & xormap). Implement XORALLBITS using
++ * hweight64(). If the hamming weight is even the XOR of those
++ * bits results in val==0, if odd the XOR result is val==1.
++ */
++
++ for (int i = 0; i < cximsd->nr_maps; i++) {
++ if (!cximsd->xormaps[i])
++ continue;
++ pos = __ffs(cximsd->xormaps[i]);
++ val = (hweight64(hpa & cximsd->xormaps[i]) & 1);
++ hpa = (hpa & ~(1ULL << pos)) | (val << pos);
++ }
++
++ return hpa;
++}
++
+ struct cxl_cxims_context {
+ struct device *dev;
+ struct cxl_root_decoder *cxlrd;
+@@ -434,6 +471,9 @@ static int __cxl_parse_cfmws(struct acpi_cedt_cfmws *cfmws,
+
+ cxlrd->qos_class = cfmws->qtg_id;
+
++ if (cfmws->interleave_arithmetic == ACPI_CEDT_CFMWS_ARITHMETIC_XOR)
++ cxlrd->hpa_to_spa = cxl_xor_hpa_to_spa;
++
+ rc = cxl_decoder_add(cxld, target_map);
+ if (rc)
+ return rc;
+diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
+index 0e30e0a29d400b..3345ccbade0bdf 100644
+--- a/drivers/cxl/core/region.c
++++ b/drivers/cxl/core/region.c
+@@ -2830,20 +2830,13 @@ struct cxl_region *cxl_dpa_to_region(const struct cxl_memdev *cxlmd, u64 dpa)
+ return ctx.cxlr;
+ }
+
+-static bool cxl_is_hpa_in_range(u64 hpa, struct cxl_region *cxlr, int pos)
++static bool cxl_is_hpa_in_chunk(u64 hpa, struct cxl_region *cxlr, int pos)
+ {
+ struct cxl_region_params *p = &cxlr->params;
+ int gran = p->interleave_granularity;
+ int ways = p->interleave_ways;
+ u64 offset;
+
+- /* Is the hpa within this region at all */
+- if (hpa < p->res->start || hpa > p->res->end) {
+- dev_dbg(&cxlr->dev,
+- "Addr trans fail: hpa 0x%llx not in region\n", hpa);
+- return false;
+- }
+-
+ /* Is the hpa in an expected chunk for its pos(-ition) */
+ offset = hpa - p->res->start;
+ offset = do_div(offset, gran * ways);
+@@ -2859,6 +2852,7 @@ static bool cxl_is_hpa_in_range(u64 hpa, struct cxl_region *cxlr, int pos)
+ static u64 cxl_dpa_to_hpa(u64 dpa, struct cxl_region *cxlr,
+ struct cxl_endpoint_decoder *cxled)
+ {
++ struct cxl_root_decoder *cxlrd = to_cxl_root_decoder(cxlr->dev.parent);
+ u64 dpa_offset, hpa_offset, bits_upper, mask_upper, hpa;
+ struct cxl_region_params *p = &cxlr->params;
+ int pos = cxled->pos;
+@@ -2898,7 +2892,18 @@ static u64 cxl_dpa_to_hpa(u64 dpa, struct cxl_region *cxlr,
+ /* Apply the hpa_offset to the region base address */
+ hpa = hpa_offset + p->res->start;
+
+- if (!cxl_is_hpa_in_range(hpa, cxlr, cxled->pos))
++ /* Root decoder translation overrides typical modulo decode */
++ if (cxlrd->hpa_to_spa)
++ hpa = cxlrd->hpa_to_spa(cxlrd, hpa);
++
++ if (hpa < p->res->start || hpa > p->res->end) {
++ dev_dbg(&cxlr->dev,
++ "Addr trans fail: hpa 0x%llx not in region\n", hpa);
++ return ULLONG_MAX;
++ }
++
++ /* Simple chunk check, by pos & gran, only applies to modulo decodes */
++ if (!cxlrd->hpa_to_spa && (!cxl_is_hpa_in_chunk(hpa, cxlr, pos)))
+ return ULLONG_MAX;
+
+ return hpa;
+diff --git a/drivers/cxl/cxl.h b/drivers/cxl/cxl.h
+index a6613a6f892370..b8e16e8697e22e 100644
+--- a/drivers/cxl/cxl.h
++++ b/drivers/cxl/cxl.h
+@@ -436,12 +436,14 @@ struct cxl_switch_decoder {
+ struct cxl_root_decoder;
+ typedef struct cxl_dport *(*cxl_calc_hb_fn)(struct cxl_root_decoder *cxlrd,
+ int pos);
++typedef u64 (*cxl_hpa_to_spa_fn)(struct cxl_root_decoder *cxlrd, u64 hpa);
+
+ /**
+ * struct cxl_root_decoder - Static platform CXL address decoder
+ * @res: host / parent resource for region allocations
+ * @region_id: region id for next region provisioning event
+ * @calc_hb: which host bridge covers the n'th position by granularity
++ * @hpa_to_spa: translate CXL host-physical-address to Platform system-physical-address
+ * @platform_data: platform specific configuration data
+ * @range_lock: sync region autodiscovery by address range
+ * @qos_class: QoS performance class cookie
+@@ -451,6 +453,7 @@ struct cxl_root_decoder {
+ struct resource *res;
+ atomic_t region_id;
+ cxl_calc_hb_fn calc_hb;
++ cxl_hpa_to_spa_fn hpa_to_spa;
+ void *platform_data;
+ struct mutex range_lock;
+ int qos_class;
+diff --git a/drivers/cxl/cxlmem.h b/drivers/cxl/cxlmem.h
+index af8169ccdbc055..feb1106559d21f 100644
+--- a/drivers/cxl/cxlmem.h
++++ b/drivers/cxl/cxlmem.h
+@@ -563,7 +563,7 @@ enum cxl_opcode {
+ 0x3b, 0x3f, 0x17)
+
+ #define DEFINE_CXL_VENDOR_DEBUG_UUID \
+- UUID_INIT(0xe1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \
++ UUID_INIT(0x5e1819d9, 0x11a9, 0x400c, 0x81, 0x1f, 0xd6, 0x07, 0x19, \
+ 0x40, 0x3d, 0x86)
+
+ struct cxl_mbox_get_supported_logs {
+diff --git a/drivers/dma-buf/heaps/cma_heap.c b/drivers/dma-buf/heaps/cma_heap.c
+index 4a63567e93bae3..20dbe9265ad7ca 100644
+--- a/drivers/dma-buf/heaps/cma_heap.c
++++ b/drivers/dma-buf/heaps/cma_heap.c
+@@ -165,7 +165,7 @@ static vm_fault_t cma_heap_vm_fault(struct vm_fault *vmf)
+ struct vm_area_struct *vma = vmf->vma;
+ struct cma_heap_buffer *buffer = vma->vm_private_data;
+
+- if (vmf->pgoff > buffer->pagecount)
++ if (vmf->pgoff >= buffer->pagecount)
+ return VM_FAULT_SIGBUS;
+
+ return vmf_insert_pfn(vma, vmf->address, page_to_pfn(buffer->pages[vmf->pgoff]));
+diff --git a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
+index bc550ad0dbe0c7..68b2c09ed22cd3 100644
+--- a/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
++++ b/drivers/firmware/qcom/qcom_qseecom_uefisecapp.c
+@@ -786,6 +786,10 @@ static int qcuefi_set_reference(struct qcuefi_client *qcuefi)
+ static struct qcuefi_client *qcuefi_acquire(void)
+ {
+ mutex_lock(&__qcuefi_lock);
++ if (!__qcuefi) {
++ mutex_unlock(&__qcuefi_lock);
++ return NULL;
++ }
+ return __qcuefi;
+ }
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+index 1a5439abd1a043..c87d68d4be5365 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+@@ -461,8 +461,11 @@ struct amdgpu_vcn5_fw_shared {
+ struct amdgpu_fw_shared_unified_queue_struct sq;
+ uint8_t pad1[8];
+ struct amdgpu_fw_shared_fw_logging fw_log;
++ uint8_t pad2[20];
+ struct amdgpu_fw_shared_rb_setup rb_setup;
+- uint8_t pad2[4];
++ struct amdgpu_fw_shared_smu_interface_info smu_dpm_interface;
++ struct amdgpu_fw_shared_drm_key_wa drm_key_wa;
++ uint8_t pad3[9];
+ };
+
+ #define VCN_BLOCK_ENCODE_DISABLE_MASK 0x80
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
+index 77595e9622da34..7ac0228fe532ee 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.c
+@@ -23,6 +23,7 @@
+
+ #include "amdgpu.h"
+ #include "amdgpu_jpeg.h"
++#include "amdgpu_cs.h"
+ #include "soc15.h"
+ #include "soc15d.h"
+ #include "vcn_v1_0.h"
+@@ -34,6 +35,9 @@
+ static void jpeg_v1_0_set_dec_ring_funcs(struct amdgpu_device *adev);
+ static void jpeg_v1_0_set_irq_funcs(struct amdgpu_device *adev);
+ static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring);
++static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
++ struct amdgpu_job *job,
++ struct amdgpu_ib *ib);
+
+ static void jpeg_v1_0_decode_ring_patch_wreg(struct amdgpu_ring *ring, uint32_t *ptr, uint32_t reg_offset, uint32_t val)
+ {
+@@ -300,7 +304,10 @@ static void jpeg_v1_0_decode_ring_emit_ib(struct amdgpu_ring *ring,
+
+ amdgpu_ring_write(ring,
+ PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JRBC_IB_VMID), 0, 0, PACKETJ_TYPE0));
+- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
++ if (ring->funcs->parse_cs)
++ amdgpu_ring_write(ring, 0);
++ else
++ amdgpu_ring_write(ring, (vmid | (vmid << 4)));
+
+ amdgpu_ring_write(ring,
+ PACKETJ(SOC15_REG_OFFSET(JPEG, 0, mmUVD_LMI_JPEG_VMID), 0, 0, PACKETJ_TYPE0));
+@@ -554,6 +561,7 @@ static const struct amdgpu_ring_funcs jpeg_v1_0_decode_ring_vm_funcs = {
+ .get_rptr = jpeg_v1_0_decode_ring_get_rptr,
+ .get_wptr = jpeg_v1_0_decode_ring_get_wptr,
+ .set_wptr = jpeg_v1_0_decode_ring_set_wptr,
++ .parse_cs = jpeg_v1_dec_ring_parse_cs,
+ .emit_frame_size =
+ 6 + 6 + /* hdp invalidate / flush */
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+@@ -612,3 +620,69 @@ static void jpeg_v1_0_ring_begin_use(struct amdgpu_ring *ring)
+
+ vcn_v1_0_set_pg_for_begin_use(ring, set_clocks);
+ }
++
++/**
++ * jpeg_v1_dec_ring_parse_cs - command submission parser
++ *
++ * @parser: Command submission parser context
++ * @job: the job to parse
++ * @ib: the IB to parse
++ *
++ * Parse the command stream, return -EINVAL for invalid packet,
++ * 0 otherwise
++ */
++static int jpeg_v1_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
++ struct amdgpu_job *job,
++ struct amdgpu_ib *ib)
++{
++ u32 i, reg, res, cond, type;
++ int ret = 0;
++ struct amdgpu_device *adev = parser->adev;
++
++ for (i = 0; i < ib->length_dw ; i += 2) {
++ reg = CP_PACKETJ_GET_REG(ib->ptr[i]);
++ res = CP_PACKETJ_GET_RES(ib->ptr[i]);
++ cond = CP_PACKETJ_GET_COND(ib->ptr[i]);
++ type = CP_PACKETJ_GET_TYPE(ib->ptr[i]);
++
++ if (res || cond != PACKETJ_CONDITION_CHECK0) /* only allow 0 for now */
++ return -EINVAL;
++
++ if (reg >= JPEG_V1_REG_RANGE_START && reg <= JPEG_V1_REG_RANGE_END)
++ continue;
++
++ switch (type) {
++ case PACKETJ_TYPE0:
++ if (reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH &&
++ reg != JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW &&
++ reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH &&
++ reg != JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW &&
++ reg != JPEG_V1_REG_CTX_INDEX &&
++ reg != JPEG_V1_REG_CTX_DATA) {
++ ret = -EINVAL;
++ }
++ break;
++ case PACKETJ_TYPE1:
++ if (reg != JPEG_V1_REG_CTX_DATA)
++ ret = -EINVAL;
++ break;
++ case PACKETJ_TYPE3:
++ if (reg != JPEG_V1_REG_SOFT_RESET)
++ ret = -EINVAL;
++ break;
++ case PACKETJ_TYPE6:
++ if (ib->ptr[i] != CP_PACKETJ_NOP)
++ ret = -EINVAL;
++ break;
++ default:
++ ret = -EINVAL;
++ }
++
++ if (ret) {
++ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
++ break;
++ }
++ }
++
++ return ret;
++}
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h
+index bbf33a6a397298..9654d22e03763c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v1_0.h
+@@ -29,4 +29,15 @@ int jpeg_v1_0_sw_init(void *handle);
+ void jpeg_v1_0_sw_fini(void *handle);
+ void jpeg_v1_0_start(struct amdgpu_device *adev, int mode);
+
++#define JPEG_V1_REG_RANGE_START 0x8000
++#define JPEG_V1_REG_RANGE_END 0x803f
++
++#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_HIGH 0x8238
++#define JPEG_V1_LMI_JPEG_WRITE_64BIT_BAR_LOW 0x8239
++#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_HIGH 0x825a
++#define JPEG_V1_LMI_JPEG_READ_64BIT_BAR_LOW 0x825b
++#define JPEG_V1_REG_CTX_INDEX 0x8328
++#define JPEG_V1_REG_CTX_DATA 0x8329
++#define JPEG_V1_REG_SOFT_RESET 0x83a0
++
+ #endif /*__JPEG_V1_0_H__*/
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+index 63f84ef6dfcf27..9e9bcf184df2b4 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+@@ -23,6 +23,7 @@
+
+ #include "amdgpu.h"
+ #include "amdgpu_jpeg.h"
++#include "amdgpu_cs.h"
+ #include "amdgpu_pm.h"
+ #include "soc15.h"
+ #include "soc15d.h"
+@@ -543,7 +544,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+- amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
++
++ if (ring->funcs->parse_cs)
++ amdgpu_ring_write(ring, 0);
++ else
++ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+@@ -769,6 +774,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_0_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v2_0_dec_ring_get_rptr,
+ .get_wptr = jpeg_v2_0_dec_ring_get_wptr,
+ .set_wptr = jpeg_v2_0_dec_ring_set_wptr,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+@@ -816,3 +822,58 @@ const struct amdgpu_ip_block_version jpeg_v2_0_ip_block = {
+ .rev = 0,
+ .funcs = &jpeg_v2_0_ip_funcs,
+ };
++
++/**
++ * jpeg_v2_dec_ring_parse_cs - command submission parser
++ *
++ * @parser: Command submission parser context
++ * @job: the job to parse
++ * @ib: the IB to parse
++ *
++ * Parse the command stream, return -EINVAL for invalid packet,
++ * 0 otherwise
++ */
++int jpeg_v2_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
++ struct amdgpu_job *job,
++ struct amdgpu_ib *ib)
++{
++ u32 i, reg, res, cond, type;
++ struct amdgpu_device *adev = parser->adev;
++
++ for (i = 0; i < ib->length_dw ; i += 2) {
++ reg = CP_PACKETJ_GET_REG(ib->ptr[i]);
++ res = CP_PACKETJ_GET_RES(ib->ptr[i]);
++ cond = CP_PACKETJ_GET_COND(ib->ptr[i]);
++ type = CP_PACKETJ_GET_TYPE(ib->ptr[i]);
++
++ if (res) /* only support 0 at the moment */
++ return -EINVAL;
++
++ switch (type) {
++ case PACKETJ_TYPE0:
++ if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START ||
++ reg > JPEG_REG_RANGE_END) {
++ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
++ return -EINVAL;
++ }
++ break;
++ case PACKETJ_TYPE3:
++ if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START ||
++ reg > JPEG_REG_RANGE_END) {
++ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
++ return -EINVAL;
++ }
++ break;
++ case PACKETJ_TYPE6:
++ if (ib->ptr[i] == CP_PACKETJ_NOP)
++ continue;
++ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
++ return -EINVAL;
++ default:
++ dev_err(adev->dev, "Unknown packet type %d !\n", type);
++ return -EINVAL;
++ }
++ }
++
++ return 0;
++}
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
+index 654e43e83e2c43..63fadda7a67332 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.h
+@@ -45,6 +45,9 @@
+
+ #define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000
+
++#define JPEG_REG_RANGE_START 0x4000
++#define JPEG_REG_RANGE_END 0x41c2
++
+ void jpeg_v2_0_dec_ring_insert_start(struct amdgpu_ring *ring);
+ void jpeg_v2_0_dec_ring_insert_end(struct amdgpu_ring *ring);
+ void jpeg_v2_0_dec_ring_emit_fence(struct amdgpu_ring *ring, u64 addr, u64 seq,
+@@ -57,6 +60,9 @@ void jpeg_v2_0_dec_ring_emit_vm_flush(struct amdgpu_ring *ring,
+ unsigned vmid, uint64_t pd_addr);
+ void jpeg_v2_0_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
+ void jpeg_v2_0_dec_ring_nop(struct amdgpu_ring *ring, uint32_t count);
++int jpeg_v2_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
++ struct amdgpu_job *job,
++ struct amdgpu_ib *ib);
+
+ extern const struct amdgpu_ip_block_version jpeg_v2_0_ip_block;
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+index afeaf3c64e2780..c27f2d30ef0c10 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_5.c
+@@ -664,6 +664,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_5_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v2_5_dec_ring_get_rptr,
+ .get_wptr = jpeg_v2_5_dec_ring_get_wptr,
+ .set_wptr = jpeg_v2_5_dec_ring_set_wptr,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+@@ -693,6 +694,7 @@ static const struct amdgpu_ring_funcs jpeg_v2_6_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v2_5_dec_ring_get_rptr,
+ .get_wptr = jpeg_v2_5_dec_ring_get_wptr,
+ .set_wptr = jpeg_v2_5_dec_ring_set_wptr,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+index 1c7cf4800bf7bb..5cdd3897358eda 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v3_0.c
+@@ -567,6 +567,7 @@ static const struct amdgpu_ring_funcs jpeg_v3_0_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v3_0_dec_ring_get_rptr,
+ .get_wptr = jpeg_v3_0_dec_ring_get_wptr,
+ .set_wptr = jpeg_v3_0_dec_ring_set_wptr,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+index 237fe5df5a8fb5..0115f83bbde680 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.c
+@@ -729,6 +729,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v4_0_dec_ring_get_rptr,
+ .get_wptr = jpeg_v4_0_dec_ring_get_wptr,
+ .set_wptr = jpeg_v4_0_dec_ring_set_wptr,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h
+index 07d36c2abd6bb9..47638fd4d4e212 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0.h
+@@ -32,5 +32,4 @@ enum amdgpu_jpeg_v4_0_sub_block {
+ };
+
+ extern const struct amdgpu_ip_block_version jpeg_v4_0_ip_block;
+-
+ #endif /* __JPEG_V4_0_H__ */
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+index d24d06f6d682aa..dfce56d672ff25 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+@@ -23,9 +23,9 @@
+
+ #include "amdgpu.h"
+ #include "amdgpu_jpeg.h"
+-#include "amdgpu_cs.h"
+ #include "soc15.h"
+ #include "soc15d.h"
++#include "jpeg_v2_0.h"
+ #include "jpeg_v4_0_3.h"
+ #include "mmsch_v4_0_3.h"
+
+@@ -1068,7 +1068,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr,
+ .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr,
+ .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr,
+- .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+@@ -1233,56 +1233,3 @@ static void jpeg_v4_0_3_set_ras_funcs(struct amdgpu_device *adev)
+ {
+ adev->jpeg.ras = &jpeg_v4_0_3_ras;
+ }
+-
+-/**
+- * jpeg_v4_0_3_dec_ring_parse_cs - command submission parser
+- *
+- * @parser: Command submission parser context
+- * @job: the job to parse
+- * @ib: the IB to parse
+- *
+- * Parse the command stream, return -EINVAL for invalid packet,
+- * 0 otherwise
+- */
+-int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
+- struct amdgpu_job *job,
+- struct amdgpu_ib *ib)
+-{
+- uint32_t i, reg, res, cond, type;
+- struct amdgpu_device *adev = parser->adev;
+-
+- for (i = 0; i < ib->length_dw ; i += 2) {
+- reg = CP_PACKETJ_GET_REG(ib->ptr[i]);
+- res = CP_PACKETJ_GET_RES(ib->ptr[i]);
+- cond = CP_PACKETJ_GET_COND(ib->ptr[i]);
+- type = CP_PACKETJ_GET_TYPE(ib->ptr[i]);
+-
+- if (res) /* only support 0 at the moment */
+- return -EINVAL;
+-
+- switch (type) {
+- case PACKETJ_TYPE0:
+- if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) {
+- dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
+- return -EINVAL;
+- }
+- break;
+- case PACKETJ_TYPE3:
+- if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) {
+- dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
+- return -EINVAL;
+- }
+- break;
+- case PACKETJ_TYPE6:
+- if (ib->ptr[i] == CP_PACKETJ_NOP)
+- continue;
+- dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
+- return -EINVAL;
+- default:
+- dev_err(adev->dev, "Unknown packet type %d !\n", type);
+- return -EINVAL;
+- }
+- }
+-
+- return 0;
+-}
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
+index 71c54b294e157e..747a3e5f68564c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
+@@ -46,9 +46,6 @@
+
+ #define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000
+
+-#define JPEG_REG_RANGE_START 0x4000
+-#define JPEG_REG_RANGE_END 0x41c2
+-
+ extern const struct amdgpu_ip_block_version jpeg_v4_0_3_ip_block;
+
+ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,
+@@ -65,7 +62,5 @@ void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring);
+ void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
+ void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+ uint32_t val, uint32_t mask);
+-int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
+- struct amdgpu_job *job,
+- struct amdgpu_ib *ib);
++
+ #endif /* __JPEG_V4_0_3_H__ */
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+index 4c8f9772437b52..713cedd57c3483 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+@@ -772,6 +772,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_5_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v4_0_5_dec_ring_get_rptr,
+ .get_wptr = jpeg_v4_0_5_dec_ring_get_wptr,
+ .set_wptr = jpeg_v4_0_5_dec_ring_set_wptr,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+index 90299f66a44456..1036867d35c88e 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+@@ -26,6 +26,7 @@
+ #include "amdgpu_pm.h"
+ #include "soc15.h"
+ #include "soc15d.h"
++#include "jpeg_v2_0.h"
+ #include "jpeg_v4_0_3.h"
+
+ #include "vcn/vcn_5_0_0_offset.h"
+@@ -523,7 +524,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr,
+ .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr,
+ .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr,
+- .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs,
++ .parse_cs = jpeg_v2_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+index 872f994dd356e1..422eb1d2c5d385 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+@@ -3223,15 +3223,19 @@ void dcn10_set_drr(struct pipe_ctx **pipe_ctx,
+ * as well.
+ */
+ for (i = 0; i < num_pipes; i++) {
+- if ((pipe_ctx[i]->stream_res.tg != NULL) && pipe_ctx[i]->stream_res.tg->funcs) {
+- if (pipe_ctx[i]->stream_res.tg->funcs->set_drr)
+- pipe_ctx[i]->stream_res.tg->funcs->set_drr(
+- pipe_ctx[i]->stream_res.tg, ¶ms);
++ /* dc_state_destruct() might null the stream resources, so fetch tg
++ * here first to avoid a race condition. The lifetime of the pointee
++ * itself (the timing_generator object) is not a problem here.
++ */
++ struct timing_generator *tg = pipe_ctx[i]->stream_res.tg;
++
++ if ((tg != NULL) && tg->funcs) {
++ if (tg->funcs->set_drr)
++ tg->funcs->set_drr(tg, ¶ms);
+ if (adjust.v_total_max != 0 && adjust.v_total_min != 0)
+- if (pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control)
+- pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(
+- pipe_ctx[i]->stream_res.tg,
+- event_triggers, num_frames);
++ if (tg->funcs->set_static_screen_control)
++ tg->funcs->set_static_screen_control(
++ tg, event_triggers, num_frames);
+ }
+ }
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+index f829ff82797e72..4f0e9e0f701dd2 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+@@ -1371,7 +1371,13 @@ void dcn35_set_drr(struct pipe_ctx **pipe_ctx,
+ params.vertical_total_mid_frame_num = adjust.v_total_mid_frame_num;
+
+ for (i = 0; i < num_pipes; i++) {
+- if ((pipe_ctx[i]->stream_res.tg != NULL) && pipe_ctx[i]->stream_res.tg->funcs) {
++ /* dc_state_destruct() might null the stream resources, so fetch tg
++ * here first to avoid a race condition. The lifetime of the pointee
++ * itself (the timing_generator object) is not a problem here.
++ */
++ struct timing_generator *tg = pipe_ctx[i]->stream_res.tg;
++
++ if ((tg != NULL) && tg->funcs) {
+ struct dc_crtc_timing *timing = &pipe_ctx[i]->stream->timing;
+ struct dc *dc = pipe_ctx[i]->stream->ctx->dc;
+
+@@ -1384,14 +1390,12 @@ void dcn35_set_drr(struct pipe_ctx **pipe_ctx,
+ num_frames = 2 * (frame_rate % 60);
+ }
+ }
+- if (pipe_ctx[i]->stream_res.tg->funcs->set_drr)
+- pipe_ctx[i]->stream_res.tg->funcs->set_drr(
+- pipe_ctx[i]->stream_res.tg, ¶ms);
++ if (tg->funcs->set_drr)
++ tg->funcs->set_drr(tg, ¶ms);
+ if (adjust.v_total_max != 0 && adjust.v_total_min != 0)
+- if (pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control)
+- pipe_ctx[i]->stream_res.tg->funcs->set_static_screen_control(
+- pipe_ctx[i]->stream_res.tg,
+- event_triggers, num_frames);
++ if (tg->funcs->set_static_screen_control)
++ tg->funcs->set_static_screen_control(
++ tg, event_triggers, num_frames);
+ }
+ }
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c
+index 2fa4e64e24306b..bafa52a0165a08 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c
++++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_phy.c
+@@ -147,32 +147,25 @@ enum dc_status dp_set_fec_ready(struct dc_link *link, const struct link_resource
+
+ link_enc = link_enc_cfg_get_link_enc(link);
+ ASSERT(link_enc);
++ if (link_enc->funcs->fec_set_ready == NULL)
++ return DC_NOT_SUPPORTED;
+
+- if (!dp_should_enable_fec(link))
+- return status;
+-
+- if (link_enc->funcs->fec_set_ready &&
+- link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) {
+- if (ready) {
+- fec_config = 1;
+- status = core_link_write_dpcd(link,
+- DP_FEC_CONFIGURATION,
+- &fec_config,
+- sizeof(fec_config));
+- if (status == DC_OK) {
+- link_enc->funcs->fec_set_ready(link_enc, true);
+- link->fec_state = dc_link_fec_ready;
+- } else {
+- link_enc->funcs->fec_set_ready(link_enc, false);
+- link->fec_state = dc_link_fec_not_ready;
+- dm_error("dpcd write failed to set fec_ready");
+- }
+- } else if (link->fec_state == dc_link_fec_ready) {
++ if (ready && dp_should_enable_fec(link)) {
++ fec_config = 1;
++
++ status = core_link_write_dpcd(link, DP_FEC_CONFIGURATION,
++ &fec_config, sizeof(fec_config));
++
++ if (status == DC_OK) {
++ link_enc->funcs->fec_set_ready(link_enc, true);
++ link->fec_state = dc_link_fec_ready;
++ }
++ } else {
++ if (link->fec_state == dc_link_fec_ready) {
+ fec_config = 0;
+- status = core_link_write_dpcd(link,
+- DP_FEC_CONFIGURATION,
+- &fec_config,
+- sizeof(fec_config));
++ core_link_write_dpcd(link, DP_FEC_CONFIGURATION,
++ &fec_config, sizeof(fec_config));
++
+ link_enc->funcs->fec_set_ready(link_enc, false);
+ link->fec_state = dc_link_fec_not_ready;
+ }
+@@ -187,14 +180,12 @@ void dp_set_fec_enable(struct dc_link *link, bool enable)
+
+ link_enc = link_enc_cfg_get_link_enc(link);
+ ASSERT(link_enc);
+-
+- if (!dp_should_enable_fec(link))
++ if (link_enc->funcs->fec_set_enable == NULL)
+ return;
+
+- if (link_enc->funcs->fec_set_enable &&
+- link->dpcd_caps.fec_cap.bits.FEC_CAPABLE) {
+- if (link->fec_state == dc_link_fec_ready && enable) {
+- /* Accord to DP spec, FEC enable sequence can first
++ if (enable && dp_should_enable_fec(link)) {
++ if (link->fec_state == dc_link_fec_ready) {
++ /* According to DP spec, FEC enable sequence can first
+ * be transmitted anytime after 1000 LL codes have
+ * been transmitted on the link after link training
+ * completion. Using 1 lane RBR should have the maximum
+@@ -204,7 +195,9 @@ void dp_set_fec_enable(struct dc_link *link, bool enable)
+ udelay(7);
+ link_enc->funcs->fec_set_enable(link_enc, true);
+ link->fec_state = dc_link_fec_enabled;
+- } else if (link->fec_state == dc_link_fec_enabled && !enable) {
++ }
++ } else {
++ if (link->fec_state == dc_link_fec_enabled) {
+ link_enc->funcs->fec_set_enable(link_enc, false);
+ link->fec_state = dc_link_fec_ready;
+ }
+diff --git a/drivers/gpu/drm/amd/include/atomfirmware.h b/drivers/gpu/drm/amd/include/atomfirmware.h
+index 09cbc3afd6d89d..b0fc22383e2874 100644
+--- a/drivers/gpu/drm/amd/include/atomfirmware.h
++++ b/drivers/gpu/drm/amd/include/atomfirmware.h
+@@ -1038,7 +1038,7 @@ struct display_object_info_table_v1_4
+ uint16_t supporteddevices;
+ uint8_t number_of_path;
+ uint8_t reserved;
+- struct atom_display_object_path_v2 display_path[8]; //the real number of this included in the structure is calculated by using the (whole structure size - the header size- number_of_path)/size of atom_display_object_path
++ struct atom_display_object_path_v2 display_path[]; //the real number of this included in the structure is calculated by using the (whole structure size - the header size- number_of_path)/size of atom_display_object_path
+ };
+
+ struct display_object_info_table_v1_5 {
+@@ -1048,7 +1048,7 @@ struct display_object_info_table_v1_5 {
+ uint8_t reserved;
+ // the real number of this included in the structure is calculated by using the
+ // (whole structure size - the header size- number_of_path)/size of atom_display_object_path
+- struct atom_display_object_path_v3 display_path[8];
++ struct atom_display_object_path_v3 display_path[];
+ };
+
+ /*
+diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
+index 903f4bfea7e837..70c9bd25f78d01 100644
+--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
++++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
+@@ -208,6 +208,18 @@ static const struct dmi_system_id orientation_data[] = {
+ DMI_MATCH(DMI_BOARD_NAME, "KUN"),
+ },
+ .driver_data = (void *)&lcd1600x2560_rightside_up,
++ }, { /* AYN Loki Max */
++ .matches = {
++ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"),
++ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Max"),
++ },
++ .driver_data = (void *)&lcd1080x1920_leftside_up,
++ }, { /* AYN Loki Zero */
++ .matches = {
++ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "ayn"),
++ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "Loki Zero"),
++ },
++ .driver_data = (void *)&lcd1080x1920_leftside_up,
+ }, { /* Chuwi HiBook (CWI514) */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_VENDOR, "Hampoo"),
+diff --git a/drivers/gpu/drm/drm_syncobj.c b/drivers/gpu/drm/drm_syncobj.c
+index a0e94217b511a1..4fcfc0b9b386cf 100644
+--- a/drivers/gpu/drm/drm_syncobj.c
++++ b/drivers/gpu/drm/drm_syncobj.c
+@@ -1464,6 +1464,7 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data,
+ struct drm_syncobj *syncobj;
+ struct eventfd_ctx *ev_fd_ctx;
+ struct syncobj_eventfd_entry *entry;
++ int ret;
+
+ if (!drm_core_check_feature(dev, DRIVER_SYNCOBJ_TIMELINE))
+ return -EOPNOTSUPP;
+@@ -1479,13 +1480,15 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data,
+ return -ENOENT;
+
+ ev_fd_ctx = eventfd_ctx_fdget(args->fd);
+- if (IS_ERR(ev_fd_ctx))
+- return PTR_ERR(ev_fd_ctx);
++ if (IS_ERR(ev_fd_ctx)) {
++ ret = PTR_ERR(ev_fd_ctx);
++ goto err_fdget;
++ }
+
+ entry = kzalloc(sizeof(*entry), GFP_KERNEL);
+ if (!entry) {
+- eventfd_ctx_put(ev_fd_ctx);
+- return -ENOMEM;
++ ret = -ENOMEM;
++ goto err_kzalloc;
+ }
+ entry->syncobj = syncobj;
+ entry->ev_fd_ctx = ev_fd_ctx;
+@@ -1496,6 +1499,12 @@ drm_syncobj_eventfd_ioctl(struct drm_device *dev, void *data,
+ drm_syncobj_put(syncobj);
+
+ return 0;
++
++err_kzalloc:
++ eventfd_ctx_put(ev_fd_ctx);
++err_fdget:
++ drm_syncobj_put(syncobj);
++ return ret;
+ }
+
+ int
+diff --git a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+index 0eaa1064242c3e..f8e189a73a7905 100644
+--- a/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
++++ b/drivers/gpu/drm/i915/gt/uc/intel_guc_submission.c
+@@ -2842,9 +2842,9 @@ static void prepare_context_registration_info_v70(struct intel_context *ce,
+ ce->parallel.guc.wqi_tail = 0;
+ ce->parallel.guc.wqi_head = 0;
+
+- wq_desc_offset = i915_ggtt_offset(ce->state) +
++ wq_desc_offset = (u64)i915_ggtt_offset(ce->state) +
+ __get_parent_scratch_offset(ce);
+- wq_base_offset = i915_ggtt_offset(ce->state) +
++ wq_base_offset = (u64)i915_ggtt_offset(ce->state) +
+ __get_wq_offset(ce);
+ info->wq_desc_lo = lower_32_bits(wq_desc_offset);
+ info->wq_desc_hi = upper_32_bits(wq_desc_offset);
+diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+index 56f409ad7f390f..ab2bace792e46a 100644
+--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
++++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+@@ -539,8 +539,8 @@ static int mtk_drm_kms_init(struct drm_device *drm)
+ }
+
+ /* IGT will check if the cursor size is configured */
+- drm->mode_config.cursor_width = drm->mode_config.max_width;
+- drm->mode_config.cursor_height = drm->mode_config.max_height;
++ drm->mode_config.cursor_width = 512;
++ drm->mode_config.cursor_height = 512;
+
+ /* Use OVL device for all DMA memory allocations */
+ crtc = drm_crtc_from_index(drm, 0);
+diff --git a/drivers/gpu/drm/msm/adreno/adreno_gpu.c b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+index 074fb498706f26..b93ed15f04a30e 100644
+--- a/drivers/gpu/drm/msm/adreno/adreno_gpu.c
++++ b/drivers/gpu/drm/msm/adreno/adreno_gpu.c
+@@ -99,7 +99,7 @@ static int zap_shader_load_mdt(struct msm_gpu *gpu, const char *fwname,
+ * was a bad idea, and is only provided for backwards
+ * compatibility for older targets.
+ */
+- return -ENODEV;
++ return -ENOENT;
+ }
+
+ if (IS_ERR(fw)) {
+diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
+index 50f0c1914f58e8..4c3f7439657987 100644
+--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
++++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ram.h
+@@ -46,6 +46,8 @@ u32 gm107_ram_probe_fbp(const struct nvkm_ram_func *,
+ u32 gm200_ram_probe_fbp_amount(const struct nvkm_ram_func *, u32,
+ struct nvkm_device *, int, int *);
+
++int gp100_ram_init(struct nvkm_ram *);
++
+ /* RAM type-specific MR calculation routines */
+ int nvkm_sddr2_calc(struct nvkm_ram *);
+ int nvkm_sddr3_calc(struct nvkm_ram *);
+diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
+index 378f6fb7099077..8987a21e81d174 100644
+--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
++++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp100.c
+@@ -27,7 +27,7 @@
+ #include <subdev/bios/init.h>
+ #include <subdev/bios/rammap.h>
+
+-static int
++int
+ gp100_ram_init(struct nvkm_ram *ram)
+ {
+ struct nvkm_subdev *subdev = &ram->fb->subdev;
+diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c
+index 8550f5e473474b..b6b6ee59019d70 100644
+--- a/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c
++++ b/drivers/gpu/drm/nouveau/nvkm/subdev/fb/ramgp102.c
+@@ -5,6 +5,7 @@
+
+ static const struct nvkm_ram_func
+ gp102_ram = {
++ .init = gp100_ram_init,
+ };
+
+ int
+diff --git a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
+index cd4632276141b0..68ade1a05ca915 100644
+--- a/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
++++ b/drivers/gpu/drm/xe/compat-i915-headers/i915_drv.h
+@@ -96,7 +96,7 @@ static inline struct drm_i915_private *kdev_to_i915(struct device *kdev)
+ #define HAS_GMD_ID(xe) GRAPHICS_VERx100(xe) >= 1270
+
+ /* Workarounds not handled yet */
+-#define IS_DISPLAY_STEP(xe, first, last) ({u8 __step = (xe)->info.step.display; first <= __step && __step <= last; })
++#define IS_DISPLAY_STEP(xe, first, last) ({u8 __step = (xe)->info.step.display; first <= __step && __step < last; })
+
+ #define IS_LP(xe) (0)
+ #define IS_GEN9_LP(xe) (0)
+diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
+index b6f3a43d637f70..f5e3012eff20d8 100644
+--- a/drivers/gpu/drm/xe/xe_bo.c
++++ b/drivers/gpu/drm/xe/xe_bo.c
+@@ -1539,7 +1539,7 @@ struct xe_bo *xe_bo_create_from_data(struct xe_device *xe, struct xe_tile *tile,
+ return bo;
+ }
+
+-static void __xe_bo_unpin_map_no_vm(struct drm_device *drm, void *arg)
++static void __xe_bo_unpin_map_no_vm(void *arg)
+ {
+ xe_bo_unpin_map_no_vm(arg);
+ }
+@@ -1554,7 +1554,7 @@ struct xe_bo *xe_managed_bo_create_pin_map(struct xe_device *xe, struct xe_tile
+ if (IS_ERR(bo))
+ return bo;
+
+- ret = drmm_add_action_or_reset(&xe->drm, __xe_bo_unpin_map_no_vm, bo);
++ ret = devm_add_action_or_reset(xe->drm.dev, __xe_bo_unpin_map_no_vm, bo);
+ if (ret)
+ return ERR_PTR(ret);
+
+@@ -1602,7 +1602,7 @@ int xe_managed_bo_reinit_in_vram(struct xe_device *xe, struct xe_tile *tile, str
+ if (IS_ERR(bo))
+ return PTR_ERR(bo);
+
+- drmm_release_action(&xe->drm, __xe_bo_unpin_map_no_vm, *src);
++ devm_release_action(xe->drm.dev, __xe_bo_unpin_map_no_vm, *src);
+ *src = bo;
+
+ return 0;
+diff --git a/drivers/gpu/drm/xe/xe_drm_client.c b/drivers/gpu/drm/xe/xe_drm_client.c
+index 08f0b7c95901f7..ee15daa2150796 100644
+--- a/drivers/gpu/drm/xe/xe_drm_client.c
++++ b/drivers/gpu/drm/xe/xe_drm_client.c
+@@ -9,6 +9,7 @@
+ #include <linux/slab.h>
+ #include <linux/types.h>
+
++#include "xe_assert.h"
+ #include "xe_bo.h"
+ #include "xe_bo_types.h"
+ #include "xe_device_types.h"
+@@ -93,10 +94,13 @@ void xe_drm_client_add_bo(struct xe_drm_client *client,
+ */
+ void xe_drm_client_remove_bo(struct xe_bo *bo)
+ {
++ struct xe_device *xe = ttm_to_xe_device(bo->ttm.bdev);
+ struct xe_drm_client *client = bo->client;
+
++ xe_assert(xe, !kref_read(&bo->ttm.base.refcount));
++
+ spin_lock(&client->bos_lock);
+- list_del(&bo->client_link);
++ list_del_init(&bo->client_link);
+ spin_unlock(&client->bos_lock);
+
+ xe_drm_client_put(client);
+@@ -108,6 +112,8 @@ static void bo_meminfo(struct xe_bo *bo,
+ u64 sz = bo->size;
+ u32 mem_type;
+
++ xe_bo_assert_held(bo);
++
+ if (bo->placement.placement)
+ mem_type = bo->placement.placement->mem_type;
+ else
+@@ -138,6 +144,7 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
+ struct xe_drm_client *client;
+ struct drm_gem_object *obj;
+ struct xe_bo *bo;
++ LLIST_HEAD(deferred);
+ unsigned int id;
+ u32 mem_type;
+
+@@ -148,7 +155,20 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
+ idr_for_each_entry(&file->object_idr, obj, id) {
+ struct xe_bo *bo = gem_to_xe_bo(obj);
+
+- bo_meminfo(bo, stats);
++ if (dma_resv_trylock(bo->ttm.base.resv)) {
++ bo_meminfo(bo, stats);
++ xe_bo_unlock(bo);
++ } else {
++ xe_bo_get(bo);
++ spin_unlock(&file->table_lock);
++
++ xe_bo_lock(bo, false);
++ bo_meminfo(bo, stats);
++ xe_bo_unlock(bo);
++
++ xe_bo_put(bo);
++ spin_lock(&file->table_lock);
++ }
+ }
+ spin_unlock(&file->table_lock);
+
+@@ -157,11 +177,28 @@ static void show_meminfo(struct drm_printer *p, struct drm_file *file)
+ list_for_each_entry(bo, &client->bos_list, client_link) {
+ if (!kref_get_unless_zero(&bo->ttm.base.refcount))
+ continue;
+- bo_meminfo(bo, stats);
+- xe_bo_put(bo);
++
++ if (dma_resv_trylock(bo->ttm.base.resv)) {
++ bo_meminfo(bo, stats);
++ xe_bo_unlock(bo);
++ } else {
++ spin_unlock(&client->bos_lock);
++
++ xe_bo_lock(bo, false);
++ bo_meminfo(bo, stats);
++ xe_bo_unlock(bo);
++
++ spin_lock(&client->bos_lock);
++ /* The bo ref will prevent this bo from being removed from the list */
++ xe_assert(xef->xe, !list_empty(&bo->client_link));
++ }
++
++ xe_bo_put_deferred(bo, &deferred);
+ }
+ spin_unlock(&client->bos_lock);
+
++ xe_bo_put_commit(&deferred);
++
+ for (mem_type = XE_PL_SYSTEM; mem_type < TTM_NUM_MEM_TYPES; ++mem_type) {
+ if (!xe_mem_type_to_name[mem_type])
+ continue;
+diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
+index 95c17b72fa5746..c9a4ffcfdcca99 100644
+--- a/drivers/gpu/drm/xe/xe_gsc.c
++++ b/drivers/gpu/drm/xe/xe_gsc.c
+@@ -256,7 +256,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
+ struct xe_tile *tile = gt_to_tile(gt);
+ int ret;
+
+- if (XE_WA(gt, 14018094691)) {
++ if (XE_WA(tile->primary_gt, 14018094691)) {
+ ret = xe_force_wake_get(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);
+
+ /*
+@@ -274,7 +274,7 @@ static int gsc_upload_and_init(struct xe_gsc *gsc)
+
+ ret = gsc_upload(gsc);
+
+- if (XE_WA(gt, 14018094691))
++ if (XE_WA(tile->primary_gt, 14018094691))
+ xe_force_wake_put(gt_to_fw(tile->primary_gt), XE_FORCEWAKE_ALL);
+
+ if (ret)
+diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
+index 66dafe980b9c2a..1f7699d7fffba1 100644
+--- a/drivers/gpu/drm/xe/xe_wa.c
++++ b/drivers/gpu/drm/xe/xe_wa.c
+@@ -542,6 +542,16 @@ static const struct xe_rtp_entry_sr engine_was[] = {
+ XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
+ },
+
++ /* Xe2_LPM */
++
++ { XE_RTP_NAME("16021639441"),
++ XE_RTP_RULES(MEDIA_VERSION(2000)),
++ XE_RTP_ACTIONS(SET(CSFE_CHICKEN1(0),
++ GHWSP_CSB_REPORT_DIS |
++ PPHWSP_CSB_AND_TIMESTAMP_REPORT_DIS,
++ XE_RTP_ACTION_FLAG(ENGINE_BASE)))
++ },
++
+ /* Xe2_HPM */
+
+ { XE_RTP_NAME("16021639441"),
+diff --git a/drivers/hid/hid-asus.c b/drivers/hid/hid-asus.c
+index 37e6d25593c211..a282388b7aa5c1 100644
+--- a/drivers/hid/hid-asus.c
++++ b/drivers/hid/hid-asus.c
+@@ -1248,6 +1248,9 @@ static const struct hid_device_id asus_devices[] = {
+ { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+ USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY),
+ QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
++ { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
++ USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X),
++ QUIRK_USE_KBD_BACKLIGHT | QUIRK_ROG_NKEY_KEYBOARD },
+ { HID_USB_DEVICE(USB_VENDOR_ID_ASUSTEK,
+ USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD),
+ QUIRK_ROG_CLAYMORE_II_KEYBOARD },
+diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
+index 72d56ee7ce1b98..781c5aa298598a 100644
+--- a/drivers/hid/hid-ids.h
++++ b/drivers/hid/hid-ids.h
+@@ -210,6 +210,7 @@
+ #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_KEYBOARD3 0x1a30
+ #define USB_DEVICE_ID_ASUSTEK_ROG_Z13_LIGHTBAR 0x18c6
+ #define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY 0x1abe
++#define USB_DEVICE_ID_ASUSTEK_ROG_NKEY_ALLY_X 0x1b4c
+ #define USB_DEVICE_ID_ASUSTEK_ROG_CLAYMORE_II_KEYBOARD 0x196b
+ #define USB_DEVICE_ID_ASUSTEK_FX503VD_KEYBOARD 0x1869
+
+@@ -520,6 +521,8 @@
+ #define USB_DEVICE_ID_GENERAL_TOUCH_WIN8_PIT_E100 0xe100
+
+ #define I2C_VENDOR_ID_GOODIX 0x27c6
++#define I2C_DEVICE_ID_GOODIX_01E8 0x01e8
++#define I2C_DEVICE_ID_GOODIX_01E9 0x01e9
+ #define I2C_DEVICE_ID_GOODIX_01F0 0x01f0
+
+ #define USB_VENDOR_ID_GOODTOUCH 0x1aad
+diff --git a/drivers/hid/hid-multitouch.c b/drivers/hid/hid-multitouch.c
+index 56fc78841f245a..99812c0f830b5e 100644
+--- a/drivers/hid/hid-multitouch.c
++++ b/drivers/hid/hid-multitouch.c
+@@ -1441,6 +1441,30 @@ static int mt_event(struct hid_device *hid, struct hid_field *field,
+ return 0;
+ }
+
++static __u8 *mt_report_fixup(struct hid_device *hdev, __u8 *rdesc,
++ unsigned int *size)
++{
++ if (hdev->vendor == I2C_VENDOR_ID_GOODIX &&
++ (hdev->product == I2C_DEVICE_ID_GOODIX_01E8 ||
++ hdev->product == I2C_DEVICE_ID_GOODIX_01E9)) {
++ if (rdesc[607] == 0x15) {
++ rdesc[607] = 0x25;
++ dev_info(
++ &hdev->dev,
++ "GT7868Q report descriptor fixup is applied.\n");
++ } else {
++ dev_info(
++ &hdev->dev,
++ "The byte is not expected for fixing the report descriptor. \
++It's possible that the touchpad firmware is not suitable for applying the fix. \
++got: %x\n",
++ rdesc[607]);
++ }
++ }
++
++ return rdesc;
++}
++
+ static void mt_report(struct hid_device *hid, struct hid_report *report)
+ {
+ struct mt_device *td = hid_get_drvdata(hid);
+@@ -2035,6 +2059,14 @@ static const struct hid_device_id mt_devices[] = {
+ MT_BT_DEVICE(USB_VENDOR_ID_FRUCTEL,
+ USB_DEVICE_ID_GAMETEL_MT_MODE) },
+
++ /* Goodix GT7868Q devices */
++ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
++ HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
++ I2C_DEVICE_ID_GOODIX_01E8) },
++ { .driver_data = MT_CLS_WIN_8_FORCE_MULTI_INPUT_NSMU,
++ HID_DEVICE(BUS_I2C, HID_GROUP_ANY, I2C_VENDOR_ID_GOODIX,
++ I2C_DEVICE_ID_GOODIX_01E8) },
++
+ /* GoodTouch panels */
+ { .driver_data = MT_CLS_NSMU,
+ MT_USB_DEVICE(USB_VENDOR_ID_GOODTOUCH,
+@@ -2270,6 +2302,7 @@ static struct hid_driver mt_driver = {
+ .feature_mapping = mt_feature_mapping,
+ .usage_table = mt_grabbed_usages,
+ .event = mt_event,
++ .report_fixup = mt_report_fixup,
+ .report = mt_report,
+ .suspend = pm_ptr(mt_suspend),
+ .reset_resume = pm_ptr(mt_reset_resume),
+diff --git a/drivers/hwmon/pmbus/pmbus.h b/drivers/hwmon/pmbus/pmbus.h
+index fb442fae7b3e35..0bea603994e7b2 100644
+--- a/drivers/hwmon/pmbus/pmbus.h
++++ b/drivers/hwmon/pmbus/pmbus.h
+@@ -418,6 +418,12 @@ enum pmbus_sensor_classes {
+ enum pmbus_data_format { linear = 0, ieee754, direct, vid };
+ enum vrm_version { vr11 = 0, vr12, vr13, imvp9, amd625mv };
+
++/* PMBus revision identifiers */
++#define PMBUS_REV_10 0x00 /* PMBus revision 1.0 */
++#define PMBUS_REV_11 0x11 /* PMBus revision 1.1 */
++#define PMBUS_REV_12 0x22 /* PMBus revision 1.2 */
++#define PMBUS_REV_13 0x33 /* PMBus revision 1.3 */
++
+ struct pmbus_driver_info {
+ int pages; /* Total number of pages */
+ u8 phases[PMBUS_PAGES]; /* Number of phases per page */
+diff --git a/drivers/hwmon/pmbus/pmbus_core.c b/drivers/hwmon/pmbus/pmbus_core.c
+index cb4c65a7f288c1..e592446b26653e 100644
+--- a/drivers/hwmon/pmbus/pmbus_core.c
++++ b/drivers/hwmon/pmbus/pmbus_core.c
+@@ -85,6 +85,8 @@ struct pmbus_data {
+
+ u32 flags; /* from platform data */
+
++ u8 revision; /* The PMBus revision the device is compliant with */
++
+ int exponent[PMBUS_PAGES];
+ /* linear mode: exponent for output voltages */
+
+@@ -1095,9 +1097,14 @@ static int pmbus_get_boolean(struct i2c_client *client, struct pmbus_boolean *b,
+
+ regval = status & mask;
+ if (regval) {
+- ret = _pmbus_write_byte_data(client, page, reg, regval);
+- if (ret)
+- goto unlock;
++ if (data->revision >= PMBUS_REV_12) {
++ ret = _pmbus_write_byte_data(client, page, reg, regval);
++ if (ret)
++ goto unlock;
++ } else {
++ pmbus_clear_fault_page(client, page);
++ }
++
+ }
+ if (s1 && s2) {
+ s64 v1, v2;
+@@ -2640,6 +2647,10 @@ static int pmbus_init_common(struct i2c_client *client, struct pmbus_data *data,
+ data->flags |= PMBUS_WRITE_PROTECTED | PMBUS_SKIP_STATUS_CHECK;
+ }
+
++ ret = i2c_smbus_read_byte_data(client, PMBUS_REVISION);
++ if (ret >= 0)
++ data->revision = ret;
++
+ if (data->info->pages)
+ pmbus_clear_faults(client);
+ else
+diff --git a/drivers/input/mouse/synaptics.c b/drivers/input/mouse/synaptics.c
+index 7a303a9d6bf72b..cff3393f0dd000 100644
+--- a/drivers/input/mouse/synaptics.c
++++ b/drivers/input/mouse/synaptics.c
+@@ -189,6 +189,7 @@ static const char * const smbus_pnp_ids[] = {
+ "LEN2054", /* E480 */
+ "LEN2055", /* E580 */
+ "LEN2068", /* T14 Gen 1 */
++ "SYN3015", /* HP EliteBook 840 G2 */
+ "SYN3052", /* HP EliteBook 840 G4 */
+ "SYN3221", /* HP 15-ay000 */
+ "SYN323d", /* HP Spectre X360 13-w013dx */
+diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
+index e9eb9554dd7bdc..bad238f69a7afd 100644
+--- a/drivers/input/serio/i8042-acpipnpio.h
++++ b/drivers/input/serio/i8042-acpipnpio.h
+@@ -627,6 +627,15 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
+ },
+ .driver_data = (void *)(SERIO_QUIRK_NOMUX)
+ },
++ {
++ /* Fujitsu Lifebook E756 */
++ /* https://bugzilla.suse.com/show_bug.cgi?id=1229056 */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "FUJITSU"),
++ DMI_MATCH(DMI_PRODUCT_NAME, "LIFEBOOK E756"),
++ },
++ .driver_data = (void *)(SERIO_QUIRK_NOMUX)
++ },
+ {
+ /* Fujitsu Lifebook E5411 */
+ .matches = {
+diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
+index 4d13db13b9e578..b42096c797bf84 100644
+--- a/drivers/input/touchscreen/ads7846.c
++++ b/drivers/input/touchscreen/ads7846.c
+@@ -805,7 +805,7 @@ static void ads7846_read_state(struct ads7846 *ts)
+ m = &ts->msg[msg_idx];
+ error = spi_sync(ts->spi, m);
+ if (error) {
+- dev_err(&ts->spi->dev, "spi_sync --> %d\n", error);
++ dev_err_ratelimited(&ts->spi->dev, "spi_sync --> %d\n", error);
+ packet->ignore = true;
+ return;
+ }
+diff --git a/drivers/input/touchscreen/edt-ft5x06.c b/drivers/input/touchscreen/edt-ft5x06.c
+index 06ec0f2e18ae3b..b0b5b6241b4434 100644
+--- a/drivers/input/touchscreen/edt-ft5x06.c
++++ b/drivers/input/touchscreen/edt-ft5x06.c
+@@ -1474,6 +1474,10 @@ static const struct edt_i2c_chip_data edt_ft6236_data = {
+ .max_support_points = 2,
+ };
+
++static const struct edt_i2c_chip_data edt_ft8201_data = {
++ .max_support_points = 10,
++};
++
+ static const struct edt_i2c_chip_data edt_ft8719_data = {
+ .max_support_points = 10,
+ };
+@@ -1485,6 +1489,7 @@ static const struct i2c_device_id edt_ft5x06_ts_id[] = {
+ { .name = "ft5452", .driver_data = (long)&edt_ft5452_data },
+ /* Note no edt- prefix for compatibility with the ft6236.c driver */
+ { .name = "ft6236", .driver_data = (long)&edt_ft6236_data },
++ { .name = "ft8201", .driver_data = (long)&edt_ft8201_data },
+ { .name = "ft8719", .driver_data = (long)&edt_ft8719_data },
+ { /* sentinel */ }
+ };
+@@ -1499,6 +1504,7 @@ static const struct of_device_id edt_ft5x06_of_match[] = {
+ { .compatible = "focaltech,ft5452", .data = &edt_ft5452_data },
+ /* Note focaltech vendor prefix for compatibility with ft6236.c */
+ { .compatible = "focaltech,ft6236", .data = &edt_ft6236_data },
++ { .compatible = "focaltech,ft8201", .data = &edt_ft8201_data },
+ { .compatible = "focaltech,ft8719", .data = &edt_ft8719_data },
+ { /* sentinel */ }
+ };
+diff --git a/drivers/md/dm-integrity.c b/drivers/md/dm-integrity.c
+index 417fddebe367a2..a74c22cb0f5319 100644
+--- a/drivers/md/dm-integrity.c
++++ b/drivers/md/dm-integrity.c
+@@ -2173,6 +2173,7 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
+ struct bio *bio = dm_bio_from_per_bio_data(dio, sizeof(struct dm_integrity_io));
+ unsigned int journal_section, journal_entry;
+ unsigned int journal_read_pos;
++ sector_t recalc_sector;
+ struct completion read_comp;
+ bool discard_retried = false;
+ bool need_sync_io = ic->internal_hash && dio->op == REQ_OP_READ;
+@@ -2313,6 +2314,7 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
+ goto lock_retry;
+ }
+ }
++ recalc_sector = le64_to_cpu(ic->sb->recalc_sector);
+ spin_unlock_irq(&ic->endio_wait.lock);
+
+ if (unlikely(journal_read_pos != NOT_FOUND)) {
+@@ -2367,7 +2369,7 @@ static void dm_integrity_map_continue(struct dm_integrity_io *dio, bool from_map
+ if (need_sync_io) {
+ wait_for_completion_io(&read_comp);
+ if (ic->sb->flags & cpu_to_le32(SB_FLAG_RECALCULATING) &&
+- dio->range.logical_sector + dio->range.n_sectors > le64_to_cpu(ic->sb->recalc_sector))
++ dio->range.logical_sector + dio->range.n_sectors > recalc_sector)
+ goto skip_check;
+ if (ic->mode == 'B') {
+ if (!block_bitmap_op(ic, ic->recalc_bitmap, dio->range.logical_sector,
+diff --git a/drivers/misc/eeprom/digsy_mtc_eeprom.c b/drivers/misc/eeprom/digsy_mtc_eeprom.c
+index f1f766b709657b..4eddc5ba1af9c8 100644
+--- a/drivers/misc/eeprom/digsy_mtc_eeprom.c
++++ b/drivers/misc/eeprom/digsy_mtc_eeprom.c
+@@ -42,7 +42,7 @@ static void digsy_mtc_op_finish(void *p)
+ }
+
+ struct eeprom_93xx46_platform_data digsy_mtc_eeprom_data = {
+- .flags = EE_ADDR8,
++ .flags = EE_ADDR8 | EE_SIZE1K,
+ .prepare = digsy_mtc_op_prepare,
+ .finish = digsy_mtc_op_finish,
+ };
+diff --git a/drivers/net/dsa/ocelot/felix_vsc9959.c b/drivers/net/dsa/ocelot/felix_vsc9959.c
+index 85952d841f2856..bd061997618d95 100644
+--- a/drivers/net/dsa/ocelot/felix_vsc9959.c
++++ b/drivers/net/dsa/ocelot/felix_vsc9959.c
+@@ -1474,10 +1474,13 @@ static int vsc9959_qos_port_tas_set(struct ocelot *ocelot, int port,
+ /* Hardware errata - Admin config could not be overwritten if
+ * config is pending, need reset the TAS module
+ */
+- val = ocelot_read(ocelot, QSYS_PARAM_STATUS_REG_8);
+- if (val & QSYS_PARAM_STATUS_REG_8_CONFIG_PENDING) {
+- ret = -EBUSY;
+- goto err_reset_tc;
++ val = ocelot_read_rix(ocelot, QSYS_TAG_CONFIG, port);
++ if (val & QSYS_TAG_CONFIG_ENABLE) {
++ val = ocelot_read(ocelot, QSYS_PARAM_STATUS_REG_8);
++ if (val & QSYS_PARAM_STATUS_REG_8_CONFIG_PENDING) {
++ ret = -EBUSY;
++ goto err_reset_tc;
++ }
+ }
+
+ ocelot_rmw_rix(ocelot,
+diff --git a/drivers/net/ethernet/faraday/ftgmac100.h b/drivers/net/ethernet/faraday/ftgmac100.h
+index 63b3e02fab162e..4968f6f0bdbc25 100644
+--- a/drivers/net/ethernet/faraday/ftgmac100.h
++++ b/drivers/net/ethernet/faraday/ftgmac100.h
+@@ -84,7 +84,7 @@
+ FTGMAC100_INT_RPKT_BUF)
+
+ /* All the interrupts we care about */
+-#define FTGMAC100_INT_ALL (FTGMAC100_INT_RPKT_BUF | \
++#define FTGMAC100_INT_ALL (FTGMAC100_INT_RXTX | \
+ FTGMAC100_INT_BAD)
+
+ /*
+diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+index 946c3d3b69d946..669fb5804d3ba0 100644
+--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
++++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+@@ -2285,12 +2285,12 @@ static netdev_tx_t
+ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
+ {
+ const int queue_mapping = skb_get_queue_mapping(skb);
+- bool nonlinear = skb_is_nonlinear(skb);
+ struct rtnl_link_stats64 *percpu_stats;
+ struct dpaa_percpu_priv *percpu_priv;
+ struct netdev_queue *txq;
+ struct dpaa_priv *priv;
+ struct qm_fd fd;
++ bool nonlinear;
+ int offset = 0;
+ int err = 0;
+
+@@ -2300,6 +2300,13 @@ dpaa_start_xmit(struct sk_buff *skb, struct net_device *net_dev)
+
+ qm_fd_clear_fd(&fd);
+
++ /* Packet data is always read as 32-bit words, so zero out any part of
++ * the skb which might be sent if we have to pad the packet
++ */
++ if (__skb_put_padto(skb, ETH_ZLEN, false))
++ goto enomem;
++
++ nonlinear = skb_is_nonlinear(skb);
+ if (!nonlinear) {
+ /* We're going to store the skb backpointer at the beginning
+ * of the data buffer, so we need a privately owned skb
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index 465f0d58228374..6c33195a1168f8 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -11456,7 +11456,7 @@ static void hclge_pci_uninit(struct hclge_dev *hdev)
+
+ pcim_iounmap(pdev, hdev->hw.hw.io_base);
+ pci_free_irq_vectors(pdev);
+- pci_release_mem_regions(pdev);
++ pci_release_regions(pdev);
+ pci_disable_device(pdev);
+ }
+
+diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
+index 7076a77388641c..c2ba586593475c 100644
+--- a/drivers/net/ethernet/intel/ice/ice_lib.c
++++ b/drivers/net/ethernet/intel/ice/ice_lib.c
+@@ -2413,13 +2413,6 @@ void ice_vsi_decfg(struct ice_vsi *vsi)
+ struct ice_pf *pf = vsi->back;
+ int err;
+
+- /* The Rx rule will only exist to remove if the LLDP FW
+- * engine is currently stopped
+- */
+- if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
+- !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
+- ice_cfg_sw_lldp(vsi, false, false);
+-
+ ice_rm_vsi_lan_cfg(vsi->port_info, vsi->idx);
+ err = ice_rm_vsi_rdma_cfg(vsi->port_info, vsi->idx);
+ if (err)
+@@ -2764,6 +2757,14 @@ int ice_vsi_release(struct ice_vsi *vsi)
+ ice_rss_clean(vsi);
+
+ ice_vsi_close(vsi);
++
++ /* The Rx rule will only exist to remove if the LLDP FW
++ * engine is currently stopped
++ */
++ if (!ice_is_safe_mode(pf) && vsi->type == ICE_VSI_PF &&
++ !test_bit(ICE_FLAG_FW_LLDP_AGENT, pf->flags))
++ ice_cfg_sw_lldp(vsi, false, false);
++
+ ice_vsi_decfg(vsi);
+
+ /* retain SW VSI data structure since it is needed to unregister and
+diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
+index ffd6c42bda1ed4..0b85b3653a686d 100644
+--- a/drivers/net/ethernet/intel/ice/ice_switch.c
++++ b/drivers/net/ethernet/intel/ice/ice_switch.c
+@@ -3219,7 +3219,7 @@ ice_add_update_vsi_list(struct ice_hw *hw,
+
+ /* A rule already exists with the new VSI being added */
+ if (test_bit(vsi_handle, m_entry->vsi_list_info->vsi_map))
+- return 0;
++ return -EEXIST;
+
+ /* Update the previously created VSI list set with
+ * the new VSI ID passed in
+@@ -3289,7 +3289,7 @@ ice_find_vsi_list_entry(struct ice_hw *hw, u8 recp_id, u16 vsi_handle,
+
+ list_head = &sw->recp_list[recp_id].filt_rules;
+ list_for_each_entry(list_itr, list_head, list_entry) {
+- if (list_itr->vsi_list_info) {
++ if (list_itr->vsi_count == 1 && list_itr->vsi_list_info) {
+ map_info = list_itr->vsi_list_info;
+ if (test_bit(vsi_handle, map_info->vsi_map)) {
+ *vsi_list_id = map_info->vsi_list_id;
+diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
+index a27d0a4d3d9c4b..6dc5c11aebbd3a 100644
+--- a/drivers/net/ethernet/intel/igb/igb_main.c
++++ b/drivers/net/ethernet/intel/igb/igb_main.c
+@@ -33,6 +33,7 @@
+ #include <linux/bpf_trace.h>
+ #include <linux/pm_runtime.h>
+ #include <linux/etherdevice.h>
++#include <linux/lockdep.h>
+ #ifdef CONFIG_IGB_DCA
+ #include <linux/dca.h>
+ #endif
+@@ -2915,8 +2916,11 @@ static int igb_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+ }
+ }
+
++/* This function assumes __netif_tx_lock is held by the caller. */
+ static void igb_xdp_ring_update_tail(struct igb_ring *ring)
+ {
++ lockdep_assert_held(&txring_txq(ring)->_xmit_lock);
++
+ /* Force memory writes to complete before letting h/w know there
+ * are new descriptors to fetch.
+ */
+@@ -3001,11 +3005,11 @@ static int igb_xdp_xmit(struct net_device *dev, int n,
+ nxmit++;
+ }
+
+- __netif_tx_unlock(nq);
+-
+ if (unlikely(flags & XDP_XMIT_FLUSH))
+ igb_xdp_ring_update_tail(tx_ring);
+
++ __netif_tx_unlock(nq);
++
+ return nxmit;
+ }
+
+@@ -8865,12 +8869,14 @@ static void igb_put_rx_buffer(struct igb_ring *rx_ring,
+
+ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
+ {
++ unsigned int total_bytes = 0, total_packets = 0;
+ struct igb_adapter *adapter = q_vector->adapter;
+ struct igb_ring *rx_ring = q_vector->rx.ring;
+- struct sk_buff *skb = rx_ring->skb;
+- unsigned int total_bytes = 0, total_packets = 0;
+ u16 cleaned_count = igb_desc_unused(rx_ring);
++ struct sk_buff *skb = rx_ring->skb;
++ int cpu = smp_processor_id();
+ unsigned int xdp_xmit = 0;
++ struct netdev_queue *nq;
+ struct xdp_buff xdp;
+ u32 frame_sz = 0;
+ int rx_buf_pgcnt;
+@@ -8998,7 +9004,10 @@ static int igb_clean_rx_irq(struct igb_q_vector *q_vector, const int budget)
+ if (xdp_xmit & IGB_XDP_TX) {
+ struct igb_ring *tx_ring = igb_xdp_tx_queue_mapping(adapter);
+
++ nq = txring_txq(tx_ring);
++ __netif_tx_lock(nq, cpu);
+ igb_xdp_ring_update_tail(tx_ring);
++ __netif_tx_unlock(nq);
+ }
+
+ u64_stats_update_begin(&rx_ring->rx_syncp);
+diff --git a/drivers/net/ethernet/jme.c b/drivers/net/ethernet/jme.c
+index b06e245629739f..d8be0e4dcb072b 100644
+--- a/drivers/net/ethernet/jme.c
++++ b/drivers/net/ethernet/jme.c
+@@ -946,15 +946,13 @@ jme_udpsum(struct sk_buff *skb)
+ if (skb->protocol != htons(ETH_P_IP))
+ return csum;
+ skb_set_network_header(skb, ETH_HLEN);
+- if ((ip_hdr(skb)->protocol != IPPROTO_UDP) ||
+- (skb->len < (ETH_HLEN +
+- (ip_hdr(skb)->ihl << 2) +
+- sizeof(struct udphdr)))) {
++
++ if (ip_hdr(skb)->protocol != IPPROTO_UDP ||
++ skb->len < (ETH_HLEN + ip_hdrlen(skb) + sizeof(struct udphdr))) {
+ skb_reset_network_header(skb);
+ return csum;
+ }
+- skb_set_transport_header(skb,
+- ETH_HLEN + (ip_hdr(skb)->ihl << 2));
++ skb_set_transport_header(skb, ETH_HLEN + ip_hdrlen(skb));
+ csum = udp_hdr(skb)->check;
+ skb_reset_transport_header(skb);
+ skb_reset_network_header(skb);
+diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+index 35834687e40fe9..96a7b23428be24 100644
+--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
++++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu.h
+@@ -318,6 +318,7 @@ struct nix_mark_format {
+
+ /* smq(flush) to tl1 cir/pir info */
+ struct nix_smq_tree_ctx {
++ u16 schq;
+ u64 cir_off;
+ u64 cir_val;
+ u64 pir_off;
+@@ -327,8 +328,6 @@ struct nix_smq_tree_ctx {
+ /* smq flush context */
+ struct nix_smq_flush_ctx {
+ int smq;
+- u16 tl1_schq;
+- u16 tl2_schq;
+ struct nix_smq_tree_ctx smq_tree_ctx[NIX_TXSCH_LVL_CNT];
+ };
+
+diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+index 3dc828cf6c5a6f..10f8efff7843de 100644
+--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
++++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_nix.c
+@@ -2259,14 +2259,13 @@ static void nix_smq_flush_fill_ctx(struct rvu *rvu, int blkaddr, int smq,
+ schq = smq;
+ for (lvl = NIX_TXSCH_LVL_SMQ; lvl <= NIX_TXSCH_LVL_TL1; lvl++) {
+ smq_tree_ctx = &smq_flush_ctx->smq_tree_ctx[lvl];
++ smq_tree_ctx->schq = schq;
+ if (lvl == NIX_TXSCH_LVL_TL1) {
+- smq_flush_ctx->tl1_schq = schq;
+ smq_tree_ctx->cir_off = NIX_AF_TL1X_CIR(schq);
+ smq_tree_ctx->pir_off = 0;
+ smq_tree_ctx->pir_val = 0;
+ parent_off = 0;
+ } else if (lvl == NIX_TXSCH_LVL_TL2) {
+- smq_flush_ctx->tl2_schq = schq;
+ smq_tree_ctx->cir_off = NIX_AF_TL2X_CIR(schq);
+ smq_tree_ctx->pir_off = NIX_AF_TL2X_PIR(schq);
+ parent_off = NIX_AF_TL2X_PARENT(schq);
+@@ -2301,8 +2300,8 @@ static void nix_smq_flush_enadis_xoff(struct rvu *rvu, int blkaddr,
+ {
+ struct nix_txsch *txsch;
+ struct nix_hw *nix_hw;
++ int tl2, tl2_schq;
+ u64 regoff;
+- int tl2;
+
+ nix_hw = get_nix_hw(rvu->hw, blkaddr);
+ if (!nix_hw)
+@@ -2310,16 +2309,17 @@ static void nix_smq_flush_enadis_xoff(struct rvu *rvu, int blkaddr,
+
+ /* loop through all TL2s with matching PF_FUNC */
+ txsch = &nix_hw->txsch[NIX_TXSCH_LVL_TL2];
++ tl2_schq = smq_flush_ctx->smq_tree_ctx[NIX_TXSCH_LVL_TL2].schq;
+ for (tl2 = 0; tl2 < txsch->schq.max; tl2++) {
+ /* skip the smq(flush) TL2 */
+- if (tl2 == smq_flush_ctx->tl2_schq)
++ if (tl2 == tl2_schq)
+ continue;
+ /* skip unused TL2s */
+ if (TXSCH_MAP_FLAGS(txsch->pfvf_map[tl2]) & NIX_TXSCHQ_FREE)
+ continue;
+ /* skip if PF_FUNC doesn't match */
+ if ((TXSCH_MAP_FUNC(txsch->pfvf_map[tl2]) & ~RVU_PFVF_FUNC_MASK) !=
+- (TXSCH_MAP_FUNC(txsch->pfvf_map[smq_flush_ctx->tl2_schq] &
++ (TXSCH_MAP_FUNC(txsch->pfvf_map[tl2_schq] &
+ ~RVU_PFVF_FUNC_MASK)))
+ continue;
+ /* enable/disable XOFF */
+@@ -2361,10 +2361,12 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
+ int smq, u16 pcifunc, int nixlf)
+ {
+ struct nix_smq_flush_ctx *smq_flush_ctx;
++ int err, restore_tx_en = 0, i;
+ int pf = rvu_get_pf(pcifunc);
+ u8 cgx_id = 0, lmac_id = 0;
+- int err, restore_tx_en = 0;
+- u64 cfg;
++ u16 tl2_tl3_link_schq;
++ u8 link, link_level;
++ u64 cfg, bmap = 0;
+
+ if (!is_rvu_otx2(rvu)) {
+ /* Skip SMQ flush if pkt count is zero */
+@@ -2388,16 +2390,38 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
+ nix_smq_flush_enadis_xoff(rvu, blkaddr, smq_flush_ctx, true);
+ nix_smq_flush_enadis_rate(rvu, blkaddr, smq_flush_ctx, false);
+
+- cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq));
+- /* Do SMQ flush and set enqueue xoff */
+- cfg |= BIT_ULL(50) | BIT_ULL(49);
+- rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg);
+-
+ /* Disable backpressure from physical link,
+ * otherwise SMQ flush may stall.
+ */
+ rvu_cgx_enadis_rx_bp(rvu, pf, false);
+
++ link_level = rvu_read64(rvu, blkaddr, NIX_AF_PSE_CHANNEL_LEVEL) & 0x01 ?
++ NIX_TXSCH_LVL_TL3 : NIX_TXSCH_LVL_TL2;
++ tl2_tl3_link_schq = smq_flush_ctx->smq_tree_ctx[link_level].schq;
++ link = smq_flush_ctx->smq_tree_ctx[NIX_TXSCH_LVL_TL1].schq;
++
++ /* SMQ set enqueue xoff */
++ cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq));
++ cfg |= BIT_ULL(50);
++ rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg);
++
++ /* Clear all NIX_AF_TL3_TL2_LINK_CFG[ENA] for the TL3/TL2 queue */
++ for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) {
++ cfg = rvu_read64(rvu, blkaddr,
++ NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link));
++ if (!(cfg & BIT_ULL(12)))
++ continue;
++ bmap |= (1 << i);
++ cfg &= ~BIT_ULL(12);
++ rvu_write64(rvu, blkaddr,
++ NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg);
++ }
++
++ /* Do SMQ flush and set enqueue xoff */
++ cfg = rvu_read64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq));
++ cfg |= BIT_ULL(50) | BIT_ULL(49);
++ rvu_write64(rvu, blkaddr, NIX_AF_SMQX_CFG(smq), cfg);
++
+ /* Wait for flush to complete */
+ err = rvu_poll_reg(rvu, blkaddr,
+ NIX_AF_SMQX_CFG(smq), BIT_ULL(49), true);
+@@ -2406,6 +2430,17 @@ static int nix_smq_flush(struct rvu *rvu, int blkaddr,
+ "NIXLF%d: SMQ%d flush failed, txlink might be busy\n",
+ nixlf, smq);
+
++ /* Set NIX_AF_TL3_TL2_LINKX_CFG[ENA] for the TL3/TL2 queue */
++ for (i = 0; i < (rvu->hw->cgx_links + rvu->hw->lbk_links); i++) {
++ if (!(bmap & (1 << i)))
++ continue;
++ cfg = rvu_read64(rvu, blkaddr,
++ NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link));
++ cfg |= BIT_ULL(12);
++ rvu_write64(rvu, blkaddr,
++ NIX_AF_TL3_TL2X_LINKX_CFG(tl2_tl3_link_schq, link), cfg);
++ }
++
+ /* clear XOFF on TL2s */
+ nix_smq_flush_enadis_rate(rvu, blkaddr, smq_flush_ctx, true);
+ nix_smq_flush_enadis_xoff(rvu, blkaddr, smq_flush_ctx, false);
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+index 58eb96a688533c..9d2d67e24205ec 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+@@ -139,6 +139,10 @@ void mlx5e_build_ptys2ethtool_map(void)
+ ETHTOOL_LINK_MODE_100000baseKR4_Full_BIT);
+ MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GBASE_LR4, legacy,
+ ETHTOOL_LINK_MODE_100000baseLR4_ER4_Full_BIT);
++ MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100BASE_TX, legacy,
++ ETHTOOL_LINK_MODE_100baseT_Full_BIT);
++ MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_1000BASE_T, legacy,
++ ETHTOOL_LINK_MODE_1000baseT_Full_BIT);
+ MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_10GBASE_T, legacy,
+ ETHTOOL_LINK_MODE_10000baseT_Full_BIT);
+ MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_25GBASE_CR, legacy,
+@@ -204,6 +208,12 @@ void mlx5e_build_ptys2ethtool_map(void)
+ ETHTOOL_LINK_MODE_200000baseLR4_ER4_FR4_Full_BIT,
+ ETHTOOL_LINK_MODE_200000baseDR4_Full_BIT,
+ ETHTOOL_LINK_MODE_200000baseCR4_Full_BIT);
++ MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_400GAUI_8_400GBASE_CR8, ext,
++ ETHTOOL_LINK_MODE_400000baseKR8_Full_BIT,
++ ETHTOOL_LINK_MODE_400000baseSR8_Full_BIT,
++ ETHTOOL_LINK_MODE_400000baseLR8_ER8_FR8_Full_BIT,
++ ETHTOOL_LINK_MODE_400000baseDR8_Full_BIT,
++ ETHTOOL_LINK_MODE_400000baseCR8_Full_BIT);
+ MLX5_BUILD_PTYS2ETHTOOL_CONFIG(MLX5E_100GAUI_1_100GBASE_CR_KR, ext,
+ ETHTOOL_LINK_MODE_100000baseKR_Full_BIT,
+ ETHTOOL_LINK_MODE_100000baseSR_Full_BIT,
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+index 255bc8b749f9a5..8587cd572da536 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/legacy.c
+@@ -319,7 +319,7 @@ int mlx5_eswitch_set_vepa(struct mlx5_eswitch *esw, u8 setting)
+ return -EPERM;
+
+ mutex_lock(&esw->state_lock);
+- if (esw->mode != MLX5_ESWITCH_LEGACY) {
++ if (esw->mode != MLX5_ESWITCH_LEGACY || !mlx5_esw_is_fdb_created(esw)) {
+ err = -EOPNOTSUPP;
+ goto out;
+ }
+@@ -339,7 +339,7 @@ int mlx5_eswitch_get_vepa(struct mlx5_eswitch *esw, u8 *setting)
+ if (!mlx5_esw_allowed(esw))
+ return -EPERM;
+
+- if (esw->mode != MLX5_ESWITCH_LEGACY)
++ if (esw->mode != MLX5_ESWITCH_LEGACY || !mlx5_esw_is_fdb_created(esw))
+ return -EOPNOTSUPP;
+
+ *setting = esw->fdb_table.legacy.vepa_uplink_rule ? 1 : 0;
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+index d2ebe56c3977cc..02a3563f51ad26 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/esw/qos.c
+@@ -312,6 +312,25 @@ static int esw_qos_set_group_max_rate(struct mlx5_eswitch *esw,
+ return err;
+ }
+
++static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type)
++{
++ switch (type) {
++ case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
++ return MLX5_CAP_QOS(dev, esw_element_type) &
++ ELEMENT_TYPE_CAP_MASK_TSAR;
++ case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
++ return MLX5_CAP_QOS(dev, esw_element_type) &
++ ELEMENT_TYPE_CAP_MASK_VPORT;
++ case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
++ return MLX5_CAP_QOS(dev, esw_element_type) &
++ ELEMENT_TYPE_CAP_MASK_VPORT_TC;
++ case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
++ return MLX5_CAP_QOS(dev, esw_element_type) &
++ ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
++ }
++ return false;
++}
++
+ static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw,
+ struct mlx5_vport *vport,
+ u32 max_rate, u32 bw_share)
+@@ -323,6 +342,9 @@ static int esw_qos_vport_create_sched_element(struct mlx5_eswitch *esw,
+ void *vport_elem;
+ int err;
+
++ if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT))
++ return -EOPNOTSUPP;
++
+ parent_tsar_ix = group ? group->tsar_ix : esw->qos.root_tsar_ix;
+ MLX5_SET(scheduling_context, sched_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT);
+@@ -421,6 +443,7 @@ __esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *ex
+ {
+ u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+ struct mlx5_esw_rate_group *group;
++ __be32 *attr;
+ u32 divider;
+ int err;
+
+@@ -428,6 +451,12 @@ __esw_qos_create_rate_group(struct mlx5_eswitch *esw, struct netlink_ext_ack *ex
+ if (!group)
+ return ERR_PTR(-ENOMEM);
+
++ MLX5_SET(scheduling_context, tsar_ctx, element_type,
++ SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
++
++ attr = MLX5_ADDR_OF(scheduling_context, tsar_ctx, element_attributes);
++ *attr = cpu_to_be32(TSAR_ELEMENT_TSAR_TYPE_DWRR << 16);
++
+ MLX5_SET(scheduling_context, tsar_ctx, parent_element_id,
+ esw->qos.root_tsar_ix);
+ err = mlx5_create_scheduling_element_cmd(esw->dev,
+@@ -526,25 +555,6 @@ static int esw_qos_destroy_rate_group(struct mlx5_eswitch *esw,
+ return err;
+ }
+
+-static bool esw_qos_element_type_supported(struct mlx5_core_dev *dev, int type)
+-{
+- switch (type) {
+- case SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR:
+- return MLX5_CAP_QOS(dev, esw_element_type) &
+- ELEMENT_TYPE_CAP_MASK_TASR;
+- case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT:
+- return MLX5_CAP_QOS(dev, esw_element_type) &
+- ELEMENT_TYPE_CAP_MASK_VPORT;
+- case SCHEDULING_CONTEXT_ELEMENT_TYPE_VPORT_TC:
+- return MLX5_CAP_QOS(dev, esw_element_type) &
+- ELEMENT_TYPE_CAP_MASK_VPORT_TC;
+- case SCHEDULING_CONTEXT_ELEMENT_TYPE_PARA_VPORT_TC:
+- return MLX5_CAP_QOS(dev, esw_element_type) &
+- ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC;
+- }
+- return false;
+-}
+-
+ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *extack)
+ {
+ u32 tsar_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {};
+@@ -555,7 +565,8 @@ static int esw_qos_create(struct mlx5_eswitch *esw, struct netlink_ext_ack *exta
+ if (!MLX5_CAP_GEN(dev, qos) || !MLX5_CAP_QOS(dev, esw_scheduling))
+ return -EOPNOTSUPP;
+
+- if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR))
++ if (!esw_qos_element_type_supported(dev, SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR) ||
++ !(MLX5_CAP_QOS(dev, esw_tsar_type) & TSAR_TYPE_CAP_MASK_DWRR))
+ return -EOPNOTSUPP;
+
+ MLX5_SET(scheduling_context, tsar_ctx, element_type,
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
+index 3e55a6c6a7c9bf..211194df9619c4 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
+@@ -2215,6 +2215,7 @@ static const struct pci_device_id mlx5_core_pci_table[] = {
+ { PCI_VDEVICE(MELLANOX, 0x101f) }, /* ConnectX-6 LX */
+ { PCI_VDEVICE(MELLANOX, 0x1021) }, /* ConnectX-7 */
+ { PCI_VDEVICE(MELLANOX, 0x1023) }, /* ConnectX-8 */
++ { PCI_VDEVICE(MELLANOX, 0x1025) }, /* ConnectX-9 */
+ { PCI_VDEVICE(MELLANOX, 0xa2d2) }, /* BlueField integrated ConnectX-5 network controller */
+ { PCI_VDEVICE(MELLANOX, 0xa2d3), MLX5_PCI_DEV_IS_VF}, /* BlueField integrated ConnectX-5 network controller VF */
+ { PCI_VDEVICE(MELLANOX, 0xa2d6) }, /* BlueField-2 integrated ConnectX-6 Dx network controller */
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qos.c b/drivers/net/ethernet/mellanox/mlx5/core/qos.c
+index 8bce730b5c5bef..db2bd3ad63ba36 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/qos.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/qos.c
+@@ -28,6 +28,9 @@ int mlx5_qos_create_leaf_node(struct mlx5_core_dev *mdev, u32 parent_id,
+ {
+ u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+
++ if (!(MLX5_CAP_QOS(mdev, nic_element_type) & ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP))
++ return -EOPNOTSUPP;
++
+ MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id);
+ MLX5_SET(scheduling_context, sched_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_QUEUE_GROUP);
+@@ -44,6 +47,10 @@ int mlx5_qos_create_inner_node(struct mlx5_core_dev *mdev, u32 parent_id,
+ u32 sched_ctx[MLX5_ST_SZ_DW(scheduling_context)] = {0};
+ void *attr;
+
++ if (!(MLX5_CAP_QOS(mdev, nic_element_type) & ELEMENT_TYPE_CAP_MASK_TSAR) ||
++ !(MLX5_CAP_QOS(mdev, nic_tsar_type) & TSAR_TYPE_CAP_MASK_DWRR))
++ return -EOPNOTSUPP;
++
+ MLX5_SET(scheduling_context, sched_ctx, parent_element_id, parent_id);
+ MLX5_SET(scheduling_context, sched_ctx, element_type,
+ SCHEDULING_CONTEXT_ELEMENT_TYPE_TSAR);
+diff --git a/drivers/net/ethernet/wangxun/libwx/wx_type.h b/drivers/net/ethernet/wangxun/libwx/wx_type.h
+index 0df7f5712b6f71..9f98f5749064b6 100644
+--- a/drivers/net/ethernet/wangxun/libwx/wx_type.h
++++ b/drivers/net/ethernet/wangxun/libwx/wx_type.h
+@@ -424,9 +424,9 @@ enum WX_MSCA_CMD_value {
+ #define WX_MIN_RXD 128
+ #define WX_MIN_TXD 128
+
+-/* Number of Transmit and Receive Descriptors must be a multiple of 8 */
+-#define WX_REQ_RX_DESCRIPTOR_MULTIPLE 8
+-#define WX_REQ_TX_DESCRIPTOR_MULTIPLE 8
++/* Number of Transmit and Receive Descriptors must be a multiple of 128 */
++#define WX_REQ_RX_DESCRIPTOR_MULTIPLE 128
++#define WX_REQ_TX_DESCRIPTOR_MULTIPLE 128
+
+ #define WX_MAX_JUMBO_FRAME_SIZE 9432 /* max payload 9414 */
+ #define VMDQ_P(p) p
+diff --git a/drivers/net/phy/dp83822.c b/drivers/net/phy/dp83822.c
+index efeb643c13733c..fc247f479257ae 100644
+--- a/drivers/net/phy/dp83822.c
++++ b/drivers/net/phy/dp83822.c
+@@ -271,8 +271,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
+ DP83822_ENERGY_DET_INT_EN |
+ DP83822_LINK_QUAL_INT_EN);
+
+- /* Private data pointer is NULL on DP83825 */
+- if (!dp83822 || !dp83822->fx_enabled)
++ if (!dp83822->fx_enabled)
+ misr_status |= DP83822_ANEG_COMPLETE_INT_EN |
+ DP83822_DUP_MODE_CHANGE_INT_EN |
+ DP83822_SPEED_CHANGED_INT_EN;
+@@ -292,8 +291,7 @@ static int dp83822_config_intr(struct phy_device *phydev)
+ DP83822_PAGE_RX_INT_EN |
+ DP83822_EEE_ERROR_CHANGE_INT_EN);
+
+- /* Private data pointer is NULL on DP83825 */
+- if (!dp83822 || !dp83822->fx_enabled)
++ if (!dp83822->fx_enabled)
+ misr_status |= DP83822_ANEG_ERR_INT_EN |
+ DP83822_WOL_PKT_INT_EN;
+
+@@ -691,10 +689,9 @@ static int dp83822_read_straps(struct phy_device *phydev)
+ return 0;
+ }
+
+-static int dp83822_probe(struct phy_device *phydev)
++static int dp8382x_probe(struct phy_device *phydev)
+ {
+ struct dp83822_private *dp83822;
+- int ret;
+
+ dp83822 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83822),
+ GFP_KERNEL);
+@@ -703,6 +700,20 @@ static int dp83822_probe(struct phy_device *phydev)
+
+ phydev->priv = dp83822;
+
++ return 0;
++}
++
++static int dp83822_probe(struct phy_device *phydev)
++{
++ struct dp83822_private *dp83822;
++ int ret;
++
++ ret = dp8382x_probe(phydev);
++ if (ret)
++ return ret;
++
++ dp83822 = phydev->priv;
++
+ ret = dp83822_read_straps(phydev);
+ if (ret)
+ return ret;
+@@ -717,14 +728,11 @@ static int dp83822_probe(struct phy_device *phydev)
+
+ static int dp83826_probe(struct phy_device *phydev)
+ {
+- struct dp83822_private *dp83822;
+-
+- dp83822 = devm_kzalloc(&phydev->mdio.dev, sizeof(*dp83822),
+- GFP_KERNEL);
+- if (!dp83822)
+- return -ENOMEM;
++ int ret;
+
+- phydev->priv = dp83822;
++ ret = dp8382x_probe(phydev);
++ if (ret)
++ return ret;
+
+ dp83826_of_init(phydev);
+
+@@ -795,6 +803,7 @@ static int dp83822_resume(struct phy_device *phydev)
+ PHY_ID_MATCH_MODEL(_id), \
+ .name = (_name), \
+ /* PHY_BASIC_FEATURES */ \
++ .probe = dp8382x_probe, \
+ .soft_reset = dp83822_phy_reset, \
+ .config_init = dp8382x_config_init, \
+ .get_wol = dp83822_get_wol, \
+diff --git a/drivers/net/phy/vitesse.c b/drivers/net/phy/vitesse.c
+index 897b979ec03c81..3b5fcaf0dd36db 100644
+--- a/drivers/net/phy/vitesse.c
++++ b/drivers/net/phy/vitesse.c
+@@ -237,16 +237,6 @@ static int vsc739x_config_init(struct phy_device *phydev)
+ return 0;
+ }
+
+-static int vsc73xx_config_aneg(struct phy_device *phydev)
+-{
+- /* The VSC73xx switches does not like to be instructed to
+- * do autonegotiation in any way, it prefers that you just go
+- * with the power-on/reset defaults. Writing some registers will
+- * just make autonegotiation permanently fail.
+- */
+- return 0;
+-}
+-
+ /* This adds a skew for both TX and RX clocks, so the skew should only be
+ * applied to "rgmii-id" interfaces. It may not work as expected
+ * on "rgmii-txid", "rgmii-rxid" or "rgmii" interfaces.
+@@ -444,7 +434,6 @@ static struct phy_driver vsc82xx_driver[] = {
+ .phy_id_mask = 0x000ffff0,
+ /* PHY_GBIT_FEATURES */
+ .config_init = vsc738x_config_init,
+- .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
+ }, {
+@@ -453,7 +442,6 @@ static struct phy_driver vsc82xx_driver[] = {
+ .phy_id_mask = 0x000ffff0,
+ /* PHY_GBIT_FEATURES */
+ .config_init = vsc738x_config_init,
+- .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
+ }, {
+@@ -462,7 +450,6 @@ static struct phy_driver vsc82xx_driver[] = {
+ .phy_id_mask = 0x000ffff0,
+ /* PHY_GBIT_FEATURES */
+ .config_init = vsc739x_config_init,
+- .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
+ }, {
+@@ -471,7 +458,6 @@ static struct phy_driver vsc82xx_driver[] = {
+ .phy_id_mask = 0x000ffff0,
+ /* PHY_GBIT_FEATURES */
+ .config_init = vsc739x_config_init,
+- .config_aneg = vsc73xx_config_aneg,
+ .read_page = vsc73xx_read_page,
+ .write_page = vsc73xx_write_page,
+ }, {
+diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
+index 6eeef10edadad1..46afb95ffabe3b 100644
+--- a/drivers/net/usb/ipheth.c
++++ b/drivers/net/usb/ipheth.c
+@@ -286,10 +286,11 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
+ return;
+ }
+
+- if (urb->actual_length <= IPHETH_IP_ALIGN) {
+- dev->net->stats.rx_length_errors++;
+- return;
+- }
++ /* iPhone may periodically send URBs with no payload
++ * on the "bulk in" endpoint. It is safe to ignore them.
++ */
++ if (urb->actual_length == 0)
++ goto rx_submit;
+
+ /* RX URBs starting with 0x00 0x01 do not encapsulate Ethernet frames,
+ * but rather are control frames. Their purpose is not documented, and
+@@ -298,7 +299,8 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
+ * URB received from the bulk IN endpoint.
+ */
+ if (unlikely
+- (((char *)urb->transfer_buffer)[0] == 0 &&
++ (urb->actual_length == 4 &&
++ ((char *)urb->transfer_buffer)[0] == 0 &&
+ ((char *)urb->transfer_buffer)[1] == 1))
+ goto rx_submit;
+
+@@ -306,7 +308,6 @@ static void ipheth_rcvbulk_callback(struct urb *urb)
+ if (retval != 0) {
+ dev_err(&dev->intf->dev, "%s: callback retval: %d\n",
+ __func__, retval);
+- return;
+ }
+
+ rx_submit:
+@@ -354,13 +355,14 @@ static int ipheth_carrier_set(struct ipheth_device *dev)
+ 0x02, /* index */
+ dev->ctrl_buf, IPHETH_CTRL_BUF_SIZE,
+ IPHETH_CTRL_TIMEOUT);
+- if (retval < 0) {
++ if (retval <= 0) {
+ dev_err(&dev->intf->dev, "%s: usb_control_msg: %d\n",
+ __func__, retval);
+ return retval;
+ }
+
+- if (dev->ctrl_buf[0] == IPHETH_CARRIER_ON) {
++ if ((retval == 1 && dev->ctrl_buf[0] == IPHETH_CARRIER_ON) ||
++ (retval >= 2 && dev->ctrl_buf[1] == IPHETH_CARRIER_ON)) {
+ netif_carrier_on(dev->net);
+ if (dev->tx_urb->status != -EINPROGRESS)
+ netif_wake_queue(dev->net);
+diff --git a/drivers/net/wireless/mediatek/mt76/mt7921/main.c b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+index 3e3ad3518d85f9..cca7132ed6ab19 100644
+--- a/drivers/net/wireless/mediatek/mt76/mt7921/main.c
++++ b/drivers/net/wireless/mediatek/mt76/mt7921/main.c
+@@ -1182,7 +1182,7 @@ static void mt7921_ipv6_addr_change(struct ieee80211_hw *hw,
+ struct inet6_dev *idev)
+ {
+ struct mt792x_vif *mvif = (struct mt792x_vif *)vif->drv_priv;
+- struct mt792x_dev *dev = mvif->phy->dev;
++ struct mt792x_dev *dev = mt792x_hw_dev(hw);
+ struct inet6_ifaddr *ifa;
+ struct in6_addr ns_addrs[IEEE80211_BSS_ARP_ADDR_LIST_LEN];
+ struct sk_buff *skb;
+diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
+index 11c7c85047ed42..765bda7924f7bf 100644
+--- a/drivers/perf/riscv_pmu_sbi.c
++++ b/drivers/perf/riscv_pmu_sbi.c
+@@ -1368,11 +1368,15 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
+
+ /* SBI PMU Snapsphot is only available in SBI v2.0 */
+ if (sbi_v2_available) {
++ int cpu;
++
+ ret = pmu_sbi_snapshot_alloc(pmu);
+ if (ret)
+ goto out_unregister;
+
+- ret = pmu_sbi_snapshot_setup(pmu, smp_processor_id());
++ cpu = get_cpu();
++
++ ret = pmu_sbi_snapshot_setup(pmu, cpu);
+ if (ret) {
+ /* Snapshot is an optional feature. Continue if not available */
+ pmu_sbi_snapshot_free(pmu);
+@@ -1386,6 +1390,7 @@ static int pmu_sbi_device_probe(struct platform_device *pdev)
+ */
+ static_branch_enable(&sbi_pmu_snapshot_available);
+ }
++ put_cpu();
+ }
+
+ register_sysctl("kernel", sbi_pmu_sysctl_table);
+diff --git a/drivers/pinctrl/intel/pinctrl-meteorlake.c b/drivers/pinctrl/intel/pinctrl-meteorlake.c
+index cc44890c6699dc..885fa3b0d6d95f 100644
+--- a/drivers/pinctrl/intel/pinctrl-meteorlake.c
++++ b/drivers/pinctrl/intel/pinctrl-meteorlake.c
+@@ -584,6 +584,7 @@ static const struct intel_pinctrl_soc_data mtls_soc_data = {
+ };
+
+ static const struct acpi_device_id mtl_pinctrl_acpi_match[] = {
++ { "INTC105E", (kernel_ulong_t)&mtlp_soc_data },
+ { "INTC1083", (kernel_ulong_t)&mtlp_soc_data },
+ { "INTC1082", (kernel_ulong_t)&mtls_soc_data },
+ { }
+diff --git a/drivers/platform/surface/surface_aggregator_registry.c b/drivers/platform/surface/surface_aggregator_registry.c
+index 1c4d74db08c954..a23dff35f8ca23 100644
+--- a/drivers/platform/surface/surface_aggregator_registry.c
++++ b/drivers/platform/surface/surface_aggregator_registry.c
+@@ -265,16 +265,34 @@ static const struct software_node *ssam_node_group_sl5[] = {
+ &ssam_node_root,
+ &ssam_node_bat_ac,
+ &ssam_node_bat_main,
+- &ssam_node_tmp_perf_profile,
++ &ssam_node_tmp_perf_profile_with_fan,
++ &ssam_node_tmp_sensors,
++ &ssam_node_fan_speed,
++ &ssam_node_hid_main_keyboard,
++ &ssam_node_hid_main_touchpad,
++ &ssam_node_hid_main_iid5,
++ &ssam_node_hid_sam_ucm_ucsi,
++ NULL,
++};
++
++/* Devices for Surface Laptop 6. */
++static const struct software_node *ssam_node_group_sl6[] = {
++ &ssam_node_root,
++ &ssam_node_bat_ac,
++ &ssam_node_bat_main,
++ &ssam_node_tmp_perf_profile_with_fan,
++ &ssam_node_tmp_sensors,
++ &ssam_node_fan_speed,
+ &ssam_node_hid_main_keyboard,
+ &ssam_node_hid_main_touchpad,
+ &ssam_node_hid_main_iid5,
++ &ssam_node_hid_sam_sensors,
+ &ssam_node_hid_sam_ucm_ucsi,
+ NULL,
+ };
+
+-/* Devices for Surface Laptop Studio. */
+-static const struct software_node *ssam_node_group_sls[] = {
++/* Devices for Surface Laptop Studio 1. */
++static const struct software_node *ssam_node_group_sls1[] = {
+ &ssam_node_root,
+ &ssam_node_bat_ac,
+ &ssam_node_bat_main,
+@@ -289,6 +307,22 @@ static const struct software_node *ssam_node_group_sls[] = {
+ NULL,
+ };
+
++/* Devices for Surface Laptop Studio 2. */
++static const struct software_node *ssam_node_group_sls2[] = {
++ &ssam_node_root,
++ &ssam_node_bat_ac,
++ &ssam_node_bat_main,
++ &ssam_node_tmp_perf_profile_with_fan,
++ &ssam_node_tmp_sensors,
++ &ssam_node_fan_speed,
++ &ssam_node_pos_tablet_switch,
++ &ssam_node_hid_sam_keyboard,
++ &ssam_node_hid_sam_penstash,
++ &ssam_node_hid_sam_sensors,
++ &ssam_node_hid_sam_ucm_ucsi,
++ NULL,
++};
++
+ /* Devices for Surface Laptop Go. */
+ static const struct software_node *ssam_node_group_slg1[] = {
+ &ssam_node_root,
+@@ -324,7 +358,7 @@ static const struct software_node *ssam_node_group_sp8[] = {
+ NULL,
+ };
+
+-/* Devices for Surface Pro 9 */
++/* Devices for Surface Pro 9 and 10 */
+ static const struct software_node *ssam_node_group_sp9[] = {
+ &ssam_node_root,
+ &ssam_node_hub_kip,
+@@ -365,6 +399,9 @@ static const struct acpi_device_id ssam_platform_hub_match[] = {
+ /* Surface Pro 9 */
+ { "MSHW0343", (unsigned long)ssam_node_group_sp9 },
+
++ /* Surface Pro 10 */
++ { "MSHW0510", (unsigned long)ssam_node_group_sp9 },
++
+ /* Surface Book 2 */
+ { "MSHW0107", (unsigned long)ssam_node_group_gen5 },
+
+@@ -389,14 +426,23 @@ static const struct acpi_device_id ssam_platform_hub_match[] = {
+ /* Surface Laptop 5 */
+ { "MSHW0350", (unsigned long)ssam_node_group_sl5 },
+
++ /* Surface Laptop 6 */
++ { "MSHW0530", (unsigned long)ssam_node_group_sl6 },
++
+ /* Surface Laptop Go 1 */
+ { "MSHW0118", (unsigned long)ssam_node_group_slg1 },
+
+ /* Surface Laptop Go 2 */
+ { "MSHW0290", (unsigned long)ssam_node_group_slg1 },
+
+- /* Surface Laptop Studio */
+- { "MSHW0123", (unsigned long)ssam_node_group_sls },
++ /* Surface Laptop Go 3 */
++ { "MSHW0440", (unsigned long)ssam_node_group_slg1 },
++
++ /* Surface Laptop Studio 1 */
++ { "MSHW0123", (unsigned long)ssam_node_group_sls1 },
++
++ /* Surface Laptop Studio 2 */
++ { "MSHW0360", (unsigned long)ssam_node_group_sls2 },
+
+ { },
+ };
+diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
+index bc9c5db3832445..5fe5149549cc9e 100644
+--- a/drivers/platform/x86/asus-wmi.c
++++ b/drivers/platform/x86/asus-wmi.c
+@@ -146,6 +146,20 @@ static const char * const ashs_ids[] = { "ATK4001", "ATK4002", NULL };
+
+ static int throttle_thermal_policy_write(struct asus_wmi *);
+
++static const struct dmi_system_id asus_ally_mcu_quirk[] = {
++ {
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "RC71L"),
++ },
++ },
++ {
++ .matches = {
++ DMI_MATCH(DMI_BOARD_NAME, "RC72L"),
++ },
++ },
++ { },
++};
++
+ static bool ashs_present(void)
+ {
+ int i = 0;
+@@ -4650,7 +4664,7 @@ static int asus_wmi_add(struct platform_device *pdev)
+ asus->dgpu_disable_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_DGPU);
+ asus->kbd_rgb_state_available = asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_TUF_RGB_STATE);
+ asus->ally_mcu_usb_switch = acpi_has_method(NULL, ASUS_USB0_PWR_EC0_CSEE)
+- && dmi_match(DMI_BOARD_NAME, "RC71L");
++ && dmi_check_system(asus_ally_mcu_quirk);
+
+ if (asus_wmi_dev_is_present(asus, ASUS_WMI_DEVID_MINI_LED_MODE))
+ asus->mini_led_dev_id = ASUS_WMI_DEVID_MINI_LED_MODE;
+diff --git a/drivers/platform/x86/panasonic-laptop.c b/drivers/platform/x86/panasonic-laptop.c
+index cf845ee1c7b1f0..ebd81846e2d564 100644
+--- a/drivers/platform/x86/panasonic-laptop.c
++++ b/drivers/platform/x86/panasonic-laptop.c
+@@ -337,7 +337,8 @@ static int acpi_pcc_retrieve_biosdata(struct pcc_acpi *pcc)
+ }
+
+ if (pcc->num_sifr < hkey->package.count) {
+- pr_err("SQTY reports bad SINF length\n");
++ pr_err("SQTY reports bad SINF length SQTY: %lu SINF-pkg-count: %u\n",
++ pcc->num_sifr, hkey->package.count);
+ status = AE_ERROR;
+ goto end;
+ }
+@@ -773,6 +774,24 @@ static DEVICE_ATTR_RW(dc_brightness);
+ static DEVICE_ATTR_RW(current_brightness);
+ static DEVICE_ATTR_RW(cdpower);
+
++static umode_t pcc_sysfs_is_visible(struct kobject *kobj, struct attribute *attr, int idx)
++{
++ struct device *dev = kobj_to_dev(kobj);
++ struct acpi_device *acpi = to_acpi_device(dev);
++ struct pcc_acpi *pcc = acpi_driver_data(acpi);
++
++ if (attr == &dev_attr_mute.attr)
++ return (pcc->num_sifr > SINF_MUTE) ? attr->mode : 0;
++
++ if (attr == &dev_attr_eco_mode.attr)
++ return (pcc->num_sifr > SINF_ECO_MODE) ? attr->mode : 0;
++
++ if (attr == &dev_attr_current_brightness.attr)
++ return (pcc->num_sifr > SINF_CUR_BRIGHT) ? attr->mode : 0;
++
++ return attr->mode;
++}
++
+ static struct attribute *pcc_sysfs_entries[] = {
+ &dev_attr_numbatt.attr,
+ &dev_attr_lcdtype.attr,
+@@ -787,8 +806,9 @@ static struct attribute *pcc_sysfs_entries[] = {
+ };
+
+ static const struct attribute_group pcc_attr_group = {
+- .name = NULL, /* put in device directory */
+- .attrs = pcc_sysfs_entries,
++ .name = NULL, /* put in device directory */
++ .attrs = pcc_sysfs_entries,
++ .is_visible = pcc_sysfs_is_visible,
+ };
+
+
+@@ -941,12 +961,15 @@ static int acpi_pcc_hotkey_resume(struct device *dev)
+ if (!pcc)
+ return -EINVAL;
+
+- acpi_pcc_write_sset(pcc, SINF_MUTE, pcc->mute);
+- acpi_pcc_write_sset(pcc, SINF_ECO_MODE, pcc->eco_mode);
++ if (pcc->num_sifr > SINF_MUTE)
++ acpi_pcc_write_sset(pcc, SINF_MUTE, pcc->mute);
++ if (pcc->num_sifr > SINF_ECO_MODE)
++ acpi_pcc_write_sset(pcc, SINF_ECO_MODE, pcc->eco_mode);
+ acpi_pcc_write_sset(pcc, SINF_STICKY_KEY, pcc->sticky_key);
+ acpi_pcc_write_sset(pcc, SINF_AC_CUR_BRIGHT, pcc->ac_brightness);
+ acpi_pcc_write_sset(pcc, SINF_DC_CUR_BRIGHT, pcc->dc_brightness);
+- acpi_pcc_write_sset(pcc, SINF_CUR_BRIGHT, pcc->current_brightness);
++ if (pcc->num_sifr > SINF_CUR_BRIGHT)
++ acpi_pcc_write_sset(pcc, SINF_CUR_BRIGHT, pcc->current_brightness);
+
+ return 0;
+ }
+@@ -963,11 +986,21 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device)
+
+ num_sifr = acpi_pcc_get_sqty(device);
+
+- if (num_sifr < 0 || num_sifr > 255) {
+- pr_err("num_sifr out of range");
++ /*
++ * pcc->sinf is expected to at least have the AC+DC brightness entries.
++ * Accesses to higher SINF entries are checked against num_sifr.
++ */
++ if (num_sifr <= SINF_DC_CUR_BRIGHT || num_sifr > 255) {
++ pr_err("num_sifr %d out of range %d - 255\n", num_sifr, SINF_DC_CUR_BRIGHT + 1);
+ return -ENODEV;
+ }
+
++ /*
++ * Some DSDT-s have an off-by-one bug where the SINF package count is
++ * one higher than the SQTY reported value, allocate 1 entry extra.
++ */
++ num_sifr++;
++
+ pcc = kzalloc(sizeof(struct pcc_acpi), GFP_KERNEL);
+ if (!pcc) {
+ pr_err("Couldn't allocate mem for pcc");
+@@ -1020,11 +1053,14 @@ static int acpi_pcc_hotkey_add(struct acpi_device *device)
+ acpi_pcc_write_sset(pcc, SINF_STICKY_KEY, 0);
+ pcc->sticky_key = 0;
+
+- pcc->eco_mode = pcc->sinf[SINF_ECO_MODE];
+- pcc->mute = pcc->sinf[SINF_MUTE];
+ pcc->ac_brightness = pcc->sinf[SINF_AC_CUR_BRIGHT];
+ pcc->dc_brightness = pcc->sinf[SINF_DC_CUR_BRIGHT];
+- pcc->current_brightness = pcc->sinf[SINF_CUR_BRIGHT];
++ if (pcc->num_sifr > SINF_MUTE)
++ pcc->mute = pcc->sinf[SINF_MUTE];
++ if (pcc->num_sifr > SINF_ECO_MODE)
++ pcc->eco_mode = pcc->sinf[SINF_ECO_MODE];
++ if (pcc->num_sifr > SINF_CUR_BRIGHT)
++ pcc->current_brightness = pcc->sinf[SINF_CUR_BRIGHT];
+
+ /* add sysfs attributes */
+ result = sysfs_create_group(&device->dev.kobj, &pcc_attr_group);
+diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
+index 00191b1d226014..4e9e7d2a942d8a 100644
+--- a/drivers/soundwire/stream.c
++++ b/drivers/soundwire/stream.c
+@@ -1286,18 +1286,18 @@ struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave,
+ unsigned int port_num)
+ {
+ struct sdw_dpn_prop *dpn_prop;
+- unsigned long mask;
++ u8 num_ports;
+ int i;
+
+ if (direction == SDW_DATA_DIR_TX) {
+- mask = slave->prop.source_ports;
++ num_ports = hweight32(slave->prop.source_ports);
+ dpn_prop = slave->prop.src_dpn_prop;
+ } else {
+- mask = slave->prop.sink_ports;
++ num_ports = hweight32(slave->prop.sink_ports);
+ dpn_prop = slave->prop.sink_dpn_prop;
+ }
+
+- for_each_set_bit(i, &mask, 32) {
++ for (i = 0; i < num_ports; i++) {
+ if (dpn_prop[i].num == port_num)
+ return &dpn_prop[i];
+ }
+diff --git a/drivers/spi/spi-geni-qcom.c b/drivers/spi/spi-geni-qcom.c
+index 37ef8c40b2762e..6f4057330444d5 100644
+--- a/drivers/spi/spi-geni-qcom.c
++++ b/drivers/spi/spi-geni-qcom.c
+@@ -1110,25 +1110,27 @@ static int spi_geni_probe(struct platform_device *pdev)
+ spin_lock_init(&mas->lock);
+ pm_runtime_use_autosuspend(&pdev->dev);
+ pm_runtime_set_autosuspend_delay(&pdev->dev, 250);
+- pm_runtime_enable(dev);
++ ret = devm_pm_runtime_enable(dev);
++ if (ret)
++ return ret;
+
+ if (device_property_read_bool(&pdev->dev, "spi-slave"))
+ spi->target = true;
+
+ ret = geni_icc_get(&mas->se, NULL);
+ if (ret)
+- goto spi_geni_probe_runtime_disable;
++ return ret;
+ /* Set the bus quota to a reasonable value for register access */
+ mas->se.icc_paths[GENI_TO_CORE].avg_bw = Bps_to_icc(CORE_2X_50_MHZ);
+ mas->se.icc_paths[CPU_TO_GENI].avg_bw = GENI_DEFAULT_BW;
+
+ ret = geni_icc_set_bw(&mas->se);
+ if (ret)
+- goto spi_geni_probe_runtime_disable;
++ return ret;
+
+ ret = spi_geni_init(mas);
+ if (ret)
+- goto spi_geni_probe_runtime_disable;
++ return ret;
+
+ /*
+ * check the mode supported and set_cs for fifo mode only
+@@ -1157,8 +1159,6 @@ static int spi_geni_probe(struct platform_device *pdev)
+ free_irq(mas->irq, spi);
+ spi_geni_release_dma:
+ spi_geni_release_dma_chan(mas);
+-spi_geni_probe_runtime_disable:
+- pm_runtime_disable(dev);
+ return ret;
+ }
+
+@@ -1170,10 +1170,9 @@ static void spi_geni_remove(struct platform_device *pdev)
+ /* Unregister _before_ disabling pm_runtime() so we stop transfers */
+ spi_unregister_controller(spi);
+
+- spi_geni_release_dma_chan(mas);
+-
+ free_irq(mas->irq, spi);
+- pm_runtime_disable(&pdev->dev);
++
++ spi_geni_release_dma_chan(mas);
+ }
+
+ static int __maybe_unused spi_geni_runtime_suspend(struct device *dev)
+diff --git a/drivers/spi/spi-nxp-fspi.c b/drivers/spi/spi-nxp-fspi.c
+index 88397f712a3b5e..6585b19a48662d 100644
+--- a/drivers/spi/spi-nxp-fspi.c
++++ b/drivers/spi/spi-nxp-fspi.c
+@@ -805,14 +805,15 @@ static void nxp_fspi_fill_txfifo(struct nxp_fspi *f,
+ if (i < op->data.nbytes) {
+ u32 data = 0;
+ int j;
++ int remaining = op->data.nbytes - i;
+ /* Wait for TXFIFO empty */
+ ret = fspi_readl_poll_tout(f, f->iobase + FSPI_INTR,
+ FSPI_INTR_IPTXWE, 0,
+ POLL_TOUT, true);
+ WARN_ON(ret);
+
+- for (j = 0; j < ALIGN(op->data.nbytes - i, 4); j += 4) {
+- memcpy(&data, buf + i + j, 4);
++ for (j = 0; j < ALIGN(remaining, 4); j += 4) {
++ memcpy(&data, buf + i + j, min_t(int, 4, remaining - j));
+ fspi_writel(f, data, base + FSPI_TFDR + j);
+ }
+ fspi_writel(f, FSPI_INTR_IPTXWE, base + FSPI_INTR);
+diff --git a/drivers/spi/spi-zynqmp-gqspi.c b/drivers/spi/spi-zynqmp-gqspi.c
+index 99524a3c9f382e..558c466135a51b 100644
+--- a/drivers/spi/spi-zynqmp-gqspi.c
++++ b/drivers/spi/spi-zynqmp-gqspi.c
+@@ -1033,6 +1033,18 @@ static int __maybe_unused zynqmp_runtime_resume(struct device *dev)
+ return 0;
+ }
+
++static unsigned long zynqmp_qspi_timeout(struct zynqmp_qspi *xqspi, u8 bits,
++ unsigned long bytes)
++{
++ unsigned long timeout;
++
++ /* Assume we are at most 2x slower than the nominal bus speed */
++ timeout = mult_frac(bytes, 2 * 8 * MSEC_PER_SEC,
++ bits * xqspi->speed_hz);
++ /* And add 100 ms for scheduling delays */
++ return msecs_to_jiffies(timeout + 100);
++}
++
+ /**
+ * zynqmp_qspi_exec_op() - Initiates the QSPI transfer
+ * @mem: The SPI memory
+@@ -1049,6 +1061,7 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
+ {
+ struct zynqmp_qspi *xqspi = spi_controller_get_devdata
+ (mem->spi->controller);
++ unsigned long timeout;
+ int err = 0, i;
+ u32 genfifoentry = 0;
+ u16 opcode = op->cmd.opcode;
+@@ -1077,8 +1090,10 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
+ zynqmp_gqspi_write(xqspi, GQSPI_IER_OFST,
+ GQSPI_IER_GENFIFOEMPTY_MASK |
+ GQSPI_IER_TXNOT_FULL_MASK);
+- if (!wait_for_completion_timeout
+- (&xqspi->data_completion, msecs_to_jiffies(1000))) {
++ timeout = zynqmp_qspi_timeout(xqspi, op->cmd.buswidth,
++ op->cmd.nbytes);
++ if (!wait_for_completion_timeout(&xqspi->data_completion,
++ timeout)) {
+ err = -ETIMEDOUT;
+ goto return_err;
+ }
+@@ -1104,8 +1119,10 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
+ GQSPI_IER_TXEMPTY_MASK |
+ GQSPI_IER_GENFIFOEMPTY_MASK |
+ GQSPI_IER_TXNOT_FULL_MASK);
+- if (!wait_for_completion_timeout
+- (&xqspi->data_completion, msecs_to_jiffies(1000))) {
++ timeout = zynqmp_qspi_timeout(xqspi, op->addr.buswidth,
++ op->addr.nbytes);
++ if (!wait_for_completion_timeout(&xqspi->data_completion,
++ timeout)) {
+ err = -ETIMEDOUT;
+ goto return_err;
+ }
+@@ -1173,8 +1190,9 @@ static int zynqmp_qspi_exec_op(struct spi_mem *mem,
+ GQSPI_IER_RXEMPTY_MASK);
+ }
+ }
+- if (!wait_for_completion_timeout
+- (&xqspi->data_completion, msecs_to_jiffies(1000)))
++ timeout = zynqmp_qspi_timeout(xqspi, op->data.buswidth,
++ op->data.nbytes);
++ if (!wait_for_completion_timeout(&xqspi->data_completion, timeout))
+ err = -ETIMEDOUT;
+ }
+
+diff --git a/drivers/staging/media/atomisp/pci/sh_css_frac.h b/drivers/staging/media/atomisp/pci/sh_css_frac.h
+index 8f08df5c88cc36..569a2f59e5519f 100644
+--- a/drivers/staging/media/atomisp/pci/sh_css_frac.h
++++ b/drivers/staging/media/atomisp/pci/sh_css_frac.h
+@@ -30,12 +30,24 @@
+ #define uISP_VAL_MAX ((unsigned int)((1 << uISP_REG_BIT) - 1))
+
+ /* a:fraction bits for 16bit precision, b:fraction bits for ISP precision */
+-#define sDIGIT_FITTING(v, a, b) \
+- min_t(int, max_t(int, (((v) >> sSHIFT) >> max(sFRACTION_BITS_FITTING(a) - (b), 0)), \
+- sISP_VAL_MIN), sISP_VAL_MAX)
+-#define uDIGIT_FITTING(v, a, b) \
+- min((unsigned int)max((unsigned)(((v) >> uSHIFT) \
+- >> max((int)(uFRACTION_BITS_FITTING(a) - (b)), 0)), \
+- uISP_VAL_MIN), uISP_VAL_MAX)
++static inline int sDIGIT_FITTING(int v, int a, int b)
++{
++ int fit_shift = sFRACTION_BITS_FITTING(a) - b;
++
++ v >>= sSHIFT;
++ v >>= fit_shift > 0 ? fit_shift : 0;
++
++ return clamp_t(int, v, sISP_VAL_MIN, sISP_VAL_MAX);
++}
++
++static inline unsigned int uDIGIT_FITTING(unsigned int v, int a, int b)
++{
++ int fit_shift = uFRACTION_BITS_FITTING(a) - b;
++
++ v >>= uSHIFT;
++ v >>= fit_shift > 0 ? fit_shift : 0;
++
++ return clamp_t(unsigned int, v, uISP_VAL_MIN, uISP_VAL_MAX);
++}
+
+ #endif /* __SH_CSS_FRAC_H */
+diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
+index 45e91d065b3bdb..8e00f21c7d139d 100644
+--- a/drivers/usb/typec/ucsi/ucsi.c
++++ b/drivers/usb/typec/ucsi/ucsi.c
+@@ -817,10 +817,11 @@ static int ucsi_check_altmodes(struct ucsi_connector *con)
+ /* Ignoring the errors in this case. */
+ if (con->partner_altmode[0]) {
+ num_partner_am = ucsi_get_num_altmode(con->partner_altmode);
+- if (num_partner_am > 0)
+- typec_partner_set_num_altmodes(con->partner, num_partner_am);
++ typec_partner_set_num_altmodes(con->partner, num_partner_am);
+ ucsi_altmode_update_active(con);
+ return 0;
++ } else {
++ typec_partner_set_num_altmodes(con->partner, 0);
+ }
+
+ return ret;
+@@ -914,10 +915,20 @@ static void ucsi_unregister_plug(struct ucsi_connector *con)
+
+ static int ucsi_register_cable(struct ucsi_connector *con)
+ {
++ struct ucsi_cable_property cable_prop;
+ struct typec_cable *cable;
+ struct typec_cable_desc desc = {};
++ u64 command;
++ int ret;
++
++ command = UCSI_GET_CABLE_PROPERTY | UCSI_CONNECTOR_NUMBER(con->num);
++ ret = ucsi_send_command(con->ucsi, command, &cable_prop, sizeof(cable_prop));
++ if (ret < 0) {
++ dev_err(con->ucsi->dev, "GET_CABLE_PROPERTY failed (%d)\n", ret);
++ return ret;
++ }
+
+- switch (UCSI_CABLE_PROP_FLAG_PLUG_TYPE(con->cable_prop.flags)) {
++ switch (UCSI_CABLE_PROP_FLAG_PLUG_TYPE(cable_prop.flags)) {
+ case UCSI_CABLE_PROPERTY_PLUG_TYPE_A:
+ desc.type = USB_PLUG_TYPE_A;
+ break;
+@@ -933,10 +944,10 @@ static int ucsi_register_cable(struct ucsi_connector *con)
+ }
+
+ desc.identity = &con->cable_identity;
+- desc.active = !!(UCSI_CABLE_PROP_FLAG_ACTIVE_CABLE &
+- con->cable_prop.flags);
+- desc.pd_revision = UCSI_CABLE_PROP_FLAG_PD_MAJOR_REV_AS_BCD(
+- con->cable_prop.flags);
++ desc.active = !!(UCSI_CABLE_PROP_FLAG_ACTIVE_CABLE & cable_prop.flags);
++
++ if (con->ucsi->version >= UCSI_VERSION_2_1)
++ desc.pd_revision = UCSI_CABLE_PROP_FLAG_PD_MAJOR_REV_AS_BCD(cable_prop.flags);
+
+ cable = typec_register_cable(con->port, &desc);
+ if (IS_ERR(cable)) {
+@@ -1142,21 +1153,11 @@ static int ucsi_check_connection(struct ucsi_connector *con)
+
+ static int ucsi_check_cable(struct ucsi_connector *con)
+ {
+- u64 command;
+- int ret;
++ int ret, num_plug_am;
+
+ if (con->cable)
+ return 0;
+
+- command = UCSI_GET_CABLE_PROPERTY | UCSI_CONNECTOR_NUMBER(con->num);
+- ret = ucsi_send_command(con->ucsi, command, &con->cable_prop,
+- sizeof(con->cable_prop));
+- if (ret < 0) {
+- dev_err(con->ucsi->dev, "GET_CABLE_PROPERTY failed (%d)\n",
+- ret);
+- return ret;
+- }
+-
+ ret = ucsi_register_cable(con);
+ if (ret < 0)
+ return ret;
+@@ -1175,6 +1176,13 @@ static int ucsi_check_cable(struct ucsi_connector *con)
+ ret = ucsi_register_altmodes(con, UCSI_RECIPIENT_SOP_P);
+ if (ret < 0)
+ return ret;
++
++ if (con->plug_altmode[0]) {
++ num_plug_am = ucsi_get_num_altmode(con->plug_altmode);
++ typec_plug_set_num_altmodes(con->plug, num_plug_am);
++ } else {
++ typec_plug_set_num_altmodes(con->plug, 0);
++ }
+ }
+
+ return 0;
+diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
+index f66224a270bc6a..46c37643b59cad 100644
+--- a/drivers/usb/typec/ucsi/ucsi.h
++++ b/drivers/usb/typec/ucsi/ucsi.h
+@@ -444,7 +444,6 @@ struct ucsi_connector {
+
+ struct ucsi_connector_status status;
+ struct ucsi_connector_capability cap;
+- struct ucsi_cable_property cable_prop;
+ struct power_supply *psy;
+ struct power_supply_desc psy_desc;
+ u32 rdo;
+diff --git a/fs/bcachefs/extents.c b/fs/bcachefs/extents.c
+index 410b8bd81b5a6e..7582e8ee6c21c7 100644
+--- a/fs/bcachefs/extents.c
++++ b/fs/bcachefs/extents.c
+@@ -932,8 +932,29 @@ bool bch2_extents_match(struct bkey_s_c k1, struct bkey_s_c k2)
+ bkey_for_each_ptr_decode(k2.k, ptrs2, p2, entry2)
+ if (p1.ptr.dev == p2.ptr.dev &&
+ p1.ptr.gen == p2.ptr.gen &&
++
++ /*
++ * This checks that the two pointers point
++ * to the same region on disk - adjusting
++ * for the difference in where the extents
++ * start, since one may have been trimmed:
++ */
+ (s64) p1.ptr.offset + p1.crc.offset - bkey_start_offset(k1.k) ==
+- (s64) p2.ptr.offset + p2.crc.offset - bkey_start_offset(k2.k))
++ (s64) p2.ptr.offset + p2.crc.offset - bkey_start_offset(k2.k) &&
++
++ /*
++ * This additionally checks that the
++ * extents overlap on disk, since the
++ * previous check may trigger spuriously
++ * when one extent is immediately partially
++ * overwritten with another extent (so that
++ * on disk they are adjacent) and
++ * compression is in use:
++ */
++ ((p1.ptr.offset >= p2.ptr.offset &&
++ p1.ptr.offset < p2.ptr.offset + p2.crc.compressed_size) ||
++ (p2.ptr.offset >= p1.ptr.offset &&
++ p2.ptr.offset < p1.ptr.offset + p1.crc.compressed_size)))
+ return true;
+
+ return false;
+diff --git a/fs/bcachefs/fs-io-buffered.c b/fs/bcachefs/fs-io-buffered.c
+index 54873ecc635cb0..98c1e26a313a67 100644
+--- a/fs/bcachefs/fs-io-buffered.c
++++ b/fs/bcachefs/fs-io-buffered.c
+@@ -802,8 +802,7 @@ static noinline void folios_trunc(folios *fs, struct folio **fi)
+ static int __bch2_buffered_write(struct bch_inode_info *inode,
+ struct address_space *mapping,
+ struct iov_iter *iter,
+- loff_t pos, unsigned len,
+- bool inode_locked)
++ loff_t pos, unsigned len)
+ {
+ struct bch_fs *c = inode->v.i_sb->s_fs_info;
+ struct bch2_folio_reservation res;
+@@ -828,15 +827,6 @@ static int __bch2_buffered_write(struct bch_inode_info *inode,
+
+ BUG_ON(!fs.nr);
+
+- /*
+- * If we're not using the inode lock, we need to lock all the folios for
+- * atomiticity of writes vs. other writes:
+- */
+- if (!inode_locked && folio_end_pos(darray_last(fs)) < end) {
+- ret = -BCH_ERR_need_inode_lock;
+- goto out;
+- }
+-
+ f = darray_first(fs);
+ if (pos != folio_pos(f) && !folio_test_uptodate(f)) {
+ ret = bch2_read_single_folio(f, mapping);
+@@ -931,10 +921,8 @@ static int __bch2_buffered_write(struct bch_inode_info *inode,
+ end = pos + copied;
+
+ spin_lock(&inode->v.i_lock);
+- if (end > inode->v.i_size) {
+- BUG_ON(!inode_locked);
++ if (end > inode->v.i_size)
+ i_size_write(&inode->v, end);
+- }
+ spin_unlock(&inode->v.i_lock);
+
+ f_pos = pos;
+@@ -978,68 +966,12 @@ static ssize_t bch2_buffered_write(struct kiocb *iocb, struct iov_iter *iter)
+ struct file *file = iocb->ki_filp;
+ struct address_space *mapping = file->f_mapping;
+ struct bch_inode_info *inode = file_bch_inode(file);
+- loff_t pos;
+- bool inode_locked = false;
+- ssize_t written = 0, written2 = 0, ret = 0;
+-
+- /*
+- * We don't take the inode lock unless i_size will be changing. Folio
+- * locks provide exclusion with other writes, and the pagecache add lock
+- * provides exclusion with truncate and hole punching.
+- *
+- * There is one nasty corner case where atomicity would be broken
+- * without great care: when copying data from userspace to the page
+- * cache, we do that with faults disable - a page fault would recurse
+- * back into the filesystem, taking filesystem locks again, and
+- * deadlock; so it's done with faults disabled, and we fault in the user
+- * buffer when we aren't holding locks.
+- *
+- * If we do part of the write, but we then race and in the userspace
+- * buffer have been evicted and are no longer resident, then we have to
+- * drop our folio locks to re-fault them in, breaking write atomicity.
+- *
+- * To fix this, we restart the write from the start, if we weren't
+- * holding the inode lock.
+- *
+- * There is another wrinkle after that; if we restart the write from the
+- * start, and then get an unrecoverable error, we _cannot_ claim to
+- * userspace that we did not write data we actually did - so we must
+- * track (written2) the most we ever wrote.
+- */
+-
+- if ((iocb->ki_flags & IOCB_APPEND) ||
+- (iocb->ki_pos + iov_iter_count(iter) > i_size_read(&inode->v))) {
+- inode_lock(&inode->v);
+- inode_locked = true;
+- }
+-
+- ret = generic_write_checks(iocb, iter);
+- if (ret <= 0)
+- goto unlock;
+-
+- ret = file_remove_privs_flags(file, !inode_locked ? IOCB_NOWAIT : 0);
+- if (ret) {
+- if (!inode_locked) {
+- inode_lock(&inode->v);
+- inode_locked = true;
+- ret = file_remove_privs_flags(file, 0);
+- }
+- if (ret)
+- goto unlock;
+- }
+-
+- ret = file_update_time(file);
+- if (ret)
+- goto unlock;
+-
+- pos = iocb->ki_pos;
++ loff_t pos = iocb->ki_pos;
++ ssize_t written = 0;
++ int ret = 0;
+
+ bch2_pagecache_add_get(inode);
+
+- if (!inode_locked &&
+- (iocb->ki_pos + iov_iter_count(iter) > i_size_read(&inode->v)))
+- goto get_inode_lock;
+-
+ do {
+ unsigned offset = pos & (PAGE_SIZE - 1);
+ unsigned bytes = iov_iter_count(iter);
+@@ -1064,17 +996,12 @@ static ssize_t bch2_buffered_write(struct kiocb *iocb, struct iov_iter *iter)
+ }
+ }
+
+- if (unlikely(bytes != iov_iter_count(iter) && !inode_locked))
+- goto get_inode_lock;
+-
+ if (unlikely(fatal_signal_pending(current))) {
+ ret = -EINTR;
+ break;
+ }
+
+- ret = __bch2_buffered_write(inode, mapping, iter, pos, bytes, inode_locked);
+- if (ret == -BCH_ERR_need_inode_lock)
+- goto get_inode_lock;
++ ret = __bch2_buffered_write(inode, mapping, iter, pos, bytes);
+ if (unlikely(ret < 0))
+ break;
+
+@@ -1095,46 +1022,50 @@ static ssize_t bch2_buffered_write(struct kiocb *iocb, struct iov_iter *iter)
+ }
+ pos += ret;
+ written += ret;
+- written2 = max(written, written2);
+-
+- if (ret != bytes && !inode_locked)
+- goto get_inode_lock;
+ ret = 0;
+
+ balance_dirty_pages_ratelimited(mapping);
+-
+- if (0) {
+-get_inode_lock:
+- bch2_pagecache_add_put(inode);
+- inode_lock(&inode->v);
+- inode_locked = true;
+- bch2_pagecache_add_get(inode);
+-
+- iov_iter_revert(iter, written);
+- pos -= written;
+- written = 0;
+- ret = 0;
+- }
+ } while (iov_iter_count(iter));
+- bch2_pagecache_add_put(inode);
+-unlock:
+- if (inode_locked)
+- inode_unlock(&inode->v);
+
+- iocb->ki_pos += written;
++ bch2_pagecache_add_put(inode);
+
+- ret = max(written, written2) ?: ret;
+- if (ret > 0)
+- ret = generic_write_sync(iocb, ret);
+- return ret;
++ return written ? written : ret;
+ }
+
+-ssize_t bch2_write_iter(struct kiocb *iocb, struct iov_iter *iter)
++ssize_t bch2_write_iter(struct kiocb *iocb, struct iov_iter *from)
+ {
+- ssize_t ret = iocb->ki_flags & IOCB_DIRECT
+- ? bch2_direct_write(iocb, iter)
+- : bch2_buffered_write(iocb, iter);
++ struct file *file = iocb->ki_filp;
++ struct bch_inode_info *inode = file_bch_inode(file);
++ ssize_t ret;
++
++ if (iocb->ki_flags & IOCB_DIRECT) {
++ ret = bch2_direct_write(iocb, from);
++ goto out;
++ }
++
++ inode_lock(&inode->v);
++
++ ret = generic_write_checks(iocb, from);
++ if (ret <= 0)
++ goto unlock;
++
++ ret = file_remove_privs(file);
++ if (ret)
++ goto unlock;
++
++ ret = file_update_time(file);
++ if (ret)
++ goto unlock;
++
++ ret = bch2_buffered_write(iocb, from);
++ if (likely(ret > 0))
++ iocb->ki_pos += ret;
++unlock:
++ inode_unlock(&inode->v);
+
++ if (ret > 0)
++ ret = generic_write_sync(iocb, ret);
++out:
+ return bch2_err_class(ret);
+ }
+
+diff --git a/fs/bcachefs/fs.c b/fs/bcachefs/fs.c
+index fa1fee05cf8f57..162f7836ca795c 100644
+--- a/fs/bcachefs/fs.c
++++ b/fs/bcachefs/fs.c
+@@ -177,6 +177,14 @@ static unsigned bch2_inode_hash(subvol_inum inum)
+ return jhash_3words(inum.subvol, inum.inum >> 32, inum.inum, JHASH_INITVAL);
+ }
+
++struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum)
++{
++ return to_bch_ei(ilookup5_nowait(c->vfs_sb,
++ bch2_inode_hash(inum),
++ bch2_iget5_test,
++ &inum));
++}
++
+ static struct bch_inode_info *bch2_inode_insert(struct bch_fs *c, struct bch_inode_info *inode)
+ {
+ subvol_inum inum = inode_inum(inode);
+diff --git a/fs/bcachefs/fs.h b/fs/bcachefs/fs.h
+index c3af7225ff693e..990ec43e0365d3 100644
+--- a/fs/bcachefs/fs.h
++++ b/fs/bcachefs/fs.h
+@@ -56,6 +56,8 @@ static inline subvol_inum inode_inum(struct bch_inode_info *inode)
+ };
+ }
+
++struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *, subvol_inum);
++
+ /*
+ * Set if we've gotten a btree error for this inode, and thus the vfs inode and
+ * btree inode may be inconsistent:
+@@ -194,6 +196,11 @@ int bch2_vfs_init(void);
+
+ #define bch2_inode_update_after_write(_trans, _inode, _inode_u, _fields) ({ do {} while (0); })
+
++static inline struct bch_inode_info *__bch2_inode_hash_find(struct bch_fs *c, subvol_inum inum)
++{
++ return NULL;
++}
++
+ static inline void bch2_evict_subvolume_inodes(struct bch_fs *c,
+ snapshot_id_list *s) {}
+ static inline void bch2_vfs_exit(void) {}
+diff --git a/fs/bcachefs/fsck.c b/fs/bcachefs/fsck.c
+index 921bcdb3e5e4ed..08d0eb39e7d65d 100644
+--- a/fs/bcachefs/fsck.c
++++ b/fs/bcachefs/fsck.c
+@@ -8,6 +8,7 @@
+ #include "darray.h"
+ #include "dirent.h"
+ #include "error.h"
++#include "fs.h"
+ #include "fs-common.h"
+ #include "fsck.h"
+ #include "inode.h"
+@@ -948,6 +949,22 @@ static int check_inode_dirent_inode(struct btree_trans *trans, struct bkey_s_c i
+ return ret;
+ }
+
++static bool bch2_inode_open(struct bch_fs *c, struct bpos p)
++{
++ subvol_inum inum = {
++ .subvol = snapshot_t(c, p.snapshot)->subvol,
++ .inum = p.offset,
++ };
++
++ /* snapshot tree corruption, can't safely delete */
++ if (!inum.subvol) {
++ bch_err_ratelimited(c, "%s(): snapshot %u has no subvol", __func__, p.snapshot);
++ return true;
++ }
++
++ return __bch2_inode_hash_find(c, inum) != NULL;
++}
++
+ static int check_inode(struct btree_trans *trans,
+ struct btree_iter *iter,
+ struct bkey_s_c k,
+@@ -1025,6 +1042,7 @@ static int check_inode(struct btree_trans *trans,
+ }
+
+ if (u.bi_flags & BCH_INODE_unlinked &&
++ !bch2_inode_open(c, k.k->p) &&
+ (!c->sb.clean ||
+ fsck_err(c, inode_unlinked_but_clean,
+ "filesystem marked clean, but inode %llu unlinked",
+diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
+index 2951aa0039fc67..5d23421b62437e 100644
+--- a/fs/btrfs/inode.c
++++ b/fs/btrfs/inode.c
+@@ -4213,6 +4213,7 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
+
+ btrfs_i_size_write(dir, dir->vfs_inode.i_size - name->len * 2);
+ inode_inc_iversion(&inode->vfs_inode);
++ inode_set_ctime_current(&inode->vfs_inode);
+ inode_inc_iversion(&dir->vfs_inode);
+ inode_set_mtime_to_ts(&dir->vfs_inode, inode_set_ctime_current(&dir->vfs_inode));
+ ret = btrfs_update_inode(trans, dir);
+diff --git a/fs/nfs/delegation.c b/fs/nfs/delegation.c
+index 6bace5fece04e2..ed362d291b902f 100644
+--- a/fs/nfs/delegation.c
++++ b/fs/nfs/delegation.c
+@@ -624,6 +624,9 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
+ prev = delegation;
+ continue;
+ }
++ inode = nfs_delegation_grab_inode(delegation);
++ if (inode == NULL)
++ continue;
+
+ if (prev) {
+ struct inode *tmp = nfs_delegation_grab_inode(prev);
+@@ -634,12 +637,6 @@ static int nfs_server_return_marked_delegations(struct nfs_server *server,
+ }
+ }
+
+- inode = nfs_delegation_grab_inode(delegation);
+- if (inode == NULL) {
+- rcu_read_unlock();
+- iput(to_put);
+- goto restart;
+- }
+ delegation = nfs_start_delegation_return_locked(NFS_I(inode));
+ rcu_read_unlock();
+
+@@ -1161,7 +1158,6 @@ static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server,
+ struct inode *inode;
+ restart:
+ rcu_read_lock();
+-restart_locked:
+ list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
+ if (test_bit(NFS_DELEGATION_INODE_FREEING,
+ &delegation->flags) ||
+@@ -1172,7 +1168,7 @@ static int nfs_server_reap_unclaimed_delegations(struct nfs_server *server,
+ continue;
+ inode = nfs_delegation_grab_inode(delegation);
+ if (inode == NULL)
+- goto restart_locked;
++ continue;
+ delegation = nfs_start_delegation_return_locked(NFS_I(inode));
+ rcu_read_unlock();
+ if (delegation != NULL) {
+@@ -1295,7 +1291,6 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
+
+ restart:
+ rcu_read_lock();
+-restart_locked:
+ list_for_each_entry_rcu(delegation, &server->delegations, super_list) {
+ if (test_bit(NFS_DELEGATION_INODE_FREEING,
+ &delegation->flags) ||
+@@ -1307,7 +1302,7 @@ static int nfs_server_reap_expired_delegations(struct nfs_server *server,
+ continue;
+ inode = nfs_delegation_grab_inode(delegation);
+ if (inode == NULL)
+- goto restart_locked;
++ continue;
+ spin_lock(&delegation->lock);
+ cred = get_cred_rcu(delegation->cred);
+ nfs4_stateid_copy(&stateid, &delegation->stateid);
+diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
+index bff9d6600741e2..3b76e89b6d028f 100644
+--- a/fs/nfs/nfs4proc.c
++++ b/fs/nfs/nfs4proc.c
+@@ -9873,13 +9873,16 @@ static void nfs4_layoutreturn_done(struct rpc_task *task, void *calldata)
+ fallthrough;
+ default:
+ task->tk_status = 0;
++ lrp->res.lrs_present = 0;
+ fallthrough;
+ case 0:
+ break;
+ case -NFS4ERR_DELAY:
+- if (nfs4_async_handle_error(task, server, NULL, NULL) != -EAGAIN)
+- break;
+- goto out_restart;
++ if (nfs4_async_handle_error(task, server, NULL, NULL) ==
++ -EAGAIN)
++ goto out_restart;
++ lrp->res.lrs_present = 0;
++ break;
+ }
+ return;
+ out_restart:
+diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
+index b5834728f31b32..d1e3c17dcceb0d 100644
+--- a/fs/nfs/pnfs.c
++++ b/fs/nfs/pnfs.c
+@@ -1172,10 +1172,9 @@ void pnfs_layoutreturn_free_lsegs(struct pnfs_layout_hdr *lo,
+ LIST_HEAD(freeme);
+
+ spin_lock(&inode->i_lock);
+- if (!pnfs_layout_is_valid(lo) ||
+- !nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
++ if (!nfs4_stateid_match_other(&lo->plh_stateid, arg_stateid))
+ goto out_unlock;
+- if (stateid) {
++ if (stateid && pnfs_layout_is_valid(lo)) {
+ u32 seq = be32_to_cpu(arg_stateid->seqid);
+
+ pnfs_mark_matching_lsegs_invalid(lo, &freeme, range, seq);
+diff --git a/fs/smb/client/cifsencrypt.c b/fs/smb/client/cifsencrypt.c
+index 6322f0f68a176b..b0473c2567fe68 100644
+--- a/fs/smb/client/cifsencrypt.c
++++ b/fs/smb/client/cifsencrypt.c
+@@ -129,7 +129,7 @@ static ssize_t cifs_shash_xarray(const struct iov_iter *iter, ssize_t maxsize,
+ for (j = foffset / PAGE_SIZE; j < npages; j++) {
+ len = min_t(size_t, maxsize, PAGE_SIZE - offset);
+ p = kmap_local_page(folio_page(folio, j));
+- ret = crypto_shash_update(shash, p, len);
++ ret = crypto_shash_update(shash, p + offset, len);
+ kunmap_local(p);
+ if (ret < 0)
+ return ret;
+diff --git a/fs/smb/server/mgmt/share_config.c b/fs/smb/server/mgmt/share_config.c
+index e0a6b758094fc5..d8d03070ae44b4 100644
+--- a/fs/smb/server/mgmt/share_config.c
++++ b/fs/smb/server/mgmt/share_config.c
+@@ -15,6 +15,7 @@
+ #include "share_config.h"
+ #include "user_config.h"
+ #include "user_session.h"
++#include "../connection.h"
+ #include "../transport_ipc.h"
+ #include "../misc.h"
+
+@@ -120,12 +121,13 @@ static int parse_veto_list(struct ksmbd_share_config *share,
+ return 0;
+ }
+
+-static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
++static struct ksmbd_share_config *share_config_request(struct ksmbd_work *work,
+ const char *name)
+ {
+ struct ksmbd_share_config_response *resp;
+ struct ksmbd_share_config *share = NULL;
+ struct ksmbd_share_config *lookup;
++ struct unicode_map *um = work->conn->um;
+ int ret;
+
+ resp = ksmbd_ipc_share_config_request(name);
+@@ -181,7 +183,14 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
+ KSMBD_SHARE_CONFIG_VETO_LIST(resp),
+ resp->veto_list_sz);
+ if (!ret && share->path) {
++ if (__ksmbd_override_fsids(work, share)) {
++ kill_share(share);
++ share = NULL;
++ goto out;
++ }
++
+ ret = kern_path(share->path, 0, &share->vfs_path);
++ ksmbd_revert_fsids(work);
+ if (ret) {
+ ksmbd_debug(SMB, "failed to access '%s'\n",
+ share->path);
+@@ -214,7 +223,7 @@ static struct ksmbd_share_config *share_config_request(struct unicode_map *um,
+ return share;
+ }
+
+-struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
++struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work,
+ const char *name)
+ {
+ struct ksmbd_share_config *share;
+@@ -227,7 +236,7 @@ struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
+
+ if (share)
+ return share;
+- return share_config_request(um, name);
++ return share_config_request(work, name);
+ }
+
+ bool ksmbd_share_veto_filename(struct ksmbd_share_config *share,
+diff --git a/fs/smb/server/mgmt/share_config.h b/fs/smb/server/mgmt/share_config.h
+index 5f591751b92365..d4ac2dd4de2040 100644
+--- a/fs/smb/server/mgmt/share_config.h
++++ b/fs/smb/server/mgmt/share_config.h
+@@ -11,6 +11,8 @@
+ #include <linux/path.h>
+ #include <linux/unicode.h>
+
++struct ksmbd_work;
++
+ struct ksmbd_share_config {
+ char *name;
+ char *path;
+@@ -68,7 +70,7 @@ static inline void ksmbd_share_config_put(struct ksmbd_share_config *share)
+ __ksmbd_share_config_put(share);
+ }
+
+-struct ksmbd_share_config *ksmbd_share_config_get(struct unicode_map *um,
++struct ksmbd_share_config *ksmbd_share_config_get(struct ksmbd_work *work,
+ const char *name);
+ bool ksmbd_share_veto_filename(struct ksmbd_share_config *share,
+ const char *filename);
+diff --git a/fs/smb/server/mgmt/tree_connect.c b/fs/smb/server/mgmt/tree_connect.c
+index d2c81a8a11dda1..94a52a75014a43 100644
+--- a/fs/smb/server/mgmt/tree_connect.c
++++ b/fs/smb/server/mgmt/tree_connect.c
+@@ -16,17 +16,18 @@
+ #include "user_session.h"
+
+ struct ksmbd_tree_conn_status
+-ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
+- const char *share_name)
++ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name)
+ {
+ struct ksmbd_tree_conn_status status = {-ENOENT, NULL};
+ struct ksmbd_tree_connect_response *resp = NULL;
+ struct ksmbd_share_config *sc;
+ struct ksmbd_tree_connect *tree_conn = NULL;
+ struct sockaddr *peer_addr;
++ struct ksmbd_conn *conn = work->conn;
++ struct ksmbd_session *sess = work->sess;
+ int ret;
+
+- sc = ksmbd_share_config_get(conn->um, share_name);
++ sc = ksmbd_share_config_get(work, share_name);
+ if (!sc)
+ return status;
+
+@@ -61,7 +62,7 @@ ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
+ struct ksmbd_share_config *new_sc;
+
+ ksmbd_share_config_del(sc);
+- new_sc = ksmbd_share_config_get(conn->um, share_name);
++ new_sc = ksmbd_share_config_get(work, share_name);
+ if (!new_sc) {
+ pr_err("Failed to update stale share config\n");
+ status.ret = -ESTALE;
+diff --git a/fs/smb/server/mgmt/tree_connect.h b/fs/smb/server/mgmt/tree_connect.h
+index 6377a70b811c89..a42cdd05104114 100644
+--- a/fs/smb/server/mgmt/tree_connect.h
++++ b/fs/smb/server/mgmt/tree_connect.h
+@@ -13,6 +13,7 @@
+ struct ksmbd_share_config;
+ struct ksmbd_user;
+ struct ksmbd_conn;
++struct ksmbd_work;
+
+ enum {
+ TREE_NEW = 0,
+@@ -50,8 +51,7 @@ static inline int test_tree_conn_flag(struct ksmbd_tree_connect *tree_conn,
+ struct ksmbd_session;
+
+ struct ksmbd_tree_conn_status
+-ksmbd_tree_conn_connect(struct ksmbd_conn *conn, struct ksmbd_session *sess,
+- const char *share_name);
++ksmbd_tree_conn_connect(struct ksmbd_work *work, const char *share_name);
+ void ksmbd_tree_connect_put(struct ksmbd_tree_connect *tcon);
+
+ int ksmbd_tree_conn_disconnect(struct ksmbd_session *sess,
+diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
+index 39dfecf082ba08..adfd6046275a56 100644
+--- a/fs/smb/server/smb2pdu.c
++++ b/fs/smb/server/smb2pdu.c
+@@ -1959,7 +1959,7 @@ int smb2_tree_connect(struct ksmbd_work *work)
+ ksmbd_debug(SMB, "tree connect request for tree %s treename %s\n",
+ name, treename);
+
+- status = ksmbd_tree_conn_connect(conn, sess, name);
++ status = ksmbd_tree_conn_connect(work, name);
+ if (status.ret == KSMBD_TREE_CONN_STATUS_OK)
+ rsp->hdr.Id.SyncId.TreeId = cpu_to_le32(status.tree_conn->id);
+ else
+@@ -3714,7 +3714,7 @@ int smb2_open(struct ksmbd_work *work)
+ kfree(name);
+ kfree(lc);
+
+- return 0;
++ return rc;
+ }
+
+ static int readdir_info_level_struct_sz(int info_level)
+@@ -5601,6 +5601,11 @@ int smb2_query_info(struct ksmbd_work *work)
+
+ ksmbd_debug(SMB, "GOT query info request\n");
+
++ if (ksmbd_override_fsids(work)) {
++ rc = -ENOMEM;
++ goto err_out;
++ }
++
+ switch (req->InfoType) {
+ case SMB2_O_INFO_FILE:
+ ksmbd_debug(SMB, "GOT SMB2_O_INFO_FILE\n");
+@@ -5619,6 +5624,7 @@ int smb2_query_info(struct ksmbd_work *work)
+ req->InfoType);
+ rc = -EOPNOTSUPP;
+ }
++ ksmbd_revert_fsids(work);
+
+ if (!rc) {
+ rsp->StructureSize = cpu_to_le16(9);
+@@ -5628,6 +5634,7 @@ int smb2_query_info(struct ksmbd_work *work)
+ le32_to_cpu(rsp->OutputBufferLength));
+ }
+
++err_out:
+ if (rc < 0) {
+ if (rc == -EACCES)
+ rsp->hdr.Status = STATUS_ACCESS_DENIED;
+diff --git a/fs/smb/server/smb_common.c b/fs/smb/server/smb_common.c
+index 474dadf6b7b8bc..13818ecb6e1b2f 100644
+--- a/fs/smb/server/smb_common.c
++++ b/fs/smb/server/smb_common.c
+@@ -732,10 +732,10 @@ bool is_asterisk(char *p)
+ return p && p[0] == '*';
+ }
+
+-int ksmbd_override_fsids(struct ksmbd_work *work)
++int __ksmbd_override_fsids(struct ksmbd_work *work,
++ struct ksmbd_share_config *share)
+ {
+ struct ksmbd_session *sess = work->sess;
+- struct ksmbd_share_config *share = work->tcon->share_conf;
+ struct cred *cred;
+ struct group_info *gi;
+ unsigned int uid;
+@@ -775,6 +775,11 @@ int ksmbd_override_fsids(struct ksmbd_work *work)
+ return 0;
+ }
+
++int ksmbd_override_fsids(struct ksmbd_work *work)
++{
++ return __ksmbd_override_fsids(work, work->tcon->share_conf);
++}
++
+ void ksmbd_revert_fsids(struct ksmbd_work *work)
+ {
+ const struct cred *cred;
+diff --git a/fs/smb/server/smb_common.h b/fs/smb/server/smb_common.h
+index f1092519c0c288..4a3148b0167f54 100644
+--- a/fs/smb/server/smb_common.h
++++ b/fs/smb/server/smb_common.h
+@@ -447,6 +447,8 @@ int ksmbd_extract_shortname(struct ksmbd_conn *conn,
+ int ksmbd_smb_negotiate_common(struct ksmbd_work *work, unsigned int command);
+
+ int ksmbd_smb_check_shared_mode(struct file *filp, struct ksmbd_file *curr_fp);
++int __ksmbd_override_fsids(struct ksmbd_work *work,
++ struct ksmbd_share_config *share);
+ int ksmbd_override_fsids(struct ksmbd_work *work);
+ void ksmbd_revert_fsids(struct ksmbd_work *work);
+
+diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h
+index d45bfb7cf81d0f..6ffafd596d39d3 100644
+--- a/include/linux/mlx5/mlx5_ifc.h
++++ b/include/linux/mlx5/mlx5_ifc.h
+@@ -1027,7 +1027,8 @@ struct mlx5_ifc_qos_cap_bits {
+
+ u8 max_tsar_bw_share[0x20];
+
+- u8 reserved_at_100[0x20];
++ u8 nic_element_type[0x10];
++ u8 nic_tsar_type[0x10];
+
+ u8 reserved_at_120[0x3];
+ u8 log_meter_aso_granularity[0x5];
+@@ -3912,10 +3913,11 @@ enum {
+ };
+
+ enum {
+- ELEMENT_TYPE_CAP_MASK_TASR = 1 << 0,
++ ELEMENT_TYPE_CAP_MASK_TSAR = 1 << 0,
+ ELEMENT_TYPE_CAP_MASK_VPORT = 1 << 1,
+ ELEMENT_TYPE_CAP_MASK_VPORT_TC = 1 << 2,
+ ELEMENT_TYPE_CAP_MASK_PARA_VPORT_TC = 1 << 3,
++ ELEMENT_TYPE_CAP_MASK_QUEUE_GROUP = 1 << 4,
+ };
+
+ struct mlx5_ifc_scheduling_context_bits {
+@@ -4623,6 +4625,12 @@ enum {
+ TSAR_ELEMENT_TSAR_TYPE_ETS = 0x2,
+ };
+
++enum {
++ TSAR_TYPE_CAP_MASK_DWRR = 1 << 0,
++ TSAR_TYPE_CAP_MASK_ROUND_ROBIN = 1 << 1,
++ TSAR_TYPE_CAP_MASK_ETS = 1 << 2,
++};
++
+ struct mlx5_ifc_tsar_element_bits {
+ u8 reserved_at_0[0x8];
+ u8 tsar_type[0x8];
+diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
+index 6c395a2600e8d1..276ca543ef44d8 100644
+--- a/include/linux/virtio_net.h
++++ b/include/linux/virtio_net.h
+@@ -173,7 +173,8 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+ break;
+ case SKB_GSO_TCPV4:
+ case SKB_GSO_TCPV6:
+- if (skb->csum_offset != offsetof(struct tcphdr, check))
++ if (skb->ip_summed == CHECKSUM_PARTIAL &&
++ skb->csum_offset != offsetof(struct tcphdr, check))
+ return -EINVAL;
+ break;
+ }
+diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
+index e8f24483e05f04..c03a2bc106d4bc 100644
+--- a/kernel/cgroup/cpuset.c
++++ b/kernel/cgroup/cpuset.c
+@@ -223,6 +223,13 @@ static cpumask_var_t isolated_cpus;
+ /* List of remote partition root children */
+ static struct list_head remote_children;
+
++/*
++ * A flag to force sched domain rebuild at the end of an operation while
++ * inhibiting it in the intermediate stages when set. Currently it is only
++ * set in hotplug code.
++ */
++static bool force_sd_rebuild;
++
+ /*
+ * Partition root states:
+ *
+@@ -1442,7 +1449,7 @@ static void update_partition_sd_lb(struct cpuset *cs, int old_prs)
+ clear_bit(CS_SCHED_LOAD_BALANCE, &cs->flags);
+ }
+
+- if (rebuild_domains)
++ if (rebuild_domains && !force_sd_rebuild)
+ rebuild_sched_domains_locked();
+ }
+
+@@ -1805,7 +1812,7 @@ static void remote_partition_check(struct cpuset *cs, struct cpumask *newmask,
+ remote_partition_disable(child, tmp);
+ disable_cnt++;
+ }
+- if (disable_cnt)
++ if (disable_cnt && !force_sd_rebuild)
+ rebuild_sched_domains_locked();
+ }
+
+@@ -2415,7 +2422,8 @@ static void update_cpumasks_hier(struct cpuset *cs, struct tmpmasks *tmp,
+ }
+ rcu_read_unlock();
+
+- if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD))
++ if (need_rebuild_sched_domains && !(flags & HIER_NO_SD_REBUILD) &&
++ !force_sd_rebuild)
+ rebuild_sched_domains_locked();
+ }
+
+@@ -3077,7 +3085,8 @@ static int update_flag(cpuset_flagbits_t bit, struct cpuset *cs,
+ cs->flags = trialcs->flags;
+ spin_unlock_irq(&callback_lock);
+
+- if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed)
++ if (!cpumask_empty(trialcs->cpus_allowed) && balance_flag_changed &&
++ !force_sd_rebuild)
+ rebuild_sched_domains_locked();
+
+ if (spread_flag_changed)
+@@ -4478,11 +4487,9 @@ hotplug_update_tasks(struct cpuset *cs,
+ update_tasks_nodemask(cs);
+ }
+
+-static bool force_rebuild;
+-
+ void cpuset_force_rebuild(void)
+ {
+- force_rebuild = true;
++ force_sd_rebuild = true;
+ }
+
+ /**
+@@ -4630,15 +4637,9 @@ static void cpuset_handle_hotplug(void)
+ !cpumask_empty(subpartitions_cpus);
+ mems_updated = !nodes_equal(top_cpuset.effective_mems, new_mems);
+
+- /*
+- * In the rare case that hotplug removes all the cpus in
+- * subpartitions_cpus, we assumed that cpus are updated.
+- */
+- if (!cpus_updated && !cpumask_empty(subpartitions_cpus))
+- cpus_updated = true;
+-
+ /* For v1, synchronize cpus_allowed to cpu_active_mask */
+ if (cpus_updated) {
++ cpuset_force_rebuild();
+ spin_lock_irq(&callback_lock);
+ if (!on_dfl)
+ cpumask_copy(top_cpuset.cpus_allowed, &new_cpus);
+@@ -4694,8 +4695,8 @@ static void cpuset_handle_hotplug(void)
+ }
+
+ /* rebuild sched domains if cpus_allowed has changed */
+- if (cpus_updated || force_rebuild) {
+- force_rebuild = false;
++ if (force_sd_rebuild) {
++ force_sd_rebuild = false;
+ rebuild_sched_domains_cpuslocked();
+ }
+
+diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
+index 0d88922f8763c9..4481f8913dcc35 100644
+--- a/kernel/trace/trace_kprobe.c
++++ b/kernel/trace/trace_kprobe.c
+@@ -794,6 +794,24 @@ static int validate_module_probe_symbol(const char *modname, const char *symbol)
+ return 0;
+ }
+
++#ifdef CONFIG_MODULES
++/* Return NULL if the module is not loaded or under unloading. */
++static struct module *try_module_get_by_name(const char *name)
++{
++ struct module *mod;
++
++ rcu_read_lock_sched();
++ mod = find_module(name);
++ if (mod && !try_module_get(mod))
++ mod = NULL;
++ rcu_read_unlock_sched();
++
++ return mod;
++}
++#else
++#define try_module_get_by_name(name) (NULL)
++#endif
++
+ static int validate_probe_symbol(char *symbol)
+ {
+ struct module *mod = NULL;
+@@ -805,12 +823,7 @@ static int validate_probe_symbol(char *symbol)
+ modname = symbol;
+ symbol = p + 1;
+ *p = '\0';
+- /* Return 0 (defer) if the module does not exist yet. */
+- rcu_read_lock_sched();
+- mod = find_module(modname);
+- if (mod && !try_module_get(mod))
+- mod = NULL;
+- rcu_read_unlock_sched();
++ mod = try_module_get_by_name(modname);
+ if (!mod)
+ goto out;
+ }
+diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
+index 5b06f67879f5fa..461b4ab60b501a 100644
+--- a/kernel/trace/trace_osnoise.c
++++ b/kernel/trace/trace_osnoise.c
+@@ -228,6 +228,11 @@ static inline struct osnoise_variables *this_cpu_osn_var(void)
+ return this_cpu_ptr(&per_cpu_osnoise_var);
+ }
+
++/*
++ * Protect the interface.
++ */
++static struct mutex interface_lock;
++
+ #ifdef CONFIG_TIMERLAT_TRACER
+ /*
+ * Runtime information for the timer mode.
+@@ -252,11 +257,6 @@ static inline struct timerlat_variables *this_cpu_tmr_var(void)
+ return this_cpu_ptr(&per_cpu_timerlat_var);
+ }
+
+-/*
+- * Protect the interface.
+- */
+-static struct mutex interface_lock;
+-
+ /*
+ * tlat_var_reset - Reset the values of the given timerlat_variables
+ */
+diff --git a/mm/memory.c b/mm/memory.c
+index 72d00a38585d02..7a898b85788dd9 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -2581,11 +2581,7 @@ static inline int remap_p4d_range(struct mm_struct *mm, pgd_t *pgd,
+ return 0;
+ }
+
+-/*
+- * Variant of remap_pfn_range that does not call track_pfn_remap. The caller
+- * must have pre-validated the caching bits of the pgprot_t.
+- */
+-int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
++static int remap_pfn_range_internal(struct vm_area_struct *vma, unsigned long addr,
+ unsigned long pfn, unsigned long size, pgprot_t prot)
+ {
+ pgd_t *pgd;
+@@ -2638,6 +2634,27 @@ int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
+ return 0;
+ }
+
++/*
++ * Variant of remap_pfn_range that does not call track_pfn_remap. The caller
++ * must have pre-validated the caching bits of the pgprot_t.
++ */
++int remap_pfn_range_notrack(struct vm_area_struct *vma, unsigned long addr,
++ unsigned long pfn, unsigned long size, pgprot_t prot)
++{
++ int error = remap_pfn_range_internal(vma, addr, pfn, size, prot);
++
++ if (!error)
++ return 0;
++
++ /*
++ * A partial pfn range mapping is dangerous: it does not
++ * maintain page reference counts, and callers may free
++ * pages due to the error. So zap it early.
++ */
++ zap_page_range_single(vma, addr, size, NULL);
++ return error;
++}
++
+ /**
+ * remap_pfn_range - remap kernel memory to userspace
+ * @vma: user vma to map to
+diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c
+index e6904288d40dca..b3191968e53af3 100644
+--- a/net/hsr/hsr_device.c
++++ b/net/hsr/hsr_device.c
+@@ -73,9 +73,15 @@ static void hsr_check_announce(struct net_device *hsr_dev)
+ mod_timer(&hsr->announce_timer, jiffies +
+ msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL));
+ }
++
++ if (hsr->redbox && !timer_pending(&hsr->announce_proxy_timer))
++ mod_timer(&hsr->announce_proxy_timer, jiffies +
++ msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL) / 2);
+ } else {
+ /* Deactivate the announce timer */
+ timer_delete(&hsr->announce_timer);
++ if (hsr->redbox)
++ timer_delete(&hsr->announce_proxy_timer);
+ }
+ }
+
+@@ -279,10 +285,11 @@ static struct sk_buff *hsr_init_skb(struct hsr_port *master)
+ return NULL;
+ }
+
+-static void send_hsr_supervision_frame(struct hsr_port *master,
+- unsigned long *interval)
++static void send_hsr_supervision_frame(struct hsr_port *port,
++ unsigned long *interval,
++ const unsigned char *addr)
+ {
+- struct hsr_priv *hsr = master->hsr;
++ struct hsr_priv *hsr = port->hsr;
+ __u8 type = HSR_TLV_LIFE_CHECK;
+ struct hsr_sup_payload *hsr_sp;
+ struct hsr_sup_tlv *hsr_stlv;
+@@ -296,9 +303,9 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
+ hsr->announce_count++;
+ }
+
+- skb = hsr_init_skb(master);
++ skb = hsr_init_skb(port);
+ if (!skb) {
+- netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n");
++ netdev_warn_once(port->dev, "HSR: Could not send supervision frame\n");
+ return;
+ }
+
+@@ -321,11 +328,12 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
+ hsr_stag->tlv.HSR_TLV_length = hsr->prot_version ?
+ sizeof(struct hsr_sup_payload) : 12;
+
+- /* Payload: MacAddressA */
++ /* Payload: MacAddressA / SAN MAC from ProxyNodeTable */
+ hsr_sp = skb_put(skb, sizeof(struct hsr_sup_payload));
+- ether_addr_copy(hsr_sp->macaddress_A, master->dev->dev_addr);
++ ether_addr_copy(hsr_sp->macaddress_A, addr);
+
+- if (hsr->redbox) {
++ if (hsr->redbox &&
++ hsr_is_node_in_db(&hsr->proxy_node_db, addr)) {
+ hsr_stlv = skb_put(skb, sizeof(struct hsr_sup_tlv));
+ hsr_stlv->HSR_TLV_type = PRP_TLV_REDBOX_MAC;
+ hsr_stlv->HSR_TLV_length = sizeof(struct hsr_sup_payload);
+@@ -340,13 +348,14 @@ static void send_hsr_supervision_frame(struct hsr_port *master,
+ return;
+ }
+
+- hsr_forward_skb(skb, master);
++ hsr_forward_skb(skb, port);
+ spin_unlock_bh(&hsr->seqnr_lock);
+ return;
+ }
+
+ static void send_prp_supervision_frame(struct hsr_port *master,
+- unsigned long *interval)
++ unsigned long *interval,
++ const unsigned char *addr)
+ {
+ struct hsr_priv *hsr = master->hsr;
+ struct hsr_sup_payload *hsr_sp;
+@@ -396,7 +405,7 @@ static void hsr_announce(struct timer_list *t)
+
+ rcu_read_lock();
+ master = hsr_port_get_hsr(hsr, HSR_PT_MASTER);
+- hsr->proto_ops->send_sv_frame(master, &interval);
++ hsr->proto_ops->send_sv_frame(master, &interval, master->dev->dev_addr);
+
+ if (is_admin_up(master->dev))
+ mod_timer(&hsr->announce_timer, jiffies + interval);
+@@ -404,6 +413,41 @@ static void hsr_announce(struct timer_list *t)
+ rcu_read_unlock();
+ }
+
++/* Announce (supervision frame) timer function for RedBox
++ */
++static void hsr_proxy_announce(struct timer_list *t)
++{
++ struct hsr_priv *hsr = from_timer(hsr, t, announce_proxy_timer);
++ struct hsr_port *interlink;
++ unsigned long interval = 0;
++ struct hsr_node *node;
++
++ rcu_read_lock();
++ /* RedBOX sends supervisory frames to HSR network with MAC addresses
++ * of SAN nodes stored in ProxyNodeTable.
++ */
++ interlink = hsr_port_get_hsr(hsr, HSR_PT_INTERLINK);
++ if (!interlink)
++ goto done;
++
++ list_for_each_entry_rcu(node, &hsr->proxy_node_db, mac_list) {
++ if (hsr_addr_is_redbox(hsr, node->macaddress_A))
++ continue;
++ hsr->proto_ops->send_sv_frame(interlink, &interval,
++ node->macaddress_A);
++ }
++
++ if (is_admin_up(interlink->dev)) {
++ if (!interval)
++ interval = msecs_to_jiffies(HSR_ANNOUNCE_INTERVAL);
++
++ mod_timer(&hsr->announce_proxy_timer, jiffies + interval);
++ }
++
++done:
++ rcu_read_unlock();
++}
++
+ void hsr_del_ports(struct hsr_priv *hsr)
+ {
+ struct hsr_port *port;
+@@ -590,6 +634,7 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2],
+ timer_setup(&hsr->announce_timer, hsr_announce, 0);
+ timer_setup(&hsr->prune_timer, hsr_prune_nodes, 0);
+ timer_setup(&hsr->prune_proxy_timer, hsr_prune_proxy_nodes, 0);
++ timer_setup(&hsr->announce_proxy_timer, hsr_proxy_announce, 0);
+
+ ether_addr_copy(hsr->sup_multicast_addr, def_multicast_addr);
+ hsr->sup_multicast_addr[ETH_ALEN - 1] = multicast_spec;
+diff --git a/net/hsr/hsr_forward.c b/net/hsr/hsr_forward.c
+index 05a61b8286ec13..960ef386bc3a14 100644
+--- a/net/hsr/hsr_forward.c
++++ b/net/hsr/hsr_forward.c
+@@ -117,6 +117,35 @@ static bool is_supervision_frame(struct hsr_priv *hsr, struct sk_buff *skb)
+ return true;
+ }
+
++static bool is_proxy_supervision_frame(struct hsr_priv *hsr,
++ struct sk_buff *skb)
++{
++ struct hsr_sup_payload *payload;
++ struct ethhdr *eth_hdr;
++ u16 total_length = 0;
++
++ eth_hdr = (struct ethhdr *)skb_mac_header(skb);
++
++ /* Get the HSR protocol revision. */
++ if (eth_hdr->h_proto == htons(ETH_P_HSR))
++ total_length = sizeof(struct hsrv1_ethhdr_sp);
++ else
++ total_length = sizeof(struct hsrv0_ethhdr_sp);
++
++ if (!pskb_may_pull(skb, total_length + sizeof(struct hsr_sup_payload)))
++ return false;
++
++ skb_pull(skb, total_length);
++ payload = (struct hsr_sup_payload *)skb->data;
++ skb_push(skb, total_length);
++
++ /* For RedBox (HSR-SAN) check if we have received the supervision
++ * frame with MAC addresses from own ProxyNodeTable.
++ */
++ return hsr_is_node_in_db(&hsr->proxy_node_db,
++ payload->macaddress_A);
++}
++
+ static struct sk_buff *create_stripped_skb_hsr(struct sk_buff *skb_in,
+ struct hsr_frame_info *frame)
+ {
+@@ -499,7 +528,8 @@ static void hsr_forward_do(struct hsr_frame_info *frame)
+ frame->sequence_nr))
+ continue;
+
+- if (frame->is_supervision && port->type == HSR_PT_MASTER) {
++ if (frame->is_supervision && port->type == HSR_PT_MASTER &&
++ !frame->is_proxy_supervision) {
+ hsr_handle_sup_frame(frame);
+ continue;
+ }
+@@ -637,6 +667,9 @@ static int fill_frame_info(struct hsr_frame_info *frame,
+
+ memset(frame, 0, sizeof(*frame));
+ frame->is_supervision = is_supervision_frame(port->hsr, skb);
++ if (frame->is_supervision && hsr->redbox)
++ frame->is_proxy_supervision =
++ is_proxy_supervision_frame(port->hsr, skb);
+
+ n_db = &hsr->node_db;
+ if (port->type == HSR_PT_INTERLINK)
+@@ -688,7 +721,7 @@ void hsr_forward_skb(struct sk_buff *skb, struct hsr_port *port)
+ /* Gets called for ingress frames as well as egress from master port.
+ * So check and increment stats for master port only here.
+ */
+- if (port->type == HSR_PT_MASTER) {
++ if (port->type == HSR_PT_MASTER || port->type == HSR_PT_INTERLINK) {
+ port->dev->stats.tx_packets++;
+ port->dev->stats.tx_bytes += skb->len;
+ }
+diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c
+index 614df964979407..73bc6f659812f6 100644
+--- a/net/hsr/hsr_framereg.c
++++ b/net/hsr/hsr_framereg.c
+@@ -36,6 +36,14 @@ static bool seq_nr_after(u16 a, u16 b)
+ #define seq_nr_before(a, b) seq_nr_after((b), (a))
+ #define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b)))
+
++bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr)
++{
++ if (!hsr->redbox || !is_valid_ether_addr(hsr->macaddress_redbox))
++ return false;
++
++ return ether_addr_equal(addr, hsr->macaddress_redbox);
++}
++
+ bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr)
+ {
+ struct hsr_self_node *sn;
+@@ -591,6 +599,10 @@ void hsr_prune_proxy_nodes(struct timer_list *t)
+
+ spin_lock_bh(&hsr->list_lock);
+ list_for_each_entry_safe(node, tmp, &hsr->proxy_node_db, mac_list) {
++ /* Don't prune RedBox node. */
++ if (hsr_addr_is_redbox(hsr, node->macaddress_A))
++ continue;
++
+ timestamp = node->time_in[HSR_PT_INTERLINK];
+
+ /* Prune old entries */
+diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h
+index 7619e31c1d2de2..993fa950d81449 100644
+--- a/net/hsr/hsr_framereg.h
++++ b/net/hsr/hsr_framereg.h
+@@ -22,6 +22,7 @@ struct hsr_frame_info {
+ struct hsr_node *node_src;
+ u16 sequence_nr;
+ bool is_supervision;
++ bool is_proxy_supervision;
+ bool is_vlan;
+ bool is_local_dest;
+ bool is_local_exclusive;
+@@ -35,6 +36,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db,
+ enum hsr_port_type rx_port);
+ void hsr_handle_sup_frame(struct hsr_frame_info *frame);
+ bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr);
++bool hsr_addr_is_redbox(struct hsr_priv *hsr, unsigned char *addr);
+
+ void hsr_addr_subst_source(struct hsr_node *node, struct sk_buff *skb);
+ void hsr_addr_subst_dest(struct hsr_node *node_src, struct sk_buff *skb,
+diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h
+index 23850b16d1eacd..ab1f8d35d9dcf5 100644
+--- a/net/hsr/hsr_main.h
++++ b/net/hsr/hsr_main.h
+@@ -170,7 +170,8 @@ struct hsr_node;
+
+ struct hsr_proto_ops {
+ /* format and send supervision frame */
+- void (*send_sv_frame)(struct hsr_port *port, unsigned long *interval);
++ void (*send_sv_frame)(struct hsr_port *port, unsigned long *interval,
++ const unsigned char addr[ETH_ALEN]);
+ void (*handle_san_frame)(bool san, enum hsr_port_type port,
+ struct hsr_node *node);
+ bool (*drop_frame)(struct hsr_frame_info *frame, struct hsr_port *port);
+@@ -197,6 +198,7 @@ struct hsr_priv {
+ struct list_head proxy_node_db; /* RedBox HSR proxy nodes */
+ struct hsr_self_node __rcu *self_node; /* MACs of slaves */
+ struct timer_list announce_timer; /* Supervision frame dispatch */
++ struct timer_list announce_proxy_timer;
+ struct timer_list prune_timer;
+ struct timer_list prune_proxy_timer;
+ int announce_count;
+diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c
+index 898f18c6da53eb..f6ff0b61e08a96 100644
+--- a/net/hsr/hsr_netlink.c
++++ b/net/hsr/hsr_netlink.c
+@@ -131,6 +131,7 @@ static void hsr_dellink(struct net_device *dev, struct list_head *head)
+ del_timer_sync(&hsr->prune_timer);
+ del_timer_sync(&hsr->prune_proxy_timer);
+ del_timer_sync(&hsr->announce_timer);
++ timer_delete_sync(&hsr->announce_proxy_timer);
+
+ hsr_debugfs_term(hsr);
+ hsr_del_ports(hsr);
+diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
+index 78b869b314921b..3e30745e2c09ac 100644
+--- a/net/ipv4/fou_core.c
++++ b/net/ipv4/fou_core.c
+@@ -336,11 +336,11 @@ static struct sk_buff *gue_gro_receive(struct sock *sk,
+ struct gro_remcsum grc;
+ u8 proto;
+
++ skb_gro_remcsum_init(&grc);
++
+ if (!fou)
+ goto out;
+
+- skb_gro_remcsum_init(&grc);
+-
+ off = skb_gro_offset(skb);
+ len = off + sizeof(*guehdr);
+
+diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
+index f891bc714668c5..ad935d34c973a9 100644
+--- a/net/mptcp/pm_netlink.c
++++ b/net/mptcp/pm_netlink.c
+@@ -334,15 +334,21 @@ mptcp_pm_del_add_timer(struct mptcp_sock *msk,
+ {
+ struct mptcp_pm_add_entry *entry;
+ struct sock *sk = (struct sock *)msk;
++ struct timer_list *add_timer = NULL;
+
+ spin_lock_bh(&msk->pm.lock);
+ entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
+- if (entry && (!check_id || entry->addr.id == addr->id))
++ if (entry && (!check_id || entry->addr.id == addr->id)) {
+ entry->retrans_times = ADD_ADDR_RETRANS_MAX;
++ add_timer = &entry->add_timer;
++ }
++ if (!check_id && entry)
++ list_del(&entry->list);
+ spin_unlock_bh(&msk->pm.lock);
+
+- if (entry && (!check_id || entry->addr.id == addr->id))
+- sk_stop_timer_sync(sk, &entry->add_timer);
++ /* no lock, because sk_stop_timer_sync() is calling del_timer_sync() */
++ if (add_timer)
++ sk_stop_timer_sync(sk, add_timer);
+
+ return entry;
+ }
+@@ -1462,7 +1468,6 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
+
+ entry = mptcp_pm_del_add_timer(msk, addr, false);
+ if (entry) {
+- list_del(&entry->list);
+ kfree(entry);
+ return true;
+ }
+diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c
+index f30163e2ca6207..765ffd6e06bc41 100644
+--- a/net/netfilter/nft_socket.c
++++ b/net/netfilter/nft_socket.c
+@@ -110,13 +110,13 @@ static void nft_socket_eval(const struct nft_expr *expr,
+ *dest = READ_ONCE(sk->sk_mark);
+ } else {
+ regs->verdict.code = NFT_BREAK;
+- return;
++ goto out_put_sk;
+ }
+ break;
+ case NFT_SOCKET_WILDCARD:
+ if (!sk_fullsock(sk)) {
+ regs->verdict.code = NFT_BREAK;
+- return;
++ goto out_put_sk;
+ }
+ nft_socket_wildcard(pkt, regs, sk, dest);
+ break;
+@@ -124,7 +124,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
+ case NFT_SOCKET_CGROUPV2:
+ if (!nft_sock_get_eval_cgroupv2(dest, sk, pkt, priv->level)) {
+ regs->verdict.code = NFT_BREAK;
+- return;
++ goto out_put_sk;
+ }
+ break;
+ #endif
+@@ -133,6 +133,7 @@ static void nft_socket_eval(const struct nft_expr *expr,
+ regs->verdict.code = NFT_BREAK;
+ }
+
++out_put_sk:
+ if (sk != skb->sk)
+ sock_gen_put(sk);
+ }
+diff --git a/scripts/kconfig/merge_config.sh b/scripts/kconfig/merge_config.sh
+index 902eb429b9dbd9..0b7952471c18f6 100755
+--- a/scripts/kconfig/merge_config.sh
++++ b/scripts/kconfig/merge_config.sh
+@@ -167,6 +167,8 @@ for ORIG_MERGE_FILE in $MERGE_LIST ; do
+ sed -i "/$CFG[ =]/d" $MERGE_FILE
+ fi
+ done
++ # In case the previous file lacks a new line at the end
++ echo >> $TMP_FILE
+ cat $MERGE_FILE >> $TMP_FILE
+ done
+
+diff --git a/sound/soc/codecs/peb2466.c b/sound/soc/codecs/peb2466.c
+index 5dec69be0acb2e..06c83d2042f3e5 100644
+--- a/sound/soc/codecs/peb2466.c
++++ b/sound/soc/codecs/peb2466.c
+@@ -229,7 +229,8 @@ static int peb2466_reg_read(void *context, unsigned int reg, unsigned int *val)
+ case PEB2466_CMD_XOP:
+ case PEB2466_CMD_SOP:
+ ret = peb2466_read_byte(peb2466, reg, &tmp);
+- *val = tmp;
++ if (!ret)
++ *val = tmp;
+ break;
+ default:
+ dev_err(&peb2466->spi->dev, "Not a XOP or SOP command\n");
+diff --git a/sound/soc/intel/common/soc-acpi-intel-lnl-match.c b/sound/soc/intel/common/soc-acpi-intel-lnl-match.c
+index e6ffcd5be6c5af..edfb668d0580d3 100644
+--- a/sound/soc/intel/common/soc-acpi-intel-lnl-match.c
++++ b/sound/soc/intel/common/soc-acpi-intel-lnl-match.c
+@@ -208,6 +208,7 @@ static const struct snd_soc_acpi_link_adr lnl_cs42l43_l0[] = {
+ .num_adr = ARRAY_SIZE(cs42l43_0_adr),
+ .adr_d = cs42l43_0_adr,
+ },
++ {}
+ };
+
+ static const struct snd_soc_acpi_link_adr lnl_rvp[] = {
+diff --git a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
+index 8e0ae3635a35d7..d4435a34a3a3f4 100644
+--- a/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
++++ b/sound/soc/intel/common/soc-acpi-intel-mtl-match.c
+@@ -674,6 +674,7 @@ static const struct snd_soc_acpi_link_adr mtl_cs42l43_l0[] = {
+ .num_adr = ARRAY_SIZE(cs42l43_0_adr),
+ .adr_d = cs42l43_0_adr,
+ },
++ {}
+ };
+
+ static const struct snd_soc_acpi_link_adr mtl_cs42l43_cs35l56[] = {
+diff --git a/sound/soc/meson/axg-card.c b/sound/soc/meson/axg-card.c
+index 8c5605c1e34e8a..eb0302f2074070 100644
+--- a/sound/soc/meson/axg-card.c
++++ b/sound/soc/meson/axg-card.c
+@@ -104,7 +104,7 @@ static int axg_card_add_tdm_loopback(struct snd_soc_card *card,
+ int *index)
+ {
+ struct meson_card *priv = snd_soc_card_get_drvdata(card);
+- struct snd_soc_dai_link *pad = &card->dai_link[*index];
++ struct snd_soc_dai_link *pad;
+ struct snd_soc_dai_link *lb;
+ struct snd_soc_dai_link_component *dlc;
+ int ret;
+@@ -114,6 +114,7 @@ static int axg_card_add_tdm_loopback(struct snd_soc_card *card,
+ if (ret)
+ return ret;
+
++ pad = &card->dai_link[*index];
+ lb = &card->dai_link[*index + 1];
+
+ lb->name = devm_kasprintf(card->dev, GFP_KERNEL, "%s-lb", pad->name);
+diff --git a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+index e91b5936603018..c075d376fcabfd 100644
+--- a/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
++++ b/tools/testing/selftests/bpf/prog_tests/sockmap_listen.c
+@@ -1828,7 +1828,7 @@ static void unix_inet_redir_to_connected(int family, int type,
+ if (err)
+ return;
+
+- if (socketpair(AF_UNIX, SOCK_DGRAM | SOCK_NONBLOCK, 0, sfd))
++ if (socketpair(AF_UNIX, type | SOCK_NONBLOCK, 0, sfd))
+ goto close_cli0;
+ c1 = sfd[0], p1 = sfd[1];
+
+@@ -1840,7 +1840,6 @@ static void unix_inet_redir_to_connected(int family, int type,
+ close_cli0:
+ xclose(c0);
+ xclose(p0);
+-
+ }
+
+ static void unix_inet_skb_redir_to_connected(struct test_sockmap_listen *skel,
+diff --git a/tools/testing/selftests/net/lib/csum.c b/tools/testing/selftests/net/lib/csum.c
+index b9f3fc3c34263d..e0a34e5e8dd5c6 100644
+--- a/tools/testing/selftests/net/lib/csum.c
++++ b/tools/testing/selftests/net/lib/csum.c
+@@ -654,10 +654,16 @@ static int recv_verify_packet_ipv4(void *nh, int len)
+ {
+ struct iphdr *iph = nh;
+ uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto;
++ uint16_t ip_len;
+
+ if (len < sizeof(*iph) || iph->protocol != proto)
+ return -1;
+
++ ip_len = ntohs(iph->tot_len);
++ if (ip_len > len || ip_len < sizeof(*iph))
++ return -1;
++
++ len = ip_len;
+ iph_addr_p = &iph->saddr;
+ if (proto == IPPROTO_TCP)
+ return recv_verify_packet_tcp(iph + 1, len - sizeof(*iph));
+@@ -669,16 +675,22 @@ static int recv_verify_packet_ipv6(void *nh, int len)
+ {
+ struct ipv6hdr *ip6h = nh;
+ uint16_t proto = cfg_encap ? IPPROTO_UDP : cfg_proto;
++ uint16_t ip_len;
+
+ if (len < sizeof(*ip6h) || ip6h->nexthdr != proto)
+ return -1;
+
++ ip_len = ntohs(ip6h->payload_len);
++ if (ip_len > len - sizeof(*ip6h))
++ return -1;
++
++ len = ip_len;
+ iph_addr_p = &ip6h->saddr;
+
+ if (proto == IPPROTO_TCP)
+- return recv_verify_packet_tcp(ip6h + 1, len - sizeof(*ip6h));
++ return recv_verify_packet_tcp(ip6h + 1, len);
+ else
+- return recv_verify_packet_udp(ip6h + 1, len - sizeof(*ip6h));
++ return recv_verify_packet_udp(ip6h + 1, len);
+ }
+
+ /* return whether auxdata includes TP_STATUS_CSUM_VALID */
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+index a4762c49a87861..cde041c93906df 100755
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+@@ -3064,7 +3064,9 @@ fullmesh_tests()
+ pm_nl_set_limits $ns1 1 3
+ pm_nl_set_limits $ns2 1 3
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+- pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh
++ if mptcp_lib_kallsyms_has "mptcp_pm_subflow_check_next$"; then
++ pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh
++ fi
+ fullmesh=1 speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 3 3 3
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-12 13:08 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-12 13:08 UTC (permalink / raw
To: gentoo-commits
commit: 9ca4d20e2535253eb3da4c5d4b5d84ed351d1a11
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Thu Sep 12 13:07:11 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Thu Sep 12 13:07:11 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=9ca4d20e
Remove redundant patches
Removed:
1710_parisc-Delay-write-protection.patch
1900_xfs-finobt-count-blocks-fix.patch
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 8 -----
1710_parisc-Delay-write-protection.patch | 61 --------------------------------
1900_xfs-finobt-count-blocks-fix.patch | 55 ----------------------------
3 files changed, 124 deletions(-)
diff --git a/0000_README b/0000_README
index 3b3f17cf..fbbb6719 100644
--- a/0000_README
+++ b/0000_README
@@ -91,18 +91,10 @@ Patch: 1700_sparc-address-warray-bound-warnings.patch
From: https://github.com/KSPP/linux/issues/109
Desc: Address -Warray-bounds warnings
-Patch: 1710_parisc-Delay-write-protection.patch
-From: https://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
-Desc: parisc: Delay write-protection until mark_rodata_ro() call
-
Patch: 1730_parisc-Disable-prctl.patch
From: https://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
Desc: prctl: Temporarily disable prctl(PR_SET_MDWE) on parisc
-Patch: 1900_xfs-finobt-count-blocks-fix.patch
-From: https://lore.kernel.org/linux-xfs/20240813152530.GF6051@frogsfrogsfrogs/T/#mdc718f38912ccc1b9b53b46d9adfaeff0828b55f
-Desc: xfs: xfs_finobt_count_blocks() walks the wrong btree
-
Patch: 2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch
From: https://lore.kernel.org/linux-bluetooth/20190522070540.48895-1-marcel@holtmann.org/raw
Desc: Bluetooth: Check key sizes only when Secure Simple Pairing is enabled. See bug #686758
diff --git a/1710_parisc-Delay-write-protection.patch b/1710_parisc-Delay-write-protection.patch
deleted file mode 100644
index efdd4c27..00000000
--- a/1710_parisc-Delay-write-protection.patch
+++ /dev/null
@@ -1,61 +0,0 @@
-From 213aa670153ed675a007c1f35c5db544b0fefc94 Mon Sep 17 00:00:00 2001
-From: Helge Deller <deller@gmx.de>
-Date: Sat, 31 Aug 2024 14:02:06 +0200
-Subject: parisc: Delay write-protection until mark_rodata_ro() call
-
-Do not write-protect the kernel read-only and __ro_after_init sections
-earlier than before mark_rodata_ro() is called. This fixes a boot issue on
-parisc which is triggered by commit 91a1d97ef482 ("jump_label,module: Don't
-alloc static_key_mod for __ro_after_init keys"). That commit may modify
-static key contents in the __ro_after_init section at bootup, so this
-section needs to be writable at least until mark_rodata_ro() is called.
-
-Signed-off-by: Helge Deller <deller@gmx.de>
-Reported-by: matoro <matoro_mailinglist_kernel@matoro.tk>
-Reported-by: Christoph Biedl <linux-kernel.bfrz@manchmal.in-ulm.de>
-Tested-by: Christoph Biedl <linux-kernel.bfrz@manchmal.in-ulm.de>
-Link: https://lore.kernel.org/linux-parisc/096cad5aada514255cd7b0b9dbafc768@matoro.tk/#r
-Fixes: 91a1d97ef482 ("jump_label,module: Don't alloc static_key_mod for __ro_after_init keys")
-Cc: stable@vger.kernel.org # v6.10+
----
- arch/parisc/mm/init.c | 16 +++++++++++-----
- 1 file changed, 11 insertions(+), 5 deletions(-)
-
-diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
-index 34d91cb8b25905..96970fa75e4ac9 100644
---- a/arch/parisc/mm/init.c
-+++ b/arch/parisc/mm/init.c
-@@ -459,7 +459,6 @@ void free_initmem(void)
- unsigned long kernel_end = (unsigned long)&_end;
-
- /* Remap kernel text and data, but do not touch init section yet. */
-- kernel_set_to_readonly = true;
- map_pages(init_end, __pa(init_end), kernel_end - init_end,
- PAGE_KERNEL, 0);
-
-@@ -493,11 +492,18 @@ void free_initmem(void)
- #ifdef CONFIG_STRICT_KERNEL_RWX
- void mark_rodata_ro(void)
- {
-- /* rodata memory was already mapped with KERNEL_RO access rights by
-- pagetable_init() and map_pages(). No need to do additional stuff here */
-- unsigned long roai_size = __end_ro_after_init - __start_ro_after_init;
-+ unsigned long start = (unsigned long) &__start_rodata;
-+ unsigned long end = (unsigned long) &__end_rodata;
-+
-+ pr_info("Write protecting the kernel read-only data: %luk\n",
-+ (end - start) >> 10);
-+
-+ kernel_set_to_readonly = true;
-+ map_pages(start, __pa(start), end - start, PAGE_KERNEL, 0);
-
-- pr_info("Write protected read-only-after-init data: %luk\n", roai_size >> 10);
-+ /* force the kernel to see the new page table entries */
-+ flush_cache_all();
-+ flush_tlb_all();
- }
- #endif
-
---
-cgit 1.2.3-korg
-
diff --git a/1900_xfs-finobt-count-blocks-fix.patch b/1900_xfs-finobt-count-blocks-fix.patch
deleted file mode 100644
index 02f60712..00000000
--- a/1900_xfs-finobt-count-blocks-fix.patch
+++ /dev/null
@@ -1,55 +0,0 @@
-xfs: xfs_finobt_count_blocks() walks the wrong btree
-
-From: Dave Chinner <dchinner@redhat.com>
-
-As a result of the factoring in commit 14dd46cf31f4 ("xfs: split
-xfs_inobt_init_cursor"), mount started taking a long time on a
-user's filesystem. For Anders, this made mount times regress from
-under a second to over 15 minutes for a filesystem with only 30
-million inodes in it.
-
-Anders bisected it down to the above commit, but even then the bug
-was not obvious. In this commit, over 20 calls to
-xfs_inobt_init_cursor() were modified, and some we modified to call
-a new function named xfs_finobt_init_cursor().
-
-If that takes you a moment to reread those function names to see
-what the rename was, then you have realised why this bug wasn't
-spotted during review. And it wasn't spotted on inspection even
-after the bisect pointed at this commit - a single missing "f" isn't
-the easiest thing for a human eye to notice....
-
-The result is that xfs_finobt_count_blocks() now incorrectly calls
-xfs_inobt_init_cursor() so it is now walking the inobt instead of
-the finobt. Hence when there are lots of allocated inodes in a
-filesystem, mount takes a -long- time run because it now walks a
-massive allocated inode btrees instead of the small, nearly empty
-free inode btrees. It also means all the finobt space reservations
-are wrong, so mount could potentially given ENOSPC on kernel
-upgrade.
-
-In hindsight, commit 14dd46cf31f4 should have been two commits - the
-first to convert the finobt callers to the new API, the second to
-modify the xfs_inobt_init_cursor() API for the inobt callers. That
-would have made the bug very obvious during review.
-
-Fixes: 14dd46cf31f4 ("xfs: split xfs_inobt_init_cursor")
-Reported-by: Anders Blomdell <anders.blomdell@gmail.com>
-Signed-off-by: Dave Chinner <dchinner@redhat.com>
----
- fs/xfs/libxfs/xfs_ialloc_btree.c | 2 +-
- 1 file changed, 1 insertion(+), 1 deletion(-)
-
-diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
-index 496e2f72a85b..797d5b5f7b72 100644
---- a/fs/xfs/libxfs/xfs_ialloc_btree.c
-+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
-@@ -749,7 +749,7 @@ xfs_finobt_count_blocks(
- if (error)
- return error;
-
-- cur = xfs_inobt_init_cursor(pag, tp, agbp);
-+ cur = xfs_finobt_init_cursor(pag, tp, agbp);
- error = xfs_btree_count_blocks(cur, tree_blocks);
- xfs_btree_del_cursor(cur, error);
- xfs_trans_brelse(tp, agbp);
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-12 12:30 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-12 12:30 UTC (permalink / raw
To: gentoo-commits
commit: 0e58d5899781a7e637af315dada54546b9564ee9
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Thu Sep 12 12:30:16 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Thu Sep 12 12:30:16 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=0e58d589
Linux patch 6.10.10
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1009_linux-6.10.10.patch | 18867 +++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 18871 insertions(+)
diff --git a/0000_README b/0000_README
index 20bc0dd9..3b3f17cf 100644
--- a/0000_README
+++ b/0000_README
@@ -79,6 +79,10 @@ Patch: 1008_linux-6.10.9.patch
From: https://www.kernel.org
Desc: Linux 6.10.9
+Patch: 1009_linux-6.10.10.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.10
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1009_linux-6.10.10.patch b/1009_linux-6.10.10.patch
new file mode 100644
index 00000000..3481e02a
--- /dev/null
+++ b/1009_linux-6.10.10.patch
@@ -0,0 +1,18867 @@
+diff --git a/Documentation/admin-guide/cgroup-v2.rst b/Documentation/admin-guide/cgroup-v2.rst
+index 8fbb0519d5569..4a7a59bbf76f8 100644
+--- a/Documentation/admin-guide/cgroup-v2.rst
++++ b/Documentation/admin-guide/cgroup-v2.rst
+@@ -1706,9 +1706,10 @@ PAGE_SIZE multiple when read back.
+ entries fault back in or are written out to disk.
+
+ memory.zswap.writeback
+- A read-write single value file. The default value is "1". The
+- initial value of the root cgroup is 1, and when a new cgroup is
+- created, it inherits the current value of its parent.
++ A read-write single value file. The default value is "1".
++ Note that this setting is hierarchical, i.e. the writeback would be
++ implicitly disabled for child cgroups if the upper hierarchy
++ does so.
+
+ When this is set to 0, all swapping attempts to swapping devices
+ are disabled. This included both zswap writebacks, and swapping due
+@@ -2346,8 +2347,12 @@ Cpuset Interface Files
+ is always a subset of it.
+
+ Users can manually set it to a value that is different from
+- "cpuset.cpus". The only constraint in setting it is that the
+- list of CPUs must be exclusive with respect to its sibling.
++ "cpuset.cpus". One constraint in setting it is that the list of
++ CPUs must be exclusive with respect to "cpuset.cpus.exclusive"
++ of its sibling. If "cpuset.cpus.exclusive" of a sibling cgroup
++ isn't set, its "cpuset.cpus" value, if set, cannot be a subset
++ of it to leave at least one CPU available when the exclusive
++ CPUs are taken away.
+
+ For a parent cgroup, any one of its exclusive CPUs can only
+ be distributed to at most one of its child cgroups. Having an
+diff --git a/Documentation/devicetree/bindings/nvmem/xlnx,zynqmp-nvmem.yaml b/Documentation/devicetree/bindings/nvmem/xlnx,zynqmp-nvmem.yaml
+index 917c40d5c382f..1cbe44ab23b1d 100644
+--- a/Documentation/devicetree/bindings/nvmem/xlnx,zynqmp-nvmem.yaml
++++ b/Documentation/devicetree/bindings/nvmem/xlnx,zynqmp-nvmem.yaml
+@@ -28,7 +28,7 @@ unevaluatedProperties: false
+
+ examples:
+ - |
+- nvmem {
++ soc-nvmem {
+ compatible = "xlnx,zynqmp-nvmem-fw";
+ nvmem-layout {
+ compatible = "fixed-layout";
+diff --git a/Makefile b/Makefile
+index 5945cce6b0663..9b4614c0fcbb6 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 9
++SUBLEVEL = 10
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm64/include/asm/acpi.h b/arch/arm64/include/asm/acpi.h
+index 6792a1f83f2ad..a407f9cd549ed 100644
+--- a/arch/arm64/include/asm/acpi.h
++++ b/arch/arm64/include/asm/acpi.h
+@@ -119,6 +119,18 @@ static inline u32 get_acpi_id_for_cpu(unsigned int cpu)
+ return acpi_cpu_get_madt_gicc(cpu)->uid;
+ }
+
++static inline int get_cpu_for_acpi_id(u32 uid)
++{
++ int cpu;
++
++ for (cpu = 0; cpu < nr_cpu_ids; cpu++)
++ if (acpi_cpu_get_madt_gicc(cpu) &&
++ uid == get_acpi_id_for_cpu(cpu))
++ return cpu;
++
++ return -EINVAL;
++}
++
+ static inline void arch_fix_phys_package_id(int num, u32 slot) { }
+ void __init acpi_init_cpus(void);
+ int apei_claim_sea(struct pt_regs *regs);
+diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
+index ccbff21ce1faf..2465f291c7e17 100644
+--- a/arch/arm64/kernel/acpi_numa.c
++++ b/arch/arm64/kernel/acpi_numa.c
+@@ -34,17 +34,6 @@ int __init acpi_numa_get_nid(unsigned int cpu)
+ return acpi_early_node_map[cpu];
+ }
+
+-static inline int get_cpu_for_acpi_id(u32 uid)
+-{
+- int cpu;
+-
+- for (cpu = 0; cpu < nr_cpu_ids; cpu++)
+- if (uid == get_acpi_id_for_cpu(cpu))
+- return cpu;
+-
+- return -EINVAL;
+-}
+-
+ static int __init acpi_parse_gicc_pxm(union acpi_subtable_headers *header,
+ const unsigned long end)
+ {
+diff --git a/arch/loongarch/include/asm/hugetlb.h b/arch/loongarch/include/asm/hugetlb.h
+index aa44b3fe43dde..5da32c00d483f 100644
+--- a/arch/loongarch/include/asm/hugetlb.h
++++ b/arch/loongarch/include/asm/hugetlb.h
+@@ -34,7 +34,7 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm,
+ unsigned long addr, pte_t *ptep)
+ {
+ pte_t clear;
+- pte_t pte = *ptep;
++ pte_t pte = ptep_get(ptep);
+
+ pte_val(clear) = (unsigned long)invalid_pte_table;
+ set_pte_at(mm, addr, ptep, clear);
+@@ -65,7 +65,7 @@ static inline int huge_ptep_set_access_flags(struct vm_area_struct *vma,
+ pte_t *ptep, pte_t pte,
+ int dirty)
+ {
+- int changed = !pte_same(*ptep, pte);
++ int changed = !pte_same(ptep_get(ptep), pte);
+
+ if (changed) {
+ set_pte_at(vma->vm_mm, addr, ptep, pte);
+diff --git a/arch/loongarch/include/asm/kfence.h b/arch/loongarch/include/asm/kfence.h
+index 92636e82957c7..da9e93024626c 100644
+--- a/arch/loongarch/include/asm/kfence.h
++++ b/arch/loongarch/include/asm/kfence.h
+@@ -53,13 +53,13 @@ static inline bool kfence_protect_page(unsigned long addr, bool protect)
+ {
+ pte_t *pte = virt_to_kpte(addr);
+
+- if (WARN_ON(!pte) || pte_none(*pte))
++ if (WARN_ON(!pte) || pte_none(ptep_get(pte)))
+ return false;
+
+ if (protect)
+- set_pte(pte, __pte(pte_val(*pte) & ~(_PAGE_VALID | _PAGE_PRESENT)));
++ set_pte(pte, __pte(pte_val(ptep_get(pte)) & ~(_PAGE_VALID | _PAGE_PRESENT)));
+ else
+- set_pte(pte, __pte(pte_val(*pte) | (_PAGE_VALID | _PAGE_PRESENT)));
++ set_pte(pte, __pte(pte_val(ptep_get(pte)) | (_PAGE_VALID | _PAGE_PRESENT)));
+
+ preempt_disable();
+ local_flush_tlb_one(addr);
+diff --git a/arch/loongarch/include/asm/pgtable.h b/arch/loongarch/include/asm/pgtable.h
+index af3acdf3481a6..c4b1a7595c4eb 100644
+--- a/arch/loongarch/include/asm/pgtable.h
++++ b/arch/loongarch/include/asm/pgtable.h
+@@ -106,6 +106,9 @@ extern unsigned long empty_zero_page[PAGE_SIZE / sizeof(unsigned long)];
+ #define KFENCE_AREA_START (VMEMMAP_END + 1)
+ #define KFENCE_AREA_END (KFENCE_AREA_START + KFENCE_AREA_SIZE - 1)
+
++#define ptep_get(ptep) READ_ONCE(*(ptep))
++#define pmdp_get(pmdp) READ_ONCE(*(pmdp))
++
+ #define pte_ERROR(e) \
+ pr_err("%s:%d: bad pte %016lx.\n", __FILE__, __LINE__, pte_val(e))
+ #ifndef __PAGETABLE_PMD_FOLDED
+@@ -147,11 +150,6 @@ static inline int p4d_present(p4d_t p4d)
+ return p4d_val(p4d) != (unsigned long)invalid_pud_table;
+ }
+
+-static inline void p4d_clear(p4d_t *p4dp)
+-{
+- p4d_val(*p4dp) = (unsigned long)invalid_pud_table;
+-}
+-
+ static inline pud_t *p4d_pgtable(p4d_t p4d)
+ {
+ return (pud_t *)p4d_val(p4d);
+@@ -159,7 +157,12 @@ static inline pud_t *p4d_pgtable(p4d_t p4d)
+
+ static inline void set_p4d(p4d_t *p4d, p4d_t p4dval)
+ {
+- *p4d = p4dval;
++ WRITE_ONCE(*p4d, p4dval);
++}
++
++static inline void p4d_clear(p4d_t *p4dp)
++{
++ set_p4d(p4dp, __p4d((unsigned long)invalid_pud_table));
+ }
+
+ #define p4d_phys(p4d) PHYSADDR(p4d_val(p4d))
+@@ -193,17 +196,20 @@ static inline int pud_present(pud_t pud)
+ return pud_val(pud) != (unsigned long)invalid_pmd_table;
+ }
+
+-static inline void pud_clear(pud_t *pudp)
++static inline pmd_t *pud_pgtable(pud_t pud)
+ {
+- pud_val(*pudp) = ((unsigned long)invalid_pmd_table);
++ return (pmd_t *)pud_val(pud);
+ }
+
+-static inline pmd_t *pud_pgtable(pud_t pud)
++static inline void set_pud(pud_t *pud, pud_t pudval)
+ {
+- return (pmd_t *)pud_val(pud);
++ WRITE_ONCE(*pud, pudval);
+ }
+
+-#define set_pud(pudptr, pudval) do { *(pudptr) = (pudval); } while (0)
++static inline void pud_clear(pud_t *pudp)
++{
++ set_pud(pudp, __pud((unsigned long)invalid_pmd_table));
++}
+
+ #define pud_phys(pud) PHYSADDR(pud_val(pud))
+ #define pud_page(pud) (pfn_to_page(pud_phys(pud) >> PAGE_SHIFT))
+@@ -231,12 +237,15 @@ static inline int pmd_present(pmd_t pmd)
+ return pmd_val(pmd) != (unsigned long)invalid_pte_table;
+ }
+
+-static inline void pmd_clear(pmd_t *pmdp)
++static inline void set_pmd(pmd_t *pmd, pmd_t pmdval)
+ {
+- pmd_val(*pmdp) = ((unsigned long)invalid_pte_table);
++ WRITE_ONCE(*pmd, pmdval);
+ }
+
+-#define set_pmd(pmdptr, pmdval) do { *(pmdptr) = (pmdval); } while (0)
++static inline void pmd_clear(pmd_t *pmdp)
++{
++ set_pmd(pmdp, __pmd((unsigned long)invalid_pte_table));
++}
+
+ #define pmd_phys(pmd) PHYSADDR(pmd_val(pmd))
+
+@@ -314,7 +323,8 @@ extern void paging_init(void);
+
+ static inline void set_pte(pte_t *ptep, pte_t pteval)
+ {
+- *ptep = pteval;
++ WRITE_ONCE(*ptep, pteval);
++
+ if (pte_val(pteval) & _PAGE_GLOBAL) {
+ pte_t *buddy = ptep_buddy(ptep);
+ /*
+@@ -341,8 +351,8 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
+ : [buddy] "+m" (buddy->pte), [tmp] "=&r" (tmp)
+ : [global] "r" (page_global));
+ #else /* !CONFIG_SMP */
+- if (pte_none(*buddy))
+- pte_val(*buddy) = pte_val(*buddy) | _PAGE_GLOBAL;
++ if (pte_none(ptep_get(buddy)))
++ WRITE_ONCE(*buddy, __pte(pte_val(ptep_get(buddy)) | _PAGE_GLOBAL));
+ #endif /* CONFIG_SMP */
+ }
+ }
+@@ -350,7 +360,7 @@ static inline void set_pte(pte_t *ptep, pte_t pteval)
+ static inline void pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
+ {
+ /* Preserve global status for the pair */
+- if (pte_val(*ptep_buddy(ptep)) & _PAGE_GLOBAL)
++ if (pte_val(ptep_get(ptep_buddy(ptep))) & _PAGE_GLOBAL)
+ set_pte(ptep, __pte(_PAGE_GLOBAL));
+ else
+ set_pte(ptep, __pte(0));
+@@ -589,7 +599,7 @@ static inline pmd_t pmd_mkinvalid(pmd_t pmd)
+ static inline pmd_t pmdp_huge_get_and_clear(struct mm_struct *mm,
+ unsigned long address, pmd_t *pmdp)
+ {
+- pmd_t old = *pmdp;
++ pmd_t old = pmdp_get(pmdp);
+
+ pmd_clear(pmdp);
+
+diff --git a/arch/loongarch/kernel/relocate.c b/arch/loongarch/kernel/relocate.c
+index 1acfa704c8d09..0eddd4a66b874 100644
+--- a/arch/loongarch/kernel/relocate.c
++++ b/arch/loongarch/kernel/relocate.c
+@@ -13,6 +13,7 @@
+ #include <asm/bootinfo.h>
+ #include <asm/early_ioremap.h>
+ #include <asm/inst.h>
++#include <asm/io.h>
+ #include <asm/sections.h>
+ #include <asm/setup.h>
+
+@@ -170,7 +171,7 @@ unsigned long __init relocate_kernel(void)
+ unsigned long kernel_length;
+ unsigned long random_offset = 0;
+ void *location_new = _text; /* Default to original kernel start */
+- char *cmdline = early_ioremap(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */
++ char *cmdline = early_memremap_ro(fw_arg1, COMMAND_LINE_SIZE); /* Boot command line is passed in fw_arg1 */
+
+ strscpy(boot_command_line, cmdline, COMMAND_LINE_SIZE);
+
+@@ -182,6 +183,7 @@ unsigned long __init relocate_kernel(void)
+ random_offset = (unsigned long)location_new - (unsigned long)(_text);
+ #endif
+ reloc_offset = (unsigned long)_text - VMLINUX_LOAD_ADDRESS;
++ early_memunmap(cmdline, COMMAND_LINE_SIZE);
+
+ if (random_offset) {
+ kernel_length = (long)(_end) - (long)(_text);
+diff --git a/arch/loongarch/kvm/mmu.c b/arch/loongarch/kvm/mmu.c
+index 98883aa23ab82..357f775abd49d 100644
+--- a/arch/loongarch/kvm/mmu.c
++++ b/arch/loongarch/kvm/mmu.c
+@@ -695,19 +695,19 @@ static int host_pfn_mapping_level(struct kvm *kvm, gfn_t gfn,
+ * value) and then p*d_offset() walks into the target huge page instead
+ * of the old page table (sees the new value).
+ */
+- pgd = READ_ONCE(*pgd_offset(kvm->mm, hva));
++ pgd = pgdp_get(pgd_offset(kvm->mm, hva));
+ if (pgd_none(pgd))
+ goto out;
+
+- p4d = READ_ONCE(*p4d_offset(&pgd, hva));
++ p4d = p4dp_get(p4d_offset(&pgd, hva));
+ if (p4d_none(p4d) || !p4d_present(p4d))
+ goto out;
+
+- pud = READ_ONCE(*pud_offset(&p4d, hva));
++ pud = pudp_get(pud_offset(&p4d, hva));
+ if (pud_none(pud) || !pud_present(pud))
+ goto out;
+
+- pmd = READ_ONCE(*pmd_offset(&pud, hva));
++ pmd = pmdp_get(pmd_offset(&pud, hva));
+ if (pmd_none(pmd) || !pmd_present(pmd))
+ goto out;
+
+diff --git a/arch/loongarch/mm/hugetlbpage.c b/arch/loongarch/mm/hugetlbpage.c
+index 12222c56cb594..e4068906143b3 100644
+--- a/arch/loongarch/mm/hugetlbpage.c
++++ b/arch/loongarch/mm/hugetlbpage.c
+@@ -39,11 +39,11 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmd = NULL;
+
+ pgd = pgd_offset(mm, addr);
+- if (pgd_present(*pgd)) {
++ if (pgd_present(pgdp_get(pgd))) {
+ p4d = p4d_offset(pgd, addr);
+- if (p4d_present(*p4d)) {
++ if (p4d_present(p4dp_get(p4d))) {
+ pud = pud_offset(p4d, addr);
+- if (pud_present(*pud))
++ if (pud_present(pudp_get(pud)))
+ pmd = pmd_offset(pud, addr);
+ }
+ }
+diff --git a/arch/loongarch/mm/init.c b/arch/loongarch/mm/init.c
+index bf789d114c2d7..8a87a482c8f44 100644
+--- a/arch/loongarch/mm/init.c
++++ b/arch/loongarch/mm/init.c
+@@ -141,7 +141,7 @@ void __meminit vmemmap_set_pmd(pmd_t *pmd, void *p, int node,
+ int __meminit vmemmap_check_pmd(pmd_t *pmd, int node,
+ unsigned long addr, unsigned long next)
+ {
+- int huge = pmd_val(*pmd) & _PAGE_HUGE;
++ int huge = pmd_val(pmdp_get(pmd)) & _PAGE_HUGE;
+
+ if (huge)
+ vmemmap_verify((pte_t *)pmd, node, addr, next);
+@@ -173,7 +173,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
+ pud_t *pud;
+ pmd_t *pmd;
+
+- if (p4d_none(*p4d)) {
++ if (p4d_none(p4dp_get(p4d))) {
+ pud = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ if (!pud)
+ panic("%s: Failed to allocate memory\n", __func__);
+@@ -184,7 +184,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
+ }
+
+ pud = pud_offset(p4d, addr);
+- if (pud_none(*pud)) {
++ if (pud_none(pudp_get(pud))) {
+ pmd = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+ if (!pmd)
+ panic("%s: Failed to allocate memory\n", __func__);
+@@ -195,7 +195,7 @@ pte_t * __init populate_kernel_pte(unsigned long addr)
+ }
+
+ pmd = pmd_offset(pud, addr);
+- if (!pmd_present(*pmd)) {
++ if (!pmd_present(pmdp_get(pmd))) {
+ pte_t *pte;
+
+ pte = memblock_alloc(PAGE_SIZE, PAGE_SIZE);
+@@ -216,7 +216,7 @@ void __init __set_fixmap(enum fixed_addresses idx,
+ BUG_ON(idx <= FIX_HOLE || idx >= __end_of_fixed_addresses);
+
+ ptep = populate_kernel_pte(addr);
+- if (!pte_none(*ptep)) {
++ if (!pte_none(ptep_get(ptep))) {
+ pte_ERROR(*ptep);
+ return;
+ }
+diff --git a/arch/loongarch/mm/kasan_init.c b/arch/loongarch/mm/kasan_init.c
+index c608adc998458..427d6b1aec09e 100644
+--- a/arch/loongarch/mm/kasan_init.c
++++ b/arch/loongarch/mm/kasan_init.c
+@@ -105,7 +105,7 @@ static phys_addr_t __init kasan_alloc_zeroed_page(int node)
+
+ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node, bool early)
+ {
+- if (__pmd_none(early, READ_ONCE(*pmdp))) {
++ if (__pmd_none(early, pmdp_get(pmdp))) {
+ phys_addr_t pte_phys = early ?
+ __pa_symbol(kasan_early_shadow_pte) : kasan_alloc_zeroed_page(node);
+ if (!early)
+@@ -118,7 +118,7 @@ static pte_t *__init kasan_pte_offset(pmd_t *pmdp, unsigned long addr, int node,
+
+ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node, bool early)
+ {
+- if (__pud_none(early, READ_ONCE(*pudp))) {
++ if (__pud_none(early, pudp_get(pudp))) {
+ phys_addr_t pmd_phys = early ?
+ __pa_symbol(kasan_early_shadow_pmd) : kasan_alloc_zeroed_page(node);
+ if (!early)
+@@ -131,7 +131,7 @@ static pmd_t *__init kasan_pmd_offset(pud_t *pudp, unsigned long addr, int node,
+
+ static pud_t *__init kasan_pud_offset(p4d_t *p4dp, unsigned long addr, int node, bool early)
+ {
+- if (__p4d_none(early, READ_ONCE(*p4dp))) {
++ if (__p4d_none(early, p4dp_get(p4dp))) {
+ phys_addr_t pud_phys = early ?
+ __pa_symbol(kasan_early_shadow_pud) : kasan_alloc_zeroed_page(node);
+ if (!early)
+@@ -154,7 +154,7 @@ static void __init kasan_pte_populate(pmd_t *pmdp, unsigned long addr,
+ : kasan_alloc_zeroed_page(node);
+ next = addr + PAGE_SIZE;
+ set_pte(ptep, pfn_pte(__phys_to_pfn(page_phys), PAGE_KERNEL));
+- } while (ptep++, addr = next, addr != end && __pte_none(early, READ_ONCE(*ptep)));
++ } while (ptep++, addr = next, addr != end && __pte_none(early, ptep_get(ptep)));
+ }
+
+ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
+@@ -166,7 +166,7 @@ static void __init kasan_pmd_populate(pud_t *pudp, unsigned long addr,
+ do {
+ next = pmd_addr_end(addr, end);
+ kasan_pte_populate(pmdp, addr, next, node, early);
+- } while (pmdp++, addr = next, addr != end && __pmd_none(early, READ_ONCE(*pmdp)));
++ } while (pmdp++, addr = next, addr != end && __pmd_none(early, pmdp_get(pmdp)));
+ }
+
+ static void __init kasan_pud_populate(p4d_t *p4dp, unsigned long addr,
+diff --git a/arch/loongarch/mm/pgtable.c b/arch/loongarch/mm/pgtable.c
+index bda018150000e..eb6a29b491a72 100644
+--- a/arch/loongarch/mm/pgtable.c
++++ b/arch/loongarch/mm/pgtable.c
+@@ -128,7 +128,7 @@ pmd_t mk_pmd(struct page *page, pgprot_t prot)
+ void set_pmd_at(struct mm_struct *mm, unsigned long addr,
+ pmd_t *pmdp, pmd_t pmd)
+ {
+- *pmdp = pmd;
++ WRITE_ONCE(*pmdp, pmd);
+ flush_tlb_all();
+ }
+
+diff --git a/arch/mips/kernel/cevt-r4k.c b/arch/mips/kernel/cevt-r4k.c
+index 368e8475870f0..5f6e9e2ebbdbb 100644
+--- a/arch/mips/kernel/cevt-r4k.c
++++ b/arch/mips/kernel/cevt-r4k.c
+@@ -303,13 +303,6 @@ int r4k_clockevent_init(void)
+ if (!c0_compare_int_usable())
+ return -ENXIO;
+
+- /*
+- * With vectored interrupts things are getting platform specific.
+- * get_c0_compare_int is a hook to allow a platform to return the
+- * interrupt number of its liking.
+- */
+- irq = get_c0_compare_int();
+-
+ cd = &per_cpu(mips_clockevent_device, cpu);
+
+ cd->name = "MIPS";
+@@ -320,7 +313,6 @@ int r4k_clockevent_init(void)
+ min_delta = calculate_min_delta();
+
+ cd->rating = 300;
+- cd->irq = irq;
+ cd->cpumask = cpumask_of(cpu);
+ cd->set_next_event = mips_next_event;
+ cd->event_handler = mips_event_handler;
+@@ -332,6 +324,13 @@ int r4k_clockevent_init(void)
+
+ cp0_timer_irq_installed = 1;
+
++ /*
++ * With vectored interrupts things are getting platform specific.
++ * get_c0_compare_int is a hook to allow a platform to return the
++ * interrupt number of its liking.
++ */
++ irq = get_c0_compare_int();
++
+ if (request_irq(irq, c0_compare_interrupt, flags, "timer",
+ c0_compare_interrupt))
+ pr_err("Failed to request irq %d (timer)\n", irq);
+diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
+index 34d91cb8b2590..96970fa75e4ac 100644
+--- a/arch/parisc/mm/init.c
++++ b/arch/parisc/mm/init.c
+@@ -459,7 +459,6 @@ void free_initmem(void)
+ unsigned long kernel_end = (unsigned long)&_end;
+
+ /* Remap kernel text and data, but do not touch init section yet. */
+- kernel_set_to_readonly = true;
+ map_pages(init_end, __pa(init_end), kernel_end - init_end,
+ PAGE_KERNEL, 0);
+
+@@ -493,11 +492,18 @@ void free_initmem(void)
+ #ifdef CONFIG_STRICT_KERNEL_RWX
+ void mark_rodata_ro(void)
+ {
+- /* rodata memory was already mapped with KERNEL_RO access rights by
+- pagetable_init() and map_pages(). No need to do additional stuff here */
+- unsigned long roai_size = __end_ro_after_init - __start_ro_after_init;
++ unsigned long start = (unsigned long) &__start_rodata;
++ unsigned long end = (unsigned long) &__end_rodata;
++
++ pr_info("Write protecting the kernel read-only data: %luk\n",
++ (end - start) >> 10);
++
++ kernel_set_to_readonly = true;
++ map_pages(start, __pa(start), end - start, PAGE_KERNEL, 0);
+
+- pr_info("Write protected read-only-after-init data: %luk\n", roai_size >> 10);
++ /* force the kernel to see the new page table entries */
++ flush_cache_all();
++ flush_tlb_all();
+ }
+ #endif
+
+diff --git a/arch/powerpc/include/asm/nohash/mmu-e500.h b/arch/powerpc/include/asm/nohash/mmu-e500.h
+index 6ddced0415cb5..7dc24b8632d7c 100644
+--- a/arch/powerpc/include/asm/nohash/mmu-e500.h
++++ b/arch/powerpc/include/asm/nohash/mmu-e500.h
+@@ -303,8 +303,7 @@ extern unsigned long linear_map_top;
+ extern int book3e_htw_mode;
+
+ #define PPC_HTW_NONE 0
+-#define PPC_HTW_IBM 1
+-#define PPC_HTW_E6500 2
++#define PPC_HTW_E6500 1
+
+ /*
+ * 64-bit booke platforms don't load the tlb in the tlb miss handler code.
+diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
+index 8064d9c3de862..f7e86e09c49fa 100644
+--- a/arch/powerpc/kernel/rtas.c
++++ b/arch/powerpc/kernel/rtas.c
+@@ -19,6 +19,7 @@
+ #include <linux/lockdep.h>
+ #include <linux/memblock.h>
+ #include <linux/mutex.h>
++#include <linux/nospec.h>
+ #include <linux/of.h>
+ #include <linux/of_fdt.h>
+ #include <linux/reboot.h>
+@@ -1916,6 +1917,9 @@ SYSCALL_DEFINE1(rtas, struct rtas_args __user *, uargs)
+ || nargs + nret > ARRAY_SIZE(args.args))
+ return -EINVAL;
+
++ nargs = array_index_nospec(nargs, ARRAY_SIZE(args.args));
++ nret = array_index_nospec(nret, ARRAY_SIZE(args.args) - nargs);
++
+ /* Copy in args. */
+ if (copy_from_user(args.args, uargs->args,
+ nargs * sizeof(rtas_arg_t)) != 0)
+diff --git a/arch/powerpc/kernel/vdso/vdso32.lds.S b/arch/powerpc/kernel/vdso/vdso32.lds.S
+index 426e1ccc6971a..8f57107000a24 100644
+--- a/arch/powerpc/kernel/vdso/vdso32.lds.S
++++ b/arch/powerpc/kernel/vdso/vdso32.lds.S
+@@ -74,6 +74,8 @@ SECTIONS
+ .got : { *(.got) } :text
+ .plt : { *(.plt) }
+
++ .rela.dyn : { *(.rela .rela*) }
++
+ _end = .;
+ __end = .;
+ PROVIDE(end = .);
+@@ -87,7 +89,7 @@ SECTIONS
+ *(.branch_lt)
+ *(.data .data.* .gnu.linkonce.d.* .sdata*)
+ *(.bss .sbss .dynbss .dynsbss)
+- *(.got1 .glink .iplt .rela*)
++ *(.got1 .glink .iplt)
+ }
+ }
+
+diff --git a/arch/powerpc/kernel/vdso/vdso64.lds.S b/arch/powerpc/kernel/vdso/vdso64.lds.S
+index bda6c8cdd459c..400819258c06b 100644
+--- a/arch/powerpc/kernel/vdso/vdso64.lds.S
++++ b/arch/powerpc/kernel/vdso/vdso64.lds.S
+@@ -69,7 +69,7 @@ SECTIONS
+ .eh_frame_hdr : { *(.eh_frame_hdr) } :text :eh_frame_hdr
+ .eh_frame : { KEEP (*(.eh_frame)) } :text
+ .gcc_except_table : { *(.gcc_except_table) }
+- .rela.dyn ALIGN(8) : { *(.rela.dyn) }
++ .rela.dyn ALIGN(8) : { *(.rela .rela*) }
+
+ .got ALIGN(8) : { *(.got .toc) }
+
+@@ -86,7 +86,7 @@ SECTIONS
+ *(.data .data.* .gnu.linkonce.d.* .sdata*)
+ *(.bss .sbss .dynbss .dynsbss)
+ *(.opd)
+- *(.glink .iplt .plt .rela*)
++ *(.glink .iplt .plt)
+ }
+ }
+
+diff --git a/arch/powerpc/lib/qspinlock.c b/arch/powerpc/lib/qspinlock.c
+index 5de4dd549f6ec..bcc7e4dff8c30 100644
+--- a/arch/powerpc/lib/qspinlock.c
++++ b/arch/powerpc/lib/qspinlock.c
+@@ -697,7 +697,15 @@ static __always_inline void queued_spin_lock_mcs_queue(struct qspinlock *lock, b
+ }
+
+ release:
+- qnodesp->count--; /* release the node */
++ /*
++ * Clear the lock before releasing the node, as another CPU might see stale
++ * values if an interrupt occurs after we increment qnodesp->count
++ * but before node->lock is initialized. The barrier ensures that
++ * there are no further stores to the node after it has been released.
++ */
++ node->lock = NULL;
++ barrier();
++ qnodesp->count--;
+ }
+
+ void queued_spin_lock_slowpath(struct qspinlock *lock)
+diff --git a/arch/powerpc/mm/nohash/Makefile b/arch/powerpc/mm/nohash/Makefile
+index b3f0498dd42f3..90e846f0c46c7 100644
+--- a/arch/powerpc/mm/nohash/Makefile
++++ b/arch/powerpc/mm/nohash/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+
+ obj-y += mmu_context.o tlb.o tlb_low.o kup.o
+-obj-$(CONFIG_PPC_BOOK3E_64) += tlb_low_64e.o book3e_pgtable.o
++obj-$(CONFIG_PPC_BOOK3E_64) += tlb_64e.o tlb_low_64e.o book3e_pgtable.o
+ obj-$(CONFIG_40x) += 40x.o
+ obj-$(CONFIG_44x) += 44x.o
+ obj-$(CONFIG_PPC_8xx) += 8xx.o
+diff --git a/arch/powerpc/mm/nohash/tlb.c b/arch/powerpc/mm/nohash/tlb.c
+index 5ffa0af4328af..f57dc721d0636 100644
+--- a/arch/powerpc/mm/nohash/tlb.c
++++ b/arch/powerpc/mm/nohash/tlb.c
+@@ -110,28 +110,6 @@ struct mmu_psize_def mmu_psize_defs[MMU_PAGE_COUNT] = {
+ };
+ #endif
+
+-/* The variables below are currently only used on 64-bit Book3E
+- * though this will probably be made common with other nohash
+- * implementations at some point
+- */
+-#ifdef CONFIG_PPC64
+-
+-int mmu_pte_psize; /* Page size used for PTE pages */
+-int mmu_vmemmap_psize; /* Page size used for the virtual mem map */
+-int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */
+-unsigned long linear_map_top; /* Top of linear mapping */
+-
+-
+-/*
+- * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
+- * exceptions. This is used for bolted and e6500 TLB miss handlers which
+- * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
+- * this is set to zero.
+- */
+-int extlb_level_exc;
+-
+-#endif /* CONFIG_PPC64 */
+-
+ #ifdef CONFIG_PPC_E500
+ /* next_tlbcam_idx is used to round-robin tlbcam entry assignment */
+ DEFINE_PER_CPU(int, next_tlbcam_idx);
+@@ -358,381 +336,7 @@ void tlb_flush(struct mmu_gather *tlb)
+ flush_tlb_mm(tlb->mm);
+ }
+
+-/*
+- * Below are functions specific to the 64-bit variant of Book3E though that
+- * may change in the future
+- */
+-
+-#ifdef CONFIG_PPC64
+-
+-/*
+- * Handling of virtual linear page tables or indirect TLB entries
+- * flushing when PTE pages are freed
+- */
+-void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
+-{
+- int tsize = mmu_psize_defs[mmu_pte_psize].enc;
+-
+- if (book3e_htw_mode != PPC_HTW_NONE) {
+- unsigned long start = address & PMD_MASK;
+- unsigned long end = address + PMD_SIZE;
+- unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
+-
+- /* This isn't the most optimal, ideally we would factor out the
+- * while preempt & CPU mask mucking around, or even the IPI but
+- * it will do for now
+- */
+- while (start < end) {
+- __flush_tlb_page(tlb->mm, start, tsize, 1);
+- start += size;
+- }
+- } else {
+- unsigned long rmask = 0xf000000000000000ul;
+- unsigned long rid = (address & rmask) | 0x1000000000000000ul;
+- unsigned long vpte = address & ~rmask;
+-
+- vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
+- vpte |= rid;
+- __flush_tlb_page(tlb->mm, vpte, tsize, 0);
+- }
+-}
+-
+-static void __init setup_page_sizes(void)
+-{
+- unsigned int tlb0cfg;
+- unsigned int tlb0ps;
+- unsigned int eptcfg;
+- int i, psize;
+-
+-#ifdef CONFIG_PPC_E500
+- unsigned int mmucfg = mfspr(SPRN_MMUCFG);
+- int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E);
+-
+- if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
+- unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
+- unsigned int min_pg, max_pg;
+-
+- min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
+- max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
+-
+- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+- struct mmu_psize_def *def;
+- unsigned int shift;
+-
+- def = &mmu_psize_defs[psize];
+- shift = def->shift;
+-
+- if (shift == 0 || shift & 1)
+- continue;
+-
+- /* adjust to be in terms of 4^shift Kb */
+- shift = (shift - 10) >> 1;
+-
+- if ((shift >= min_pg) && (shift <= max_pg))
+- def->flags |= MMU_PAGE_SIZE_DIRECT;
+- }
+-
+- goto out;
+- }
+-
+- if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
+- u32 tlb1cfg, tlb1ps;
+-
+- tlb0cfg = mfspr(SPRN_TLB0CFG);
+- tlb1cfg = mfspr(SPRN_TLB1CFG);
+- tlb1ps = mfspr(SPRN_TLB1PS);
+- eptcfg = mfspr(SPRN_EPTCFG);
+-
+- if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
+- book3e_htw_mode = PPC_HTW_E6500;
+-
+- /*
+- * We expect 4K subpage size and unrestricted indirect size.
+- * The lack of a restriction on indirect size is a Freescale
+- * extension, indicated by PSn = 0 but SPSn != 0.
+- */
+- if (eptcfg != 2)
+- book3e_htw_mode = PPC_HTW_NONE;
+-
+- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+- struct mmu_psize_def *def = &mmu_psize_defs[psize];
+-
+- if (!def->shift)
+- continue;
+-
+- if (tlb1ps & (1U << (def->shift - 10))) {
+- def->flags |= MMU_PAGE_SIZE_DIRECT;
+-
+- if (book3e_htw_mode && psize == MMU_PAGE_2M)
+- def->flags |= MMU_PAGE_SIZE_INDIRECT;
+- }
+- }
+-
+- goto out;
+- }
+-#endif
+-
+- tlb0cfg = mfspr(SPRN_TLB0CFG);
+- tlb0ps = mfspr(SPRN_TLB0PS);
+- eptcfg = mfspr(SPRN_EPTCFG);
+-
+- /* Look for supported direct sizes */
+- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+- struct mmu_psize_def *def = &mmu_psize_defs[psize];
+-
+- if (tlb0ps & (1U << (def->shift - 10)))
+- def->flags |= MMU_PAGE_SIZE_DIRECT;
+- }
+-
+- /* Indirect page sizes supported ? */
+- if ((tlb0cfg & TLBnCFG_IND) == 0 ||
+- (tlb0cfg & TLBnCFG_PT) == 0)
+- goto out;
+-
+- book3e_htw_mode = PPC_HTW_IBM;
+-
+- /* Now, we only deal with one IND page size for each
+- * direct size. Hopefully all implementations today are
+- * unambiguous, but we might want to be careful in the
+- * future.
+- */
+- for (i = 0; i < 3; i++) {
+- unsigned int ps, sps;
+-
+- sps = eptcfg & 0x1f;
+- eptcfg >>= 5;
+- ps = eptcfg & 0x1f;
+- eptcfg >>= 5;
+- if (!ps || !sps)
+- continue;
+- for (psize = 0; psize < MMU_PAGE_COUNT; psize++) {
+- struct mmu_psize_def *def = &mmu_psize_defs[psize];
+-
+- if (ps == (def->shift - 10))
+- def->flags |= MMU_PAGE_SIZE_INDIRECT;
+- if (sps == (def->shift - 10))
+- def->ind = ps + 10;
+- }
+- }
+-
+-out:
+- /* Cleanup array and print summary */
+- pr_info("MMU: Supported page sizes\n");
+- for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
+- struct mmu_psize_def *def = &mmu_psize_defs[psize];
+- const char *__page_type_names[] = {
+- "unsupported",
+- "direct",
+- "indirect",
+- "direct & indirect"
+- };
+- if (def->flags == 0) {
+- def->shift = 0;
+- continue;
+- }
+- pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10),
+- __page_type_names[def->flags & 0x3]);
+- }
+-}
+-
+-static void __init setup_mmu_htw(void)
+-{
+- /*
+- * If we want to use HW tablewalk, enable it by patching the TLB miss
+- * handlers to branch to the one dedicated to it.
+- */
+-
+- switch (book3e_htw_mode) {
+- case PPC_HTW_IBM:
+- patch_exception(0x1c0, exc_data_tlb_miss_htw_book3e);
+- patch_exception(0x1e0, exc_instruction_tlb_miss_htw_book3e);
+- break;
+-#ifdef CONFIG_PPC_E500
+- case PPC_HTW_E6500:
+- extlb_level_exc = EX_TLB_SIZE;
+- patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
+- patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
+- break;
+-#endif
+- }
+- pr_info("MMU: Book3E HW tablewalk %s\n",
+- book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
+-}
+-
+-/*
+- * Early initialization of the MMU TLB code
+- */
+-static void early_init_this_mmu(void)
+-{
+- unsigned int mas4;
+-
+- /* Set MAS4 based on page table setting */
+-
+- mas4 = 0x4 << MAS4_WIMGED_SHIFT;
+- switch (book3e_htw_mode) {
+- case PPC_HTW_E6500:
+- mas4 |= MAS4_INDD;
+- mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
+- mas4 |= MAS4_TLBSELD(1);
+- mmu_pte_psize = MMU_PAGE_2M;
+- break;
+-
+- case PPC_HTW_IBM:
+- mas4 |= MAS4_INDD;
+- mas4 |= BOOK3E_PAGESZ_1M << MAS4_TSIZED_SHIFT;
+- mmu_pte_psize = MMU_PAGE_1M;
+- break;
+-
+- case PPC_HTW_NONE:
+- mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
+- mmu_pte_psize = mmu_virtual_psize;
+- break;
+- }
+- mtspr(SPRN_MAS4, mas4);
+-
+-#ifdef CONFIG_PPC_E500
+- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+- unsigned int num_cams;
+- bool map = true;
+-
+- /* use a quarter of the TLBCAM for bolted linear map */
+- num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+-
+- /*
+- * Only do the mapping once per core, or else the
+- * transient mapping would cause problems.
+- */
+-#ifdef CONFIG_SMP
+- if (hweight32(get_tensr()) > 1)
+- map = false;
+-#endif
+-
+- if (map)
+- linear_map_top = map_mem_in_cams(linear_map_top,
+- num_cams, false, true);
+- }
+-#endif
+-
+- /* A sync won't hurt us after mucking around with
+- * the MMU configuration
+- */
+- mb();
+-}
+-
+-static void __init early_init_mmu_global(void)
+-{
+- /* XXX This should be decided at runtime based on supported
+- * page sizes in the TLB, but for now let's assume 16M is
+- * always there and a good fit (which it probably is)
+- *
+- * Freescale booke only supports 4K pages in TLB0, so use that.
+- */
+- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
+- mmu_vmemmap_psize = MMU_PAGE_4K;
+- else
+- mmu_vmemmap_psize = MMU_PAGE_16M;
+-
+- /* XXX This code only checks for TLB 0 capabilities and doesn't
+- * check what page size combos are supported by the HW. It
+- * also doesn't handle the case where a separate array holds
+- * the IND entries from the array loaded by the PT.
+- */
+- /* Look for supported page sizes */
+- setup_page_sizes();
+-
+- /* Look for HW tablewalk support */
+- setup_mmu_htw();
+-
+-#ifdef CONFIG_PPC_E500
+- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+- if (book3e_htw_mode == PPC_HTW_NONE) {
+- extlb_level_exc = EX_TLB_SIZE;
+- patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
+- patch_exception(0x1e0,
+- exc_instruction_tlb_miss_bolted_book3e);
+- }
+- }
+-#endif
+-
+- /* Set the global containing the top of the linear mapping
+- * for use by the TLB miss code
+- */
+- linear_map_top = memblock_end_of_DRAM();
+-
+- ioremap_bot = IOREMAP_BASE;
+-}
+-
+-static void __init early_mmu_set_memory_limit(void)
+-{
+-#ifdef CONFIG_PPC_E500
+- if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+- /*
+- * Limit memory so we dont have linear faults.
+- * Unlike memblock_set_current_limit, which limits
+- * memory available during early boot, this permanently
+- * reduces the memory available to Linux. We need to
+- * do this because highmem is not supported on 64-bit.
+- */
+- memblock_enforce_memory_limit(linear_map_top);
+- }
+-#endif
+-
+- memblock_set_current_limit(linear_map_top);
+-}
+-
+-/* boot cpu only */
+-void __init early_init_mmu(void)
+-{
+- early_init_mmu_global();
+- early_init_this_mmu();
+- early_mmu_set_memory_limit();
+-}
+-
+-void early_init_mmu_secondary(void)
+-{
+- early_init_this_mmu();
+-}
+-
+-void setup_initial_memory_limit(phys_addr_t first_memblock_base,
+- phys_addr_t first_memblock_size)
+-{
+- /* On non-FSL Embedded 64-bit, we adjust the RMA size to match
+- * the bolted TLB entry. We know for now that only 1G
+- * entries are supported though that may eventually
+- * change.
+- *
+- * on FSL Embedded 64-bit, usually all RAM is bolted, but with
+- * unusual memory sizes it's possible for some RAM to not be mapped
+- * (such RAM is not used at all by Linux, since we don't support
+- * highmem on 64-bit). We limit ppc64_rma_size to what would be
+- * mappable if this memblock is the only one. Additional memblocks
+- * can only increase, not decrease, the amount that ends up getting
+- * mapped. We still limit max to 1G even if we'll eventually map
+- * more. This is due to what the early init code is set up to do.
+- *
+- * We crop it to the size of the first MEMBLOCK to
+- * avoid going over total available memory just in case...
+- */
+-#ifdef CONFIG_PPC_E500
+- if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
+- unsigned long linear_sz;
+- unsigned int num_cams;
+-
+- /* use a quarter of the TLBCAM for bolted linear map */
+- num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
+-
+- linear_sz = map_mem_in_cams(first_memblock_size, num_cams,
+- true, true);
+-
+- ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
+- } else
+-#endif
+- ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
+-
+- /* Finally limit subsequent allocations */
+- memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
+-}
+-#else /* ! CONFIG_PPC64 */
++#ifndef CONFIG_PPC64
+ void __init early_init_mmu(void)
+ {
+ unsigned long root = of_get_flat_dt_root();
+diff --git a/arch/powerpc/mm/nohash/tlb_64e.c b/arch/powerpc/mm/nohash/tlb_64e.c
+new file mode 100644
+index 0000000000000..b6af3ec4d001d
+--- /dev/null
++++ b/arch/powerpc/mm/nohash/tlb_64e.c
+@@ -0,0 +1,361 @@
++// SPDX-License-Identifier: GPL-2.0-or-later
++/*
++ * Copyright 2008,2009 Ben Herrenschmidt <benh@kernel.crashing.org>
++ * IBM Corp.
++ *
++ * Derived from arch/ppc/mm/init.c:
++ * Copyright (C) 1995-1996 Gary Thomas (gdt@linuxppc.org)
++ *
++ * Modifications by Paul Mackerras (PowerMac) (paulus@cs.anu.edu.au)
++ * and Cort Dougan (PReP) (cort@cs.nmt.edu)
++ * Copyright (C) 1996 Paul Mackerras
++ *
++ * Derived from "arch/i386/mm/init.c"
++ * Copyright (C) 1991, 1992, 1993, 1994 Linus Torvalds
++ */
++
++#include <linux/kernel.h>
++#include <linux/export.h>
++#include <linux/mm.h>
++#include <linux/init.h>
++#include <linux/pagemap.h>
++#include <linux/memblock.h>
++
++#include <asm/pgalloc.h>
++#include <asm/tlbflush.h>
++#include <asm/tlb.h>
++#include <asm/code-patching.h>
++#include <asm/cputhreads.h>
++
++#include <mm/mmu_decl.h>
++
++/* The variables below are currently only used on 64-bit Book3E
++ * though this will probably be made common with other nohash
++ * implementations at some point
++ */
++static int mmu_pte_psize; /* Page size used for PTE pages */
++int mmu_vmemmap_psize; /* Page size used for the virtual mem map */
++int book3e_htw_mode; /* HW tablewalk? Value is PPC_HTW_* */
++unsigned long linear_map_top; /* Top of linear mapping */
++
++
++/*
++ * Number of bytes to add to SPRN_SPRG_TLB_EXFRAME on crit/mcheck/debug
++ * exceptions. This is used for bolted and e6500 TLB miss handlers which
++ * do not modify this SPRG in the TLB miss code; for other TLB miss handlers,
++ * this is set to zero.
++ */
++int extlb_level_exc;
++
++/*
++ * Handling of virtual linear page tables or indirect TLB entries
++ * flushing when PTE pages are freed
++ */
++void tlb_flush_pgtable(struct mmu_gather *tlb, unsigned long address)
++{
++ int tsize = mmu_psize_defs[mmu_pte_psize].enc;
++
++ if (book3e_htw_mode != PPC_HTW_NONE) {
++ unsigned long start = address & PMD_MASK;
++ unsigned long end = address + PMD_SIZE;
++ unsigned long size = 1UL << mmu_psize_defs[mmu_pte_psize].shift;
++
++ /* This isn't the most optimal, ideally we would factor out the
++ * while preempt & CPU mask mucking around, or even the IPI but
++ * it will do for now
++ */
++ while (start < end) {
++ __flush_tlb_page(tlb->mm, start, tsize, 1);
++ start += size;
++ }
++ } else {
++ unsigned long rmask = 0xf000000000000000ul;
++ unsigned long rid = (address & rmask) | 0x1000000000000000ul;
++ unsigned long vpte = address & ~rmask;
++
++ vpte = (vpte >> (PAGE_SHIFT - 3)) & ~0xffful;
++ vpte |= rid;
++ __flush_tlb_page(tlb->mm, vpte, tsize, 0);
++ }
++}
++
++static void __init setup_page_sizes(void)
++{
++ unsigned int tlb0cfg;
++ unsigned int eptcfg;
++ int psize;
++
++#ifdef CONFIG_PPC_E500
++ unsigned int mmucfg = mfspr(SPRN_MMUCFG);
++ int fsl_mmu = mmu_has_feature(MMU_FTR_TYPE_FSL_E);
++
++ if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V1) {
++ unsigned int tlb1cfg = mfspr(SPRN_TLB1CFG);
++ unsigned int min_pg, max_pg;
++
++ min_pg = (tlb1cfg & TLBnCFG_MINSIZE) >> TLBnCFG_MINSIZE_SHIFT;
++ max_pg = (tlb1cfg & TLBnCFG_MAXSIZE) >> TLBnCFG_MAXSIZE_SHIFT;
++
++ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
++ struct mmu_psize_def *def;
++ unsigned int shift;
++
++ def = &mmu_psize_defs[psize];
++ shift = def->shift;
++
++ if (shift == 0 || shift & 1)
++ continue;
++
++ /* adjust to be in terms of 4^shift Kb */
++ shift = (shift - 10) >> 1;
++
++ if ((shift >= min_pg) && (shift <= max_pg))
++ def->flags |= MMU_PAGE_SIZE_DIRECT;
++ }
++
++ goto out;
++ }
++
++ if (fsl_mmu && (mmucfg & MMUCFG_MAVN) == MMUCFG_MAVN_V2) {
++ u32 tlb1cfg, tlb1ps;
++
++ tlb0cfg = mfspr(SPRN_TLB0CFG);
++ tlb1cfg = mfspr(SPRN_TLB1CFG);
++ tlb1ps = mfspr(SPRN_TLB1PS);
++ eptcfg = mfspr(SPRN_EPTCFG);
++
++ if ((tlb1cfg & TLBnCFG_IND) && (tlb0cfg & TLBnCFG_PT))
++ book3e_htw_mode = PPC_HTW_E6500;
++
++ /*
++ * We expect 4K subpage size and unrestricted indirect size.
++ * The lack of a restriction on indirect size is a Freescale
++ * extension, indicated by PSn = 0 but SPSn != 0.
++ */
++ if (eptcfg != 2)
++ book3e_htw_mode = PPC_HTW_NONE;
++
++ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
++ struct mmu_psize_def *def = &mmu_psize_defs[psize];
++
++ if (!def->shift)
++ continue;
++
++ if (tlb1ps & (1U << (def->shift - 10))) {
++ def->flags |= MMU_PAGE_SIZE_DIRECT;
++
++ if (book3e_htw_mode && psize == MMU_PAGE_2M)
++ def->flags |= MMU_PAGE_SIZE_INDIRECT;
++ }
++ }
++
++ goto out;
++ }
++#endif
++out:
++ /* Cleanup array and print summary */
++ pr_info("MMU: Supported page sizes\n");
++ for (psize = 0; psize < MMU_PAGE_COUNT; ++psize) {
++ struct mmu_psize_def *def = &mmu_psize_defs[psize];
++ const char *__page_type_names[] = {
++ "unsupported",
++ "direct",
++ "indirect",
++ "direct & indirect"
++ };
++ if (def->flags == 0) {
++ def->shift = 0;
++ continue;
++ }
++ pr_info(" %8ld KB as %s\n", 1ul << (def->shift - 10),
++ __page_type_names[def->flags & 0x3]);
++ }
++}
++
++static void __init setup_mmu_htw(void)
++{
++ /*
++ * If we want to use HW tablewalk, enable it by patching the TLB miss
++ * handlers to branch to the one dedicated to it.
++ */
++
++ switch (book3e_htw_mode) {
++#ifdef CONFIG_PPC_E500
++ case PPC_HTW_E6500:
++ extlb_level_exc = EX_TLB_SIZE;
++ patch_exception(0x1c0, exc_data_tlb_miss_e6500_book3e);
++ patch_exception(0x1e0, exc_instruction_tlb_miss_e6500_book3e);
++ break;
++#endif
++ }
++ pr_info("MMU: Book3E HW tablewalk %s\n",
++ book3e_htw_mode != PPC_HTW_NONE ? "enabled" : "not supported");
++}
++
++/*
++ * Early initialization of the MMU TLB code
++ */
++static void early_init_this_mmu(void)
++{
++ unsigned int mas4;
++
++ /* Set MAS4 based on page table setting */
++
++ mas4 = 0x4 << MAS4_WIMGED_SHIFT;
++ switch (book3e_htw_mode) {
++ case PPC_HTW_E6500:
++ mas4 |= MAS4_INDD;
++ mas4 |= BOOK3E_PAGESZ_2M << MAS4_TSIZED_SHIFT;
++ mas4 |= MAS4_TLBSELD(1);
++ mmu_pte_psize = MMU_PAGE_2M;
++ break;
++
++ case PPC_HTW_NONE:
++ mas4 |= BOOK3E_PAGESZ_4K << MAS4_TSIZED_SHIFT;
++ mmu_pte_psize = mmu_virtual_psize;
++ break;
++ }
++ mtspr(SPRN_MAS4, mas4);
++
++#ifdef CONFIG_PPC_E500
++ if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
++ unsigned int num_cams;
++ bool map = true;
++
++ /* use a quarter of the TLBCAM for bolted linear map */
++ num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
++
++ /*
++ * Only do the mapping once per core, or else the
++ * transient mapping would cause problems.
++ */
++#ifdef CONFIG_SMP
++ if (hweight32(get_tensr()) > 1)
++ map = false;
++#endif
++
++ if (map)
++ linear_map_top = map_mem_in_cams(linear_map_top,
++ num_cams, false, true);
++ }
++#endif
++
++ /* A sync won't hurt us after mucking around with
++ * the MMU configuration
++ */
++ mb();
++}
++
++static void __init early_init_mmu_global(void)
++{
++ /* XXX This should be decided at runtime based on supported
++ * page sizes in the TLB, but for now let's assume 16M is
++ * always there and a good fit (which it probably is)
++ *
++ * Freescale booke only supports 4K pages in TLB0, so use that.
++ */
++ if (mmu_has_feature(MMU_FTR_TYPE_FSL_E))
++ mmu_vmemmap_psize = MMU_PAGE_4K;
++ else
++ mmu_vmemmap_psize = MMU_PAGE_16M;
++
++ /* XXX This code only checks for TLB 0 capabilities and doesn't
++ * check what page size combos are supported by the HW. It
++ * also doesn't handle the case where a separate array holds
++ * the IND entries from the array loaded by the PT.
++ */
++ /* Look for supported page sizes */
++ setup_page_sizes();
++
++ /* Look for HW tablewalk support */
++ setup_mmu_htw();
++
++#ifdef CONFIG_PPC_E500
++ if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
++ if (book3e_htw_mode == PPC_HTW_NONE) {
++ extlb_level_exc = EX_TLB_SIZE;
++ patch_exception(0x1c0, exc_data_tlb_miss_bolted_book3e);
++ patch_exception(0x1e0,
++ exc_instruction_tlb_miss_bolted_book3e);
++ }
++ }
++#endif
++
++ /* Set the global containing the top of the linear mapping
++ * for use by the TLB miss code
++ */
++ linear_map_top = memblock_end_of_DRAM();
++
++ ioremap_bot = IOREMAP_BASE;
++}
++
++static void __init early_mmu_set_memory_limit(void)
++{
++#ifdef CONFIG_PPC_E500
++ if (mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
++ /*
++ * Limit memory so we dont have linear faults.
++ * Unlike memblock_set_current_limit, which limits
++ * memory available during early boot, this permanently
++ * reduces the memory available to Linux. We need to
++ * do this because highmem is not supported on 64-bit.
++ */
++ memblock_enforce_memory_limit(linear_map_top);
++ }
++#endif
++
++ memblock_set_current_limit(linear_map_top);
++}
++
++/* boot cpu only */
++void __init early_init_mmu(void)
++{
++ early_init_mmu_global();
++ early_init_this_mmu();
++ early_mmu_set_memory_limit();
++}
++
++void early_init_mmu_secondary(void)
++{
++ early_init_this_mmu();
++}
++
++void setup_initial_memory_limit(phys_addr_t first_memblock_base,
++ phys_addr_t first_memblock_size)
++{
++ /* On non-FSL Embedded 64-bit, we adjust the RMA size to match
++ * the bolted TLB entry. We know for now that only 1G
++ * entries are supported though that may eventually
++ * change.
++ *
++ * on FSL Embedded 64-bit, usually all RAM is bolted, but with
++ * unusual memory sizes it's possible for some RAM to not be mapped
++ * (such RAM is not used at all by Linux, since we don't support
++ * highmem on 64-bit). We limit ppc64_rma_size to what would be
++ * mappable if this memblock is the only one. Additional memblocks
++ * can only increase, not decrease, the amount that ends up getting
++ * mapped. We still limit max to 1G even if we'll eventually map
++ * more. This is due to what the early init code is set up to do.
++ *
++ * We crop it to the size of the first MEMBLOCK to
++ * avoid going over total available memory just in case...
++ */
++#ifdef CONFIG_PPC_E500
++ if (early_mmu_has_feature(MMU_FTR_TYPE_FSL_E)) {
++ unsigned long linear_sz;
++ unsigned int num_cams;
++
++ /* use a quarter of the TLBCAM for bolted linear map */
++ num_cams = (mfspr(SPRN_TLB1CFG) & TLBnCFG_N_ENTRY) / 4;
++
++ linear_sz = map_mem_in_cams(first_memblock_size, num_cams,
++ true, true);
++
++ ppc64_rma_size = min_t(u64, linear_sz, 0x40000000);
++ } else
++#endif
++ ppc64_rma_size = min_t(u64, first_memblock_size, 0x40000000);
++
++ /* Finally limit subsequent allocations */
++ memblock_set_current_limit(first_memblock_base + ppc64_rma_size);
++}
+diff --git a/arch/powerpc/mm/nohash/tlb_low_64e.S b/arch/powerpc/mm/nohash/tlb_low_64e.S
+index 7e0b8fe1c2797..b0eb3f7eaed14 100644
+--- a/arch/powerpc/mm/nohash/tlb_low_64e.S
++++ b/arch/powerpc/mm/nohash/tlb_low_64e.S
+@@ -893,201 +893,6 @@ virt_page_table_tlb_miss_whacko_fault:
+ TLB_MISS_EPILOG_ERROR
+ b exc_data_storage_book3e
+
+-
+-/**************************************************************
+- * *
+- * TLB miss handling for Book3E with hw page table support *
+- * *
+- **************************************************************/
+-
+-
+-/* Data TLB miss */
+- START_EXCEPTION(data_tlb_miss_htw)
+- TLB_MISS_PROLOG
+-
+- /* Now we handle the fault proper. We only save DEAR in normal
+- * fault case since that's the only interesting values here.
+- * We could probably also optimize by not saving SRR0/1 in the
+- * linear mapping case but I'll leave that for later
+- */
+- mfspr r14,SPRN_ESR
+- mfspr r16,SPRN_DEAR /* get faulting address */
+- srdi r11,r16,44 /* get region */
+- xoris r11,r11,0xc
+- cmpldi cr0,r11,0 /* linear mapping ? */
+- beq tlb_load_linear /* yes -> go to linear map load */
+- cmpldi cr1,r11,1 /* vmalloc mapping ? */
+-
+- /* We do the user/kernel test for the PID here along with the RW test
+- */
+- srdi. r11,r16,60 /* Check for user region */
+- ld r15,PACAPGD(r13) /* Load user pgdir */
+- beq htw_tlb_miss
+-
+- /* XXX replace the RMW cycles with immediate loads + writes */
+-1: mfspr r10,SPRN_MAS1
+- rlwinm r10,r10,0,16,1 /* Clear TID */
+- mtspr SPRN_MAS1,r10
+- ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */
+- beq+ cr1,htw_tlb_miss
+-
+- /* We got a crappy address, just fault with whatever DEAR and ESR
+- * are here
+- */
+- TLB_MISS_EPILOG_ERROR
+- b exc_data_storage_book3e
+-
+-/* Instruction TLB miss */
+- START_EXCEPTION(instruction_tlb_miss_htw)
+- TLB_MISS_PROLOG
+-
+- /* If we take a recursive fault, the second level handler may need
+- * to know whether we are handling a data or instruction fault in
+- * order to get to the right store fault handler. We provide that
+- * info by keeping a crazy value for ESR in r14
+- */
+- li r14,-1 /* store to exception frame is done later */
+-
+- /* Now we handle the fault proper. We only save DEAR in the non
+- * linear mapping case since we know the linear mapping case will
+- * not re-enter. We could indeed optimize and also not save SRR0/1
+- * in the linear mapping case but I'll leave that for later
+- *
+- * Faulting address is SRR0 which is already in r16
+- */
+- srdi r11,r16,44 /* get region */
+- xoris r11,r11,0xc
+- cmpldi cr0,r11,0 /* linear mapping ? */
+- beq tlb_load_linear /* yes -> go to linear map load */
+- cmpldi cr1,r11,1 /* vmalloc mapping ? */
+-
+- /* We do the user/kernel test for the PID here along with the RW test
+- */
+- srdi. r11,r16,60 /* Check for user region */
+- ld r15,PACAPGD(r13) /* Load user pgdir */
+- beq htw_tlb_miss
+-
+- /* XXX replace the RMW cycles with immediate loads + writes */
+-1: mfspr r10,SPRN_MAS1
+- rlwinm r10,r10,0,16,1 /* Clear TID */
+- mtspr SPRN_MAS1,r10
+- ld r15,PACA_KERNELPGD(r13) /* Load kernel pgdir */
+- beq+ htw_tlb_miss
+-
+- /* We got a crappy address, just fault */
+- TLB_MISS_EPILOG_ERROR
+- b exc_instruction_storage_book3e
+-
+-
+-/*
+- * This is the guts of the second-level TLB miss handler for direct
+- * misses. We are entered with:
+- *
+- * r16 = virtual page table faulting address
+- * r15 = PGD pointer
+- * r14 = ESR
+- * r13 = PACA
+- * r12 = TLB exception frame in PACA
+- * r11 = crap (free to use)
+- * r10 = crap (free to use)
+- *
+- * It can be re-entered by the linear mapping miss handler. However, to
+- * avoid too much complication, it will save/restore things for us
+- */
+-htw_tlb_miss:
+-#ifdef CONFIG_PPC_KUAP
+- mfspr r10,SPRN_MAS1
+- rlwinm. r10,r10,0,0x3fff0000
+- beq- htw_tlb_miss_fault /* KUAP fault */
+-#endif
+- /* Search if we already have a TLB entry for that virtual address, and
+- * if we do, bail out.
+- *
+- * MAS1:IND should be already set based on MAS4
+- */
+- PPC_TLBSRX_DOT(0,R16)
+- beq htw_tlb_miss_done
+-
+- /* Now, we need to walk the page tables. First check if we are in
+- * range.
+- */
+- rldicl. r10,r16,64-PGTABLE_EADDR_SIZE,PGTABLE_EADDR_SIZE+4
+- bne- htw_tlb_miss_fault
+-
+- /* Get the PGD pointer */
+- cmpldi cr0,r15,0
+- beq- htw_tlb_miss_fault
+-
+- /* Get to PGD entry */
+- rldicl r11,r16,64-(PGDIR_SHIFT-3),64-PGD_INDEX_SIZE-3
+- clrrdi r10,r11,3
+- ldx r15,r10,r15
+- cmpdi cr0,r15,0
+- bge htw_tlb_miss_fault
+-
+- /* Get to PUD entry */
+- rldicl r11,r16,64-(PUD_SHIFT-3),64-PUD_INDEX_SIZE-3
+- clrrdi r10,r11,3
+- ldx r15,r10,r15
+- cmpdi cr0,r15,0
+- bge htw_tlb_miss_fault
+-
+- /* Get to PMD entry */
+- rldicl r11,r16,64-(PMD_SHIFT-3),64-PMD_INDEX_SIZE-3
+- clrrdi r10,r11,3
+- ldx r15,r10,r15
+- cmpdi cr0,r15,0
+- bge htw_tlb_miss_fault
+-
+- /* Ok, we're all right, we can now create an indirect entry for
+- * a 1M or 256M page.
+- *
+- * The last trick is now that because we use "half" pages for
+- * the HTW (1M IND is 2K and 256M IND is 32K) we need to account
+- * for an added LSB bit to the RPN. For 64K pages, there is no
+- * problem as we already use 32K arrays (half PTE pages), but for
+- * 4K page we need to extract a bit from the virtual address and
+- * insert it into the "PA52" bit of the RPN.
+- */
+- rlwimi r15,r16,32-9,20,20
+- /* Now we build the MAS:
+- *
+- * MAS 0 : Fully setup with defaults in MAS4 and TLBnCFG
+- * MAS 1 : Almost fully setup
+- * - PID already updated by caller if necessary
+- * - TSIZE for now is base ind page size always
+- * MAS 2 : Use defaults
+- * MAS 3+7 : Needs to be done
+- */
+- ori r10,r15,(BOOK3E_PAGESZ_4K << MAS3_SPSIZE_SHIFT)
+-
+- srdi r16,r10,32
+- mtspr SPRN_MAS3,r10
+- mtspr SPRN_MAS7,r16
+-
+- tlbwe
+-
+-htw_tlb_miss_done:
+- /* We don't bother with restoring DEAR or ESR since we know we are
+- * level 0 and just going back to userland. They are only needed
+- * if you are going to take an access fault
+- */
+- TLB_MISS_EPILOG_SUCCESS
+- rfi
+-
+-htw_tlb_miss_fault:
+- /* We need to check if it was an instruction miss. We know this
+- * though because r14 would contain -1
+- */
+- cmpdi cr0,r14,-1
+- beq 1f
+- mtspr SPRN_DEAR,r16
+- mtspr SPRN_ESR,r14
+- TLB_MISS_EPILOG_ERROR
+- b exc_data_storage_book3e
+-1: TLB_MISS_EPILOG_ERROR
+- b exc_instruction_storage_book3e
+-
+ /*
+ * This is the guts of "any" level TLB miss handler for kernel linear
+ * mapping misses. We are entered with:
+diff --git a/arch/riscv/Kconfig b/arch/riscv/Kconfig
+index 0525ee2d63c71..006232b67b467 100644
+--- a/arch/riscv/Kconfig
++++ b/arch/riscv/Kconfig
+@@ -545,8 +545,8 @@ config RISCV_ISA_SVPBMT
+ config TOOLCHAIN_HAS_V
+ bool
+ default y
+- depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64iv)
+- depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32iv)
++ depends on !64BIT || $(cc-option,-mabi=lp64 -march=rv64imv)
++ depends on !32BIT || $(cc-option,-mabi=ilp32 -march=rv32imv)
+ depends on LLD_VERSION >= 140000 || LD_VERSION >= 23800
+ depends on AS_HAS_OPTION_ARCH
+
+diff --git a/arch/riscv/include/asm/processor.h b/arch/riscv/include/asm/processor.h
+index 68c3432dc6ea4..6c129144ef190 100644
+--- a/arch/riscv/include/asm/processor.h
++++ b/arch/riscv/include/asm/processor.h
+@@ -14,36 +14,14 @@
+
+ #include <asm/ptrace.h>
+
+-/*
+- * addr is a hint to the maximum userspace address that mmap should provide, so
+- * this macro needs to return the largest address space available so that
+- * mmap_end < addr, being mmap_end the top of that address space.
+- * See Documentation/arch/riscv/vm-layout.rst for more details.
+- */
+ #define arch_get_mmap_end(addr, len, flags) \
+ ({ \
+- unsigned long mmap_end; \
+- typeof(addr) _addr = (addr); \
+- if ((_addr) == 0 || is_compat_task() || \
+- ((_addr + len) > BIT(VA_BITS - 1))) \
+- mmap_end = STACK_TOP_MAX; \
+- else \
+- mmap_end = (_addr + len); \
+- mmap_end; \
++ STACK_TOP_MAX; \
+ })
+
+ #define arch_get_mmap_base(addr, base) \
+ ({ \
+- unsigned long mmap_base; \
+- typeof(addr) _addr = (addr); \
+- typeof(base) _base = (base); \
+- unsigned long rnd_gap = DEFAULT_MAP_WINDOW - (_base); \
+- if ((_addr) == 0 || is_compat_task() || \
+- ((_addr + len) > BIT(VA_BITS - 1))) \
+- mmap_base = (_base); \
+- else \
+- mmap_base = (_addr + len) - rnd_gap; \
+- mmap_base; \
++ base; \
+ })
+
+ #ifdef CONFIG_64BIT
+diff --git a/arch/riscv/include/asm/sbi.h b/arch/riscv/include/asm/sbi.h
+index 1079e214fe855..7bd3746028c9e 100644
+--- a/arch/riscv/include/asm/sbi.h
++++ b/arch/riscv/include/asm/sbi.h
+@@ -9,6 +9,7 @@
+
+ #include <linux/types.h>
+ #include <linux/cpumask.h>
++#include <linux/jump_label.h>
+
+ #ifdef CONFIG_RISCV_SBI
+ enum sbi_ext_id {
+@@ -304,10 +305,13 @@ struct sbiret {
+ };
+
+ void sbi_init(void);
+-struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+- unsigned long arg1, unsigned long arg2,
+- unsigned long arg3, unsigned long arg4,
+- unsigned long arg5);
++long __sbi_base_ecall(int fid);
++struct sbiret __sbi_ecall(unsigned long arg0, unsigned long arg1,
++ unsigned long arg2, unsigned long arg3,
++ unsigned long arg4, unsigned long arg5,
++ int fid, int ext);
++#define sbi_ecall(e, f, a0, a1, a2, a3, a4, a5) \
++ __sbi_ecall(a0, a1, a2, a3, a4, a5, f, e)
+
+ #ifdef CONFIG_RISCV_SBI_V01
+ void sbi_console_putchar(int ch);
+@@ -371,7 +375,23 @@ static inline unsigned long sbi_mk_version(unsigned long major,
+ | (minor & SBI_SPEC_VERSION_MINOR_MASK);
+ }
+
+-int sbi_err_map_linux_errno(int err);
++static inline int sbi_err_map_linux_errno(int err)
++{
++ switch (err) {
++ case SBI_SUCCESS:
++ return 0;
++ case SBI_ERR_DENIED:
++ return -EPERM;
++ case SBI_ERR_INVALID_PARAM:
++ return -EINVAL;
++ case SBI_ERR_INVALID_ADDRESS:
++ return -EFAULT;
++ case SBI_ERR_NOT_SUPPORTED:
++ case SBI_ERR_FAILURE:
++ default:
++ return -ENOTSUPP;
++ };
++}
+
+ extern bool sbi_debug_console_available;
+ int sbi_debug_console_write(const char *bytes, unsigned int num_bytes);
+diff --git a/arch/riscv/include/asm/trace.h b/arch/riscv/include/asm/trace.h
+new file mode 100644
+index 0000000000000..6151cee5450cd
+--- /dev/null
++++ b/arch/riscv/include/asm/trace.h
+@@ -0,0 +1,54 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++#undef TRACE_SYSTEM
++#define TRACE_SYSTEM riscv
++
++#if !defined(_TRACE_RISCV_H) || defined(TRACE_HEADER_MULTI_READ)
++#define _TRACE_RISCV_H
++
++#include <linux/tracepoint.h>
++
++TRACE_EVENT_CONDITION(sbi_call,
++ TP_PROTO(int ext, int fid),
++ TP_ARGS(ext, fid),
++ TP_CONDITION(ext != SBI_EXT_HSM),
++
++ TP_STRUCT__entry(
++ __field(int, ext)
++ __field(int, fid)
++ ),
++
++ TP_fast_assign(
++ __entry->ext = ext;
++ __entry->fid = fid;
++ ),
++
++ TP_printk("ext=0x%x fid=%d", __entry->ext, __entry->fid)
++);
++
++TRACE_EVENT_CONDITION(sbi_return,
++ TP_PROTO(int ext, long error, long value),
++ TP_ARGS(ext, error, value),
++ TP_CONDITION(ext != SBI_EXT_HSM),
++
++ TP_STRUCT__entry(
++ __field(long, error)
++ __field(long, value)
++ ),
++
++ TP_fast_assign(
++ __entry->error = error;
++ __entry->value = value;
++ ),
++
++ TP_printk("error=%ld value=0x%lx", __entry->error, __entry->value)
++);
++
++#endif /* _TRACE_RISCV_H */
++
++#undef TRACE_INCLUDE_PATH
++#undef TRACE_INCLUDE_FILE
++
++#define TRACE_INCLUDE_PATH asm
++#define TRACE_INCLUDE_FILE trace
++
++#include <trace/define_trace.h>
+diff --git a/arch/riscv/kernel/Makefile b/arch/riscv/kernel/Makefile
+index 5b243d46f4b17..1d71002e4f7b4 100644
+--- a/arch/riscv/kernel/Makefile
++++ b/arch/riscv/kernel/Makefile
+@@ -20,17 +20,21 @@ endif
+ ifdef CONFIG_RISCV_ALTERNATIVE_EARLY
+ CFLAGS_alternative.o := -mcmodel=medany
+ CFLAGS_cpufeature.o := -mcmodel=medany
++CFLAGS_sbi_ecall.o := -mcmodel=medany
+ ifdef CONFIG_FTRACE
+ CFLAGS_REMOVE_alternative.o = $(CC_FLAGS_FTRACE)
+ CFLAGS_REMOVE_cpufeature.o = $(CC_FLAGS_FTRACE)
++CFLAGS_REMOVE_sbi_ecall.o = $(CC_FLAGS_FTRACE)
+ endif
+ ifdef CONFIG_RELOCATABLE
+ CFLAGS_alternative.o += -fno-pie
+ CFLAGS_cpufeature.o += -fno-pie
++CFLAGS_sbi_ecall.o += -fno-pie
+ endif
+ ifdef CONFIG_KASAN
+ KASAN_SANITIZE_alternative.o := n
+ KASAN_SANITIZE_cpufeature.o := n
++KASAN_SANITIZE_sbi_ecall.o := n
+ endif
+ endif
+
+@@ -86,7 +90,7 @@ obj-$(CONFIG_DYNAMIC_FTRACE) += mcount-dyn.o
+
+ obj-$(CONFIG_PERF_EVENTS) += perf_callchain.o
+ obj-$(CONFIG_HAVE_PERF_REGS) += perf_regs.o
+-obj-$(CONFIG_RISCV_SBI) += sbi.o
++obj-$(CONFIG_RISCV_SBI) += sbi.o sbi_ecall.o
+ ifeq ($(CONFIG_RISCV_SBI), y)
+ obj-$(CONFIG_SMP) += sbi-ipi.o
+ obj-$(CONFIG_SMP) += cpu_ops_sbi.o
+diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
+index a00f7523cb91f..356d5397b2a25 100644
+--- a/arch/riscv/kernel/head.S
++++ b/arch/riscv/kernel/head.S
+@@ -305,6 +305,9 @@ SYM_CODE_START(_start_kernel)
+ #else
+ mv a0, a1
+ #endif /* CONFIG_BUILTIN_DTB */
++ /* Set trap vector to spin forever to help debug */
++ la a3, .Lsecondary_park
++ csrw CSR_TVEC, a3
+ call setup_vm
+ #ifdef CONFIG_MMU
+ la a0, early_pg_dir
+diff --git a/arch/riscv/kernel/probes/kprobes.c b/arch/riscv/kernel/probes/kprobes.c
+index dfb28e57d9001..03cd103b84494 100644
+--- a/arch/riscv/kernel/probes/kprobes.c
++++ b/arch/riscv/kernel/probes/kprobes.c
+@@ -29,9 +29,8 @@ static void __kprobes arch_prepare_ss_slot(struct kprobe *p)
+
+ p->ainsn.api.restore = (unsigned long)p->addr + offset;
+
+- patch_text(p->ainsn.api.insn, &p->opcode, 1);
+- patch_text((void *)((unsigned long)(p->ainsn.api.insn) + offset),
+- &insn, 1);
++ patch_text_nosync(p->ainsn.api.insn, &p->opcode, 1);
++ patch_text_nosync(p->ainsn.api.insn + offset, &insn, 1);
+ }
+
+ static void __kprobes arch_prepare_simulate(struct kprobe *p)
+diff --git a/arch/riscv/kernel/sbi.c b/arch/riscv/kernel/sbi.c
+index e66e0999a8005..1989b8cade1b9 100644
+--- a/arch/riscv/kernel/sbi.c
++++ b/arch/riscv/kernel/sbi.c
+@@ -24,51 +24,6 @@ static int (*__sbi_rfence)(int fid, const struct cpumask *cpu_mask,
+ unsigned long start, unsigned long size,
+ unsigned long arg4, unsigned long arg5) __ro_after_init;
+
+-struct sbiret sbi_ecall(int ext, int fid, unsigned long arg0,
+- unsigned long arg1, unsigned long arg2,
+- unsigned long arg3, unsigned long arg4,
+- unsigned long arg5)
+-{
+- struct sbiret ret;
+-
+- register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
+- register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
+- register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
+- register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
+- register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
+- register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
+- register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
+- register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
+- asm volatile ("ecall"
+- : "+r" (a0), "+r" (a1)
+- : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
+- : "memory");
+- ret.error = a0;
+- ret.value = a1;
+-
+- return ret;
+-}
+-EXPORT_SYMBOL(sbi_ecall);
+-
+-int sbi_err_map_linux_errno(int err)
+-{
+- switch (err) {
+- case SBI_SUCCESS:
+- return 0;
+- case SBI_ERR_DENIED:
+- return -EPERM;
+- case SBI_ERR_INVALID_PARAM:
+- return -EINVAL;
+- case SBI_ERR_INVALID_ADDRESS:
+- return -EFAULT;
+- case SBI_ERR_NOT_SUPPORTED:
+- case SBI_ERR_FAILURE:
+- default:
+- return -ENOTSUPP;
+- };
+-}
+-EXPORT_SYMBOL(sbi_err_map_linux_errno);
+-
+ #ifdef CONFIG_RISCV_SBI_V01
+ static unsigned long __sbi_v01_cpumask_to_hartmask(const struct cpumask *cpu_mask)
+ {
+@@ -528,17 +483,6 @@ long sbi_probe_extension(int extid)
+ }
+ EXPORT_SYMBOL(sbi_probe_extension);
+
+-static long __sbi_base_ecall(int fid)
+-{
+- struct sbiret ret;
+-
+- ret = sbi_ecall(SBI_EXT_BASE, fid, 0, 0, 0, 0, 0, 0);
+- if (!ret.error)
+- return ret.value;
+- else
+- return sbi_err_map_linux_errno(ret.error);
+-}
+-
+ static inline long sbi_get_spec_version(void)
+ {
+ return __sbi_base_ecall(SBI_EXT_BASE_GET_SPEC_VERSION);
+diff --git a/arch/riscv/kernel/sbi_ecall.c b/arch/riscv/kernel/sbi_ecall.c
+new file mode 100644
+index 0000000000000..24aabb4fbde3a
+--- /dev/null
++++ b/arch/riscv/kernel/sbi_ecall.c
+@@ -0,0 +1,48 @@
++// SPDX-License-Identifier: GPL-2.0
++/* Copyright (c) 2024 Rivos Inc. */
++
++#include <asm/sbi.h>
++#define CREATE_TRACE_POINTS
++#include <asm/trace.h>
++
++long __sbi_base_ecall(int fid)
++{
++ struct sbiret ret;
++
++ ret = sbi_ecall(SBI_EXT_BASE, fid, 0, 0, 0, 0, 0, 0);
++ if (!ret.error)
++ return ret.value;
++ else
++ return sbi_err_map_linux_errno(ret.error);
++}
++EXPORT_SYMBOL(__sbi_base_ecall);
++
++struct sbiret __sbi_ecall(unsigned long arg0, unsigned long arg1,
++ unsigned long arg2, unsigned long arg3,
++ unsigned long arg4, unsigned long arg5,
++ int fid, int ext)
++{
++ struct sbiret ret;
++
++ trace_sbi_call(ext, fid);
++
++ register uintptr_t a0 asm ("a0") = (uintptr_t)(arg0);
++ register uintptr_t a1 asm ("a1") = (uintptr_t)(arg1);
++ register uintptr_t a2 asm ("a2") = (uintptr_t)(arg2);
++ register uintptr_t a3 asm ("a3") = (uintptr_t)(arg3);
++ register uintptr_t a4 asm ("a4") = (uintptr_t)(arg4);
++ register uintptr_t a5 asm ("a5") = (uintptr_t)(arg5);
++ register uintptr_t a6 asm ("a6") = (uintptr_t)(fid);
++ register uintptr_t a7 asm ("a7") = (uintptr_t)(ext);
++ asm volatile ("ecall"
++ : "+r" (a0), "+r" (a1)
++ : "r" (a2), "r" (a3), "r" (a4), "r" (a5), "r" (a6), "r" (a7)
++ : "memory");
++ ret.error = a0;
++ ret.value = a1;
++
++ trace_sbi_return(ext, ret.error, ret.value);
++
++ return ret;
++}
++EXPORT_SYMBOL(__sbi_ecall);
+diff --git a/arch/riscv/kernel/traps_misaligned.c b/arch/riscv/kernel/traps_misaligned.c
+index b62d5a2f4541e..1a76f99ff185a 100644
+--- a/arch/riscv/kernel/traps_misaligned.c
++++ b/arch/riscv/kernel/traps_misaligned.c
+@@ -417,7 +417,7 @@ int handle_misaligned_load(struct pt_regs *regs)
+
+ val.data_u64 = 0;
+ if (user_mode(regs)) {
+- if (raw_copy_from_user(&val, (u8 __user *)addr, len))
++ if (copy_from_user(&val, (u8 __user *)addr, len))
+ return -1;
+ } else {
+ memcpy(&val, (u8 *)addr, len);
+@@ -515,7 +515,7 @@ int handle_misaligned_store(struct pt_regs *regs)
+ return -EOPNOTSUPP;
+
+ if (user_mode(regs)) {
+- if (raw_copy_to_user((u8 __user *)addr, &val, len))
++ if (copy_to_user((u8 __user *)addr, &val, len))
+ return -1;
+ } else {
+ memcpy((u8 *)addr, &val, len);
+diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
+index c5c66f53971af..91346c9da8ef4 100644
+--- a/arch/riscv/mm/init.c
++++ b/arch/riscv/mm/init.c
+@@ -251,7 +251,7 @@ static void __init setup_bootmem(void)
+ * The size of the linear page mapping may restrict the amount of
+ * usable RAM.
+ */
+- if (IS_ENABLED(CONFIG_64BIT)) {
++ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU)) {
+ max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE;
+ memblock_cap_memory_range(phys_ram_base,
+ max_mapped_addr - phys_ram_base);
+diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
+index 6d88f241dd43a..66ee97ac803de 100644
+--- a/arch/s390/boot/startup.c
++++ b/arch/s390/boot/startup.c
+@@ -476,8 +476,12 @@ void startup_kernel(void)
+ * before the kernel started. Therefore, in case the two sections
+ * overlap there is no risk of corrupting any data.
+ */
+- if (kaslr_enabled())
+- amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G);
++ if (kaslr_enabled()) {
++ unsigned long amode31_min;
++
++ amode31_min = (unsigned long)_decompressor_end;
++ amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, amode31_min, SZ_2G);
++ }
+ if (!amode31_lma)
+ amode31_lma = text_lma - vmlinux.amode31_size;
+ physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size);
+diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
+index 52bd969b28283..779162c664c4e 100644
+--- a/arch/s390/kernel/vmlinux.lds.S
++++ b/arch/s390/kernel/vmlinux.lds.S
+@@ -59,14 +59,6 @@ SECTIONS
+ } :text = 0x0700
+
+ RO_DATA(PAGE_SIZE)
+- .data.rel.ro : {
+- *(.data.rel.ro .data.rel.ro.*)
+- }
+- .got : {
+- __got_start = .;
+- *(.got)
+- __got_end = .;
+- }
+
+ . = ALIGN(PAGE_SIZE);
+ _sdata = .; /* Start of data section */
+@@ -80,6 +72,15 @@ SECTIONS
+ . = ALIGN(PAGE_SIZE);
+ __end_ro_after_init = .;
+
++ .data.rel.ro : {
++ *(.data.rel.ro .data.rel.ro.*)
++ }
++ .got : {
++ __got_start = .;
++ *(.got)
++ __got_end = .;
++ }
++
+ RW_DATA(0x100, PAGE_SIZE, THREAD_SIZE)
+ .data.rel : {
+ *(.data.rel*)
+diff --git a/arch/um/drivers/line.c b/arch/um/drivers/line.c
+index d82bc3fdb86e7..43d8959cc746f 100644
+--- a/arch/um/drivers/line.c
++++ b/arch/um/drivers/line.c
+@@ -383,6 +383,7 @@ int setup_one_line(struct line *lines, int n, char *init,
+ parse_chan_pair(NULL, line, n, opts, error_out);
+ err = 0;
+ }
++ *error_out = "configured as 'none'";
+ } else {
+ char *new = kstrdup(init, GFP_KERNEL);
+ if (!new) {
+@@ -406,6 +407,7 @@ int setup_one_line(struct line *lines, int n, char *init,
+ }
+ }
+ if (err) {
++ *error_out = "failed to parse channel pair";
+ line->init_str = NULL;
+ line->valid = 0;
+ kfree(new);
+diff --git a/arch/x86/coco/tdx/tdx.c b/arch/x86/coco/tdx/tdx.c
+index c1cb90369915b..8fe4c2b07128e 100644
+--- a/arch/x86/coco/tdx/tdx.c
++++ b/arch/x86/coco/tdx/tdx.c
+@@ -385,7 +385,6 @@ static bool mmio_read(int size, unsigned long addr, unsigned long *val)
+ .r12 = size,
+ .r13 = EPT_READ,
+ .r14 = addr,
+- .r15 = *val,
+ };
+
+ if (__tdx_hypercall(&args))
+diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
+index f25205d047e83..dcac96133cb6a 100644
+--- a/arch/x86/events/intel/core.c
++++ b/arch/x86/events/intel/core.c
+@@ -4529,6 +4529,25 @@ static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
+ return HYBRID_INTEL_CORE;
+ }
+
++static inline bool erratum_hsw11(struct perf_event *event)
++{
++ return (event->hw.config & INTEL_ARCH_EVENT_MASK) ==
++ X86_CONFIG(.event=0xc0, .umask=0x01);
++}
++
++/*
++ * The HSW11 requires a period larger than 100 which is the same as the BDM11.
++ * A minimum period of 128 is enforced as well for the INST_RETIRED.ALL.
++ *
++ * The message 'interrupt took too long' can be observed on any counter which
++ * was armed with a period < 32 and two events expired in the same NMI.
++ * A minimum period of 32 is enforced for the rest of the events.
++ */
++static void hsw_limit_period(struct perf_event *event, s64 *left)
++{
++ *left = max(*left, erratum_hsw11(event) ? 128 : 32);
++}
++
+ /*
+ * Broadwell:
+ *
+@@ -4546,8 +4565,7 @@ static enum hybrid_cpu_type adl_get_hybrid_cpu_type(void)
+ */
+ static void bdw_limit_period(struct perf_event *event, s64 *left)
+ {
+- if ((event->hw.config & INTEL_ARCH_EVENT_MASK) ==
+- X86_CONFIG(.event=0xc0, .umask=0x01)) {
++ if (erratum_hsw11(event)) {
+ if (*left < 128)
+ *left = 128;
+ *left &= ~0x3fULL;
+@@ -5715,8 +5733,22 @@ exra_is_visible(struct kobject *kobj, struct attribute *attr, int i)
+ return x86_pmu.version >= 2 ? attr->mode : 0;
+ }
+
++static umode_t
++td_is_visible(struct kobject *kobj, struct attribute *attr, int i)
++{
++ /*
++ * Hide the perf metrics topdown events
++ * if the feature is not enumerated.
++ */
++ if (x86_pmu.num_topdown_events)
++ return x86_pmu.intel_cap.perf_metrics ? attr->mode : 0;
++
++ return attr->mode;
++}
++
+ static struct attribute_group group_events_td = {
+ .name = "events",
++ .is_visible = td_is_visible,
+ };
+
+ static struct attribute_group group_events_mem = {
+@@ -5918,9 +5950,27 @@ static umode_t hybrid_format_is_visible(struct kobject *kobj,
+ return (cpu >= 0) && (pmu->pmu_type & pmu_attr->pmu_type) ? attr->mode : 0;
+ }
+
++static umode_t hybrid_td_is_visible(struct kobject *kobj,
++ struct attribute *attr, int i)
++{
++ struct device *dev = kobj_to_dev(kobj);
++ struct x86_hybrid_pmu *pmu =
++ container_of(dev_get_drvdata(dev), struct x86_hybrid_pmu, pmu);
++
++ if (!is_attr_for_this_pmu(kobj, attr))
++ return 0;
++
++
++ /* Only the big core supports perf metrics */
++ if (pmu->pmu_type == hybrid_big)
++ return pmu->intel_cap.perf_metrics ? attr->mode : 0;
++
++ return attr->mode;
++}
++
+ static struct attribute_group hybrid_group_events_td = {
+ .name = "events",
+- .is_visible = hybrid_events_is_visible,
++ .is_visible = hybrid_td_is_visible,
+ };
+
+ static struct attribute_group hybrid_group_events_mem = {
+@@ -6573,6 +6623,7 @@ __init int intel_pmu_init(void)
+
+ x86_pmu.hw_config = hsw_hw_config;
+ x86_pmu.get_event_constraints = hsw_get_event_constraints;
++ x86_pmu.limit_period = hsw_limit_period;
+ x86_pmu.lbr_double_abort = true;
+ extra_attr = boot_cpu_has(X86_FEATURE_RTM) ?
+ hsw_format_attr : nhm_format_attr;
+diff --git a/arch/x86/include/asm/fpu/types.h b/arch/x86/include/asm/fpu/types.h
+index eb17f31b06d25..de16862bf230b 100644
+--- a/arch/x86/include/asm/fpu/types.h
++++ b/arch/x86/include/asm/fpu/types.h
+@@ -591,6 +591,13 @@ struct fpu_state_config {
+ * even without XSAVE support, i.e. legacy features FP + SSE
+ */
+ u64 legacy_features;
++ /*
++ * @independent_features:
++ *
++ * Features that are supported by XSAVES, but not managed as part of
++ * the FPU core, such as LBR
++ */
++ u64 independent_features;
+ };
+
+ /* FPU state configuration information */
+diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
+index cc6b8e087192e..9dab85aba7afd 100644
+--- a/arch/x86/include/asm/page_64.h
++++ b/arch/x86/include/asm/page_64.h
+@@ -17,6 +17,7 @@ extern unsigned long phys_base;
+ extern unsigned long page_offset_base;
+ extern unsigned long vmalloc_base;
+ extern unsigned long vmemmap_base;
++extern unsigned long physmem_end;
+
+ static __always_inline unsigned long __phys_addr_nodebug(unsigned long x)
+ {
+diff --git a/arch/x86/include/asm/pgtable_64_types.h b/arch/x86/include/asm/pgtable_64_types.h
+index 9053dfe9fa03f..a98e53491a4e6 100644
+--- a/arch/x86/include/asm/pgtable_64_types.h
++++ b/arch/x86/include/asm/pgtable_64_types.h
+@@ -140,6 +140,10 @@ extern unsigned int ptrs_per_p4d;
+ # define VMEMMAP_START __VMEMMAP_BASE_L4
+ #endif /* CONFIG_DYNAMIC_MEMORY_LAYOUT */
+
++#ifdef CONFIG_RANDOMIZE_MEMORY
++# define PHYSMEM_END physmem_end
++#endif
++
+ /*
+ * End of the region for which vmalloc page tables are pre-allocated.
+ * For non-KMSAN builds, this is the same as VMALLOC_END.
+diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c
+index 66fd4b2a37a3a..373638691cd48 100644
+--- a/arch/x86/kernel/apic/apic.c
++++ b/arch/x86/kernel/apic/apic.c
+@@ -1775,12 +1775,9 @@ static __init void apic_set_fixmap(bool read_apic);
+
+ static __init void x2apic_disable(void)
+ {
+- u32 x2apic_id, state = x2apic_state;
++ u32 x2apic_id;
+
+- x2apic_mode = 0;
+- x2apic_state = X2APIC_DISABLED;
+-
+- if (state != X2APIC_ON)
++ if (x2apic_state < X2APIC_ON)
+ return;
+
+ x2apic_id = read_apic_id();
+@@ -1793,6 +1790,10 @@ static __init void x2apic_disable(void)
+ }
+
+ __x2apic_disable();
++
++ x2apic_mode = 0;
++ x2apic_state = X2APIC_DISABLED;
++
+ /*
+ * Don't reread the APIC ID as it was already done from
+ * check_x2apic() and the APIC driver still is a x2APIC variant,
+diff --git a/arch/x86/kernel/fpu/xstate.c b/arch/x86/kernel/fpu/xstate.c
+index c5a026fee5e06..1339f8328db5a 100644
+--- a/arch/x86/kernel/fpu/xstate.c
++++ b/arch/x86/kernel/fpu/xstate.c
+@@ -788,6 +788,9 @@ void __init fpu__init_system_xstate(unsigned int legacy_size)
+ goto out_disable;
+ }
+
++ fpu_kernel_cfg.independent_features = fpu_kernel_cfg.max_features &
++ XFEATURE_MASK_INDEPENDENT;
++
+ /*
+ * Clear XSAVE features that are disabled in the normal CPUID.
+ */
+diff --git a/arch/x86/kernel/fpu/xstate.h b/arch/x86/kernel/fpu/xstate.h
+index 05df04f396282..f2611145f3caa 100644
+--- a/arch/x86/kernel/fpu/xstate.h
++++ b/arch/x86/kernel/fpu/xstate.h
+@@ -62,9 +62,9 @@ static inline u64 xfeatures_mask_supervisor(void)
+ static inline u64 xfeatures_mask_independent(void)
+ {
+ if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR))
+- return XFEATURE_MASK_INDEPENDENT & ~XFEATURE_MASK_LBR;
++ return fpu_kernel_cfg.independent_features & ~XFEATURE_MASK_LBR;
+
+- return XFEATURE_MASK_INDEPENDENT;
++ return fpu_kernel_cfg.independent_features;
+ }
+
+ /* XSAVE/XRSTOR wrapper functions */
+diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c
+index c95d3900fe564..0357f7af55966 100644
+--- a/arch/x86/kvm/svm/svm.c
++++ b/arch/x86/kvm/svm/svm.c
+@@ -2863,6 +2863,12 @@ static int svm_get_msr(struct kvm_vcpu *vcpu, struct msr_data *msr_info)
+ case MSR_CSTAR:
+ msr_info->data = svm->vmcb01.ptr->save.cstar;
+ break;
++ case MSR_GS_BASE:
++ msr_info->data = svm->vmcb01.ptr->save.gs.base;
++ break;
++ case MSR_FS_BASE:
++ msr_info->data = svm->vmcb01.ptr->save.fs.base;
++ break;
+ case MSR_KERNEL_GS_BASE:
+ msr_info->data = svm->vmcb01.ptr->save.kernel_gs_base;
+ break;
+@@ -3088,6 +3094,12 @@ static int svm_set_msr(struct kvm_vcpu *vcpu, struct msr_data *msr)
+ case MSR_CSTAR:
+ svm->vmcb01.ptr->save.cstar = data;
+ break;
++ case MSR_GS_BASE:
++ svm->vmcb01.ptr->save.gs.base = data;
++ break;
++ case MSR_FS_BASE:
++ svm->vmcb01.ptr->save.fs.base = data;
++ break;
+ case MSR_KERNEL_GS_BASE:
+ svm->vmcb01.ptr->save.kernel_gs_base = data;
+ break;
+@@ -5211,6 +5223,9 @@ static __init void svm_set_cpu_caps(void)
+
+ /* CPUID 0x8000001F (SME/SEV features) */
+ sev_set_cpu_caps();
++
++ /* Don't advertise Bus Lock Detect to guest if SVM support is absent */
++ kvm_cpu_cap_clear(X86_FEATURE_BUS_LOCK_DETECT);
+ }
+
+ static __init int svm_hardware_setup(void)
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index 0b7adf3bc58a6..d8fc894706eff 100644
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -6040,7 +6040,9 @@ long kvm_arch_vcpu_ioctl(struct file *filp,
+ if (copy_from_user(&events, argp, sizeof(struct kvm_vcpu_events)))
+ break;
+
++ kvm_vcpu_srcu_read_lock(vcpu);
+ r = kvm_vcpu_ioctl_x86_set_vcpu_events(vcpu, &events);
++ kvm_vcpu_srcu_read_unlock(vcpu);
+ break;
+ }
+ case KVM_GET_DEBUGREGS: {
+diff --git a/arch/x86/lib/iomem.c b/arch/x86/lib/iomem.c
+index e0411a3774d49..5eecb45d05d5d 100644
+--- a/arch/x86/lib/iomem.c
++++ b/arch/x86/lib/iomem.c
+@@ -25,6 +25,9 @@ static __always_inline void rep_movs(void *to, const void *from, size_t n)
+
+ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, size_t n)
+ {
++ const void *orig_to = to;
++ const size_t orig_n = n;
++
+ if (unlikely(!n))
+ return;
+
+@@ -39,7 +42,7 @@ static void string_memcpy_fromio(void *to, const volatile void __iomem *from, si
+ }
+ rep_movs(to, (const void *)from, n);
+ /* KMSAN must treat values read from devices as initialized. */
+- kmsan_unpoison_memory(to, n);
++ kmsan_unpoison_memory(orig_to, orig_n);
+ }
+
+ static void string_memcpy_toio(volatile void __iomem *to, const void *from, size_t n)
+diff --git a/arch/x86/mm/init_64.c b/arch/x86/mm/init_64.c
+index 7e177856ee4fe..59087c8712469 100644
+--- a/arch/x86/mm/init_64.c
++++ b/arch/x86/mm/init_64.c
+@@ -950,8 +950,12 @@ static void update_end_of_memory_vars(u64 start, u64 size)
+ int add_pages(int nid, unsigned long start_pfn, unsigned long nr_pages,
+ struct mhp_params *params)
+ {
++ unsigned long end = ((start_pfn + nr_pages) << PAGE_SHIFT) - 1;
+ int ret;
+
++ if (WARN_ON_ONCE(end > PHYSMEM_END))
++ return -ERANGE;
++
+ ret = __add_pages(nid, start_pfn, nr_pages, params);
+ WARN_ON_ONCE(ret);
+
+diff --git a/arch/x86/mm/kaslr.c b/arch/x86/mm/kaslr.c
+index 37db264866b64..230f1dee4f095 100644
+--- a/arch/x86/mm/kaslr.c
++++ b/arch/x86/mm/kaslr.c
+@@ -47,13 +47,24 @@ static const unsigned long vaddr_end = CPU_ENTRY_AREA_BASE;
+ */
+ static __initdata struct kaslr_memory_region {
+ unsigned long *base;
++ unsigned long *end;
+ unsigned long size_tb;
+ } kaslr_regions[] = {
+- { &page_offset_base, 0 },
+- { &vmalloc_base, 0 },
+- { &vmemmap_base, 0 },
++ {
++ .base = &page_offset_base,
++ .end = &physmem_end,
++ },
++ {
++ .base = &vmalloc_base,
++ },
++ {
++ .base = &vmemmap_base,
++ },
+ };
+
++/* The end of the possible address space for physical memory */
++unsigned long physmem_end __ro_after_init;
++
+ /* Get size in bytes used by the memory region */
+ static inline unsigned long get_padding(struct kaslr_memory_region *region)
+ {
+@@ -82,6 +93,8 @@ void __init kernel_randomize_memory(void)
+ BUILD_BUG_ON(vaddr_end != CPU_ENTRY_AREA_BASE);
+ BUILD_BUG_ON(vaddr_end > __START_KERNEL_map);
+
++ /* Preset the end of the possible address space for physical memory */
++ physmem_end = ((1ULL << MAX_PHYSMEM_BITS) - 1);
+ if (!kaslr_memory_enabled())
+ return;
+
+@@ -128,11 +141,18 @@ void __init kernel_randomize_memory(void)
+ vaddr += entropy;
+ *kaslr_regions[i].base = vaddr;
+
++ /* Calculate the end of the region */
++ vaddr += get_padding(&kaslr_regions[i]);
+ /*
+- * Jump the region and add a minimum padding based on
+- * randomization alignment.
++ * KASLR trims the maximum possible size of the
++ * direct-map. Update the physmem_end boundary.
++ * No rounding required as the region starts
++ * PUD aligned and size is in units of TB.
+ */
+- vaddr += get_padding(&kaslr_regions[i]);
++ if (kaslr_regions[i].end)
++ *kaslr_regions[i].end = __pa_nodebug(vaddr - 1);
++
++ /* Add a minimum padding based on randomization alignment. */
+ vaddr = round_up(vaddr + 1, PUD_SIZE);
+ remain_entropy -= entropy;
+ }
+diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
+index bfdf5f45b1370..851ec8f1363a8 100644
+--- a/arch/x86/mm/pti.c
++++ b/arch/x86/mm/pti.c
+@@ -241,7 +241,7 @@ static pmd_t *pti_user_pagetable_walk_pmd(unsigned long address)
+ *
+ * Returns a pointer to a PTE on success, or NULL on failure.
+ */
+-static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
++static pte_t *pti_user_pagetable_walk_pte(unsigned long address, bool late_text)
+ {
+ gfp_t gfp = (GFP_KERNEL | __GFP_NOTRACK | __GFP_ZERO);
+ pmd_t *pmd;
+@@ -251,10 +251,15 @@ static pte_t *pti_user_pagetable_walk_pte(unsigned long address)
+ if (!pmd)
+ return NULL;
+
+- /* We can't do anything sensible if we hit a large mapping. */
++ /* Large PMD mapping found */
+ if (pmd_leaf(*pmd)) {
+- WARN_ON(1);
+- return NULL;
++ /* Clear the PMD if we hit a large mapping from the first round */
++ if (late_text) {
++ set_pmd(pmd, __pmd(0));
++ } else {
++ WARN_ON_ONCE(1);
++ return NULL;
++ }
+ }
+
+ if (pmd_none(*pmd)) {
+@@ -283,7 +288,7 @@ static void __init pti_setup_vsyscall(void)
+ if (!pte || WARN_ON(level != PG_LEVEL_4K) || pte_none(*pte))
+ return;
+
+- target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR);
++ target_pte = pti_user_pagetable_walk_pte(VSYSCALL_ADDR, false);
+ if (WARN_ON(!target_pte))
+ return;
+
+@@ -301,7 +306,7 @@ enum pti_clone_level {
+
+ static void
+ pti_clone_pgtable(unsigned long start, unsigned long end,
+- enum pti_clone_level level)
++ enum pti_clone_level level, bool late_text)
+ {
+ unsigned long addr;
+
+@@ -390,7 +395,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
+ return;
+
+ /* Allocate PTE in the user page-table */
+- target_pte = pti_user_pagetable_walk_pte(addr);
++ target_pte = pti_user_pagetable_walk_pte(addr, late_text);
+ if (WARN_ON(!target_pte))
+ return;
+
+@@ -452,7 +457,7 @@ static void __init pti_clone_user_shared(void)
+ phys_addr_t pa = per_cpu_ptr_to_phys((void *)va);
+ pte_t *target_pte;
+
+- target_pte = pti_user_pagetable_walk_pte(va);
++ target_pte = pti_user_pagetable_walk_pte(va, false);
+ if (WARN_ON(!target_pte))
+ return;
+
+@@ -475,7 +480,7 @@ static void __init pti_clone_user_shared(void)
+ start = CPU_ENTRY_AREA_BASE;
+ end = start + (PAGE_SIZE * CPU_ENTRY_AREA_PAGES);
+
+- pti_clone_pgtable(start, end, PTI_CLONE_PMD);
++ pti_clone_pgtable(start, end, PTI_CLONE_PMD, false);
+ }
+ #endif /* CONFIG_X86_64 */
+
+@@ -492,11 +497,11 @@ static void __init pti_setup_espfix64(void)
+ /*
+ * Clone the populated PMDs of the entry text and force it RO.
+ */
+-static void pti_clone_entry_text(void)
++static void pti_clone_entry_text(bool late)
+ {
+ pti_clone_pgtable((unsigned long) __entry_text_start,
+ (unsigned long) __entry_text_end,
+- PTI_LEVEL_KERNEL_IMAGE);
++ PTI_LEVEL_KERNEL_IMAGE, late);
+ }
+
+ /*
+@@ -571,7 +576,7 @@ static void pti_clone_kernel_text(void)
+ * pti_set_kernel_image_nonglobal() did to clear the
+ * global bit.
+ */
+- pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE);
++ pti_clone_pgtable(start, end_clone, PTI_LEVEL_KERNEL_IMAGE, false);
+
+ /*
+ * pti_clone_pgtable() will set the global bit in any PMDs
+@@ -638,8 +643,15 @@ void __init pti_init(void)
+
+ /* Undo all global bits from the init pagetables in head_64.S: */
+ pti_set_kernel_image_nonglobal();
++
+ /* Replace some of the global bits just for shared entry text: */
+- pti_clone_entry_text();
++ /*
++ * This is very early in boot. Device and Late initcalls can do
++ * modprobe before free_initmem() and mark_readonly(). This
++ * pti_clone_entry_text() allows those user-mode-helpers to function,
++ * but notably the text is still RW.
++ */
++ pti_clone_entry_text(false);
+ pti_setup_espfix64();
+ pti_setup_vsyscall();
+ }
+@@ -656,10 +668,11 @@ void pti_finalize(void)
+ if (!boot_cpu_has(X86_FEATURE_PTI))
+ return;
+ /*
+- * We need to clone everything (again) that maps parts of the
+- * kernel image.
++ * This is after free_initmem() (all initcalls are done) and we've done
++ * mark_readonly(). Text is now NX which might've split some PMDs
++ * relative to the early clone.
+ */
+- pti_clone_entry_text();
++ pti_clone_entry_text(true);
+ pti_clone_kernel_text();
+
+ debug_checkwx_user();
+diff --git a/block/bio.c b/block/bio.c
+index e9e809a63c597..c7a4bc05c43e7 100644
+--- a/block/bio.c
++++ b/block/bio.c
+@@ -1630,8 +1630,18 @@ void bio_endio(struct bio *bio)
+ goto again;
+ }
+
+- /* release cgroup info */
+- bio_uninit(bio);
++#ifdef CONFIG_BLK_CGROUP
++ /*
++ * Release cgroup info. We shouldn't have to do this here, but quite
++ * a few callers of bio_init fail to call bio_uninit, so we cover up
++ * for that here at least for now.
++ */
++ if (bio->bi_blkg) {
++ blkg_put(bio->bi_blkg);
++ bio->bi_blkg = NULL;
++ }
++#endif
++
+ if (bio->bi_end_io)
+ bio->bi_end_io(bio);
+ }
+diff --git a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
+index 34bf80c5a44bf..307ccb912ccd6 100644
+--- a/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
++++ b/drivers/accel/habanalabs/gaudi2/gaudi2_security.c
+@@ -479,6 +479,7 @@ static const u32 gaudi2_pb_dcr0_edma0_unsecured_regs[] = {
+ mmDCORE0_EDMA0_CORE_CTX_TE_NUMROWS,
+ mmDCORE0_EDMA0_CORE_CTX_IDX,
+ mmDCORE0_EDMA0_CORE_CTX_IDX_INC,
++ mmDCORE0_EDMA0_CORE_WR_COMP_MAX_OUTSTAND,
+ mmDCORE0_EDMA0_CORE_RD_LBW_RATE_LIM_CFG,
+ mmDCORE0_EDMA0_QM_CQ_CFG0_0,
+ mmDCORE0_EDMA0_QM_CQ_CFG0_1,
+diff --git a/drivers/acpi/acpi_processor.c b/drivers/acpi/acpi_processor.c
+index 7a0dd35d62c94..5f5a01ccfc3ab 100644
+--- a/drivers/acpi/acpi_processor.c
++++ b/drivers/acpi/acpi_processor.c
+@@ -400,7 +400,7 @@ static int acpi_processor_add(struct acpi_device *device,
+
+ result = acpi_processor_get_info(device);
+ if (result) /* Processor is not physically present or unavailable */
+- return 0;
++ goto err_clear_driver_data;
+
+ BUG_ON(pr->id >= nr_cpu_ids);
+
+@@ -415,7 +415,7 @@ static int acpi_processor_add(struct acpi_device *device,
+ "BIOS reported wrong ACPI id %d for the processor\n",
+ pr->id);
+ /* Give up, but do not abort the namespace scan. */
+- goto err;
++ goto err_clear_driver_data;
+ }
+ /*
+ * processor_device_array is not cleared on errors to allow buggy BIOS
+@@ -427,12 +427,12 @@ static int acpi_processor_add(struct acpi_device *device,
+ dev = get_cpu_device(pr->id);
+ if (!dev) {
+ result = -ENODEV;
+- goto err;
++ goto err_clear_per_cpu;
+ }
+
+ result = acpi_bind_one(dev, device);
+ if (result)
+- goto err;
++ goto err_clear_per_cpu;
+
+ pr->dev = dev;
+
+@@ -443,10 +443,11 @@ static int acpi_processor_add(struct acpi_device *device,
+ dev_err(dev, "Processor driver could not be attached\n");
+ acpi_unbind_one(dev);
+
+- err:
+- free_cpumask_var(pr->throttling.shared_cpu_map);
+- device->driver_data = NULL;
++ err_clear_per_cpu:
+ per_cpu(processors, pr->id) = NULL;
++ err_clear_driver_data:
++ device->driver_data = NULL;
++ free_cpumask_var(pr->throttling.shared_cpu_map);
+ err_free_pr:
+ kfree(pr);
+ return result;
+diff --git a/drivers/android/binder.c b/drivers/android/binder.c
+index 2d0a24a565084..2ca71b1d36780 100644
+--- a/drivers/android/binder.c
++++ b/drivers/android/binder.c
+@@ -3342,6 +3342,7 @@ static void binder_transaction(struct binder_proc *proc,
+ */
+ copy_size = object_offset - user_offset;
+ if (copy_size && (user_offset > object_offset ||
++ object_offset > tr->data_size ||
+ binder_alloc_copy_user_to_buffer(
+ &target_proc->alloc,
+ t->buffer, user_offset,
+diff --git a/drivers/ata/libata-core.c b/drivers/ata/libata-core.c
+index 74b59b78d278c..71801001ee09f 100644
+--- a/drivers/ata/libata-core.c
++++ b/drivers/ata/libata-core.c
+@@ -5583,8 +5583,10 @@ struct ata_host *ata_host_alloc(struct device *dev, int max_ports)
+ }
+
+ dr = devres_alloc(ata_devres_release, 0, GFP_KERNEL);
+- if (!dr)
++ if (!dr) {
++ kfree(host);
+ goto err_out;
++ }
+
+ devres_add(dev, dr);
+ dev_set_drvdata(dev, host);
+diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
+index 4e08476011039..4116ae0887191 100644
+--- a/drivers/ata/libata-scsi.c
++++ b/drivers/ata/libata-scsi.c
+@@ -242,10 +242,17 @@ void ata_scsi_set_sense_information(struct ata_device *dev,
+ */
+ static void ata_scsi_set_passthru_sense_fields(struct ata_queued_cmd *qc)
+ {
++ struct ata_device *dev = qc->dev;
+ struct scsi_cmnd *cmd = qc->scsicmd;
+ struct ata_taskfile *tf = &qc->result_tf;
+ unsigned char *sb = cmd->sense_buffer;
+
++ if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) {
++ ata_dev_dbg(dev,
++ "missing result TF: can't set ATA PT sense fields\n");
++ return;
++ }
++
+ if ((sb[0] & 0x7f) >= 0x72) {
+ unsigned char *desc;
+ u8 len;
+@@ -924,12 +931,16 @@ static void ata_to_sense_error(unsigned id, u8 drv_stat, u8 drv_err, u8 *sk,
+ */
+ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc)
+ {
++ struct ata_device *dev = qc->dev;
+ struct scsi_cmnd *cmd = qc->scsicmd;
+ struct ata_taskfile *tf = &qc->result_tf;
+- unsigned char *sb = cmd->sense_buffer;
+ u8 sense_key, asc, ascq;
+
+- memset(sb, 0, SCSI_SENSE_BUFFERSIZE);
++ if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) {
++ ata_dev_dbg(dev,
++ "missing result TF: can't generate ATA PT sense data\n");
++ return;
++ }
+
+ /*
+ * Use ata_to_sense_error() to map status register bits
+@@ -976,14 +987,19 @@ static void ata_gen_ata_sense(struct ata_queued_cmd *qc)
+ u64 block;
+ u8 sense_key, asc, ascq;
+
+- memset(sb, 0, SCSI_SENSE_BUFFERSIZE);
+-
+ if (ata_dev_disabled(dev)) {
+ /* Device disabled after error recovery */
+ /* LOGICAL UNIT NOT READY, HARD RESET REQUIRED */
+ ata_scsi_set_sense(dev, cmd, NOT_READY, 0x04, 0x21);
+ return;
+ }
++
++ if (!(qc->flags & ATA_QCFLAG_RTF_FILLED)) {
++ ata_dev_dbg(dev,
++ "missing result TF: can't generate sense data\n");
++ return;
++ }
++
+ /* Use ata_to_sense_error() to map status register bits
+ * onto sense key, asc & ascq.
+ */
+diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
+index 99fc5d9d95d7a..cac022eb1492f 100644
+--- a/drivers/ata/pata_macio.c
++++ b/drivers/ata/pata_macio.c
+@@ -554,7 +554,8 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
+
+ while (sg_len) {
+ /* table overflow should never happen */
+- BUG_ON (pi++ >= MAX_DCMDS);
++ if (WARN_ON_ONCE(pi >= MAX_DCMDS))
++ return AC_ERR_SYSTEM;
+
+ len = (sg_len < MAX_DBDMA_SEG) ? sg_len : MAX_DBDMA_SEG;
+ table->command = cpu_to_le16(write ? OUTPUT_MORE: INPUT_MORE);
+@@ -566,11 +567,13 @@ static enum ata_completion_errors pata_macio_qc_prep(struct ata_queued_cmd *qc)
+ addr += len;
+ sg_len -= len;
+ ++table;
++ ++pi;
+ }
+ }
+
+ /* Should never happen according to Tejun */
+- BUG_ON(!pi);
++ if (WARN_ON_ONCE(!pi))
++ return AC_ERR_SYSTEM;
+
+ /* Convert the last command to an input/output */
+ table--;
+diff --git a/drivers/base/devres.c b/drivers/base/devres.c
+index 8d709dbd4e0c1..e9b0d94aeabd9 100644
+--- a/drivers/base/devres.c
++++ b/drivers/base/devres.c
+@@ -567,6 +567,7 @@ void * devres_open_group(struct device *dev, void *id, gfp_t gfp)
+ grp->id = grp;
+ if (id)
+ grp->id = id;
++ grp->color = 0;
+
+ spin_lock_irqsave(&dev->devres_lock, flags);
+ add_dr(dev, &grp->node[0]);
+diff --git a/drivers/base/regmap/regcache-maple.c b/drivers/base/regmap/regcache-maple.c
+index e424334048549..4c034c8131267 100644
+--- a/drivers/base/regmap/regcache-maple.c
++++ b/drivers/base/regmap/regcache-maple.c
+@@ -110,7 +110,8 @@ static int regcache_maple_drop(struct regmap *map, unsigned int min,
+ struct maple_tree *mt = map->cache;
+ MA_STATE(mas, mt, min, max);
+ unsigned long *entry, *lower, *upper;
+- unsigned long lower_index, lower_last;
++ /* initialized to work around false-positive -Wuninitialized warning */
++ unsigned long lower_index = 0, lower_last = 0;
+ unsigned long upper_index, upper_last;
+ int ret = 0;
+
+diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
+index 3b58839321333..fc001e9f95f61 100644
+--- a/drivers/block/ublk_drv.c
++++ b/drivers/block/ublk_drv.c
+@@ -2664,6 +2664,8 @@ static int ublk_ctrl_start_recovery(struct ublk_device *ub,
+ mutex_lock(&ub->mutex);
+ if (!ublk_can_use_recovery(ub))
+ goto out_unlock;
++ if (!ub->nr_queues_ready)
++ goto out_unlock;
+ /*
+ * START_RECOVERY is only allowd after:
+ *
+diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
+index eeba2d26d1cb9..5890ecd8e9488 100644
+--- a/drivers/bluetooth/btnxpuart.c
++++ b/drivers/bluetooth/btnxpuart.c
+@@ -1326,8 +1326,10 @@ static int btnxpuart_close(struct hci_dev *hdev)
+
+ serdev_device_close(nxpdev->serdev);
+ skb_queue_purge(&nxpdev->txq);
+- kfree_skb(nxpdev->rx_skb);
+- nxpdev->rx_skb = NULL;
++ if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) {
++ kfree_skb(nxpdev->rx_skb);
++ nxpdev->rx_skb = NULL;
++ }
+ clear_bit(BTNXPUART_SERDEV_OPEN, &nxpdev->tx_state);
+ return 0;
+ }
+@@ -1342,8 +1344,10 @@ static int btnxpuart_flush(struct hci_dev *hdev)
+
+ cancel_work_sync(&nxpdev->tx_work);
+
+- kfree_skb(nxpdev->rx_skb);
+- nxpdev->rx_skb = NULL;
++ if (!IS_ERR_OR_NULL(nxpdev->rx_skb)) {
++ kfree_skb(nxpdev->rx_skb);
++ nxpdev->rx_skb = NULL;
++ }
+
+ return 0;
+ }
+diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
+index 34c36f0f781ea..c5606a62f230a 100644
+--- a/drivers/bluetooth/hci_qca.c
++++ b/drivers/bluetooth/hci_qca.c
+@@ -1090,6 +1090,7 @@ static void qca_controller_memdump(struct work_struct *work)
+ qca->memdump_state = QCA_MEMDUMP_COLLECTED;
+ cancel_delayed_work(&qca->ctrl_memdump_timeout);
+ clear_bit(QCA_MEMDUMP_COLLECTION, &qca->flags);
++ clear_bit(QCA_IBS_DISABLED, &qca->flags);
+ mutex_unlock(&qca->hci_memdump_lock);
+ return;
+ }
+diff --git a/drivers/clk/qcom/clk-alpha-pll.c b/drivers/clk/qcom/clk-alpha-pll.c
+index c51647e37df8e..25a7b4b15c56a 100644
+--- a/drivers/clk/qcom/clk-alpha-pll.c
++++ b/drivers/clk/qcom/clk-alpha-pll.c
+@@ -40,7 +40,7 @@
+
+ #define PLL_USER_CTL(p) ((p)->offset + (p)->regs[PLL_OFF_USER_CTL])
+ # define PLL_POST_DIV_SHIFT 8
+-# define PLL_POST_DIV_MASK(p) GENMASK((p)->width, 0)
++# define PLL_POST_DIV_MASK(p) GENMASK((p)->width - 1, 0)
+ # define PLL_ALPHA_EN BIT(24)
+ # define PLL_ALPHA_MODE BIT(25)
+ # define PLL_VCO_SHIFT 20
+@@ -1505,8 +1505,8 @@ clk_trion_pll_postdiv_set_rate(struct clk_hw *hw, unsigned long rate,
+ }
+
+ return regmap_update_bits(regmap, PLL_USER_CTL(pll),
+- PLL_POST_DIV_MASK(pll) << PLL_POST_DIV_SHIFT,
+- val << PLL_POST_DIV_SHIFT);
++ PLL_POST_DIV_MASK(pll) << pll->post_div_shift,
++ val << pll->post_div_shift);
+ }
+
+ const struct clk_ops clk_alpha_pll_postdiv_trion_ops = {
+diff --git a/drivers/clk/qcom/clk-rcg.h b/drivers/clk/qcom/clk-rcg.h
+index d7414361e432e..8e0f3372dc7a8 100644
+--- a/drivers/clk/qcom/clk-rcg.h
++++ b/drivers/clk/qcom/clk-rcg.h
+@@ -198,6 +198,7 @@ extern const struct clk_ops clk_byte2_ops;
+ extern const struct clk_ops clk_pixel_ops;
+ extern const struct clk_ops clk_gfx3d_ops;
+ extern const struct clk_ops clk_rcg2_shared_ops;
++extern const struct clk_ops clk_rcg2_shared_no_init_park_ops;
+ extern const struct clk_ops clk_dp_ops;
+
+ struct clk_rcg_dfs_data {
+diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
+index 30b19bd39d087..bf26c5448f006 100644
+--- a/drivers/clk/qcom/clk-rcg2.c
++++ b/drivers/clk/qcom/clk-rcg2.c
+@@ -1348,6 +1348,36 @@ const struct clk_ops clk_rcg2_shared_ops = {
+ };
+ EXPORT_SYMBOL_GPL(clk_rcg2_shared_ops);
+
++static int clk_rcg2_shared_no_init_park(struct clk_hw *hw)
++{
++ struct clk_rcg2 *rcg = to_clk_rcg2(hw);
++
++ /*
++ * Read the config register so that the parent is properly mapped at
++ * registration time.
++ */
++ regmap_read(rcg->clkr.regmap, rcg->cmd_rcgr + CFG_REG, &rcg->parked_cfg);
++
++ return 0;
++}
++
++/*
++ * Like clk_rcg2_shared_ops but skip the init so that the clk frequency is left
++ * unchanged at registration time.
++ */
++const struct clk_ops clk_rcg2_shared_no_init_park_ops = {
++ .init = clk_rcg2_shared_no_init_park,
++ .enable = clk_rcg2_shared_enable,
++ .disable = clk_rcg2_shared_disable,
++ .get_parent = clk_rcg2_shared_get_parent,
++ .set_parent = clk_rcg2_shared_set_parent,
++ .recalc_rate = clk_rcg2_shared_recalc_rate,
++ .determine_rate = clk_rcg2_determine_rate,
++ .set_rate = clk_rcg2_shared_set_rate,
++ .set_rate_and_parent = clk_rcg2_shared_set_rate_and_parent,
++};
++EXPORT_SYMBOL_GPL(clk_rcg2_shared_no_init_park_ops);
++
+ /* Common APIs to be used for DFS based RCGR */
+ static void clk_rcg2_dfs_populate_freq(struct clk_hw *hw, unsigned int l,
+ struct freq_tbl *f)
+diff --git a/drivers/clk/qcom/gcc-ipq9574.c b/drivers/clk/qcom/gcc-ipq9574.c
+index f8b9a1e93bef2..cdbbf2cc9c5d1 100644
+--- a/drivers/clk/qcom/gcc-ipq9574.c
++++ b/drivers/clk/qcom/gcc-ipq9574.c
+@@ -65,7 +65,7 @@ static const struct clk_parent_data gcc_sleep_clk_data[] = {
+
+ static struct clk_alpha_pll gpll0_main = {
+ .offset = 0x20000,
+- .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
++ .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO],
+ .clkr = {
+ .enable_reg = 0x0b000,
+ .enable_mask = BIT(0),
+@@ -93,7 +93,7 @@ static struct clk_fixed_factor gpll0_out_main_div2 = {
+
+ static struct clk_alpha_pll_postdiv gpll0 = {
+ .offset = 0x20000,
+- .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
++ .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO],
+ .width = 4,
+ .clkr.hw.init = &(const struct clk_init_data) {
+ .name = "gpll0",
+@@ -107,7 +107,7 @@ static struct clk_alpha_pll_postdiv gpll0 = {
+
+ static struct clk_alpha_pll gpll4_main = {
+ .offset = 0x22000,
+- .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
++ .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO],
+ .clkr = {
+ .enable_reg = 0x0b000,
+ .enable_mask = BIT(2),
+@@ -122,7 +122,7 @@ static struct clk_alpha_pll gpll4_main = {
+
+ static struct clk_alpha_pll_postdiv gpll4 = {
+ .offset = 0x22000,
+- .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
++ .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO],
+ .width = 4,
+ .clkr.hw.init = &(const struct clk_init_data) {
+ .name = "gpll4",
+@@ -136,7 +136,7 @@ static struct clk_alpha_pll_postdiv gpll4 = {
+
+ static struct clk_alpha_pll gpll2_main = {
+ .offset = 0x21000,
+- .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
++ .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO],
+ .clkr = {
+ .enable_reg = 0x0b000,
+ .enable_mask = BIT(1),
+@@ -151,7 +151,7 @@ static struct clk_alpha_pll gpll2_main = {
+
+ static struct clk_alpha_pll_postdiv gpll2 = {
+ .offset = 0x21000,
+- .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT],
++ .regs = clk_alpha_pll_regs[CLK_ALPHA_PLL_TYPE_DEFAULT_EVO],
+ .width = 4,
+ .clkr.hw.init = &(const struct clk_init_data) {
+ .name = "gpll2",
+diff --git a/drivers/clk/qcom/gcc-sm8550.c b/drivers/clk/qcom/gcc-sm8550.c
+index 26d7349e76424..eae42f756c13a 100644
+--- a/drivers/clk/qcom/gcc-sm8550.c
++++ b/drivers/clk/qcom/gcc-sm8550.c
+@@ -536,7 +536,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s0_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -551,7 +551,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s1_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -566,7 +566,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s2_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -581,7 +581,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s3_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -596,7 +596,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s4_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -611,7 +611,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s5_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -626,7 +626,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s6_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -641,7 +641,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s7_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -656,7 +656,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s8_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -671,7 +671,7 @@ static struct clk_rcg2 gcc_qupv3_i2c_s9_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ },
+ };
+
+@@ -700,7 +700,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = {
+@@ -717,7 +717,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = {
+@@ -750,7 +750,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s2_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s2_clk_src = {
+@@ -767,7 +767,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = {
+@@ -784,7 +784,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = {
+@@ -801,7 +801,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = {
+@@ -818,7 +818,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s6_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s6_clk_src = {
+@@ -835,7 +835,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s7_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s7_clk_src = {
+@@ -852,7 +852,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s0_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s0_clk_src = {
+@@ -869,7 +869,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s1_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s1_clk_src = {
+@@ -886,7 +886,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s2_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s2_clk_src = {
+@@ -903,7 +903,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s3_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s3_clk_src = {
+@@ -920,7 +920,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s4_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s4_clk_src = {
+@@ -937,7 +937,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s5_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s5_clk_src = {
+@@ -975,7 +975,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s6_clk_src_init = {
+ .parent_data = gcc_parent_data_8,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_8),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s6_clk_src = {
+@@ -992,7 +992,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s7_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s7_clk_src = {
+@@ -1159,7 +1159,7 @@ static struct clk_rcg2 gcc_usb30_prim_master_clk_src = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_shared_no_init_park_ops,
+ },
+ };
+
+diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c
+index a263f0c412f5a..52ea2a0888f37 100644
+--- a/drivers/clk/qcom/gcc-x1e80100.c
++++ b/drivers/clk/qcom/gcc-x1e80100.c
+@@ -670,7 +670,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s0_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s0_clk_src = {
+@@ -687,7 +687,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s1_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s1_clk_src = {
+@@ -719,7 +719,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s2_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s2_clk_src = {
+@@ -736,7 +736,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s3_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s3_clk_src = {
+@@ -768,7 +768,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s4_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s4_clk_src = {
+@@ -785,7 +785,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s5_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s5_clk_src = {
+@@ -802,7 +802,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s6_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s6_clk_src = {
+@@ -819,7 +819,7 @@ static struct clk_init_data gcc_qupv3_wrap0_s7_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap0_s7_clk_src = {
+@@ -836,7 +836,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s0_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s0_clk_src = {
+@@ -853,7 +853,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s1_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s1_clk_src = {
+@@ -870,7 +870,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s2_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s2_clk_src = {
+@@ -887,7 +887,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s3_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s3_clk_src = {
+@@ -904,7 +904,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s4_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s4_clk_src = {
+@@ -921,7 +921,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s5_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s5_clk_src = {
+@@ -938,7 +938,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s6_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s6_clk_src = {
+@@ -955,7 +955,7 @@ static struct clk_init_data gcc_qupv3_wrap1_s7_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap1_s7_clk_src = {
+@@ -972,7 +972,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s0_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s0_clk_src = {
+@@ -989,7 +989,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s1_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s1_clk_src = {
+@@ -1006,7 +1006,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s2_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s2_clk_src = {
+@@ -1023,7 +1023,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s3_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s3_clk_src = {
+@@ -1040,7 +1040,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s4_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s4_clk_src = {
+@@ -1057,7 +1057,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s5_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s5_clk_src = {
+@@ -1074,7 +1074,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s6_clk_src_init = {
+ .parent_data = gcc_parent_data_8,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_8),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s6_clk_src = {
+@@ -1091,7 +1091,7 @@ static struct clk_init_data gcc_qupv3_wrap2_s7_clk_src_init = {
+ .parent_data = gcc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gcc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_shared_ops,
++ .ops = &clk_rcg2_ops,
+ };
+
+ static struct clk_rcg2 gcc_qupv3_wrap2_s7_clk_src = {
+@@ -6203,7 +6203,7 @@ static struct gdsc gcc_usb_0_phy_gdsc = {
+ .pd = {
+ .name = "gcc_usb_0_phy_gdsc",
+ },
+- .pwrsts = PWRSTS_OFF_ON,
++ .pwrsts = PWRSTS_RET_ON,
+ .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
+ };
+
+@@ -6215,7 +6215,7 @@ static struct gdsc gcc_usb_1_phy_gdsc = {
+ .pd = {
+ .name = "gcc_usb_1_phy_gdsc",
+ },
+- .pwrsts = PWRSTS_OFF_ON,
++ .pwrsts = PWRSTS_RET_ON,
+ .flags = POLL_CFG_GDSCR | RETAIN_FF_ENABLE,
+ };
+
+diff --git a/drivers/clk/starfive/clk-starfive-jh7110-sys.c b/drivers/clk/starfive/clk-starfive-jh7110-sys.c
+index 8f5e5abfa178d..17325f17696f6 100644
+--- a/drivers/clk/starfive/clk-starfive-jh7110-sys.c
++++ b/drivers/clk/starfive/clk-starfive-jh7110-sys.c
+@@ -385,6 +385,32 @@ int jh7110_reset_controller_register(struct jh71x0_clk_priv *priv,
+ }
+ EXPORT_SYMBOL_GPL(jh7110_reset_controller_register);
+
++/*
++ * This clock notifier is called when the rate of PLL0 clock is to be changed.
++ * The cpu_root clock should save the curent parent clock and switch its parent
++ * clock to osc before PLL0 rate will be changed. Then switch its parent clock
++ * back after the PLL0 rate is completed.
++ */
++static int jh7110_pll0_clk_notifier_cb(struct notifier_block *nb,
++ unsigned long action, void *data)
++{
++ struct jh71x0_clk_priv *priv = container_of(nb, struct jh71x0_clk_priv, pll_clk_nb);
++ struct clk *cpu_root = priv->reg[JH7110_SYSCLK_CPU_ROOT].hw.clk;
++ int ret = 0;
++
++ if (action == PRE_RATE_CHANGE) {
++ struct clk *osc = clk_get(priv->dev, "osc");
++
++ priv->original_clk = clk_get_parent(cpu_root);
++ ret = clk_set_parent(cpu_root, osc);
++ clk_put(osc);
++ } else if (action == POST_RATE_CHANGE) {
++ ret = clk_set_parent(cpu_root, priv->original_clk);
++ }
++
++ return notifier_from_errno(ret);
++}
++
+ static int __init jh7110_syscrg_probe(struct platform_device *pdev)
+ {
+ struct jh71x0_clk_priv *priv;
+@@ -413,7 +439,10 @@ static int __init jh7110_syscrg_probe(struct platform_device *pdev)
+ if (IS_ERR(priv->pll[0]))
+ return PTR_ERR(priv->pll[0]);
+ } else {
+- clk_put(pllclk);
++ priv->pll_clk_nb.notifier_call = jh7110_pll0_clk_notifier_cb;
++ ret = clk_notifier_register(pllclk, &priv->pll_clk_nb);
++ if (ret)
++ return ret;
+ priv->pll[0] = NULL;
+ }
+
+diff --git a/drivers/clk/starfive/clk-starfive-jh71x0.h b/drivers/clk/starfive/clk-starfive-jh71x0.h
+index 23e052fc15495..e3f441393e48f 100644
+--- a/drivers/clk/starfive/clk-starfive-jh71x0.h
++++ b/drivers/clk/starfive/clk-starfive-jh71x0.h
+@@ -114,6 +114,8 @@ struct jh71x0_clk_priv {
+ spinlock_t rmw_lock;
+ struct device *dev;
+ void __iomem *base;
++ struct clk *original_clk;
++ struct notifier_block pll_clk_nb;
+ struct clk_hw *pll[3];
+ struct jh71x0_clk reg[];
+ };
+diff --git a/drivers/clocksource/timer-imx-tpm.c b/drivers/clocksource/timer-imx-tpm.c
+index bd64a8a8427f3..92c025b70eb62 100644
+--- a/drivers/clocksource/timer-imx-tpm.c
++++ b/drivers/clocksource/timer-imx-tpm.c
+@@ -83,20 +83,28 @@ static u64 notrace tpm_read_sched_clock(void)
+ static int tpm_set_next_event(unsigned long delta,
+ struct clock_event_device *evt)
+ {
+- unsigned long next, now;
++ unsigned long next, prev, now;
+
+- next = tpm_read_counter();
+- next += delta;
++ prev = tpm_read_counter();
++ next = prev + delta;
+ writel(next, timer_base + TPM_C0V);
+ now = tpm_read_counter();
+
++ /*
++ * Need to wait CNT increase at least 1 cycle to make sure
++ * the C0V has been updated into HW.
++ */
++ if ((next & 0xffffffff) != readl(timer_base + TPM_C0V))
++ while (now == tpm_read_counter())
++ ;
++
+ /*
+ * NOTE: We observed in a very small probability, the bus fabric
+ * contention between GPU and A7 may results a few cycles delay
+ * of writing CNT registers which may cause the min_delta event got
+ * missed, so we need add a ETIME check here in case it happened.
+ */
+- return (int)(next - now) <= 0 ? -ETIME : 0;
++ return (now - prev) >= delta ? -ETIME : 0;
+ }
+
+ static int tpm_set_state_oneshot(struct clock_event_device *evt)
+diff --git a/drivers/clocksource/timer-of.c b/drivers/clocksource/timer-of.c
+index c3f54d9912be7..420202bf76e42 100644
+--- a/drivers/clocksource/timer-of.c
++++ b/drivers/clocksource/timer-of.c
+@@ -25,10 +25,7 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq)
+
+ struct clock_event_device *clkevt = &to->clkevt;
+
+- if (of_irq->percpu)
+- free_percpu_irq(of_irq->irq, clkevt);
+- else
+- free_irq(of_irq->irq, clkevt);
++ free_irq(of_irq->irq, clkevt);
+ }
+
+ /**
+@@ -42,9 +39,6 @@ static __init void timer_of_irq_exit(struct of_timer_irq *of_irq)
+ * - Get interrupt number by name
+ * - Get interrupt number by index
+ *
+- * When the interrupt is per CPU, 'request_percpu_irq()' is called,
+- * otherwise 'request_irq()' is used.
+- *
+ * Returns 0 on success, < 0 otherwise
+ */
+ static __init int timer_of_irq_init(struct device_node *np,
+@@ -69,12 +63,9 @@ static __init int timer_of_irq_init(struct device_node *np,
+ return -EINVAL;
+ }
+
+- ret = of_irq->percpu ?
+- request_percpu_irq(of_irq->irq, of_irq->handler,
+- np->full_name, clkevt) :
+- request_irq(of_irq->irq, of_irq->handler,
+- of_irq->flags ? of_irq->flags : IRQF_TIMER,
+- np->full_name, clkevt);
++ ret = request_irq(of_irq->irq, of_irq->handler,
++ of_irq->flags ? of_irq->flags : IRQF_TIMER,
++ np->full_name, clkevt);
+ if (ret) {
+ pr_err("Failed to request irq %d for %pOF\n", of_irq->irq, np);
+ return ret;
+diff --git a/drivers/clocksource/timer-of.h b/drivers/clocksource/timer-of.h
+index a5478f3e8589d..01a2c6b7db065 100644
+--- a/drivers/clocksource/timer-of.h
++++ b/drivers/clocksource/timer-of.h
+@@ -11,7 +11,6 @@
+ struct of_timer_irq {
+ int irq;
+ int index;
+- int percpu;
+ const char *name;
+ unsigned long flags;
+ irq_handler_t handler;
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c
+index 70ef119639381..43af81fcab868 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c
++++ b/drivers/crypto/intel/qat/qat_common/adf_gen2_pfvf.c
+@@ -100,7 +100,9 @@ static u32 adf_gen2_disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr)
+ errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK);
+ ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3);
+
+- errmsk3 &= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled);
++ /* Update only section of errmsk3 related to VF2PF */
++ errmsk3 &= ~ADF_GEN2_ERR_MSK_VF2PF(ADF_GEN2_VF_MSK);
++ errmsk3 |= ADF_GEN2_ERR_MSK_VF2PF(sources | disabled);
+ ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3);
+
+ /* Return the sources of the (new) interrupt(s) */
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_rl.c b/drivers/crypto/intel/qat/qat_common/adf_rl.c
+index 346ef8bee99d9..e782c23fc1bfc 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_rl.c
++++ b/drivers/crypto/intel/qat/qat_common/adf_rl.c
+@@ -1106,6 +1106,7 @@ int adf_rl_init(struct adf_accel_dev *accel_dev)
+ mutex_init(&rl->rl_lock);
+ rl->device_data = &accel_dev->hw_device->rl_data;
+ rl->accel_dev = accel_dev;
++ init_rwsem(&rl->user_input.lock);
+ accel_dev->rate_limiting = rl;
+
+ err_ret:
+diff --git a/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+index 6e24d57e6b98e..c0661ff5e9292 100644
+--- a/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
++++ b/drivers/crypto/intel/qat/qat_dh895xcc/adf_dh895xcc_hw_data.c
+@@ -193,8 +193,12 @@ static u32 disable_pending_vf2pf_interrupts(void __iomem *pmisc_addr)
+ ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3);
+ ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5);
+
+- errmsk3 &= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled);
+- errmsk5 &= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled);
++ /* Update only section of errmsk3 and errmsk5 related to VF2PF */
++ errmsk3 &= ~ADF_DH895XCC_ERR_MSK_VF2PF_L(ADF_DH895XCC_VF_MSK);
++ errmsk5 &= ~ADF_DH895XCC_ERR_MSK_VF2PF_U(ADF_DH895XCC_VF_MSK);
++
++ errmsk3 |= ADF_DH895XCC_ERR_MSK_VF2PF_L(sources | disabled);
++ errmsk5 |= ADF_DH895XCC_ERR_MSK_VF2PF_U(sources | disabled);
+ ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK3, errmsk3);
+ ADF_CSR_WR(pmisc_addr, ADF_GEN2_ERRMSK5, errmsk5);
+
+diff --git a/drivers/crypto/starfive/jh7110-cryp.h b/drivers/crypto/starfive/jh7110-cryp.h
+index 494a74f527064..5ed4ba5da7f9e 100644
+--- a/drivers/crypto/starfive/jh7110-cryp.h
++++ b/drivers/crypto/starfive/jh7110-cryp.h
+@@ -30,6 +30,7 @@
+ #define MAX_KEY_SIZE SHA512_BLOCK_SIZE
+ #define STARFIVE_AES_IV_LEN AES_BLOCK_SIZE
+ #define STARFIVE_AES_CTR_LEN AES_BLOCK_SIZE
++#define STARFIVE_RSA_MAX_KEYSZ 256
+
+ union starfive_aes_csr {
+ u32 v;
+@@ -217,12 +218,11 @@ struct starfive_cryp_request_ctx {
+ struct scatterlist *out_sg;
+ struct ahash_request ahash_fbk_req;
+ size_t total;
+- size_t nents;
+ unsigned int blksize;
+ unsigned int digsize;
+ unsigned long in_sg_len;
+ unsigned char *adata;
+- u8 rsa_data[] __aligned(sizeof(u32));
++ u8 rsa_data[STARFIVE_RSA_MAX_KEYSZ] __aligned(sizeof(u32));
+ };
+
+ struct starfive_cryp_dev *starfive_cryp_find_dev(struct starfive_cryp_ctx *ctx);
+diff --git a/drivers/crypto/starfive/jh7110-rsa.c b/drivers/crypto/starfive/jh7110-rsa.c
+index 33093ba4b13af..a778c48460253 100644
+--- a/drivers/crypto/starfive/jh7110-rsa.c
++++ b/drivers/crypto/starfive/jh7110-rsa.c
+@@ -31,7 +31,6 @@
+ /* A * A * R mod N ==> A */
+ #define CRYPTO_CMD_AARN 0x7
+
+-#define STARFIVE_RSA_MAX_KEYSZ 256
+ #define STARFIVE_RSA_RESET 0x2
+
+ static inline int starfive_pka_wait_done(struct starfive_cryp_ctx *ctx)
+@@ -74,7 +73,7 @@ static int starfive_rsa_montgomery_form(struct starfive_cryp_ctx *ctx,
+ {
+ struct starfive_cryp_dev *cryp = ctx->cryp;
+ struct starfive_cryp_request_ctx *rctx = ctx->rctx;
+- int count = rctx->total / sizeof(u32) - 1;
++ int count = (ALIGN(rctx->total, 4) / 4) - 1;
+ int loop;
+ u32 temp;
+ u8 opsize;
+@@ -251,12 +250,17 @@ static int starfive_rsa_enc_core(struct starfive_cryp_ctx *ctx, int enc)
+ struct starfive_cryp_dev *cryp = ctx->cryp;
+ struct starfive_cryp_request_ctx *rctx = ctx->rctx;
+ struct starfive_rsa_key *key = &ctx->rsa_key;
+- int ret = 0;
++ int ret = 0, shift = 0;
+
+ writel(STARFIVE_RSA_RESET, cryp->base + STARFIVE_PKA_CACR_OFFSET);
+
+- rctx->total = sg_copy_to_buffer(rctx->in_sg, rctx->nents,
+- rctx->rsa_data, rctx->total);
++ if (!IS_ALIGNED(rctx->total, sizeof(u32))) {
++ shift = sizeof(u32) - (rctx->total & 0x3);
++ memset(rctx->rsa_data, 0, shift);
++ }
++
++ rctx->total = sg_copy_to_buffer(rctx->in_sg, sg_nents(rctx->in_sg),
++ rctx->rsa_data + shift, rctx->total);
+
+ if (enc) {
+ key->bitlen = key->e_bitlen;
+@@ -305,7 +309,6 @@ static int starfive_rsa_enc(struct akcipher_request *req)
+ rctx->in_sg = req->src;
+ rctx->out_sg = req->dst;
+ rctx->total = req->src_len;
+- rctx->nents = sg_nents(rctx->in_sg);
+ ctx->rctx = rctx;
+
+ return starfive_rsa_enc_core(ctx, 1);
+diff --git a/drivers/cxl/core/region.c b/drivers/cxl/core/region.c
+index 538ebd5a64fd9..0e30e0a29d400 100644
+--- a/drivers/cxl/core/region.c
++++ b/drivers/cxl/core/region.c
+@@ -1632,10 +1632,13 @@ static int cxl_region_attach_position(struct cxl_region *cxlr,
+ const struct cxl_dport *dport, int pos)
+ {
+ struct cxl_memdev *cxlmd = cxled_to_memdev(cxled);
++ struct cxl_switch_decoder *cxlsd = &cxlrd->cxlsd;
++ struct cxl_decoder *cxld = &cxlsd->cxld;
++ int iw = cxld->interleave_ways;
+ struct cxl_port *iter;
+ int rc;
+
+- if (cxlrd->calc_hb(cxlrd, pos) != dport) {
++ if (dport != cxlrd->cxlsd.target[pos % iw]) {
+ dev_dbg(&cxlr->dev, "%s:%s invalid target position for %s\n",
+ dev_name(&cxlmd->dev), dev_name(&cxled->cxld.dev),
+ dev_name(&cxlrd->cxlsd.cxld.dev));
+@@ -2386,14 +2389,25 @@ static bool cxl_region_update_coordinates(struct cxl_region *cxlr, int nid)
+ return true;
+ }
+
++static int cxl_region_nid(struct cxl_region *cxlr)
++{
++ struct cxl_region_params *p = &cxlr->params;
++ struct cxl_endpoint_decoder *cxled;
++ struct cxl_decoder *cxld;
++
++ guard(rwsem_read)(&cxl_region_rwsem);
++ cxled = p->targets[0];
++ if (!cxled)
++ return NUMA_NO_NODE;
++ cxld = &cxled->cxld;
++ return phys_to_target_node(cxld->hpa_range.start);
++}
++
+ static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
+ unsigned long action, void *arg)
+ {
+ struct cxl_region *cxlr = container_of(nb, struct cxl_region,
+ memory_notifier);
+- struct cxl_region_params *p = &cxlr->params;
+- struct cxl_endpoint_decoder *cxled = p->targets[0];
+- struct cxl_decoder *cxld = &cxled->cxld;
+ struct memory_notify *mnb = arg;
+ int nid = mnb->status_change_nid;
+ int region_nid;
+@@ -2401,7 +2415,7 @@ static int cxl_region_perf_attrs_callback(struct notifier_block *nb,
+ if (nid == NUMA_NO_NODE || action != MEM_ONLINE)
+ return NOTIFY_DONE;
+
+- region_nid = phys_to_target_node(cxld->hpa_range.start);
++ region_nid = cxl_region_nid(cxlr);
+ if (nid != region_nid)
+ return NOTIFY_DONE;
+
+diff --git a/drivers/firmware/cirrus/cs_dsp.c b/drivers/firmware/cirrus/cs_dsp.c
+index 8a347b9384064..89fd63205a6e1 100644
+--- a/drivers/firmware/cirrus/cs_dsp.c
++++ b/drivers/firmware/cirrus/cs_dsp.c
+@@ -796,6 +796,9 @@ int cs_dsp_coeff_write_ctrl(struct cs_dsp_coeff_ctl *ctl,
+
+ lockdep_assert_held(&ctl->dsp->pwr_lock);
+
++ if (ctl->flags && !(ctl->flags & WMFW_CTL_FLAG_WRITEABLE))
++ return -EPERM;
++
+ if (len + off * sizeof(u32) > ctl->len)
+ return -EINVAL;
+
+diff --git a/drivers/gpio/gpio-rockchip.c b/drivers/gpio/gpio-rockchip.c
+index 0bd339813110e..365ab947983ca 100644
+--- a/drivers/gpio/gpio-rockchip.c
++++ b/drivers/gpio/gpio-rockchip.c
+@@ -713,6 +713,7 @@ static int rockchip_gpio_probe(struct platform_device *pdev)
+ return -ENODEV;
+
+ pctldev = of_pinctrl_get(pctlnp);
++ of_node_put(pctlnp);
+ if (!pctldev)
+ return -EPROBE_DEFER;
+
+diff --git a/drivers/gpio/gpio-zynqmp-modepin.c b/drivers/gpio/gpio-zynqmp-modepin.c
+index a0d69387c1532..2f3c9ebfa78d1 100644
+--- a/drivers/gpio/gpio-zynqmp-modepin.c
++++ b/drivers/gpio/gpio-zynqmp-modepin.c
+@@ -146,6 +146,7 @@ static const struct of_device_id modepin_platform_id[] = {
+ { .compatible = "xlnx,zynqmp-gpio-modepin", },
+ { }
+ };
++MODULE_DEVICE_TABLE(of, modepin_platform_id);
+
+ static struct platform_driver modepin_platform_driver = {
+ .driver = {
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+index 936c98a13a240..6dfdff58bffd1 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+@@ -1096,6 +1096,21 @@ static int amdgpu_cs_vm_handling(struct amdgpu_cs_parser *p)
+ unsigned int i;
+ int r;
+
++ /*
++ * We can't use gang submit on with reserved VMIDs when the VM changes
++ * can't be invalidated by more than one engine at the same time.
++ */
++ if (p->gang_size > 1 && !p->adev->vm_manager.concurrent_flush) {
++ for (i = 0; i < p->gang_size; ++i) {
++ struct drm_sched_entity *entity = p->entities[i];
++ struct drm_gpu_scheduler *sched = entity->rq->sched;
++ struct amdgpu_ring *ring = to_amdgpu_ring(sched);
++
++ if (amdgpu_vmid_uses_reserved(vm, ring->vm_hub))
++ return -EINVAL;
++ }
++ }
++
+ r = amdgpu_vm_clear_freed(adev, vm, NULL);
+ if (r)
+ return r;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+index d24d7a1086240..e66546df0bc19 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+@@ -5057,29 +5057,26 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
+ * amdgpu_device_reset_sriov - reset ASIC for SR-IOV vf
+ *
+ * @adev: amdgpu_device pointer
+- * @from_hypervisor: request from hypervisor
++ * @reset_context: amdgpu reset context pointer
+ *
+ * do VF FLR and reinitialize Asic
+ * return 0 means succeeded otherwise failed
+ */
+ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
+- bool from_hypervisor)
++ struct amdgpu_reset_context *reset_context)
+ {
+ int r;
+ struct amdgpu_hive_info *hive = NULL;
+- int retry_limit = 0;
+-
+-retry:
+- amdgpu_amdkfd_pre_reset(adev);
+-
+- amdgpu_device_stop_pending_resets(adev);
+
+- if (from_hypervisor)
++ if (test_bit(AMDGPU_HOST_FLR, &reset_context->flags)) {
++ clear_bit(AMDGPU_HOST_FLR, &reset_context->flags);
+ r = amdgpu_virt_request_full_gpu(adev, true);
+- else
++ } else {
+ r = amdgpu_virt_reset_gpu(adev);
++ }
+ if (r)
+ return r;
++
+ amdgpu_ras_set_fed(adev, false);
+ amdgpu_irq_gpu_reset_resume_helper(adev);
+
+@@ -5089,7 +5086,7 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
+ /* Resume IP prior to SMC */
+ r = amdgpu_device_ip_reinit_early_sriov(adev);
+ if (r)
+- goto error;
++ return r;
+
+ amdgpu_virt_init_data_exchange(adev);
+
+@@ -5100,38 +5097,35 @@ static int amdgpu_device_reset_sriov(struct amdgpu_device *adev,
+ /* now we are okay to resume SMC/CP/SDMA */
+ r = amdgpu_device_ip_reinit_late_sriov(adev);
+ if (r)
+- goto error;
++ return r;
+
+ hive = amdgpu_get_xgmi_hive(adev);
+ /* Update PSP FW topology after reset */
+ if (hive && adev->gmc.xgmi.num_physical_nodes > 1)
+ r = amdgpu_xgmi_update_topology(hive, adev);
+-
+ if (hive)
+ amdgpu_put_xgmi_hive(hive);
++ if (r)
++ return r;
+
+- if (!r) {
+- r = amdgpu_ib_ring_tests(adev);
+-
+- amdgpu_amdkfd_post_reset(adev);
+- }
++ r = amdgpu_ib_ring_tests(adev);
++ if (r)
++ return r;
+
+-error:
+- if (!r && adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
++ if (adev->virt.gim_feature & AMDGIM_FEATURE_GIM_FLR_VRAMLOST) {
+ amdgpu_inc_vram_lost(adev);
+ r = amdgpu_device_recover_vram(adev);
+ }
+- amdgpu_virt_release_full_gpu(adev, true);
++ if (r)
++ return r;
+
+- if (AMDGPU_RETRY_SRIOV_RESET(r)) {
+- if (retry_limit < AMDGPU_MAX_RETRY_LIMIT) {
+- retry_limit++;
+- goto retry;
+- } else
+- DRM_ERROR("GPU reset retry is beyond the retry limit\n");
+- }
++ /* need to be called during full access so we can't do it later like
++ * bare-metal does.
++ */
++ amdgpu_amdkfd_post_reset(adev);
++ amdgpu_virt_release_full_gpu(adev, true);
+
+- return r;
++ return 0;
+ }
+
+ /**
+@@ -5693,6 +5687,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+ int i, r = 0;
+ bool need_emergency_restart = false;
+ bool audio_suspended = false;
++ int retry_limit = AMDGPU_MAX_RETRY_LIMIT;
+
+ /*
+ * Special case: RAS triggered and full reset isn't supported
+@@ -5774,8 +5769,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+
+ cancel_delayed_work_sync(&tmp_adev->delayed_init_work);
+
+- if (!amdgpu_sriov_vf(tmp_adev))
+- amdgpu_amdkfd_pre_reset(tmp_adev);
++ amdgpu_amdkfd_pre_reset(tmp_adev);
+
+ /*
+ * Mark these ASICs to be reseted as untracked first
+@@ -5828,19 +5822,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+ r, adev_to_drm(tmp_adev)->unique);
+ tmp_adev->asic_reset_res = r;
+ }
+-
+- if (!amdgpu_sriov_vf(tmp_adev))
+- /*
+- * Drop all pending non scheduler resets. Scheduler resets
+- * were already dropped during drm_sched_stop
+- */
+- amdgpu_device_stop_pending_resets(tmp_adev);
+ }
+
+ /* Actual ASIC resets if needed.*/
+ /* Host driver will handle XGMI hive reset for SRIOV */
+ if (amdgpu_sriov_vf(adev)) {
+- r = amdgpu_device_reset_sriov(adev, job ? false : true);
++ r = amdgpu_device_reset_sriov(adev, reset_context);
++ if (AMDGPU_RETRY_SRIOV_RESET(r) && (retry_limit--) > 0) {
++ amdgpu_virt_release_full_gpu(adev, true);
++ goto retry;
++ }
+ if (r)
+ adev->asic_reset_res = r;
+
+@@ -5856,6 +5847,16 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+ goto retry;
+ }
+
++ list_for_each_entry(tmp_adev, device_list_handle, reset_list) {
++ /*
++ * Drop any pending non scheduler resets queued before reset is done.
++ * Any reset scheduled after this point would be valid. Scheduler resets
++ * were already dropped during drm_sched_stop and no new ones can come
++ * in before drm_sched_start.
++ */
++ amdgpu_device_stop_pending_resets(tmp_adev);
++ }
++
+ skip_hw_reset:
+
+ /* Post ASIC reset for all devs .*/
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+index 3ecc7ef95172c..30755ce4002dd 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_display.c
+@@ -917,8 +917,7 @@ static int check_tiling_flags_gfx6(struct amdgpu_framebuffer *afb)
+ {
+ u64 micro_tile_mode;
+
+- /* Zero swizzle mode means linear */
+- if (AMDGPU_TILING_GET(afb->tiling_flags, SWIZZLE_MODE) == 0)
++ if (AMDGPU_TILING_GET(afb->tiling_flags, ARRAY_MODE) == 1) /* LINEAR_ALIGNED */
+ return 0;
+
+ micro_tile_mode = AMDGPU_TILING_GET(afb->tiling_flags, MICRO_TILE_MODE);
+@@ -1042,6 +1041,30 @@ static int amdgpu_display_verify_sizes(struct amdgpu_framebuffer *rfb)
+ block_width = 256 / format_info->cpp[i];
+ block_height = 1;
+ block_size_log2 = 8;
++ } else if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) >= AMD_FMT_MOD_TILE_VER_GFX12) {
++ int swizzle = AMD_FMT_MOD_GET(TILE, modifier);
++
++ switch (swizzle) {
++ case AMD_FMT_MOD_TILE_GFX12_256B_2D:
++ block_size_log2 = 8;
++ break;
++ case AMD_FMT_MOD_TILE_GFX12_4K_2D:
++ block_size_log2 = 12;
++ break;
++ case AMD_FMT_MOD_TILE_GFX12_64K_2D:
++ block_size_log2 = 16;
++ break;
++ case AMD_FMT_MOD_TILE_GFX12_256K_2D:
++ block_size_log2 = 18;
++ break;
++ default:
++ drm_dbg_kms(rfb->base.dev,
++ "Gfx12 swizzle mode with unknown block size: %d\n", swizzle);
++ return -EINVAL;
++ }
++
++ get_block_dimensions(block_size_log2, format_info->cpp[i],
++ &block_width, &block_height);
+ } else {
+ int swizzle = AMD_FMT_MOD_GET(TILE, modifier);
+
+@@ -1077,7 +1100,8 @@ static int amdgpu_display_verify_sizes(struct amdgpu_framebuffer *rfb)
+ return ret;
+ }
+
+- if (AMD_FMT_MOD_GET(DCC, modifier)) {
++ if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) <= AMD_FMT_MOD_TILE_VER_GFX11 &&
++ AMD_FMT_MOD_GET(DCC, modifier)) {
+ if (AMD_FMT_MOD_GET(DCC_RETILE, modifier)) {
+ block_size_log2 = get_dcc_block_size(modifier, false, false);
+ get_block_dimensions(block_size_log2 + 8, format_info->cpp[0],
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+index 3adaa46701036..dc65c32bb1b2f 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gem.c
+@@ -347,6 +347,9 @@ int amdgpu_gem_create_ioctl(struct drm_device *dev, void *data,
+ return -EINVAL;
+ }
+
++ /* always clear VRAM */
++ flags |= AMDGPU_GEM_CREATE_VRAM_CLEARED;
++
+ /* create a gem object to contain this object in */
+ if (args->in.domains & (AMDGPU_GEM_DOMAIN_GDS |
+ AMDGPU_GEM_DOMAIN_GWS | AMDGPU_GEM_DOMAIN_OA)) {
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+index 86b096ad0319c..f4478f2d5305c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+@@ -720,7 +720,11 @@ int amdgpu_gmc_flush_gpu_tlb_pasid(struct amdgpu_device *adev, uint16_t pasid,
+ ndw += kiq->pmf->invalidate_tlbs_size;
+
+ spin_lock(&adev->gfx.kiq[inst].ring_lock);
+- amdgpu_ring_alloc(ring, ndw);
++ r = amdgpu_ring_alloc(ring, ndw);
++ if (r) {
++ spin_unlock(&adev->gfx.kiq[inst].ring_lock);
++ goto error_unlock_reset;
++ }
+ if (adev->gmc.flush_tlb_needs_extra_type_2)
+ kiq->pmf->kiq_invalidate_tlbs(ring, pasid, 2, all_hub);
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+index 3d7fcdeaf8cf0..e8f6e4dbc5a4e 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.c
+@@ -406,7 +406,7 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+ if (r || !idle)
+ goto error;
+
+- if (vm->reserved_vmid[vmhub] || (enforce_isolation && (vmhub == AMDGPU_GFXHUB(0)))) {
++ if (amdgpu_vmid_uses_reserved(vm, vmhub)) {
+ r = amdgpu_vmid_grab_reserved(vm, ring, job, &id, fence);
+ if (r || !id)
+ goto error;
+@@ -456,6 +456,19 @@ int amdgpu_vmid_grab(struct amdgpu_vm *vm, struct amdgpu_ring *ring,
+ return r;
+ }
+
++/*
++ * amdgpu_vmid_uses_reserved - check if a VM will use a reserved VMID
++ * @vm: the VM to check
++ * @vmhub: the VMHUB which will be used
++ *
++ * Returns: True if the VM will use a reserved VMID.
++ */
++bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub)
++{
++ return vm->reserved_vmid[vmhub] ||
++ (enforce_isolation && (vmhub == AMDGPU_GFXHUB(0)));
++}
++
+ int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
+ unsigned vmhub)
+ {
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+index fa8c42c83d5d2..240fa67512602 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ids.h
+@@ -78,6 +78,7 @@ void amdgpu_pasid_free_delayed(struct dma_resv *resv,
+
+ bool amdgpu_vmid_had_gpu_reset(struct amdgpu_device *adev,
+ struct amdgpu_vmid *id);
++bool amdgpu_vmid_uses_reserved(struct amdgpu_vm *vm, unsigned int vmhub);
+ int amdgpu_vmid_alloc_reserved(struct amdgpu_device *adev,
+ unsigned vmhub);
+ void amdgpu_vmid_free_reserved(struct amdgpu_device *adev,
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+index b3df27ce76634..ee19af2d20fb1 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+@@ -1584,6 +1584,68 @@ static void psp_ras_ta_check_status(struct psp_context *psp)
+ }
+ }
+
++static int psp_ras_send_cmd(struct psp_context *psp,
++ enum ras_command cmd_id, void *in, void *out)
++{
++ struct ta_ras_shared_memory *ras_cmd;
++ uint32_t cmd = cmd_id;
++ int ret = 0;
++
++ if (!in)
++ return -EINVAL;
++
++ mutex_lock(&psp->ras_context.mutex);
++ ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
++ memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
++
++ switch (cmd) {
++ case TA_RAS_COMMAND__ENABLE_FEATURES:
++ case TA_RAS_COMMAND__DISABLE_FEATURES:
++ memcpy(&ras_cmd->ras_in_message,
++ in, sizeof(ras_cmd->ras_in_message));
++ break;
++ case TA_RAS_COMMAND__TRIGGER_ERROR:
++ memcpy(&ras_cmd->ras_in_message.trigger_error,
++ in, sizeof(ras_cmd->ras_in_message.trigger_error));
++ break;
++ case TA_RAS_COMMAND__QUERY_ADDRESS:
++ memcpy(&ras_cmd->ras_in_message.address,
++ in, sizeof(ras_cmd->ras_in_message.address));
++ break;
++ default:
++ dev_err(psp->adev->dev, "Invalid ras cmd id: %u\n", cmd);
++ ret = -EINVAL;
++ goto err_out;
++ }
++
++ ras_cmd->cmd_id = cmd;
++ ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
++
++ switch (cmd) {
++ case TA_RAS_COMMAND__TRIGGER_ERROR:
++ if (ret || psp->cmd_buf_mem->resp.status)
++ ret = -EINVAL;
++ else if (out)
++ memcpy(out, &ras_cmd->ras_status, sizeof(ras_cmd->ras_status));
++ break;
++ case TA_RAS_COMMAND__QUERY_ADDRESS:
++ if (ret || ras_cmd->ras_status || psp->cmd_buf_mem->resp.status)
++ ret = -EINVAL;
++ else if (out)
++ memcpy(out,
++ &ras_cmd->ras_out_message.address,
++ sizeof(ras_cmd->ras_out_message.address));
++ break;
++ default:
++ break;
++ }
++
++err_out:
++ mutex_unlock(&psp->ras_context.mutex);
++
++ return ret;
++}
++
+ int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
+ {
+ struct ta_ras_shared_memory *ras_cmd;
+@@ -1625,23 +1687,15 @@ int psp_ras_invoke(struct psp_context *psp, uint32_t ta_cmd_id)
+ int psp_ras_enable_features(struct psp_context *psp,
+ union ta_ras_cmd_input *info, bool enable)
+ {
+- struct ta_ras_shared_memory *ras_cmd;
++ enum ras_command cmd_id;
+ int ret;
+
+- if (!psp->ras_context.context.initialized)
++ if (!psp->ras_context.context.initialized || !info)
+ return -EINVAL;
+
+- ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
+- memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
+-
+- if (enable)
+- ras_cmd->cmd_id = TA_RAS_COMMAND__ENABLE_FEATURES;
+- else
+- ras_cmd->cmd_id = TA_RAS_COMMAND__DISABLE_FEATURES;
+-
+- ras_cmd->ras_in_message = *info;
+-
+- ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
++ cmd_id = enable ?
++ TA_RAS_COMMAND__ENABLE_FEATURES : TA_RAS_COMMAND__DISABLE_FEATURES;
++ ret = psp_ras_send_cmd(psp, cmd_id, info, NULL);
+ if (ret)
+ return -EINVAL;
+
+@@ -1665,6 +1719,8 @@ int psp_ras_terminate(struct psp_context *psp)
+
+ psp->ras_context.context.initialized = false;
+
++ mutex_destroy(&psp->ras_context.mutex);
++
+ return ret;
+ }
+
+@@ -1749,9 +1805,10 @@ int psp_ras_initialize(struct psp_context *psp)
+
+ ret = psp_ta_load(psp, &psp->ras_context.context);
+
+- if (!ret && !ras_cmd->ras_status)
++ if (!ret && !ras_cmd->ras_status) {
+ psp->ras_context.context.initialized = true;
+- else {
++ mutex_init(&psp->ras_context.mutex);
++ } else {
+ if (ras_cmd->ras_status)
+ dev_warn(adev->dev, "RAS Init Status: 0x%X\n", ras_cmd->ras_status);
+
+@@ -1765,12 +1822,12 @@ int psp_ras_initialize(struct psp_context *psp)
+ int psp_ras_trigger_error(struct psp_context *psp,
+ struct ta_ras_trigger_error_input *info, uint32_t instance_mask)
+ {
+- struct ta_ras_shared_memory *ras_cmd;
+ struct amdgpu_device *adev = psp->adev;
+ int ret;
+ uint32_t dev_mask;
++ uint32_t ras_status = 0;
+
+- if (!psp->ras_context.context.initialized)
++ if (!psp->ras_context.context.initialized || !info)
+ return -EINVAL;
+
+ switch (info->block_id) {
+@@ -1794,13 +1851,8 @@ int psp_ras_trigger_error(struct psp_context *psp,
+ dev_mask &= AMDGPU_RAS_INST_MASK;
+ info->sub_block_index |= dev_mask;
+
+- ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
+- memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
+-
+- ras_cmd->cmd_id = TA_RAS_COMMAND__TRIGGER_ERROR;
+- ras_cmd->ras_in_message.trigger_error = *info;
+-
+- ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
++ ret = psp_ras_send_cmd(psp,
++ TA_RAS_COMMAND__TRIGGER_ERROR, info, &ras_status);
+ if (ret)
+ return -EINVAL;
+
+@@ -1810,9 +1862,9 @@ int psp_ras_trigger_error(struct psp_context *psp,
+ if (amdgpu_ras_intr_triggered())
+ return 0;
+
+- if (ras_cmd->ras_status == TA_RAS_STATUS__TEE_ERROR_ACCESS_DENIED)
++ if (ras_status == TA_RAS_STATUS__TEE_ERROR_ACCESS_DENIED)
+ return -EACCES;
+- else if (ras_cmd->ras_status)
++ else if (ras_status)
+ return -EINVAL;
+
+ return 0;
+@@ -1822,25 +1874,16 @@ int psp_ras_query_address(struct psp_context *psp,
+ struct ta_ras_query_address_input *addr_in,
+ struct ta_ras_query_address_output *addr_out)
+ {
+- struct ta_ras_shared_memory *ras_cmd;
+ int ret;
+
+- if (!psp->ras_context.context.initialized)
+- return -EINVAL;
+-
+- ras_cmd = (struct ta_ras_shared_memory *)psp->ras_context.context.mem_context.shared_buf;
+- memset(ras_cmd, 0, sizeof(struct ta_ras_shared_memory));
+-
+- ras_cmd->cmd_id = TA_RAS_COMMAND__QUERY_ADDRESS;
+- ras_cmd->ras_in_message.address = *addr_in;
+-
+- ret = psp_ras_invoke(psp, ras_cmd->cmd_id);
+- if (ret || ras_cmd->ras_status || psp->cmd_buf_mem->resp.status)
++ if (!psp->ras_context.context.initialized ||
++ !addr_in || !addr_out)
+ return -EINVAL;
+
+- *addr_out = ras_cmd->ras_out_message.address;
++ ret = psp_ras_send_cmd(psp,
++ TA_RAS_COMMAND__QUERY_ADDRESS, addr_in, addr_out);
+
+- return 0;
++ return ret;
+ }
+ // ras end
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+index 3635303e65484..74a96516c9138 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.h
+@@ -200,6 +200,7 @@ struct psp_xgmi_context {
+ struct psp_ras_context {
+ struct ta_context context;
+ struct amdgpu_ras *ras;
++ struct mutex mutex;
+ };
+
+ #define MEM_TRAIN_SYSTEM_SIGNATURE 0x54534942
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+index 9aff579c6abf5..38face981c3e3 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+@@ -351,6 +351,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
+
+ context->session_id = ta_id;
+
++ mutex_lock(&psp->ras_context.mutex);
+ ret = prep_ta_mem_context(&context->mem_context, shared_buf, shared_buf_len);
+ if (ret)
+ goto err_free_shared_buf;
+@@ -369,6 +370,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
+ ret = -EFAULT;
+
+ err_free_shared_buf:
++ mutex_unlock(&psp->ras_context.mutex);
+ kfree(shared_buf);
+
+ return ret;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+index b11d190ece535..5a9cc043b8583 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_reset.h
+@@ -33,6 +33,7 @@ enum AMDGPU_RESET_FLAGS {
+ AMDGPU_NEED_FULL_RESET = 0,
+ AMDGPU_SKIP_HW_RESET = 1,
+ AMDGPU_SKIP_COREDUMP = 2,
++ AMDGPU_HOST_FLR = 3,
+ };
+
+ struct amdgpu_reset_context {
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+index 2359d1d602751..e12d179a451b6 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+@@ -86,8 +86,10 @@ int amdgpu_virt_request_full_gpu(struct amdgpu_device *adev, bool init)
+
+ if (virt->ops && virt->ops->req_full_gpu) {
+ r = virt->ops->req_full_gpu(adev, init);
+- if (r)
++ if (r) {
++ adev->no_hw_access = true;
+ return r;
++ }
+
+ adev->virt.caps &= ~AMDGPU_SRIOV_CAPS_RUNTIME;
+ }
+@@ -599,7 +601,7 @@ static void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work)
+ if (ret) {
+ adev->virt.vf2pf_update_retry_cnt++;
+ if ((adev->virt.vf2pf_update_retry_cnt >= AMDGPU_VF2PF_UPDATE_MAX_RETRY_LIMIT) &&
+- amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev)) {
++ amdgpu_sriov_runtime(adev)) {
+ amdgpu_ras_set_fed(adev, true);
+ if (amdgpu_reset_domain_schedule(adev->reset_domain,
+ &adev->kfd.reset_work))
+diff --git a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+index ad6431013c738..4ba8eb45ac174 100644
+--- a/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/gfx_v11_0.c
+@@ -4293,11 +4293,11 @@ static int gfx_v11_0_hw_init(void *handle)
+ /* RLC autoload sequence 1: Program rlc ram */
+ if (adev->gfx.imu.funcs->program_rlc_ram)
+ adev->gfx.imu.funcs->program_rlc_ram(adev);
++ /* rlc autoload firmware */
++ r = gfx_v11_0_rlc_backdoor_autoload_enable(adev);
++ if (r)
++ return r;
+ }
+- /* rlc autoload firmware */
+- r = gfx_v11_0_rlc_backdoor_autoload_enable(adev);
+- if (r)
+- return r;
+ } else {
+ if (adev->firmware.load_type == AMDGPU_FW_LOAD_DIRECT) {
+ if (adev->gfx.imu.funcs && (amdgpu_dpm > 0)) {
+diff --git a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+index 77df8c9cbad2f..9e10e552952e1 100644
+--- a/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
++++ b/drivers/gpu/drm/amd/amdgpu/gfxhub_v1_2.c
+@@ -627,9 +627,11 @@ static bool gfxhub_v1_2_query_utcl2_poison_status(struct amdgpu_device *adev,
+
+ status = RREG32_SOC15(GC, GET_INST(GC, xcc_id), regVM_L2_PROTECTION_FAULT_STATUS);
+ fed = REG_GET_FIELD(status, VM_L2_PROTECTION_FAULT_STATUS, FED);
+- /* reset page fault status */
+- WREG32_P(SOC15_REG_OFFSET(GC, GET_INST(GC, xcc_id),
+- regVM_L2_PROTECTION_FAULT_STATUS), 1, ~1);
++ if (!amdgpu_sriov_vf(adev)) {
++ /* clear page fault status and address */
++ WREG32_P(SOC15_REG_OFFSET(GC, GET_INST(GC, xcc_id),
++ regVM_L2_PROTECTION_FAULT_CNTL), 1, ~1);
++ }
+
+ return fed;
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+index f7f4924751020..bd55a7e43f077 100644
+--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+@@ -671,7 +671,8 @@ static int gmc_v9_0_process_interrupt(struct amdgpu_device *adev,
+ (amdgpu_ip_version(adev, GC_HWIP, 0) >= IP_VERSION(9, 4, 2)))
+ return 0;
+
+- WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
++ if (!amdgpu_sriov_vf(adev))
++ WREG32_P(hub->vm_l2_pro_fault_cntl, 1, ~1);
+
+ amdgpu_vm_update_fault_cache(adev, entry->pasid, addr, status, vmhub);
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+index 3cb64c8f71758..18a761d6ef330 100644
+--- a/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/ih_v6_0.c
+@@ -135,6 +135,34 @@ static int ih_v6_0_toggle_ring_interrupts(struct amdgpu_device *adev,
+
+ tmp = RREG32(ih_regs->ih_rb_cntl);
+ tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, RB_ENABLE, (enable ? 1 : 0));
++
++ if (enable) {
++ /* Unset the CLEAR_OVERFLOW bit to make sure the next step
++ * is switching the bit from 0 to 1
++ */
++ tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
++ if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) {
++ if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp))
++ return -ETIMEDOUT;
++ } else {
++ WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
++ }
++
++ /* Clear RB_OVERFLOW bit */
++ tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 1);
++ if (amdgpu_sriov_vf(adev) && amdgpu_sriov_reg_indirect_ih(adev)) {
++ if (psp_reg_program(&adev->psp, ih_regs->psp_reg_id, tmp))
++ return -ETIMEDOUT;
++ } else {
++ WREG32_NO_KIQ(ih_regs->ih_rb_cntl, tmp);
++ }
++
++ /* Unset the CLEAR_OVERFLOW bit immediately so new overflows
++ * can be detected.
++ */
++ tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, WPTR_OVERFLOW_CLEAR, 0);
++ }
++
+ /* enable_intr field is only valid in ring0 */
+ if (ih == &adev->irq.ih)
+ tmp = REG_SET_FIELD(tmp, IH_RB_CNTL, ENABLE_INTR, (enable ? 1 : 0));
+diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
+index 7a1ff298417ab..621761a17ac74 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
++++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_8.c
+@@ -566,9 +566,11 @@ static bool mmhub_v1_8_query_utcl2_poison_status(struct amdgpu_device *adev,
+
+ status = RREG32_SOC15(MMHUB, hub_inst, regVM_L2_PROTECTION_FAULT_STATUS);
+ fed = REG_GET_FIELD(status, VM_L2_PROTECTION_FAULT_STATUS, FED);
+- /* reset page fault status */
+- WREG32_P(SOC15_REG_OFFSET(MMHUB, hub_inst,
+- regVM_L2_PROTECTION_FAULT_STATUS), 1, ~1);
++ if (!amdgpu_sriov_vf(adev)) {
++ /* clear page fault status and address */
++ WREG32_P(SOC15_REG_OFFSET(MMHUB, hub_inst,
++ regVM_L2_PROTECTION_FAULT_CNTL), 1, ~1);
++ }
+
+ return fed;
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+index 0c7275bca8f73..f4c47492e0cd5 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
++++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_ai.c
+@@ -292,6 +292,7 @@ static void xgpu_ai_mailbox_flr_work(struct work_struct *work)
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
++ set_bit(AMDGPU_HOST_FLR, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+ }
+@@ -319,7 +320,7 @@ static int xgpu_ai_mailbox_rcv_irq(struct amdgpu_device *adev,
+
+ switch (event) {
+ case IDH_FLR_NOTIFICATION:
+- if (amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev))
++ if (amdgpu_sriov_runtime(adev))
+ WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
+ &adev->virt.flr_work),
+ "Failed to queue work! at %s",
+diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+index aba00d961627b..14cc7910e5cfc 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
++++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_nv.c
+@@ -328,6 +328,7 @@ static void xgpu_nv_mailbox_flr_work(struct work_struct *work)
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
++ set_bit(AMDGPU_HOST_FLR, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+ }
+@@ -358,7 +359,7 @@ static int xgpu_nv_mailbox_rcv_irq(struct amdgpu_device *adev,
+
+ switch (event) {
+ case IDH_FLR_NOTIFICATION:
+- if (amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev))
++ if (amdgpu_sriov_runtime(adev))
+ WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
+ &adev->virt.flr_work),
+ "Failed to queue work! at %s",
+diff --git a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+index 59f53c7433620..78cd07744ebe4 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
++++ b/drivers/gpu/drm/amd/amdgpu/mxgpu_vi.c
+@@ -529,6 +529,7 @@ static void xgpu_vi_mailbox_flr_work(struct work_struct *work)
+ reset_context.method = AMD_RESET_METHOD_NONE;
+ reset_context.reset_req_dev = adev;
+ clear_bit(AMDGPU_NEED_FULL_RESET, &reset_context.flags);
++ set_bit(AMDGPU_HOST_FLR, &reset_context.flags);
+
+ amdgpu_device_gpu_recover(adev, NULL, &reset_context);
+ }
+@@ -560,7 +561,7 @@ static int xgpu_vi_mailbox_rcv_irq(struct amdgpu_device *adev,
+ r = xgpu_vi_mailbox_rcv_msg(adev, IDH_FLR_NOTIFICATION);
+
+ /* only handle FLR_NOTIFY now */
+- if (!r && !amdgpu_in_reset(adev))
++ if (!r)
+ WARN_ONCE(!amdgpu_reset_domain_schedule(adev->reset_domain,
+ &adev->virt.flr_work),
+ "Failed to queue work! at %s",
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+index 382a41c5b5152..27e641f176289 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+@@ -4237,7 +4237,7 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+ struct amdgpu_dm_backlight_caps caps;
+ struct dc_link *link;
+ u32 brightness;
+- bool rc;
++ bool rc, reallow_idle = false;
+
+ amdgpu_dm_update_backlight_caps(dm, bl_idx);
+ caps = dm->backlight_caps[bl_idx];
+@@ -4250,6 +4250,12 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+ link = (struct dc_link *)dm->backlight_link[bl_idx];
+
+ /* Change brightness based on AUX property */
++ mutex_lock(&dm->dc_lock);
++ if (dm->dc->caps.ips_support && dm->dc->ctx->dmub_srv->idle_allowed) {
++ dc_allow_idle_optimizations(dm->dc, false);
++ reallow_idle = true;
++ }
++
+ if (caps.aux_support) {
+ rc = dc_link_set_backlight_level_nits(link, true, brightness,
+ AUX_BL_DEFAULT_TRANSITION_TIME_MS);
+@@ -4261,6 +4267,11 @@ static void amdgpu_dm_backlight_set_level(struct amdgpu_display_manager *dm,
+ DRM_DEBUG("DM: Failed to update backlight on eDP[%d]\n", bl_idx);
+ }
+
++ if (dm->dc->caps.ips_support && reallow_idle)
++ dc_allow_idle_optimizations(dm->dc, true);
++
++ mutex_unlock(&dm->dc_lock);
++
+ if (rc)
+ dm->actual_brightness[bl_idx] = user_brightness;
+ }
+@@ -7291,7 +7302,7 @@ static int dm_update_mst_vcpi_slots_for_dsc(struct drm_atomic_state *state,
+ }
+ }
+
+- if (j == dc_state->stream_count)
++ if (j == dc_state->stream_count || pbn_div == 0)
+ continue;
+
+ slot_num = DIV_ROUND_UP(pbn, pbn_div);
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+index 70e45d980bb93..7d47acdd11d55 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+@@ -1400,8 +1400,6 @@ static bool amdgpu_dm_plane_format_mod_supported(struct drm_plane *plane,
+ const struct drm_format_info *info = drm_format_info(format);
+ int i;
+
+- enum dm_micro_swizzle microtile = amdgpu_dm_plane_modifier_gfx9_swizzle_mode(modifier) & 3;
+-
+ if (!info)
+ return false;
+
+@@ -1423,29 +1421,34 @@ static bool amdgpu_dm_plane_format_mod_supported(struct drm_plane *plane,
+ if (i == plane->modifier_count)
+ return false;
+
+- /*
+- * For D swizzle the canonical modifier depends on the bpp, so check
+- * it here.
+- */
+- if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) == AMD_FMT_MOD_TILE_VER_GFX9 &&
+- adev->family >= AMDGPU_FAMILY_NV) {
+- if (microtile == MICRO_SWIZZLE_D && info->cpp[0] == 4)
+- return false;
+- }
+-
+- if (adev->family >= AMDGPU_FAMILY_RV && microtile == MICRO_SWIZZLE_D &&
+- info->cpp[0] < 8)
+- return false;
++ /* GFX12 doesn't have these limitations. */
++ if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) <= AMD_FMT_MOD_TILE_VER_GFX11) {
++ enum dm_micro_swizzle microtile = amdgpu_dm_plane_modifier_gfx9_swizzle_mode(modifier) & 3;
+
+- if (amdgpu_dm_plane_modifier_has_dcc(modifier)) {
+- /* Per radeonsi comments 16/64 bpp are more complicated. */
+- if (info->cpp[0] != 4)
+- return false;
+- /* We support multi-planar formats, but not when combined with
+- * additional DCC metadata planes.
++ /*
++ * For D swizzle the canonical modifier depends on the bpp, so check
++ * it here.
+ */
+- if (info->num_planes > 1)
++ if (AMD_FMT_MOD_GET(TILE_VERSION, modifier) == AMD_FMT_MOD_TILE_VER_GFX9 &&
++ adev->family >= AMDGPU_FAMILY_NV) {
++ if (microtile == MICRO_SWIZZLE_D && info->cpp[0] == 4)
++ return false;
++ }
++
++ if (adev->family >= AMDGPU_FAMILY_RV && microtile == MICRO_SWIZZLE_D &&
++ info->cpp[0] < 8)
+ return false;
++
++ if (amdgpu_dm_plane_modifier_has_dcc(modifier)) {
++ /* Per radeonsi comments 16/64 bpp are more complicated. */
++ if (info->cpp[0] != 4)
++ return false;
++ /* We support multi-planar formats, but not when combined with
++ * additional DCC metadata planes.
++ */
++ if (info->num_planes > 1)
++ return false;
++ }
+ }
+
+ return true;
+diff --git a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+index 2293a92df3bed..22d2ab8ce7f8b 100644
+--- a/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
++++ b/drivers/gpu/drm/amd/display/dc/dc_dmub_srv.c
+@@ -245,7 +245,9 @@ bool dc_dmub_srv_cmd_run_list(struct dc_dmub_srv *dc_dmub_srv, unsigned int coun
+ if (status == DMUB_STATUS_POWER_STATE_D3)
+ return false;
+
+- dmub_srv_wait_for_idle(dmub, 100000);
++ status = dmub_srv_wait_for_idle(dmub, 100000);
++ if (status != DMUB_STATUS_OK)
++ return false;
+
+ /* Requeue the command. */
+ status = dmub_srv_cmd_queue(dmub, &cmd_list[i]);
+@@ -511,7 +513,8 @@ void dc_dmub_srv_get_visual_confirm_color_cmd(struct dc *dc, struct pipe_ctx *pi
+ union dmub_rb_cmd cmd = { 0 };
+ unsigned int panel_inst = 0;
+
+- dc_get_edp_link_panel_inst(dc, pipe_ctx->stream->link, &panel_inst);
++ if (!dc_get_edp_link_panel_inst(dc, pipe_ctx->stream->link, &panel_inst))
++ return;
+
+ memset(&cmd, 0, sizeof(cmd));
+
+diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
+index c6f859871d11e..7e4ca2022d649 100644
+--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
++++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_hubbub.c
+@@ -595,7 +595,8 @@ static bool hubbub2_program_watermarks(
+ hubbub1->base.ctx->dc->clk_mgr->clks.p_state_change_support == false)
+ safe_to_lower = true;
+
+- hubbub1_program_pstate_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower);
++ if (hubbub1_program_pstate_watermarks(hubbub, watermarks, refclk_mhz, safe_to_lower))
++ wm_pending = true;
+
+ REG_SET(DCHUBBUB_ARB_SAT_LEVEL, 0,
+ DCHUBBUB_ARB_SAT_LEVEL, 60 * refclk_mhz);
+diff --git a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+index 3e919f5c00ca2..fee1df342f122 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
++++ b/drivers/gpu/drm/amd/display/dc/dml2/display_mode_core.c
+@@ -4282,7 +4282,7 @@ static void CalculateSwathAndDETConfiguration(struct display_mode_lib_scratch_st
+ }
+
+ *p->compbuf_reserved_space_64b = 2 * p->PixelChunkSizeInKByte * 1024 / 64;
+- if (p->UnboundedRequestEnabled) {
++ if (*p->UnboundedRequestEnabled) {
+ *p->compbuf_reserved_space_64b = dml_max(*p->compbuf_reserved_space_64b,
+ (dml_float_t)(p->ROBBufferSizeInKByte * 1024/64)
+ - (dml_float_t)(RoundedUpSwathSizeBytesY[SurfaceDoingUnboundedRequest] * TTUFIFODEPTH / MAXIMUMCOMPRESSION/64));
+diff --git a/drivers/gpu/drm/amd/display/dc/link/link_factory.c b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+index cf22b8f28ba6c..72df9bdfb23ff 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/link_factory.c
++++ b/drivers/gpu/drm/amd/display/dc/link/link_factory.c
+@@ -611,14 +611,14 @@ static bool construct_phy(struct dc_link *link,
+ link->link_enc =
+ link->dc->res_pool->funcs->link_enc_create(dc_ctx, &enc_init_data);
+
+- DC_LOG_DC("BIOS object table - DP_IS_USB_C: %d", link->link_enc->features.flags.bits.DP_IS_USB_C);
+- DC_LOG_DC("BIOS object table - IS_DP2_CAPABLE: %d", link->link_enc->features.flags.bits.IS_DP2_CAPABLE);
+-
+ if (!link->link_enc) {
+ DC_ERROR("Failed to create link encoder!\n");
+ goto link_enc_create_fail;
+ }
+
++ DC_LOG_DC("BIOS object table - DP_IS_USB_C: %d", link->link_enc->features.flags.bits.DP_IS_USB_C);
++ DC_LOG_DC("BIOS object table - IS_DP2_CAPABLE: %d", link->link_enc->features.flags.bits.IS_DP2_CAPABLE);
++
+ /* Update link encoder tracking variables. These are used for the dynamic
+ * assignment of link encoders to streams.
+ */
+diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+index b8e704dbe9567..8c0dea6f75bf1 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
++++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+@@ -1659,8 +1659,7 @@ bool perform_link_training_with_retries(
+ if (status == LINK_TRAINING_ABORT) {
+ enum dc_connection_type type = dc_connection_none;
+
+- link_detect_connection_type(link, &type);
+- if (type == dc_connection_none) {
++ if (link_detect_connection_type(link, &type) && type == dc_connection_none) {
+ DC_LOG_HW_LINK_TRAINING("%s: Aborting training because sink unplugged\n", __func__);
+ break;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
+index 4ce0f4bf1d9bb..3329eaecfb15b 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn315/dcn315_resource.c
+@@ -1756,7 +1756,7 @@ static int dcn315_populate_dml_pipes_from_context(
+ bool split_required = pipe->stream->timing.pix_clk_100hz >= dcn_get_max_non_odm_pix_rate_100hz(&dc->dml.soc)
+ || (pipe->plane_state && pipe->plane_state->src_rect.width > 5120);
+
+- if (remaining_det_segs > MIN_RESERVED_DET_SEGS)
++ if (remaining_det_segs > MIN_RESERVED_DET_SEGS && crb_pipes != 0)
+ pipes[pipe_cnt].pipe.src.det_size_override += (remaining_det_segs - MIN_RESERVED_DET_SEGS) / crb_pipes +
+ (crb_idx < (remaining_det_segs - MIN_RESERVED_DET_SEGS) % crb_pipes ? 1 : 0);
+ if (pipes[pipe_cnt].pipe.src.det_size_override > 2 * DCN3_15_MAX_DET_SEGS) {
+diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
+index 182e7532dda8a..d77836cef5635 100644
+--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
++++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp1_execution.c
+@@ -433,17 +433,20 @@ static enum mod_hdcp_status authenticated_dp(struct mod_hdcp *hdcp,
+ }
+
+ if (status == MOD_HDCP_STATUS_SUCCESS)
+- mod_hdcp_execute_and_set(mod_hdcp_read_bstatus,
++ if (!mod_hdcp_execute_and_set(mod_hdcp_read_bstatus,
+ &input->bstatus_read, &status,
+- hdcp, "bstatus_read");
++ hdcp, "bstatus_read"))
++ goto out;
+ if (status == MOD_HDCP_STATUS_SUCCESS)
+- mod_hdcp_execute_and_set(check_link_integrity_dp,
++ if (!mod_hdcp_execute_and_set(check_link_integrity_dp,
+ &input->link_integrity_check, &status,
+- hdcp, "link_integrity_check");
++ hdcp, "link_integrity_check"))
++ goto out;
+ if (status == MOD_HDCP_STATUS_SUCCESS)
+- mod_hdcp_execute_and_set(check_no_reauthentication_request_dp,
++ if (!mod_hdcp_execute_and_set(check_no_reauthentication_request_dp,
+ &input->reauth_request_check, &status,
+- hdcp, "reauth_request_check");
++ hdcp, "reauth_request_check"))
++ goto out;
+ out:
+ return status;
+ }
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+index 95f690b70c057..45d053497f497 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+@@ -2257,7 +2257,8 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
+ smu_dpm_ctx->dpm_level = level;
+ }
+
+- if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
++ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
++ smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
+ index = fls(smu->workload_mask);
+ index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
+ workload[0] = smu->workload_setting[index];
+@@ -2336,7 +2337,8 @@ static int smu_switch_power_profile(void *handle,
+ workload[0] = smu->workload_setting[index];
+ }
+
+- if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
++ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
++ smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
+ smu_bump_power_profile_mode(smu, workload, 0);
+
+ return 0;
+diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
+index 6747c10da298e..48c5809e01b57 100644
+--- a/drivers/gpu/drm/i915/display/intel_display_types.h
++++ b/drivers/gpu/drm/i915/display/intel_display_types.h
+@@ -1840,6 +1840,10 @@ struct intel_dp {
+ unsigned long last_oui_write;
+
+ bool colorimetry_support;
++
++ struct {
++ unsigned long mask;
++ } quirks;
+ };
+
+ enum lspcon_vendor {
+diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
+index 8ea00c8ee74a3..a7d91ca1d8baf 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp.c
++++ b/drivers/gpu/drm/i915/display/intel_dp.c
+@@ -79,6 +79,7 @@
+ #include "intel_pch_display.h"
+ #include "intel_pps.h"
+ #include "intel_psr.h"
++#include "intel_quirks.h"
+ #include "intel_tc.h"
+ #include "intel_vdsc.h"
+ #include "intel_vrr.h"
+@@ -3941,6 +3942,7 @@ intel_edp_init_dpcd(struct intel_dp *intel_dp, struct intel_connector *connector
+
+ drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc,
+ drm_dp_is_branch(intel_dp->dpcd));
++ intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident);
+
+ /*
+ * Read the eDP display control registers.
+@@ -4053,6 +4055,8 @@ intel_dp_get_dpcd(struct intel_dp *intel_dp)
+ drm_dp_read_desc(&intel_dp->aux, &intel_dp->desc,
+ drm_dp_is_branch(intel_dp->dpcd));
+
++ intel_init_dpcd_quirks(intel_dp, &intel_dp->desc.ident);
++
+ intel_dp_update_sink_caps(intel_dp);
+ }
+
+diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.c b/drivers/gpu/drm/i915/display/intel_dp_aux.c
+index b8a53bb174dab..be58185a77c01 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp_aux.c
++++ b/drivers/gpu/drm/i915/display/intel_dp_aux.c
+@@ -13,6 +13,7 @@
+ #include "intel_dp_aux.h"
+ #include "intel_dp_aux_regs.h"
+ #include "intel_pps.h"
++#include "intel_quirks.h"
+ #include "intel_tc.h"
+
+ #define AUX_CH_NAME_BUFSIZE 6
+@@ -142,16 +143,21 @@ static int intel_dp_aux_sync_len(void)
+ return precharge + preamble;
+ }
+
+-int intel_dp_aux_fw_sync_len(void)
++int intel_dp_aux_fw_sync_len(struct intel_dp *intel_dp)
+ {
++ int precharge = 10; /* 10-16 */
++ int preamble = 8;
++
+ /*
+ * We faced some glitches on Dell Precision 5490 MTL laptop with panel:
+ * "Manufacturer: AUO, Model: 63898" when using HW default 18. Using 20
+ * is fixing these problems with the panel. It is still within range
+- * mentioned in eDP specification.
++ * mentioned in eDP specification. Increasing Fast Wake sync length is
++ * causing problems with other panels: increase length as a quirk for
++ * this specific laptop.
+ */
+- int precharge = 12; /* 10-16 */
+- int preamble = 8;
++ if (intel_has_dpcd_quirk(intel_dp, QUIRK_FW_SYNC_LEN))
++ precharge += 2;
+
+ return precharge + preamble;
+ }
+@@ -211,7 +217,7 @@ static u32 skl_get_aux_send_ctl(struct intel_dp *intel_dp,
+ DP_AUX_CH_CTL_TIME_OUT_MAX |
+ DP_AUX_CH_CTL_RECEIVE_ERROR |
+ DP_AUX_CH_CTL_MESSAGE_SIZE(send_bytes) |
+- DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(intel_dp_aux_fw_sync_len()) |
++ DP_AUX_CH_CTL_FW_SYNC_PULSE_SKL(intel_dp_aux_fw_sync_len(intel_dp)) |
+ DP_AUX_CH_CTL_SYNC_PULSE_SKL(intel_dp_aux_sync_len());
+
+ if (intel_tc_port_in_tbt_alt_mode(dig_port))
+diff --git a/drivers/gpu/drm/i915/display/intel_dp_aux.h b/drivers/gpu/drm/i915/display/intel_dp_aux.h
+index 76d1f2ed7c2f4..593f58fafab71 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp_aux.h
++++ b/drivers/gpu/drm/i915/display/intel_dp_aux.h
+@@ -20,6 +20,6 @@ enum aux_ch intel_dp_aux_ch(struct intel_encoder *encoder);
+
+ void intel_dp_aux_irq_handler(struct drm_i915_private *i915);
+ u32 intel_dp_aux_pack(const u8 *src, int src_bytes);
+-int intel_dp_aux_fw_sync_len(void);
++int intel_dp_aux_fw_sync_len(struct intel_dp *intel_dp);
+
+ #endif /* __INTEL_DP_AUX_H__ */
+diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
+index 3c7da862222bf..7173ffc7c66c1 100644
+--- a/drivers/gpu/drm/i915/display/intel_psr.c
++++ b/drivers/gpu/drm/i915/display/intel_psr.c
+@@ -1356,7 +1356,7 @@ static bool _compute_alpm_params(struct intel_dp *intel_dp,
+ int tfw_exit_latency = 20; /* eDP spec */
+ int phy_wake = 4; /* eDP spec */
+ int preamble = 8; /* eDP spec */
+- int precharge = intel_dp_aux_fw_sync_len() - preamble;
++ int precharge = intel_dp_aux_fw_sync_len(intel_dp) - preamble;
+ u8 max_wake_lines;
+
+ io_wake_time = max(precharge, io_buffer_wake_time(crtc_state)) +
+diff --git a/drivers/gpu/drm/i915/display/intel_quirks.c b/drivers/gpu/drm/i915/display/intel_quirks.c
+index 14d5fefc9c5b2..dfd8b4960e6d6 100644
+--- a/drivers/gpu/drm/i915/display/intel_quirks.c
++++ b/drivers/gpu/drm/i915/display/intel_quirks.c
+@@ -14,6 +14,11 @@ static void intel_set_quirk(struct intel_display *display, enum intel_quirk_id q
+ display->quirks.mask |= BIT(quirk);
+ }
+
++static void intel_set_dpcd_quirk(struct intel_dp *intel_dp, enum intel_quirk_id quirk)
++{
++ intel_dp->quirks.mask |= BIT(quirk);
++}
++
+ /*
+ * Some machines (Lenovo U160) do not work with SSC on LVDS for some reason
+ */
+@@ -65,6 +70,14 @@ static void quirk_no_pps_backlight_power_hook(struct intel_display *display)
+ drm_info(display->drm, "Applying no pps backlight power quirk\n");
+ }
+
++static void quirk_fw_sync_len(struct intel_dp *intel_dp)
++{
++ struct intel_display *display = to_intel_display(intel_dp);
++
++ intel_set_dpcd_quirk(intel_dp, QUIRK_FW_SYNC_LEN);
++ drm_info(display->drm, "Applying Fast Wake sync pulse count quirk\n");
++}
++
+ struct intel_quirk {
+ int device;
+ int subsystem_vendor;
+@@ -72,6 +85,21 @@ struct intel_quirk {
+ void (*hook)(struct intel_display *display);
+ };
+
++struct intel_dpcd_quirk {
++ int device;
++ int subsystem_vendor;
++ int subsystem_device;
++ u8 sink_oui[3];
++ u8 sink_device_id[6];
++ void (*hook)(struct intel_dp *intel_dp);
++};
++
++#define SINK_OUI(first, second, third) { (first), (second), (third) }
++#define SINK_DEVICE_ID(first, second, third, fourth, fifth, sixth) \
++ { (first), (second), (third), (fourth), (fifth), (sixth) }
++
++#define SINK_DEVICE_ID_ANY SINK_DEVICE_ID(0, 0, 0, 0, 0, 0)
++
+ /* For systems that don't have a meaningful PCI subdevice/subvendor ID */
+ struct intel_dmi_quirk {
+ void (*hook)(struct intel_display *display);
+@@ -203,6 +231,18 @@ static struct intel_quirk intel_quirks[] = {
+ { 0x0f31, 0x103c, 0x220f, quirk_invert_brightness },
+ };
+
++static struct intel_dpcd_quirk intel_dpcd_quirks[] = {
++ /* Dell Precision 5490 */
++ {
++ .device = 0x7d55,
++ .subsystem_vendor = 0x1028,
++ .subsystem_device = 0x0cc7,
++ .sink_oui = SINK_OUI(0x38, 0xec, 0x11),
++ .hook = quirk_fw_sync_len,
++ },
++
++};
++
+ void intel_init_quirks(struct intel_display *display)
+ {
+ struct pci_dev *d = to_pci_dev(display->drm->dev);
+@@ -224,7 +264,35 @@ void intel_init_quirks(struct intel_display *display)
+ }
+ }
+
++void intel_init_dpcd_quirks(struct intel_dp *intel_dp,
++ const struct drm_dp_dpcd_ident *ident)
++{
++ struct intel_display *display = to_intel_display(intel_dp);
++ struct pci_dev *d = to_pci_dev(display->drm->dev);
++ int i;
++
++ for (i = 0; i < ARRAY_SIZE(intel_dpcd_quirks); i++) {
++ struct intel_dpcd_quirk *q = &intel_dpcd_quirks[i];
++
++ if (d->device == q->device &&
++ (d->subsystem_vendor == q->subsystem_vendor ||
++ q->subsystem_vendor == PCI_ANY_ID) &&
++ (d->subsystem_device == q->subsystem_device ||
++ q->subsystem_device == PCI_ANY_ID) &&
++ !memcmp(q->sink_oui, ident->oui, sizeof(ident->oui)) &&
++ (!memcmp(q->sink_device_id, ident->device_id,
++ sizeof(ident->device_id)) ||
++ !memchr_inv(q->sink_device_id, 0, sizeof(q->sink_device_id))))
++ q->hook(intel_dp);
++ }
++}
++
+ bool intel_has_quirk(struct intel_display *display, enum intel_quirk_id quirk)
+ {
+ return display->quirks.mask & BIT(quirk);
+ }
++
++bool intel_has_dpcd_quirk(struct intel_dp *intel_dp, enum intel_quirk_id quirk)
++{
++ return intel_dp->quirks.mask & BIT(quirk);
++}
+diff --git a/drivers/gpu/drm/i915/display/intel_quirks.h b/drivers/gpu/drm/i915/display/intel_quirks.h
+index 151c8f4ae5760..cafdebda75354 100644
+--- a/drivers/gpu/drm/i915/display/intel_quirks.h
++++ b/drivers/gpu/drm/i915/display/intel_quirks.h
+@@ -9,6 +9,8 @@
+ #include <linux/types.h>
+
+ struct intel_display;
++struct intel_dp;
++struct drm_dp_dpcd_ident;
+
+ enum intel_quirk_id {
+ QUIRK_BACKLIGHT_PRESENT,
+@@ -17,9 +19,13 @@ enum intel_quirk_id {
+ QUIRK_INVERT_BRIGHTNESS,
+ QUIRK_LVDS_SSC_DISABLE,
+ QUIRK_NO_PPS_BACKLIGHT_POWER_HOOK,
++ QUIRK_FW_SYNC_LEN,
+ };
+
+ void intel_init_quirks(struct intel_display *display);
++void intel_init_dpcd_quirks(struct intel_dp *intel_dp,
++ const struct drm_dp_dpcd_ident *ident);
+ bool intel_has_quirk(struct intel_display *display, enum intel_quirk_id quirk);
++bool intel_has_dpcd_quirk(struct intel_dp *intel_dp, enum intel_quirk_id quirk);
+
+ #endif /* __INTEL_QUIRKS_H__ */
+diff --git a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c
+index 453d855dd1de7..3d3191deb0ab9 100644
+--- a/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c
++++ b/drivers/gpu/drm/i915/gt/uc/intel_gsc_uc.c
+@@ -302,7 +302,7 @@ void intel_gsc_uc_load_start(struct intel_gsc_uc *gsc)
+ {
+ struct intel_gt *gt = gsc_uc_to_gt(gsc);
+
+- if (!intel_uc_fw_is_loadable(&gsc->fw))
++ if (!intel_uc_fw_is_loadable(&gsc->fw) || intel_uc_fw_is_in_error(&gsc->fw))
+ return;
+
+ if (intel_gsc_uc_fw_init_done(gsc))
+diff --git a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+index 9a431726c8d5b..ac7b3aad2222e 100644
+--- a/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
++++ b/drivers/gpu/drm/i915/gt/uc/intel_uc_fw.h
+@@ -258,6 +258,11 @@ static inline bool intel_uc_fw_is_running(struct intel_uc_fw *uc_fw)
+ return __intel_uc_fw_status(uc_fw) == INTEL_UC_FIRMWARE_RUNNING;
+ }
+
++static inline bool intel_uc_fw_is_in_error(struct intel_uc_fw *uc_fw)
++{
++ return intel_uc_fw_status_to_error(__intel_uc_fw_status(uc_fw)) != 0;
++}
++
+ static inline bool intel_uc_fw_is_overridden(const struct intel_uc_fw *uc_fw)
+ {
+ return uc_fw->user_overridden;
+diff --git a/drivers/gpu/drm/i915/i915_sw_fence.c b/drivers/gpu/drm/i915/i915_sw_fence.c
+index 8a9aad523eec2..1d4cc91c0e40d 100644
+--- a/drivers/gpu/drm/i915/i915_sw_fence.c
++++ b/drivers/gpu/drm/i915/i915_sw_fence.c
+@@ -51,7 +51,7 @@ static inline void debug_fence_init(struct i915_sw_fence *fence)
+ debug_object_init(fence, &i915_sw_fence_debug_descr);
+ }
+
+-static inline void debug_fence_init_onstack(struct i915_sw_fence *fence)
++static inline __maybe_unused void debug_fence_init_onstack(struct i915_sw_fence *fence)
+ {
+ debug_object_init_on_stack(fence, &i915_sw_fence_debug_descr);
+ }
+@@ -77,7 +77,7 @@ static inline void debug_fence_destroy(struct i915_sw_fence *fence)
+ debug_object_destroy(fence, &i915_sw_fence_debug_descr);
+ }
+
+-static inline void debug_fence_free(struct i915_sw_fence *fence)
++static inline __maybe_unused void debug_fence_free(struct i915_sw_fence *fence)
+ {
+ debug_object_free(fence, &i915_sw_fence_debug_descr);
+ smp_wmb(); /* flush the change in state before reallocation */
+@@ -94,7 +94,7 @@ static inline void debug_fence_init(struct i915_sw_fence *fence)
+ {
+ }
+
+-static inline void debug_fence_init_onstack(struct i915_sw_fence *fence)
++static inline __maybe_unused void debug_fence_init_onstack(struct i915_sw_fence *fence)
+ {
+ }
+
+@@ -115,7 +115,7 @@ static inline void debug_fence_destroy(struct i915_sw_fence *fence)
+ {
+ }
+
+-static inline void debug_fence_free(struct i915_sw_fence *fence)
++static inline __maybe_unused void debug_fence_free(struct i915_sw_fence *fence)
+ {
+ }
+
+diff --git a/drivers/gpu/drm/imagination/pvr_vm.c b/drivers/gpu/drm/imagination/pvr_vm.c
+index e59517ba039ef..97c0f772ed65f 100644
+--- a/drivers/gpu/drm/imagination/pvr_vm.c
++++ b/drivers/gpu/drm/imagination/pvr_vm.c
+@@ -114,6 +114,8 @@ struct pvr_vm_gpuva {
+ struct drm_gpuva base;
+ };
+
++#define to_pvr_vm_gpuva(va) container_of_const(va, struct pvr_vm_gpuva, base)
++
+ enum pvr_vm_bind_type {
+ PVR_VM_BIND_TYPE_MAP,
+ PVR_VM_BIND_TYPE_UNMAP,
+@@ -386,6 +388,7 @@ pvr_vm_gpuva_unmap(struct drm_gpuva_op *op, void *op_ctx)
+
+ drm_gpuva_unmap(&op->unmap);
+ drm_gpuva_unlink(op->unmap.va);
++ kfree(to_pvr_vm_gpuva(op->unmap.va));
+
+ return 0;
+ }
+@@ -433,6 +436,7 @@ pvr_vm_gpuva_remap(struct drm_gpuva_op *op, void *op_ctx)
+ }
+
+ drm_gpuva_unlink(op->remap.unmap->va);
++ kfree(to_pvr_vm_gpuva(op->remap.unmap->va));
+
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
+index 330d72b1a4af1..52412965fac10 100644
+--- a/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
++++ b/drivers/gpu/drm/nouveau/nvkm/subdev/gsp/fwsec.c
+@@ -324,7 +324,7 @@ nvkm_gsp_fwsec_sb(struct nvkm_gsp *gsp)
+ return ret;
+
+ /* Verify. */
+- err = nvkm_rd32(device, 0x001400 + (0xf * 4)) & 0x0000ffff;
++ err = nvkm_rd32(device, 0x001400 + (0x15 * 4)) & 0x0000ffff;
+ if (err) {
+ nvkm_error(subdev, "fwsec-sb: 0x%04x\n", err);
+ return -EIO;
+diff --git a/drivers/gpu/drm/panthor/panthor_drv.c b/drivers/gpu/drm/panthor/panthor_drv.c
+index b5e7b919f241e..34182f67136c1 100644
+--- a/drivers/gpu/drm/panthor/panthor_drv.c
++++ b/drivers/gpu/drm/panthor/panthor_drv.c
+@@ -10,6 +10,7 @@
+ #include <linux/platform_device.h>
+ #include <linux/pm_runtime.h>
+
++#include <drm/drm_auth.h>
+ #include <drm/drm_debugfs.h>
+ #include <drm/drm_drv.h>
+ #include <drm/drm_exec.h>
+@@ -996,6 +997,24 @@ static int panthor_ioctl_group_destroy(struct drm_device *ddev, void *data,
+ return panthor_group_destroy(pfile, args->group_handle);
+ }
+
++static int group_priority_permit(struct drm_file *file,
++ u8 priority)
++{
++ /* Ensure that priority is valid */
++ if (priority > PANTHOR_GROUP_PRIORITY_HIGH)
++ return -EINVAL;
++
++ /* Medium priority and below are always allowed */
++ if (priority <= PANTHOR_GROUP_PRIORITY_MEDIUM)
++ return 0;
++
++ /* Higher priorities require CAP_SYS_NICE or DRM_MASTER */
++ if (capable(CAP_SYS_NICE) || drm_is_current_master(file))
++ return 0;
++
++ return -EACCES;
++}
++
+ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data,
+ struct drm_file *file)
+ {
+@@ -1011,6 +1030,10 @@ static int panthor_ioctl_group_create(struct drm_device *ddev, void *data,
+ if (ret)
+ return ret;
+
++ ret = group_priority_permit(file, args->priority);
++ if (ret)
++ return ret;
++
+ ret = panthor_group_create(pfile, args, queue_args);
+ if (ret >= 0) {
+ args->group_handle = ret;
+diff --git a/drivers/gpu/drm/panthor/panthor_fw.c b/drivers/gpu/drm/panthor/panthor_fw.c
+index 857f3f11258aa..ef232c0c20493 100644
+--- a/drivers/gpu/drm/panthor/panthor_fw.c
++++ b/drivers/gpu/drm/panthor/panthor_fw.c
+@@ -1089,6 +1089,12 @@ int panthor_fw_post_reset(struct panthor_device *ptdev)
+ panthor_fw_stop(ptdev);
+ ptdev->fw->fast_reset = false;
+ drm_err(&ptdev->base, "FW fast reset failed, trying a slow reset");
++
++ ret = panthor_vm_flush_all(ptdev->fw->vm);
++ if (ret) {
++ drm_err(&ptdev->base, "FW slow reset failed (couldn't flush FW's AS l2cache)");
++ return ret;
++ }
+ }
+
+ /* Reload all sections, including RO ones. We're not supposed
+@@ -1099,7 +1105,7 @@ int panthor_fw_post_reset(struct panthor_device *ptdev)
+
+ ret = panthor_fw_start(ptdev);
+ if (ret) {
+- drm_err(&ptdev->base, "FW slow reset failed");
++ drm_err(&ptdev->base, "FW slow reset failed (couldn't start the FW )");
+ return ret;
+ }
+
+diff --git a/drivers/gpu/drm/panthor/panthor_mmu.c b/drivers/gpu/drm/panthor/panthor_mmu.c
+index fa0a002b1016e..cc6e13a977835 100644
+--- a/drivers/gpu/drm/panthor/panthor_mmu.c
++++ b/drivers/gpu/drm/panthor/panthor_mmu.c
+@@ -576,6 +576,12 @@ static int mmu_hw_do_operation_locked(struct panthor_device *ptdev, int as_nr,
+ if (as_nr < 0)
+ return 0;
+
++ /*
++ * If the AS number is greater than zero, then we can be sure
++ * the device is up and running, so we don't need to explicitly
++ * power it up
++ */
++
+ if (op != AS_COMMAND_UNLOCK)
+ lock_region(ptdev, as_nr, iova, size);
+
+@@ -874,14 +880,23 @@ static int panthor_vm_flush_range(struct panthor_vm *vm, u64 iova, u64 size)
+ if (!drm_dev_enter(&ptdev->base, &cookie))
+ return 0;
+
+- /* Flush the PTs only if we're already awake */
+- if (pm_runtime_active(ptdev->base.dev))
+- ret = mmu_hw_do_operation(vm, iova, size, AS_COMMAND_FLUSH_PT);
++ ret = mmu_hw_do_operation(vm, iova, size, AS_COMMAND_FLUSH_PT);
+
+ drm_dev_exit(cookie);
+ return ret;
+ }
+
++/**
++ * panthor_vm_flush_all() - Flush L2 caches for the entirety of a VM's AS
++ * @vm: VM whose cache to flush
++ *
++ * Return: 0 on success, a negative error code if flush failed.
++ */
++int panthor_vm_flush_all(struct panthor_vm *vm)
++{
++ return panthor_vm_flush_range(vm, vm->base.mm_start, vm->base.mm_range);
++}
++
+ static int panthor_vm_unmap_pages(struct panthor_vm *vm, u64 iova, u64 size)
+ {
+ struct panthor_device *ptdev = vm->ptdev;
+diff --git a/drivers/gpu/drm/panthor/panthor_mmu.h b/drivers/gpu/drm/panthor/panthor_mmu.h
+index f3c1ed19f973f..6788771071e35 100644
+--- a/drivers/gpu/drm/panthor/panthor_mmu.h
++++ b/drivers/gpu/drm/panthor/panthor_mmu.h
+@@ -31,6 +31,7 @@ panthor_vm_get_bo_for_va(struct panthor_vm *vm, u64 va, u64 *bo_offset);
+ int panthor_vm_active(struct panthor_vm *vm);
+ void panthor_vm_idle(struct panthor_vm *vm);
+ int panthor_vm_as(struct panthor_vm *vm);
++int panthor_vm_flush_all(struct panthor_vm *vm);
+
+ struct panthor_heap_pool *
+ panthor_vm_get_heap_pool(struct panthor_vm *vm, bool create);
+diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
+index 463bcd3cf00f3..12b272a912f86 100644
+--- a/drivers/gpu/drm/panthor/panthor_sched.c
++++ b/drivers/gpu/drm/panthor/panthor_sched.c
+@@ -3092,7 +3092,7 @@ int panthor_group_create(struct panthor_file *pfile,
+ if (group_args->pad)
+ return -EINVAL;
+
+- if (group_args->priority > PANTHOR_CSG_PRIORITY_HIGH)
++ if (group_args->priority >= PANTHOR_CSG_PRIORITY_COUNT)
+ return -EINVAL;
+
+ if ((group_args->compute_core_mask & ~ptdev->gpu_info.shader_present) ||
+diff --git a/drivers/gpu/drm/xe/regs/xe_gt_regs.h b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+index 94445810ccc93..23c302af4cd57 100644
+--- a/drivers/gpu/drm/xe/regs/xe_gt_regs.h
++++ b/drivers/gpu/drm/xe/regs/xe_gt_regs.h
+@@ -350,6 +350,7 @@
+
+ #define HALF_SLICE_CHICKEN7 XE_REG_MCR(0xe194, XE_REG_OPTION_MASKED)
+ #define DG2_DISABLE_ROUND_ENABLE_ALLOW_FOR_SSLA REG_BIT(15)
++#define CLEAR_OPTIMIZATION_DISABLE REG_BIT(6)
+
+ #define CACHE_MODE_SS XE_REG_MCR(0xe420, XE_REG_OPTION_MASKED)
+ #define DISABLE_ECC REG_BIT(5)
+diff --git a/drivers/gpu/drm/xe/xe_gsc.c b/drivers/gpu/drm/xe/xe_gsc.c
+index 60202b9036877..95c17b72fa574 100644
+--- a/drivers/gpu/drm/xe/xe_gsc.c
++++ b/drivers/gpu/drm/xe/xe_gsc.c
+@@ -511,10 +511,22 @@ int xe_gsc_init_post_hwconfig(struct xe_gsc *gsc)
+ void xe_gsc_load_start(struct xe_gsc *gsc)
+ {
+ struct xe_gt *gt = gsc_to_gt(gsc);
++ struct xe_device *xe = gt_to_xe(gt);
+
+ if (!xe_uc_fw_is_loadable(&gsc->fw) || !gsc->q)
+ return;
+
++ /*
++ * The GSC HW is only reset by driver FLR or D3cold entry. We don't
++ * support the former at runtime, while the latter is only supported on
++ * DGFX, for which we don't support GSC. Therefore, if GSC failed to
++ * load previously there is no need to try again because the HW is
++ * stuck in the error state.
++ */
++ xe_assert(xe, !IS_DGFX(xe));
++ if (xe_uc_fw_is_in_error_state(&gsc->fw))
++ return;
++
+ /* GSC FW survives GT reset and D3Hot */
+ if (gsc_fw_is_loaded(gt)) {
+ xe_uc_fw_change_status(&gsc->fw, XE_UC_FIRMWARE_TRANSFERRED);
+diff --git a/drivers/gpu/drm/xe/xe_uc_fw.h b/drivers/gpu/drm/xe/xe_uc_fw.h
+index 35078038797e7..03951cb6de1ce 100644
+--- a/drivers/gpu/drm/xe/xe_uc_fw.h
++++ b/drivers/gpu/drm/xe/xe_uc_fw.h
+@@ -65,7 +65,7 @@ const char *xe_uc_fw_status_repr(enum xe_uc_fw_status status)
+ return "<invalid>";
+ }
+
+-static inline int xe_uc_fw_status_to_error(enum xe_uc_fw_status status)
++static inline int xe_uc_fw_status_to_error(const enum xe_uc_fw_status status)
+ {
+ switch (status) {
+ case XE_UC_FIRMWARE_NOT_SUPPORTED:
+@@ -108,7 +108,7 @@ static inline const char *xe_uc_fw_type_repr(enum xe_uc_fw_type type)
+ }
+
+ static inline enum xe_uc_fw_status
+-__xe_uc_fw_status(struct xe_uc_fw *uc_fw)
++__xe_uc_fw_status(const struct xe_uc_fw *uc_fw)
+ {
+ /* shouldn't call this before checking hw/blob availability */
+ XE_WARN_ON(uc_fw->status == XE_UC_FIRMWARE_UNINITIALIZED);
+@@ -156,6 +156,11 @@ static inline bool xe_uc_fw_is_overridden(const struct xe_uc_fw *uc_fw)
+ return uc_fw->user_overridden;
+ }
+
++static inline bool xe_uc_fw_is_in_error_state(const struct xe_uc_fw *uc_fw)
++{
++ return xe_uc_fw_status_to_error(__xe_uc_fw_status(uc_fw)) < 0;
++}
++
+ static inline void xe_uc_fw_sanitize(struct xe_uc_fw *uc_fw)
+ {
+ if (xe_uc_fw_is_loaded(uc_fw))
+diff --git a/drivers/gpu/drm/xe/xe_wa.c b/drivers/gpu/drm/xe/xe_wa.c
+index dd214d95e4b63..66dafe980b9c2 100644
+--- a/drivers/gpu/drm/xe/xe_wa.c
++++ b/drivers/gpu/drm/xe/xe_wa.c
+@@ -485,6 +485,10 @@ static const struct xe_rtp_entry_sr engine_was[] = {
+ XE_RTP_RULES(GRAPHICS_VERSION(2004), FUNC(xe_rtp_match_first_render_or_compute)),
+ XE_RTP_ACTIONS(SET(TDL_TSL_CHICKEN, SLM_WMTP_RESTORE))
+ },
++ { XE_RTP_NAME("14021402888"),
++ XE_RTP_RULES(GRAPHICS_VERSION(2004), ENGINE_CLASS(RENDER)),
++ XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
++ },
+
+ /* Xe2_HPG */
+
+@@ -533,6 +537,10 @@ static const struct xe_rtp_entry_sr engine_was[] = {
+ FUNC(xe_rtp_match_first_render_or_compute)),
+ XE_RTP_ACTIONS(SET(LSC_CHICKEN_BIT_0, WR_REQ_CHAINING_DIS))
+ },
++ { XE_RTP_NAME("14021402888"),
++ XE_RTP_RULES(GRAPHICS_VERSION(2001), ENGINE_CLASS(RENDER)),
++ XE_RTP_ACTIONS(SET(HALF_SLICE_CHICKEN7, CLEAR_OPTIMIZATION_DISABLE))
++ },
+
+ /* Xe2_HPM */
+
+diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
+index 705b523370684..81f3024b7b1b5 100644
+--- a/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
++++ b/drivers/hid/amd-sfh-hid/amd_sfh_hid.c
+@@ -171,11 +171,13 @@ int amdtp_hid_probe(u32 cur_hid_dev, struct amdtp_cl_data *cli_data)
+ void amdtp_hid_remove(struct amdtp_cl_data *cli_data)
+ {
+ int i;
++ struct amdtp_hid_data *hid_data;
+
+ for (i = 0; i < cli_data->num_hid_devices; ++i) {
+ if (cli_data->hid_sensor_hubs[i]) {
+- kfree(cli_data->hid_sensor_hubs[i]->driver_data);
++ hid_data = cli_data->hid_sensor_hubs[i]->driver_data;
+ hid_destroy_device(cli_data->hid_sensor_hubs[i]);
++ kfree(hid_data);
+ cli_data->hid_sensor_hubs[i] = NULL;
+ }
+ }
+diff --git a/drivers/hid/bpf/Kconfig b/drivers/hid/bpf/Kconfig
+index 83214bae67687..d65482e02a6c2 100644
+--- a/drivers/hid/bpf/Kconfig
++++ b/drivers/hid/bpf/Kconfig
+@@ -3,7 +3,7 @@ menu "HID-BPF support"
+
+ config HID_BPF
+ bool "HID-BPF support"
+- depends on BPF
++ depends on BPF_JIT
+ depends on BPF_SYSCALL
+ depends on DYNAMIC_FTRACE_WITH_DIRECT_CALLS
+ help
+diff --git a/drivers/hid/hid-cougar.c b/drivers/hid/hid-cougar.c
+index cb8bd8aae15b5..0fa785f52707a 100644
+--- a/drivers/hid/hid-cougar.c
++++ b/drivers/hid/hid-cougar.c
+@@ -106,7 +106,7 @@ static void cougar_fix_g6_mapping(void)
+ static __u8 *cougar_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+ unsigned int *rsize)
+ {
+- if (rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
++ if (*rsize >= 117 && rdesc[2] == 0x09 && rdesc[3] == 0x02 &&
+ (rdesc[115] | rdesc[116] << 8) >= HID_MAX_USAGES) {
+ hid_info(hdev,
+ "usage count exceeds max: fixing up report descriptor\n");
+diff --git a/drivers/hv/vmbus_drv.c b/drivers/hv/vmbus_drv.c
+index 12a707ab73f85..4d8378b677a62 100644
+--- a/drivers/hv/vmbus_drv.c
++++ b/drivers/hv/vmbus_drv.c
+@@ -1952,6 +1952,7 @@ void vmbus_device_unregister(struct hv_device *device_obj)
+ */
+ device_unregister(&device_obj->device);
+ }
++EXPORT_SYMBOL_GPL(vmbus_device_unregister);
+
+ #ifdef CONFIG_ACPI
+ /*
+diff --git a/drivers/hwmon/adc128d818.c b/drivers/hwmon/adc128d818.c
+index 8ac6e735ec5cf..5e805d4ee76ab 100644
+--- a/drivers/hwmon/adc128d818.c
++++ b/drivers/hwmon/adc128d818.c
+@@ -175,7 +175,7 @@ static ssize_t adc128_in_store(struct device *dev,
+
+ mutex_lock(&data->update_lock);
+ /* 10 mV LSB on limit registers */
+- regval = clamp_val(DIV_ROUND_CLOSEST(val, 10), 0, 255);
++ regval = DIV_ROUND_CLOSEST(clamp_val(val, 0, 2550), 10);
+ data->in[index][nr] = regval << 4;
+ reg = index == 1 ? ADC128_REG_IN_MIN(nr) : ADC128_REG_IN_MAX(nr);
+ i2c_smbus_write_byte_data(data->client, reg, regval);
+@@ -213,7 +213,7 @@ static ssize_t adc128_temp_store(struct device *dev,
+ return err;
+
+ mutex_lock(&data->update_lock);
+- regval = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -128, 127);
++ regval = DIV_ROUND_CLOSEST(clamp_val(val, -128000, 127000), 1000);
+ data->temp[index] = regval << 1;
+ i2c_smbus_write_byte_data(data->client,
+ index == 1 ? ADC128_REG_TEMP_MAX
+diff --git a/drivers/hwmon/hp-wmi-sensors.c b/drivers/hwmon/hp-wmi-sensors.c
+index b5325d0e72b9c..dfa1d6926deac 100644
+--- a/drivers/hwmon/hp-wmi-sensors.c
++++ b/drivers/hwmon/hp-wmi-sensors.c
+@@ -1637,6 +1637,8 @@ static void hp_wmi_notify(u32 value, void *context)
+ goto out_unlock;
+
+ wobj = out.pointer;
++ if (!wobj)
++ goto out_unlock;
+
+ err = populate_event_from_wobj(dev, &event, wobj);
+ if (err) {
+diff --git a/drivers/hwmon/lm95234.c b/drivers/hwmon/lm95234.c
+index 67b9d7636ee42..37e8e9679aeb6 100644
+--- a/drivers/hwmon/lm95234.c
++++ b/drivers/hwmon/lm95234.c
+@@ -301,7 +301,8 @@ static ssize_t tcrit2_store(struct device *dev, struct device_attribute *attr,
+ if (ret < 0)
+ return ret;
+
+- val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, index ? 255 : 127);
++ val = DIV_ROUND_CLOSEST(clamp_val(val, 0, (index ? 255 : 127) * 1000),
++ 1000);
+
+ mutex_lock(&data->update_lock);
+ data->tcrit2[index] = val;
+@@ -350,7 +351,7 @@ static ssize_t tcrit1_store(struct device *dev, struct device_attribute *attr,
+ if (ret < 0)
+ return ret;
+
+- val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 255);
++ val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 255000), 1000);
+
+ mutex_lock(&data->update_lock);
+ data->tcrit1[index] = val;
+@@ -391,7 +392,7 @@ static ssize_t tcrit1_hyst_store(struct device *dev,
+ if (ret < 0)
+ return ret;
+
+- val = DIV_ROUND_CLOSEST(val, 1000);
++ val = DIV_ROUND_CLOSEST(clamp_val(val, -255000, 255000), 1000);
+ val = clamp_val((int)data->tcrit1[index] - val, 0, 31);
+
+ mutex_lock(&data->update_lock);
+@@ -431,7 +432,7 @@ static ssize_t offset_store(struct device *dev, struct device_attribute *attr,
+ return ret;
+
+ /* Accuracy is 1/2 degrees C */
+- val = clamp_val(DIV_ROUND_CLOSEST(val, 500), -128, 127);
++ val = DIV_ROUND_CLOSEST(clamp_val(val, -64000, 63500), 500);
+
+ mutex_lock(&data->update_lock);
+ data->toffset[index] = val;
+diff --git a/drivers/hwmon/ltc2991.c b/drivers/hwmon/ltc2991.c
+index f74ce9c25bf71..d5e120dfd592d 100644
+--- a/drivers/hwmon/ltc2991.c
++++ b/drivers/hwmon/ltc2991.c
+@@ -42,9 +42,9 @@
+ #define LTC2991_V7_V8_FILT_EN BIT(7)
+ #define LTC2991_V7_V8_TEMP_EN BIT(5)
+ #define LTC2991_V7_V8_DIFF_EN BIT(4)
+-#define LTC2991_V5_V6_FILT_EN BIT(7)
+-#define LTC2991_V5_V6_TEMP_EN BIT(5)
+-#define LTC2991_V5_V6_DIFF_EN BIT(4)
++#define LTC2991_V5_V6_FILT_EN BIT(3)
++#define LTC2991_V5_V6_TEMP_EN BIT(1)
++#define LTC2991_V5_V6_DIFF_EN BIT(0)
+
+ #define LTC2991_REPEAT_ACQ_EN BIT(4)
+ #define LTC2991_T_INT_FILT_EN BIT(3)
+diff --git a/drivers/hwmon/nct6775-core.c b/drivers/hwmon/nct6775-core.c
+index 9fbab8f023340..934fed3dd5866 100644
+--- a/drivers/hwmon/nct6775-core.c
++++ b/drivers/hwmon/nct6775-core.c
+@@ -2262,7 +2262,7 @@ store_temp_offset(struct device *dev, struct device_attribute *attr,
+ if (err < 0)
+ return err;
+
+- val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), -128, 127);
++ val = DIV_ROUND_CLOSEST(clamp_val(val, -128000, 127000), 1000);
+
+ mutex_lock(&data->update_lock);
+ data->temp_offset[nr] = val;
+diff --git a/drivers/hwmon/w83627ehf.c b/drivers/hwmon/w83627ehf.c
+index fe960c0a624f7..7d7d70afde655 100644
+--- a/drivers/hwmon/w83627ehf.c
++++ b/drivers/hwmon/w83627ehf.c
+@@ -895,7 +895,7 @@ store_target_temp(struct device *dev, struct device_attribute *attr,
+ if (err < 0)
+ return err;
+
+- val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 127);
++ val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 127000), 1000);
+
+ mutex_lock(&data->update_lock);
+ data->target_temp[nr] = val;
+@@ -920,7 +920,7 @@ store_tolerance(struct device *dev, struct device_attribute *attr,
+ return err;
+
+ /* Limit the temp to 0C - 15C */
+- val = clamp_val(DIV_ROUND_CLOSEST(val, 1000), 0, 15);
++ val = DIV_ROUND_CLOSEST(clamp_val(val, 0, 15000), 1000);
+
+ mutex_lock(&data->update_lock);
+ reg = w83627ehf_read_value(data, W83627EHF_REG_TOLERANCE[nr]);
+diff --git a/drivers/i3c/master/mipi-i3c-hci/dma.c b/drivers/i3c/master/mipi-i3c-hci/dma.c
+index 4e01a95cc4d0a..1a96bf5a0bf87 100644
+--- a/drivers/i3c/master/mipi-i3c-hci/dma.c
++++ b/drivers/i3c/master/mipi-i3c-hci/dma.c
+@@ -294,7 +294,10 @@ static int hci_dma_init(struct i3c_hci *hci)
+
+ rh->ibi_chunk_sz = dma_get_cache_alignment();
+ rh->ibi_chunk_sz *= IBI_CHUNK_CACHELINES;
+- BUG_ON(rh->ibi_chunk_sz > 256);
++ if (rh->ibi_chunk_sz > 256) {
++ ret = -EINVAL;
++ goto err_out;
++ }
+
+ ibi_status_ring_sz = rh->ibi_status_sz * rh->ibi_status_entries;
+ ibi_data_ring_sz = rh->ibi_chunk_sz * rh->ibi_chunks_total;
+diff --git a/drivers/i3c/master/svc-i3c-master.c b/drivers/i3c/master/svc-i3c-master.c
+index bb299ce02cccb..f0362509319e0 100644
+--- a/drivers/i3c/master/svc-i3c-master.c
++++ b/drivers/i3c/master/svc-i3c-master.c
+@@ -1052,29 +1052,59 @@ static int svc_i3c_master_xfer(struct svc_i3c_master *master,
+ u8 *in, const u8 *out, unsigned int xfer_len,
+ unsigned int *actual_len, bool continued)
+ {
++ int retry = 2;
+ u32 reg;
+ int ret;
+
+ /* clean SVC_I3C_MINT_IBIWON w1c bits */
+ writel(SVC_I3C_MINT_IBIWON, master->regs + SVC_I3C_MSTATUS);
+
+- writel(SVC_I3C_MCTRL_REQUEST_START_ADDR |
+- xfer_type |
+- SVC_I3C_MCTRL_IBIRESP_NACK |
+- SVC_I3C_MCTRL_DIR(rnw) |
+- SVC_I3C_MCTRL_ADDR(addr) |
+- SVC_I3C_MCTRL_RDTERM(*actual_len),
+- master->regs + SVC_I3C_MCTRL);
+
+- ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
++ while (retry--) {
++ writel(SVC_I3C_MCTRL_REQUEST_START_ADDR |
++ xfer_type |
++ SVC_I3C_MCTRL_IBIRESP_NACK |
++ SVC_I3C_MCTRL_DIR(rnw) |
++ SVC_I3C_MCTRL_ADDR(addr) |
++ SVC_I3C_MCTRL_RDTERM(*actual_len),
++ master->regs + SVC_I3C_MCTRL);
++
++ ret = readl_poll_timeout(master->regs + SVC_I3C_MSTATUS, reg,
+ SVC_I3C_MSTATUS_MCTRLDONE(reg), 0, 1000);
+- if (ret)
+- goto emit_stop;
++ if (ret)
++ goto emit_stop;
+
+- if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
+- ret = -ENXIO;
+- *actual_len = 0;
+- goto emit_stop;
++ if (readl(master->regs + SVC_I3C_MERRWARN) & SVC_I3C_MERRWARN_NACK) {
++ /*
++ * According to I3C Spec 1.1.1, 11-Jun-2021, section: 5.1.2.2.3.
++ * If the Controller chooses to start an I3C Message with an I3C Dynamic
++ * Address, then special provisions shall be made because that same I3C
++ * Target may be initiating an IBI or a Controller Role Request. So, one of
++ * three things may happen: (skip 1, 2)
++ *
++ * 3. The Addresses match and the RnW bits also match, and so neither
++ * Controller nor Target will ACK since both are expecting the other side to
++ * provide ACK. As a result, each side might think it had "won" arbitration,
++ * but neither side would continue, as each would subsequently see that the
++ * other did not provide ACK.
++ * ...
++ * For either value of RnW: Due to the NACK, the Controller shall defer the
++ * Private Write or Private Read, and should typically transmit the Target
++ * Address again after a Repeated START (i.e., the next one or any one prior
++ * to a STOP in the Frame). Since the Address Header following a Repeated
++ * START is not arbitrated, the Controller will always win (see Section
++ * 5.1.2.2.4).
++ */
++ if (retry && addr != 0x7e) {
++ writel(SVC_I3C_MERRWARN_NACK, master->regs + SVC_I3C_MERRWARN);
++ } else {
++ ret = -ENXIO;
++ *actual_len = 0;
++ goto emit_stop;
++ }
++ } else {
++ break;
++ }
+ }
+
+ /*
+diff --git a/drivers/iio/adc/ad7124.c b/drivers/iio/adc/ad7124.c
+index e7b1d517d3def..d2fe0269b6d3a 100644
+--- a/drivers/iio/adc/ad7124.c
++++ b/drivers/iio/adc/ad7124.c
+@@ -147,15 +147,18 @@ struct ad7124_chip_info {
+ struct ad7124_channel_config {
+ bool live;
+ unsigned int cfg_slot;
+- enum ad7124_ref_sel refsel;
+- bool bipolar;
+- bool buf_positive;
+- bool buf_negative;
+- unsigned int vref_mv;
+- unsigned int pga_bits;
+- unsigned int odr;
+- unsigned int odr_sel_bits;
+- unsigned int filter_type;
++ /* Following fields are used to compare equality. */
++ struct_group(config_props,
++ enum ad7124_ref_sel refsel;
++ bool bipolar;
++ bool buf_positive;
++ bool buf_negative;
++ unsigned int vref_mv;
++ unsigned int pga_bits;
++ unsigned int odr;
++ unsigned int odr_sel_bits;
++ unsigned int filter_type;
++ );
+ };
+
+ struct ad7124_channel {
+@@ -334,11 +337,12 @@ static struct ad7124_channel_config *ad7124_find_similar_live_cfg(struct ad7124_
+ ptrdiff_t cmp_size;
+ int i;
+
+- cmp_size = (u8 *)&cfg->live - (u8 *)cfg;
++ cmp_size = sizeof_field(struct ad7124_channel_config, config_props);
+ for (i = 0; i < st->num_channels; i++) {
+ cfg_aux = &st->channels[i].cfg;
+
+- if (cfg_aux->live && !memcmp(cfg, cfg_aux, cmp_size))
++ if (cfg_aux->live &&
++ !memcmp(&cfg->config_props, &cfg_aux->config_props, cmp_size))
+ return cfg_aux;
+ }
+
+@@ -762,6 +766,7 @@ static int ad7124_soft_reset(struct ad7124_state *st)
+ if (ret < 0)
+ return ret;
+
++ fsleep(200);
+ timeout = 100;
+ do {
+ ret = ad_sd_read_reg(&st->sd, AD7124_STATUS, 1, &readval);
+@@ -837,8 +842,6 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev,
+ st->channels = channels;
+
+ device_for_each_child_node_scoped(dev, child) {
+- cfg = &st->channels[channel].cfg;
+-
+ ret = fwnode_property_read_u32(child, "reg", &channel);
+ if (ret)
+ return ret;
+@@ -856,6 +859,7 @@ static int ad7124_parse_channel_config(struct iio_dev *indio_dev,
+ st->channels[channel].ain = AD7124_CHANNEL_AINP(ain[0]) |
+ AD7124_CHANNEL_AINM(ain[1]);
+
++ cfg = &st->channels[channel].cfg;
+ cfg->bipolar = fwnode_property_read_bool(child, "bipolar");
+
+ ret = fwnode_property_read_u32(child, "adi,reference-select", &tmp);
+diff --git a/drivers/iio/adc/ad7606.c b/drivers/iio/adc/ad7606.c
+index 1928d9ae5bcff..1c08c0921ee71 100644
+--- a/drivers/iio/adc/ad7606.c
++++ b/drivers/iio/adc/ad7606.c
+@@ -49,7 +49,7 @@ static const unsigned int ad7616_oversampling_avail[8] = {
+ 1, 2, 4, 8, 16, 32, 64, 128,
+ };
+
+-static int ad7606_reset(struct ad7606_state *st)
++int ad7606_reset(struct ad7606_state *st)
+ {
+ if (st->gpio_reset) {
+ gpiod_set_value(st->gpio_reset, 1);
+@@ -60,6 +60,7 @@ static int ad7606_reset(struct ad7606_state *st)
+
+ return -ENODEV;
+ }
++EXPORT_SYMBOL_NS_GPL(ad7606_reset, IIO_AD7606);
+
+ static int ad7606_reg_access(struct iio_dev *indio_dev,
+ unsigned int reg,
+@@ -88,31 +89,6 @@ static int ad7606_read_samples(struct ad7606_state *st)
+ {
+ unsigned int num = st->chip_info->num_channels - 1;
+ u16 *data = st->data;
+- int ret;
+-
+- /*
+- * The frstdata signal is set to high while and after reading the sample
+- * of the first channel and low for all other channels. This can be used
+- * to check that the incoming data is correctly aligned. During normal
+- * operation the data should never become unaligned, but some glitch or
+- * electrostatic discharge might cause an extra read or clock cycle.
+- * Monitoring the frstdata signal allows to recover from such failure
+- * situations.
+- */
+-
+- if (st->gpio_frstdata) {
+- ret = st->bops->read_block(st->dev, 1, data);
+- if (ret)
+- return ret;
+-
+- if (!gpiod_get_value(st->gpio_frstdata)) {
+- ad7606_reset(st);
+- return -EIO;
+- }
+-
+- data++;
+- num--;
+- }
+
+ return st->bops->read_block(st->dev, num, data);
+ }
+diff --git a/drivers/iio/adc/ad7606.h b/drivers/iio/adc/ad7606.h
+index 0c6a88cc46958..6649e84d25de6 100644
+--- a/drivers/iio/adc/ad7606.h
++++ b/drivers/iio/adc/ad7606.h
+@@ -151,6 +151,8 @@ int ad7606_probe(struct device *dev, int irq, void __iomem *base_address,
+ const char *name, unsigned int id,
+ const struct ad7606_bus_ops *bops);
+
++int ad7606_reset(struct ad7606_state *st);
++
+ enum ad7606_supported_device_ids {
+ ID_AD7605_4,
+ ID_AD7606_8,
+diff --git a/drivers/iio/adc/ad7606_par.c b/drivers/iio/adc/ad7606_par.c
+index d8408052262e4..6bc587b20f05d 100644
+--- a/drivers/iio/adc/ad7606_par.c
++++ b/drivers/iio/adc/ad7606_par.c
+@@ -7,6 +7,7 @@
+
+ #include <linux/mod_devicetable.h>
+ #include <linux/module.h>
++#include <linux/gpio/consumer.h>
+ #include <linux/platform_device.h>
+ #include <linux/types.h>
+ #include <linux/err.h>
+@@ -21,8 +22,29 @@ static int ad7606_par16_read_block(struct device *dev,
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct ad7606_state *st = iio_priv(indio_dev);
+
+- insw((unsigned long)st->base_address, buf, count);
+
++ /*
++ * On the parallel interface, the frstdata signal is set to high while
++ * and after reading the sample of the first channel and low for all
++ * other channels. This can be used to check that the incoming data is
++ * correctly aligned. During normal operation the data should never
++ * become unaligned, but some glitch or electrostatic discharge might
++ * cause an extra read or clock cycle. Monitoring the frstdata signal
++ * allows to recover from such failure situations.
++ */
++ int num = count;
++ u16 *_buf = buf;
++
++ if (st->gpio_frstdata) {
++ insw((unsigned long)st->base_address, _buf, 1);
++ if (!gpiod_get_value(st->gpio_frstdata)) {
++ ad7606_reset(st);
++ return -EIO;
++ }
++ _buf++;
++ num--;
++ }
++ insw((unsigned long)st->base_address, _buf, num);
+ return 0;
+ }
+
+@@ -35,8 +57,28 @@ static int ad7606_par8_read_block(struct device *dev,
+ {
+ struct iio_dev *indio_dev = dev_get_drvdata(dev);
+ struct ad7606_state *st = iio_priv(indio_dev);
+-
+- insb((unsigned long)st->base_address, buf, count * 2);
++ /*
++ * On the parallel interface, the frstdata signal is set to high while
++ * and after reading the sample of the first channel and low for all
++ * other channels. This can be used to check that the incoming data is
++ * correctly aligned. During normal operation the data should never
++ * become unaligned, but some glitch or electrostatic discharge might
++ * cause an extra read or clock cycle. Monitoring the frstdata signal
++ * allows to recover from such failure situations.
++ */
++ int num = count;
++ u16 *_buf = buf;
++
++ if (st->gpio_frstdata) {
++ insb((unsigned long)st->base_address, _buf, 2);
++ if (!gpiod_get_value(st->gpio_frstdata)) {
++ ad7606_reset(st);
++ return -EIO;
++ }
++ _buf++;
++ num--;
++ }
++ insb((unsigned long)st->base_address, _buf, num * 2);
+
+ return 0;
+ }
+diff --git a/drivers/iio/adc/ad_sigma_delta.c b/drivers/iio/adc/ad_sigma_delta.c
+index a2b87f6b7a071..6231c635803d1 100644
+--- a/drivers/iio/adc/ad_sigma_delta.c
++++ b/drivers/iio/adc/ad_sigma_delta.c
+@@ -568,7 +568,7 @@ EXPORT_SYMBOL_NS_GPL(ad_sd_validate_trigger, IIO_AD_SIGMA_DELTA);
+ static int devm_ad_sd_probe_trigger(struct device *dev, struct iio_dev *indio_dev)
+ {
+ struct ad_sigma_delta *sigma_delta = iio_device_get_drvdata(indio_dev);
+- unsigned long irq_flags = irq_get_trigger_type(sigma_delta->spi->irq);
++ unsigned long irq_flags = irq_get_trigger_type(sigma_delta->irq_line);
+ int ret;
+
+ if (dev != &sigma_delta->spi->dev) {
+diff --git a/drivers/iio/buffer/industrialio-buffer-dmaengine.c b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
+index 918f6f8d65b6c..0f50a99e89676 100644
+--- a/drivers/iio/buffer/industrialio-buffer-dmaengine.c
++++ b/drivers/iio/buffer/industrialio-buffer-dmaengine.c
+@@ -193,7 +193,7 @@ static struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
+
+ ret = dma_get_slave_caps(chan, &caps);
+ if (ret < 0)
+- goto err_free;
++ goto err_release;
+
+ /* Needs to be aligned to the maximum of the minimums */
+ if (caps.src_addr_widths)
+@@ -219,6 +219,8 @@ static struct iio_buffer *iio_dmaengine_buffer_alloc(struct device *dev,
+
+ return &dmaengine_buffer->queue.buffer;
+
++err_release:
++ dma_release_channel(chan);
+ err_free:
+ kfree(dmaengine_buffer);
+ return ERR_PTR(ret);
+diff --git a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+index 84273660ca2eb..3bfeabab0ec4f 100644
+--- a/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
++++ b/drivers/iio/imu/inv_mpu6050/inv_mpu_trigger.c
+@@ -248,12 +248,20 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p)
+ int result;
+
+ switch (st->chip_type) {
++ case INV_MPU6000:
+ case INV_MPU6050:
++ case INV_MPU9150:
++ /*
++ * WoM is not supported and interrupt status read seems to be broken for
++ * some chips. Since data ready is the only interrupt, bypass interrupt
++ * status read and always assert data ready bit.
++ */
++ wom_bits = 0;
++ int_status = INV_MPU6050_BIT_RAW_DATA_RDY_INT;
++ goto data_ready_interrupt;
+ case INV_MPU6500:
+ case INV_MPU6515:
+ case INV_MPU6880:
+- case INV_MPU6000:
+- case INV_MPU9150:
+ case INV_MPU9250:
+ case INV_MPU9255:
+ wom_bits = INV_MPU6500_BIT_WOM_INT;
+@@ -279,6 +287,7 @@ static irqreturn_t inv_mpu6050_interrupt_handle(int irq, void *p)
+ }
+ }
+
++data_ready_interrupt:
+ /* handle raw data interrupt */
+ if (int_status & INV_MPU6050_BIT_RAW_DATA_RDY_INT) {
+ indio_dev->pollfunc->timestamp = st->it_timestamp;
+diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
+index 39cf26d69d17a..e1e1b31bf8b4b 100644
+--- a/drivers/iio/inkern.c
++++ b/drivers/iio/inkern.c
+@@ -647,17 +647,17 @@ static int iio_convert_raw_to_processed_unlocked(struct iio_channel *chan,
+ break;
+ case IIO_VAL_INT_PLUS_MICRO:
+ if (scale_val2 < 0)
+- *processed = -raw64 * scale_val;
++ *processed = -raw64 * scale_val * scale;
+ else
+- *processed = raw64 * scale_val;
++ *processed = raw64 * scale_val * scale;
+ *processed += div_s64(raw64 * (s64)scale_val2 * scale,
+ 1000000LL);
+ break;
+ case IIO_VAL_INT_PLUS_NANO:
+ if (scale_val2 < 0)
+- *processed = -raw64 * scale_val;
++ *processed = -raw64 * scale_val * scale;
+ else
+- *processed = raw64 * scale_val;
++ *processed = raw64 * scale_val * scale;
+ *processed += div_s64(raw64 * (s64)scale_val2 * scale,
+ 1000000000LL);
+ break;
+diff --git a/drivers/input/misc/uinput.c b/drivers/input/misc/uinput.c
+index d98212d55108c..2c973f15cab7d 100644
+--- a/drivers/input/misc/uinput.c
++++ b/drivers/input/misc/uinput.c
+@@ -417,6 +417,20 @@ static int uinput_validate_absinfo(struct input_dev *dev, unsigned int code,
+ return -EINVAL;
+ }
+
++ /*
++ * Limit number of contacts to a reasonable value (100). This
++ * ensures that we need less than 2 pages for struct input_mt
++ * (we are not using in-kernel slot assignment so not going to
++ * allocate memory for the "red" table), and we should have no
++ * trouble getting this much memory.
++ */
++ if (code == ABS_MT_SLOT && max > 99) {
++ printk(KERN_DEBUG
++ "%s: unreasonably large number of slots requested: %d\n",
++ UINPUT_NAME, max);
++ return -EINVAL;
++ }
++
+ return 0;
+ }
+
+diff --git a/drivers/input/touchscreen/ili210x.c b/drivers/input/touchscreen/ili210x.c
+index 79bdb2b109496..f3c3ad70244f1 100644
+--- a/drivers/input/touchscreen/ili210x.c
++++ b/drivers/input/touchscreen/ili210x.c
+@@ -597,7 +597,7 @@ static int ili251x_firmware_to_buffer(const struct firmware *fw,
+ * once, copy them all into this buffer at the right locations, and then
+ * do all operations on this linear buffer.
+ */
+- fw_buf = kzalloc(SZ_64K, GFP_KERNEL);
++ fw_buf = kvmalloc(SZ_64K, GFP_KERNEL);
+ if (!fw_buf)
+ return -ENOMEM;
+
+@@ -627,7 +627,7 @@ static int ili251x_firmware_to_buffer(const struct firmware *fw,
+ return 0;
+
+ err_big:
+- kfree(fw_buf);
++ kvfree(fw_buf);
+ return error;
+ }
+
+@@ -870,7 +870,7 @@ static ssize_t ili210x_firmware_update_store(struct device *dev,
+ ili210x_hardware_reset(priv->reset_gpio);
+ dev_dbg(dev, "Firmware update ended, error=%i\n", error);
+ enable_irq(client->irq);
+- kfree(fwbuf);
++ kvfree(fwbuf);
+ return error;
+ }
+
+diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
+index 304e84949ca72..1c8d3141cb55c 100644
+--- a/drivers/iommu/intel/dmar.c
++++ b/drivers/iommu/intel/dmar.c
+@@ -1446,7 +1446,7 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
+ */
+ writel(qi->free_head << shift, iommu->reg + DMAR_IQT_REG);
+
+- while (qi->desc_status[wait_index] != QI_DONE) {
++ while (READ_ONCE(qi->desc_status[wait_index]) != QI_DONE) {
+ /*
+ * We will leave the interrupts disabled, to prevent interrupt
+ * context to queue another cmd while a cmd is already submitted
+diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
+index f55ec1fd7942a..e9bea0305c268 100644
+--- a/drivers/iommu/intel/iommu.c
++++ b/drivers/iommu/intel/iommu.c
+@@ -854,7 +854,7 @@ static struct dma_pte *pfn_to_dma_pte(struct dmar_domain *domain,
+ domain_flush_cache(domain, tmp_page, VTD_PAGE_SIZE);
+ pteval = ((uint64_t)virt_to_dma_pfn(tmp_page) << VTD_PAGE_SHIFT) | DMA_PTE_READ | DMA_PTE_WRITE;
+ if (domain->use_first_level)
+- pteval |= DMA_FL_PTE_XD | DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
++ pteval |= DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
+
+ tmp = 0ULL;
+ if (!try_cmpxchg64(&pte->val, &tmp, pteval))
+@@ -1872,7 +1872,7 @@ __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
+ attr = prot & (DMA_PTE_READ | DMA_PTE_WRITE | DMA_PTE_SNP);
+ attr |= DMA_FL_PTE_PRESENT;
+ if (domain->use_first_level) {
+- attr |= DMA_FL_PTE_XD | DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
++ attr |= DMA_FL_PTE_US | DMA_FL_PTE_ACCESS;
+ if (prot & DMA_PTE_WRITE)
+ attr |= DMA_FL_PTE_DIRTY;
+ }
+diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
+index eaf015b4353b1..9a3b064126de9 100644
+--- a/drivers/iommu/intel/iommu.h
++++ b/drivers/iommu/intel/iommu.h
+@@ -49,7 +49,6 @@
+ #define DMA_FL_PTE_US BIT_ULL(2)
+ #define DMA_FL_PTE_ACCESS BIT_ULL(5)
+ #define DMA_FL_PTE_DIRTY BIT_ULL(6)
+-#define DMA_FL_PTE_XD BIT_ULL(63)
+
+ #define DMA_SL_PTE_DIRTY_BIT 9
+ #define DMA_SL_PTE_DIRTY BIT_ULL(DMA_SL_PTE_DIRTY_BIT)
+@@ -831,11 +830,10 @@ static inline void dma_clear_pte(struct dma_pte *pte)
+ static inline u64 dma_pte_addr(struct dma_pte *pte)
+ {
+ #ifdef CONFIG_64BIT
+- return pte->val & VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
++ return pte->val & VTD_PAGE_MASK;
+ #else
+ /* Must have a full atomic 64-bit read */
+- return __cmpxchg64(&pte->val, 0ULL, 0ULL) &
+- VTD_PAGE_MASK & (~DMA_FL_PTE_XD);
++ return __cmpxchg64(&pte->val, 0ULL, 0ULL) & VTD_PAGE_MASK;
+ #endif
+ }
+
+diff --git a/drivers/iommu/intel/pasid.c b/drivers/iommu/intel/pasid.c
+index abce19e2ad6f4..aabcdf7565817 100644
+--- a/drivers/iommu/intel/pasid.c
++++ b/drivers/iommu/intel/pasid.c
+@@ -333,7 +333,6 @@ int intel_pasid_setup_first_level(struct intel_iommu *iommu,
+ pasid_set_domain_id(pte, did);
+ pasid_set_address_width(pte, iommu->agaw);
+ pasid_set_page_snoop(pte, !!ecap_smpwc(iommu->ecap));
+- pasid_set_nxe(pte);
+
+ /* Setup Present and PASID Granular Transfer Type: */
+ pasid_set_translation_type(pte, PASID_ENTRY_PGTT_FL_ONLY);
+diff --git a/drivers/iommu/intel/pasid.h b/drivers/iommu/intel/pasid.h
+index da9978fef7ac5..dde6d3ba5ae0f 100644
+--- a/drivers/iommu/intel/pasid.h
++++ b/drivers/iommu/intel/pasid.h
+@@ -247,16 +247,6 @@ static inline void pasid_set_page_snoop(struct pasid_entry *pe, bool value)
+ pasid_set_bits(&pe->val[1], 1 << 23, value << 23);
+ }
+
+-/*
+- * Setup No Execute Enable bit (Bit 133) of a scalable mode PASID
+- * entry. It is required when XD bit of the first level page table
+- * entry is about to be set.
+- */
+-static inline void pasid_set_nxe(struct pasid_entry *pe)
+-{
+- pasid_set_bits(&pe->val[2], 1 << 5, 1 << 5);
+-}
+-
+ /*
+ * Setup the Page Snoop (PGSNP) field (Bit 88) of a scalable mode
+ * PASID entry.
+diff --git a/drivers/iommu/iommufd/hw_pagetable.c b/drivers/iommu/iommufd/hw_pagetable.c
+index 33d142f8057d7..a9f1fe44c4c0b 100644
+--- a/drivers/iommu/iommufd/hw_pagetable.c
++++ b/drivers/iommu/iommufd/hw_pagetable.c
+@@ -236,7 +236,8 @@ iommufd_hwpt_nested_alloc(struct iommufd_ctx *ictx,
+ }
+ hwpt->domain->owner = ops;
+
+- if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED)) {
++ if (WARN_ON_ONCE(hwpt->domain->type != IOMMU_DOMAIN_NESTED ||
++ !hwpt->domain->ops->cache_invalidate_user)) {
+ rc = -EINVAL;
+ goto out_abort;
+ }
+diff --git a/drivers/iommu/sun50i-iommu.c b/drivers/iommu/sun50i-iommu.c
+index c519b991749d7..dd3f07384624c 100644
+--- a/drivers/iommu/sun50i-iommu.c
++++ b/drivers/iommu/sun50i-iommu.c
+@@ -452,6 +452,7 @@ static int sun50i_iommu_enable(struct sun50i_iommu *iommu)
+ IOMMU_TLB_PREFETCH_MASTER_ENABLE(3) |
+ IOMMU_TLB_PREFETCH_MASTER_ENABLE(4) |
+ IOMMU_TLB_PREFETCH_MASTER_ENABLE(5));
++ iommu_write(iommu, IOMMU_BYPASS_REG, 0);
+ iommu_write(iommu, IOMMU_INT_ENABLE_REG, IOMMU_INT_MASK);
+ iommu_write(iommu, IOMMU_DM_AUT_CTRL_REG(SUN50I_IOMMU_ACI_NONE),
+ IOMMU_DM_AUT_CTRL_RD_UNAVAIL(SUN50I_IOMMU_ACI_NONE, 0) |
+diff --git a/drivers/irqchip/irq-armada-370-xp.c b/drivers/irqchip/irq-armada-370-xp.c
+index 4b021a67bdfe4..f488c35d91308 100644
+--- a/drivers/irqchip/irq-armada-370-xp.c
++++ b/drivers/irqchip/irq-armada-370-xp.c
+@@ -566,6 +566,10 @@ static struct irq_chip armada_370_xp_irq_chip = {
+ static int armada_370_xp_mpic_irq_map(struct irq_domain *h,
+ unsigned int virq, irq_hw_number_t hw)
+ {
++ /* IRQs 0 and 1 cannot be mapped, they are handled internally */
++ if (hw <= 1)
++ return -EINVAL;
++
+ armada_370_xp_irq_mask(irq_get_irq_data(virq));
+ if (!is_percpu_irq(hw))
+ writel(hw, per_cpu_int_base +
+diff --git a/drivers/irqchip/irq-gic-v2m.c b/drivers/irqchip/irq-gic-v2m.c
+index f2ff4387870d6..d83c2c85962c3 100644
+--- a/drivers/irqchip/irq-gic-v2m.c
++++ b/drivers/irqchip/irq-gic-v2m.c
+@@ -438,12 +438,12 @@ static int __init gicv2m_of_init(struct fwnode_handle *parent_handle,
+
+ ret = gicv2m_init_one(&child->fwnode, spi_start, nr_spis,
+ &res, 0);
+- if (ret) {
+- of_node_put(child);
++ if (ret)
+ break;
+- }
+ }
+
++ if (ret && child)
++ of_node_put(child);
+ if (!ret)
+ ret = gicv2m_allocate_domains(parent);
+ if (ret)
+diff --git a/drivers/irqchip/irq-renesas-rzg2l.c b/drivers/irqchip/irq-renesas-rzg2l.c
+index f6484bf15e0b8..5a4521cf3ec6e 100644
+--- a/drivers/irqchip/irq-renesas-rzg2l.c
++++ b/drivers/irqchip/irq-renesas-rzg2l.c
+@@ -162,8 +162,8 @@ static void rzg2l_tint_irq_endisable(struct irq_data *d, bool enable)
+
+ static void rzg2l_irqc_irq_disable(struct irq_data *d)
+ {
+- rzg2l_tint_irq_endisable(d, false);
+ irq_chip_disable_parent(d);
++ rzg2l_tint_irq_endisable(d, false);
+ }
+
+ static void rzg2l_irqc_irq_enable(struct irq_data *d)
+diff --git a/drivers/irqchip/irq-riscv-aplic-main.c b/drivers/irqchip/irq-riscv-aplic-main.c
+index 774a0c97fdab6..362db30ed7755 100644
+--- a/drivers/irqchip/irq-riscv-aplic-main.c
++++ b/drivers/irqchip/irq-riscv-aplic-main.c
+@@ -175,9 +175,9 @@ static int aplic_probe(struct platform_device *pdev)
+
+ /* Map the MMIO registers */
+ regs = devm_platform_ioremap_resource(pdev, 0);
+- if (!regs) {
++ if (IS_ERR(regs)) {
+ dev_err(dev, "failed map MMIO registers\n");
+- return -ENOMEM;
++ return PTR_ERR(regs);
+ }
+
+ /*
+diff --git a/drivers/irqchip/irq-sifive-plic.c b/drivers/irqchip/irq-sifive-plic.c
+index 9e22f7e378f50..4d9ea718086d3 100644
+--- a/drivers/irqchip/irq-sifive-plic.c
++++ b/drivers/irqchip/irq-sifive-plic.c
+@@ -3,6 +3,7 @@
+ * Copyright (C) 2017 SiFive
+ * Copyright (C) 2018 Christoph Hellwig
+ */
++#define pr_fmt(fmt) "riscv-plic: " fmt
+ #include <linux/cpu.h>
+ #include <linux/interrupt.h>
+ #include <linux/io.h>
+@@ -63,7 +64,7 @@
+ #define PLIC_QUIRK_EDGE_INTERRUPT 0
+
+ struct plic_priv {
+- struct device *dev;
++ struct fwnode_handle *fwnode;
+ struct cpumask lmask;
+ struct irq_domain *irqdomain;
+ void __iomem *regs;
+@@ -378,8 +379,8 @@ static void plic_handle_irq(struct irq_desc *desc)
+ int err = generic_handle_domain_irq(handler->priv->irqdomain,
+ hwirq);
+ if (unlikely(err)) {
+- dev_warn_ratelimited(handler->priv->dev,
+- "can't find mapping for hwirq %lu\n", hwirq);
++ pr_warn_ratelimited("%pfwP: can't find mapping for hwirq %lu\n",
++ handler->priv->fwnode, hwirq);
+ }
+ }
+
+@@ -408,7 +409,8 @@ static int plic_starting_cpu(unsigned int cpu)
+ enable_percpu_irq(plic_parent_irq,
+ irq_get_trigger_type(plic_parent_irq));
+ else
+- dev_warn(handler->priv->dev, "cpu%d: parent irq not available\n", cpu);
++ pr_warn("%pfwP: cpu%d: parent irq not available\n",
++ handler->priv->fwnode, cpu);
+ plic_set_threshold(handler, PLIC_ENABLE_THRESHOLD);
+
+ return 0;
+@@ -424,38 +426,36 @@ static const struct of_device_id plic_match[] = {
+ {}
+ };
+
+-static int plic_parse_nr_irqs_and_contexts(struct platform_device *pdev,
++static int plic_parse_nr_irqs_and_contexts(struct fwnode_handle *fwnode,
+ u32 *nr_irqs, u32 *nr_contexts)
+ {
+- struct device *dev = &pdev->dev;
+ int rc;
+
+ /*
+ * Currently, only OF fwnode is supported so extend this
+ * function for ACPI support.
+ */
+- if (!is_of_node(dev->fwnode))
++ if (!is_of_node(fwnode))
+ return -EINVAL;
+
+- rc = of_property_read_u32(to_of_node(dev->fwnode), "riscv,ndev", nr_irqs);
++ rc = of_property_read_u32(to_of_node(fwnode), "riscv,ndev", nr_irqs);
+ if (rc) {
+- dev_err(dev, "riscv,ndev property not available\n");
++ pr_err("%pfwP: riscv,ndev property not available\n", fwnode);
+ return rc;
+ }
+
+- *nr_contexts = of_irq_count(to_of_node(dev->fwnode));
++ *nr_contexts = of_irq_count(to_of_node(fwnode));
+ if (WARN_ON(!(*nr_contexts))) {
+- dev_err(dev, "no PLIC context available\n");
++ pr_err("%pfwP: no PLIC context available\n", fwnode);
+ return -EINVAL;
+ }
+
+ return 0;
+ }
+
+-static int plic_parse_context_parent(struct platform_device *pdev, u32 context,
++static int plic_parse_context_parent(struct fwnode_handle *fwnode, u32 context,
+ u32 *parent_hwirq, int *parent_cpu)
+ {
+- struct device *dev = &pdev->dev;
+ struct of_phandle_args parent;
+ unsigned long hartid;
+ int rc;
+@@ -464,10 +464,10 @@ static int plic_parse_context_parent(struct platform_device *pdev, u32 context,
+ * Currently, only OF fwnode is supported so extend this
+ * function for ACPI support.
+ */
+- if (!is_of_node(dev->fwnode))
++ if (!is_of_node(fwnode))
+ return -EINVAL;
+
+- rc = of_irq_parse_one(to_of_node(dev->fwnode), context, &parent);
++ rc = of_irq_parse_one(to_of_node(fwnode), context, &parent);
+ if (rc)
+ return rc;
+
+@@ -480,48 +480,55 @@ static int plic_parse_context_parent(struct platform_device *pdev, u32 context,
+ return 0;
+ }
+
+-static int plic_probe(struct platform_device *pdev)
++static int plic_probe(struct fwnode_handle *fwnode)
+ {
+ int error = 0, nr_contexts, nr_handlers = 0, cpu, i;
+- struct device *dev = &pdev->dev;
+ unsigned long plic_quirks = 0;
+ struct plic_handler *handler;
+ u32 nr_irqs, parent_hwirq;
+ struct plic_priv *priv;
+ irq_hw_number_t hwirq;
++ void __iomem *regs;
+
+- if (is_of_node(dev->fwnode)) {
++ if (is_of_node(fwnode)) {
+ const struct of_device_id *id;
+
+- id = of_match_node(plic_match, to_of_node(dev->fwnode));
++ id = of_match_node(plic_match, to_of_node(fwnode));
+ if (id)
+ plic_quirks = (unsigned long)id->data;
++
++ regs = of_iomap(to_of_node(fwnode), 0);
++ if (!regs)
++ return -ENOMEM;
++ } else {
++ return -ENODEV;
+ }
+
+- error = plic_parse_nr_irqs_and_contexts(pdev, &nr_irqs, &nr_contexts);
++ error = plic_parse_nr_irqs_and_contexts(fwnode, &nr_irqs, &nr_contexts);
+ if (error)
+- return error;
++ goto fail_free_regs;
+
+- priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+- if (!priv)
+- return -ENOMEM;
++ priv = kzalloc(sizeof(*priv), GFP_KERNEL);
++ if (!priv) {
++ error = -ENOMEM;
++ goto fail_free_regs;
++ }
+
+- priv->dev = dev;
++ priv->fwnode = fwnode;
+ priv->plic_quirks = plic_quirks;
+ priv->nr_irqs = nr_irqs;
++ priv->regs = regs;
+
+- priv->regs = devm_platform_ioremap_resource(pdev, 0);
+- if (WARN_ON(!priv->regs))
+- return -EIO;
+-
+- priv->prio_save = devm_bitmap_zalloc(dev, nr_irqs, GFP_KERNEL);
+- if (!priv->prio_save)
+- return -ENOMEM;
++ priv->prio_save = bitmap_zalloc(nr_irqs, GFP_KERNEL);
++ if (!priv->prio_save) {
++ error = -ENOMEM;
++ goto fail_free_priv;
++ }
+
+ for (i = 0; i < nr_contexts; i++) {
+- error = plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu);
++ error = plic_parse_context_parent(fwnode, i, &parent_hwirq, &cpu);
+ if (error) {
+- dev_warn(dev, "hwirq for context%d not found\n", i);
++ pr_warn("%pfwP: hwirq for context%d not found\n", fwnode, i);
+ continue;
+ }
+
+@@ -543,7 +550,7 @@ static int plic_probe(struct platform_device *pdev)
+ }
+
+ if (cpu < 0) {
+- dev_warn(dev, "Invalid cpuid for context %d\n", i);
++ pr_warn("%pfwP: Invalid cpuid for context %d\n", fwnode, i);
+ continue;
+ }
+
+@@ -554,7 +561,7 @@ static int plic_probe(struct platform_device *pdev)
+ */
+ handler = per_cpu_ptr(&plic_handlers, cpu);
+ if (handler->present) {
+- dev_warn(dev, "handler already present for context %d.\n", i);
++ pr_warn("%pfwP: handler already present for context %d.\n", fwnode, i);
+ plic_set_threshold(handler, PLIC_DISABLE_THRESHOLD);
+ goto done;
+ }
+@@ -568,8 +575,8 @@ static int plic_probe(struct platform_device *pdev)
+ i * CONTEXT_ENABLE_SIZE;
+ handler->priv = priv;
+
+- handler->enable_save = devm_kcalloc(dev, DIV_ROUND_UP(nr_irqs, 32),
+- sizeof(*handler->enable_save), GFP_KERNEL);
++ handler->enable_save = kcalloc(DIV_ROUND_UP(nr_irqs, 32),
++ sizeof(*handler->enable_save), GFP_KERNEL);
+ if (!handler->enable_save)
+ goto fail_cleanup_contexts;
+ done:
+@@ -581,7 +588,7 @@ static int plic_probe(struct platform_device *pdev)
+ nr_handlers++;
+ }
+
+- priv->irqdomain = irq_domain_add_linear(to_of_node(dev->fwnode), nr_irqs + 1,
++ priv->irqdomain = irq_domain_add_linear(to_of_node(fwnode), nr_irqs + 1,
+ &plic_irqdomain_ops, priv);
+ if (WARN_ON(!priv->irqdomain))
+ goto fail_cleanup_contexts;
+@@ -619,13 +626,13 @@ static int plic_probe(struct platform_device *pdev)
+ }
+ }
+
+- dev_info(dev, "mapped %d interrupts with %d handlers for %d contexts.\n",
+- nr_irqs, nr_handlers, nr_contexts);
++ pr_info("%pfwP: mapped %d interrupts with %d handlers for %d contexts.\n",
++ fwnode, nr_irqs, nr_handlers, nr_contexts);
+ return 0;
+
+ fail_cleanup_contexts:
+ for (i = 0; i < nr_contexts; i++) {
+- if (plic_parse_context_parent(pdev, i, &parent_hwirq, &cpu))
++ if (plic_parse_context_parent(fwnode, i, &parent_hwirq, &cpu))
+ continue;
+ if (parent_hwirq != RV_IRQ_EXT || cpu < 0)
+ continue;
+@@ -634,17 +641,37 @@ static int plic_probe(struct platform_device *pdev)
+ handler->present = false;
+ handler->hart_base = NULL;
+ handler->enable_base = NULL;
++ kfree(handler->enable_save);
+ handler->enable_save = NULL;
+ handler->priv = NULL;
+ }
+- return -ENOMEM;
++ bitmap_free(priv->prio_save);
++fail_free_priv:
++ kfree(priv);
++fail_free_regs:
++ iounmap(regs);
++ return error;
++}
++
++static int plic_platform_probe(struct platform_device *pdev)
++{
++ return plic_probe(pdev->dev.fwnode);
+ }
+
+ static struct platform_driver plic_driver = {
+ .driver = {
+ .name = "riscv-plic",
+ .of_match_table = plic_match,
++ .suppress_bind_attrs = true,
+ },
+- .probe = plic_probe,
++ .probe = plic_platform_probe,
+ };
+ builtin_platform_driver(plic_driver);
++
++static int __init plic_early_probe(struct device_node *node,
++ struct device_node *parent)
++{
++ return plic_probe(&node->fwnode);
++}
++
++IRQCHIP_DECLARE(riscv, "allwinner,sun20i-d1-plic", plic_early_probe);
+diff --git a/drivers/leds/leds-spi-byte.c b/drivers/leds/leds-spi-byte.c
+index 96296db5f410d..b04cf502e6035 100644
+--- a/drivers/leds/leds-spi-byte.c
++++ b/drivers/leds/leds-spi-byte.c
+@@ -91,7 +91,6 @@ static int spi_byte_probe(struct spi_device *spi)
+ dev_err(dev, "Device must have exactly one LED sub-node.");
+ return -EINVAL;
+ }
+- child = of_get_next_available_child(dev_of_node(dev), NULL);
+
+ led = devm_kzalloc(dev, sizeof(*led), GFP_KERNEL);
+ if (!led)
+@@ -104,11 +103,13 @@ static int spi_byte_probe(struct spi_device *spi)
+ led->ldev.max_brightness = led->cdef->max_value - led->cdef->off_value;
+ led->ldev.brightness_set_blocking = spi_byte_brightness_set_blocking;
+
++ child = of_get_next_available_child(dev_of_node(dev), NULL);
+ state = of_get_property(child, "default-state", NULL);
+ if (state) {
+ if (!strcmp(state, "on")) {
+ led->ldev.brightness = led->ldev.max_brightness;
+ } else if (strcmp(state, "off")) {
++ of_node_put(child);
+ /* all other cases except "off" */
+ dev_err(dev, "default-state can only be 'on' or 'off'");
+ return -EINVAL;
+@@ -123,9 +124,12 @@ static int spi_byte_probe(struct spi_device *spi)
+
+ ret = devm_led_classdev_register_ext(&spi->dev, &led->ldev, &init_data);
+ if (ret) {
++ of_node_put(child);
+ mutex_destroy(&led->mutex);
+ return ret;
+ }
++
++ of_node_put(child);
+ spi_set_drvdata(spi, led);
+
+ return 0;
+diff --git a/drivers/md/dm-init.c b/drivers/md/dm-init.c
+index 2a71bcdba92d1..b37bbe7625003 100644
+--- a/drivers/md/dm-init.c
++++ b/drivers/md/dm-init.c
+@@ -212,8 +212,10 @@ static char __init *dm_parse_device_entry(struct dm_device *dev, char *str)
+ strscpy(dev->dmi.uuid, field[1], sizeof(dev->dmi.uuid));
+ /* minor */
+ if (strlen(field[2])) {
+- if (kstrtoull(field[2], 0, &dev->dmi.dev))
++ if (kstrtoull(field[2], 0, &dev->dmi.dev) ||
++ dev->dmi.dev >= (1 << MINORBITS))
+ return ERR_PTR(-EINVAL);
++ dev->dmi.dev = huge_encode_dev((dev_t)dev->dmi.dev);
+ dev->dmi.flags |= DM_PERSISTENT_DEV_FLAG;
+ }
+ /* flags */
+diff --git a/drivers/media/platform/qcom/camss/camss.c b/drivers/media/platform/qcom/camss/camss.c
+index 1923615f0eea7..c90a28fa8891f 100644
+--- a/drivers/media/platform/qcom/camss/camss.c
++++ b/drivers/media/platform/qcom/camss/camss.c
+@@ -1406,8 +1406,11 @@ static int camss_of_parse_endpoint_node(struct device *dev,
+ struct v4l2_mbus_config_mipi_csi2 *mipi_csi2;
+ struct v4l2_fwnode_endpoint vep = { { 0 } };
+ unsigned int i;
++ int ret;
+
+- v4l2_fwnode_endpoint_parse(of_fwnode_handle(node), &vep);
++ ret = v4l2_fwnode_endpoint_parse(of_fwnode_handle(node), &vep);
++ if (ret)
++ return ret;
+
+ csd->interface.csiphy_id = vep.base.port;
+
+diff --git a/drivers/media/test-drivers/vivid/vivid-vid-cap.c b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
+index 2804975fe2787..afa0dc5bcdae1 100644
+--- a/drivers/media/test-drivers/vivid/vivid-vid-cap.c
++++ b/drivers/media/test-drivers/vivid/vivid-vid-cap.c
+@@ -106,8 +106,9 @@ static int vid_cap_queue_setup(struct vb2_queue *vq,
+ if (*nplanes != buffers)
+ return -EINVAL;
+ for (p = 0; p < buffers; p++) {
+- if (sizes[p] < tpg_g_line_width(&dev->tpg, p) * h +
+- dev->fmt_cap->data_offset[p])
++ if (sizes[p] < tpg_g_line_width(&dev->tpg, p) * h /
++ dev->fmt_cap->vdownsampling[p] +
++ dev->fmt_cap->data_offset[p])
+ return -EINVAL;
+ }
+ } else {
+@@ -1553,8 +1554,10 @@ int vidioc_s_edid(struct file *file, void *_fh,
+ return -EINVAL;
+ if (edid->blocks == 0) {
+ dev->edid_blocks = 0;
+- v4l2_ctrl_s_ctrl(dev->ctrl_tx_edid_present, 0);
+- v4l2_ctrl_s_ctrl(dev->ctrl_tx_hotplug, 0);
++ if (dev->num_outputs) {
++ v4l2_ctrl_s_ctrl(dev->ctrl_tx_edid_present, 0);
++ v4l2_ctrl_s_ctrl(dev->ctrl_tx_hotplug, 0);
++ }
+ phys_addr = CEC_PHYS_ADDR_INVALID;
+ goto set_phys_addr;
+ }
+@@ -1578,8 +1581,10 @@ int vidioc_s_edid(struct file *file, void *_fh,
+ display_present |=
+ dev->display_present[i] << j++;
+
+- v4l2_ctrl_s_ctrl(dev->ctrl_tx_edid_present, display_present);
+- v4l2_ctrl_s_ctrl(dev->ctrl_tx_hotplug, display_present);
++ if (dev->num_outputs) {
++ v4l2_ctrl_s_ctrl(dev->ctrl_tx_edid_present, display_present);
++ v4l2_ctrl_s_ctrl(dev->ctrl_tx_hotplug, display_present);
++ }
+
+ set_phys_addr:
+ /* TODO: a proper hotplug detect cycle should be emulated here */
+diff --git a/drivers/media/test-drivers/vivid/vivid-vid-out.c b/drivers/media/test-drivers/vivid/vivid-vid-out.c
+index 1653b2988f7e3..7a0f4c61ac807 100644
+--- a/drivers/media/test-drivers/vivid/vivid-vid-out.c
++++ b/drivers/media/test-drivers/vivid/vivid-vid-out.c
+@@ -63,14 +63,16 @@ static int vid_out_queue_setup(struct vb2_queue *vq,
+ if (sizes[0] < size)
+ return -EINVAL;
+ for (p = 1; p < planes; p++) {
+- if (sizes[p] < dev->bytesperline_out[p] * h +
+- vfmt->data_offset[p])
++ if (sizes[p] < dev->bytesperline_out[p] * h /
++ vfmt->vdownsampling[p] +
++ vfmt->data_offset[p])
+ return -EINVAL;
+ }
+ } else {
+ for (p = 0; p < planes; p++)
+- sizes[p] = p ? dev->bytesperline_out[p] * h +
+- vfmt->data_offset[p] : size;
++ sizes[p] = p ? dev->bytesperline_out[p] * h /
++ vfmt->vdownsampling[p] +
++ vfmt->data_offset[p] : size;
+ }
+
+ *nplanes = planes;
+@@ -124,7 +126,7 @@ static int vid_out_buf_prepare(struct vb2_buffer *vb)
+
+ for (p = 0; p < planes; p++) {
+ if (p)
+- size = dev->bytesperline_out[p] * h;
++ size = dev->bytesperline_out[p] * h / vfmt->vdownsampling[p];
+ size += vb->planes[p].data_offset;
+
+ if (vb2_get_plane_payload(vb, p) < size) {
+@@ -331,8 +333,8 @@ int vivid_g_fmt_vid_out(struct file *file, void *priv,
+ for (p = 0; p < mp->num_planes; p++) {
+ mp->plane_fmt[p].bytesperline = dev->bytesperline_out[p];
+ mp->plane_fmt[p].sizeimage =
+- mp->plane_fmt[p].bytesperline * mp->height +
+- fmt->data_offset[p];
++ mp->plane_fmt[p].bytesperline * mp->height /
++ fmt->vdownsampling[p] + fmt->data_offset[p];
+ }
+ for (p = fmt->buffers; p < fmt->planes; p++) {
+ unsigned stride = dev->bytesperline_out[p];
+diff --git a/drivers/media/usb/b2c2/flexcop-usb.c b/drivers/media/usb/b2c2/flexcop-usb.c
+index 90f1aea99dac0..8033622543f28 100644
+--- a/drivers/media/usb/b2c2/flexcop-usb.c
++++ b/drivers/media/usb/b2c2/flexcop-usb.c
+@@ -179,7 +179,7 @@ static int flexcop_usb_memory_req(struct flexcop_usb *fc_usb,
+ flexcop_usb_request_t req, flexcop_usb_mem_page_t page_start,
+ u32 addr, int extended, u8 *buf, u32 len)
+ {
+- int i, ret = 0;
++ int ret = 0;
+ u16 wMax;
+ u32 pagechunk = 0;
+
+@@ -196,7 +196,7 @@ static int flexcop_usb_memory_req(struct flexcop_usb *fc_usb,
+ default:
+ return -EINVAL;
+ }
+- for (i = 0; i < len;) {
++ while (len) {
+ pagechunk = min(wMax, bytes_left_to_read_on_page(addr, len));
+ deb_info("%x\n",
+ (addr & V8_MEMORY_PAGE_MASK) |
+@@ -206,11 +206,12 @@ static int flexcop_usb_memory_req(struct flexcop_usb *fc_usb,
+ page_start + (addr / V8_MEMORY_PAGE_SIZE),
+ (addr & V8_MEMORY_PAGE_MASK) |
+ (V8_MEMORY_EXTENDED*extended),
+- &buf[i], pagechunk);
++ buf, pagechunk);
+
+ if (ret < 0)
+ return ret;
+ addr += pagechunk;
++ buf += pagechunk;
+ len -= pagechunk;
+ }
+ return 0;
+diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
+index 5680856c0fb82..f525971601e4d 100644
+--- a/drivers/misc/fastrpc.c
++++ b/drivers/misc/fastrpc.c
+@@ -1912,7 +1912,8 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
+ &args[0]);
+ if (err) {
+ dev_err(dev, "mmap error (len 0x%08llx)\n", buf->size);
+- goto err_invoke;
++ fastrpc_buf_free(buf);
++ return err;
+ }
+
+ /* update the buffer to be able to deallocate the memory on the DSP */
+@@ -1950,8 +1951,6 @@ static int fastrpc_req_mmap(struct fastrpc_user *fl, char __user *argp)
+
+ err_assign:
+ fastrpc_req_munmap_impl(fl, buf);
+-err_invoke:
+- fastrpc_buf_free(buf);
+
+ return err;
+ }
+diff --git a/drivers/misc/vmw_vmci/vmci_resource.c b/drivers/misc/vmw_vmci/vmci_resource.c
+index 692daa9eff341..19c9d2cdd277b 100644
+--- a/drivers/misc/vmw_vmci/vmci_resource.c
++++ b/drivers/misc/vmw_vmci/vmci_resource.c
+@@ -144,7 +144,8 @@ void vmci_resource_remove(struct vmci_resource *resource)
+ spin_lock(&vmci_resource_table.lock);
+
+ hlist_for_each_entry(r, &vmci_resource_table.entries[idx], node) {
+- if (vmci_handle_is_equal(r->handle, resource->handle)) {
++ if (vmci_handle_is_equal(r->handle, resource->handle) &&
++ resource->type == r->type) {
+ hlist_del_init_rcu(&r->node);
+ break;
+ }
+diff --git a/drivers/mmc/core/quirks.h b/drivers/mmc/core/quirks.h
+index cca71867bc4ad..92905fc46436d 100644
+--- a/drivers/mmc/core/quirks.h
++++ b/drivers/mmc/core/quirks.h
+@@ -15,6 +15,19 @@
+
+ #include "card.h"
+
++static const struct mmc_fixup __maybe_unused mmc_sd_fixups[] = {
++ /*
++ * Kingston Canvas Go! Plus microSD cards never finish SD cache flush.
++ * This has so far only been observed on cards from 11/2019, while new
++ * cards from 2023/05 do not exhibit this behavior.
++ */
++ _FIXUP_EXT("SD64G", CID_MANFID_KINGSTON_SD, 0x5449, 2019, 11,
++ 0, -1ull, SDIO_ANY_ID, SDIO_ANY_ID, add_quirk_sd,
++ MMC_QUIRK_BROKEN_SD_CACHE, EXT_CSD_REV_ANY),
++
++ END_FIXUP
++};
++
+ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = {
+ #define INAND_CMD38_ARG_EXT_CSD 113
+ #define INAND_CMD38_ARG_ERASE 0x00
+@@ -53,15 +66,6 @@ static const struct mmc_fixup __maybe_unused mmc_blk_fixups[] = {
+ MMC_FIXUP("MMC32G", CID_MANFID_TOSHIBA, CID_OEMID_ANY, add_quirk_mmc,
+ MMC_QUIRK_BLK_NO_CMD23),
+
+- /*
+- * Kingston Canvas Go! Plus microSD cards never finish SD cache flush.
+- * This has so far only been observed on cards from 11/2019, while new
+- * cards from 2023/05 do not exhibit this behavior.
+- */
+- _FIXUP_EXT("SD64G", CID_MANFID_KINGSTON_SD, 0x5449, 2019, 11,
+- 0, -1ull, SDIO_ANY_ID, SDIO_ANY_ID, add_quirk_sd,
+- MMC_QUIRK_BROKEN_SD_CACHE, EXT_CSD_REV_ANY),
+-
+ /*
+ * Some SD cards lockup while using CMD23 multiblock transfers.
+ */
+diff --git a/drivers/mmc/core/sd.c b/drivers/mmc/core/sd.c
+index 1c8148cdda505..ee37ad14e79ee 100644
+--- a/drivers/mmc/core/sd.c
++++ b/drivers/mmc/core/sd.c
+@@ -26,6 +26,7 @@
+ #include "host.h"
+ #include "bus.h"
+ #include "mmc_ops.h"
++#include "quirks.h"
+ #include "sd.h"
+ #include "sd_ops.h"
+
+@@ -1475,6 +1476,9 @@ static int mmc_sd_init_card(struct mmc_host *host, u32 ocr,
+ goto free_card;
+ }
+
++ /* Apply quirks prior to card setup */
++ mmc_fixup_device(card, mmc_sd_fixups);
++
+ err = mmc_sd_setup_card(host, card, oldcard != NULL);
+ if (err)
+ goto free_card;
+diff --git a/drivers/mmc/host/cqhci-core.c b/drivers/mmc/host/cqhci-core.c
+index c14d7251d0bbe..a02da26a1efd1 100644
+--- a/drivers/mmc/host/cqhci-core.c
++++ b/drivers/mmc/host/cqhci-core.c
+@@ -617,7 +617,7 @@ static int cqhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
+ cqhci_writel(cq_host, 0, CQHCI_CTL);
+ mmc->cqe_on = true;
+ pr_debug("%s: cqhci: CQE on\n", mmc_hostname(mmc));
+- if (cqhci_readl(cq_host, CQHCI_CTL) && CQHCI_HALT) {
++ if (cqhci_readl(cq_host, CQHCI_CTL) & CQHCI_HALT) {
+ pr_err("%s: cqhci: CQE failed to exit halt state\n",
+ mmc_hostname(mmc));
+ }
+diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
+index a4f813ea177a8..c27e9ab9ff821 100644
+--- a/drivers/mmc/host/dw_mmc.c
++++ b/drivers/mmc/host/dw_mmc.c
+@@ -2951,8 +2951,8 @@ static int dw_mci_init_slot(struct dw_mci *host)
+ if (host->use_dma == TRANS_MODE_IDMAC) {
+ mmc->max_segs = host->ring_size;
+ mmc->max_blk_size = 65535;
+- mmc->max_seg_size = 0x1000;
+- mmc->max_req_size = mmc->max_seg_size * host->ring_size;
++ mmc->max_req_size = DW_MCI_DESC_DATA_LENGTH * host->ring_size;
++ mmc->max_seg_size = mmc->max_req_size;
+ mmc->max_blk_count = mmc->max_req_size / 512;
+ } else if (host->use_dma == TRANS_MODE_EDMAC) {
+ mmc->max_segs = 64;
+diff --git a/drivers/mmc/host/sdhci-of-aspeed.c b/drivers/mmc/host/sdhci-of-aspeed.c
+index 430c1f90037b5..37240895ffaaf 100644
+--- a/drivers/mmc/host/sdhci-of-aspeed.c
++++ b/drivers/mmc/host/sdhci-of-aspeed.c
+@@ -510,6 +510,7 @@ static const struct of_device_id aspeed_sdhci_of_match[] = {
+ { .compatible = "aspeed,ast2600-sdhci", .data = &ast2600_sdhci_pdata, },
+ { }
+ };
++MODULE_DEVICE_TABLE(of, aspeed_sdhci_of_match);
+
+ static struct platform_driver aspeed_sdhci_driver = {
+ .driver = {
+diff --git a/drivers/net/bareudp.c b/drivers/net/bareudp.c
+index d5c56ca91b771..7aca0544fb29c 100644
+--- a/drivers/net/bareudp.c
++++ b/drivers/net/bareudp.c
+@@ -83,7 +83,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+
+ if (skb_copy_bits(skb, BAREUDP_BASE_HLEN, &ipversion,
+ sizeof(ipversion))) {
+- bareudp->dev->stats.rx_dropped++;
++ DEV_STATS_INC(bareudp->dev, rx_dropped);
+ goto drop;
+ }
+ ipversion >>= 4;
+@@ -93,7 +93,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+ } else if (ipversion == 6 && bareudp->multi_proto_mode) {
+ proto = htons(ETH_P_IPV6);
+ } else {
+- bareudp->dev->stats.rx_dropped++;
++ DEV_STATS_INC(bareudp->dev, rx_dropped);
+ goto drop;
+ }
+ } else if (bareudp->ethertype == htons(ETH_P_MPLS_UC)) {
+@@ -107,7 +107,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+ ipv4_is_multicast(tunnel_hdr->daddr)) {
+ proto = htons(ETH_P_MPLS_MC);
+ } else {
+- bareudp->dev->stats.rx_dropped++;
++ DEV_STATS_INC(bareudp->dev, rx_dropped);
+ goto drop;
+ }
+ } else {
+@@ -123,7 +123,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+ (addr_type & IPV6_ADDR_MULTICAST)) {
+ proto = htons(ETH_P_MPLS_MC);
+ } else {
+- bareudp->dev->stats.rx_dropped++;
++ DEV_STATS_INC(bareudp->dev, rx_dropped);
+ goto drop;
+ }
+ }
+@@ -135,7 +135,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+ proto,
+ !net_eq(bareudp->net,
+ dev_net(bareudp->dev)))) {
+- bareudp->dev->stats.rx_dropped++;
++ DEV_STATS_INC(bareudp->dev, rx_dropped);
+ goto drop;
+ }
+
+@@ -143,7 +143,7 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+
+ tun_dst = udp_tun_rx_dst(skb, family, key, 0, 0);
+ if (!tun_dst) {
+- bareudp->dev->stats.rx_dropped++;
++ DEV_STATS_INC(bareudp->dev, rx_dropped);
+ goto drop;
+ }
+ skb_dst_set(skb, &tun_dst->dst);
+@@ -169,8 +169,8 @@ static int bareudp_udp_encap_recv(struct sock *sk, struct sk_buff *skb)
+ &((struct ipv6hdr *)oiph)->saddr);
+ }
+ if (err > 1) {
+- ++bareudp->dev->stats.rx_frame_errors;
+- ++bareudp->dev->stats.rx_errors;
++ DEV_STATS_INC(bareudp->dev, rx_frame_errors);
++ DEV_STATS_INC(bareudp->dev, rx_errors);
+ goto drop;
+ }
+ }
+@@ -467,11 +467,11 @@ static netdev_tx_t bareudp_xmit(struct sk_buff *skb, struct net_device *dev)
+ dev_kfree_skb(skb);
+
+ if (err == -ELOOP)
+- dev->stats.collisions++;
++ DEV_STATS_INC(dev, collisions);
+ else if (err == -ENETUNREACH)
+- dev->stats.tx_carrier_errors++;
++ DEV_STATS_INC(dev, tx_carrier_errors);
+
+- dev->stats.tx_errors++;
++ DEV_STATS_INC(dev, tx_errors);
+ return NETDEV_TX_OK;
+ }
+
+diff --git a/drivers/net/can/kvaser_pciefd.c b/drivers/net/can/kvaser_pciefd.c
+index 7b5028b67cd5c..ab15a2ae8a202 100644
+--- a/drivers/net/can/kvaser_pciefd.c
++++ b/drivers/net/can/kvaser_pciefd.c
+@@ -1640,23 +1640,15 @@ static int kvaser_pciefd_read_buffer(struct kvaser_pciefd *pcie, int dma_buf)
+ return res;
+ }
+
+-static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
++static u32 kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
+ {
+ u32 irq = ioread32(KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
+
+- if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0) {
++ if (irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
+ kvaser_pciefd_read_buffer(pcie, 0);
+- /* Reset DMA buffer 0 */
+- iowrite32(KVASER_PCIEFD_SRB_CMD_RDB0,
+- KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
+- }
+
+- if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1) {
++ if (irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
+ kvaser_pciefd_read_buffer(pcie, 1);
+- /* Reset DMA buffer 1 */
+- iowrite32(KVASER_PCIEFD_SRB_CMD_RDB1,
+- KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
+- }
+
+ if (irq & KVASER_PCIEFD_SRB_IRQ_DOF0 ||
+ irq & KVASER_PCIEFD_SRB_IRQ_DOF1 ||
+@@ -1665,6 +1657,7 @@ static void kvaser_pciefd_receive_irq(struct kvaser_pciefd *pcie)
+ dev_err(&pcie->pci->dev, "DMA IRQ error 0x%08X\n", irq);
+
+ iowrite32(irq, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_IRQ_REG);
++ return irq;
+ }
+
+ static void kvaser_pciefd_transmit_irq(struct kvaser_pciefd_can *can)
+@@ -1691,27 +1684,31 @@ static irqreturn_t kvaser_pciefd_irq_handler(int irq, void *dev)
+ {
+ struct kvaser_pciefd *pcie = (struct kvaser_pciefd *)dev;
+ const struct kvaser_pciefd_irq_mask *irq_mask = pcie->driver_data->irq_mask;
+- u32 board_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
++ u32 pci_irq = ioread32(KVASER_PCIEFD_PCI_IRQ_ADDR(pcie));
++ u32 srb_irq = 0;
++ u32 srb_release = 0;
+ int i;
+
+- if (!(board_irq & irq_mask->all))
++ if (!(pci_irq & irq_mask->all))
+ return IRQ_NONE;
+
+- if (board_irq & irq_mask->kcan_rx0)
+- kvaser_pciefd_receive_irq(pcie);
++ if (pci_irq & irq_mask->kcan_rx0)
++ srb_irq = kvaser_pciefd_receive_irq(pcie);
+
+ for (i = 0; i < pcie->nr_channels; i++) {
+- if (!pcie->can[i]) {
+- dev_err(&pcie->pci->dev,
+- "IRQ mask points to unallocated controller\n");
+- break;
+- }
+-
+- /* Check that mask matches channel (i) IRQ mask */
+- if (board_irq & irq_mask->kcan_tx[i])
++ if (pci_irq & irq_mask->kcan_tx[i])
+ kvaser_pciefd_transmit_irq(pcie->can[i]);
+ }
+
++ if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD0)
++ srb_release |= KVASER_PCIEFD_SRB_CMD_RDB0;
++
++ if (srb_irq & KVASER_PCIEFD_SRB_IRQ_DPD1)
++ srb_release |= KVASER_PCIEFD_SRB_CMD_RDB1;
++
++ if (srb_release)
++ iowrite32(srb_release, KVASER_PCIEFD_SRB_ADDR(pcie) + KVASER_PCIEFD_SRB_CMD_REG);
++
+ return IRQ_HANDLED;
+ }
+
+diff --git a/drivers/net/can/m_can/m_can.c b/drivers/net/can/m_can/m_can.c
+index 14b231c4d7ecf..e4f0a382c2165 100644
+--- a/drivers/net/can/m_can/m_can.c
++++ b/drivers/net/can/m_can/m_can.c
+@@ -449,11 +449,10 @@ static inline void m_can_disable_all_interrupts(struct m_can_classdev *cdev)
+ {
+ m_can_coalescing_disable(cdev);
+ m_can_write(cdev, M_CAN_ILE, 0x0);
+- cdev->active_interrupts = 0x0;
+
+ if (!cdev->net->irq) {
+ dev_dbg(cdev->dev, "Stop hrtimer\n");
+- hrtimer_cancel(&cdev->hrtimer);
++ hrtimer_try_to_cancel(&cdev->hrtimer);
+ }
+ }
+
+@@ -1003,22 +1002,6 @@ static int m_can_rx_handler(struct net_device *dev, int quota, u32 irqstatus)
+ return work_done;
+ }
+
+-static int m_can_rx_peripheral(struct net_device *dev, u32 irqstatus)
+-{
+- struct m_can_classdev *cdev = netdev_priv(dev);
+- int work_done;
+-
+- work_done = m_can_rx_handler(dev, NAPI_POLL_WEIGHT, irqstatus);
+-
+- /* Don't re-enable interrupts if the driver had a fatal error
+- * (e.g., FIFO read failure).
+- */
+- if (work_done < 0)
+- m_can_disable_all_interrupts(cdev);
+-
+- return work_done;
+-}
+-
+ static int m_can_poll(struct napi_struct *napi, int quota)
+ {
+ struct net_device *dev = napi->dev;
+@@ -1183,16 +1166,18 @@ static void m_can_coalescing_update(struct m_can_classdev *cdev, u32 ir)
+ HRTIMER_MODE_REL);
+ }
+
+-static irqreturn_t m_can_isr(int irq, void *dev_id)
++/* This interrupt handler is called either from the interrupt thread or a
++ * hrtimer. This has implications like cancelling a timer won't be possible
++ * blocking.
++ */
++static int m_can_interrupt_handler(struct m_can_classdev *cdev)
+ {
+- struct net_device *dev = (struct net_device *)dev_id;
+- struct m_can_classdev *cdev = netdev_priv(dev);
++ struct net_device *dev = cdev->net;
+ u32 ir;
++ int ret;
+
+- if (pm_runtime_suspended(cdev->dev)) {
+- m_can_coalescing_disable(cdev);
++ if (pm_runtime_suspended(cdev->dev))
+ return IRQ_NONE;
+- }
+
+ ir = m_can_read(cdev, M_CAN_IR);
+ m_can_coalescing_update(cdev, ir);
+@@ -1216,11 +1201,9 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
+ m_can_disable_all_interrupts(cdev);
+ napi_schedule(&cdev->napi);
+ } else {
+- int pkts;
+-
+- pkts = m_can_rx_peripheral(dev, ir);
+- if (pkts < 0)
+- goto out_fail;
++ ret = m_can_rx_handler(dev, NAPI_POLL_WEIGHT, ir);
++ if (ret < 0)
++ return ret;
+ }
+ }
+
+@@ -1238,8 +1221,9 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
+ } else {
+ if (ir & (IR_TEFN | IR_TEFW)) {
+ /* New TX FIFO Element arrived */
+- if (m_can_echo_tx_event(dev) != 0)
+- goto out_fail;
++ ret = m_can_echo_tx_event(dev);
++ if (ret != 0)
++ return ret;
+ }
+ }
+
+@@ -1247,16 +1231,31 @@ static irqreturn_t m_can_isr(int irq, void *dev_id)
+ can_rx_offload_threaded_irq_finish(&cdev->offload);
+
+ return IRQ_HANDLED;
++}
+
+-out_fail:
+- m_can_disable_all_interrupts(cdev);
+- return IRQ_HANDLED;
++static irqreturn_t m_can_isr(int irq, void *dev_id)
++{
++ struct net_device *dev = (struct net_device *)dev_id;
++ struct m_can_classdev *cdev = netdev_priv(dev);
++ int ret;
++
++ ret = m_can_interrupt_handler(cdev);
++ if (ret < 0) {
++ m_can_disable_all_interrupts(cdev);
++ return IRQ_HANDLED;
++ }
++
++ return ret;
+ }
+
+ static enum hrtimer_restart m_can_coalescing_timer(struct hrtimer *timer)
+ {
+ struct m_can_classdev *cdev = container_of(timer, struct m_can_classdev, hrtimer);
+
++ if (cdev->can.state == CAN_STATE_BUS_OFF ||
++ cdev->can.state == CAN_STATE_STOPPED)
++ return HRTIMER_NORESTART;
++
+ irq_wake_thread(cdev->net->irq, cdev->net);
+
+ return HRTIMER_NORESTART;
+@@ -1506,6 +1505,7 @@ static int m_can_chip_config(struct net_device *dev)
+ else
+ interrupts &= ~(IR_ERR_LEC_31X);
+ }
++ cdev->active_interrupts = 0;
+ m_can_interrupt_enable(cdev, interrupts);
+
+ /* route all interrupts to INT0 */
+@@ -1948,8 +1948,17 @@ static enum hrtimer_restart hrtimer_callback(struct hrtimer *timer)
+ {
+ struct m_can_classdev *cdev = container_of(timer, struct
+ m_can_classdev, hrtimer);
++ int ret;
+
+- m_can_isr(0, cdev->net);
++ if (cdev->can.state == CAN_STATE_BUS_OFF ||
++ cdev->can.state == CAN_STATE_STOPPED)
++ return HRTIMER_NORESTART;
++
++ ret = m_can_interrupt_handler(cdev);
++
++ /* On error or if napi is scheduled to read, stop the timer */
++ if (ret < 0 || napi_is_scheduled(&cdev->napi))
++ return HRTIMER_NORESTART;
+
+ hrtimer_forward_now(timer, ms_to_ktime(HRTIMER_POLL_INTERVAL_MS));
+
+@@ -2009,7 +2018,7 @@ static int m_can_open(struct net_device *dev)
+ /* start the m_can controller */
+ err = m_can_start(dev);
+ if (err)
+- goto exit_irq_fail;
++ goto exit_start_fail;
+
+ if (!cdev->is_peripheral)
+ napi_enable(&cdev->napi);
+@@ -2018,6 +2027,9 @@ static int m_can_open(struct net_device *dev)
+
+ return 0;
+
++exit_start_fail:
++ if (cdev->is_peripheral || dev->irq)
++ free_irq(dev->irq, dev);
+ exit_irq_fail:
+ if (cdev->is_peripheral)
+ destroy_workqueue(cdev->tx_wq);
+@@ -2384,12 +2396,15 @@ int m_can_class_suspend(struct device *dev)
+ netif_device_detach(ndev);
+
+ /* leave the chip running with rx interrupt enabled if it is
+- * used as a wake-up source.
++ * used as a wake-up source. Coalescing needs to be reset then,
++ * the timer is cancelled here, interrupts are done in resume.
+ */
+- if (cdev->pm_wake_source)
++ if (cdev->pm_wake_source) {
++ hrtimer_cancel(&cdev->hrtimer);
+ m_can_write(cdev, M_CAN_IE, IR_RF0N);
+- else
++ } else {
+ m_can_stop(ndev);
++ }
+
+ m_can_clk_stop(cdev);
+ }
+@@ -2419,6 +2434,13 @@ int m_can_class_resume(struct device *dev)
+ return ret;
+
+ if (cdev->pm_wake_source) {
++ /* Restore active interrupts but disable coalescing as
++ * we may have missed important waterlevel interrupts
++ * between suspend and resume. Timers are already
++ * stopped in suspend. Here we enable all interrupts
++ * again.
++ */
++ cdev->active_interrupts |= IR_RF0N | IR_TEFN;
+ m_can_write(cdev, M_CAN_IE, cdev->active_interrupts);
+ } else {
+ ret = m_can_start(ndev);
+diff --git a/drivers/net/can/spi/mcp251x.c b/drivers/net/can/spi/mcp251x.c
+index 79c4bab5f7246..8c56f85e87c1a 100644
+--- a/drivers/net/can/spi/mcp251x.c
++++ b/drivers/net/can/spi/mcp251x.c
+@@ -753,7 +753,7 @@ static int mcp251x_hw_wake(struct spi_device *spi)
+ int ret;
+
+ /* Force wakeup interrupt to wake device, but don't execute IST */
+- disable_irq(spi->irq);
++ disable_irq_nosync(spi->irq);
+ mcp251x_write_2regs(spi, CANINTE, CANINTE_WAKIE, CANINTF_WAKIF);
+
+ /* Wait for oscillator startup timer after wake up */
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+index bf1589aef1fc6..f1e6007b74cec 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-core.c
+@@ -2,7 +2,7 @@
+ //
+ // mcp251xfd - Microchip MCP251xFD Family CAN controller driver
+ //
+-// Copyright (c) 2019, 2020, 2021 Pengutronix,
++// Copyright (c) 2019, 2020, 2021, 2023 Pengutronix,
+ // Marc Kleine-Budde <kernel@pengutronix.de>
+ //
+ // Based on:
+@@ -867,18 +867,18 @@ static int mcp251xfd_get_berr_counter(const struct net_device *ndev,
+
+ static struct sk_buff *
+ mcp251xfd_alloc_can_err_skb(struct mcp251xfd_priv *priv,
+- struct can_frame **cf, u32 *timestamp)
++ struct can_frame **cf, u32 *ts_raw)
+ {
+ struct sk_buff *skb;
+ int err;
+
+- err = mcp251xfd_get_timestamp(priv, timestamp);
++ err = mcp251xfd_get_timestamp_raw(priv, ts_raw);
+ if (err)
+ return NULL;
+
+ skb = alloc_can_err_skb(priv->ndev, cf);
+ if (skb)
+- mcp251xfd_skb_set_timestamp(priv, skb, *timestamp);
++ mcp251xfd_skb_set_timestamp_raw(priv, skb, *ts_raw);
+
+ return skb;
+ }
+@@ -889,7 +889,7 @@ static int mcp251xfd_handle_rxovif(struct mcp251xfd_priv *priv)
+ struct mcp251xfd_rx_ring *ring;
+ struct sk_buff *skb;
+ struct can_frame *cf;
+- u32 timestamp, rxovif;
++ u32 ts_raw, rxovif;
+ int err, i;
+
+ stats->rx_over_errors++;
+@@ -924,14 +924,14 @@ static int mcp251xfd_handle_rxovif(struct mcp251xfd_priv *priv)
+ return err;
+ }
+
+- skb = mcp251xfd_alloc_can_err_skb(priv, &cf, ×tamp);
++ skb = mcp251xfd_alloc_can_err_skb(priv, &cf, &ts_raw);
+ if (!skb)
+ return 0;
+
+ cf->can_id |= CAN_ERR_CRTL;
+ cf->data[1] = CAN_ERR_CRTL_RX_OVERFLOW;
+
+- err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
++ err = can_rx_offload_queue_timestamp(&priv->offload, skb, ts_raw);
+ if (err)
+ stats->rx_fifo_errors++;
+
+@@ -948,12 +948,12 @@ static int mcp251xfd_handle_txatif(struct mcp251xfd_priv *priv)
+ static int mcp251xfd_handle_ivmif(struct mcp251xfd_priv *priv)
+ {
+ struct net_device_stats *stats = &priv->ndev->stats;
+- u32 bdiag1, timestamp;
++ u32 bdiag1, ts_raw;
+ struct sk_buff *skb;
+ struct can_frame *cf = NULL;
+ int err;
+
+- err = mcp251xfd_get_timestamp(priv, ×tamp);
++ err = mcp251xfd_get_timestamp_raw(priv, &ts_raw);
+ if (err)
+ return err;
+
+@@ -1035,8 +1035,8 @@ static int mcp251xfd_handle_ivmif(struct mcp251xfd_priv *priv)
+ if (!cf)
+ return 0;
+
+- mcp251xfd_skb_set_timestamp(priv, skb, timestamp);
+- err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
++ mcp251xfd_skb_set_timestamp_raw(priv, skb, ts_raw);
++ err = can_rx_offload_queue_timestamp(&priv->offload, skb, ts_raw);
+ if (err)
+ stats->rx_fifo_errors++;
+
+@@ -1049,7 +1049,7 @@ static int mcp251xfd_handle_cerrif(struct mcp251xfd_priv *priv)
+ struct sk_buff *skb;
+ struct can_frame *cf = NULL;
+ enum can_state new_state, rx_state, tx_state;
+- u32 trec, timestamp;
++ u32 trec, ts_raw;
+ int err;
+
+ err = regmap_read(priv->map_reg, MCP251XFD_REG_TREC, &trec);
+@@ -1079,7 +1079,7 @@ static int mcp251xfd_handle_cerrif(struct mcp251xfd_priv *priv)
+ /* The skb allocation might fail, but can_change_state()
+ * handles cf == NULL.
+ */
+- skb = mcp251xfd_alloc_can_err_skb(priv, &cf, ×tamp);
++ skb = mcp251xfd_alloc_can_err_skb(priv, &cf, &ts_raw);
+ can_change_state(priv->ndev, cf, tx_state, rx_state);
+
+ if (new_state == CAN_STATE_BUS_OFF) {
+@@ -1110,7 +1110,7 @@ static int mcp251xfd_handle_cerrif(struct mcp251xfd_priv *priv)
+ cf->data[7] = bec.rxerr;
+ }
+
+- err = can_rx_offload_queue_timestamp(&priv->offload, skb, timestamp);
++ err = can_rx_offload_queue_timestamp(&priv->offload, skb, ts_raw);
+ if (err)
+ stats->rx_fifo_errors++;
+
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ram.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ram.c
+index 9e8e82cdba461..61b0d6fa52dd8 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ram.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ram.c
+@@ -97,7 +97,16 @@ void can_ram_get_layout(struct can_ram_layout *layout,
+ if (ring) {
+ u8 num_rx_coalesce = 0, num_tx_coalesce = 0;
+
+- num_rx = can_ram_rounddown_pow_of_two(config, &config->rx, 0, ring->rx_pending);
++ /* If the ring parameters have been configured in
++ * CAN-CC mode, but and we are in CAN-FD mode now,
++ * they might be to big. Use the default CAN-FD values
++ * in this case.
++ */
++ num_rx = ring->rx_pending;
++ if (num_rx > layout->max_rx)
++ num_rx = layout->default_rx;
++
++ num_rx = can_ram_rounddown_pow_of_two(config, &config->rx, 0, num_rx);
+
+ /* The ethtool doc says:
+ * To disable coalescing, set usecs = 0 and max_frames = 1.
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+index 4cb79a4f24612..f72582d4d3e8e 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+@@ -206,6 +206,7 @@ mcp251xfd_ring_init_rx(struct mcp251xfd_priv *priv, u16 *base, u8 *fifo_nr)
+ int i, j;
+
+ mcp251xfd_for_each_rx_ring(priv, rx_ring, i) {
++ rx_ring->last_valid = timecounter_read(&priv->tc);
+ rx_ring->head = 0;
+ rx_ring->tail = 0;
+ rx_ring->base = *base;
+@@ -468,11 +469,25 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
+
+ /* switching from CAN-2.0 to CAN-FD mode or vice versa */
+ if (fd_mode != test_bit(MCP251XFD_FLAGS_FD_MODE, priv->flags)) {
++ const struct ethtool_ringparam ring = {
++ .rx_pending = priv->rx_obj_num,
++ .tx_pending = priv->tx->obj_num,
++ };
++ const struct ethtool_coalesce ec = {
++ .rx_coalesce_usecs_irq = priv->rx_coalesce_usecs_irq,
++ .rx_max_coalesced_frames_irq = priv->rx_obj_num_coalesce_irq,
++ .tx_coalesce_usecs_irq = priv->tx_coalesce_usecs_irq,
++ .tx_max_coalesced_frames_irq = priv->tx_obj_num_coalesce_irq,
++ };
+ struct can_ram_layout layout;
+
+- can_ram_get_layout(&layout, &mcp251xfd_ram_config, NULL, NULL, fd_mode);
+- priv->rx_obj_num = layout.default_rx;
+- tx_ring->obj_num = layout.default_tx;
++ can_ram_get_layout(&layout, &mcp251xfd_ram_config, &ring, &ec, fd_mode);
++
++ priv->rx_obj_num = layout.cur_rx;
++ priv->rx_obj_num_coalesce_irq = layout.rx_coalesce;
++
++ tx_ring->obj_num = layout.cur_tx;
++ priv->tx_obj_num_coalesce_irq = layout.tx_coalesce;
+ }
+
+ if (fd_mode) {
+@@ -509,6 +524,8 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
+ }
+
+ rx_ring->obj_num = rx_obj_num;
++ rx_ring->obj_num_shift_to_u8 = BITS_PER_TYPE(rx_ring->obj_num_shift_to_u8) -
++ ilog2(rx_obj_num);
+ rx_ring->obj_size = rx_obj_size;
+ priv->rx[i] = rx_ring;
+ }
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c
+index ced8d9c81f8c6..fe897f3e4c12a 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-rx.c
+@@ -2,7 +2,7 @@
+ //
+ // mcp251xfd - Microchip MCP251xFD Family CAN controller driver
+ //
+-// Copyright (c) 2019, 2020, 2021 Pengutronix,
++// Copyright (c) 2019, 2020, 2021, 2023 Pengutronix,
+ // Marc Kleine-Budde <kernel@pengutronix.de>
+ //
+ // Based on:
+@@ -16,23 +16,14 @@
+
+ #include "mcp251xfd.h"
+
+-static inline int
+-mcp251xfd_rx_head_get_from_chip(const struct mcp251xfd_priv *priv,
+- const struct mcp251xfd_rx_ring *ring,
+- u8 *rx_head, bool *fifo_empty)
++static inline bool mcp251xfd_rx_fifo_sta_empty(const u32 fifo_sta)
+ {
+- u32 fifo_sta;
+- int err;
+-
+- err = regmap_read(priv->map_reg, MCP251XFD_REG_FIFOSTA(ring->fifo_nr),
+- &fifo_sta);
+- if (err)
+- return err;
+-
+- *rx_head = FIELD_GET(MCP251XFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
+- *fifo_empty = !(fifo_sta & MCP251XFD_REG_FIFOSTA_TFNRFNIF);
++ return !(fifo_sta & MCP251XFD_REG_FIFOSTA_TFNRFNIF);
++}
+
+- return 0;
++static inline bool mcp251xfd_rx_fifo_sta_full(const u32 fifo_sta)
++{
++ return fifo_sta & MCP251XFD_REG_FIFOSTA_TFERFFIF;
+ }
+
+ static inline int
+@@ -80,29 +71,49 @@ mcp251xfd_check_rx_tail(const struct mcp251xfd_priv *priv,
+ }
+
+ static int
+-mcp251xfd_rx_ring_update(const struct mcp251xfd_priv *priv,
+- struct mcp251xfd_rx_ring *ring)
++mcp251xfd_get_rx_len(const struct mcp251xfd_priv *priv,
++ const struct mcp251xfd_rx_ring *ring,
++ u8 *len_p)
+ {
+- u32 new_head;
+- u8 chip_rx_head;
+- bool fifo_empty;
++ const u8 shift = ring->obj_num_shift_to_u8;
++ u8 chip_head, tail, len;
++ u32 fifo_sta;
+ int err;
+
+- err = mcp251xfd_rx_head_get_from_chip(priv, ring, &chip_rx_head,
+- &fifo_empty);
+- if (err || fifo_empty)
++ err = regmap_read(priv->map_reg, MCP251XFD_REG_FIFOSTA(ring->fifo_nr),
++ &fifo_sta);
++ if (err)
++ return err;
++
++ if (mcp251xfd_rx_fifo_sta_empty(fifo_sta)) {
++ *len_p = 0;
++ return 0;
++ }
++
++ if (mcp251xfd_rx_fifo_sta_full(fifo_sta)) {
++ *len_p = ring->obj_num;
++ return 0;
++ }
++
++ chip_head = FIELD_GET(MCP251XFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
++
++ err = mcp251xfd_check_rx_tail(priv, ring);
++ if (err)
+ return err;
++ tail = mcp251xfd_get_rx_tail(ring);
+
+- /* chip_rx_head, is the next RX-Object filled by the HW.
+- * The new RX head must be >= the old head.
++ /* First shift to full u8. The subtraction works on signed
++ * values, that keeps the difference steady around the u8
++ * overflow. The right shift acts on len, which is an u8.
+ */
+- new_head = round_down(ring->head, ring->obj_num) + chip_rx_head;
+- if (new_head <= ring->head)
+- new_head += ring->obj_num;
++ BUILD_BUG_ON(sizeof(ring->obj_num) != sizeof(chip_head));
++ BUILD_BUG_ON(sizeof(ring->obj_num) != sizeof(tail));
++ BUILD_BUG_ON(sizeof(ring->obj_num) != sizeof(len));
+
+- ring->head = new_head;
++ len = (chip_head << shift) - (tail << shift);
++ *len_p = len >> shift;
+
+- return mcp251xfd_check_rx_tail(priv, ring);
++ return 0;
+ }
+
+ static void
+@@ -148,8 +159,6 @@ mcp251xfd_hw_rx_obj_to_skb(const struct mcp251xfd_priv *priv,
+
+ if (!(hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_RTR))
+ memcpy(cfd->data, hw_rx_obj->data, cfd->len);
+-
+- mcp251xfd_skb_set_timestamp(priv, skb, hw_rx_obj->ts);
+ }
+
+ static int
+@@ -160,8 +169,26 @@ mcp251xfd_handle_rxif_one(struct mcp251xfd_priv *priv,
+ struct net_device_stats *stats = &priv->ndev->stats;
+ struct sk_buff *skb;
+ struct canfd_frame *cfd;
++ u64 timestamp;
+ int err;
+
++ /* According to mcp2518fd erratum DS80000789E 6. the FIFOCI
++ * bits of a FIFOSTA register, here the RX FIFO head index
++ * might be corrupted and we might process past the RX FIFO's
++ * head into old CAN frames.
++ *
++ * Compare the timestamp of currently processed CAN frame with
++ * last valid frame received. Abort with -EBADMSG if an old
++ * CAN frame is detected.
++ */
++ timestamp = timecounter_cyc2time(&priv->tc, hw_rx_obj->ts);
++ if (timestamp <= ring->last_valid) {
++ stats->rx_fifo_errors++;
++
++ return -EBADMSG;
++ }
++ ring->last_valid = timestamp;
++
+ if (hw_rx_obj->flags & MCP251XFD_OBJ_FLAGS_FDF)
+ skb = alloc_canfd_skb(priv->ndev, &cfd);
+ else
+@@ -172,6 +199,7 @@ mcp251xfd_handle_rxif_one(struct mcp251xfd_priv *priv,
+ return 0;
+ }
+
++ mcp251xfd_skb_set_timestamp(skb, timestamp);
+ mcp251xfd_hw_rx_obj_to_skb(priv, hw_rx_obj, skb);
+ err = can_rx_offload_queue_timestamp(&priv->offload, skb, hw_rx_obj->ts);
+ if (err)
+@@ -197,52 +225,81 @@ mcp251xfd_rx_obj_read(const struct mcp251xfd_priv *priv,
+ return err;
+ }
+
++static int
++mcp251xfd_handle_rxif_ring_uinc(const struct mcp251xfd_priv *priv,
++ struct mcp251xfd_rx_ring *ring,
++ u8 len)
++{
++ int offset;
++ int err;
++
++ if (!len)
++ return 0;
++
++ ring->head += len;
++
++ /* Increment the RX FIFO tail pointer 'len' times in a
++ * single SPI message.
++ *
++ * Note:
++ * Calculate offset, so that the SPI transfer ends on
++ * the last message of the uinc_xfer array, which has
++ * "cs_change == 0", to properly deactivate the chip
++ * select.
++ */
++ offset = ARRAY_SIZE(ring->uinc_xfer) - len;
++ err = spi_sync_transfer(priv->spi,
++ ring->uinc_xfer + offset, len);
++ if (err)
++ return err;
++
++ ring->tail += len;
++
++ return 0;
++}
++
+ static int
+ mcp251xfd_handle_rxif_ring(struct mcp251xfd_priv *priv,
+ struct mcp251xfd_rx_ring *ring)
+ {
+ struct mcp251xfd_hw_rx_obj_canfd *hw_rx_obj = ring->obj;
+- u8 rx_tail, len;
++ u8 rx_tail, len, l;
+ int err, i;
+
+- err = mcp251xfd_rx_ring_update(priv, ring);
++ err = mcp251xfd_get_rx_len(priv, ring, &len);
+ if (err)
+ return err;
+
+- while ((len = mcp251xfd_get_rx_linear_len(ring))) {
+- int offset;
+-
++ while ((l = mcp251xfd_get_rx_linear_len(ring, len))) {
+ rx_tail = mcp251xfd_get_rx_tail(ring);
+
+ err = mcp251xfd_rx_obj_read(priv, ring, hw_rx_obj,
+- rx_tail, len);
++ rx_tail, l);
+ if (err)
+ return err;
+
+- for (i = 0; i < len; i++) {
++ for (i = 0; i < l; i++) {
+ err = mcp251xfd_handle_rxif_one(priv, ring,
+ (void *)hw_rx_obj +
+ i * ring->obj_size);
+- if (err)
++
++ /* -EBADMSG means we're affected by mcp2518fd
++ * erratum DS80000789E 6., i.e. the timestamp
++ * in the RX object is older that the last
++ * valid received CAN frame. Don't process any
++ * further and mark processed frames as good.
++ */
++ if (err == -EBADMSG)
++ return mcp251xfd_handle_rxif_ring_uinc(priv, ring, i);
++ else if (err)
+ return err;
+ }
+
+- /* Increment the RX FIFO tail pointer 'len' times in a
+- * single SPI message.
+- *
+- * Note:
+- * Calculate offset, so that the SPI transfer ends on
+- * the last message of the uinc_xfer array, which has
+- * "cs_change == 0", to properly deactivate the chip
+- * select.
+- */
+- offset = ARRAY_SIZE(ring->uinc_xfer) - len;
+- err = spi_sync_transfer(priv->spi,
+- ring->uinc_xfer + offset, len);
++ err = mcp251xfd_handle_rxif_ring_uinc(priv, ring, l);
+ if (err)
+ return err;
+
+- ring->tail += len;
++ len -= l;
+ }
+
+ return 0;
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+index 5b0c7890d4b44..3886476a8f8ef 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+@@ -97,7 +97,7 @@ mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
+ tef_tail = mcp251xfd_get_tef_tail(priv);
+ skb = priv->can.echo_skb[tef_tail];
+ if (skb)
+- mcp251xfd_skb_set_timestamp(priv, skb, hw_tef_obj->ts);
++ mcp251xfd_skb_set_timestamp_raw(priv, skb, hw_tef_obj->ts);
+ stats->tx_bytes +=
+ can_rx_offload_get_echo_skb_queue_timestamp(&priv->offload,
+ tef_tail, hw_tef_obj->ts,
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
+index 712e091869870..1db99aabe85c5 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-timestamp.c
+@@ -2,7 +2,7 @@
+ //
+ // mcp251xfd - Microchip MCP251xFD Family CAN controller driver
+ //
+-// Copyright (c) 2021 Pengutronix,
++// Copyright (c) 2021, 2023 Pengutronix,
+ // Marc Kleine-Budde <kernel@pengutronix.de>
+ //
+
+@@ -11,20 +11,20 @@
+
+ #include "mcp251xfd.h"
+
+-static u64 mcp251xfd_timestamp_read(const struct cyclecounter *cc)
++static u64 mcp251xfd_timestamp_raw_read(const struct cyclecounter *cc)
+ {
+ const struct mcp251xfd_priv *priv;
+- u32 timestamp = 0;
++ u32 ts_raw = 0;
+ int err;
+
+ priv = container_of(cc, struct mcp251xfd_priv, cc);
+- err = mcp251xfd_get_timestamp(priv, ×tamp);
++ err = mcp251xfd_get_timestamp_raw(priv, &ts_raw);
+ if (err)
+ netdev_err(priv->ndev,
+ "Error %d while reading timestamp. HW timestamps may be inaccurate.",
+ err);
+
+- return timestamp;
++ return ts_raw;
+ }
+
+ static void mcp251xfd_timestamp_work(struct work_struct *work)
+@@ -39,21 +39,11 @@ static void mcp251xfd_timestamp_work(struct work_struct *work)
+ MCP251XFD_TIMESTAMP_WORK_DELAY_SEC * HZ);
+ }
+
+-void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv,
+- struct sk_buff *skb, u32 timestamp)
+-{
+- struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
+- u64 ns;
+-
+- ns = timecounter_cyc2time(&priv->tc, timestamp);
+- hwtstamps->hwtstamp = ns_to_ktime(ns);
+-}
+-
+ void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv)
+ {
+ struct cyclecounter *cc = &priv->cc;
+
+- cc->read = mcp251xfd_timestamp_read;
++ cc->read = mcp251xfd_timestamp_raw_read;
+ cc->mask = CYCLECOUNTER_MASK(32);
+ cc->shift = 1;
+ cc->mult = clocksource_hz2mult(priv->can.clock.freq, cc->shift);
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+index 4628bf847bc9b..991662fbba42e 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+@@ -2,7 +2,7 @@
+ *
+ * mcp251xfd - Microchip MCP251xFD Family CAN controller driver
+ *
+- * Copyright (c) 2019, 2020, 2021 Pengutronix,
++ * Copyright (c) 2019, 2020, 2021, 2023 Pengutronix,
+ * Marc Kleine-Budde <kernel@pengutronix.de>
+ * Copyright (c) 2019 Martin Sperl <kernel@martin.sperl.org>
+ */
+@@ -554,10 +554,14 @@ struct mcp251xfd_rx_ring {
+ unsigned int head;
+ unsigned int tail;
+
++ /* timestamp of the last valid received CAN frame */
++ u64 last_valid;
++
+ u16 base;
+ u8 nr;
+ u8 fifo_nr;
+ u8 obj_num;
++ u8 obj_num_shift_to_u8;
+ u8 obj_size;
+
+ union mcp251xfd_write_reg_buf irq_enable_buf;
+@@ -811,10 +815,27 @@ mcp251xfd_spi_cmd_write(const struct mcp251xfd_priv *priv,
+ return data;
+ }
+
+-static inline int mcp251xfd_get_timestamp(const struct mcp251xfd_priv *priv,
+- u32 *timestamp)
++static inline int mcp251xfd_get_timestamp_raw(const struct mcp251xfd_priv *priv,
++ u32 *ts_raw)
++{
++ return regmap_read(priv->map_reg, MCP251XFD_REG_TBC, ts_raw);
++}
++
++static inline void mcp251xfd_skb_set_timestamp(struct sk_buff *skb, u64 ns)
++{
++ struct skb_shared_hwtstamps *hwtstamps = skb_hwtstamps(skb);
++
++ hwtstamps->hwtstamp = ns_to_ktime(ns);
++}
++
++static inline
++void mcp251xfd_skb_set_timestamp_raw(const struct mcp251xfd_priv *priv,
++ struct sk_buff *skb, u32 ts_raw)
+ {
+- return regmap_read(priv->map_reg, MCP251XFD_REG_TBC, timestamp);
++ u64 ns;
++
++ ns = timecounter_cyc2time(&priv->tc, ts_raw);
++ mcp251xfd_skb_set_timestamp(skb, ns);
+ }
+
+ static inline u16 mcp251xfd_get_tef_obj_addr(u8 n)
+@@ -907,18 +928,9 @@ static inline u8 mcp251xfd_get_rx_tail(const struct mcp251xfd_rx_ring *ring)
+ return ring->tail & (ring->obj_num - 1);
+ }
+
+-static inline u8 mcp251xfd_get_rx_len(const struct mcp251xfd_rx_ring *ring)
+-{
+- return ring->head - ring->tail;
+-}
+-
+ static inline u8
+-mcp251xfd_get_rx_linear_len(const struct mcp251xfd_rx_ring *ring)
++mcp251xfd_get_rx_linear_len(const struct mcp251xfd_rx_ring *ring, u8 len)
+ {
+- u8 len;
+-
+- len = mcp251xfd_get_rx_len(ring);
+-
+ return min_t(u8, len, ring->obj_num - mcp251xfd_get_rx_tail(ring));
+ }
+
+@@ -944,8 +956,6 @@ void mcp251xfd_ring_free(struct mcp251xfd_priv *priv);
+ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv);
+ int mcp251xfd_handle_rxif(struct mcp251xfd_priv *priv);
+ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv);
+-void mcp251xfd_skb_set_timestamp(const struct mcp251xfd_priv *priv,
+- struct sk_buff *skb, u32 timestamp);
+ void mcp251xfd_timestamp_init(struct mcp251xfd_priv *priv);
+ void mcp251xfd_timestamp_stop(struct mcp251xfd_priv *priv);
+
+diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
+index 56bb77dbd28a2..cefddcf3cc6fe 100644
+--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
++++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
+@@ -34,7 +34,7 @@
+ #define VSC73XX_BLOCK_ANALYZER 0x2 /* Only subblock 0 */
+ #define VSC73XX_BLOCK_MII 0x3 /* Subblocks 0 and 1 */
+ #define VSC73XX_BLOCK_MEMINIT 0x3 /* Only subblock 2 */
+-#define VSC73XX_BLOCK_CAPTURE 0x4 /* Only subblock 2 */
++#define VSC73XX_BLOCK_CAPTURE 0x4 /* Subblocks 0-4, 6, 7 */
+ #define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */
+ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */
+
+@@ -370,13 +370,19 @@ int vsc73xx_is_addr_valid(u8 block, u8 subblock)
+ break;
+
+ case VSC73XX_BLOCK_MII:
+- case VSC73XX_BLOCK_CAPTURE:
+ case VSC73XX_BLOCK_ARBITER:
+ switch (subblock) {
+ case 0 ... 1:
+ return 1;
+ }
+ break;
++ case VSC73XX_BLOCK_CAPTURE:
++ switch (subblock) {
++ case 0 ... 4:
++ case 6 ... 7:
++ return 1;
++ }
++ break;
+ }
+
+ return 0;
+diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+index baa0b3c2ce6ff..946c3d3b69d94 100644
+--- a/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
++++ b/drivers/net/ethernet/freescale/dpaa/dpaa_eth.c
+@@ -931,14 +931,18 @@ static inline void dpaa_setup_egress(const struct dpaa_priv *priv,
+ }
+ }
+
+-static void dpaa_fq_setup(struct dpaa_priv *priv,
+- const struct dpaa_fq_cbs *fq_cbs,
+- struct fman_port *tx_port)
++static int dpaa_fq_setup(struct dpaa_priv *priv,
++ const struct dpaa_fq_cbs *fq_cbs,
++ struct fman_port *tx_port)
+ {
+ int egress_cnt = 0, conf_cnt = 0, num_portals = 0, portal_cnt = 0, cpu;
+ const cpumask_t *affine_cpus = qman_affine_cpus();
+- u16 channels[NR_CPUS];
+ struct dpaa_fq *fq;
++ u16 *channels;
++
++ channels = kcalloc(num_possible_cpus(), sizeof(u16), GFP_KERNEL);
++ if (!channels)
++ return -ENOMEM;
+
+ for_each_cpu_and(cpu, affine_cpus, cpu_online_mask)
+ channels[num_portals++] = qman_affine_channel(cpu);
+@@ -997,6 +1001,10 @@ static void dpaa_fq_setup(struct dpaa_priv *priv,
+ break;
+ }
+ }
++
++ kfree(channels);
++
++ return 0;
+ }
+
+ static inline int dpaa_tx_fq_to_id(const struct dpaa_priv *priv,
+@@ -3416,7 +3424,9 @@ static int dpaa_eth_probe(struct platform_device *pdev)
+ */
+ dpaa_eth_add_channel(priv->channel, &pdev->dev);
+
+- dpaa_fq_setup(priv, &dpaa_fq_cbs, priv->mac_dev->port[TX]);
++ err = dpaa_fq_setup(priv, &dpaa_fq_cbs, priv->mac_dev->port[TX]);
++ if (err)
++ goto free_dpaa_bps;
+
+ /* Create a congestion group for this netdev, with
+ * dynamically-allocated CGR ID.
+diff --git a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+index 5bd0b36d1feb5..3f8cd4a7d8457 100644
+--- a/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
++++ b/drivers/net/ethernet/freescale/dpaa/dpaa_ethtool.c
+@@ -457,12 +457,16 @@ static int dpaa_set_coalesce(struct net_device *dev,
+ struct netlink_ext_ack *extack)
+ {
+ const cpumask_t *cpus = qman_affine_cpus();
+- bool needs_revert[NR_CPUS] = {false};
+ struct qman_portal *portal;
+ u32 period, prev_period;
+ u8 thresh, prev_thresh;
++ bool *needs_revert;
+ int cpu, res;
+
++ needs_revert = kcalloc(num_possible_cpus(), sizeof(bool), GFP_KERNEL);
++ if (!needs_revert)
++ return -ENOMEM;
++
+ period = c->rx_coalesce_usecs;
+ thresh = c->rx_max_coalesced_frames;
+
+@@ -485,6 +489,8 @@ static int dpaa_set_coalesce(struct net_device *dev,
+ needs_revert[cpu] = true;
+ }
+
++ kfree(needs_revert);
++
+ return 0;
+
+ revert_values:
+@@ -498,6 +504,8 @@ static int dpaa_set_coalesce(struct net_device *dev,
+ qman_dqrr_set_ithresh(portal, prev_thresh);
+ }
+
++ kfree(needs_revert);
++
+ return res;
+ }
+
+diff --git a/drivers/net/ethernet/google/gve/gve.h b/drivers/net/ethernet/google/gve/gve.h
+index ae1e21c9b0a54..ca7fce17f2c05 100644
+--- a/drivers/net/ethernet/google/gve/gve.h
++++ b/drivers/net/ethernet/google/gve/gve.h
+@@ -724,6 +724,7 @@ struct gve_priv {
+ union gve_adminq_command *adminq;
+ dma_addr_t adminq_bus_addr;
+ struct dma_pool *adminq_pool;
++ struct mutex adminq_lock; /* Protects adminq command execution */
+ u32 adminq_mask; /* masks prod_cnt to adminq size */
+ u32 adminq_prod_cnt; /* free-running count of AQ cmds executed */
+ u32 adminq_cmd_fail; /* free-running count of AQ cmds failed */
+diff --git a/drivers/net/ethernet/google/gve/gve_adminq.c b/drivers/net/ethernet/google/gve/gve_adminq.c
+index 8ca0def176ef4..2e0c1eb87b11c 100644
+--- a/drivers/net/ethernet/google/gve/gve_adminq.c
++++ b/drivers/net/ethernet/google/gve/gve_adminq.c
+@@ -284,6 +284,7 @@ int gve_adminq_alloc(struct device *dev, struct gve_priv *priv)
+ &priv->reg_bar0->adminq_base_address_lo);
+ iowrite32be(GVE_DRIVER_STATUS_RUN_MASK, &priv->reg_bar0->driver_status);
+ }
++ mutex_init(&priv->adminq_lock);
+ gve_set_admin_queue_ok(priv);
+ return 0;
+ }
+@@ -511,28 +512,29 @@ static int gve_adminq_issue_cmd(struct gve_priv *priv,
+ return 0;
+ }
+
+-/* This function is not threadsafe - the caller is responsible for any
+- * necessary locks.
+- * The caller is also responsible for making sure there are no commands
+- * waiting to be executed.
+- */
+ static int gve_adminq_execute_cmd(struct gve_priv *priv,
+ union gve_adminq_command *cmd_orig)
+ {
+ u32 tail, head;
+ int err;
+
++ mutex_lock(&priv->adminq_lock);
+ tail = ioread32be(&priv->reg_bar0->adminq_event_counter);
+ head = priv->adminq_prod_cnt;
+- if (tail != head)
+- // This is not a valid path
+- return -EINVAL;
++ if (tail != head) {
++ err = -EINVAL;
++ goto out;
++ }
+
+ err = gve_adminq_issue_cmd(priv, cmd_orig);
+ if (err)
+- return err;
++ goto out;
+
+- return gve_adminq_kick_and_wait(priv);
++ err = gve_adminq_kick_and_wait(priv);
++
++out:
++ mutex_unlock(&priv->adminq_lock);
++ return err;
+ }
+
+ /* The device specifies that the management vector can either be the first irq
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+index e132c2f095609..cc7f46c0b35ff 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_err.c
+@@ -1598,8 +1598,7 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev)
+ {
+ u32 loop_para[HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE] = {0};
+ struct hclge_mod_reg_common_msg msg;
+- u8 i, j, num;
+- u32 loop_time;
++ u8 i, j, num, loop_time;
+
+ num = ARRAY_SIZE(hclge_ssu_reg_common_msg);
+ for (i = 0; i < num; i++) {
+@@ -1609,7 +1608,8 @@ static void hclge_query_reg_info_of_ssu(struct hclge_dev *hdev)
+ loop_time = 1;
+ loop_para[0] = 0;
+ if (msg.need_para) {
+- loop_time = hdev->ae_dev->dev_specs.tnl_num;
++ loop_time = min(hdev->ae_dev->dev_specs.tnl_num,
++ HCLGE_MOD_MSG_PARA_ARRAY_MAX_SIZE);
+ for (j = 0; j < loop_time; j++)
+ loop_para[j] = j + 1;
+ }
+diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
+index caaa10157909e..ce8b5505b16da 100644
+--- a/drivers/net/ethernet/intel/ice/ice.h
++++ b/drivers/net/ethernet/intel/ice/ice.h
+@@ -318,6 +318,7 @@ enum ice_vsi_state {
+ ICE_VSI_UMAC_FLTR_CHANGED,
+ ICE_VSI_MMAC_FLTR_CHANGED,
+ ICE_VSI_PROMISC_CHANGED,
++ ICE_VSI_REBUILD_PENDING,
+ ICE_VSI_STATE_NBITS /* must be last */
+ };
+
+@@ -411,6 +412,7 @@ struct ice_vsi {
+ struct ice_tx_ring **xdp_rings; /* XDP ring array */
+ u16 num_xdp_txq; /* Used XDP queues */
+ u8 xdp_mapping_mode; /* ICE_MAP_MODE_[CONTIG|SCATTER] */
++ struct mutex xdp_state_lock;
+
+ struct net_device **target_netdevs;
+
+diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
+index f448d3a845642..c158749a80e05 100644
+--- a/drivers/net/ethernet/intel/ice/ice_base.c
++++ b/drivers/net/ethernet/intel/ice/ice_base.c
+@@ -190,16 +190,11 @@ static void ice_free_q_vector(struct ice_vsi *vsi, int v_idx)
+ }
+ q_vector = vsi->q_vectors[v_idx];
+
+- ice_for_each_tx_ring(tx_ring, q_vector->tx) {
+- ice_queue_set_napi(vsi, tx_ring->q_index, NETDEV_QUEUE_TYPE_TX,
+- NULL);
++ ice_for_each_tx_ring(tx_ring, vsi->q_vectors[v_idx]->tx)
+ tx_ring->q_vector = NULL;
+- }
+- ice_for_each_rx_ring(rx_ring, q_vector->rx) {
+- ice_queue_set_napi(vsi, rx_ring->q_index, NETDEV_QUEUE_TYPE_RX,
+- NULL);
++
++ ice_for_each_rx_ring(rx_ring, vsi->q_vectors[v_idx]->rx)
+ rx_ring->q_vector = NULL;
+- }
+
+ /* only VSI with an associated netdev is set up with NAPI */
+ if (vsi->netdev)
+diff --git a/drivers/net/ethernet/intel/ice/ice_lib.c b/drivers/net/ethernet/intel/ice/ice_lib.c
+index 7629b0190578b..7076a77388641 100644
+--- a/drivers/net/ethernet/intel/ice/ice_lib.c
++++ b/drivers/net/ethernet/intel/ice/ice_lib.c
+@@ -447,6 +447,7 @@ static void ice_vsi_free(struct ice_vsi *vsi)
+
+ ice_vsi_free_stats(vsi);
+ ice_vsi_free_arrays(vsi);
++ mutex_destroy(&vsi->xdp_state_lock);
+ mutex_unlock(&pf->sw_mutex);
+ devm_kfree(dev, vsi);
+ }
+@@ -626,6 +627,8 @@ static struct ice_vsi *ice_vsi_alloc(struct ice_pf *pf)
+ pf->next_vsi = ice_get_free_slot(pf->vsi, pf->num_alloc_vsi,
+ pf->next_vsi);
+
++ mutex_init(&vsi->xdp_state_lock);
++
+ unlock_pf:
+ mutex_unlock(&pf->sw_mutex);
+ return vsi;
+@@ -2286,9 +2289,6 @@ static int ice_vsi_cfg_def(struct ice_vsi *vsi)
+
+ ice_vsi_map_rings_to_vectors(vsi);
+
+- /* Associate q_vector rings to napi */
+- ice_vsi_set_napi_queues(vsi);
+-
+ vsi->stat_offsets_loaded = false;
+
+ /* ICE_VSI_CTRL does not need RSS so skip RSS processing */
+@@ -2628,6 +2628,7 @@ void ice_vsi_close(struct ice_vsi *vsi)
+ if (!test_and_set_bit(ICE_VSI_DOWN, vsi->state))
+ ice_down(vsi);
+
++ ice_vsi_clear_napi_queues(vsi);
+ ice_vsi_free_irq(vsi);
+ ice_vsi_free_tx_rings(vsi);
+ ice_vsi_free_rx_rings(vsi);
+@@ -2671,8 +2672,7 @@ int ice_ena_vsi(struct ice_vsi *vsi, bool locked)
+ */
+ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
+ {
+- if (test_bit(ICE_VSI_DOWN, vsi->state))
+- return;
++ bool already_down = test_bit(ICE_VSI_DOWN, vsi->state);
+
+ set_bit(ICE_VSI_NEEDS_RESTART, vsi->state);
+
+@@ -2680,134 +2680,70 @@ void ice_dis_vsi(struct ice_vsi *vsi, bool locked)
+ if (netif_running(vsi->netdev)) {
+ if (!locked)
+ rtnl_lock();
+-
+- ice_vsi_close(vsi);
++ already_down = test_bit(ICE_VSI_DOWN, vsi->state);
++ if (!already_down)
++ ice_vsi_close(vsi);
+
+ if (!locked)
+ rtnl_unlock();
+- } else {
++ } else if (!already_down) {
+ ice_vsi_close(vsi);
+ }
+- } else if (vsi->type == ICE_VSI_CTRL) {
++ } else if (vsi->type == ICE_VSI_CTRL && !already_down) {
+ ice_vsi_close(vsi);
+ }
+ }
+
+ /**
+- * __ice_queue_set_napi - Set the napi instance for the queue
+- * @dev: device to which NAPI and queue belong
+- * @queue_index: Index of queue
+- * @type: queue type as RX or TX
+- * @napi: NAPI context
+- * @locked: is the rtnl_lock already held
+- *
+- * Set the napi instance for the queue. Caller indicates the lock status.
+- */
+-static void
+-__ice_queue_set_napi(struct net_device *dev, unsigned int queue_index,
+- enum netdev_queue_type type, struct napi_struct *napi,
+- bool locked)
+-{
+- if (!locked)
+- rtnl_lock();
+- netif_queue_set_napi(dev, queue_index, type, napi);
+- if (!locked)
+- rtnl_unlock();
+-}
+-
+-/**
+- * ice_queue_set_napi - Set the napi instance for the queue
+- * @vsi: VSI being configured
+- * @queue_index: Index of queue
+- * @type: queue type as RX or TX
+- * @napi: NAPI context
++ * ice_vsi_set_napi_queues - associate netdev queues with napi
++ * @vsi: VSI pointer
+ *
+- * Set the napi instance for the queue. The rtnl lock state is derived from the
+- * execution path.
++ * Associate queue[s] with napi for all vectors.
++ * The caller must hold rtnl_lock.
+ */
+-void
+-ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
+- enum netdev_queue_type type, struct napi_struct *napi)
++void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
+ {
+- struct ice_pf *pf = vsi->back;
++ struct net_device *netdev = vsi->netdev;
++ int q_idx, v_idx;
+
+- if (!vsi->netdev)
++ if (!netdev)
+ return;
+
+- if (current_work() == &pf->serv_task ||
+- test_bit(ICE_PREPARED_FOR_RESET, pf->state) ||
+- test_bit(ICE_DOWN, pf->state) ||
+- test_bit(ICE_SUSPENDED, pf->state))
+- __ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
+- false);
+- else
+- __ice_queue_set_napi(vsi->netdev, queue_index, type, napi,
+- true);
+-}
++ ice_for_each_rxq(vsi, q_idx)
++ netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX,
++ &vsi->rx_rings[q_idx]->q_vector->napi);
+
+-/**
+- * __ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
+- * @q_vector: q_vector pointer
+- * @locked: is the rtnl_lock already held
+- *
+- * Associate the q_vector napi with all the queue[s] on the vector.
+- * Caller indicates the lock status.
+- */
+-void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked)
+-{
+- struct ice_rx_ring *rx_ring;
+- struct ice_tx_ring *tx_ring;
+-
+- ice_for_each_rx_ring(rx_ring, q_vector->rx)
+- __ice_queue_set_napi(q_vector->vsi->netdev, rx_ring->q_index,
+- NETDEV_QUEUE_TYPE_RX, &q_vector->napi,
+- locked);
+-
+- ice_for_each_tx_ring(tx_ring, q_vector->tx)
+- __ice_queue_set_napi(q_vector->vsi->netdev, tx_ring->q_index,
+- NETDEV_QUEUE_TYPE_TX, &q_vector->napi,
+- locked);
++ ice_for_each_txq(vsi, q_idx)
++ netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX,
++ &vsi->tx_rings[q_idx]->q_vector->napi);
+ /* Also set the interrupt number for the NAPI */
+- netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
+-}
+-
+-/**
+- * ice_q_vector_set_napi_queues - Map queue[s] associated with the napi
+- * @q_vector: q_vector pointer
+- *
+- * Associate the q_vector napi with all the queue[s] on the vector
+- */
+-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector)
+-{
+- struct ice_rx_ring *rx_ring;
+- struct ice_tx_ring *tx_ring;
+-
+- ice_for_each_rx_ring(rx_ring, q_vector->rx)
+- ice_queue_set_napi(q_vector->vsi, rx_ring->q_index,
+- NETDEV_QUEUE_TYPE_RX, &q_vector->napi);
++ ice_for_each_q_vector(vsi, v_idx) {
++ struct ice_q_vector *q_vector = vsi->q_vectors[v_idx];
+
+- ice_for_each_tx_ring(tx_ring, q_vector->tx)
+- ice_queue_set_napi(q_vector->vsi, tx_ring->q_index,
+- NETDEV_QUEUE_TYPE_TX, &q_vector->napi);
+- /* Also set the interrupt number for the NAPI */
+- netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
++ netif_napi_set_irq(&q_vector->napi, q_vector->irq.virq);
++ }
+ }
+
+ /**
+- * ice_vsi_set_napi_queues
++ * ice_vsi_clear_napi_queues - dissociate netdev queues from napi
+ * @vsi: VSI pointer
+ *
+- * Associate queue[s] with napi for all vectors
++ * Clear the association between all VSI queues queue[s] and napi.
++ * The caller must hold rtnl_lock.
+ */
+-void ice_vsi_set_napi_queues(struct ice_vsi *vsi)
++void ice_vsi_clear_napi_queues(struct ice_vsi *vsi)
+ {
+- int i;
++ struct net_device *netdev = vsi->netdev;
++ int q_idx;
+
+- if (!vsi->netdev)
++ if (!netdev)
+ return;
+
+- ice_for_each_q_vector(vsi, i)
+- ice_q_vector_set_napi_queues(vsi->q_vectors[i]);
++ ice_for_each_txq(vsi, q_idx)
++ netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_TX, NULL);
++
++ ice_for_each_rxq(vsi, q_idx)
++ netif_queue_set_napi(netdev, q_idx, NETDEV_QUEUE_TYPE_RX, NULL);
+ }
+
+ /**
+@@ -3039,19 +2975,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
+ if (WARN_ON(vsi->type == ICE_VSI_VF && !vsi->vf))
+ return -EINVAL;
+
++ mutex_lock(&vsi->xdp_state_lock);
++
+ ret = ice_vsi_realloc_stat_arrays(vsi);
+ if (ret)
+- goto err_vsi_cfg;
++ goto unlock;
+
+ ice_vsi_decfg(vsi);
+ ret = ice_vsi_cfg_def(vsi);
+ if (ret)
+- goto err_vsi_cfg;
++ goto unlock;
+
+ coalesce = kcalloc(vsi->num_q_vectors,
+ sizeof(struct ice_coalesce_stored), GFP_KERNEL);
+- if (!coalesce)
+- return -ENOMEM;
++ if (!coalesce) {
++ ret = -ENOMEM;
++ goto decfg;
++ }
+
+ prev_num_q_vectors = ice_vsi_rebuild_get_coalesce(vsi, coalesce);
+
+@@ -3059,22 +2999,23 @@ int ice_vsi_rebuild(struct ice_vsi *vsi, u32 vsi_flags)
+ if (ret) {
+ if (vsi_flags & ICE_VSI_FLAG_INIT) {
+ ret = -EIO;
+- goto err_vsi_cfg_tc_lan;
++ goto free_coalesce;
+ }
+
+- kfree(coalesce);
+- return ice_schedule_reset(pf, ICE_RESET_PFR);
++ ret = ice_schedule_reset(pf, ICE_RESET_PFR);
++ goto free_coalesce;
+ }
+
+ ice_vsi_rebuild_set_coalesce(vsi, coalesce, prev_num_q_vectors);
+- kfree(coalesce);
+-
+- return 0;
++ clear_bit(ICE_VSI_REBUILD_PENDING, vsi->state);
+
+-err_vsi_cfg_tc_lan:
+- ice_vsi_decfg(vsi);
++free_coalesce:
+ kfree(coalesce);
+-err_vsi_cfg:
++decfg:
++ if (ret)
++ ice_vsi_decfg(vsi);
++unlock:
++ mutex_unlock(&vsi->xdp_state_lock);
+ return ret;
+ }
+
+diff --git a/drivers/net/ethernet/intel/ice/ice_lib.h b/drivers/net/ethernet/intel/ice/ice_lib.h
+index 94ce8964dda66..36d86535695dd 100644
+--- a/drivers/net/ethernet/intel/ice/ice_lib.h
++++ b/drivers/net/ethernet/intel/ice/ice_lib.h
+@@ -44,16 +44,10 @@ void ice_vsi_cfg_netdev_tc(struct ice_vsi *vsi, u8 ena_tc);
+ struct ice_vsi *
+ ice_vsi_setup(struct ice_pf *pf, struct ice_vsi_cfg_params *params);
+
+-void
+-ice_queue_set_napi(struct ice_vsi *vsi, unsigned int queue_index,
+- enum netdev_queue_type type, struct napi_struct *napi);
+-
+-void __ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector, bool locked);
+-
+-void ice_q_vector_set_napi_queues(struct ice_q_vector *q_vector);
+-
+ void ice_vsi_set_napi_queues(struct ice_vsi *vsi);
+
++void ice_vsi_clear_napi_queues(struct ice_vsi *vsi);
++
+ int ice_vsi_release(struct ice_vsi *vsi);
+
+ void ice_vsi_close(struct ice_vsi *vsi);
+diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
+index f16d13e9ff6e3..766f9a466bc35 100644
+--- a/drivers/net/ethernet/intel/ice/ice_main.c
++++ b/drivers/net/ethernet/intel/ice/ice_main.c
+@@ -609,11 +609,15 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
+ memset(&vsi->mqprio_qopt, 0, sizeof(vsi->mqprio_qopt));
+ }
+ }
++
++ if (vsi->netdev)
++ netif_device_detach(vsi->netdev);
+ skip:
+
+ /* clear SW filtering DB */
+ ice_clear_hw_tbls(hw);
+ /* disable the VSIs and their queues that are not already DOWN */
++ set_bit(ICE_VSI_REBUILD_PENDING, ice_get_main_vsi(pf)->state);
+ ice_pf_dis_all_vsi(pf, false);
+
+ if (test_bit(ICE_FLAG_PTP_SUPPORTED, pf->flags))
+@@ -3002,8 +3006,8 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
+ struct netlink_ext_ack *extack)
+ {
+ unsigned int frame_size = vsi->netdev->mtu + ICE_ETH_PKT_HDR_PAD;
+- bool if_running = netif_running(vsi->netdev);
+ int ret = 0, xdp_ring_err = 0;
++ bool if_running;
+
+ if (prog && !prog->aux->xdp_has_frags) {
+ if (frame_size > ice_max_xdp_frame_size(vsi)) {
+@@ -3014,13 +3018,17 @@ ice_xdp_setup_prog(struct ice_vsi *vsi, struct bpf_prog *prog,
+ }
+
+ /* hot swap progs and avoid toggling link */
+- if (ice_is_xdp_ena_vsi(vsi) == !!prog) {
++ if (ice_is_xdp_ena_vsi(vsi) == !!prog ||
++ test_bit(ICE_VSI_REBUILD_PENDING, vsi->state)) {
+ ice_vsi_assign_bpf_prog(vsi, prog);
+ return 0;
+ }
+
++ if_running = netif_running(vsi->netdev) &&
++ !test_and_set_bit(ICE_VSI_DOWN, vsi->state);
++
+ /* need to stop netdev while setting up the program for Rx rings */
+- if (if_running && !test_and_set_bit(ICE_VSI_DOWN, vsi->state)) {
++ if (if_running) {
+ ret = ice_down(vsi);
+ if (ret) {
+ NL_SET_ERR_MSG_MOD(extack, "Preparing device for XDP attach failed");
+@@ -3086,21 +3094,28 @@ static int ice_xdp(struct net_device *dev, struct netdev_bpf *xdp)
+ {
+ struct ice_netdev_priv *np = netdev_priv(dev);
+ struct ice_vsi *vsi = np->vsi;
++ int ret;
+
+ if (vsi->type != ICE_VSI_PF) {
+ NL_SET_ERR_MSG_MOD(xdp->extack, "XDP can be loaded only on PF VSI");
+ return -EINVAL;
+ }
+
++ mutex_lock(&vsi->xdp_state_lock);
++
+ switch (xdp->command) {
+ case XDP_SETUP_PROG:
+- return ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
++ ret = ice_xdp_setup_prog(vsi, xdp->prog, xdp->extack);
++ break;
+ case XDP_SETUP_XSK_POOL:
+- return ice_xsk_pool_setup(vsi, xdp->xsk.pool,
+- xdp->xsk.queue_id);
++ ret = ice_xsk_pool_setup(vsi, xdp->xsk.pool, xdp->xsk.queue_id);
++ break;
+ default:
+- return -EINVAL;
++ ret = -EINVAL;
+ }
++
++ mutex_unlock(&vsi->xdp_state_lock);
++ return ret;
+ }
+
+ /**
+@@ -3556,11 +3571,9 @@ static void ice_napi_add(struct ice_vsi *vsi)
+ if (!vsi->netdev)
+ return;
+
+- ice_for_each_q_vector(vsi, v_idx) {
++ ice_for_each_q_vector(vsi, v_idx)
+ netif_napi_add(vsi->netdev, &vsi->q_vectors[v_idx]->napi,
+ ice_napi_poll);
+- __ice_q_vector_set_napi_queues(vsi->q_vectors[v_idx], false);
+- }
+ }
+
+ /**
+@@ -4160,13 +4173,17 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
+
+ /* set for the next time the netdev is started */
+ if (!netif_running(vsi->netdev)) {
+- ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
++ err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
++ if (err)
++ goto rebuild_err;
+ dev_dbg(ice_pf_to_dev(pf), "Link is down, queue count change happens when link is brought up\n");
+ goto done;
+ }
+
+ ice_vsi_close(vsi);
+- ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
++ err = ice_vsi_rebuild(vsi, ICE_VSI_FLAG_NO_INIT);
++ if (err)
++ goto rebuild_err;
+
+ ice_for_each_traffic_class(i) {
+ if (vsi->tc_cfg.ena_tc & BIT(i))
+@@ -4177,6 +4194,11 @@ int ice_vsi_recfg_qs(struct ice_vsi *vsi, int new_rx, int new_tx, bool locked)
+ }
+ ice_pf_dcb_recfg(pf, locked);
+ ice_vsi_open(vsi);
++ goto done;
++
++rebuild_err:
++ dev_err(ice_pf_to_dev(pf), "Error during VSI rebuild: %d. Unload and reload the driver.\n",
++ err);
+ done:
+ clear_bit(ICE_CFG_BUSY, pf->state);
+ return err;
+@@ -5529,7 +5551,9 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
+ if (ret)
+ goto err_reinit;
+ ice_vsi_map_rings_to_vectors(pf->vsi[v]);
++ rtnl_lock();
+ ice_vsi_set_napi_queues(pf->vsi[v]);
++ rtnl_unlock();
+ }
+
+ ret = ice_req_irq_msix_misc(pf);
+@@ -5543,8 +5567,12 @@ static int ice_reinit_interrupt_scheme(struct ice_pf *pf)
+
+ err_reinit:
+ while (v--)
+- if (pf->vsi[v])
++ if (pf->vsi[v]) {
++ rtnl_lock();
++ ice_vsi_clear_napi_queues(pf->vsi[v]);
++ rtnl_unlock();
+ ice_vsi_free_q_vectors(pf->vsi[v]);
++ }
+
+ return ret;
+ }
+@@ -5609,6 +5637,9 @@ static int ice_suspend(struct device *dev)
+ ice_for_each_vsi(pf, v) {
+ if (!pf->vsi[v])
+ continue;
++ rtnl_lock();
++ ice_vsi_clear_napi_queues(pf->vsi[v]);
++ rtnl_unlock();
+ ice_vsi_free_q_vectors(pf->vsi[v]);
+ }
+ ice_clear_interrupt_scheme(pf);
+@@ -7444,6 +7475,8 @@ int ice_vsi_open(struct ice_vsi *vsi)
+ err = netif_set_real_num_rx_queues(vsi->netdev, vsi->num_rxq);
+ if (err)
+ goto err_set_qs;
++
++ ice_vsi_set_napi_queues(vsi);
+ }
+
+ err = ice_up_complete(vsi);
+@@ -7581,6 +7614,7 @@ static void ice_update_pf_netdev_link(struct ice_pf *pf)
+ */
+ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
+ {
++ struct ice_vsi *vsi = ice_get_main_vsi(pf);
+ struct device *dev = ice_pf_to_dev(pf);
+ struct ice_hw *hw = &pf->hw;
+ bool dvm;
+@@ -7725,6 +7759,9 @@ static void ice_rebuild(struct ice_pf *pf, enum ice_reset_req reset_type)
+ ice_rebuild_arfs(pf);
+ }
+
++ if (vsi && vsi->netdev)
++ netif_device_attach(vsi->netdev);
++
+ ice_update_pf_netdev_link(pf);
+
+ /* tell the firmware we are up */
+diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
+index 240a7bec242be..87a5427570d76 100644
+--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
++++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
+@@ -165,7 +165,6 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+ struct ice_q_vector *q_vector;
+ struct ice_tx_ring *tx_ring;
+ struct ice_rx_ring *rx_ring;
+- int timeout = 50;
+ int fail = 0;
+ int err;
+
+@@ -176,13 +175,6 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+ rx_ring = vsi->rx_rings[q_idx];
+ q_vector = rx_ring->q_vector;
+
+- while (test_and_set_bit(ICE_CFG_BUSY, vsi->state)) {
+- timeout--;
+- if (!timeout)
+- return -EBUSY;
+- usleep_range(1000, 2000);
+- }
+-
+ synchronize_net();
+ netif_carrier_off(vsi->netdev);
+ netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+@@ -261,7 +253,6 @@ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
+ netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+ netif_carrier_on(vsi->netdev);
+ }
+- clear_bit(ICE_CFG_BUSY, vsi->state);
+
+ return fail;
+ }
+@@ -390,7 +381,8 @@ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool, u16 qid)
+ goto failure;
+ }
+
+- if_running = netif_running(vsi->netdev) && ice_is_xdp_ena_vsi(vsi);
++ if_running = !test_bit(ICE_VSI_DOWN, vsi->state) &&
++ ice_is_xdp_ena_vsi(vsi);
+
+ if (if_running) {
+ struct ice_rx_ring *rx_ring = vsi->rx_rings[qid];
+diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
+index b6aa449aa56af..a27d0a4d3d9c4 100644
+--- a/drivers/net/ethernet/intel/igb/igb_main.c
++++ b/drivers/net/ethernet/intel/igb/igb_main.c
+@@ -6961,10 +6961,20 @@ static void igb_extts(struct igb_adapter *adapter, int tsintr_tt)
+
+ static void igb_tsync_interrupt(struct igb_adapter *adapter)
+ {
++ const u32 mask = (TSINTR_SYS_WRAP | E1000_TSICR_TXTS |
++ TSINTR_TT0 | TSINTR_TT1 |
++ TSINTR_AUTT0 | TSINTR_AUTT1);
+ struct e1000_hw *hw = &adapter->hw;
+ u32 tsicr = rd32(E1000_TSICR);
+ struct ptp_clock_event event;
+
++ if (hw->mac.type == e1000_82580) {
++ /* 82580 has a hardware bug that requires an explicit
++ * write to clear the TimeSync interrupt cause.
++ */
++ wr32(E1000_TSICR, tsicr & mask);
++ }
++
+ if (tsicr & TSINTR_SYS_WRAP) {
+ event.type = PTP_CLOCK_PPS;
+ if (adapter->ptp_caps.pps)
+diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
+index 3041f8142324f..773136925fd07 100644
+--- a/drivers/net/ethernet/intel/igc/igc_main.c
++++ b/drivers/net/ethernet/intel/igc/igc_main.c
+@@ -7417,6 +7417,7 @@ static void igc_io_resume(struct pci_dev *pdev)
+ rtnl_lock();
+ if (netif_running(netdev)) {
+ if (igc_open(netdev)) {
++ rtnl_unlock();
+ netdev_err(netdev, "igc_open failed after reset\n");
+ return;
+ }
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h
+index e85fb71bf0b46..3cebc3a435db5 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en.h
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h
+@@ -80,6 +80,7 @@ struct page_pool;
+ SKB_DATA_ALIGN(sizeof(struct skb_shared_info)))
+
+ #define MLX5E_RX_MAX_HEAD (256)
++#define MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE (8)
+ #define MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE (9)
+ #define MLX5E_SHAMPO_WQ_HEADER_PER_PAGE (PAGE_SIZE >> MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE)
+ #define MLX5E_SHAMPO_WQ_BASE_HEAD_ENTRY_SIZE (64)
+@@ -146,25 +147,6 @@ struct page_pool;
+ #define MLX5E_TX_XSK_POLL_BUDGET 64
+ #define MLX5E_SQ_RECOVER_MIN_INTERVAL 500 /* msecs */
+
+-#define MLX5E_KLM_UMR_WQE_SZ(sgl_len)\
+- (sizeof(struct mlx5e_umr_wqe) +\
+- (sizeof(struct mlx5_klm) * (sgl_len)))
+-
+-#define MLX5E_KLM_UMR_WQEBBS(klm_entries) \
+- (DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_BB))
+-
+-#define MLX5E_KLM_UMR_DS_CNT(klm_entries)\
+- (DIV_ROUND_UP(MLX5E_KLM_UMR_WQE_SZ(klm_entries), MLX5_SEND_WQE_DS))
+-
+-#define MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size)\
+- (((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_klm))
+-
+-#define MLX5E_KLM_ENTRIES_PER_WQE(wqe_size)\
+- ALIGN_DOWN(MLX5E_KLM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT)
+-
+-#define MLX5E_MAX_KLM_PER_WQE(mdev) \
+- MLX5E_KLM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev))
+-
+ #define mlx5e_state_dereference(priv, p) \
+ rcu_dereference_protected((p), lockdep_is_held(&(priv)->state_lock))
+
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+index ec819dfc98be2..6c9ccccca81e2 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en/params.c
+@@ -1071,18 +1071,18 @@ static u32 mlx5e_shampo_icosq_sz(struct mlx5_core_dev *mdev,
+ struct mlx5e_params *params,
+ struct mlx5e_rq_param *rq_param)
+ {
+- int max_num_of_umr_per_wqe, max_hd_per_wqe, max_klm_per_umr, rest;
++ int max_num_of_umr_per_wqe, max_hd_per_wqe, max_ksm_per_umr, rest;
+ void *wqc = MLX5_ADDR_OF(rqc, rq_param->rqc, wq);
+ int wq_size = BIT(MLX5_GET(wq, wqc, log_wq_sz));
+ u32 wqebbs;
+
+- max_klm_per_umr = MLX5E_MAX_KLM_PER_WQE(mdev);
++ max_ksm_per_umr = MLX5E_MAX_KSM_PER_WQE(mdev);
+ max_hd_per_wqe = mlx5e_shampo_hd_per_wqe(mdev, params, rq_param);
+- max_num_of_umr_per_wqe = max_hd_per_wqe / max_klm_per_umr;
+- rest = max_hd_per_wqe % max_klm_per_umr;
+- wqebbs = MLX5E_KLM_UMR_WQEBBS(max_klm_per_umr) * max_num_of_umr_per_wqe;
++ max_num_of_umr_per_wqe = max_hd_per_wqe / max_ksm_per_umr;
++ rest = max_hd_per_wqe % max_ksm_per_umr;
++ wqebbs = MLX5E_KSM_UMR_WQEBBS(max_ksm_per_umr) * max_num_of_umr_per_wqe;
+ if (rest)
+- wqebbs += MLX5E_KLM_UMR_WQEBBS(rest);
++ wqebbs += MLX5E_KSM_UMR_WQEBBS(rest);
+ wqebbs *= wq_size;
+ return wqebbs;
+ }
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+index 879d698b61193..d1f0f868d494e 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en/txrx.h
+@@ -34,6 +34,25 @@
+
+ #define MLX5E_RX_ERR_CQE(cqe) (get_cqe_opcode(cqe) != MLX5_CQE_RESP_SEND)
+
++#define MLX5E_KSM_UMR_WQE_SZ(sgl_len)\
++ (sizeof(struct mlx5e_umr_wqe) +\
++ (sizeof(struct mlx5_ksm) * (sgl_len)))
++
++#define MLX5E_KSM_UMR_WQEBBS(ksm_entries) \
++ (DIV_ROUND_UP(MLX5E_KSM_UMR_WQE_SZ(ksm_entries), MLX5_SEND_WQE_BB))
++
++#define MLX5E_KSM_UMR_DS_CNT(ksm_entries)\
++ (DIV_ROUND_UP(MLX5E_KSM_UMR_WQE_SZ(ksm_entries), MLX5_SEND_WQE_DS))
++
++#define MLX5E_KSM_MAX_ENTRIES_PER_WQE(wqe_size)\
++ (((wqe_size) - sizeof(struct mlx5e_umr_wqe)) / sizeof(struct mlx5_ksm))
++
++#define MLX5E_KSM_ENTRIES_PER_WQE(wqe_size)\
++ ALIGN_DOWN(MLX5E_KSM_MAX_ENTRIES_PER_WQE(wqe_size), MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT)
++
++#define MLX5E_MAX_KSM_PER_WQE(mdev) \
++ MLX5E_KSM_ENTRIES_PER_WQE(MLX5_SEND_WQE_BB * mlx5e_get_max_sq_aligned_wqebbs(mdev))
++
+ static inline
+ ktime_t mlx5e_cqe_ts_to_ns(cqe_ts_to_ns func, struct mlx5_clock *clock, u64 cqe_ts)
+ {
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+index 409f525f1703c..632129de24ba1 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+@@ -504,8 +504,8 @@ static int mlx5e_create_umr_mkey(struct mlx5_core_dev *mdev,
+ return err;
+ }
+
+-static int mlx5e_create_umr_klm_mkey(struct mlx5_core_dev *mdev,
+- u64 nentries,
++static int mlx5e_create_umr_ksm_mkey(struct mlx5_core_dev *mdev,
++ u64 nentries, u8 log_entry_size,
+ u32 *umr_mkey)
+ {
+ int inlen;
+@@ -525,12 +525,13 @@ static int mlx5e_create_umr_klm_mkey(struct mlx5_core_dev *mdev,
+ MLX5_SET(mkc, mkc, umr_en, 1);
+ MLX5_SET(mkc, mkc, lw, 1);
+ MLX5_SET(mkc, mkc, lr, 1);
+- MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_KLMS);
++ MLX5_SET(mkc, mkc, access_mode_1_0, MLX5_MKC_ACCESS_MODE_KSM);
+ mlx5e_mkey_set_relaxed_ordering(mdev, mkc);
+ MLX5_SET(mkc, mkc, qpn, 0xffffff);
+ MLX5_SET(mkc, mkc, pd, mdev->mlx5e_res.hw_objs.pdn);
+ MLX5_SET(mkc, mkc, translations_octword_size, nentries);
+- MLX5_SET(mkc, mkc, length64, 1);
++ MLX5_SET(mkc, mkc, log_page_size, log_entry_size);
++ MLX5_SET64(mkc, mkc, len, nentries << log_entry_size);
+ err = mlx5_core_create_mkey(mdev, umr_mkey, in, inlen);
+
+ kvfree(in);
+@@ -565,14 +566,16 @@ static int mlx5e_create_rq_umr_mkey(struct mlx5_core_dev *mdev, struct mlx5e_rq
+ static int mlx5e_create_rq_hd_umr_mkey(struct mlx5_core_dev *mdev,
+ struct mlx5e_rq *rq)
+ {
+- u32 max_klm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size));
++ u32 max_ksm_size = BIT(MLX5_CAP_GEN(mdev, log_max_klm_list_size));
+
+- if (max_klm_size < rq->mpwqe.shampo->hd_per_wq) {
+- mlx5_core_err(mdev, "max klm list size 0x%x is smaller than shampo header buffer list size 0x%x\n",
+- max_klm_size, rq->mpwqe.shampo->hd_per_wq);
++ if (max_ksm_size < rq->mpwqe.shampo->hd_per_wq) {
++ mlx5_core_err(mdev, "max ksm list size 0x%x is smaller than shampo header buffer list size 0x%x\n",
++ max_ksm_size, rq->mpwqe.shampo->hd_per_wq);
+ return -EINVAL;
+ }
+- return mlx5e_create_umr_klm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq,
++
++ return mlx5e_create_umr_ksm_mkey(mdev, rq->mpwqe.shampo->hd_per_wq,
++ MLX5E_SHAMPO_LOG_HEADER_ENTRY_SIZE,
+ &rq->mpwqe.shampo->mkey);
+ }
+
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+index 0138f77eaeed0..cbc45dc34a60f 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+@@ -619,25 +619,25 @@ static int bitmap_find_window(unsigned long *bitmap, int len,
+ return min(len, count);
+ }
+
+-static void build_klm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe,
+- __be32 key, u16 offset, u16 klm_len, u16 wqe_bbs)
++static void build_ksm_umr(struct mlx5e_icosq *sq, struct mlx5e_umr_wqe *umr_wqe,
++ __be32 key, u16 offset, u16 ksm_len)
+ {
+- memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_klms));
++ memset(umr_wqe, 0, offsetof(struct mlx5e_umr_wqe, inline_ksms));
+ umr_wqe->ctrl.opmod_idx_opcode =
+ cpu_to_be32((sq->pc << MLX5_WQE_CTRL_WQE_INDEX_SHIFT) |
+ MLX5_OPCODE_UMR);
+ umr_wqe->ctrl.umr_mkey = key;
+ umr_wqe->ctrl.qpn_ds = cpu_to_be32((sq->sqn << MLX5_WQE_CTRL_QPN_SHIFT)
+- | MLX5E_KLM_UMR_DS_CNT(klm_len));
++ | MLX5E_KSM_UMR_DS_CNT(ksm_len));
+ umr_wqe->uctrl.flags = MLX5_UMR_TRANSLATION_OFFSET_EN | MLX5_UMR_INLINE;
+ umr_wqe->uctrl.xlt_offset = cpu_to_be16(offset);
+- umr_wqe->uctrl.xlt_octowords = cpu_to_be16(klm_len);
++ umr_wqe->uctrl.xlt_octowords = cpu_to_be16(ksm_len);
+ umr_wqe->uctrl.mkey_mask = cpu_to_be64(MLX5_MKEY_MASK_FREE);
+ }
+
+ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
+ struct mlx5e_icosq *sq,
+- u16 klm_entries, u16 index)
++ u16 ksm_entries, u16 index)
+ {
+ struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+ u16 entries, pi, header_offset, err, wqe_bbs, new_entries;
+@@ -650,20 +650,20 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
+ int headroom, i;
+
+ headroom = rq->buff.headroom;
+- new_entries = klm_entries - (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1));
+- entries = ALIGN(klm_entries, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT);
+- wqe_bbs = MLX5E_KLM_UMR_WQEBBS(entries);
++ new_entries = ksm_entries - (shampo->pi & (MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT - 1));
++ entries = ALIGN(ksm_entries, MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT);
++ wqe_bbs = MLX5E_KSM_UMR_WQEBBS(entries);
+ pi = mlx5e_icosq_get_next_pi(sq, wqe_bbs);
+ umr_wqe = mlx5_wq_cyc_get_wqe(&sq->wq, pi);
+- build_klm_umr(sq, umr_wqe, shampo->key, index, entries, wqe_bbs);
++ build_ksm_umr(sq, umr_wqe, shampo->key, index, entries);
+
+ frag_page = &shampo->pages[page_index];
+
+ for (i = 0; i < entries; i++, index++) {
+ dma_info = &shampo->info[index];
+- if (i >= klm_entries || (index < shampo->pi && shampo->pi - index <
+- MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT))
+- goto update_klm;
++ if (i >= ksm_entries || (index < shampo->pi && shampo->pi - index <
++ MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT))
++ goto update_ksm;
+ header_offset = (index & (MLX5E_SHAMPO_WQ_HEADER_PER_PAGE - 1)) <<
+ MLX5E_SHAMPO_LOG_MAX_HEADER_ENTRY_SIZE;
+ if (!(header_offset & (PAGE_SIZE - 1))) {
+@@ -683,12 +683,11 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
+ dma_info->frag_page = frag_page;
+ }
+
+-update_klm:
+- umr_wqe->inline_klms[i].bcount =
+- cpu_to_be32(MLX5E_RX_MAX_HEAD);
+- umr_wqe->inline_klms[i].key = cpu_to_be32(lkey);
+- umr_wqe->inline_klms[i].va =
+- cpu_to_be64(dma_info->addr + headroom);
++update_ksm:
++ umr_wqe->inline_ksms[i] = (struct mlx5_ksm) {
++ .key = cpu_to_be32(lkey),
++ .va = cpu_to_be64(dma_info->addr + headroom),
++ };
+ }
+
+ sq->db.wqe_info[pi] = (struct mlx5e_icosq_wqe_info) {
+@@ -720,37 +719,38 @@ static int mlx5e_build_shampo_hd_umr(struct mlx5e_rq *rq,
+ static int mlx5e_alloc_rx_hd_mpwqe(struct mlx5e_rq *rq)
+ {
+ struct mlx5e_shampo_hd *shampo = rq->mpwqe.shampo;
+- u16 klm_entries, num_wqe, index, entries_before;
++ u16 ksm_entries, num_wqe, index, entries_before;
+ struct mlx5e_icosq *sq = rq->icosq;
+- int i, err, max_klm_entries, len;
++ int i, err, max_ksm_entries, len;
+
+- max_klm_entries = MLX5E_MAX_KLM_PER_WQE(rq->mdev);
+- klm_entries = bitmap_find_window(shampo->bitmap,
++ max_ksm_entries = MLX5E_MAX_KSM_PER_WQE(rq->mdev);
++ ksm_entries = bitmap_find_window(shampo->bitmap,
+ shampo->hd_per_wqe,
+ shampo->hd_per_wq, shampo->pi);
+- if (!klm_entries)
++ ksm_entries = ALIGN_DOWN(ksm_entries, MLX5E_SHAMPO_WQ_HEADER_PER_PAGE);
++ if (!ksm_entries)
+ return 0;
+
+- klm_entries += (shampo->pi & (MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT - 1));
+- index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT);
++ ksm_entries += (shampo->pi & (MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT - 1));
++ index = ALIGN_DOWN(shampo->pi, MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT);
+ entries_before = shampo->hd_per_wq - index;
+
+- if (unlikely(entries_before < klm_entries))
+- num_wqe = DIV_ROUND_UP(entries_before, max_klm_entries) +
+- DIV_ROUND_UP(klm_entries - entries_before, max_klm_entries);
++ if (unlikely(entries_before < ksm_entries))
++ num_wqe = DIV_ROUND_UP(entries_before, max_ksm_entries) +
++ DIV_ROUND_UP(ksm_entries - entries_before, max_ksm_entries);
+ else
+- num_wqe = DIV_ROUND_UP(klm_entries, max_klm_entries);
++ num_wqe = DIV_ROUND_UP(ksm_entries, max_ksm_entries);
+
+ for (i = 0; i < num_wqe; i++) {
+- len = (klm_entries > max_klm_entries) ? max_klm_entries :
+- klm_entries;
++ len = (ksm_entries > max_ksm_entries) ? max_ksm_entries :
++ ksm_entries;
+ if (unlikely(index + len > shampo->hd_per_wq))
+ len = shampo->hd_per_wq - index;
+ err = mlx5e_build_shampo_hd_umr(rq, sq, len, index);
+ if (unlikely(err))
+ return err;
+ index = (index + len) & (rq->mpwqe.shampo->hd_per_wq - 1);
+- klm_entries -= len;
++ ksm_entries -= len;
+ }
+
+ return 0;
+diff --git a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c
+index fe4e166de8a04..79276bc3d4951 100644
+--- a/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c
++++ b/drivers/net/ethernet/microchip/vcap/vcap_api_kunit.c
+@@ -1442,18 +1442,8 @@ static void vcap_api_encode_rule_test(struct kunit *test)
+ vcap_enable_lookups(&test_vctrl, &test_netdev, 0, 0,
+ rule->cookie, false);
+
+- vcap_free_rule(rule);
+-
+- /* Check that the rule has been freed: tricky to access since this
+- * memory should not be accessible anymore
+- */
+- KUNIT_EXPECT_PTR_NE(test, NULL, rule);
+- ret = list_empty(&rule->keyfields);
+- KUNIT_EXPECT_EQ(test, true, ret);
+- ret = list_empty(&rule->actionfields);
+- KUNIT_EXPECT_EQ(test, true, ret);
+-
+- vcap_del_rule(&test_vctrl, &test_netdev, id);
++ ret = vcap_del_rule(&test_vctrl, &test_netdev, id);
++ KUNIT_EXPECT_EQ(test, 0, ret);
+ }
+
+ static void vcap_api_set_rule_counter_test(struct kunit *test)
+diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
+index 482b9cd369508..bb77327bfa815 100644
+--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
+@@ -1857,10 +1857,12 @@ static void mana_destroy_txq(struct mana_port_context *apc)
+
+ for (i = 0; i < apc->num_queues; i++) {
+ napi = &apc->tx_qp[i].tx_cq.napi;
+- napi_synchronize(napi);
+- napi_disable(napi);
+- netif_napi_del(napi);
+-
++ if (apc->tx_qp[i].txq.napi_initialized) {
++ napi_synchronize(napi);
++ napi_disable(napi);
++ netif_napi_del(napi);
++ apc->tx_qp[i].txq.napi_initialized = false;
++ }
+ mana_destroy_wq_obj(apc, GDMA_SQ, apc->tx_qp[i].tx_object);
+
+ mana_deinit_cq(apc, &apc->tx_qp[i].tx_cq);
+@@ -1916,6 +1918,7 @@ static int mana_create_txq(struct mana_port_context *apc,
+ txq->ndev = net;
+ txq->net_txq = netdev_get_tx_queue(net, i);
+ txq->vp_offset = apc->tx_vp_offset;
++ txq->napi_initialized = false;
+ skb_queue_head_init(&txq->pending_skbs);
+
+ memset(&spec, 0, sizeof(spec));
+@@ -1982,6 +1985,7 @@ static int mana_create_txq(struct mana_port_context *apc,
+
+ netif_napi_add_tx(net, &cq->napi, mana_poll);
+ napi_enable(&cq->napi);
++ txq->napi_initialized = true;
+
+ mana_gd_ring_cq(cq->gdma_cq, SET_ARM_BIT);
+ }
+@@ -1993,7 +1997,7 @@ static int mana_create_txq(struct mana_port_context *apc,
+ }
+
+ static void mana_destroy_rxq(struct mana_port_context *apc,
+- struct mana_rxq *rxq, bool validate_state)
++ struct mana_rxq *rxq, bool napi_initialized)
+
+ {
+ struct gdma_context *gc = apc->ac->gdma_dev->gdma_context;
+@@ -2008,15 +2012,15 @@ static void mana_destroy_rxq(struct mana_port_context *apc,
+
+ napi = &rxq->rx_cq.napi;
+
+- if (validate_state)
++ if (napi_initialized) {
+ napi_synchronize(napi);
+
+- napi_disable(napi);
++ napi_disable(napi);
+
++ netif_napi_del(napi);
++ }
+ xdp_rxq_info_unreg(&rxq->xdp_rxq);
+
+- netif_napi_del(napi);
+-
+ mana_destroy_wq_obj(apc, GDMA_RQ, rxq->rxobj);
+
+ mana_deinit_cq(apc, &rxq->rx_cq);
+diff --git a/drivers/net/ethernet/ti/am65-cpsw-nuss.c b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+index 4e50b37928885..330eea349caae 100644
+--- a/drivers/net/ethernet/ti/am65-cpsw-nuss.c
++++ b/drivers/net/ethernet/ti/am65-cpsw-nuss.c
+@@ -156,12 +156,13 @@
+ #define AM65_CPSW_CPPI_TX_PKT_TYPE 0x7
+
+ /* XDP */
+-#define AM65_CPSW_XDP_CONSUMED 2
+-#define AM65_CPSW_XDP_REDIRECT 1
++#define AM65_CPSW_XDP_CONSUMED BIT(1)
++#define AM65_CPSW_XDP_REDIRECT BIT(0)
+ #define AM65_CPSW_XDP_PASS 0
+
+ /* Include headroom compatible with both skb and xdpf */
+-#define AM65_CPSW_HEADROOM (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN)
++#define AM65_CPSW_HEADROOM_NA (max(NET_SKB_PAD, XDP_PACKET_HEADROOM) + NET_IP_ALIGN)
++#define AM65_CPSW_HEADROOM ALIGN(AM65_CPSW_HEADROOM_NA, sizeof(long))
+
+ static void am65_cpsw_port_set_sl_mac(struct am65_cpsw_port *slave,
+ const u8 *dev_addr)
+@@ -933,7 +934,7 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
+ host_desc = k3_cppi_desc_pool_alloc(tx_chn->desc_pool);
+ if (unlikely(!host_desc)) {
+ ndev->stats.tx_dropped++;
+- return -ENOMEM;
++ return AM65_CPSW_XDP_CONSUMED; /* drop */
+ }
+
+ am65_cpsw_nuss_set_buf_type(tx_chn, host_desc, buf_type);
+@@ -942,7 +943,7 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
+ pkt_len, DMA_TO_DEVICE);
+ if (unlikely(dma_mapping_error(tx_chn->dma_dev, dma_buf))) {
+ ndev->stats.tx_dropped++;
+- ret = -ENOMEM;
++ ret = AM65_CPSW_XDP_CONSUMED; /* drop */
+ goto pool_free;
+ }
+
+@@ -977,6 +978,7 @@ static int am65_cpsw_xdp_tx_frame(struct net_device *ndev,
+ /* Inform BQL */
+ netdev_tx_completed_queue(netif_txq, 1, pkt_len);
+ ndev->stats.tx_errors++;
++ ret = AM65_CPSW_XDP_CONSUMED; /* drop */
+ goto dma_unmap;
+ }
+
+@@ -996,7 +998,9 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
+ int desc_idx, int cpu, int *len)
+ {
+ struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
++ struct am65_cpsw_ndev_priv *ndev_priv;
+ struct net_device *ndev = port->ndev;
++ struct am65_cpsw_ndev_stats *stats;
+ int ret = AM65_CPSW_XDP_CONSUMED;
+ struct am65_cpsw_tx_chn *tx_chn;
+ struct netdev_queue *netif_txq;
+@@ -1004,6 +1008,7 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
+ struct bpf_prog *prog;
+ struct page *page;
+ u32 act;
++ int err;
+
+ prog = READ_ONCE(port->xdp_prog);
+ if (!prog)
+@@ -1013,6 +1018,9 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
+ /* XDP prog might have changed packet data and boundaries */
+ *len = xdp->data_end - xdp->data;
+
++ ndev_priv = netdev_priv(ndev);
++ stats = this_cpu_ptr(ndev_priv->stats);
++
+ switch (act) {
+ case XDP_PASS:
+ ret = AM65_CPSW_XDP_PASS;
+@@ -1023,31 +1031,36 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
+
+ xdpf = xdp_convert_buff_to_frame(xdp);
+ if (unlikely(!xdpf))
+- break;
++ goto drop;
+
+ __netif_tx_lock(netif_txq, cpu);
+- ret = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf,
++ err = am65_cpsw_xdp_tx_frame(ndev, tx_chn, xdpf,
+ AM65_CPSW_TX_BUF_TYPE_XDP_TX);
+ __netif_tx_unlock(netif_txq);
+- if (ret)
+- break;
++ if (err)
++ goto drop;
+
+- ndev->stats.rx_bytes += *len;
+- ndev->stats.rx_packets++;
++ u64_stats_update_begin(&stats->syncp);
++ stats->rx_bytes += *len;
++ stats->rx_packets++;
++ u64_stats_update_end(&stats->syncp);
+ ret = AM65_CPSW_XDP_CONSUMED;
+ goto out;
+ case XDP_REDIRECT:
+ if (unlikely(xdp_do_redirect(ndev, xdp, prog)))
+- break;
++ goto drop;
+
+- ndev->stats.rx_bytes += *len;
+- ndev->stats.rx_packets++;
++ u64_stats_update_begin(&stats->syncp);
++ stats->rx_bytes += *len;
++ stats->rx_packets++;
++ u64_stats_update_end(&stats->syncp);
+ ret = AM65_CPSW_XDP_REDIRECT;
+ goto out;
+ default:
+ bpf_warn_invalid_xdp_action(ndev, prog, act);
+ fallthrough;
+ case XDP_ABORTED:
++drop:
+ trace_xdp_exception(ndev, prog, act);
+ fallthrough;
+ case XDP_DROP:
+@@ -1056,7 +1069,6 @@ static int am65_cpsw_run_xdp(struct am65_cpsw_common *common,
+
+ page = virt_to_head_page(xdp->data);
+ am65_cpsw_put_page(rx_chn, page, true, desc_idx);
+-
+ out:
+ return ret;
+ }
+@@ -1095,7 +1107,7 @@ static void am65_cpsw_nuss_rx_csum(struct sk_buff *skb, u32 csum_info)
+ }
+
+ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
+- u32 flow_idx, int cpu)
++ u32 flow_idx, int cpu, int *xdp_state)
+ {
+ struct am65_cpsw_rx_chn *rx_chn = &common->rx_chns;
+ u32 buf_dma_len, pkt_len, port_id = 0, csum_info;
+@@ -1114,6 +1126,7 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
+ void **swdata;
+ u32 *psdata;
+
++ *xdp_state = AM65_CPSW_XDP_PASS;
+ ret = k3_udma_glue_pop_rx_chn(rx_chn->rx_chn, flow_idx, &desc_dma);
+ if (ret) {
+ if (ret != -ENODATA)
+@@ -1161,15 +1174,13 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
+ }
+
+ if (port->xdp_prog) {
+- xdp_init_buff(&xdp, AM65_CPSW_MAX_PACKET_SIZE, &port->xdp_rxq);
+-
+- xdp_prepare_buff(&xdp, page_addr, skb_headroom(skb),
++ xdp_init_buff(&xdp, PAGE_SIZE, &port->xdp_rxq);
++ xdp_prepare_buff(&xdp, page_addr, AM65_CPSW_HEADROOM,
+ pkt_len, false);
+-
+- ret = am65_cpsw_run_xdp(common, port, &xdp, desc_idx,
+- cpu, &pkt_len);
+- if (ret != AM65_CPSW_XDP_PASS)
+- return ret;
++ *xdp_state = am65_cpsw_run_xdp(common, port, &xdp, desc_idx,
++ cpu, &pkt_len);
++ if (*xdp_state != AM65_CPSW_XDP_PASS)
++ goto allocate;
+
+ /* Compute additional headroom to be reserved */
+ headroom = (xdp.data - xdp.data_hard_start) - skb_headroom(skb);
+@@ -1193,9 +1204,13 @@ static int am65_cpsw_nuss_rx_packets(struct am65_cpsw_common *common,
+ stats->rx_bytes += pkt_len;
+ u64_stats_update_end(&stats->syncp);
+
++allocate:
+ new_page = page_pool_dev_alloc_pages(rx_chn->page_pool);
+- if (unlikely(!new_page))
++ if (unlikely(!new_page)) {
++ dev_err(dev, "page alloc failed\n");
+ return -ENOMEM;
++ }
++
+ rx_chn->pages[desc_idx] = new_page;
+
+ if (netif_dormant(ndev)) {
+@@ -1229,8 +1244,9 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
+ struct am65_cpsw_common *common = am65_cpsw_napi_to_common(napi_rx);
+ int flow = AM65_CPSW_MAX_RX_FLOWS;
+ int cpu = smp_processor_id();
+- bool xdp_redirect = false;
++ int xdp_state_or = 0;
+ int cur_budget, ret;
++ int xdp_state;
+ int num_rx = 0;
+
+ /* process every flow */
+@@ -1238,12 +1254,11 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
+ cur_budget = budget - num_rx;
+
+ while (cur_budget--) {
+- ret = am65_cpsw_nuss_rx_packets(common, flow, cpu);
+- if (ret) {
+- if (ret == AM65_CPSW_XDP_REDIRECT)
+- xdp_redirect = true;
++ ret = am65_cpsw_nuss_rx_packets(common, flow, cpu,
++ &xdp_state);
++ xdp_state_or |= xdp_state;
++ if (ret)
+ break;
+- }
+ num_rx++;
+ }
+
+@@ -1251,7 +1266,7 @@ static int am65_cpsw_nuss_rx_poll(struct napi_struct *napi_rx, int budget)
+ break;
+ }
+
+- if (xdp_redirect)
++ if (xdp_state_or & AM65_CPSW_XDP_REDIRECT)
+ xdp_do_flush();
+
+ dev_dbg(common->dev, "%s num_rx:%d %d\n", __func__, num_rx, budget);
+@@ -1918,12 +1933,13 @@ static int am65_cpsw_ndo_bpf(struct net_device *ndev, struct netdev_bpf *bpf)
+ static int am65_cpsw_ndo_xdp_xmit(struct net_device *ndev, int n,
+ struct xdp_frame **frames, u32 flags)
+ {
++ struct am65_cpsw_common *common = am65_ndev_to_common(ndev);
+ struct am65_cpsw_tx_chn *tx_chn;
+ struct netdev_queue *netif_txq;
+ int cpu = smp_processor_id();
+ int i, nxmit = 0;
+
+- tx_chn = &am65_ndev_to_common(ndev)->tx_chns[cpu % AM65_CPSW_MAX_TX_QUEUES];
++ tx_chn = &common->tx_chns[cpu % common->tx_ch_num];
+ netif_txq = netdev_get_tx_queue(ndev, tx_chn->id);
+
+ __netif_tx_lock(netif_txq, cpu);
+diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
+index 09c9f9787180b..1223fcc1a8dae 100644
+--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
++++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
+@@ -436,6 +436,8 @@ struct skbuf_dma_descriptor {
+ * @tx_bytes: TX byte count for statistics
+ * @tx_stat_sync: Synchronization object for TX stats
+ * @dma_err_task: Work structure to process Axi DMA errors
++ * @stopping: Set when @dma_err_task shouldn't do anything because we are
++ * about to stop the device.
+ * @tx_irq: Axidma TX IRQ number
+ * @rx_irq: Axidma RX IRQ number
+ * @eth_irq: Ethernet core IRQ number
+@@ -507,6 +509,7 @@ struct axienet_local {
+ struct u64_stats_sync tx_stat_sync;
+
+ struct work_struct dma_err_task;
++ bool stopping;
+
+ int tx_irq;
+ int rx_irq;
+diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+index 559c0d60d9483..88d7bc2ea7132 100644
+--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
++++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+@@ -1460,6 +1460,7 @@ static int axienet_init_legacy_dma(struct net_device *ndev)
+ struct axienet_local *lp = netdev_priv(ndev);
+
+ /* Enable worker thread for Axi DMA error handling */
++ lp->stopping = false;
+ INIT_WORK(&lp->dma_err_task, axienet_dma_err_handler);
+
+ napi_enable(&lp->napi_rx);
+@@ -1580,6 +1581,9 @@ static int axienet_stop(struct net_device *ndev)
+ dev_dbg(&ndev->dev, "axienet_close()\n");
+
+ if (!lp->use_dmaengine) {
++ WRITE_ONCE(lp->stopping, true);
++ flush_work(&lp->dma_err_task);
++
+ napi_disable(&lp->napi_tx);
+ napi_disable(&lp->napi_rx);
+ }
+@@ -2154,6 +2158,10 @@ static void axienet_dma_err_handler(struct work_struct *work)
+ dma_err_task);
+ struct net_device *ndev = lp->ndev;
+
++ /* Don't bother if we are going to stop anyway */
++ if (READ_ONCE(lp->stopping))
++ return;
++
+ napi_disable(&lp->napi_tx);
+ napi_disable(&lp->napi_rx);
+
+diff --git a/drivers/net/mctp/mctp-serial.c b/drivers/net/mctp/mctp-serial.c
+index 5bf6fdff701cd..346e6ad36054e 100644
+--- a/drivers/net/mctp/mctp-serial.c
++++ b/drivers/net/mctp/mctp-serial.c
+@@ -91,8 +91,8 @@ static int next_chunk_len(struct mctp_serial *dev)
+ * will be those non-escaped bytes, and does not include the escaped
+ * byte.
+ */
+- for (i = 1; i + dev->txpos + 1 < dev->txlen; i++) {
+- if (needs_escape(dev->txbuf[dev->txpos + i + 1]))
++ for (i = 1; i + dev->txpos < dev->txlen; i++) {
++ if (needs_escape(dev->txbuf[dev->txpos + i]))
+ break;
+ }
+
+diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c
+index 6c6ec94757092..2c0ee5cf8b6e0 100644
+--- a/drivers/net/phy/phy_device.c
++++ b/drivers/net/phy/phy_device.c
+@@ -3346,11 +3346,13 @@ static int of_phy_leds(struct phy_device *phydev)
+ err = of_phy_led(phydev, led);
+ if (err) {
+ of_node_put(led);
++ of_node_put(leds);
+ phy_leds_unregister(phydev);
+ return err;
+ }
+ }
+
++ of_node_put(leds);
+ return 0;
+ }
+
+diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c
+index 687d70cfc5563..6eeef10edadad 100644
+--- a/drivers/net/usb/ipheth.c
++++ b/drivers/net/usb/ipheth.c
+@@ -475,8 +475,8 @@ static int ipheth_close(struct net_device *net)
+ {
+ struct ipheth_device *dev = netdev_priv(net);
+
+- cancel_delayed_work_sync(&dev->carrier_work);
+ netif_stop_queue(net);
++ cancel_delayed_work_sync(&dev->carrier_work);
+ return 0;
+ }
+
+diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c
+index 19df1cd9f0724..51d5d4f0a8f9f 100644
+--- a/drivers/net/usb/r8152.c
++++ b/drivers/net/usb/r8152.c
+@@ -5177,14 +5177,23 @@ static void rtl8152_fw_mac_apply(struct r8152 *tp, struct fw_mac *mac)
+ data = (u8 *)mac;
+ data += __le16_to_cpu(mac->fw_offset);
+
+- generic_ocp_write(tp, __le16_to_cpu(mac->fw_reg), 0xff, length, data,
+- type);
++ if (generic_ocp_write(tp, __le16_to_cpu(mac->fw_reg), 0xff, length,
++ data, type) < 0) {
++ dev_err(&tp->intf->dev, "Write %s fw fail\n",
++ type ? "PLA" : "USB");
++ return;
++ }
+
+ ocp_write_word(tp, type, __le16_to_cpu(mac->bp_ba_addr),
+ __le16_to_cpu(mac->bp_ba_value));
+
+- generic_ocp_write(tp, __le16_to_cpu(mac->bp_start), BYTE_EN_DWORD,
+- __le16_to_cpu(mac->bp_num) << 1, mac->bp, type);
++ if (generic_ocp_write(tp, __le16_to_cpu(mac->bp_start), BYTE_EN_DWORD,
++ ALIGN(__le16_to_cpu(mac->bp_num) << 1, 4),
++ mac->bp, type) < 0) {
++ dev_err(&tp->intf->dev, "Write %s bp fail\n",
++ type ? "PLA" : "USB");
++ return;
++ }
+
+ bp_en_addr = __le16_to_cpu(mac->bp_en_addr);
+ if (bp_en_addr)
+diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c
+index 9fd516e8bb107..18eb5ba436df6 100644
+--- a/drivers/net/usb/usbnet.c
++++ b/drivers/net/usb/usbnet.c
+@@ -61,9 +61,6 @@
+
+ /*-------------------------------------------------------------------------*/
+
+-// randomly generated ethernet address
+-static u8 node_id [ETH_ALEN];
+-
+ /* use ethtool to change the level for any given device */
+ static int msg_level = -1;
+ module_param (msg_level, int, 0);
+@@ -1725,7 +1722,6 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
+
+ dev->net = net;
+ strscpy(net->name, "usb%d", sizeof(net->name));
+- eth_hw_addr_set(net, node_id);
+
+ /* rx and tx sides can use different message sizes;
+ * bind() should set rx_urb_size in that case.
+@@ -1801,9 +1797,9 @@ usbnet_probe (struct usb_interface *udev, const struct usb_device_id *prod)
+ goto out4;
+ }
+
+- /* let userspace know we have a random address */
+- if (ether_addr_equal(net->dev_addr, node_id))
+- net->addr_assign_type = NET_ADDR_RANDOM;
++ /* this flags the device for user space */
++ if (!is_valid_ether_addr(net->dev_addr))
++ eth_hw_addr_random(net);
+
+ if ((dev->driver_info->flags & FLAG_WLAN) != 0)
+ SET_NETDEV_DEVTYPE(net, &wlan_type);
+@@ -2211,7 +2207,6 @@ static int __init usbnet_init(void)
+ BUILD_BUG_ON(
+ sizeof_field(struct sk_buff, cb) < sizeof(struct skb_data));
+
+- eth_random_addr(node_id);
+ return 0;
+ }
+ module_init(usbnet_init);
+diff --git a/drivers/net/wireless/ath/ath11k/ahb.c b/drivers/net/wireless/ath/ath11k/ahb.c
+index ca0f17ddebbaa..0360ee5f0b65c 100644
+--- a/drivers/net/wireless/ath/ath11k/ahb.c
++++ b/drivers/net/wireless/ath/ath11k/ahb.c
+@@ -413,7 +413,7 @@ static int ath11k_ahb_power_up(struct ath11k_base *ab)
+ return ret;
+ }
+
+-static void ath11k_ahb_power_down(struct ath11k_base *ab, bool is_suspend)
++static void ath11k_ahb_power_down(struct ath11k_base *ab)
+ {
+ struct ath11k_ahb *ab_ahb = ath11k_ahb_priv(ab);
+
+@@ -1261,7 +1261,7 @@ static void ath11k_ahb_remove(struct platform_device *pdev)
+ struct ath11k_base *ab = platform_get_drvdata(pdev);
+
+ if (test_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags)) {
+- ath11k_ahb_power_down(ab, false);
++ ath11k_ahb_power_down(ab);
+ ath11k_debugfs_soc_destroy(ab);
+ ath11k_qmi_deinit_service(ab);
+ goto qmi_fail;
+diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
+index 47554c3619633..0edfea68afadf 100644
+--- a/drivers/net/wireless/ath/ath11k/core.c
++++ b/drivers/net/wireless/ath/ath11k/core.c
+@@ -906,6 +906,12 @@ int ath11k_core_suspend(struct ath11k_base *ab)
+ return ret;
+ }
+
++ ret = ath11k_wow_enable(ab);
++ if (ret) {
++ ath11k_warn(ab, "failed to enable wow during suspend: %d\n", ret);
++ return ret;
++ }
++
+ ret = ath11k_dp_rx_pktlog_stop(ab, false);
+ if (ret) {
+ ath11k_warn(ab, "failed to stop dp rx pktlog during suspend: %d\n",
+@@ -916,85 +922,29 @@ int ath11k_core_suspend(struct ath11k_base *ab)
+ ath11k_ce_stop_shadow_timers(ab);
+ ath11k_dp_stop_shadow_timers(ab);
+
+- /* PM framework skips suspend_late/resume_early callbacks
+- * if other devices report errors in their suspend callbacks.
+- * However ath11k_core_resume() would still be called because
+- * here we return success thus kernel put us on dpm_suspended_list.
+- * Since we won't go through a power down/up cycle, there is
+- * no chance to call complete(&ab->restart_completed) in
+- * ath11k_core_restart(), making ath11k_core_resume() timeout.
+- * So call it here to avoid this issue. This also works in case
+- * no error happens thus suspend_late/resume_early get called,
+- * because it will be reinitialized in ath11k_core_resume_early().
+- */
+- complete(&ab->restart_completed);
+-
+- return 0;
+-}
+-EXPORT_SYMBOL(ath11k_core_suspend);
+-
+-int ath11k_core_suspend_late(struct ath11k_base *ab)
+-{
+- struct ath11k_pdev *pdev;
+- struct ath11k *ar;
+-
+- if (!ab->hw_params.supports_suspend)
+- return -EOPNOTSUPP;
+-
+- /* so far single_pdev_only chips have supports_suspend as true
+- * and only the first pdev is valid.
+- */
+- pdev = ath11k_core_get_single_pdev(ab);
+- ar = pdev->ar;
+- if (!ar || ar->state != ATH11K_STATE_OFF)
+- return 0;
+-
+ ath11k_hif_irq_disable(ab);
+ ath11k_hif_ce_irq_disable(ab);
+
+- ath11k_hif_power_down(ab, true);
++ ret = ath11k_hif_suspend(ab);
++ if (ret) {
++ ath11k_warn(ab, "failed to suspend hif: %d\n", ret);
++ return ret;
++ }
+
+ return 0;
+ }
+-EXPORT_SYMBOL(ath11k_core_suspend_late);
+-
+-int ath11k_core_resume_early(struct ath11k_base *ab)
+-{
+- int ret;
+- struct ath11k_pdev *pdev;
+- struct ath11k *ar;
+-
+- if (!ab->hw_params.supports_suspend)
+- return -EOPNOTSUPP;
+-
+- /* so far single_pdev_only chips have supports_suspend as true
+- * and only the first pdev is valid.
+- */
+- pdev = ath11k_core_get_single_pdev(ab);
+- ar = pdev->ar;
+- if (!ar || ar->state != ATH11K_STATE_OFF)
+- return 0;
+-
+- reinit_completion(&ab->restart_completed);
+- ret = ath11k_hif_power_up(ab);
+- if (ret)
+- ath11k_warn(ab, "failed to power up hif during resume: %d\n", ret);
+-
+- return ret;
+-}
+-EXPORT_SYMBOL(ath11k_core_resume_early);
++EXPORT_SYMBOL(ath11k_core_suspend);
+
+ int ath11k_core_resume(struct ath11k_base *ab)
+ {
+ int ret;
+ struct ath11k_pdev *pdev;
+ struct ath11k *ar;
+- long time_left;
+
+ if (!ab->hw_params.supports_suspend)
+ return -EOPNOTSUPP;
+
+- /* so far single_pdev_only chips have supports_suspend as true
++ /* so far signle_pdev_only chips have supports_suspend as true
+ * and only the first pdev is valid.
+ */
+ pdev = ath11k_core_get_single_pdev(ab);
+@@ -1002,29 +952,29 @@ int ath11k_core_resume(struct ath11k_base *ab)
+ if (!ar || ar->state != ATH11K_STATE_OFF)
+ return 0;
+
+- time_left = wait_for_completion_timeout(&ab->restart_completed,
+- ATH11K_RESET_TIMEOUT_HZ);
+- if (time_left == 0) {
+- ath11k_warn(ab, "timeout while waiting for restart complete");
+- return -ETIMEDOUT;
++ ret = ath11k_hif_resume(ab);
++ if (ret) {
++ ath11k_warn(ab, "failed to resume hif during resume: %d\n", ret);
++ return ret;
+ }
+
+- if (ab->hw_params.current_cc_support &&
+- ar->alpha2[0] != 0 && ar->alpha2[1] != 0) {
+- ret = ath11k_reg_set_cc(ar);
+- if (ret) {
+- ath11k_warn(ab, "failed to set country code during resume: %d\n",
+- ret);
+- return ret;
+- }
+- }
++ ath11k_hif_ce_irq_enable(ab);
++ ath11k_hif_irq_enable(ab);
+
+ ret = ath11k_dp_rx_pktlog_start(ab);
+- if (ret)
++ if (ret) {
+ ath11k_warn(ab, "failed to start rx pktlog during resume: %d\n",
+ ret);
++ return ret;
++ }
+
+- return ret;
++ ret = ath11k_wow_wakeup(ab);
++ if (ret) {
++ ath11k_warn(ab, "failed to wakeup wow during resume: %d\n", ret);
++ return ret;
++ }
++
++ return 0;
+ }
+ EXPORT_SYMBOL(ath11k_core_resume);
+
+@@ -2119,8 +2069,6 @@ static void ath11k_core_restart(struct work_struct *work)
+
+ if (!ab->is_reset)
+ ath11k_core_post_reconfigure_recovery(ab);
+-
+- complete(&ab->restart_completed);
+ }
+
+ static void ath11k_core_reset(struct work_struct *work)
+@@ -2190,7 +2138,7 @@ static void ath11k_core_reset(struct work_struct *work)
+ ath11k_hif_irq_disable(ab);
+ ath11k_hif_ce_irq_disable(ab);
+
+- ath11k_hif_power_down(ab, false);
++ ath11k_hif_power_down(ab);
+ ath11k_hif_power_up(ab);
+
+ ath11k_dbg(ab, ATH11K_DBG_BOOT, "reset started\n");
+@@ -2263,7 +2211,7 @@ void ath11k_core_deinit(struct ath11k_base *ab)
+
+ mutex_unlock(&ab->core_lock);
+
+- ath11k_hif_power_down(ab, false);
++ ath11k_hif_power_down(ab);
+ ath11k_mac_destroy(ab);
+ ath11k_core_soc_destroy(ab);
+ ath11k_fw_destroy(ab);
+@@ -2316,7 +2264,6 @@ struct ath11k_base *ath11k_core_alloc(struct device *dev, size_t priv_size,
+ timer_setup(&ab->rx_replenish_retry, ath11k_ce_rx_replenish_retry, 0);
+ init_completion(&ab->htc_suspend);
+ init_completion(&ab->wow.wakeup_completed);
+- init_completion(&ab->restart_completed);
+
+ ab->dev = dev;
+ ab->hif.bus = bus;
+diff --git a/drivers/net/wireless/ath/ath11k/core.h b/drivers/net/wireless/ath/ath11k/core.h
+index 205f40ee6b666..141ba4487cb42 100644
+--- a/drivers/net/wireless/ath/ath11k/core.h
++++ b/drivers/net/wireless/ath/ath11k/core.h
+@@ -1033,8 +1033,6 @@ struct ath11k_base {
+ DECLARE_BITMAP(fw_features, ATH11K_FW_FEATURE_COUNT);
+ } fw;
+
+- struct completion restart_completed;
+-
+ #ifdef CONFIG_NL80211_TESTMODE
+ struct {
+ u32 data_pos;
+@@ -1234,10 +1232,8 @@ void ath11k_core_free_bdf(struct ath11k_base *ab, struct ath11k_board_data *bd);
+ int ath11k_core_check_dt(struct ath11k_base *ath11k);
+ int ath11k_core_check_smbios(struct ath11k_base *ab);
+ void ath11k_core_halt(struct ath11k *ar);
+-int ath11k_core_resume_early(struct ath11k_base *ab);
+ int ath11k_core_resume(struct ath11k_base *ab);
+ int ath11k_core_suspend(struct ath11k_base *ab);
+-int ath11k_core_suspend_late(struct ath11k_base *ab);
+ void ath11k_core_pre_reconfigure_recovery(struct ath11k_base *ab);
+ bool ath11k_core_coldboot_cal_support(struct ath11k_base *ab);
+
+diff --git a/drivers/net/wireless/ath/ath11k/hif.h b/drivers/net/wireless/ath/ath11k/hif.h
+index c4c6cc09c7c16..674ff772b181b 100644
+--- a/drivers/net/wireless/ath/ath11k/hif.h
++++ b/drivers/net/wireless/ath/ath11k/hif.h
+@@ -18,7 +18,7 @@ struct ath11k_hif_ops {
+ int (*start)(struct ath11k_base *ab);
+ void (*stop)(struct ath11k_base *ab);
+ int (*power_up)(struct ath11k_base *ab);
+- void (*power_down)(struct ath11k_base *ab, bool is_suspend);
++ void (*power_down)(struct ath11k_base *ab);
+ int (*suspend)(struct ath11k_base *ab);
+ int (*resume)(struct ath11k_base *ab);
+ int (*map_service_to_pipe)(struct ath11k_base *ab, u16 service_id,
+@@ -67,18 +67,12 @@ static inline void ath11k_hif_irq_disable(struct ath11k_base *ab)
+
+ static inline int ath11k_hif_power_up(struct ath11k_base *ab)
+ {
+- if (!ab->hif.ops->power_up)
+- return -EOPNOTSUPP;
+-
+ return ab->hif.ops->power_up(ab);
+ }
+
+-static inline void ath11k_hif_power_down(struct ath11k_base *ab, bool is_suspend)
++static inline void ath11k_hif_power_down(struct ath11k_base *ab)
+ {
+- if (!ab->hif.ops->power_down)
+- return;
+-
+- ab->hif.ops->power_down(ab, is_suspend);
++ ab->hif.ops->power_down(ab);
+ }
+
+ static inline int ath11k_hif_suspend(struct ath11k_base *ab)
+diff --git a/drivers/net/wireless/ath/ath11k/mhi.c b/drivers/net/wireless/ath/ath11k/mhi.c
+index ab182690aed32..6974a551883fc 100644
+--- a/drivers/net/wireless/ath/ath11k/mhi.c
++++ b/drivers/net/wireless/ath/ath11k/mhi.c
+@@ -453,17 +453,9 @@ int ath11k_mhi_start(struct ath11k_pci *ab_pci)
+ return 0;
+ }
+
+-void ath11k_mhi_stop(struct ath11k_pci *ab_pci, bool is_suspend)
++void ath11k_mhi_stop(struct ath11k_pci *ab_pci)
+ {
+- /* During suspend we need to use mhi_power_down_keep_dev()
+- * workaround, otherwise ath11k_core_resume() will timeout
+- * during resume.
+- */
+- if (is_suspend)
+- mhi_power_down_keep_dev(ab_pci->mhi_ctrl, true);
+- else
+- mhi_power_down(ab_pci->mhi_ctrl, true);
+-
++ mhi_power_down(ab_pci->mhi_ctrl, true);
+ mhi_unprepare_after_power_down(ab_pci->mhi_ctrl);
+ }
+
+diff --git a/drivers/net/wireless/ath/ath11k/mhi.h b/drivers/net/wireless/ath/ath11k/mhi.h
+index 2d567705e7323..a682aad52fc51 100644
+--- a/drivers/net/wireless/ath/ath11k/mhi.h
++++ b/drivers/net/wireless/ath/ath11k/mhi.h
+@@ -18,7 +18,7 @@
+ #define MHICTRL_RESET_MASK 0x2
+
+ int ath11k_mhi_start(struct ath11k_pci *ar_pci);
+-void ath11k_mhi_stop(struct ath11k_pci *ar_pci, bool is_suspend);
++void ath11k_mhi_stop(struct ath11k_pci *ar_pci);
+ int ath11k_mhi_register(struct ath11k_pci *ar_pci);
+ void ath11k_mhi_unregister(struct ath11k_pci *ar_pci);
+ void ath11k_mhi_set_mhictrl_reset(struct ath11k_base *ab);
+@@ -26,4 +26,5 @@ void ath11k_mhi_clear_vector(struct ath11k_base *ab);
+
+ int ath11k_mhi_suspend(struct ath11k_pci *ar_pci);
+ int ath11k_mhi_resume(struct ath11k_pci *ar_pci);
++
+ #endif
+diff --git a/drivers/net/wireless/ath/ath11k/pci.c b/drivers/net/wireless/ath/ath11k/pci.c
+index 8d63b84d12614..be9d2c69cc413 100644
+--- a/drivers/net/wireless/ath/ath11k/pci.c
++++ b/drivers/net/wireless/ath/ath11k/pci.c
+@@ -638,7 +638,7 @@ static int ath11k_pci_power_up(struct ath11k_base *ab)
+ return 0;
+ }
+
+-static void ath11k_pci_power_down(struct ath11k_base *ab, bool is_suspend)
++static void ath11k_pci_power_down(struct ath11k_base *ab)
+ {
+ struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
+
+@@ -649,7 +649,7 @@ static void ath11k_pci_power_down(struct ath11k_base *ab, bool is_suspend)
+
+ ath11k_pci_msi_disable(ab_pci);
+
+- ath11k_mhi_stop(ab_pci, is_suspend);
++ ath11k_mhi_stop(ab_pci);
+ clear_bit(ATH11K_FLAG_DEVICE_INIT_DONE, &ab->dev_flags);
+ ath11k_pci_sw_reset(ab_pci->ab, false);
+ }
+@@ -970,7 +970,7 @@ static void ath11k_pci_remove(struct pci_dev *pdev)
+ ath11k_pci_set_irq_affinity_hint(ab_pci, NULL);
+
+ if (test_bit(ATH11K_FLAG_QMI_FAIL, &ab->dev_flags)) {
+- ath11k_pci_power_down(ab, false);
++ ath11k_pci_power_down(ab);
+ ath11k_debugfs_soc_destroy(ab);
+ ath11k_qmi_deinit_service(ab);
+ goto qmi_fail;
+@@ -998,7 +998,7 @@ static void ath11k_pci_shutdown(struct pci_dev *pdev)
+ struct ath11k_pci *ab_pci = ath11k_pci_priv(ab);
+
+ ath11k_pci_set_irq_affinity_hint(ab_pci, NULL);
+- ath11k_pci_power_down(ab, false);
++ ath11k_pci_power_down(ab);
+ }
+
+ static __maybe_unused int ath11k_pci_pm_suspend(struct device *dev)
+@@ -1035,39 +1035,9 @@ static __maybe_unused int ath11k_pci_pm_resume(struct device *dev)
+ return ret;
+ }
+
+-static __maybe_unused int ath11k_pci_pm_suspend_late(struct device *dev)
+-{
+- struct ath11k_base *ab = dev_get_drvdata(dev);
+- int ret;
+-
+- ret = ath11k_core_suspend_late(ab);
+- if (ret)
+- ath11k_warn(ab, "failed to late suspend core: %d\n", ret);
+-
+- /* Similar to ath11k_pci_pm_suspend(), we return success here
+- * even error happens, to allow system suspend/hibernation survive.
+- */
+- return 0;
+-}
+-
+-static __maybe_unused int ath11k_pci_pm_resume_early(struct device *dev)
+-{
+- struct ath11k_base *ab = dev_get_drvdata(dev);
+- int ret;
+-
+- ret = ath11k_core_resume_early(ab);
+- if (ret)
+- ath11k_warn(ab, "failed to early resume core: %d\n", ret);
+-
+- return ret;
+-}
+-
+-static const struct dev_pm_ops __maybe_unused ath11k_pci_pm_ops = {
+- SET_SYSTEM_SLEEP_PM_OPS(ath11k_pci_pm_suspend,
+- ath11k_pci_pm_resume)
+- SET_LATE_SYSTEM_SLEEP_PM_OPS(ath11k_pci_pm_suspend_late,
+- ath11k_pci_pm_resume_early)
+-};
++static SIMPLE_DEV_PM_OPS(ath11k_pci_pm_ops,
++ ath11k_pci_pm_suspend,
++ ath11k_pci_pm_resume);
+
+ static struct pci_driver ath11k_pci_driver = {
+ .name = "ath11k_pci",
+diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
+index aa160e6fe24f1..e0d052f186b2f 100644
+--- a/drivers/net/wireless/ath/ath11k/qmi.c
++++ b/drivers/net/wireless/ath/ath11k/qmi.c
+@@ -2877,7 +2877,7 @@ int ath11k_qmi_fwreset_from_cold_boot(struct ath11k_base *ab)
+ }
+
+ /* reset the firmware */
+- ath11k_hif_power_down(ab, false);
++ ath11k_hif_power_down(ab);
+ ath11k_hif_power_up(ab);
+ ath11k_dbg(ab, ATH11K_DBG_QMI, "exit wait for cold boot done\n");
+ return 0;
+diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
+index 8474e25d2ac64..7037004ce9771 100644
+--- a/drivers/net/wireless/ath/ath12k/mac.c
++++ b/drivers/net/wireless/ath/ath12k/mac.c
+@@ -1881,7 +1881,9 @@ static void ath12k_peer_assoc_h_he(struct ath12k *ar,
+ {
+ const struct ieee80211_sta_he_cap *he_cap = &sta->deflink.he_cap;
+ int i;
+- u8 ampdu_factor, rx_mcs_80, rx_mcs_160, max_nss;
++ u8 ampdu_factor, max_nss;
++ u8 rx_mcs_80 = IEEE80211_HE_MCS_NOT_SUPPORTED;
++ u8 rx_mcs_160 = IEEE80211_HE_MCS_NOT_SUPPORTED;
+ u16 mcs_160_map, mcs_80_map;
+ bool support_160;
+ u16 v;
+@@ -3845,6 +3847,11 @@ static int ath12k_station_assoc(struct ath12k *ar,
+
+ ath12k_peer_assoc_prepare(ar, vif, sta, &peer_arg, reassoc);
+
++ if (peer_arg.peer_nss < 1) {
++ ath12k_warn(ar->ab,
++ "invalid peer NSS %d\n", peer_arg.peer_nss);
++ return -EINVAL;
++ }
+ ret = ath12k_wmi_send_peer_assoc_cmd(ar, &peer_arg);
+ if (ret) {
+ ath12k_warn(ar->ab, "failed to run peer assoc for STA %pM vdev %i: %d\n",
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+index 92860dc0a92eb..676604cb5a227 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/mac80211_if.c
+@@ -1090,6 +1090,7 @@ static int ieee_hw_init(struct ieee80211_hw *hw)
+ ieee80211_hw_set(hw, AMPDU_AGGREGATION);
+ ieee80211_hw_set(hw, SIGNAL_DBM);
+ ieee80211_hw_set(hw, REPORTS_TX_ACK_STATUS);
++ ieee80211_hw_set(hw, MFP_CAPABLE);
+
+ hw->extra_tx_headroom = brcms_c_get_header_len();
+ hw->queues = N_TX_QUEUES;
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+index ded094b6b63df..bc40242aaadd3 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+@@ -1442,7 +1442,8 @@ iwl_mvm_rcu_dereference_vif_id(struct iwl_mvm *mvm, u8 vif_id, bool rcu)
+ static inline struct ieee80211_bss_conf *
+ iwl_mvm_rcu_fw_link_id_to_link_conf(struct iwl_mvm *mvm, u8 link_id, bool rcu)
+ {
+- if (WARN_ON(link_id >= ARRAY_SIZE(mvm->link_id_to_link_conf)))
++ if (IWL_FW_CHECK(mvm, link_id >= ARRAY_SIZE(mvm->link_id_to_link_conf),
++ "erroneous FW link ID: %d\n", link_id))
+ return NULL;
+
+ if (rcu)
+diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h
+index 175882485a195..c5164ae41b547 100644
+--- a/drivers/net/wireless/marvell/mwifiex/main.h
++++ b/drivers/net/wireless/marvell/mwifiex/main.h
+@@ -1287,6 +1287,9 @@ mwifiex_get_priv_by_id(struct mwifiex_adapter *adapter,
+
+ for (i = 0; i < adapter->priv_num; i++) {
+ if (adapter->priv[i]) {
++ if (adapter->priv[i]->bss_mode == NL80211_IFTYPE_UNSPECIFIED)
++ continue;
++
+ if ((adapter->priv[i]->bss_num == bss_num) &&
+ (adapter->priv[i]->bss_type == bss_type))
+ break;
+diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
+index 0001a1ab6f38b..edc1507514f6d 100644
+--- a/drivers/net/wireless/realtek/rtw88/usb.c
++++ b/drivers/net/wireless/realtek/rtw88/usb.c
+@@ -744,7 +744,6 @@ static struct rtw_hci_ops rtw_usb_ops = {
+ static int rtw_usb_init_rx(struct rtw_dev *rtwdev)
+ {
+ struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
+- int i;
+
+ rtwusb->rxwq = create_singlethread_workqueue("rtw88_usb: rx wq");
+ if (!rtwusb->rxwq) {
+@@ -756,13 +755,19 @@ static int rtw_usb_init_rx(struct rtw_dev *rtwdev)
+
+ INIT_WORK(&rtwusb->rx_work, rtw_usb_rx_handler);
+
++ return 0;
++}
++
++static void rtw_usb_setup_rx(struct rtw_dev *rtwdev)
++{
++ struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev);
++ int i;
++
+ for (i = 0; i < RTW_USB_RXCB_NUM; i++) {
+ struct rx_usb_ctrl_block *rxcb = &rtwusb->rx_cb[i];
+
+ rtw_usb_rx_resubmit(rtwusb, rxcb);
+ }
+-
+- return 0;
+ }
+
+ static void rtw_usb_deinit_rx(struct rtw_dev *rtwdev)
+@@ -899,6 +904,8 @@ int rtw_usb_probe(struct usb_interface *intf, const struct usb_device_id *id)
+ goto err_destroy_rxwq;
+ }
+
++ rtw_usb_setup_rx(rtwdev);
++
+ return 0;
+
+ err_destroy_rxwq:
+diff --git a/drivers/net/wireless/realtek/rtw89/core.c b/drivers/net/wireless/realtek/rtw89/core.c
+index ddc390d24ec1a..ddf45828086d2 100644
+--- a/drivers/net/wireless/realtek/rtw89/core.c
++++ b/drivers/net/wireless/realtek/rtw89/core.c
+@@ -1917,7 +1917,8 @@ static void rtw89_vif_rx_stats_iter(void *data, u8 *mac,
+ return;
+
+ if (ieee80211_is_beacon(hdr->frame_control)) {
+- if (vif->type == NL80211_IFTYPE_STATION) {
++ if (vif->type == NL80211_IFTYPE_STATION &&
++ !test_bit(RTW89_FLAG_WOWLAN, rtwdev->flags)) {
+ rtw89_vif_sync_bcn_tsf(rtwvif, hdr, skb->len);
+ rtw89_fw_h2c_rssi_offload(rtwdev, phy_ppdu);
+ }
+diff --git a/drivers/nvme/host/constants.c b/drivers/nvme/host/constants.c
+index 6f2ebb5fcdb05..2b9e6cfaf2a80 100644
+--- a/drivers/nvme/host/constants.c
++++ b/drivers/nvme/host/constants.c
+@@ -173,7 +173,7 @@ static const char * const nvme_statuses[] = {
+
+ const char *nvme_get_error_status_str(u16 status)
+ {
+- status &= 0x7ff;
++ status &= NVME_SCT_SC_MASK;
+ if (status < ARRAY_SIZE(nvme_statuses) && nvme_statuses[status])
+ return nvme_statuses[status];
+ return "Unknown";
+diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
+index d973d063bbf50..5569cf4183b2a 100644
+--- a/drivers/nvme/host/core.c
++++ b/drivers/nvme/host/core.c
+@@ -261,7 +261,7 @@ void nvme_delete_ctrl_sync(struct nvme_ctrl *ctrl)
+
+ static blk_status_t nvme_error_status(u16 status)
+ {
+- switch (status & 0x7ff) {
++ switch (status & NVME_SCT_SC_MASK) {
+ case NVME_SC_SUCCESS:
+ return BLK_STS_OK;
+ case NVME_SC_CAP_EXCEEDED:
+@@ -307,7 +307,7 @@ static void nvme_retry_req(struct request *req)
+ u16 crd;
+
+ /* The mask and shift result must be <= 3 */
+- crd = (nvme_req(req)->status & NVME_SC_CRD) >> 11;
++ crd = (nvme_req(req)->status & NVME_STATUS_CRD) >> 11;
+ if (crd)
+ delay = nvme_req(req)->ctrl->crdt[crd - 1] * 100;
+
+@@ -329,10 +329,10 @@ static void nvme_log_error(struct request *req)
+ nvme_sect_to_lba(ns->head, blk_rq_pos(req)),
+ blk_rq_bytes(req) >> ns->head->lba_shift,
+ nvme_get_error_status_str(nr->status),
+- nr->status >> 8 & 7, /* Status Code Type */
+- nr->status & 0xff, /* Status Code */
+- nr->status & NVME_SC_MORE ? "MORE " : "",
+- nr->status & NVME_SC_DNR ? "DNR " : "");
++ NVME_SCT(nr->status), /* Status Code Type */
++ nr->status & NVME_SC_MASK, /* Status Code */
++ nr->status & NVME_STATUS_MORE ? "MORE " : "",
++ nr->status & NVME_STATUS_DNR ? "DNR " : "");
+ return;
+ }
+
+@@ -341,10 +341,10 @@ static void nvme_log_error(struct request *req)
+ nvme_get_admin_opcode_str(nr->cmd->common.opcode),
+ nr->cmd->common.opcode,
+ nvme_get_error_status_str(nr->status),
+- nr->status >> 8 & 7, /* Status Code Type */
+- nr->status & 0xff, /* Status Code */
+- nr->status & NVME_SC_MORE ? "MORE " : "",
+- nr->status & NVME_SC_DNR ? "DNR " : "");
++ NVME_SCT(nr->status), /* Status Code Type */
++ nr->status & NVME_SC_MASK, /* Status Code */
++ nr->status & NVME_STATUS_MORE ? "MORE " : "",
++ nr->status & NVME_STATUS_DNR ? "DNR " : "");
+ }
+
+ static void nvme_log_err_passthru(struct request *req)
+@@ -359,10 +359,10 @@ static void nvme_log_err_passthru(struct request *req)
+ nvme_get_admin_opcode_str(nr->cmd->common.opcode),
+ nr->cmd->common.opcode,
+ nvme_get_error_status_str(nr->status),
+- nr->status >> 8 & 7, /* Status Code Type */
+- nr->status & 0xff, /* Status Code */
+- nr->status & NVME_SC_MORE ? "MORE " : "",
+- nr->status & NVME_SC_DNR ? "DNR " : "",
++ NVME_SCT(nr->status), /* Status Code Type */
++ nr->status & NVME_SC_MASK, /* Status Code */
++ nr->status & NVME_STATUS_MORE ? "MORE " : "",
++ nr->status & NVME_STATUS_DNR ? "DNR " : "",
+ nr->cmd->common.cdw10,
+ nr->cmd->common.cdw11,
+ nr->cmd->common.cdw12,
+@@ -384,11 +384,11 @@ static inline enum nvme_disposition nvme_decide_disposition(struct request *req)
+ return COMPLETE;
+
+ if (blk_noretry_request(req) ||
+- (nvme_req(req)->status & NVME_SC_DNR) ||
++ (nvme_req(req)->status & NVME_STATUS_DNR) ||
+ nvme_req(req)->retries >= nvme_max_retries)
+ return COMPLETE;
+
+- if ((nvme_req(req)->status & 0x7ff) == NVME_SC_AUTH_REQUIRED)
++ if ((nvme_req(req)->status & NVME_SCT_SC_MASK) == NVME_SC_AUTH_REQUIRED)
+ return AUTHENTICATE;
+
+ if (req->cmd_flags & REQ_NVME_MPATH) {
+@@ -1224,7 +1224,7 @@ EXPORT_SYMBOL_NS_GPL(nvme_passthru_end, NVME_TARGET_PASSTHRU);
+
+ /*
+ * Recommended frequency for KATO commands per NVMe 1.4 section 7.12.1:
+- *
++ *
+ * The host should send Keep Alive commands at half of the Keep Alive Timeout
+ * accounting for transport roundtrip times [..].
+ */
+@@ -3887,7 +3887,7 @@ static void nvme_ns_remove_by_nsid(struct nvme_ctrl *ctrl, u32 nsid)
+
+ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info)
+ {
+- int ret = NVME_SC_INVALID_NS | NVME_SC_DNR;
++ int ret = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
+
+ if (!nvme_ns_ids_equal(&ns->head->ids, &info->ids)) {
+ dev_err(ns->ctrl->device,
+@@ -3903,7 +3903,7 @@ static void nvme_validate_ns(struct nvme_ns *ns, struct nvme_ns_info *info)
+ *
+ * TODO: we should probably schedule a delayed retry here.
+ */
+- if (ret > 0 && (ret & NVME_SC_DNR))
++ if (ret > 0 && (ret & NVME_STATUS_DNR))
+ nvme_ns_remove(ns);
+ }
+
+@@ -4095,7 +4095,7 @@ static void nvme_scan_work(struct work_struct *work)
+ * they report) but don't actually support it.
+ */
+ ret = nvme_scan_ns_list(ctrl);
+- if (ret > 0 && ret & NVME_SC_DNR)
++ if (ret > 0 && ret & NVME_STATUS_DNR)
+ nvme_scan_ns_sequential(ctrl);
+ }
+ mutex_unlock(&ctrl->scan_lock);
+diff --git a/drivers/nvme/host/fabrics.c b/drivers/nvme/host/fabrics.c
+index ceb9c0ed3120b..b5a4b5fd573e0 100644
+--- a/drivers/nvme/host/fabrics.c
++++ b/drivers/nvme/host/fabrics.c
+@@ -187,7 +187,7 @@ int nvmf_reg_read32(struct nvme_ctrl *ctrl, u32 off, u32 *val)
+ if (unlikely(ret != 0))
+ dev_err(ctrl->device,
+ "Property Get error: %d, offset %#x\n",
+- ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
++ ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
+
+ return ret;
+ }
+@@ -233,7 +233,7 @@ int nvmf_reg_read64(struct nvme_ctrl *ctrl, u32 off, u64 *val)
+ if (unlikely(ret != 0))
+ dev_err(ctrl->device,
+ "Property Get error: %d, offset %#x\n",
+- ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
++ ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
+ return ret;
+ }
+ EXPORT_SYMBOL_GPL(nvmf_reg_read64);
+@@ -275,7 +275,7 @@ int nvmf_reg_write32(struct nvme_ctrl *ctrl, u32 off, u32 val)
+ if (unlikely(ret))
+ dev_err(ctrl->device,
+ "Property Set error: %d, offset %#x\n",
+- ret > 0 ? ret & ~NVME_SC_DNR : ret, off);
++ ret > 0 ? ret & ~NVME_STATUS_DNR : ret, off);
+ return ret;
+ }
+ EXPORT_SYMBOL_GPL(nvmf_reg_write32);
+@@ -295,7 +295,7 @@ static void nvmf_log_connect_error(struct nvme_ctrl *ctrl,
+ int errval, int offset, struct nvme_command *cmd,
+ struct nvmf_connect_data *data)
+ {
+- int err_sctype = errval & ~NVME_SC_DNR;
++ int err_sctype = errval & ~NVME_STATUS_DNR;
+
+ if (errval < 0) {
+ dev_err(ctrl->device,
+@@ -573,7 +573,7 @@ EXPORT_SYMBOL_GPL(nvmf_connect_io_queue);
+ */
+ bool nvmf_should_reconnect(struct nvme_ctrl *ctrl, int status)
+ {
+- if (status > 0 && (status & NVME_SC_DNR))
++ if (status > 0 && (status & NVME_STATUS_DNR))
+ return false;
+
+ if (status == -EKEYREJECTED)
+diff --git a/drivers/nvme/host/fault_inject.c b/drivers/nvme/host/fault_inject.c
+index 1ba10a5c656d1..1d1b6441a3398 100644
+--- a/drivers/nvme/host/fault_inject.c
++++ b/drivers/nvme/host/fault_inject.c
+@@ -75,7 +75,7 @@ void nvme_should_fail(struct request *req)
+ /* inject status code and DNR bit */
+ status = fault_inject->status;
+ if (fault_inject->dont_retry)
+- status |= NVME_SC_DNR;
++ status |= NVME_STATUS_DNR;
+ nvme_req(req)->status = status;
+ }
+ }
+diff --git a/drivers/nvme/host/fc.c b/drivers/nvme/host/fc.c
+index f0b0813327491..beaad6576a670 100644
+--- a/drivers/nvme/host/fc.c
++++ b/drivers/nvme/host/fc.c
+@@ -3132,7 +3132,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
+ if (ctrl->ctrl.icdoff) {
+ dev_err(ctrl->ctrl.device, "icdoff %d is not supported!\n",
+ ctrl->ctrl.icdoff);
+- ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out_stop_keep_alive;
+ }
+
+@@ -3140,7 +3140,7 @@ nvme_fc_create_association(struct nvme_fc_ctrl *ctrl)
+ if (!nvme_ctrl_sgl_supported(&ctrl->ctrl)) {
+ dev_err(ctrl->ctrl.device,
+ "Mandatory sgls are not supported!\n");
+- ret = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ ret = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out_stop_keep_alive;
+ }
+
+@@ -3325,7 +3325,7 @@ nvme_fc_reconnect_or_delete(struct nvme_fc_ctrl *ctrl, int status)
+ queue_delayed_work(nvme_wq, &ctrl->connect_work, recon_delay);
+ } else {
+ if (portptr->port_state == FC_OBJSTATE_ONLINE) {
+- if (status > 0 && (status & NVME_SC_DNR))
++ if (status > 0 && (status & NVME_STATUS_DNR))
+ dev_warn(ctrl->ctrl.device,
+ "NVME-FC{%d}: reconnect failure\n",
+ ctrl->cnum);
+diff --git a/drivers/nvme/host/multipath.c b/drivers/nvme/host/multipath.c
+index d8b6b4648eaff..03a6868f4dbc1 100644
+--- a/drivers/nvme/host/multipath.c
++++ b/drivers/nvme/host/multipath.c
+@@ -83,7 +83,7 @@ void nvme_mpath_start_freeze(struct nvme_subsystem *subsys)
+ void nvme_failover_req(struct request *req)
+ {
+ struct nvme_ns *ns = req->q->queuedata;
+- u16 status = nvme_req(req)->status & 0x7ff;
++ u16 status = nvme_req(req)->status & NVME_SCT_SC_MASK;
+ unsigned long flags;
+ struct bio *bio;
+
+diff --git a/drivers/nvme/host/nvme.h b/drivers/nvme/host/nvme.h
+index 68b400f9c42d5..5e66bcb34d530 100644
+--- a/drivers/nvme/host/nvme.h
++++ b/drivers/nvme/host/nvme.h
+@@ -689,7 +689,7 @@ static inline u32 nvme_bytes_to_numd(size_t len)
+
+ static inline bool nvme_is_ana_error(u16 status)
+ {
+- switch (status & 0x7ff) {
++ switch (status & NVME_SCT_SC_MASK) {
+ case NVME_SC_ANA_TRANSITION:
+ case NVME_SC_ANA_INACCESSIBLE:
+ case NVME_SC_ANA_PERSISTENT_LOSS:
+@@ -702,7 +702,7 @@ static inline bool nvme_is_ana_error(u16 status)
+ static inline bool nvme_is_path_error(u16 status)
+ {
+ /* check for a status code type of 'path related status' */
+- return (status & 0x700) == 0x300;
++ return (status & NVME_SCT_MASK) == NVME_SCT_PATH;
+ }
+
+ /*
+@@ -877,7 +877,7 @@ enum {
+ NVME_SUBMIT_NOWAIT = (__force nvme_submit_flags_t)(1 << 1),
+ /* Set BLK_MQ_REQ_RESERVED when allocating request */
+ NVME_SUBMIT_RESERVED = (__force nvme_submit_flags_t)(1 << 2),
+- /* Retry command when NVME_SC_DNR is not set in the result */
++ /* Retry command when NVME_STATUS_DNR is not set in the result */
+ NVME_SUBMIT_RETRY = (__force nvme_submit_flags_t)(1 << 3),
+ };
+
+diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
+index a823330567ff8..18d85575cdb48 100644
+--- a/drivers/nvme/host/pci.c
++++ b/drivers/nvme/host/pci.c
+@@ -2473,6 +2473,12 @@ static unsigned int nvme_pci_nr_maps(struct nvme_dev *dev)
+
+ static void nvme_pci_update_nr_queues(struct nvme_dev *dev)
+ {
++ if (!dev->ctrl.tagset) {
++ nvme_alloc_io_tag_set(&dev->ctrl, &dev->tagset, &nvme_mq_ops,
++ nvme_pci_nr_maps(dev), sizeof(struct nvme_iod));
++ return;
++ }
++
+ blk_mq_update_nr_hw_queues(&dev->tagset, dev->online_queues - 1);
+ /* free previously allocated queues that are no longer usable */
+ nvme_free_queues(dev, dev->online_queues);
+@@ -2931,6 +2937,17 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
+ dmi_match(DMI_BOARD_NAME, "NS5x_7xPU") ||
+ dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1"))
+ return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
++ } else if (pdev->vendor == 0x144d && pdev->device == 0xa80d) {
++ /*
++ * Exclude Samsung 990 Evo from NVME_QUIRK_SIMPLE_SUSPEND
++ * because of high power consumption (> 2 Watt) in s2idle
++ * sleep. Only some boards with Intel CPU are affected.
++ */
++ if (dmi_match(DMI_BOARD_NAME, "GMxPXxx") ||
++ dmi_match(DMI_BOARD_NAME, "PH4PG31") ||
++ dmi_match(DMI_BOARD_NAME, "PH4PRX1_PH6PRX1") ||
++ dmi_match(DMI_BOARD_NAME, "PH6PG01_PH6PG71"))
++ return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
+ }
+
+ /*
+diff --git a/drivers/nvme/host/pr.c b/drivers/nvme/host/pr.c
+index 8fa1ffcdaed48..7347ddf85f00b 100644
+--- a/drivers/nvme/host/pr.c
++++ b/drivers/nvme/host/pr.c
+@@ -72,12 +72,12 @@ static int nvme_send_ns_pr_command(struct nvme_ns *ns, struct nvme_command *c,
+ return nvme_submit_sync_cmd(ns->queue, c, data, data_len);
+ }
+
+-static int nvme_sc_to_pr_err(int nvme_sc)
++static int nvme_status_to_pr_err(int status)
+ {
+- if (nvme_is_path_error(nvme_sc))
++ if (nvme_is_path_error(status))
+ return PR_STS_PATH_FAILED;
+
+- switch (nvme_sc & 0x7ff) {
++ switch (status & NVME_SCT_SC_MASK) {
+ case NVME_SC_SUCCESS:
+ return PR_STS_SUCCESS;
+ case NVME_SC_RESERVATION_CONFLICT:
+@@ -121,7 +121,7 @@ static int nvme_pr_command(struct block_device *bdev, u32 cdw10,
+ if (ret < 0)
+ return ret;
+
+- return nvme_sc_to_pr_err(ret);
++ return nvme_status_to_pr_err(ret);
+ }
+
+ static int nvme_pr_register(struct block_device *bdev, u64 old,
+@@ -196,7 +196,7 @@ static int nvme_pr_resv_report(struct block_device *bdev, void *data,
+ if (ret < 0)
+ return ret;
+
+- return nvme_sc_to_pr_err(ret);
++ return nvme_status_to_pr_err(ret);
+ }
+
+ static int nvme_pr_read_keys(struct block_device *bdev,
+diff --git a/drivers/nvme/target/admin-cmd.c b/drivers/nvme/target/admin-cmd.c
+index f5b7054a4a05e..85006b2df8ae0 100644
+--- a/drivers/nvme/target/admin-cmd.c
++++ b/drivers/nvme/target/admin-cmd.c
+@@ -344,7 +344,7 @@ static void nvmet_execute_get_log_page(struct nvmet_req *req)
+ pr_debug("unhandled lid %d on qid %d\n",
+ req->cmd->get_log_page.lid, req->sq->qid);
+ req->error_loc = offsetof(struct nvme_get_log_page_command, lid);
+- nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
++ nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_STATUS_DNR);
+ }
+
+ static void nvmet_execute_identify_ctrl(struct nvmet_req *req)
+@@ -496,7 +496,7 @@ static void nvmet_execute_identify_ns(struct nvmet_req *req)
+
+ if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
+ req->error_loc = offsetof(struct nvme_identify, nsid);
+- status = NVME_SC_INVALID_NS | NVME_SC_DNR;
++ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -587,6 +587,16 @@ static void nvmet_execute_identify_nslist(struct nvmet_req *req)
+ u16 status = 0;
+ int i = 0;
+
++ /*
++ * NSID values 0xFFFFFFFE and NVME_NSID_ALL are invalid
++ * See NVMe Base Specification, Active Namespace ID list (CNS 02h).
++ */
++ if (min_nsid == 0xFFFFFFFE || min_nsid == NVME_NSID_ALL) {
++ req->error_loc = offsetof(struct nvme_identify, nsid);
++ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
++ goto out;
++ }
++
+ list = kzalloc(buf_size, GFP_KERNEL);
+ if (!list) {
+ status = NVME_SC_INTERNAL;
+@@ -662,7 +672,7 @@ static void nvmet_execute_identify_desclist(struct nvmet_req *req)
+
+ if (sg_zero_buffer(req->sg, req->sg_cnt, NVME_IDENTIFY_DATA_SIZE - off,
+ off) != NVME_IDENTIFY_DATA_SIZE - off)
+- status = NVME_SC_INTERNAL | NVME_SC_DNR;
++ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+
+ out:
+ nvmet_req_complete(req, status);
+@@ -724,7 +734,7 @@ static void nvmet_execute_identify(struct nvmet_req *req)
+ pr_debug("unhandled identify cns %d on qid %d\n",
+ req->cmd->identify.cns, req->sq->qid);
+ req->error_loc = offsetof(struct nvme_identify, cns);
+- nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_SC_DNR);
++ nvmet_req_complete(req, NVME_SC_INVALID_FIELD | NVME_STATUS_DNR);
+ }
+
+ /*
+@@ -807,7 +817,7 @@ u16 nvmet_set_feat_async_event(struct nvmet_req *req, u32 mask)
+
+ if (val32 & ~mask) {
+ req->error_loc = offsetof(struct nvme_common_command, cdw11);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ WRITE_ONCE(req->sq->ctrl->aen_enabled, val32);
+@@ -833,7 +843,7 @@ void nvmet_execute_set_features(struct nvmet_req *req)
+ ncqr = (cdw11 >> 16) & 0xffff;
+ nsqr = cdw11 & 0xffff;
+ if (ncqr == 0xffff || nsqr == 0xffff) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+ nvmet_set_result(req,
+@@ -846,14 +856,14 @@ void nvmet_execute_set_features(struct nvmet_req *req)
+ status = nvmet_set_feat_async_event(req, NVMET_AEN_CFG_ALL);
+ break;
+ case NVME_FEAT_HOST_ID:
+- status = NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
++ status = NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
+ break;
+ case NVME_FEAT_WRITE_PROTECT:
+ status = nvmet_set_feat_write_protect(req);
+ break;
+ default:
+ req->error_loc = offsetof(struct nvme_common_command, cdw10);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+
+@@ -939,7 +949,7 @@ void nvmet_execute_get_features(struct nvmet_req *req)
+ if (!(req->cmd->common.cdw11 & cpu_to_le32(1 << 0))) {
+ req->error_loc =
+ offsetof(struct nvme_common_command, cdw11);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+
+@@ -952,7 +962,7 @@ void nvmet_execute_get_features(struct nvmet_req *req)
+ default:
+ req->error_loc =
+ offsetof(struct nvme_common_command, cdw10);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+
+@@ -969,7 +979,7 @@ void nvmet_execute_async_event(struct nvmet_req *req)
+ mutex_lock(&ctrl->lock);
+ if (ctrl->nr_async_event_cmds >= NVMET_ASYNC_EVENTS) {
+ mutex_unlock(&ctrl->lock);
+- nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_SC_DNR);
++ nvmet_req_complete(req, NVME_SC_ASYNC_LIMIT | NVME_STATUS_DNR);
+ return;
+ }
+ ctrl->async_event_cmds[ctrl->nr_async_event_cmds++] = req;
+@@ -1006,7 +1016,7 @@ u16 nvmet_parse_admin_cmd(struct nvmet_req *req)
+ if (nvme_is_fabrics(cmd))
+ return nvmet_parse_fabrics_admin_cmd(req);
+ if (unlikely(!nvmet_check_auth_status(req)))
+- return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR;
++ return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR;
+ if (nvmet_is_disc_subsys(nvmet_req_subsys(req)))
+ return nvmet_parse_discovery_cmd(req);
+
+diff --git a/drivers/nvme/target/core.c b/drivers/nvme/target/core.c
+index 4ff460ba28263..c0973810e6af5 100644
+--- a/drivers/nvme/target/core.c
++++ b/drivers/nvme/target/core.c
+@@ -55,18 +55,18 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
+ return NVME_SC_SUCCESS;
+ case -ENOSPC:
+ req->error_loc = offsetof(struct nvme_rw_command, length);
+- return NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
++ return NVME_SC_CAP_EXCEEDED | NVME_STATUS_DNR;
+ case -EREMOTEIO:
+ req->error_loc = offsetof(struct nvme_rw_command, slba);
+- return NVME_SC_LBA_RANGE | NVME_SC_DNR;
++ return NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
+ case -EOPNOTSUPP:
+ req->error_loc = offsetof(struct nvme_common_command, opcode);
+ switch (req->cmd->common.opcode) {
+ case nvme_cmd_dsm:
+ case nvme_cmd_write_zeroes:
+- return NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
++ return NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
+ default:
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+ break;
+ case -ENODATA:
+@@ -76,7 +76,7 @@ inline u16 errno_to_nvme_status(struct nvmet_req *req, int errno)
+ fallthrough;
+ default:
+ req->error_loc = offsetof(struct nvme_common_command, opcode);
+- return NVME_SC_INTERNAL | NVME_SC_DNR;
++ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ }
+ }
+
+@@ -86,7 +86,7 @@ u16 nvmet_report_invalid_opcode(struct nvmet_req *req)
+ req->sq->qid);
+
+ req->error_loc = offsetof(struct nvme_common_command, opcode);
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+
+ static struct nvmet_subsys *nvmet_find_get_subsys(struct nvmet_port *port,
+@@ -97,7 +97,7 @@ u16 nvmet_copy_to_sgl(struct nvmet_req *req, off_t off, const void *buf,
+ {
+ if (sg_pcopy_from_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
+ req->error_loc = offsetof(struct nvme_common_command, dptr);
+- return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
++ return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR;
+ }
+ return 0;
+ }
+@@ -106,7 +106,7 @@ u16 nvmet_copy_from_sgl(struct nvmet_req *req, off_t off, void *buf, size_t len)
+ {
+ if (sg_pcopy_to_buffer(req->sg, req->sg_cnt, buf, len, off) != len) {
+ req->error_loc = offsetof(struct nvme_common_command, dptr);
+- return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
++ return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR;
+ }
+ return 0;
+ }
+@@ -115,7 +115,7 @@ u16 nvmet_zero_sgl(struct nvmet_req *req, off_t off, size_t len)
+ {
+ if (sg_zero_buffer(req->sg, req->sg_cnt, len, off) != len) {
+ req->error_loc = offsetof(struct nvme_common_command, dptr);
+- return NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR;
++ return NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR;
+ }
+ return 0;
+ }
+@@ -145,7 +145,7 @@ static void nvmet_async_events_failall(struct nvmet_ctrl *ctrl)
+ while (ctrl->nr_async_event_cmds) {
+ req = ctrl->async_event_cmds[--ctrl->nr_async_event_cmds];
+ mutex_unlock(&ctrl->lock);
+- nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_SC_DNR);
++ nvmet_req_complete(req, NVME_SC_INTERNAL | NVME_STATUS_DNR);
+ mutex_lock(&ctrl->lock);
+ }
+ mutex_unlock(&ctrl->lock);
+@@ -444,7 +444,7 @@ u16 nvmet_req_find_ns(struct nvmet_req *req)
+ req->error_loc = offsetof(struct nvme_common_command, nsid);
+ if (nvmet_subsys_nsid_exists(subsys, nsid))
+ return NVME_SC_INTERNAL_PATH_ERROR;
+- return NVME_SC_INVALID_NS | NVME_SC_DNR;
++ return NVME_SC_INVALID_NS | NVME_STATUS_DNR;
+ }
+
+ percpu_ref_get(&req->ns->ref);
+@@ -904,7 +904,7 @@ static u16 nvmet_parse_io_cmd(struct nvmet_req *req)
+ return nvmet_parse_fabrics_io_cmd(req);
+
+ if (unlikely(!nvmet_check_auth_status(req)))
+- return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR;
++ return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR;
+
+ ret = nvmet_check_ctrl_status(req);
+ if (unlikely(ret))
+@@ -967,7 +967,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
+ /* no support for fused commands yet */
+ if (unlikely(flags & (NVME_CMD_FUSE_FIRST | NVME_CMD_FUSE_SECOND))) {
+ req->error_loc = offsetof(struct nvme_common_command, flags);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto fail;
+ }
+
+@@ -978,7 +978,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
+ */
+ if (unlikely((flags & NVME_CMD_SGL_ALL) != NVME_CMD_SGL_METABUF)) {
+ req->error_loc = offsetof(struct nvme_common_command, flags);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto fail;
+ }
+
+@@ -996,7 +996,7 @@ bool nvmet_req_init(struct nvmet_req *req, struct nvmet_cq *cq,
+ trace_nvmet_req_init(req, req->cmd);
+
+ if (unlikely(!percpu_ref_tryget_live(&sq->ref))) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto fail;
+ }
+
+@@ -1023,7 +1023,7 @@ bool nvmet_check_transfer_len(struct nvmet_req *req, size_t len)
+ {
+ if (unlikely(len != req->transfer_len)) {
+ req->error_loc = offsetof(struct nvme_common_command, dptr);
+- nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
++ nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR);
+ return false;
+ }
+
+@@ -1035,7 +1035,7 @@ bool nvmet_check_data_len_lte(struct nvmet_req *req, size_t data_len)
+ {
+ if (unlikely(data_len > req->transfer_len)) {
+ req->error_loc = offsetof(struct nvme_common_command, dptr);
+- nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_SC_DNR);
++ nvmet_req_complete(req, NVME_SC_SGL_INVALID_DATA | NVME_STATUS_DNR);
+ return false;
+ }
+
+@@ -1304,18 +1304,18 @@ u16 nvmet_check_ctrl_status(struct nvmet_req *req)
+ if (unlikely(!(req->sq->ctrl->cc & NVME_CC_ENABLE))) {
+ pr_err("got cmd %d while CC.EN == 0 on qid = %d\n",
+ req->cmd->common.opcode, req->sq->qid);
+- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
++ return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
+ }
+
+ if (unlikely(!(req->sq->ctrl->csts & NVME_CSTS_RDY))) {
+ pr_err("got cmd %d while CSTS.RDY == 0 on qid = %d\n",
+ req->cmd->common.opcode, req->sq->qid);
+- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
++ return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
+ }
+
+ if (unlikely(!nvmet_check_auth_status(req))) {
+ pr_warn("qid %d not authenticated\n", req->sq->qid);
+- return NVME_SC_AUTH_REQUIRED | NVME_SC_DNR;
++ return NVME_SC_AUTH_REQUIRED | NVME_STATUS_DNR;
+ }
+ return 0;
+ }
+@@ -1389,7 +1389,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
+ int ret;
+ u16 status;
+
+- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ subsys = nvmet_find_get_subsys(req->port, subsysnqn);
+ if (!subsys) {
+ pr_warn("connect request for invalid subsystem %s!\n",
+@@ -1405,7 +1405,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
+ hostnqn, subsysnqn);
+ req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(hostnqn);
+ up_read(&nvmet_config_sem);
+- status = NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR;
+ req->error_loc = offsetof(struct nvme_common_command, dptr);
+ goto out_put_subsystem;
+ }
+@@ -1456,7 +1456,7 @@ u16 nvmet_alloc_ctrl(const char *subsysnqn, const char *hostnqn,
+ subsys->cntlid_min, subsys->cntlid_max,
+ GFP_KERNEL);
+ if (ret < 0) {
+- status = NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR;
+ goto out_free_sqs;
+ }
+ ctrl->cntlid = ret;
+diff --git a/drivers/nvme/target/discovery.c b/drivers/nvme/target/discovery.c
+index ce54da8c6b366..28843df5fa7c7 100644
+--- a/drivers/nvme/target/discovery.c
++++ b/drivers/nvme/target/discovery.c
+@@ -179,7 +179,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
+ if (req->cmd->get_log_page.lid != NVME_LOG_DISC) {
+ req->error_loc =
+ offsetof(struct nvme_get_log_page_command, lid);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -187,7 +187,7 @@ static void nvmet_execute_disc_get_log_page(struct nvmet_req *req)
+ if (offset & 0x3) {
+ req->error_loc =
+ offsetof(struct nvme_get_log_page_command, lpo);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -256,7 +256,7 @@ static void nvmet_execute_disc_identify(struct nvmet_req *req)
+
+ if (req->cmd->identify.cns != NVME_ID_CNS_CTRL) {
+ req->error_loc = offsetof(struct nvme_identify, cns);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -320,7 +320,7 @@ static void nvmet_execute_disc_set_features(struct nvmet_req *req)
+ default:
+ req->error_loc =
+ offsetof(struct nvme_common_command, cdw10);
+- stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ stat = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+
+@@ -345,7 +345,7 @@ static void nvmet_execute_disc_get_features(struct nvmet_req *req)
+ default:
+ req->error_loc =
+ offsetof(struct nvme_common_command, cdw10);
+- stat = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ stat = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+
+@@ -361,7 +361,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
+ cmd->common.opcode);
+ req->error_loc =
+ offsetof(struct nvme_common_command, opcode);
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+
+ switch (cmd->common.opcode) {
+@@ -386,7 +386,7 @@ u16 nvmet_parse_discovery_cmd(struct nvmet_req *req)
+ default:
+ pr_debug("unhandled cmd %d\n", cmd->common.opcode);
+ req->error_loc = offsetof(struct nvme_common_command, opcode);
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+
+ }
+diff --git a/drivers/nvme/target/fabrics-cmd-auth.c b/drivers/nvme/target/fabrics-cmd-auth.c
+index cb34d644ed086..3f2857c17d956 100644
+--- a/drivers/nvme/target/fabrics-cmd-auth.c
++++ b/drivers/nvme/target/fabrics-cmd-auth.c
+@@ -189,26 +189,26 @@ void nvmet_execute_auth_send(struct nvmet_req *req)
+ u8 dhchap_status;
+
+ if (req->cmd->auth_send.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_send_command, secp);
+ goto done;
+ }
+ if (req->cmd->auth_send.spsp0 != 0x01) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_send_command, spsp0);
+ goto done;
+ }
+ if (req->cmd->auth_send.spsp1 != 0x01) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_send_command, spsp1);
+ goto done;
+ }
+ tl = le32_to_cpu(req->cmd->auth_send.tl);
+ if (!tl) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_send_command, tl);
+ goto done;
+@@ -437,26 +437,26 @@ void nvmet_execute_auth_receive(struct nvmet_req *req)
+ u16 status = 0;
+
+ if (req->cmd->auth_receive.secp != NVME_AUTH_DHCHAP_PROTOCOL_IDENTIFIER) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_receive_command, secp);
+ goto done;
+ }
+ if (req->cmd->auth_receive.spsp0 != 0x01) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_receive_command, spsp0);
+ goto done;
+ }
+ if (req->cmd->auth_receive.spsp1 != 0x01) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_receive_command, spsp1);
+ goto done;
+ }
+ al = le32_to_cpu(req->cmd->auth_receive.al);
+ if (!al) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc =
+ offsetof(struct nvmf_auth_receive_command, al);
+ goto done;
+diff --git a/drivers/nvme/target/fabrics-cmd.c b/drivers/nvme/target/fabrics-cmd.c
+index 69d77d34bec11..c4b2eddd5666a 100644
+--- a/drivers/nvme/target/fabrics-cmd.c
++++ b/drivers/nvme/target/fabrics-cmd.c
+@@ -18,7 +18,7 @@ static void nvmet_execute_prop_set(struct nvmet_req *req)
+ if (req->cmd->prop_set.attrib & 1) {
+ req->error_loc =
+ offsetof(struct nvmf_property_set_command, attrib);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -29,7 +29,7 @@ static void nvmet_execute_prop_set(struct nvmet_req *req)
+ default:
+ req->error_loc =
+ offsetof(struct nvmf_property_set_command, offset);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+ out:
+ nvmet_req_complete(req, status);
+@@ -50,7 +50,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
+ val = ctrl->cap;
+ break;
+ default:
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+ } else {
+@@ -65,7 +65,7 @@ static void nvmet_execute_prop_get(struct nvmet_req *req)
+ val = ctrl->csts;
+ break;
+ default:
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ break;
+ }
+ }
+@@ -105,7 +105,7 @@ u16 nvmet_parse_fabrics_admin_cmd(struct nvmet_req *req)
+ pr_debug("received unknown capsule type 0x%x\n",
+ cmd->fabrics.fctype);
+ req->error_loc = offsetof(struct nvmf_common_command, fctype);
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+
+ return 0;
+@@ -128,7 +128,7 @@ u16 nvmet_parse_fabrics_io_cmd(struct nvmet_req *req)
+ pr_debug("received unknown capsule type 0x%x\n",
+ cmd->fabrics.fctype);
+ req->error_loc = offsetof(struct nvmf_common_command, fctype);
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+
+ return 0;
+@@ -147,14 +147,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
+ pr_warn("queue size zero!\n");
+ req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
+ req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize);
+- ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
++ ret = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ goto err;
+ }
+
+ if (ctrl->sqs[qid] != NULL) {
+ pr_warn("qid %u has already been created\n", qid);
+ req->error_loc = offsetof(struct nvmf_connect_command, qid);
+- return NVME_SC_CMD_SEQ_ERROR | NVME_SC_DNR;
++ return NVME_SC_CMD_SEQ_ERROR | NVME_STATUS_DNR;
+ }
+
+ /* for fabrics, this value applies to only the I/O Submission Queues */
+@@ -163,14 +163,14 @@ static u16 nvmet_install_queue(struct nvmet_ctrl *ctrl, struct nvmet_req *req)
+ sqsize, mqes, ctrl->cntlid);
+ req->error_loc = offsetof(struct nvmf_connect_command, sqsize);
+ req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(sqsize);
+- return NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
++ return NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ }
+
+ old = cmpxchg(&req->sq->ctrl, NULL, ctrl);
+ if (old) {
+ pr_warn("queue already connected!\n");
+ req->error_loc = offsetof(struct nvmf_connect_command, opcode);
+- return NVME_SC_CONNECT_CTRL_BUSY | NVME_SC_DNR;
++ return NVME_SC_CONNECT_CTRL_BUSY | NVME_STATUS_DNR;
+ }
+
+ /* note: convert queue size from 0's-based value to 1's-based value */
+@@ -230,14 +230,14 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
+ pr_warn("invalid connect version (%d).\n",
+ le16_to_cpu(c->recfmt));
+ req->error_loc = offsetof(struct nvmf_connect_command, recfmt);
+- status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ if (unlikely(d->cntlid != cpu_to_le16(0xffff))) {
+ pr_warn("connect attempt for invalid controller ID %#x\n",
+ d->cntlid);
+- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ req->cqe->result.u32 = IPO_IATTR_CONNECT_DATA(cntlid);
+ goto out;
+ }
+@@ -257,7 +257,7 @@ static void nvmet_execute_admin_connect(struct nvmet_req *req)
+ dhchap_status);
+ nvmet_ctrl_put(ctrl);
+ if (dhchap_status == NVME_AUTH_DHCHAP_FAILURE_FAILED)
+- status = (NVME_SC_CONNECT_INVALID_HOST | NVME_SC_DNR);
++ status = (NVME_SC_CONNECT_INVALID_HOST | NVME_STATUS_DNR);
+ else
+ status = NVME_SC_INTERNAL;
+ goto out;
+@@ -305,7 +305,7 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
+ if (c->recfmt != 0) {
+ pr_warn("invalid connect version (%d).\n",
+ le16_to_cpu(c->recfmt));
+- status = NVME_SC_CONNECT_FORMAT | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_FORMAT | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -314,13 +314,13 @@ static void nvmet_execute_io_connect(struct nvmet_req *req)
+ ctrl = nvmet_ctrl_find_get(d->subsysnqn, d->hostnqn,
+ le16_to_cpu(d->cntlid), req);
+ if (!ctrl) {
+- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ if (unlikely(qid > ctrl->subsys->max_qid)) {
+ pr_warn("invalid queue id (%d)\n", qid);
+- status = NVME_SC_CONNECT_INVALID_PARAM | NVME_SC_DNR;
++ status = NVME_SC_CONNECT_INVALID_PARAM | NVME_STATUS_DNR;
+ req->cqe->result.u32 = IPO_IATTR_CONNECT_SQE(qid);
+ goto out_ctrl_put;
+ }
+@@ -350,13 +350,13 @@ u16 nvmet_parse_connect_cmd(struct nvmet_req *req)
+ pr_debug("invalid command 0x%x on unconnected queue.\n",
+ cmd->fabrics.opcode);
+ req->error_loc = offsetof(struct nvme_common_command, opcode);
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+ if (cmd->fabrics.fctype != nvme_fabrics_type_connect) {
+ pr_debug("invalid capsule type 0x%x on unconnected queue.\n",
+ cmd->fabrics.fctype);
+ req->error_loc = offsetof(struct nvmf_common_command, fctype);
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+
+ if (cmd->connect.qid == 0)
+diff --git a/drivers/nvme/target/io-cmd-bdev.c b/drivers/nvme/target/io-cmd-bdev.c
+index 6426aac2634ae..e511b055ece71 100644
+--- a/drivers/nvme/target/io-cmd-bdev.c
++++ b/drivers/nvme/target/io-cmd-bdev.c
+@@ -135,11 +135,11 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
+ */
+ switch (blk_sts) {
+ case BLK_STS_NOSPC:
+- status = NVME_SC_CAP_EXCEEDED | NVME_SC_DNR;
++ status = NVME_SC_CAP_EXCEEDED | NVME_STATUS_DNR;
+ req->error_loc = offsetof(struct nvme_rw_command, length);
+ break;
+ case BLK_STS_TARGET:
+- status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
++ status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
+ req->error_loc = offsetof(struct nvme_rw_command, slba);
+ break;
+ case BLK_STS_NOTSUPP:
+@@ -147,10 +147,10 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
+ switch (req->cmd->common.opcode) {
+ case nvme_cmd_dsm:
+ case nvme_cmd_write_zeroes:
+- status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_SC_DNR;
++ status = NVME_SC_ONCS_NOT_SUPPORTED | NVME_STATUS_DNR;
+ break;
+ default:
+- status = NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ status = NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+ break;
+ case BLK_STS_MEDIUM:
+@@ -159,7 +159,7 @@ u16 blk_to_nvme_status(struct nvmet_req *req, blk_status_t blk_sts)
+ break;
+ case BLK_STS_IOERR:
+ default:
+- status = NVME_SC_INTERNAL | NVME_SC_DNR;
++ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ req->error_loc = offsetof(struct nvme_common_command, opcode);
+ }
+
+@@ -356,7 +356,7 @@ u16 nvmet_bdev_flush(struct nvmet_req *req)
+ return 0;
+
+ if (blkdev_issue_flush(req->ns->bdev))
+- return NVME_SC_INTERNAL | NVME_SC_DNR;
++ return NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ return 0;
+ }
+
+diff --git a/drivers/nvme/target/passthru.c b/drivers/nvme/target/passthru.c
+index f003782d4ecff..24d0e2418d2e6 100644
+--- a/drivers/nvme/target/passthru.c
++++ b/drivers/nvme/target/passthru.c
+@@ -306,7 +306,7 @@ static void nvmet_passthru_execute_cmd(struct nvmet_req *req)
+ ns = nvme_find_get_ns(ctrl, nsid);
+ if (unlikely(!ns)) {
+ pr_err("failed to get passthru ns nsid:%u\n", nsid);
+- status = NVME_SC_INVALID_NS | NVME_SC_DNR;
++ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -426,7 +426,7 @@ u16 nvmet_parse_passthru_io_cmd(struct nvmet_req *req)
+ * emulated in the future if regular targets grow support for
+ * this feature.
+ */
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+
+ return nvmet_setup_passthru_command(req);
+@@ -478,7 +478,7 @@ static u16 nvmet_passthru_get_set_features(struct nvmet_req *req)
+ case NVME_FEAT_RESV_PERSIST:
+ /* No reservations, see nvmet_parse_passthru_io_cmd() */
+ default:
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ }
+ }
+
+@@ -546,7 +546,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
+ req->p.use_workqueue = true;
+ return NVME_SC_SUCCESS;
+ }
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ case NVME_ID_CNS_NS:
+ req->execute = nvmet_passthru_execute_cmd;
+ req->p.use_workqueue = true;
+@@ -558,7 +558,7 @@ u16 nvmet_parse_passthru_admin_cmd(struct nvmet_req *req)
+ req->p.use_workqueue = true;
+ return NVME_SC_SUCCESS;
+ }
+- return NVME_SC_INVALID_OPCODE | NVME_SC_DNR;
++ return NVME_SC_INVALID_OPCODE | NVME_STATUS_DNR;
+ default:
+ return nvmet_setup_passthru_command(req);
+ }
+diff --git a/drivers/nvme/target/rdma.c b/drivers/nvme/target/rdma.c
+index 689bb5d3cfdcf..498b3ca596510 100644
+--- a/drivers/nvme/target/rdma.c
++++ b/drivers/nvme/target/rdma.c
+@@ -852,12 +852,12 @@ static u16 nvmet_rdma_map_sgl_inline(struct nvmet_rdma_rsp *rsp)
+ if (!nvme_is_write(rsp->req.cmd)) {
+ rsp->req.error_loc =
+ offsetof(struct nvme_common_command, opcode);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ if (off + len > rsp->queue->dev->inline_data_size) {
+ pr_err("invalid inline data offset!\n");
+- return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
++ return NVME_SC_SGL_INVALID_OFFSET | NVME_STATUS_DNR;
+ }
+
+ /* no data command? */
+@@ -919,7 +919,7 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
+ pr_err("invalid SGL subtype: %#x\n", sgl->type);
+ rsp->req.error_loc =
+ offsetof(struct nvme_common_command, dptr);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+ case NVME_KEY_SGL_FMT_DATA_DESC:
+ switch (sgl->type & 0xf) {
+@@ -931,12 +931,12 @@ static u16 nvmet_rdma_map_sgl(struct nvmet_rdma_rsp *rsp)
+ pr_err("invalid SGL subtype: %#x\n", sgl->type);
+ rsp->req.error_loc =
+ offsetof(struct nvme_common_command, dptr);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+ default:
+ pr_err("invalid SGL type: %#x\n", sgl->type);
+ rsp->req.error_loc = offsetof(struct nvme_common_command, dptr);
+- return NVME_SC_SGL_INVALID_TYPE | NVME_SC_DNR;
++ return NVME_SC_SGL_INVALID_TYPE | NVME_STATUS_DNR;
+ }
+ }
+
+diff --git a/drivers/nvme/target/tcp.c b/drivers/nvme/target/tcp.c
+index 380f22ee3ebba..45b46c55681f7 100644
+--- a/drivers/nvme/target/tcp.c
++++ b/drivers/nvme/target/tcp.c
+@@ -416,10 +416,10 @@ static int nvmet_tcp_map_data(struct nvmet_tcp_cmd *cmd)
+ if (sgl->type == ((NVME_SGL_FMT_DATA_DESC << 4) |
+ NVME_SGL_FMT_OFFSET)) {
+ if (!nvme_is_write(cmd->req.cmd))
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+
+ if (len > cmd->req.port->inline_data_size)
+- return NVME_SC_SGL_INVALID_OFFSET | NVME_SC_DNR;
++ return NVME_SC_SGL_INVALID_OFFSET | NVME_STATUS_DNR;
+ cmd->pdu_len = len;
+ }
+ cmd->req.transfer_len += len;
+@@ -2146,8 +2146,10 @@ static u16 nvmet_tcp_install_queue(struct nvmet_sq *sq)
+ }
+
+ queue->nr_cmds = sq->size * 2;
+- if (nvmet_tcp_alloc_cmds(queue))
++ if (nvmet_tcp_alloc_cmds(queue)) {
++ queue->nr_cmds = 0;
+ return NVME_SC_INTERNAL;
++ }
+ return 0;
+ }
+
+diff --git a/drivers/nvme/target/zns.c b/drivers/nvme/target/zns.c
+index 0021d06041c1e..af9e13be76786 100644
+--- a/drivers/nvme/target/zns.c
++++ b/drivers/nvme/target/zns.c
+@@ -100,7 +100,7 @@ void nvmet_execute_identify_ns_zns(struct nvmet_req *req)
+
+ if (le32_to_cpu(req->cmd->identify.nsid) == NVME_NSID_ALL) {
+ req->error_loc = offsetof(struct nvme_identify, nsid);
+- status = NVME_SC_INVALID_NS | NVME_SC_DNR;
++ status = NVME_SC_INVALID_NS | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -121,7 +121,7 @@ void nvmet_execute_identify_ns_zns(struct nvmet_req *req)
+ }
+
+ if (!bdev_is_zoned(req->ns->bdev)) {
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ req->error_loc = offsetof(struct nvme_identify, nsid);
+ goto out;
+ }
+@@ -158,17 +158,17 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
+
+ if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
+ req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, slba);
+- return NVME_SC_LBA_RANGE | NVME_SC_DNR;
++ return NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
+ }
+
+ if (out_bufsize < sizeof(struct nvme_zone_report)) {
+ req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, numd);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ if (req->cmd->zmr.zra != NVME_ZRA_ZONE_REPORT) {
+ req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, zra);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ switch (req->cmd->zmr.pr) {
+@@ -177,7 +177,7 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
+ break;
+ default:
+ req->error_loc = offsetof(struct nvme_zone_mgmt_recv_cmd, pr);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ switch (req->cmd->zmr.zrasf) {
+@@ -193,7 +193,7 @@ static u16 nvmet_bdev_validate_zone_mgmt_recv(struct nvmet_req *req)
+ default:
+ req->error_loc =
+ offsetof(struct nvme_zone_mgmt_recv_cmd, zrasf);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ return NVME_SC_SUCCESS;
+@@ -341,7 +341,7 @@ static u16 blkdev_zone_mgmt_errno_to_nvme_status(int ret)
+ return NVME_SC_SUCCESS;
+ case -EINVAL:
+ case -EIO:
+- return NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
++ return NVME_SC_ZONE_INVALID_TRANSITION | NVME_STATUS_DNR;
+ default:
+ return NVME_SC_INTERNAL;
+ }
+@@ -463,7 +463,7 @@ static u16 nvmet_bdev_execute_zmgmt_send_all(struct nvmet_req *req)
+ default:
+ /* this is needed to quiet compiler warning */
+ req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
+- return NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ return NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ }
+
+ return NVME_SC_SUCCESS;
+@@ -481,7 +481,7 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
+
+ if (op == REQ_OP_LAST) {
+ req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, zsa);
+- status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_SC_DNR;
++ status = NVME_SC_ZONE_INVALID_TRANSITION | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -493,13 +493,13 @@ static void nvmet_bdev_zmgmt_send_work(struct work_struct *w)
+
+ if (sect >= get_capacity(bdev->bd_disk)) {
+ req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
+- status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
++ status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ if (sect & (zone_sectors - 1)) {
+ req->error_loc = offsetof(struct nvme_zone_mgmt_send_cmd, slba);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -551,13 +551,13 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
+
+ if (sect >= get_capacity(req->ns->bdev->bd_disk)) {
+ req->error_loc = offsetof(struct nvme_rw_command, slba);
+- status = NVME_SC_LBA_RANGE | NVME_SC_DNR;
++ status = NVME_SC_LBA_RANGE | NVME_STATUS_DNR;
+ goto out;
+ }
+
+ if (sect & (bdev_zone_sectors(req->ns->bdev) - 1)) {
+ req->error_loc = offsetof(struct nvme_rw_command, slba);
+- status = NVME_SC_INVALID_FIELD | NVME_SC_DNR;
++ status = NVME_SC_INVALID_FIELD | NVME_STATUS_DNR;
+ goto out;
+ }
+
+@@ -590,7 +590,7 @@ void nvmet_bdev_execute_zone_append(struct nvmet_req *req)
+ }
+
+ if (total_len != nvmet_rw_data_len(req)) {
+- status = NVME_SC_INTERNAL | NVME_SC_DNR;
++ status = NVME_SC_INTERNAL | NVME_STATUS_DNR;
+ goto out_put_bio;
+ }
+
+diff --git a/drivers/nvmem/core.c b/drivers/nvmem/core.c
+index f8dd7eb40fbe1..cccfa9fe81192 100644
+--- a/drivers/nvmem/core.c
++++ b/drivers/nvmem/core.c
+@@ -1258,13 +1258,13 @@ void nvmem_device_put(struct nvmem_device *nvmem)
+ EXPORT_SYMBOL_GPL(nvmem_device_put);
+
+ /**
+- * devm_nvmem_device_get() - Get nvmem cell of device form a given id
++ * devm_nvmem_device_get() - Get nvmem device of device form a given id
+ *
+ * @dev: Device that requests the nvmem device.
+ * @id: name id for the requested nvmem device.
+ *
+- * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_cell
+- * on success. The nvmem_cell will be freed by the automatically once the
++ * Return: ERR_PTR() on error or a valid pointer to a struct nvmem_device
++ * on success. The nvmem_device will be freed by the automatically once the
+ * device is freed.
+ */
+ struct nvmem_device *devm_nvmem_device_get(struct device *dev, const char *id)
+diff --git a/drivers/nvmem/u-boot-env.c b/drivers/nvmem/u-boot-env.c
+index befbab156cda1..adabbfdad6fb6 100644
+--- a/drivers/nvmem/u-boot-env.c
++++ b/drivers/nvmem/u-boot-env.c
+@@ -176,6 +176,13 @@ static int u_boot_env_parse(struct u_boot_env *priv)
+ data_offset = offsetof(struct u_boot_env_image_broadcom, data);
+ break;
+ }
++
++ if (dev_size < data_offset) {
++ dev_err(dev, "Device too small for u-boot-env\n");
++ err = -EIO;
++ goto err_kfree;
++ }
++
+ crc32_addr = (__le32 *)(buf + crc32_offset);
+ crc32 = le32_to_cpu(*crc32_addr);
+ crc32_data_len = dev_size - crc32_data_offset;
+diff --git a/drivers/of/irq.c b/drivers/of/irq.c
+index c94203ce65bb3..8fd63100ba8f0 100644
+--- a/drivers/of/irq.c
++++ b/drivers/of/irq.c
+@@ -344,7 +344,8 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
+ struct device_node *p;
+ const __be32 *addr;
+ u32 intsize;
+- int i, res;
++ int i, res, addr_len;
++ __be32 addr_buf[3] = { 0 };
+
+ pr_debug("of_irq_parse_one: dev=%pOF, index=%d\n", device, index);
+
+@@ -353,13 +354,19 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
+ return of_irq_parse_oldworld(device, index, out_irq);
+
+ /* Get the reg property (if any) */
+- addr = of_get_property(device, "reg", NULL);
++ addr = of_get_property(device, "reg", &addr_len);
++
++ /* Prevent out-of-bounds read in case of longer interrupt parent address size */
++ if (addr_len > (3 * sizeof(__be32)))
++ addr_len = 3 * sizeof(__be32);
++ if (addr)
++ memcpy(addr_buf, addr, addr_len);
+
+ /* Try the new-style interrupts-extended first */
+ res = of_parse_phandle_with_args(device, "interrupts-extended",
+ "#interrupt-cells", index, out_irq);
+ if (!res)
+- return of_irq_parse_raw(addr, out_irq);
++ return of_irq_parse_raw(addr_buf, out_irq);
+
+ /* Look for the interrupt parent. */
+ p = of_irq_find_parent(device);
+@@ -389,7 +396,7 @@ int of_irq_parse_one(struct device_node *device, int index, struct of_phandle_ar
+
+
+ /* Check if there are any interrupt-map translations to process */
+- res = of_irq_parse_raw(addr, out_irq);
++ res = of_irq_parse_raw(addr_buf, out_irq);
+ out:
+ of_node_put(p);
+ return res;
+diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
+index cd0e0022f91d6..483c954065135 100644
+--- a/drivers/pci/controller/dwc/pci-keystone.c
++++ b/drivers/pci/controller/dwc/pci-keystone.c
+@@ -34,6 +34,11 @@
+ #define PCIE_DEVICEID_SHIFT 16
+
+ /* Application registers */
++#define PID 0x000
++#define RTL GENMASK(15, 11)
++#define RTL_SHIFT 11
++#define AM6_PCI_PG1_RTL_VER 0x15
++
+ #define CMD_STATUS 0x004
+ #define LTSSM_EN_VAL BIT(0)
+ #define OB_XLAT_EN_VAL BIT(1)
+@@ -104,6 +109,8 @@
+
+ #define to_keystone_pcie(x) dev_get_drvdata((x)->dev)
+
++#define PCI_DEVICE_ID_TI_AM654X 0xb00c
++
+ struct ks_pcie_of_data {
+ enum dw_pcie_device_mode mode;
+ const struct dw_pcie_host_ops *host_ops;
+@@ -516,7 +523,11 @@ static int ks_pcie_start_link(struct dw_pcie *pci)
+ static void ks_pcie_quirk(struct pci_dev *dev)
+ {
+ struct pci_bus *bus = dev->bus;
++ struct keystone_pcie *ks_pcie;
++ struct device *bridge_dev;
+ struct pci_dev *bridge;
++ u32 val;
++
+ static const struct pci_device_id rc_pci_devids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_TI, PCIE_RC_K2HK),
+ .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
+@@ -528,6 +539,11 @@ static void ks_pcie_quirk(struct pci_dev *dev)
+ .class = PCI_CLASS_BRIDGE_PCI_NORMAL, .class_mask = ~0, },
+ { 0, },
+ };
++ static const struct pci_device_id am6_pci_devids[] = {
++ { PCI_DEVICE(PCI_VENDOR_ID_TI, PCI_DEVICE_ID_TI_AM654X),
++ .class = PCI_CLASS_BRIDGE_PCI << 8, .class_mask = ~0, },
++ { 0, },
++ };
+
+ if (pci_is_root_bus(bus))
+ bridge = dev;
+@@ -549,10 +565,36 @@ static void ks_pcie_quirk(struct pci_dev *dev)
+ */
+ if (pci_match_id(rc_pci_devids, bridge)) {
+ if (pcie_get_readrq(dev) > 256) {
+- dev_info(&dev->dev, "limiting MRRS to 256\n");
++ dev_info(&dev->dev, "limiting MRRS to 256 bytes\n");
+ pcie_set_readrq(dev, 256);
+ }
+ }
++
++ /*
++ * Memory transactions fail with PCI controller in AM654 PG1.0
++ * when MRRS is set to more than 128 bytes. Force the MRRS to
++ * 128 bytes in all downstream devices.
++ */
++ if (pci_match_id(am6_pci_devids, bridge)) {
++ bridge_dev = pci_get_host_bridge_device(dev);
++ if (!bridge_dev && !bridge_dev->parent)
++ return;
++
++ ks_pcie = dev_get_drvdata(bridge_dev->parent);
++ if (!ks_pcie)
++ return;
++
++ val = ks_pcie_app_readl(ks_pcie, PID);
++ val &= RTL;
++ val >>= RTL_SHIFT;
++ if (val != AM6_PCI_PG1_RTL_VER)
++ return;
++
++ if (pcie_get_readrq(dev) > 128) {
++ dev_info(&dev->dev, "limiting MRRS to 128 bytes\n");
++ pcie_set_readrq(dev, 128);
++ }
++ }
+ }
+ DECLARE_PCI_FIXUP_ENABLE(PCI_ANY_ID, PCI_ANY_ID, ks_pcie_quirk);
+
+diff --git a/drivers/pci/controller/dwc/pcie-qcom.c b/drivers/pci/controller/dwc/pcie-qcom.c
+index 14772edcf0d34..7fa1fe5a29e3d 100644
+--- a/drivers/pci/controller/dwc/pcie-qcom.c
++++ b/drivers/pci/controller/dwc/pcie-qcom.c
+@@ -51,6 +51,7 @@
+ #define PARF_SID_OFFSET 0x234
+ #define PARF_BDF_TRANSLATE_CFG 0x24c
+ #define PARF_SLV_ADDR_SPACE_SIZE 0x358
++#define PARF_NO_SNOOP_OVERIDE 0x3d4
+ #define PARF_DEVICE_TYPE 0x1000
+ #define PARF_BDF_TO_SID_TABLE_N 0x2000
+ #define PARF_BDF_TO_SID_CFG 0x2c00
+@@ -118,6 +119,10 @@
+ /* PARF_LTSSM register fields */
+ #define LTSSM_EN BIT(8)
+
++/* PARF_NO_SNOOP_OVERIDE register fields */
++#define WR_NO_SNOOP_OVERIDE_EN BIT(1)
++#define RD_NO_SNOOP_OVERIDE_EN BIT(3)
++
+ /* PARF_DEVICE_TYPE register fields */
+ #define DEVICE_TYPE_RC 0x4
+
+@@ -231,8 +236,15 @@ struct qcom_pcie_ops {
+ int (*config_sid)(struct qcom_pcie *pcie);
+ };
+
++ /**
++ * struct qcom_pcie_cfg - Per SoC config struct
++ * @ops: qcom PCIe ops structure
++ * @override_no_snoop: Override NO_SNOOP attribute in TLP to enable cache
++ * snooping
++ */
+ struct qcom_pcie_cfg {
+ const struct qcom_pcie_ops *ops;
++ bool override_no_snoop;
+ bool no_l0s;
+ };
+
+@@ -986,6 +998,12 @@ static int qcom_pcie_init_2_7_0(struct qcom_pcie *pcie)
+
+ static int qcom_pcie_post_init_2_7_0(struct qcom_pcie *pcie)
+ {
++ const struct qcom_pcie_cfg *pcie_cfg = pcie->cfg;
++
++ if (pcie_cfg->override_no_snoop)
++ writel(WR_NO_SNOOP_OVERIDE_EN | RD_NO_SNOOP_OVERIDE_EN,
++ pcie->parf + PARF_NO_SNOOP_OVERIDE);
++
+ qcom_pcie_clear_aspm_l0s(pcie->pci);
+ qcom_pcie_clear_hpc(pcie->pci);
+
+@@ -1366,6 +1384,11 @@ static const struct qcom_pcie_cfg cfg_1_9_0 = {
+ .ops = &ops_1_9_0,
+ };
+
++static const struct qcom_pcie_cfg cfg_1_34_0 = {
++ .ops = &ops_1_9_0,
++ .override_no_snoop = true,
++};
++
+ static const struct qcom_pcie_cfg cfg_2_1_0 = {
+ .ops = &ops_2_1_0,
+ };
+@@ -1667,7 +1690,7 @@ static const struct of_device_id qcom_pcie_match[] = {
+ { .compatible = "qcom,pcie-msm8996", .data = &cfg_2_3_2 },
+ { .compatible = "qcom,pcie-qcs404", .data = &cfg_2_4_0 },
+ { .compatible = "qcom,pcie-sa8540p", .data = &cfg_sc8280xp },
+- { .compatible = "qcom,pcie-sa8775p", .data = &cfg_1_9_0},
++ { .compatible = "qcom,pcie-sa8775p", .data = &cfg_1_34_0},
+ { .compatible = "qcom,pcie-sc7280", .data = &cfg_1_9_0 },
+ { .compatible = "qcom,pcie-sc8180x", .data = &cfg_1_9_0 },
+ { .compatible = "qcom,pcie-sc8280xp", .data = &cfg_sc8280xp },
+diff --git a/drivers/pci/hotplug/pnv_php.c b/drivers/pci/hotplug/pnv_php.c
+index 694349be9d0aa..573a41869c153 100644
+--- a/drivers/pci/hotplug/pnv_php.c
++++ b/drivers/pci/hotplug/pnv_php.c
+@@ -40,7 +40,6 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
+ bool disable_device)
+ {
+ struct pci_dev *pdev = php_slot->pdev;
+- int irq = php_slot->irq;
+ u16 ctrl;
+
+ if (php_slot->irq > 0) {
+@@ -59,7 +58,7 @@ static void pnv_php_disable_irq(struct pnv_php_slot *php_slot,
+ php_slot->wq = NULL;
+ }
+
+- if (disable_device || irq > 0) {
++ if (disable_device) {
+ if (pdev->msix_enabled)
+ pci_disable_msix(pdev);
+ else if (pdev->msi_enabled)
+diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
+index dff09e4892d39..8db214d4b1d46 100644
+--- a/drivers/pci/pci.c
++++ b/drivers/pci/pci.c
+@@ -5441,10 +5441,12 @@ static void pci_bus_lock(struct pci_bus *bus)
+ {
+ struct pci_dev *dev;
+
++ pci_dev_lock(bus->self);
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+- pci_dev_lock(dev);
+ if (dev->subordinate)
+ pci_bus_lock(dev->subordinate);
++ else
++ pci_dev_lock(dev);
+ }
+ }
+
+@@ -5456,8 +5458,10 @@ static void pci_bus_unlock(struct pci_bus *bus)
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+ if (dev->subordinate)
+ pci_bus_unlock(dev->subordinate);
+- pci_dev_unlock(dev);
++ else
++ pci_dev_unlock(dev);
+ }
++ pci_dev_unlock(bus->self);
+ }
+
+ /* Return 1 on successful lock, 0 on contention */
+@@ -5465,15 +5469,15 @@ static int pci_bus_trylock(struct pci_bus *bus)
+ {
+ struct pci_dev *dev;
+
++ if (!pci_dev_trylock(bus->self))
++ return 0;
++
+ list_for_each_entry(dev, &bus->devices, bus_list) {
+- if (!pci_dev_trylock(dev))
+- goto unlock;
+ if (dev->subordinate) {
+- if (!pci_bus_trylock(dev->subordinate)) {
+- pci_dev_unlock(dev);
++ if (!pci_bus_trylock(dev->subordinate))
+ goto unlock;
+- }
+- }
++ } else if (!pci_dev_trylock(dev))
++ goto unlock;
+ }
+ return 1;
+
+@@ -5481,8 +5485,10 @@ static int pci_bus_trylock(struct pci_bus *bus)
+ list_for_each_entry_continue_reverse(dev, &bus->devices, bus_list) {
+ if (dev->subordinate)
+ pci_bus_unlock(dev->subordinate);
+- pci_dev_unlock(dev);
++ else
++ pci_dev_unlock(dev);
+ }
++ pci_dev_unlock(bus->self);
+ return 0;
+ }
+
+@@ -5514,9 +5520,10 @@ static void pci_slot_lock(struct pci_slot *slot)
+ list_for_each_entry(dev, &slot->bus->devices, bus_list) {
+ if (!dev->slot || dev->slot != slot)
+ continue;
+- pci_dev_lock(dev);
+ if (dev->subordinate)
+ pci_bus_lock(dev->subordinate);
++ else
++ pci_dev_lock(dev);
+ }
+ }
+
+@@ -5542,14 +5549,13 @@ static int pci_slot_trylock(struct pci_slot *slot)
+ list_for_each_entry(dev, &slot->bus->devices, bus_list) {
+ if (!dev->slot || dev->slot != slot)
+ continue;
+- if (!pci_dev_trylock(dev))
+- goto unlock;
+ if (dev->subordinate) {
+ if (!pci_bus_trylock(dev->subordinate)) {
+ pci_dev_unlock(dev);
+ goto unlock;
+ }
+- }
++ } else if (!pci_dev_trylock(dev))
++ goto unlock;
+ }
+ return 1;
+
+@@ -5560,7 +5566,8 @@ static int pci_slot_trylock(struct pci_slot *slot)
+ continue;
+ if (dev->subordinate)
+ pci_bus_unlock(dev->subordinate);
+- pci_dev_unlock(dev);
++ else
++ pci_dev_unlock(dev);
+ }
+ return 0;
+ }
+diff --git a/drivers/pcmcia/yenta_socket.c b/drivers/pcmcia/yenta_socket.c
+index 1365eaa20ff49..ff169124929cc 100644
+--- a/drivers/pcmcia/yenta_socket.c
++++ b/drivers/pcmcia/yenta_socket.c
+@@ -638,11 +638,11 @@ static int yenta_search_one_res(struct resource *root, struct resource *res,
+ start = PCIBIOS_MIN_CARDBUS_IO;
+ end = ~0U;
+ } else {
+- unsigned long avail = root->end - root->start;
++ unsigned long avail = resource_size(root);
+ int i;
+ size = BRIDGE_MEM_MAX;
+- if (size > avail/8) {
+- size = (avail+1)/8;
++ if (size > (avail - 1) / 8) {
++ size = avail / 8;
+ /* round size down to next power of 2 */
+ i = 0;
+ while ((size /= 2) != 0)
+diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c
+index d7d12cf3011a2..9cf0007cfd647 100644
+--- a/drivers/phy/xilinx/phy-zynqmp.c
++++ b/drivers/phy/xilinx/phy-zynqmp.c
+@@ -846,6 +846,7 @@ static struct phy *xpsgtr_xlate(struct device *dev,
+ phy_type = args->args[1];
+ phy_instance = args->args[2];
+
++ guard(mutex)(>r_phy->phy->mutex);
+ ret = xpsgtr_set_lane_type(gtr_phy, phy_type, phy_instance);
+ if (ret < 0) {
+ dev_err(gtr_dev->dev, "Invalid PHY type and/or instance\n");
+diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+index 65ed933f05ce1..abfcdd3da9e82 100644
+--- a/drivers/pinctrl/qcom/pinctrl-x1e80100.c
++++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+@@ -1839,7 +1839,9 @@ static const struct msm_pinctrl_soc_data x1e80100_pinctrl = {
+ .ngroups = ARRAY_SIZE(x1e80100_groups),
+ .ngpios = 239,
+ .wakeirq_map = x1e80100_pdc_map,
+- .nwakeirq_map = ARRAY_SIZE(x1e80100_pdc_map),
++ /* TODO: Enabling PDC currently breaks GPIO interrupts */
++ .nwakeirq_map = 0,
++ /* .nwakeirq_map = ARRAY_SIZE(x1e80100_pdc_map), */
+ .egpio_func = 9,
+ };
+
+diff --git a/drivers/platform/x86/dell/dell-smbios-base.c b/drivers/platform/x86/dell/dell-smbios-base.c
+index b562ed99ec4e7..4702669dbb605 100644
+--- a/drivers/platform/x86/dell/dell-smbios-base.c
++++ b/drivers/platform/x86/dell/dell-smbios-base.c
+@@ -587,7 +587,10 @@ static int __init dell_smbios_init(void)
+ return 0;
+
+ fail_sysfs:
+- free_group(platform_device);
++ if (!wmi)
++ exit_dell_smbios_wmi();
++ if (!smm)
++ exit_dell_smbios_smm();
+
+ fail_create_group:
+ platform_device_del(platform_device);
+diff --git a/drivers/ptp/ptp_ocp.c b/drivers/ptp/ptp_ocp.c
+index ee2ced88ab34f..e7479b9b90cb1 100644
+--- a/drivers/ptp/ptp_ocp.c
++++ b/drivers/ptp/ptp_ocp.c
+@@ -316,6 +316,15 @@ struct ptp_ocp_serial_port {
+ #define OCP_SERIAL_LEN 6
+ #define OCP_SMA_NUM 4
+
++enum {
++ PORT_GNSS,
++ PORT_GNSS2,
++ PORT_MAC, /* miniature atomic clock */
++ PORT_NMEA,
++
++ __PORT_COUNT,
++};
++
+ struct ptp_ocp {
+ struct pci_dev *pdev;
+ struct device dev;
+@@ -357,10 +366,7 @@ struct ptp_ocp {
+ struct delayed_work sync_work;
+ int id;
+ int n_irqs;
+- struct ptp_ocp_serial_port gnss_port;
+- struct ptp_ocp_serial_port gnss2_port;
+- struct ptp_ocp_serial_port mac_port; /* miniature atomic clock */
+- struct ptp_ocp_serial_port nmea_port;
++ struct ptp_ocp_serial_port port[__PORT_COUNT];
+ bool fw_loader;
+ u8 fw_tag;
+ u16 fw_version;
+@@ -655,28 +661,28 @@ static struct ocp_resource ocp_fb_resource[] = {
+ },
+ },
+ {
+- OCP_SERIAL_RESOURCE(gnss_port),
++ OCP_SERIAL_RESOURCE(port[PORT_GNSS]),
+ .offset = 0x00160000 + 0x1000, .irq_vec = 3,
+ .extra = &(struct ptp_ocp_serial_port) {
+ .baud = 115200,
+ },
+ },
+ {
+- OCP_SERIAL_RESOURCE(gnss2_port),
++ OCP_SERIAL_RESOURCE(port[PORT_GNSS2]),
+ .offset = 0x00170000 + 0x1000, .irq_vec = 4,
+ .extra = &(struct ptp_ocp_serial_port) {
+ .baud = 115200,
+ },
+ },
+ {
+- OCP_SERIAL_RESOURCE(mac_port),
++ OCP_SERIAL_RESOURCE(port[PORT_MAC]),
+ .offset = 0x00180000 + 0x1000, .irq_vec = 5,
+ .extra = &(struct ptp_ocp_serial_port) {
+ .baud = 57600,
+ },
+ },
+ {
+- OCP_SERIAL_RESOURCE(nmea_port),
++ OCP_SERIAL_RESOURCE(port[PORT_NMEA]),
+ .offset = 0x00190000 + 0x1000, .irq_vec = 10,
+ },
+ {
+@@ -740,7 +746,7 @@ static struct ocp_resource ocp_art_resource[] = {
+ .offset = 0x01000000, .size = 0x10000,
+ },
+ {
+- OCP_SERIAL_RESOURCE(gnss_port),
++ OCP_SERIAL_RESOURCE(port[PORT_GNSS]),
+ .offset = 0x00160000 + 0x1000, .irq_vec = 3,
+ .extra = &(struct ptp_ocp_serial_port) {
+ .baud = 115200,
+@@ -839,7 +845,7 @@ static struct ocp_resource ocp_art_resource[] = {
+ },
+ },
+ {
+- OCP_SERIAL_RESOURCE(mac_port),
++ OCP_SERIAL_RESOURCE(port[PORT_MAC]),
+ .offset = 0x00190000, .irq_vec = 7,
+ .extra = &(struct ptp_ocp_serial_port) {
+ .baud = 9600,
+@@ -950,14 +956,14 @@ static struct ocp_resource ocp_adva_resource[] = {
+ .offset = 0x00220000, .size = 0x1000,
+ },
+ {
+- OCP_SERIAL_RESOURCE(gnss_port),
++ OCP_SERIAL_RESOURCE(port[PORT_GNSS]),
+ .offset = 0x00160000 + 0x1000, .irq_vec = 3,
+ .extra = &(struct ptp_ocp_serial_port) {
+ .baud = 9600,
+ },
+ },
+ {
+- OCP_SERIAL_RESOURCE(mac_port),
++ OCP_SERIAL_RESOURCE(port[PORT_MAC]),
+ .offset = 0x00180000 + 0x1000, .irq_vec = 5,
+ .extra = &(struct ptp_ocp_serial_port) {
+ .baud = 115200,
+@@ -1649,6 +1655,15 @@ ptp_ocp_tod_gnss_name(int idx)
+ return gnss_name[idx];
+ }
+
++static const char *
++ptp_ocp_tty_port_name(int idx)
++{
++ static const char * const tty_name[] = {
++ "GNSS", "GNSS2", "MAC", "NMEA"
++ };
++ return tty_name[idx];
++}
++
+ struct ptp_ocp_nvmem_match_info {
+ struct ptp_ocp *bp;
+ const void * const tag;
+@@ -3346,6 +3361,54 @@ static EXT_ATTR_RO(freq, frequency, 1);
+ static EXT_ATTR_RO(freq, frequency, 2);
+ static EXT_ATTR_RO(freq, frequency, 3);
+
++static ssize_t
++ptp_ocp_tty_show(struct device *dev, struct device_attribute *attr, char *buf)
++{
++ struct dev_ext_attribute *ea = to_ext_attr(attr);
++ struct ptp_ocp *bp = dev_get_drvdata(dev);
++
++ return sysfs_emit(buf, "ttyS%d", bp->port[(uintptr_t)ea->var].line);
++}
++
++static umode_t
++ptp_ocp_timecard_tty_is_visible(struct kobject *kobj, struct attribute *attr, int n)
++{
++ struct ptp_ocp *bp = dev_get_drvdata(kobj_to_dev(kobj));
++ struct ptp_ocp_serial_port *port;
++ struct device_attribute *dattr;
++ struct dev_ext_attribute *ea;
++
++ if (strncmp(attr->name, "tty", 3))
++ return attr->mode;
++
++ dattr = container_of(attr, struct device_attribute, attr);
++ ea = container_of(dattr, struct dev_ext_attribute, attr);
++ port = &bp->port[(uintptr_t)ea->var];
++ return port->line == -1 ? 0 : 0444;
++}
++
++#define EXT_TTY_ATTR_RO(_name, _val) \
++ struct dev_ext_attribute dev_attr_tty##_name = \
++ { __ATTR(tty##_name, 0444, ptp_ocp_tty_show, NULL), (void *)_val }
++
++static EXT_TTY_ATTR_RO(GNSS, PORT_GNSS);
++static EXT_TTY_ATTR_RO(GNSS2, PORT_GNSS2);
++static EXT_TTY_ATTR_RO(MAC, PORT_MAC);
++static EXT_TTY_ATTR_RO(NMEA, PORT_NMEA);
++static struct attribute *ptp_ocp_timecard_tty_attrs[] = {
++ &dev_attr_ttyGNSS.attr.attr,
++ &dev_attr_ttyGNSS2.attr.attr,
++ &dev_attr_ttyMAC.attr.attr,
++ &dev_attr_ttyNMEA.attr.attr,
++ NULL,
++};
++
++static const struct attribute_group ptp_ocp_timecard_tty_group = {
++ .name = "tty",
++ .attrs = ptp_ocp_timecard_tty_attrs,
++ .is_visible = ptp_ocp_timecard_tty_is_visible,
++};
++
+ static ssize_t
+ serialnum_show(struct device *dev, struct device_attribute *attr, char *buf)
+ {
+@@ -3775,6 +3838,7 @@ static const struct attribute_group fb_timecard_group = {
+
+ static const struct ocp_attr_group fb_timecard_groups[] = {
+ { .cap = OCP_CAP_BASIC, .group = &fb_timecard_group },
++ { .cap = OCP_CAP_BASIC, .group = &ptp_ocp_timecard_tty_group },
+ { .cap = OCP_CAP_SIGNAL, .group = &fb_timecard_signal0_group },
+ { .cap = OCP_CAP_SIGNAL, .group = &fb_timecard_signal1_group },
+ { .cap = OCP_CAP_SIGNAL, .group = &fb_timecard_signal2_group },
+@@ -3814,6 +3878,7 @@ static const struct attribute_group art_timecard_group = {
+
+ static const struct ocp_attr_group art_timecard_groups[] = {
+ { .cap = OCP_CAP_BASIC, .group = &art_timecard_group },
++ { .cap = OCP_CAP_BASIC, .group = &ptp_ocp_timecard_tty_group },
+ { },
+ };
+
+@@ -3841,6 +3906,7 @@ static const struct attribute_group adva_timecard_group = {
+
+ static const struct ocp_attr_group adva_timecard_groups[] = {
+ { .cap = OCP_CAP_BASIC, .group = &adva_timecard_group },
++ { .cap = OCP_CAP_BASIC, .group = &ptp_ocp_timecard_tty_group },
+ { .cap = OCP_CAP_SIGNAL, .group = &fb_timecard_signal0_group },
+ { .cap = OCP_CAP_SIGNAL, .group = &fb_timecard_signal1_group },
+ { .cap = OCP_CAP_FREQ, .group = &fb_timecard_freq0_group },
+@@ -3960,16 +4026,11 @@ ptp_ocp_summary_show(struct seq_file *s, void *data)
+ bp = dev_get_drvdata(dev);
+
+ seq_printf(s, "%7s: /dev/ptp%d\n", "PTP", ptp_clock_index(bp->ptp));
+- if (bp->gnss_port.line != -1)
+- seq_printf(s, "%7s: /dev/ttyS%d\n", "GNSS1",
+- bp->gnss_port.line);
+- if (bp->gnss2_port.line != -1)
+- seq_printf(s, "%7s: /dev/ttyS%d\n", "GNSS2",
+- bp->gnss2_port.line);
+- if (bp->mac_port.line != -1)
+- seq_printf(s, "%7s: /dev/ttyS%d\n", "MAC", bp->mac_port.line);
+- if (bp->nmea_port.line != -1)
+- seq_printf(s, "%7s: /dev/ttyS%d\n", "NMEA", bp->nmea_port.line);
++ for (i = 0; i < __PORT_COUNT; i++) {
++ if (bp->port[i].line != -1)
++ seq_printf(s, "%7s: /dev/ttyS%d\n", ptp_ocp_tty_port_name(i),
++ bp->port[i].line);
++ }
+
+ memset(sma_val, 0xff, sizeof(sma_val));
+ if (bp->sma_map1) {
+@@ -4279,7 +4340,7 @@ ptp_ocp_dev_release(struct device *dev)
+ static int
+ ptp_ocp_device_init(struct ptp_ocp *bp, struct pci_dev *pdev)
+ {
+- int err;
++ int i, err;
+
+ mutex_lock(&ptp_ocp_lock);
+ err = idr_alloc(&ptp_ocp_idr, bp, 0, 0, GFP_KERNEL);
+@@ -4292,10 +4353,10 @@ ptp_ocp_device_init(struct ptp_ocp *bp, struct pci_dev *pdev)
+
+ bp->ptp_info = ptp_ocp_clock_info;
+ spin_lock_init(&bp->lock);
+- bp->gnss_port.line = -1;
+- bp->gnss2_port.line = -1;
+- bp->mac_port.line = -1;
+- bp->nmea_port.line = -1;
++
++ for (i = 0; i < __PORT_COUNT; i++)
++ bp->port[i].line = -1;
++
+ bp->pdev = pdev;
+
+ device_initialize(&bp->dev);
+@@ -4352,22 +4413,6 @@ ptp_ocp_complete(struct ptp_ocp *bp)
+ struct pps_device *pps;
+ char buf[32];
+
+- if (bp->gnss_port.line != -1) {
+- sprintf(buf, "ttyS%d", bp->gnss_port.line);
+- ptp_ocp_link_child(bp, buf, "ttyGNSS");
+- }
+- if (bp->gnss2_port.line != -1) {
+- sprintf(buf, "ttyS%d", bp->gnss2_port.line);
+- ptp_ocp_link_child(bp, buf, "ttyGNSS2");
+- }
+- if (bp->mac_port.line != -1) {
+- sprintf(buf, "ttyS%d", bp->mac_port.line);
+- ptp_ocp_link_child(bp, buf, "ttyMAC");
+- }
+- if (bp->nmea_port.line != -1) {
+- sprintf(buf, "ttyS%d", bp->nmea_port.line);
+- ptp_ocp_link_child(bp, buf, "ttyNMEA");
+- }
+ sprintf(buf, "ptp%d", ptp_clock_index(bp->ptp));
+ ptp_ocp_link_child(bp, buf, "ptp");
+
+@@ -4416,23 +4461,20 @@ ptp_ocp_info(struct ptp_ocp *bp)
+ };
+ struct device *dev = &bp->pdev->dev;
+ u32 reg;
++ int i;
+
+ ptp_ocp_phc_info(bp);
+
+- ptp_ocp_serial_info(dev, "GNSS", bp->gnss_port.line,
+- bp->gnss_port.baud);
+- ptp_ocp_serial_info(dev, "GNSS2", bp->gnss2_port.line,
+- bp->gnss2_port.baud);
+- ptp_ocp_serial_info(dev, "MAC", bp->mac_port.line, bp->mac_port.baud);
+- if (bp->nmea_out && bp->nmea_port.line != -1) {
+- bp->nmea_port.baud = -1;
++ for (i = 0; i < __PORT_COUNT; i++) {
++ if (i == PORT_NMEA && bp->nmea_out && bp->port[PORT_NMEA].line != -1) {
++ bp->port[PORT_NMEA].baud = -1;
+
+- reg = ioread32(&bp->nmea_out->uart_baud);
+- if (reg < ARRAY_SIZE(nmea_baud))
+- bp->nmea_port.baud = nmea_baud[reg];
+-
+- ptp_ocp_serial_info(dev, "NMEA", bp->nmea_port.line,
+- bp->nmea_port.baud);
++ reg = ioread32(&bp->nmea_out->uart_baud);
++ if (reg < ARRAY_SIZE(nmea_baud))
++ bp->port[PORT_NMEA].baud = nmea_baud[reg];
++ }
++ ptp_ocp_serial_info(dev, ptp_ocp_tty_port_name(i), bp->port[i].line,
++ bp->port[i].baud);
+ }
+ }
+
+@@ -4441,9 +4483,6 @@ ptp_ocp_detach_sysfs(struct ptp_ocp *bp)
+ {
+ struct device *dev = &bp->dev;
+
+- sysfs_remove_link(&dev->kobj, "ttyGNSS");
+- sysfs_remove_link(&dev->kobj, "ttyGNSS2");
+- sysfs_remove_link(&dev->kobj, "ttyMAC");
+ sysfs_remove_link(&dev->kobj, "ptp");
+ sysfs_remove_link(&dev->kobj, "pps");
+ }
+@@ -4473,14 +4512,9 @@ ptp_ocp_detach(struct ptp_ocp *bp)
+ for (i = 0; i < 4; i++)
+ if (bp->signal_out[i])
+ ptp_ocp_unregister_ext(bp->signal_out[i]);
+- if (bp->gnss_port.line != -1)
+- serial8250_unregister_port(bp->gnss_port.line);
+- if (bp->gnss2_port.line != -1)
+- serial8250_unregister_port(bp->gnss2_port.line);
+- if (bp->mac_port.line != -1)
+- serial8250_unregister_port(bp->mac_port.line);
+- if (bp->nmea_port.line != -1)
+- serial8250_unregister_port(bp->nmea_port.line);
++ for (i = 0; i < __PORT_COUNT; i++)
++ if (bp->port[i].line != -1)
++ serial8250_unregister_port(bp->port[i].line);
+ platform_device_unregister(bp->spi_flash);
+ platform_device_unregister(bp->i2c_ctrl);
+ if (bp->i2c_clk)
+diff --git a/drivers/scsi/lpfc/lpfc_els.c b/drivers/scsi/lpfc/lpfc_els.c
+index c32bc773ab29d..445cb6c2e80f5 100644
+--- a/drivers/scsi/lpfc/lpfc_els.c
++++ b/drivers/scsi/lpfc/lpfc_els.c
+@@ -7302,13 +7302,13 @@ int lpfc_get_sfp_info_wait(struct lpfc_hba *phba,
+ mbox->u.mqe.un.mem_dump_type3.addr_hi = putPaddrHigh(mp->phys);
+ }
+ mbox->vport = phba->pport;
+-
+- rc = lpfc_sli_issue_mbox_wait(phba, mbox, 30);
++ rc = lpfc_sli_issue_mbox_wait(phba, mbox, LPFC_MBOX_SLI4_CONFIG_TMO);
+ if (rc == MBX_NOT_FINISHED) {
+ rc = 1;
+ goto error;
+ }
+-
++ if (rc == MBX_TIMEOUT)
++ goto error;
+ if (phba->sli_rev == LPFC_SLI_REV4)
+ mp = mbox->ctx_buf;
+ else
+@@ -7361,7 +7361,10 @@ int lpfc_get_sfp_info_wait(struct lpfc_hba *phba,
+ mbox->u.mqe.un.mem_dump_type3.addr_hi = putPaddrHigh(mp->phys);
+ }
+
+- rc = lpfc_sli_issue_mbox_wait(phba, mbox, 30);
++ rc = lpfc_sli_issue_mbox_wait(phba, mbox, LPFC_MBOX_SLI4_CONFIG_TMO);
++
++ if (rc == MBX_TIMEOUT)
++ goto error;
+ if (bf_get(lpfc_mqe_status, &mbox->u.mqe)) {
+ rc = 1;
+ goto error;
+@@ -7372,8 +7375,10 @@ int lpfc_get_sfp_info_wait(struct lpfc_hba *phba,
+ DMP_SFF_PAGE_A2_SIZE);
+
+ error:
+- mbox->ctx_buf = mpsave;
+- lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
++ if (mbox->mbox_flag & LPFC_MBX_WAKE) {
++ mbox->ctx_buf = mpsave;
++ lpfc_mbox_rsrc_cleanup(phba, mbox, MBOX_THD_UNLOCKED);
++ }
+
+ return rc;
+
+diff --git a/drivers/scsi/pm8001/pm8001_sas.c b/drivers/scsi/pm8001/pm8001_sas.c
+index a5a31dfa45122..ee2da8e49d4cf 100644
+--- a/drivers/scsi/pm8001/pm8001_sas.c
++++ b/drivers/scsi/pm8001/pm8001_sas.c
+@@ -166,7 +166,6 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func,
+ unsigned long flags;
+ pm8001_ha = sas_phy->ha->lldd_ha;
+ phy = &pm8001_ha->phy[phy_id];
+- pm8001_ha->phy[phy_id].enable_completion = &completion;
+
+ if (PM8001_CHIP_DISP->fatal_errors(pm8001_ha)) {
+ /*
+@@ -190,6 +189,7 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func,
+ rates->maximum_linkrate;
+ }
+ if (pm8001_ha->phy[phy_id].phy_state == PHY_LINK_DISABLE) {
++ pm8001_ha->phy[phy_id].enable_completion = &completion;
+ PM8001_CHIP_DISP->phy_start_req(pm8001_ha, phy_id);
+ wait_for_completion(&completion);
+ }
+@@ -198,6 +198,7 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func,
+ break;
+ case PHY_FUNC_HARD_RESET:
+ if (pm8001_ha->phy[phy_id].phy_state == PHY_LINK_DISABLE) {
++ pm8001_ha->phy[phy_id].enable_completion = &completion;
+ PM8001_CHIP_DISP->phy_start_req(pm8001_ha, phy_id);
+ wait_for_completion(&completion);
+ }
+@@ -206,6 +207,7 @@ int pm8001_phy_control(struct asd_sas_phy *sas_phy, enum phy_func func,
+ break;
+ case PHY_FUNC_LINK_RESET:
+ if (pm8001_ha->phy[phy_id].phy_state == PHY_LINK_DISABLE) {
++ pm8001_ha->phy[phy_id].enable_completion = &completion;
+ PM8001_CHIP_DISP->phy_start_req(pm8001_ha, phy_id);
+ wait_for_completion(&completion);
+ }
+diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
+index f2d7eedd324b7..d2f603e1014cf 100644
+--- a/drivers/spi/spi-fsl-lpspi.c
++++ b/drivers/spi/spi-fsl-lpspi.c
+@@ -82,6 +82,10 @@
+ #define TCR_RXMSK BIT(19)
+ #define TCR_TXMSK BIT(18)
+
++struct fsl_lpspi_devtype_data {
++ u8 prescale_max;
++};
++
+ struct lpspi_config {
+ u8 bpw;
+ u8 chip_select;
+@@ -119,10 +123,25 @@ struct fsl_lpspi_data {
+ bool usedma;
+ struct completion dma_rx_completion;
+ struct completion dma_tx_completion;
++
++ const struct fsl_lpspi_devtype_data *devtype_data;
++};
++
++/*
++ * ERR051608 fixed or not:
++ * https://www.nxp.com/docs/en/errata/i.MX93_1P87f.pdf
++ */
++static struct fsl_lpspi_devtype_data imx93_lpspi_devtype_data = {
++ .prescale_max = 1,
++};
++
++static struct fsl_lpspi_devtype_data imx7ulp_lpspi_devtype_data = {
++ .prescale_max = 7,
+ };
+
+ static const struct of_device_id fsl_lpspi_dt_ids[] = {
+- { .compatible = "fsl,imx7ulp-spi", },
++ { .compatible = "fsl,imx7ulp-spi", .data = &imx7ulp_lpspi_devtype_data,},
++ { .compatible = "fsl,imx93-spi", .data = &imx93_lpspi_devtype_data,},
+ { /* sentinel */ }
+ };
+ MODULE_DEVICE_TABLE(of, fsl_lpspi_dt_ids);
+@@ -297,9 +316,11 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
+ {
+ struct lpspi_config config = fsl_lpspi->config;
+ unsigned int perclk_rate, scldiv, div;
++ u8 prescale_max;
+ u8 prescale;
+
+ perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
++ prescale_max = fsl_lpspi->devtype_data->prescale_max;
+
+ if (!config.speed_hz) {
+ dev_err(fsl_lpspi->dev,
+@@ -315,7 +336,7 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
+
+ div = DIV_ROUND_UP(perclk_rate, config.speed_hz);
+
+- for (prescale = 0; prescale < 8; prescale++) {
++ for (prescale = 0; prescale <= prescale_max; prescale++) {
+ scldiv = div / (1 << prescale) - 2;
+ if (scldiv < 256) {
+ fsl_lpspi->config.prescale = prescale;
+@@ -822,6 +843,7 @@ static int fsl_lpspi_init_rpm(struct fsl_lpspi_data *fsl_lpspi)
+
+ static int fsl_lpspi_probe(struct platform_device *pdev)
+ {
++ const struct fsl_lpspi_devtype_data *devtype_data;
+ struct fsl_lpspi_data *fsl_lpspi;
+ struct spi_controller *controller;
+ struct resource *res;
+@@ -830,6 +852,10 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
+ u32 temp;
+ bool is_target;
+
++ devtype_data = of_device_get_match_data(&pdev->dev);
++ if (!devtype_data)
++ return -ENODEV;
++
+ is_target = of_property_read_bool((&pdev->dev)->of_node, "spi-slave");
+ if (is_target)
+ controller = devm_spi_alloc_target(&pdev->dev,
+@@ -848,6 +874,7 @@ static int fsl_lpspi_probe(struct platform_device *pdev)
+ fsl_lpspi->is_target = is_target;
+ fsl_lpspi->is_only_cs1 = of_property_read_bool((&pdev->dev)->of_node,
+ "fsl,spi-only-use-cs1-sel");
++ fsl_lpspi->devtype_data = devtype_data;
+
+ init_completion(&fsl_lpspi->xfer_done);
+
+diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c
+index 6910b4d4c427b..16054695bdb04 100644
+--- a/drivers/spi/spi-hisi-kunpeng.c
++++ b/drivers/spi/spi-hisi-kunpeng.c
+@@ -481,6 +481,9 @@ static int hisi_spi_probe(struct platform_device *pdev)
+ return -EINVAL;
+ }
+
++ if (host->max_speed_hz == 0)
++ return dev_err_probe(dev, -EINVAL, "spi-max-frequency can't be 0\n");
++
+ ret = device_property_read_u16(dev, "num-cs",
+ &host->num_chipselect);
+ if (ret)
+diff --git a/drivers/spi/spi-intel.c b/drivers/spi/spi-intel.c
+index 3e5dcf2b3c8a1..795b7e72baead 100644
+--- a/drivers/spi/spi-intel.c
++++ b/drivers/spi/spi-intel.c
+@@ -1390,6 +1390,9 @@ static int intel_spi_populate_chip(struct intel_spi *ispi)
+
+ pdata->name = devm_kasprintf(ispi->dev, GFP_KERNEL, "%s-chip1",
+ dev_name(ispi->dev));
++ if (!pdata->name)
++ return -ENOMEM;
++
+ pdata->nr_parts = 1;
+ parts = devm_kcalloc(ispi->dev, pdata->nr_parts, sizeof(*parts),
+ GFP_KERNEL);
+diff --git a/drivers/spi/spi-rockchip.c b/drivers/spi/spi-rockchip.c
+index e1ecd96c78581..0bb33c43b1b46 100644
+--- a/drivers/spi/spi-rockchip.c
++++ b/drivers/spi/spi-rockchip.c
+@@ -945,14 +945,16 @@ static int rockchip_spi_suspend(struct device *dev)
+ {
+ int ret;
+ struct spi_controller *ctlr = dev_get_drvdata(dev);
+- struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
+
+ ret = spi_controller_suspend(ctlr);
+ if (ret < 0)
+ return ret;
+
+- clk_disable_unprepare(rs->spiclk);
+- clk_disable_unprepare(rs->apb_pclk);
++ ret = pm_runtime_force_suspend(dev);
++ if (ret < 0) {
++ spi_controller_resume(ctlr);
++ return ret;
++ }
+
+ pinctrl_pm_select_sleep_state(dev);
+
+@@ -963,25 +965,14 @@ static int rockchip_spi_resume(struct device *dev)
+ {
+ int ret;
+ struct spi_controller *ctlr = dev_get_drvdata(dev);
+- struct rockchip_spi *rs = spi_controller_get_devdata(ctlr);
+
+ pinctrl_pm_select_default_state(dev);
+
+- ret = clk_prepare_enable(rs->apb_pclk);
++ ret = pm_runtime_force_resume(dev);
+ if (ret < 0)
+ return ret;
+
+- ret = clk_prepare_enable(rs->spiclk);
+- if (ret < 0)
+- clk_disable_unprepare(rs->apb_pclk);
+-
+- ret = spi_controller_resume(ctlr);
+- if (ret < 0) {
+- clk_disable_unprepare(rs->spiclk);
+- clk_disable_unprepare(rs->apb_pclk);
+- }
+-
+- return 0;
++ return spi_controller_resume(ctlr);
+ }
+ #endif /* CONFIG_PM_SLEEP */
+
+diff --git a/drivers/staging/iio/frequency/ad9834.c b/drivers/staging/iio/frequency/ad9834.c
+index a7a5cdcc65903..47e7d7e6d9208 100644
+--- a/drivers/staging/iio/frequency/ad9834.c
++++ b/drivers/staging/iio/frequency/ad9834.c
+@@ -114,7 +114,7 @@ static int ad9834_write_frequency(struct ad9834_state *st,
+
+ clk_freq = clk_get_rate(st->mclk);
+
+- if (fout > (clk_freq / 2))
++ if (!clk_freq || fout > (clk_freq / 2))
+ return -EINVAL;
+
+ regval = ad9834_calc_freqreg(clk_freq, fout);
+diff --git a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+index df3af821f2187..fb1907414cc14 100644
+--- a/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
++++ b/drivers/staging/vc04_services/interface/vchiq_arm/vchiq_core.c
+@@ -501,16 +501,21 @@ remote_event_create(wait_queue_head_t *wq, struct remote_event *event)
+ * routines where switched to the "interruptible" family of functions, as the
+ * former was deemed unjustified and the use "killable" set all VCHIQ's
+ * threads in D state.
++ *
++ * Returns: 0 on success, a negative error code on failure
+ */
+ static inline int
+ remote_event_wait(wait_queue_head_t *wq, struct remote_event *event)
+ {
++ int ret = 0;
++
+ if (!event->fired) {
+ event->armed = 1;
+ dsb(sy);
+- if (wait_event_interruptible(*wq, event->fired)) {
++ ret = wait_event_interruptible(*wq, event->fired);
++ if (ret) {
+ event->armed = 0;
+- return 0;
++ return ret;
+ }
+ event->armed = 0;
+ /* Ensure that the peer sees that we are not waiting (armed == 0). */
+@@ -518,7 +523,7 @@ remote_event_wait(wait_queue_head_t *wq, struct remote_event *event)
+ }
+
+ event->fired = 0;
+- return 1;
++ return ret;
+ }
+
+ /*
+@@ -1140,6 +1145,7 @@ queue_message_sync(struct vchiq_state *state, struct vchiq_service *service,
+ struct vchiq_header *header;
+ ssize_t callback_result;
+ int svc_fourcc;
++ int ret;
+
+ local = state->local;
+
+@@ -1147,7 +1153,9 @@ queue_message_sync(struct vchiq_state *state, struct vchiq_service *service,
+ mutex_lock_killable(&state->sync_mutex))
+ return -EAGAIN;
+
+- remote_event_wait(&state->sync_release_event, &local->sync_release);
++ ret = remote_event_wait(&state->sync_release_event, &local->sync_release);
++ if (ret)
++ return ret;
+
+ /* Ensure that reads don't overtake the remote_event_wait. */
+ rmb();
+@@ -1929,13 +1937,16 @@ slot_handler_func(void *v)
+ {
+ struct vchiq_state *state = v;
+ struct vchiq_shared_state *local = state->local;
++ int ret;
+
+ DEBUG_INITIALISE(local);
+
+ while (1) {
+ DEBUG_COUNT(SLOT_HANDLER_COUNT);
+ DEBUG_TRACE(SLOT_HANDLER_LINE);
+- remote_event_wait(&state->trigger_event, &local->trigger);
++ ret = remote_event_wait(&state->trigger_event, &local->trigger);
++ if (ret)
++ return ret;
+
+ /* Ensure that reads don't overtake the remote_event_wait. */
+ rmb();
+@@ -1966,6 +1977,7 @@ recycle_func(void *v)
+ struct vchiq_shared_state *local = state->local;
+ u32 *found;
+ size_t length;
++ int ret;
+
+ length = sizeof(*found) * BITSET_SIZE(VCHIQ_MAX_SERVICES);
+
+@@ -1975,7 +1987,9 @@ recycle_func(void *v)
+ return -ENOMEM;
+
+ while (1) {
+- remote_event_wait(&state->recycle_event, &local->recycle);
++ ret = remote_event_wait(&state->recycle_event, &local->recycle);
++ if (ret)
++ return ret;
+
+ process_free_queue(state, found, length);
+ }
+@@ -1992,6 +2006,7 @@ sync_func(void *v)
+ (struct vchiq_header *)SLOT_DATA_FROM_INDEX(state,
+ state->remote->slot_sync);
+ int svc_fourcc;
++ int ret;
+
+ while (1) {
+ struct vchiq_service *service;
+@@ -1999,7 +2014,9 @@ sync_func(void *v)
+ int type;
+ unsigned int localport, remoteport;
+
+- remote_event_wait(&state->sync_trigger_event, &local->sync_trigger);
++ ret = remote_event_wait(&state->sync_trigger_event, &local->sync_trigger);
++ if (ret)
++ return ret;
+
+ /* Ensure that reads don't overtake the remote_event_wait. */
+ rmb();
+diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
+index 91bfdc17eedb3..b9c436a002a1b 100644
+--- a/drivers/ufs/core/ufshcd.c
++++ b/drivers/ufs/core/ufshcd.c
+@@ -10196,7 +10196,8 @@ void ufshcd_remove(struct ufs_hba *hba)
+ blk_mq_destroy_queue(hba->tmf_queue);
+ blk_put_queue(hba->tmf_queue);
+ blk_mq_free_tag_set(&hba->tmf_tag_set);
+- scsi_remove_host(hba->host);
++ if (hba->scsi_host_added)
++ scsi_remove_host(hba->host);
+ /* disable interrupts */
+ ufshcd_disable_intr(hba, hba->intr_mask);
+ ufshcd_hba_stop(hba);
+@@ -10478,6 +10479,7 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
+ dev_err(hba->dev, "scsi_add_host failed\n");
+ goto out_disable;
+ }
++ hba->scsi_host_added = true;
+ }
+
+ hba->tmf_tag_set = (struct blk_mq_tag_set) {
+@@ -10560,7 +10562,8 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
+ free_tmf_tag_set:
+ blk_mq_free_tag_set(&hba->tmf_tag_set);
+ out_remove_scsi_host:
+- scsi_remove_host(hba->host);
++ if (hba->scsi_host_added)
++ scsi_remove_host(hba->host);
+ out_disable:
+ hba->is_irq_enabled = false;
+ ufshcd_hba_exit(hba);
+diff --git a/drivers/uio/uio_hv_generic.c b/drivers/uio/uio_hv_generic.c
+index b45653752301d..8704095994118 100644
+--- a/drivers/uio/uio_hv_generic.c
++++ b/drivers/uio/uio_hv_generic.c
+@@ -106,10 +106,11 @@ static void hv_uio_channel_cb(void *context)
+
+ /*
+ * Callback from vmbus_event when channel is rescinded.
++ * It is meant for rescind of primary channels only.
+ */
+ static void hv_uio_rescind(struct vmbus_channel *channel)
+ {
+- struct hv_device *hv_dev = channel->primary_channel->device_obj;
++ struct hv_device *hv_dev = channel->device_obj;
+ struct hv_uio_private_data *pdata = hv_get_drvdata(hv_dev);
+
+ /*
+@@ -120,6 +121,14 @@ static void hv_uio_rescind(struct vmbus_channel *channel)
+
+ /* Wake up reader */
+ uio_event_notify(&pdata->info);
++
++ /*
++ * With rescind callback registered, rescind path will not unregister the device
++ * from vmbus when the primary channel is rescinded.
++ * Without it, rescind handling is incomplete and next onoffer msg does not come.
++ * Unregister the device from vmbus here.
++ */
++ vmbus_device_unregister(channel->device_obj);
+ }
+
+ /* Sysfs API to allow mmap of the ring buffers
+diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
+index 31df6fdc233ef..ee95d39094302 100644
+--- a/drivers/usb/dwc3/core.c
++++ b/drivers/usb/dwc3/core.c
+@@ -1367,6 +1367,21 @@ static int dwc3_core_init(struct dwc3 *dwc)
+ dwc3_writel(dwc->regs, DWC3_GUCTL2, reg);
+ }
+
++ /*
++ * STAR 9001285599: This issue affects DWC_usb3 version 3.20a
++ * only. If the PM TIMER ECM is enabled through GUCTL2[19], the
++ * link compliance test (TD7.21) may fail. If the ECN is not
++ * enabled (GUCTL2[19] = 0), the controller will use the old timer
++ * value (5us), which is still acceptable for the link compliance
++ * test. Therefore, do not enable PM TIMER ECM in 3.20a by
++ * setting GUCTL2[19] by default; instead, use GUCTL2[19] = 0.
++ */
++ if (DWC3_VER_IS(DWC3, 320A)) {
++ reg = dwc3_readl(dwc->regs, DWC3_GUCTL2);
++ reg &= ~DWC3_GUCTL2_LC_TIMER;
++ dwc3_writel(dwc->regs, DWC3_GUCTL2, reg);
++ }
++
+ /*
+ * When configured in HOST mode, after issuing U3/L2 exit controller
+ * fails to send proper CRC checksum in CRC5 feild. Because of this
+diff --git a/drivers/usb/dwc3/core.h b/drivers/usb/dwc3/core.h
+index 3781c736c1a17..ed7f999e05bb5 100644
+--- a/drivers/usb/dwc3/core.h
++++ b/drivers/usb/dwc3/core.h
+@@ -417,6 +417,7 @@
+
+ /* Global User Control Register 2 */
+ #define DWC3_GUCTL2_RST_ACTBITLATER BIT(14)
++#define DWC3_GUCTL2_LC_TIMER BIT(19)
+
+ /* Global User Control Register 3 */
+ #define DWC3_GUCTL3_SPLITDISABLE BIT(14)
+@@ -1262,6 +1263,7 @@ struct dwc3 {
+ #define DWC3_REVISION_290A 0x5533290a
+ #define DWC3_REVISION_300A 0x5533300a
+ #define DWC3_REVISION_310A 0x5533310a
++#define DWC3_REVISION_320A 0x5533320a
+ #define DWC3_REVISION_330A 0x5533330a
+
+ #define DWC31_REVISION_ANY 0x0
+diff --git a/drivers/usb/dwc3/gadget.c b/drivers/usb/dwc3/gadget.c
+index 89fc690fdf34a..291bc549935bb 100644
+--- a/drivers/usb/dwc3/gadget.c
++++ b/drivers/usb/dwc3/gadget.c
+@@ -287,6 +287,23 @@ static int __dwc3_gadget_wakeup(struct dwc3 *dwc, bool async);
+ *
+ * Caller should handle locking. This function will issue @cmd with given
+ * @params to @dep and wait for its completion.
++ *
++ * According to the programming guide, if the link state is in L1/L2/U3,
++ * then sending the Start Transfer command may not complete. The
++ * programming guide suggested to bring the link state back to ON/U0 by
++ * performing remote wakeup prior to sending the command. However, don't
++ * initiate remote wakeup when the user/function does not send wakeup
++ * request via wakeup ops. Send the command when it's allowed.
++ *
++ * Notes:
++ * For L1 link state, issuing a command requires the clearing of
++ * GUSB2PHYCFG.SUSPENDUSB2, which turns on the signal required to complete
++ * the given command (usually within 50us). This should happen within the
++ * command timeout set by driver. No additional step is needed.
++ *
++ * For L2 or U3 link state, the gadget is in USB suspend. Care should be
++ * taken when sending Start Transfer command to ensure that it's done after
++ * USB resume.
+ */
+ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd,
+ struct dwc3_gadget_ep_cmd_params *params)
+@@ -327,30 +344,6 @@ int dwc3_send_gadget_ep_cmd(struct dwc3_ep *dep, unsigned int cmd,
+ dwc3_writel(dwc->regs, DWC3_GUSB2PHYCFG(0), reg);
+ }
+
+- if (DWC3_DEPCMD_CMD(cmd) == DWC3_DEPCMD_STARTTRANSFER) {
+- int link_state;
+-
+- /*
+- * Initiate remote wakeup if the link state is in U3 when
+- * operating in SS/SSP or L1/L2 when operating in HS/FS. If the
+- * link state is in U1/U2, no remote wakeup is needed. The Start
+- * Transfer command will initiate the link recovery.
+- */
+- link_state = dwc3_gadget_get_link_state(dwc);
+- switch (link_state) {
+- case DWC3_LINK_STATE_U2:
+- if (dwc->gadget->speed >= USB_SPEED_SUPER)
+- break;
+-
+- fallthrough;
+- case DWC3_LINK_STATE_U3:
+- ret = __dwc3_gadget_wakeup(dwc, false);
+- dev_WARN_ONCE(dwc->dev, ret, "wakeup failed --> %d\n",
+- ret);
+- break;
+- }
+- }
+-
+ /*
+ * For some commands such as Update Transfer command, DEPCMDPARn
+ * registers are reserved. Since the driver often sends Update Transfer
+diff --git a/drivers/usb/gadget/udc/aspeed_udc.c b/drivers/usb/gadget/udc/aspeed_udc.c
+index 821a6ab5da56f..f4781e611aaa2 100644
+--- a/drivers/usb/gadget/udc/aspeed_udc.c
++++ b/drivers/usb/gadget/udc/aspeed_udc.c
+@@ -1009,6 +1009,8 @@ static void ast_udc_getstatus(struct ast_udc_dev *udc)
+ break;
+ case USB_RECIP_ENDPOINT:
+ epnum = crq.wIndex & USB_ENDPOINT_NUMBER_MASK;
++ if (epnum >= AST_UDC_NUM_ENDPOINTS)
++ goto stall;
+ status = udc->ep[epnum].stopped;
+ break;
+ default:
+diff --git a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c
+index 0eed0e03842cf..d394affb70723 100644
+--- a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c
++++ b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.c
+@@ -2251,7 +2251,6 @@ static int cdns2_gadget_start(struct cdns2_device *pdev)
+ {
+ u32 max_speed;
+ void *buf;
+- int val;
+ int ret;
+
+ pdev->usb_regs = pdev->regs;
+@@ -2261,14 +2260,9 @@ static int cdns2_gadget_start(struct cdns2_device *pdev)
+ pdev->adma_regs = pdev->regs + CDNS2_ADMA_REGS_OFFSET;
+
+ /* Reset controller. */
+- set_reg_bit_8(&pdev->usb_regs->cpuctrl, CPUCTRL_SW_RST);
+-
+- ret = readl_poll_timeout_atomic(&pdev->usb_regs->cpuctrl, val,
+- !(val & CPUCTRL_SW_RST), 1, 10000);
+- if (ret) {
+- dev_err(pdev->dev, "Error: reset controller timeout\n");
+- return -EINVAL;
+- }
++ writeb(CPUCTRL_SW_RST | CPUCTRL_UPCLK | CPUCTRL_WUEN,
++ &pdev->usb_regs->cpuctrl);
++ usleep_range(5, 10);
+
+ usb_initialize_gadget(pdev->dev, &pdev->gadget, NULL);
+
+diff --git a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.h b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.h
+index 71e2f62d653a5..b5d5ec12e986e 100644
+--- a/drivers/usb/gadget/udc/cdns2/cdns2-gadget.h
++++ b/drivers/usb/gadget/udc/cdns2/cdns2-gadget.h
+@@ -292,8 +292,17 @@ struct cdns2_usb_regs {
+ #define SPEEDCTRL_HSDISABLE BIT(7)
+
+ /* CPUCTRL- bitmasks. */
++/* UP clock enable */
++#define CPUCTRL_UPCLK BIT(0)
+ /* Controller reset bit. */
+ #define CPUCTRL_SW_RST BIT(1)
++/**
++ * If the wuen bit is ‘1’, the upclken is automatically set to ‘1’ after
++ * detecting rising edge of wuintereq interrupt. If the wuen bit is ‘0’,
++ * the wuintereq interrupt is ignored.
++ */
++#define CPUCTRL_WUEN BIT(7)
++
+
+ /**
+ * struct cdns2_adma_regs - ADMA controller registers.
+diff --git a/drivers/usb/storage/uas.c b/drivers/usb/storage/uas.c
+index b610a2de4ae5d..a04b4cb1382d5 100644
+--- a/drivers/usb/storage/uas.c
++++ b/drivers/usb/storage/uas.c
+@@ -423,6 +423,7 @@ static void uas_data_cmplt(struct urb *urb)
+ uas_log_cmd_state(cmnd, "data cmplt err", status);
+ /* error: no data transfered */
+ scsi_set_resid(cmnd, sdb->length);
++ set_host_byte(cmnd, DID_ERROR);
+ } else {
+ scsi_set_resid(cmnd, sdb->length - urb->actual_length);
+ }
+diff --git a/drivers/usb/typec/ucsi/ucsi.c b/drivers/usb/typec/ucsi/ucsi.c
+index 2cc7aedd490f1..45e91d065b3bd 100644
+--- a/drivers/usb/typec/ucsi/ucsi.c
++++ b/drivers/usb/typec/ucsi/ucsi.c
+@@ -961,6 +961,27 @@ static void ucsi_unregister_cable(struct ucsi_connector *con)
+ con->cable = NULL;
+ }
+
++static int ucsi_check_connector_capability(struct ucsi_connector *con)
++{
++ u64 command;
++ int ret;
++
++ if (!con->partner || con->ucsi->version < UCSI_VERSION_2_1)
++ return 0;
++
++ command = UCSI_GET_CONNECTOR_CAPABILITY | UCSI_CONNECTOR_NUMBER(con->num);
++ ret = ucsi_send_command(con->ucsi, command, &con->cap, sizeof(con->cap));
++ if (ret < 0) {
++ dev_err(con->ucsi->dev, "GET_CONNECTOR_CAPABILITY failed (%d)\n", ret);
++ return ret;
++ }
++
++ typec_partner_set_pd_revision(con->partner,
++ UCSI_CONCAP_FLAG_PARTNER_PD_MAJOR_REV_AS_BCD(con->cap.flags));
++
++ return ret;
++}
++
+ static void ucsi_pwr_opmode_change(struct ucsi_connector *con)
+ {
+ switch (UCSI_CONSTAT_PWR_OPMODE(con->status.flags)) {
+@@ -970,6 +991,7 @@ static void ucsi_pwr_opmode_change(struct ucsi_connector *con)
+ ucsi_partner_task(con, ucsi_get_src_pdos, 30, 0);
+ ucsi_partner_task(con, ucsi_check_altmodes, 30, 0);
+ ucsi_partner_task(con, ucsi_register_partner_pdos, 1, HZ);
++ ucsi_partner_task(con, ucsi_check_connector_capability, 1, HZ);
+ break;
+ case UCSI_CONSTAT_PWR_OPMODE_TYPEC1_5:
+ con->rdo = 0;
+@@ -1013,7 +1035,6 @@ static int ucsi_register_partner(struct ucsi_connector *con)
+
+ desc.identity = &con->partner_identity;
+ desc.usb_pd = pwr_opmode == UCSI_CONSTAT_PWR_OPMODE_PD;
+- desc.pd_revision = UCSI_CONCAP_FLAG_PARTNER_PD_MAJOR_REV_AS_BCD(con->cap.flags);
+
+ partner = typec_register_partner(con->port, &desc);
+ if (IS_ERR(partner)) {
+@@ -1090,27 +1111,6 @@ static void ucsi_partner_change(struct ucsi_connector *con)
+ con->num, u_role);
+ }
+
+-static int ucsi_check_connector_capability(struct ucsi_connector *con)
+-{
+- u64 command;
+- int ret;
+-
+- if (!con->partner || con->ucsi->version < UCSI_VERSION_2_0)
+- return 0;
+-
+- command = UCSI_GET_CONNECTOR_CAPABILITY | UCSI_CONNECTOR_NUMBER(con->num);
+- ret = ucsi_send_command(con->ucsi, command, &con->cap, sizeof(con->cap));
+- if (ret < 0) {
+- dev_err(con->ucsi->dev, "GET_CONNECTOR_CAPABILITY failed (%d)\n", ret);
+- return ret;
+- }
+-
+- typec_partner_set_pd_revision(con->partner,
+- UCSI_CONCAP_FLAG_PARTNER_PD_MAJOR_REV_AS_BCD(con->cap.flags));
+-
+- return ret;
+-}
+-
+ static int ucsi_check_connection(struct ucsi_connector *con)
+ {
+ u8 prev_flags = con->status.flags;
+@@ -1225,15 +1225,16 @@ static void ucsi_handle_connector_change(struct work_struct *work)
+ if (con->status.flags & UCSI_CONSTAT_CONNECTED) {
+ ucsi_register_partner(con);
+ ucsi_partner_task(con, ucsi_check_connection, 1, HZ);
+- ucsi_partner_task(con, ucsi_check_connector_capability, 1, HZ);
+ if (con->ucsi->cap.features & UCSI_CAP_GET_PD_MESSAGE)
+ ucsi_partner_task(con, ucsi_get_partner_identity, 1, HZ);
+ if (con->ucsi->cap.features & UCSI_CAP_CABLE_DETAILS)
+ ucsi_partner_task(con, ucsi_check_cable, 1, HZ);
+
+ if (UCSI_CONSTAT_PWR_OPMODE(con->status.flags) ==
+- UCSI_CONSTAT_PWR_OPMODE_PD)
++ UCSI_CONSTAT_PWR_OPMODE_PD) {
+ ucsi_partner_task(con, ucsi_register_partner_pdos, 1, HZ);
++ ucsi_partner_task(con, ucsi_check_connector_capability, 1, HZ);
++ }
+ } else {
+ ucsi_unregister_partner(con);
+ }
+@@ -1650,6 +1651,7 @@ static int ucsi_register_port(struct ucsi *ucsi, struct ucsi_connector *con)
+ ucsi_register_device_pdos(con);
+ ucsi_get_src_pdos(con);
+ ucsi_check_altmodes(con);
++ ucsi_check_connector_capability(con);
+ }
+
+ trace_ucsi_register_port(con->num, &con->status);
+diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
+index a94ec6225d31a..5f9e7e4770783 100644
+--- a/drivers/vfio/vfio_iommu_spapr_tce.c
++++ b/drivers/vfio/vfio_iommu_spapr_tce.c
+@@ -364,7 +364,6 @@ static void tce_iommu_release(void *iommu_data)
+ if (!tbl)
+ continue;
+
+- tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
+ tce_iommu_free_table(container, tbl);
+ }
+
+@@ -720,6 +719,8 @@ static long tce_iommu_remove_window(struct tce_container *container,
+
+ BUG_ON(!tbl->it_size);
+
++ tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
++
+ /* Detach groups from IOMMUs */
+ list_for_each_entry(tcegrp, &container->group_list, next) {
+ table_group = iommu_group_get_iommudata(tcegrp->grp);
+@@ -738,7 +739,6 @@ static long tce_iommu_remove_window(struct tce_container *container,
+ }
+
+ /* Free table */
+- tce_iommu_clear(container, tbl, tbl->it_offset, tbl->it_size);
+ tce_iommu_free_table(container, tbl);
+ container->tables[num] = NULL;
+
+@@ -1197,9 +1197,14 @@ static void tce_iommu_release_ownership(struct tce_container *container,
+ return;
+ }
+
+- for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i)
+- if (container->tables[i])
++ for (i = 0; i < IOMMU_TABLE_GROUP_MAX_TABLES; ++i) {
++ if (container->tables[i]) {
++ tce_iommu_clear(container, container->tables[i],
++ container->tables[i]->it_offset,
++ container->tables[i]->it_size);
+ table_group->ops->unset_window(table_group, i);
++ }
++ }
+ }
+
+ static long tce_iommu_take_ownership(struct tce_container *container,
+diff --git a/drivers/virt/coco/sev-guest/sev-guest.c b/drivers/virt/coco/sev-guest/sev-guest.c
+index 654290a8e1ba3..a100d6241992c 100644
+--- a/drivers/virt/coco/sev-guest/sev-guest.c
++++ b/drivers/virt/coco/sev-guest/sev-guest.c
+@@ -1009,8 +1009,13 @@ static void __exit sev_guest_remove(struct platform_device *pdev)
+ * This driver is meant to be a common SEV guest interface driver and to
+ * support any SEV guest API. As such, even though it has been introduced
+ * with the SEV-SNP support, it is named "sev-guest".
++ *
++ * sev_guest_remove() lives in .exit.text. For drivers registered via
++ * module_platform_driver_probe() this is ok because they cannot get unbound
++ * at runtime. So mark the driver struct with __refdata to prevent modpost
++ * triggering a section mismatch warning.
+ */
+-static struct platform_driver sev_guest_driver = {
++static struct platform_driver sev_guest_driver __refdata = {
+ .remove_new = __exit_p(sev_guest_remove),
+ .driver = {
+ .name = "sev-guest",
+diff --git a/drivers/virtio/virtio_ring.c b/drivers/virtio/virtio_ring.c
+index 2a972752ff1bc..9d3a9942c8c82 100644
+--- a/drivers/virtio/virtio_ring.c
++++ b/drivers/virtio/virtio_ring.c
+@@ -3121,8 +3121,10 @@ dma_addr_t virtqueue_dma_map_single_attrs(struct virtqueue *_vq, void *ptr,
+ {
+ struct vring_virtqueue *vq = to_vvq(_vq);
+
+- if (!vq->use_dma_api)
++ if (!vq->use_dma_api) {
++ kmsan_handle_dma(virt_to_page(ptr), offset_in_page(ptr), size, dir);
+ return (dma_addr_t)virt_to_phys(ptr);
++ }
+
+ return dma_map_single_attrs(vring_dma_dev(vq), ptr, size, dir, attrs);
+ }
+diff --git a/drivers/watchdog/imx7ulp_wdt.c b/drivers/watchdog/imx7ulp_wdt.c
+index b21d7a74a42df..94914a22daff7 100644
+--- a/drivers/watchdog/imx7ulp_wdt.c
++++ b/drivers/watchdog/imx7ulp_wdt.c
+@@ -290,6 +290,11 @@ static int imx7ulp_wdt_init(struct imx7ulp_wdt_device *wdt, unsigned int timeout
+ if (wdt->ext_reset)
+ val |= WDOG_CS_INT_EN;
+
++ if (readl(wdt->base + WDOG_CS) & WDOG_CS_EN) {
++ set_bit(WDOG_HW_RUNNING, &wdt->wdd.status);
++ val |= WDOG_CS_EN;
++ }
++
+ do {
+ ret = _imx7ulp_wdt_init(wdt, timeout, val);
+ toval = readl(wdt->base + WDOG_TOVAL);
+diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
+index c9c620e32fa8b..39e726d7280ef 100644
+--- a/drivers/xen/privcmd.c
++++ b/drivers/xen/privcmd.c
+@@ -17,6 +17,7 @@
+ #include <linux/poll.h>
+ #include <linux/sched.h>
+ #include <linux/slab.h>
++#include <linux/srcu.h>
+ #include <linux/string.h>
+ #include <linux/workqueue.h>
+ #include <linux/errno.h>
+@@ -846,6 +847,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file,
+ /* Irqfd support */
+ static struct workqueue_struct *irqfd_cleanup_wq;
+ static DEFINE_SPINLOCK(irqfds_lock);
++DEFINE_STATIC_SRCU(irqfds_srcu);
+ static LIST_HEAD(irqfds_list);
+
+ struct privcmd_kernel_irqfd {
+@@ -873,6 +875,9 @@ static void irqfd_shutdown(struct work_struct *work)
+ container_of(work, struct privcmd_kernel_irqfd, shutdown);
+ u64 cnt;
+
++ /* Make sure irqfd has been initialized in assign path */
++ synchronize_srcu(&irqfds_srcu);
++
+ eventfd_ctx_remove_wait_queue(kirqfd->eventfd, &kirqfd->wait, &cnt);
+ eventfd_ctx_put(kirqfd->eventfd);
+ kfree(kirqfd);
+@@ -935,7 +940,7 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd)
+ __poll_t events;
+ struct fd f;
+ void *dm_op;
+- int ret;
++ int ret, idx;
+
+ kirqfd = kzalloc(sizeof(*kirqfd) + irqfd->size, GFP_KERNEL);
+ if (!kirqfd)
+@@ -981,6 +986,7 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd)
+ }
+ }
+
++ idx = srcu_read_lock(&irqfds_srcu);
+ list_add_tail(&kirqfd->list, &irqfds_list);
+ spin_unlock_irqrestore(&irqfds_lock, flags);
+
+@@ -992,6 +998,8 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd)
+ if (events & EPOLLIN)
+ irqfd_inject(kirqfd);
+
++ srcu_read_unlock(&irqfds_srcu, idx);
++
+ /*
+ * Do not drop the file until the kirqfd is fully initialized, otherwise
+ * we might race against the EPOLLHUP.
+diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
+index a43897b03ce94..777405719de85 100644
+--- a/fs/binfmt_elf.c
++++ b/fs/binfmt_elf.c
+@@ -1003,7 +1003,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
+ if (elf_read_implies_exec(*elf_ex, executable_stack))
+ current->personality |= READ_IMPLIES_EXEC;
+
+- if (!(current->personality & ADDR_NO_RANDOMIZE) && randomize_va_space)
++ const int snapshot_randomize_va_space = READ_ONCE(randomize_va_space);
++ if (!(current->personality & ADDR_NO_RANDOMIZE) && snapshot_randomize_va_space)
+ current->flags |= PF_RANDOMIZE;
+
+ setup_new_exec(bprm);
+@@ -1251,7 +1252,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
+ mm->end_data = end_data;
+ mm->start_stack = bprm->p;
+
+- if ((current->flags & PF_RANDOMIZE) && (randomize_va_space > 1)) {
++ if ((current->flags & PF_RANDOMIZE) && (snapshot_randomize_va_space > 1)) {
+ /*
+ * For architectures with ELF randomization, when executing
+ * a loader directly (i.e. no interpreter listed in ELF
+diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
+index 8a791b648ac53..f56914507fceb 100644
+--- a/fs/btrfs/ctree.c
++++ b/fs/btrfs/ctree.c
+@@ -462,8 +462,16 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
+ }
+
+ owner = btrfs_header_owner(buf);
+- BUG_ON(owner == BTRFS_TREE_RELOC_OBJECTID &&
+- !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF));
++ if (unlikely(owner == BTRFS_TREE_RELOC_OBJECTID &&
++ !(flags & BTRFS_BLOCK_FLAG_FULL_BACKREF))) {
++ btrfs_crit(fs_info,
++"found tree block at bytenr %llu level %d root %llu refs %llu flags %llx without full backref flag set",
++ buf->start, btrfs_header_level(buf),
++ btrfs_root_id(root), refs, flags);
++ ret = -EUCLEAN;
++ btrfs_abort_transaction(trans, ret);
++ return ret;
++ }
+
+ if (refs > 1) {
+ if ((owner == btrfs_root_id(root) ||
+diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
+index a56209d275c15..b2e4b30b8fae9 100644
+--- a/fs/btrfs/ctree.h
++++ b/fs/btrfs/ctree.h
+@@ -457,7 +457,6 @@ struct btrfs_file_private {
+ void *filldir_buf;
+ u64 last_index;
+ struct extent_state *llseek_cached_state;
+- bool fsync_skip_inode_lock;
+ };
+
+ static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
+diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
+index 8bf980123c5c5..55be8a7f0bb18 100644
+--- a/fs/btrfs/extent-tree.c
++++ b/fs/btrfs/extent-tree.c
+@@ -173,9 +173,16 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+
+ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
+ num_refs = btrfs_extent_refs(leaf, ei);
++ if (unlikely(num_refs == 0)) {
++ ret = -EUCLEAN;
++ btrfs_err(fs_info,
++ "unexpected zero reference count for extent item (%llu %u %llu)",
++ key.objectid, key.type, key.offset);
++ btrfs_abort_transaction(trans, ret);
++ goto out_free;
++ }
+ extent_flags = btrfs_extent_flags(leaf, ei);
+ owner = btrfs_get_extent_owner_root(fs_info, leaf, path->slots[0]);
+- BUG_ON(num_refs == 0);
+ } else {
+ num_refs = 0;
+ extent_flags = 0;
+@@ -205,10 +212,19 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+ goto search_again;
+ }
+ spin_lock(&head->lock);
+- if (head->extent_op && head->extent_op->update_flags)
++ if (head->extent_op && head->extent_op->update_flags) {
+ extent_flags |= head->extent_op->flags_to_set;
+- else
+- BUG_ON(num_refs == 0);
++ } else if (unlikely(num_refs == 0)) {
++ spin_unlock(&head->lock);
++ mutex_unlock(&head->mutex);
++ spin_unlock(&delayed_refs->lock);
++ ret = -EUCLEAN;
++ btrfs_err(fs_info,
++ "unexpected zero reference count for extent %llu (%s)",
++ bytenr, metadata ? "metadata" : "data");
++ btrfs_abort_transaction(trans, ret);
++ goto out_free;
++ }
+
+ num_refs += head->ref_mod;
+ spin_unlock(&head->lock);
+@@ -5275,7 +5291,15 @@ static noinline void reada_walk_down(struct btrfs_trans_handle *trans,
+ /* We don't care about errors in readahead. */
+ if (ret < 0)
+ continue;
+- BUG_ON(refs == 0);
++
++ /*
++ * This could be racey, it's conceivable that we raced and end
++ * up with a bogus refs count, if that's the case just skip, if
++ * we are actually corrupt we will notice when we look up
++ * everything again with our locks.
++ */
++ if (refs == 0)
++ continue;
+
+ if (wc->stage == DROP_REFERENCE) {
+ if (refs == 1)
+@@ -5333,16 +5357,19 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
+ if (lookup_info &&
+ ((wc->stage == DROP_REFERENCE && wc->refs[level] != 1) ||
+ (wc->stage == UPDATE_BACKREF && !(wc->flags[level] & flag)))) {
+- BUG_ON(!path->locks[level]);
++ ASSERT(path->locks[level]);
+ ret = btrfs_lookup_extent_info(trans, fs_info,
+ eb->start, level, 1,
+ &wc->refs[level],
+ &wc->flags[level],
+ NULL);
+- BUG_ON(ret == -ENOMEM);
+ if (ret)
+ return ret;
+- BUG_ON(wc->refs[level] == 0);
++ if (unlikely(wc->refs[level] == 0)) {
++ btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0",
++ eb->start);
++ return -EUCLEAN;
++ }
+ }
+
+ if (wc->stage == DROP_REFERENCE) {
+@@ -5358,7 +5385,7 @@ static noinline int walk_down_proc(struct btrfs_trans_handle *trans,
+
+ /* wc->stage == UPDATE_BACKREF */
+ if (!(wc->flags[level] & flag)) {
+- BUG_ON(!path->locks[level]);
++ ASSERT(path->locks[level]);
+ ret = btrfs_inc_ref(trans, root, eb, 1);
+ BUG_ON(ret); /* -ENOMEM */
+ ret = btrfs_dec_ref(trans, root, eb, 0);
+@@ -5515,8 +5542,9 @@ static noinline int do_walk_down(struct btrfs_trans_handle *trans,
+ goto out_unlock;
+
+ if (unlikely(wc->refs[level - 1] == 0)) {
+- btrfs_err(fs_info, "Missing references.");
+- ret = -EIO;
++ btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0",
++ bytenr);
++ ret = -EUCLEAN;
+ goto out_unlock;
+ }
+ *lookup_info = 0;
+@@ -5719,7 +5747,12 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
+ path->locks[level] = 0;
+ return ret;
+ }
+- BUG_ON(wc->refs[level] == 0);
++ if (unlikely(wc->refs[level] == 0)) {
++ btrfs_tree_unlock_rw(eb, path->locks[level]);
++ btrfs_err(fs_info, "bytenr %llu has 0 references, expect > 0",
++ eb->start);
++ return -EUCLEAN;
++ }
+ if (wc->refs[level] == 1) {
+ btrfs_tree_unlock_rw(eb, path->locks[level]);
+ path->locks[level] = 0;
+@@ -5737,7 +5770,10 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
+ ret = btrfs_dec_ref(trans, root, eb, 1);
+ else
+ ret = btrfs_dec_ref(trans, root, eb, 0);
+- BUG_ON(ret); /* -ENOMEM */
++ if (ret) {
++ btrfs_abort_transaction(trans, ret);
++ return ret;
++ }
+ if (is_fstree(btrfs_root_id(root))) {
+ ret = btrfs_qgroup_trace_leaf_items(trans, eb);
+ if (ret) {
+diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
+index ca434f0cd27f0..66dfee8739067 100644
+--- a/fs/btrfs/file.c
++++ b/fs/btrfs/file.c
+@@ -1558,13 +1558,6 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
+ if (IS_ERR_OR_NULL(dio)) {
+ ret = PTR_ERR_OR_ZERO(dio);
+ } else {
+- struct btrfs_file_private stack_private = { 0 };
+- struct btrfs_file_private *private;
+- const bool have_private = (file->private_data != NULL);
+-
+- if (!have_private)
+- file->private_data = &stack_private;
+-
+ /*
+ * If we have a synchoronous write, we must make sure the fsync
+ * triggered by the iomap_dio_complete() call below doesn't
+@@ -1573,13 +1566,10 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
+ * partial writes due to the input buffer (or parts of it) not
+ * being already faulted in.
+ */
+- private = file->private_data;
+- private->fsync_skip_inode_lock = true;
++ ASSERT(current->journal_info == NULL);
++ current->journal_info = BTRFS_TRANS_DIO_WRITE_STUB;
+ ret = iomap_dio_complete(dio);
+- private->fsync_skip_inode_lock = false;
+-
+- if (!have_private)
+- file->private_data = NULL;
++ current->journal_info = NULL;
+ }
+
+ /* No increment (+=) because iomap returns a cumulative value. */
+@@ -1811,7 +1801,6 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
+ */
+ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+ {
+- struct btrfs_file_private *private = file->private_data;
+ struct dentry *dentry = file_dentry(file);
+ struct inode *inode = d_inode(dentry);
+ struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
+@@ -1821,7 +1810,13 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+ int ret = 0, err;
+ u64 len;
+ bool full_sync;
+- const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false);
++ bool skip_ilock = false;
++
++ if (current->journal_info == BTRFS_TRANS_DIO_WRITE_STUB) {
++ skip_ilock = true;
++ current->journal_info = NULL;
++ lockdep_assert_held(&inode->i_rwsem);
++ }
+
+ trace_btrfs_sync_file(file, datasync);
+
+diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
+index c2f48fc159e5a..2951aa0039fc6 100644
+--- a/fs/btrfs/inode.c
++++ b/fs/btrfs/inode.c
+@@ -5699,7 +5699,7 @@ struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry)
+ struct inode *inode;
+ struct btrfs_root *root = BTRFS_I(dir)->root;
+ struct btrfs_root *sub_root = root;
+- struct btrfs_key location;
++ struct btrfs_key location = { 0 };
+ u8 di_type = 0;
+ int ret = 0;
+
+diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
+index 3faf2181d1ee8..24df831770075 100644
+--- a/fs/btrfs/qgroup.c
++++ b/fs/btrfs/qgroup.c
+@@ -1750,13 +1750,55 @@ int btrfs_create_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
+ return ret;
+ }
+
+-static bool qgroup_has_usage(struct btrfs_qgroup *qgroup)
++/*
++ * Return 0 if we can not delete the qgroup (not empty or has children etc).
++ * Return >0 if we can delete the qgroup.
++ * Return <0 for other errors during tree search.
++ */
++static int can_delete_qgroup(struct btrfs_fs_info *fs_info, struct btrfs_qgroup *qgroup)
+ {
+- return (qgroup->rfer > 0 || qgroup->rfer_cmpr > 0 ||
+- qgroup->excl > 0 || qgroup->excl_cmpr > 0 ||
+- qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] > 0 ||
+- qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] > 0 ||
+- qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS] > 0);
++ struct btrfs_key key;
++ struct btrfs_path *path;
++ int ret;
++
++ /*
++ * Squota would never be inconsistent, but there can still be case
++ * where a dropped subvolume still has qgroup numbers, and squota
++ * relies on such qgroup for future accounting.
++ *
++ * So for squota, do not allow dropping any non-zero qgroup.
++ */
++ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_SIMPLE &&
++ (qgroup->rfer || qgroup->excl || qgroup->excl_cmpr || qgroup->rfer_cmpr))
++ return 0;
++
++ /* For higher level qgroup, we can only delete it if it has no child. */
++ if (btrfs_qgroup_level(qgroup->qgroupid)) {
++ if (!list_empty(&qgroup->members))
++ return 0;
++ return 1;
++ }
++
++ /*
++ * For level-0 qgroups, we can only delete it if it has no subvolume
++ * for it.
++ * This means even a subvolume is unlinked but not yet fully dropped,
++ * we can not delete the qgroup.
++ */
++ key.objectid = qgroup->qgroupid;
++ key.type = BTRFS_ROOT_ITEM_KEY;
++ key.offset = -1ULL;
++ path = btrfs_alloc_path();
++ if (!path)
++ return -ENOMEM;
++
++ ret = btrfs_find_root(fs_info->tree_root, &key, path, NULL, NULL);
++ btrfs_free_path(path);
++ /*
++ * The @ret from btrfs_find_root() exactly matches our definition for
++ * the return value, thus can be returned directly.
++ */
++ return ret;
+ }
+
+ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
+@@ -1778,7 +1820,10 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
+ goto out;
+ }
+
+- if (is_fstree(qgroupid) && qgroup_has_usage(qgroup)) {
++ ret = can_delete_qgroup(fs_info, qgroup);
++ if (ret < 0)
++ goto out;
++ if (ret == 0) {
+ ret = -EBUSY;
+ goto out;
+ }
+@@ -1803,6 +1848,34 @@ int btrfs_remove_qgroup(struct btrfs_trans_handle *trans, u64 qgroupid)
+ }
+
+ spin_lock(&fs_info->qgroup_lock);
++ /*
++ * Warn on reserved space. The subvolume should has no child nor
++ * corresponding subvolume.
++ * Thus its reserved space should all be zero, no matter if qgroup
++ * is consistent or the mode.
++ */
++ WARN_ON(qgroup->rsv.values[BTRFS_QGROUP_RSV_DATA] ||
++ qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PREALLOC] ||
++ qgroup->rsv.values[BTRFS_QGROUP_RSV_META_PERTRANS]);
++ /*
++ * The same for rfer/excl numbers, but that's only if our qgroup is
++ * consistent and if it's in regular qgroup mode.
++ * For simple mode it's not as accurate thus we can hit non-zero values
++ * very frequently.
++ */
++ if (btrfs_qgroup_mode(fs_info) == BTRFS_QGROUP_MODE_FULL &&
++ !(fs_info->qgroup_flags & BTRFS_QGROUP_STATUS_FLAG_INCONSISTENT)) {
++ if (WARN_ON(qgroup->rfer || qgroup->excl ||
++ qgroup->rfer_cmpr || qgroup->excl_cmpr)) {
++ btrfs_warn_rl(fs_info,
++"to be deleted qgroup %u/%llu has non-zero numbers, rfer %llu rfer_cmpr %llu excl %llu excl_cmpr %llu",
++ btrfs_qgroup_level(qgroup->qgroupid),
++ btrfs_qgroup_subvolid(qgroup->qgroupid),
++ qgroup->rfer, qgroup->rfer_cmpr,
++ qgroup->excl, qgroup->excl_cmpr);
++ qgroup_mark_inconsistent(fs_info);
++ }
++ }
+ del_qgroup_rb(fs_info, qgroupid);
+ spin_unlock(&fs_info->qgroup_lock);
+
+@@ -4269,10 +4342,9 @@ static int __btrfs_qgroup_release_data(struct btrfs_inode *inode,
+ int ret;
+
+ if (btrfs_qgroup_mode(inode->root->fs_info) == BTRFS_QGROUP_MODE_DISABLED) {
+- extent_changeset_init(&changeset);
+ return clear_record_extent_bits(&inode->io_tree, start,
+ start + len - 1,
+- EXTENT_QGROUP_RESERVED, &changeset);
++ EXTENT_QGROUP_RESERVED, NULL);
+ }
+
+ /* In release case, we shouldn't have @reserved */
+diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
+index 4e451ab173b10..62ec85f4b7774 100644
+--- a/fs/btrfs/transaction.h
++++ b/fs/btrfs/transaction.h
+@@ -27,6 +27,12 @@ struct btrfs_root_item;
+ struct btrfs_root;
+ struct btrfs_path;
+
++/*
++ * Signal that a direct IO write is in progress, to avoid deadlock for sync
++ * direct IO writes when fsync is called during the direct IO write path.
++ */
++#define BTRFS_TRANS_DIO_WRITE_STUB ((void *) 1)
++
+ /* Radix-tree tag for roots that are part of the trasaction. */
+ #define BTRFS_ROOT_TRANS_TAG 0
+
+diff --git a/fs/btrfs/zoned.c b/fs/btrfs/zoned.c
+index 947a87576f6c6..35829a1a2238e 100644
+--- a/fs/btrfs/zoned.c
++++ b/fs/btrfs/zoned.c
+@@ -1408,6 +1408,8 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
+ return -EINVAL;
+ }
+
++ bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity);
++
+ if (zone_info[0].alloc_offset == WP_MISSING_DEV) {
+ btrfs_err(bg->fs_info,
+ "zoned: cannot recover write pointer for zone %llu",
+@@ -1434,7 +1436,6 @@ static int btrfs_load_block_group_dup(struct btrfs_block_group *bg,
+ }
+
+ bg->alloc_offset = zone_info[0].alloc_offset;
+- bg->zone_capacity = min(zone_info[0].capacity, zone_info[1].capacity);
+ return 0;
+ }
+
+@@ -1452,6 +1453,9 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
+ return -EINVAL;
+ }
+
++ /* In case a device is missing we have a cap of 0, so don't use it. */
++ bg->zone_capacity = min_not_zero(zone_info[0].capacity, zone_info[1].capacity);
++
+ for (i = 0; i < map->num_stripes; i++) {
+ if (zone_info[i].alloc_offset == WP_MISSING_DEV ||
+ zone_info[i].alloc_offset == WP_CONVENTIONAL)
+@@ -1473,9 +1477,6 @@ static int btrfs_load_block_group_raid1(struct btrfs_block_group *bg,
+ if (test_bit(0, active))
+ set_bit(BLOCK_GROUP_FLAG_ZONE_IS_ACTIVE, &bg->runtime_flags);
+ }
+- /* In case a device is missing we have a cap of 0, so don't use it. */
+- bg->zone_capacity = min_not_zero(zone_info[0].capacity,
+- zone_info[1].capacity);
+ }
+
+ if (zone_info[0].alloc_offset != WP_MISSING_DEV)
+@@ -1565,6 +1566,7 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
+ unsigned long *active = NULL;
+ u64 last_alloc = 0;
+ u32 num_sequential = 0, num_conventional = 0;
++ u64 profile;
+
+ if (!btrfs_is_zoned(fs_info))
+ return 0;
+@@ -1625,7 +1627,8 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
+ }
+ }
+
+- switch (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
++ profile = map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK;
++ switch (profile) {
+ case 0: /* single */
+ ret = btrfs_load_block_group_single(cache, &zone_info[0], active);
+ break;
+@@ -1652,6 +1655,23 @@ int btrfs_load_block_group_zone_info(struct btrfs_block_group *cache, bool new)
+ goto out;
+ }
+
++ if (ret == -EIO && profile != 0 && profile != BTRFS_BLOCK_GROUP_RAID0 &&
++ profile != BTRFS_BLOCK_GROUP_RAID10) {
++ /*
++ * Detected broken write pointer. Make this block group
++ * unallocatable by setting the allocation pointer at the end of
++ * allocatable region. Relocating this block group will fix the
++ * mismatch.
++ *
++ * Currently, we cannot handle RAID0 or RAID10 case like this
++ * because we don't have a proper zone_capacity value. But,
++ * reading from this block group won't work anyway by a missing
++ * stripe.
++ */
++ cache->alloc_offset = cache->zone_capacity;
++ ret = 0;
++ }
++
+ out:
+ /* Reject non SINGLE data profiles without RST */
+ if ((map->type & BTRFS_BLOCK_GROUP_DATA) &&
+diff --git a/fs/cachefiles/io.c b/fs/cachefiles/io.c
+index e667dbcd20e8c..a91acd03ee129 100644
+--- a/fs/cachefiles/io.c
++++ b/fs/cachefiles/io.c
+@@ -630,7 +630,7 @@ static void cachefiles_prepare_write_subreq(struct netfs_io_subrequest *subreq)
+
+ _enter("W=%x[%x] %llx", wreq->debug_id, subreq->debug_index, subreq->start);
+
+- subreq->max_len = ULONG_MAX;
++ subreq->max_len = MAX_RW_COUNT;
+ subreq->max_nr_segs = BIO_MAX_VECS;
+
+ if (!cachefiles_cres_file(cres)) {
+diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
+index d3a67bc06d109..3926a05eceeed 100644
+--- a/fs/ext4/fast_commit.c
++++ b/fs/ext4/fast_commit.c
+@@ -353,7 +353,7 @@ void ext4_fc_mark_ineligible(struct super_block *sb, int reason, handle_t *handl
+ read_unlock(&sbi->s_journal->j_state_lock);
+ }
+ spin_lock(&sbi->s_fc_lock);
+- if (sbi->s_fc_ineligible_tid < tid)
++ if (tid_gt(tid, sbi->s_fc_ineligible_tid))
+ sbi->s_fc_ineligible_tid = tid;
+ spin_unlock(&sbi->s_fc_lock);
+ WARN_ON(reason >= EXT4_FC_REASON_MAX);
+@@ -1213,7 +1213,7 @@ int ext4_fc_commit(journal_t *journal, tid_t commit_tid)
+ if (ret == -EALREADY) {
+ /* There was an ongoing commit, check if we need to restart */
+ if (atomic_read(&sbi->s_fc_subtid) <= subtid &&
+- commit_tid > journal->j_commit_sequence)
++ tid_gt(commit_tid, journal->j_commit_sequence))
+ goto restart_fc;
+ ext4_fc_update_stats(sb, EXT4_FC_STATUS_SKIPPED, 0, 0,
+ commit_tid);
+@@ -1288,7 +1288,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
+ list_del_init(&iter->i_fc_list);
+ ext4_clear_inode_state(&iter->vfs_inode,
+ EXT4_STATE_FC_COMMITTING);
+- if (iter->i_sync_tid <= tid)
++ if (tid_geq(tid, iter->i_sync_tid))
+ ext4_fc_reset_inode(&iter->vfs_inode);
+ /* Make sure EXT4_STATE_FC_COMMITTING bit is clear */
+ smp_mb();
+@@ -1319,7 +1319,7 @@ static void ext4_fc_cleanup(journal_t *journal, int full, tid_t tid)
+ list_splice_init(&sbi->s_fc_q[FC_Q_STAGING],
+ &sbi->s_fc_q[FC_Q_MAIN]);
+
+- if (tid >= sbi->s_fc_ineligible_tid) {
++ if (tid_geq(tid, sbi->s_fc_ineligible_tid)) {
+ sbi->s_fc_ineligible_tid = 0;
+ ext4_clear_mount_flag(sb, EXT4_MF_FC_INELIGIBLE);
+ }
+diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
+index 7146038b2fe7d..f0c9cd1a0b397 100644
+--- a/fs/fuse/dev.c
++++ b/fs/fuse/dev.c
+@@ -31,6 +31,8 @@ MODULE_ALIAS("devname:fuse");
+
+ static struct kmem_cache *fuse_req_cachep;
+
++static void end_requests(struct list_head *head);
++
+ static struct fuse_dev *fuse_get_dev(struct file *file)
+ {
+ /*
+@@ -773,7 +775,6 @@ static int fuse_check_folio(struct folio *folio)
+ (folio->flags & PAGE_FLAGS_CHECK_AT_PREP &
+ ~(1 << PG_locked |
+ 1 << PG_referenced |
+- 1 << PG_uptodate |
+ 1 << PG_lru |
+ 1 << PG_active |
+ 1 << PG_workingset |
+@@ -818,9 +819,7 @@ static int fuse_try_move_page(struct fuse_copy_state *cs, struct page **pagep)
+
+ newfolio = page_folio(buf->page);
+
+- if (!folio_test_uptodate(newfolio))
+- folio_mark_uptodate(newfolio);
+-
++ folio_clear_uptodate(newfolio);
+ folio_clear_mappedtodisk(newfolio);
+
+ if (fuse_check_folio(newfolio) != 0)
+@@ -1822,6 +1821,13 @@ static void fuse_resend(struct fuse_conn *fc)
+ }
+
+ spin_lock(&fiq->lock);
++ if (!fiq->connected) {
++ spin_unlock(&fiq->lock);
++ list_for_each_entry(req, &to_queue, list)
++ clear_bit(FR_PENDING, &req->flags);
++ end_requests(&to_queue);
++ return;
++ }
+ /* iq and pq requests are both oldest to newest */
+ list_splice(&to_queue, &fiq->pending);
+ fiq->ops->wake_pending_and_unlock(fiq);
+diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
+index 2b0d4781f3948..8e96df9fd76c9 100644
+--- a/fs/fuse/dir.c
++++ b/fs/fuse/dir.c
+@@ -670,7 +670,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
+
+ err = get_create_ext(&args, dir, entry, mode);
+ if (err)
+- goto out_put_forget_req;
++ goto out_free_ff;
+
+ err = fuse_simple_request(fm, &args);
+ free_ext_value(&args);
+diff --git a/fs/fuse/file.c b/fs/fuse/file.c
+index f39456c65ed7f..ed76121f73f2e 100644
+--- a/fs/fuse/file.c
++++ b/fs/fuse/file.c
+@@ -1832,10 +1832,16 @@ __acquires(fi->lock)
+ fuse_writepage_finish(fm, wpa);
+ spin_unlock(&fi->lock);
+
+- /* After fuse_writepage_finish() aux request list is private */
++ /* After rb_erase() aux request list is private */
+ for (aux = wpa->next; aux; aux = next) {
++ struct backing_dev_info *bdi = inode_to_bdi(aux->inode);
++
+ next = aux->next;
+ aux->next = NULL;
++
++ dec_wb_stat(&bdi->wb, WB_WRITEBACK);
++ dec_node_page_state(aux->ia.ap.pages[0], NR_WRITEBACK_TEMP);
++ wb_writeout_inc(&bdi->wb);
+ fuse_writepage_free(aux);
+ }
+
+diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
+index 32fe6fa72f460..57863e7739821 100644
+--- a/fs/fuse/inode.c
++++ b/fs/fuse/inode.c
+@@ -1336,11 +1336,16 @@ static void process_init_reply(struct fuse_mount *fm, struct fuse_args *args,
+ * on a stacked fs (e.g. overlayfs) themselves and with
+ * max_stack_depth == 1, FUSE fs can be stacked as the
+ * underlying fs of a stacked fs (e.g. overlayfs).
++ *
++ * Also don't allow the combination of FUSE_PASSTHROUGH
++ * and FUSE_WRITEBACK_CACHE, current design doesn't handle
++ * them together.
+ */
+ if (IS_ENABLED(CONFIG_FUSE_PASSTHROUGH) &&
+ (flags & FUSE_PASSTHROUGH) &&
+ arg->max_stack_depth > 0 &&
+- arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH) {
++ arg->max_stack_depth <= FILESYSTEM_MAX_STACK_DEPTH &&
++ !(flags & FUSE_WRITEBACK_CACHE)) {
+ fc->passthrough = 1;
+ fc->max_stack_depth = arg->max_stack_depth;
+ fm->sb->s_stack_depth = arg->max_stack_depth;
+diff --git a/fs/fuse/xattr.c b/fs/fuse/xattr.c
+index 5b423fdbb13f8..9f568d345c512 100644
+--- a/fs/fuse/xattr.c
++++ b/fs/fuse/xattr.c
+@@ -81,7 +81,7 @@ ssize_t fuse_getxattr(struct inode *inode, const char *name, void *value,
+ }
+ ret = fuse_simple_request(fm, &args);
+ if (!ret && !size)
+- ret = min_t(ssize_t, outarg.size, XATTR_SIZE_MAX);
++ ret = min_t(size_t, outarg.size, XATTR_SIZE_MAX);
+ if (ret == -ENOSYS) {
+ fm->fc->no_getxattr = 1;
+ ret = -EOPNOTSUPP;
+@@ -143,7 +143,7 @@ ssize_t fuse_listxattr(struct dentry *entry, char *list, size_t size)
+ }
+ ret = fuse_simple_request(fm, &args);
+ if (!ret && !size)
+- ret = min_t(ssize_t, outarg.size, XATTR_LIST_MAX);
++ ret = min_t(size_t, outarg.size, XATTR_LIST_MAX);
+ if (ret > 0 && size)
+ ret = fuse_verify_xattr_list(list, ret);
+ if (ret == -ENOSYS) {
+diff --git a/fs/jbd2/recovery.c b/fs/jbd2/recovery.c
+index 1f7664984d6e4..0d14b5f39be6a 100644
+--- a/fs/jbd2/recovery.c
++++ b/fs/jbd2/recovery.c
+@@ -443,6 +443,27 @@ static int jbd2_commit_block_csum_verify(journal_t *j, void *buf)
+ return provided == cpu_to_be32(calculated);
+ }
+
++static bool jbd2_commit_block_csum_verify_partial(journal_t *j, void *buf)
++{
++ struct commit_header *h;
++ __be32 provided;
++ __u32 calculated;
++ void *tmpbuf;
++
++ tmpbuf = kzalloc(j->j_blocksize, GFP_KERNEL);
++ if (!tmpbuf)
++ return false;
++
++ memcpy(tmpbuf, buf, sizeof(struct commit_header));
++ h = tmpbuf;
++ provided = h->h_chksum[0];
++ h->h_chksum[0] = 0;
++ calculated = jbd2_chksum(j, j->j_csum_seed, tmpbuf, j->j_blocksize);
++ kfree(tmpbuf);
++
++ return provided == cpu_to_be32(calculated);
++}
++
+ static int jbd2_block_tag_csum_verify(journal_t *j, journal_block_tag_t *tag,
+ journal_block_tag3_t *tag3,
+ void *buf, __u32 sequence)
+@@ -810,6 +831,13 @@ static int do_one_pass(journal_t *journal,
+ if (pass == PASS_SCAN &&
+ !jbd2_commit_block_csum_verify(journal,
+ bh->b_data)) {
++ if (jbd2_commit_block_csum_verify_partial(
++ journal,
++ bh->b_data)) {
++ pr_notice("JBD2: Find incomplete commit block in transaction %u block %lu\n",
++ next_commit_ID, next_log_block);
++ goto chksum_ok;
++ }
+ chksum_error:
+ if (commit_time < last_trans_commit_time)
+ goto ignore_crc_mismatch;
+@@ -824,6 +852,7 @@ static int do_one_pass(journal_t *journal,
+ }
+ }
+ if (pass == PASS_SCAN) {
++ chksum_ok:
+ last_trans_commit_time = commit_time;
+ head_block = next_log_block;
+ }
+@@ -843,6 +872,7 @@ static int do_one_pass(journal_t *journal,
+ next_log_block);
+ need_check_commit_time = true;
+ }
++
+ /* If we aren't in the REVOKE pass, then we can
+ * just skip over this block. */
+ if (pass != PASS_REVOKE) {
+diff --git a/fs/libfs.c b/fs/libfs.c
+index 65279e53fbf27..bb7d6e523ee34 100644
+--- a/fs/libfs.c
++++ b/fs/libfs.c
+@@ -2043,12 +2043,12 @@ struct timespec64 simple_inode_init_ts(struct inode *inode)
+ }
+ EXPORT_SYMBOL(simple_inode_init_ts);
+
+-static inline struct dentry *get_stashed_dentry(struct dentry *stashed)
++static inline struct dentry *get_stashed_dentry(struct dentry **stashed)
+ {
+ struct dentry *dentry;
+
+ guard(rcu)();
+- dentry = READ_ONCE(stashed);
++ dentry = rcu_dereference(*stashed);
+ if (!dentry)
+ return NULL;
+ if (!lockref_get_not_dead(&dentry->d_lockref))
+@@ -2145,7 +2145,7 @@ int path_from_stashed(struct dentry **stashed, struct vfsmount *mnt, void *data,
+ const struct stashed_operations *sops = mnt->mnt_sb->s_fs_info;
+
+ /* See if dentry can be reused. */
+- path->dentry = get_stashed_dentry(*stashed);
++ path->dentry = get_stashed_dentry(stashed);
+ if (path->dentry) {
+ sops->put_data(data);
+ goto out_path;
+diff --git a/fs/namespace.c b/fs/namespace.c
+index 5a51315c66781..e1ced589d8357 100644
+--- a/fs/namespace.c
++++ b/fs/namespace.c
+@@ -4906,6 +4906,7 @@ static int copy_statmount_to_user(struct kstatmount *s)
+ static int do_statmount(struct kstatmount *s)
+ {
+ struct mount *m = real_mount(s->mnt);
++ struct mnt_namespace *ns = m->mnt_ns;
+ int err;
+
+ /*
+@@ -4913,7 +4914,7 @@ static int do_statmount(struct kstatmount *s)
+ * mounts to show users.
+ */
+ if (!is_path_reachable(m, m->mnt.mnt_root, &s->root) &&
+- !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
++ !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+ err = security_sb_statfs(s->mnt->mnt_root);
+@@ -5047,32 +5048,50 @@ static struct mount *listmnt_next(struct mount *curr)
+ return node_to_mount(rb_next(&curr->mnt_node));
+ }
+
+-static ssize_t do_listmount(struct mount *first, struct path *orig,
+- u64 mnt_parent_id, u64 __user *mnt_ids,
+- size_t nr_mnt_ids, const struct path *root)
++static ssize_t do_listmount(u64 mnt_parent_id, u64 last_mnt_id, u64 *mnt_ids,
++ size_t nr_mnt_ids)
+ {
+- struct mount *r;
++ struct path root __free(path_put) = {};
++ struct mnt_namespace *ns = current->nsproxy->mnt_ns;
++ struct path orig;
++ struct mount *r, *first;
+ ssize_t ret;
+
++ rwsem_assert_held(&namespace_sem);
++
++ get_fs_root(current->fs, &root);
++ if (mnt_parent_id == LSMT_ROOT) {
++ orig = root;
++ } else {
++ orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns);
++ if (!orig.mnt)
++ return -ENOENT;
++ orig.dentry = orig.mnt->mnt_root;
++ }
++
+ /*
+ * Don't trigger audit denials. We just want to determine what
+ * mounts to show users.
+ */
+- if (!is_path_reachable(real_mount(orig->mnt), orig->dentry, root) &&
+- !ns_capable_noaudit(&init_user_ns, CAP_SYS_ADMIN))
++ if (!is_path_reachable(real_mount(orig.mnt), orig.dentry, &root) &&
++ !ns_capable_noaudit(ns->user_ns, CAP_SYS_ADMIN))
+ return -EPERM;
+
+- ret = security_sb_statfs(orig->dentry);
++ ret = security_sb_statfs(orig.dentry);
+ if (ret)
+ return ret;
+
++ if (!last_mnt_id)
++ first = node_to_mount(rb_first(&ns->mounts));
++ else
++ first = mnt_find_id_at(ns, last_mnt_id + 1);
++
+ for (ret = 0, r = first; r && nr_mnt_ids; r = listmnt_next(r)) {
+ if (r->mnt_id_unique == mnt_parent_id)
+ continue;
+- if (!is_path_reachable(r, r->mnt.mnt_root, orig))
++ if (!is_path_reachable(r, r->mnt.mnt_root, &orig))
+ continue;
+- if (put_user(r->mnt_id_unique, mnt_ids))
+- return -EFAULT;
++ *mnt_ids = r->mnt_id_unique;
+ mnt_ids++;
+ nr_mnt_ids--;
+ ret++;
+@@ -5080,22 +5099,24 @@ static ssize_t do_listmount(struct mount *first, struct path *orig,
+ return ret;
+ }
+
+-SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *,
+- mnt_ids, size_t, nr_mnt_ids, unsigned int, flags)
++SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req,
++ u64 __user *, mnt_ids, size_t, nr_mnt_ids, unsigned int, flags)
+ {
+- struct mnt_namespace *ns = current->nsproxy->mnt_ns;
++ u64 *kmnt_ids __free(kvfree) = NULL;
++ const size_t maxcount = 1000000;
+ struct mnt_id_req kreq;
+- struct mount *first;
+- struct path root, orig;
+- u64 mnt_parent_id, last_mnt_id;
+- const size_t maxcount = (size_t)-1 >> 3;
+ ssize_t ret;
+
+ if (flags)
+ return -EINVAL;
+
++ /*
++ * If the mount namespace really has more than 1 million mounts the
++ * caller must iterate over the mount namespace (and reconsider their
++ * system design...).
++ */
+ if (unlikely(nr_mnt_ids > maxcount))
+- return -EFAULT;
++ return -EOVERFLOW;
+
+ if (!access_ok(mnt_ids, nr_mnt_ids * sizeof(*mnt_ids)))
+ return -EFAULT;
+@@ -5103,33 +5124,23 @@ SYSCALL_DEFINE4(listmount, const struct mnt_id_req __user *, req, u64 __user *,
+ ret = copy_mnt_id_req(req, &kreq);
+ if (ret)
+ return ret;
+- mnt_parent_id = kreq.mnt_id;
+- last_mnt_id = kreq.param;
+
+- down_read(&namespace_sem);
+- get_fs_root(current->fs, &root);
+- if (mnt_parent_id == LSMT_ROOT) {
+- orig = root;
+- } else {
+- ret = -ENOENT;
+- orig.mnt = lookup_mnt_in_ns(mnt_parent_id, ns);
+- if (!orig.mnt)
+- goto err;
+- orig.dentry = orig.mnt->mnt_root;
+- }
+- if (!last_mnt_id)
+- first = node_to_mount(rb_first(&ns->mounts));
+- else
+- first = mnt_find_id_at(ns, last_mnt_id + 1);
++ kmnt_ids = kvmalloc_array(nr_mnt_ids, sizeof(*kmnt_ids),
++ GFP_KERNEL_ACCOUNT);
++ if (!kmnt_ids)
++ return -ENOMEM;
++
++ scoped_guard(rwsem_read, &namespace_sem)
++ ret = do_listmount(kreq.mnt_id, kreq.param, kmnt_ids, nr_mnt_ids);
++ if (ret <= 0)
++ return ret;
++
++ if (copy_to_user(mnt_ids, kmnt_ids, ret * sizeof(*mnt_ids)))
++ return -EFAULT;
+
+- ret = do_listmount(first, &orig, mnt_parent_id, mnt_ids, nr_mnt_ids, &root);
+-err:
+- path_put(&root);
+- up_read(&namespace_sem);
+ return ret;
+ }
+
+-
+ static void __init init_mount_tree(void)
+ {
+ struct vfsmount *mnt;
+diff --git a/fs/netfs/fscache_main.c b/fs/netfs/fscache_main.c
+index bf9b33d26e312..8e0aacbcfc8e6 100644
+--- a/fs/netfs/fscache_main.c
++++ b/fs/netfs/fscache_main.c
+@@ -103,6 +103,7 @@ void __exit fscache_exit(void)
+
+ kmem_cache_destroy(fscache_cookie_jar);
+ fscache_proc_cleanup();
++ timer_shutdown_sync(&fscache_cookie_lru_timer);
+ destroy_workqueue(fscache_wq);
+ pr_notice("FS-Cache unloaded\n");
+ }
+diff --git a/fs/netfs/io.c b/fs/netfs/io.c
+index c96431d3da6d8..c91e7b12bbf18 100644
+--- a/fs/netfs/io.c
++++ b/fs/netfs/io.c
+@@ -306,6 +306,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
+ break;
+ subreq->source = NETFS_DOWNLOAD_FROM_SERVER;
+ subreq->error = 0;
++ __set_bit(NETFS_SREQ_RETRYING, &subreq->flags);
+ netfs_stat(&netfs_n_rh_download_instead);
+ trace_netfs_sreq(subreq, netfs_sreq_trace_download_instead);
+ netfs_get_subrequest(subreq, netfs_sreq_trace_get_resubmit);
+@@ -313,6 +314,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
+ netfs_reset_subreq_iter(rreq, subreq);
+ netfs_read_from_server(rreq, subreq);
+ } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
++ __set_bit(NETFS_SREQ_RETRYING, &subreq->flags);
+ netfs_reset_subreq_iter(rreq, subreq);
+ netfs_rreq_short_read(rreq, subreq);
+ }
+@@ -366,7 +368,8 @@ static void netfs_rreq_assess_dio(struct netfs_io_request *rreq)
+ if (subreq->error || subreq->transferred == 0)
+ break;
+ transferred += subreq->transferred;
+- if (subreq->transferred < subreq->len)
++ if (subreq->transferred < subreq->len ||
++ test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags))
+ break;
+ }
+
+@@ -501,7 +504,8 @@ void netfs_subreq_terminated(struct netfs_io_subrequest *subreq,
+
+ subreq->error = 0;
+ subreq->transferred += transferred_or_error;
+- if (subreq->transferred < subreq->len)
++ if (subreq->transferred < subreq->len &&
++ !test_bit(NETFS_SREQ_HIT_EOF, &subreq->flags))
+ goto incomplete;
+
+ complete:
+@@ -775,10 +779,13 @@ int netfs_begin_read(struct netfs_io_request *rreq, bool sync)
+ TASK_UNINTERRUPTIBLE);
+
+ ret = rreq->error;
+- if (ret == 0 && rreq->submitted < rreq->len &&
+- rreq->origin != NETFS_DIO_READ) {
+- trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
+- ret = -EIO;
++ if (ret == 0) {
++ if (rreq->origin == NETFS_DIO_READ) {
++ ret = rreq->transferred;
++ } else if (rreq->submitted < rreq->len) {
++ trace_netfs_failure(rreq, NULL, ret, netfs_fail_short_read);
++ ret = -EIO;
++ }
+ }
+ } else {
+ /* If we decrement nr_outstanding to 0, the ref belongs to us. */
+diff --git a/fs/nfs/super.c b/fs/nfs/super.c
+index cbbd4866b0b7a..97b386032b717 100644
+--- a/fs/nfs/super.c
++++ b/fs/nfs/super.c
+@@ -47,6 +47,7 @@
+ #include <linux/vfs.h>
+ #include <linux/inet.h>
+ #include <linux/in6.h>
++#include <linux/sched.h>
+ #include <linux/slab.h>
+ #include <net/ipv6.h>
+ #include <linux/netdevice.h>
+@@ -228,6 +229,7 @@ static int __nfs_list_for_each_server(struct list_head *head,
+ ret = fn(server, data);
+ if (ret)
+ goto out;
++ cond_resched();
+ rcu_read_lock();
+ }
+ rcu_read_unlock();
+diff --git a/fs/nilfs2/recovery.c b/fs/nilfs2/recovery.c
+index b638dc06df2f7..61e25a980f73e 100644
+--- a/fs/nilfs2/recovery.c
++++ b/fs/nilfs2/recovery.c
+@@ -715,6 +715,33 @@ static void nilfs_finish_roll_forward(struct the_nilfs *nilfs,
+ brelse(bh);
+ }
+
++/**
++ * nilfs_abort_roll_forward - cleaning up after a failed rollforward recovery
++ * @nilfs: nilfs object
++ */
++static void nilfs_abort_roll_forward(struct the_nilfs *nilfs)
++{
++ struct nilfs_inode_info *ii, *n;
++ LIST_HEAD(head);
++
++ /* Abandon inodes that have read recovery data */
++ spin_lock(&nilfs->ns_inode_lock);
++ list_splice_init(&nilfs->ns_dirty_files, &head);
++ spin_unlock(&nilfs->ns_inode_lock);
++ if (list_empty(&head))
++ return;
++
++ set_nilfs_purging(nilfs);
++ list_for_each_entry_safe(ii, n, &head, i_dirty) {
++ spin_lock(&nilfs->ns_inode_lock);
++ list_del_init(&ii->i_dirty);
++ spin_unlock(&nilfs->ns_inode_lock);
++
++ iput(&ii->vfs_inode);
++ }
++ clear_nilfs_purging(nilfs);
++}
++
+ /**
+ * nilfs_salvage_orphan_logs - salvage logs written after the latest checkpoint
+ * @nilfs: nilfs object
+@@ -773,15 +800,19 @@ int nilfs_salvage_orphan_logs(struct the_nilfs *nilfs,
+ if (unlikely(err)) {
+ nilfs_err(sb, "error %d writing segment for recovery",
+ err);
+- goto failed;
++ goto put_root;
+ }
+
+ nilfs_finish_roll_forward(nilfs, ri);
+ }
+
+- failed:
++put_root:
+ nilfs_put_root(root);
+ return err;
++
++failed:
++ nilfs_abort_roll_forward(nilfs);
++ goto put_root;
+ }
+
+ /**
+diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
+index d02fd92cdb432..f090f19df3e3b 100644
+--- a/fs/nilfs2/segment.c
++++ b/fs/nilfs2/segment.c
+@@ -1788,6 +1788,9 @@ static void nilfs_segctor_abort_construction(struct nilfs_sc_info *sci,
+ nilfs_abort_logs(&logs, ret ? : err);
+
+ list_splice_tail_init(&sci->sc_segbufs, &logs);
++ if (list_empty(&logs))
++ return; /* if the first segment buffer preparation failed */
++
+ nilfs_cancel_segusage(&logs, nilfs->ns_sufile);
+ nilfs_free_incomplete_logs(&logs, nilfs);
+
+@@ -2032,7 +2035,7 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
+
+ err = nilfs_segctor_begin_construction(sci, nilfs);
+ if (unlikely(err))
+- goto out;
++ goto failed;
+
+ /* Update time stamp */
+ sci->sc_seg_ctime = ktime_get_real_seconds();
+@@ -2099,10 +2102,9 @@ static int nilfs_segctor_do_construct(struct nilfs_sc_info *sci, int mode)
+ return err;
+
+ failed_to_write:
+- if (sci->sc_stage.flags & NILFS_CF_IFILE_STARTED)
+- nilfs_redirty_inodes(&sci->sc_dirty_files);
+-
+ failed:
++ if (mode == SC_LSEG_SR && nilfs_sc_cstage_get(sci) >= NILFS_ST_IFILE)
++ nilfs_redirty_inodes(&sci->sc_dirty_files);
+ if (nilfs_doing_gc())
+ nilfs_redirty_inodes(&sci->sc_gc_inodes);
+ nilfs_segctor_abort_construction(sci, nilfs, err);
+diff --git a/fs/nilfs2/sysfs.c b/fs/nilfs2/sysfs.c
+index 379d22e28ed62..905c7eadf9676 100644
+--- a/fs/nilfs2/sysfs.c
++++ b/fs/nilfs2/sysfs.c
+@@ -836,9 +836,15 @@ ssize_t nilfs_dev_revision_show(struct nilfs_dev_attr *attr,
+ struct the_nilfs *nilfs,
+ char *buf)
+ {
+- struct nilfs_super_block **sbp = nilfs->ns_sbp;
+- u32 major = le32_to_cpu(sbp[0]->s_rev_level);
+- u16 minor = le16_to_cpu(sbp[0]->s_minor_rev_level);
++ struct nilfs_super_block *raw_sb;
++ u32 major;
++ u16 minor;
++
++ down_read(&nilfs->ns_sem);
++ raw_sb = nilfs->ns_sbp[0];
++ major = le32_to_cpu(raw_sb->s_rev_level);
++ minor = le16_to_cpu(raw_sb->s_minor_rev_level);
++ up_read(&nilfs->ns_sem);
+
+ return sysfs_emit(buf, "%d.%d\n", major, minor);
+ }
+@@ -856,8 +862,13 @@ ssize_t nilfs_dev_device_size_show(struct nilfs_dev_attr *attr,
+ struct the_nilfs *nilfs,
+ char *buf)
+ {
+- struct nilfs_super_block **sbp = nilfs->ns_sbp;
+- u64 dev_size = le64_to_cpu(sbp[0]->s_dev_size);
++ struct nilfs_super_block *raw_sb;
++ u64 dev_size;
++
++ down_read(&nilfs->ns_sem);
++ raw_sb = nilfs->ns_sbp[0];
++ dev_size = le64_to_cpu(raw_sb->s_dev_size);
++ up_read(&nilfs->ns_sem);
+
+ return sysfs_emit(buf, "%llu\n", dev_size);
+ }
+@@ -879,9 +890,15 @@ ssize_t nilfs_dev_uuid_show(struct nilfs_dev_attr *attr,
+ struct the_nilfs *nilfs,
+ char *buf)
+ {
+- struct nilfs_super_block **sbp = nilfs->ns_sbp;
++ struct nilfs_super_block *raw_sb;
++ ssize_t len;
+
+- return sysfs_emit(buf, "%pUb\n", sbp[0]->s_uuid);
++ down_read(&nilfs->ns_sem);
++ raw_sb = nilfs->ns_sbp[0];
++ len = sysfs_emit(buf, "%pUb\n", raw_sb->s_uuid);
++ up_read(&nilfs->ns_sem);
++
++ return len;
+ }
+
+ static
+@@ -889,10 +906,16 @@ ssize_t nilfs_dev_volume_name_show(struct nilfs_dev_attr *attr,
+ struct the_nilfs *nilfs,
+ char *buf)
+ {
+- struct nilfs_super_block **sbp = nilfs->ns_sbp;
++ struct nilfs_super_block *raw_sb;
++ ssize_t len;
++
++ down_read(&nilfs->ns_sem);
++ raw_sb = nilfs->ns_sbp[0];
++ len = scnprintf(buf, sizeof(raw_sb->s_volume_name), "%s\n",
++ raw_sb->s_volume_name);
++ up_read(&nilfs->ns_sem);
+
+- return scnprintf(buf, sizeof(sbp[0]->s_volume_name), "%s\n",
+- sbp[0]->s_volume_name);
++ return len;
+ }
+
+ static const char dev_readme_str[] =
+diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
+index 858efe255f6f3..1ec09f2fca64a 100644
+--- a/fs/ntfs3/dir.c
++++ b/fs/ntfs3/dir.c
+@@ -272,9 +272,12 @@ struct inode *dir_search_u(struct inode *dir, const struct cpu_str *uni,
+ return err == -ENOENT ? NULL : err ? ERR_PTR(err) : inode;
+ }
+
+-static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+- const struct NTFS_DE *e, u8 *name,
+- struct dir_context *ctx)
++/*
++ * returns false if 'ctx' if full
++ */
++static inline bool ntfs_dir_emit(struct ntfs_sb_info *sbi,
++ struct ntfs_inode *ni, const struct NTFS_DE *e,
++ u8 *name, struct dir_context *ctx)
+ {
+ const struct ATTR_FILE_NAME *fname;
+ unsigned long ino;
+@@ -284,29 +287,29 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+ fname = Add2Ptr(e, sizeof(struct NTFS_DE));
+
+ if (fname->type == FILE_NAME_DOS)
+- return 0;
++ return true;
+
+ if (!mi_is_ref(&ni->mi, &fname->home))
+- return 0;
++ return true;
+
+ ino = ino_get(&e->ref);
+
+ if (ino == MFT_REC_ROOT)
+- return 0;
++ return true;
+
+ /* Skip meta files. Unless option to show metafiles is set. */
+ if (!sbi->options->showmeta && ntfs_is_meta_file(sbi, ino))
+- return 0;
++ return true;
+
+ if (sbi->options->nohidden && (fname->dup.fa & FILE_ATTRIBUTE_HIDDEN))
+- return 0;
++ return true;
+
+ name_len = ntfs_utf16_to_nls(sbi, fname->name, fname->name_len, name,
+ PATH_MAX);
+ if (name_len <= 0) {
+ ntfs_warn(sbi->sb, "failed to convert name for inode %lx.",
+ ino);
+- return 0;
++ return true;
+ }
+
+ /*
+@@ -336,17 +339,20 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+ }
+ }
+
+- return !dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
++ return dir_emit(ctx, (s8 *)name, name_len, ino, dt_type);
+ }
+
+ /*
+ * ntfs_read_hdr - Helper function for ntfs_readdir().
++ *
++ * returns 0 if ok.
++ * returns -EINVAL if directory is corrupted.
++ * returns +1 if 'ctx' is full.
+ */
+ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+ const struct INDEX_HDR *hdr, u64 vbo, u64 pos,
+ u8 *name, struct dir_context *ctx)
+ {
+- int err;
+ const struct NTFS_DE *e;
+ u32 e_size;
+ u32 end = le32_to_cpu(hdr->used);
+@@ -354,12 +360,12 @@ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+
+ for (;; off += e_size) {
+ if (off + sizeof(struct NTFS_DE) > end)
+- return -1;
++ return -EINVAL;
+
+ e = Add2Ptr(hdr, off);
+ e_size = le16_to_cpu(e->size);
+ if (e_size < sizeof(struct NTFS_DE) || off + e_size > end)
+- return -1;
++ return -EINVAL;
+
+ if (de_is_last(e))
+ return 0;
+@@ -369,14 +375,15 @@ static int ntfs_read_hdr(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+ continue;
+
+ if (le16_to_cpu(e->key_size) < SIZEOF_ATTRIBUTE_FILENAME)
+- return -1;
++ return -EINVAL;
+
+ ctx->pos = vbo + off;
+
+ /* Submit the name to the filldir callback. */
+- err = ntfs_filldir(sbi, ni, e, name, ctx);
+- if (err)
+- return err;
++ if (!ntfs_dir_emit(sbi, ni, e, name, ctx)) {
++ /* ctx is full. */
++ return +1;
++ }
+ }
+ }
+
+@@ -475,8 +482,6 @@ static int ntfs_readdir(struct file *file, struct dir_context *ctx)
+
+ vbo = (u64)bit << index_bits;
+ if (vbo >= i_size) {
+- ntfs_inode_err(dir, "Looks like your dir is corrupt");
+- ctx->pos = eod;
+ err = -EINVAL;
+ goto out;
+ }
+@@ -499,9 +504,16 @@ static int ntfs_readdir(struct file *file, struct dir_context *ctx)
+ __putname(name);
+ put_indx_node(node);
+
+- if (err == -ENOENT) {
++ if (err == 1) {
++ /* 'ctx' is full. */
++ err = 0;
++ } else if (err == -ENOENT) {
+ err = 0;
+ ctx->pos = pos;
++ } else if (err < 0) {
++ if (err == -EINVAL)
++ ntfs_inode_err(dir, "directory corrupted");
++ ctx->pos = eod;
+ }
+
+ return err;
+diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
+index ded451a84b773..7a73df871037a 100644
+--- a/fs/ntfs3/frecord.c
++++ b/fs/ntfs3/frecord.c
+@@ -1601,8 +1601,10 @@ int ni_delete_all(struct ntfs_inode *ni)
+ asize = le32_to_cpu(attr->size);
+ roff = le16_to_cpu(attr->nres.run_off);
+
+- if (roff > asize)
++ if (roff > asize) {
++ _ntfs_bad_inode(&ni->vfs_inode);
+ return -EINVAL;
++ }
+
+ /* run==1 means unpack and deallocate. */
+ run_unpack_ex(RUN_DEALLOCATE, sbi, ni->mi.rno, svcn, evcn, svcn,
+diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
+index 2c4b357d85e22..a1acf5bd1e3a4 100644
+--- a/fs/smb/client/cifsfs.c
++++ b/fs/smb/client/cifsfs.c
+@@ -1341,7 +1341,6 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
+ struct cifsFileInfo *smb_file_target;
+ struct cifs_tcon *src_tcon;
+ struct cifs_tcon *target_tcon;
+- unsigned long long destend, fstart, fend;
+ ssize_t rc;
+
+ cifs_dbg(FYI, "copychunk range\n");
+@@ -1391,25 +1390,13 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
+ goto unlock;
+ }
+
+- destend = destoff + len - 1;
+-
+- /* Flush the folios at either end of the destination range to prevent
+- * accidental loss of dirty data outside of the range.
++ /* Flush and invalidate all the folios in the destination region. If
++ * the copy was successful, then some of the flush is extra overhead,
++ * but we need to allow for the copy failing in some way (eg. ENOSPC).
+ */
+- fstart = destoff;
+- fend = destend;
+-
+- rc = cifs_flush_folio(target_inode, destoff, &fstart, &fend, true);
++ rc = filemap_invalidate_inode(target_inode, true, destoff, destoff + len - 1);
+ if (rc)
+ goto unlock;
+- rc = cifs_flush_folio(target_inode, destend, &fstart, &fend, false);
+- if (rc)
+- goto unlock;
+- if (fend > target_cifsi->netfs.zero_point)
+- target_cifsi->netfs.zero_point = fend + 1;
+-
+- /* Discard all the folios that overlap the destination region. */
+- truncate_inode_pages_range(&target_inode->i_data, fstart, fend);
+
+ fscache_invalidate(cifs_inode_cookie(target_inode), NULL,
+ i_size_read(target_inode), 0);
+diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
+index 1e4da268de3b4..552792f28122c 100644
+--- a/fs/smb/client/cifsglob.h
++++ b/fs/smb/client/cifsglob.h
+@@ -1508,6 +1508,7 @@ struct cifs_io_subrequest {
+ struct cifs_io_request *req;
+ };
+ ssize_t got_bytes;
++ size_t actual_len;
+ unsigned int xid;
+ int result;
+ bool have_xid;
+diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
+index 6dce70f172082..cfae2e9182099 100644
+--- a/fs/smb/client/cifssmb.c
++++ b/fs/smb/client/cifssmb.c
+@@ -1261,16 +1261,32 @@ CIFS_open(const unsigned int xid, struct cifs_open_parms *oparms, int *oplock,
+ return rc;
+ }
+
++static void cifs_readv_worker(struct work_struct *work)
++{
++ struct cifs_io_subrequest *rdata =
++ container_of(work, struct cifs_io_subrequest, subreq.work);
++
++ netfs_subreq_terminated(&rdata->subreq,
++ (rdata->result == 0 || rdata->result == -EAGAIN) ?
++ rdata->got_bytes : rdata->result, true);
++}
++
+ static void
+ cifs_readv_callback(struct mid_q_entry *mid)
+ {
+ struct cifs_io_subrequest *rdata = mid->callback_data;
++ struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode);
+ struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
+ struct TCP_Server_Info *server = tcon->ses->server;
+ struct smb_rqst rqst = { .rq_iov = rdata->iov,
+ .rq_nvec = 2,
+ .rq_iter = rdata->subreq.io_iter };
+- struct cifs_credits credits = { .value = 1, .instance = 0 };
++ struct cifs_credits credits = {
++ .value = 1,
++ .instance = 0,
++ .rreq_debug_id = rdata->rreq->debug_id,
++ .rreq_debug_index = rdata->subreq.debug_index,
++ };
+
+ cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n",
+ __func__, mid->mid, mid->mid_state, rdata->result,
+@@ -1282,6 +1298,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
+ if (server->sign) {
+ int rc = 0;
+
++ iov_iter_truncate(&rqst.rq_iter, rdata->got_bytes);
+ rc = cifs_verify_signature(&rqst, server,
+ mid->sequence_number);
+ if (rc)
+@@ -1306,13 +1323,21 @@ cifs_readv_callback(struct mid_q_entry *mid)
+ rdata->result = -EIO;
+ }
+
+- if (rdata->result == 0 || rdata->result == -EAGAIN)
+- iov_iter_advance(&rdata->subreq.io_iter, rdata->got_bytes);
++ if (rdata->result == -ENODATA) {
++ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
++ rdata->result = 0;
++ } else {
++ if (rdata->got_bytes < rdata->actual_len &&
++ rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes ==
++ ictx->remote_i_size) {
++ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
++ rdata->result = 0;
++ }
++ }
++
+ rdata->credits.value = 0;
+- netfs_subreq_terminated(&rdata->subreq,
+- (rdata->result == 0 || rdata->result == -EAGAIN) ?
+- rdata->got_bytes : rdata->result,
+- false);
++ INIT_WORK(&rdata->subreq.work, cifs_readv_worker);
++ queue_work(cifsiod_wq, &rdata->subreq.work);
+ release_mid(mid);
+ add_credits(server, &credits, 0);
+ }
+@@ -1619,9 +1644,15 @@ static void
+ cifs_writev_callback(struct mid_q_entry *mid)
+ {
+ struct cifs_io_subrequest *wdata = mid->callback_data;
++ struct TCP_Server_Info *server = wdata->server;
+ struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
+ WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
+- struct cifs_credits credits = { .value = 1, .instance = 0 };
++ struct cifs_credits credits = {
++ .value = 1,
++ .instance = 0,
++ .rreq_debug_id = wdata->rreq->debug_id,
++ .rreq_debug_index = wdata->subreq.debug_index,
++ };
+ ssize_t result;
+ size_t written;
+
+@@ -1657,9 +1688,16 @@ cifs_writev_callback(struct mid_q_entry *mid)
+ break;
+ }
+
++ trace_smb3_rw_credits(credits.rreq_debug_id, credits.rreq_debug_index,
++ wdata->credits.value,
++ server->credits, server->in_flight,
++ 0, cifs_trace_rw_credits_write_response_clear);
+ wdata->credits.value = 0;
+ cifs_write_subrequest_terminated(wdata, result, true);
+ release_mid(mid);
++ trace_smb3_rw_credits(credits.rreq_debug_id, credits.rreq_debug_index, 0,
++ server->credits, server->in_flight,
++ credits.value, cifs_trace_rw_credits_write_response_add);
+ add_credits(tcon->ses->server, &credits, 0);
+ }
+
+diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
+index b202eac6584e1..533f761183160 100644
+--- a/fs/smb/client/file.c
++++ b/fs/smb/client/file.c
+@@ -111,6 +111,7 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq)
+ goto fail;
+ }
+
++ wdata->actual_len = wdata->subreq.len;
+ rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust);
+ if (rc)
+ goto fail;
+@@ -153,7 +154,7 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
+ struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
+ struct TCP_Server_Info *server = req->server;
+ struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
+- size_t rsize = 0;
++ size_t rsize;
+ int rc;
+
+ rdata->xid = get_xid();
+@@ -166,8 +167,8 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
+ cifs_sb->ctx);
+
+
+- rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize, &rsize,
+- &rdata->credits);
++ rc = server->ops->wait_mtu_credits(server, cifs_sb->ctx->rsize,
++ &rsize, &rdata->credits);
+ if (rc) {
+ subreq->error = rc;
+ return false;
+@@ -183,7 +184,8 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
+ server->credits, server->in_flight, 0,
+ cifs_trace_rw_credits_read_submit);
+
+- subreq->len = min_t(size_t, subreq->len, rsize);
++ subreq->len = umin(subreq->len, rsize);
++ rdata->actual_len = subreq->len;
+
+ #ifdef CONFIG_CIFS_SMB_DIRECT
+ if (server->smbd_conn)
+@@ -203,12 +205,39 @@ static void cifs_req_issue_read(struct netfs_io_subrequest *subreq)
+ struct netfs_io_request *rreq = subreq->rreq;
+ struct cifs_io_subrequest *rdata = container_of(subreq, struct cifs_io_subrequest, subreq);
+ struct cifs_io_request *req = container_of(subreq->rreq, struct cifs_io_request, rreq);
++ struct TCP_Server_Info *server = req->server;
++ struct cifs_sb_info *cifs_sb = CIFS_SB(rreq->inode->i_sb);
+ int rc = 0;
+
+ cifs_dbg(FYI, "%s: op=%08x[%x] mapping=%p len=%zu/%zu\n",
+ __func__, rreq->debug_id, subreq->debug_index, rreq->mapping,
+ subreq->transferred, subreq->len);
+
++ if (test_bit(NETFS_SREQ_RETRYING, &subreq->flags)) {
++ /*
++ * As we're issuing a retry, we need to negotiate some new
++ * credits otherwise the server may reject the op with
++ * INVALID_PARAMETER. Note, however, we may get back less
++ * credit than we need to complete the op, in which case, we
++ * shorten the op and rely on additional rounds of retry.
++ */
++ size_t rsize = umin(subreq->len - subreq->transferred,
++ cifs_sb->ctx->rsize);
++
++ rc = server->ops->wait_mtu_credits(server, rsize, &rdata->actual_len,
++ &rdata->credits);
++ if (rc)
++ goto out;
++
++ rdata->credits.in_flight_check = 1;
++
++ trace_smb3_rw_credits(rdata->rreq->debug_id,
++ rdata->subreq.debug_index,
++ rdata->credits.value,
++ server->credits, server->in_flight, 0,
++ cifs_trace_rw_credits_read_resubmit);
++ }
++
+ if (req->cfile->invalidHandle) {
+ do {
+ rc = cifs_reopen_file(req->cfile, true);
+diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
+index dd0afa23734c8..73e2e6c230b73 100644
+--- a/fs/smb/client/inode.c
++++ b/fs/smb/client/inode.c
+@@ -172,6 +172,8 @@ cifs_fattr_to_inode(struct inode *inode, struct cifs_fattr *fattr,
+ CIFS_I(inode)->time = 0; /* force reval */
+ return -ESTALE;
+ }
++ if (inode->i_state & I_NEW)
++ CIFS_I(inode)->netfs.zero_point = fattr->cf_eof;
+
+ cifs_revalidate_cache(inode, fattr);
+
+diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
+index 9f5bc41433c15..11a1c53c64e0b 100644
+--- a/fs/smb/client/smb2inode.c
++++ b/fs/smb/client/smb2inode.c
+@@ -1106,6 +1106,8 @@ int smb2_rename_path(const unsigned int xid,
+ co, DELETE, SMB2_OP_RENAME, cfile, source_dentry);
+ if (rc == -EINVAL) {
+ cifs_dbg(FYI, "invalid lease key, resending request without lease");
++ cifs_get_writable_path(tcon, from_name,
++ FIND_WR_WITH_DELETE, &cfile);
+ rc = smb2_set_path_attr(xid, tcon, from_name, to_name, cifs_sb,
+ co, DELETE, SMB2_OP_RENAME, cfile, NULL);
+ }
+@@ -1149,6 +1151,7 @@ smb2_set_path_size(const unsigned int xid, struct cifs_tcon *tcon,
+ cfile, NULL, NULL, dentry);
+ if (rc == -EINVAL) {
+ cifs_dbg(FYI, "invalid lease key, resending request without lease");
++ cifs_get_writable_path(tcon, full_path, FIND_WR_ANY, &cfile);
+ rc = smb2_compound_op(xid, tcon, cifs_sb,
+ full_path, &oparms, &in_iov,
+ &(int){SMB2_OP_SET_EOF}, 1,
+diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
+index f44f5f2494006..1d6e8eacdd742 100644
+--- a/fs/smb/client/smb2ops.c
++++ b/fs/smb/client/smb2ops.c
+@@ -301,7 +301,7 @@ smb2_adjust_credits(struct TCP_Server_Info *server,
+ unsigned int /*enum smb3_rw_credits_trace*/ trace)
+ {
+ struct cifs_credits *credits = &subreq->credits;
+- int new_val = DIV_ROUND_UP(subreq->subreq.len, SMB2_MAX_BUFFER_SIZE);
++ int new_val = DIV_ROUND_UP(subreq->actual_len, SMB2_MAX_BUFFER_SIZE);
+ int scredits, in_flight;
+
+ if (!credits->value || credits->value == new_val)
+@@ -3219,13 +3219,15 @@ static long smb3_zero_data(struct file *file, struct cifs_tcon *tcon,
+ }
+
+ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
+- loff_t offset, loff_t len, bool keep_size)
++ unsigned long long offset, unsigned long long len,
++ bool keep_size)
+ {
+ struct cifs_ses *ses = tcon->ses;
+ struct inode *inode = file_inode(file);
+ struct cifsInodeInfo *cifsi = CIFS_I(inode);
+ struct cifsFileInfo *cfile = file->private_data;
+- unsigned long long new_size;
++ struct netfs_inode *ictx = netfs_inode(inode);
++ unsigned long long i_size, new_size, remote_size;
+ long rc;
+ unsigned int xid;
+
+@@ -3237,6 +3239,16 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
+ inode_lock(inode);
+ filemap_invalidate_lock(inode->i_mapping);
+
++ i_size = i_size_read(inode);
++ remote_size = ictx->remote_i_size;
++ if (offset + len >= remote_size && offset < i_size) {
++ unsigned long long top = umin(offset + len, i_size);
++
++ rc = filemap_write_and_wait_range(inode->i_mapping, offset, top - 1);
++ if (rc < 0)
++ goto zero_range_exit;
++ }
++
+ /*
+ * We zero the range through ioctl, so we need remove the page caches
+ * first, otherwise the data may be inconsistent with the server.
+diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
+index d262e70100c9c..8e02e9f45e0e1 100644
+--- a/fs/smb/client/smb2pdu.c
++++ b/fs/smb/client/smb2pdu.c
+@@ -4501,6 +4501,7 @@ static void
+ smb2_readv_callback(struct mid_q_entry *mid)
+ {
+ struct cifs_io_subrequest *rdata = mid->callback_data;
++ struct netfs_inode *ictx = netfs_inode(rdata->rreq->inode);
+ struct cifs_tcon *tcon = tlink_tcon(rdata->req->cfile->tlink);
+ struct TCP_Server_Info *server = rdata->server;
+ struct smb2_hdr *shdr =
+@@ -4523,9 +4524,9 @@ smb2_readv_callback(struct mid_q_entry *mid)
+ "rdata server %p != mid server %p",
+ rdata->server, mid->server);
+
+- cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu\n",
++ cifs_dbg(FYI, "%s: mid=%llu state=%d result=%d bytes=%zu/%zu\n",
+ __func__, mid->mid, mid->mid_state, rdata->result,
+- rdata->subreq.len);
++ rdata->actual_len, rdata->subreq.len - rdata->subreq.transferred);
+
+ switch (mid->mid_state) {
+ case MID_RESPONSE_RECEIVED:
+@@ -4579,22 +4580,29 @@ smb2_readv_callback(struct mid_q_entry *mid)
+ rdata->subreq.debug_index,
+ rdata->xid,
+ rdata->req->cfile->fid.persistent_fid,
+- tcon->tid, tcon->ses->Suid, rdata->subreq.start,
+- rdata->subreq.len, rdata->result);
++ tcon->tid, tcon->ses->Suid,
++ rdata->subreq.start + rdata->subreq.transferred,
++ rdata->actual_len,
++ rdata->result);
+ } else
+ trace_smb3_read_done(rdata->rreq->debug_id,
+ rdata->subreq.debug_index,
+ rdata->xid,
+ rdata->req->cfile->fid.persistent_fid,
+ tcon->tid, tcon->ses->Suid,
+- rdata->subreq.start, rdata->got_bytes);
++ rdata->subreq.start + rdata->subreq.transferred,
++ rdata->got_bytes);
+
+ if (rdata->result == -ENODATA) {
+- /* We may have got an EOF error because fallocate
+- * failed to enlarge the file.
+- */
+- if (rdata->subreq.start < rdata->subreq.rreq->i_size)
++ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
++ rdata->result = 0;
++ } else {
++ if (rdata->got_bytes < rdata->actual_len &&
++ rdata->subreq.start + rdata->subreq.transferred + rdata->got_bytes ==
++ ictx->remote_i_size) {
++ __set_bit(NETFS_SREQ_HIT_EOF, &rdata->subreq.flags);
+ rdata->result = 0;
++ }
+ }
+ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value,
+ server->credits, server->in_flight,
+@@ -4615,6 +4623,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
+ {
+ int rc, flags = 0;
+ char *buf;
++ struct netfs_io_subrequest *subreq = &rdata->subreq;
+ struct smb2_hdr *shdr;
+ struct cifs_io_parms io_parms;
+ struct smb_rqst rqst = { .rq_iov = rdata->iov,
+@@ -4625,15 +4634,15 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
+ int credit_request;
+
+ cifs_dbg(FYI, "%s: offset=%llu bytes=%zu\n",
+- __func__, rdata->subreq.start, rdata->subreq.len);
++ __func__, subreq->start, subreq->len);
+
+ if (!rdata->server)
+ rdata->server = cifs_pick_channel(tcon->ses);
+
+ io_parms.tcon = tlink_tcon(rdata->req->cfile->tlink);
+ io_parms.server = server = rdata->server;
+- io_parms.offset = rdata->subreq.start;
+- io_parms.length = rdata->subreq.len;
++ io_parms.offset = subreq->start + subreq->transferred;
++ io_parms.length = rdata->actual_len;
+ io_parms.persistent_fid = rdata->req->cfile->fid.persistent_fid;
+ io_parms.volatile_fid = rdata->req->cfile->fid.volatile_fid;
+ io_parms.pid = rdata->req->pid;
+@@ -4648,11 +4657,13 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
+
+ rdata->iov[0].iov_base = buf;
+ rdata->iov[0].iov_len = total_len;
++ rdata->got_bytes = 0;
++ rdata->result = 0;
+
+ shdr = (struct smb2_hdr *)buf;
+
+ if (rdata->credits.value > 0) {
+- shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->subreq.len,
++ shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->actual_len,
+ SMB2_MAX_BUFFER_SIZE));
+ credit_request = le16_to_cpu(shdr->CreditCharge) + 8;
+ if (server->credits >= server->max_credits)
+@@ -4676,11 +4687,11 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
+ if (rc) {
+ cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
+ trace_smb3_read_err(rdata->rreq->debug_id,
+- rdata->subreq.debug_index,
++ subreq->debug_index,
+ rdata->xid, io_parms.persistent_fid,
+ io_parms.tcon->tid,
+ io_parms.tcon->ses->Suid,
+- io_parms.offset, io_parms.length, rc);
++ io_parms.offset, rdata->actual_len, rc);
+ }
+
+ async_readv_out:
+diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
+index 36d5295c2a6f9..13adfe550b992 100644
+--- a/fs/smb/client/trace.h
++++ b/fs/smb/client/trace.h
+@@ -30,6 +30,7 @@
+ EM(cifs_trace_rw_credits_old_session, "old-session") \
+ EM(cifs_trace_rw_credits_read_response_add, "rd-resp-add") \
+ EM(cifs_trace_rw_credits_read_response_clear, "rd-resp-clr") \
++ EM(cifs_trace_rw_credits_read_resubmit, "rd-resubmit") \
+ EM(cifs_trace_rw_credits_read_submit, "rd-submit ") \
+ EM(cifs_trace_rw_credits_write_prepare, "wr-prepare ") \
+ EM(cifs_trace_rw_credits_write_response_add, "wr-resp-add") \
+diff --git a/fs/smb/server/oplock.c b/fs/smb/server/oplock.c
+index a8f52c4ebbdad..e546ffa57b55a 100644
+--- a/fs/smb/server/oplock.c
++++ b/fs/smb/server/oplock.c
+@@ -1510,7 +1510,7 @@ void create_lease_buf(u8 *rbuf, struct lease *lease)
+ * parse_lease_state() - parse lease context containted in file open request
+ * @open_req: buffer containing smb2 file open(create) request
+ *
+- * Return: oplock state, -ENOENT if create lease context not found
++ * Return: allocated lease context object on success, otherwise NULL
+ */
+ struct lease_ctx_info *parse_lease_state(void *open_req)
+ {
+diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
+index 8cfdf0d1a186e..39dfecf082ba0 100644
+--- a/fs/smb/server/smb2pdu.c
++++ b/fs/smb/server/smb2pdu.c
+@@ -1687,6 +1687,8 @@ int smb2_sess_setup(struct ksmbd_work *work)
+ rc = ksmbd_session_register(conn, sess);
+ if (rc)
+ goto out_err;
++
++ conn->binding = false;
+ } else if (conn->dialect >= SMB30_PROT_ID &&
+ (server_conf.flags & KSMBD_GLOBAL_FLAG_SMB3_MULTICHANNEL) &&
+ req->Flags & SMB2_SESSION_REQ_FLAG_BINDING) {
+@@ -1765,6 +1767,8 @@ int smb2_sess_setup(struct ksmbd_work *work)
+ sess = NULL;
+ goto out_err;
+ }
++
++ conn->binding = false;
+ }
+ work->sess = sess;
+
+@@ -2767,8 +2771,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work,
+ }
+ }
+
+- if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
+- req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) {
++ if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
++ req_op_level == SMB2_OPLOCK_LEVEL_BATCH) {
+ dh_info->CreateGuid =
+ durable_v2_blob->CreateGuid;
+ dh_info->persistent =
+@@ -2788,8 +2792,8 @@ static int parse_durable_handle_context(struct ksmbd_work *work,
+ goto out;
+ }
+
+- if (((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
+- req_op_level == SMB2_OPLOCK_LEVEL_BATCH)) {
++ if ((lc && (lc->req_state & SMB2_LEASE_HANDLE_CACHING_LE)) ||
++ req_op_level == SMB2_OPLOCK_LEVEL_BATCH) {
+ ksmbd_debug(SMB, "Request for durable open\n");
+ dh_info->type = dh_idx;
+ }
+@@ -3411,7 +3415,7 @@ int smb2_open(struct ksmbd_work *work)
+ goto err_out1;
+ }
+ } else {
+- if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE) {
++ if (req_op_level == SMB2_OPLOCK_LEVEL_LEASE && lc) {
+ if (S_ISDIR(file_inode(filp)->i_mode)) {
+ lc->req_state &= ~SMB2_LEASE_WRITE_CACHING_LE;
+ lc->is_dir = true;
+diff --git a/fs/smb/server/transport_tcp.c b/fs/smb/server/transport_tcp.c
+index 6633fa78e9b96..2ce7f75059cb3 100644
+--- a/fs/smb/server/transport_tcp.c
++++ b/fs/smb/server/transport_tcp.c
+@@ -624,8 +624,10 @@ int ksmbd_tcp_set_interfaces(char *ifc_list, int ifc_list_sz)
+ for_each_netdev(&init_net, netdev) {
+ if (netif_is_bridge_port(netdev))
+ continue;
+- if (!alloc_iface(kstrdup(netdev->name, GFP_KERNEL)))
++ if (!alloc_iface(kstrdup(netdev->name, GFP_KERNEL))) {
++ rtnl_unlock();
+ return -ENOMEM;
++ }
+ }
+ rtnl_unlock();
+ bind_additional_ifaces = 1;
+diff --git a/fs/squashfs/inode.c b/fs/squashfs/inode.c
+index 16bd693d0b3aa..d5918eba27e37 100644
+--- a/fs/squashfs/inode.c
++++ b/fs/squashfs/inode.c
+@@ -279,8 +279,13 @@ int squashfs_read_inode(struct inode *inode, long long ino)
+ if (err < 0)
+ goto failed_read;
+
+- set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
+ inode->i_size = le32_to_cpu(sqsh_ino->symlink_size);
++ if (inode->i_size > PAGE_SIZE) {
++ ERROR("Corrupted symlink\n");
++ return -EINVAL;
++ }
++
++ set_nlink(inode, le32_to_cpu(sqsh_ino->nlink));
+ inode->i_op = &squashfs_symlink_inode_ops;
+ inode_nohighmem(inode);
+ inode->i_data.a_ops = &squashfs_symlink_aops;
+diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
+index 01e99e98457dd..8705c77a9e75a 100644
+--- a/fs/tracefs/event_inode.c
++++ b/fs/tracefs/event_inode.c
+@@ -862,7 +862,7 @@ static void eventfs_remove_rec(struct eventfs_inode *ei, int level)
+ list_for_each_entry(ei_child, &ei->children, list)
+ eventfs_remove_rec(ei_child, level + 1);
+
+- list_del(&ei->list);
++ list_del_rcu(&ei->list);
+ free_ei(ei);
+ }
+
+diff --git a/fs/udf/super.c b/fs/udf/super.c
+index 92d4770539056..3460ecc826d16 100644
+--- a/fs/udf/super.c
++++ b/fs/udf/super.c
+@@ -1111,12 +1111,19 @@ static int udf_fill_partdesc_info(struct super_block *sb,
+ struct udf_part_map *map;
+ struct udf_sb_info *sbi = UDF_SB(sb);
+ struct partitionHeaderDesc *phd;
++ u32 sum;
+ int err;
+
+ map = &sbi->s_partmaps[p_index];
+
+ map->s_partition_len = le32_to_cpu(p->partitionLength); /* blocks */
+ map->s_partition_root = le32_to_cpu(p->partitionStartingLocation);
++ if (check_add_overflow(map->s_partition_root, map->s_partition_len,
++ &sum)) {
++ udf_err(sb, "Partition %d has invalid location %u + %u\n",
++ p_index, map->s_partition_root, map->s_partition_len);
++ return -EFSCORRUPTED;
++ }
+
+ if (p->accessType == cpu_to_le32(PD_ACCESS_TYPE_READ_ONLY))
+ map->s_partition_flags |= UDF_PART_FLAG_READ_ONLY;
+@@ -1172,6 +1179,14 @@ static int udf_fill_partdesc_info(struct super_block *sb,
+ bitmap->s_extPosition = le32_to_cpu(
+ phd->unallocSpaceBitmap.extPosition);
+ map->s_partition_flags |= UDF_PART_FLAG_UNALLOC_BITMAP;
++ /* Check whether math over bitmap won't overflow. */
++ if (check_add_overflow(map->s_partition_len,
++ sizeof(struct spaceBitmapDesc) << 3,
++ &sum)) {
++ udf_err(sb, "Partition %d is too long (%u)\n", p_index,
++ map->s_partition_len);
++ return -EFSCORRUPTED;
++ }
+ udf_debug("unallocSpaceBitmap (part %d) @ %u\n",
+ p_index, bitmap->s_extPosition);
+ }
+diff --git a/fs/xattr.c b/fs/xattr.c
+index f8b643f91a981..7672ce5486c53 100644
+--- a/fs/xattr.c
++++ b/fs/xattr.c
+@@ -630,10 +630,9 @@ int do_setxattr(struct mnt_idmap *idmap, struct dentry *dentry,
+ ctx->kvalue, ctx->size, ctx->flags);
+ }
+
+-static long
+-setxattr(struct mnt_idmap *idmap, struct dentry *d,
+- const char __user *name, const void __user *value, size_t size,
+- int flags)
++static int path_setxattr(const char __user *pathname,
++ const char __user *name, const void __user *value,
++ size_t size, int flags, unsigned int lookup_flags)
+ {
+ struct xattr_name kname;
+ struct xattr_ctx ctx = {
+@@ -643,33 +642,20 @@ setxattr(struct mnt_idmap *idmap, struct dentry *d,
+ .kname = &kname,
+ .flags = flags,
+ };
++ struct path path;
+ int error;
+
+ error = setxattr_copy(name, &ctx);
+ if (error)
+ return error;
+
+- error = do_setxattr(idmap, d, &ctx);
+-
+- kvfree(ctx.kvalue);
+- return error;
+-}
+-
+-static int path_setxattr(const char __user *pathname,
+- const char __user *name, const void __user *value,
+- size_t size, int flags, unsigned int lookup_flags)
+-{
+- struct path path;
+- int error;
+-
+ retry:
+ error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+ if (error)
+- return error;
++ goto out;
+ error = mnt_want_write(path.mnt);
+ if (!error) {
+- error = setxattr(mnt_idmap(path.mnt), path.dentry, name,
+- value, size, flags);
++ error = do_setxattr(mnt_idmap(path.mnt), path.dentry, &ctx);
+ mnt_drop_write(path.mnt);
+ }
+ path_put(&path);
+@@ -677,6 +663,9 @@ static int path_setxattr(const char __user *pathname,
+ lookup_flags |= LOOKUP_REVAL;
+ goto retry;
+ }
++
++out:
++ kvfree(ctx.kvalue);
+ return error;
+ }
+
+@@ -697,20 +686,32 @@ SYSCALL_DEFINE5(lsetxattr, const char __user *, pathname,
+ SYSCALL_DEFINE5(fsetxattr, int, fd, const char __user *, name,
+ const void __user *,value, size_t, size, int, flags)
+ {
+- struct fd f = fdget(fd);
+- int error = -EBADF;
++ struct xattr_name kname;
++ struct xattr_ctx ctx = {
++ .cvalue = value,
++ .kvalue = NULL,
++ .size = size,
++ .kname = &kname,
++ .flags = flags,
++ };
++ int error;
+
++ CLASS(fd, f)(fd);
+ if (!f.file)
+- return error;
++ return -EBADF;
++
+ audit_file(f.file);
++ error = setxattr_copy(name, &ctx);
++ if (error)
++ return error;
++
+ error = mnt_want_write_file(f.file);
+ if (!error) {
+- error = setxattr(file_mnt_idmap(f.file),
+- f.file->f_path.dentry, name,
+- value, size, flags);
++ error = do_setxattr(file_mnt_idmap(f.file),
++ f.file->f_path.dentry, &ctx);
+ mnt_drop_write_file(f.file);
+ }
+- fdput(f);
++ kvfree(ctx.kvalue);
+ return error;
+ }
+
+@@ -899,9 +900,17 @@ SYSCALL_DEFINE3(flistxattr, int, fd, char __user *, list, size_t, size)
+ * Extended attribute REMOVE operations
+ */
+ static long
+-removexattr(struct mnt_idmap *idmap, struct dentry *d,
+- const char __user *name)
++removexattr(struct mnt_idmap *idmap, struct dentry *d, const char *name)
+ {
++ if (is_posix_acl_xattr(name))
++ return vfs_remove_acl(idmap, d, name);
++ return vfs_removexattr(idmap, d, name);
++}
++
++static int path_removexattr(const char __user *pathname,
++ const char __user *name, unsigned int lookup_flags)
++{
++ struct path path;
+ int error;
+ char kname[XATTR_NAME_MAX + 1];
+
+@@ -910,25 +919,13 @@ removexattr(struct mnt_idmap *idmap, struct dentry *d,
+ error = -ERANGE;
+ if (error < 0)
+ return error;
+-
+- if (is_posix_acl_xattr(kname))
+- return vfs_remove_acl(idmap, d, kname);
+-
+- return vfs_removexattr(idmap, d, kname);
+-}
+-
+-static int path_removexattr(const char __user *pathname,
+- const char __user *name, unsigned int lookup_flags)
+-{
+- struct path path;
+- int error;
+ retry:
+ error = user_path_at(AT_FDCWD, pathname, lookup_flags, &path);
+ if (error)
+ return error;
+ error = mnt_want_write(path.mnt);
+ if (!error) {
+- error = removexattr(mnt_idmap(path.mnt), path.dentry, name);
++ error = removexattr(mnt_idmap(path.mnt), path.dentry, kname);
+ mnt_drop_write(path.mnt);
+ }
+ path_put(&path);
+@@ -954,15 +951,23 @@ SYSCALL_DEFINE2(lremovexattr, const char __user *, pathname,
+ SYSCALL_DEFINE2(fremovexattr, int, fd, const char __user *, name)
+ {
+ struct fd f = fdget(fd);
++ char kname[XATTR_NAME_MAX + 1];
+ int error = -EBADF;
+
+ if (!f.file)
+ return error;
+ audit_file(f.file);
++
++ error = strncpy_from_user(kname, name, sizeof(kname));
++ if (error == 0 || error == sizeof(kname))
++ error = -ERANGE;
++ if (error < 0)
++ return error;
++
+ error = mnt_want_write_file(f.file);
+ if (!error) {
+ error = removexattr(file_mnt_idmap(f.file),
+- f.file->f_path.dentry, name);
++ f.file->f_path.dentry, kname);
+ mnt_drop_write_file(f.file);
+ }
+ fdput(f);
+diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
+index 42e9fd47f6c73..ffef1c75dd57c 100644
+--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
++++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
+@@ -749,7 +749,7 @@ xfs_finobt_count_blocks(
+ if (error)
+ return error;
+
+- cur = xfs_inobt_init_cursor(pag, tp, agbp);
++ cur = xfs_finobt_init_cursor(pag, tp, agbp);
+ error = xfs_btree_count_blocks(cur, tree_blocks);
+ xfs_btree_del_cursor(cur, error);
+ xfs_trans_brelse(tp, agbp);
+diff --git a/include/linux/bpf-cgroup.h b/include/linux/bpf-cgroup.h
+index fb3c3e7181e6d..ce91d9b2acb9f 100644
+--- a/include/linux/bpf-cgroup.h
++++ b/include/linux/bpf-cgroup.h
+@@ -390,14 +390,6 @@ static inline bool cgroup_bpf_sock_enabled(struct sock *sk,
+ __ret; \
+ })
+
+-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) \
+-({ \
+- int __ret = 0; \
+- if (cgroup_bpf_enabled(CGROUP_GETSOCKOPT)) \
+- copy_from_sockptr(&__ret, optlen, sizeof(int)); \
+- __ret; \
+-})
+-
+ #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, optlen, \
+ max_optlen, retval) \
+ ({ \
+@@ -518,7 +510,6 @@ static inline int bpf_percpu_cgroup_storage_update(struct bpf_map *map,
+ #define BPF_CGROUP_RUN_PROG_SOCK_OPS(sock_ops) ({ 0; })
+ #define BPF_CGROUP_RUN_PROG_DEVICE_CGROUP(atype, major, minor, access) ({ 0; })
+ #define BPF_CGROUP_RUN_PROG_SYSCTL(head,table,write,buf,count,pos) ({ 0; })
+-#define BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen) ({ 0; })
+ #define BPF_CGROUP_RUN_PROG_GETSOCKOPT(sock, level, optname, optval, \
+ optlen, max_optlen, retval) ({ retval; })
+ #define BPF_CGROUP_RUN_PROG_GETSOCKOPT_KERN(sock, level, optname, optval, \
+diff --git a/include/linux/mlx5/device.h b/include/linux/mlx5/device.h
+index d7bb31d9a4463..da09bfaa7b813 100644
+--- a/include/linux/mlx5/device.h
++++ b/include/linux/mlx5/device.h
+@@ -294,6 +294,7 @@ enum {
+ #define MLX5_UMR_FLEX_ALIGNMENT 0x40
+ #define MLX5_UMR_MTT_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_mtt))
+ #define MLX5_UMR_KLM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_klm))
++#define MLX5_UMR_KSM_NUM_ENTRIES_ALIGNMENT (MLX5_UMR_FLEX_ALIGNMENT / sizeof(struct mlx5_ksm))
+
+ #define MLX5_USER_INDEX_LEN (MLX5_FLD_SZ_BYTES(qpc, user_index) * 8)
+
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index f32177152921e..81562397e8347 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -97,6 +97,10 @@ extern const int mmap_rnd_compat_bits_max;
+ extern int mmap_rnd_compat_bits __read_mostly;
+ #endif
+
++#ifndef PHYSMEM_END
++# define PHYSMEM_END ((1ULL << MAX_PHYSMEM_BITS) - 1)
++#endif
++
+ #include <asm/page.h>
+ #include <asm/processor.h>
+
+diff --git a/include/linux/netfs.h b/include/linux/netfs.h
+index 5d0288938cc2d..d8892b1a2dd77 100644
+--- a/include/linux/netfs.h
++++ b/include/linux/netfs.h
+@@ -200,6 +200,7 @@ struct netfs_io_subrequest {
+ #define NETFS_SREQ_NEED_RETRY 9 /* Set if the filesystem requests a retry */
+ #define NETFS_SREQ_RETRYING 10 /* Set if we're retrying */
+ #define NETFS_SREQ_FAILED 11 /* Set if the subreq failed unretryably */
++#define NETFS_SREQ_HIT_EOF 12 /* Set if we hit the EOF */
+ };
+
+ enum netfs_io_origin {
+diff --git a/include/linux/nvme.h b/include/linux/nvme.h
+index c693ac344ec05..efda407622c16 100644
+--- a/include/linux/nvme.h
++++ b/include/linux/nvme.h
+@@ -1848,6 +1848,7 @@ enum {
+ /*
+ * Generic Command Status:
+ */
++ NVME_SCT_GENERIC = 0x0,
+ NVME_SC_SUCCESS = 0x0,
+ NVME_SC_INVALID_OPCODE = 0x1,
+ NVME_SC_INVALID_FIELD = 0x2,
+@@ -1895,6 +1896,7 @@ enum {
+ /*
+ * Command Specific Status:
+ */
++ NVME_SCT_COMMAND_SPECIFIC = 0x100,
+ NVME_SC_CQ_INVALID = 0x100,
+ NVME_SC_QID_INVALID = 0x101,
+ NVME_SC_QUEUE_SIZE = 0x102,
+@@ -1968,6 +1970,7 @@ enum {
+ /*
+ * Media and Data Integrity Errors:
+ */
++ NVME_SCT_MEDIA_ERROR = 0x200,
+ NVME_SC_WRITE_FAULT = 0x280,
+ NVME_SC_READ_ERROR = 0x281,
+ NVME_SC_GUARD_CHECK = 0x282,
+@@ -1980,6 +1983,7 @@ enum {
+ /*
+ * Path-related Errors:
+ */
++ NVME_SCT_PATH = 0x300,
+ NVME_SC_INTERNAL_PATH_ERROR = 0x300,
+ NVME_SC_ANA_PERSISTENT_LOSS = 0x301,
+ NVME_SC_ANA_INACCESSIBLE = 0x302,
+@@ -1988,11 +1992,17 @@ enum {
+ NVME_SC_HOST_PATH_ERROR = 0x370,
+ NVME_SC_HOST_ABORTED_CMD = 0x371,
+
+- NVME_SC_CRD = 0x1800,
+- NVME_SC_MORE = 0x2000,
+- NVME_SC_DNR = 0x4000,
++ NVME_SC_MASK = 0x00ff, /* Status Code */
++ NVME_SCT_MASK = 0x0700, /* Status Code Type */
++ NVME_SCT_SC_MASK = NVME_SCT_MASK | NVME_SC_MASK,
++
++ NVME_STATUS_CRD = 0x1800, /* Command Retry Delayed */
++ NVME_STATUS_MORE = 0x2000,
++ NVME_STATUS_DNR = 0x4000, /* Do Not Retry */
+ };
+
++#define NVME_SCT(status) ((status) >> 8 & 7)
++
+ struct nvme_completion {
+ /*
+ * Used by Admin and Fabrics commands to return data:
+diff --git a/include/linux/path.h b/include/linux/path.h
+index 475225a03d0dc..ca073e70decd5 100644
+--- a/include/linux/path.h
++++ b/include/linux/path.h
+@@ -24,4 +24,13 @@ static inline void path_put_init(struct path *path)
+ *path = (struct path) { };
+ }
+
++/*
++ * Cleanup macro for use with __free(path_put). Avoids dereference and
++ * copying @path unlike DEFINE_FREE(). path_put() will handle the empty
++ * path correctly just ensure @path is initialized:
++ *
++ * struct path path __free(path_put) = {};
++ */
++#define __free_path_put path_put
++
+ #endif /* _LINUX_PATH_H */
+diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
+index 59d0b9a79e6e0..e6ad927bb4a8a 100644
+--- a/include/linux/regulator/consumer.h
++++ b/include/linux/regulator/consumer.h
+@@ -451,6 +451,14 @@ static inline int of_regulator_bulk_get_all(struct device *dev, struct device_no
+ return 0;
+ }
+
++static inline int devm_regulator_bulk_get_const(
++ struct device *dev, int num_consumers,
++ const struct regulator_bulk_data *in_consumers,
++ struct regulator_bulk_data **out_consumers)
++{
++ return 0;
++}
++
+ static inline int regulator_bulk_enable(int num_consumers,
+ struct regulator_bulk_data *consumers)
+ {
+diff --git a/include/linux/zswap.h b/include/linux/zswap.h
+index 2a85b941db975..ce5e7bfe8f1ec 100644
+--- a/include/linux/zswap.h
++++ b/include/linux/zswap.h
+@@ -35,7 +35,7 @@ void zswap_swapoff(int type);
+ void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg);
+ void zswap_lruvec_state_init(struct lruvec *lruvec);
+ void zswap_folio_swapin(struct folio *folio);
+-bool is_zswap_enabled(void);
++bool zswap_is_enabled(void);
+ #else
+
+ struct zswap_lruvec_state {};
+@@ -60,7 +60,7 @@ static inline void zswap_memcg_offline_cleanup(struct mem_cgroup *memcg) {}
+ static inline void zswap_lruvec_state_init(struct lruvec *lruvec) {}
+ static inline void zswap_folio_swapin(struct folio *folio) {}
+
+-static inline bool is_zswap_enabled(void)
++static inline bool zswap_is_enabled(void)
+ {
+ return false;
+ }
+diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
+index c97ff64c9189f..ecb6824e9add8 100644
+--- a/include/net/bluetooth/hci_core.h
++++ b/include/net/bluetooth/hci_core.h
+@@ -186,7 +186,6 @@ struct blocked_key {
+ struct smp_csrk {
+ bdaddr_t bdaddr;
+ u8 bdaddr_type;
+- u8 link_type;
+ u8 type;
+ u8 val[16];
+ };
+@@ -196,7 +195,6 @@ struct smp_ltk {
+ struct rcu_head rcu;
+ bdaddr_t bdaddr;
+ u8 bdaddr_type;
+- u8 link_type;
+ u8 authenticated;
+ u8 type;
+ u8 enc_size;
+@@ -211,7 +209,6 @@ struct smp_irk {
+ bdaddr_t rpa;
+ bdaddr_t bdaddr;
+ u8 addr_type;
+- u8 link_type;
+ u8 val[16];
+ };
+
+@@ -219,8 +216,6 @@ struct link_key {
+ struct list_head list;
+ struct rcu_head rcu;
+ bdaddr_t bdaddr;
+- u8 bdaddr_type;
+- u8 link_type;
+ u8 type;
+ u8 val[HCI_LINK_KEY_SIZE];
+ u8 pin_len;
+diff --git a/include/net/bluetooth/hci_sync.h b/include/net/bluetooth/hci_sync.h
+index 534c3386e714f..3cb2d10cac930 100644
+--- a/include/net/bluetooth/hci_sync.h
++++ b/include/net/bluetooth/hci_sync.h
+@@ -52,6 +52,10 @@ int hci_cmd_sync_queue(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
+ void *data, hci_cmd_sync_work_destroy_t destroy);
+ int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
+ void *data, hci_cmd_sync_work_destroy_t destroy);
++int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
++ void *data, hci_cmd_sync_work_destroy_t destroy);
++int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
++ void *data, hci_cmd_sync_work_destroy_t destroy);
+ struct hci_cmd_sync_work_entry *
+ hci_cmd_sync_lookup_entry(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
+ void *data, hci_cmd_sync_work_destroy_t destroy);
+diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
+index 9bdb1fdc7c51b..5927bd9d46bef 100644
+--- a/include/net/mana/mana.h
++++ b/include/net/mana/mana.h
+@@ -97,6 +97,8 @@ struct mana_txq {
+
+ atomic_t pending_sends;
+
++ bool napi_initialized;
++
+ struct mana_stats_tx stats;
+ };
+
+diff --git a/include/uapi/drm/drm_fourcc.h b/include/uapi/drm/drm_fourcc.h
+index 84d502e429614..2d84a8052b157 100644
+--- a/include/uapi/drm/drm_fourcc.h
++++ b/include/uapi/drm/drm_fourcc.h
+@@ -1476,6 +1476,7 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
+ #define AMD_FMT_MOD_TILE_VER_GFX10 2
+ #define AMD_FMT_MOD_TILE_VER_GFX10_RBPLUS 3
+ #define AMD_FMT_MOD_TILE_VER_GFX11 4
++#define AMD_FMT_MOD_TILE_VER_GFX12 5
+
+ /*
+ * 64K_S is the same for GFX9/GFX10/GFX10_RBPLUS and hence has GFX9 as canonical
+@@ -1486,6 +1487,8 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
+ /*
+ * 64K_D for non-32 bpp is the same for GFX9/GFX10/GFX10_RBPLUS and hence has
+ * GFX9 as canonical version.
++ *
++ * 64K_D_2D on GFX12 is identical to 64K_D on GFX11.
+ */
+ #define AMD_FMT_MOD_TILE_GFX9_64K_D 10
+ #define AMD_FMT_MOD_TILE_GFX9_64K_S_X 25
+@@ -1493,6 +1496,21 @@ drm_fourcc_canonicalize_nvidia_format_mod(__u64 modifier)
+ #define AMD_FMT_MOD_TILE_GFX9_64K_R_X 27
+ #define AMD_FMT_MOD_TILE_GFX11_256K_R_X 31
+
++/* Gfx12 swizzle modes:
++ * 0 - LINEAR
++ * 1 - 256B_2D - 2D block dimensions
++ * 2 - 4KB_2D
++ * 3 - 64KB_2D
++ * 4 - 256KB_2D
++ * 5 - 4KB_3D - 3D block dimensions
++ * 6 - 64KB_3D
++ * 7 - 256KB_3D
++ */
++#define AMD_FMT_MOD_TILE_GFX12_256B_2D 1
++#define AMD_FMT_MOD_TILE_GFX12_4K_2D 2
++#define AMD_FMT_MOD_TILE_GFX12_64K_2D 3
++#define AMD_FMT_MOD_TILE_GFX12_256K_2D 4
++
+ #define AMD_FMT_MOD_DCC_BLOCK_64B 0
+ #define AMD_FMT_MOD_DCC_BLOCK_128B 1
+ #define AMD_FMT_MOD_DCC_BLOCK_256B 2
+diff --git a/include/uapi/drm/panthor_drm.h b/include/uapi/drm/panthor_drm.h
+index 926b1deb11166..e23a7f9b0eacd 100644
+--- a/include/uapi/drm/panthor_drm.h
++++ b/include/uapi/drm/panthor_drm.h
+@@ -692,7 +692,11 @@ enum drm_panthor_group_priority {
+ /** @PANTHOR_GROUP_PRIORITY_MEDIUM: Medium priority group. */
+ PANTHOR_GROUP_PRIORITY_MEDIUM,
+
+- /** @PANTHOR_GROUP_PRIORITY_HIGH: High priority group. */
++ /**
++ * @PANTHOR_GROUP_PRIORITY_HIGH: High priority group.
++ *
++ * Requires CAP_SYS_NICE or DRM_MASTER.
++ */
+ PANTHOR_GROUP_PRIORITY_HIGH,
+ };
+
+diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
+index fe360b5b211d1..2f157ffbc67ce 100644
+--- a/kernel/bpf/btf.c
++++ b/kernel/bpf/btf.c
+@@ -817,9 +817,11 @@ static bool btf_name_valid_section(const struct btf *btf, u32 offset)
+ const char *src = btf_str_by_offset(btf, offset);
+ const char *src_limit;
+
++ if (!*src)
++ return false;
++
+ /* set a limit on identifier length */
+ src_limit = src + KSYM_NAME_LEN;
+- src++;
+ while (*src && src < src_limit) {
+ if (!isprint(*src))
+ return false;
+diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
+index 521bd7efae038..73f55f4b945ee 100644
+--- a/kernel/bpf/verifier.c
++++ b/kernel/bpf/verifier.c
+@@ -2982,8 +2982,10 @@ static int check_subprogs(struct bpf_verifier_env *env)
+
+ if (code == (BPF_JMP | BPF_CALL) &&
+ insn[i].src_reg == 0 &&
+- insn[i].imm == BPF_FUNC_tail_call)
++ insn[i].imm == BPF_FUNC_tail_call) {
+ subprog[cur_subprog].has_tail_call = true;
++ subprog[cur_subprog].tail_call_reachable = true;
++ }
+ if (BPF_CLASS(code) == BPF_LD &&
+ (BPF_MODE(code) == BPF_ABS || BPF_MODE(code) == BPF_IND))
+ subprog[cur_subprog].has_ld_abs = true;
+diff --git a/kernel/cgroup/cgroup.c b/kernel/cgroup/cgroup.c
+index e32b6972c4784..278889170f941 100644
+--- a/kernel/cgroup/cgroup.c
++++ b/kernel/cgroup/cgroup.c
+@@ -1839,9 +1839,9 @@ int rebind_subsystems(struct cgroup_root *dst_root, u16 ss_mask)
+ RCU_INIT_POINTER(scgrp->subsys[ssid], NULL);
+ rcu_assign_pointer(dcgrp->subsys[ssid], css);
+ ss->root = dst_root;
+- css->cgroup = dcgrp;
+
+ spin_lock_irq(&css_set_lock);
++ css->cgroup = dcgrp;
+ WARN_ON(!list_empty(&dcgrp->e_csets[ss->id]));
+ list_for_each_entry_safe(cset, cset_pos, &scgrp->e_csets[ss->id],
+ e_cset_node[ss->id]) {
+diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
+index fc1c6236460d2..e8f24483e05f0 100644
+--- a/kernel/cgroup/cpuset.c
++++ b/kernel/cgroup/cpuset.c
+@@ -826,17 +826,41 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
+
+ /*
+ * If either I or some sibling (!= me) is exclusive, we can't
+- * overlap
++ * overlap. exclusive_cpus cannot overlap with each other if set.
+ */
+ ret = -EINVAL;
+ cpuset_for_each_child(c, css, par) {
+- if ((is_cpu_exclusive(trial) || is_cpu_exclusive(c)) &&
+- c != cur) {
++ bool txset, cxset; /* Are exclusive_cpus set? */
++
++ if (c == cur)
++ continue;
++
++ txset = !cpumask_empty(trial->exclusive_cpus);
++ cxset = !cpumask_empty(c->exclusive_cpus);
++ if (is_cpu_exclusive(trial) || is_cpu_exclusive(c) ||
++ (txset && cxset)) {
+ if (!cpusets_are_exclusive(trial, c))
+ goto out;
++ } else if (txset || cxset) {
++ struct cpumask *xcpus, *acpus;
++
++ /*
++ * When just one of the exclusive_cpus's is set,
++ * cpus_allowed of the other cpuset, if set, cannot be
++ * a subset of it or none of those CPUs will be
++ * available if these exclusive CPUs are activated.
++ */
++ if (txset) {
++ xcpus = trial->exclusive_cpus;
++ acpus = c->cpus_allowed;
++ } else {
++ xcpus = c->exclusive_cpus;
++ acpus = trial->cpus_allowed;
++ }
++ if (!cpumask_empty(acpus) && cpumask_subset(acpus, xcpus))
++ goto out;
+ }
+ if ((is_mem_exclusive(trial) || is_mem_exclusive(c)) &&
+- c != cur &&
+ nodes_intersects(trial->mems_allowed, c->mems_allowed))
+ goto out;
+ }
+@@ -1376,7 +1400,7 @@ static void update_sibling_cpumasks(struct cpuset *parent, struct cpuset *cs,
+ */
+ static int update_partition_exclusive(struct cpuset *cs, int new_prs)
+ {
+- bool exclusive = (new_prs > 0);
++ bool exclusive = (new_prs > PRS_MEMBER);
+
+ if (exclusive && !is_cpu_exclusive(cs)) {
+ if (update_flag(CS_CPU_EXCLUSIVE, cs, 1))
+@@ -2624,8 +2648,6 @@ static int update_exclusive_cpumask(struct cpuset *cs, struct cpuset *trialcs,
+ retval = cpulist_parse(buf, trialcs->exclusive_cpus);
+ if (retval < 0)
+ return retval;
+- if (!is_cpu_exclusive(cs))
+- set_bit(CS_CPU_EXCLUSIVE, &trialcs->flags);
+ }
+
+ /* Nothing to do if the CPUs didn't change */
+diff --git a/kernel/dma/map_benchmark.c b/kernel/dma/map_benchmark.c
+index 4950e0b622b1f..cc19a3efea896 100644
+--- a/kernel/dma/map_benchmark.c
++++ b/kernel/dma/map_benchmark.c
+@@ -89,6 +89,22 @@ static int map_benchmark_thread(void *data)
+ atomic64_add(map_sq, &map->sum_sq_map);
+ atomic64_add(unmap_sq, &map->sum_sq_unmap);
+ atomic64_inc(&map->loops);
++
++ /*
++ * We may test for a long time so periodically check whether
++ * we need to schedule to avoid starving the others. Otherwise
++ * we may hangup the kernel in a non-preemptible kernel when
++ * the test kthreads number >= CPU number, the test kthreads
++ * will run endless on every CPU since the thread resposible
++ * for notifying the kthread stop (in do_map_benchmark())
++ * could not be scheduled.
++ *
++ * Note this may degrade the test concurrency since the test
++ * threads may need to share the CPU time with other load
++ * in the system. So it's recommended to run this benchmark
++ * on an idle system.
++ */
++ cond_resched();
+ }
+
+ out:
+diff --git a/kernel/events/core.c b/kernel/events/core.c
+index 7891d5a75526a..36191add55c37 100644
+--- a/kernel/events/core.c
++++ b/kernel/events/core.c
+@@ -1255,8 +1255,9 @@ static void put_ctx(struct perf_event_context *ctx)
+ * perf_event_context::mutex
+ * perf_event::child_mutex;
+ * perf_event_context::lock
+- * perf_event::mmap_mutex
+ * mmap_lock
++ * perf_event::mmap_mutex
++ * perf_buffer::aux_mutex
+ * perf_addr_filters_head::lock
+ *
+ * cpu_hotplug_lock
+@@ -6383,12 +6384,11 @@ static void perf_mmap_close(struct vm_area_struct *vma)
+ event->pmu->event_unmapped(event, vma->vm_mm);
+
+ /*
+- * rb->aux_mmap_count will always drop before rb->mmap_count and
+- * event->mmap_count, so it is ok to use event->mmap_mutex to
+- * serialize with perf_mmap here.
++ * The AUX buffer is strictly a sub-buffer, serialize using aux_mutex
++ * to avoid complications.
+ */
+ if (rb_has_aux(rb) && vma->vm_pgoff == rb->aux_pgoff &&
+- atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &event->mmap_mutex)) {
++ atomic_dec_and_mutex_lock(&rb->aux_mmap_count, &rb->aux_mutex)) {
+ /*
+ * Stop all AUX events that are writing to this buffer,
+ * so that we can free its AUX pages and corresponding PMU
+@@ -6405,7 +6405,7 @@ static void perf_mmap_close(struct vm_area_struct *vma)
+ rb_free_aux(rb);
+ WARN_ON_ONCE(refcount_read(&rb->aux_refcount));
+
+- mutex_unlock(&event->mmap_mutex);
++ mutex_unlock(&rb->aux_mutex);
+ }
+
+ if (atomic_dec_and_test(&rb->mmap_count))
+@@ -6493,6 +6493,7 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
+ struct perf_event *event = file->private_data;
+ unsigned long user_locked, user_lock_limit;
+ struct user_struct *user = current_user();
++ struct mutex *aux_mutex = NULL;
+ struct perf_buffer *rb = NULL;
+ unsigned long locked, lock_limit;
+ unsigned long vma_size;
+@@ -6541,6 +6542,9 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
+ if (!rb)
+ goto aux_unlock;
+
++ aux_mutex = &rb->aux_mutex;
++ mutex_lock(aux_mutex);
++
+ aux_offset = READ_ONCE(rb->user_page->aux_offset);
+ aux_size = READ_ONCE(rb->user_page->aux_size);
+
+@@ -6691,6 +6695,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
+ atomic_dec(&rb->mmap_count);
+ }
+ aux_unlock:
++ if (aux_mutex)
++ mutex_unlock(aux_mutex);
+ mutex_unlock(&event->mmap_mutex);
+
+ /*
+diff --git a/kernel/events/internal.h b/kernel/events/internal.h
+index 386d21c7edfa0..f376b057320ce 100644
+--- a/kernel/events/internal.h
++++ b/kernel/events/internal.h
+@@ -40,6 +40,7 @@ struct perf_buffer {
+ struct user_struct *mmap_user;
+
+ /* AUX area */
++ struct mutex aux_mutex;
+ long aux_head;
+ unsigned int aux_nest;
+ long aux_wakeup; /* last aux_watermark boundary crossed by aux_head */
+diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
+index 485cf0a66631b..e4f208df31029 100644
+--- a/kernel/events/ring_buffer.c
++++ b/kernel/events/ring_buffer.c
+@@ -337,6 +337,8 @@ ring_buffer_init(struct perf_buffer *rb, long watermark, int flags)
+ */
+ if (!rb->nr_pages)
+ rb->paused = 1;
++
++ mutex_init(&rb->aux_mutex);
+ }
+
+ void perf_aux_output_flag(struct perf_output_handle *handle, u64 flags)
+diff --git a/kernel/events/uprobes.c b/kernel/events/uprobes.c
+index 2c83ba776fc7b..47cdec3e1df11 100644
+--- a/kernel/events/uprobes.c
++++ b/kernel/events/uprobes.c
+@@ -1480,7 +1480,7 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
+ uprobe_opcode_t insn = UPROBE_SWBP_INSN;
+ struct xol_area *area;
+
+- area = kmalloc(sizeof(*area), GFP_KERNEL);
++ area = kzalloc(sizeof(*area), GFP_KERNEL);
+ if (unlikely(!area))
+ goto out;
+
+@@ -1490,7 +1490,6 @@ static struct xol_area *__create_xol_area(unsigned long vaddr)
+ goto free_area;
+
+ area->xol_mapping.name = "[uprobes]";
+- area->xol_mapping.fault = NULL;
+ area->xol_mapping.pages = area->pages;
+ area->pages[0] = alloc_page(GFP_HIGHUSER);
+ if (!area->pages[0])
+diff --git a/kernel/exit.c b/kernel/exit.c
+index 81fcee45d6302..be81342caf1bb 100644
+--- a/kernel/exit.c
++++ b/kernel/exit.c
+@@ -277,7 +277,6 @@ void release_task(struct task_struct *p)
+ }
+
+ write_unlock_irq(&tasklist_lock);
+- seccomp_filter_release(p);
+ proc_flush_pid(thread_pid);
+ put_pid(thread_pid);
+ release_thread(p);
+@@ -834,6 +833,8 @@ void __noreturn do_exit(long code)
+ io_uring_files_cancel();
+ exit_signals(tsk); /* sets PF_EXITING */
+
++ seccomp_filter_release(tsk);
++
+ acct_update_integrals(tsk);
+ group_dead = atomic_dec_and_test(&tsk->signal->live);
+ if (group_dead) {
+diff --git a/kernel/kexec_file.c b/kernel/kexec_file.c
+index 3d64290d24c9a..3eedb8c226ad8 100644
+--- a/kernel/kexec_file.c
++++ b/kernel/kexec_file.c
+@@ -752,7 +752,7 @@ static int kexec_calculate_store_digests(struct kimage *image)
+
+ #ifdef CONFIG_CRASH_HOTPLUG
+ /* Exclude elfcorehdr segment to allow future changes via hotplug */
+- if (j == image->elfcorehdr_index)
++ if (i == image->elfcorehdr_index)
+ continue;
+ #endif
+
+diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
+index 88d08eeb8bc03..fba1229f1de66 100644
+--- a/kernel/locking/rtmutex.c
++++ b/kernel/locking/rtmutex.c
+@@ -1644,6 +1644,7 @@ static int __sched rt_mutex_slowlock_block(struct rt_mutex_base *lock,
+ }
+
+ static void __sched rt_mutex_handle_deadlock(int res, int detect_deadlock,
++ struct rt_mutex_base *lock,
+ struct rt_mutex_waiter *w)
+ {
+ /*
+@@ -1656,10 +1657,10 @@ static void __sched rt_mutex_handle_deadlock(int res, int detect_deadlock,
+ if (build_ww_mutex() && w->ww_ctx)
+ return;
+
+- /*
+- * Yell loudly and stop the task right here.
+- */
++ raw_spin_unlock_irq(&lock->wait_lock);
++
+ WARN(1, "rtmutex deadlock detected\n");
++
+ while (1) {
+ set_current_state(TASK_INTERRUPTIBLE);
+ rt_mutex_schedule();
+@@ -1713,7 +1714,7 @@ static int __sched __rt_mutex_slowlock(struct rt_mutex_base *lock,
+ } else {
+ __set_current_state(TASK_RUNNING);
+ remove_waiter(lock, waiter);
+- rt_mutex_handle_deadlock(ret, chwalk, waiter);
++ rt_mutex_handle_deadlock(ret, chwalk, lock, waiter);
+ }
+
+ /*
+diff --git a/kernel/resource.c b/kernel/resource.c
+index fcbca39dbc450..b0e2b15ecb409 100644
+--- a/kernel/resource.c
++++ b/kernel/resource.c
+@@ -1832,8 +1832,7 @@ static resource_size_t gfr_start(struct resource *base, resource_size_t size,
+ if (flags & GFR_DESCENDING) {
+ resource_size_t end;
+
+- end = min_t(resource_size_t, base->end,
+- (1ULL << MAX_PHYSMEM_BITS) - 1);
++ end = min_t(resource_size_t, base->end, PHYSMEM_END);
+ return end - size + 1;
+ }
+
+@@ -1850,8 +1849,7 @@ static bool gfr_continue(struct resource *base, resource_size_t addr,
+ * @size did not wrap 0.
+ */
+ return addr > addr - size &&
+- addr <= min_t(resource_size_t, base->end,
+- (1ULL << MAX_PHYSMEM_BITS) - 1);
++ addr <= min_t(resource_size_t, base->end, PHYSMEM_END);
+ }
+
+ static resource_size_t gfr_next(resource_size_t addr, resource_size_t size,
+diff --git a/kernel/seccomp.c b/kernel/seccomp.c
+index e30b60b57614e..b02337e956644 100644
+--- a/kernel/seccomp.c
++++ b/kernel/seccomp.c
+@@ -502,6 +502,9 @@ static inline pid_t seccomp_can_sync_threads(void)
+ /* Skip current, since it is initiating the sync. */
+ if (thread == caller)
+ continue;
++ /* Skip exited threads. */
++ if (thread->flags & PF_EXITING)
++ continue;
+
+ if (thread->seccomp.mode == SECCOMP_MODE_DISABLED ||
+ (thread->seccomp.mode == SECCOMP_MODE_FILTER &&
+@@ -563,18 +566,21 @@ static void __seccomp_filter_release(struct seccomp_filter *orig)
+ * @tsk: task the filter should be released from.
+ *
+ * This function should only be called when the task is exiting as
+- * it detaches it from its filter tree. As such, READ_ONCE() and
+- * barriers are not needed here, as would normally be needed.
++ * it detaches it from its filter tree. PF_EXITING has to be set
++ * for the task.
+ */
+ void seccomp_filter_release(struct task_struct *tsk)
+ {
+- struct seccomp_filter *orig = tsk->seccomp.filter;
++ struct seccomp_filter *orig;
+
+- /* We are effectively holding the siglock by not having any sighand. */
+- WARN_ON(tsk->sighand != NULL);
++ if (WARN_ON((tsk->flags & PF_EXITING) == 0))
++ return;
+
++ spin_lock_irq(&tsk->sighand->siglock);
++ orig = tsk->seccomp.filter;
+ /* Detach task from its filter tree. */
+ tsk->seccomp.filter = NULL;
++ spin_unlock_irq(&tsk->sighand->siglock);
+ __seccomp_filter_release(orig);
+ }
+
+@@ -602,6 +608,13 @@ static inline void seccomp_sync_threads(unsigned long flags)
+ if (thread == caller)
+ continue;
+
++ /*
++ * Skip exited threads. seccomp_filter_release could have
++ * been already called for this task.
++ */
++ if (thread->flags & PF_EXITING)
++ continue;
++
+ /* Get a task reference for the new leaf node. */
+ get_seccomp_filter(caller);
+
+diff --git a/kernel/smp.c b/kernel/smp.c
+index f085ebcdf9e70..af9b2d0736c86 100644
+--- a/kernel/smp.c
++++ b/kernel/smp.c
+@@ -1119,6 +1119,7 @@ int smp_call_on_cpu(unsigned int cpu, int (*func)(void *), void *par, bool phys)
+
+ queue_work_on(cpu, system_wq, &sscs.work);
+ wait_for_completion(&sscs.done);
++ destroy_work_on_stack(&sscs.work);
+
+ return sscs.ret;
+ }
+diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
+index cb507860163d0..c566ad068b40d 100644
+--- a/kernel/trace/trace.c
++++ b/kernel/trace/trace.c
+@@ -3958,6 +3958,8 @@ void tracing_iter_reset(struct trace_iterator *iter, int cpu)
+ break;
+ entries++;
+ ring_buffer_iter_advance(buf_iter);
++ /* This could be a big loop */
++ cond_resched();
+ }
+
+ per_cpu_ptr(iter->array_buffer->data, cpu)->skipped_entries = entries;
+diff --git a/kernel/trace/trace_kprobe.c b/kernel/trace/trace_kprobe.c
+index 16383247bdbf1..0d88922f8763c 100644
+--- a/kernel/trace/trace_kprobe.c
++++ b/kernel/trace/trace_kprobe.c
+@@ -678,6 +678,21 @@ static int register_trace_kprobe(struct trace_kprobe *tk)
+ }
+
+ #ifdef CONFIG_MODULES
++static int validate_module_probe_symbol(const char *modname, const char *symbol);
++
++static int register_module_trace_kprobe(struct module *mod, struct trace_kprobe *tk)
++{
++ const char *p;
++ int ret = 0;
++
++ p = strchr(trace_kprobe_symbol(tk), ':');
++ if (p)
++ ret = validate_module_probe_symbol(module_name(mod), p + 1);
++ if (!ret)
++ ret = __register_trace_kprobe(tk);
++ return ret;
++}
++
+ /* Module notifier call back, checking event on the module */
+ static int trace_kprobe_module_callback(struct notifier_block *nb,
+ unsigned long val, void *data)
+@@ -696,7 +711,7 @@ static int trace_kprobe_module_callback(struct notifier_block *nb,
+ if (trace_kprobe_within_module(tk, mod)) {
+ /* Don't need to check busy - this should have gone. */
+ __unregister_trace_kprobe(tk);
+- ret = __register_trace_kprobe(tk);
++ ret = register_module_trace_kprobe(mod, tk);
+ if (ret)
+ pr_warn("Failed to re-register probe %s on %s: %d\n",
+ trace_probe_name(&tk->tp),
+@@ -747,17 +762,68 @@ static int count_mod_symbols(void *data, const char *name, unsigned long unused)
+ return 0;
+ }
+
+-static unsigned int number_of_same_symbols(char *func_name)
++static unsigned int number_of_same_symbols(const char *mod, const char *func_name)
+ {
+ struct sym_count_ctx ctx = { .count = 0, .name = func_name };
+
+- kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count);
++ if (!mod)
++ kallsyms_on_each_match_symbol(count_symbols, func_name, &ctx.count);
+
+- module_kallsyms_on_each_symbol(NULL, count_mod_symbols, &ctx);
++ module_kallsyms_on_each_symbol(mod, count_mod_symbols, &ctx);
+
+ return ctx.count;
+ }
+
++static int validate_module_probe_symbol(const char *modname, const char *symbol)
++{
++ unsigned int count = number_of_same_symbols(modname, symbol);
++
++ if (count > 1) {
++ /*
++ * Users should use ADDR to remove the ambiguity of
++ * using KSYM only.
++ */
++ return -EADDRNOTAVAIL;
++ } else if (count == 0) {
++ /*
++ * We can return ENOENT earlier than when register the
++ * kprobe.
++ */
++ return -ENOENT;
++ }
++ return 0;
++}
++
++static int validate_probe_symbol(char *symbol)
++{
++ struct module *mod = NULL;
++ char *modname = NULL, *p;
++ int ret = 0;
++
++ p = strchr(symbol, ':');
++ if (p) {
++ modname = symbol;
++ symbol = p + 1;
++ *p = '\0';
++ /* Return 0 (defer) if the module does not exist yet. */
++ rcu_read_lock_sched();
++ mod = find_module(modname);
++ if (mod && !try_module_get(mod))
++ mod = NULL;
++ rcu_read_unlock_sched();
++ if (!mod)
++ goto out;
++ }
++
++ ret = validate_module_probe_symbol(modname, symbol);
++out:
++ if (p)
++ *p = ':';
++ if (mod)
++ module_put(mod);
++ return ret;
++}
++
+ static int trace_kprobe_entry_handler(struct kretprobe_instance *ri,
+ struct pt_regs *regs);
+
+@@ -881,6 +947,14 @@ static int __trace_kprobe_create(int argc, const char *argv[])
+ trace_probe_log_err(0, BAD_PROBE_ADDR);
+ goto parse_error;
+ }
++ ret = validate_probe_symbol(symbol);
++ if (ret) {
++ if (ret == -EADDRNOTAVAIL)
++ trace_probe_log_err(0, NON_UNIQ_SYMBOL);
++ else
++ trace_probe_log_err(0, BAD_PROBE_ADDR);
++ goto parse_error;
++ }
+ if (is_return)
+ ctx.flags |= TPARG_FL_RETURN;
+ ret = kprobe_on_func_entry(NULL, symbol, offset);
+@@ -893,31 +967,6 @@ static int __trace_kprobe_create(int argc, const char *argv[])
+ }
+ }
+
+- if (symbol && !strchr(symbol, ':')) {
+- unsigned int count;
+-
+- count = number_of_same_symbols(symbol);
+- if (count > 1) {
+- /*
+- * Users should use ADDR to remove the ambiguity of
+- * using KSYM only.
+- */
+- trace_probe_log_err(0, NON_UNIQ_SYMBOL);
+- ret = -EADDRNOTAVAIL;
+-
+- goto error;
+- } else if (count == 0) {
+- /*
+- * We can return ENOENT earlier than when register the
+- * kprobe.
+- */
+- trace_probe_log_err(0, BAD_PROBE_ADDR);
+- ret = -ENOENT;
+-
+- goto error;
+- }
+- }
+-
+ trace_probe_log_set_index(0);
+ if (event) {
+ ret = traceprobe_parse_event_name(&event, &group, gbuf,
+@@ -1835,21 +1884,9 @@ create_local_trace_kprobe(char *func, void *addr, unsigned long offs,
+ char *event;
+
+ if (func) {
+- unsigned int count;
+-
+- count = number_of_same_symbols(func);
+- if (count > 1)
+- /*
+- * Users should use addr to remove the ambiguity of
+- * using func only.
+- */
+- return ERR_PTR(-EADDRNOTAVAIL);
+- else if (count == 0)
+- /*
+- * We can return ENOENT earlier than when register the
+- * kprobe.
+- */
+- return ERR_PTR(-ENOENT);
++ ret = validate_probe_symbol(func);
++ if (ret)
++ return ERR_PTR(ret);
+ }
+
+ /*
+diff --git a/kernel/trace/trace_osnoise.c b/kernel/trace/trace_osnoise.c
+index a8e28f9b9271c..5b06f67879f5f 100644
+--- a/kernel/trace/trace_osnoise.c
++++ b/kernel/trace/trace_osnoise.c
+@@ -252,6 +252,11 @@ static inline struct timerlat_variables *this_cpu_tmr_var(void)
+ return this_cpu_ptr(&per_cpu_timerlat_var);
+ }
+
++/*
++ * Protect the interface.
++ */
++static struct mutex interface_lock;
++
+ /*
+ * tlat_var_reset - Reset the values of the given timerlat_variables
+ */
+@@ -259,14 +264,20 @@ static inline void tlat_var_reset(void)
+ {
+ struct timerlat_variables *tlat_var;
+ int cpu;
++
++ /* Synchronize with the timerlat interfaces */
++ mutex_lock(&interface_lock);
+ /*
+ * So far, all the values are initialized as 0, so
+ * zeroing the structure is perfect.
+ */
+ for_each_cpu(cpu, cpu_online_mask) {
+ tlat_var = per_cpu_ptr(&per_cpu_timerlat_var, cpu);
++ if (tlat_var->kthread)
++ hrtimer_cancel(&tlat_var->timer);
+ memset(tlat_var, 0, sizeof(*tlat_var));
+ }
++ mutex_unlock(&interface_lock);
+ }
+ #else /* CONFIG_TIMERLAT_TRACER */
+ #define tlat_var_reset() do {} while (0)
+@@ -331,11 +342,6 @@ struct timerlat_sample {
+ };
+ #endif
+
+-/*
+- * Protect the interface.
+- */
+-static struct mutex interface_lock;
+-
+ /*
+ * Tracer data.
+ */
+@@ -1612,6 +1618,7 @@ static int run_osnoise(void)
+
+ static struct cpumask osnoise_cpumask;
+ static struct cpumask save_cpumask;
++static struct cpumask kthread_cpumask;
+
+ /*
+ * osnoise_sleep - sleep until the next period
+@@ -1675,6 +1682,7 @@ static inline int osnoise_migration_pending(void)
+ */
+ mutex_lock(&interface_lock);
+ this_cpu_osn_var()->kthread = NULL;
++ cpumask_clear_cpu(smp_processor_id(), &kthread_cpumask);
+ mutex_unlock(&interface_lock);
+
+ return 1;
+@@ -1945,11 +1953,16 @@ static void stop_kthread(unsigned int cpu)
+ {
+ struct task_struct *kthread;
+
++ mutex_lock(&interface_lock);
+ kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
+ if (kthread) {
+- if (test_bit(OSN_WORKLOAD, &osnoise_options)) {
++ per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
++ mutex_unlock(&interface_lock);
++
++ if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask) &&
++ !WARN_ON(!test_bit(OSN_WORKLOAD, &osnoise_options))) {
+ kthread_stop(kthread);
+- } else {
++ } else if (!WARN_ON(test_bit(OSN_WORKLOAD, &osnoise_options))) {
+ /*
+ * This is a user thread waiting on the timerlat_fd. We need
+ * to close all users, and the best way to guarantee this is
+@@ -1958,8 +1971,8 @@ static void stop_kthread(unsigned int cpu)
+ kill_pid(kthread->thread_pid, SIGKILL, 1);
+ put_task_struct(kthread);
+ }
+- per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
+ } else {
++ mutex_unlock(&interface_lock);
+ /* if no workload, just return */
+ if (!test_bit(OSN_WORKLOAD, &osnoise_options)) {
+ /*
+@@ -1967,7 +1980,6 @@ static void stop_kthread(unsigned int cpu)
+ */
+ per_cpu(per_cpu_osnoise_var, cpu).sampling = false;
+ barrier();
+- return;
+ }
+ }
+ }
+@@ -1982,12 +1994,8 @@ static void stop_per_cpu_kthreads(void)
+ {
+ int cpu;
+
+- cpus_read_lock();
+-
+- for_each_online_cpu(cpu)
++ for_each_possible_cpu(cpu)
+ stop_kthread(cpu);
+-
+- cpus_read_unlock();
+ }
+
+ /*
+@@ -2021,6 +2029,7 @@ static int start_kthread(unsigned int cpu)
+ }
+
+ per_cpu(per_cpu_osnoise_var, cpu).kthread = kthread;
++ cpumask_set_cpu(cpu, &kthread_cpumask);
+
+ return 0;
+ }
+@@ -2048,8 +2057,16 @@ static int start_per_cpu_kthreads(void)
+ */
+ cpumask_and(current_mask, cpu_online_mask, &osnoise_cpumask);
+
+- for_each_possible_cpu(cpu)
++ for_each_possible_cpu(cpu) {
++ if (cpumask_test_and_clear_cpu(cpu, &kthread_cpumask)) {
++ struct task_struct *kthread;
++
++ kthread = per_cpu(per_cpu_osnoise_var, cpu).kthread;
++ if (!WARN_ON(!kthread))
++ kthread_stop(kthread);
++ }
+ per_cpu(per_cpu_osnoise_var, cpu).kthread = NULL;
++ }
+
+ for_each_cpu(cpu, current_mask) {
+ retval = start_kthread(cpu);
+@@ -2579,7 +2596,8 @@ static int timerlat_fd_release(struct inode *inode, struct file *file)
+ osn_var = per_cpu_ptr(&per_cpu_osnoise_var, cpu);
+ tlat_var = per_cpu_ptr(&per_cpu_timerlat_var, cpu);
+
+- hrtimer_cancel(&tlat_var->timer);
++ if (tlat_var->kthread)
++ hrtimer_cancel(&tlat_var->timer);
+ memset(tlat_var, 0, sizeof(*tlat_var));
+
+ osn_var->sampling = 0;
+diff --git a/kernel/workqueue.c b/kernel/workqueue.c
+index c970eec25c5a0..ffbf99fb53bfb 100644
+--- a/kernel/workqueue.c
++++ b/kernel/workqueue.c
+@@ -7586,10 +7586,18 @@ static void wq_watchdog_timer_fn(struct timer_list *unused)
+
+ notrace void wq_watchdog_touch(int cpu)
+ {
++ unsigned long thresh = READ_ONCE(wq_watchdog_thresh) * HZ;
++ unsigned long touch_ts = READ_ONCE(wq_watchdog_touched);
++ unsigned long now = jiffies;
++
+ if (cpu >= 0)
+- per_cpu(wq_watchdog_touched_cpu, cpu) = jiffies;
++ per_cpu(wq_watchdog_touched_cpu, cpu) = now;
++ else
++ WARN_ONCE(1, "%s should be called with valid CPU", __func__);
+
+- wq_watchdog_touched = jiffies;
++ /* Don't unnecessarily store to global cacheline */
++ if (time_after(now, touch_ts + thresh / 4))
++ WRITE_ONCE(wq_watchdog_touched, jiffies);
+ }
+
+ static void wq_watchdog_set_thresh(unsigned long thresh)
+diff --git a/lib/codetag.c b/lib/codetag.c
+index 5ace625f2328f..afa8a2d4f3173 100644
+--- a/lib/codetag.c
++++ b/lib/codetag.c
+@@ -125,7 +125,6 @@ static inline size_t range_size(const struct codetag_type *cttype,
+ cttype->desc.tag_size;
+ }
+
+-#ifdef CONFIG_MODULES
+ static void *get_symbol(struct module *mod, const char *prefix, const char *name)
+ {
+ DECLARE_SEQ_BUF(sb, KSYM_NAME_LEN);
+@@ -155,6 +154,15 @@ static struct codetag_range get_section_range(struct module *mod,
+ };
+ }
+
++static const char *get_mod_name(__maybe_unused struct module *mod)
++{
++#ifdef CONFIG_MODULES
++ if (mod)
++ return mod->name;
++#endif
++ return "(built-in)";
++}
++
+ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
+ {
+ struct codetag_range range;
+@@ -164,8 +172,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
+ range = get_section_range(mod, cttype->desc.section);
+ if (!range.start || !range.stop) {
+ pr_warn("Failed to load code tags of type %s from the module %s\n",
+- cttype->desc.section,
+- mod ? mod->name : "(built-in)");
++ cttype->desc.section, get_mod_name(mod));
+ return -EINVAL;
+ }
+
+@@ -199,6 +206,7 @@ static int codetag_module_init(struct codetag_type *cttype, struct module *mod)
+ return 0;
+ }
+
++#ifdef CONFIG_MODULES
+ void codetag_load_module(struct module *mod)
+ {
+ struct codetag_type *cttype;
+@@ -248,9 +256,6 @@ bool codetag_unload_module(struct module *mod)
+
+ return unload_ok;
+ }
+-
+-#else /* CONFIG_MODULES */
+-static int codetag_module_init(struct codetag_type *cttype, struct module *mod) { return 0; }
+ #endif /* CONFIG_MODULES */
+
+ struct codetag_type *
+diff --git a/lib/generic-radix-tree.c b/lib/generic-radix-tree.c
+index aaefb9b678c8e..fa692c86f0696 100644
+--- a/lib/generic-radix-tree.c
++++ b/lib/generic-radix-tree.c
+@@ -121,6 +121,8 @@ void *__genradix_ptr_alloc(struct __genradix *radix, size_t offset,
+ if ((v = cmpxchg_release(&radix->root, r, new_root)) == r) {
+ v = new_root;
+ new_node = NULL;
++ } else {
++ new_node->children[0] = NULL;
+ }
+ }
+
+diff --git a/lib/maple_tree.c b/lib/maple_tree.c
+index 2d7d27e6ae3c6..f5ae38fd66969 100644
+--- a/lib/maple_tree.c
++++ b/lib/maple_tree.c
+@@ -7569,14 +7569,14 @@ static void mt_validate_nulls(struct maple_tree *mt)
+ * 2. The gap is correctly set in the parents
+ */
+ void mt_validate(struct maple_tree *mt)
++ __must_hold(mas->tree->ma_lock)
+ {
+ unsigned char end;
+
+ MA_STATE(mas, mt, 0, 0);
+- rcu_read_lock();
+ mas_start(&mas);
+ if (!mas_is_active(&mas))
+- goto done;
++ return;
+
+ while (!mte_is_leaf(mas.node))
+ mas_descend(&mas);
+@@ -7597,9 +7597,6 @@ void mt_validate(struct maple_tree *mt)
+ mas_dfs_postorder(&mas, ULONG_MAX);
+ }
+ mt_validate_nulls(mt);
+-done:
+- rcu_read_unlock();
+-
+ }
+ EXPORT_SYMBOL_GPL(mt_validate);
+
+diff --git a/lib/overflow_kunit.c b/lib/overflow_kunit.c
+index d305b0c054bb7..9249181fff37a 100644
+--- a/lib/overflow_kunit.c
++++ b/lib/overflow_kunit.c
+@@ -668,7 +668,6 @@ DEFINE_TEST_ALLOC(devm_kzalloc, devm_kfree, 1, 1, 0);
+
+ static void overflow_allocation_test(struct kunit *test)
+ {
+- const char device_name[] = "overflow-test";
+ struct device *dev;
+ int count = 0;
+
+@@ -678,7 +677,7 @@ static void overflow_allocation_test(struct kunit *test)
+ } while (0)
+
+ /* Create dummy device for devm_kmalloc()-family tests. */
+- dev = kunit_device_register(test, device_name);
++ dev = kunit_device_register(test, "overflow-test");
+ KUNIT_ASSERT_FALSE_MSG(test, IS_ERR(dev),
+ "Cannot register test device\n");
+
+diff --git a/mm/memcontrol.c b/mm/memcontrol.c
+index 332f190bf3d6b..5c44d3d304dac 100644
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@ -5804,8 +5804,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
+ WRITE_ONCE(memcg->soft_limit, PAGE_COUNTER_MAX);
+ #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_ZSWAP)
+ memcg->zswap_max = PAGE_COUNTER_MAX;
+- WRITE_ONCE(memcg->zswap_writeback,
+- !parent || READ_ONCE(parent->zswap_writeback));
++ WRITE_ONCE(memcg->zswap_writeback, true);
+ #endif
+ page_counter_set_high(&memcg->swap, PAGE_COUNTER_MAX);
+ if (parent) {
+@@ -8444,7 +8443,14 @@ void obj_cgroup_uncharge_zswap(struct obj_cgroup *objcg, size_t size)
+ bool mem_cgroup_zswap_writeback_enabled(struct mem_cgroup *memcg)
+ {
+ /* if zswap is disabled, do not block pages going to the swapping device */
+- return !is_zswap_enabled() || !memcg || READ_ONCE(memcg->zswap_writeback);
++ if (!zswap_is_enabled())
++ return true;
++
++ for (; memcg; memcg = parent_mem_cgroup(memcg))
++ if (!READ_ONCE(memcg->zswap_writeback))
++ return false;
++
++ return true;
+ }
+
+ static u64 zswap_current_read(struct cgroup_subsys_state *css,
+diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
+index 431b1f6753c0b..52553b13e2770 100644
+--- a/mm/memory_hotplug.c
++++ b/mm/memory_hotplug.c
+@@ -1682,7 +1682,7 @@ struct range __weak arch_get_mappable_range(void)
+
+ struct range mhp_get_pluggable_range(bool need_mapping)
+ {
+- const u64 max_phys = (1ULL << MAX_PHYSMEM_BITS) - 1;
++ const u64 max_phys = PHYSMEM_END;
+ struct range mhp_range;
+
+ if (need_mapping) {
+diff --git a/mm/page_alloc.c b/mm/page_alloc.c
+index b50060405d947..21016573f1870 100644
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -1053,6 +1053,13 @@ __always_inline bool free_pages_prepare(struct page *page,
+ reset_page_owner(page, order);
+ page_table_check_free(page, order);
+ pgalloc_tag_sub(page, 1 << order);
++
++ /*
++ * The page is isolated and accounted for.
++ * Mark the codetag as empty to avoid accounting error
++ * when the page is freed by unpoison_memory().
++ */
++ clear_page_tag_ref(page);
+ return false;
+ }
+
+diff --git a/mm/slub.c b/mm/slub.c
+index 849e8972e2ffc..be0ef60984ac4 100644
+--- a/mm/slub.c
++++ b/mm/slub.c
+@@ -2044,6 +2044,10 @@ alloc_tagging_slab_free_hook(struct kmem_cache *s, struct slab *slab, void **p,
+ if (!mem_alloc_profiling_enabled())
+ return;
+
++ /* slab->obj_exts might not be NULL if it was created for MEMCG accounting. */
++ if (s->flags & (SLAB_NO_OBJ_EXT | SLAB_NOLEAKTRACE))
++ return;
++
+ obj_exts = slab_obj_exts(slab);
+ if (!obj_exts)
+ return;
+diff --git a/mm/sparse.c b/mm/sparse.c
+index de40b2c734067..168278d61bdef 100644
+--- a/mm/sparse.c
++++ b/mm/sparse.c
+@@ -129,7 +129,7 @@ static inline int sparse_early_nid(struct mem_section *section)
+ static void __meminit mminit_validate_memmodel_limits(unsigned long *start_pfn,
+ unsigned long *end_pfn)
+ {
+- unsigned long max_sparsemem_pfn = 1UL << (MAX_PHYSMEM_BITS-PAGE_SHIFT);
++ unsigned long max_sparsemem_pfn = (PHYSMEM_END + 1) >> PAGE_SHIFT;
+
+ /*
+ * Sanity checks - do not allow an architecture to pass
+diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c
+index defa5109cc62a..75f47706882fb 100644
+--- a/mm/userfaultfd.c
++++ b/mm/userfaultfd.c
+@@ -787,27 +787,30 @@ static __always_inline ssize_t mfill_atomic(struct userfaultfd_ctx *ctx,
+ }
+
+ dst_pmdval = pmdp_get_lockless(dst_pmd);
+- /*
+- * If the dst_pmd is mapped as THP don't
+- * override it and just be strict.
+- */
+- if (unlikely(pmd_trans_huge(dst_pmdval))) {
+- err = -EEXIST;
+- break;
+- }
+ if (unlikely(pmd_none(dst_pmdval)) &&
+ unlikely(__pte_alloc(dst_mm, dst_pmd))) {
+ err = -ENOMEM;
+ break;
+ }
+- /* If an huge pmd materialized from under us fail */
+- if (unlikely(pmd_trans_huge(*dst_pmd))) {
++ dst_pmdval = pmdp_get_lockless(dst_pmd);
++ /*
++ * If the dst_pmd is THP don't override it and just be strict.
++ * (This includes the case where the PMD used to be THP and
++ * changed back to none after __pte_alloc().)
++ */
++ if (unlikely(!pmd_present(dst_pmdval) || pmd_trans_huge(dst_pmdval) ||
++ pmd_devmap(dst_pmdval))) {
++ err = -EEXIST;
++ break;
++ }
++ if (unlikely(pmd_bad(dst_pmdval))) {
+ err = -EFAULT;
+ break;
+ }
+-
+- BUG_ON(pmd_none(*dst_pmd));
+- BUG_ON(pmd_trans_huge(*dst_pmd));
++ /*
++ * For shmem mappings, khugepaged is allowed to remove page
++ * tables under us; pte_offset_map_lock() will deal with that.
++ */
+
+ err = mfill_atomic_pte(dst_pmd, dst_vma, dst_addr,
+ src_addr, flags, &folio);
+diff --git a/mm/vmalloc.c b/mm/vmalloc.c
+index 881e497137e5d..bc6be460457d8 100644
+--- a/mm/vmalloc.c
++++ b/mm/vmalloc.c
+@@ -2190,6 +2190,7 @@ static void purge_vmap_node(struct work_struct *work)
+ {
+ struct vmap_node *vn = container_of(work,
+ struct vmap_node, purge_work);
++ unsigned long nr_purged_pages = 0;
+ struct vmap_area *va, *n_va;
+ LIST_HEAD(local_list);
+
+@@ -2207,7 +2208,7 @@ static void purge_vmap_node(struct work_struct *work)
+ kasan_release_vmalloc(orig_start, orig_end,
+ va->va_start, va->va_end);
+
+- atomic_long_sub(nr, &vmap_lazy_nr);
++ nr_purged_pages += nr;
+ vn->nr_purged++;
+
+ if (is_vn_id_valid(vn_id) && !vn->skip_populate)
+@@ -2218,6 +2219,8 @@ static void purge_vmap_node(struct work_struct *work)
+ list_add(&va->list, &local_list);
+ }
+
++ atomic_long_sub(nr_purged_pages, &vmap_lazy_nr);
++
+ reclaim_list_global(&local_list);
+ }
+
+@@ -2625,6 +2628,7 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
+ vb->dirty_max = 0;
+ bitmap_set(vb->used_map, 0, (1UL << order));
+ INIT_LIST_HEAD(&vb->free_list);
++ vb->cpu = raw_smp_processor_id();
+
+ xa = addr_to_vb_xa(va->va_start);
+ vb_idx = addr_to_vb_idx(va->va_start);
+@@ -2641,7 +2645,6 @@ static void *new_vmap_block(unsigned int order, gfp_t gfp_mask)
+ * integrity together with list_for_each_rcu from read
+ * side.
+ */
+- vb->cpu = raw_smp_processor_id();
+ vbq = per_cpu_ptr(&vmap_block_queue, vb->cpu);
+ spin_lock(&vbq->lock);
+ list_add_tail_rcu(&vb->free_list, &vbq->free);
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 68ac33bea3a3c..99a0c152a85e2 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -1587,25 +1587,6 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
+
+ }
+
+-#ifdef CONFIG_CMA
+-/*
+- * It is waste of effort to scan and reclaim CMA pages if it is not available
+- * for current allocation context. Kswapd can not be enrolled as it can not
+- * distinguish this scenario by using sc->gfp_mask = GFP_KERNEL
+- */
+-static bool skip_cma(struct folio *folio, struct scan_control *sc)
+-{
+- return !current_is_kswapd() &&
+- gfp_migratetype(sc->gfp_mask) != MIGRATE_MOVABLE &&
+- folio_migratetype(folio) == MIGRATE_CMA;
+-}
+-#else
+-static bool skip_cma(struct folio *folio, struct scan_control *sc)
+-{
+- return false;
+-}
+-#endif
+-
+ /*
+ * Isolating page from the lruvec to fill in @dst list by nr_to_scan times.
+ *
+@@ -1652,8 +1633,7 @@ static unsigned long isolate_lru_folios(unsigned long nr_to_scan,
+ nr_pages = folio_nr_pages(folio);
+ total_scan += nr_pages;
+
+- if (folio_zonenum(folio) > sc->reclaim_idx ||
+- skip_cma(folio, sc)) {
++ if (folio_zonenum(folio) > sc->reclaim_idx) {
+ nr_skipped[folio_zonenum(folio)] += nr_pages;
+ move_to = &folios_skipped;
+ goto move;
+@@ -4314,7 +4294,7 @@ static bool sort_folio(struct lruvec *lruvec, struct folio *folio, struct scan_c
+ }
+
+ /* ineligible */
+- if (zone > sc->reclaim_idx || skip_cma(folio, sc)) {
++ if (zone > sc->reclaim_idx) {
+ gen = folio_inc_gen(lruvec, folio, false);
+ list_move_tail(&folio->lru, &lrugen->folios[gen][type][zone]);
+ return true;
+diff --git a/mm/zswap.c b/mm/zswap.c
+index a50e2986cd2fa..ac65758dd2af6 100644
+--- a/mm/zswap.c
++++ b/mm/zswap.c
+@@ -131,7 +131,7 @@ static bool zswap_shrinker_enabled = IS_ENABLED(
+ CONFIG_ZSWAP_SHRINKER_DEFAULT_ON);
+ module_param_named(shrinker_enabled, zswap_shrinker_enabled, bool, 0644);
+
+-bool is_zswap_enabled(void)
++bool zswap_is_enabled(void)
+ {
+ return zswap_enabled;
+ }
+diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c
+index 080053a85b4d6..3c74d171085de 100644
+--- a/net/bluetooth/hci_conn.c
++++ b/net/bluetooth/hci_conn.c
+@@ -2953,5 +2953,9 @@ int hci_abort_conn(struct hci_conn *conn, u8 reason)
+ return 0;
+ }
+
+- return hci_cmd_sync_queue_once(hdev, abort_conn_sync, conn, NULL);
++ /* Run immediately if on cmd_sync_work since this may be called
++ * as a result to MGMT_OP_DISCONNECT/MGMT_OP_UNPAIR which does
++ * already queue its callback on cmd_sync_work.
++ */
++ return hci_cmd_sync_run_once(hdev, abort_conn_sync, conn, NULL);
+ }
+diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
+index 4e90bd722e7b5..f4a54dbc07f19 100644
+--- a/net/bluetooth/hci_sync.c
++++ b/net/bluetooth/hci_sync.c
+@@ -114,7 +114,7 @@ static void hci_cmd_sync_add(struct hci_request *req, u16 opcode, u32 plen,
+ skb_queue_tail(&req->cmd_q, skb);
+ }
+
+-static int hci_cmd_sync_run(struct hci_request *req)
++static int hci_req_sync_run(struct hci_request *req)
+ {
+ struct hci_dev *hdev = req->hdev;
+ struct sk_buff *skb;
+@@ -164,7 +164,7 @@ struct sk_buff *__hci_cmd_sync_sk(struct hci_dev *hdev, u16 opcode, u32 plen,
+
+ hdev->req_status = HCI_REQ_PEND;
+
+- err = hci_cmd_sync_run(&req);
++ err = hci_req_sync_run(&req);
+ if (err < 0)
+ return ERR_PTR(err);
+
+@@ -730,6 +730,44 @@ int hci_cmd_sync_queue_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
+ }
+ EXPORT_SYMBOL(hci_cmd_sync_queue_once);
+
++/* Run HCI command:
++ *
++ * - hdev must be running
++ * - if on cmd_sync_work then run immediately otherwise queue
++ */
++int hci_cmd_sync_run(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
++ void *data, hci_cmd_sync_work_destroy_t destroy)
++{
++ /* Only queue command if hdev is running which means it had been opened
++ * and is either on init phase or is already up.
++ */
++ if (!test_bit(HCI_RUNNING, &hdev->flags))
++ return -ENETDOWN;
++
++ /* If on cmd_sync_work then run immediately otherwise queue */
++ if (current_work() == &hdev->cmd_sync_work)
++ return func(hdev, data);
++
++ return hci_cmd_sync_submit(hdev, func, data, destroy);
++}
++EXPORT_SYMBOL(hci_cmd_sync_run);
++
++/* Run HCI command entry once:
++ *
++ * - Lookup if an entry already exist and only if it doesn't creates a new entry
++ * and run it.
++ * - if on cmd_sync_work then run immediately otherwise queue
++ */
++int hci_cmd_sync_run_once(struct hci_dev *hdev, hci_cmd_sync_work_func_t func,
++ void *data, hci_cmd_sync_work_destroy_t destroy)
++{
++ if (hci_cmd_sync_lookup_entry(hdev, func, data, destroy))
++ return 0;
++
++ return hci_cmd_sync_run(hdev, func, data, destroy);
++}
++EXPORT_SYMBOL(hci_cmd_sync_run_once);
++
+ /* Lookup HCI command entry:
+ *
+ * - Return first entry that matches by function callback or data or
+diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
+index ad4793ea052df..ba28907afb3fa 100644
+--- a/net/bluetooth/mgmt.c
++++ b/net/bluetooth/mgmt.c
+@@ -2831,16 +2831,6 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
+ bt_dev_dbg(hdev, "debug_keys %u key_count %u", cp->debug_keys,
+ key_count);
+
+- for (i = 0; i < key_count; i++) {
+- struct mgmt_link_key_info *key = &cp->keys[i];
+-
+- /* Considering SMP over BREDR/LE, there is no need to check addr_type */
+- if (key->type > 0x08)
+- return mgmt_cmd_status(sk, hdev->id,
+- MGMT_OP_LOAD_LINK_KEYS,
+- MGMT_STATUS_INVALID_PARAMS);
+- }
+-
+ hci_dev_lock(hdev);
+
+ hci_link_keys_clear(hdev);
+@@ -2865,6 +2855,19 @@ static int load_link_keys(struct sock *sk, struct hci_dev *hdev, void *data,
+ continue;
+ }
+
++ if (key->addr.type != BDADDR_BREDR) {
++ bt_dev_warn(hdev,
++ "Invalid link address type %u for %pMR",
++ key->addr.type, &key->addr.bdaddr);
++ continue;
++ }
++
++ if (key->type > 0x08) {
++ bt_dev_warn(hdev, "Invalid link key type %u for %pMR",
++ key->type, &key->addr.bdaddr);
++ continue;
++ }
++
+ /* Always ignore debug keys and require a new pairing if
+ * the user wants to use them.
+ */
+@@ -2922,7 +2925,12 @@ static int unpair_device_sync(struct hci_dev *hdev, void *data)
+ if (!conn)
+ return 0;
+
+- return hci_abort_conn_sync(hdev, conn, HCI_ERROR_REMOTE_USER_TERM);
++ /* Disregard any possible error since the likes of hci_abort_conn_sync
++ * will clean up the connection no matter the error.
++ */
++ hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM);
++
++ return 0;
+ }
+
+ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
+@@ -3054,13 +3062,44 @@ static int unpair_device(struct sock *sk, struct hci_dev *hdev, void *data,
+ return err;
+ }
+
++static void disconnect_complete(struct hci_dev *hdev, void *data, int err)
++{
++ struct mgmt_pending_cmd *cmd = data;
++
++ cmd->cmd_complete(cmd, mgmt_status(err));
++ mgmt_pending_free(cmd);
++}
++
++static int disconnect_sync(struct hci_dev *hdev, void *data)
++{
++ struct mgmt_pending_cmd *cmd = data;
++ struct mgmt_cp_disconnect *cp = cmd->param;
++ struct hci_conn *conn;
++
++ if (cp->addr.type == BDADDR_BREDR)
++ conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
++ &cp->addr.bdaddr);
++ else
++ conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr,
++ le_addr_type(cp->addr.type));
++
++ if (!conn)
++ return -ENOTCONN;
++
++ /* Disregard any possible error since the likes of hci_abort_conn_sync
++ * will clean up the connection no matter the error.
++ */
++ hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM);
++
++ return 0;
++}
++
+ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data,
+ u16 len)
+ {
+ struct mgmt_cp_disconnect *cp = data;
+ struct mgmt_rp_disconnect rp;
+ struct mgmt_pending_cmd *cmd;
+- struct hci_conn *conn;
+ int err;
+
+ bt_dev_dbg(hdev, "sock %p", sk);
+@@ -3083,27 +3122,7 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data,
+ goto failed;
+ }
+
+- if (pending_find(MGMT_OP_DISCONNECT, hdev)) {
+- err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
+- MGMT_STATUS_BUSY, &rp, sizeof(rp));
+- goto failed;
+- }
+-
+- if (cp->addr.type == BDADDR_BREDR)
+- conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK,
+- &cp->addr.bdaddr);
+- else
+- conn = hci_conn_hash_lookup_le(hdev, &cp->addr.bdaddr,
+- le_addr_type(cp->addr.type));
+-
+- if (!conn || conn->state == BT_OPEN || conn->state == BT_CLOSED) {
+- err = mgmt_cmd_complete(sk, hdev->id, MGMT_OP_DISCONNECT,
+- MGMT_STATUS_NOT_CONNECTED, &rp,
+- sizeof(rp));
+- goto failed;
+- }
+-
+- cmd = mgmt_pending_add(sk, MGMT_OP_DISCONNECT, hdev, data, len);
++ cmd = mgmt_pending_new(sk, MGMT_OP_DISCONNECT, hdev, data, len);
+ if (!cmd) {
+ err = -ENOMEM;
+ goto failed;
+@@ -3111,9 +3130,10 @@ static int disconnect(struct sock *sk, struct hci_dev *hdev, void *data,
+
+ cmd->cmd_complete = generic_cmd_complete;
+
+- err = hci_disconnect(conn, HCI_ERROR_REMOTE_USER_TERM);
++ err = hci_cmd_sync_queue(hdev, disconnect_sync, cmd,
++ disconnect_complete);
+ if (err < 0)
+- mgmt_pending_remove(cmd);
++ mgmt_pending_free(cmd);
+
+ failed:
+ hci_dev_unlock(hdev);
+@@ -7073,7 +7093,6 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
+
+ for (i = 0; i < irk_count; i++) {
+ struct mgmt_irk_info *irk = &cp->irks[i];
+- u8 addr_type = le_addr_type(irk->addr.type);
+
+ if (hci_is_blocked_key(hdev,
+ HCI_BLOCKED_KEY_TYPE_IRK,
+@@ -7083,12 +7102,8 @@ static int load_irks(struct sock *sk, struct hci_dev *hdev, void *cp_data,
+ continue;
+ }
+
+- /* When using SMP over BR/EDR, the addr type should be set to BREDR */
+- if (irk->addr.type == BDADDR_BREDR)
+- addr_type = BDADDR_BREDR;
+-
+ hci_add_irk(hdev, &irk->addr.bdaddr,
+- addr_type, irk->val,
++ le_addr_type(irk->addr.type), irk->val,
+ BDADDR_ANY);
+ }
+
+@@ -7153,15 +7168,6 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
+
+ bt_dev_dbg(hdev, "key_count %u", key_count);
+
+- for (i = 0; i < key_count; i++) {
+- struct mgmt_ltk_info *key = &cp->keys[i];
+-
+- if (!ltk_is_valid(key))
+- return mgmt_cmd_status(sk, hdev->id,
+- MGMT_OP_LOAD_LONG_TERM_KEYS,
+- MGMT_STATUS_INVALID_PARAMS);
+- }
+-
+ hci_dev_lock(hdev);
+
+ hci_smp_ltks_clear(hdev);
+@@ -7169,7 +7175,6 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
+ for (i = 0; i < key_count; i++) {
+ struct mgmt_ltk_info *key = &cp->keys[i];
+ u8 type, authenticated;
+- u8 addr_type = le_addr_type(key->addr.type);
+
+ if (hci_is_blocked_key(hdev,
+ HCI_BLOCKED_KEY_TYPE_LTK,
+@@ -7179,6 +7184,12 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
+ continue;
+ }
+
++ if (!ltk_is_valid(key)) {
++ bt_dev_warn(hdev, "Invalid LTK for %pMR",
++ &key->addr.bdaddr);
++ continue;
++ }
++
+ switch (key->type) {
+ case MGMT_LTK_UNAUTHENTICATED:
+ authenticated = 0x00;
+@@ -7204,12 +7215,8 @@ static int load_long_term_keys(struct sock *sk, struct hci_dev *hdev,
+ continue;
+ }
+
+- /* When using SMP over BR/EDR, the addr type should be set to BREDR */
+- if (key->addr.type == BDADDR_BREDR)
+- addr_type = BDADDR_BREDR;
+-
+ hci_add_ltk(hdev, &key->addr.bdaddr,
+- addr_type, type, authenticated,
++ le_addr_type(key->addr.type), type, authenticated,
+ key->val, key->enc_size, key->ediv, key->rand);
+ }
+
+@@ -9457,7 +9464,7 @@ void mgmt_new_link_key(struct hci_dev *hdev, struct link_key *key,
+
+ ev.store_hint = persistent;
+ bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
+- ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
++ ev.key.addr.type = BDADDR_BREDR;
+ ev.key.type = key->type;
+ memcpy(ev.key.val, key->val, HCI_LINK_KEY_SIZE);
+ ev.key.pin_len = key->pin_len;
+@@ -9508,7 +9515,7 @@ void mgmt_new_ltk(struct hci_dev *hdev, struct smp_ltk *key, bool persistent)
+ ev.store_hint = persistent;
+
+ bacpy(&ev.key.addr.bdaddr, &key->bdaddr);
+- ev.key.addr.type = link_to_bdaddr(key->link_type, key->bdaddr_type);
++ ev.key.addr.type = link_to_bdaddr(LE_LINK, key->bdaddr_type);
+ ev.key.type = mgmt_ltk_type(key);
+ ev.key.enc_size = key->enc_size;
+ ev.key.ediv = key->ediv;
+@@ -9537,7 +9544,7 @@ void mgmt_new_irk(struct hci_dev *hdev, struct smp_irk *irk, bool persistent)
+
+ bacpy(&ev.rpa, &irk->rpa);
+ bacpy(&ev.irk.addr.bdaddr, &irk->bdaddr);
+- ev.irk.addr.type = link_to_bdaddr(irk->link_type, irk->addr_type);
++ ev.irk.addr.type = link_to_bdaddr(LE_LINK, irk->addr_type);
+ memcpy(ev.irk.val, irk->val, sizeof(irk->val));
+
+ mgmt_event(MGMT_EV_NEW_IRK, hdev, &ev, sizeof(ev), NULL);
+@@ -9566,7 +9573,7 @@ void mgmt_new_csrk(struct hci_dev *hdev, struct smp_csrk *csrk,
+ ev.store_hint = persistent;
+
+ bacpy(&ev.key.addr.bdaddr, &csrk->bdaddr);
+- ev.key.addr.type = link_to_bdaddr(csrk->link_type, csrk->bdaddr_type);
++ ev.key.addr.type = link_to_bdaddr(LE_LINK, csrk->bdaddr_type);
+ ev.key.type = csrk->type;
+ memcpy(ev.key.val, csrk->val, sizeof(csrk->val));
+
+@@ -9644,18 +9651,6 @@ void mgmt_device_connected(struct hci_dev *hdev, struct hci_conn *conn,
+ mgmt_event_skb(skb, NULL);
+ }
+
+-static void disconnect_rsp(struct mgmt_pending_cmd *cmd, void *data)
+-{
+- struct sock **sk = data;
+-
+- cmd->cmd_complete(cmd, 0);
+-
+- *sk = cmd->sk;
+- sock_hold(*sk);
+-
+- mgmt_pending_remove(cmd);
+-}
+-
+ static void unpair_device_rsp(struct mgmt_pending_cmd *cmd, void *data)
+ {
+ struct hci_dev *hdev = data;
+@@ -9699,8 +9694,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
+ if (link_type != ACL_LINK && link_type != LE_LINK)
+ return;
+
+- mgmt_pending_foreach(MGMT_OP_DISCONNECT, hdev, disconnect_rsp, &sk);
+-
+ bacpy(&ev.addr.bdaddr, bdaddr);
+ ev.addr.type = link_to_bdaddr(link_type, addr_type);
+ ev.reason = reason;
+@@ -9713,9 +9706,6 @@ void mgmt_device_disconnected(struct hci_dev *hdev, bdaddr_t *bdaddr,
+
+ if (sk)
+ sock_put(sk);
+-
+- mgmt_pending_foreach(MGMT_OP_UNPAIR_DEVICE, hdev, unpair_device_rsp,
+- hdev);
+ }
+
+ void mgmt_disconnect_failed(struct hci_dev *hdev, bdaddr_t *bdaddr,
+diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
+index 4f9fdf400584e..8b9724fd752a1 100644
+--- a/net/bluetooth/smp.c
++++ b/net/bluetooth/smp.c
+@@ -1060,7 +1060,6 @@ static void smp_notify_keys(struct l2cap_conn *conn)
+ }
+
+ if (smp->remote_irk) {
+- smp->remote_irk->link_type = hcon->type;
+ mgmt_new_irk(hdev, smp->remote_irk, persistent);
+
+ /* Now that user space can be considered to know the
+@@ -1080,28 +1079,24 @@ static void smp_notify_keys(struct l2cap_conn *conn)
+ }
+
+ if (smp->csrk) {
+- smp->csrk->link_type = hcon->type;
+ smp->csrk->bdaddr_type = hcon->dst_type;
+ bacpy(&smp->csrk->bdaddr, &hcon->dst);
+ mgmt_new_csrk(hdev, smp->csrk, persistent);
+ }
+
+ if (smp->responder_csrk) {
+- smp->responder_csrk->link_type = hcon->type;
+ smp->responder_csrk->bdaddr_type = hcon->dst_type;
+ bacpy(&smp->responder_csrk->bdaddr, &hcon->dst);
+ mgmt_new_csrk(hdev, smp->responder_csrk, persistent);
+ }
+
+ if (smp->ltk) {
+- smp->ltk->link_type = hcon->type;
+ smp->ltk->bdaddr_type = hcon->dst_type;
+ bacpy(&smp->ltk->bdaddr, &hcon->dst);
+ mgmt_new_ltk(hdev, smp->ltk, persistent);
+ }
+
+ if (smp->responder_ltk) {
+- smp->responder_ltk->link_type = hcon->type;
+ smp->responder_ltk->bdaddr_type = hcon->dst_type;
+ bacpy(&smp->responder_ltk->bdaddr, &hcon->dst);
+ mgmt_new_ltk(hdev, smp->responder_ltk, persistent);
+@@ -1121,8 +1116,6 @@ static void smp_notify_keys(struct l2cap_conn *conn)
+ key = hci_add_link_key(hdev, smp->conn->hcon, &hcon->dst,
+ smp->link_key, type, 0, &persistent);
+ if (key) {
+- key->link_type = hcon->type;
+- key->bdaddr_type = hcon->dst_type;
+ mgmt_new_link_key(hdev, key, persistent);
+
+ /* Don't keep debug keys around if the relevant
+diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c
+index c77591e638417..ad7a42b505ef9 100644
+--- a/net/bridge/br_fdb.c
++++ b/net/bridge/br_fdb.c
+@@ -1469,12 +1469,10 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p,
+ modified = true;
+ }
+
+- if (test_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) {
++ if (test_and_set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags)) {
+ /* Refresh entry */
+ fdb->used = jiffies;
+- } else if (!test_bit(BR_FDB_ADDED_BY_USER, &fdb->flags)) {
+- /* Take over SW learned entry */
+- set_bit(BR_FDB_ADDED_BY_EXT_LEARN, &fdb->flags);
++ } else {
+ modified = true;
+ }
+
+diff --git a/net/can/bcm.c b/net/can/bcm.c
+index 27d5fcf0eac9d..46d3ec3aa44b4 100644
+--- a/net/can/bcm.c
++++ b/net/can/bcm.c
+@@ -1470,6 +1470,10 @@ static void bcm_notify(struct bcm_sock *bo, unsigned long msg,
+
+ /* remove device reference, if this is our bound device */
+ if (bo->bound && bo->ifindex == dev->ifindex) {
++#if IS_ENABLED(CONFIG_PROC_FS)
++ if (sock_net(sk)->can.bcmproc_dir && bo->bcm_proc_read)
++ remove_proc_entry(bo->procname, sock_net(sk)->can.bcmproc_dir);
++#endif
+ bo->bound = 0;
+ bo->ifindex = 0;
+ notify_enodev = 1;
+diff --git a/net/core/filter.c b/net/core/filter.c
+index ab0455c64e49a..55b1d9de2334d 100644
+--- a/net/core/filter.c
++++ b/net/core/filter.c
+@@ -11047,7 +11047,6 @@ const struct bpf_verifier_ops lwt_seg6local_verifier_ops = {
+ };
+
+ const struct bpf_prog_ops lwt_seg6local_prog_ops = {
+- .test_run = bpf_prog_test_run_skb,
+ };
+
+ const struct bpf_verifier_ops cg_sock_verifier_ops = {
+diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
+index dc91921da4ea0..15ad775ddd3c1 100644
+--- a/net/core/net-sysfs.c
++++ b/net/core/net-sysfs.c
+@@ -1524,7 +1524,7 @@ static const struct attribute_group dql_group = {
+ };
+ #else
+ /* Fake declaration, all the code using it should be dead */
+-extern const struct attribute_group dql_group;
++static const struct attribute_group dql_group = {};
+ #endif /* CONFIG_BQL */
+
+ #ifdef CONFIG_XPS
+diff --git a/net/ethtool/channels.c b/net/ethtool/channels.c
+index 7b4bbd674bae7..cee188da54f85 100644
+--- a/net/ethtool/channels.c
++++ b/net/ethtool/channels.c
+@@ -171,11 +171,9 @@ ethnl_set_channels(struct ethnl_req_info *req_info, struct genl_info *info)
+ */
+ if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use))
+ max_rxnfc_in_use = 0;
+- if (!netif_is_rxfh_configured(dev) ||
+- ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use))
+- max_rxfh_in_use = 0;
++ max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev);
+ if (channels.combined_count + channels.rx_count <= max_rxfh_in_use) {
+- GENL_SET_ERR_MSG(info, "requested channel counts are too low for existing indirection table settings");
++ GENL_SET_ERR_MSG_FMT(info, "requested channel counts are too low for existing indirection table (%d)", max_rxfh_in_use);
+ return -EINVAL;
+ }
+ if (channels.combined_count + channels.rx_count <= max_rxnfc_in_use) {
+diff --git a/net/ethtool/common.c b/net/ethtool/common.c
+index 6b2a360dcdf06..8a62375ebd1f0 100644
+--- a/net/ethtool/common.c
++++ b/net/ethtool/common.c
+@@ -587,35 +587,39 @@ int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max)
+ return err;
+ }
+
+-int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max)
++u32 ethtool_get_max_rxfh_channel(struct net_device *dev)
+ {
+ struct ethtool_rxfh_param rxfh = {};
+- u32 dev_size, current_max = 0;
++ u32 dev_size, current_max;
+ int ret;
+
++ if (!netif_is_rxfh_configured(dev))
++ return 0;
++
+ if (!dev->ethtool_ops->get_rxfh_indir_size ||
+ !dev->ethtool_ops->get_rxfh)
+- return -EOPNOTSUPP;
++ return 0;
+ dev_size = dev->ethtool_ops->get_rxfh_indir_size(dev);
+ if (dev_size == 0)
+- return -EOPNOTSUPP;
++ return 0;
+
+ rxfh.indir = kcalloc(dev_size, sizeof(rxfh.indir[0]), GFP_USER);
+ if (!rxfh.indir)
+- return -ENOMEM;
++ return U32_MAX;
+
+ ret = dev->ethtool_ops->get_rxfh(dev, &rxfh);
+- if (ret)
+- goto out;
++ if (ret) {
++ current_max = U32_MAX;
++ goto out_free;
++ }
+
++ current_max = 0;
+ while (dev_size--)
+ current_max = max(current_max, rxfh.indir[dev_size]);
+
+- *max = current_max;
+-
+-out:
++out_free:
+ kfree(rxfh.indir);
+- return ret;
++ return current_max;
+ }
+
+ int ethtool_check_ops(const struct ethtool_ops *ops)
+diff --git a/net/ethtool/common.h b/net/ethtool/common.h
+index 28b8aaaf9bcb3..b55705a9ad5aa 100644
+--- a/net/ethtool/common.h
++++ b/net/ethtool/common.h
+@@ -42,7 +42,7 @@ int __ethtool_get_link(struct net_device *dev);
+ bool convert_legacy_settings_to_link_ksettings(
+ struct ethtool_link_ksettings *link_ksettings,
+ const struct ethtool_cmd *legacy_settings);
+-int ethtool_get_max_rxfh_channel(struct net_device *dev, u32 *max);
++u32 ethtool_get_max_rxfh_channel(struct net_device *dev);
+ int ethtool_get_max_rxnfc_channel(struct net_device *dev, u64 *max);
+ int __ethtool_get_ts_info(struct net_device *dev, struct ethtool_ts_info *info);
+
+diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
+index f99fd564d0ee5..2f5b69d5d4b00 100644
+--- a/net/ethtool/ioctl.c
++++ b/net/ethtool/ioctl.c
+@@ -1928,9 +1928,7 @@ static noinline_for_stack int ethtool_set_channels(struct net_device *dev,
+ * indirection table/rxnfc settings */
+ if (ethtool_get_max_rxnfc_channel(dev, &max_rxnfc_in_use))
+ max_rxnfc_in_use = 0;
+- if (!netif_is_rxfh_configured(dev) ||
+- ethtool_get_max_rxfh_channel(dev, &max_rxfh_in_use))
+- max_rxfh_in_use = 0;
++ max_rxfh_in_use = ethtool_get_max_rxfh_channel(dev);
+ if (channels.combined_count + channels.rx_count <=
+ max_t(u64, max_rxnfc_in_use, max_rxfh_in_use))
+ return -EINVAL;
+diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
+index 0abbc413e0fe5..78b869b314921 100644
+--- a/net/ipv4/fou_core.c
++++ b/net/ipv4/fou_core.c
+@@ -50,7 +50,7 @@ struct fou_net {
+
+ static inline struct fou *fou_from_sock(struct sock *sk)
+ {
+- return sk->sk_user_data;
++ return rcu_dereference_sk_user_data(sk);
+ }
+
+ static int fou_recv_pull(struct sk_buff *skb, struct fou *fou, size_t len)
+@@ -233,9 +233,15 @@ static struct sk_buff *fou_gro_receive(struct sock *sk,
+ struct sk_buff *skb)
+ {
+ const struct net_offload __rcu **offloads;
+- u8 proto = fou_from_sock(sk)->protocol;
++ struct fou *fou = fou_from_sock(sk);
+ const struct net_offload *ops;
+ struct sk_buff *pp = NULL;
++ u8 proto;
++
++ if (!fou)
++ goto out;
++
++ proto = fou->protocol;
+
+ /* We can clear the encap_mark for FOU as we are essentially doing
+ * one of two possible things. We are either adding an L4 tunnel
+@@ -263,14 +269,24 @@ static int fou_gro_complete(struct sock *sk, struct sk_buff *skb,
+ int nhoff)
+ {
+ const struct net_offload __rcu **offloads;
+- u8 proto = fou_from_sock(sk)->protocol;
++ struct fou *fou = fou_from_sock(sk);
+ const struct net_offload *ops;
+- int err = -ENOSYS;
++ u8 proto;
++ int err;
++
++ if (!fou) {
++ err = -ENOENT;
++ goto out;
++ }
++
++ proto = fou->protocol;
+
+ offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
+ ops = rcu_dereference(offloads[proto]);
+- if (WARN_ON(!ops || !ops->callbacks.gro_complete))
++ if (WARN_ON(!ops || !ops->callbacks.gro_complete)) {
++ err = -ENOSYS;
+ goto out;
++ }
+
+ err = ops->callbacks.gro_complete(skb, nhoff);
+
+@@ -320,6 +336,9 @@ static struct sk_buff *gue_gro_receive(struct sock *sk,
+ struct gro_remcsum grc;
+ u8 proto;
+
++ if (!fou)
++ goto out;
++
+ skb_gro_remcsum_init(&grc);
+
+ off = skb_gro_offset(skb);
+diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c
+index 53b0d62fd2c2d..fe6178715ba05 100644
+--- a/net/ipv4/tcp_bpf.c
++++ b/net/ipv4/tcp_bpf.c
+@@ -577,7 +577,7 @@ static int tcp_bpf_sendmsg(struct sock *sk, struct msghdr *msg, size_t size)
+ err = sk_stream_error(sk, msg->msg_flags, err);
+ release_sock(sk);
+ sk_psock_put(sk, psock);
+- return copied ? copied : err;
++ return copied > 0 ? copied : err;
+ }
+
+ enum {
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+index 2c52f6dcbd290..f130eccade393 100644
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -6004,6 +6004,11 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
+ * RFC 5961 4.2 : Send a challenge ack
+ */
+ if (th->syn) {
++ if (sk->sk_state == TCP_SYN_RECV && sk->sk_socket && th->ack &&
++ TCP_SKB_CB(skb)->seq + 1 == TCP_SKB_CB(skb)->end_seq &&
++ TCP_SKB_CB(skb)->seq + 1 == tp->rcv_nxt &&
++ TCP_SKB_CB(skb)->ack_seq == tp->snd_nxt)
++ goto pass;
+ syn_challenge:
+ if (syn_inerr)
+ TCP_INC_STATS(sock_net(sk), TCP_MIB_INERRS);
+@@ -6013,6 +6018,7 @@ static bool tcp_validate_incoming(struct sock *sk, struct sk_buff *skb,
+ goto discard;
+ }
+
++pass:
+ bpf_skops_parse_hdr(sk, skb);
+
+ return true;
+diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h
+index ad5f6f6ba3330..85b92917849bf 100644
+--- a/net/ipv6/ila/ila.h
++++ b/net/ipv6/ila/ila.h
+@@ -108,6 +108,7 @@ int ila_lwt_init(void);
+ void ila_lwt_fini(void);
+
+ int ila_xlat_init_net(struct net *net);
++void ila_xlat_pre_exit_net(struct net *net);
+ void ila_xlat_exit_net(struct net *net);
+
+ int ila_xlat_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info);
+diff --git a/net/ipv6/ila/ila_main.c b/net/ipv6/ila/ila_main.c
+index 69caed07315f0..976c78efbae17 100644
+--- a/net/ipv6/ila/ila_main.c
++++ b/net/ipv6/ila/ila_main.c
+@@ -71,6 +71,11 @@ static __net_init int ila_init_net(struct net *net)
+ return err;
+ }
+
++static __net_exit void ila_pre_exit_net(struct net *net)
++{
++ ila_xlat_pre_exit_net(net);
++}
++
+ static __net_exit void ila_exit_net(struct net *net)
+ {
+ ila_xlat_exit_net(net);
+@@ -78,6 +83,7 @@ static __net_exit void ila_exit_net(struct net *net)
+
+ static struct pernet_operations ila_net_ops = {
+ .init = ila_init_net,
++ .pre_exit = ila_pre_exit_net,
+ .exit = ila_exit_net,
+ .id = &ila_net_id,
+ .size = sizeof(struct ila_net),
+diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c
+index 67e8c9440977a..534a4498e280d 100644
+--- a/net/ipv6/ila/ila_xlat.c
++++ b/net/ipv6/ila/ila_xlat.c
+@@ -619,6 +619,15 @@ int ila_xlat_init_net(struct net *net)
+ return 0;
+ }
+
++void ila_xlat_pre_exit_net(struct net *net)
++{
++ struct ila_net *ilan = net_generic(net, ila_net_id);
++
++ if (ilan->xlat.hooks_registered)
++ nf_unregister_net_hooks(net, ila_nf_hook_ops,
++ ARRAY_SIZE(ila_nf_hook_ops));
++}
++
+ void ila_xlat_exit_net(struct net *net)
+ {
+ struct ila_net *ilan = net_generic(net, ila_net_id);
+@@ -626,10 +635,6 @@ void ila_xlat_exit_net(struct net *net)
+ rhashtable_free_and_destroy(&ilan->xlat.rhash_table, ila_free_cb, NULL);
+
+ free_bucket_spinlocks(ilan->xlat.locks);
+-
+- if (ilan->xlat.hooks_registered)
+- nf_unregister_net_hooks(net, ila_nf_hook_ops,
+- ARRAY_SIZE(ila_nf_hook_ops));
+ }
+
+ static int ila_xlat_addr(struct sk_buff *skb, bool sir2ila)
+diff --git a/net/netfilter/nf_conncount.c b/net/netfilter/nf_conncount.c
+index 8715617b02fe6..34ba14e59e95a 100644
+--- a/net/netfilter/nf_conncount.c
++++ b/net/netfilter/nf_conncount.c
+@@ -321,7 +321,6 @@ insert_tree(struct net *net,
+ struct nf_conncount_rb *rbconn;
+ struct nf_conncount_tuple *conn;
+ unsigned int count = 0, gc_count = 0;
+- u8 keylen = data->keylen;
+ bool do_gc = true;
+
+ spin_lock_bh(&nf_conncount_locks[hash]);
+@@ -333,7 +332,7 @@ insert_tree(struct net *net,
+ rbconn = rb_entry(*rbnode, struct nf_conncount_rb, node);
+
+ parent = *rbnode;
+- diff = key_diff(key, rbconn->key, keylen);
++ diff = key_diff(key, rbconn->key, data->keylen);
+ if (diff < 0) {
+ rbnode = &((*rbnode)->rb_left);
+ } else if (diff > 0) {
+@@ -378,7 +377,7 @@ insert_tree(struct net *net,
+
+ conn->tuple = *tuple;
+ conn->zone = *zone;
+- memcpy(rbconn->key, key, sizeof(u32) * keylen);
++ memcpy(rbconn->key, key, sizeof(u32) * data->keylen);
+
+ nf_conncount_list_init(&rbconn->list);
+ list_add(&conn->node, &rbconn->list.head);
+@@ -403,7 +402,6 @@ count_tree(struct net *net,
+ struct rb_node *parent;
+ struct nf_conncount_rb *rbconn;
+ unsigned int hash;
+- u8 keylen = data->keylen;
+
+ hash = jhash2(key, data->keylen, conncount_rnd) % CONNCOUNT_SLOTS;
+ root = &data->root[hash];
+@@ -414,7 +412,7 @@ count_tree(struct net *net,
+
+ rbconn = rb_entry(parent, struct nf_conncount_rb, node);
+
+- diff = key_diff(key, rbconn->key, keylen);
++ diff = key_diff(key, rbconn->key, data->keylen);
+ if (diff < 0) {
+ parent = rcu_dereference_raw(parent->rb_left);
+ } else if (diff > 0) {
+diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c
+index 9602dafe32e61..d2f49db705232 100644
+--- a/net/sched/sch_cake.c
++++ b/net/sched/sch_cake.c
+@@ -786,12 +786,15 @@ static u32 cake_hash(struct cake_tin_data *q, const struct sk_buff *skb,
+ * queue, accept the collision, update the host tags.
+ */
+ q->way_collisions++;
+- if (q->flows[outer_hash + k].set == CAKE_SET_BULK) {
+- q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--;
+- q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--;
+- }
+ allocate_src = cake_dsrc(flow_mode);
+ allocate_dst = cake_ddst(flow_mode);
++
++ if (q->flows[outer_hash + k].set == CAKE_SET_BULK) {
++ if (allocate_src)
++ q->hosts[q->flows[reduced_hash].srchost].srchost_bulk_flow_count--;
++ if (allocate_dst)
++ q->hosts[q->flows[reduced_hash].dsthost].dsthost_bulk_flow_count--;
++ }
+ found:
+ /* reserve queue for future packets in same flow */
+ reduced_hash = outer_hash + k;
+diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
+index 0f8d581438c39..39382ee1e3310 100644
+--- a/net/sched/sch_netem.c
++++ b/net/sched/sch_netem.c
+@@ -742,11 +742,10 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch)
+
+ err = qdisc_enqueue(skb, q->qdisc, &to_free);
+ kfree_skb_list(to_free);
+- if (err != NET_XMIT_SUCCESS &&
+- net_xmit_drop_count(err)) {
+- qdisc_qstats_drop(sch);
+- qdisc_tree_reduce_backlog(sch, 1,
+- pkt_len);
++ if (err != NET_XMIT_SUCCESS) {
++ if (net_xmit_drop_count(err))
++ qdisc_qstats_drop(sch);
++ qdisc_tree_reduce_backlog(sch, 1, pkt_len);
+ }
+ goto tfifo_dequeue;
+ }
+diff --git a/net/socket.c b/net/socket.c
+index e416920e9399e..b5a003974058f 100644
+--- a/net/socket.c
++++ b/net/socket.c
+@@ -2350,7 +2350,7 @@ INDIRECT_CALLABLE_DECLARE(bool tcp_bpf_bypass_getsockopt(int level,
+ int do_sock_getsockopt(struct socket *sock, bool compat, int level,
+ int optname, sockptr_t optval, sockptr_t optlen)
+ {
+- int max_optlen __maybe_unused;
++ int max_optlen __maybe_unused = 0;
+ const struct proto_ops *ops;
+ int err;
+
+@@ -2359,7 +2359,7 @@ int do_sock_getsockopt(struct socket *sock, bool compat, int level,
+ return err;
+
+ if (!compat)
+- max_optlen = BPF_CGROUP_GETSOCKOPT_MAX_OPTLEN(optlen);
++ copy_from_sockptr(&max_optlen, optlen, sizeof(int));
+
+ ops = READ_ONCE(sock->ops);
+ if (level == SOL_SOCKET) {
+diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
+index be5266007b489..84a332f95aa85 100644
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -692,9 +692,6 @@ static void init_peercred(struct sock *sk)
+
+ static void copy_peercred(struct sock *sk, struct sock *peersk)
+ {
+- const struct cred *old_cred;
+- struct pid *old_pid;
+-
+ if (sk < peersk) {
+ spin_lock(&sk->sk_peer_lock);
+ spin_lock_nested(&peersk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+@@ -702,16 +699,12 @@ static void copy_peercred(struct sock *sk, struct sock *peersk)
+ spin_lock(&peersk->sk_peer_lock);
+ spin_lock_nested(&sk->sk_peer_lock, SINGLE_DEPTH_NESTING);
+ }
+- old_pid = sk->sk_peer_pid;
+- old_cred = sk->sk_peer_cred;
++
+ sk->sk_peer_pid = get_pid(peersk->sk_peer_pid);
+ sk->sk_peer_cred = get_cred(peersk->sk_peer_cred);
+
+ spin_unlock(&sk->sk_peer_lock);
+ spin_unlock(&peersk->sk_peer_lock);
+-
+- put_pid(old_pid);
+- put_cred(old_cred);
+ }
+
+ static int unix_listen(struct socket *sock, int backlog)
+diff --git a/rust/Makefile b/rust/Makefile
+index f70d5e244fee5..47f9a9f1bdb39 100644
+--- a/rust/Makefile
++++ b/rust/Makefile
+@@ -359,7 +359,7 @@ $(obj)/bindings/bindings_helpers_generated.rs: $(src)/helpers.c FORCE
+ quiet_cmd_exports = EXPORTS $@
+ cmd_exports = \
+ $(NM) -p --defined-only $< \
+- | awk '/ (T|R|D) / {printf "EXPORT_SYMBOL_RUST_GPL(%s);\n",$$3}' > $@
++ | awk '/ (T|R|D|B) / {printf "EXPORT_SYMBOL_RUST_GPL(%s);\n",$$3}' > $@
+
+ $(obj)/exports_core_generated.h: $(obj)/core.o FORCE
+ $(call if_changed,exports)
+diff --git a/rust/macros/module.rs b/rust/macros/module.rs
+index acd0393b50957..7dee348ef0cc8 100644
+--- a/rust/macros/module.rs
++++ b/rust/macros/module.rs
+@@ -203,7 +203,11 @@ pub(crate) fn module(ts: TokenStream) -> TokenStream {
+ // freed until the module is unloaded.
+ #[cfg(MODULE)]
+ static THIS_MODULE: kernel::ThisModule = unsafe {{
+- kernel::ThisModule::from_ptr(&kernel::bindings::__this_module as *const _ as *mut _)
++ extern \"C\" {{
++ static __this_module: kernel::types::Opaque<kernel::bindings::module>;
++ }}
++
++ kernel::ThisModule::from_ptr(__this_module.get())
+ }};
+ #[cfg(not(MODULE))]
+ static THIS_MODULE: kernel::ThisModule = unsafe {{
+diff --git a/scripts/gfp-translate b/scripts/gfp-translate
+index 6c9aed17cf563..8385ae0d5af93 100755
+--- a/scripts/gfp-translate
++++ b/scripts/gfp-translate
+@@ -62,25 +62,57 @@ if [ "$GFPMASK" = "none" ]; then
+ fi
+
+ # Extract GFP flags from the kernel source
+-TMPFILE=`mktemp -t gfptranslate-XXXXXX` || exit 1
+-grep -q ___GFP $SOURCE/include/linux/gfp_types.h
+-if [ $? -eq 0 ]; then
+- grep "^#define ___GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/u$//' | grep -v GFP_BITS > $TMPFILE
+-else
+- grep "^#define __GFP" $SOURCE/include/linux/gfp_types.h | sed -e 's/(__force gfp_t)//' | sed -e 's/u)/)/' | grep -v GFP_BITS | sed -e 's/)\//) \//' > $TMPFILE
+-fi
++TMPFILE=`mktemp -t gfptranslate-XXXXXX.c` || exit 1
+
+-# Parse the flags
+-IFS="
+-"
+ echo Source: $SOURCE
+ echo Parsing: $GFPMASK
+-for LINE in `cat $TMPFILE`; do
+- MASK=`echo $LINE | awk '{print $3}'`
+- if [ $(($GFPMASK&$MASK)) -ne 0 ]; then
+- echo $LINE
+- fi
+-done
+
+-rm -f $TMPFILE
++(
++ cat <<EOF
++#include <stdint.h>
++#include <stdio.h>
++
++// Try to fool compiler.h into not including extra stuff
++#define __ASSEMBLY__ 1
++
++#include <generated/autoconf.h>
++#include <linux/gfp_types.h>
++
++static const char *masks[] = {
++EOF
++
++ sed -nEe 's/^[[:space:]]+(___GFP_.*)_BIT,.*$/\1/p' $SOURCE/include/linux/gfp_types.h |
++ while read b; do
++ cat <<EOF
++#if defined($b) && ($b > 0)
++ [${b}_BIT] = "$b",
++#endif
++EOF
++ done
++
++ cat <<EOF
++};
++
++int main(int argc, char *argv[])
++{
++ unsigned long long mask = $GFPMASK;
++
++ for (int i = 0; i < sizeof(mask) * 8; i++) {
++ unsigned long long bit = 1ULL << i;
++ if (mask & bit)
++ printf("\t%-25s0x%llx\n",
++ (i < ___GFP_LAST_BIT && masks[i]) ?
++ masks[i] : "*** INVALID ***",
++ bit);
++ }
++
++ return 0;
++}
++EOF
++) > $TMPFILE
++
++${CC:-gcc} -Wall -o ${TMPFILE}.bin -I $SOURCE/include $TMPFILE && ${TMPFILE}.bin
++
++rm -f $TMPFILE ${TMPFILE}.bin
++
+ exit 0
+diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
+index ab939e6449e41..002a1b9ed83a5 100644
+--- a/security/smack/smack_lsm.c
++++ b/security/smack/smack_lsm.c
+@@ -3871,12 +3871,18 @@ static int smack_unix_stream_connect(struct sock *sock,
+ }
+ }
+
+- /*
+- * Cross reference the peer labels for SO_PEERSEC.
+- */
+ if (rc == 0) {
++ /*
++ * Cross reference the peer labels for SO_PEERSEC.
++ */
+ nsp->smk_packet = ssp->smk_out;
+ ssp->smk_packet = osp->smk_out;
++
++ /*
++ * new/child/established socket must inherit listening socket labels
++ */
++ nsp->smk_out = osp->smk_out;
++ nsp->smk_in = osp->smk_in;
+ }
+
+ return rc;
+diff --git a/sound/core/control.c b/sound/core/control.c
+index fb0c60044f7b3..1dd2337e29300 100644
+--- a/sound/core/control.c
++++ b/sound/core/control.c
+@@ -1480,12 +1480,16 @@ static int snd_ctl_elem_user_get(struct snd_kcontrol *kcontrol,
+ static int snd_ctl_elem_user_put(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+ {
+- int change;
++ int err, change;
+ struct user_element *ue = kcontrol->private_data;
+ unsigned int size = ue->elem_data_size;
+ char *dst = ue->elem_data +
+ snd_ctl_get_ioff(kcontrol, &ucontrol->id) * size;
+
++ err = sanity_check_input_values(ue->card, ucontrol, &ue->info, false);
++ if (err < 0)
++ return err;
++
+ change = memcmp(&ucontrol->value, dst, size) != 0;
+ if (change)
+ memcpy(dst, &ucontrol->value, size);
+diff --git a/sound/hda/hdmi_chmap.c b/sound/hda/hdmi_chmap.c
+index 5d8e1d944b0af..7b276047f85a7 100644
+--- a/sound/hda/hdmi_chmap.c
++++ b/sound/hda/hdmi_chmap.c
+@@ -753,6 +753,20 @@ static int hdmi_chmap_ctl_get(struct snd_kcontrol *kcontrol,
+ return 0;
+ }
+
++/* a simple sanity check for input values to chmap kcontrol */
++static int chmap_value_check(struct hdac_chmap *hchmap,
++ const struct snd_ctl_elem_value *ucontrol)
++{
++ int i;
++
++ for (i = 0; i < hchmap->channels_max; i++) {
++ if (ucontrol->value.integer.value[i] < 0 ||
++ ucontrol->value.integer.value[i] > SNDRV_CHMAP_LAST)
++ return -EINVAL;
++ }
++ return 0;
++}
++
+ static int hdmi_chmap_ctl_put(struct snd_kcontrol *kcontrol,
+ struct snd_ctl_elem_value *ucontrol)
+ {
+@@ -764,6 +778,10 @@ static int hdmi_chmap_ctl_put(struct snd_kcontrol *kcontrol,
+ unsigned char chmap[8], per_pin_chmap[8];
+ int i, err, ca, prepared = 0;
+
++ err = chmap_value_check(hchmap, ucontrol);
++ if (err < 0)
++ return err;
++
+ /* No monitor is connected in dyn_pcm_assign.
+ * It's invalid to setup the chmap
+ */
+diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
+index f030669243f9a..e851785ff0581 100644
+--- a/sound/pci/hda/patch_conexant.c
++++ b/sound/pci/hda/patch_conexant.c
+@@ -307,6 +307,7 @@ enum {
+ CXT_FIXUP_HEADSET_MIC,
+ CXT_FIXUP_HP_MIC_NO_PRESENCE,
+ CXT_PINCFG_SWS_JS201D,
++ CXT_PINCFG_TOP_SPEAKER,
+ };
+
+ /* for hda_fixup_thinkpad_acpi() */
+@@ -974,6 +975,13 @@ static const struct hda_fixup cxt_fixups[] = {
+ .type = HDA_FIXUP_PINS,
+ .v.pins = cxt_pincfg_sws_js201d,
+ },
++ [CXT_PINCFG_TOP_SPEAKER] = {
++ .type = HDA_FIXUP_PINS,
++ .v.pins = (const struct hda_pintbl[]) {
++ { 0x1d, 0x82170111 },
++ { }
++ },
++ },
+ };
+
+ static const struct snd_pci_quirk cxt5045_fixups[] = {
+@@ -1070,6 +1078,8 @@ static const struct snd_pci_quirk cxt5066_fixups[] = {
+ SND_PCI_QUIRK_VENDOR(0x17aa, "Thinkpad", CXT_FIXUP_THINKPAD_ACPI),
+ SND_PCI_QUIRK(0x1c06, 0x2011, "Lemote A1004", CXT_PINCFG_LEMOTE_A1004),
+ SND_PCI_QUIRK(0x1c06, 0x2012, "Lemote A1205", CXT_PINCFG_LEMOTE_A1205),
++ SND_PCI_QUIRK(0x2782, 0x12c3, "Sirius Gen1", CXT_PINCFG_TOP_SPEAKER),
++ SND_PCI_QUIRK(0x2782, 0x12c5, "Sirius Gen2", CXT_PINCFG_TOP_SPEAKER),
+ {}
+ };
+
+@@ -1089,6 +1099,7 @@ static const struct hda_model_fixup cxt5066_fixup_models[] = {
+ { .id = CXT_FIXUP_HP_MIC_NO_PRESENCE, .name = "hp-mic-fix" },
+ { .id = CXT_PINCFG_LENOVO_NOTEBOOK, .name = "lenovo-20149" },
+ { .id = CXT_PINCFG_SWS_JS201D, .name = "sws-js201d" },
++ { .id = CXT_PINCFG_TOP_SPEAKER, .name = "sirius-top-speaker" },
+ {}
+ };
+
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index 1a7b7e790fca9..0cde024d1d33c 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -7428,6 +7428,7 @@ enum {
+ ALC236_FIXUP_HP_GPIO_LED,
+ ALC236_FIXUP_HP_MUTE_LED,
+ ALC236_FIXUP_HP_MUTE_LED_MICMUTE_VREF,
++ ALC236_FIXUP_LENOVO_INV_DMIC,
+ ALC298_FIXUP_SAMSUNG_AMP,
+ ALC298_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
+ ALC256_FIXUP_SAMSUNG_HEADPHONE_VERY_QUIET,
+@@ -7525,6 +7526,7 @@ enum {
+ ALC256_FIXUP_CHROME_BOOK,
+ ALC287_FIXUP_LENOVO_14ARP8_LEGION_IAH7,
+ ALC287_FIXUP_LENOVO_SSID_17AA3820,
++ ALC245_FIXUP_CLEVO_NOISY_MIC,
+ };
+
+ /* A special fixup for Lenovo C940 and Yoga Duet 7;
+@@ -9049,6 +9051,12 @@ static const struct hda_fixup alc269_fixups[] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc236_fixup_hp_mute_led_micmute_vref,
+ },
++ [ALC236_FIXUP_LENOVO_INV_DMIC] = {
++ .type = HDA_FIXUP_FUNC,
++ .v.func = alc_fixup_inv_dmic,
++ .chained = true,
++ .chain_id = ALC283_FIXUP_INT_MIC,
++ },
+ [ALC298_FIXUP_SAMSUNG_AMP] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc298_fixup_samsung_amp,
+@@ -9850,6 +9858,12 @@ static const struct hda_fixup alc269_fixups[] = {
+ .type = HDA_FIXUP_FUNC,
+ .v.func = alc287_fixup_lenovo_ssid_17aa3820,
+ },
++ [ALC245_FIXUP_CLEVO_NOISY_MIC] = {
++ .type = HDA_FIXUP_FUNC,
++ .v.func = alc269_fixup_limit_int_mic_boost,
++ .chained = true,
++ .chain_id = ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE,
++ },
+ };
+
+ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+@@ -10098,6 +10112,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x103c, 0x87f5, "HP", ALC287_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x87f6, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
+ SND_PCI_QUIRK(0x103c, 0x87f7, "HP Spectre x360 14", ALC245_FIXUP_HP_X360_AMP),
++ SND_PCI_QUIRK(0x103c, 0x87fd, "HP Laptop 14-dq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
+ SND_PCI_QUIRK(0x103c, 0x87fe, "HP Laptop 15s-fq2xxx", ALC236_FIXUP_HP_MUTE_LED_COEFBIT2),
+ SND_PCI_QUIRK(0x103c, 0x8805, "HP ProBook 650 G8 Notebook PC", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x880d, "HP EliteBook 830 G8 Notebook PC", ALC285_FIXUP_HP_GPIO_LED),
+@@ -10222,6 +10237,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x103c, 0x8c16, "HP Spectre 16", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8c17, "HP Spectre 16", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8c21, "HP Pavilion Plus Laptop 14-ey0XXX", ALC245_FIXUP_HP_X360_MUTE_LEDS),
++ SND_PCI_QUIRK(0x103c, 0x8c30, "HP Victus 15-fb1xxx", ALC245_FIXUP_HP_MUTE_LED_COEFBIT),
+ SND_PCI_QUIRK(0x103c, 0x8c46, "HP EliteBook 830 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8c47, "HP EliteBook 840 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8c48, "HP EliteBook 860 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+@@ -10348,6 +10364,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1043, 0x1e02, "ASUS UX3402ZA", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x1e11, "ASUS Zephyrus G15", ALC289_FIXUP_ASUS_GA502),
+ SND_PCI_QUIRK(0x1043, 0x1e12, "ASUS UM3402", ALC287_FIXUP_CS35L41_I2C_2),
++ SND_PCI_QUIRK(0x1043, 0x1e1f, "ASUS Vivobook 15 X1504VAP", ALC2XX_FIXUP_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1043, 0x1e51, "ASUS Zephyrus M15", ALC294_FIXUP_ASUS_GU502_PINS),
+ SND_PCI_QUIRK(0x1043, 0x1e5e, "ASUS ROG Strix G513", ALC294_FIXUP_ASUS_G513_PINS),
+ SND_PCI_QUIRK(0x1043, 0x1e63, "ASUS H7606W", ALC285_FIXUP_CS35L56_I2C_2),
+@@ -10486,7 +10503,8 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1558, 0xa600, "Clevo NL50NU", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0xa650, "Clevo NP[567]0SN[CD]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0xa671, "Clevo NP70SN[CDE]", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+- SND_PCI_QUIRK(0x1558, 0xa763, "Clevo V54x_6x_TU", ALC256_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
++ SND_PCI_QUIRK(0x1558, 0xa741, "Clevo V54x_6x_TNE", ALC245_FIXUP_CLEVO_NOISY_MIC),
++ SND_PCI_QUIRK(0x1558, 0xa763, "Clevo V54x_6x_TU", ALC245_FIXUP_CLEVO_NOISY_MIC),
+ SND_PCI_QUIRK(0x1558, 0xb018, "Clevo NP50D[BE]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0xb019, "Clevo NH77D[BE]Q", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1558, 0xb022, "Clevo NH77D[DC][QW]", ALC293_FIXUP_SYSTEM76_MIC_NO_PRESENCE),
+@@ -10609,6 +10627,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x17aa, 0x38f9, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x17aa, 0x38fa, "Thinkbook 16P Gen5", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x17aa, 0x3902, "Lenovo E50-80", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
++ SND_PCI_QUIRK(0x17aa, 0x3913, "Lenovo 145", ALC236_FIXUP_LENOVO_INV_DMIC),
+ SND_PCI_QUIRK(0x17aa, 0x3977, "IdeaPad S210", ALC283_FIXUP_INT_MIC),
+ SND_PCI_QUIRK(0x17aa, 0x3978, "Lenovo B50-70", ALC269_FIXUP_DMIC_THINKPAD_ACPI),
+ SND_PCI_QUIRK(0x17aa, 0x3bf8, "Quanta FL1", ALC269_FIXUP_PCM_44K),
+@@ -10860,6 +10879,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = {
+ {.id = ALC623_FIXUP_LENOVO_THINKSTATION_P340, .name = "alc623-lenovo-thinkstation-p340"},
+ {.id = ALC255_FIXUP_ACER_HEADPHONE_AND_MIC, .name = "alc255-acer-headphone-and-mic"},
+ {.id = ALC285_FIXUP_HP_GPIO_AMP_INIT, .name = "alc285-hp-amp-init"},
++ {.id = ALC236_FIXUP_LENOVO_INV_DMIC, .name = "alc236-fixup-lenovo-inv-mic"},
+ {}
+ };
+ #define ALC225_STANDARD_PINS \
+diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
+index 08082806d5892..8f9a3ae7153e9 100644
+--- a/sound/soc/codecs/tas2781-fmwlib.c
++++ b/sound/soc/codecs/tas2781-fmwlib.c
+@@ -21,7 +21,7 @@
+ #include <sound/soc.h>
+ #include <sound/tlv.h>
+ #include <sound/tas2781.h>
+-
++#include <asm/unaligned.h>
+
+ #define ERROR_PRAM_CRCCHK 0x0000000
+ #define ERROR_YRAM_CRCCHK 0x0000001
+@@ -187,8 +187,7 @@ static struct tasdevice_config_info *tasdevice_add_config(
+ /* convert data[offset], data[offset + 1], data[offset + 2] and
+ * data[offset + 3] into host
+ */
+- cfg_info->nblocks =
+- be32_to_cpup((__be32 *)&config_data[config_offset]);
++ cfg_info->nblocks = get_unaligned_be32(&config_data[config_offset]);
+ config_offset += 4;
+
+ /* Several kinds of dsp/algorithm firmwares can run on tas2781,
+@@ -232,14 +231,14 @@ static struct tasdevice_config_info *tasdevice_add_config(
+
+ }
+ bk_da[i]->yram_checksum =
+- be16_to_cpup((__be16 *)&config_data[config_offset]);
++ get_unaligned_be16(&config_data[config_offset]);
+ config_offset += 2;
+ bk_da[i]->block_size =
+- be32_to_cpup((__be32 *)&config_data[config_offset]);
++ get_unaligned_be32(&config_data[config_offset]);
+ config_offset += 4;
+
+ bk_da[i]->n_subblks =
+- be32_to_cpup((__be32 *)&config_data[config_offset]);
++ get_unaligned_be32(&config_data[config_offset]);
+
+ config_offset += 4;
+
+@@ -289,7 +288,7 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
+ }
+ buf = (unsigned char *)fmw->data;
+
+- fw_hdr->img_sz = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->img_sz = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+ if (fw_hdr->img_sz != fmw->size) {
+ dev_err(tas_priv->dev,
+@@ -300,9 +299,9 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
+ goto out;
+ }
+
+- fw_hdr->checksum = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->checksum = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+- fw_hdr->binary_version_num = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->binary_version_num = get_unaligned_be32(&buf[offset]);
+ if (fw_hdr->binary_version_num < 0x103) {
+ dev_err(tas_priv->dev, "File version 0x%04x is too low",
+ fw_hdr->binary_version_num);
+@@ -311,7 +310,7 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
+ goto out;
+ }
+ offset += 4;
+- fw_hdr->drv_fw_version = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->drv_fw_version = get_unaligned_be32(&buf[offset]);
+ offset += 8;
+ fw_hdr->plat_type = buf[offset];
+ offset += 1;
+@@ -339,11 +338,11 @@ int tasdevice_rca_parser(void *context, const struct firmware *fmw)
+ for (i = 0; i < TASDEVICE_DEVICE_SUM; i++, offset++)
+ fw_hdr->devs[i] = buf[offset];
+
+- fw_hdr->nconfig = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->nconfig = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+
+ for (i = 0; i < TASDEVICE_CONFIG_SUM; i++) {
+- fw_hdr->config_size[i] = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->config_size[i] = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+ total_config_sz += fw_hdr->config_size[i];
+ }
+@@ -423,7 +422,7 @@ static int fw_parse_block_data_kernel(struct tasdevice_fw *tas_fmw,
+ /* convert data[offset], data[offset + 1], data[offset + 2] and
+ * data[offset + 3] into host
+ */
+- block->type = be32_to_cpup((__be32 *)&data[offset]);
++ block->type = get_unaligned_be32(&data[offset]);
+ offset += 4;
+
+ block->is_pchksum_present = data[offset];
+@@ -438,10 +437,10 @@ static int fw_parse_block_data_kernel(struct tasdevice_fw *tas_fmw,
+ block->ychksum = data[offset];
+ offset++;
+
+- block->blk_size = be32_to_cpup((__be32 *)&data[offset]);
++ block->blk_size = get_unaligned_be32(&data[offset]);
+ offset += 4;
+
+- block->nr_subblocks = be32_to_cpup((__be32 *)&data[offset]);
++ block->nr_subblocks = get_unaligned_be32(&data[offset]);
+ offset += 4;
+
+ /* fixed m68k compiling issue:
+@@ -482,7 +481,7 @@ static int fw_parse_data_kernel(struct tasdevice_fw *tas_fmw,
+ offset = -EINVAL;
+ goto out;
+ }
+- img_data->nr_blk = be32_to_cpup((__be32 *)&data[offset]);
++ img_data->nr_blk = get_unaligned_be32(&data[offset]);
+ offset += 4;
+
+ img_data->dev_blks = kcalloc(img_data->nr_blk,
+@@ -578,14 +577,14 @@ static int fw_parse_variable_header_kernel(
+ offset = -EINVAL;
+ goto out;
+ }
+- fw_hdr->device_family = be16_to_cpup((__be16 *)&buf[offset]);
++ fw_hdr->device_family = get_unaligned_be16(&buf[offset]);
+ if (fw_hdr->device_family != 0) {
+ dev_err(tas_priv->dev, "%s:not TAS device\n", __func__);
+ offset = -EINVAL;
+ goto out;
+ }
+ offset += 2;
+- fw_hdr->device = be16_to_cpup((__be16 *)&buf[offset]);
++ fw_hdr->device = get_unaligned_be16(&buf[offset]);
+ if (fw_hdr->device >= TASDEVICE_DSP_TAS_MAX_DEVICE ||
+ fw_hdr->device == 6) {
+ dev_err(tas_priv->dev, "Unsupported dev %d\n", fw_hdr->device);
+@@ -603,7 +602,7 @@ static int fw_parse_variable_header_kernel(
+ goto out;
+ }
+
+- tas_fmw->nr_programs = be32_to_cpup((__be32 *)&buf[offset]);
++ tas_fmw->nr_programs = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+
+ if (tas_fmw->nr_programs == 0 || tas_fmw->nr_programs >
+@@ -622,14 +621,14 @@ static int fw_parse_variable_header_kernel(
+
+ for (i = 0; i < tas_fmw->nr_programs; i++) {
+ program = &(tas_fmw->programs[i]);
+- program->prog_size = be32_to_cpup((__be32 *)&buf[offset]);
++ program->prog_size = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+ }
+
+ /* Skip the unused prog_size */
+ offset += 4 * (TASDEVICE_MAXPROGRAM_NUM_KERNEL - tas_fmw->nr_programs);
+
+- tas_fmw->nr_configurations = be32_to_cpup((__be32 *)&buf[offset]);
++ tas_fmw->nr_configurations = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+
+ /* The max number of config in firmware greater than 4 pieces of
+@@ -661,7 +660,7 @@ static int fw_parse_variable_header_kernel(
+
+ for (i = 0; i < tas_fmw->nr_programs; i++) {
+ config = &(tas_fmw->configs[i]);
+- config->cfg_size = be32_to_cpup((__be32 *)&buf[offset]);
++ config->cfg_size = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+ }
+
+@@ -699,7 +698,7 @@ static int tasdevice_process_block(void *context, unsigned char *data,
+ switch (subblk_typ) {
+ case TASDEVICE_CMD_SING_W: {
+ int i;
+- unsigned short len = be16_to_cpup((__be16 *)&data[2]);
++ unsigned short len = get_unaligned_be16(&data[2]);
+
+ subblk_offset += 2;
+ if (subblk_offset + 4 * len > sublocksize) {
+@@ -725,7 +724,7 @@ static int tasdevice_process_block(void *context, unsigned char *data,
+ }
+ break;
+ case TASDEVICE_CMD_BURST: {
+- unsigned short len = be16_to_cpup((__be16 *)&data[2]);
++ unsigned short len = get_unaligned_be16(&data[2]);
+
+ subblk_offset += 2;
+ if (subblk_offset + 4 + len > sublocksize) {
+@@ -766,7 +765,7 @@ static int tasdevice_process_block(void *context, unsigned char *data,
+ is_err = true;
+ break;
+ }
+- sleep_time = be16_to_cpup((__be16 *)&data[2]) * 1000;
++ sleep_time = get_unaligned_be16(&data[2]) * 1000;
+ usleep_range(sleep_time, sleep_time + 50);
+ subblk_offset += 2;
+ }
+@@ -910,7 +909,7 @@ static int fw_parse_variable_hdr(struct tasdevice_priv
+
+ offset += len;
+
+- fw_hdr->device_family = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->device_family = get_unaligned_be32(&buf[offset]);
+ if (fw_hdr->device_family != 0) {
+ dev_err(tas_priv->dev, "%s: not TAS device\n", __func__);
+ offset = -EINVAL;
+@@ -918,7 +917,7 @@ static int fw_parse_variable_hdr(struct tasdevice_priv
+ }
+ offset += 4;
+
+- fw_hdr->device = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_hdr->device = get_unaligned_be32(&buf[offset]);
+ if (fw_hdr->device >= TASDEVICE_DSP_TAS_MAX_DEVICE ||
+ fw_hdr->device == 6) {
+ dev_err(tas_priv->dev, "Unsupported dev %d\n", fw_hdr->device);
+@@ -963,7 +962,7 @@ static int fw_parse_block_data(struct tasdevice_fw *tas_fmw,
+ offset = -EINVAL;
+ goto out;
+ }
+- block->type = be32_to_cpup((__be32 *)&data[offset]);
++ block->type = get_unaligned_be32(&data[offset]);
+ offset += 4;
+
+ if (tas_fmw->fw_hdr.fixed_hdr.drv_ver >= PPC_DRIVER_CRCCHK) {
+@@ -988,7 +987,7 @@ static int fw_parse_block_data(struct tasdevice_fw *tas_fmw,
+ block->is_ychksum_present = 0;
+ }
+
+- block->nr_cmds = be32_to_cpup((__be32 *)&data[offset]);
++ block->nr_cmds = get_unaligned_be32(&data[offset]);
+ offset += 4;
+
+ n = block->nr_cmds * 4;
+@@ -1039,7 +1038,7 @@ static int fw_parse_data(struct tasdevice_fw *tas_fmw,
+ goto out;
+ }
+ offset += n;
+- img_data->nr_blk = be16_to_cpup((__be16 *)&data[offset]);
++ img_data->nr_blk = get_unaligned_be16(&data[offset]);
+ offset += 2;
+
+ img_data->dev_blks = kcalloc(img_data->nr_blk,
+@@ -1076,7 +1075,7 @@ static int fw_parse_program_data(struct tasdevice_priv *tas_priv,
+ offset = -EINVAL;
+ goto out;
+ }
+- tas_fmw->nr_programs = be16_to_cpup((__be16 *)&buf[offset]);
++ tas_fmw->nr_programs = get_unaligned_be16(&buf[offset]);
+ offset += 2;
+
+ if (tas_fmw->nr_programs == 0) {
+@@ -1143,7 +1142,7 @@ static int fw_parse_configuration_data(
+ offset = -EINVAL;
+ goto out;
+ }
+- tas_fmw->nr_configurations = be16_to_cpup((__be16 *)&data[offset]);
++ tas_fmw->nr_configurations = get_unaligned_be16(&data[offset]);
+ offset += 2;
+
+ if (tas_fmw->nr_configurations == 0) {
+@@ -1775,7 +1774,7 @@ static int fw_parse_header(struct tasdevice_priv *tas_priv,
+ /* Convert data[offset], data[offset + 1], data[offset + 2] and
+ * data[offset + 3] into host
+ */
+- fw_fixed_hdr->fwsize = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_fixed_hdr->fwsize = get_unaligned_be32(&buf[offset]);
+ offset += 4;
+ if (fw_fixed_hdr->fwsize != fmw->size) {
+ dev_err(tas_priv->dev, "File size not match, %lu %u",
+@@ -1784,9 +1783,9 @@ static int fw_parse_header(struct tasdevice_priv *tas_priv,
+ goto out;
+ }
+ offset += 4;
+- fw_fixed_hdr->ppcver = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_fixed_hdr->ppcver = get_unaligned_be32(&buf[offset]);
+ offset += 8;
+- fw_fixed_hdr->drv_ver = be32_to_cpup((__be32 *)&buf[offset]);
++ fw_fixed_hdr->drv_ver = get_unaligned_be32(&buf[offset]);
+ offset += 72;
+
+ out:
+@@ -1828,7 +1827,7 @@ static int fw_parse_calibration_data(struct tasdevice_priv *tas_priv,
+ offset = -EINVAL;
+ goto out;
+ }
+- tas_fmw->nr_calibrations = be16_to_cpup((__be16 *)&data[offset]);
++ tas_fmw->nr_calibrations = get_unaligned_be16(&data[offset]);
+ offset += 2;
+
+ if (tas_fmw->nr_calibrations != 1) {
+diff --git a/sound/soc/intel/boards/bxt_rt298.c b/sound/soc/intel/boards/bxt_rt298.c
+index dce6a2086f2a4..6da1517c53c6e 100644
+--- a/sound/soc/intel/boards/bxt_rt298.c
++++ b/sound/soc/intel/boards/bxt_rt298.c
+@@ -605,7 +605,7 @@ static int broxton_audio_probe(struct platform_device *pdev)
+ int i;
+
+ for (i = 0; i < ARRAY_SIZE(broxton_rt298_dais); i++) {
+- if (card->dai_link[i].codecs->name &&
++ if (card->dai_link[i].num_codecs &&
+ !strncmp(card->dai_link[i].codecs->name, "i2c-INT343A:00",
+ I2C_NAME_SIZE)) {
+ if (!strncmp(card->name, "broxton-rt298",
+diff --git a/sound/soc/intel/boards/bytcht_cx2072x.c b/sound/soc/intel/boards/bytcht_cx2072x.c
+index c014d85a08b24..df3c2a7b64d23 100644
+--- a/sound/soc/intel/boards/bytcht_cx2072x.c
++++ b/sound/soc/intel/boards/bytcht_cx2072x.c
+@@ -241,7 +241,7 @@ static int snd_byt_cht_cx2072x_probe(struct platform_device *pdev)
+
+ /* fix index of codec dai */
+ for (i = 0; i < ARRAY_SIZE(byt_cht_cx2072x_dais); i++) {
+- if (byt_cht_cx2072x_dais[i].codecs->name &&
++ if (byt_cht_cx2072x_dais[i].num_codecs &&
+ !strcmp(byt_cht_cx2072x_dais[i].codecs->name,
+ "i2c-14F10720:00")) {
+ dai_index = i;
+diff --git a/sound/soc/intel/boards/bytcht_da7213.c b/sound/soc/intel/boards/bytcht_da7213.c
+index f4ac3ddd148b8..08c598b7e1eee 100644
+--- a/sound/soc/intel/boards/bytcht_da7213.c
++++ b/sound/soc/intel/boards/bytcht_da7213.c
+@@ -245,7 +245,7 @@ static int bytcht_da7213_probe(struct platform_device *pdev)
+
+ /* fix index of codec dai */
+ for (i = 0; i < ARRAY_SIZE(dailink); i++) {
+- if (dailink[i].codecs->name &&
++ if (dailink[i].num_codecs &&
+ !strcmp(dailink[i].codecs->name, "i2c-DLGS7213:00")) {
+ dai_index = i;
+ break;
+diff --git a/sound/soc/intel/boards/bytcht_es8316.c b/sound/soc/intel/boards/bytcht_es8316.c
+index 2fcec2e02bb53..77b91ea4dc32c 100644
+--- a/sound/soc/intel/boards/bytcht_es8316.c
++++ b/sound/soc/intel/boards/bytcht_es8316.c
+@@ -546,7 +546,7 @@ static int snd_byt_cht_es8316_mc_probe(struct platform_device *pdev)
+
+ /* fix index of codec dai */
+ for (i = 0; i < ARRAY_SIZE(byt_cht_es8316_dais); i++) {
+- if (byt_cht_es8316_dais[i].codecs->name &&
++ if (byt_cht_es8316_dais[i].num_codecs &&
+ !strcmp(byt_cht_es8316_dais[i].codecs->name,
+ "i2c-ESSX8316:00")) {
+ dai_index = i;
+diff --git a/sound/soc/intel/boards/bytcr_rt5640.c b/sound/soc/intel/boards/bytcr_rt5640.c
+index a64d1989e28a5..db4a33680d948 100644
+--- a/sound/soc/intel/boards/bytcr_rt5640.c
++++ b/sound/soc/intel/boards/bytcr_rt5640.c
+@@ -1677,7 +1677,7 @@ static int snd_byt_rt5640_mc_probe(struct platform_device *pdev)
+
+ /* fix index of codec dai */
+ for (i = 0; i < ARRAY_SIZE(byt_rt5640_dais); i++) {
+- if (byt_rt5640_dais[i].codecs->name &&
++ if (byt_rt5640_dais[i].num_codecs &&
+ !strcmp(byt_rt5640_dais[i].codecs->name,
+ "i2c-10EC5640:00")) {
+ dai_index = i;
+diff --git a/sound/soc/intel/boards/bytcr_rt5651.c b/sound/soc/intel/boards/bytcr_rt5651.c
+index 80c841b000a31..8514b79f389bb 100644
+--- a/sound/soc/intel/boards/bytcr_rt5651.c
++++ b/sound/soc/intel/boards/bytcr_rt5651.c
+@@ -910,7 +910,7 @@ static int snd_byt_rt5651_mc_probe(struct platform_device *pdev)
+
+ /* fix index of codec dai */
+ for (i = 0; i < ARRAY_SIZE(byt_rt5651_dais); i++) {
+- if (byt_rt5651_dais[i].codecs->name &&
++ if (byt_rt5651_dais[i].num_codecs &&
+ !strcmp(byt_rt5651_dais[i].codecs->name,
+ "i2c-10EC5651:00")) {
+ dai_index = i;
+diff --git a/sound/soc/intel/boards/bytcr_wm5102.c b/sound/soc/intel/boards/bytcr_wm5102.c
+index cccb5e90c0fef..e5a7cc606aa90 100644
+--- a/sound/soc/intel/boards/bytcr_wm5102.c
++++ b/sound/soc/intel/boards/bytcr_wm5102.c
+@@ -605,7 +605,7 @@ static int snd_byt_wm5102_mc_probe(struct platform_device *pdev)
+
+ /* find index of codec dai */
+ for (i = 0; i < ARRAY_SIZE(byt_wm5102_dais); i++) {
+- if (byt_wm5102_dais[i].codecs->name &&
++ if (byt_wm5102_dais[i].num_codecs &&
+ !strcmp(byt_wm5102_dais[i].codecs->name,
+ "wm5102-codec")) {
+ dai_index = i;
+diff --git a/sound/soc/intel/boards/cht_bsw_rt5645.c b/sound/soc/intel/boards/cht_bsw_rt5645.c
+index eb41b7115d01d..1da9ceee4d593 100644
+--- a/sound/soc/intel/boards/cht_bsw_rt5645.c
++++ b/sound/soc/intel/boards/cht_bsw_rt5645.c
+@@ -569,7 +569,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
+
+ /* set correct codec name */
+ for (i = 0; i < ARRAY_SIZE(cht_dailink); i++)
+- if (cht_dailink[i].codecs->name &&
++ if (cht_dailink[i].num_codecs &&
+ !strcmp(cht_dailink[i].codecs->name,
+ "i2c-10EC5645:00")) {
+ dai_index = i;
+diff --git a/sound/soc/intel/boards/cht_bsw_rt5672.c b/sound/soc/intel/boards/cht_bsw_rt5672.c
+index be2d1a8dbca80..d68e5bc755dee 100644
+--- a/sound/soc/intel/boards/cht_bsw_rt5672.c
++++ b/sound/soc/intel/boards/cht_bsw_rt5672.c
+@@ -466,7 +466,7 @@ static int snd_cht_mc_probe(struct platform_device *pdev)
+
+ /* find index of codec dai */
+ for (i = 0; i < ARRAY_SIZE(cht_dailink); i++) {
+- if (cht_dailink[i].codecs->name &&
++ if (cht_dailink[i].num_codecs &&
+ !strcmp(cht_dailink[i].codecs->name, RT5672_I2C_DEFAULT)) {
+ dai_index = i;
+ break;
+diff --git a/sound/soc/soc-dapm.c b/sound/soc/soc-dapm.c
+index 16dad4a454434..1680c2498fe94 100644
+--- a/sound/soc/soc-dapm.c
++++ b/sound/soc/soc-dapm.c
+@@ -4066,6 +4066,7 @@ static int snd_soc_dai_link_event(struct snd_soc_dapm_widget *w,
+
+ case SND_SOC_DAPM_POST_PMD:
+ kfree(substream->runtime);
++ substream->runtime = NULL;
+ break;
+
+ default:
+diff --git a/sound/soc/soc-topology.c b/sound/soc/soc-topology.c
+index 6951ff7bc61e7..73d44dff45d6e 100644
+--- a/sound/soc/soc-topology.c
++++ b/sound/soc/soc-topology.c
+@@ -851,6 +851,8 @@ static int soc_tplg_denum_create_values(struct soc_tplg *tplg, struct soc_enum *
+ se->dobj.control.dvalues[i] = le32_to_cpu(ec->values[i]);
+ }
+
++ se->items = le32_to_cpu(ec->items);
++ se->values = (const unsigned int *)se->dobj.control.dvalues;
+ return 0;
+ }
+
+diff --git a/sound/soc/sof/topology.c b/sound/soc/sof/topology.c
+index da182314aa874..ebbd99e341437 100644
+--- a/sound/soc/sof/topology.c
++++ b/sound/soc/sof/topology.c
+@@ -2050,6 +2050,8 @@ static int sof_link_unload(struct snd_soc_component *scomp, struct snd_soc_dobj
+ if (!slink)
+ return 0;
+
++ slink->link->platforms->name = NULL;
++
+ kfree(slink->tuples);
+ list_del(&slink->list);
+ kfree(slink->hw_configs);
+diff --git a/sound/soc/sunxi/sun4i-i2s.c b/sound/soc/sunxi/sun4i-i2s.c
+index 5f8d979585b69..3af0b2aab2914 100644
+--- a/sound/soc/sunxi/sun4i-i2s.c
++++ b/sound/soc/sunxi/sun4i-i2s.c
+@@ -100,8 +100,8 @@
+ #define SUN8I_I2S_CTRL_MODE_PCM (0 << 4)
+
+ #define SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK BIT(19)
+-#define SUN8I_I2S_FMT0_LRCLK_POLARITY_INVERTED (1 << 19)
+-#define SUN8I_I2S_FMT0_LRCLK_POLARITY_NORMAL (0 << 19)
++#define SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH (1 << 19)
++#define SUN8I_I2S_FMT0_LRCLK_POLARITY_START_LOW (0 << 19)
+ #define SUN8I_I2S_FMT0_LRCK_PERIOD_MASK GENMASK(17, 8)
+ #define SUN8I_I2S_FMT0_LRCK_PERIOD(period) ((period - 1) << 8)
+ #define SUN8I_I2S_FMT0_BCLK_POLARITY_MASK BIT(7)
+@@ -729,65 +729,37 @@ static int sun4i_i2s_set_soc_fmt(const struct sun4i_i2s *i2s,
+ static int sun8i_i2s_set_soc_fmt(const struct sun4i_i2s *i2s,
+ unsigned int fmt)
+ {
+- u32 mode, val;
++ u32 mode, lrclk_pol, bclk_pol, val;
+ u8 offset;
+
+- /*
+- * DAI clock polarity
+- *
+- * The setup for LRCK contradicts the datasheet, but under a
+- * scope it's clear that the LRCK polarity is reversed
+- * compared to the expected polarity on the bus.
+- */
+- switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+- case SND_SOC_DAIFMT_IB_IF:
+- /* Invert both clocks */
+- val = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED;
+- break;
+- case SND_SOC_DAIFMT_IB_NF:
+- /* Invert bit clock */
+- val = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED |
+- SUN8I_I2S_FMT0_LRCLK_POLARITY_INVERTED;
+- break;
+- case SND_SOC_DAIFMT_NB_IF:
+- /* Invert frame clock */
+- val = 0;
+- break;
+- case SND_SOC_DAIFMT_NB_NF:
+- val = SUN8I_I2S_FMT0_LRCLK_POLARITY_INVERTED;
+- break;
+- default:
+- return -EINVAL;
+- }
+-
+- regmap_update_bits(i2s->regmap, SUN4I_I2S_FMT0_REG,
+- SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK |
+- SUN8I_I2S_FMT0_BCLK_POLARITY_MASK,
+- val);
+-
+ /* DAI Mode */
+ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+ case SND_SOC_DAIFMT_DSP_A:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_PCM;
+ offset = 1;
+ break;
+
+ case SND_SOC_DAIFMT_DSP_B:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_PCM;
+ offset = 0;
+ break;
+
+ case SND_SOC_DAIFMT_I2S:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_LOW;
+ mode = SUN8I_I2S_CTRL_MODE_LEFT;
+ offset = 1;
+ break;
+
+ case SND_SOC_DAIFMT_LEFT_J:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_LEFT;
+ offset = 0;
+ break;
+
+ case SND_SOC_DAIFMT_RIGHT_J:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_RIGHT;
+ offset = 0;
+ break;
+@@ -805,6 +777,35 @@ static int sun8i_i2s_set_soc_fmt(const struct sun4i_i2s *i2s,
+ SUN8I_I2S_TX_CHAN_OFFSET_MASK,
+ SUN8I_I2S_TX_CHAN_OFFSET(offset));
+
++ /* DAI clock polarity */
++ bclk_pol = SUN8I_I2S_FMT0_BCLK_POLARITY_NORMAL;
++
++ switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
++ case SND_SOC_DAIFMT_IB_IF:
++ /* Invert both clocks */
++ lrclk_pol ^= SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK;
++ bclk_pol = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED;
++ break;
++ case SND_SOC_DAIFMT_IB_NF:
++ /* Invert bit clock */
++ bclk_pol = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED;
++ break;
++ case SND_SOC_DAIFMT_NB_IF:
++ /* Invert frame clock */
++ lrclk_pol ^= SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK;
++ break;
++ case SND_SOC_DAIFMT_NB_NF:
++ /* No inversion */
++ break;
++ default:
++ return -EINVAL;
++ }
++
++ regmap_update_bits(i2s->regmap, SUN4I_I2S_FMT0_REG,
++ SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK |
++ SUN8I_I2S_FMT0_BCLK_POLARITY_MASK,
++ lrclk_pol | bclk_pol);
++
+ /* DAI clock master masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_BP_FP:
+@@ -836,65 +837,37 @@ static int sun8i_i2s_set_soc_fmt(const struct sun4i_i2s *i2s,
+ static int sun50i_h6_i2s_set_soc_fmt(const struct sun4i_i2s *i2s,
+ unsigned int fmt)
+ {
+- u32 mode, val;
++ u32 mode, lrclk_pol, bclk_pol, val;
+ u8 offset;
+
+- /*
+- * DAI clock polarity
+- *
+- * The setup for LRCK contradicts the datasheet, but under a
+- * scope it's clear that the LRCK polarity is reversed
+- * compared to the expected polarity on the bus.
+- */
+- switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
+- case SND_SOC_DAIFMT_IB_IF:
+- /* Invert both clocks */
+- val = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED;
+- break;
+- case SND_SOC_DAIFMT_IB_NF:
+- /* Invert bit clock */
+- val = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED |
+- SUN8I_I2S_FMT0_LRCLK_POLARITY_INVERTED;
+- break;
+- case SND_SOC_DAIFMT_NB_IF:
+- /* Invert frame clock */
+- val = 0;
+- break;
+- case SND_SOC_DAIFMT_NB_NF:
+- val = SUN8I_I2S_FMT0_LRCLK_POLARITY_INVERTED;
+- break;
+- default:
+- return -EINVAL;
+- }
+-
+- regmap_update_bits(i2s->regmap, SUN4I_I2S_FMT0_REG,
+- SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK |
+- SUN8I_I2S_FMT0_BCLK_POLARITY_MASK,
+- val);
+-
+ /* DAI Mode */
+ switch (fmt & SND_SOC_DAIFMT_FORMAT_MASK) {
+ case SND_SOC_DAIFMT_DSP_A:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_PCM;
+ offset = 1;
+ break;
+
+ case SND_SOC_DAIFMT_DSP_B:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_PCM;
+ offset = 0;
+ break;
+
+ case SND_SOC_DAIFMT_I2S:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_LOW;
+ mode = SUN8I_I2S_CTRL_MODE_LEFT;
+ offset = 1;
+ break;
+
+ case SND_SOC_DAIFMT_LEFT_J:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_LEFT;
+ offset = 0;
+ break;
+
+ case SND_SOC_DAIFMT_RIGHT_J:
++ lrclk_pol = SUN8I_I2S_FMT0_LRCLK_POLARITY_START_HIGH;
+ mode = SUN8I_I2S_CTRL_MODE_RIGHT;
+ offset = 0;
+ break;
+@@ -912,6 +885,36 @@ static int sun50i_h6_i2s_set_soc_fmt(const struct sun4i_i2s *i2s,
+ SUN50I_H6_I2S_TX_CHAN_SEL_OFFSET_MASK,
+ SUN50I_H6_I2S_TX_CHAN_SEL_OFFSET(offset));
+
++ /* DAI clock polarity */
++ bclk_pol = SUN8I_I2S_FMT0_BCLK_POLARITY_NORMAL;
++
++ switch (fmt & SND_SOC_DAIFMT_INV_MASK) {
++ case SND_SOC_DAIFMT_IB_IF:
++ /* Invert both clocks */
++ lrclk_pol ^= SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK;
++ bclk_pol = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED;
++ break;
++ case SND_SOC_DAIFMT_IB_NF:
++ /* Invert bit clock */
++ bclk_pol = SUN8I_I2S_FMT0_BCLK_POLARITY_INVERTED;
++ break;
++ case SND_SOC_DAIFMT_NB_IF:
++ /* Invert frame clock */
++ lrclk_pol ^= SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK;
++ break;
++ case SND_SOC_DAIFMT_NB_NF:
++ /* No inversion */
++ break;
++ default:
++ return -EINVAL;
++ }
++
++ regmap_update_bits(i2s->regmap, SUN4I_I2S_FMT0_REG,
++ SUN8I_I2S_FMT0_LRCLK_POLARITY_MASK |
++ SUN8I_I2S_FMT0_BCLK_POLARITY_MASK,
++ lrclk_pol | bclk_pol);
++
++
+ /* DAI clock master masks */
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_BP_FP:
+diff --git a/sound/soc/tegra/tegra210_ahub.c b/sound/soc/tegra/tegra210_ahub.c
+index 3f114a2adfced..ab3c6b2544d20 100644
+--- a/sound/soc/tegra/tegra210_ahub.c
++++ b/sound/soc/tegra/tegra210_ahub.c
+@@ -2,7 +2,7 @@
+ //
+ // tegra210_ahub.c - Tegra210 AHUB driver
+ //
+-// Copyright (c) 2020-2022, NVIDIA CORPORATION. All rights reserved.
++// Copyright (c) 2020-2024, NVIDIA CORPORATION. All rights reserved.
+
+ #include <linux/clk.h>
+ #include <linux/device.h>
+@@ -1391,11 +1391,13 @@ static int tegra_ahub_probe(struct platform_device *pdev)
+ return err;
+ }
+
++ pm_runtime_enable(&pdev->dev);
++
+ err = of_platform_populate(pdev->dev.of_node, NULL, NULL, &pdev->dev);
+- if (err)
++ if (err) {
++ pm_runtime_disable(&pdev->dev);
+ return err;
+-
+- pm_runtime_enable(&pdev->dev);
++ }
+
+ return 0;
+ }
+diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
+index 5401f2df463d2..5edb717647847 100644
+--- a/tools/lib/bpf/libbpf.c
++++ b/tools/lib/bpf/libbpf.c
+@@ -10336,7 +10336,7 @@ __bpf_map__iter(const struct bpf_map *m, const struct bpf_object *obj, int i)
+ struct bpf_map *
+ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
+ {
+- if (prev == NULL)
++ if (prev == NULL && obj != NULL)
+ return obj->maps;
+
+ return __bpf_map__iter(prev, obj, 1);
+@@ -10345,7 +10345,7 @@ bpf_object__next_map(const struct bpf_object *obj, const struct bpf_map *prev)
+ struct bpf_map *
+ bpf_object__prev_map(const struct bpf_object *obj, const struct bpf_map *next)
+ {
+- if (next == NULL) {
++ if (next == NULL && obj != NULL) {
+ if (!obj->nr_maps)
+ return NULL;
+ return obj->maps + obj->nr_maps - 1;
+diff --git a/tools/net/ynl/lib/ynl.py b/tools/net/ynl/lib/ynl.py
+index 35e666928119b..ed7b6fff69997 100644
+--- a/tools/net/ynl/lib/ynl.py
++++ b/tools/net/ynl/lib/ynl.py
+@@ -388,6 +388,8 @@ class NetlinkProtocol:
+
+ def decode(self, ynl, nl_msg, op):
+ msg = self._decode(nl_msg)
++ if op is None:
++ op = ynl.rsp_by_value[msg.cmd()]
+ fixed_header_size = ynl._struct_size(op.fixed_header)
+ msg.raw_attrs = NlAttrs(msg.raw, fixed_header_size)
+ return msg
+@@ -919,8 +921,7 @@ class YnlFamily(SpecFamily):
+ print("Netlink done while checking for ntf!?")
+ continue
+
+- op = self.rsp_by_value[nl_msg.cmd()]
+- decoded = self.nlproto.decode(self, nl_msg, op)
++ decoded = self.nlproto.decode(self, nl_msg, None)
+ if decoded.cmd() not in self.async_msg_ids:
+ print("Unexpected msg id done while checking for ntf", decoded)
+ continue
+@@ -978,7 +979,7 @@ class YnlFamily(SpecFamily):
+ if nl_msg.extack:
+ self._decode_extack(req_msg, op, nl_msg.extack)
+ else:
+- op = self.rsp_by_value[nl_msg.cmd()]
++ op = None
+ req_flags = []
+
+ if nl_msg.error:
+diff --git a/tools/perf/util/bpf_lock_contention.c b/tools/perf/util/bpf_lock_contention.c
+index b4cb3fe5cc254..bc4e92c0c08b8 100644
+--- a/tools/perf/util/bpf_lock_contention.c
++++ b/tools/perf/util/bpf_lock_contention.c
+@@ -286,6 +286,9 @@ static void account_end_timestamp(struct lock_contention *con)
+ goto next;
+
+ for (int i = 0; i < total_cpus; i++) {
++ if (cpu_data[i].lock == 0)
++ continue;
++
+ update_lock_stat(stat_fd, -1, end_ts, aggr_mode,
+ &cpu_data[i]);
+ }
+diff --git a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
+index 5f541522364fb..5d0a809dc2df9 100644
+--- a/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
++++ b/tools/testing/selftests/dmabuf-heaps/dmabuf-heap.c
+@@ -29,9 +29,11 @@ static int check_vgem(int fd)
+ version.name = name;
+
+ ret = ioctl(fd, DRM_IOCTL_VERSION, &version);
+- if (ret)
++ if (ret || version.name_len != 4)
+ return 0;
+
++ name[4] = '\0';
++
+ return !strcmp(name, "vgem");
+ }
+
+diff --git a/tools/testing/selftests/mm/mseal_test.c b/tools/testing/selftests/mm/mseal_test.c
+index 41998cf1dcf57..09faffbc3d87c 100644
+--- a/tools/testing/selftests/mm/mseal_test.c
++++ b/tools/testing/selftests/mm/mseal_test.c
+@@ -128,17 +128,6 @@ static int sys_mprotect_pkey(void *ptr, size_t size, unsigned long orig_prot,
+ return sret;
+ }
+
+-static void *sys_mmap(void *addr, unsigned long len, unsigned long prot,
+- unsigned long flags, unsigned long fd, unsigned long offset)
+-{
+- void *sret;
+-
+- errno = 0;
+- sret = (void *) syscall(__NR_mmap, addr, len, prot,
+- flags, fd, offset);
+- return sret;
+-}
+-
+ static int sys_munmap(void *ptr, size_t size)
+ {
+ int sret;
+@@ -219,7 +208,7 @@ static void setup_single_address(int size, void **ptrOut)
+ {
+ void *ptr;
+
+- ptr = sys_mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
++ ptr = mmap(NULL, size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ *ptrOut = ptr;
+ }
+
+@@ -228,7 +217,7 @@ static void setup_single_address_rw(int size, void **ptrOut)
+ void *ptr;
+ unsigned long mapflags = MAP_ANONYMOUS | MAP_PRIVATE;
+
+- ptr = sys_mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0);
++ ptr = mmap(NULL, size, PROT_READ | PROT_WRITE, mapflags, -1, 0);
+ *ptrOut = ptr;
+ }
+
+@@ -252,7 +241,7 @@ bool seal_support(void)
+ void *ptr;
+ unsigned long page_size = getpagesize();
+
+- ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
++ ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (ptr == (void *) -1)
+ return false;
+
+@@ -528,8 +517,8 @@ static void test_seal_zero_address(void)
+ int prot;
+
+ /* use mmap to change protection. */
+- ptr = sys_mmap(0, size, PROT_NONE,
+- MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
++ ptr = mmap(0, size, PROT_NONE,
++ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ FAIL_TEST_IF_FALSE(ptr == 0);
+
+ size = get_vma_size(ptr, &prot);
+@@ -1256,8 +1245,8 @@ static void test_seal_mmap_overwrite_prot(bool seal)
+ }
+
+ /* use mmap to change protection. */
+- ret2 = sys_mmap(ptr, size, PROT_NONE,
+- MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
++ ret2 = mmap(ptr, size, PROT_NONE,
++ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+@@ -1287,8 +1276,8 @@ static void test_seal_mmap_expand(bool seal)
+ }
+
+ /* use mmap to expand. */
+- ret2 = sys_mmap(ptr, size, PROT_READ,
+- MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
++ ret2 = mmap(ptr, size, PROT_READ,
++ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+@@ -1315,8 +1304,8 @@ static void test_seal_mmap_shrink(bool seal)
+ }
+
+ /* use mmap to shrink. */
+- ret2 = sys_mmap(ptr, 8 * page_size, PROT_READ,
+- MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
++ ret2 = mmap(ptr, 8 * page_size, PROT_READ,
++ MAP_ANONYMOUS | MAP_PRIVATE | MAP_FIXED, -1, 0);
+ if (seal) {
+ FAIL_TEST_IF_FALSE(ret2 == MAP_FAILED);
+ FAIL_TEST_IF_FALSE(errno == EPERM);
+@@ -1697,7 +1686,7 @@ static void test_seal_discard_ro_anon_on_filebacked(bool seal)
+ ret = fallocate(fd, 0, 0, size);
+ FAIL_TEST_IF_FALSE(!ret);
+
+- ptr = sys_mmap(NULL, size, PROT_READ, mapflags, fd, 0);
++ ptr = mmap(NULL, size, PROT_READ, mapflags, fd, 0);
+ FAIL_TEST_IF_FALSE(ptr != MAP_FAILED);
+
+ if (seal) {
+@@ -1727,7 +1716,7 @@ static void test_seal_discard_ro_anon_on_shared(bool seal)
+ int ret;
+ unsigned long mapflags = MAP_ANONYMOUS | MAP_SHARED;
+
+- ptr = sys_mmap(NULL, size, PROT_READ, mapflags, -1, 0);
++ ptr = mmap(NULL, size, PROT_READ, mapflags, -1, 0);
+ FAIL_TEST_IF_FALSE(ptr != (void *)-1);
+
+ if (seal) {
+diff --git a/tools/testing/selftests/mm/seal_elf.c b/tools/testing/selftests/mm/seal_elf.c
+index f2babec79bb63..07727d4892ac9 100644
+--- a/tools/testing/selftests/mm/seal_elf.c
++++ b/tools/testing/selftests/mm/seal_elf.c
+@@ -61,17 +61,6 @@ static int sys_mseal(void *start, size_t len)
+ return sret;
+ }
+
+-static void *sys_mmap(void *addr, unsigned long len, unsigned long prot,
+- unsigned long flags, unsigned long fd, unsigned long offset)
+-{
+- void *sret;
+-
+- errno = 0;
+- sret = (void *) syscall(__NR_mmap, addr, len, prot,
+- flags, fd, offset);
+- return sret;
+-}
+-
+ static inline int sys_mprotect(void *ptr, size_t size, unsigned long prot)
+ {
+ int sret;
+@@ -87,7 +76,7 @@ static bool seal_support(void)
+ void *ptr;
+ unsigned long page_size = getpagesize();
+
+- ptr = sys_mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
++ ptr = mmap(NULL, page_size, PROT_READ, MAP_ANONYMOUS | MAP_PRIVATE, -1, 0);
+ if (ptr == (void *) -1)
+ return false;
+
+diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile
+index d9393569d03a4..ec5377ffda315 100644
+--- a/tools/testing/selftests/net/Makefile
++++ b/tools/testing/selftests/net/Makefile
+@@ -84,7 +84,8 @@ TEST_GEN_PROGS += so_incoming_cpu
+ TEST_PROGS += sctp_vrf.sh
+ TEST_GEN_FILES += sctp_hello
+ TEST_GEN_FILES += ip_local_port_range
+-TEST_GEN_FILES += bind_wildcard
++TEST_GEN_PROGS += bind_wildcard
++TEST_GEN_PROGS += bind_timewait
+ TEST_PROGS += test_vxlan_mdb.sh
+ TEST_PROGS += test_bridge_neigh_suppress.sh
+ TEST_PROGS += test_vxlan_nolocalbypass.sh
+diff --git a/tools/testing/selftests/riscv/mm/mmap_bottomup.c b/tools/testing/selftests/riscv/mm/mmap_bottomup.c
+index 7f7d3eb8b9c92..f9ccae50349bc 100644
+--- a/tools/testing/selftests/riscv/mm/mmap_bottomup.c
++++ b/tools/testing/selftests/riscv/mm/mmap_bottomup.c
+@@ -7,8 +7,6 @@
+ TEST(infinite_rlimit)
+ {
+ EXPECT_EQ(BOTTOM_UP, memory_layout());
+-
+- TEST_MMAPS;
+ }
+
+ TEST_HARNESS_MAIN
+diff --git a/tools/testing/selftests/riscv/mm/mmap_default.c b/tools/testing/selftests/riscv/mm/mmap_default.c
+index 2ba3ec9900064..3f53b6ecc3261 100644
+--- a/tools/testing/selftests/riscv/mm/mmap_default.c
++++ b/tools/testing/selftests/riscv/mm/mmap_default.c
+@@ -7,8 +7,6 @@
+ TEST(default_rlimit)
+ {
+ EXPECT_EQ(TOP_DOWN, memory_layout());
+-
+- TEST_MMAPS;
+ }
+
+ TEST_HARNESS_MAIN
+diff --git a/tools/testing/selftests/riscv/mm/mmap_test.h b/tools/testing/selftests/riscv/mm/mmap_test.h
+index 3b29ca3bb3d40..75918d15919f2 100644
+--- a/tools/testing/selftests/riscv/mm/mmap_test.h
++++ b/tools/testing/selftests/riscv/mm/mmap_test.h
+@@ -10,76 +10,9 @@
+ #define TOP_DOWN 0
+ #define BOTTOM_UP 1
+
+-#if __riscv_xlen == 64
+-uint64_t random_addresses[] = {
+- 0x19764f0d73b3a9f0, 0x016049584cecef59, 0x3580bdd3562f4acd,
+- 0x1164219f20b17da0, 0x07d97fcb40ff2373, 0x76ec528921272ee7,
+- 0x4dd48c38a3de3f70, 0x2e11415055f6997d, 0x14b43334ac476c02,
+- 0x375a60795aff19f6, 0x47f3051725b8ee1a, 0x4e697cf240494a9f,
+- 0x456b59b5c2f9e9d1, 0x101724379d63cb96, 0x7fe9ad31619528c1,
+- 0x2f417247c495c2ea, 0x329a5a5b82943a5e, 0x06d7a9d6adcd3827,
+- 0x327b0b9ee37f62d5, 0x17c7b1851dfd9b76, 0x006ebb6456ec2cd9,
+- 0x00836cd14146a134, 0x00e5c4dcde7126db, 0x004c29feadf75753,
+- 0x00d8b20149ed930c, 0x00d71574c269387a, 0x0006ebe4a82acb7a,
+- 0x0016135df51f471b, 0x00758bdb55455160, 0x00d0bdd949b13b32,
+- 0x00ecea01e7c5f54b, 0x00e37b071b9948b1, 0x0011fdd00ff57ab3,
+- 0x00e407294b52f5ea, 0x00567748c200ed20, 0x000d073084651046,
+- 0x00ac896f4365463c, 0x00eb0d49a0b26216, 0x0066a2564a982a31,
+- 0x002e0d20237784ae, 0x0000554ff8a77a76, 0x00006ce07a54c012,
+- 0x000009570516d799, 0x00000954ca15b84d, 0x0000684f0d453379,
+- 0x00002ae5816302b5, 0x0000042403fb54bf, 0x00004bad7392bf30,
+- 0x00003e73bfa4b5e3, 0x00005442c29978e0, 0x00002803f11286b6,
+- 0x000073875d745fc6, 0x00007cede9cb8240, 0x000027df84cc6a4f,
+- 0x00006d7e0e74242a, 0x00004afd0b836e02, 0x000047d0e837cd82,
+- 0x00003b42405efeda, 0x00001531bafa4c95, 0x00007172cae34ac4,
+-};
+-#else
+-uint32_t random_addresses[] = {
+- 0x8dc302e0, 0x929ab1e0, 0xb47683ba, 0xea519c73, 0xa19f1c90, 0xc49ba213,
+- 0x8f57c625, 0xadfe5137, 0x874d4d95, 0xaa20f09d, 0xcf21ebfc, 0xda7737f1,
+- 0xcedf392a, 0x83026c14, 0xccedca52, 0xc6ccf826, 0xe0cd9415, 0x997472ca,
+- 0xa21a44c1, 0xe82196f5, 0xa23fd66b, 0xc28d5590, 0xd009cdce, 0xcf0be646,
+- 0x8fc8c7ff, 0xe2a85984, 0xa3d3236b, 0x89a0619d, 0xc03db924, 0xb5d4cc1b,
+- 0xb96ee04c, 0xd191da48, 0xb432a000, 0xaa2bebbc, 0xa2fcb289, 0xb0cca89b,
+- 0xb0c18d6a, 0x88f58deb, 0xa4d42d1c, 0xe4d74e86, 0x99902b09, 0x8f786d31,
+- 0xbec5e381, 0x9a727e65, 0xa9a65040, 0xa880d789, 0x8f1b335e, 0xfc821c1e,
+- 0x97e34be4, 0xbbef84ed, 0xf447d197, 0xfd7ceee2, 0xe632348d, 0xee4590f4,
+- 0x958992a5, 0xd57e05d6, 0xfd240970, 0xc5b0dcff, 0xd96da2c2, 0xa7ae041d,
+-};
+-#endif
+-
+-// Only works on 64 bit
+-#if __riscv_xlen == 64
+ #define PROT (PROT_READ | PROT_WRITE)
+ #define FLAGS (MAP_PRIVATE | MAP_ANONYMOUS)
+
+-/* mmap must return a value that doesn't use more bits than the hint address. */
+-static inline unsigned long get_max_value(unsigned long input)
+-{
+- unsigned long max_bit = (1UL << (((sizeof(unsigned long) * 8) - 1 -
+- __builtin_clzl(input))));
+-
+- return max_bit + (max_bit - 1);
+-}
+-
+-#define TEST_MMAPS \
+- ({ \
+- void *mmap_addr; \
+- for (int i = 0; i < ARRAY_SIZE(random_addresses); i++) { \
+- mmap_addr = mmap((void *)random_addresses[i], \
+- 5 * sizeof(int), PROT, FLAGS, 0, 0); \
+- EXPECT_NE(MAP_FAILED, mmap_addr); \
+- EXPECT_GE((void *)get_max_value(random_addresses[i]), \
+- mmap_addr); \
+- mmap_addr = mmap((void *)random_addresses[i], \
+- 5 * sizeof(int), PROT, FLAGS, 0, 0); \
+- EXPECT_NE(MAP_FAILED, mmap_addr); \
+- EXPECT_GE((void *)get_max_value(random_addresses[i]), \
+- mmap_addr); \
+- } \
+- })
+-#endif /* __riscv_xlen == 64 */
+-
+ static inline int memory_layout(void)
+ {
+ void *value1 = mmap(NULL, sizeof(int), PROT, FLAGS, 0, 0);
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-08 11:05 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-08 11:05 UTC (permalink / raw
To: gentoo-commits
commit: a965b43020306cd4562bffa7f427356df8ab29de
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sun Sep 8 11:05:11 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sun Sep 8 11:05:11 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=a965b430
Linux patch 6.10.9
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1008_linux-6.10.9.patch | 7005 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 7009 insertions(+)
diff --git a/0000_README b/0000_README
index 574cd30b..20bc0dd9 100644
--- a/0000_README
+++ b/0000_README
@@ -75,6 +75,10 @@ Patch: 1007_linux-6.10.8.patch
From: https://www.kernel.org
Desc: Linux 6.10.8
+Patch: 1008_linux-6.10.9.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.9
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1008_linux-6.10.9.patch b/1008_linux-6.10.9.patch
new file mode 100644
index 00000000..d0922587
--- /dev/null
+++ b/1008_linux-6.10.9.patch
@@ -0,0 +1,7005 @@
+diff --git a/Documentation/locking/hwspinlock.rst b/Documentation/locking/hwspinlock.rst
+index 6f03713b70039..2ffaa3cbd63f1 100644
+--- a/Documentation/locking/hwspinlock.rst
++++ b/Documentation/locking/hwspinlock.rst
+@@ -85,6 +85,17 @@ is already free).
+
+ Should be called from a process context (might sleep).
+
++::
++
++ int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id);
++
++After verifying the owner of the hwspinlock, release a previously acquired
++hwspinlock; returns 0 on success, or an appropriate error code on failure
++(e.g. -EOPNOTSUPP if the bust operation is not defined for the specific
++hwspinlock).
++
++Should be called from a process context (might sleep).
++
+ ::
+
+ int hwspin_lock_timeout(struct hwspinlock *hwlock, unsigned int timeout);
+diff --git a/Makefile b/Makefile
+index 2e5ac6ab3d476..5945cce6b0663 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 8
++SUBLEVEL = 9
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+index 7d03316c279df..9f72e748c8041 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+@@ -173,6 +173,20 @@ vreg_edp_3p3: regulator-edp-3p3 {
+ regulator-always-on;
+ regulator-boot-on;
+ };
++
++ vreg_nvme: regulator-nvme {
++ compatible = "regulator-fixed";
++
++ regulator-name = "VREG_NVME_3P3";
++ regulator-min-microvolt = <3300000>;
++ regulator-max-microvolt = <3300000>;
++
++ gpio = <&tlmm 18 GPIO_ACTIVE_HIGH>;
++ enable-active-high;
++
++ pinctrl-names = "default";
++ pinctrl-0 = <&nvme_reg_en>;
++ };
+ };
+
+ &apps_rsc {
+@@ -644,6 +658,12 @@ &mdss_dp3_phy {
+ };
+
+ &pcie4 {
++ perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
++ wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
++
++ pinctrl-0 = <&pcie4_default>;
++ pinctrl-names = "default";
++
+ status = "okay";
+ };
+
+@@ -655,6 +675,14 @@ &pcie4_phy {
+ };
+
+ &pcie6a {
++ perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
++ wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
++
++ vddpe-3v3-supply = <&vreg_nvme>;
++
++ pinctrl-names = "default";
++ pinctrl-0 = <&pcie6a_default>;
++
+ status = "okay";
+ };
+
+@@ -804,6 +832,59 @@ kybd_default: kybd-default-state {
+ bias-disable;
+ };
+
++ nvme_reg_en: nvme-reg-en-state {
++ pins = "gpio18";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-disable;
++ };
++
++ pcie4_default: pcie4-default-state {
++ clkreq-n-pins {
++ pins = "gpio147";
++ function = "pcie4_clk";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++
++ perst-n-pins {
++ pins = "gpio146";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-disable;
++ };
++
++ wake-n-pins {
++ pins = "gpio148";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++ };
++
++ pcie6a_default: pcie6a-default-state {
++ clkreq-n-pins {
++ pins = "gpio153";
++ function = "pcie6a_clk";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++
++ perst-n-pins {
++ pins = "gpio152";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-pull-down;
++ };
++
++ wake-n-pins {
++ pins = "gpio154";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++ };
++
+ tpad_default: tpad-default-state {
+ pins = "gpio3";
+ function = "gpio";
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+index 2d7dedb7e30f2..f90177a662b7d 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+@@ -59,6 +59,20 @@ vreg_edp_3p3: regulator-edp-3p3 {
+ regulator-always-on;
+ regulator-boot-on;
+ };
++
++ vreg_nvme: regulator-nvme {
++ compatible = "regulator-fixed";
++
++ regulator-name = "VREG_NVME_3P3";
++ regulator-min-microvolt = <3300000>;
++ regulator-max-microvolt = <3300000>;
++
++ gpio = <&tlmm 18 GPIO_ACTIVE_HIGH>;
++ enable-active-high;
++
++ pinctrl-names = "default";
++ pinctrl-0 = <&nvme_reg_en>;
++ };
+ };
+
+ &apps_rsc {
+@@ -455,6 +469,12 @@ &mdss_dp3_phy {
+ };
+
+ &pcie4 {
++ perst-gpios = <&tlmm 146 GPIO_ACTIVE_LOW>;
++ wake-gpios = <&tlmm 148 GPIO_ACTIVE_LOW>;
++
++ pinctrl-0 = <&pcie4_default>;
++ pinctrl-names = "default";
++
+ status = "okay";
+ };
+
+@@ -466,6 +486,14 @@ &pcie4_phy {
+ };
+
+ &pcie6a {
++ perst-gpios = <&tlmm 152 GPIO_ACTIVE_LOW>;
++ wake-gpios = <&tlmm 154 GPIO_ACTIVE_LOW>;
++
++ vddpe-3v3-supply = <&vreg_nvme>;
++
++ pinctrl-names = "default";
++ pinctrl-0 = <&pcie6a_default>;
++
+ status = "okay";
+ };
+
+@@ -528,6 +556,59 @@ edp_reg_en: edp-reg-en-state {
+ drive-strength = <16>;
+ bias-disable;
+ };
++
++ nvme_reg_en: nvme-reg-en-state {
++ pins = "gpio18";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-disable;
++ };
++
++ pcie4_default: pcie4-default-state {
++ clkreq-n-pins {
++ pins = "gpio147";
++ function = "pcie4_clk";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++
++ perst-n-pins {
++ pins = "gpio146";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-disable;
++ };
++
++ wake-n-pins {
++ pins = "gpio148";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++ };
++
++ pcie6a_default: pcie6a-default-state {
++ clkreq-n-pins {
++ pins = "gpio153";
++ function = "pcie6a_clk";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++
++ perst-n-pins {
++ pins = "gpio152";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-pull-down;
++ };
++
++ wake-n-pins {
++ pins = "gpio154";
++ function = "gpio";
++ drive-strength = <2>;
++ bias-pull-up;
++ };
++ };
+ };
+
+ &uart21 {
+diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c
+index 44df3f11e7319..7b4940530b462 100644
+--- a/arch/x86/kernel/cpu/amd.c
++++ b/arch/x86/kernel/cpu/amd.c
+@@ -462,7 +462,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c)
+ switch (c->x86_model) {
+ case 0x00 ... 0x2f:
+ case 0x40 ... 0x4f:
+- case 0x70 ... 0x7f:
++ case 0x60 ... 0x7f:
+ setup_force_cpu_cap(X86_FEATURE_ZEN5);
+ break;
+ default:
+diff --git a/block/blk-integrity.c b/block/blk-integrity.c
+index ccbeb6dfa87a4..8dd8a0126274b 100644
+--- a/block/blk-integrity.c
++++ b/block/blk-integrity.c
+@@ -397,8 +397,6 @@ void blk_integrity_unregister(struct gendisk *disk)
+ if (!bi->profile)
+ return;
+
+- /* ensure all bios are off the integrity workqueue */
+- blk_flush_integrity();
+ blk_queue_flag_clear(QUEUE_FLAG_STABLE_WRITES, disk->queue);
+ memset(bi, 0, sizeof(*bi));
+ }
+diff --git a/crypto/ecc.c b/crypto/ecc.c
+index fe761256e335b..dd48d9928a210 100644
+--- a/crypto/ecc.c
++++ b/crypto/ecc.c
+@@ -78,7 +78,7 @@ void ecc_digits_from_bytes(const u8 *in, unsigned int nbytes,
+ /* diff > 0: not enough input bytes: set most significant digits to 0 */
+ if (diff > 0) {
+ ndigits -= diff;
+- memset(&out[ndigits - 1], 0, diff * sizeof(u64));
++ memset(&out[ndigits], 0, diff * sizeof(u64));
+ }
+
+ if (o) {
+diff --git a/drivers/base/regmap/regmap-spi.c b/drivers/base/regmap/regmap-spi.c
+index 094cf2a2ca3cd..14b1d88997cbe 100644
+--- a/drivers/base/regmap/regmap-spi.c
++++ b/drivers/base/regmap/regmap-spi.c
+@@ -122,8 +122,7 @@ static const struct regmap_bus *regmap_get_spi_bus(struct spi_device *spi,
+ return ERR_PTR(-ENOMEM);
+
+ max_msg_size = spi_max_message_size(spi);
+- reg_reserve_size = config->reg_bits / BITS_PER_BYTE
+- + config->pad_bits / BITS_PER_BYTE;
++ reg_reserve_size = (config->reg_bits + config->pad_bits) / BITS_PER_BYTE;
+ if (max_size + reg_reserve_size > max_msg_size)
+ max_size -= reg_reserve_size;
+
+diff --git a/drivers/cpufreq/scmi-cpufreq.c b/drivers/cpufreq/scmi-cpufreq.c
+index 3b4f6bfb2f4cf..b87fd127aa433 100644
+--- a/drivers/cpufreq/scmi-cpufreq.c
++++ b/drivers/cpufreq/scmi-cpufreq.c
+@@ -63,9 +63,9 @@ static unsigned int scmi_cpufreq_fast_switch(struct cpufreq_policy *policy,
+ unsigned int target_freq)
+ {
+ struct scmi_data *priv = policy->driver_data;
++ unsigned long freq = target_freq;
+
+- if (!perf_ops->freq_set(ph, priv->domain_id,
+- target_freq * 1000, true))
++ if (!perf_ops->freq_set(ph, priv->domain_id, freq * 1000, true))
+ return target_freq;
+
+ return 0;
+diff --git a/drivers/crypto/stm32/stm32-cryp.c b/drivers/crypto/stm32/stm32-cryp.c
+index 11ad4ffdce0d4..84f5f30d5dddb 100644
+--- a/drivers/crypto/stm32/stm32-cryp.c
++++ b/drivers/crypto/stm32/stm32-cryp.c
+@@ -11,6 +11,7 @@
+ #include <crypto/internal/des.h>
+ #include <crypto/internal/skcipher.h>
+ #include <crypto/scatterwalk.h>
++#include <linux/bottom_half.h>
+ #include <linux/clk.h>
+ #include <linux/delay.h>
+ #include <linux/err.h>
+@@ -1665,8 +1666,11 @@ static irqreturn_t stm32_cryp_irq_thread(int irq, void *arg)
+ it_mask &= ~IMSCR_OUT;
+ stm32_cryp_write(cryp, cryp->caps->imsc, it_mask);
+
+- if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out)
++ if (!cryp->payload_in && !cryp->header_in && !cryp->payload_out) {
++ local_bh_disable();
+ stm32_cryp_finish_req(cryp, 0);
++ local_bh_enable();
++ }
+
+ return IRQ_HANDLED;
+ }
+diff --git a/drivers/dma/altera-msgdma.c b/drivers/dma/altera-msgdma.c
+index a8e3615235b8e..041f549c8c990 100644
+--- a/drivers/dma/altera-msgdma.c
++++ b/drivers/dma/altera-msgdma.c
+@@ -233,7 +233,7 @@ static void msgdma_free_descriptor(struct msgdma_device *mdev,
+ struct msgdma_sw_desc *child, *next;
+
+ mdev->desc_free_cnt++;
+- list_add_tail(&desc->node, &mdev->free_list);
++ list_move_tail(&desc->node, &mdev->free_list);
+ list_for_each_entry_safe(child, next, &desc->tx_list, node) {
+ mdev->desc_free_cnt++;
+ list_move_tail(&child->node, &mdev->free_list);
+@@ -583,17 +583,16 @@ static void msgdma_issue_pending(struct dma_chan *chan)
+ static void msgdma_chan_desc_cleanup(struct msgdma_device *mdev)
+ {
+ struct msgdma_sw_desc *desc, *next;
++ unsigned long irqflags;
+
+ list_for_each_entry_safe(desc, next, &mdev->done_list, node) {
+ struct dmaengine_desc_callback cb;
+
+- list_del(&desc->node);
+-
+ dmaengine_desc_get_callback(&desc->async_tx, &cb);
+ if (dmaengine_desc_callback_valid(&cb)) {
+- spin_unlock(&mdev->lock);
++ spin_unlock_irqrestore(&mdev->lock, irqflags);
+ dmaengine_desc_callback_invoke(&cb, NULL);
+- spin_lock(&mdev->lock);
++ spin_lock_irqsave(&mdev->lock, irqflags);
+ }
+
+ /* Run any dependencies, then free the descriptor */
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+index c50202215f6b1..9baee7c246b6d 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_aca.c
+@@ -534,7 +534,7 @@ int amdgpu_aca_get_error_data(struct amdgpu_device *adev, struct aca_handle *han
+ if (aca_handle_is_valid(handle))
+ return -EOPNOTSUPP;
+
+- if (!(BIT(type) & handle->mask))
++ if ((type < 0) || (!(BIT(type) & handle->mask)))
+ return 0;
+
+ return __aca_get_error_data(adev, handle, type, err_data, qctx);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c
+index a4d65973bf7cf..80771b1480fff 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_afmt.c
+@@ -100,6 +100,7 @@ struct amdgpu_afmt_acr amdgpu_afmt_acr(uint32_t clock)
+ amdgpu_afmt_calc_cts(clock, &res.cts_32khz, &res.n_32khz, 32000);
+ amdgpu_afmt_calc_cts(clock, &res.cts_44_1khz, &res.n_44_1khz, 44100);
+ amdgpu_afmt_calc_cts(clock, &res.cts_48khz, &res.n_48khz, 48000);
++ res.clock = clock;
+
+ return res;
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+index 48ad0c04aa72b..e675e4815650b 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_amdkfd_gpuvm.c
+@@ -415,6 +415,10 @@ static int amdgpu_amdkfd_bo_validate(struct amdgpu_bo *bo, uint32_t domain,
+ "Called with userptr BO"))
+ return -EINVAL;
+
++ /* bo has been pinned, not need validate it */
++ if (bo->tbo.pin_count)
++ return 0;
++
+ amdgpu_bo_placement_from_domain(bo, domain);
+
+ ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
+@@ -2712,7 +2716,7 @@ static int confirm_valid_user_pages_locked(struct amdkfd_process_info *process_i
+
+ /* keep mem without hmm range at userptr_inval_list */
+ if (!mem->range)
+- continue;
++ continue;
+
+ /* Only check mem with hmm range associated */
+ valid = amdgpu_ttm_tt_get_user_pages_done(
+@@ -2957,9 +2961,6 @@ int amdgpu_amdkfd_gpuvm_restore_process_bos(void *info, struct dma_fence __rcu *
+ if (!attachment->is_mapped)
+ continue;
+
+- if (attachment->bo_va->base.bo->tbo.pin_count)
+- continue;
+-
+ kfd_mem_dmaunmap_attachment(mem, attachment);
+ ret = update_gpuvm_pte(mem, attachment, &sync_obj);
+ if (ret) {
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+index 52b12c1718eb0..7dc102f0bc1d3 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_atombios.c
+@@ -1484,6 +1484,8 @@ int amdgpu_atombios_init_mc_reg_table(struct amdgpu_device *adev,
+ (u32)le32_to_cpu(*((u32 *)reg_data + j));
+ j++;
+ } else if ((reg_table->mc_reg_address[i].pre_reg_data & LOW_NIBBLE_MASK) == DATA_EQU_PREV) {
++ if (i == 0)
++ continue;
+ reg_table->mc_reg_table_entry[num_ranges].mc_data[i] =
+ reg_table->mc_reg_table_entry[num_ranges].mc_data[i - 1];
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+index b8280be6225d9..c3d89088123db 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cgs.c
+@@ -213,6 +213,9 @@ static int amdgpu_cgs_get_firmware_info(struct cgs_device *cgs_device,
+ struct amdgpu_firmware_info *ucode;
+
+ id = fw_type_convert(cgs_device, type);
++ if (id >= AMDGPU_UCODE_ID_MAXIMUM)
++ return -EINVAL;
++
+ ucode = &adev->firmware.ucode[id];
+ if (ucode->fw == NULL)
+ return -EINVAL;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+index 89cf9ac6da174..d24d7a1086240 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+@@ -5012,7 +5012,8 @@ static int amdgpu_device_recover_vram(struct amdgpu_device *adev)
+ shadow = vmbo->shadow;
+
+ /* No need to recover an evicted BO */
+- if (shadow->tbo.resource->mem_type != TTM_PL_TT ||
++ if (!shadow->tbo.resource ||
++ shadow->tbo.resource->mem_type != TTM_PL_TT ||
+ shadow->tbo.resource->start == AMDGPU_BO_INVALID_OFFSET ||
+ shadow->parent->tbo.resource->mem_type != TTM_PL_VRAM)
+ continue;
+@@ -5726,7 +5727,7 @@ int amdgpu_device_gpu_recover(struct amdgpu_device *adev,
+ * to put adev in the 1st position.
+ */
+ INIT_LIST_HEAD(&device_list);
+- if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1)) {
++ if (!amdgpu_sriov_vf(adev) && (adev->gmc.xgmi.num_physical_nodes > 1) && hive) {
+ list_for_each_entry(tmp_adev, &hive->device_list, gmc.xgmi.head) {
+ list_add_tail(&tmp_adev->reset_list, &device_list);
+ if (adev->shutdown)
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+index f1b08893765cf..1ea55ee4796e0 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+@@ -1597,7 +1597,7 @@ static int amdgpu_discovery_get_mall_info(struct amdgpu_device *adev)
+ break;
+ case 2:
+ mall_size_per_umc = le32_to_cpu(mall_info->v2.mall_size_per_umc);
+- adev->gmc.mall_size = mall_size_per_umc * adev->gmc.num_umc;
++ adev->gmc.mall_size = (uint64_t)mall_size_per_umc * adev->gmc.num_umc;
+ break;
+ default:
+ dev_err(adev->dev,
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c
+index e71768661ca8d..09a34c7258e22 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.c
+@@ -179,7 +179,7 @@ static int __amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr,
+ * Returns the number of bytes read/written; -errno on error.
+ */
+ static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr,
+- u8 *eeprom_buf, u16 buf_size, bool read)
++ u8 *eeprom_buf, u32 buf_size, bool read)
+ {
+ const struct i2c_adapter_quirks *quirks = i2c_adap->quirks;
+ u16 limit;
+@@ -225,7 +225,7 @@ static int amdgpu_eeprom_xfer(struct i2c_adapter *i2c_adap, u32 eeprom_addr,
+
+ int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap,
+ u32 eeprom_addr, u8 *eeprom_buf,
+- u16 bytes)
++ u32 bytes)
+ {
+ return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes,
+ true);
+@@ -233,7 +233,7 @@ int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap,
+
+ int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap,
+ u32 eeprom_addr, u8 *eeprom_buf,
+- u16 bytes)
++ u32 bytes)
+ {
+ return amdgpu_eeprom_xfer(i2c_adap, eeprom_addr, eeprom_buf, bytes,
+ false);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h
+index 6935adb2be1f1..8083b8253ef43 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_eeprom.h
+@@ -28,10 +28,10 @@
+
+ int amdgpu_eeprom_read(struct i2c_adapter *i2c_adap,
+ u32 eeprom_addr, u8 *eeprom_buf,
+- u16 bytes);
++ u32 bytes);
+
+ int amdgpu_eeprom_write(struct i2c_adapter *i2c_adap,
+ u32 eeprom_addr, u8 *eeprom_buf,
+- u16 bytes);
++ u32 bytes);
+
+ #endif
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+index c623e23049d1d..a6ddffbf8b4df 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gart.c
+@@ -34,6 +34,7 @@
+ #include <asm/set_memory.h>
+ #endif
+ #include "amdgpu.h"
++#include "amdgpu_reset.h"
+ #include <drm/drm_drv.h>
+ #include <drm/ttm/ttm_tt.h>
+
+@@ -408,7 +409,10 @@ void amdgpu_gart_invalidate_tlb(struct amdgpu_device *adev)
+ return;
+
+ mb();
+- amdgpu_device_flush_hdp(adev, NULL);
++ if (down_read_trylock(&adev->reset_domain->sem)) {
++ amdgpu_device_flush_hdp(adev, NULL);
++ up_read(&adev->reset_domain->sem);
++ }
+ for_each_set_bit(i, adev->vmhubs_mask, AMDGPU_MAX_VMHUBS)
+ amdgpu_gmc_flush_gpu_tlb(adev, 0, i, 0);
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+index a0ea6fe8d0606..977cde6d13626 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_kms.c
+@@ -623,25 +623,32 @@ int amdgpu_info_ioctl(struct drm_device *dev, void *data, struct drm_file *filp)
+ switch (type) {
+ case AMD_IP_BLOCK_TYPE_GFX:
+ ret = amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_GFX, &inst_mask);
++ if (ret)
++ return ret;
+ count = hweight32(inst_mask);
+ break;
+ case AMD_IP_BLOCK_TYPE_SDMA:
+ ret = amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_SDMA, &inst_mask);
++ if (ret)
++ return ret;
+ count = hweight32(inst_mask);
+ break;
+ case AMD_IP_BLOCK_TYPE_JPEG:
+ ret = amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_VCN, &inst_mask);
++ if (ret)
++ return ret;
+ count = hweight32(inst_mask) * adev->jpeg.num_jpeg_rings;
+ break;
+ case AMD_IP_BLOCK_TYPE_VCN:
+ ret = amdgpu_xcp_get_inst_details(xcp, AMDGPU_XCP_VCN, &inst_mask);
++ if (ret)
++ return ret;
+ count = hweight32(inst_mask);
+ break;
+ default:
+ return -EINVAL;
+ }
+- if (ret)
+- return ret;
++
+ return copy_to_user(out, &count, min(size, 4u)) ? -EFAULT : 0;
+ }
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+index cef9dd0a012b5..b3df27ce76634 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp.c
+@@ -1375,6 +1375,9 @@ static void psp_xgmi_reflect_topology_info(struct psp_context *psp,
+ uint8_t dst_num_links = node_info.num_links;
+
+ hive = amdgpu_get_xgmi_hive(psp->adev);
++ if (WARN_ON(!hive))
++ return;
++
+ list_for_each_entry(mirror_adev, &hive->device_list, gmc.xgmi.head) {
+ struct psp_xgmi_topology_info *mirror_top_info;
+ int j;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+index 0c4ee06451e9c..7ba90c5974ed3 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+@@ -2112,6 +2112,7 @@ static void amdgpu_ras_interrupt_umc_handler(struct ras_manager *obj,
+ /* Let IP handle its data, maybe we need get the output
+ * from the callback to update the error type/count, etc
+ */
++ amdgpu_ras_set_fed(obj->adev, true);
+ ret = data->cb(obj->adev, &err_data, entry);
+ /* ue will trigger an interrupt, and in that case
+ * we need do a reset to recovery the whole system.
+@@ -4504,3 +4505,21 @@ int amdgpu_ras_reserve_page(struct amdgpu_device *adev, uint64_t pfn)
+
+ return ret;
+ }
++
++void amdgpu_ras_event_log_print(struct amdgpu_device *adev, u64 event_id,
++ const char *fmt, ...)
++{
++ struct va_format vaf;
++ va_list args;
++
++ va_start(args, fmt);
++ vaf.fmt = fmt;
++ vaf.va = &args;
++
++ if (amdgpu_ras_event_id_is_valid(adev, event_id))
++ dev_printk(KERN_INFO, adev->dev, "{%llu}%pV", event_id, &vaf);
++ else
++ dev_printk(KERN_INFO, adev->dev, "%pV", &vaf);
++
++ va_end(args);
++}
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+index 7021c4a66fb5e..18d20f6faa5fc 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.h
+@@ -67,13 +67,8 @@ struct amdgpu_iv_entry;
+ /* The high three bits indicates socketid */
+ #define AMDGPU_RAS_GET_FEATURES(val) ((val) & ~AMDGPU_RAS_FEATURES_SOCKETID_MASK)
+
+-#define RAS_EVENT_LOG(_adev, _id, _fmt, ...) \
+-do { \
+- if (amdgpu_ras_event_id_is_valid((_adev), (_id))) \
+- dev_info((_adev)->dev, "{%llu}" _fmt, (_id), ##__VA_ARGS__); \
+- else \
+- dev_info((_adev)->dev, _fmt, ##__VA_ARGS__); \
+-} while (0)
++#define RAS_EVENT_LOG(adev, id, fmt, ...) \
++ amdgpu_ras_event_log_print((adev), (id), (fmt), ##__VA_ARGS__)
+
+ enum amdgpu_ras_block {
+ AMDGPU_RAS_BLOCK__UMC = 0,
+@@ -956,4 +951,8 @@ int amdgpu_ras_put_poison_req(struct amdgpu_device *adev,
+ enum amdgpu_ras_block block, uint16_t pasid,
+ pasid_notify pasid_fn, void *data, uint32_t reset);
+
++__printf(3, 4)
++void amdgpu_ras_event_log_print(struct amdgpu_device *adev, u64 event_id,
++ const char *fmt, ...);
++
+ #endif
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+index 88ffb15e25ccc..e6344a6b0a9f6 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+@@ -354,7 +354,7 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
+ ring->max_dw = max_dw;
+ ring->hw_prio = hw_prio;
+
+- if (!ring->no_scheduler) {
++ if (!ring->no_scheduler && ring->funcs->type < AMDGPU_HW_IP_NUM) {
+ hw_ip = ring->funcs->type;
+ num_sched = &adev->gpu_sched[hw_ip][hw_prio].num_scheds;
+ adev->gpu_sched[hw_ip][hw_prio].sched[(*num_sched)++] =
+@@ -475,8 +475,9 @@ static ssize_t amdgpu_debugfs_ring_read(struct file *f, char __user *buf,
+ size_t size, loff_t *pos)
+ {
+ struct amdgpu_ring *ring = file_inode(f)->i_private;
+- int r, i;
+ uint32_t value, result, early[3];
++ loff_t i;
++ int r;
+
+ if (*pos & 3 || size & 3)
+ return -EINVAL;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c
+index 8ed0e073656f8..41ebe690eeffa 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_securedisplay.c
+@@ -135,6 +135,10 @@ static ssize_t amdgpu_securedisplay_debugfs_write(struct file *f, const char __u
+ mutex_unlock(&psp->securedisplay_context.mutex);
+ break;
+ case 2:
++ if (size < 3 || phy_id >= TA_SECUREDISPLAY_MAX_PHY) {
++ dev_err(adev->dev, "Invalid input: %s\n", str);
++ return -EINVAL;
++ }
+ mutex_lock(&psp->securedisplay_context.mutex);
+ psp_prep_securedisplay_cmd_buf(psp, &securedisplay_cmd,
+ TA_SECUREDISPLAY_COMMAND__SEND_ROI_CRC);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+index 972a58f0f4924..2359d1d602751 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+@@ -395,6 +395,8 @@ static void amdgpu_virt_add_bad_page(struct amdgpu_device *adev,
+ else
+ vram_usage_va = adev->mman.drv_vram_usage_va;
+
++ memset(&bp, 0, sizeof(bp));
++
+ if (bp_block_size) {
+ bp_cnt = bp_block_size / sizeof(uint64_t);
+ for (bp_idx = 0; bp_idx < bp_cnt; bp_idx++) {
+@@ -583,7 +585,7 @@ static int amdgpu_virt_write_vf2pf_data(struct amdgpu_device *adev)
+ }
+ vf2pf_info->checksum =
+ amd_sriov_msg_checksum(
+- vf2pf_info, vf2pf_info->header.size, 0, 0);
++ vf2pf_info, sizeof(*vf2pf_info), 0, 0);
+
+ return 0;
+ }
+@@ -600,7 +602,7 @@ static void amdgpu_virt_update_vf2pf_work_item(struct work_struct *work)
+ amdgpu_sriov_runtime(adev) && !amdgpu_in_reset(adev)) {
+ amdgpu_ras_set_fed(adev, true);
+ if (amdgpu_reset_domain_schedule(adev->reset_domain,
+- &adev->virt.flr_work))
++ &adev->kfd.reset_work))
+ return;
+ else
+ dev_err(adev->dev, "Failed to queue work! at %s", __func__);
+@@ -975,6 +977,9 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
+ return 0;
+ }
+
++ if (amdgpu_device_skip_hw_access(adev))
++ return 0;
++
+ reg_access_ctrl = &adev->gfx.rlc.reg_access_ctrl[xcc_id];
+ scratch_reg0 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg0;
+ scratch_reg1 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg1;
+@@ -1051,6 +1056,9 @@ void amdgpu_sriov_wreg(struct amdgpu_device *adev,
+ {
+ u32 rlcg_flag;
+
++ if (amdgpu_device_skip_hw_access(adev))
++ return;
++
+ if (!amdgpu_sriov_runtime(adev) &&
+ amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags, hwip, true, &rlcg_flag)) {
+ amdgpu_virt_rlcg_reg_rw(adev, offset, value, rlcg_flag, xcc_id);
+@@ -1068,6 +1076,9 @@ u32 amdgpu_sriov_rreg(struct amdgpu_device *adev,
+ {
+ u32 rlcg_flag;
+
++ if (amdgpu_device_skip_hw_access(adev))
++ return 0;
++
+ if (!amdgpu_sriov_runtime(adev) &&
+ amdgpu_virt_get_rlcg_reg_access_flag(adev, acc_flags, hwip, false, &rlcg_flag))
+ return amdgpu_virt_rlcg_reg_rw(adev, offset, 0, rlcg_flag, xcc_id);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+index 6c30eceec8965..f91cc149d06c8 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vram_mgr.c
+@@ -31,6 +31,8 @@
+ #include "amdgpu_atomfirmware.h"
+ #include "atom.h"
+
++#define AMDGPU_MAX_SG_SEGMENT_SIZE (2UL << 30)
++
+ struct amdgpu_vram_reservation {
+ u64 start;
+ u64 size;
+@@ -518,9 +520,7 @@ static int amdgpu_vram_mgr_new(struct ttm_resource_manager *man,
+ else
+ min_block_size = mgr->default_page_size;
+
+- /* Limit maximum size to 2GiB due to SG table limitations */
+- size = min(remaining_size, 2ULL << 30);
+-
++ size = remaining_size;
+ if ((size >= (u64)pages_per_block << PAGE_SHIFT) &&
+ !(size & (((u64)pages_per_block << PAGE_SHIFT) - 1)))
+ min_block_size = (u64)pages_per_block << PAGE_SHIFT;
+@@ -660,7 +660,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
+ amdgpu_res_first(res, offset, length, &cursor);
+ while (cursor.remaining) {
+ num_entries++;
+- amdgpu_res_next(&cursor, cursor.size);
++ amdgpu_res_next(&cursor, min(cursor.size, AMDGPU_MAX_SG_SEGMENT_SIZE));
+ }
+
+ r = sg_alloc_table(*sgt, num_entries, GFP_KERNEL);
+@@ -680,7 +680,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
+ amdgpu_res_first(res, offset, length, &cursor);
+ for_each_sgtable_sg((*sgt), sg, i) {
+ phys_addr_t phys = cursor.start + adev->gmc.aper_base;
+- size_t size = cursor.size;
++ unsigned long size = min(cursor.size, AMDGPU_MAX_SG_SEGMENT_SIZE);
+ dma_addr_t addr;
+
+ addr = dma_map_resource(dev, phys, size, dir,
+@@ -693,7 +693,7 @@ int amdgpu_vram_mgr_alloc_sgt(struct amdgpu_device *adev,
+ sg_dma_address(sg) = addr;
+ sg_dma_len(sg) = size;
+
+- amdgpu_res_next(&cursor, cursor.size);
++ amdgpu_res_next(&cursor, size);
+ }
+
+ return 0;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+index dd2ec48cf5c26..4a14f9c1bfe89 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_xgmi.c
+@@ -434,6 +434,9 @@ static ssize_t amdgpu_xgmi_show_connected_port_num(struct device *dev,
+ }
+ }
+
++ if (i == top->num_nodes)
++ return -EINVAL;
++
+ for (i = 0; i < top->num_nodes; i++) {
+ for (j = 0; j < top->nodes[i].num_links; j++)
+ /* node id in sysfs starts from 1 rather than 0 so +1 here */
+diff --git a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+index d4e2aed2efa33..2c9a0aa41e2d5 100644
+--- a/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
++++ b/drivers/gpu/drm/amd/amdgpu/aqua_vanjaram.c
+@@ -501,6 +501,12 @@ static int aqua_vanjaram_switch_partition_mode(struct amdgpu_xcp_mgr *xcp_mgr,
+
+ if (mode == AMDGPU_AUTO_COMPUTE_PARTITION_MODE) {
+ mode = __aqua_vanjaram_get_auto_mode(xcp_mgr);
++ if (mode == AMDGPU_UNKNOWN_COMPUTE_PARTITION_MODE) {
++ dev_err(adev->dev,
++ "Invalid config, no compatible compute partition mode found, available memory partitions: %d",
++ adev->gmc.num_mem_partitions);
++ return -EINVAL;
++ }
+ } else if (!__aqua_vanjaram_is_valid_mode(xcp_mgr, mode)) {
+ dev_err(adev->dev,
+ "Invalid compute partition mode requested, requested: %s, available memory partitions: %d",
+diff --git a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
+index 5dfab80ffff21..cd298556f7a60 100644
+--- a/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
++++ b/drivers/gpu/drm/amd/amdgpu/df_v1_7.c
+@@ -70,6 +70,8 @@ static u32 df_v1_7_get_hbm_channel_number(struct amdgpu_device *adev)
+ int fb_channel_number;
+
+ fb_channel_number = adev->df.funcs->get_fb_channel_number(adev);
++ if (fb_channel_number >= ARRAY_SIZE(df_v1_7_channel_number))
++ fb_channel_number = 0;
+
+ return df_v1_7_channel_number[fb_channel_number];
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+index da6bb9022b804..4c8f9772437b5 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_5.c
+@@ -187,7 +187,7 @@ static int jpeg_v4_0_5_hw_init(void *handle)
+ {
+ struct amdgpu_device *adev = (struct amdgpu_device *)handle;
+ struct amdgpu_ring *ring;
+- int r, i;
++ int i, r = 0;
+
+ // TODO: Enable ring test with DPG support
+ if (adev->pg_flags & AMD_PG_SUPPORT_JPEG_DPG) {
+diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
+index 92432cd2c0c7b..9689e2b5d4e51 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
++++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v1_7.c
+@@ -544,7 +544,7 @@ static int mmhub_v1_7_set_clockgating(struct amdgpu_device *adev,
+
+ static void mmhub_v1_7_get_clockgating(struct amdgpu_device *adev, u64 *flags)
+ {
+- int data, data1;
++ u32 data, data1;
+
+ if (amdgpu_sriov_vf(adev))
+ *flags = 0;
+diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+index 02fd45261399c..a0cc8e218ca1e 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v2_0.c
+@@ -671,7 +671,7 @@ static int mmhub_v2_0_set_clockgating(struct amdgpu_device *adev,
+
+ static void mmhub_v2_0_get_clockgating(struct amdgpu_device *adev, u64 *flags)
+ {
+- int data, data1;
++ u32 data, data1;
+
+ if (amdgpu_sriov_vf(adev))
+ *flags = 0;
+diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
+index 238ea40c24500..d7c3178254973 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
++++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v3_3.c
+@@ -560,7 +560,7 @@ static int mmhub_v3_3_set_clockgating(struct amdgpu_device *adev,
+
+ static void mmhub_v3_3_get_clockgating(struct amdgpu_device *adev, u64 *flags)
+ {
+- int data;
++ u32 data;
+
+ if (amdgpu_sriov_vf(adev))
+ *flags = 0;
+diff --git a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+index 1b7da4aff2b8f..ff1b58e446892 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
++++ b/drivers/gpu/drm/amd/amdgpu/mmhub_v9_4.c
+@@ -657,7 +657,7 @@ static int mmhub_v9_4_set_clockgating(struct amdgpu_device *adev,
+
+ static void mmhub_v9_4_get_clockgating(struct amdgpu_device *adev, u64 *flags)
+ {
+- int data, data1;
++ u32 data, data1;
+
+ if (amdgpu_sriov_vf(adev))
+ *flags = 0;
+diff --git a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+index 19986ff6a48d7..e326d6f06ca92 100644
+--- a/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
++++ b/drivers/gpu/drm/amd/amdgpu/nbio_v7_4.c
+@@ -387,7 +387,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
+ else
+ WREG32_SOC15(NBIO, 0, mmBIF_DOORBELL_INT_CNTL, bif_doorbell_intr_cntl);
+
+- if (!ras->disable_ras_err_cnt_harvest) {
++ if (ras && !ras->disable_ras_err_cnt_harvest && obj) {
+ /*
+ * clear error status after ras_controller_intr
+ * according to hw team and count ue number
+@@ -418,6 +418,7 @@ static void nbio_v7_4_handle_ras_controller_intr_no_bifring(struct amdgpu_device
+ /* ras_controller_int is dedicated for nbif ras error,
+ * not the global interrupt for sync flood
+ */
++ amdgpu_ras_set_fed(adev, true);
+ amdgpu_ras_reset_gpu(adev);
+ }
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+index fbd3f7a582c12..55465b8a3df6c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+@@ -229,8 +229,6 @@ static int vcn_v5_0_0_hw_fini(void *handle)
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
+ if (adev->vcn.harvest_config & (1 << i))
+ continue;
+-
+- amdgpu_irq_put(adev, &adev->vcn.inst[i].irq, 0);
+ }
+
+ return 0;
+@@ -1232,22 +1230,6 @@ static int vcn_v5_0_0_set_powergating_state(void *handle, enum amd_powergating_s
+ return ret;
+ }
+
+-/**
+- * vcn_v5_0_0_set_interrupt_state - set VCN block interrupt state
+- *
+- * @adev: amdgpu_device pointer
+- * @source: interrupt sources
+- * @type: interrupt types
+- * @state: interrupt states
+- *
+- * Set VCN block interrupt state
+- */
+-static int vcn_v5_0_0_set_interrupt_state(struct amdgpu_device *adev, struct amdgpu_irq_src *source,
+- unsigned type, enum amdgpu_interrupt_state state)
+-{
+- return 0;
+-}
+-
+ /**
+ * vcn_v5_0_0_process_interrupt - process VCN block interrupt
+ *
+@@ -1293,7 +1275,6 @@ static int vcn_v5_0_0_process_interrupt(struct amdgpu_device *adev, struct amdgp
+ }
+
+ static const struct amdgpu_irq_src_funcs vcn_v5_0_0_irq_funcs = {
+- .set = vcn_v5_0_0_set_interrupt_state,
+ .process = vcn_v5_0_0_process_interrupt,
+ };
+
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
+index 300634b9f6683..a8ca7ecb6d271 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_crat.h
+@@ -42,8 +42,6 @@
+ #define CRAT_OEMTABLEID_LENGTH 8
+ #define CRAT_RESERVED_LENGTH 6
+
+-#define CRAT_OEMID_64BIT_MASK ((1ULL << (CRAT_OEMID_LENGTH * 8)) - 1)
+-
+ /* Compute Unit flags */
+ #define COMPUTE_UNIT_CPU (1 << 0) /* Create Virtual CRAT for CPU */
+ #define COMPUTE_UNIT_GPU (1 << 1) /* Create Virtual CRAT for GPU */
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+index d889e3545120a..6c2f6a26c479c 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_debug.c
+@@ -103,7 +103,8 @@ void debug_event_write_work_handler(struct work_struct *work)
+ struct kfd_process,
+ debug_event_workarea);
+
+- kernel_write(process->dbg_ev_file, &write_data, 1, &pos);
++ if (process->debug_trap_enabled && process->dbg_ev_file)
++ kernel_write(process->dbg_ev_file, &write_data, 1, &pos);
+ }
+
+ /* update process/device/queue exception status, write to descriptor
+@@ -645,6 +646,7 @@ int kfd_dbg_trap_disable(struct kfd_process *target)
+ else if (target->runtime_info.runtime_state != DEBUG_RUNTIME_STATE_DISABLED)
+ target->runtime_info.runtime_state = DEBUG_RUNTIME_STATE_ENABLED;
+
++ cancel_work_sync(&target->debug_event_workarea);
+ fput(target->dbg_ev_file);
+ target->dbg_ev_file = NULL;
+
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+index e1c21d2506112..78dde62fb04ad 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_int_process_v9.c
+@@ -164,7 +164,7 @@ static void event_interrupt_poison_consumption_v9(struct kfd_node *dev,
+ case SOC15_IH_CLIENTID_SE3SH:
+ case SOC15_IH_CLIENTID_UTCL2:
+ block = AMDGPU_RAS_BLOCK__GFX;
+- reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET;
++ reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET;
+ break;
+ case SOC15_IH_CLIENTID_VMC:
+ case SOC15_IH_CLIENTID_VMC1:
+@@ -177,7 +177,7 @@ static void event_interrupt_poison_consumption_v9(struct kfd_node *dev,
+ case SOC15_IH_CLIENTID_SDMA3:
+ case SOC15_IH_CLIENTID_SDMA4:
+ block = AMDGPU_RAS_BLOCK__SDMA;
+- reset = AMDGPU_RAS_GPU_RESET_MODE2_RESET;
++ reset = AMDGPU_RAS_GPU_RESET_MODE1_RESET;
+ break;
+ default:
+ dev_warn(dev->adev->dev,
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+index 4858112f9a53b..a5bdc3258ae54 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_process_queue_manager.c
+@@ -28,6 +28,7 @@
+ #include "kfd_priv.h"
+ #include "kfd_kernel_queue.h"
+ #include "amdgpu_amdkfd.h"
++#include "amdgpu_reset.h"
+
+ static inline struct process_queue_node *get_queue_by_qid(
+ struct process_queue_manager *pqm, unsigned int qid)
+@@ -87,8 +88,12 @@ void kfd_process_dequeue_from_device(struct kfd_process_device *pdd)
+ return;
+
+ dev->dqm->ops.process_termination(dev->dqm, &pdd->qpd);
+- if (dev->kfd->shared_resources.enable_mes)
+- amdgpu_mes_flush_shader_debugger(dev->adev, pdd->proc_ctx_gpu_addr);
++ if (dev->kfd->shared_resources.enable_mes &&
++ down_read_trylock(&dev->adev->reset_domain->sem)) {
++ amdgpu_mes_flush_shader_debugger(dev->adev,
++ pdd->proc_ctx_gpu_addr);
++ up_read(&dev->adev->reset_domain->sem);
++ }
+ pdd->already_dequeued = true;
+ }
+
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+index bc9eb847ecfe7..1d271ecc386f0 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.c
+@@ -958,8 +958,7 @@ static void kfd_update_system_properties(void)
+ dev = list_last_entry(&topology_device_list,
+ struct kfd_topology_device, list);
+ if (dev) {
+- sys_props.platform_id =
+- (*((uint64_t *)dev->oem_id)) & CRAT_OEMID_64BIT_MASK;
++ sys_props.platform_id = dev->oem_id64;
+ sys_props.platform_oem = *((uint64_t *)dev->oem_table_id);
+ sys_props.platform_rev = dev->oem_revision;
+ }
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+index 27386ce9a021d..2d1c9d771bef2 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_topology.h
+@@ -154,7 +154,10 @@ struct kfd_topology_device {
+ struct attribute attr_gpuid;
+ struct attribute attr_name;
+ struct attribute attr_props;
+- uint8_t oem_id[CRAT_OEMID_LENGTH];
++ union {
++ uint8_t oem_id[CRAT_OEMID_LENGTH];
++ uint64_t oem_id64;
++ };
+ uint8_t oem_table_id[CRAT_OEMTABLEID_LENGTH];
+ uint32_t oem_revision;
+ };
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+index 8d4ad15b8e171..382a41c5b5152 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+@@ -594,12 +594,14 @@ static void dm_crtc_high_irq(void *interrupt_params)
+ if (!acrtc)
+ return;
+
+- if (acrtc->wb_pending) {
+- if (acrtc->wb_conn) {
+- spin_lock_irqsave(&acrtc->wb_conn->job_lock, flags);
++ if (acrtc->wb_conn) {
++ spin_lock_irqsave(&acrtc->wb_conn->job_lock, flags);
++
++ if (acrtc->wb_pending) {
+ job = list_first_entry_or_null(&acrtc->wb_conn->job_queue,
+ struct drm_writeback_job,
+ list_entry);
++ acrtc->wb_pending = false;
+ spin_unlock_irqrestore(&acrtc->wb_conn->job_lock, flags);
+
+ if (job) {
+@@ -617,8 +619,7 @@ static void dm_crtc_high_irq(void *interrupt_params)
+ acrtc->dm_irq_params.stream, 0);
+ }
+ } else
+- DRM_ERROR("%s: no amdgpu_crtc wb_conn\n", __func__);
+- acrtc->wb_pending = false;
++ spin_unlock_irqrestore(&acrtc->wb_conn->job_lock, flags);
+ }
+
+ vrr_active = amdgpu_dm_crtc_vrr_active_irq(acrtc);
+@@ -4129,8 +4130,11 @@ static int amdgpu_dm_mode_config_init(struct amdgpu_device *adev)
+ }
+
+ #ifdef AMD_PRIVATE_COLOR
+- if (amdgpu_dm_create_color_properties(adev))
++ if (amdgpu_dm_create_color_properties(adev)) {
++ dc_state_release(state->context);
++ kfree(state);
+ return -ENOMEM;
++ }
+ #endif
+
+ r = amdgpu_dm_audio_init(adev);
+@@ -4466,7 +4470,10 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
+
+ /* There is one primary plane per CRTC */
+ primary_planes = dm->dc->caps.max_streams;
+- ASSERT(primary_planes <= AMDGPU_MAX_PLANES);
++ if (primary_planes > AMDGPU_MAX_PLANES) {
++ DRM_ERROR("DM: Plane nums out of 6 planes\n");
++ return -EINVAL;
++ }
+
+ /*
+ * Initialize primary planes, implicit planes for legacy IOCTLS.
+@@ -4584,17 +4591,17 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
+ }
+ }
+
++ if (link_cnt > MAX_LINKS) {
++ DRM_ERROR(
++ "KMS: Cannot support more than %d display indexes\n",
++ MAX_LINKS);
++ goto fail;
++ }
++
+ /* loops over all connectors on the board */
+ for (i = 0; i < link_cnt; i++) {
+ struct dc_link *link = NULL;
+
+- if (i > AMDGPU_DM_MAX_DISPLAY_INDEX) {
+- DRM_ERROR(
+- "KMS: Cannot support more than %d display indexes\n",
+- AMDGPU_DM_MAX_DISPLAY_INDEX);
+- continue;
+- }
+-
+ link = dc_get_link_at_index(dm->dc, i);
+
+ if (link->connector_signal == SIGNAL_TYPE_VIRTUAL) {
+@@ -8639,15 +8646,13 @@ static void amdgpu_dm_commit_planes(struct drm_atomic_state *state,
+ bundle->stream_update.vrr_infopacket =
+ &acrtc_state->stream->vrr_infopacket;
+ }
+- } else if (cursor_update && acrtc_state->active_planes > 0 &&
+- acrtc_attach->base.state->event) {
+- drm_crtc_vblank_get(pcrtc);
+-
++ } else if (cursor_update && acrtc_state->active_planes > 0) {
+ spin_lock_irqsave(&pcrtc->dev->event_lock, flags);
+-
+- acrtc_attach->event = acrtc_attach->base.state->event;
+- acrtc_attach->base.state->event = NULL;
+-
++ if (acrtc_attach->base.state->event) {
++ drm_crtc_vblank_get(pcrtc);
++ acrtc_attach->event = acrtc_attach->base.state->event;
++ acrtc_attach->base.state->event = NULL;
++ }
+ spin_unlock_irqrestore(&pcrtc->dev->event_lock, flags);
+ }
+
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+index 09519b7abf67b..5c9d32dff8538 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.h
+@@ -50,7 +50,7 @@
+
+ #define AMDGPU_DM_MAX_NUM_EDP 2
+
+-#define AMDGPU_DMUB_NOTIFICATION_MAX 5
++#define AMDGPU_DMUB_NOTIFICATION_MAX 6
+
+ #define HDMI_AMD_VENDOR_SPECIFIC_DATA_BLOCK_IEEE_REGISTRATION_ID 0x00001A
+ #define AMD_VSDB_VERSION_3_FEATURECAP_REPLAYMODE 0x40
+diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+index bc16db69a6636..3bacf470f7c5b 100644
+--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
++++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser.c
+@@ -665,6 +665,9 @@ static enum bp_result get_ss_info_v3_1(
+ ss_table_header_include = ((ATOM_ASIC_INTERNAL_SS_INFO_V3 *) bios_get_image(&bp->base,
+ DATA_TABLES(ASIC_InternalSS_Info),
+ struct_size(ss_table_header_include, asSpreadSpectrum, 1)));
++ if (!ss_table_header_include)
++ return BP_RESULT_UNSUPPORTED;
++
+ table_size =
+ (le16_to_cpu(ss_table_header_include->sHeader.usStructureSize)
+ - sizeof(ATOM_COMMON_TABLE_HEADER))
+@@ -1034,6 +1037,8 @@ static enum bp_result get_ss_info_from_internal_ss_info_tbl_V2_1(
+ &bp->base,
+ DATA_TABLES(ASIC_InternalSS_Info),
+ struct_size(header, asSpreadSpectrum, 1)));
++ if (!header)
++ return result;
+
+ memset(info, 0, sizeof(struct spread_spectrum_info));
+
+@@ -1107,6 +1112,8 @@ static enum bp_result get_ss_info_from_ss_info_table(
+ get_atom_data_table_revision(header, &revision);
+
+ tbl = GET_IMAGE(ATOM_SPREAD_SPECTRUM_INFO, DATA_TABLES(SS_Info));
++ if (!tbl)
++ return result;
+
+ if (1 != revision.major || 2 > revision.minor)
+ return result;
+@@ -1634,6 +1641,8 @@ static uint32_t get_ss_entry_number_from_ss_info_tbl(
+
+ tbl = GET_IMAGE(ATOM_SPREAD_SPECTRUM_INFO,
+ DATA_TABLES(SS_Info));
++ if (!tbl)
++ return number;
+
+ if (1 != revision.major || 2 > revision.minor)
+ return number;
+@@ -1716,6 +1725,8 @@ static uint32_t get_ss_entry_number_from_internal_ss_info_tbl_v2_1(
+ &bp->base,
+ DATA_TABLES(ASIC_InternalSS_Info),
+ struct_size(header_include, asSpreadSpectrum, 1)));
++ if (!header_include)
++ return 0;
+
+ size = (le16_to_cpu(header_include->sHeader.usStructureSize)
+ - sizeof(ATOM_COMMON_TABLE_HEADER))
+@@ -1755,6 +1766,9 @@ static uint32_t get_ss_entry_number_from_internal_ss_info_tbl_V3_1(
+ header_include = ((ATOM_ASIC_INTERNAL_SS_INFO_V3 *) bios_get_image(&bp->base,
+ DATA_TABLES(ASIC_InternalSS_Info),
+ struct_size(header_include, asSpreadSpectrum, 1)));
++ if (!header_include)
++ return number;
++
+ size = (le16_to_cpu(header_include->sHeader.usStructureSize) -
+ sizeof(ATOM_COMMON_TABLE_HEADER)) /
+ sizeof(ATOM_ASIC_SS_ASSIGNMENT_V3);
+@@ -2551,8 +2565,8 @@ static enum bp_result construct_integrated_info(
+
+ /* Sort voltage table from low to high*/
+ if (result == BP_RESULT_OK) {
+- uint32_t i;
+- uint32_t j;
++ int32_t i;
++ int32_t j;
+
+ for (i = 1; i < NUMBER_OF_DISP_CLK_VOLTAGE; ++i) {
+ for (j = i; j > 0; --j) {
+diff --git a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+index 9fe0020bcb9c2..c8c8587a059d9 100644
+--- a/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
++++ b/drivers/gpu/drm/amd/display/dc/bios/bios_parser2.c
+@@ -2920,8 +2920,11 @@ static enum bp_result construct_integrated_info(
+ struct atom_common_table_header *header;
+ struct atom_data_revision revision;
+
+- uint32_t i;
+- uint32_t j;
++ int32_t i;
++ int32_t j;
++
++ if (!info)
++ return result;
+
+ if (info && DATA_TABLES(integratedsysteminfo)) {
+ header = GET_IMAGE(struct atom_common_table_header,
+diff --git a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+index 5ef0879f6ad9c..aea4bb46856ef 100644
+--- a/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
++++ b/drivers/gpu/drm/amd/display/dc/clk_mgr/dcn21/rn_clk_mgr.c
+@@ -484,7 +484,8 @@ static void build_watermark_ranges(struct clk_bw_params *bw_params, struct pp_sm
+ ranges->reader_wm_sets[num_valid_sets].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+
+ /* Modify previous watermark range to cover up to max */
+- ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
++ if (num_valid_sets > 0)
++ ranges->reader_wm_sets[num_valid_sets - 1].max_fill_clk_mhz = PP_SMU_WM_SET_RANGE_CLK_UNCONSTRAINED_MAX;
+ }
+ num_valid_sets++;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc.c b/drivers/gpu/drm/amd/display/dc/core/dc.c
+index 236876d95185b..da237f718dbdd 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc.c
+@@ -1421,6 +1421,7 @@ struct dc *dc_create(const struct dc_init_data *init_params)
+ return NULL;
+
+ if (init_params->dce_environment == DCE_ENV_VIRTUAL_HW) {
++ dc->caps.linear_pitch_alignment = 64;
+ if (!dc_construct_ctx(dc, init_params))
+ goto destruct_dc;
+ } else {
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c
+index c6c35037bdb8b..dfdfe22d9e851 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc_link_exports.c
+@@ -37,6 +37,9 @@
+ #include "dce/dce_i2c.h"
+ struct dc_link *dc_get_link_at_index(struct dc *dc, uint32_t link_index)
+ {
++ if (link_index >= MAX_LINKS)
++ return NULL;
++
+ return dc->links[link_index];
+ }
+
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+index 8ed599324693e..786b56e96a816 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+@@ -2283,6 +2283,9 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state)
+ state->stream_status[stream_idx].mall_stream_config.paired_stream);
+ otg_master = resource_get_otg_master_for_stream(
+ &state->res_ctx, state->streams[phantom_stream_idx]);
++ if (!otg_master)
++ continue;
++
+ resource_log_pipe_for_stream(dc, state, otg_master, stream_idx);
+ }
+ }
+@@ -3508,7 +3511,7 @@ static bool acquire_otg_master_pipe_for_stream(
+ if (pool->dpps[pipe_idx])
+ pipe_ctx->plane_res.mpcc_inst = pool->dpps[pipe_idx]->inst;
+
+- if (pipe_idx >= pool->timing_generator_count) {
++ if (pipe_idx >= pool->timing_generator_count && pool->timing_generator_count != 0) {
+ int tg_inst = pool->timing_generator_count - 1;
+
+ pipe_ctx->stream_res.tg = pool->timing_generators[tg_inst];
+@@ -4669,6 +4672,9 @@ void resource_build_bit_depth_reduction_params(struct dc_stream_state *stream,
+
+ enum dc_status dc_validate_stream(struct dc *dc, struct dc_stream_state *stream)
+ {
++ if (dc == NULL || stream == NULL)
++ return DC_ERROR_UNEXPECTED;
++
+ struct dc_link *link = stream->link;
+ struct timing_generator *tg = dc->res_pool->timing_generators[0];
+ enum dc_status res = DC_OK;
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+index 52a1cfc5feed8..502740f6fb2ce 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+@@ -191,7 +191,7 @@ static void init_state(struct dc *dc, struct dc_state *state)
+ struct dc_state *dc_state_create(struct dc *dc, struct dc_state_create_params *params)
+ {
+ #ifdef CONFIG_DRM_AMD_DC_FP
+- struct dml2_configuration_options *dml2_opt = &dc->dml2_options;
++ struct dml2_configuration_options dml2_opt = dc->dml2_options;
+ #endif
+ struct dc_state *state = kvzalloc(sizeof(struct dc_state),
+ GFP_KERNEL);
+@@ -205,11 +205,11 @@ struct dc_state *dc_state_create(struct dc *dc, struct dc_state_create_params *p
+
+ #ifdef CONFIG_DRM_AMD_DC_FP
+ if (dc->debug.using_dml2) {
+- dml2_opt->use_clock_dc_limits = false;
+- dml2_create(dc, dml2_opt, &state->bw_ctx.dml2);
++ dml2_opt.use_clock_dc_limits = false;
++ dml2_create(dc, &dml2_opt, &state->bw_ctx.dml2);
+
+- dml2_opt->use_clock_dc_limits = true;
+- dml2_create(dc, dml2_opt, &state->bw_ctx.dml2_dc_power_source);
++ dml2_opt.use_clock_dc_limits = true;
++ dml2_create(dc, &dml2_opt, &state->bw_ctx.dml2_dc_power_source);
+ }
+ #endif
+
+diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c
+index b851fc65f5b7c..5c2d6642633d9 100644
+--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c
++++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_abm_lcd.c
+@@ -258,7 +258,7 @@ bool dmub_abm_set_pipe(struct abm *abm,
+ {
+ union dmub_rb_cmd cmd;
+ struct dc_context *dc = abm->ctx;
+- uint32_t ramping_boundary = 0xFFFF;
++ uint8_t ramping_boundary = 0xFF;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.abm_set_pipe.header.type = DMUB_CMD__ABM;
+diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+index 09cf54586fd5d..424669632b3b9 100644
+--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
++++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+@@ -102,7 +102,8 @@ static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait,
+ break;
+ }
+
+- fsleep(500);
++ /* must *not* be fsleep - this can be called from high irq levels */
++ udelay(500);
+ }
+
+ /* assert if max retry hit */
+diff --git a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c
+index 994fb732a7cb7..a0d437f0ce2ba 100644
+--- a/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c
++++ b/drivers/gpu/drm/amd/display/dc/dcn20/dcn20_dwb_scl.c
+@@ -690,6 +690,9 @@ static void wbscl_set_scaler_filter(
+ int pair;
+ uint16_t odd_coef, even_coef;
+
++ if (!filter)
++ return;
++
+ for (phase = 0; phase < (NUM_PHASES / 2 + 1); phase++) {
+ for (pair = 0; pair < tap_pairs; pair++) {
+ even_coef = filter[phase * taps + 2 * pair];
+diff --git a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
+index 58dd3c5bbff09..4677eb485f945 100644
+--- a/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
++++ b/drivers/gpu/drm/amd/display/dc/dcn35/dcn35_dccg.c
+@@ -940,7 +940,7 @@ static uint8_t dccg35_get_other_enabled_symclk_fe(struct dccg *dccg, uint32_t st
+ /* for DPMST, this backend could be used by multiple front end.
+ only disable the backend if this stream_enc_ins is the last active stream enc connected to this back_end*/
+ uint8_t i;
+- for (i = 0; i != link_enc_inst && i < sizeof(fe_clk_en); i++) {
++ for (i = 0; i != link_enc_inst && i < ARRAY_SIZE(fe_clk_en); i++) {
+ if (fe_clk_en[i] && be_clk_sel[i] == link_enc_inst)
+ num_enabled_symclk_fe++;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c
+index 0c4a8fe8e5ca6..f1cde1e4265f3 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c
++++ b/drivers/gpu/drm/amd/display/dc/dml/calcs/dcn_calcs.c
+@@ -1453,10 +1453,9 @@ void dcn_bw_update_from_pplib_fclks(
+ ASSERT(fclks->num_levels);
+
+ vmin0p65_idx = 0;
+- vmid0p72_idx = fclks->num_levels -
+- (fclks->num_levels > 2 ? 3 : (fclks->num_levels > 1 ? 2 : 1));
+- vnom0p8_idx = fclks->num_levels - (fclks->num_levels > 1 ? 2 : 1);
+- vmax0p9_idx = fclks->num_levels - 1;
++ vmid0p72_idx = fclks->num_levels > 2 ? fclks->num_levels - 3 : 0;
++ vnom0p8_idx = fclks->num_levels > 1 ? fclks->num_levels - 2 : 0;
++ vmax0p9_idx = fclks->num_levels > 0 ? fclks->num_levels - 1 : 0;
+
+ dc->dcn_soc->fabric_and_dram_bandwidth_vmin0p65 =
+ 32 * (fclks->data[vmin0p65_idx].clocks_in_khz / 1000.0) / 1000.0;
+diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
+index e2bcd205aa936..8da97a96b1ceb 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
++++ b/drivers/gpu/drm/amd/display/dc/dml/dcn302/dcn302_fpu.c
+@@ -304,6 +304,16 @@ void dcn302_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p
+ dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
+ }
+
++ /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL].
++ * MAX_NUM_DPM_LVL is 8.
++ * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES].
++ * DC__VOLTAGE_STATES is 40.
++ */
++ if (num_states > MAX_NUM_DPM_LVL) {
++ ASSERT(0);
++ return;
++ }
++
+ dcn3_02_soc.num_states = num_states;
+ for (i = 0; i < dcn3_02_soc.num_states; i++) {
+ dcn3_02_soc.clock_limits[i].state = i;
+diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c
+index 3f02bb806d421..e968870a4b810 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c
++++ b/drivers/gpu/drm/amd/display/dc/dml/dcn303/dcn303_fpu.c
+@@ -310,6 +310,16 @@ void dcn303_fpu_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_p
+ dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
+ }
+
++ /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL].
++ * MAX_NUM_DPM_LVL is 8.
++ * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES].
++ * DC__VOLTAGE_STATES is 40.
++ */
++ if (num_states > MAX_NUM_DPM_LVL) {
++ ASSERT(0);
++ return;
++ }
++
+ dcn3_03_soc.num_states = num_states;
+ for (i = 0; i < dcn3_03_soc.num_states; i++) {
+ dcn3_03_soc.clock_limits[i].state = i;
+diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+index f6fe0a64beacf..ebcf5ece209a4 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
++++ b/drivers/gpu/drm/amd/display/dc/dml/dcn32/dcn32_fpu.c
+@@ -3232,6 +3232,16 @@ void dcn32_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_pa
+ dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
+ }
+
++ /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL].
++ * MAX_NUM_DPM_LVL is 8.
++ * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES].
++ * DC__VOLTAGE_STATES is 40.
++ */
++ if (num_states > MAX_NUM_DPM_LVL) {
++ ASSERT(0);
++ return;
++ }
++
+ dcn3_2_soc.num_states = num_states;
+ for (i = 0; i < dcn3_2_soc.num_states; i++) {
+ dcn3_2_soc.clock_limits[i].state = i;
+diff --git a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+index ff4d795c79664..4297402bdab39 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
++++ b/drivers/gpu/drm/amd/display/dc/dml/dcn321/dcn321_fpu.c
+@@ -803,6 +803,16 @@ void dcn321_update_bw_bounding_box_fpu(struct dc *dc, struct clk_bw_params *bw_p
+ dram_speed_mts[num_states++] = bw_params->clk_table.entries[j++].memclk_mhz * 16;
+ }
+
++ /* bw_params->clk_table.entries[MAX_NUM_DPM_LVL].
++ * MAX_NUM_DPM_LVL is 8.
++ * dcn3_02_soc.clock_limits[DC__VOLTAGE_STATES].
++ * DC__VOLTAGE_STATES is 40.
++ */
++ if (num_states > MAX_NUM_DPM_LVL) {
++ ASSERT(0);
++ return;
++ }
++
+ dcn3_21_soc.num_states = num_states;
+ for (i = 0; i < dcn3_21_soc.num_states; i++) {
+ dcn3_21_soc.clock_limits[i].state = i;
+diff --git a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+index 9a3ded3111952..85453bbb4f9b1 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
++++ b/drivers/gpu/drm/amd/display/dc/dml/display_mode_vba.c
+@@ -1099,8 +1099,13 @@ void ModeSupportAndSystemConfiguration(struct display_mode_lib *mode_lib)
+
+ // Total Available Pipes Support Check
+ for (k = 0; k < mode_lib->vba.NumberOfActivePlanes; ++k) {
+- total_pipes += mode_lib->vba.DPPPerPlane[k];
+ pipe_idx = get_pipe_idx(mode_lib, k);
++ if (pipe_idx == -1) {
++ ASSERT(0);
++ continue; // skip inactive planes
++ }
++ total_pipes += mode_lib->vba.DPPPerPlane[k];
++
+ if (mode_lib->vba.cache_pipes[pipe_idx].clks_cfg.dppclk_mhz > 0.0)
+ mode_lib->vba.DPPCLK[k] = mode_lib->vba.cache_pipes[pipe_idx].clks_cfg.dppclk_mhz;
+ else
+diff --git a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
+index 663c17f52779c..f344478e9bd47 100644
+--- a/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
++++ b/drivers/gpu/drm/amd/display/dc/gpio/gpio_service.c
+@@ -56,7 +56,7 @@ struct gpio_service *dal_gpio_service_create(
+ struct dc_context *ctx)
+ {
+ struct gpio_service *service;
+- uint32_t index_of_id;
++ int32_t index_of_id;
+
+ service = kzalloc(sizeof(struct gpio_service), GFP_KERNEL);
+
+@@ -112,7 +112,7 @@ struct gpio_service *dal_gpio_service_create(
+ return service;
+
+ failure_2:
+- while (index_of_id) {
++ while (index_of_id > 0) {
+ --index_of_id;
+ kfree(service->busyness[index_of_id]);
+ }
+@@ -239,6 +239,9 @@ static bool is_pin_busy(
+ enum gpio_id id,
+ uint32_t en)
+ {
++ if (id == GPIO_ID_UNKNOWN)
++ return false;
++
+ return service->busyness[id][en];
+ }
+
+@@ -247,6 +250,9 @@ static void set_pin_busy(
+ enum gpio_id id,
+ uint32_t en)
+ {
++ if (id == GPIO_ID_UNKNOWN)
++ return;
++
+ service->busyness[id][en] = true;
+ }
+
+@@ -255,6 +261,9 @@ static void set_pin_free(
+ enum gpio_id id,
+ uint32_t en)
+ {
++ if (id == GPIO_ID_UNKNOWN)
++ return;
++
+ service->busyness[id][en] = false;
+ }
+
+@@ -263,7 +272,7 @@ enum gpio_result dal_gpio_service_lock(
+ enum gpio_id id,
+ uint32_t en)
+ {
+- if (!service->busyness[id]) {
++ if (id != GPIO_ID_UNKNOWN && !service->busyness[id]) {
+ ASSERT_CRITICAL(false);
+ return GPIO_RESULT_OPEN_FAILED;
+ }
+@@ -277,7 +286,7 @@ enum gpio_result dal_gpio_service_unlock(
+ enum gpio_id id,
+ uint32_t en)
+ {
+- if (!service->busyness[id]) {
++ if (id != GPIO_ID_UNKNOWN && !service->busyness[id]) {
+ ASSERT_CRITICAL(false);
+ return GPIO_RESULT_OPEN_FAILED;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c
+index 99e17c164ce7b..1d3e8f0b915b6 100644
+--- a/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c
++++ b/drivers/gpu/drm/amd/display/dc/hdcp/hdcp_msg.c
+@@ -128,13 +128,21 @@ static bool hdmi_14_process_transaction(
+ const uint8_t hdcp_i2c_addr_link_primary = 0x3a; /* 0x74 >> 1*/
+ const uint8_t hdcp_i2c_addr_link_secondary = 0x3b; /* 0x76 >> 1*/
+ struct i2c_command i2c_command;
+- uint8_t offset = hdcp_i2c_offsets[message_info->msg_id];
++ uint8_t offset;
+ struct i2c_payload i2c_payloads[] = {
+- { true, 0, 1, &offset },
++ { true, 0, 1, 0 },
+ /* actual hdcp payload, will be filled later, zeroed for now*/
+ { 0 }
+ };
+
++ if (message_info->msg_id == HDCP_MESSAGE_ID_INVALID) {
++ DC_LOG_ERROR("%s: Invalid message_info msg_id - %d\n", __func__, message_info->msg_id);
++ return false;
++ }
++
++ offset = hdcp_i2c_offsets[message_info->msg_id];
++ i2c_payloads[0].data = &offset;
++
+ switch (message_info->link) {
+ case HDCP_LINK_SECONDARY:
+ i2c_payloads[0].address = hdcp_i2c_addr_link_secondary;
+@@ -308,6 +316,11 @@ static bool dp_11_process_transaction(
+ struct dc_link *link,
+ struct hdcp_protection_message *message_info)
+ {
++ if (message_info->msg_id == HDCP_MESSAGE_ID_INVALID) {
++ DC_LOG_ERROR("%s: Invalid message_info msg_id - %d\n", __func__, message_info->msg_id);
++ return false;
++ }
++
+ return dpcd_access_helper(
+ link,
+ message_info->length,
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c
+index 6be846635a798..59f46df015511 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn201/dcn201_hwseq.c
+@@ -95,8 +95,11 @@ static bool gpu_addr_to_uma(struct dce_hwseq *hwseq,
+ } else if (hwseq->fb_offset.quad_part <= addr->quad_part &&
+ addr->quad_part <= hwseq->uma_top.quad_part) {
+ is_in_uma = true;
++ } else if (addr->quad_part == 0) {
++ is_in_uma = false;
+ } else {
+ is_in_uma = false;
++ BREAK_TO_DEBUGGER();
+ }
+ return is_in_uma;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+index 804be977ea47b..3de65a9f0e6f2 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn21/dcn21_hwseq.c
+@@ -142,7 +142,7 @@ static bool dmub_abm_set_pipe(struct abm *abm, uint32_t otg_inst,
+ {
+ union dmub_rb_cmd cmd;
+ struct dc_context *dc = abm->ctx;
+- uint32_t ramping_boundary = 0xFFFF;
++ uint8_t ramping_boundary = 0xFF;
+
+ memset(&cmd, 0, sizeof(cmd));
+ cmd.abm_set_pipe.header.type = DMUB_CMD__ABM;
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+index dcced89c07b38..f829ff82797e7 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn35/dcn35_hwseq.c
+@@ -1077,7 +1077,8 @@ void dcn35_calc_blocks_to_ungate(struct dc *dc, struct dc_state *context,
+ continue;
+
+ if ((!cur_pipe->plane_state && new_pipe->plane_state) ||
+- (!cur_pipe->stream && new_pipe->stream)) {
++ (!cur_pipe->stream && new_pipe->stream) ||
++ (cur_pipe->stream != new_pipe->stream && new_pipe->stream)) {
+ // New pipe addition
+ for (j = 0; j < PG_HW_PIPE_RESOURCES_NUM_ELEMENT; j++) {
+ if (j == PG_HUBP && new_pipe->plane_res.hubp)
+diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+index d487dfcd219b0..a3df1b55e48b7 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
++++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_capability.c
+@@ -534,7 +534,7 @@ static bool decide_fallback_link_setting_max_bw_policy(
+ struct dc_link_settings *cur,
+ enum link_training_result training_result)
+ {
+- uint8_t cur_idx = 0, next_idx;
++ uint32_t cur_idx = 0, next_idx;
+ bool found = false;
+
+ if (training_result == LINK_TRAINING_ABORT)
+@@ -914,21 +914,17 @@ bool link_decide_link_settings(struct dc_stream_state *stream,
+
+ memset(link_setting, 0, sizeof(*link_setting));
+
+- /* if preferred is specified through AMDDP, use it, if it's enough
+- * to drive the mode
+- */
+- if (link->preferred_link_setting.lane_count !=
+- LANE_COUNT_UNKNOWN &&
+- link->preferred_link_setting.link_rate !=
+- LINK_RATE_UNKNOWN) {
++ if (dc_is_dp_signal(stream->signal) &&
++ link->preferred_link_setting.lane_count != LANE_COUNT_UNKNOWN &&
++ link->preferred_link_setting.link_rate != LINK_RATE_UNKNOWN) {
++ /* if preferred is specified through AMDDP, use it, if it's enough
++ * to drive the mode
++ */
+ *link_setting = link->preferred_link_setting;
+- return true;
+- }
+-
+- /* MST doesn't perform link training for now
+- * TODO: add MST specific link training routine
+- */
+- if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
++ } else if (stream->signal == SIGNAL_TYPE_DISPLAY_PORT_MST) {
++ /* MST doesn't perform link training for now
++ * TODO: add MST specific link training routine
++ */
+ decide_mst_link_settings(link, link_setting);
+ } else if (link->connector_signal == SIGNAL_TYPE_EDP) {
+ /* enable edp link optimization for DSC eDP case */
+diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+index 1818970b8eaf7..b8e704dbe9567 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
++++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_training.c
+@@ -914,10 +914,10 @@ static enum dc_status configure_lttpr_mode_non_transparent(
+ /* Driver does not need to train the first hop. Skip DPCD read and clear
+ * AUX_RD_INTERVAL for DPTX-to-DPIA hop.
+ */
+- if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA)
++ if (link->ep_type == DISPLAY_ENDPOINT_USB4_DPIA && repeater_cnt > 0 && repeater_cnt < MAX_REPEATER_CNT)
+ link->dpcd_caps.lttpr_caps.aux_rd_interval[--repeater_cnt] = 0;
+
+- for (repeater_id = repeater_cnt; repeater_id > 0; repeater_id--) {
++ for (repeater_id = repeater_cnt; repeater_id > 0 && repeater_id < MAX_REPEATER_CNT; repeater_id--) {
+ aux_interval_address = DP_TRAINING_AUX_RD_INTERVAL_PHY_REPEATER1 +
+ ((DP_REPEATER_CONFIGURATION_AND_STATUS_SIZE) * (repeater_id - 1));
+ core_link_read_dpcd(
+diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
+index a72c898b64fab..584b9295a12af 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
++++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dpcd.c
+@@ -165,6 +165,7 @@ static void dpcd_extend_address_range(
+ *out_address = new_addr_range.start;
+ *out_size = ADDRESS_RANGE_SIZE(new_addr_range.start, new_addr_range.end);
+ *out_data = kcalloc(*out_size, sizeof(**out_data), GFP_KERNEL);
++ ASSERT(*out_data);
+ }
+ }
+
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
+index 56ee45e12b461..a73d3c6ef4258 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dce80/dce80_resource.c
+@@ -1538,6 +1538,7 @@ struct resource_pool *dce83_create_resource_pool(
+ if (dce83_construct(num_virtual_links, dc, pool))
+ return &pool->base;
+
++ kfree(pool);
+ BREAK_TO_DEBUGGER();
+ return NULL;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+index d4c3e2754f516..5d1801dce2730 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn31/dcn31_resource.c
+@@ -1864,6 +1864,7 @@ static struct clock_source *dcn30_clock_source_create(
+ return &clk_src->base;
+ }
+
++ kfree(clk_src);
+ BREAK_TO_DEBUGGER();
+ return NULL;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+index ff50f43e4c000..da73e842c55c8 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn314/dcn314_resource.c
+@@ -1660,8 +1660,8 @@ static struct clock_source *dcn31_clock_source_create(
+ return &clk_src->base;
+ }
+
+- BREAK_TO_DEBUGGER();
+ kfree(clk_src);
++ BREAK_TO_DEBUGGER();
+ return NULL;
+ }
+
+@@ -1821,8 +1821,8 @@ static struct clock_source *dcn30_clock_source_create(
+ return &clk_src->base;
+ }
+
+- BREAK_TO_DEBUGGER();
+ kfree(clk_src);
++ BREAK_TO_DEBUGGER();
+ return NULL;
+ }
+
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+index 2df8a742516c8..915d68cc04e9c 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn35/dcn35_resource.c
+@@ -785,6 +785,7 @@ static const struct dc_debug_options debug_defaults_drv = {
+ .ips2_entry_delay_us = 800,
+ .disable_dmub_reallow_idle = false,
+ .static_screen_wait_frames = 2,
++ .disable_timeout = true,
+ };
+
+ static const struct dc_panel_config panel_config_defaults = {
+@@ -1716,6 +1717,7 @@ static struct clock_source *dcn35_clock_source_create(
+ return &clk_src->base;
+ }
+
++ kfree(clk_src);
+ BREAK_TO_DEBUGGER();
+ return NULL;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+index ddf9560ab7722..b7bd0f36125a4 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn351/dcn351_resource.c
+@@ -1696,6 +1696,7 @@ static struct clock_source *dcn35_clock_source_create(
+ return &clk_src->base;
+ }
+
++ kfree(clk_src);
+ BREAK_TO_DEBUGGER();
+ return NULL;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
+index 70e63aeb8f89b..a330827f900c3 100644
+--- a/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
++++ b/drivers/gpu/drm/amd/display/dmub/src/dmub_dcn35.c
+@@ -459,7 +459,7 @@ uint32_t dmub_dcn35_get_current_time(struct dmub_srv *dmub)
+ void dmub_dcn35_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnostic_data *diag_data)
+ {
+ uint32_t is_dmub_enabled, is_soft_reset, is_sec_reset;
+- uint32_t is_traceport_enabled, is_cw0_enabled, is_cw6_enabled;
++ uint32_t is_traceport_enabled, is_cw6_enabled;
+
+ if (!dmub || !diag_data)
+ return;
+@@ -510,9 +510,6 @@ void dmub_dcn35_get_diagnostic_data(struct dmub_srv *dmub, struct dmub_diagnosti
+ REG_GET(DMCUB_CNTL, DMCUB_TRACEPORT_EN, &is_traceport_enabled);
+ diag_data->is_traceport_en = is_traceport_enabled;
+
+- REG_GET(DMCUB_REGION3_CW0_TOP_ADDRESS, DMCUB_REGION3_CW0_ENABLE, &is_cw0_enabled);
+- diag_data->is_cw0_enabled = is_cw0_enabled;
+-
+ REG_GET(DMCUB_REGION3_CW6_TOP_ADDRESS, DMCUB_REGION3_CW6_ENABLE, &is_cw6_enabled);
+ diag_data->is_cw6_enabled = is_cw6_enabled;
+
+diff --git a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
+index 8e9caae7c9559..1b2df97226a3f 100644
+--- a/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
++++ b/drivers/gpu/drm/amd/display/modules/hdcp/hdcp_ddc.c
+@@ -156,11 +156,16 @@ static enum mod_hdcp_status read(struct mod_hdcp *hdcp,
+ uint32_t cur_size = 0;
+ uint32_t data_offset = 0;
+
+- if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID) {
++ if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID ||
++ msg_id >= MOD_HDCP_MESSAGE_ID_MAX)
+ return MOD_HDCP_STATUS_DDC_FAILURE;
+- }
+
+ if (is_dp_hdcp(hdcp)) {
++ int num_dpcd_addrs = sizeof(hdcp_dpcd_addrs) /
++ sizeof(hdcp_dpcd_addrs[0]);
++ if (msg_id >= num_dpcd_addrs)
++ return MOD_HDCP_STATUS_DDC_FAILURE;
++
+ while (buf_len > 0) {
+ cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE);
+ success = hdcp->config.ddc.funcs.read_dpcd(hdcp->config.ddc.handle,
+@@ -175,6 +180,11 @@ static enum mod_hdcp_status read(struct mod_hdcp *hdcp,
+ data_offset += cur_size;
+ }
+ } else {
++ int num_i2c_offsets = sizeof(hdcp_i2c_offsets) /
++ sizeof(hdcp_i2c_offsets[0]);
++ if (msg_id >= num_i2c_offsets)
++ return MOD_HDCP_STATUS_DDC_FAILURE;
++
+ success = hdcp->config.ddc.funcs.read_i2c(
+ hdcp->config.ddc.handle,
+ HDCP_I2C_ADDR,
+@@ -219,11 +229,16 @@ static enum mod_hdcp_status write(struct mod_hdcp *hdcp,
+ uint32_t cur_size = 0;
+ uint32_t data_offset = 0;
+
+- if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID) {
++ if (msg_id == MOD_HDCP_MESSAGE_ID_INVALID ||
++ msg_id >= MOD_HDCP_MESSAGE_ID_MAX)
+ return MOD_HDCP_STATUS_DDC_FAILURE;
+- }
+
+ if (is_dp_hdcp(hdcp)) {
++ int num_dpcd_addrs = sizeof(hdcp_dpcd_addrs) /
++ sizeof(hdcp_dpcd_addrs[0]);
++ if (msg_id >= num_dpcd_addrs)
++ return MOD_HDCP_STATUS_DDC_FAILURE;
++
+ while (buf_len > 0) {
+ cur_size = MIN(buf_len, HDCP_MAX_AUX_TRANSACTION_SIZE);
+ success = hdcp->config.ddc.funcs.write_dpcd(
+@@ -239,6 +254,11 @@ static enum mod_hdcp_status write(struct mod_hdcp *hdcp,
+ data_offset += cur_size;
+ }
+ } else {
++ int num_i2c_offsets = sizeof(hdcp_i2c_offsets) /
++ sizeof(hdcp_i2c_offsets[0]);
++ if (msg_id >= num_i2c_offsets)
++ return MOD_HDCP_STATUS_DDC_FAILURE;
++
+ hdcp->buf[0] = hdcp_i2c_offsets[msg_id];
+ memmove(&hdcp->buf[1], buf, buf_len);
+ success = hdcp->config.ddc.funcs.write_i2c(
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+index f531ce1d2b1dc..a71c6117d7e54 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+@@ -99,7 +99,7 @@ static void pp_swctf_delayed_work_handler(struct work_struct *work)
+ struct amdgpu_device *adev = hwmgr->adev;
+ struct amdgpu_dpm_thermal *range =
+ &adev->pm.dpm.thermal;
+- uint32_t gpu_temperature, size;
++ uint32_t gpu_temperature, size = sizeof(gpu_temperature);
+ int ret;
+
+ /*
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
+index f4bd8e9357e22..18f00038d8441 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
+@@ -30,9 +30,8 @@ int psm_init_power_state_table(struct pp_hwmgr *hwmgr)
+ {
+ int result;
+ unsigned int i;
+- unsigned int table_entries;
+ struct pp_power_state *state;
+- int size;
++ int size, table_entries;
+
+ if (hwmgr->hwmgr_func->get_num_of_pp_table_entries == NULL)
+ return 0;
+@@ -40,15 +39,19 @@ int psm_init_power_state_table(struct pp_hwmgr *hwmgr)
+ if (hwmgr->hwmgr_func->get_power_state_size == NULL)
+ return 0;
+
+- hwmgr->num_ps = table_entries = hwmgr->hwmgr_func->get_num_of_pp_table_entries(hwmgr);
++ table_entries = hwmgr->hwmgr_func->get_num_of_pp_table_entries(hwmgr);
+
+- hwmgr->ps_size = size = hwmgr->hwmgr_func->get_power_state_size(hwmgr) +
++ size = hwmgr->hwmgr_func->get_power_state_size(hwmgr) +
+ sizeof(struct pp_power_state);
+
+- if (table_entries == 0 || size == 0) {
++ if (table_entries <= 0 || size == 0) {
+ pr_warn("Please check whether power state management is supported on this asic\n");
++ hwmgr->num_ps = 0;
++ hwmgr->ps_size = 0;
+ return 0;
+ }
++ hwmgr->num_ps = table_entries;
++ hwmgr->ps_size = size;
+
+ hwmgr->ps = kcalloc(table_entries, size, GFP_KERNEL);
+ if (hwmgr->ps == NULL)
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
+index b1b4c09c34671..b56298d9da98f 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/ppatomctrl.c
+@@ -73,8 +73,9 @@ static int atomctrl_retrieve_ac_timing(
+ j++;
+ } else if ((table->mc_reg_address[i].uc_pre_reg_data &
+ LOW_NIBBLE_MASK) == DATA_EQU_PREV) {
+- table->mc_reg_table_entry[num_ranges].mc_data[i] =
+- table->mc_reg_table_entry[num_ranges].mc_data[i-1];
++ if (i)
++ table->mc_reg_table_entry[num_ranges].mc_data[i] =
++ table->mc_reg_table_entry[num_ranges].mc_data[i-1];
+ }
+ }
+ num_ranges++;
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+index 02ba68d7c6546..f62381b189ade 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu10_hwmgr.c
+@@ -1036,7 +1036,9 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
+
+ switch (type) {
+ case PP_SCLK:
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetGfxclkFrequency, &now);
++ if (ret)
++ return ret;
+
+ /* driver only know min/max gfx_clk, Add level 1 for all other gfx clks */
+ if (now == data->gfx_max_freq_limit/100)
+@@ -1057,7 +1059,9 @@ static int smu10_print_clock_levels(struct pp_hwmgr *hwmgr,
+ i == 2 ? "*" : "");
+ break;
+ case PP_MCLK:
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetFclkFrequency, &now);
++ if (ret)
++ return ret;
+
+ for (i = 0; i < mclk_table->count; i++)
+ size += sprintf(buf + size, "%d: %uMhz %s\n",
+@@ -1550,7 +1554,10 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
+ }
+
+ if (input[0] == 0) {
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
++ if (ret)
++ return ret;
++
+ if (input[1] < min_freq) {
+ pr_err("Fine grain setting minimum sclk (%ld) MHz is less than the minimum allowed (%d) MHz\n",
+ input[1], min_freq);
+@@ -1558,7 +1565,10 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
+ }
+ smu10_data->gfx_actual_soft_min_freq = input[1];
+ } else if (input[0] == 1) {
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
++ if (ret)
++ return ret;
++
+ if (input[1] > max_freq) {
+ pr_err("Fine grain setting maximum sclk (%ld) MHz is greater than the maximum allowed (%d) MHz\n",
+ input[1], max_freq);
+@@ -1573,10 +1583,15 @@ static int smu10_set_fine_grain_clk_vol(struct pp_hwmgr *hwmgr,
+ pr_err("Input parameter number not correct\n");
+ return -EINVAL;
+ }
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
+-
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMinGfxclkFrequency, &min_freq);
++ if (ret)
++ return ret;
+ smu10_data->gfx_actual_soft_min_freq = min_freq;
++
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxGfxclkFrequency, &max_freq);
++ if (ret)
++ return ret;
++
+ smu10_data->gfx_actual_soft_max_freq = max_freq;
+ } else if (type == PP_OD_COMMIT_DPM_TABLE) {
+ if (size != 0) {
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+index f1c369945ac5d..bc27a70a1224f 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+@@ -5641,7 +5641,7 @@ static int smu7_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, uint
+ mode = input[size];
+ switch (mode) {
+ case PP_SMC_POWER_PROFILE_CUSTOM:
+- if (size < 8 && size != 0)
++ if (size != 8 && size != 0)
+ return -EINVAL;
+ /* If only CUSTOM is passed in, use the saved values. Check
+ * that we actually have a CUSTOM profile by ensuring that
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+index eb744401e0567..7e11974208732 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+@@ -584,6 +584,7 @@ static int smu8_init_uvd_limit(struct pp_hwmgr *hwmgr)
+ hwmgr->dyn_state.uvd_clock_voltage_dependency_table;
+ unsigned long clock = 0;
+ uint32_t level;
++ int ret;
+
+ if (NULL == table || table->count <= 0)
+ return -EINVAL;
+@@ -591,7 +592,9 @@ static int smu8_init_uvd_limit(struct pp_hwmgr *hwmgr)
+ data->uvd_dpm.soft_min_clk = 0;
+ data->uvd_dpm.hard_min_clk = 0;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxUvdLevel, &level);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxUvdLevel, &level);
++ if (ret)
++ return ret;
+
+ if (level < table->count)
+ clock = table->entries[level].vclk;
+@@ -611,6 +614,7 @@ static int smu8_init_vce_limit(struct pp_hwmgr *hwmgr)
+ hwmgr->dyn_state.vce_clock_voltage_dependency_table;
+ unsigned long clock = 0;
+ uint32_t level;
++ int ret;
+
+ if (NULL == table || table->count <= 0)
+ return -EINVAL;
+@@ -618,7 +622,9 @@ static int smu8_init_vce_limit(struct pp_hwmgr *hwmgr)
+ data->vce_dpm.soft_min_clk = 0;
+ data->vce_dpm.hard_min_clk = 0;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxEclkLevel, &level);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxEclkLevel, &level);
++ if (ret)
++ return ret;
+
+ if (level < table->count)
+ clock = table->entries[level].ecclk;
+@@ -638,6 +644,7 @@ static int smu8_init_acp_limit(struct pp_hwmgr *hwmgr)
+ hwmgr->dyn_state.acp_clock_voltage_dependency_table;
+ unsigned long clock = 0;
+ uint32_t level;
++ int ret;
+
+ if (NULL == table || table->count <= 0)
+ return -EINVAL;
+@@ -645,7 +652,9 @@ static int smu8_init_acp_limit(struct pp_hwmgr *hwmgr)
+ data->acp_dpm.soft_min_clk = 0;
+ data->acp_dpm.hard_min_clk = 0;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxAclkLevel, &level);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetMaxAclkLevel, &level);
++ if (ret)
++ return ret;
+
+ if (level < table->count)
+ clock = table->entries[level].acpclk;
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+index f4acdb2267416..ff605063d7ef0 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+@@ -354,13 +354,13 @@ static int vega10_odn_initial_default_setting(struct pp_hwmgr *hwmgr)
+ return 0;
+ }
+
+-static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr)
++static int vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr)
+ {
+ struct vega10_hwmgr *data = hwmgr->backend;
+- int i;
+ uint32_t sub_vendor_id, hw_revision;
+ uint32_t top32, bottom32;
+ struct amdgpu_device *adev = hwmgr->adev;
++ int ret, i;
+
+ vega10_initialize_power_tune_defaults(hwmgr);
+
+@@ -485,9 +485,12 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr)
+ if (data->registry_data.vr0hot_enabled)
+ data->smu_features[GNLD_VR0HOT].supported = true;
+
+- smum_send_msg_to_smc(hwmgr,
++ ret = smum_send_msg_to_smc(hwmgr,
+ PPSMC_MSG_GetSmuVersion,
+ &hwmgr->smu_version);
++ if (ret)
++ return ret;
++
+ /* ACG firmware has major version 5 */
+ if ((hwmgr->smu_version & 0xff000000) == 0x5000000)
+ data->smu_features[GNLD_ACG].supported = true;
+@@ -505,10 +508,16 @@ static void vega10_init_dpm_defaults(struct pp_hwmgr *hwmgr)
+ data->smu_features[GNLD_PCC_LIMIT].supported = true;
+
+ /* Get the SN to turn into a Unique ID */
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32);
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32);
++ if (ret)
++ return ret;
++
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32);
++ if (ret)
++ return ret;
+
+ adev->unique_id = ((uint64_t)bottom32 << 32) | top32;
++ return 0;
+ }
+
+ #ifdef PPLIB_VEGA10_EVV_SUPPORT
+@@ -882,7 +891,9 @@ static int vega10_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
+
+ vega10_set_features_platform_caps(hwmgr);
+
+- vega10_init_dpm_defaults(hwmgr);
++ result = vega10_init_dpm_defaults(hwmgr);
++ if (result)
++ return result;
+
+ #ifdef PPLIB_VEGA10_EVV_SUPPORT
+ /* Get leakage voltage based on leakage ID. */
+@@ -2350,15 +2361,20 @@ static int vega10_acg_enable(struct pp_hwmgr *hwmgr)
+ {
+ struct vega10_hwmgr *data = hwmgr->backend;
+ uint32_t agc_btc_response;
++ int ret;
+
+ if (data->smu_features[GNLD_ACG].supported) {
+ if (0 == vega10_enable_smc_features(hwmgr, true,
+ data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_bitmap))
+ data->smu_features[GNLD_DPM_PREFETCHER].enabled = true;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_InitializeAcg, NULL);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_InitializeAcg, NULL);
++ if (ret)
++ return ret;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_RunAcgBtc, &agc_btc_response);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_RunAcgBtc, &agc_btc_response);
++ if (ret)
++ agc_btc_response = 0;
+
+ if (1 == agc_btc_response) {
+ if (1 == data->acg_loop_state)
+@@ -2571,8 +2587,11 @@ static int vega10_init_smc_table(struct pp_hwmgr *hwmgr)
+ }
+ }
+
+- pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC,
++ result = pp_atomfwctrl_get_voltage_table_v4(hwmgr, VOLTAGE_TYPE_VDDC,
+ VOLTAGE_OBJ_SVID2, &voltage_table);
++ PP_ASSERT_WITH_CODE(!result,
++ "Failed to get voltage table!",
++ return result);
+ pp_table->MaxVidStep = voltage_table.max_vid_step;
+
+ pp_table->GfxDpmVoltageMode =
+@@ -3910,11 +3929,14 @@ static int vega10_get_gpu_power(struct pp_hwmgr *hwmgr,
+ uint32_t *query)
+ {
+ uint32_t value;
++ int ret;
+
+ if (!query)
+ return -EINVAL;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrPkgPwr, &value);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrPkgPwr, &value);
++ if (ret)
++ return ret;
+
+ /* SMC returning actual watts, keep consistent with legacy asics, low 8 bit as 8 fractional bits */
+ *query = value << 8;
+@@ -4810,14 +4832,16 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
+ uint32_t gen_speed, lane_width, current_gen_speed, current_lane_width;
+ PPTable_t *pptable = &(data->smc_state_table.pp_table);
+
+- int i, now, size = 0, count = 0;
++ int i, ret, now, size = 0, count = 0;
+
+ switch (type) {
+ case PP_SCLK:
+ if (data->registry_data.sclk_dpm_key_disabled)
+ break;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex, &now);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentGfxclkIndex, &now);
++ if (ret)
++ break;
+
+ if (hwmgr->pp_one_vf &&
+ (hwmgr->dpm_level == AMD_DPM_FORCED_LEVEL_PROFILE_PEAK))
+@@ -4833,7 +4857,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
+ if (data->registry_data.mclk_dpm_key_disabled)
+ break;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentUclkIndex, &now);
++ if (ret)
++ break;
+
+ for (i = 0; i < mclk_table->count; i++)
+ size += sprintf(buf + size, "%d: %uMhz %s\n",
+@@ -4844,7 +4870,9 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
+ if (data->registry_data.socclk_dpm_key_disabled)
+ break;
+
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_GetCurrentSocclkIndex, &now);
++ if (ret)
++ break;
+
+ for (i = 0; i < soc_table->count; i++)
+ size += sprintf(buf + size, "%d: %uMhz %s\n",
+@@ -4855,8 +4883,10 @@ static int vega10_print_clock_levels(struct pp_hwmgr *hwmgr,
+ if (data->registry_data.dcefclk_dpm_key_disabled)
+ break;
+
+- smum_send_msg_to_smc_with_parameter(hwmgr,
++ ret = smum_send_msg_to_smc_with_parameter(hwmgr,
+ PPSMC_MSG_GetClockFreqMHz, CLK_DCEFCLK, &now);
++ if (ret)
++ break;
+
+ for (i = 0; i < dcef_table->count; i++)
+ size += sprintf(buf + size, "%d: %uMhz %s\n",
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+index c223e3a6bfca5..10fd4e9f016cd 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega12_hwmgr.c
+@@ -293,12 +293,12 @@ static int vega12_set_features_platform_caps(struct pp_hwmgr *hwmgr)
+ return 0;
+ }
+
+-static void vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr)
++static int vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr)
+ {
+ struct vega12_hwmgr *data = (struct vega12_hwmgr *)(hwmgr->backend);
+ struct amdgpu_device *adev = hwmgr->adev;
+ uint32_t top32, bottom32;
+- int i;
++ int i, ret;
+
+ data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_id =
+ FEATURE_DPM_PREFETCHER_BIT;
+@@ -364,10 +364,16 @@ static void vega12_init_dpm_defaults(struct pp_hwmgr *hwmgr)
+ }
+
+ /* Get the SN to turn into a Unique ID */
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32);
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32);
++ if (ret)
++ return ret;
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32);
++ if (ret)
++ return ret;
+
+ adev->unique_id = ((uint64_t)bottom32 << 32) | top32;
++
++ return 0;
+ }
+
+ static int vega12_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr)
+@@ -410,7 +416,11 @@ static int vega12_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
+
+ vega12_set_features_platform_caps(hwmgr);
+
+- vega12_init_dpm_defaults(hwmgr);
++ result = vega12_init_dpm_defaults(hwmgr);
++ if (result) {
++ pr_err("%s failed\n", __func__);
++ return result;
++ }
+
+ /* Parse pptable data read from VBIOS */
+ vega12_set_private_data_based_on_pptable(hwmgr);
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+index f9efb0bad8072..baf251fe5d828 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega20_hwmgr.c
+@@ -328,12 +328,12 @@ static int vega20_set_features_platform_caps(struct pp_hwmgr *hwmgr)
+ return 0;
+ }
+
+-static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr)
++static int vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr)
+ {
+ struct vega20_hwmgr *data = (struct vega20_hwmgr *)(hwmgr->backend);
+ struct amdgpu_device *adev = hwmgr->adev;
+ uint32_t top32, bottom32;
+- int i;
++ int i, ret;
+
+ data->smu_features[GNLD_DPM_PREFETCHER].smu_feature_id =
+ FEATURE_DPM_PREFETCHER_BIT;
+@@ -404,10 +404,17 @@ static void vega20_init_dpm_defaults(struct pp_hwmgr *hwmgr)
+ }
+
+ /* Get the SN to turn into a Unique ID */
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32);
+- smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32);
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumTop32, &top32);
++ if (ret)
++ return ret;
++
++ ret = smum_send_msg_to_smc(hwmgr, PPSMC_MSG_ReadSerialNumBottom32, &bottom32);
++ if (ret)
++ return ret;
+
+ adev->unique_id = ((uint64_t)bottom32 << 32) | top32;
++
++ return 0;
+ }
+
+ static int vega20_set_private_data_based_on_pptable(struct pp_hwmgr *hwmgr)
+@@ -427,6 +434,7 @@ static int vega20_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
+ {
+ struct vega20_hwmgr *data;
+ struct amdgpu_device *adev = hwmgr->adev;
++ int result;
+
+ data = kzalloc(sizeof(struct vega20_hwmgr), GFP_KERNEL);
+ if (data == NULL)
+@@ -452,8 +460,11 @@ static int vega20_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
+
+ vega20_set_features_platform_caps(hwmgr);
+
+- vega20_init_dpm_defaults(hwmgr);
+-
++ result = vega20_init_dpm_defaults(hwmgr);
++ if (result) {
++ pr_err("%s failed\n", __func__);
++ return result;
++ }
+ /* Parse pptable data read from VBIOS */
+ vega20_set_private_data_based_on_pptable(hwmgr);
+
+@@ -4091,9 +4102,11 @@ static int vega20_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui
+ if (power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
+ struct vega20_hwmgr *data =
+ (struct vega20_hwmgr *)(hwmgr->backend);
+- if (size == 0 && !data->is_custom_profile_set)
++
++ if (size != 10 && size != 0)
+ return -EINVAL;
+- if (size < 10 && size != 0)
++
++ if (size == 0 && !data->is_custom_profile_set)
+ return -EINVAL;
+
+ result = vega20_get_activity_monitor_coeff(hwmgr,
+@@ -4155,6 +4168,8 @@ static int vega20_set_power_profile_mode(struct pp_hwmgr *hwmgr, long *input, ui
+ activity_monitor.Fclk_PD_Data_error_coeff = input[8];
+ activity_monitor.Fclk_PD_Data_error_rate_coeff = input[9];
+ break;
++ default:
++ return -EINVAL;
+ }
+
+ result = vega20_set_activity_monitor_coeff(hwmgr,
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
+index a70d738966490..f9c0f117725dd 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/smumgr/vega10_smumgr.c
+@@ -130,13 +130,17 @@ int vega10_get_enabled_smc_features(struct pp_hwmgr *hwmgr,
+ uint64_t *features_enabled)
+ {
+ uint32_t enabled_features;
++ int ret;
+
+ if (features_enabled == NULL)
+ return -EINVAL;
+
+- smum_send_msg_to_smc(hwmgr,
++ ret = smum_send_msg_to_smc(hwmgr,
+ PPSMC_MSG_GetEnabledSmuFeatures,
+ &enabled_features);
++ if (ret)
++ return ret;
++
+ *features_enabled = enabled_features;
+
+ return 0;
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+index d9700a3f28d2f..e58220a7ee2f7 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
++++ b/drivers/gpu/drm/amd/pm/swsmu/inc/smu_v13_0.h
+@@ -298,5 +298,9 @@ int smu_v13_0_enable_uclk_shadow(struct smu_context *smu, bool enable);
+
+ int smu_v13_0_set_wbrf_exclusion_ranges(struct smu_context *smu,
+ struct freq_band_range *exclusion_ranges);
++
++int smu_v13_0_get_boot_freq_by_index(struct smu_context *smu,
++ enum smu_clk_type clk_type,
++ uint32_t *value);
+ #endif
+ #endif
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+index 6d334a2aff672..623f6052f97ed 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/arcturus_ppt.c
+@@ -1416,6 +1416,9 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
+
+ if ((profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) &&
+ (smu->smc_fw_version >= 0x360d00)) {
++ if (size != 10)
++ return -EINVAL;
++
+ ret = smu_cmn_update_table(smu,
+ SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+ WORKLOAD_PPLIB_CUSTOM_BIT,
+@@ -1449,6 +1452,8 @@ static int arcturus_set_power_profile_mode(struct smu_context *smu,
+ activity_monitor.Mem_PD_Data_error_coeff = input[8];
+ activity_monitor.Mem_PD_Data_error_rate_coeff = input[9];
+ break;
++ default:
++ return -EINVAL;
+ }
+
+ ret = smu_cmn_update_table(smu,
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+index 5a68d365967f7..01039cdd456b0 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/navi10_ppt.c
+@@ -1219,19 +1219,22 @@ static int navi10_get_current_clk_freq_by_table(struct smu_context *smu,
+ value);
+ }
+
+-static bool navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type)
++static int navi10_is_support_fine_grained_dpm(struct smu_context *smu, enum smu_clk_type clk_type)
+ {
+ PPTable_t *pptable = smu->smu_table.driver_pptable;
+ DpmDescriptor_t *dpm_desc = NULL;
+- uint32_t clk_index = 0;
++ int clk_index = 0;
+
+ clk_index = smu_cmn_to_asic_specific_index(smu,
+ CMN2ASIC_MAPPING_CLK,
+ clk_type);
++ if (clk_index < 0)
++ return clk_index;
++
+ dpm_desc = &pptable->DpmDescriptor[clk_index];
+
+ /* 0 - Fine grained DPM, 1 - Discrete DPM */
+- return dpm_desc->SnapToDiscrete == 0;
++ return dpm_desc->SnapToDiscrete == 0 ? 1 : 0;
+ }
+
+ static inline bool navi10_od_feature_is_supported(struct smu_11_0_overdrive_table *od_table, enum SMU_11_0_ODFEATURE_CAP cap)
+@@ -1287,7 +1290,11 @@ static int navi10_emit_clk_levels(struct smu_context *smu,
+ if (ret)
+ return ret;
+
+- if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) {
++ ret = navi10_is_support_fine_grained_dpm(smu, clk_type);
++ if (ret < 0)
++ return ret;
++
++ if (!ret) {
+ for (i = 0; i < count; i++) {
+ ret = smu_v11_0_get_dpm_freq_by_index(smu,
+ clk_type, i, &value);
+@@ -1496,7 +1503,11 @@ static int navi10_print_clk_levels(struct smu_context *smu,
+ if (ret)
+ return size;
+
+- if (!navi10_is_support_fine_grained_dpm(smu, clk_type)) {
++ ret = navi10_is_support_fine_grained_dpm(smu, clk_type);
++ if (ret < 0)
++ return ret;
++
++ if (!ret) {
+ for (i = 0; i < count; i++) {
+ ret = smu_v11_0_get_dpm_freq_by_index(smu, clk_type, i, &value);
+ if (ret)
+@@ -1665,7 +1676,11 @@ static int navi10_force_clk_levels(struct smu_context *smu,
+ case SMU_UCLK:
+ case SMU_FCLK:
+ /* There is only 2 levels for fine grained DPM */
+- if (navi10_is_support_fine_grained_dpm(smu, clk_type)) {
++ ret = navi10_is_support_fine_grained_dpm(smu, clk_type);
++ if (ret < 0)
++ return ret;
++
++ if (ret) {
+ soft_max_level = (soft_max_level >= 1 ? 1 : 0);
+ soft_min_level = (soft_min_level >= 1 ? 1 : 0);
+ }
+@@ -2006,6 +2021,8 @@ static int navi10_set_power_profile_mode(struct smu_context *smu, long *input, u
+ }
+
+ if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
++ if (size != 10)
++ return -EINVAL;
+
+ ret = smu_cmn_update_table(smu,
+ SMU_TABLE_ACTIVITY_MONITOR_COEFF, WORKLOAD_PPLIB_CUSTOM_BIT,
+@@ -2049,6 +2066,8 @@ static int navi10_set_power_profile_mode(struct smu_context *smu, long *input, u
+ activity_monitor.Mem_PD_Data_error_coeff = input[8];
+ activity_monitor.Mem_PD_Data_error_rate_coeff = input[9];
+ break;
++ default:
++ return -EINVAL;
+ }
+
+ ret = smu_cmn_update_table(smu,
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+index e426f457a017f..d5a21d7836cc6 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/sienna_cichlid_ppt.c
+@@ -1722,6 +1722,8 @@ static int sienna_cichlid_set_power_profile_mode(struct smu_context *smu, long *
+ }
+
+ if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
++ if (size != 10)
++ return -EINVAL;
+
+ ret = smu_cmn_update_table(smu,
+ SMU_TABLE_ACTIVITY_MONITOR_COEFF, WORKLOAD_PPLIB_CUSTOM_BIT,
+@@ -1765,6 +1767,8 @@ static int sienna_cichlid_set_power_profile_mode(struct smu_context *smu, long *
+ activity_monitor->Mem_PD_Data_error_coeff = input[8];
+ activity_monitor->Mem_PD_Data_error_rate_coeff = input[9];
+ break;
++ default:
++ return -EINVAL;
+ }
+
+ ret = smu_cmn_update_table(smu,
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+index 379e44eb0019d..22737b11b1bfb 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu11/vangogh_ppt.c
+@@ -976,6 +976,18 @@ static int vangogh_get_dpm_ultimate_freq(struct smu_context *smu,
+ }
+ }
+ if (min) {
++ ret = vangogh_get_profiling_clk_mask(smu,
++ AMD_DPM_FORCED_LEVEL_PROFILE_MIN_MCLK,
++ NULL,
++ NULL,
++ &mclk_mask,
++ &fclk_mask,
++ &soc_mask);
++ if (ret)
++ goto failed;
++
++ vclk_mask = dclk_mask = 0;
++
+ switch (clk_type) {
+ case SMU_UCLK:
+ case SMU_MCLK:
+@@ -2450,6 +2462,8 @@ static u32 vangogh_set_gfxoff_residency(struct smu_context *smu, bool start)
+
+ ret = smu_cmn_send_smc_msg_with_param(smu, SMU_MSG_LogGfxOffResidency,
+ start, &residency);
++ if (ret)
++ return ret;
+
+ if (!start)
+ adev->gfx.gfx_off_residency = residency;
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+index ce941fbb9cfbe..a22eb6bbb05ed 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/aldebaran_ppt.c
+@@ -1886,7 +1886,8 @@ static int aldebaran_mode2_reset(struct smu_context *smu)
+
+ index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG,
+ SMU_MSG_GfxDeviceDriverReset);
+-
++ if (index < 0 )
++ return -EINVAL;
+ mutex_lock(&smu->message_lock);
+ if (smu->smc_fw_version >= 0x00441400) {
+ ret = smu_cmn_send_msg_without_waiting(smu, (uint16_t)index, SMU_RESET_MODE_2);
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+index b63ad9cb24bfd..933fe93c8d1e6 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+@@ -1559,22 +1559,9 @@ int smu_v13_0_get_dpm_ultimate_freq(struct smu_context *smu, enum smu_clk_type c
+ uint32_t clock_limit;
+
+ if (!smu_cmn_clk_dpm_is_enabled(smu, clk_type)) {
+- switch (clk_type) {
+- case SMU_MCLK:
+- case SMU_UCLK:
+- clock_limit = smu->smu_table.boot_values.uclk;
+- break;
+- case SMU_GFXCLK:
+- case SMU_SCLK:
+- clock_limit = smu->smu_table.boot_values.gfxclk;
+- break;
+- case SMU_SOCCLK:
+- clock_limit = smu->smu_table.boot_values.socclk;
+- break;
+- default:
+- clock_limit = 0;
+- break;
+- }
++ ret = smu_v13_0_get_boot_freq_by_index(smu, clk_type, &clock_limit);
++ if (ret)
++ return ret;
+
+ /* clock in Mhz unit */
+ if (min)
+@@ -1894,6 +1881,40 @@ int smu_v13_0_set_power_source(struct smu_context *smu,
+ NULL);
+ }
+
++int smu_v13_0_get_boot_freq_by_index(struct smu_context *smu,
++ enum smu_clk_type clk_type,
++ uint32_t *value)
++{
++ int ret = 0;
++
++ switch (clk_type) {
++ case SMU_MCLK:
++ case SMU_UCLK:
++ *value = smu->smu_table.boot_values.uclk;
++ break;
++ case SMU_FCLK:
++ *value = smu->smu_table.boot_values.fclk;
++ break;
++ case SMU_GFXCLK:
++ case SMU_SCLK:
++ *value = smu->smu_table.boot_values.gfxclk;
++ break;
++ case SMU_SOCCLK:
++ *value = smu->smu_table.boot_values.socclk;
++ break;
++ case SMU_VCLK:
++ *value = smu->smu_table.boot_values.vclk;
++ break;
++ case SMU_DCLK:
++ *value = smu->smu_table.boot_values.dclk;
++ break;
++ default:
++ ret = -EINVAL;
++ break;
++ }
++ return ret;
++}
++
+ int smu_v13_0_get_dpm_freq_by_index(struct smu_context *smu,
+ enum smu_clk_type clk_type, uint16_t level,
+ uint32_t *value)
+@@ -1905,7 +1926,7 @@ int smu_v13_0_get_dpm_freq_by_index(struct smu_context *smu,
+ return -EINVAL;
+
+ if (!smu_cmn_clk_dpm_is_enabled(smu, clk_type))
+- return 0;
++ return smu_v13_0_get_boot_freq_by_index(smu, clk_type, value);
+
+ clk_id = smu_cmn_to_asic_specific_index(smu,
+ CMN2ASIC_MAPPING_CLK,
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+index 1e09d5f2d82fe..f7e756ca36dcd 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_0_ppt.c
+@@ -2495,6 +2495,9 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
+ }
+
+ if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
++ if (size != 9)
++ return -EINVAL;
++
+ ret = smu_cmn_update_table(smu,
+ SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+ WORKLOAD_PPLIB_CUSTOM_BIT,
+@@ -2526,6 +2529,8 @@ static int smu_v13_0_0_set_power_profile_mode(struct smu_context *smu,
+ activity_monitor->Fclk_PD_Data_error_coeff = input[7];
+ activity_monitor->Fclk_PD_Data_error_rate_coeff = input[8];
+ break;
++ default:
++ return -EINVAL;
+ }
+
+ ret = smu_cmn_update_table(smu,
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+index b6257f34a7c65..b081ae3e8f43c 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_4_ppt.c
+@@ -758,31 +758,9 @@ static int smu_v13_0_4_get_dpm_ultimate_freq(struct smu_context *smu,
+ int ret = 0;
+
+ if (!smu_v13_0_4_clk_dpm_is_enabled(smu, clk_type)) {
+- switch (clk_type) {
+- case SMU_MCLK:
+- case SMU_UCLK:
+- clock_limit = smu->smu_table.boot_values.uclk;
+- break;
+- case SMU_FCLK:
+- clock_limit = smu->smu_table.boot_values.fclk;
+- break;
+- case SMU_GFXCLK:
+- case SMU_SCLK:
+- clock_limit = smu->smu_table.boot_values.gfxclk;
+- break;
+- case SMU_SOCCLK:
+- clock_limit = smu->smu_table.boot_values.socclk;
+- break;
+- case SMU_VCLK:
+- clock_limit = smu->smu_table.boot_values.vclk;
+- break;
+- case SMU_DCLK:
+- clock_limit = smu->smu_table.boot_values.dclk;
+- break;
+- default:
+- clock_limit = 0;
+- break;
+- }
++ ret = smu_v13_0_get_boot_freq_by_index(smu, clk_type, &clock_limit);
++ if (ret)
++ return ret;
+
+ /* clock in Mhz unit */
+ if (min)
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
+index 218f209c37756..59854465d7115 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_5_ppt.c
+@@ -733,31 +733,9 @@ static int smu_v13_0_5_get_dpm_ultimate_freq(struct smu_context *smu,
+ int ret = 0;
+
+ if (!smu_v13_0_5_clk_dpm_is_enabled(smu, clk_type)) {
+- switch (clk_type) {
+- case SMU_MCLK:
+- case SMU_UCLK:
+- clock_limit = smu->smu_table.boot_values.uclk;
+- break;
+- case SMU_FCLK:
+- clock_limit = smu->smu_table.boot_values.fclk;
+- break;
+- case SMU_GFXCLK:
+- case SMU_SCLK:
+- clock_limit = smu->smu_table.boot_values.gfxclk;
+- break;
+- case SMU_SOCCLK:
+- clock_limit = smu->smu_table.boot_values.socclk;
+- break;
+- case SMU_VCLK:
+- clock_limit = smu->smu_table.boot_values.vclk;
+- break;
+- case SMU_DCLK:
+- clock_limit = smu->smu_table.boot_values.dclk;
+- break;
+- default:
+- clock_limit = 0;
+- break;
+- }
++ ret = smu_v13_0_get_boot_freq_by_index(smu, clk_type, &clock_limit);
++ if (ret)
++ return ret;
+
+ /* clock in Mhz unit */
+ if (min)
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+index 4d3eca2fc3f11..f4469d001d7c4 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_6_ppt.c
+@@ -2333,6 +2333,8 @@ static int smu_v13_0_6_mode2_reset(struct smu_context *smu)
+
+ index = smu_cmn_to_asic_specific_index(smu, CMN2ASIC_MAPPING_MSG,
+ SMU_MSG_GfxDeviceDriverReset);
++ if (index < 0)
++ return index;
+
+ mutex_lock(&smu->message_lock);
+
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+index e996a0a4d33e1..4f98869e02848 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0_7_ppt.c
+@@ -2450,6 +2450,8 @@ static int smu_v13_0_7_set_power_profile_mode(struct smu_context *smu, long *inp
+ }
+
+ if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
++ if (size != 8)
++ return -EINVAL;
+
+ ret = smu_cmn_update_table(smu,
+ SMU_TABLE_ACTIVITY_MONITOR_COEFF, WORKLOAD_PPLIB_CUSTOM_BIT,
+@@ -2478,6 +2480,8 @@ static int smu_v13_0_7_set_power_profile_mode(struct smu_context *smu, long *inp
+ activity_monitor->Fclk_MinActiveFreq = input[6];
+ activity_monitor->Fclk_BoosterFreq = input[7];
+ break;
++ default:
++ return -EINVAL;
+ }
+
+ ret = smu_cmn_update_table(smu,
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+index d8bcf765a8038..5917c88cc87d6 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/yellow_carp_ppt.c
+@@ -867,31 +867,9 @@ static int yellow_carp_get_dpm_ultimate_freq(struct smu_context *smu,
+ int ret = 0;
+
+ if (!yellow_carp_clk_dpm_is_enabled(smu, clk_type)) {
+- switch (clk_type) {
+- case SMU_MCLK:
+- case SMU_UCLK:
+- clock_limit = smu->smu_table.boot_values.uclk;
+- break;
+- case SMU_FCLK:
+- clock_limit = smu->smu_table.boot_values.fclk;
+- break;
+- case SMU_GFXCLK:
+- case SMU_SCLK:
+- clock_limit = smu->smu_table.boot_values.gfxclk;
+- break;
+- case SMU_SOCCLK:
+- clock_limit = smu->smu_table.boot_values.socclk;
+- break;
+- case SMU_VCLK:
+- clock_limit = smu->smu_table.boot_values.vclk;
+- break;
+- case SMU_DCLK:
+- clock_limit = smu->smu_table.boot_values.dclk;
+- break;
+- default:
+- clock_limit = 0;
+- break;
+- }
++ ret = smu_v13_0_get_boot_freq_by_index(smu, clk_type, &clock_limit);
++ if (ret)
++ return ret;
+
+ /* clock in Mhz unit */
+ if (min)
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+index 90703f4542aba..06b65159f7b4a 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu14/smu_v14_0_2_ppt.c
+@@ -1364,6 +1364,9 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
+ }
+
+ if (smu->power_profile_mode == PP_SMC_POWER_PROFILE_CUSTOM) {
++ if (size != 9)
++ return -EINVAL;
++
+ ret = smu_cmn_update_table(smu,
+ SMU_TABLE_ACTIVITY_MONITOR_COEFF,
+ WORKLOAD_PPLIB_CUSTOM_BIT,
+@@ -1395,6 +1398,8 @@ static int smu_v14_0_2_set_power_profile_mode(struct smu_context *smu,
+ activity_monitor->Fclk_PD_Data_error_coeff = input[7];
+ activity_monitor->Fclk_PD_Data_error_rate_coeff = input[8];
+ break;
++ default:
++ return -EINVAL;
+ }
+
+ ret = smu_cmn_update_table(smu,
+diff --git a/drivers/gpu/drm/bridge/tc358767.c b/drivers/gpu/drm/bridge/tc358767.c
+index 166f9a3e9622d..332f0aa50fee4 100644
+--- a/drivers/gpu/drm/bridge/tc358767.c
++++ b/drivers/gpu/drm/bridge/tc358767.c
+@@ -2135,7 +2135,7 @@ static irqreturn_t tc_irq_handler(int irq, void *arg)
+ dev_err(tc->dev, "syserr %x\n", stat);
+ }
+
+- if (tc->hpd_pin >= 0 && tc->bridge.dev) {
++ if (tc->hpd_pin >= 0 && tc->bridge.dev && tc->aux.drm_dev) {
+ /*
+ * H is triggered when the GPIO goes high.
+ *
+diff --git a/drivers/gpu/drm/drm_bridge.c b/drivers/gpu/drm/drm_bridge.c
+index 28abe9aa99ca5..584d109330ab1 100644
+--- a/drivers/gpu/drm/drm_bridge.c
++++ b/drivers/gpu/drm/drm_bridge.c
+@@ -353,13 +353,8 @@ int drm_bridge_attach(struct drm_encoder *encoder, struct drm_bridge *bridge,
+ bridge->encoder = NULL;
+ list_del(&bridge->chain_node);
+
+-#ifdef CONFIG_OF
+ DRM_ERROR("failed to attach bridge %pOF to encoder %s: %d\n",
+ bridge->of_node, encoder->name, ret);
+-#else
+- DRM_ERROR("failed to attach bridge to encoder %s: %d\n",
+- encoder->name, ret);
+-#endif
+
+ return ret;
+ }
+diff --git a/drivers/gpu/drm/drm_fb_helper.c b/drivers/gpu/drm/drm_fb_helper.c
+index 117237d3528bd..618b045230336 100644
+--- a/drivers/gpu/drm/drm_fb_helper.c
++++ b/drivers/gpu/drm/drm_fb_helper.c
+@@ -631,6 +631,17 @@ static void drm_fb_helper_add_damage_clip(struct drm_fb_helper *helper, u32 x, u
+ static void drm_fb_helper_damage(struct drm_fb_helper *helper, u32 x, u32 y,
+ u32 width, u32 height)
+ {
++ /*
++ * This function may be invoked by panic() to flush the frame
++ * buffer, where all CPUs except the panic CPU are stopped.
++ * During the following schedule_work(), the panic CPU needs
++ * the worker_pool lock, which might be held by a stopped CPU,
++ * causing schedule_work() and panic() to block. Return early on
++ * oops_in_progress to prevent this blocking.
++ */
++ if (oops_in_progress)
++ return;
++
+ drm_fb_helper_add_damage_clip(helper, x, y, width, height);
+
+ schedule_work(&helper->damage_work);
+diff --git a/drivers/gpu/drm/drm_panel_orientation_quirks.c b/drivers/gpu/drm/drm_panel_orientation_quirks.c
+index 3860a8ce1e2d4..903f4bfea7e83 100644
+--- a/drivers/gpu/drm/drm_panel_orientation_quirks.c
++++ b/drivers/gpu/drm/drm_panel_orientation_quirks.c
+@@ -414,6 +414,12 @@ static const struct dmi_system_id orientation_data[] = {
+ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "ONE XPLAYER"),
+ },
+ .driver_data = (void *)&lcd1600x2560_leftside_up,
++ }, { /* OrangePi Neo */
++ .matches = {
++ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "OrangePi"),
++ DMI_EXACT_MATCH(DMI_PRODUCT_NAME, "NEO-01"),
++ },
++ .driver_data = (void *)&lcd1200x1920_rightside_up,
+ }, { /* Samsung GalaxyBook 10.6 */
+ .matches = {
+ DMI_EXACT_MATCH(DMI_SYS_VENDOR, "SAMSUNG ELECTRONICS CO., LTD."),
+diff --git a/drivers/gpu/drm/meson/meson_plane.c b/drivers/gpu/drm/meson/meson_plane.c
+index 815dfe30492b6..b43ac61201f31 100644
+--- a/drivers/gpu/drm/meson/meson_plane.c
++++ b/drivers/gpu/drm/meson/meson_plane.c
+@@ -534,6 +534,7 @@ int meson_plane_create(struct meson_drm *priv)
+ struct meson_plane *meson_plane;
+ struct drm_plane *plane;
+ const uint64_t *format_modifiers = format_modifiers_default;
++ int ret;
+
+ meson_plane = devm_kzalloc(priv->drm->dev, sizeof(*meson_plane),
+ GFP_KERNEL);
+@@ -548,12 +549,16 @@ int meson_plane_create(struct meson_drm *priv)
+ else if (meson_vpu_is_compatible(priv, VPU_COMPATIBLE_G12A))
+ format_modifiers = format_modifiers_afbc_g12a;
+
+- drm_universal_plane_init(priv->drm, plane, 0xFF,
+- &meson_plane_funcs,
+- supported_drm_formats,
+- ARRAY_SIZE(supported_drm_formats),
+- format_modifiers,
+- DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane");
++ ret = drm_universal_plane_init(priv->drm, plane, 0xFF,
++ &meson_plane_funcs,
++ supported_drm_formats,
++ ARRAY_SIZE(supported_drm_formats),
++ format_modifiers,
++ DRM_PLANE_TYPE_PRIMARY, "meson_primary_plane");
++ if (ret) {
++ devm_kfree(priv->drm->dev, meson_plane);
++ return ret;
++ }
+
+ drm_plane_helper_add(plane, &meson_plane_helper_funcs);
+
+diff --git a/drivers/gpu/drm/xe/xe_force_wake.h b/drivers/gpu/drm/xe/xe_force_wake.h
+index 83cb157da7cc6..a2577672f4e3e 100644
+--- a/drivers/gpu/drm/xe/xe_force_wake.h
++++ b/drivers/gpu/drm/xe/xe_force_wake.h
+@@ -24,14 +24,25 @@ static inline int
+ xe_force_wake_ref(struct xe_force_wake *fw,
+ enum xe_force_wake_domains domain)
+ {
+- xe_gt_assert(fw->gt, domain);
++ xe_gt_assert(fw->gt, domain != XE_FORCEWAKE_ALL);
+ return fw->domains[ffs(domain) - 1].ref;
+ }
+
++/**
++ * xe_force_wake_assert_held - asserts domain is awake
++ * @fw : xe_force_wake structure
++ * @domain: xe_force_wake_domains apart from XE_FORCEWAKE_ALL
++ *
++ * xe_force_wake_assert_held() is designed to confirm a particular
++ * forcewake domain's wakefulness; it doesn't verify the wakefulness of
++ * multiple domains. Make sure the caller doesn't input multiple
++ * domains(XE_FORCEWAKE_ALL) as a parameter.
++ */
+ static inline void
+ xe_force_wake_assert_held(struct xe_force_wake *fw,
+ enum xe_force_wake_domains domain)
+ {
++ xe_gt_assert(fw->gt, domain != XE_FORCEWAKE_ALL);
+ xe_gt_assert(fw->gt, fw->awake_domains & domain);
+ }
+
+diff --git a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
+index 396aeb5b99242..a34c9a24dafc7 100644
+--- a/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
++++ b/drivers/gpu/drm/xe/xe_gt_ccs_mode.c
+@@ -68,8 +68,8 @@ static void __xe_gt_apply_ccs_mode(struct xe_gt *gt, u32 num_engines)
+
+ xe_mmio_write32(gt, CCS_MODE, mode);
+
+- xe_gt_info(gt, "CCS_MODE=%x config:%08x, num_engines:%d, num_slices:%d\n",
+- mode, config, num_engines, num_slices);
++ xe_gt_dbg(gt, "CCS_MODE=%x config:%08x, num_engines:%d, num_slices:%d\n",
++ mode, config, num_engines, num_slices);
+ }
+
+ void xe_gt_apply_ccs_mode(struct xe_gt *gt)
+diff --git a/drivers/gpu/drm/xe/xe_gt_topology.c b/drivers/gpu/drm/xe/xe_gt_topology.c
+index 3733e7a6860d3..d224ed1b5c0f9 100644
+--- a/drivers/gpu/drm/xe/xe_gt_topology.c
++++ b/drivers/gpu/drm/xe/xe_gt_topology.c
+@@ -108,7 +108,9 @@ gen_l3_mask_from_pattern(struct xe_device *xe, xe_l3_bank_mask_t dst,
+ {
+ unsigned long bit;
+
+- xe_assert(xe, fls(mask) <= patternbits);
++ xe_assert(xe, find_last_bit(pattern, XE_MAX_L3_BANK_MASK_BITS) < patternbits ||
++ bitmap_empty(pattern, XE_MAX_L3_BANK_MASK_BITS));
++ xe_assert(xe, !mask || patternbits * (__fls(mask) + 1) <= XE_MAX_L3_BANK_MASK_BITS);
+ for_each_set_bit(bit, &mask, 32) {
+ xe_l3_bank_mask_t shifted_pattern = {};
+
+diff --git a/drivers/gpu/drm/xe/xe_guc_relay.c b/drivers/gpu/drm/xe/xe_guc_relay.c
+index c0a2d8d5d3b3c..b49137ea6d843 100644
+--- a/drivers/gpu/drm/xe/xe_guc_relay.c
++++ b/drivers/gpu/drm/xe/xe_guc_relay.c
+@@ -757,7 +757,14 @@ static void relay_process_incoming_action(struct xe_guc_relay *relay)
+
+ static bool relay_needs_worker(struct xe_guc_relay *relay)
+ {
+- return !list_empty(&relay->incoming_actions);
++ bool is_empty;
++
++ spin_lock(&relay->lock);
++ is_empty = list_empty(&relay->incoming_actions);
++ spin_unlock(&relay->lock);
++
++ return !is_empty;
++
+ }
+
+ static void relay_kick_worker(struct xe_guc_relay *relay)
+diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
+index e48285c81bf57..0a496612c810f 100644
+--- a/drivers/gpu/drm/xe/xe_guc_submit.c
++++ b/drivers/gpu/drm/xe/xe_guc_submit.c
+@@ -1551,6 +1551,11 @@ static void deregister_exec_queue(struct xe_guc *guc, struct xe_exec_queue *q)
+ q->guc->id,
+ };
+
++ xe_gt_assert(guc_to_gt(guc), exec_queue_destroyed(q));
++ xe_gt_assert(guc_to_gt(guc), exec_queue_registered(q));
++ xe_gt_assert(guc_to_gt(guc), !exec_queue_pending_disable(q));
++ xe_gt_assert(guc_to_gt(guc), !exec_queue_pending_enable(q));
++
+ trace_xe_exec_queue_deregister(q);
+
+ xe_guc_ct_send_g2h_handler(&guc->ct, action, ARRAY_SIZE(action));
+diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
+index bb815dbde63a6..daf0d15354fea 100644
+--- a/drivers/gpu/drm/xe/xe_hwmon.c
++++ b/drivers/gpu/drm/xe/xe_hwmon.c
+@@ -551,12 +551,17 @@ xe_hwmon_curr_is_visible(const struct xe_hwmon *hwmon, u32 attr, int channel)
+ {
+ u32 uval;
+
++ /* hwmon sysfs attribute of current available only for package */
++ if (channel != CHANNEL_PKG)
++ return 0;
++
+ switch (attr) {
+ case hwmon_curr_crit:
+- case hwmon_curr_label:
+- if (channel == CHANNEL_PKG)
+ return (xe_hwmon_pcode_read_i1(hwmon->gt, &uval) ||
+ (uval & POWER_SETUP_I1_WATTS)) ? 0 : 0644;
++ case hwmon_curr_label:
++ return (xe_hwmon_pcode_read_i1(hwmon->gt, &uval) ||
++ (uval & POWER_SETUP_I1_WATTS)) ? 0 : 0444;
+ break;
+ default:
+ return 0;
+diff --git a/drivers/gpu/drm/xe/xe_migrate.c b/drivers/gpu/drm/xe/xe_migrate.c
+index 198f5c2189cb4..208649436fdb3 100644
+--- a/drivers/gpu/drm/xe/xe_migrate.c
++++ b/drivers/gpu/drm/xe/xe_migrate.c
+@@ -69,7 +69,7 @@ struct xe_migrate {
+
+ #define MAX_PREEMPTDISABLE_TRANSFER SZ_8M /* Around 1ms. */
+ #define MAX_CCS_LIMITED_TRANSFER SZ_4M /* XE_PAGE_SIZE * (FIELD_MAX(XE2_CCS_SIZE_MASK) + 1) */
+-#define NUM_KERNEL_PDE 17
++#define NUM_KERNEL_PDE 15
+ #define NUM_PT_SLOTS 32
+ #define LEVEL0_PAGE_TABLE_ENCODE_SIZE SZ_2M
+ #define MAX_NUM_PTE 512
+@@ -137,10 +137,11 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
+ struct xe_device *xe = tile_to_xe(tile);
+ u16 pat_index = xe->pat.idx[XE_CACHE_WB];
+ u8 id = tile->id;
+- u32 num_entries = NUM_PT_SLOTS, num_level = vm->pt_root[id]->level;
++ u32 num_entries = NUM_PT_SLOTS, num_level = vm->pt_root[id]->level,
++ num_setup = num_level + 1;
+ u32 map_ofs, level, i;
+ struct xe_bo *bo, *batch = tile->mem.kernel_bb_pool->bo;
+- u64 entry;
++ u64 entry, pt30_ofs;
+
+ /* Can't bump NUM_PT_SLOTS too high */
+ BUILD_BUG_ON(NUM_PT_SLOTS > SZ_2M/XE_PAGE_SIZE);
+@@ -160,10 +161,12 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
+ if (IS_ERR(bo))
+ return PTR_ERR(bo);
+
+- entry = vm->pt_ops->pde_encode_bo(bo, bo->size - XE_PAGE_SIZE, pat_index);
++ /* PT31 reserved for 2M identity map */
++ pt30_ofs = bo->size - 2 * XE_PAGE_SIZE;
++ entry = vm->pt_ops->pde_encode_bo(bo, pt30_ofs, pat_index);
+ xe_pt_write(xe, &vm->pt_root[id]->bo->vmap, 0, entry);
+
+- map_ofs = (num_entries - num_level) * XE_PAGE_SIZE;
++ map_ofs = (num_entries - num_setup) * XE_PAGE_SIZE;
+
+ /* Map the entire BO in our level 0 pt */
+ for (i = 0, level = 0; i < num_entries; level++) {
+@@ -234,7 +237,7 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
+ }
+
+ /* Write PDE's that point to our BO. */
+- for (i = 0; i < num_entries - num_level; i++) {
++ for (i = 0; i < map_ofs / PAGE_SIZE; i++) {
+ entry = vm->pt_ops->pde_encode_bo(bo, (u64)i * XE_PAGE_SIZE,
+ pat_index);
+
+@@ -252,28 +255,54 @@ static int xe_migrate_prepare_vm(struct xe_tile *tile, struct xe_migrate *m,
+ /* Identity map the entire vram at 256GiB offset */
+ if (IS_DGFX(xe)) {
+ u64 pos, ofs, flags;
++ /* XXX: Unclear if this should be usable_size? */
++ u64 vram_limit = xe->mem.vram.actual_physical_size +
++ xe->mem.vram.dpa_base;
+
+ level = 2;
+ ofs = map_ofs + XE_PAGE_SIZE * level + 256 * 8;
+ flags = vm->pt_ops->pte_encode_addr(xe, 0, pat_index, level,
+ true, 0);
+
++ xe_assert(xe, IS_ALIGNED(xe->mem.vram.usable_size, SZ_2M));
++
+ /*
+- * Use 1GB pages, it shouldn't matter the physical amount of
+- * vram is less, when we don't access it.
++ * Use 1GB pages when possible, last chunk always use 2M
++ * pages as mixing reserved memory (stolen, WOCPM) with a single
++ * mapping is not allowed on certain platforms.
+ */
+- for (pos = xe->mem.vram.dpa_base;
+- pos < xe->mem.vram.actual_physical_size + xe->mem.vram.dpa_base;
+- pos += SZ_1G, ofs += 8)
++ for (pos = xe->mem.vram.dpa_base; pos < vram_limit;
++ pos += SZ_1G, ofs += 8) {
++ if (pos + SZ_1G >= vram_limit) {
++ u64 pt31_ofs = bo->size - XE_PAGE_SIZE;
++
++ entry = vm->pt_ops->pde_encode_bo(bo, pt31_ofs,
++ pat_index);
++ xe_map_wr(xe, &bo->vmap, ofs, u64, entry);
++
++ flags = vm->pt_ops->pte_encode_addr(xe, 0,
++ pat_index,
++ level - 1,
++ true, 0);
++
++ for (ofs = pt31_ofs; pos < vram_limit;
++ pos += SZ_2M, ofs += 8)
++ xe_map_wr(xe, &bo->vmap, ofs, u64, pos | flags);
++ break; /* Ensure pos == vram_limit assert correct */
++ }
++
+ xe_map_wr(xe, &bo->vmap, ofs, u64, pos | flags);
++ }
++
++ xe_assert(xe, pos == vram_limit);
+ }
+
+ /*
+ * Example layout created above, with root level = 3:
+ * [PT0...PT7]: kernel PT's for copy/clear; 64 or 4KiB PTE's
+ * [PT8]: Kernel PT for VM_BIND, 4 KiB PTE's
+- * [PT9...PT28]: Userspace PT's for VM_BIND, 4 KiB PTE's
+- * [PT29 = PDE 0] [PT30 = PDE 1] [PT31 = PDE 2]
++ * [PT9...PT27]: Userspace PT's for VM_BIND, 4 KiB PTE's
++ * [PT28 = PDE 0] [PT29 = PDE 1] [PT30 = PDE 2] [PT31 = 2M vram identity map]
+ *
+ * This makes the lowest part of the VM point to the pagetables.
+ * Hence the lowest 2M in the vm should point to itself, with a few writes
+diff --git a/drivers/gpu/drm/xe/xe_pcode.c b/drivers/gpu/drm/xe/xe_pcode.c
+index a5e7da8cf9441..9c4eefdf66428 100644
+--- a/drivers/gpu/drm/xe/xe_pcode.c
++++ b/drivers/gpu/drm/xe/xe_pcode.c
+@@ -10,6 +10,7 @@
+
+ #include <drm/drm_managed.h>
+
++#include "xe_assert.h"
+ #include "xe_device.h"
+ #include "xe_gt.h"
+ #include "xe_mmio.h"
+@@ -124,6 +125,8 @@ static int pcode_try_request(struct xe_gt *gt, u32 mbox,
+ {
+ int slept, wait = 10;
+
++ xe_gt_assert(gt, timeout_us > 0);
++
+ for (slept = 0; slept < timeout_us; slept += wait) {
+ if (locked)
+ *status = pcode_mailbox_rw(gt, mbox, &request, NULL, 1, true,
+@@ -169,6 +172,8 @@ int xe_pcode_request(struct xe_gt *gt, u32 mbox, u32 request,
+ u32 status;
+ int ret;
+
++ xe_gt_assert(gt, timeout_base_ms <= 3);
++
+ mutex_lock(>->pcode.lock);
+
+ ret = pcode_try_request(gt, mbox, request, reply_mask, reply, &status,
+@@ -188,7 +193,6 @@ int xe_pcode_request(struct xe_gt *gt, u32 mbox, u32 request,
+ */
+ drm_err(>_to_xe(gt)->drm,
+ "PCODE timeout, retrying with preemption disabled\n");
+- drm_WARN_ON_ONCE(>_to_xe(gt)->drm, timeout_base_ms > 1);
+ preempt_disable();
+ ret = pcode_try_request(gt, mbox, request, reply_mask, reply, &status,
+ true, 50 * 1000, true);
+diff --git a/drivers/hwmon/k10temp.c b/drivers/hwmon/k10temp.c
+index 8092312c0a877..6cad35e7f1828 100644
+--- a/drivers/hwmon/k10temp.c
++++ b/drivers/hwmon/k10temp.c
+@@ -153,8 +153,9 @@ static void read_tempreg_nb_f15(struct pci_dev *pdev, u32 *regval)
+
+ static void read_tempreg_nb_zen(struct pci_dev *pdev, u32 *regval)
+ {
+- amd_smn_read(amd_pci_dev_to_node_id(pdev),
+- ZEN_REPORTED_TEMP_CTRL_BASE, regval);
++ if (amd_smn_read(amd_pci_dev_to_node_id(pdev),
++ ZEN_REPORTED_TEMP_CTRL_BASE, regval))
++ *regval = 0;
+ }
+
+ static long get_raw_temp(struct k10temp_data *data)
+@@ -205,6 +206,7 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel,
+ long *val)
+ {
+ struct k10temp_data *data = dev_get_drvdata(dev);
++ int ret = -EOPNOTSUPP;
+ u32 regval;
+
+ switch (attr) {
+@@ -221,13 +223,17 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel,
+ *val = 0;
+ break;
+ case 2 ... 13: /* Tccd{1-12} */
+- amd_smn_read(amd_pci_dev_to_node_id(data->pdev),
+- ZEN_CCD_TEMP(data->ccd_offset, channel - 2),
+- ®val);
++ ret = amd_smn_read(amd_pci_dev_to_node_id(data->pdev),
++ ZEN_CCD_TEMP(data->ccd_offset, channel - 2),
++ ®val);
++
++ if (ret)
++ return ret;
++
+ *val = (regval & ZEN_CCD_TEMP_MASK) * 125 - 49000;
+ break;
+ default:
+- return -EOPNOTSUPP;
++ return ret;
+ }
+ break;
+ case hwmon_temp_max:
+@@ -243,7 +249,7 @@ static int k10temp_read_temp(struct device *dev, u32 attr, int channel,
+ - ((regval >> 24) & 0xf)) * 500 + 52000;
+ break;
+ default:
+- return -EOPNOTSUPP;
++ return ret;
+ }
+ return 0;
+ }
+@@ -381,8 +387,20 @@ static void k10temp_get_ccd_support(struct pci_dev *pdev,
+ int i;
+
+ for (i = 0; i < limit; i++) {
+- amd_smn_read(amd_pci_dev_to_node_id(pdev),
+- ZEN_CCD_TEMP(data->ccd_offset, i), ®val);
++ /*
++ * Ignore inaccessible CCDs.
++ *
++ * Some systems will return a register value of 0, and the TEMP_VALID
++ * bit check below will naturally fail.
++ *
++ * Other systems will return a PCI_ERROR_RESPONSE (0xFFFFFFFF) for
++ * the register value. And this will incorrectly pass the TEMP_VALID
++ * bit check.
++ */
++ if (amd_smn_read(amd_pci_dev_to_node_id(pdev),
++ ZEN_CCD_TEMP(data->ccd_offset, i), ®val))
++ continue;
++
+ if (regval & ZEN_CCD_TEMP_VALID)
+ data->show_temp |= BIT(TCCD_BIT(i));
+ }
+diff --git a/drivers/hwspinlock/hwspinlock_core.c b/drivers/hwspinlock/hwspinlock_core.c
+index 0c0a932c00f35..6505261e60686 100644
+--- a/drivers/hwspinlock/hwspinlock_core.c
++++ b/drivers/hwspinlock/hwspinlock_core.c
+@@ -305,6 +305,34 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags)
+ }
+ EXPORT_SYMBOL_GPL(__hwspin_unlock);
+
++/**
++ * hwspin_lock_bust() - bust a specific hwspinlock
++ * @hwlock: a previously-acquired hwspinlock which we want to bust
++ * @id: identifier of the remote lock holder, if applicable
++ *
++ * This function will bust a hwspinlock that was previously acquired as
++ * long as the current owner of the lock matches the id given by the caller.
++ *
++ * Context: Process context.
++ *
++ * Returns: 0 on success, or -EINVAL if the hwspinlock does not exist, or
++ * the bust operation fails, and -EOPNOTSUPP if the bust operation is not
++ * defined for the hwspinlock.
++ */
++int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id)
++{
++ if (WARN_ON(!hwlock))
++ return -EINVAL;
++
++ if (!hwlock->bank->ops->bust) {
++ pr_err("bust operation not defined\n");
++ return -EOPNOTSUPP;
++ }
++
++ return hwlock->bank->ops->bust(hwlock, id);
++}
++EXPORT_SYMBOL_GPL(hwspin_lock_bust);
++
+ /**
+ * of_hwspin_lock_simple_xlate - translate hwlock_spec to return a lock id
+ * @hwlock_spec: hwlock specifier as found in the device tree
+diff --git a/drivers/hwspinlock/hwspinlock_internal.h b/drivers/hwspinlock/hwspinlock_internal.h
+index 29892767bb7a0..f298fc0ee5adb 100644
+--- a/drivers/hwspinlock/hwspinlock_internal.h
++++ b/drivers/hwspinlock/hwspinlock_internal.h
+@@ -21,6 +21,8 @@ struct hwspinlock_device;
+ * @trylock: make a single attempt to take the lock. returns 0 on
+ * failure and true on success. may _not_ sleep.
+ * @unlock: release the lock. always succeed. may _not_ sleep.
++ * @bust: optional, platform-specific bust handler, called by hwspinlock
++ * core to bust a specific lock.
+ * @relax: optional, platform-specific relax handler, called by hwspinlock
+ * core while spinning on a lock, between two successive
+ * invocations of @trylock. may _not_ sleep.
+@@ -28,6 +30,7 @@ struct hwspinlock_device;
+ struct hwspinlock_ops {
+ int (*trylock)(struct hwspinlock *lock);
+ void (*unlock)(struct hwspinlock *lock);
++ int (*bust)(struct hwspinlock *lock, unsigned int id);
+ void (*relax)(struct hwspinlock *lock);
+ };
+
+diff --git a/drivers/iio/industrialio-core.c b/drivers/iio/industrialio-core.c
+index fa7cc051b4c49..2f185b3869495 100644
+--- a/drivers/iio/industrialio-core.c
++++ b/drivers/iio/industrialio-core.c
+@@ -758,9 +758,11 @@ static ssize_t iio_read_channel_info(struct device *dev,
+ INDIO_MAX_RAW_ELEMENTS,
+ vals, &val_len,
+ this_attr->address);
+- else
++ else if (indio_dev->info->read_raw)
+ ret = indio_dev->info->read_raw(indio_dev, this_attr->c,
+ &vals[0], &vals[1], this_attr->address);
++ else
++ return -EINVAL;
+
+ if (ret < 0)
+ return ret;
+@@ -842,6 +844,9 @@ static ssize_t iio_read_channel_info_avail(struct device *dev,
+ int length;
+ int type;
+
++ if (!indio_dev->info->read_avail)
++ return -EINVAL;
++
+ ret = indio_dev->info->read_avail(indio_dev, this_attr->c,
+ &vals, &type, &length,
+ this_attr->address);
+diff --git a/drivers/iio/industrialio-event.c b/drivers/iio/industrialio-event.c
+index 910c1f14abd55..a64f8fbac597e 100644
+--- a/drivers/iio/industrialio-event.c
++++ b/drivers/iio/industrialio-event.c
+@@ -285,6 +285,9 @@ static ssize_t iio_ev_state_store(struct device *dev,
+ if (ret < 0)
+ return ret;
+
++ if (!indio_dev->info->write_event_config)
++ return -EINVAL;
++
+ ret = indio_dev->info->write_event_config(indio_dev,
+ this_attr->c, iio_ev_attr_type(this_attr),
+ iio_ev_attr_dir(this_attr), val);
+@@ -300,6 +303,9 @@ static ssize_t iio_ev_state_show(struct device *dev,
+ struct iio_dev_attr *this_attr = to_iio_dev_attr(attr);
+ int val;
+
++ if (!indio_dev->info->read_event_config)
++ return -EINVAL;
++
+ val = indio_dev->info->read_event_config(indio_dev,
+ this_attr->c, iio_ev_attr_type(this_attr),
+ iio_ev_attr_dir(this_attr));
+@@ -318,6 +324,9 @@ static ssize_t iio_ev_value_show(struct device *dev,
+ int val, val2, val_arr[2];
+ int ret;
+
++ if (!indio_dev->info->read_event_value)
++ return -EINVAL;
++
+ ret = indio_dev->info->read_event_value(indio_dev,
+ this_attr->c, iio_ev_attr_type(this_attr),
+ iio_ev_attr_dir(this_attr), iio_ev_attr_info(this_attr),
+diff --git a/drivers/iio/inkern.c b/drivers/iio/inkern.c
+index 485e6fc44a04c..39cf26d69d17a 100644
+--- a/drivers/iio/inkern.c
++++ b/drivers/iio/inkern.c
+@@ -543,6 +543,7 @@ EXPORT_SYMBOL_GPL(devm_iio_channel_get_all);
+ static int iio_channel_read(struct iio_channel *chan, int *val, int *val2,
+ enum iio_chan_info_enum info)
+ {
++ const struct iio_info *iio_info = chan->indio_dev->info;
+ int unused;
+ int vals[INDIO_MAX_RAW_ELEMENTS];
+ int ret;
+@@ -554,15 +555,18 @@ static int iio_channel_read(struct iio_channel *chan, int *val, int *val2,
+ if (!iio_channel_has_info(chan->channel, info))
+ return -EINVAL;
+
+- if (chan->indio_dev->info->read_raw_multi) {
+- ret = chan->indio_dev->info->read_raw_multi(chan->indio_dev,
+- chan->channel, INDIO_MAX_RAW_ELEMENTS,
+- vals, &val_len, info);
++ if (iio_info->read_raw_multi) {
++ ret = iio_info->read_raw_multi(chan->indio_dev,
++ chan->channel,
++ INDIO_MAX_RAW_ELEMENTS,
++ vals, &val_len, info);
+ *val = vals[0];
+ *val2 = vals[1];
++ } else if (iio_info->read_raw) {
++ ret = iio_info->read_raw(chan->indio_dev,
++ chan->channel, val, val2, info);
+ } else {
+- ret = chan->indio_dev->info->read_raw(chan->indio_dev,
+- chan->channel, val, val2, info);
++ return -EINVAL;
+ }
+
+ return ret;
+@@ -750,11 +754,15 @@ static int iio_channel_read_avail(struct iio_channel *chan,
+ const int **vals, int *type, int *length,
+ enum iio_chan_info_enum info)
+ {
++ const struct iio_info *iio_info = chan->indio_dev->info;
++
+ if (!iio_channel_has_available(chan->channel, info))
+ return -EINVAL;
+
+- return chan->indio_dev->info->read_avail(chan->indio_dev, chan->channel,
+- vals, type, length, info);
++ if (iio_info->read_avail)
++ return iio_info->read_avail(chan->indio_dev, chan->channel,
++ vals, type, length, info);
++ return -EINVAL;
+ }
+
+ int iio_read_avail_channel_attribute(struct iio_channel *chan,
+@@ -917,8 +925,12 @@ EXPORT_SYMBOL_GPL(iio_get_channel_type);
+ static int iio_channel_write(struct iio_channel *chan, int val, int val2,
+ enum iio_chan_info_enum info)
+ {
+- return chan->indio_dev->info->write_raw(chan->indio_dev,
+- chan->channel, val, val2, info);
++ const struct iio_info *iio_info = chan->indio_dev->info;
++
++ if (iio_info->write_raw)
++ return iio_info->write_raw(chan->indio_dev,
++ chan->channel, val, val2, info);
++ return -EINVAL;
+ }
+
+ int iio_write_channel_attribute(struct iio_channel *chan, int val, int val2,
+diff --git a/drivers/infiniband/hw/efa/efa_com.c b/drivers/infiniband/hw/efa/efa_com.c
+index 16a24a05fc2a6..bafd210dd43e8 100644
+--- a/drivers/infiniband/hw/efa/efa_com.c
++++ b/drivers/infiniband/hw/efa/efa_com.c
+@@ -1,6 +1,6 @@
+ // SPDX-License-Identifier: GPL-2.0 OR BSD-2-Clause
+ /*
+- * Copyright 2018-2021 Amazon.com, Inc. or its affiliates. All rights reserved.
++ * Copyright 2018-2024 Amazon.com, Inc. or its affiliates. All rights reserved.
+ */
+
+ #include "efa_com.h"
+@@ -406,8 +406,8 @@ static struct efa_comp_ctx *efa_com_submit_admin_cmd(struct efa_com_admin_queue
+ return comp_ctx;
+ }
+
+-static void efa_com_handle_single_admin_completion(struct efa_com_admin_queue *aq,
+- struct efa_admin_acq_entry *cqe)
++static int efa_com_handle_single_admin_completion(struct efa_com_admin_queue *aq,
++ struct efa_admin_acq_entry *cqe)
+ {
+ struct efa_comp_ctx *comp_ctx;
+ u16 cmd_id;
+@@ -416,11 +416,11 @@ static void efa_com_handle_single_admin_completion(struct efa_com_admin_queue *a
+ EFA_ADMIN_ACQ_COMMON_DESC_COMMAND_ID);
+
+ comp_ctx = efa_com_get_comp_ctx(aq, cmd_id, false);
+- if (!comp_ctx) {
++ if (comp_ctx->status != EFA_CMD_SUBMITTED) {
+ ibdev_err(aq->efa_dev,
+- "comp_ctx is NULL. Changing the admin queue running state\n");
+- clear_bit(EFA_AQ_STATE_RUNNING_BIT, &aq->state);
+- return;
++ "Received completion with unexpected command id[%d], sq producer: %d, sq consumer: %d, cq consumer: %d\n",
++ cmd_id, aq->sq.pc, aq->sq.cc, aq->cq.cc);
++ return -EINVAL;
+ }
+
+ comp_ctx->status = EFA_CMD_COMPLETED;
+@@ -428,14 +428,17 @@ static void efa_com_handle_single_admin_completion(struct efa_com_admin_queue *a
+
+ if (!test_bit(EFA_AQ_STATE_POLLING_BIT, &aq->state))
+ complete(&comp_ctx->wait_event);
++
++ return 0;
+ }
+
+ static void efa_com_handle_admin_completion(struct efa_com_admin_queue *aq)
+ {
+ struct efa_admin_acq_entry *cqe;
+ u16 queue_size_mask;
+- u16 comp_num = 0;
++ u16 comp_cmds = 0;
+ u8 phase;
++ int err;
+ u16 ci;
+
+ queue_size_mask = aq->depth - 1;
+@@ -453,10 +456,12 @@ static void efa_com_handle_admin_completion(struct efa_com_admin_queue *aq)
+ * phase bit was validated
+ */
+ dma_rmb();
+- efa_com_handle_single_admin_completion(aq, cqe);
++ err = efa_com_handle_single_admin_completion(aq, cqe);
++ if (!err)
++ comp_cmds++;
+
++ aq->cq.cc++;
+ ci++;
+- comp_num++;
+ if (ci == aq->depth) {
+ ci = 0;
+ phase = !phase;
+@@ -465,10 +470,9 @@ static void efa_com_handle_admin_completion(struct efa_com_admin_queue *aq)
+ cqe = &aq->cq.entries[ci];
+ }
+
+- aq->cq.cc += comp_num;
+ aq->cq.phase = phase;
+- aq->sq.cc += comp_num;
+- atomic64_add(comp_num, &aq->stats.completed_cmd);
++ aq->sq.cc += comp_cmds;
++ atomic64_add(comp_cmds, &aq->stats.completed_cmd);
+ }
+
+ static int efa_com_comp_status_to_errno(u8 comp_status)
+diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
+index d435b6a6c295d..13c2c11cfdf64 100644
+--- a/drivers/media/usb/uvc/uvc_driver.c
++++ b/drivers/media/usb/uvc/uvc_driver.c
+@@ -687,16 +687,26 @@ static int uvc_parse_streaming(struct uvc_device *dev,
+ goto error;
+ }
+
+- size = nformats * sizeof(*format) + nframes * sizeof(*frame)
++ /*
++ * Allocate memory for the formats, the frames and the intervals,
++ * plus any required padding to guarantee that everything has the
++ * correct alignment.
++ */
++ size = nformats * sizeof(*format);
++ size = ALIGN(size, __alignof__(*frame)) + nframes * sizeof(*frame);
++ size = ALIGN(size, __alignof__(*interval))
+ + nintervals * sizeof(*interval);
++
+ format = kzalloc(size, GFP_KERNEL);
+- if (format == NULL) {
++ if (!format) {
+ ret = -ENOMEM;
+ goto error;
+ }
+
+- frame = (struct uvc_frame *)&format[nformats];
+- interval = (u32 *)&frame[nframes];
++ frame = (void *)format + nformats * sizeof(*format);
++ frame = PTR_ALIGN(frame, __alignof__(*frame));
++ interval = (void *)frame + nframes * sizeof(*frame);
++ interval = PTR_ALIGN(interval, __alignof__(*interval));
+
+ streaming->formats = format;
+ streaming->nformats = 0;
+diff --git a/drivers/media/v4l2-core/v4l2-cci.c b/drivers/media/v4l2-core/v4l2-cci.c
+index ee3475bed37fa..1ff94affbaf3a 100644
+--- a/drivers/media/v4l2-core/v4l2-cci.c
++++ b/drivers/media/v4l2-core/v4l2-cci.c
+@@ -23,6 +23,15 @@ int cci_read(struct regmap *map, u32 reg, u64 *val, int *err)
+ u8 buf[8];
+ int ret;
+
++ /*
++ * TODO: Fix smatch. Assign *val to 0 here in order to avoid
++ * failing a smatch check on caller when the caller proceeds to
++ * read *val without initialising it on caller's side. *val is set
++ * to a valid value whenever this function returns 0 but smatch
++ * can't figure that out currently.
++ */
++ *val = 0;
++
+ if (err && *err)
+ return *err;
+
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+index cdc84a27a04ed..0138f77eaeed0 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+@@ -2369,7 +2369,8 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
+ if (flush)
+ mlx5e_shampo_flush_skb(rq, cqe, match);
+ free_hd_entry:
+- mlx5e_free_rx_shampo_hd_entry(rq, header_index);
++ if (likely(head_size))
++ mlx5e_free_rx_shampo_hd_entry(rq, header_index);
+ mpwrq_cqe_out:
+ if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
+ return;
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+index 042ca03491243..d1db04baa1fa6 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/steering/dr_rule.c
+@@ -7,7 +7,7 @@
+ /* don't try to optimize STE allocation if the stack is too constaraining */
+ #define DR_RULE_MAX_STES_OPTIMIZED 0
+ #else
+-#define DR_RULE_MAX_STES_OPTIMIZED 5
++#define DR_RULE_MAX_STES_OPTIMIZED 2
+ #endif
+ #define DR_RULE_MAX_STE_CHAIN_OPTIMIZED (DR_RULE_MAX_STES_OPTIMIZED + DR_ACTION_MAX_STES)
+
+diff --git a/drivers/net/ethernet/pensando/ionic/ionic_lif.c b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+index 1837a30ba08ac..f64d18949f68b 100644
+--- a/drivers/net/ethernet/pensando/ionic/ionic_lif.c
++++ b/drivers/net/ethernet/pensando/ionic/ionic_lif.c
+@@ -242,7 +242,7 @@ static int ionic_request_irq(struct ionic_lif *lif, struct ionic_qcq *qcq)
+ name = dev_name(dev);
+
+ snprintf(intr->name, sizeof(intr->name),
+- "%s-%s-%s", IONIC_DRV_NAME, name, q->name);
++ "%.5s-%.16s-%.8s", IONIC_DRV_NAME, name, q->name);
+
+ return devm_request_irq(dev, intr->vector, ionic_isr,
+ 0, intr->name, &qcq->napi);
+diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
+index cfda32047cffb..4823dbdf54656 100644
+--- a/drivers/net/usb/qmi_wwan.c
++++ b/drivers/net/usb/qmi_wwan.c
+@@ -1432,6 +1432,7 @@ static const struct usb_device_id products[] = {
+ {QMI_QUIRK_SET_DTR(0x1546, 0x1312, 4)}, /* u-blox LARA-R6 01B */
+ {QMI_QUIRK_SET_DTR(0x1546, 0x1342, 4)}, /* u-blox LARA-L6 */
+ {QMI_QUIRK_SET_DTR(0x33f8, 0x0104, 4)}, /* Rolling RW101 RMNET */
++ {QMI_FIXED_INTF(0x2dee, 0x4d22, 5)}, /* MeiG Smart SRM825L */
+
+ /* 4. Gobi 1000 devices */
+ {QMI_GOBI1K_DEVICE(0x05c6, 0x9212)}, /* Acer Gobi Modem Device */
+diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
+index f32e017b62e9b..21bd0c127b05a 100644
+--- a/drivers/net/virtio_net.c
++++ b/drivers/net/virtio_net.c
+@@ -3172,6 +3172,9 @@ static int virtnet_send_rx_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+ {
+ int err;
+
++ if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
++ return -EOPNOTSUPP;
++
+ err = virtnet_send_ctrl_coal_vq_cmd(vi, rxq2vq(queue),
+ max_usecs, max_packets);
+ if (err)
+@@ -3189,6 +3192,9 @@ static int virtnet_send_tx_ctrl_coal_vq_cmd(struct virtnet_info *vi,
+ {
+ int err;
+
++ if (!virtio_has_feature(vi->vdev, VIRTIO_NET_F_VQ_NOTF_COAL))
++ return -EOPNOTSUPP;
++
+ err = virtnet_send_ctrl_coal_vq_cmd(vi, txq2vq(queue),
+ max_usecs, max_packets);
+ if (err)
+diff --git a/drivers/net/wireless/ath/ath11k/qmi.c b/drivers/net/wireless/ath/ath11k/qmi.c
+index d4a243b64f6c3..aa160e6fe24f1 100644
+--- a/drivers/net/wireless/ath/ath11k/qmi.c
++++ b/drivers/net/wireless/ath/ath11k/qmi.c
+@@ -2293,7 +2293,7 @@ static int ath11k_qmi_load_file_target_mem(struct ath11k_base *ab,
+ struct qmi_txn txn;
+ const u8 *temp = data;
+ void __iomem *bdf_addr = NULL;
+- int ret;
++ int ret = 0;
+ u32 remaining = len;
+
+ req = kzalloc(sizeof(*req), GFP_KERNEL);
+diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
+index 1d287ed25a949..3cdc4c51d6dfe 100644
+--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
++++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
+@@ -4058,7 +4058,7 @@ int ath12k_dp_rxdma_ring_sel_config_wcn7850(struct ath12k_base *ab)
+ struct ath12k_dp *dp = &ab->dp;
+ struct htt_rx_ring_tlv_filter tlv_filter = {0};
+ u32 ring_id;
+- int ret;
++ int ret = 0;
+ u32 hal_rx_desc_sz = ab->hal.hal_desc_sz;
+ int i;
+
+diff --git a/drivers/net/wireless/ath/ath12k/qmi.c b/drivers/net/wireless/ath/ath12k/qmi.c
+index 5484112859a66..6d1ebbba17d9b 100644
+--- a/drivers/net/wireless/ath/ath12k/qmi.c
++++ b/drivers/net/wireless/ath/ath12k/qmi.c
+@@ -2538,7 +2538,7 @@ static int ath12k_qmi_load_file_target_mem(struct ath12k_base *ab,
+ struct qmi_wlanfw_bdf_download_resp_msg_v01 resp = {};
+ struct qmi_txn txn;
+ const u8 *temp = data;
+- int ret;
++ int ret = 0;
+ u32 remaining = len;
+
+ req = kzalloc(sizeof(*req), GFP_KERNEL);
+diff --git a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
+index 751a125a1566f..893b21fcaf87c 100644
+--- a/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
++++ b/drivers/net/wireless/intel/iwlwifi/fw/debugfs.c
+@@ -230,8 +230,7 @@ static ssize_t iwl_dbgfs_send_hcmd_write(struct iwl_fw_runtime *fwrt, char *buf,
+ .data = { NULL, },
+ };
+
+- if (fwrt->ops && fwrt->ops->fw_running &&
+- !fwrt->ops->fw_running(fwrt->ops_ctx))
++ if (!iwl_trans_fw_running(fwrt->trans))
+ return -EIO;
+
+ if (count < header_size + 1 || count > 1024 * 4)
+diff --git a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+index 9122f9a1260ae..d201440066ea9 100644
+--- a/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
++++ b/drivers/net/wireless/intel/iwlwifi/fw/runtime.h
+@@ -19,7 +19,6 @@
+ struct iwl_fw_runtime_ops {
+ void (*dump_start)(void *ctx);
+ void (*dump_end)(void *ctx);
+- bool (*fw_running)(void *ctx);
+ int (*send_hcmd)(void *ctx, struct iwl_host_cmd *host_cmd);
+ bool (*d3_debug_enable)(void *ctx);
+ };
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+index 92ac6cc40faa7..61b5648d3ab07 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+@@ -504,17 +504,27 @@ iwl_mvm_get_puncturing_factor(const struct ieee80211_bss_conf *link_conf)
+ static unsigned int
+ iwl_mvm_get_chan_load(struct ieee80211_bss_conf *link_conf)
+ {
++ struct ieee80211_vif *vif = link_conf->vif;
+ struct iwl_mvm_vif_link_info *mvm_link =
+ iwl_mvm_vif_from_mac80211(link_conf->vif)->link[link_conf->link_id];
+ const struct element *bss_load_elem;
+ const struct ieee80211_bss_load_elem *bss_load;
+ enum nl80211_band band = link_conf->chanreq.oper.chan->band;
++ const struct cfg80211_bss_ies *ies;
+ unsigned int chan_load;
+ u32 chan_load_by_us;
+
+ rcu_read_lock();
+- bss_load_elem = ieee80211_bss_get_elem(link_conf->bss,
+- WLAN_EID_QBSS_LOAD);
++ if (ieee80211_vif_link_active(vif, link_conf->link_id))
++ ies = rcu_dereference(link_conf->bss->beacon_ies);
++ else
++ ies = rcu_dereference(link_conf->bss->ies);
++
++ if (ies)
++ bss_load_elem = cfg80211_find_elem(WLAN_EID_QBSS_LOAD,
++ ies->data, ies->len);
++ else
++ bss_load_elem = NULL;
+
+ /* If there isn't BSS Load element, take the defaults */
+ if (!bss_load_elem ||
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+index 1380ae5155f35..498afbe4ee6be 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+@@ -770,11 +770,6 @@ static void iwl_mvm_fwrt_dump_end(void *ctx)
+ mutex_unlock(&mvm->mutex);
+ }
+
+-static bool iwl_mvm_fwrt_fw_running(void *ctx)
+-{
+- return iwl_mvm_firmware_running(ctx);
+-}
+-
+ static int iwl_mvm_fwrt_send_hcmd(void *ctx, struct iwl_host_cmd *host_cmd)
+ {
+ struct iwl_mvm *mvm = (struct iwl_mvm *)ctx;
+@@ -795,7 +790,6 @@ static bool iwl_mvm_d3_debug_enable(void *ctx)
+ static const struct iwl_fw_runtime_ops iwl_mvm_fwrt_ops = {
+ .dump_start = iwl_mvm_fwrt_dump_start,
+ .dump_end = iwl_mvm_fwrt_dump_end,
+- .fw_running = iwl_mvm_fwrt_fw_running,
+ .send_hcmd = iwl_mvm_fwrt_send_hcmd,
+ .d3_debug_enable = iwl_mvm_d3_debug_enable,
+ };
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
+index f49e3c98b1ba4..991dc875a7ead 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/tests/links.c
+@@ -208,6 +208,7 @@ static void setup_link_conf(struct kunit *test)
+ bss_load->channel_util = params->channel_util;
+
+ rcu_assign_pointer(bss.ies, ies);
++ rcu_assign_pointer(bss.beacon_ies, ies);
+ }
+
+ static void test_link_grading(struct kunit *test)
+diff --git a/drivers/net/wireless/realtek/rtw89/ser.c b/drivers/net/wireless/realtek/rtw89/ser.c
+index 99896d85d2f81..5fc2faa9ba5a7 100644
+--- a/drivers/net/wireless/realtek/rtw89/ser.c
++++ b/drivers/net/wireless/realtek/rtw89/ser.c
+@@ -308,9 +308,13 @@ static void ser_reset_vif(struct rtw89_dev *rtwdev, struct rtw89_vif *rtwvif)
+
+ static void ser_sta_deinit_cam_iter(void *data, struct ieee80211_sta *sta)
+ {
+- struct rtw89_vif *rtwvif = (struct rtw89_vif *)data;
+- struct rtw89_dev *rtwdev = rtwvif->rtwdev;
++ struct rtw89_vif *target_rtwvif = (struct rtw89_vif *)data;
+ struct rtw89_sta *rtwsta = (struct rtw89_sta *)sta->drv_priv;
++ struct rtw89_vif *rtwvif = rtwsta->rtwvif;
++ struct rtw89_dev *rtwdev = rtwvif->rtwdev;
++
++ if (rtwvif != target_rtwvif)
++ return;
+
+ if (rtwvif->net_type == RTW89_NET_TYPE_AP_MODE || sta->tdls)
+ rtw89_cam_deinit_addr_cam(rtwdev, &rtwsta->addr_cam);
+diff --git a/drivers/pci/controller/dwc/pcie-al.c b/drivers/pci/controller/dwc/pcie-al.c
+index 6dfdda59f3283..643115f74092d 100644
+--- a/drivers/pci/controller/dwc/pcie-al.c
++++ b/drivers/pci/controller/dwc/pcie-al.c
+@@ -242,18 +242,24 @@ static struct pci_ops al_child_pci_ops = {
+ .write = pci_generic_config_write,
+ };
+
+-static void al_pcie_config_prepare(struct al_pcie *pcie)
++static int al_pcie_config_prepare(struct al_pcie *pcie)
+ {
+ struct al_pcie_target_bus_cfg *target_bus_cfg;
+ struct dw_pcie_rp *pp = &pcie->pci->pp;
+ unsigned int ecam_bus_mask;
++ struct resource_entry *ft;
+ u32 cfg_control_offset;
++ struct resource *bus;
+ u8 subordinate_bus;
+ u8 secondary_bus;
+ u32 cfg_control;
+ u32 reg;
+- struct resource *bus = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS)->res;
+
++ ft = resource_list_first_type(&pp->bridge->windows, IORESOURCE_BUS);
++ if (!ft)
++ return -ENODEV;
++
++ bus = ft->res;
+ target_bus_cfg = &pcie->target_bus_cfg;
+
+ ecam_bus_mask = (pcie->ecam_size >> PCIE_ECAM_BUS_SHIFT) - 1;
+@@ -287,6 +293,8 @@ static void al_pcie_config_prepare(struct al_pcie *pcie)
+ FIELD_PREP(CFG_CONTROL_SEC_BUS_MASK, secondary_bus);
+
+ al_pcie_controller_writel(pcie, cfg_control_offset, reg);
++
++ return 0;
+ }
+
+ static int al_pcie_host_init(struct dw_pcie_rp *pp)
+@@ -305,7 +313,9 @@ static int al_pcie_host_init(struct dw_pcie_rp *pp)
+ if (rc)
+ return rc;
+
+- al_pcie_config_prepare(pcie);
++ rc = al_pcie_config_prepare(pcie);
++ if (rc)
++ return rc;
+
+ return 0;
+ }
+diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
+index 4438f3b4b5ef9..60f866f1e6d78 100644
+--- a/drivers/pinctrl/core.c
++++ b/drivers/pinctrl/core.c
+@@ -1670,6 +1670,7 @@ static int pinctrl_pins_show(struct seq_file *s, void *what)
+ seq_printf(s, "pin %d (%s) ", pin, desc->name);
+
+ #ifdef CONFIG_GPIOLIB
++ gdev = NULL;
+ gpio_num = -1;
+ list_for_each_entry(range, &pctldev->gpio_ranges, node) {
+ if ((pin >= range->pin_base) &&
+diff --git a/drivers/pinctrl/renesas/pinctrl-rzg2l.c b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+index 60be78da9f529..389602e4d7ab3 100644
+--- a/drivers/pinctrl/renesas/pinctrl-rzg2l.c
++++ b/drivers/pinctrl/renesas/pinctrl-rzg2l.c
+@@ -2583,8 +2583,10 @@ static int rzg2l_pinctrl_suspend_noirq(struct device *dev)
+ rzg2l_pinctrl_pm_setup_dedicated_regs(pctrl, true);
+
+ for (u8 i = 0; i < 2; i++) {
+- cache->sd_ch[i] = readb(pctrl->base + SD_CH(regs->sd_ch, i));
+- cache->eth_poc[i] = readb(pctrl->base + ETH_POC(regs->eth_poc, i));
++ if (regs->sd_ch)
++ cache->sd_ch[i] = readb(pctrl->base + SD_CH(regs->sd_ch, i));
++ if (regs->eth_poc)
++ cache->eth_poc[i] = readb(pctrl->base + ETH_POC(regs->eth_poc, i));
+ }
+
+ cache->qspi = readb(pctrl->base + QSPI);
+@@ -2615,8 +2617,10 @@ static int rzg2l_pinctrl_resume_noirq(struct device *dev)
+ writeb(cache->qspi, pctrl->base + QSPI);
+ writeb(cache->eth_mode, pctrl->base + ETH_MODE);
+ for (u8 i = 0; i < 2; i++) {
+- writeb(cache->sd_ch[i], pctrl->base + SD_CH(regs->sd_ch, i));
+- writeb(cache->eth_poc[i], pctrl->base + ETH_POC(regs->eth_poc, i));
++ if (regs->sd_ch)
++ writeb(cache->sd_ch[i], pctrl->base + SD_CH(regs->sd_ch, i));
++ if (regs->eth_poc)
++ writeb(cache->eth_poc[i], pctrl->base + ETH_POC(regs->eth_poc, i));
+ }
+
+ rzg2l_pinctrl_pm_setup_pfc(pctrl);
+diff --git a/drivers/platform/chrome/cros_ec_lpc_mec.c b/drivers/platform/chrome/cros_ec_lpc_mec.c
+index 0d9c79b270ce2..63b6b261b8e58 100644
+--- a/drivers/platform/chrome/cros_ec_lpc_mec.c
++++ b/drivers/platform/chrome/cros_ec_lpc_mec.c
+@@ -10,13 +10,65 @@
+
+ #include "cros_ec_lpc_mec.h"
+
++#define ACPI_LOCK_DELAY_MS 500
++
+ /*
+ * This mutex must be held while accessing the EMI unit. We can't rely on the
+ * EC mutex because memmap data may be accessed without it being held.
+ */
+ static DEFINE_MUTEX(io_mutex);
++/*
++ * An alternative mutex to be used when the ACPI AML code may also
++ * access memmap data. When set, this mutex is used in preference to
++ * io_mutex.
++ */
++static acpi_handle aml_mutex;
++
+ static u16 mec_emi_base, mec_emi_end;
+
++/**
++ * cros_ec_lpc_mec_lock() - Acquire mutex for EMI
++ *
++ * @return: Negative error code, or zero for success
++ */
++static int cros_ec_lpc_mec_lock(void)
++{
++ bool success;
++
++ if (!aml_mutex) {
++ mutex_lock(&io_mutex);
++ return 0;
++ }
++
++ success = ACPI_SUCCESS(acpi_acquire_mutex(aml_mutex,
++ NULL, ACPI_LOCK_DELAY_MS));
++ if (!success)
++ return -EBUSY;
++
++ return 0;
++}
++
++/**
++ * cros_ec_lpc_mec_unlock() - Release mutex for EMI
++ *
++ * @return: Negative error code, or zero for success
++ */
++static int cros_ec_lpc_mec_unlock(void)
++{
++ bool success;
++
++ if (!aml_mutex) {
++ mutex_unlock(&io_mutex);
++ return 0;
++ }
++
++ success = ACPI_SUCCESS(acpi_release_mutex(aml_mutex, NULL));
++ if (!success)
++ return -EBUSY;
++
++ return 0;
++}
++
+ /**
+ * cros_ec_lpc_mec_emi_write_address() - Initialize EMI at a given address.
+ *
+@@ -77,6 +129,7 @@ u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type,
+ int io_addr;
+ u8 sum = 0;
+ enum cros_ec_lpc_mec_emi_access_mode access, new_access;
++ int ret;
+
+ /* Return checksum of 0 if window is not initialized */
+ WARN_ON(mec_emi_base == 0 || mec_emi_end == 0);
+@@ -92,7 +145,9 @@ u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type,
+ else
+ access = ACCESS_TYPE_LONG_AUTO_INCREMENT;
+
+- mutex_lock(&io_mutex);
++ ret = cros_ec_lpc_mec_lock();
++ if (ret)
++ return ret;
+
+ /* Initialize I/O at desired address */
+ cros_ec_lpc_mec_emi_write_address(offset, access);
+@@ -134,7 +189,9 @@ u8 cros_ec_lpc_io_bytes_mec(enum cros_ec_lpc_mec_io_type io_type,
+ }
+
+ done:
+- mutex_unlock(&io_mutex);
++ ret = cros_ec_lpc_mec_unlock();
++ if (ret)
++ return ret;
+
+ return sum;
+ }
+@@ -146,3 +203,18 @@ void cros_ec_lpc_mec_init(unsigned int base, unsigned int end)
+ mec_emi_end = end;
+ }
+ EXPORT_SYMBOL(cros_ec_lpc_mec_init);
++
++int cros_ec_lpc_mec_acpi_mutex(struct acpi_device *adev, const char *pathname)
++{
++ int status;
++
++ if (!adev)
++ return -ENOENT;
++
++ status = acpi_get_handle(adev->handle, pathname, &aml_mutex);
++ if (ACPI_FAILURE(status))
++ return -ENOENT;
++
++ return 0;
++}
++EXPORT_SYMBOL(cros_ec_lpc_mec_acpi_mutex);
+diff --git a/drivers/platform/chrome/cros_ec_lpc_mec.h b/drivers/platform/chrome/cros_ec_lpc_mec.h
+index 9d0521b23e8ae..3f3af37e58a50 100644
+--- a/drivers/platform/chrome/cros_ec_lpc_mec.h
++++ b/drivers/platform/chrome/cros_ec_lpc_mec.h
+@@ -8,6 +8,8 @@
+ #ifndef __CROS_EC_LPC_MEC_H
+ #define __CROS_EC_LPC_MEC_H
+
++#include <linux/acpi.h>
++
+ enum cros_ec_lpc_mec_emi_access_mode {
+ /* 8-bit access */
+ ACCESS_TYPE_BYTE = 0x0,
+@@ -45,6 +47,15 @@ enum cros_ec_lpc_mec_io_type {
+ */
+ void cros_ec_lpc_mec_init(unsigned int base, unsigned int end);
+
++/**
++ * cros_ec_lpc_mec_acpi_mutex() - Find and set ACPI mutex for MEC
++ *
++ * @adev: Parent ACPI device
++ * @pathname: Name of AML mutex
++ * @return: Negative error code, or zero for success
++ */
++int cros_ec_lpc_mec_acpi_mutex(struct acpi_device *adev, const char *pathname);
++
+ /**
+ * cros_ec_lpc_mec_in_range() - Determine if addresses are in MEC EMI range.
+ *
+diff --git a/drivers/platform/x86/amd/pmf/core.c b/drivers/platform/x86/amd/pmf/core.c
+index 2d6e2558863c5..8f1f719befa3e 100644
+--- a/drivers/platform/x86/amd/pmf/core.c
++++ b/drivers/platform/x86/amd/pmf/core.c
+@@ -41,6 +41,7 @@
+ #define AMD_CPU_ID_RMB 0x14b5
+ #define AMD_CPU_ID_PS 0x14e8
+ #define PCI_DEVICE_ID_AMD_1AH_M20H_ROOT 0x1507
++#define PCI_DEVICE_ID_AMD_1AH_M60H_ROOT 0x1122
+
+ #define PMF_MSG_DELAY_MIN_US 50
+ #define RESPONSE_REGISTER_LOOP_MAX 20000
+@@ -249,6 +250,7 @@ static const struct pci_device_id pmf_pci_ids[] = {
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_RMB) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, AMD_CPU_ID_PS) },
+ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_ROOT) },
++ { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M60H_ROOT) },
+ { }
+ };
+
+@@ -382,6 +384,7 @@ static const struct acpi_device_id amd_pmf_acpi_ids[] = {
+ {"AMDI0102", 0},
+ {"AMDI0103", 0},
+ {"AMDI0105", 0},
++ {"AMDI0107", 0},
+ { }
+ };
+ MODULE_DEVICE_TABLE(acpi, amd_pmf_acpi_ids);
+diff --git a/drivers/platform/x86/amd/pmf/pmf-quirks.c b/drivers/platform/x86/amd/pmf/pmf-quirks.c
+index 0b2eb0ae85feb..460444cda1b29 100644
+--- a/drivers/platform/x86/amd/pmf/pmf-quirks.c
++++ b/drivers/platform/x86/amd/pmf/pmf-quirks.c
+@@ -29,6 +29,14 @@ static const struct dmi_system_id fwbug_list[] = {
+ },
+ .driver_data = &quirk_no_sps_bug,
+ },
++ {
++ .ident = "ROG Ally X",
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
++ DMI_MATCH(DMI_PRODUCT_NAME, "RC72LA"),
++ },
++ .driver_data = &quirk_no_sps_bug,
++ },
+ {}
+ };
+
+@@ -48,4 +56,3 @@ void amd_pmf_quirks_init(struct amd_pmf_dev *dev)
+ dmi_id->ident);
+ }
+ }
+-
+diff --git a/drivers/ras/amd/atl/dehash.c b/drivers/ras/amd/atl/dehash.c
+index 4ea46262c4f58..d4ee7ecabaeee 100644
+--- a/drivers/ras/amd/atl/dehash.c
++++ b/drivers/ras/amd/atl/dehash.c
+@@ -12,41 +12,10 @@
+
+ #include "internal.h"
+
+-/*
+- * Verify the interleave bits are correct in the different interleaving
+- * settings.
+- *
+- * If @num_intlv_dies and/or @num_intlv_sockets are 1, it means the
+- * respective interleaving is disabled.
+- */
+-static inline bool map_bits_valid(struct addr_ctx *ctx, u8 bit1, u8 bit2,
+- u8 num_intlv_dies, u8 num_intlv_sockets)
+-{
+- if (!(ctx->map.intlv_bit_pos == bit1 || ctx->map.intlv_bit_pos == bit2)) {
+- pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos);
+- return false;
+- }
+-
+- if (ctx->map.num_intlv_dies > num_intlv_dies) {
+- pr_debug("Invalid number of interleave dies: %u", ctx->map.num_intlv_dies);
+- return false;
+- }
+-
+- if (ctx->map.num_intlv_sockets > num_intlv_sockets) {
+- pr_debug("Invalid number of interleave sockets: %u", ctx->map.num_intlv_sockets);
+- return false;
+- }
+-
+- return true;
+-}
+-
+ static int df2_dehash_addr(struct addr_ctx *ctx)
+ {
+ u8 hashed_bit, intlv_bit, intlv_bit_pos;
+
+- if (!map_bits_valid(ctx, 8, 9, 1, 1))
+- return -EINVAL;
+-
+ intlv_bit_pos = ctx->map.intlv_bit_pos;
+ intlv_bit = !!(BIT_ULL(intlv_bit_pos) & ctx->ret_addr);
+
+@@ -67,9 +36,6 @@ static int df3_dehash_addr(struct addr_ctx *ctx)
+ bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G;
+ u8 hashed_bit, intlv_bit, intlv_bit_pos;
+
+- if (!map_bits_valid(ctx, 8, 9, 1, 1))
+- return -EINVAL;
+-
+ hash_ctl_64k = FIELD_GET(DF3_HASH_CTL_64K, ctx->map.ctl);
+ hash_ctl_2M = FIELD_GET(DF3_HASH_CTL_2M, ctx->map.ctl);
+ hash_ctl_1G = FIELD_GET(DF3_HASH_CTL_1G, ctx->map.ctl);
+@@ -171,9 +137,6 @@ static int df4_dehash_addr(struct addr_ctx *ctx)
+ bool hash_ctl_64k, hash_ctl_2M, hash_ctl_1G;
+ u8 hashed_bit, intlv_bit;
+
+- if (!map_bits_valid(ctx, 8, 8, 1, 2))
+- return -EINVAL;
+-
+ hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl);
+ hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl);
+ hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl);
+@@ -247,9 +210,6 @@ static int df4p5_dehash_addr(struct addr_ctx *ctx)
+ u8 hashed_bit, intlv_bit;
+ u64 rehash_vector;
+
+- if (!map_bits_valid(ctx, 8, 8, 1, 2))
+- return -EINVAL;
+-
+ hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl);
+ hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl);
+ hash_ctl_1G = FIELD_GET(DF4_HASH_CTL_1G, ctx->map.ctl);
+@@ -360,9 +320,6 @@ static int mi300_dehash_addr(struct addr_ctx *ctx)
+ bool hashed_bit, intlv_bit, test_bit;
+ u8 num_intlv_bits, base_bit, i;
+
+- if (!map_bits_valid(ctx, 8, 8, 4, 1))
+- return -EINVAL;
+-
+ hash_ctl_4k = FIELD_GET(DF4p5_HASH_CTL_4K, ctx->map.ctl);
+ hash_ctl_64k = FIELD_GET(DF4_HASH_CTL_64K, ctx->map.ctl);
+ hash_ctl_2M = FIELD_GET(DF4_HASH_CTL_2M, ctx->map.ctl);
+diff --git a/drivers/ras/amd/atl/map.c b/drivers/ras/amd/atl/map.c
+index 8b908e8d7495f..04419923f0884 100644
+--- a/drivers/ras/amd/atl/map.c
++++ b/drivers/ras/amd/atl/map.c
+@@ -642,6 +642,79 @@ static int get_global_map_data(struct addr_ctx *ctx)
+ return 0;
+ }
+
++/*
++ * Verify the interleave bits are correct in the different interleaving
++ * settings.
++ *
++ * If @num_intlv_dies and/or @num_intlv_sockets are 1, it means the
++ * respective interleaving is disabled.
++ */
++static inline bool map_bits_valid(struct addr_ctx *ctx, u8 bit1, u8 bit2,
++ u8 num_intlv_dies, u8 num_intlv_sockets)
++{
++ if (!(ctx->map.intlv_bit_pos == bit1 || ctx->map.intlv_bit_pos == bit2)) {
++ pr_debug("Invalid interleave bit: %u", ctx->map.intlv_bit_pos);
++ return false;
++ }
++
++ if (ctx->map.num_intlv_dies > num_intlv_dies) {
++ pr_debug("Invalid number of interleave dies: %u", ctx->map.num_intlv_dies);
++ return false;
++ }
++
++ if (ctx->map.num_intlv_sockets > num_intlv_sockets) {
++ pr_debug("Invalid number of interleave sockets: %u", ctx->map.num_intlv_sockets);
++ return false;
++ }
++
++ return true;
++}
++
++static int validate_address_map(struct addr_ctx *ctx)
++{
++ switch (ctx->map.intlv_mode) {
++ case DF2_2CHAN_HASH:
++ case DF3_COD4_2CHAN_HASH:
++ case DF3_COD2_4CHAN_HASH:
++ case DF3_COD1_8CHAN_HASH:
++ if (!map_bits_valid(ctx, 8, 9, 1, 1))
++ goto err;
++ break;
++
++ case DF4_NPS4_2CHAN_HASH:
++ case DF4_NPS2_4CHAN_HASH:
++ case DF4_NPS1_8CHAN_HASH:
++ case DF4p5_NPS4_2CHAN_1K_HASH:
++ case DF4p5_NPS4_2CHAN_2K_HASH:
++ case DF4p5_NPS2_4CHAN_1K_HASH:
++ case DF4p5_NPS2_4CHAN_2K_HASH:
++ case DF4p5_NPS1_8CHAN_1K_HASH:
++ case DF4p5_NPS1_8CHAN_2K_HASH:
++ case DF4p5_NPS1_16CHAN_1K_HASH:
++ case DF4p5_NPS1_16CHAN_2K_HASH:
++ if (!map_bits_valid(ctx, 8, 8, 1, 2))
++ goto err;
++ break;
++
++ case MI3_HASH_8CHAN:
++ case MI3_HASH_16CHAN:
++ case MI3_HASH_32CHAN:
++ if (!map_bits_valid(ctx, 8, 8, 4, 1))
++ goto err;
++ break;
++
++ /* Nothing to do for modes that don't need special validation checks. */
++ default:
++ break;
++ }
++
++ return 0;
++
++err:
++ atl_debug(ctx, "Inconsistent address map");
++ return -EINVAL;
++}
++
+ static void dump_address_map(struct dram_addr_map *map)
+ {
+ u8 i;
+@@ -678,5 +751,9 @@ int get_address_map(struct addr_ctx *ctx)
+
+ dump_address_map(&ctx->map);
+
++ ret = validate_address_map(ctx);
++ if (ret)
++ return ret;
++
+ return ret;
+ }
+diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
+index abf7b371b8604..e744c07507eed 100644
+--- a/drivers/remoteproc/mtk_scp.c
++++ b/drivers/remoteproc/mtk_scp.c
+@@ -117,8 +117,8 @@ static void scp_ipi_handler(struct mtk_scp *scp)
+ return;
+ }
+
+- memset(scp->share_buf, 0, scp_sizes->ipi_share_buffer_size);
+ memcpy_fromio(scp->share_buf, &rcv_obj->share_buf, len);
++ memset(&scp->share_buf[len], 0, scp_sizes->ipi_share_buffer_size - len);
+ handler(scp->share_buf, len, ipi_desc[id].priv);
+ scp_ipi_unlock(scp, id);
+
+diff --git a/drivers/remoteproc/qcom_q6v5_pas.c b/drivers/remoteproc/qcom_q6v5_pas.c
+index 54d8005d40a34..8458bcfe9e19e 100644
+--- a/drivers/remoteproc/qcom_q6v5_pas.c
++++ b/drivers/remoteproc/qcom_q6v5_pas.c
+@@ -52,6 +52,7 @@ struct adsp_data {
+ const char *ssr_name;
+ const char *sysmon_name;
+ int ssctl_id;
++ unsigned int smem_host_id;
+
+ int region_assign_idx;
+ int region_assign_count;
+@@ -81,6 +82,7 @@ struct qcom_adsp {
+ int lite_pas_id;
+ unsigned int minidump_id;
+ int crash_reason_smem;
++ unsigned int smem_host_id;
+ bool decrypt_shutdown;
+ const char *info_name;
+
+@@ -399,6 +401,9 @@ static int adsp_stop(struct rproc *rproc)
+ if (handover)
+ qcom_pas_handover(&adsp->q6v5);
+
++ if (adsp->smem_host_id)
++ ret = qcom_smem_bust_hwspin_lock_by_host(adsp->smem_host_id);
++
+ return ret;
+ }
+
+@@ -727,6 +732,7 @@ static int adsp_probe(struct platform_device *pdev)
+ adsp->pas_id = desc->pas_id;
+ adsp->lite_pas_id = desc->lite_pas_id;
+ adsp->info_name = desc->sysmon_name;
++ adsp->smem_host_id = desc->smem_host_id;
+ adsp->decrypt_shutdown = desc->decrypt_shutdown;
+ adsp->region_assign_idx = desc->region_assign_idx;
+ adsp->region_assign_count = min_t(int, MAX_ASSIGN_COUNT, desc->region_assign_count);
+@@ -1196,6 +1202,7 @@ static const struct adsp_data sm8550_adsp_resource = {
+ .ssr_name = "lpass",
+ .sysmon_name = "adsp",
+ .ssctl_id = 0x14,
++ .smem_host_id = 2,
+ };
+
+ static const struct adsp_data sm8550_cdsp_resource = {
+@@ -1216,6 +1223,7 @@ static const struct adsp_data sm8550_cdsp_resource = {
+ .ssr_name = "cdsp",
+ .sysmon_name = "cdsp",
+ .ssctl_id = 0x17,
++ .smem_host_id = 5,
+ };
+
+ static const struct adsp_data sm8550_mpss_resource = {
+@@ -1236,6 +1244,7 @@ static const struct adsp_data sm8550_mpss_resource = {
+ .ssr_name = "mpss",
+ .sysmon_name = "modem",
+ .ssctl_id = 0x12,
++ .smem_host_id = 1,
+ .region_assign_idx = 2,
+ .region_assign_count = 1,
+ .region_assign_vmid = QCOM_SCM_VMID_MSS_MSA,
+@@ -1275,6 +1284,7 @@ static const struct adsp_data sm8650_cdsp_resource = {
+ .ssr_name = "cdsp",
+ .sysmon_name = "cdsp",
+ .ssctl_id = 0x17,
++ .smem_host_id = 5,
+ .region_assign_idx = 2,
+ .region_assign_count = 1,
+ .region_assign_shared = true,
+@@ -1299,6 +1309,7 @@ static const struct adsp_data sm8650_mpss_resource = {
+ .ssr_name = "mpss",
+ .sysmon_name = "modem",
+ .ssctl_id = 0x12,
++ .smem_host_id = 1,
+ .region_assign_idx = 2,
+ .region_assign_count = 3,
+ .region_assign_vmid = QCOM_SCM_VMID_MSS_MSA,
+diff --git a/drivers/soc/qcom/smem.c b/drivers/soc/qcom/smem.c
+index 7191fa0c087f2..50039e983ebaa 100644
+--- a/drivers/soc/qcom/smem.c
++++ b/drivers/soc/qcom/smem.c
+@@ -359,6 +359,32 @@ static struct qcom_smem *__smem;
+ /* Timeout (ms) for the trylock of remote spinlocks */
+ #define HWSPINLOCK_TIMEOUT 1000
+
++/* The qcom hwspinlock id is always plus one from the smem host id */
++#define SMEM_HOST_ID_TO_HWSPINLOCK_ID(__x) ((__x) + 1)
++
++/**
++ * qcom_smem_bust_hwspin_lock_by_host() - bust the smem hwspinlock for a host
++ * @host: remote processor id
++ *
++ * Busts the hwspin_lock for the given smem host id. This helper is intended
++ * for remoteproc drivers that manage remoteprocs with an equivalent smem
++ * driver instance in the remote firmware. Drivers can force a release of the
++ * smem hwspin_lock if the rproc unexpectedly goes into a bad state.
++ *
++ * Context: Process context.
++ *
++ * Returns: 0 on success, otherwise negative errno.
++ */
++int qcom_smem_bust_hwspin_lock_by_host(unsigned int host)
++{
++ /* This function is for remote procs, so ignore SMEM_HOST_APPS */
++ if (host == SMEM_HOST_APPS || host >= SMEM_HOST_COUNT)
++ return -EINVAL;
++
++ return hwspin_lock_bust(__smem->hwlock, SMEM_HOST_ID_TO_HWSPINLOCK_ID(host));
++}
++EXPORT_SYMBOL_GPL(qcom_smem_bust_hwspin_lock_by_host);
++
+ /**
+ * qcom_smem_is_available() - Check if SMEM is available
+ *
+diff --git a/drivers/spi/spi-hisi-kunpeng.c b/drivers/spi/spi-hisi-kunpeng.c
+index 77e9738e42f60..6910b4d4c427b 100644
+--- a/drivers/spi/spi-hisi-kunpeng.c
++++ b/drivers/spi/spi-hisi-kunpeng.c
+@@ -495,6 +495,7 @@ static int hisi_spi_probe(struct platform_device *pdev)
+ host->transfer_one = hisi_spi_transfer_one;
+ host->handle_err = hisi_spi_handle_err;
+ host->dev.fwnode = dev->fwnode;
++ host->min_speed_hz = DIV_ROUND_UP(host->max_speed_hz, CLK_DIV_MAX);
+
+ hisi_spi_hw_init(hs);
+
+diff --git a/drivers/thermal/thermal_sysfs.c b/drivers/thermal/thermal_sysfs.c
+index 88211ccdfbd62..5be6113e7c80f 100644
+--- a/drivers/thermal/thermal_sysfs.c
++++ b/drivers/thermal/thermal_sysfs.c
+@@ -150,7 +150,7 @@ trip_point_temp_show(struct device *dev, struct device_attribute *attr,
+ if (sscanf(attr->attr.name, "trip_point_%d_temp", &trip_id) != 1)
+ return -EINVAL;
+
+- return sprintf(buf, "%d\n", tz->trips[trip_id].trip.temperature);
++ return sprintf(buf, "%d\n", READ_ONCE(tz->trips[trip_id].trip.temperature));
+ }
+
+ static ssize_t
+@@ -174,7 +174,7 @@ trip_point_hyst_store(struct device *dev, struct device_attribute *attr,
+ trip = &tz->trips[trip_id].trip;
+
+ if (hyst != trip->hysteresis) {
+- trip->hysteresis = hyst;
++ WRITE_ONCE(trip->hysteresis, hyst);
+
+ thermal_zone_trip_updated(tz, trip);
+ }
+@@ -194,7 +194,7 @@ trip_point_hyst_show(struct device *dev, struct device_attribute *attr,
+ if (sscanf(attr->attr.name, "trip_point_%d_hyst", &trip_id) != 1)
+ return -EINVAL;
+
+- return sprintf(buf, "%d\n", tz->trips[trip_id].trip.hysteresis);
++ return sprintf(buf, "%d\n", READ_ONCE(tz->trips[trip_id].trip.hysteresis));
+ }
+
+ static ssize_t
+diff --git a/drivers/thermal/thermal_trip.c b/drivers/thermal/thermal_trip.c
+index 49e63db685172..b4e7411b2fe74 100644
+--- a/drivers/thermal/thermal_trip.c
++++ b/drivers/thermal/thermal_trip.c
+@@ -152,7 +152,7 @@ void thermal_zone_set_trip_temp(struct thermal_zone_device *tz,
+ if (trip->temperature == temp)
+ return;
+
+- trip->temperature = temp;
++ WRITE_ONCE(trip->temperature, temp);
+ thermal_notify_tz_trip_change(tz, trip);
+
+ if (temp == THERMAL_TEMP_INVALID) {
+diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
+index 5864d65448ce5..91bfdc17eedb3 100644
+--- a/drivers/ufs/core/ufshcd.c
++++ b/drivers/ufs/core/ufshcd.c
+@@ -2412,7 +2412,17 @@ static inline int ufshcd_hba_capabilities(struct ufs_hba *hba)
+ return err;
+ }
+
++ /*
++ * The UFSHCI 3.0 specification does not define MCQ_SUPPORT and
++ * LSDB_SUPPORT, but [31:29] as reserved bits with reset value 0s, which
++ * means we can simply read values regardless of version.
++ */
+ hba->mcq_sup = FIELD_GET(MASK_MCQ_SUPPORT, hba->capabilities);
++ /*
++ * 0h: legacy single doorbell support is available
++ * 1h: indicate that legacy single doorbell support has been removed
++ */
++ hba->lsdb_sup = !FIELD_GET(MASK_LSDB_SUPPORT, hba->capabilities);
+ if (!hba->mcq_sup)
+ return 0;
+
+@@ -6550,7 +6560,8 @@ static void ufshcd_err_handler(struct work_struct *work)
+ if (ufshcd_err_handling_should_stop(hba))
+ goto skip_err_handling;
+
+- if (hba->dev_quirks & UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS) {
++ if ((hba->dev_quirks & UFS_DEVICE_QUIRK_RECOVERY_FROM_DL_NAC_ERRORS) &&
++ !hba->force_reset) {
+ bool ret;
+
+ spin_unlock_irqrestore(hba->host->host_lock, flags);
+@@ -10456,6 +10467,12 @@ int ufshcd_init(struct ufs_hba *hba, void __iomem *mmio_base, unsigned int irq)
+ }
+
+ if (!is_mcq_supported(hba)) {
++ if (!hba->lsdb_sup) {
++ dev_err(hba->dev, "%s: failed to initialize (legacy doorbell mode not supported)\n",
++ __func__);
++ err = -EINVAL;
++ goto out_disable;
++ }
+ err = scsi_add_host(host, hba->dev);
+ if (err) {
+ dev_err(hba->dev, "scsi_add_host failed\n");
+diff --git a/drivers/usb/typec/ucsi/ucsi.h b/drivers/usb/typec/ucsi/ucsi.h
+index c4d103db9d0f8..f66224a270bc6 100644
+--- a/drivers/usb/typec/ucsi/ucsi.h
++++ b/drivers/usb/typec/ucsi/ucsi.h
+@@ -496,7 +496,7 @@ ucsi_register_displayport(struct ucsi_connector *con,
+ bool override, int offset,
+ struct typec_altmode_desc *desc)
+ {
+- return NULL;
++ return typec_port_register_altmode(con->port, desc);
+ }
+
+ static inline void
+diff --git a/drivers/usb/usbip/stub_rx.c b/drivers/usb/usbip/stub_rx.c
+index fc01b31bbb875..6338d818bc8bc 100644
+--- a/drivers/usb/usbip/stub_rx.c
++++ b/drivers/usb/usbip/stub_rx.c
+@@ -144,53 +144,62 @@ static int tweak_set_configuration_cmd(struct urb *urb)
+ if (err && err != -ENODEV)
+ dev_err(&sdev->udev->dev, "can't set config #%d, error %d\n",
+ config, err);
+- return 0;
++ return err;
+ }
+
+ static int tweak_reset_device_cmd(struct urb *urb)
+ {
+ struct stub_priv *priv = (struct stub_priv *) urb->context;
+ struct stub_device *sdev = priv->sdev;
++ int err;
+
+ dev_info(&urb->dev->dev, "usb_queue_reset_device\n");
+
+- if (usb_lock_device_for_reset(sdev->udev, NULL) < 0) {
++ err = usb_lock_device_for_reset(sdev->udev, NULL);
++ if (err < 0) {
+ dev_err(&urb->dev->dev, "could not obtain lock to reset device\n");
+- return 0;
++ return err;
+ }
+- usb_reset_device(sdev->udev);
++ err = usb_reset_device(sdev->udev);
+ usb_unlock_device(sdev->udev);
+
+- return 0;
++ return err;
+ }
+
+ /*
+ * clear_halt, set_interface, and set_configuration require special tricks.
++ * Returns 1 if request was tweaked, 0 otherwise.
+ */
+-static void tweak_special_requests(struct urb *urb)
++static int tweak_special_requests(struct urb *urb)
+ {
++ int err;
++
+ if (!urb || !urb->setup_packet)
+- return;
++ return 0;
+
+ if (usb_pipetype(urb->pipe) != PIPE_CONTROL)
+- return;
++ return 0;
+
+ if (is_clear_halt_cmd(urb))
+ /* tweak clear_halt */
+- tweak_clear_halt_cmd(urb);
++ err = tweak_clear_halt_cmd(urb);
+
+ else if (is_set_interface_cmd(urb))
+ /* tweak set_interface */
+- tweak_set_interface_cmd(urb);
++ err = tweak_set_interface_cmd(urb);
+
+ else if (is_set_configuration_cmd(urb))
+ /* tweak set_configuration */
+- tweak_set_configuration_cmd(urb);
++ err = tweak_set_configuration_cmd(urb);
+
+ else if (is_reset_device_cmd(urb))
+- tweak_reset_device_cmd(urb);
+- else
++ err = tweak_reset_device_cmd(urb);
++ else {
+ usbip_dbg_stub_rx("no need to tweak\n");
++ return 0;
++ }
++
++ return !err;
+ }
+
+ /*
+@@ -468,6 +477,7 @@ static void stub_recv_cmd_submit(struct stub_device *sdev,
+ int support_sg = 1;
+ int np = 0;
+ int ret, i;
++ int is_tweaked;
+
+ if (pipe == -1)
+ return;
+@@ -580,8 +590,11 @@ static void stub_recv_cmd_submit(struct stub_device *sdev,
+ priv->urbs[i]->pipe = pipe;
+ priv->urbs[i]->complete = stub_complete;
+
+- /* no need to submit an intercepted request, but harmless? */
+- tweak_special_requests(priv->urbs[i]);
++ /*
++ * all URBs belong to a single PDU, so a global is_tweaked flag is
++ * enough
++ */
++ is_tweaked = tweak_special_requests(priv->urbs[i]);
+
+ masking_bogus_flags(priv->urbs[i]);
+ }
+@@ -594,22 +607,32 @@ static void stub_recv_cmd_submit(struct stub_device *sdev,
+
+ /* urb is now ready to submit */
+ for (i = 0; i < priv->num_urbs; i++) {
+- ret = usb_submit_urb(priv->urbs[i], GFP_KERNEL);
++ if (!is_tweaked) {
++ ret = usb_submit_urb(priv->urbs[i], GFP_KERNEL);
+
+- if (ret == 0)
+- usbip_dbg_stub_rx("submit urb ok, seqnum %u\n",
+- pdu->base.seqnum);
+- else {
+- dev_err(&udev->dev, "submit_urb error, %d\n", ret);
+- usbip_dump_header(pdu);
+- usbip_dump_urb(priv->urbs[i]);
++ if (ret == 0)
++ usbip_dbg_stub_rx("submit urb ok, seqnum %u\n",
++ pdu->base.seqnum);
++ else {
++ dev_err(&udev->dev, "submit_urb error, %d\n", ret);
++ usbip_dump_header(pdu);
++ usbip_dump_urb(priv->urbs[i]);
+
++ /*
++ * Pessimistic.
++ * This connection will be discarded.
++ */
++ usbip_event_add(ud, SDEV_EVENT_ERROR_SUBMIT);
++ break;
++ }
++ } else {
+ /*
+- * Pessimistic.
+- * This connection will be discarded.
++ * An identical URB was already submitted in
++ * tweak_special_requests(). Skip submitting this URB to not
++ * duplicate the request.
+ */
+- usbip_event_add(ud, SDEV_EVENT_ERROR_SUBMIT);
+- break;
++ priv->urbs[i]->status = 0;
++ stub_complete(priv->urbs[i]);
+ }
+ }
+
+diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
+index 39d22693e47b6..c2f48fc159e5a 100644
+--- a/fs/btrfs/inode.c
++++ b/fs/btrfs/inode.c
+@@ -1586,6 +1586,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
+ locked_page, &cached,
+ clear_bits,
+ page_ops);
++ btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
+ start += cur_alloc_size;
+ }
+
+@@ -1599,6 +1600,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
+ clear_bits |= EXTENT_CLEAR_DATA_RESV;
+ extent_clear_unlock_delalloc(inode, start, end, locked_page,
+ &cached, clear_bits, page_ops);
++ btrfs_qgroup_free_data(inode, NULL, start, cur_alloc_size, NULL);
+ }
+ return ret;
+ }
+@@ -2269,6 +2271,7 @@ static noinline int run_delalloc_nocow(struct btrfs_inode *inode,
+ EXTENT_DO_ACCOUNTING, PAGE_UNLOCK |
+ PAGE_START_WRITEBACK |
+ PAGE_END_WRITEBACK);
++ btrfs_qgroup_free_data(inode, NULL, cur_offset, end - cur_offset + 1, NULL);
+ }
+ btrfs_free_path(path);
+ return ret;
+diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
+index d7caa3732f074..731d7d562db1a 100644
+--- a/fs/btrfs/scrub.c
++++ b/fs/btrfs/scrub.c
+@@ -1648,14 +1648,20 @@ static void scrub_reset_stripe(struct scrub_stripe *stripe)
+ }
+ }
+
++static u32 stripe_length(const struct scrub_stripe *stripe)
++{
++ ASSERT(stripe->bg);
++
++ return min(BTRFS_STRIPE_LEN,
++ stripe->bg->start + stripe->bg->length - stripe->logical);
++}
++
+ static void scrub_submit_extent_sector_read(struct scrub_ctx *sctx,
+ struct scrub_stripe *stripe)
+ {
+ struct btrfs_fs_info *fs_info = stripe->bg->fs_info;
+ struct btrfs_bio *bbio = NULL;
+- unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+- stripe->bg->length - stripe->logical) >>
+- fs_info->sectorsize_bits;
++ unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
+ u64 stripe_len = BTRFS_STRIPE_LEN;
+ int mirror = stripe->mirror_num;
+ int i;
+@@ -1729,9 +1735,7 @@ static void scrub_submit_initial_read(struct scrub_ctx *sctx,
+ {
+ struct btrfs_fs_info *fs_info = sctx->fs_info;
+ struct btrfs_bio *bbio;
+- unsigned int nr_sectors = min(BTRFS_STRIPE_LEN, stripe->bg->start +
+- stripe->bg->length - stripe->logical) >>
+- fs_info->sectorsize_bits;
++ unsigned int nr_sectors = stripe_length(stripe) >> fs_info->sectorsize_bits;
+ int mirror = stripe->mirror_num;
+
+ ASSERT(stripe->bg);
+@@ -1871,6 +1875,9 @@ static int flush_scrub_stripes(struct scrub_ctx *sctx)
+ stripe = &sctx->stripes[i];
+
+ wait_scrub_stripe_io(stripe);
++ spin_lock(&sctx->stat_lock);
++ sctx->stat.last_physical = stripe->physical + stripe_length(stripe);
++ spin_unlock(&sctx->stat_lock);
+ scrub_reset_stripe(stripe);
+ }
+ out:
+@@ -2139,7 +2146,9 @@ static int scrub_simple_mirror(struct scrub_ctx *sctx,
+ cur_physical, &found_logical);
+ if (ret > 0) {
+ /* No more extent, just update the accounting */
++ spin_lock(&sctx->stat_lock);
+ sctx->stat.last_physical = physical + logical_length;
++ spin_unlock(&sctx->stat_lock);
+ ret = 0;
+ break;
+ }
+@@ -2336,6 +2345,10 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
+ stripe_logical += chunk_logical;
+ ret = scrub_raid56_parity_stripe(sctx, scrub_dev, bg,
+ map, stripe_logical);
++ spin_lock(&sctx->stat_lock);
++ sctx->stat.last_physical = min(physical + BTRFS_STRIPE_LEN,
++ physical_end);
++ spin_unlock(&sctx->stat_lock);
+ if (ret)
+ goto out;
+ goto next;
+diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
+index 897e19790522d..de1c063bc39db 100644
+--- a/fs/btrfs/tree-checker.c
++++ b/fs/btrfs/tree-checker.c
+@@ -1272,6 +1272,19 @@ static void extent_err(const struct extent_buffer *eb, int slot,
+ va_end(args);
+ }
+
++static bool is_valid_dref_root(u64 rootid)
++{
++ /*
++ * The following tree root objectids are allowed to have a data backref:
++ * - subvolume trees
++ * - data reloc tree
++ * - tree root
++ * For v1 space cache
++ */
++ return is_fstree(rootid) || rootid == BTRFS_DATA_RELOC_TREE_OBJECTID ||
++ rootid == BTRFS_ROOT_TREE_OBJECTID;
++}
++
+ static int check_extent_item(struct extent_buffer *leaf,
+ struct btrfs_key *key, int slot,
+ struct btrfs_key *prev_key)
+@@ -1424,6 +1437,8 @@ static int check_extent_item(struct extent_buffer *leaf,
+ struct btrfs_extent_data_ref *dref;
+ struct btrfs_shared_data_ref *sref;
+ u64 seq;
++ u64 dref_root;
++ u64 dref_objectid;
+ u64 dref_offset;
+ u64 inline_offset;
+ u8 inline_type;
+@@ -1467,11 +1482,26 @@ static int check_extent_item(struct extent_buffer *leaf,
+ */
+ case BTRFS_EXTENT_DATA_REF_KEY:
+ dref = (struct btrfs_extent_data_ref *)(&iref->offset);
++ dref_root = btrfs_extent_data_ref_root(leaf, dref);
++ dref_objectid = btrfs_extent_data_ref_objectid(leaf, dref);
+ dref_offset = btrfs_extent_data_ref_offset(leaf, dref);
+ seq = hash_extent_data_ref(
+ btrfs_extent_data_ref_root(leaf, dref),
+ btrfs_extent_data_ref_objectid(leaf, dref),
+ btrfs_extent_data_ref_offset(leaf, dref));
++ if (unlikely(!is_valid_dref_root(dref_root))) {
++ extent_err(leaf, slot,
++ "invalid data ref root value %llu",
++ dref_root);
++ return -EUCLEAN;
++ }
++ if (unlikely(dref_objectid < BTRFS_FIRST_FREE_OBJECTID ||
++ dref_objectid > BTRFS_LAST_FREE_OBJECTID)) {
++ extent_err(leaf, slot,
++ "invalid data ref objectid value %llu",
++ dref_root);
++ return -EUCLEAN;
++ }
+ if (unlikely(!IS_ALIGNED(dref_offset,
+ fs_info->sectorsize))) {
+ extent_err(leaf, slot,
+@@ -1610,6 +1640,8 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
+ return -EUCLEAN;
+ }
+ for (; ptr < end; ptr += sizeof(*dref)) {
++ u64 root;
++ u64 objectid;
+ u64 offset;
+
+ /*
+@@ -1617,7 +1649,22 @@ static int check_extent_data_ref(struct extent_buffer *leaf,
+ * overflow from the leaf due to hash collisions.
+ */
+ dref = (struct btrfs_extent_data_ref *)ptr;
++ root = btrfs_extent_data_ref_root(leaf, dref);
++ objectid = btrfs_extent_data_ref_objectid(leaf, dref);
+ offset = btrfs_extent_data_ref_offset(leaf, dref);
++ if (unlikely(!is_valid_dref_root(root))) {
++ extent_err(leaf, slot,
++ "invalid extent data backref root value %llu",
++ root);
++ return -EUCLEAN;
++ }
++ if (unlikely(objectid < BTRFS_FIRST_FREE_OBJECTID ||
++ objectid > BTRFS_LAST_FREE_OBJECTID)) {
++ extent_err(leaf, slot,
++ "invalid extent data backref objectid value %llu",
++ root);
++ return -EUCLEAN;
++ }
+ if (unlikely(!IS_ALIGNED(offset, leaf->fs_info->sectorsize))) {
+ extent_err(leaf, slot,
+ "invalid extent data backref offset, have %llu expect aligned to %u",
+diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
+index 5556ab491368d..92fda31c68cdc 100644
+--- a/fs/f2fs/f2fs.h
++++ b/fs/f2fs/f2fs.h
+@@ -4154,7 +4154,7 @@ extern struct kmem_cache *f2fs_inode_entry_slab;
+ * inline.c
+ */
+ bool f2fs_may_inline_data(struct inode *inode);
+-bool f2fs_sanity_check_inline_data(struct inode *inode);
++bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage);
+ bool f2fs_may_inline_dentry(struct inode *inode);
+ void f2fs_do_read_inline_data(struct folio *folio, struct page *ipage);
+ void f2fs_truncate_inline_inode(struct inode *inode,
+diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
+index 215daa71dc18a..cca7d448e55cb 100644
+--- a/fs/f2fs/inline.c
++++ b/fs/f2fs/inline.c
+@@ -33,11 +33,29 @@ bool f2fs_may_inline_data(struct inode *inode)
+ return !f2fs_post_read_required(inode);
+ }
+
+-bool f2fs_sanity_check_inline_data(struct inode *inode)
++static bool inode_has_blocks(struct inode *inode, struct page *ipage)
++{
++ struct f2fs_inode *ri = F2FS_INODE(ipage);
++ int i;
++
++ if (F2FS_HAS_BLOCKS(inode))
++ return true;
++
++ for (i = 0; i < DEF_NIDS_PER_INODE; i++) {
++ if (ri->i_nid[i])
++ return true;
++ }
++ return false;
++}
++
++bool f2fs_sanity_check_inline_data(struct inode *inode, struct page *ipage)
+ {
+ if (!f2fs_has_inline_data(inode))
+ return false;
+
++ if (inode_has_blocks(inode, ipage))
++ return false;
++
+ if (!support_inline_data(inode))
+ return true;
+
+diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
+index ed629dabbfda4..57da02bfa823e 100644
+--- a/fs/f2fs/inode.c
++++ b/fs/f2fs/inode.c
+@@ -347,7 +347,7 @@ static bool sanity_check_inode(struct inode *inode, struct page *node_page)
+ }
+ }
+
+- if (f2fs_sanity_check_inline_data(inode)) {
++ if (f2fs_sanity_check_inline_data(inode, node_page)) {
+ f2fs_warn(sbi, "%s: inode (ino=%lx, mode=%u) should not have inline_data, run fsck to fix",
+ __func__, inode->i_ino, inode->i_mode);
+ return false;
+diff --git a/fs/gfs2/quota.c b/fs/gfs2/quota.c
+index aa9cf01028489..52556b6bae6b1 100644
+--- a/fs/gfs2/quota.c
++++ b/fs/gfs2/quota.c
+@@ -75,9 +75,6 @@
+ #define GFS2_QD_HASH_SIZE BIT(GFS2_QD_HASH_SHIFT)
+ #define GFS2_QD_HASH_MASK (GFS2_QD_HASH_SIZE - 1)
+
+-#define QC_CHANGE 0
+-#define QC_SYNC 1
+-
+ /* Lock order: qd_lock -> bucket lock -> qd->lockref.lock -> lru lock */
+ /* -> sd_bitmap_lock */
+ static DEFINE_SPINLOCK(qd_lock);
+@@ -710,7 +707,7 @@ static int sort_qd(const void *a, const void *b)
+ return 0;
+ }
+
+-static void do_qc(struct gfs2_quota_data *qd, s64 change, int qc_type)
++static void do_qc(struct gfs2_quota_data *qd, s64 change)
+ {
+ struct gfs2_sbd *sdp = qd->qd_sbd;
+ struct gfs2_inode *ip = GFS2_I(sdp->sd_qc_inode);
+@@ -735,18 +732,16 @@ static void do_qc(struct gfs2_quota_data *qd, s64 change, int qc_type)
+ qd->qd_change = x;
+ spin_unlock(&qd_lock);
+
+- if (qc_type == QC_CHANGE) {
+- if (!test_and_set_bit(QDF_CHANGE, &qd->qd_flags)) {
+- qd_hold(qd);
+- slot_hold(qd);
+- }
+- } else {
++ if (!x) {
+ gfs2_assert_warn(sdp, test_bit(QDF_CHANGE, &qd->qd_flags));
+ clear_bit(QDF_CHANGE, &qd->qd_flags);
+ qc->qc_flags = 0;
+ qc->qc_id = 0;
+ slot_put(qd);
+ qd_put(qd);
++ } else if (!test_and_set_bit(QDF_CHANGE, &qd->qd_flags)) {
++ qd_hold(qd);
++ slot_hold(qd);
+ }
+
+ if (change < 0) /* Reset quiet flag if we freed some blocks */
+@@ -992,7 +987,7 @@ static int do_sync(unsigned int num_qd, struct gfs2_quota_data **qda)
+ if (error)
+ goto out_end_trans;
+
+- do_qc(qd, -qd->qd_change_sync, QC_SYNC);
++ do_qc(qd, -qd->qd_change_sync);
+ set_bit(QDF_REFRESH, &qd->qd_flags);
+ }
+
+@@ -1312,7 +1307,7 @@ void gfs2_quota_change(struct gfs2_inode *ip, s64 change,
+
+ if (qid_eq(qd->qd_id, make_kqid_uid(uid)) ||
+ qid_eq(qd->qd_id, make_kqid_gid(gid))) {
+- do_qc(qd, change, QC_CHANGE);
++ do_qc(qd, change);
+ }
+ }
+ }
+diff --git a/fs/gfs2/util.c b/fs/gfs2/util.c
+index af4758d8d894c..551efd7820ad8 100644
+--- a/fs/gfs2/util.c
++++ b/fs/gfs2/util.c
+@@ -99,12 +99,12 @@ int check_journal_clean(struct gfs2_sbd *sdp, struct gfs2_jdesc *jd,
+ */
+ int gfs2_freeze_lock_shared(struct gfs2_sbd *sdp)
+ {
++ int flags = LM_FLAG_NOEXP | GL_EXACT;
+ int error;
+
+- error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED,
+- LM_FLAG_NOEXP | GL_EXACT,
++ error = gfs2_glock_nq_init(sdp->sd_freeze_gl, LM_ST_SHARED, flags,
+ &sdp->sd_freeze_gh);
+- if (error)
++ if (error && error != GLR_TRYFAILED)
+ fs_err(sdp, "can't lock the freeze glock: %d\n", error);
+ return error;
+ }
+diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
+index ff69ae24c4e89..272c8a1dab3c2 100644
+--- a/fs/notify/fsnotify.c
++++ b/fs/notify/fsnotify.c
+@@ -117,17 +117,13 @@ void fsnotify_sb_free(struct super_block *sb)
+ * parent cares. Thus when an event happens on a child it can quickly tell
+ * if there is a need to find a parent and send the event to the parent.
+ */
+-void __fsnotify_update_child_dentry_flags(struct inode *inode)
++void fsnotify_set_children_dentry_flags(struct inode *inode)
+ {
+ struct dentry *alias;
+- int watched;
+
+ if (!S_ISDIR(inode->i_mode))
+ return;
+
+- /* determine if the children should tell inode about their events */
+- watched = fsnotify_inode_watches_children(inode);
+-
+ spin_lock(&inode->i_lock);
+ /* run all of the dentries associated with this inode. Since this is a
+ * directory, there damn well better only be one item on this list */
+@@ -143,10 +139,7 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
+ continue;
+
+ spin_lock_nested(&child->d_lock, DENTRY_D_LOCK_NESTED);
+- if (watched)
+- child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+- else
+- child->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
++ child->d_flags |= DCACHE_FSNOTIFY_PARENT_WATCHED;
+ spin_unlock(&child->d_lock);
+ }
+ spin_unlock(&alias->d_lock);
+@@ -154,6 +147,24 @@ void __fsnotify_update_child_dentry_flags(struct inode *inode)
+ spin_unlock(&inode->i_lock);
+ }
+
++/*
++ * Lazily clear false positive PARENT_WATCHED flag for child whose parent had
++ * stopped watching children.
++ */
++static void fsnotify_clear_child_dentry_flag(struct inode *pinode,
++ struct dentry *dentry)
++{
++ spin_lock(&dentry->d_lock);
++ /*
++ * d_lock is a sufficient barrier to prevent observing a non-watched
++ * parent state from before the fsnotify_set_children_dentry_flags()
++ * or fsnotify_update_flags() call that had set PARENT_WATCHED.
++ */
++ if (!fsnotify_inode_watches_children(pinode))
++ dentry->d_flags &= ~DCACHE_FSNOTIFY_PARENT_WATCHED;
++ spin_unlock(&dentry->d_lock);
++}
++
+ /* Are inode/sb/mount interested in parent and name info with this event? */
+ static bool fsnotify_event_needs_parent(struct inode *inode, __u32 mnt_mask,
+ __u32 mask)
+@@ -228,7 +239,7 @@ int __fsnotify_parent(struct dentry *dentry, __u32 mask, const void *data,
+ p_inode = parent->d_inode;
+ p_mask = fsnotify_inode_watches_children(p_inode);
+ if (unlikely(parent_watched && !p_mask))
+- __fsnotify_update_child_dentry_flags(p_inode);
++ fsnotify_clear_child_dentry_flag(p_inode, dentry);
+
+ /*
+ * Include parent/name in notification either if some notification
+diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
+index 2d059f789ee35..663759ed6fbc1 100644
+--- a/fs/notify/fsnotify.h
++++ b/fs/notify/fsnotify.h
+@@ -93,7 +93,7 @@ static inline void fsnotify_clear_marks_by_sb(struct super_block *sb)
+ * update the dentry->d_flags of all of inode's children to indicate if inode cares
+ * about events that happen to its children.
+ */
+-extern void __fsnotify_update_child_dentry_flags(struct inode *inode);
++extern void fsnotify_set_children_dentry_flags(struct inode *inode);
+
+ extern struct kmem_cache *fsnotify_mark_connector_cachep;
+
+diff --git a/fs/notify/mark.c b/fs/notify/mark.c
+index c3eefa70633c4..5e170e7130886 100644
+--- a/fs/notify/mark.c
++++ b/fs/notify/mark.c
+@@ -250,6 +250,24 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+ return fsnotify_update_iref(conn, want_iref);
+ }
+
++static bool fsnotify_conn_watches_children(
++ struct fsnotify_mark_connector *conn)
++{
++ if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
++ return false;
++
++ return fsnotify_inode_watches_children(fsnotify_conn_inode(conn));
++}
++
++static void fsnotify_conn_set_children_dentry_flags(
++ struct fsnotify_mark_connector *conn)
++{
++ if (conn->type != FSNOTIFY_OBJ_TYPE_INODE)
++ return;
++
++ fsnotify_set_children_dentry_flags(fsnotify_conn_inode(conn));
++}
++
+ /*
+ * Calculate mask of events for a list of marks. The caller must make sure
+ * connector and connector->obj cannot disappear under us. Callers achieve
+@@ -258,15 +276,23 @@ static void *__fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+ */
+ void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+ {
++ bool update_children;
++
+ if (!conn)
+ return;
+
+ spin_lock(&conn->lock);
++ update_children = !fsnotify_conn_watches_children(conn);
+ __fsnotify_recalc_mask(conn);
++ update_children &= fsnotify_conn_watches_children(conn);
+ spin_unlock(&conn->lock);
+- if (conn->type == FSNOTIFY_OBJ_TYPE_INODE)
+- __fsnotify_update_child_dentry_flags(
+- fsnotify_conn_inode(conn));
++ /*
++ * Set children's PARENT_WATCHED flags only if parent started watching.
++ * When parent stops watching, we clear false positive PARENT_WATCHED
++ * flags lazily in __fsnotify_parent().
++ */
++ if (update_children)
++ fsnotify_conn_set_children_dentry_flags(conn);
+ }
+
+ /* Free all connectors queued for freeing once SRCU period ends */
+diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
+index 062b86a4936fd..9f5bc41433c15 100644
+--- a/fs/smb/client/smb2inode.c
++++ b/fs/smb/client/smb2inode.c
+@@ -950,7 +950,8 @@ int smb2_query_path_info(const unsigned int xid,
+ cmds[num_cmds++] = SMB2_OP_GET_REPARSE;
+
+ oparms = CIFS_OPARMS(cifs_sb, tcon, full_path,
+- FILE_READ_ATTRIBUTES | FILE_READ_EA,
++ FILE_READ_ATTRIBUTES |
++ FILE_READ_EA | SYNCHRONIZE,
+ FILE_OPEN, create_options |
+ OPEN_REPARSE_POINT, ACL_NO_MODE);
+ cifs_get_readable_path(tcon, full_path, &cfile);
+@@ -1258,7 +1259,8 @@ int smb2_query_reparse_point(const unsigned int xid,
+ cifs_dbg(FYI, "%s: path: %s\n", __func__, full_path);
+
+ cifs_get_readable_path(tcon, full_path, &cfile);
+- oparms = CIFS_OPARMS(cifs_sb, tcon, full_path, FILE_READ_ATTRIBUTES,
++ oparms = CIFS_OPARMS(cifs_sb, tcon, full_path,
++ FILE_READ_ATTRIBUTES | FILE_READ_EA | SYNCHRONIZE,
+ FILE_OPEN, OPEN_REPARSE_POINT, ACL_NO_MODE);
+ rc = smb2_compound_op(xid, tcon, cifs_sb,
+ full_path, &oparms, &in_iov,
+diff --git a/include/clocksource/timer-xilinx.h b/include/clocksource/timer-xilinx.h
+index c0f56fe6d22ae..d116f18de899c 100644
+--- a/include/clocksource/timer-xilinx.h
++++ b/include/clocksource/timer-xilinx.h
+@@ -41,7 +41,7 @@ struct regmap;
+ struct xilinx_timer_priv {
+ struct regmap *map;
+ struct clk *clk;
+- u32 max;
++ u64 max;
+ };
+
+ /**
+diff --git a/include/linux/fsnotify_backend.h b/include/linux/fsnotify_backend.h
+index 4dd6143db2716..8be029bc50b1e 100644
+--- a/include/linux/fsnotify_backend.h
++++ b/include/linux/fsnotify_backend.h
+@@ -594,12 +594,14 @@ static inline __u32 fsnotify_parent_needed_mask(__u32 mask)
+
+ static inline int fsnotify_inode_watches_children(struct inode *inode)
+ {
++ __u32 parent_mask = READ_ONCE(inode->i_fsnotify_mask);
++
+ /* FS_EVENT_ON_CHILD is set if the inode may care */
+- if (!(inode->i_fsnotify_mask & FS_EVENT_ON_CHILD))
++ if (!(parent_mask & FS_EVENT_ON_CHILD))
+ return 0;
+ /* this inode might care about child events, does it care about the
+ * specific set of events that can happen on a child? */
+- return inode->i_fsnotify_mask & FS_EVENTS_POSS_ON_CHILD;
++ return parent_mask & FS_EVENTS_POSS_ON_CHILD;
+ }
+
+ /*
+@@ -613,7 +615,7 @@ static inline void fsnotify_update_flags(struct dentry *dentry)
+ /*
+ * Serialisation of setting PARENT_WATCHED on the dentries is provided
+ * by d_lock. If inotify_inode_watched changes after we have taken
+- * d_lock, the following __fsnotify_update_child_dentry_flags call will
++ * d_lock, the following fsnotify_set_children_dentry_flags call will
+ * find our entry, so it will spin until we complete here, and update
+ * us with the new state.
+ */
+diff --git a/include/linux/hwspinlock.h b/include/linux/hwspinlock.h
+index bfe7c1f1ac6d1..f0231dbc47771 100644
+--- a/include/linux/hwspinlock.h
++++ b/include/linux/hwspinlock.h
+@@ -68,6 +68,7 @@ int __hwspin_lock_timeout(struct hwspinlock *, unsigned int, int,
+ int __hwspin_trylock(struct hwspinlock *, int, unsigned long *);
+ void __hwspin_unlock(struct hwspinlock *, int, unsigned long *);
+ int of_hwspin_lock_get_id_byname(struct device_node *np, const char *name);
++int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id);
+ int devm_hwspin_lock_free(struct device *dev, struct hwspinlock *hwlock);
+ struct hwspinlock *devm_hwspin_lock_request(struct device *dev);
+ struct hwspinlock *devm_hwspin_lock_request_specific(struct device *dev,
+@@ -127,6 +128,11 @@ void __hwspin_unlock(struct hwspinlock *hwlock, int mode, unsigned long *flags)
+ {
+ }
+
++static inline int hwspin_lock_bust(struct hwspinlock *hwlock, unsigned int id)
++{
++ return 0;
++}
++
+ static inline int of_hwspin_lock_get_id(struct device_node *np, int index)
+ {
+ return 0;
+diff --git a/include/linux/i2c.h b/include/linux/i2c.h
+index 424acb98c7c26..c11624a3d9c04 100644
+--- a/include/linux/i2c.h
++++ b/include/linux/i2c.h
+@@ -1053,7 +1053,7 @@ static inline int of_i2c_get_board_info(struct device *dev,
+ struct acpi_resource;
+ struct acpi_resource_i2c_serialbus;
+
+-#if IS_ENABLED(CONFIG_ACPI)
++#if IS_REACHABLE(CONFIG_ACPI) && IS_REACHABLE(CONFIG_I2C)
+ bool i2c_acpi_get_i2c_resource(struct acpi_resource *ares,
+ struct acpi_resource_i2c_serialbus **i2c);
+ int i2c_acpi_client_count(struct acpi_device *adev);
+diff --git a/include/linux/soc/qcom/smem.h b/include/linux/soc/qcom/smem.h
+index a36a3b9d4929e..03187bc958518 100644
+--- a/include/linux/soc/qcom/smem.h
++++ b/include/linux/soc/qcom/smem.h
+@@ -14,4 +14,6 @@ phys_addr_t qcom_smem_virt_to_phys(void *p);
+
+ int qcom_smem_get_soc_id(u32 *id);
+
++int qcom_smem_bust_hwspin_lock_by_host(unsigned int host);
++
+ #endif
+diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h
+index 2a536eea9424e..5b43d220243de 100644
+--- a/include/net/inet_timewait_sock.h
++++ b/include/net/inet_timewait_sock.h
+@@ -93,8 +93,10 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk,
+ struct inet_timewait_death_row *dr,
+ const int state);
+
+-void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
+- struct inet_hashinfo *hashinfo);
++void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
++ struct sock *sk,
++ struct inet_hashinfo *hashinfo,
++ int timeo);
+
+ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo,
+ bool rearm);
+diff --git a/include/net/ip.h b/include/net/ip.h
+index 6d735e00d3f3e..c5606cadb1a55 100644
+--- a/include/net/ip.h
++++ b/include/net/ip.h
+@@ -506,8 +506,7 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk,
+ return mtu - lwtunnel_headroom(skb_dst(skb)->lwtstate, mtu);
+ }
+
+-struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
+- int fc_mx_len,
++struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx, int fc_mx_len,
+ struct netlink_ext_ack *extack);
+ static inline void ip_fib_metrics_put(struct dst_metrics *fib_metrics)
+ {
+diff --git a/include/net/tcp.h b/include/net/tcp.h
+index 32815a40dea16..45bbb54e42e85 100644
+--- a/include/net/tcp.h
++++ b/include/net/tcp.h
+@@ -1216,7 +1216,7 @@ extern struct tcp_congestion_ops tcp_reno;
+
+ struct tcp_congestion_ops *tcp_ca_find(const char *name);
+ struct tcp_congestion_ops *tcp_ca_find_key(u32 key);
+-u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca);
++u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca);
+ #ifdef CONFIG_INET
+ char *tcp_ca_get_name_by_key(u32 key, char *buffer);
+ #else
+diff --git a/include/sound/ump_convert.h b/include/sound/ump_convert.h
+index 28c364c63245d..d099ae27f8491 100644
+--- a/include/sound/ump_convert.h
++++ b/include/sound/ump_convert.h
+@@ -13,6 +13,7 @@ struct ump_cvt_to_ump_bank {
+ unsigned char cc_nrpn_msb, cc_nrpn_lsb;
+ unsigned char cc_data_msb, cc_data_lsb;
+ unsigned char cc_bank_msb, cc_bank_lsb;
++ bool cc_data_msb_set, cc_data_lsb_set;
+ };
+
+ /* context for converting from MIDI1 byte stream to UMP packet */
+diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
+index d965e4d1277e6..52f0094a8c083 100644
+--- a/include/ufs/ufshcd.h
++++ b/include/ufs/ufshcd.h
+@@ -1074,6 +1074,7 @@ struct ufs_hba {
+ bool ext_iid_sup;
+ bool scsi_host_added;
+ bool mcq_sup;
++ bool lsdb_sup;
+ bool mcq_enabled;
+ struct ufshcd_res_info res[RES_MAX];
+ void __iomem *mcq_base;
+diff --git a/include/ufs/ufshci.h b/include/ufs/ufshci.h
+index 385e1c6b8d604..22ba85e81d8c9 100644
+--- a/include/ufs/ufshci.h
++++ b/include/ufs/ufshci.h
+@@ -75,6 +75,7 @@ enum {
+ MASK_OUT_OF_ORDER_DATA_DELIVERY_SUPPORT = 0x02000000,
+ MASK_UIC_DME_TEST_MODE_SUPPORT = 0x04000000,
+ MASK_CRYPTO_SUPPORT = 0x10000000,
++ MASK_LSDB_SUPPORT = 0x20000000,
+ MASK_MCQ_SUPPORT = 0x40000000,
+ };
+
+diff --git a/kernel/dma/debug.c b/kernel/dma/debug.c
+index a6e3792b15f8a..d570535342cb7 100644
+--- a/kernel/dma/debug.c
++++ b/kernel/dma/debug.c
+@@ -416,8 +416,11 @@ static unsigned long long phys_addr(struct dma_debug_entry *entry)
+ * dma_active_cacheline entry to track per event. dma_map_sg(), on the
+ * other hand, consumes a single dma_debug_entry, but inserts 'nents'
+ * entries into the tree.
++ *
++ * Use __GFP_NOWARN because the printk from an OOM, to netconsole, could end
++ * up right back in the DMA debugging code, leading to a deadlock.
+ */
+-static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC);
++static RADIX_TREE(dma_active_cacheline, GFP_ATOMIC | __GFP_NOWARN);
+ static DEFINE_SPINLOCK(radix_lock);
+ #define ACTIVE_CACHELINE_MAX_OVERLAP ((1 << RADIX_TREE_MAX_TAGS) - 1)
+ #define CACHELINE_PER_PAGE_SHIFT (PAGE_SHIFT - L1_CACHE_SHIFT)
+diff --git a/kernel/rcu/tree.h b/kernel/rcu/tree.h
+index bae7925c497fe..179f60ca03130 100644
+--- a/kernel/rcu/tree.h
++++ b/kernel/rcu/tree.h
+@@ -223,7 +223,6 @@ struct rcu_data {
+ struct swait_queue_head nocb_state_wq; /* For offloading state changes */
+ struct task_struct *nocb_gp_kthread;
+ raw_spinlock_t nocb_lock; /* Guard following pair of fields. */
+- atomic_t nocb_lock_contended; /* Contention experienced. */
+ int nocb_defer_wakeup; /* Defer wakeup of nocb_kthread. */
+ struct timer_list nocb_timer; /* Enforce finite deferral. */
+ unsigned long nocb_gp_adv_time; /* Last call_rcu() CB adv (jiffies). */
+diff --git a/kernel/rcu/tree_nocb.h b/kernel/rcu/tree_nocb.h
+index 3f85577bddd4e..2d9eed2bf7509 100644
+--- a/kernel/rcu/tree_nocb.h
++++ b/kernel/rcu/tree_nocb.h
+@@ -91,8 +91,7 @@ module_param(nocb_nobypass_lim_per_jiffy, int, 0);
+
+ /*
+ * Acquire the specified rcu_data structure's ->nocb_bypass_lock. If the
+- * lock isn't immediately available, increment ->nocb_lock_contended to
+- * flag the contention.
++ * lock isn't immediately available, perform minimal sanity check.
+ */
+ static void rcu_nocb_bypass_lock(struct rcu_data *rdp)
+ __acquires(&rdp->nocb_bypass_lock)
+@@ -100,29 +99,12 @@ static void rcu_nocb_bypass_lock(struct rcu_data *rdp)
+ lockdep_assert_irqs_disabled();
+ if (raw_spin_trylock(&rdp->nocb_bypass_lock))
+ return;
+- atomic_inc(&rdp->nocb_lock_contended);
++ /*
++ * Contention expected only when local enqueue collide with
++ * remote flush from kthreads.
++ */
+ WARN_ON_ONCE(smp_processor_id() != rdp->cpu);
+- smp_mb__after_atomic(); /* atomic_inc() before lock. */
+ raw_spin_lock(&rdp->nocb_bypass_lock);
+- smp_mb__before_atomic(); /* atomic_dec() after lock. */
+- atomic_dec(&rdp->nocb_lock_contended);
+-}
+-
+-/*
+- * Spinwait until the specified rcu_data structure's ->nocb_lock is
+- * not contended. Please note that this is extremely special-purpose,
+- * relying on the fact that at most two kthreads and one CPU contend for
+- * this lock, and also that the two kthreads are guaranteed to have frequent
+- * grace-period-duration time intervals between successive acquisitions
+- * of the lock. This allows us to use an extremely simple throttling
+- * mechanism, and further to apply it only to the CPU doing floods of
+- * call_rcu() invocations. Don't try this at home!
+- */
+-static void rcu_nocb_wait_contended(struct rcu_data *rdp)
+-{
+- WARN_ON_ONCE(smp_processor_id() != rdp->cpu);
+- while (WARN_ON_ONCE(atomic_read(&rdp->nocb_lock_contended)))
+- cpu_relax();
+ }
+
+ /*
+@@ -510,7 +492,6 @@ static bool rcu_nocb_try_bypass(struct rcu_data *rdp, struct rcu_head *rhp,
+ }
+
+ // We need to use the bypass.
+- rcu_nocb_wait_contended(rdp);
+ rcu_nocb_bypass_lock(rdp);
+ ncbs = rcu_cblist_n_cbs(&rdp->nocb_bypass);
+ rcu_segcblist_inc_len(&rdp->cblist); /* Must precede enqueue. */
+@@ -1678,12 +1659,11 @@ static void show_rcu_nocb_state(struct rcu_data *rdp)
+
+ sprintf(bufw, "%ld", rsclp->gp_seq[RCU_WAIT_TAIL]);
+ sprintf(bufr, "%ld", rsclp->gp_seq[RCU_NEXT_READY_TAIL]);
+- pr_info(" CB %d^%d->%d %c%c%c%c%c%c F%ld L%ld C%d %c%c%s%c%s%c%c q%ld %c CPU %d%s\n",
++ pr_info(" CB %d^%d->%d %c%c%c%c%c F%ld L%ld C%d %c%c%s%c%s%c%c q%ld %c CPU %d%s\n",
+ rdp->cpu, rdp->nocb_gp_rdp->cpu,
+ nocb_next_rdp ? nocb_next_rdp->cpu : -1,
+ "kK"[!!rdp->nocb_cb_kthread],
+ "bB"[raw_spin_is_locked(&rdp->nocb_bypass_lock)],
+- "cC"[!!atomic_read(&rdp->nocb_lock_contended)],
+ "lL"[raw_spin_is_locked(&rdp->nocb_lock)],
+ "sS"[!!rdp->nocb_cb_sleep],
+ ".W"[swait_active(&rdp->nocb_cb_wq)],
+diff --git a/mm/filemap.c b/mm/filemap.c
+index 657bcd887fdb8..3577f94f69d97 100644
+--- a/mm/filemap.c
++++ b/mm/filemap.c
+@@ -4221,7 +4221,7 @@ int filemap_invalidate_inode(struct inode *inode, bool flush,
+ }
+
+ /* Wait for writeback to complete on all folios and discard. */
+- truncate_inode_pages_range(mapping, start, end);
++ invalidate_inode_pages2_range(mapping, start / PAGE_SIZE, end / PAGE_SIZE);
+
+ unlock:
+ filemap_invalidate_unlock(mapping);
+diff --git a/net/dccp/minisocks.c b/net/dccp/minisocks.c
+index 251a57cf58223..deb52d7d31b48 100644
+--- a/net/dccp/minisocks.c
++++ b/net/dccp/minisocks.c
+@@ -59,11 +59,10 @@ void dccp_time_wait(struct sock *sk, int state, int timeo)
+ * we complete the initialization.
+ */
+ local_bh_disable();
+- inet_twsk_schedule(tw, timeo);
+ /* Linkage updates.
+ * Note that access to tw after this point is illegal.
+ */
+- inet_twsk_hashdance(tw, sk, &dccp_hashinfo);
++ inet_twsk_hashdance_schedule(tw, sk, &dccp_hashinfo, timeo);
+ local_bh_enable();
+ } else {
+ /* Sorry, if we're out of memory, just CLOSE this
+diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
+index 8956026bc0a2c..2b57cd2b96e2a 100644
+--- a/net/ipv4/fib_semantics.c
++++ b/net/ipv4/fib_semantics.c
+@@ -1030,7 +1030,7 @@ bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi)
+ bool ecn_ca = false;
+
+ nla_strscpy(tmp, nla, sizeof(tmp));
+- val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca);
++ val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
+ } else {
+ if (nla_len(nla) != sizeof(u32))
+ return false;
+@@ -1459,8 +1459,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg,
+ fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL);
+ if (!fi)
+ goto failure;
+- fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx,
+- cfg->fc_mx_len, extack);
++ fi->fib_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len, extack);
+ if (IS_ERR(fi->fib_metrics)) {
+ err = PTR_ERR(fi->fib_metrics);
+ kfree(fi);
+diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c
+index e28075f0006e3..628d33a41ce5f 100644
+--- a/net/ipv4/inet_timewait_sock.c
++++ b/net/ipv4/inet_timewait_sock.c
+@@ -96,9 +96,13 @@ static void inet_twsk_add_node_rcu(struct inet_timewait_sock *tw,
+ * Enter the time wait state. This is called with locally disabled BH.
+ * Essentially we whip up a timewait bucket, copy the relevant info into it
+ * from the SK, and mess with hash chains and list linkage.
++ *
++ * The caller must not access @tw anymore after this function returns.
+ */
+-void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
+- struct inet_hashinfo *hashinfo)
++void inet_twsk_hashdance_schedule(struct inet_timewait_sock *tw,
++ struct sock *sk,
++ struct inet_hashinfo *hashinfo,
++ int timeo)
+ {
+ const struct inet_sock *inet = inet_sk(sk);
+ const struct inet_connection_sock *icsk = inet_csk(sk);
+@@ -129,26 +133,33 @@ void inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk,
+
+ spin_lock(lock);
+
++ /* Step 2: Hash TW into tcp ehash chain */
+ inet_twsk_add_node_rcu(tw, &ehead->chain);
+
+ /* Step 3: Remove SK from hash chain */
+ if (__sk_nulls_del_node_init_rcu(sk))
+ sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1);
+
+- spin_unlock(lock);
+
++ /* Ensure above writes are committed into memory before updating the
++ * refcount.
++ * Provides ordering vs later refcount_inc().
++ */
++ smp_wmb();
+ /* tw_refcnt is set to 3 because we have :
+ * - one reference for bhash chain.
+ * - one reference for ehash chain.
+ * - one reference for timer.
+- * We can use atomic_set() because prior spin_lock()/spin_unlock()
+- * committed into memory all tw fields.
+ * Also note that after this point, we lost our implicit reference
+ * so we are not allowed to use tw anymore.
+ */
+ refcount_set(&tw->tw_refcnt, 3);
++
++ inet_twsk_schedule(tw, timeo);
++
++ spin_unlock(lock);
+ }
+-EXPORT_SYMBOL_GPL(inet_twsk_hashdance);
++EXPORT_SYMBOL_GPL(inet_twsk_hashdance_schedule);
+
+ static void tw_timer_handler(struct timer_list *t)
+ {
+@@ -217,7 +228,34 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc);
+ */
+ void inet_twsk_deschedule_put(struct inet_timewait_sock *tw)
+ {
+- if (del_timer_sync(&tw->tw_timer))
++ struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo;
++ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash);
++
++ /* inet_twsk_purge() walks over all sockets, including tw ones,
++ * and removes them via inet_twsk_deschedule_put() after a
++ * refcount_inc_not_zero().
++ *
++ * inet_twsk_hashdance_schedule() must (re)init the refcount before
++ * arming the timer, i.e. inet_twsk_purge can obtain a reference to
++ * a twsk that did not yet schedule the timer.
++ *
++ * The ehash lock synchronizes these two:
++ * After acquiring the lock, the timer is always scheduled (else
++ * timer_shutdown returns false), because hashdance_schedule releases
++ * the ehash lock only after completing the timer initialization.
++ *
++ * Without grabbing the ehash lock, we get:
++ * 1) cpu x sets twsk refcount to 3
++ * 2) cpu y bumps refcount to 4
++ * 3) cpu y calls inet_twsk_deschedule_put() and shuts timer down
++ * 4) cpu x tries to start timer, but mod_timer is a noop post-shutdown
++ * -> timer refcount is never decremented.
++ */
++ spin_lock(lock);
++ /* Makes sure hashdance_schedule() has completed */
++ spin_unlock(lock);
++
++ if (timer_shutdown_sync(&tw->tw_timer))
+ inet_twsk_kill(tw);
+ inet_twsk_put(tw);
+ }
+diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c
+index 0e3ee1532848c..8ddac1f595ed8 100644
+--- a/net/ipv4/metrics.c
++++ b/net/ipv4/metrics.c
+@@ -7,7 +7,7 @@
+ #include <net/net_namespace.h>
+ #include <net/tcp.h>
+
+-static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
++static int ip_metrics_convert(struct nlattr *fc_mx,
+ int fc_mx_len, u32 *metrics,
+ struct netlink_ext_ack *extack)
+ {
+@@ -31,7 +31,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
+ char tmp[TCP_CA_NAME_MAX];
+
+ nla_strscpy(tmp, nla, sizeof(tmp));
+- val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca);
++ val = tcp_ca_get_key_by_name(tmp, &ecn_ca);
+ if (val == TCP_CA_UNSPEC) {
+ NL_SET_ERR_MSG(extack, "Unknown tcp congestion algorithm");
+ return -EINVAL;
+@@ -63,7 +63,7 @@ static int ip_metrics_convert(struct net *net, struct nlattr *fc_mx,
+ return 0;
+ }
+
+-struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
++struct dst_metrics *ip_fib_metrics_init(struct nlattr *fc_mx,
+ int fc_mx_len,
+ struct netlink_ext_ack *extack)
+ {
+@@ -77,7 +77,7 @@ struct dst_metrics *ip_fib_metrics_init(struct net *net, struct nlattr *fc_mx,
+ if (unlikely(!fib_metrics))
+ return ERR_PTR(-ENOMEM);
+
+- err = ip_metrics_convert(net, fc_mx, fc_mx_len, fib_metrics->metrics,
++ err = ip_metrics_convert(fc_mx, fc_mx_len, fib_metrics->metrics,
+ extack);
+ if (!err) {
+ refcount_set(&fib_metrics->refcnt, 1);
+diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c
+index 28ffcfbeef14e..48617d99abb0d 100644
+--- a/net/ipv4/tcp_cong.c
++++ b/net/ipv4/tcp_cong.c
+@@ -46,8 +46,7 @@ void tcp_set_ca_state(struct sock *sk, const u8 ca_state)
+ }
+
+ /* Must be called with rcu lock held */
+-static struct tcp_congestion_ops *tcp_ca_find_autoload(struct net *net,
+- const char *name)
++static struct tcp_congestion_ops *tcp_ca_find_autoload(const char *name)
+ {
+ struct tcp_congestion_ops *ca = tcp_ca_find(name);
+
+@@ -178,7 +177,7 @@ int tcp_update_congestion_control(struct tcp_congestion_ops *ca, struct tcp_cong
+ return ret;
+ }
+
+-u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
++u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca)
+ {
+ const struct tcp_congestion_ops *ca;
+ u32 key = TCP_CA_UNSPEC;
+@@ -186,7 +185,7 @@ u32 tcp_ca_get_key_by_name(struct net *net, const char *name, bool *ecn_ca)
+ might_sleep();
+
+ rcu_read_lock();
+- ca = tcp_ca_find_autoload(net, name);
++ ca = tcp_ca_find_autoload(name);
+ if (ca) {
+ key = ca->key;
+ *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN;
+@@ -283,7 +282,7 @@ int tcp_set_default_congestion_control(struct net *net, const char *name)
+ int ret;
+
+ rcu_read_lock();
+- ca = tcp_ca_find_autoload(net, name);
++ ca = tcp_ca_find_autoload(name);
+ if (!ca) {
+ ret = -ENOENT;
+ } else if (!bpf_try_module_get(ca, ca->owner)) {
+@@ -421,7 +420,7 @@ int tcp_set_congestion_control(struct sock *sk, const char *name, bool load,
+ if (!load)
+ ca = tcp_ca_find(name);
+ else
+- ca = tcp_ca_find_autoload(sock_net(sk), name);
++ ca = tcp_ca_find_autoload(name);
+
+ /* No change asking for existing value */
+ if (ca == icsk->icsk_ca_ops) {
+diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
+index 8f8f93716ff85..da0f502553991 100644
+--- a/net/ipv4/tcp_ipv4.c
++++ b/net/ipv4/tcp_ipv4.c
+@@ -116,6 +116,7 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
+ const struct inet_timewait_sock *tw = inet_twsk(sktw);
+ const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw);
+ struct tcp_sock *tp = tcp_sk(sk);
++ int ts_recent_stamp;
+
+ if (reuse == 2) {
+ /* Still does not detect *everything* that goes through
+@@ -154,10 +155,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
+ If TW bucket has been already destroyed we fall back to VJ's scheme
+ and use initial timestamp retrieved from peer table.
+ */
+- if (tcptw->tw_ts_recent_stamp &&
++ ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
++ if (ts_recent_stamp &&
+ (!twp || (reuse && time_after32(ktime_get_seconds(),
+- tcptw->tw_ts_recent_stamp)))) {
+- /* inet_twsk_hashdance() sets sk_refcnt after putting twsk
++ ts_recent_stamp)))) {
++ /* inet_twsk_hashdance_schedule() sets sk_refcnt after putting twsk
+ * and releasing the bucket lock.
+ */
+ if (unlikely(!refcount_inc_not_zero(&sktw->sk_refcnt)))
+@@ -180,8 +182,8 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp)
+ if (!seq)
+ seq = 1;
+ WRITE_ONCE(tp->write_seq, seq);
+- tp->rx_opt.ts_recent = tcptw->tw_ts_recent;
+- tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
++ tp->rx_opt.ts_recent = READ_ONCE(tcptw->tw_ts_recent);
++ tp->rx_opt.ts_recent_stamp = ts_recent_stamp;
+ }
+
+ return 1;
+@@ -1066,7 +1068,7 @@ static void tcp_v4_timewait_ack(struct sock *sk, struct sk_buff *skb)
+ tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
+ tcp_tw_tsval(tcptw),
+- tcptw->tw_ts_recent,
++ READ_ONCE(tcptw->tw_ts_recent),
+ tw->tw_bound_dev_if, &key,
+ tw->tw_transparent ? IP_REPLY_ARG_NOSRCCHECK : 0,
+ tw->tw_tos,
+diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
+index 0fbebf6266e91..d5da3ec8f846e 100644
+--- a/net/ipv4/tcp_minisocks.c
++++ b/net/ipv4/tcp_minisocks.c
+@@ -101,16 +101,18 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
+ struct tcp_options_received tmp_opt;
+ struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw);
+ bool paws_reject = false;
++ int ts_recent_stamp;
+
+ tmp_opt.saw_tstamp = 0;
+- if (th->doff > (sizeof(*th) >> 2) && tcptw->tw_ts_recent_stamp) {
++ ts_recent_stamp = READ_ONCE(tcptw->tw_ts_recent_stamp);
++ if (th->doff > (sizeof(*th) >> 2) && ts_recent_stamp) {
+ tcp_parse_options(twsk_net(tw), skb, &tmp_opt, 0, NULL);
+
+ if (tmp_opt.saw_tstamp) {
+ if (tmp_opt.rcv_tsecr)
+ tmp_opt.rcv_tsecr -= tcptw->tw_ts_offset;
+- tmp_opt.ts_recent = tcptw->tw_ts_recent;
+- tmp_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp;
++ tmp_opt.ts_recent = READ_ONCE(tcptw->tw_ts_recent);
++ tmp_opt.ts_recent_stamp = ts_recent_stamp;
+ paws_reject = tcp_paws_reject(&tmp_opt, th->rst);
+ }
+ }
+@@ -152,8 +154,10 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
+ twsk_rcv_nxt_update(tcptw, TCP_SKB_CB(skb)->end_seq);
+
+ if (tmp_opt.saw_tstamp) {
+- tcptw->tw_ts_recent_stamp = ktime_get_seconds();
+- tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
++ WRITE_ONCE(tcptw->tw_ts_recent_stamp,
++ ktime_get_seconds());
++ WRITE_ONCE(tcptw->tw_ts_recent,
++ tmp_opt.rcv_tsval);
+ }
+
+ inet_twsk_reschedule(tw, TCP_TIMEWAIT_LEN);
+@@ -197,8 +201,10 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
+ }
+
+ if (tmp_opt.saw_tstamp) {
+- tcptw->tw_ts_recent = tmp_opt.rcv_tsval;
+- tcptw->tw_ts_recent_stamp = ktime_get_seconds();
++ WRITE_ONCE(tcptw->tw_ts_recent,
++ tmp_opt.rcv_tsval);
++ WRITE_ONCE(tcptw->tw_ts_recent_stamp,
++ ktime_get_seconds());
+ }
+
+ inet_twsk_put(tw);
+@@ -225,7 +231,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb,
+ if (th->syn && !th->rst && !th->ack && !paws_reject &&
+ (after(TCP_SKB_CB(skb)->seq, tcptw->tw_rcv_nxt) ||
+ (tmp_opt.saw_tstamp &&
+- (s32)(tcptw->tw_ts_recent - tmp_opt.rcv_tsval) < 0))) {
++ (s32)(READ_ONCE(tcptw->tw_ts_recent) - tmp_opt.rcv_tsval) < 0))) {
+ u32 isn = tcptw->tw_snd_nxt + 65535 + 2;
+ if (isn == 0)
+ isn++;
+@@ -344,11 +350,10 @@ void tcp_time_wait(struct sock *sk, int state, int timeo)
+ * we complete the initialization.
+ */
+ local_bh_disable();
+- inet_twsk_schedule(tw, timeo);
+ /* Linkage updates.
+ * Note that access to tw after this point is illegal.
+ */
+- inet_twsk_hashdance(tw, sk, net->ipv4.tcp_death_row.hashinfo);
++ inet_twsk_hashdance_schedule(tw, sk, net->ipv4.tcp_death_row.hashinfo, timeo);
+ local_bh_enable();
+ } else {
+ /* Sorry, if we're out of memory, just CLOSE this
+diff --git a/net/ipv6/route.c b/net/ipv6/route.c
+index c9a9506b714d7..a9644a8edb960 100644
+--- a/net/ipv6/route.c
++++ b/net/ipv6/route.c
+@@ -3764,7 +3764,7 @@ static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg,
+ if (!rt)
+ goto out;
+
+- rt->fib6_metrics = ip_fib_metrics_init(net, cfg->fc_mx, cfg->fc_mx_len,
++ rt->fib6_metrics = ip_fib_metrics_init(cfg->fc_mx, cfg->fc_mx_len,
+ extack);
+ if (IS_ERR(rt->fib6_metrics)) {
+ err = PTR_ERR(rt->fib6_metrics);
+diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
+index 3385faf1d5dcb..66f6fe5afb030 100644
+--- a/net/ipv6/tcp_ipv6.c
++++ b/net/ipv6/tcp_ipv6.c
+@@ -1196,9 +1196,9 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb)
+ tcp_v6_send_ack(sk, skb, tcptw->tw_snd_nxt, tcptw->tw_rcv_nxt,
+ tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale,
+ tcp_tw_tsval(tcptw),
+- tcptw->tw_ts_recent, tw->tw_bound_dev_if, &key,
+- tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel), tw->tw_priority,
+- tw->tw_txhash);
++ READ_ONCE(tcptw->tw_ts_recent), tw->tw_bound_dev_if,
++ &key, tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel),
++ tw->tw_priority, tw->tw_txhash);
+
+ #ifdef CONFIG_TCP_AO
+ out:
+diff --git a/net/mac80211/main.c b/net/mac80211/main.c
+index 7ba329ebdda91..e44b2a26354b5 100644
+--- a/net/mac80211/main.c
++++ b/net/mac80211/main.c
+@@ -337,6 +337,8 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata,
+
+ might_sleep();
+
++ WARN_ON_ONCE(ieee80211_vif_is_mld(&sdata->vif));
++
+ if (!changed || sdata->vif.type == NL80211_IFTYPE_AP_VLAN)
+ return;
+
+@@ -369,7 +371,6 @@ void ieee80211_bss_info_change_notify(struct ieee80211_sub_if_data *sdata,
+ if (changed & ~BSS_CHANGED_VIF_CFG_FLAGS) {
+ u64 ch = changed & ~BSS_CHANGED_VIF_CFG_FLAGS;
+
+- /* FIXME: should be for each link */
+ trace_drv_link_info_changed(local, sdata, &sdata->vif.bss_conf,
+ changed);
+ if (local->ops->link_info_changed)
+diff --git a/net/wireless/ibss.c b/net/wireless/ibss.c
+index 9f02ee5f08beb..34e5acff39351 100644
+--- a/net/wireless/ibss.c
++++ b/net/wireless/ibss.c
+@@ -3,7 +3,7 @@
+ * Some IBSS support code for cfg80211.
+ *
+ * Copyright 2009 Johannes Berg <johannes@sipsolutions.net>
+- * Copyright (C) 2020-2023 Intel Corporation
++ * Copyright (C) 2020-2024 Intel Corporation
+ */
+
+ #include <linux/etherdevice.h>
+@@ -94,6 +94,9 @@ int __cfg80211_join_ibss(struct cfg80211_registered_device *rdev,
+
+ lockdep_assert_held(&rdev->wiphy.mtx);
+
++ if (wdev->cac_started)
++ return -EBUSY;
++
+ if (wdev->u.ibss.ssid_len)
+ return -EALREADY;
+
+diff --git a/net/wireless/mesh.c b/net/wireless/mesh.c
+index 83306979fbe21..aaca65b66af48 100644
+--- a/net/wireless/mesh.c
++++ b/net/wireless/mesh.c
+@@ -1,7 +1,7 @@
+ // SPDX-License-Identifier: GPL-2.0
+ /*
+ * Portions
+- * Copyright (C) 2022-2023 Intel Corporation
++ * Copyright (C) 2022-2024 Intel Corporation
+ */
+ #include <linux/ieee80211.h>
+ #include <linux/export.h>
+@@ -127,6 +127,9 @@ int __cfg80211_join_mesh(struct cfg80211_registered_device *rdev,
+ if (!rdev->ops->join_mesh)
+ return -EOPNOTSUPP;
+
++ if (wdev->cac_started)
++ return -EBUSY;
++
+ if (!setup->chandef.chan) {
+ /* if no channel explicitly given, use preset channel */
+ setup->chandef = wdev->u.mesh.preset_chandef;
+diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
+index c2829d673bc76..967bc4935b4ed 100644
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -5965,6 +5965,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info)
+ if (!rdev->ops->start_ap)
+ return -EOPNOTSUPP;
+
++ if (wdev->cac_started)
++ return -EBUSY;
++
+ if (wdev->links[link_id].ap.beacon_interval)
+ return -EALREADY;
+
+@@ -9957,6 +9960,17 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
+
+ flush_delayed_work(&rdev->dfs_update_channels_wk);
+
++ switch (wdev->iftype) {
++ case NL80211_IFTYPE_AP:
++ case NL80211_IFTYPE_P2P_GO:
++ case NL80211_IFTYPE_MESH_POINT:
++ case NL80211_IFTYPE_ADHOC:
++ break;
++ default:
++ /* caution - see cfg80211_beaconing_iface_active() below */
++ return -EINVAL;
++ }
++
+ wiphy_lock(wiphy);
+
+ dfs_region = reg_get_dfs_region(wiphy);
+@@ -9987,12 +10001,7 @@ static int nl80211_start_radar_detection(struct sk_buff *skb,
+ goto unlock;
+ }
+
+- if (netif_carrier_ok(dev)) {
+- err = -EBUSY;
+- goto unlock;
+- }
+-
+- if (wdev->cac_started) {
++ if (cfg80211_beaconing_iface_active(wdev) || wdev->cac_started) {
+ err = -EBUSY;
+ goto unlock;
+ }
+diff --git a/net/wireless/scan.c b/net/wireless/scan.c
+index 292b530a6dd31..64c779788a646 100644
+--- a/net/wireless/scan.c
++++ b/net/wireless/scan.c
+@@ -1604,7 +1604,7 @@ struct cfg80211_bss *__cfg80211_get_bss(struct wiphy *wiphy,
+ }
+ EXPORT_SYMBOL(__cfg80211_get_bss);
+
+-static void rb_insert_bss(struct cfg80211_registered_device *rdev,
++static bool rb_insert_bss(struct cfg80211_registered_device *rdev,
+ struct cfg80211_internal_bss *bss)
+ {
+ struct rb_node **p = &rdev->bss_tree.rb_node;
+@@ -1620,7 +1620,7 @@ static void rb_insert_bss(struct cfg80211_registered_device *rdev,
+
+ if (WARN_ON(!cmp)) {
+ /* will sort of leak this BSS */
+- return;
++ return false;
+ }
+
+ if (cmp < 0)
+@@ -1631,6 +1631,7 @@ static void rb_insert_bss(struct cfg80211_registered_device *rdev,
+
+ rb_link_node(&bss->rbn, parent, p);
+ rb_insert_color(&bss->rbn, &rdev->bss_tree);
++ return true;
+ }
+
+ static struct cfg80211_internal_bss *
+@@ -1657,6 +1658,34 @@ rb_find_bss(struct cfg80211_registered_device *rdev,
+ return NULL;
+ }
+
++static void cfg80211_insert_bss(struct cfg80211_registered_device *rdev,
++ struct cfg80211_internal_bss *bss)
++{
++ lockdep_assert_held(&rdev->bss_lock);
++
++ if (!rb_insert_bss(rdev, bss))
++ return;
++ list_add_tail(&bss->list, &rdev->bss_list);
++ rdev->bss_entries++;
++}
++
++static void cfg80211_rehash_bss(struct cfg80211_registered_device *rdev,
++ struct cfg80211_internal_bss *bss)
++{
++ lockdep_assert_held(&rdev->bss_lock);
++
++ rb_erase(&bss->rbn, &rdev->bss_tree);
++ if (!rb_insert_bss(rdev, bss)) {
++ list_del(&bss->list);
++ if (!list_empty(&bss->hidden_list))
++ list_del_init(&bss->hidden_list);
++ if (!list_empty(&bss->pub.nontrans_list))
++ list_del_init(&bss->pub.nontrans_list);
++ rdev->bss_entries--;
++ }
++ rdev->bss_generation++;
++}
++
+ static bool cfg80211_combine_bsses(struct cfg80211_registered_device *rdev,
+ struct cfg80211_internal_bss *new)
+ {
+@@ -1969,9 +1998,7 @@ __cfg80211_bss_update(struct cfg80211_registered_device *rdev,
+ bss_ref_get(rdev, bss_from_pub(tmp->pub.transmitted_bss));
+ }
+
+- list_add_tail(&new->list, &rdev->bss_list);
+- rdev->bss_entries++;
+- rb_insert_bss(rdev, new);
++ cfg80211_insert_bss(rdev, new);
+ found = new;
+ }
+
+@@ -3354,19 +3381,14 @@ void cfg80211_update_assoc_bss_entry(struct wireless_dev *wdev,
+ if (!WARN_ON(!__cfg80211_unlink_bss(rdev, new)))
+ rdev->bss_generation++;
+ }
+-
+- rb_erase(&cbss->rbn, &rdev->bss_tree);
+- rb_insert_bss(rdev, cbss);
+- rdev->bss_generation++;
++ cfg80211_rehash_bss(rdev, cbss);
+
+ list_for_each_entry_safe(nontrans_bss, tmp,
+ &cbss->pub.nontrans_list,
+ nontrans_list) {
+ bss = bss_from_pub(nontrans_bss);
+ bss->pub.channel = chan;
+- rb_erase(&bss->rbn, &rdev->bss_tree);
+- rb_insert_bss(rdev, bss);
+- rdev->bss_generation++;
++ cfg80211_rehash_bss(rdev, bss);
+ }
+
+ done:
+diff --git a/security/apparmor/apparmorfs.c b/security/apparmor/apparmorfs.c
+index bcfea073e3f2e..01b923d97a446 100644
+--- a/security/apparmor/apparmorfs.c
++++ b/security/apparmor/apparmorfs.c
+@@ -1692,6 +1692,10 @@ int __aafs_profile_mkdir(struct aa_profile *profile, struct dentry *parent)
+ struct aa_profile *p;
+ p = aa_deref_parent(profile);
+ dent = prof_dir(p);
++ if (!dent) {
++ error = -ENOENT;
++ goto fail2;
++ }
+ /* adding to parent that previously didn't have children */
+ dent = aafs_create_dir("profiles", dent);
+ if (IS_ERR(dent))
+diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
+index 081129be5b62c..ab939e6449e41 100644
+--- a/security/smack/smack_lsm.c
++++ b/security/smack/smack_lsm.c
+@@ -4456,7 +4456,7 @@ static int smack_inet_conn_request(const struct sock *sk, struct sk_buff *skb,
+ rcu_read_unlock();
+
+ if (hskp == NULL)
+- rc = netlbl_req_setattr(req, &skp->smk_netlabel);
++ rc = netlbl_req_setattr(req, &ssp->smk_out->smk_netlabel);
+ else
+ netlbl_req_delattr(req);
+
+diff --git a/sound/core/seq/seq_ports.h b/sound/core/seq/seq_ports.h
+index b111382f697aa..9e36738c0dd04 100644
+--- a/sound/core/seq/seq_ports.h
++++ b/sound/core/seq/seq_ports.h
+@@ -7,6 +7,7 @@
+ #define __SND_SEQ_PORTS_H
+
+ #include <sound/seq_kernel.h>
++#include <sound/ump_convert.h>
+ #include "seq_lock.h"
+
+ /* list of 'exported' ports */
+@@ -42,17 +43,6 @@ struct snd_seq_port_subs_info {
+ int (*close)(void *private_data, struct snd_seq_port_subscribe *info);
+ };
+
+-/* context for converting from legacy control event to UMP packet */
+-struct snd_seq_ump_midi2_bank {
+- bool rpn_set;
+- bool nrpn_set;
+- bool bank_set;
+- unsigned char cc_rpn_msb, cc_rpn_lsb;
+- unsigned char cc_nrpn_msb, cc_nrpn_lsb;
+- unsigned char cc_data_msb, cc_data_lsb;
+- unsigned char cc_bank_msb, cc_bank_lsb;
+-};
+-
+ struct snd_seq_client_port {
+
+ struct snd_seq_addr addr; /* client/port number */
+@@ -88,7 +78,7 @@ struct snd_seq_client_port {
+ unsigned char ump_group;
+
+ #if IS_ENABLED(CONFIG_SND_SEQ_UMP)
+- struct snd_seq_ump_midi2_bank midi2_bank[16]; /* per channel */
++ struct ump_cvt_to_ump_bank midi2_bank[16]; /* per channel */
+ #endif
+ };
+
+diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
+index d9dacfbe4a9ae..4dd540cbb1cbb 100644
+--- a/sound/core/seq/seq_ump_convert.c
++++ b/sound/core/seq/seq_ump_convert.c
+@@ -368,7 +368,7 @@ static int cvt_ump_midi1_to_midi2(struct snd_seq_client *dest,
+ struct snd_seq_ump_event ev_cvt;
+ const union snd_ump_midi1_msg *midi1 = (const union snd_ump_midi1_msg *)event->ump;
+ union snd_ump_midi2_msg *midi2 = (union snd_ump_midi2_msg *)ev_cvt.ump;
+- struct snd_seq_ump_midi2_bank *cc;
++ struct ump_cvt_to_ump_bank *cc;
+
+ ev_cvt = *event;
+ memset(&ev_cvt.ump, 0, sizeof(ev_cvt.ump));
+@@ -789,28 +789,45 @@ static int paf_ev_to_ump_midi2(const struct snd_seq_event *event,
+ return 1;
+ }
+
++static void reset_rpn(struct ump_cvt_to_ump_bank *cc)
++{
++ cc->rpn_set = 0;
++ cc->nrpn_set = 0;
++ cc->cc_rpn_msb = cc->cc_rpn_lsb = 0;
++ cc->cc_data_msb = cc->cc_data_lsb = 0;
++ cc->cc_data_msb_set = cc->cc_data_lsb_set = 0;
++}
++
+ /* set up the MIDI2 RPN/NRPN packet data from the parsed info */
+-static void fill_rpn(struct snd_seq_ump_midi2_bank *cc,
+- union snd_ump_midi2_msg *data,
+- unsigned char channel)
++static int fill_rpn(struct ump_cvt_to_ump_bank *cc,
++ union snd_ump_midi2_msg *data,
++ unsigned char channel,
++ bool flush)
+ {
++ if (!(cc->cc_data_lsb_set || cc->cc_data_msb_set))
++ return 0; // skip
++ /* when not flushing, wait for complete data set */
++ if (!flush && (!cc->cc_data_lsb_set || !cc->cc_data_msb_set))
++ return 0; // skip
++
+ if (cc->rpn_set) {
+ data->rpn.status = UMP_MSG_STATUS_RPN;
+ data->rpn.bank = cc->cc_rpn_msb;
+ data->rpn.index = cc->cc_rpn_lsb;
+- cc->rpn_set = 0;
+- cc->cc_rpn_msb = cc->cc_rpn_lsb = 0;
+- } else {
++ } else if (cc->nrpn_set) {
+ data->rpn.status = UMP_MSG_STATUS_NRPN;
+ data->rpn.bank = cc->cc_nrpn_msb;
+ data->rpn.index = cc->cc_nrpn_lsb;
+- cc->nrpn_set = 0;
+- cc->cc_nrpn_msb = cc->cc_nrpn_lsb = 0;
++ } else {
++ return 0; // skip
+ }
++
+ data->rpn.data = upscale_14_to_32bit((cc->cc_data_msb << 7) |
+ cc->cc_data_lsb);
+ data->rpn.channel = channel;
+- cc->cc_data_msb = cc->cc_data_lsb = 0;
++
++ reset_rpn(cc);
++ return 1;
+ }
+
+ /* convert CC event to MIDI 2.0 UMP */
+@@ -822,29 +839,39 @@ static int cc_ev_to_ump_midi2(const struct snd_seq_event *event,
+ unsigned char channel = event->data.control.channel & 0x0f;
+ unsigned char index = event->data.control.param & 0x7f;
+ unsigned char val = event->data.control.value & 0x7f;
+- struct snd_seq_ump_midi2_bank *cc = &dest_port->midi2_bank[channel];
++ struct ump_cvt_to_ump_bank *cc = &dest_port->midi2_bank[channel];
++ int ret;
+
+ /* process special CC's (bank/rpn/nrpn) */
+ switch (index) {
+ case UMP_CC_RPN_MSB:
++ ret = fill_rpn(cc, data, channel, true);
+ cc->rpn_set = 1;
+ cc->cc_rpn_msb = val;
+- return 0; // skip
++ if (cc->cc_rpn_msb == 0x7f && cc->cc_rpn_lsb == 0x7f)
++ reset_rpn(cc);
++ return ret;
+ case UMP_CC_RPN_LSB:
++ ret = fill_rpn(cc, data, channel, true);
+ cc->rpn_set = 1;
+ cc->cc_rpn_lsb = val;
+- return 0; // skip
++ if (cc->cc_rpn_msb == 0x7f && cc->cc_rpn_lsb == 0x7f)
++ reset_rpn(cc);
++ return ret;
+ case UMP_CC_NRPN_MSB:
++ ret = fill_rpn(cc, data, channel, true);
+ cc->nrpn_set = 1;
+ cc->cc_nrpn_msb = val;
+- return 0; // skip
++ return ret;
+ case UMP_CC_NRPN_LSB:
++ ret = fill_rpn(cc, data, channel, true);
+ cc->nrpn_set = 1;
+ cc->cc_nrpn_lsb = val;
+- return 0; // skip
++ return ret;
+ case UMP_CC_DATA:
++ cc->cc_data_msb_set = 1;
+ cc->cc_data_msb = val;
+- return 0; // skip
++ return fill_rpn(cc, data, channel, false);
+ case UMP_CC_BANK_SELECT:
+ cc->bank_set = 1;
+ cc->cc_bank_msb = val;
+@@ -854,11 +881,9 @@ static int cc_ev_to_ump_midi2(const struct snd_seq_event *event,
+ cc->cc_bank_lsb = val;
+ return 0; // skip
+ case UMP_CC_DATA_LSB:
++ cc->cc_data_lsb_set = 1;
+ cc->cc_data_lsb = val;
+- if (!(cc->rpn_set || cc->nrpn_set))
+- return 0; // skip
+- fill_rpn(cc, data, channel);
+- return 1;
++ return fill_rpn(cc, data, channel, false);
+ }
+
+ data->cc.status = status;
+@@ -887,7 +912,7 @@ static int pgm_ev_to_ump_midi2(const struct snd_seq_event *event,
+ unsigned char status)
+ {
+ unsigned char channel = event->data.control.channel & 0x0f;
+- struct snd_seq_ump_midi2_bank *cc = &dest_port->midi2_bank[channel];
++ struct ump_cvt_to_ump_bank *cc = &dest_port->midi2_bank[channel];
+
+ data->pg.status = status;
+ data->pg.channel = channel;
+@@ -924,8 +949,9 @@ static int ctrl14_ev_to_ump_midi2(const struct snd_seq_event *event,
+ {
+ unsigned char channel = event->data.control.channel & 0x0f;
+ unsigned char index = event->data.control.param & 0x7f;
+- struct snd_seq_ump_midi2_bank *cc = &dest_port->midi2_bank[channel];
++ struct ump_cvt_to_ump_bank *cc = &dest_port->midi2_bank[channel];
+ unsigned char msb, lsb;
++ int ret;
+
+ msb = (event->data.control.value >> 7) & 0x7f;
+ lsb = event->data.control.value & 0x7f;
+@@ -939,28 +965,27 @@ static int ctrl14_ev_to_ump_midi2(const struct snd_seq_event *event,
+ cc->cc_bank_lsb = lsb;
+ return 0; // skip
+ case UMP_CC_RPN_MSB:
+- cc->cc_rpn_msb = msb;
+- fallthrough;
+ case UMP_CC_RPN_LSB:
+- cc->rpn_set = 1;
++ ret = fill_rpn(cc, data, channel, true);
++ cc->cc_rpn_msb = msb;
+ cc->cc_rpn_lsb = lsb;
+- return 0; // skip
++ cc->rpn_set = 1;
++ if (cc->cc_rpn_msb == 0x7f && cc->cc_rpn_lsb == 0x7f)
++ reset_rpn(cc);
++ return ret;
+ case UMP_CC_NRPN_MSB:
+- cc->cc_nrpn_msb = msb;
+- fallthrough;
+ case UMP_CC_NRPN_LSB:
++ ret = fill_rpn(cc, data, channel, true);
++ cc->cc_nrpn_msb = msb;
+ cc->nrpn_set = 1;
+ cc->cc_nrpn_lsb = lsb;
+- return 0; // skip
++ return ret;
+ case UMP_CC_DATA:
+- cc->cc_data_msb = msb;
+- fallthrough;
+ case UMP_CC_DATA_LSB:
++ cc->cc_data_msb_set = cc->cc_data_lsb_set = 1;
++ cc->cc_data_msb = msb;
+ cc->cc_data_lsb = lsb;
+- if (!(cc->rpn_set || cc->nrpn_set))
+- return 0; // skip
+- fill_rpn(cc, data, channel);
+- return 1;
++ return fill_rpn(cc, data, channel, false);
+ }
+
+ data->cc.status = UMP_MSG_STATUS_CC;
+diff --git a/sound/core/ump_convert.c b/sound/core/ump_convert.c
+index f67c44c83fde4..0fe13d0316568 100644
+--- a/sound/core/ump_convert.c
++++ b/sound/core/ump_convert.c
+@@ -287,25 +287,42 @@ static int cvt_legacy_system_to_ump(struct ump_cvt_to_ump *cvt,
+ return 4;
+ }
+
+-static void fill_rpn(struct ump_cvt_to_ump_bank *cc,
+- union snd_ump_midi2_msg *midi2)
++static void reset_rpn(struct ump_cvt_to_ump_bank *cc)
+ {
++ cc->rpn_set = 0;
++ cc->nrpn_set = 0;
++ cc->cc_rpn_msb = cc->cc_rpn_lsb = 0;
++ cc->cc_data_msb = cc->cc_data_lsb = 0;
++ cc->cc_data_msb_set = cc->cc_data_lsb_set = 0;
++}
++
++static int fill_rpn(struct ump_cvt_to_ump_bank *cc,
++ union snd_ump_midi2_msg *midi2,
++ bool flush)
++{
++ if (!(cc->cc_data_lsb_set || cc->cc_data_msb_set))
++ return 0; // skip
++ /* when not flushing, wait for complete data set */
++ if (!flush && (!cc->cc_data_lsb_set || !cc->cc_data_msb_set))
++ return 0; // skip
++
+ if (cc->rpn_set) {
+ midi2->rpn.status = UMP_MSG_STATUS_RPN;
+ midi2->rpn.bank = cc->cc_rpn_msb;
+ midi2->rpn.index = cc->cc_rpn_lsb;
+- cc->rpn_set = 0;
+- cc->cc_rpn_msb = cc->cc_rpn_lsb = 0;
+- } else {
++ } else if (cc->nrpn_set) {
+ midi2->rpn.status = UMP_MSG_STATUS_NRPN;
+ midi2->rpn.bank = cc->cc_nrpn_msb;
+ midi2->rpn.index = cc->cc_nrpn_lsb;
+- cc->nrpn_set = 0;
+- cc->cc_nrpn_msb = cc->cc_nrpn_lsb = 0;
++ } else {
++ return 0; // skip
+ }
++
+ midi2->rpn.data = upscale_14_to_32bit((cc->cc_data_msb << 7) |
+ cc->cc_data_lsb);
+- cc->cc_data_msb = cc->cc_data_lsb = 0;
++
++ reset_rpn(cc);
++ return 1;
+ }
+
+ /* convert to a MIDI 1.0 Channel Voice message */
+@@ -318,6 +335,7 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt,
+ struct ump_cvt_to_ump_bank *cc;
+ union snd_ump_midi2_msg *midi2 = (union snd_ump_midi2_msg *)data;
+ unsigned char status, channel;
++ int ret;
+
+ BUILD_BUG_ON(sizeof(union snd_ump_midi1_msg) != 4);
+ BUILD_BUG_ON(sizeof(union snd_ump_midi2_msg) != 8);
+@@ -358,24 +376,33 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt,
+ case UMP_MSG_STATUS_CC:
+ switch (buf[1]) {
+ case UMP_CC_RPN_MSB:
++ ret = fill_rpn(cc, midi2, true);
+ cc->rpn_set = 1;
+ cc->cc_rpn_msb = buf[2];
+- return 0; // skip
++ if (cc->cc_rpn_msb == 0x7f && cc->cc_rpn_lsb == 0x7f)
++ reset_rpn(cc);
++ return ret;
+ case UMP_CC_RPN_LSB:
++ ret = fill_rpn(cc, midi2, true);
+ cc->rpn_set = 1;
+ cc->cc_rpn_lsb = buf[2];
+- return 0; // skip
++ if (cc->cc_rpn_msb == 0x7f && cc->cc_rpn_lsb == 0x7f)
++ reset_rpn(cc);
++ return ret;
+ case UMP_CC_NRPN_MSB:
++ ret = fill_rpn(cc, midi2, true);
+ cc->nrpn_set = 1;
+ cc->cc_nrpn_msb = buf[2];
+- return 0; // skip
++ return ret;
+ case UMP_CC_NRPN_LSB:
++ ret = fill_rpn(cc, midi2, true);
+ cc->nrpn_set = 1;
+ cc->cc_nrpn_lsb = buf[2];
+- return 0; // skip
++ return ret;
+ case UMP_CC_DATA:
++ cc->cc_data_msb_set = 1;
+ cc->cc_data_msb = buf[2];
+- return 0; // skip
++ return fill_rpn(cc, midi2, false);
+ case UMP_CC_BANK_SELECT:
+ cc->bank_set = 1;
+ cc->cc_bank_msb = buf[2];
+@@ -385,12 +412,9 @@ static int cvt_legacy_cmd_to_ump(struct ump_cvt_to_ump *cvt,
+ cc->cc_bank_lsb = buf[2];
+ return 0; // skip
+ case UMP_CC_DATA_LSB:
++ cc->cc_data_lsb_set = 1;
+ cc->cc_data_lsb = buf[2];
+- if (cc->rpn_set || cc->nrpn_set)
+- fill_rpn(cc, midi2);
+- else
+- return 0; // skip
+- break;
++ return fill_rpn(cc, midi2, false);
+ default:
+ midi2->cc.index = buf[1];
+ midi2->cc.data = upscale_7_to_32bit(buf[2]);
+diff --git a/sound/pci/hda/hda_generic.c b/sound/pci/hda/hda_generic.c
+index f64d9dc197a31..9cff87dfbecbb 100644
+--- a/sound/pci/hda/hda_generic.c
++++ b/sound/pci/hda/hda_generic.c
+@@ -4955,6 +4955,69 @@ void snd_hda_gen_stream_pm(struct hda_codec *codec, hda_nid_t nid, bool on)
+ }
+ EXPORT_SYMBOL_GPL(snd_hda_gen_stream_pm);
+
++/* forcibly mute the speaker output without caching; return true if updated */
++static bool force_mute_output_path(struct hda_codec *codec, hda_nid_t nid)
++{
++ if (!nid)
++ return false;
++ if (!nid_has_mute(codec, nid, HDA_OUTPUT))
++ return false; /* no mute, skip */
++ if (snd_hda_codec_amp_read(codec, nid, 0, HDA_OUTPUT, 0) &
++ snd_hda_codec_amp_read(codec, nid, 1, HDA_OUTPUT, 0) &
++ HDA_AMP_MUTE)
++ return false; /* both channels already muted, skip */
++
++ /* direct amp update without caching */
++ snd_hda_codec_write(codec, nid, 0, AC_VERB_SET_AMP_GAIN_MUTE,
++ AC_AMP_SET_OUTPUT | AC_AMP_SET_LEFT |
++ AC_AMP_SET_RIGHT | HDA_AMP_MUTE);
++ return true;
++}
++
++/**
++ * snd_hda_gen_shutup_speakers - Forcibly mute the speaker outputs
++ * @codec: the HDA codec
++ *
++ * Forcibly mute the speaker outputs, to be called at suspend or shutdown.
++ *
++ * The mute state done by this function isn't cached, hence the original state
++ * will be restored at resume.
++ *
++ * Return true if the mute state has been changed.
++ */
++bool snd_hda_gen_shutup_speakers(struct hda_codec *codec)
++{
++ struct hda_gen_spec *spec = codec->spec;
++ const int *paths;
++ const struct nid_path *path;
++ int i, p, num_paths;
++ bool updated = false;
++
++ /* if already powered off, do nothing */
++ if (!snd_hdac_is_power_on(&codec->core))
++ return false;
++
++ if (spec->autocfg.line_out_type == AUTO_PIN_SPEAKER_OUT) {
++ paths = spec->out_paths;
++ num_paths = spec->autocfg.line_outs;
++ } else {
++ paths = spec->speaker_paths;
++ num_paths = spec->autocfg.speaker_outs;
++ }
++
++ for (i = 0; i < num_paths; i++) {
++ path = snd_hda_get_path_from_idx(codec, paths[i]);
++ if (!path)
++ continue;
++ for (p = 0; p < path->depth; p++)
++ if (force_mute_output_path(codec, path->path[p]))
++ updated = true;
++ }
++
++ return updated;
++}
++EXPORT_SYMBOL_GPL(snd_hda_gen_shutup_speakers);
++
+ /**
+ * snd_hda_gen_parse_auto_config - Parse the given BIOS configuration and
+ * set up the hda_gen_spec
+diff --git a/sound/pci/hda/hda_generic.h b/sound/pci/hda/hda_generic.h
+index 8f5ecf740c491..08544601b4ce2 100644
+--- a/sound/pci/hda/hda_generic.h
++++ b/sound/pci/hda/hda_generic.h
+@@ -353,5 +353,6 @@ int snd_hda_gen_add_mute_led_cdev(struct hda_codec *codec,
+ int snd_hda_gen_add_micmute_led_cdev(struct hda_codec *codec,
+ int (*callback)(struct led_classdev *,
+ enum led_brightness));
++bool snd_hda_gen_shutup_speakers(struct hda_codec *codec);
+
+ #endif /* __SOUND_HDA_GENERIC_H */
+diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
+index 4472923ba694b..f030669243f9a 100644
+--- a/sound/pci/hda/patch_conexant.c
++++ b/sound/pci/hda/patch_conexant.c
+@@ -205,6 +205,8 @@ static void cx_auto_shutdown(struct hda_codec *codec)
+ {
+ struct conexant_spec *spec = codec->spec;
+
++ snd_hda_gen_shutup_speakers(codec);
++
+ /* Turn the problematic codec into D3 to avoid spurious noises
+ from the internal speaker during (and after) reboot */
+ cx_auto_turn_eapd(codec, spec->num_eapds, spec->eapds, false);
+diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
+index d597e59863ee3..f6c1dbd0ebcf5 100644
+--- a/sound/soc/amd/yc/acp6x-mach.c
++++ b/sound/soc/amd/yc/acp6x-mach.c
+@@ -220,6 +220,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "21J6"),
+ }
+ },
++ {
++ .driver_data = &acp6x_card,
++ .matches = {
++ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
++ DMI_MATCH(DMI_PRODUCT_NAME, "21M3"),
++ }
++ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+@@ -430,6 +437,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
+ DMI_MATCH(DMI_BOARD_NAME, "8A3E"),
+ }
+ },
++ {
++ .driver_data = &acp6x_card,
++ .matches = {
++ DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
++ DMI_MATCH(DMI_BOARD_NAME, "8B27"),
++ }
++ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+diff --git a/sound/soc/codecs/es8326.c b/sound/soc/codecs/es8326.c
+index 6a4e42e5e35b9..e620af9b864cb 100644
+--- a/sound/soc/codecs/es8326.c
++++ b/sound/soc/codecs/es8326.c
+@@ -825,6 +825,8 @@ static void es8326_jack_detect_handler(struct work_struct *work)
+ es8326_disable_micbias(es8326->component);
+ if (es8326->jack->status & SND_JACK_HEADPHONE) {
+ dev_dbg(comp->dev, "Report hp remove event\n");
++ snd_soc_jack_report(es8326->jack, 0,
++ SND_JACK_BTN_0 | SND_JACK_BTN_1 | SND_JACK_BTN_2);
+ snd_soc_jack_report(es8326->jack, 0, SND_JACK_HEADSET);
+ /* mute adc when mic path switch */
+ regmap_write(es8326->regmap, ES8326_ADC1_SRC, 0x44);
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+index c0ba79a8ad6da..a4762c49a8786 100755
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+@@ -420,12 +420,17 @@ reset_with_fail()
+ fi
+ }
+
++start_events()
++{
++ mptcp_lib_events "${ns1}" "${evts_ns1}" evts_ns1_pid
++ mptcp_lib_events "${ns2}" "${evts_ns2}" evts_ns2_pid
++}
++
+ reset_with_events()
+ {
+ reset "${1}" || return 1
+
+- mptcp_lib_events "${ns1}" "${evts_ns1}" evts_ns1_pid
+- mptcp_lib_events "${ns2}" "${evts_ns2}" evts_ns2_pid
++ start_events
+ }
+
+ reset_with_tcp_filter()
+@@ -3333,6 +3338,36 @@ userspace_pm_chk_get_addr()
+ fi
+ }
+
++# $1: ns ; $2: event type ; $3: count
++chk_evt_nr()
++{
++ local ns=${1}
++ local evt_name="${2}"
++ local exp="${3}"
++
++ local evts="${evts_ns1}"
++ local evt="${!evt_name}"
++ local count
++
++ evt_name="${evt_name:16}" # without MPTCP_LIB_EVENT_
++ [ "${ns}" == "ns2" ] && evts="${evts_ns2}"
++
++ print_check "event ${ns} ${evt_name} (${exp})"
++
++ if [[ "${evt_name}" = "LISTENER_"* ]] &&
++ ! mptcp_lib_kallsyms_has "mptcp_event_pm_listener$"; then
++ print_skip "event not supported"
++ return
++ fi
++
++ count=$(grep -cw "type:${evt}" "${evts}")
++ if [ "${count}" != "${exp}" ]; then
++ fail_test "got ${count} events, expected ${exp}"
++ else
++ print_ok
++ fi
++}
++
+ userspace_tests()
+ {
+ # userspace pm type prevents add_addr
+@@ -3572,6 +3607,7 @@ endpoint_tests()
+
+ if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT &&
+ mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
++ start_events
+ pm_nl_set_limits $ns1 0 3
+ pm_nl_set_limits $ns2 0 3
+ pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
+@@ -3623,9 +3659,129 @@ endpoint_tests()
+
+ mptcp_lib_kill_wait $tests_pid
+
++ kill_events_pids
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_LISTENER_CREATED 1
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_CREATED 1
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_ESTABLISHED 1
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_ANNOUNCED 0
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_REMOVED 4
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_ESTABLISHED 6
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_CLOSED 4
++
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_CREATED 1
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_ESTABLISHED 1
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_ANNOUNCED 0
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_REMOVED 0
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_ESTABLISHED 6
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 5 # one has been closed before estab
++
+ chk_join_nr 6 6 6
+ chk_rm_nr 4 4
+ fi
++
++ # remove and re-add
++ if reset_with_events "delete re-add signal" &&
++ mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
++ pm_nl_set_limits $ns1 0 3
++ pm_nl_set_limits $ns2 3 3
++ pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
++ # broadcast IP: no packet for this address will be received on ns1
++ pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
++ pm_nl_add_endpoint $ns1 10.0.1.1 id 42 flags signal
++ test_linkfail=4 speed=5 \
++ run_tests $ns1 $ns2 10.0.1.1 &
++ local tests_pid=$!
++
++ wait_mpj $ns2
++ pm_nl_check_endpoint "creation" \
++ $ns1 10.0.2.1 id 1 flags signal
++ chk_subflow_nr "before delete" 2
++ chk_mptcp_info subflows 1 subflows 1
++
++ pm_nl_del_endpoint $ns1 1 10.0.2.1
++ pm_nl_del_endpoint $ns1 2 224.0.0.1
++ sleep 0.5
++ chk_subflow_nr "after delete" 1
++ chk_mptcp_info subflows 0 subflows 0
++
++ pm_nl_add_endpoint $ns1 10.0.2.1 id 1 flags signal
++ pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
++ wait_mpj $ns2
++ chk_subflow_nr "after re-add" 3
++ chk_mptcp_info subflows 2 subflows 2
++
++ pm_nl_del_endpoint $ns1 42 10.0.1.1
++ sleep 0.5
++ chk_subflow_nr "after delete ID 0" 2
++ chk_mptcp_info subflows 2 subflows 2
++
++ pm_nl_add_endpoint $ns1 10.0.1.1 id 99 flags signal
++ wait_mpj $ns2
++ chk_subflow_nr "after re-add ID 0" 3
++ chk_mptcp_info subflows 3 subflows 3
++
++ pm_nl_del_endpoint $ns1 99 10.0.1.1
++ sleep 0.5
++ chk_subflow_nr "after re-delete ID 0" 2
++ chk_mptcp_info subflows 2 subflows 2
++
++ pm_nl_add_endpoint $ns1 10.0.1.1 id 88 flags signal
++ wait_mpj $ns2
++ chk_subflow_nr "after re-re-add ID 0" 3
++ chk_mptcp_info subflows 3 subflows 3
++ mptcp_lib_kill_wait $tests_pid
++
++ kill_events_pids
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_LISTENER_CREATED 1
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_CREATED 1
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_ESTABLISHED 1
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_ANNOUNCED 0
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_REMOVED 0
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_ESTABLISHED 5
++ chk_evt_nr ns1 MPTCP_LIB_EVENT_SUB_CLOSED 3
++
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_CREATED 1
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_ESTABLISHED 1
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_ANNOUNCED 6
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_REMOVED 4
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_ESTABLISHED 5
++ chk_evt_nr ns2 MPTCP_LIB_EVENT_SUB_CLOSED 3
++
++ chk_join_nr 5 5 5
++ chk_add_nr 6 6
++ chk_rm_nr 4 3 invert
++ fi
++
++ # flush and re-add
++ if reset_with_tcp_filter "flush re-add" ns2 10.0.3.2 REJECT OUTPUT &&
++ mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
++ pm_nl_set_limits $ns1 0 2
++ pm_nl_set_limits $ns2 1 2
++ # broadcast IP: no packet for this address will be received on ns1
++ pm_nl_add_endpoint $ns1 224.0.0.1 id 2 flags signal
++ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
++ test_linkfail=4 speed=20 \
++ run_tests $ns1 $ns2 10.0.1.1 &
++ local tests_pid=$!
++
++ wait_attempt_fail $ns2
++ chk_subflow_nr "before flush" 1
++ chk_mptcp_info subflows 0 subflows 0
++
++ pm_nl_flush_endpoint $ns2
++ pm_nl_flush_endpoint $ns1
++ wait_rm_addr $ns2 0
++ ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
++ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
++ wait_mpj $ns2
++ pm_nl_add_endpoint $ns1 10.0.3.1 id 2 flags signal
++ wait_mpj $ns2
++ mptcp_lib_kill_wait $tests_pid
++
++ chk_join_nr 2 2 2
++ chk_add_nr 2 2
++ chk_rm_nr 1 0 invert
++ fi
+ }
+
+ # [$1: error message]
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_lib.sh b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+index 6ffa9b7a3260d..e299090eb0426 100644
+--- a/tools/testing/selftests/net/mptcp/mptcp_lib.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_lib.sh
+@@ -9,10 +9,14 @@ readonly KSFT_SKIP=4
+ readonly KSFT_TEST="${MPTCP_LIB_KSFT_TEST:-$(basename "${0}" .sh)}"
+
+ # These variables are used in some selftests, read-only
++declare -rx MPTCP_LIB_EVENT_CREATED=1 # MPTCP_EVENT_CREATED
++declare -rx MPTCP_LIB_EVENT_ESTABLISHED=2 # MPTCP_EVENT_ESTABLISHED
++declare -rx MPTCP_LIB_EVENT_CLOSED=3 # MPTCP_EVENT_CLOSED
+ declare -rx MPTCP_LIB_EVENT_ANNOUNCED=6 # MPTCP_EVENT_ANNOUNCED
+ declare -rx MPTCP_LIB_EVENT_REMOVED=7 # MPTCP_EVENT_REMOVED
+ declare -rx MPTCP_LIB_EVENT_SUB_ESTABLISHED=10 # MPTCP_EVENT_SUB_ESTABLISHED
+ declare -rx MPTCP_LIB_EVENT_SUB_CLOSED=11 # MPTCP_EVENT_SUB_CLOSED
++declare -rx MPTCP_LIB_EVENT_SUB_PRIORITY=13 # MPTCP_EVENT_SUB_PRIORITY
+ declare -rx MPTCP_LIB_EVENT_LISTENER_CREATED=15 # MPTCP_EVENT_LISTENER_CREATED
+ declare -rx MPTCP_LIB_EVENT_LISTENER_CLOSED=16 # MPTCP_EVENT_LISTENER_CLOSED
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-07 18:10 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-07 18:10 UTC (permalink / raw
To: gentoo-commits
commit: b938df58480fa18cda9e6ffd6b0793832d6f04d0
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Sep 7 18:10:27 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Sep 7 18:10:27 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=b938df58
dtrace patch for 6.10.X (CTF, modules.builtin.objs) p3
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 2 +-
...race-6.10_p2.patch => 2995_dtrace-6.10_p3.patch | 126 +++++++++------------
2 files changed, 56 insertions(+), 72 deletions(-)
diff --git a/0000_README b/0000_README
index 9948b161..574cd30b 100644
--- a/0000_README
+++ b/0000_README
@@ -123,7 +123,7 @@ Patch: 2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
From: https://lore.kernel.org/bpf/
Desc: libbpf: workaround -Wmaybe-uninitialized false positive
-Patch: 2995_dtrace-6.10_p2.patch
+Patch: 2995_dtrace-6.10_p3.patch
From: https://github.com/thesamesam/linux/tree/dtrace-sam/v2/6.10
Desc: dtrace patch for 6.10.X (CTF, modules.builtin.objs)
diff --git a/2995_dtrace-6.10_p2.patch b/2995_dtrace-6.10_p3.patch
similarity index 96%
rename from 2995_dtrace-6.10_p2.patch
rename to 2995_dtrace-6.10_p3.patch
index 3686ca5b..775a7868 100644
--- a/2995_dtrace-6.10_p2.patch
+++ b/2995_dtrace-6.10_p3.patch
@@ -115,87 +115,78 @@ index 2e5ac6ab3d476..635896f269f1f 100644
-o -name '*.dtb.S' -o -name '*.dtbo.S' \
-o -name '*.dt.yaml' -o -name 'dtbs-list' \
diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
-index 01067a2bc43b7..6464089596088 100644
+index 01067a2bc43b7..d2193b8dfad83 100644
--- a/arch/arm/vdso/Makefile
+++ b/arch/arm/vdso/Makefile
-@@ -14,6 +14,12 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+@@ -14,6 +14,10 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO32
-+ifdef CONFIG_CTF
-+ # CTF in the vDSO would introduce a new section, which would
-+ # expand the vDSO to more than a page.
-+ ccflags-y += $(call cc-option,-gctf0)
-+endif
++# CTF in the vDSO would introduce a new section, which would
++# expand the vDSO to more than a page.
++ccflags-y += $(call cc-option,-gctf0)
+
ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8
ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
-z max-page-size=4096 -shared $(ldflags-y) \
diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
-index d63930c828397..9ef2050690653 100644
+index d63930c828397..6e84d3822cfe3 100644
--- a/arch/arm64/kernel/vdso/Makefile
+++ b/arch/arm64/kernel/vdso/Makefile
-@@ -33,6 +33,12 @@ ldflags-y += -T
+@@ -33,6 +33,10 @@ ldflags-y += -T
ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-+ifdef CONFIG_CTF
-+ # CTF in the vDSO would introduce a new section, which would
-+ # expand the vDSO to more than a page.
-+ ccflags-y += $(call cc-option,-gctf0)
-+endif
++# CTF in the vDSO would introduce a new section, which would
++# expand the vDSO to more than a page.
++ccflags-y += $(call cc-option,-gctf0)
+
# -Wmissing-prototypes and -Wmissing-declarations are removed from
# the CFLAGS of vgettimeofday.c to make possible to build the
# kernel with CONFIG_WERROR enabled.
diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
-index d724d46b07c84..95ef763218f7b 100644
+index d724d46b07c84..fbedb95223ae1 100644
--- a/arch/loongarch/vdso/Makefile
+++ b/arch/loongarch/vdso/Makefile
-@@ -22,6 +22,11 @@ cflags-vdso := $(ccflags-vdso) \
+@@ -21,7 +21,8 @@ cflags-vdso := $(ccflags-vdso) \
+ -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
-fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
$(call cc-option, -fno-asynchronous-unwind-tables) \
- $(call cc-option, -fno-stack-protector)
-+
-+ifdef CONFIG_CTF
-+ cflags-vdso += $(call cc-option,-gctf0)
-+endif
-+
+- $(call cc-option, -fno-stack-protector)
++ $(call cc-option, -fno-stack-protector) \
++ $(call cc-option,-gctf0)
aflags-vdso := $(ccflags-vdso) \
-D__ASSEMBLY__ -Wa,-gdwarf-2
diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
-index b289b2c1b2946..6b5603f3b6a2d 100644
+index b289b2c1b2946..6c8d777525f9b 100644
--- a/arch/mips/vdso/Makefile
+++ b/arch/mips/vdso/Makefile
-@@ -34,6 +34,10 @@ cflags-vdso := $(ccflags-vdso) \
+@@ -30,7 +30,8 @@ cflags-vdso := $(ccflags-vdso) \
+ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+ -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \
+ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
+- $(call cc-option, -fno-asynchronous-unwind-tables)
++ $(call cc-option, -fno-asynchronous-unwind-tables) \
++ $(call cc-option,-gctf0)
aflags-vdso := $(ccflags-vdso) \
-D__ASSEMBLY__ -Wa,-gdwarf-2
-+ifdef CONFIG_CTF
-+cflags-vdso += $(call cc-option,-gctf0)
-+endif
-+
- ifneq ($(c-gettimeofday-y),)
- CFLAGS_vgettimeofday.o = -include $(c-gettimeofday-y)
-
diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
-index 243dbfc4609d8..432422fc3febb 100644
+index 243dbfc4609d8..e4f3e47074e9d 100644
--- a/arch/sparc/vdso/Makefile
+++ b/arch/sparc/vdso/Makefile
-@@ -46,6 +46,10 @@ CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64
+@@ -44,7 +44,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
-fno-omit-frame-pointer -foptimize-sibling-calls \
- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
++ $(call cc-option,-gctf0) -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-+ifdef CONFIG_CTF
-+CFL += $(call cc-option,-gctf0)
-+endif
-+
SPARC_REG_CFLAGS = -ffixed-g4 -ffixed-g5 -fcall-used-g5 -fcall-used-g7
- $(vobjs): KBUILD_CFLAGS := $(filter-out $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
-index 215a1b202a918..ffb33a1a7315b 100644
+index 215a1b202a918..2fa1613a06275 100644
--- a/arch/x86/entry/vdso/Makefile
+++ b/arch/x86/entry/vdso/Makefile
@@ -54,6 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
@@ -206,31 +197,27 @@ index 215a1b202a918..ffb33a1a7315b 100644
-DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
ifdef CONFIG_MITIGATION_RETPOLINE
-@@ -131,6 +132,9 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
+@@ -131,6 +132,7 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
KBUILD_CFLAGS_32 += -fno-stack-protector
KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
-+ifdef CONFIG_CTF
-+ KBUILD_CFLAGS_32 += $(call cc-option,-gctf0)
-+endif
++KBUILD_CFLAGS_32 += $(call cc-option,-gctf0)
KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
ifdef CONFIG_MITIGATION_RETPOLINE
diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
-index 6a77ea6434ffd..d99a60494286a 100644
+index 6a77ea6434ffd..6db233b5edd75 100644
--- a/arch/x86/um/vdso/Makefile
+++ b/arch/x86/um/vdso/Makefile
-@@ -42,6 +42,10 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+@@ -40,7 +40,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
+ #
+ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
$(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
- -fno-omit-frame-pointer -foptimize-sibling-calls
+- -fno-omit-frame-pointer -foptimize-sibling-calls
++ -fno-omit-frame-pointer -foptimize-sibling-calls $(call cc-option,-gctf0)
-+if CONFIG_CTF
-+CFL += $(call cc-option,-gctf0)
-+endif
-+
$(vobjs): KBUILD_CFLAGS += $(CFL)
- #
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index f00a8e18f389f..2e307c0824574 100644
--- a/include/asm-generic/vmlinux.lds.h
@@ -244,17 +231,21 @@ index f00a8e18f389f..2e307c0824574 100644
*(.gnu.version*) \
diff --git a/include/linux/module.h b/include/linux/module.h
-index 330ffb59efe51..ec828908470c9 100644
+index 330ffb59efe51..2d9fcca542d13 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
-@@ -180,7 +180,9 @@ extern void cleanup_module(void);
+@@ -180,7 +180,13 @@ extern void cleanup_module(void);
#ifdef MODULE
#define MODULE_FILE
#else
-#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
++#ifdef CONFIG_CTF
+#define MODULE_FILE \
+ MODULE_INFO(file, KBUILD_MODFILE); \
+ MODULE_INFO(objs, KBUILD_MODOBJS);
++#else
++#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
++#endif
#endif
/*
@@ -322,14 +313,6 @@ index 59b6765d86b8f..dab7e6983eace 100644
config DEBUG_FORCE_WEAK_PER_CPU
bool "Force weak per-cpu definitions"
depends on DEBUG_KERNEL
-diff --git a/scripts/.gitignore b/scripts/.gitignore
-index 3dbb8bb2457bc..11339fa922abd 100644
---- a/scripts/.gitignore
-+++ b/scripts/.gitignore
-@@ -11,3 +11,4 @@
- /sorttable
- /target.json
- /unifdef
+y!/Makefile.ctf
diff --git a/scripts/Makefile b/scripts/Makefile
index fe56eeef09dd4..8e7eb174d3154 100644
@@ -502,7 +485,7 @@ index 0000000000000..210bef3854e9b
+
+endif
diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
-index 7f8ec77bf35c9..97b0ea2eee9d4 100644
+index 7f8ec77bf35c9..8e67961ba2ec9 100644
--- a/scripts/Makefile.lib
+++ b/scripts/Makefile.lib
@@ -118,6 +118,8 @@ modname-multi = $(sort $(foreach m,$(multi-obj-ym),\
@@ -514,17 +497,18 @@ index 7f8ec77bf35c9..97b0ea2eee9d4 100644
modfile = $(addprefix $(obj)/,$(__modname))
# target with $(obj)/ and its suffix stripped
-@@ -131,7 +133,8 @@ name-fix = $(call stringify,$(call name-fix-token,$1))
- basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
- modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
+@@ -133,6 +135,10 @@ modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
-D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
--modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
-+modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile)) \
-+ -DKBUILD_MODOBJS=$(call stringify,$(modfile).o:$(subst $(space),|,$(modname-objs-prefixed)))
+ modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
++ifdef CONFIG_CTF
++modfile_flags += -DKBUILD_MODOBJS=$(call stringify,$(modfile).o:$(subst $(space),|,$(modname-objs-prefixed)))
++endif
++
_c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
$(filter-out $(ccflags-remove-y), \
-@@ -238,7 +241,7 @@ modkern_rustflags = \
+ $(KBUILD_CPPFLAGS) $(KBUILD_CFLAGS) $(ccflags-y)) \
+@@ -238,7 +244,7 @@ modkern_rustflags = \
modkern_aflags = $(if $(part-of-module), \
$(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE), \
@@ -533,7 +517,7 @@ index 7f8ec77bf35c9..97b0ea2eee9d4 100644
c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
-include $(srctree)/include/linux/compiler_types.h \
-@@ -248,7 +251,7 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+@@ -248,7 +254,7 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
rust_flags = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg
a_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-07 14:26 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-07 14:26 UTC (permalink / raw
To: gentoo-commits
commit: e6e998f862f051598cd9b9c6cdcb7ad1f9f16d65
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Sep 7 14:26:05 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Sep 7 14:26:05 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=e6e998f8
libbpf: workaround (another) -Wmaybe-uninitialized false positive
Thanks to Sam
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 ++
...workaround-Wmaybe-uninitialized-false-pos.patch | 64 ++++++++++++++++++++++
2 files changed, 68 insertions(+)
diff --git a/0000_README b/0000_README
index ad96829d..9948b161 100644
--- a/0000_README
+++ b/0000_README
@@ -111,6 +111,10 @@ Patch: 2910_bfp-mark-get-entry-ip-as--maybe-unused.patch
From: https://www.spinics.net/lists/stable/msg604665.html
Desc: bpf: mark get_entry_ip as __maybe_unused
+Patch: 2911_libbpf-second-workaround-Wmaybe-uninitialized-false-pos.patch
+From: https://lore.kernel.org/bpf/f6962729197ae7cdf4f6d1512625bd92f2322d31.1725630494.git.sam@gentoo.org/
+Desc: libbpf: workaround (another) -Wmaybe-uninitialized false positive
+
Patch: 2920_sign-file-patch-for-libressl.patch
From: https://bugs.gentoo.org/717166
Desc: sign-file: full functionality with modern LibreSSL
diff --git a/2911_libbpf-second-workaround-Wmaybe-uninitialized-false-pos.patch b/2911_libbpf-second-workaround-Wmaybe-uninitialized-false-pos.patch
new file mode 100644
index 00000000..f01221c7
--- /dev/null
+++ b/2911_libbpf-second-workaround-Wmaybe-uninitialized-false-pos.patch
@@ -0,0 +1,64 @@
+From git@z Thu Jan 1 00:00:00 1970
+Subject: [PATCH] libbpf: workaround (another) -Wmaybe-uninitialized false
+ positive
+From: Sam James <sam@gentoo.org>
+Date: Fri, 06 Sep 2024 14:48:14 +0100
+Message-Id: <f6962729197ae7cdf4f6d1512625bd92f2322d31.1725630494.git.sam@gentoo.org>
+MIME-Version: 1.0
+Content-Type: text/plain; charset="utf-8"
+Content-Transfer-Encoding: 8bit
+
+We get this with GCC 15 -O3 (at least):
+```
+libbpf.c: In function ‘bpf_map__init_kern_struct_ops’:
+libbpf.c:1109:18: error: ‘mod_btf’ may be used uninitialized [-Werror=maybe-uninitialized]
+ 1109 | kern_btf = mod_btf ? mod_btf->btf : obj->btf_vmlinux;
+ | ~~~~~~~~~^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+libbpf.c:1094:28: note: ‘mod_btf’ was declared here
+ 1094 | struct module_btf *mod_btf;
+ | ^~~~~~~
+In function ‘find_struct_ops_kern_types’,
+ inlined from ‘bpf_map__init_kern_struct_ops’ at libbpf.c:1102:8:
+libbpf.c:982:21: error: ‘btf’ may be used uninitialized [-Werror=maybe-uninitialized]
+ 982 | kern_type = btf__type_by_id(btf, kern_type_id);
+ | ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+libbpf.c: In function ‘bpf_map__init_kern_struct_ops’:
+libbpf.c:967:21: note: ‘btf’ was declared here
+ 967 | struct btf *btf;
+ | ^~~
+```
+
+This is similar to the other libbpf fix from a few weeks ago for
+the same modelling-errno issue (fab45b962749184e1a1a57c7c583782b78fad539).
+
+Link: https://bugs.gentoo.org/939106
+Signed-off-by: Sam James <sam@gentoo.org>
+---
+ tools/lib/bpf/libbpf.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
+index a3be6f8fac09e..7315120574c29 100644
+--- a/tools/lib/bpf/libbpf.c
++++ b/tools/lib/bpf/libbpf.c
+@@ -988,7 +988,7 @@ find_struct_ops_kern_types(struct bpf_object *obj, const char *tname_raw,
+ {
+ const struct btf_type *kern_type, *kern_vtype;
+ const struct btf_member *kern_data_member;
+- struct btf *btf;
++ struct btf *btf = NULL;
+ __s32 kern_vtype_id, kern_type_id;
+ char tname[256];
+ __u32 i;
+@@ -1115,7 +1115,7 @@ static int bpf_map__init_kern_struct_ops(struct bpf_map *map)
+ const struct btf *btf = obj->btf;
+ struct bpf_struct_ops *st_ops;
+ const struct btf *kern_btf;
+- struct module_btf *mod_btf;
++ struct module_btf *mod_btf = NULL;
+ void *data, *kern_data;
+ const char *tname;
+ int err;
+--
+2.46.0
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-07 14:23 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-07 14:23 UTC (permalink / raw
To: gentoo-commits
commit: 72f43edb42071a1e39ccfe03e310ad57f675af65
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Thu Sep 5 19:09:56 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Thu Sep 5 19:09:56 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=72f43edb
dtrace patch for 6.10.X (CTF, modules.builtin.objs) p2
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +-
2995_dtrace-6.10_p2.patch | 2368 +++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 2370 insertions(+), 2 deletions(-)
diff --git a/0000_README b/0000_README
index d179ade8..ad96829d 100644
--- a/0000_README
+++ b/0000_README
@@ -119,9 +119,9 @@ Patch: 2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
From: https://lore.kernel.org/bpf/
Desc: libbpf: workaround -Wmaybe-uninitialized false positive
-Patch: 2995_dtrace-6.10_p1.patch
+Patch: 2995_dtrace-6.10_p2.patch
From: https://github.com/thesamesam/linux/tree/dtrace-sam/v2/6.10
-Desc: dtrace patch 6.10_p1
+Desc: dtrace patch for 6.10.X (CTF, modules.builtin.objs)
Patch: 3000_Support-printing-firmware-info.patch
From: https://bugs.gentoo.org/732852
diff --git a/2995_dtrace-6.10_p2.patch b/2995_dtrace-6.10_p2.patch
new file mode 100644
index 00000000..3686ca5b
--- /dev/null
+++ b/2995_dtrace-6.10_p2.patch
@@ -0,0 +1,2368 @@
+diff --git a/Documentation/dontdiff b/Documentation/dontdiff
+index 3c399f132e2db..75b9655e57914 100644
+--- a/Documentation/dontdiff
++++ b/Documentation/dontdiff
+@@ -179,7 +179,7 @@ mkutf8data
+ modpost
+ modules-only.symvers
+ modules.builtin
+-modules.builtin.modinfo
++modules.builtin.*
+ modules.nsdeps
+ modules.order
+ modversions.h*
+diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst
+index 9c8d1d046ea56..79e104ffee715 100644
+--- a/Documentation/kbuild/kbuild.rst
++++ b/Documentation/kbuild/kbuild.rst
+@@ -17,6 +17,11 @@ modules.builtin
+ This file lists all modules that are built into the kernel. This is used
+ by modprobe to not fail when trying to load something builtin.
+
++modules.builtin.objs
++-----------------------
++This file contains object mapping of modules that are built into the kernel
++to their corresponding object files used to build the module.
++
+ modules.builtin.modinfo
+ -----------------------
+ This file contains modinfo from all modules that are built into the kernel.
+diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
+index 5685d7bfe4d0f..8db62fe4dadff 100644
+--- a/Documentation/process/changes.rst
++++ b/Documentation/process/changes.rst
+@@ -63,9 +63,13 @@ cpio any cpio --version
+ GNU tar 1.28 tar --version
+ gtags (optional) 6.6.5 gtags --version
+ mkimage (optional) 2017.01 mkimage --version
++GNU AWK (optional) 5.1.0 gawk --version
++GNU C\ [#f2]_ 12.0 gcc --version
++binutils\ [#f2]_ 2.36 ld -v
+ ====================== =============== ========================================
+
+ .. [#f1] Sphinx is needed only to build the Kernel documentation
++.. [#f2] These are needed at build-time when CONFIG_CTF is enabled
+
+ Kernel compilation
+ ******************
+@@ -198,6 +202,12 @@ platforms. The tool is available via the ``u-boot-tools`` package or can be
+ built from the U-Boot source code. See the instructions at
+ https://docs.u-boot.org/en/latest/build/tools.html#building-tools-for-linux
+
++GNU AWK
++-------
++
++GNU AWK is needed if you want kernel builds to generate address range data for
++builtin modules (CONFIG_BUILTIN_MODULE_RANGES).
++
+ System utilities
+ ****************
+
+diff --git a/Makefile b/Makefile
+index 2e5ac6ab3d476..635896f269f1f 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1024,6 +1024,7 @@ include-$(CONFIG_UBSAN) += scripts/Makefile.ubsan
+ include-$(CONFIG_KCOV) += scripts/Makefile.kcov
+ include-$(CONFIG_RANDSTRUCT) += scripts/Makefile.randstruct
+ include-$(CONFIG_GCC_PLUGINS) += scripts/Makefile.gcc-plugins
++include-$(CONFIG_CTF) += scripts/Makefile.ctfa-toplevel
+
+ include $(addprefix $(srctree)/, $(include-y))
+
+@@ -1151,7 +1152,11 @@ PHONY += vmlinux_o
+ vmlinux_o: vmlinux.a $(KBUILD_VMLINUX_LIBS)
+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux_o
+
+-vmlinux.o modules.builtin.modinfo modules.builtin: vmlinux_o
++MODULES_BUILTIN := modules.builtin.modinfo
++MODULES_BUILTIN += modules.builtin
++MODULES_BUILTIN += modules.builtin.objs
++
++vmlinux.o $(MODULES_BUILTIN): vmlinux_o
+ @:
+
+ PHONY += vmlinux
+@@ -1490,9 +1495,10 @@ endif # CONFIG_MODULES
+
+ # Directories & files removed with 'make clean'
+ CLEAN_FILES += vmlinux.symvers modules-only.symvers \
+- modules.builtin modules.builtin.modinfo modules.nsdeps \
++ modules.builtin modules.builtin.* modules.nsdeps \
+ compile_commands.json rust/test \
+- rust-project.json .vmlinux.objs .vmlinux.export.c
++ rust-project.json .vmlinux.objs .vmlinux.export.c \
++ vmlinux.ctfa
+
+ # Directories & files removed with 'make mrproper'
+ MRPROPER_FILES += include/config include/generated \
+@@ -1586,6 +1592,8 @@ help:
+ @echo ' (requires a recent binutils and recent build (System.map))'
+ @echo ' dir/file.ko - Build module including final link'
+ @echo ' modules_prepare - Set up for building external modules'
++ @echo ' ctf - Generate CTF type information, installed by make ctf_install'
++ @echo ' ctf_install - Install CTF to INSTALL_MOD_PATH (default: /)'
+ @echo ' tags/TAGS - Generate tags file for editors'
+ @echo ' cscope - Generate cscope index'
+ @echo ' gtags - Generate GNU GLOBAL index'
+@@ -1942,7 +1950,7 @@ clean: $(clean-dirs)
+ $(call cmd,rmfiles)
+ @find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \
+ \( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \
+- -o -name '*.ko.*' \
++ -o -name '*.ko.*' -o -name '*.ctf' \
+ -o -name '*.dtb' -o -name '*.dtbo' \
+ -o -name '*.dtb.S' -o -name '*.dtbo.S' \
+ -o -name '*.dt.yaml' -o -name 'dtbs-list' \
+diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
+index 01067a2bc43b7..6464089596088 100644
+--- a/arch/arm/vdso/Makefile
++++ b/arch/arm/vdso/Makefile
+@@ -14,6 +14,12 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+ ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
+ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO32
+
++ifdef CONFIG_CTF
++ # CTF in the vDSO would introduce a new section, which would
++ # expand the vDSO to more than a page.
++ ccflags-y += $(call cc-option,-gctf0)
++endif
++
+ ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8
+ ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
+ -z max-page-size=4096 -shared $(ldflags-y) \
+diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
+index d63930c828397..9ef2050690653 100644
+--- a/arch/arm64/kernel/vdso/Makefile
++++ b/arch/arm64/kernel/vdso/Makefile
+@@ -33,6 +33,12 @@ ldflags-y += -T
+ ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
+ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
++ifdef CONFIG_CTF
++ # CTF in the vDSO would introduce a new section, which would
++ # expand the vDSO to more than a page.
++ ccflags-y += $(call cc-option,-gctf0)
++endif
++
+ # -Wmissing-prototypes and -Wmissing-declarations are removed from
+ # the CFLAGS of vgettimeofday.c to make possible to build the
+ # kernel with CONFIG_WERROR enabled.
+diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
+index d724d46b07c84..95ef763218f7b 100644
+--- a/arch/loongarch/vdso/Makefile
++++ b/arch/loongarch/vdso/Makefile
+@@ -22,6 +22,11 @@ cflags-vdso := $(ccflags-vdso) \
+ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
+ $(call cc-option, -fno-asynchronous-unwind-tables) \
+ $(call cc-option, -fno-stack-protector)
++
++ifdef CONFIG_CTF
++ cflags-vdso += $(call cc-option,-gctf0)
++endif
++
+ aflags-vdso := $(ccflags-vdso) \
+ -D__ASSEMBLY__ -Wa,-gdwarf-2
+
+diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
+index b289b2c1b2946..6b5603f3b6a2d 100644
+--- a/arch/mips/vdso/Makefile
++++ b/arch/mips/vdso/Makefile
+@@ -34,6 +34,10 @@ cflags-vdso := $(ccflags-vdso) \
+ aflags-vdso := $(ccflags-vdso) \
+ -D__ASSEMBLY__ -Wa,-gdwarf-2
+
++ifdef CONFIG_CTF
++cflags-vdso += $(call cc-option,-gctf0)
++endif
++
+ ifneq ($(c-gettimeofday-y),)
+ CFLAGS_vgettimeofday.o = -include $(c-gettimeofday-y)
+
+diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
+index 243dbfc4609d8..432422fc3febb 100644
+--- a/arch/sparc/vdso/Makefile
++++ b/arch/sparc/vdso/Makefile
+@@ -46,6 +46,10 @@ CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
++ifdef CONFIG_CTF
++CFL += $(call cc-option,-gctf0)
++endif
++
+ SPARC_REG_CFLAGS = -ffixed-g4 -ffixed-g5 -fcall-used-g5 -fcall-used-g7
+
+ $(vobjs): KBUILD_CFLAGS := $(filter-out $(RANDSTRUCT_CFLAGS) $(GCC_PLUGINS_CFLAGS) $(SPARC_REG_CFLAGS),$(KBUILD_CFLAGS)) $(CFL)
+diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
+index 215a1b202a918..ffb33a1a7315b 100644
+--- a/arch/x86/entry/vdso/Makefile
++++ b/arch/x86/entry/vdso/Makefile
+@@ -54,6 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
++ $(call cc-option,-gctf0) \
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ ifdef CONFIG_MITIGATION_RETPOLINE
+@@ -131,6 +132,9 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
+ KBUILD_CFLAGS_32 += -fno-stack-protector
+ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
+ KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
++ifdef CONFIG_CTF
++ KBUILD_CFLAGS_32 += $(call cc-option,-gctf0)
++endif
+ KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+
+ ifdef CONFIG_MITIGATION_RETPOLINE
+diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
+index 6a77ea6434ffd..d99a60494286a 100644
+--- a/arch/x86/um/vdso/Makefile
++++ b/arch/x86/um/vdso/Makefile
+@@ -42,6 +42,10 @@ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+ -fno-omit-frame-pointer -foptimize-sibling-calls
+
++if CONFIG_CTF
++CFL += $(call cc-option,-gctf0)
++endif
++
+ $(vobjs): KBUILD_CFLAGS += $(CFL)
+
+ #
+diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
+index f00a8e18f389f..2e307c0824574 100644
+--- a/include/asm-generic/vmlinux.lds.h
++++ b/include/asm-generic/vmlinux.lds.h
+@@ -1014,6 +1014,7 @@
+ *(.discard.*) \
+ *(.export_symbol) \
+ *(.modinfo) \
++ *(.ctf) \
+ /* ld.bfd warns about .gnu.version* even when not emitted */ \
+ *(.gnu.version*) \
+
+diff --git a/include/linux/module.h b/include/linux/module.h
+index 330ffb59efe51..ec828908470c9 100644
+--- a/include/linux/module.h
++++ b/include/linux/module.h
+@@ -180,7 +180,9 @@ extern void cleanup_module(void);
+ #ifdef MODULE
+ #define MODULE_FILE
+ #else
+-#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
++#define MODULE_FILE \
++ MODULE_INFO(file, KBUILD_MODFILE); \
++ MODULE_INFO(objs, KBUILD_MODOBJS);
+ #endif
+
+ /*
+diff --git a/init/Kconfig b/init/Kconfig
+index 9684e5d2b81c6..c1b00b2e4a43d 100644
+--- a/init/Kconfig
++++ b/init/Kconfig
+@@ -111,6 +111,12 @@ config PAHOLE_VERSION
+ int
+ default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
+
++config HAVE_CTF_TOOLCHAIN
++ def_bool $(cc-option,-gctf) && $(ld-option,-lbfd -liberty -lctf -lbfd -liberty -lz -ldl -lc -o /dev/null)
++ depends on CC_IS_GCC
++ help
++ GCC and binutils support CTF generation.
++
+ config CONSTRUCTORS
+ bool
+
+diff --git a/lib/Kconfig b/lib/Kconfig
+index b0a76dff5c182..61d0be30b3562 100644
+--- a/lib/Kconfig
++++ b/lib/Kconfig
+@@ -633,6 +633,16 @@ config DIMLIB
+ #
+ config LIBFDT
+ bool
++#
++# CTF support is select'ed if needed
++#
++config CTF
++ bool "Compact Type Format generation"
++ depends on HAVE_CTF_TOOLCHAIN
++ help
++ Emit a compact, compressed description of the kernel's datatypes and
++ global variables into the vmlinux.ctfa archive (for in-tree modules)
++ or into .ctf sections in kernel modules (for out-of-tree modules).
+
+ config OID_REGISTRY
+ tristate
+diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
+index 59b6765d86b8f..dab7e6983eace 100644
+--- a/lib/Kconfig.debug
++++ b/lib/Kconfig.debug
+@@ -571,6 +571,21 @@ config VMLINUX_MAP
+ pieces of code get eliminated with
+ CONFIG_LD_DEAD_CODE_DATA_ELIMINATION.
+
++config BUILTIN_MODULE_RANGES
++ bool "Generate address range information for builtin modules"
++ depends on !LTO
++ depends on VMLINUX_MAP
++ help
++ When modules are built into the kernel, there will be no module name
++ associated with its symbols in /proc/kallsyms. Tracers may want to
++ identify symbols by module name and symbol name regardless of whether
++ the module is configured as loadable or not.
++
++ This option generates modules.builtin.ranges in the build tree with
++ offset ranges (per ELF section) for the module(s) they belong to.
++ It also records an anchor symbol to determine the load address of the
++ section.
++
+ config DEBUG_FORCE_WEAK_PER_CPU
+ bool "Force weak per-cpu definitions"
+ depends on DEBUG_KERNEL
+diff --git a/scripts/.gitignore b/scripts/.gitignore
+index 3dbb8bb2457bc..11339fa922abd 100644
+--- a/scripts/.gitignore
++++ b/scripts/.gitignore
+@@ -11,3 +11,4 @@
+ /sorttable
+ /target.json
+ /unifdef
++y!/Makefile.ctf
+diff --git a/scripts/Makefile b/scripts/Makefile
+index fe56eeef09dd4..8e7eb174d3154 100644
+--- a/scripts/Makefile
++++ b/scripts/Makefile
+@@ -54,6 +54,7 @@ targets += module.lds
+
+ subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
+ subdir-$(CONFIG_MODVERSIONS) += genksyms
++subdir-$(CONFIG_CTF) += ctf
+ subdir-$(CONFIG_SECURITY_SELINUX) += selinux
+
+ # Let clean descend into subdirs
+diff --git a/scripts/Makefile.ctfa b/scripts/Makefile.ctfa
+new file mode 100644
+index 0000000000000..b65d9d391c29c
+--- /dev/null
++++ b/scripts/Makefile.ctfa
+@@ -0,0 +1,92 @@
++# SPDX-License-Identifier: GPL-2.0-only
++# ===========================================================================
++# Module CTF/CTFA generation
++# ===========================================================================
++
++include include/config/auto.conf
++include $(srctree)/scripts/Kbuild.include
++
++# CTF is already present in every object file if CONFIG_CTF is enabled.
++# vmlinux.lds.h strips it out of the finished kernel, but if nothing is done
++# it will be deduplicated into module .ko's. For out-of-tree module builds,
++# this is what we want, but for in-tree modules we can save substantial
++# space by deduplicating it against all the core kernel types as well. So
++# split the CTF out of in-tree module .ko's into separate .ctf files so that
++# it doesn't take up space in the modules on disk, and let the specialized
++# ctfarchive tool consume it and all the CTF in the vmlinux.o files when
++# 'make ctf' is invoked, and use the same machinery that the linker uses to
++# do CTF deduplication to emit vmlinux.ctfa containing the deduplicated CTF.
++
++# Nothing special needs to be done if CTF is turned off or if a standalone
++# module is being built.
++module-ctf-postlink = mv $(1).tmp $(1)
++
++ifdef CONFIG_CTF
++
++# This is quite tricky. The CTF machinery needs to be told about all the
++# built-in objects as well as all the external modules -- but Makefile.modfinal
++# only knows about the latter. So the toplevel makefile emits the names of the
++# built-in objects into a temporary file, which is then catted and its contents
++# used as prerequisites by this rule.
++#
++# We write the names of the object files to be scanned for CTF content into a
++# file, then use that, to avoid hitting command-line length limits.
++
++ifeq ($(KBUILD_EXTMOD),)
++ctf-modules := $(shell find . -name '*.ko.ctf' -print)
++quiet_cmd_ctfa_raw = CTFARAW
++ cmd_ctfa_raw = scripts/ctf/ctfarchive $@ .tmp_objects.builtin modules.builtin.objs $(ctf-filelist)
++ctf-builtins := .tmp_objects.builtin
++ctf-filelist := .tmp_ctf.filelist
++ctf-filelist-raw := .tmp_ctf.filelist.raw
++
++define module-ctf-postlink =
++ $(OBJCOPY) --only-section=.ctf $(1).tmp $(1).ctf && \
++ $(OBJCOPY) --remove-section=.ctf $(1).tmp $(1) && rm -f $(1).tmp
++endef
++
++# Split a list up like shell xargs does.
++define xargs =
++$(1) $(wordlist 1,1024,$(2))
++$(if $(word 1025,$(2)),$(call xargs,$(1),$(wordlist 1025,$(words $(2)),$(2))))
++endef
++
++$(ctf-filelist-raw): $(ctf-builtins) $(ctf-modules)
++ @rm -f $(ctf-filelist-raw);
++ $(call xargs,@printf "%s\n" >> $(ctf-filelist-raw),$^)
++ @touch $(ctf-filelist-raw)
++
++$(ctf-filelist): $(ctf-filelist-raw)
++ @rm -f $(ctf-filelist);
++ @cat $(ctf-filelist-raw) | while read -r obj; do \
++ case $$obj in \
++ $(ctf-builtins)) cat $$obj >> $(ctf-filelist);; \
++ *.a) $(AR) t $$obj > $(ctf-filelist);; \
++ *.builtin) cat $$obj >> $(ctf-filelist);; \
++ *) echo "$$obj" >> $(ctf-filelist);; \
++ esac; \
++ done
++ @touch $(ctf-filelist)
++
++# The raw CTF depends on the output CTF file list, and that depends
++# on the .ko files for the modules.
++.tmp_vmlinux.ctfa.raw: $(ctf-filelist) FORCE
++ $(call if_changed,ctfa_raw)
++
++quiet_cmd_ctfa = CTFA
++ cmd_ctfa = { echo 'int main () { return 0; } ' | \
++ $(CC) -x c -c -o $<.stub -; \
++ $(OBJCOPY) '--remove-section=.*' --add-section=.ctf=$< \
++ $<.stub $@; }
++
++# The CTF itself is an ELF executable with one section: the CTF. This lets
++# objdump work on it, at minimal size cost.
++vmlinux.ctfa: .tmp_vmlinux.ctfa.raw FORCE
++ $(call if_changed,ctfa)
++
++targets += vmlinux.ctfa
++
++endif # KBUILD_EXTMOD
++
++endif # !CONFIG_CTF
++
+diff --git a/scripts/Makefile.ctfa-toplevel b/scripts/Makefile.ctfa-toplevel
+new file mode 100644
+index 0000000000000..210bef3854e9b
+--- /dev/null
++++ b/scripts/Makefile.ctfa-toplevel
+@@ -0,0 +1,54 @@
++# SPDX-License-Identifier: GPL-2.0-only
++# ===========================================================================
++# CTF rules for the top-level makefile only
++# ===========================================================================
++
++KBUILD_CFLAGS += $(call cc-option,-gctf)
++KBUILD_LDFLAGS += $(call ld-option, --ctf-variables)
++
++ifeq ($(KBUILD_EXTMOD),)
++
++# CTF generation for in-tree code (modules, built-in and not, and core kernel)
++
++# This contains all the object files that are built directly into the
++# kernel (including built-in modules), for consumption by ctfarchive in
++# Makefile.modfinal.
++# This is made doubly annoying by the presence of '.o' files which are actually
++# thin ar archives, and the need to support file(1) versions too old to
++# recognize them as archives at all. (So we assume that everything that is notr
++# an ELF object is an archive.)
++ifeq ($(SRCARCH),x86)
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),bzImage) FORCE
++else
++ifeq ($(SRCARCH),arm64)
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),Image) FORCE
++else
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) FORCE
++endif
++endif
++ @echo $(KBUILD_VMLINUX_OBJS) | \
++ tr " " "\n" | grep "\.o$$" | xargs -r file | \
++ grep ELF | cut -d: -f1 > .tmp_objects.builtin
++ @for archive in $$(echo $(KBUILD_VMLINUX_OBJS) |\
++ tr " " "\n" | xargs -r file | grep -v ELF | cut -d: -f1); do \
++ $(AR) t "$$archive" >> .tmp_objects.builtin; \
++ done
++
++ctf: vmlinux.ctfa
++PHONY += ctf ctf_install
++
++# Making CTF needs the builtin files. We need to force everything to be
++# built if not already done, since we need the .o files for the machinery
++# above to work.
++vmlinux.ctfa: KBUILD_BUILTIN := 1
++vmlinux.ctfa: modules.builtin.objs .tmp_objects.builtin
++ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal vmlinux.ctfa
++
++ctf_install:
++ $(Q)mkdir -p $(MODLIB)/kernel
++ @ln -sf $(abspath $(srctree)) $(MODLIB)/source
++ $(Q)cp -f $(objtree)/vmlinux.ctfa $(MODLIB)/kernel
++
++CLEAN_FILES += vmlinux.ctfa
++
++endif
+diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
+index 7f8ec77bf35c9..97b0ea2eee9d4 100644
+--- a/scripts/Makefile.lib
++++ b/scripts/Makefile.lib
+@@ -118,6 +118,8 @@ modname-multi = $(sort $(foreach m,$(multi-obj-ym),\
+ __modname = $(or $(modname-multi),$(basetarget))
+
+ modname = $(subst $(space),:,$(__modname))
++modname-objs = $($(modname)-objs) $($(modname)-y) $($(modname)-Y)
++modname-objs-prefixed = $(sort $(strip $(addprefix $(obj)/, $(modname-objs))))
+ modfile = $(addprefix $(obj)/,$(__modname))
+
+ # target with $(obj)/ and its suffix stripped
+@@ -131,7 +133,8 @@ name-fix = $(call stringify,$(call name-fix-token,$1))
+ basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
+ modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
+ -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
+-modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
++modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile)) \
++ -DKBUILD_MODOBJS=$(call stringify,$(modfile).o:$(subst $(space),|,$(modname-objs-prefixed)))
+
+ _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
+ $(filter-out $(ccflags-remove-y), \
+@@ -238,7 +241,7 @@ modkern_rustflags = \
+
+ modkern_aflags = $(if $(part-of-module), \
+ $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE), \
+- $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL))
++ $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) $(modfile_flags))
+
+ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ -include $(srctree)/include/linux/compiler_types.h \
+@@ -248,7 +251,7 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ rust_flags = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg
+
+ a_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+- $(_a_flags) $(modkern_aflags)
++ $(_a_flags) $(modkern_aflags) $(modname_flags)
+
+ cpp_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ $(_cpp_flags)
+diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
+index 3bec9043e4f38..06807e403d162 100644
+--- a/scripts/Makefile.modfinal
++++ b/scripts/Makefile.modfinal
+@@ -30,11 +30,16 @@ quiet_cmd_cc_o_c = CC [M] $@
+ %.mod.o: %.mod.c FORCE
+ $(call if_changed_dep,cc_o_c)
+
++# for module-ctf-postlink
++include $(srctree)/scripts/Makefile.ctfa
++
+ quiet_cmd_ld_ko_o = LD [M] $@
+ cmd_ld_ko_o += \
+ $(LD) -r $(KBUILD_LDFLAGS) \
+ $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
+- -T scripts/module.lds -o $@ $(filter %.o, $^)
++ -T scripts/module.lds $(LDFLAGS_$(modname)) -o $@.tmp \
++ $(filter %.o, $^) && \
++ $(call module-ctf-postlink,$@) \
+
+ quiet_cmd_btf_ko = BTF [M] $@
+ cmd_btf_ko = \
+diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
+index 0afd75472679f..e668469ce098c 100644
+--- a/scripts/Makefile.modinst
++++ b/scripts/Makefile.modinst
+@@ -30,10 +30,12 @@ $(MODLIB)/modules.order: modules.order FORCE
+ quiet_cmd_install_modorder = INSTALL $@
+ cmd_install_modorder = sed 's:^\(.*\)\.o$$:kernel/\1.ko:' $< > $@
+
+-# Install modules.builtin(.modinfo) even when CONFIG_MODULES is disabled.
+-install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo)
++# Install modules.builtin(.modinfo,.ranges,.objs) even when CONFIG_MODULES is disabled.
++install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.objs)
+
+-$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo): $(MODLIB)/%: % FORCE
++install-$(CONFIG_BUILTIN_MODULE_RANGES) += $(MODLIB)/modules.builtin.ranges
++
++$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.ranges modules.builtin.objs): $(MODLIB)/%: % FORCE
+ $(call cmd,install)
+
+ endif
+diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
+index 49946cb968440..7e8b703799c85 100644
+--- a/scripts/Makefile.vmlinux
++++ b/scripts/Makefile.vmlinux
+@@ -33,6 +33,24 @@ targets += vmlinux
+ vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE
+ +$(call if_changed_dep,link_vmlinux)
+
++# module.builtin.ranges
++# ---------------------------------------------------------------------------
++ifdef CONFIG_BUILTIN_MODULE_RANGES
++__default: modules.builtin.ranges
++
++quiet_cmd_modules_builtin_ranges = GEN $@
++ cmd_modules_builtin_ranges = $(real-prereqs) > $@
++
++targets += modules.builtin.ranges
++modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \
++ modules.builtin vmlinux.map vmlinux.o.map FORCE
++ $(call if_changed,modules_builtin_ranges)
++
++vmlinux.map: vmlinux
++ @:
++
++endif
++
+ # Add FORCE to the prequisites of a target to force it to be always rebuilt.
+ # ---------------------------------------------------------------------------
+
+diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
+index 6de297916ce68..86d6f8887313f 100644
+--- a/scripts/Makefile.vmlinux_o
++++ b/scripts/Makefile.vmlinux_o
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0-only
+
+ PHONY := __default
+-__default: vmlinux.o modules.builtin.modinfo modules.builtin
++__default: vmlinux.o modules.builtin.modinfo modules.builtin modules.builtin.objs
+
+ include include/config/auto.conf
+ include $(srctree)/scripts/Kbuild.include
+@@ -27,6 +27,18 @@ ifdef CONFIG_LTO_CLANG
+ initcalls-lds := .tmp_initcalls.lds
+ endif
+
++# Generate a linker script to delete CTF sections
++# -----------------------------------------------
++
++quiet_cmd_gen_remove_ctf.lds = GEN $@
++ cmd_gen_remove_ctf.lds = \
++ $(LD) $(KBUILD_LDFLAGS) -r --verbose | awk -f $(real-prereqs) > $@
++
++.tmp_remove-ctf.lds: $(srctree)/scripts/remove-ctf-lds.awk FORCE
++ $(call if_changed,gen_remove_ctf.lds)
++
++targets := .tmp_remove-ctf.lds
++
+ # objtool for vmlinux.o
+ # ---------------------------------------------------------------------------
+ #
+@@ -42,13 +54,18 @@ vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \
+
+ objtool-args = $(vmlinux-objtool-args-y) --link
+
+-# Link of vmlinux.o used for section mismatch analysis
++# Link of vmlinux.o used for section mismatch analysis: we also strip the CTF
++# section out at this stage, since ctfarchive gets it from the underlying object
++# files and linking it further is a waste of time.
+ # ---------------------------------------------------------------------------
+
++vmlinux-o-ld-args-$(CONFIG_BUILTIN_MODULE_RANGES) += -Map=$@.map
++
+ quiet_cmd_ld_vmlinux.o = LD $@
+ cmd_ld_vmlinux.o = \
+ $(LD) ${KBUILD_LDFLAGS} -r -o $@ \
+- $(addprefix -T , $(initcalls-lds)) \
++ $(vmlinux-o-ld-args-y) \
++ $(addprefix -T , $(initcalls-lds)) -T .tmp_remove-ctf.lds \
+ --whole-archive vmlinux.a --no-whole-archive \
+ --start-group $(KBUILD_VMLINUX_LIBS) --end-group \
+ $(cmd_objtool)
+@@ -58,7 +75,7 @@ define rule_ld_vmlinux.o
+ $(call cmd,gen_objtooldep)
+ endef
+
+-vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
++vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) .tmp_remove-ctf.lds FORCE
+ $(call if_changed_rule,ld_vmlinux.o)
+
+ targets += vmlinux.o
+@@ -87,6 +104,19 @@ targets += modules.builtin
+ modules.builtin: modules.builtin.modinfo FORCE
+ $(call if_changed,modules_builtin)
+
++# module.builtin.objs
++# ---------------------------------------------------------------------------
++quiet_cmd_modules_builtin_objs = GEN $@
++ cmd_modules_builtin_objs = \
++ tr '\0' '\n' < $< | \
++ sed -n 's/^[[:alnum:]:_]*\.objs=//p' | \
++ tr ' ' '\n' | uniq | sed -e 's|:|: |' -e 's:|: :g' | \
++ tr -s ' ' > $@
++
++targets += modules.builtin.objs
++modules.builtin.objs: modules.builtin.modinfo FORCE
++ $(call if_changed,modules_builtin_objs)
++
+ # Add FORCE to the prequisites of a target to force it to be always rebuilt.
+ # ---------------------------------------------------------------------------
+
+diff --git a/scripts/ctf/.gitignore b/scripts/ctf/.gitignore
+new file mode 100644
+index 0000000000000..6a0eb1c3ceeab
+--- /dev/null
++++ b/scripts/ctf/.gitignore
+@@ -0,0 +1 @@
++ctfarchive
+diff --git a/scripts/ctf/Makefile b/scripts/ctf/Makefile
+new file mode 100644
+index 0000000000000..3b83f93bb9f9a
+--- /dev/null
++++ b/scripts/ctf/Makefile
+@@ -0,0 +1,5 @@
++ifdef CONFIG_CTF
++hostprogs-always-y := ctfarchive
++ctfarchive-objs := ctfarchive.o modules_builtin.o
++HOSTLDLIBS_ctfarchive := -lctf
++endif
+diff --git a/scripts/ctf/ctfarchive.c b/scripts/ctf/ctfarchive.c
+new file mode 100644
+index 0000000000000..92cc4912ed0ee
+--- /dev/null
++++ b/scripts/ctf/ctfarchive.c
+@@ -0,0 +1,413 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * ctfmerge.c: Read in CTF extracted from generated object files from a
++ * specified directory and generate a CTF archive whose members are the
++ * deduplicated CTF derived from those object files, split up by kernel
++ * module.
++ *
++ * Copyright (c) 2019, 2023, Oracle and/or its affiliates.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#define _GNU_SOURCE 1
++#include <errno.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <string.h>
++#include <ctf-api.h>
++#include "modules_builtin.h"
++
++static ctf_file_t *output;
++
++static int private_ctf_link_add_ctf(ctf_file_t *fp,
++ const char *name)
++{
++#if !defined (CTF_LINK_FINAL)
++ return ctf_link_add_ctf(fp, NULL, name);
++#else
++ /* Non-upstreamed, erroneously-broken API. */
++ return ctf_link_add_ctf(fp, NULL, name, NULL, 0);
++#endif
++}
++
++/*
++ * Add a file to the link.
++ */
++static void add_to_link(const char *fn)
++{
++ if (private_ctf_link_add_ctf(output, fn) < 0)
++ {
++ fprintf(stderr, "Cannot add CTF file %s: %s\n", fn,
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++}
++
++struct from_to
++{
++ char *from;
++ char *to;
++};
++
++/*
++ * The world's stupidest hash table of FROM -> TO.
++ */
++static struct from_to **from_tos[256];
++static size_t alloc_from_tos[256];
++static size_t num_from_tos[256];
++
++static unsigned char from_to_hash(const char *from)
++{
++ unsigned char hval = 0;
++
++ const char *p;
++ for (p = from; *p; p++)
++ hval += *p;
++
++ return hval;
++}
++
++/*
++ * Note that we will need to add a CU mapping later on.
++ *
++ * Present purely to work around a binutils bug that stops
++ * ctf_link_add_cu_mapping() working right when called repeatedly
++ * with the same FROM.
++ */
++static int add_cu_mapping(const char *from, const char *to)
++{
++ ssize_t i, j;
++
++ i = from_to_hash(from);
++
++ for (j = 0; j < num_from_tos[i]; j++)
++ if (strcmp(from, from_tos[i][j]->from) == 0) {
++ char *tmp;
++
++ free(from_tos[i][j]->to);
++ tmp = strdup(to);
++ if (!tmp)
++ goto oom;
++ from_tos[i][j]->to = tmp;
++ return 0;
++ }
++
++ if (num_from_tos[i] >= alloc_from_tos[i]) {
++ struct from_to **tmp;
++ if (alloc_from_tos[i] < 16)
++ alloc_from_tos[i] = 16;
++ else
++ alloc_from_tos[i] *= 2;
++
++ tmp = realloc(from_tos[i], alloc_from_tos[i] * sizeof(struct from_to *));
++ if (!tmp)
++ goto oom;
++
++ from_tos[i] = tmp;
++ }
++
++ j = num_from_tos[i];
++ from_tos[i][j] = malloc(sizeof(struct from_to));
++ if (from_tos[i][j] == NULL)
++ goto oom;
++ from_tos[i][j]->from = strdup(from);
++ from_tos[i][j]->to = strdup(to);
++ if (!from_tos[i][j]->from || !from_tos[i][j]->to)
++ goto oom;
++ num_from_tos[i]++;
++
++ return 0;
++ oom:
++ fprintf(stderr,
++ "out of memory in add_cu_mapping\n");
++ exit(1);
++}
++
++/*
++ * Finally tell binutils to add all the CU mappings, with duplicate FROMs
++ * replaced with the most recent one.
++ */
++static void commit_cu_mappings(void)
++{
++ ssize_t i, j;
++
++ for (i = 0; i < 256; i++)
++ for (j = 0; j < num_from_tos[i]; j++)
++ ctf_link_add_cu_mapping(output, from_tos[i][j]->from,
++ from_tos[i][j]->to);
++}
++
++/*
++ * Add a CU mapping to the link.
++ *
++ * CU mappings for built-in modules are added by suck_in_modules, below: here,
++ * we only want to add mappings for names ending in '.ko.ctf', i.e. external
++ * modules, which appear only in the filelist (since they are not built-in).
++ * The pathnames are stripped off because modules don't have any, and hyphens
++ * are translated into underscores.
++ */
++static void add_cu_mappings(const char *fn)
++{
++ const char *last_slash;
++ const char *modname = fn;
++ char *dynmodname = NULL;
++ char *dash;
++ size_t n;
++
++ last_slash = strrchr(modname, '/');
++ if (last_slash)
++ last_slash++;
++ else
++ last_slash = modname;
++ modname = last_slash;
++ if (strchr(modname, '-') != NULL)
++ {
++ dynmodname = strdup(last_slash);
++ dash = dynmodname;
++ while (dash != NULL) {
++ dash = strchr(dash, '-');
++ if (dash != NULL)
++ *dash = '_';
++ }
++ modname = dynmodname;
++ }
++
++ n = strlen(modname);
++ if (strcmp(modname + n - strlen(".ko.ctf"), ".ko.ctf") == 0) {
++ char *mod;
++
++ n -= strlen(".ko.ctf");
++ mod = strndup(modname, n);
++ add_cu_mapping(fn, mod);
++ free(mod);
++ }
++ free(dynmodname);
++}
++
++/*
++ * Add the passed names as mappings to "vmlinux".
++ */
++static void add_builtins(const char *fn)
++{
++ if (add_cu_mapping(fn, "vmlinux") < 0)
++ {
++ fprintf(stderr, "Cannot add CTF CU mapping from %s to \"vmlinux\"\n",
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++}
++
++/*
++ * Do something with a file, line by line.
++ */
++static void suck_in_lines(const char *filename, void (*func)(const char *line))
++{
++ FILE *f;
++ char *line = NULL;
++ size_t line_size = 0;
++
++ f = fopen(filename, "r");
++ if (f == NULL) {
++ fprintf(stderr, "Cannot open %s: %s\n", filename,
++ strerror(errno));
++ exit(1);
++ }
++
++ while (getline(&line, &line_size, f) >= 0) {
++ size_t len = strlen(line);
++
++ if (len == 0)
++ continue;
++
++ if (line[len-1] == '\n')
++ line[len-1] = '\0';
++
++ func(line);
++ }
++ free(line);
++
++ if (ferror(f)) {
++ fprintf(stderr, "Error reading from %s: %s\n", filename,
++ strerror(errno));
++ exit(1);
++ }
++
++ fclose(f);
++}
++
++/*
++ * Pull in modules.builtin.objs and turn it into CU mappings.
++ */
++static void suck_in_modules(const char *modules_builtin_name)
++{
++ struct modules_builtin_iter *i;
++ char *module_name = NULL;
++ char **paths;
++
++ i = modules_builtin_iter_new(modules_builtin_name);
++ if (i == NULL) {
++ fprintf(stderr, "Cannot iterate over builtin module file.\n");
++ exit(1);
++ }
++
++ while ((paths = modules_builtin_iter_next(i, &module_name)) != NULL) {
++ size_t j;
++
++ for (j = 0; paths[j] != NULL; j++) {
++ char *alloc = NULL;
++ char *path = paths[j];
++ /*
++ * If the name doesn't start in ./, add it, to match the names
++ * passed to add_builtins.
++ */
++ if (strncmp(paths[j], "./", 2) != 0) {
++ char *p;
++ if ((alloc = malloc(strlen(paths[j]) + 3)) == NULL) {
++ fprintf(stderr, "Cannot allocate memory for "
++ "builtin module object name %s.\n",
++ paths[j]);
++ exit(1);
++ }
++ p = alloc;
++ p = stpcpy(p, "./");
++ p = stpcpy(p, paths[j]);
++ path = alloc;
++ }
++ if (add_cu_mapping(path, module_name) < 0) {
++ fprintf(stderr, "Cannot add path -> module mapping for "
++ "%s -> %s: %s\n", path, module_name,
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++ free (alloc);
++ }
++ free(paths);
++ }
++ free(module_name);
++ modules_builtin_iter_free(i);
++}
++
++/*
++ * Strip the leading .ctf. off all the module names: transform the default name
++ * from _CTF_SECTION into shared_ctf, and chop any trailing .ctf off (since that
++ * derives from the intermediate file used to keep the CTF out of the final
++ * module).
++ */
++static char *transform_module_names(ctf_file_t *fp __attribute__((__unused__)),
++ const char *name,
++ void *arg __attribute__((__unused__)))
++{
++ if (strcmp(name, ".ctf") == 0)
++ return strdup("shared_ctf");
++
++ if (strncmp(name, ".ctf", 4) == 0) {
++ size_t n = strlen (name);
++ if (strcmp(name + n - 4, ".ctf") == 0)
++ n -= 4;
++ return strndup(name + 4, n - 4);
++ }
++ return NULL;
++}
++
++int main(int argc, char *argv[])
++{
++ int err;
++ const char *output_file;
++ unsigned char *file_data = NULL;
++ size_t file_size;
++ FILE *fp;
++
++ if (argc != 5) {
++ fprintf(stderr, "Syntax: ctfarchive output-file objects.builtin modules.builtin\n");
++ fprintf(stderr, " filelist\n");
++ exit(1);
++ }
++
++ output_file = argv[1];
++
++ /*
++ * First pull in the input files and add them to the link.
++ */
++
++ output = ctf_create(&err);
++ if (!output) {
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ ctf_errmsg(err));
++ return 1;
++ }
++
++ suck_in_lines(argv[4], add_to_link);
++
++ /*
++ * Make sure that, even if all their types are shared, all modules have
++ * a ctf member that can be used as a child of the shared CTF.
++ */
++ suck_in_lines(argv[4], add_cu_mappings);
++
++ /*
++ * Then pull in the builtin objects list and add them as
++ * mappings to "vmlinux".
++ */
++
++ suck_in_lines(argv[2], add_builtins);
++
++ /*
++ * Finally, pull in the object -> module mapping and add it
++ * as appropriate mappings.
++ */
++ suck_in_modules(argv[3]);
++
++ /*
++ * Commit the added CU mappings.
++ */
++ commit_cu_mappings();
++
++ /*
++ * Arrange to fix up the module names.
++ */
++ ctf_link_set_memb_name_changer(output, transform_module_names, NULL);
++
++ /*
++ * Do the link.
++ */
++ if (ctf_link(output, CTF_LINK_SHARE_DUPLICATED |
++ CTF_LINK_EMPTY_CU_MAPPINGS) < 0)
++ goto ctf_err;
++
++ /*
++ * Write the output.
++ */
++
++ file_data = ctf_link_write(output, &file_size, 4096);
++ if (!file_data)
++ goto ctf_err;
++
++ fp = fopen(output_file, "w");
++ if (!fp)
++ goto err;
++
++ while ((err = fwrite(file_data, file_size, 1, fp)) == 0);
++ if (ferror(fp)) {
++ errno = ferror(fp);
++ goto err;
++ }
++ if (fclose(fp) < 0)
++ goto err;
++ free(file_data);
++ ctf_file_close(output);
++
++ return 0;
++err:
++ free(file_data);
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ strerror(errno));
++ return 1;
++ctf_err:
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ ctf_errmsg(ctf_errno(output)));
++ return 1;
++}
+diff --git a/scripts/ctf/modules_builtin.c b/scripts/ctf/modules_builtin.c
+new file mode 100644
+index 0000000000000..10af2bbc80e0c
+--- /dev/null
++++ b/scripts/ctf/modules_builtin.c
+@@ -0,0 +1,2 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++#include "../modules_builtin.c"
+diff --git a/scripts/ctf/modules_builtin.h b/scripts/ctf/modules_builtin.h
+new file mode 100644
+index 0000000000000..5e0299e5600c2
+--- /dev/null
++++ b/scripts/ctf/modules_builtin.h
+@@ -0,0 +1,2 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++#include "../modules_builtin.h"
+diff --git a/scripts/generate_builtin_ranges.awk b/scripts/generate_builtin_ranges.awk
+new file mode 100755
+index 0000000000000..51ae0458ffbdd
+--- /dev/null
++++ b/scripts/generate_builtin_ranges.awk
+@@ -0,0 +1,516 @@
++#!/usr/bin/gawk -f
++# SPDX-License-Identifier: GPL-2.0
++# generate_builtin_ranges.awk: Generate address range data for builtin modules
++# Written by Kris Van Hees <kris.van.hees@oracle.com>
++#
++# Usage: generate_builtin_ranges.awk modules.builtin vmlinux.map \
++# vmlinux.o.map [ <build-dir> ] > modules.builtin.ranges
++#
++
++# Return the module name(s) (if any) associated with the given object.
++#
++# If we have seen this object before, return information from the cache.
++# Otherwise, retrieve it from the corresponding .cmd file.
++#
++function get_module_info(fn, mod, obj, s) {
++ if (fn in omod)
++ return omod[fn];
++
++ if (match(fn, /\/[^/]+$/) == 0)
++ return "";
++
++ obj = fn;
++ mod = "";
++ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
++ if (getline s <fn == 1) {
++ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
++ mod = substr(s, RSTART + 16, RLENGTH - 16);
++ gsub(/['"]/, "", mod);
++ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
++ mod = substr(s, RSTART + 13, RLENGTH - 13);
++ }
++ close(fn);
++
++ # A single module (common case) also reflects objects that are not part
++ # of a module. Some of those objects have names that are also a module
++ # name (e.g. core). We check the associated module file name, and if
++ # they do not match, the object is not part of a module.
++ if (mod !~ / /) {
++ if (!(mod in mods))
++ mod = "";
++ }
++
++ gsub(/([^/ ]*\/)+/, "", mod);
++ gsub(/-/, "_", mod);
++
++ # At this point, mod is a single (valid) module name, or a list of
++ # module names (that do not need validation).
++ omod[obj] = mod;
++
++ return mod;
++}
++
++# Update the ranges entry for the given module 'mod' in section 'osect'.
++#
++# We use a modified absolute start address (soff + base) as index because we
++# may need to insert an anchor record later that must be at the start of the
++# section data, and the first module may very well start at the same address.
++# So, we use (addr << 1) + 1 to allow a possible anchor record to be placed at
++# (addr << 1). This is safe because the index is only used to sort the entries
++# before writing them out.
++#
++function update_entry(osect, mod, soff, eoff, sect, idx) {
++ sect = sect_in[osect];
++ idx = (soff + sect_base[osect]) * 2 + 1;
++ entries[idx] = sprintf("%s %08x-%08x %s", sect, soff, eoff, mod);
++ count[sect]++;
++}
++
++# Determine the kernel build directory to use (default is .).
++#
++BEGIN {
++ if (ARGC > 4) {
++ kdir = ARGV[ARGC - 1];
++ ARGV[ARGC - 1] = "";
++ } else
++ kdir = ".";
++}
++
++# (1) Build a lookup map of built-in module names.
++#
++# The first file argument is used as input (modules.builtin).
++#
++# Lines will be like:
++# kernel/crypto/lzo-rle.ko
++# and we record the object name "crypto/lzo-rle".
++#
++ARGIND == 1 {
++ sub(/kernel\//, ""); # strip off "kernel/" prefix
++ sub(/\.ko$/, ""); # strip off .ko suffix
++
++ mods[$1] = 1;
++ next;
++}
++
++# (2) Collect address information for each section.
++#
++# The second file argument is used as input (vmlinux.map).
++#
++# We collect the base address of the section in order to convert all addresses
++# in the section into offset values.
++#
++# We collect the address of the anchor (or first symbol in the section if there
++# is no explicit anchor) to allow users of the range data to calculate address
++# ranges based on the actual load address of the section in the running kernel.
++#
++# We collect the start address of any sub-section (section included in the top
++# level section being processed). This is needed when the final linking was
++# done using vmlinux.a because then the list of objects contained in each
++# section is to be obtained from vmlinux.o.map. The offset of the sub-section
++# is recorded here, to be used as an addend when processing vmlinux.o.map
++# later.
++#
++
++# Both GNU ld and LLVM lld linker map format are supported by converting LLVM
++# lld linker map records into equivalent GNU ld linker map records.
++#
++# The first record of the vmlinux.map file provides enough information to know
++# which format we are dealing with.
++#
++ARGIND == 2 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
++ map_is_lld = 1;
++ if (dbg)
++ printf "NOTE: %s uses LLVM lld linker map format\n", FILENAME >"/dev/stderr";
++ next;
++}
++
++# (LLD) Convert a section record fronm lld format to ld format.
++#
++# lld: ffffffff82c00000 2c00000 2493c0 8192 .data
++# ->
++# ld: .data 0xffffffff82c00000 0x2493c0 load address 0x0000000002c00000
++#
++ARGIND == 2 && map_is_lld && NF == 5 && /[0-9] [^ ]+$/ {
++ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
++}
++
++# (LLD) Convert an anchor record from lld format to ld format.
++#
++# lld: ffffffff81000000 1000000 0 1 _text = .
++# ->
++# ld: 0xffffffff81000000 _text = .
++#
++ARGIND == 2 && map_is_lld && !anchor && NF == 7 && raw_addr == "0x"$1 && $6 == "=" && $7 == "." {
++ $0 = " 0x"$1 " " $5 " = .";
++}
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++# lld: 11480 11480 1f07 16 vmlinux.a(arch/x86/events/amd/uncore.o):(.text)
++# ->
++# ld: .text 0x0000000000011480 0x1f07 arch/x86/events/amd/uncore.o
++#
++ARGIND == 2 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
++ gsub(/\)/, "");
++ sub(/ vmlinux\.a\(/, " ");
++ sub(/:\(/, " ");
++ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (LLD) Convert a symbol record from lld format to ld format.
++#
++# We only care about these while processing a section for which no anchor has
++# been determined yet.
++#
++# lld: ffffffff82a859a4 2a859a4 0 1 btf_ksym_iter_id
++# ->
++# ld: 0xffffffff82a859a4 btf_ksym_iter_id
++#
++ARGIND == 2 && map_is_lld && sect && !anchor && NF == 5 && $5 ~ /^[_A-Za-z][_A-Za-z0-9]*$/ {
++ $0 = " 0x"$1 " " $5;
++}
++
++# (LLD) We do not need any other ldd linker map records.
++#
++ARGIND == 2 && map_is_lld && /^[0-9a-f]{16} / {
++ next;
++}
++
++# (LD) Section records with just the section name at the start of the line
++# need to have the next line pulled in to determine whether it is a
++# loadable section. If it is, the next line will contains a hex value
++# as first and second items.
++#
++ARGIND == 2 && !map_is_lld && NF == 1 && /^[^ ]/ {
++ s = $0;
++ getline;
++ if ($1 !~ /^0x/ || $2 !~ /^0x/)
++ next;
++
++ $0 = s " " $0;
++}
++
++# (LD) Object records with just the section name denote records with a long
++# section name for which the remainder of the record can be found on the
++# next line.
++#
++# (This is also needed for vmlinux.o.map, when used.)
++#
++ARGIND >= 2 && !map_is_lld && NF == 1 && /^ [^ \*]/ {
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# Beginning a new section - done with the previous one (if any).
++#
++ARGIND == 2 && /^[^ ]/ {
++ sect = 0;
++}
++
++# Process a loadable section (we only care about .-sections).
++#
++# Record the section name and its base address.
++# We also record the raw (non-stripped) address of the section because it can
++# be used to identify an anchor record.
++#
++# Note:
++# Since some AWK implementations cannot handle large integers, we strip off the
++# first 4 hex digits from the address. This is safe because the kernel space
++# is not large enough for addresses to extend into those digits. The portion
++# to strip off is stored in addr_prefix as a regexp, so further clauses can
++# perform a simple substitution to do the address stripping.
++#
++ARGIND == 2 && /^\./ {
++ # Explicitly ignore a few sections that are not relevant here.
++ if ($1 ~ /^\.orc_/ || $1 ~ /_sites$/ || $1 ~ /\.percpu/)
++ next;
++
++ # Sections with a 0-address can be ignored as well.
++ if ($2 ~ /^0x0+$/)
++ next;
++
++ raw_addr = $2;
++ addr_prefix = "^" substr($2, 1, 6);
++ base = $2;
++ sub(addr_prefix, "0x", base);
++ base = strtonum(base);
++ sect = $1;
++ anchor = 0;
++ sect_base[sect] = base;
++ sect_size[sect] = strtonum($3);
++
++ if (dbg)
++ printf "[%s] BASE %016x\n", sect, base >"/dev/stderr";
++
++ next;
++}
++
++# If we are not in a section we care about, we ignore the record.
++#
++ARGIND == 2 && !sect {
++ next;
++}
++
++# Record the first anchor symbol for the current section.
++#
++# An anchor record for the section bears the same raw address as the section
++# record.
++#
++ARGIND == 2 && !anchor && NF == 4 && raw_addr == $1 && $3 == "=" && $4 == "." {
++ anchor = sprintf("%s %08x-%08x = %s", sect, 0, 0, $2);
++ sect_anchor[sect] = anchor;
++
++ if (dbg)
++ printf "[%s] ANCHOR %016x = %s (.)\n", sect, 0, $2 >"/dev/stderr";
++
++ next;
++}
++
++# If no anchor record was found for the current section, use the first symbol
++# in the section as anchor.
++#
++ARGIND == 2 && !anchor && NF == 2 && $1 ~ /^0x/ && $2 !~ /^0x/ {
++ addr = $1;
++ sub(addr_prefix, "0x", addr);
++ addr = strtonum(addr) - base;
++ anchor = sprintf("%s %08x-%08x = %s", sect, addr, addr, $2);
++ sect_anchor[sect] = anchor;
++
++ if (dbg)
++ printf "[%s] ANCHOR %016x = %s\n", sect, addr, $2 >"/dev/stderr";
++
++ next;
++}
++
++# The first occurrence of a section name in an object record establishes the
++# addend (often 0) for that section. This information is needed to handle
++# sections that get combined in the final linking of vmlinux (e.g. .head.text
++# getting included at the start of .text).
++#
++# If the section does not have a base yet, use the base of the encapsulating
++# section.
++#
++ARGIND == 2 && sect && NF == 4 && /^ [^ \*]/ && !($1 in sect_addend) {
++ if (!($1 in sect_base)) {
++ sect_base[$1] = base;
++
++ if (dbg)
++ printf "[%s] BASE %016x\n", $1, base >"/dev/stderr";
++ }
++
++ addr = $2;
++ sub(addr_prefix, "0x", addr);
++ addr = strtonum(addr);
++ sect_addend[$1] = addr - sect_base[$1];
++ sect_in[$1] = sect;
++
++ if (dbg)
++ printf "[%s] ADDEND %016x - %016x = %016x\n", $1, addr, base, sect_addend[$1] >"/dev/stderr";
++
++ # If the object is vmlinux.o then we will need vmlinux.o.map to get the
++ # actual offsets of objects.
++ if ($4 == "vmlinux.o")
++ need_o_map = 1;
++}
++
++# (3) Collect offset ranges (relative to the section base address) for built-in
++# modules.
++#
++# If the final link was done using the actual objects, vmlinux.map contains all
++# the information we need (see section (3a)).
++# If linking was done using vmlinux.a as intermediary, we will need to process
++# vmlinux.o.map (see section (3b)).
++
++# (3a) Determine offset range info using vmlinux.map.
++#
++# Since we are already processing vmlinux.map, the top level section that is
++# being processed is already known. If we do not have a base address for it,
++# we do not need to process records for it.
++#
++# Given the object name, we determine the module(s) (if any) that the current
++# object is associated with.
++#
++# If we were already processing objects for a (list of) module(s):
++# - If the current object belongs to the same module(s), update the range data
++# to include the current object.
++# - Otherwise, ensure that the end offset of the range is valid.
++#
++# If the current object does not belong to a built-in module, ignore it.
++#
++# If it does, we add a new built-in module offset range record.
++#
++ARGIND == 2 && !need_o_map && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
++ if (!(sect in sect_base))
++ next;
++
++ # Turn the address into an offset from the section base.
++ soff = $2;
++ sub(addr_prefix, "0x", soff);
++ soff = strtonum(soff) - sect_base[sect];
++ eoff = soff + strtonum($3);
++
++ # Determine which (if any) built-in modules the object belongs to.
++ mod = get_module_info($4);
++
++ # If we are processing a built-in module:
++ # - If the current object is within the same module, we update its
++ # entry by extending the range and move on
++ # - Otherwise:
++ # + If we are still processing within the same main section, we
++ # validate the end offset against the start offset of the
++ # current object (e.g. .rodata.str1.[18] objects are often
++ # listed with an incorrect size in the linker map)
++ # + Otherwise, we validate the end offset against the section
++ # size
++ if (mod_name) {
++ if (mod == mod_name) {
++ mod_eoff = eoff;
++ update_entry(mod_sect, mod_name, mod_soff, eoff);
++
++ next;
++ } else if (sect == sect_in[mod_sect]) {
++ if (mod_eoff > soff)
++ update_entry(mod_sect, mod_name, mod_soff, soff);
++ } else {
++ v = sect_size[sect_in[mod_sect]];
++ if (mod_eoff > v)
++ update_entry(mod_sect, mod_name, mod_soff, v);
++ }
++ }
++
++ mod_name = mod;
++
++ # If we encountered an object that is not part of a built-in module, we
++ # do not need to record any data.
++ if (!mod)
++ next;
++
++ # At this point, we encountered the start of a new built-in module.
++ mod_name = mod;
++ mod_soff = soff;
++ mod_eoff = eoff;
++ mod_sect = $1;
++ update_entry($1, mod, soff, mod_eoff);
++
++ next;
++}
++
++# If we do not need to parse the vmlinux.o.map file, we are done.
++#
++ARGIND == 3 && !need_o_map {
++ if (dbg)
++ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
++ exit;
++}
++
++# (3) Collect offset ranges (relative to the section base address) for built-in
++# modules.
++#
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++ARGIND == 3 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
++ gsub(/\)/, "");
++ sub(/:\(/, " ");
++
++ sect = $6;
++ if (!(sect in sect_addend))
++ next;
++
++ sub(/ vmlinux\.a\(/, " ");
++ $0 = " "sect " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (3b) Determine offset range info using vmlinux.o.map.
++#
++# If we do not know an addend for the object's section, we are interested in
++# anything within that section.
++#
++# Determine the top-level section that the object's section was included in
++# during the final link. This is the section name offset range data will be
++# associated with for this object.
++#
++# The remainder of the processing of the current object record follows the
++# procedure outlined in (3a).
++#
++ARGIND == 3 && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
++ osect = $1;
++ if (!(osect in sect_addend))
++ next;
++
++ # We need to work with the main section.
++ sect = sect_in[osect];
++
++ # Turn the address into an offset from the section base.
++ soff = $2;
++ sub(addr_prefix, "0x", soff);
++ soff = strtonum(soff) + sect_addend[osect];
++ eoff = soff + strtonum($3);
++
++ # Determine which (if any) built-in modules the object belongs to.
++ mod = get_module_info($4);
++
++ # If we are processing a built-in module:
++ # - If the current object is within the same module, we update its
++ # entry by extending the range and move on
++ # - Otherwise:
++ # + If we are still processing within the same main section, we
++ # validate the end offset against the start offset of the
++ # current object (e.g. .rodata.str1.[18] objects are often
++ # listed with an incorrect size in the linker map)
++ # + Otherwise, we validate the end offset against the section
++ # size
++ if (mod_name) {
++ if (mod == mod_name) {
++ mod_eoff = eoff;
++ update_entry(mod_sect, mod_name, mod_soff, eoff);
++
++ next;
++ } else if (sect == sect_in[mod_sect]) {
++ if (mod_eoff > soff)
++ update_entry(mod_sect, mod_name, mod_soff, soff);
++ } else {
++ v = sect_size[sect_in[mod_sect]];
++ if (mod_eoff > v)
++ update_entry(mod_sect, mod_name, mod_soff, v);
++ }
++ }
++
++ mod_name = mod;
++
++ # If we encountered an object that is not part of a built-in module, we
++ # do not need to record any data.
++ if (!mod)
++ next;
++
++ # At this point, we encountered the start of a new built-in module.
++ mod_name = mod;
++ mod_soff = soff;
++ mod_eoff = eoff;
++ mod_sect = osect;
++ update_entry(osect, mod, soff, mod_eoff);
++
++ next;
++}
++
++# (4) Generate the output.
++#
++# Anchor records are added for each section that contains offset range data
++# records. They are added at an adjusted section base address (base << 1) to
++# ensure they come first in the second records (see update_entry() above for
++# more information).
++#
++# All entries are sorted by (adjusted) address to ensure that the output can be
++# parsed in strict ascending address order.
++#
++END {
++ for (sect in count) {
++ if (sect in sect_anchor)
++ entries[sect_base[sect] * 2] = sect_anchor[sect];
++ }
++
++ n = asorti(entries, indices);
++ for (i = 1; i <= n; i++)
++ print entries[indices[i]];
++}
+diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
+index f48d72d22dc2a..d7e6cd7781256 100644
+--- a/scripts/mod/modpost.c
++++ b/scripts/mod/modpost.c
+@@ -733,6 +733,7 @@ static const char *const section_white_list[] =
+ ".comment*",
+ ".debug*",
+ ".zdebug*", /* Compressed debug sections. */
++ ".ctf", /* Type info */
+ ".GCC.command.line", /* record-gcc-switches */
+ ".mdebug*", /* alpha, score, mips etc. */
+ ".pdr", /* alpha, score, mips etc. */
+diff --git a/scripts/modules_builtin.c b/scripts/modules_builtin.c
+new file mode 100644
+index 0000000000000..df52932a4417b
+--- /dev/null
++++ b/scripts/modules_builtin.c
+@@ -0,0 +1,200 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * A simple modules_builtin reader.
++ *
++ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#include <errno.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <string.h>
++
++#include "modules_builtin.h"
++
++/*
++ * Read a modules.builtin.objs file and translate it into a stream of
++ * name / module-name pairs.
++ */
++
++/*
++ * Construct a modules.builtin.objs iterator.
++ */
++struct modules_builtin_iter *
++modules_builtin_iter_new(const char *modules_builtin_file)
++{
++ struct modules_builtin_iter *i;
++
++ i = calloc(1, sizeof(struct modules_builtin_iter));
++ if (i == NULL)
++ return NULL;
++
++ i->f = fopen(modules_builtin_file, "r");
++
++ if (i->f == NULL) {
++ fprintf(stderr, "Cannot open builtin module file %s: %s\n",
++ modules_builtin_file, strerror(errno));
++ return NULL;
++ }
++
++ return i;
++}
++
++/*
++ * Iterate, returning a new null-terminated array of object file names, and a
++ * new dynamically-allocated module name. (The module name passed in is freed.)
++ *
++ * The array of object file names should be freed by the caller: the strings it
++ * points to are owned by the iterator, and should not be freed.
++ */
++
++char ** __attribute__((__nonnull__))
++modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name)
++{
++ size_t npaths = 1;
++ char **module_paths;
++ char *last_slash;
++ char *last_dot;
++ char *trailing_linefeed;
++ char *object_name = i->line;
++ char *dash;
++ int composite = 0;
++
++ /*
++ * Read in all module entries, computing the suffixless, pathless name
++ * of the module and building the next arrayful of object file names for
++ * return.
++ *
++ * Modules can consist of multiple files: in this case, the portion
++ * before the colon is the path to the module (as before): the portion
++ * after the colon is a space-separated list of files that should be
++ * considered part of this module. In this case, the portion before the
++ * name is an "object file" that does not actually exist: it is merged
++ * into built-in.a without ever being written out.
++ *
++ * All module names have - translated to _, to match what is done to the
++ * names of the same things when built as modules.
++ */
++
++ /*
++ * Reinvocation of exhausted iterator. Return NULL, once.
++ */
++retry:
++ if (getline(&i->line, &i->line_size, i->f) < 0) {
++ if (ferror(i->f)) {
++ fprintf(stderr, "Error reading from modules_builtin file:"
++ " %s\n", strerror(errno));
++ exit(1);
++ }
++ rewind(i->f);
++ return NULL;
++ }
++
++ if (i->line[0] == '\0')
++ goto retry;
++
++ trailing_linefeed = strchr(i->line, '\n');
++ if (trailing_linefeed != NULL)
++ *trailing_linefeed = '\0';
++
++ /*
++ * Slice the line in two at the colon, if any. If there is anything
++ * past the ': ', this is a composite module. (We allow for no colon
++ * for robustness, even though one should always be present.)
++ */
++ if (strchr(i->line, ':') != NULL) {
++ char *name_start;
++
++ object_name = strchr(i->line, ':');
++ *object_name = '\0';
++ object_name++;
++ name_start = object_name + strspn(object_name, " \n");
++ if (*name_start != '\0') {
++ composite = 1;
++ object_name = name_start;
++ }
++ }
++
++ /*
++ * Figure out the module name.
++ */
++ last_slash = strrchr(i->line, '/');
++ last_slash = (!last_slash) ? i->line :
++ last_slash + 1;
++ free(*module_name);
++ *module_name = strdup(last_slash);
++ dash = *module_name;
++
++ while (dash != NULL) {
++ dash = strchr(dash, '-');
++ if (dash != NULL)
++ *dash = '_';
++ }
++
++ last_dot = strrchr(*module_name, '.');
++ if (last_dot != NULL)
++ *last_dot = '\0';
++
++ /*
++ * Multifile separator? Object file names explicitly stated:
++ * slice them up and shuffle them in.
++ *
++ * The array size may be an overestimate if any object file
++ * names start or end with spaces (very unlikely) but cannot be
++ * an underestimate. (Check for it anyway.)
++ */
++ if (composite) {
++ char *one_object;
++
++ for (npaths = 0, one_object = object_name;
++ one_object != NULL;
++ npaths++, one_object = strchr(one_object + 1, ' '));
++ }
++
++ module_paths = malloc((npaths + 1) * sizeof(char *));
++ if (!module_paths) {
++ fprintf(stderr, "%s: out of memory on module %s\n", __func__,
++ *module_name);
++ exit(1);
++ }
++
++ if (composite) {
++ char *one_object;
++ size_t i = 0;
++
++ while ((one_object = strsep(&object_name, " ")) != NULL) {
++ if (i >= npaths) {
++ fprintf(stderr, "%s: num_objs overflow on module "
++ "%s: this is a bug.\n", __func__,
++ *module_name);
++ exit(1);
++ }
++
++ module_paths[i++] = one_object;
++ }
++ } else
++ module_paths[0] = i->line; /* untransformed module name */
++
++ module_paths[npaths] = NULL;
++
++ return module_paths;
++}
++
++/*
++ * Free an iterator. Can be called while iteration is underway, so even
++ * state that is freed at the end of iteration must be freed here too.
++ */
++void
++modules_builtin_iter_free(struct modules_builtin_iter *i)
++{
++ if (i == NULL)
++ return;
++ fclose(i->f);
++ free(i->line);
++ free(i);
++}
+diff --git a/scripts/modules_builtin.h b/scripts/modules_builtin.h
+new file mode 100644
+index 0000000000000..5138792b42ef0
+--- /dev/null
++++ b/scripts/modules_builtin.h
+@@ -0,0 +1,48 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * A simple modules.builtin.objs reader.
++ *
++ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#ifndef _LINUX_MODULES_BUILTIN_H
++#define _LINUX_MODULES_BUILTIN_H
++
++#include <stdio.h>
++#include <stddef.h>
++
++/*
++ * modules.builtin.objs iteration state.
++ */
++struct modules_builtin_iter {
++ FILE *f;
++ char *line;
++ size_t line_size;
++};
++
++/*
++ * Construct a modules_builtin.objs iterator.
++ */
++struct modules_builtin_iter *
++modules_builtin_iter_new(const char *modules_builtin_file);
++
++/*
++ * Iterate, returning a new null-terminated array of object file names, and a
++ * new dynamically-allocated module name. (The module name passed in is freed.)
++ *
++ * The array of object file names should be freed by the caller: the strings it
++ * points to are owned by the iterator, and should not be freed.
++ */
++
++char ** __attribute__((__nonnull__))
++modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name);
++
++void
++modules_builtin_iter_free(struct modules_builtin_iter *i);
++
++#endif
+diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
+index c52d517b93647..8f75906a96314 100644
+--- a/scripts/package/kernel.spec
++++ b/scripts/package/kernel.spec
+@@ -53,12 +53,18 @@ patch -p1 < %{SOURCE2}
+
+ %build
+ %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
++%if %{with_ctf}
++%{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release} ctf
++%endif
+
+ %install
+ mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
+ cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
+ # DEPMOD=true makes depmod no-op. We do not package depmod-generated files.
+ %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} DEPMOD=true modules_install
++%if %{with_ctf}
++%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} ctf_install
++%endif
+ %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
+ cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
+ cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
+diff --git a/scripts/package/mkspec b/scripts/package/mkspec
+index ce201bfa8377c..aeb43c7ab1229 100755
+--- a/scripts/package/mkspec
++++ b/scripts/package/mkspec
+@@ -21,10 +21,16 @@ else
+ echo '%define with_devel 0'
+ fi
+
++if grep -q CONFIG_CTF=y include/config/auto.conf; then
++echo '%define with_ctf %{?_without_ctf: 0} %{?!_without_ctf: 1}'
++else
++echo '%define with_ctf 0'
++fi
+ cat<<EOF
+ %define ARCH ${ARCH}
+ %define KERNELRELEASE ${KERNELRELEASE}
+ %define pkg_release $("${srctree}/init/build-version")
++
+ EOF
+
+ cat "${srctree}/scripts/package/kernel.spec"
+diff --git a/scripts/remove-ctf-lds.awk b/scripts/remove-ctf-lds.awk
+new file mode 100644
+index 0000000000000..5d94d6ee99227
+--- /dev/null
++++ b/scripts/remove-ctf-lds.awk
+@@ -0,0 +1,12 @@
++# SPDX-License-Identifier: GPL-2.0
++# See Makefile.vmlinux_o
++
++BEGIN {
++ discards = 0; p = 0
++}
++
++/^====/ { p = 1; next; }
++p && /\.ctf/ { next; }
++p && !discards && /DISCARD/ { sub(/\} *$/, " *(.ctf) }"); discards = 1 }
++p && /^\}/ && !discards { print " /DISCARD/ : { *(.ctf) }"; }
++p { print $0; }
+diff --git a/scripts/verify_builtin_ranges.awk b/scripts/verify_builtin_ranges.awk
+new file mode 100755
+index 0000000000000..f513841da83e1
+--- /dev/null
++++ b/scripts/verify_builtin_ranges.awk
+@@ -0,0 +1,356 @@
++#!/usr/bin/gawk -f
++# SPDX-License-Identifier: GPL-2.0
++# verify_builtin_ranges.awk: Verify address range data for builtin modules
++# Written by Kris Van Hees <kris.van.hees@oracle.com>
++#
++# Usage: verify_builtin_ranges.awk modules.builtin.ranges System.map \
++# modules.builtin vmlinux.map vmlinux.o.map \
++# [ <build-dir> ]
++#
++
++# Return the module name(s) (if any) associated with the given object.
++#
++# If we have seen this object before, return information from the cache.
++# Otherwise, retrieve it from the corresponding .cmd file.
++#
++function get_module_info(fn, mod, obj, s) {
++ if (fn in omod)
++ return omod[fn];
++
++ if (match(fn, /\/[^/]+$/) == 0)
++ return "";
++
++ obj = fn;
++ mod = "";
++ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
++ if (getline s <fn == 1) {
++ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
++ mod = substr(s, RSTART + 16, RLENGTH - 16);
++ gsub(/['"]/, "", mod);
++ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
++ mod = substr(s, RSTART + 13, RLENGTH - 13);
++ } else {
++ print "ERROR: Failed to read: " fn "\n\n" \
++ " Invalid kernel build directory (" kdir ")\n" \
++ " or its content does not match " ARGV[1] >"/dev/stderr";
++ close(fn);
++ total = 0;
++ exit(1);
++ }
++ close(fn);
++
++ # A single module (common case) also reflects objects that are not part
++ # of a module. Some of those objects have names that are also a module
++ # name (e.g. core). We check the associated module file name, and if
++ # they do not match, the object is not part of a module.
++ if (mod !~ / /) {
++ if (!(mod in mods))
++ mod = "";
++ }
++
++ gsub(/([^/ ]*\/)+/, "", mod);
++ gsub(/-/, "_", mod);
++
++ # At this point, mod is a single (valid) module name, or a list of
++ # module names (that do not need validation).
++ omod[obj] = mod;
++
++ return mod;
++}
++
++# Return a representative integer value for a given hexadecimal address.
++#
++# Since all kernel addresses fall within the same memory region, we can safely
++# strip off the first 6 hex digits before performing the hex-to-dec conversion,
++# thereby avoiding integer overflows.
++#
++function addr2val(val) {
++ sub(/^0x/, "", val);
++ if (length(val) == 16)
++ val = substr(val, 5);
++ return strtonum("0x" val);
++}
++
++# Determine the kernel build directory to use (default is .).
++#
++BEGIN {
++ if (ARGC > 6) {
++ kdir = ARGV[ARGC - 1];
++ ARGV[ARGC - 1] = "";
++ } else
++ kdir = ".";
++}
++
++# (1) Load the built-in module address range data.
++#
++ARGIND == 1 {
++ ranges[FNR] = $0;
++ rcnt++;
++ next;
++}
++
++# (2) Annotate System.map symbols with module names.
++#
++ARGIND == 2 {
++ addr = addr2val($1);
++ name = $3;
++
++ while (addr >= mod_eaddr) {
++ if (sect_symb) {
++ if (sect_symb != name)
++ next;
++
++ sect_base = addr - sect_off;
++ if (dbg)
++ printf "[%s] BASE (%s) %016x - %016x = %016x\n", sect_name, sect_symb, addr, sect_off, sect_base >"/dev/stderr";
++ sect_symb = 0;
++ }
++
++ if (++ridx > rcnt)
++ break;
++
++ $0 = ranges[ridx];
++ sub(/-/, " ");
++ if ($4 != "=") {
++ sub(/-/, " ");
++ mod_saddr = strtonum("0x" $2) + sect_base;
++ mod_eaddr = strtonum("0x" $3) + sect_base;
++ $1 = $2 = $3 = "";
++ sub(/^ +/, "");
++ mod_name = $0;
++
++ if (dbg)
++ printf "[%s] %s from %016x to %016x\n", sect_name, mod_name, mod_saddr, mod_eaddr >"/dev/stderr";
++ } else {
++ sect_name = $1;
++ sect_off = strtonum("0x" $2);
++ sect_symb = $5;
++ }
++ }
++
++ idx = addr"-"name;
++ if (addr >= mod_saddr && addr < mod_eaddr)
++ sym2mod[idx] = mod_name;
++
++ next;
++}
++
++# Once we are done annotating the System.map, we no longer need the ranges data.
++#
++FNR == 1 && ARGIND == 3 {
++ delete ranges;
++}
++
++# (3) Build a lookup map of built-in module names.
++#
++# Lines from modules.builtin will be like:
++# kernel/crypto/lzo-rle.ko
++# and we record the object name "crypto/lzo-rle".
++#
++ARGIND == 3 {
++ sub(/kernel\//, ""); # strip off "kernel/" prefix
++ sub(/\.ko$/, ""); # strip off .ko suffix
++
++ mods[$1] = 1;
++ next;
++}
++
++# (4) Get a list of symbols (per object).
++#
++# Symbols by object are read from vmlinux.map, with fallback to vmlinux.o.map
++# if vmlinux is found to have inked in vmlinux.o.
++#
++
++# If we were able to get the data we need from vmlinux.map, there is no need to
++# process vmlinux.o.map.
++#
++FNR == 1 && ARGIND == 5 && total > 0 {
++ if (dbg)
++ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
++ exit;
++}
++
++# First determine whether we are dealing with a GNU ld or LLVM lld linker map.
++#
++ARGIND >= 4 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
++ map_is_lld = 1;
++ next;
++}
++
++# (LLD) Convert a section record fronm lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && /[0-9] [^ ]/ {
++ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
++}
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /:\(\./ {
++ gsub(/\)/, "");
++ sub(/:\(/, " ");
++ sub(/ vmlinux\.a\(/, " ");
++ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (LLD) Convert a symbol record from lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /^[A-Za-z_][A-Za-z0-9_]*$/ {
++ $0 = " 0x" $1 " " $5;
++}
++
++# (LLD) We do not need any other ldd linker map records.
++#
++ARGIND >= 4 && map_is_lld && /^[0-9a-f]{16} / {
++ next;
++}
++
++# Handle section records with long section names (spilling onto a 2nd line).
++#
++ARGIND >= 4 && !map_is_lld && NF == 1 && /^[^ ]/ {
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# Next section - previous one is done.
++#
++ARGIND >= 4 && /^[^ ]/ {
++ sect = 0;
++}
++
++# Get the (top level) section name.
++#
++ARGIND >= 4 && /^[^ ]/ && $2 ~ /^0x/ && $3 ~ /^0x/ {
++ # Empty section or per-CPU section - ignore.
++ if (NF < 3 || $1 ~ /\.percpu/) {
++ sect = 0;
++ next;
++ }
++
++ sect = $1;
++
++ next;
++}
++
++# If we are not currently in a section we care about, ignore records.
++#
++!sect {
++ next;
++}
++
++# Handle object records with long section names (spilling onto a 2nd line).
++#
++ARGIND >= 4 && /^ [^ \*]/ && NF == 1 {
++ # If the section name is long, the remainder of the entry is found on
++ # the next line.
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# If the object is vmlinux.o, we need to consult vmlinux.o.map for per-object
++# symbol information
++#
++ARGIND == 4 && /^ [^ ]/ && NF == 4 {
++ idx = sect":"$1;
++ if (!(idx in sect_addend)) {
++ sect_addend[idx] = addr2val($2);
++ if (dbg)
++ printf "ADDEND %s = %016x\n", idx, sect_addend[idx] >"/dev/stderr";
++ }
++ if ($4 == "vmlinux.o") {
++ need_o_map = 1;
++ next;
++ }
++}
++
++# If data from vmlinux.o.map is needed, we only process section and object
++# records from vmlinux.map to determine which section we need to pay attention
++# to in vmlinux.o.map. So skip everything else from vmlinux.map.
++#
++ARGIND == 4 && need_o_map {
++ next;
++}
++
++# Get module information for the current object.
++#
++ARGIND >= 4 && /^ [^ ]/ && NF == 4 {
++ msect = $1;
++ mod_name = get_module_info($4);
++ mod_eaddr = addr2val($2) + addr2val($3);
++
++ next;
++}
++
++# Process a symbol record.
++#
++# Evaluate the module information obtained from vmlinux.map (or vmlinux.o.map)
++# as follows:
++# - For all symbols in a given object:
++# - If the symbol is annotated with the same module name(s) that the object
++# belongs to, count it as a match.
++# - Otherwise:
++# - If the symbol is known to have duplicates of which at least one is
++# in a built-in module, disregard it.
++# - If the symbol us not annotated with any module name(s) AND the
++# object belongs to built-in modules, count it as missing.
++# - Otherwise, count it as a mismatch.
++#
++ARGIND >= 4 && /^ / && NF == 2 && $1 ~ /^0x/ {
++ idx = sect":"msect;
++ if (!(idx in sect_addend))
++ next;
++
++ addr = addr2val($1);
++
++ # Handle the rare but annoying case where a 0-size symbol is placed at
++ # the byte *after* the module range. Based on vmlinux.map it will be
++ # considered part of the current object, but it falls just beyond the
++ # module address range. Unfortunately, its address could be at the
++ # start of another built-in module, so the only safe thing to do is to
++ # ignore it.
++ if (mod_name && addr == mod_eaddr)
++ next;
++
++ # If we are processing vmlinux.o.map, we need to apply the base address
++ # of the section to the relative address on the record.
++ #
++ if (ARGIND == 5)
++ addr += sect_addend[idx];
++
++ idx = addr"-"$2;
++ mod = "";
++ if (idx in sym2mod) {
++ mod = sym2mod[idx];
++ if (sym2mod[idx] == mod_name) {
++ mod_matches++;
++ matches++;
++ } else if (mod_name == "") {
++ print $2 " in " sym2mod[idx] " (should NOT be)";
++ mismatches++;
++ } else {
++ print $2 " in " sym2mod[idx] " (should be " mod_name ")";
++ mismatches++;
++ }
++ } else if (mod_name != "") {
++ print $2 " should be in " mod_name;
++ missing++;
++ } else
++ matches++;
++
++ total++;
++
++ next;
++}
++
++# Issue the comparison report.
++#
++END {
++ if (total) {
++ printf "Verification of %s:\n", ARGV[1];
++ printf " Correct matches: %6d (%d%% of total)\n", matches, 100 * matches / total;
++ printf " Module matches: %6d (%d%% of matches)\n", mod_matches, 100 * mod_matches / matches;
++ printf " Mismatches: %6d (%d%% of total)\n", mismatches, 100 * mismatches / total;
++ printf " Missing: %6d (%d%% of total)\n", missing, 100 * missing / total;
++ }
++}
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-07 14:23 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-07 14:23 UTC (permalink / raw
To: gentoo-commits
commit: 5076bab3888698a67d7503e02d12976f689a60b1
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Sep 7 14:22:49 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Sep 7 14:22:49 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=5076bab3
Remove old dtrace patch
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
2995_dtrace-6.10_p1.patch | 2355 ---------------------------------------------
1 file changed, 2355 deletions(-)
diff --git a/2995_dtrace-6.10_p1.patch b/2995_dtrace-6.10_p1.patch
deleted file mode 100644
index 97983060..00000000
--- a/2995_dtrace-6.10_p1.patch
+++ /dev/null
@@ -1,2355 +0,0 @@
-diff --git a/Documentation/dontdiff b/Documentation/dontdiff
-index 3c399f132e2db..75b9655e57914 100644
---- a/Documentation/dontdiff
-+++ b/Documentation/dontdiff
-@@ -179,7 +179,7 @@ mkutf8data
- modpost
- modules-only.symvers
- modules.builtin
--modules.builtin.modinfo
-+modules.builtin.*
- modules.nsdeps
- modules.order
- modversions.h*
-diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst
-index 9c8d1d046ea56..79e104ffee715 100644
---- a/Documentation/kbuild/kbuild.rst
-+++ b/Documentation/kbuild/kbuild.rst
-@@ -17,6 +17,11 @@ modules.builtin
- This file lists all modules that are built into the kernel. This is used
- by modprobe to not fail when trying to load something builtin.
-
-+modules.builtin.objs
-+-----------------------
-+This file contains object mapping of modules that are built into the kernel
-+to their corresponding object files used to build the module.
-+
- modules.builtin.modinfo
- -----------------------
- This file contains modinfo from all modules that are built into the kernel.
-diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
-index 5685d7bfe4d0f..8db62fe4dadff 100644
---- a/Documentation/process/changes.rst
-+++ b/Documentation/process/changes.rst
-@@ -63,9 +63,13 @@ cpio any cpio --version
- GNU tar 1.28 tar --version
- gtags (optional) 6.6.5 gtags --version
- mkimage (optional) 2017.01 mkimage --version
-+GNU AWK (optional) 5.1.0 gawk --version
-+GNU C\ [#f2]_ 12.0 gcc --version
-+binutils\ [#f2]_ 2.36 ld -v
- ====================== =============== ========================================
-
- .. [#f1] Sphinx is needed only to build the Kernel documentation
-+.. [#f2] These are needed at build-time when CONFIG_CTF is enabled
-
- Kernel compilation
- ******************
-@@ -198,6 +202,12 @@ platforms. The tool is available via the ``u-boot-tools`` package or can be
- built from the U-Boot source code. See the instructions at
- https://docs.u-boot.org/en/latest/build/tools.html#building-tools-for-linux
-
-+GNU AWK
-+-------
-+
-+GNU AWK is needed if you want kernel builds to generate address range data for
-+builtin modules (CONFIG_BUILTIN_MODULE_RANGES).
-+
- System utilities
- ****************
-
-diff --git a/Makefile b/Makefile
-index ab77d171e268d..425dd4d723155 100644
---- a/Makefile
-+++ b/Makefile
-@@ -1024,6 +1024,7 @@ include-$(CONFIG_UBSAN) += scripts/Makefile.ubsan
- include-$(CONFIG_KCOV) += scripts/Makefile.kcov
- include-$(CONFIG_RANDSTRUCT) += scripts/Makefile.randstruct
- include-$(CONFIG_GCC_PLUGINS) += scripts/Makefile.gcc-plugins
-+include-$(CONFIG_CTF) += scripts/Makefile.ctfa-toplevel
-
- include $(addprefix $(srctree)/, $(include-y))
-
-@@ -1151,7 +1152,11 @@ PHONY += vmlinux_o
- vmlinux_o: vmlinux.a $(KBUILD_VMLINUX_LIBS)
- $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux_o
-
--vmlinux.o modules.builtin.modinfo modules.builtin: vmlinux_o
-+MODULES_BUILTIN := modules.builtin.modinfo
-+MODULES_BUILTIN += modules.builtin
-+MODULES_BUILTIN += modules.builtin.objs
-+
-+vmlinux.o $(MODULES_BUILTIN): vmlinux_o
- @:
-
- PHONY += vmlinux
-@@ -1490,9 +1495,10 @@ endif # CONFIG_MODULES
-
- # Directories & files removed with 'make clean'
- CLEAN_FILES += vmlinux.symvers modules-only.symvers \
-- modules.builtin modules.builtin.modinfo modules.nsdeps \
-+ modules.builtin modules.builtin.* modules.nsdeps \
- compile_commands.json rust/test \
-- rust-project.json .vmlinux.objs .vmlinux.export.c
-+ rust-project.json .vmlinux.objs .vmlinux.export.c \
-+ vmlinux.ctfa
-
- # Directories & files removed with 'make mrproper'
- MRPROPER_FILES += include/config include/generated \
-@@ -1586,6 +1592,8 @@ help:
- @echo ' (requires a recent binutils and recent build (System.map))'
- @echo ' dir/file.ko - Build module including final link'
- @echo ' modules_prepare - Set up for building external modules'
-+ @echo ' ctf - Generate CTF type information, installed by make ctf_install'
-+ @echo ' ctf_install - Install CTF to INSTALL_MOD_PATH (default: /)'
- @echo ' tags/TAGS - Generate tags file for editors'
- @echo ' cscope - Generate cscope index'
- @echo ' gtags - Generate GNU GLOBAL index'
-@@ -1942,7 +1950,7 @@ clean: $(clean-dirs)
- $(call cmd,rmfiles)
- @find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \
- \( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \
-- -o -name '*.ko.*' \
-+ -o -name '*.ko.*' -o -name '*.ctf' \
- -o -name '*.dtb' -o -name '*.dtbo' \
- -o -name '*.dtb.S' -o -name '*.dtbo.S' \
- -o -name '*.dt.yaml' -o -name 'dtbs-list' \
-diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
-index 01067a2bc43b7..d2193b8dfad83 100644
---- a/arch/arm/vdso/Makefile
-+++ b/arch/arm/vdso/Makefile
-@@ -14,6 +14,10 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
- ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
- ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO32
-
-+# CTF in the vDSO would introduce a new section, which would
-+# expand the vDSO to more than a page.
-+ccflags-y += $(call cc-option,-gctf0)
-+
- ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8
- ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
- -z max-page-size=4096 -shared $(ldflags-y) \
-diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
-index d63930c828397..6e84d3822cfe3 100644
---- a/arch/arm64/kernel/vdso/Makefile
-+++ b/arch/arm64/kernel/vdso/Makefile
-@@ -33,6 +33,10 @@ ldflags-y += -T
- ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
- ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-
-+# CTF in the vDSO would introduce a new section, which would
-+# expand the vDSO to more than a page.
-+ccflags-y += $(call cc-option,-gctf0)
-+
- # -Wmissing-prototypes and -Wmissing-declarations are removed from
- # the CFLAGS of vgettimeofday.c to make possible to build the
- # kernel with CONFIG_WERROR enabled.
-diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
-index d724d46b07c84..fbedb95223ae1 100644
---- a/arch/loongarch/vdso/Makefile
-+++ b/arch/loongarch/vdso/Makefile
-@@ -21,7 +21,8 @@ cflags-vdso := $(ccflags-vdso) \
- -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
- -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
- $(call cc-option, -fno-asynchronous-unwind-tables) \
-- $(call cc-option, -fno-stack-protector)
-+ $(call cc-option, -fno-stack-protector) \
-+ $(call cc-option,-gctf0)
- aflags-vdso := $(ccflags-vdso) \
- -D__ASSEMBLY__ -Wa,-gdwarf-2
-
-diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
-index b289b2c1b2946..6c8d777525f9b 100644
---- a/arch/mips/vdso/Makefile
-+++ b/arch/mips/vdso/Makefile
-@@ -30,7 +30,8 @@ cflags-vdso := $(ccflags-vdso) \
- -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
- -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \
- -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
-- $(call cc-option, -fno-asynchronous-unwind-tables)
-+ $(call cc-option, -fno-asynchronous-unwind-tables) \
-+ $(call cc-option,-gctf0)
- aflags-vdso := $(ccflags-vdso) \
- -D__ASSEMBLY__ -Wa,-gdwarf-2
-
-diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
-index 243dbfc4609d8..e4f3e47074e9d 100644
---- a/arch/sparc/vdso/Makefile
-+++ b/arch/sparc/vdso/Makefile
-@@ -44,7 +44,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
- CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 \
- $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
- -fno-omit-frame-pointer -foptimize-sibling-calls \
-- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-+ $(call cc-option,-gctf0) -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-
- SPARC_REG_CFLAGS = -ffixed-g4 -ffixed-g5 -fcall-used-g5 -fcall-used-g7
-
-diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
-index 215a1b202a918..2fa1613a06275 100644
---- a/arch/x86/entry/vdso/Makefile
-+++ b/arch/x86/entry/vdso/Makefile
-@@ -54,6 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
- CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
- $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
- -fno-omit-frame-pointer -foptimize-sibling-calls \
-+ $(call cc-option,-gctf0) \
- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
-
- ifdef CONFIG_MITIGATION_RETPOLINE
-@@ -131,6 +132,7 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
- KBUILD_CFLAGS_32 += -fno-stack-protector
- KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
- KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
-+KBUILD_CFLAGS_32 += $(call cc-option,-gctf0)
- KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
-
- ifdef CONFIG_MITIGATION_RETPOLINE
-diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
-index 6a77ea6434ffd..6db233b5edd75 100644
---- a/arch/x86/um/vdso/Makefile
-+++ b/arch/x86/um/vdso/Makefile
-@@ -40,7 +40,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
- #
- CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
- $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
-- -fno-omit-frame-pointer -foptimize-sibling-calls
-+ -fno-omit-frame-pointer -foptimize-sibling-calls $(call cc-option,-gctf0)
-
- $(vobjs): KBUILD_CFLAGS += $(CFL)
-
-diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
-index f00a8e18f389f..2e307c0824574 100644
---- a/include/asm-generic/vmlinux.lds.h
-+++ b/include/asm-generic/vmlinux.lds.h
-@@ -1014,6 +1014,7 @@
- *(.discard.*) \
- *(.export_symbol) \
- *(.modinfo) \
-+ *(.ctf) \
- /* ld.bfd warns about .gnu.version* even when not emitted */ \
- *(.gnu.version*) \
-
-diff --git a/include/linux/module.h b/include/linux/module.h
-index 330ffb59efe51..ec828908470c9 100644
---- a/include/linux/module.h
-+++ b/include/linux/module.h
-@@ -180,7 +180,9 @@ extern void cleanup_module(void);
- #ifdef MODULE
- #define MODULE_FILE
- #else
--#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
-+#define MODULE_FILE \
-+ MODULE_INFO(file, KBUILD_MODFILE); \
-+ MODULE_INFO(objs, KBUILD_MODOBJS);
- #endif
-
- /*
-diff --git a/init/Kconfig b/init/Kconfig
-index 9684e5d2b81c6..c1b00b2e4a43d 100644
---- a/init/Kconfig
-+++ b/init/Kconfig
-@@ -111,6 +111,12 @@ config PAHOLE_VERSION
- int
- default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
-
-+config HAVE_CTF_TOOLCHAIN
-+ def_bool $(cc-option,-gctf) && $(ld-option,-lbfd -liberty -lctf -lbfd -liberty -lz -ldl -lc -o /dev/null)
-+ depends on CC_IS_GCC
-+ help
-+ GCC and binutils support CTF generation.
-+
- config CONSTRUCTORS
- bool
-
-diff --git a/lib/Kconfig b/lib/Kconfig
-index b0a76dff5c182..61d0be30b3562 100644
---- a/lib/Kconfig
-+++ b/lib/Kconfig
-@@ -633,6 +633,16 @@ config DIMLIB
- #
- config LIBFDT
- bool
-+#
-+# CTF support is select'ed if needed
-+#
-+config CTF
-+ bool "Compact Type Format generation"
-+ depends on HAVE_CTF_TOOLCHAIN
-+ help
-+ Emit a compact, compressed description of the kernel's datatypes and
-+ global variables into the vmlinux.ctfa archive (for in-tree modules)
-+ or into .ctf sections in kernel modules (for out-of-tree modules).
-
- config OID_REGISTRY
- tristate
-diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
-index 59b6765d86b8f..dab7e6983eace 100644
---- a/lib/Kconfig.debug
-+++ b/lib/Kconfig.debug
-@@ -571,6 +571,21 @@ config VMLINUX_MAP
- pieces of code get eliminated with
- CONFIG_LD_DEAD_CODE_DATA_ELIMINATION.
-
-+config BUILTIN_MODULE_RANGES
-+ bool "Generate address range information for builtin modules"
-+ depends on !LTO
-+ depends on VMLINUX_MAP
-+ help
-+ When modules are built into the kernel, there will be no module name
-+ associated with its symbols in /proc/kallsyms. Tracers may want to
-+ identify symbols by module name and symbol name regardless of whether
-+ the module is configured as loadable or not.
-+
-+ This option generates modules.builtin.ranges in the build tree with
-+ offset ranges (per ELF section) for the module(s) they belong to.
-+ It also records an anchor symbol to determine the load address of the
-+ section.
-+
- config DEBUG_FORCE_WEAK_PER_CPU
- bool "Force weak per-cpu definitions"
- depends on DEBUG_KERNEL
-diff --git a/scripts/.gitignore b/scripts/.gitignore
-index 3dbb8bb2457bc..11339fa922abd 100644
---- a/scripts/.gitignore
-+++ b/scripts/.gitignore
-@@ -11,3 +11,4 @@
- /sorttable
- /target.json
- /unifdef
-+y!/Makefile.ctf
-diff --git a/scripts/Makefile b/scripts/Makefile
-index fe56eeef09dd4..8e7eb174d3154 100644
---- a/scripts/Makefile
-+++ b/scripts/Makefile
-@@ -54,6 +54,7 @@ targets += module.lds
-
- subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
- subdir-$(CONFIG_MODVERSIONS) += genksyms
-+subdir-$(CONFIG_CTF) += ctf
- subdir-$(CONFIG_SECURITY_SELINUX) += selinux
-
- # Let clean descend into subdirs
-diff --git a/scripts/Makefile.ctfa b/scripts/Makefile.ctfa
-new file mode 100644
-index 0000000000000..2b10de139dce5
---- /dev/null
-+++ b/scripts/Makefile.ctfa
-@@ -0,0 +1,92 @@
-+# SPDX-License-Identifier: GPL-2.0-only
-+# ===========================================================================
-+# Module CTF/CTFA generation
-+# ===========================================================================
-+
-+include include/config/auto.conf
-+include $(srctree)/scripts/Kbuild.include
-+
-+# CTF is already present in every object file if CONFIG_CTF is enabled.
-+# vmlinux.lds.h strips it out of the finished kernel, but if nothing is done
-+# it will be deduplicated into module .ko's. For out-of-tree module builds,
-+# this is what we want, but for in-tree modules we can save substantial
-+# space by deduplicating it against all the core kernel types as well. So
-+# split the CTF out of in-tree module .ko's into separate .ctf files so that
-+# it doesn't take up space in the modules on disk, and let the specialized
-+# ctfarchive tool consume it and all the CTF in the vmlinux.o files when
-+# 'make ctf' is invoked, and use the same machinery that the linker uses to
-+# do CTF deduplication to emit vmlinux.ctfa containing the deduplicated CTF.
-+
-+# Nothing special needs to be done if CTF is turned off or if a standalone
-+# module is being built.
-+module-ctf-postlink = mv $(1).tmp $(1)
-+
-+ifdef CONFIG_CTF
-+
-+# This is quite tricky. The CTF machinery needs to be told about all the
-+# built-in objects as well as all the external modules -- but Makefile.modfinal
-+# only knows about the latter. So the toplevel makefile emits the names of the
-+# built-in objects into a temporary file, which is then catted and its contents
-+# used as prerequisites by this rule.
-+#
-+# We write the names of the object files to be scanned for CTF content into a
-+# file, then use that, to avoid hitting command-line length limits.
-+
-+ifeq ($(KBUILD_EXTMOD),)
-+ctf-modules := $(shell find . -name '*.ko.ctf' -print)
-+quiet_cmd_ctfa_raw = CTFARAW
-+ cmd_ctfa_raw = scripts/ctf/ctfarchive $@ .tmp_objects.builtin modules.builtin.objs $(ctf-filelist)
-+ctf-builtins := .tmp_objects.builtin
-+ctf-filelist := .tmp_ctf.filelist
-+ctf-filelist-raw := .tmp_ctf.filelist.raw
-+
-+define module-ctf-postlink =
-+ $(OBJCOPY) --only-section=.ctf $(1).tmp $(1).ctf && \
-+ $(OBJCOPY) --remove-section=.ctf $(1).tmp $(1) && rm -f $(1).tmp
-+endef
-+
-+# Split a list up like shell xargs does.
-+define xargs =
-+$(1) $(wordlist 1,1024,$(2))
-+$(if $(word 1025,$(2)),$(call xargs,$(1),$(wordlist 1025,$(words $(2)),$(2))))
-+endef
-+
-+$(ctf-filelist-raw): $(ctf-builtins) $(ctf-modules)
-+ @rm -f $(ctf-filelist-raw);
-+ $(call xargs,@printf "%s\n" >> $(ctf-filelist-raw),$^)
-+ @touch $(ctf-filelist-raw)
-+
-+$(ctf-filelist): $(ctf-filelist-raw)
-+ @rm -f $(ctf-filelist);
-+ @cat $(ctf-filelist-raw) | while read -r obj; do \
-+ case $$obj in \
-+ $(ctf-builtins)) cat $$obj >> $(ctf-filelist);; \
-+ *.a) ar t $$obj > $(ctf-filelist);; \
-+ *.builtin) cat $$obj >> $(ctf-filelist);; \
-+ *) echo "$$obj" >> $(ctf-filelist);; \
-+ esac; \
-+ done
-+ @touch $(ctf-filelist)
-+
-+# The raw CTF depends on the output CTF file list, and that depends
-+# on the .ko files for the modules.
-+.tmp_vmlinux.ctfa.raw: $(ctf-filelist) FORCE
-+ $(call if_changed,ctfa_raw)
-+
-+quiet_cmd_ctfa = CTFA
-+ cmd_ctfa = { echo 'int main () { return 0; } ' | \
-+ gcc -x c -c -o $<.stub -; \
-+ $(OBJCOPY) '--remove-section=.*' --add-section=.ctf=$< \
-+ $<.stub $@; }
-+
-+# The CTF itself is an ELF executable with one section: the CTF. This lets
-+# objdump work on it, at minimal size cost.
-+vmlinux.ctfa: .tmp_vmlinux.ctfa.raw FORCE
-+ $(call if_changed,ctfa)
-+
-+targets += vmlinux.ctfa
-+
-+endif # KBUILD_EXTMOD
-+
-+endif # !CONFIG_CTF
-+
-diff --git a/scripts/Makefile.ctfa-toplevel b/scripts/Makefile.ctfa-toplevel
-new file mode 100644
-index 0000000000000..210bef3854e9b
---- /dev/null
-+++ b/scripts/Makefile.ctfa-toplevel
-@@ -0,0 +1,54 @@
-+# SPDX-License-Identifier: GPL-2.0-only
-+# ===========================================================================
-+# CTF rules for the top-level makefile only
-+# ===========================================================================
-+
-+KBUILD_CFLAGS += $(call cc-option,-gctf)
-+KBUILD_LDFLAGS += $(call ld-option, --ctf-variables)
-+
-+ifeq ($(KBUILD_EXTMOD),)
-+
-+# CTF generation for in-tree code (modules, built-in and not, and core kernel)
-+
-+# This contains all the object files that are built directly into the
-+# kernel (including built-in modules), for consumption by ctfarchive in
-+# Makefile.modfinal.
-+# This is made doubly annoying by the presence of '.o' files which are actually
-+# thin ar archives, and the need to support file(1) versions too old to
-+# recognize them as archives at all. (So we assume that everything that is notr
-+# an ELF object is an archive.)
-+ifeq ($(SRCARCH),x86)
-+.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),bzImage) FORCE
-+else
-+ifeq ($(SRCARCH),arm64)
-+.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),Image) FORCE
-+else
-+.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) FORCE
-+endif
-+endif
-+ @echo $(KBUILD_VMLINUX_OBJS) | \
-+ tr " " "\n" | grep "\.o$$" | xargs -r file | \
-+ grep ELF | cut -d: -f1 > .tmp_objects.builtin
-+ @for archive in $$(echo $(KBUILD_VMLINUX_OBJS) |\
-+ tr " " "\n" | xargs -r file | grep -v ELF | cut -d: -f1); do \
-+ $(AR) t "$$archive" >> .tmp_objects.builtin; \
-+ done
-+
-+ctf: vmlinux.ctfa
-+PHONY += ctf ctf_install
-+
-+# Making CTF needs the builtin files. We need to force everything to be
-+# built if not already done, since we need the .o files for the machinery
-+# above to work.
-+vmlinux.ctfa: KBUILD_BUILTIN := 1
-+vmlinux.ctfa: modules.builtin.objs .tmp_objects.builtin
-+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal vmlinux.ctfa
-+
-+ctf_install:
-+ $(Q)mkdir -p $(MODLIB)/kernel
-+ @ln -sf $(abspath $(srctree)) $(MODLIB)/source
-+ $(Q)cp -f $(objtree)/vmlinux.ctfa $(MODLIB)/kernel
-+
-+CLEAN_FILES += vmlinux.ctfa
-+
-+endif
-diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
-index 7f8ec77bf35c9..97b0ea2eee9d4 100644
---- a/scripts/Makefile.lib
-+++ b/scripts/Makefile.lib
-@@ -118,6 +118,8 @@ modname-multi = $(sort $(foreach m,$(multi-obj-ym),\
- __modname = $(or $(modname-multi),$(basetarget))
-
- modname = $(subst $(space),:,$(__modname))
-+modname-objs = $($(modname)-objs) $($(modname)-y) $($(modname)-Y)
-+modname-objs-prefixed = $(sort $(strip $(addprefix $(obj)/, $(modname-objs))))
- modfile = $(addprefix $(obj)/,$(__modname))
-
- # target with $(obj)/ and its suffix stripped
-@@ -131,7 +133,8 @@ name-fix = $(call stringify,$(call name-fix-token,$1))
- basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
- modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
- -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
--modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
-+modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile)) \
-+ -DKBUILD_MODOBJS=$(call stringify,$(modfile).o:$(subst $(space),|,$(modname-objs-prefixed)))
-
- _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
- $(filter-out $(ccflags-remove-y), \
-@@ -238,7 +241,7 @@ modkern_rustflags = \
-
- modkern_aflags = $(if $(part-of-module), \
- $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE), \
-- $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL))
-+ $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) $(modfile_flags))
-
- c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
- -include $(srctree)/include/linux/compiler_types.h \
-@@ -248,7 +251,7 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
- rust_flags = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg
-
- a_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
-- $(_a_flags) $(modkern_aflags)
-+ $(_a_flags) $(modkern_aflags) $(modname_flags)
-
- cpp_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
- $(_cpp_flags)
-diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
-index 3bec9043e4f38..06807e403d162 100644
---- a/scripts/Makefile.modfinal
-+++ b/scripts/Makefile.modfinal
-@@ -30,11 +30,16 @@ quiet_cmd_cc_o_c = CC [M] $@
- %.mod.o: %.mod.c FORCE
- $(call if_changed_dep,cc_o_c)
-
-+# for module-ctf-postlink
-+include $(srctree)/scripts/Makefile.ctfa
-+
- quiet_cmd_ld_ko_o = LD [M] $@
- cmd_ld_ko_o += \
- $(LD) -r $(KBUILD_LDFLAGS) \
- $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
-- -T scripts/module.lds -o $@ $(filter %.o, $^)
-+ -T scripts/module.lds $(LDFLAGS_$(modname)) -o $@.tmp \
-+ $(filter %.o, $^) && \
-+ $(call module-ctf-postlink,$@) \
-
- quiet_cmd_btf_ko = BTF [M] $@
- cmd_btf_ko = \
-diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
-index 0afd75472679f..e668469ce098c 100644
---- a/scripts/Makefile.modinst
-+++ b/scripts/Makefile.modinst
-@@ -30,10 +30,12 @@ $(MODLIB)/modules.order: modules.order FORCE
- quiet_cmd_install_modorder = INSTALL $@
- cmd_install_modorder = sed 's:^\(.*\)\.o$$:kernel/\1.ko:' $< > $@
-
--# Install modules.builtin(.modinfo) even when CONFIG_MODULES is disabled.
--install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo)
-+# Install modules.builtin(.modinfo,.ranges,.objs) even when CONFIG_MODULES is disabled.
-+install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.objs)
-
--$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo): $(MODLIB)/%: % FORCE
-+install-$(CONFIG_BUILTIN_MODULE_RANGES) += $(MODLIB)/modules.builtin.ranges
-+
-+$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.ranges modules.builtin.objs): $(MODLIB)/%: % FORCE
- $(call cmd,install)
-
- endif
-diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
-index 49946cb968440..7e8b703799c85 100644
---- a/scripts/Makefile.vmlinux
-+++ b/scripts/Makefile.vmlinux
-@@ -33,6 +33,24 @@ targets += vmlinux
- vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE
- +$(call if_changed_dep,link_vmlinux)
-
-+# module.builtin.ranges
-+# ---------------------------------------------------------------------------
-+ifdef CONFIG_BUILTIN_MODULE_RANGES
-+__default: modules.builtin.ranges
-+
-+quiet_cmd_modules_builtin_ranges = GEN $@
-+ cmd_modules_builtin_ranges = $(real-prereqs) > $@
-+
-+targets += modules.builtin.ranges
-+modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \
-+ modules.builtin vmlinux.map vmlinux.o.map FORCE
-+ $(call if_changed,modules_builtin_ranges)
-+
-+vmlinux.map: vmlinux
-+ @:
-+
-+endif
-+
- # Add FORCE to the prequisites of a target to force it to be always rebuilt.
- # ---------------------------------------------------------------------------
-
-diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
-index 6de297916ce68..48ba44ce3b64b 100644
---- a/scripts/Makefile.vmlinux_o
-+++ b/scripts/Makefile.vmlinux_o
-@@ -1,7 +1,7 @@
- # SPDX-License-Identifier: GPL-2.0-only
-
- PHONY := __default
--__default: vmlinux.o modules.builtin.modinfo modules.builtin
-+__default: vmlinux.o modules.builtin.modinfo modules.builtin modules.builtin.objs
-
- include include/config/auto.conf
- include $(srctree)/scripts/Kbuild.include
-@@ -27,6 +27,18 @@ ifdef CONFIG_LTO_CLANG
- initcalls-lds := .tmp_initcalls.lds
- endif
-
-+# Generate a linker script to delete CTF sections
-+# -----------------------------------------------
-+
-+quiet_cmd_gen_remove_ctf.lds = GEN $@
-+ cmd_gen_remove_ctf.lds = \
-+ $(LD) -r --verbose | awk -f $(real-prereqs) > $@
-+
-+.tmp_remove-ctf.lds: $(srctree)/scripts/remove-ctf-lds.awk FORCE
-+ $(call if_changed,gen_remove_ctf.lds)
-+
-+targets := .tmp_remove-ctf.lds
-+
- # objtool for vmlinux.o
- # ---------------------------------------------------------------------------
- #
-@@ -42,13 +54,18 @@ vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \
-
- objtool-args = $(vmlinux-objtool-args-y) --link
-
--# Link of vmlinux.o used for section mismatch analysis
-+# Link of vmlinux.o used for section mismatch analysis: we also strip the CTF
-+# section out at this stage, since ctfarchive gets it from the underlying object
-+# files and linking it further is a waste of time.
- # ---------------------------------------------------------------------------
-
-+vmlinux-o-ld-args-$(CONFIG_BUILTIN_MODULE_RANGES) += -Map=$@.map
-+
- quiet_cmd_ld_vmlinux.o = LD $@
- cmd_ld_vmlinux.o = \
- $(LD) ${KBUILD_LDFLAGS} -r -o $@ \
-- $(addprefix -T , $(initcalls-lds)) \
-+ $(vmlinux-o-ld-args-y) \
-+ $(addprefix -T , $(initcalls-lds)) -T .tmp_remove-ctf.lds \
- --whole-archive vmlinux.a --no-whole-archive \
- --start-group $(KBUILD_VMLINUX_LIBS) --end-group \
- $(cmd_objtool)
-@@ -58,7 +75,7 @@ define rule_ld_vmlinux.o
- $(call cmd,gen_objtooldep)
- endef
-
--vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
-+vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) .tmp_remove-ctf.lds FORCE
- $(call if_changed_rule,ld_vmlinux.o)
-
- targets += vmlinux.o
-@@ -87,6 +104,19 @@ targets += modules.builtin
- modules.builtin: modules.builtin.modinfo FORCE
- $(call if_changed,modules_builtin)
-
-+# module.builtin.objs
-+# ---------------------------------------------------------------------------
-+quiet_cmd_modules_builtin_objs = GEN $@
-+ cmd_modules_builtin_objs = \
-+ tr '\0' '\n' < $< | \
-+ sed -n 's/^[[:alnum:]:_]*\.objs=//p' | \
-+ tr ' ' '\n' | uniq | sed -e 's|:|: |' -e 's:|: :g' | \
-+ tr -s ' ' > $@
-+
-+targets += modules.builtin.objs
-+modules.builtin.objs: modules.builtin.modinfo FORCE
-+ $(call if_changed,modules_builtin_objs)
-+
- # Add FORCE to the prequisites of a target to force it to be always rebuilt.
- # ---------------------------------------------------------------------------
-
-diff --git a/scripts/ctf/.gitignore b/scripts/ctf/.gitignore
-new file mode 100644
-index 0000000000000..6a0eb1c3ceeab
---- /dev/null
-+++ b/scripts/ctf/.gitignore
-@@ -0,0 +1 @@
-+ctfarchive
-diff --git a/scripts/ctf/Makefile b/scripts/ctf/Makefile
-new file mode 100644
-index 0000000000000..3b83f93bb9f9a
---- /dev/null
-+++ b/scripts/ctf/Makefile
-@@ -0,0 +1,5 @@
-+ifdef CONFIG_CTF
-+hostprogs-always-y := ctfarchive
-+ctfarchive-objs := ctfarchive.o modules_builtin.o
-+HOSTLDLIBS_ctfarchive := -lctf
-+endif
-diff --git a/scripts/ctf/ctfarchive.c b/scripts/ctf/ctfarchive.c
-new file mode 100644
-index 0000000000000..92cc4912ed0ee
---- /dev/null
-+++ b/scripts/ctf/ctfarchive.c
-@@ -0,0 +1,413 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * ctfmerge.c: Read in CTF extracted from generated object files from a
-+ * specified directory and generate a CTF archive whose members are the
-+ * deduplicated CTF derived from those object files, split up by kernel
-+ * module.
-+ *
-+ * Copyright (c) 2019, 2023, Oracle and/or its affiliates.
-+ *
-+ * This program is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ */
-+
-+#define _GNU_SOURCE 1
-+#include <errno.h>
-+#include <stdio.h>
-+#include <stdlib.h>
-+#include <string.h>
-+#include <ctf-api.h>
-+#include "modules_builtin.h"
-+
-+static ctf_file_t *output;
-+
-+static int private_ctf_link_add_ctf(ctf_file_t *fp,
-+ const char *name)
-+{
-+#if !defined (CTF_LINK_FINAL)
-+ return ctf_link_add_ctf(fp, NULL, name);
-+#else
-+ /* Non-upstreamed, erroneously-broken API. */
-+ return ctf_link_add_ctf(fp, NULL, name, NULL, 0);
-+#endif
-+}
-+
-+/*
-+ * Add a file to the link.
-+ */
-+static void add_to_link(const char *fn)
-+{
-+ if (private_ctf_link_add_ctf(output, fn) < 0)
-+ {
-+ fprintf(stderr, "Cannot add CTF file %s: %s\n", fn,
-+ ctf_errmsg(ctf_errno(output)));
-+ exit(1);
-+ }
-+}
-+
-+struct from_to
-+{
-+ char *from;
-+ char *to;
-+};
-+
-+/*
-+ * The world's stupidest hash table of FROM -> TO.
-+ */
-+static struct from_to **from_tos[256];
-+static size_t alloc_from_tos[256];
-+static size_t num_from_tos[256];
-+
-+static unsigned char from_to_hash(const char *from)
-+{
-+ unsigned char hval = 0;
-+
-+ const char *p;
-+ for (p = from; *p; p++)
-+ hval += *p;
-+
-+ return hval;
-+}
-+
-+/*
-+ * Note that we will need to add a CU mapping later on.
-+ *
-+ * Present purely to work around a binutils bug that stops
-+ * ctf_link_add_cu_mapping() working right when called repeatedly
-+ * with the same FROM.
-+ */
-+static int add_cu_mapping(const char *from, const char *to)
-+{
-+ ssize_t i, j;
-+
-+ i = from_to_hash(from);
-+
-+ for (j = 0; j < num_from_tos[i]; j++)
-+ if (strcmp(from, from_tos[i][j]->from) == 0) {
-+ char *tmp;
-+
-+ free(from_tos[i][j]->to);
-+ tmp = strdup(to);
-+ if (!tmp)
-+ goto oom;
-+ from_tos[i][j]->to = tmp;
-+ return 0;
-+ }
-+
-+ if (num_from_tos[i] >= alloc_from_tos[i]) {
-+ struct from_to **tmp;
-+ if (alloc_from_tos[i] < 16)
-+ alloc_from_tos[i] = 16;
-+ else
-+ alloc_from_tos[i] *= 2;
-+
-+ tmp = realloc(from_tos[i], alloc_from_tos[i] * sizeof(struct from_to *));
-+ if (!tmp)
-+ goto oom;
-+
-+ from_tos[i] = tmp;
-+ }
-+
-+ j = num_from_tos[i];
-+ from_tos[i][j] = malloc(sizeof(struct from_to));
-+ if (from_tos[i][j] == NULL)
-+ goto oom;
-+ from_tos[i][j]->from = strdup(from);
-+ from_tos[i][j]->to = strdup(to);
-+ if (!from_tos[i][j]->from || !from_tos[i][j]->to)
-+ goto oom;
-+ num_from_tos[i]++;
-+
-+ return 0;
-+ oom:
-+ fprintf(stderr,
-+ "out of memory in add_cu_mapping\n");
-+ exit(1);
-+}
-+
-+/*
-+ * Finally tell binutils to add all the CU mappings, with duplicate FROMs
-+ * replaced with the most recent one.
-+ */
-+static void commit_cu_mappings(void)
-+{
-+ ssize_t i, j;
-+
-+ for (i = 0; i < 256; i++)
-+ for (j = 0; j < num_from_tos[i]; j++)
-+ ctf_link_add_cu_mapping(output, from_tos[i][j]->from,
-+ from_tos[i][j]->to);
-+}
-+
-+/*
-+ * Add a CU mapping to the link.
-+ *
-+ * CU mappings for built-in modules are added by suck_in_modules, below: here,
-+ * we only want to add mappings for names ending in '.ko.ctf', i.e. external
-+ * modules, which appear only in the filelist (since they are not built-in).
-+ * The pathnames are stripped off because modules don't have any, and hyphens
-+ * are translated into underscores.
-+ */
-+static void add_cu_mappings(const char *fn)
-+{
-+ const char *last_slash;
-+ const char *modname = fn;
-+ char *dynmodname = NULL;
-+ char *dash;
-+ size_t n;
-+
-+ last_slash = strrchr(modname, '/');
-+ if (last_slash)
-+ last_slash++;
-+ else
-+ last_slash = modname;
-+ modname = last_slash;
-+ if (strchr(modname, '-') != NULL)
-+ {
-+ dynmodname = strdup(last_slash);
-+ dash = dynmodname;
-+ while (dash != NULL) {
-+ dash = strchr(dash, '-');
-+ if (dash != NULL)
-+ *dash = '_';
-+ }
-+ modname = dynmodname;
-+ }
-+
-+ n = strlen(modname);
-+ if (strcmp(modname + n - strlen(".ko.ctf"), ".ko.ctf") == 0) {
-+ char *mod;
-+
-+ n -= strlen(".ko.ctf");
-+ mod = strndup(modname, n);
-+ add_cu_mapping(fn, mod);
-+ free(mod);
-+ }
-+ free(dynmodname);
-+}
-+
-+/*
-+ * Add the passed names as mappings to "vmlinux".
-+ */
-+static void add_builtins(const char *fn)
-+{
-+ if (add_cu_mapping(fn, "vmlinux") < 0)
-+ {
-+ fprintf(stderr, "Cannot add CTF CU mapping from %s to \"vmlinux\"\n",
-+ ctf_errmsg(ctf_errno(output)));
-+ exit(1);
-+ }
-+}
-+
-+/*
-+ * Do something with a file, line by line.
-+ */
-+static void suck_in_lines(const char *filename, void (*func)(const char *line))
-+{
-+ FILE *f;
-+ char *line = NULL;
-+ size_t line_size = 0;
-+
-+ f = fopen(filename, "r");
-+ if (f == NULL) {
-+ fprintf(stderr, "Cannot open %s: %s\n", filename,
-+ strerror(errno));
-+ exit(1);
-+ }
-+
-+ while (getline(&line, &line_size, f) >= 0) {
-+ size_t len = strlen(line);
-+
-+ if (len == 0)
-+ continue;
-+
-+ if (line[len-1] == '\n')
-+ line[len-1] = '\0';
-+
-+ func(line);
-+ }
-+ free(line);
-+
-+ if (ferror(f)) {
-+ fprintf(stderr, "Error reading from %s: %s\n", filename,
-+ strerror(errno));
-+ exit(1);
-+ }
-+
-+ fclose(f);
-+}
-+
-+/*
-+ * Pull in modules.builtin.objs and turn it into CU mappings.
-+ */
-+static void suck_in_modules(const char *modules_builtin_name)
-+{
-+ struct modules_builtin_iter *i;
-+ char *module_name = NULL;
-+ char **paths;
-+
-+ i = modules_builtin_iter_new(modules_builtin_name);
-+ if (i == NULL) {
-+ fprintf(stderr, "Cannot iterate over builtin module file.\n");
-+ exit(1);
-+ }
-+
-+ while ((paths = modules_builtin_iter_next(i, &module_name)) != NULL) {
-+ size_t j;
-+
-+ for (j = 0; paths[j] != NULL; j++) {
-+ char *alloc = NULL;
-+ char *path = paths[j];
-+ /*
-+ * If the name doesn't start in ./, add it, to match the names
-+ * passed to add_builtins.
-+ */
-+ if (strncmp(paths[j], "./", 2) != 0) {
-+ char *p;
-+ if ((alloc = malloc(strlen(paths[j]) + 3)) == NULL) {
-+ fprintf(stderr, "Cannot allocate memory for "
-+ "builtin module object name %s.\n",
-+ paths[j]);
-+ exit(1);
-+ }
-+ p = alloc;
-+ p = stpcpy(p, "./");
-+ p = stpcpy(p, paths[j]);
-+ path = alloc;
-+ }
-+ if (add_cu_mapping(path, module_name) < 0) {
-+ fprintf(stderr, "Cannot add path -> module mapping for "
-+ "%s -> %s: %s\n", path, module_name,
-+ ctf_errmsg(ctf_errno(output)));
-+ exit(1);
-+ }
-+ free (alloc);
-+ }
-+ free(paths);
-+ }
-+ free(module_name);
-+ modules_builtin_iter_free(i);
-+}
-+
-+/*
-+ * Strip the leading .ctf. off all the module names: transform the default name
-+ * from _CTF_SECTION into shared_ctf, and chop any trailing .ctf off (since that
-+ * derives from the intermediate file used to keep the CTF out of the final
-+ * module).
-+ */
-+static char *transform_module_names(ctf_file_t *fp __attribute__((__unused__)),
-+ const char *name,
-+ void *arg __attribute__((__unused__)))
-+{
-+ if (strcmp(name, ".ctf") == 0)
-+ return strdup("shared_ctf");
-+
-+ if (strncmp(name, ".ctf", 4) == 0) {
-+ size_t n = strlen (name);
-+ if (strcmp(name + n - 4, ".ctf") == 0)
-+ n -= 4;
-+ return strndup(name + 4, n - 4);
-+ }
-+ return NULL;
-+}
-+
-+int main(int argc, char *argv[])
-+{
-+ int err;
-+ const char *output_file;
-+ unsigned char *file_data = NULL;
-+ size_t file_size;
-+ FILE *fp;
-+
-+ if (argc != 5) {
-+ fprintf(stderr, "Syntax: ctfarchive output-file objects.builtin modules.builtin\n");
-+ fprintf(stderr, " filelist\n");
-+ exit(1);
-+ }
-+
-+ output_file = argv[1];
-+
-+ /*
-+ * First pull in the input files and add them to the link.
-+ */
-+
-+ output = ctf_create(&err);
-+ if (!output) {
-+ fprintf(stderr, "Cannot create output CTF archive: %s\n",
-+ ctf_errmsg(err));
-+ return 1;
-+ }
-+
-+ suck_in_lines(argv[4], add_to_link);
-+
-+ /*
-+ * Make sure that, even if all their types are shared, all modules have
-+ * a ctf member that can be used as a child of the shared CTF.
-+ */
-+ suck_in_lines(argv[4], add_cu_mappings);
-+
-+ /*
-+ * Then pull in the builtin objects list and add them as
-+ * mappings to "vmlinux".
-+ */
-+
-+ suck_in_lines(argv[2], add_builtins);
-+
-+ /*
-+ * Finally, pull in the object -> module mapping and add it
-+ * as appropriate mappings.
-+ */
-+ suck_in_modules(argv[3]);
-+
-+ /*
-+ * Commit the added CU mappings.
-+ */
-+ commit_cu_mappings();
-+
-+ /*
-+ * Arrange to fix up the module names.
-+ */
-+ ctf_link_set_memb_name_changer(output, transform_module_names, NULL);
-+
-+ /*
-+ * Do the link.
-+ */
-+ if (ctf_link(output, CTF_LINK_SHARE_DUPLICATED |
-+ CTF_LINK_EMPTY_CU_MAPPINGS) < 0)
-+ goto ctf_err;
-+
-+ /*
-+ * Write the output.
-+ */
-+
-+ file_data = ctf_link_write(output, &file_size, 4096);
-+ if (!file_data)
-+ goto ctf_err;
-+
-+ fp = fopen(output_file, "w");
-+ if (!fp)
-+ goto err;
-+
-+ while ((err = fwrite(file_data, file_size, 1, fp)) == 0);
-+ if (ferror(fp)) {
-+ errno = ferror(fp);
-+ goto err;
-+ }
-+ if (fclose(fp) < 0)
-+ goto err;
-+ free(file_data);
-+ ctf_file_close(output);
-+
-+ return 0;
-+err:
-+ free(file_data);
-+ fprintf(stderr, "Cannot create output CTF archive: %s\n",
-+ strerror(errno));
-+ return 1;
-+ctf_err:
-+ fprintf(stderr, "Cannot create output CTF archive: %s\n",
-+ ctf_errmsg(ctf_errno(output)));
-+ return 1;
-+}
-diff --git a/scripts/ctf/modules_builtin.c b/scripts/ctf/modules_builtin.c
-new file mode 100644
-index 0000000000000..10af2bbc80e0c
---- /dev/null
-+++ b/scripts/ctf/modules_builtin.c
-@@ -0,0 +1,2 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+#include "../modules_builtin.c"
-diff --git a/scripts/ctf/modules_builtin.h b/scripts/ctf/modules_builtin.h
-new file mode 100644
-index 0000000000000..5e0299e5600c2
---- /dev/null
-+++ b/scripts/ctf/modules_builtin.h
-@@ -0,0 +1,2 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+#include "../modules_builtin.h"
-diff --git a/scripts/generate_builtin_ranges.awk b/scripts/generate_builtin_ranges.awk
-new file mode 100755
-index 0000000000000..51ae0458ffbdd
---- /dev/null
-+++ b/scripts/generate_builtin_ranges.awk
-@@ -0,0 +1,516 @@
-+#!/usr/bin/gawk -f
-+# SPDX-License-Identifier: GPL-2.0
-+# generate_builtin_ranges.awk: Generate address range data for builtin modules
-+# Written by Kris Van Hees <kris.van.hees@oracle.com>
-+#
-+# Usage: generate_builtin_ranges.awk modules.builtin vmlinux.map \
-+# vmlinux.o.map [ <build-dir> ] > modules.builtin.ranges
-+#
-+
-+# Return the module name(s) (if any) associated with the given object.
-+#
-+# If we have seen this object before, return information from the cache.
-+# Otherwise, retrieve it from the corresponding .cmd file.
-+#
-+function get_module_info(fn, mod, obj, s) {
-+ if (fn in omod)
-+ return omod[fn];
-+
-+ if (match(fn, /\/[^/]+$/) == 0)
-+ return "";
-+
-+ obj = fn;
-+ mod = "";
-+ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
-+ if (getline s <fn == 1) {
-+ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
-+ mod = substr(s, RSTART + 16, RLENGTH - 16);
-+ gsub(/['"]/, "", mod);
-+ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
-+ mod = substr(s, RSTART + 13, RLENGTH - 13);
-+ }
-+ close(fn);
-+
-+ # A single module (common case) also reflects objects that are not part
-+ # of a module. Some of those objects have names that are also a module
-+ # name (e.g. core). We check the associated module file name, and if
-+ # they do not match, the object is not part of a module.
-+ if (mod !~ / /) {
-+ if (!(mod in mods))
-+ mod = "";
-+ }
-+
-+ gsub(/([^/ ]*\/)+/, "", mod);
-+ gsub(/-/, "_", mod);
-+
-+ # At this point, mod is a single (valid) module name, or a list of
-+ # module names (that do not need validation).
-+ omod[obj] = mod;
-+
-+ return mod;
-+}
-+
-+# Update the ranges entry for the given module 'mod' in section 'osect'.
-+#
-+# We use a modified absolute start address (soff + base) as index because we
-+# may need to insert an anchor record later that must be at the start of the
-+# section data, and the first module may very well start at the same address.
-+# So, we use (addr << 1) + 1 to allow a possible anchor record to be placed at
-+# (addr << 1). This is safe because the index is only used to sort the entries
-+# before writing them out.
-+#
-+function update_entry(osect, mod, soff, eoff, sect, idx) {
-+ sect = sect_in[osect];
-+ idx = (soff + sect_base[osect]) * 2 + 1;
-+ entries[idx] = sprintf("%s %08x-%08x %s", sect, soff, eoff, mod);
-+ count[sect]++;
-+}
-+
-+# Determine the kernel build directory to use (default is .).
-+#
-+BEGIN {
-+ if (ARGC > 4) {
-+ kdir = ARGV[ARGC - 1];
-+ ARGV[ARGC - 1] = "";
-+ } else
-+ kdir = ".";
-+}
-+
-+# (1) Build a lookup map of built-in module names.
-+#
-+# The first file argument is used as input (modules.builtin).
-+#
-+# Lines will be like:
-+# kernel/crypto/lzo-rle.ko
-+# and we record the object name "crypto/lzo-rle".
-+#
-+ARGIND == 1 {
-+ sub(/kernel\//, ""); # strip off "kernel/" prefix
-+ sub(/\.ko$/, ""); # strip off .ko suffix
-+
-+ mods[$1] = 1;
-+ next;
-+}
-+
-+# (2) Collect address information for each section.
-+#
-+# The second file argument is used as input (vmlinux.map).
-+#
-+# We collect the base address of the section in order to convert all addresses
-+# in the section into offset values.
-+#
-+# We collect the address of the anchor (or first symbol in the section if there
-+# is no explicit anchor) to allow users of the range data to calculate address
-+# ranges based on the actual load address of the section in the running kernel.
-+#
-+# We collect the start address of any sub-section (section included in the top
-+# level section being processed). This is needed when the final linking was
-+# done using vmlinux.a because then the list of objects contained in each
-+# section is to be obtained from vmlinux.o.map. The offset of the sub-section
-+# is recorded here, to be used as an addend when processing vmlinux.o.map
-+# later.
-+#
-+
-+# Both GNU ld and LLVM lld linker map format are supported by converting LLVM
-+# lld linker map records into equivalent GNU ld linker map records.
-+#
-+# The first record of the vmlinux.map file provides enough information to know
-+# which format we are dealing with.
-+#
-+ARGIND == 2 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
-+ map_is_lld = 1;
-+ if (dbg)
-+ printf "NOTE: %s uses LLVM lld linker map format\n", FILENAME >"/dev/stderr";
-+ next;
-+}
-+
-+# (LLD) Convert a section record fronm lld format to ld format.
-+#
-+# lld: ffffffff82c00000 2c00000 2493c0 8192 .data
-+# ->
-+# ld: .data 0xffffffff82c00000 0x2493c0 load address 0x0000000002c00000
-+#
-+ARGIND == 2 && map_is_lld && NF == 5 && /[0-9] [^ ]+$/ {
-+ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
-+}
-+
-+# (LLD) Convert an anchor record from lld format to ld format.
-+#
-+# lld: ffffffff81000000 1000000 0 1 _text = .
-+# ->
-+# ld: 0xffffffff81000000 _text = .
-+#
-+ARGIND == 2 && map_is_lld && !anchor && NF == 7 && raw_addr == "0x"$1 && $6 == "=" && $7 == "." {
-+ $0 = " 0x"$1 " " $5 " = .";
-+}
-+
-+# (LLD) Convert an object record from lld format to ld format.
-+#
-+# lld: 11480 11480 1f07 16 vmlinux.a(arch/x86/events/amd/uncore.o):(.text)
-+# ->
-+# ld: .text 0x0000000000011480 0x1f07 arch/x86/events/amd/uncore.o
-+#
-+ARGIND == 2 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
-+ gsub(/\)/, "");
-+ sub(/ vmlinux\.a\(/, " ");
-+ sub(/:\(/, " ");
-+ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
-+}
-+
-+# (LLD) Convert a symbol record from lld format to ld format.
-+#
-+# We only care about these while processing a section for which no anchor has
-+# been determined yet.
-+#
-+# lld: ffffffff82a859a4 2a859a4 0 1 btf_ksym_iter_id
-+# ->
-+# ld: 0xffffffff82a859a4 btf_ksym_iter_id
-+#
-+ARGIND == 2 && map_is_lld && sect && !anchor && NF == 5 && $5 ~ /^[_A-Za-z][_A-Za-z0-9]*$/ {
-+ $0 = " 0x"$1 " " $5;
-+}
-+
-+# (LLD) We do not need any other ldd linker map records.
-+#
-+ARGIND == 2 && map_is_lld && /^[0-9a-f]{16} / {
-+ next;
-+}
-+
-+# (LD) Section records with just the section name at the start of the line
-+# need to have the next line pulled in to determine whether it is a
-+# loadable section. If it is, the next line will contains a hex value
-+# as first and second items.
-+#
-+ARGIND == 2 && !map_is_lld && NF == 1 && /^[^ ]/ {
-+ s = $0;
-+ getline;
-+ if ($1 !~ /^0x/ || $2 !~ /^0x/)
-+ next;
-+
-+ $0 = s " " $0;
-+}
-+
-+# (LD) Object records with just the section name denote records with a long
-+# section name for which the remainder of the record can be found on the
-+# next line.
-+#
-+# (This is also needed for vmlinux.o.map, when used.)
-+#
-+ARGIND >= 2 && !map_is_lld && NF == 1 && /^ [^ \*]/ {
-+ s = $0;
-+ getline;
-+ $0 = s " " $0;
-+}
-+
-+# Beginning a new section - done with the previous one (if any).
-+#
-+ARGIND == 2 && /^[^ ]/ {
-+ sect = 0;
-+}
-+
-+# Process a loadable section (we only care about .-sections).
-+#
-+# Record the section name and its base address.
-+# We also record the raw (non-stripped) address of the section because it can
-+# be used to identify an anchor record.
-+#
-+# Note:
-+# Since some AWK implementations cannot handle large integers, we strip off the
-+# first 4 hex digits from the address. This is safe because the kernel space
-+# is not large enough for addresses to extend into those digits. The portion
-+# to strip off is stored in addr_prefix as a regexp, so further clauses can
-+# perform a simple substitution to do the address stripping.
-+#
-+ARGIND == 2 && /^\./ {
-+ # Explicitly ignore a few sections that are not relevant here.
-+ if ($1 ~ /^\.orc_/ || $1 ~ /_sites$/ || $1 ~ /\.percpu/)
-+ next;
-+
-+ # Sections with a 0-address can be ignored as well.
-+ if ($2 ~ /^0x0+$/)
-+ next;
-+
-+ raw_addr = $2;
-+ addr_prefix = "^" substr($2, 1, 6);
-+ base = $2;
-+ sub(addr_prefix, "0x", base);
-+ base = strtonum(base);
-+ sect = $1;
-+ anchor = 0;
-+ sect_base[sect] = base;
-+ sect_size[sect] = strtonum($3);
-+
-+ if (dbg)
-+ printf "[%s] BASE %016x\n", sect, base >"/dev/stderr";
-+
-+ next;
-+}
-+
-+# If we are not in a section we care about, we ignore the record.
-+#
-+ARGIND == 2 && !sect {
-+ next;
-+}
-+
-+# Record the first anchor symbol for the current section.
-+#
-+# An anchor record for the section bears the same raw address as the section
-+# record.
-+#
-+ARGIND == 2 && !anchor && NF == 4 && raw_addr == $1 && $3 == "=" && $4 == "." {
-+ anchor = sprintf("%s %08x-%08x = %s", sect, 0, 0, $2);
-+ sect_anchor[sect] = anchor;
-+
-+ if (dbg)
-+ printf "[%s] ANCHOR %016x = %s (.)\n", sect, 0, $2 >"/dev/stderr";
-+
-+ next;
-+}
-+
-+# If no anchor record was found for the current section, use the first symbol
-+# in the section as anchor.
-+#
-+ARGIND == 2 && !anchor && NF == 2 && $1 ~ /^0x/ && $2 !~ /^0x/ {
-+ addr = $1;
-+ sub(addr_prefix, "0x", addr);
-+ addr = strtonum(addr) - base;
-+ anchor = sprintf("%s %08x-%08x = %s", sect, addr, addr, $2);
-+ sect_anchor[sect] = anchor;
-+
-+ if (dbg)
-+ printf "[%s] ANCHOR %016x = %s\n", sect, addr, $2 >"/dev/stderr";
-+
-+ next;
-+}
-+
-+# The first occurrence of a section name in an object record establishes the
-+# addend (often 0) for that section. This information is needed to handle
-+# sections that get combined in the final linking of vmlinux (e.g. .head.text
-+# getting included at the start of .text).
-+#
-+# If the section does not have a base yet, use the base of the encapsulating
-+# section.
-+#
-+ARGIND == 2 && sect && NF == 4 && /^ [^ \*]/ && !($1 in sect_addend) {
-+ if (!($1 in sect_base)) {
-+ sect_base[$1] = base;
-+
-+ if (dbg)
-+ printf "[%s] BASE %016x\n", $1, base >"/dev/stderr";
-+ }
-+
-+ addr = $2;
-+ sub(addr_prefix, "0x", addr);
-+ addr = strtonum(addr);
-+ sect_addend[$1] = addr - sect_base[$1];
-+ sect_in[$1] = sect;
-+
-+ if (dbg)
-+ printf "[%s] ADDEND %016x - %016x = %016x\n", $1, addr, base, sect_addend[$1] >"/dev/stderr";
-+
-+ # If the object is vmlinux.o then we will need vmlinux.o.map to get the
-+ # actual offsets of objects.
-+ if ($4 == "vmlinux.o")
-+ need_o_map = 1;
-+}
-+
-+# (3) Collect offset ranges (relative to the section base address) for built-in
-+# modules.
-+#
-+# If the final link was done using the actual objects, vmlinux.map contains all
-+# the information we need (see section (3a)).
-+# If linking was done using vmlinux.a as intermediary, we will need to process
-+# vmlinux.o.map (see section (3b)).
-+
-+# (3a) Determine offset range info using vmlinux.map.
-+#
-+# Since we are already processing vmlinux.map, the top level section that is
-+# being processed is already known. If we do not have a base address for it,
-+# we do not need to process records for it.
-+#
-+# Given the object name, we determine the module(s) (if any) that the current
-+# object is associated with.
-+#
-+# If we were already processing objects for a (list of) module(s):
-+# - If the current object belongs to the same module(s), update the range data
-+# to include the current object.
-+# - Otherwise, ensure that the end offset of the range is valid.
-+#
-+# If the current object does not belong to a built-in module, ignore it.
-+#
-+# If it does, we add a new built-in module offset range record.
-+#
-+ARGIND == 2 && !need_o_map && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
-+ if (!(sect in sect_base))
-+ next;
-+
-+ # Turn the address into an offset from the section base.
-+ soff = $2;
-+ sub(addr_prefix, "0x", soff);
-+ soff = strtonum(soff) - sect_base[sect];
-+ eoff = soff + strtonum($3);
-+
-+ # Determine which (if any) built-in modules the object belongs to.
-+ mod = get_module_info($4);
-+
-+ # If we are processing a built-in module:
-+ # - If the current object is within the same module, we update its
-+ # entry by extending the range and move on
-+ # - Otherwise:
-+ # + If we are still processing within the same main section, we
-+ # validate the end offset against the start offset of the
-+ # current object (e.g. .rodata.str1.[18] objects are often
-+ # listed with an incorrect size in the linker map)
-+ # + Otherwise, we validate the end offset against the section
-+ # size
-+ if (mod_name) {
-+ if (mod == mod_name) {
-+ mod_eoff = eoff;
-+ update_entry(mod_sect, mod_name, mod_soff, eoff);
-+
-+ next;
-+ } else if (sect == sect_in[mod_sect]) {
-+ if (mod_eoff > soff)
-+ update_entry(mod_sect, mod_name, mod_soff, soff);
-+ } else {
-+ v = sect_size[sect_in[mod_sect]];
-+ if (mod_eoff > v)
-+ update_entry(mod_sect, mod_name, mod_soff, v);
-+ }
-+ }
-+
-+ mod_name = mod;
-+
-+ # If we encountered an object that is not part of a built-in module, we
-+ # do not need to record any data.
-+ if (!mod)
-+ next;
-+
-+ # At this point, we encountered the start of a new built-in module.
-+ mod_name = mod;
-+ mod_soff = soff;
-+ mod_eoff = eoff;
-+ mod_sect = $1;
-+ update_entry($1, mod, soff, mod_eoff);
-+
-+ next;
-+}
-+
-+# If we do not need to parse the vmlinux.o.map file, we are done.
-+#
-+ARGIND == 3 && !need_o_map {
-+ if (dbg)
-+ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
-+ exit;
-+}
-+
-+# (3) Collect offset ranges (relative to the section base address) for built-in
-+# modules.
-+#
-+
-+# (LLD) Convert an object record from lld format to ld format.
-+#
-+ARGIND == 3 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
-+ gsub(/\)/, "");
-+ sub(/:\(/, " ");
-+
-+ sect = $6;
-+ if (!(sect in sect_addend))
-+ next;
-+
-+ sub(/ vmlinux\.a\(/, " ");
-+ $0 = " "sect " 0x"$1 " 0x"$3 " " $5;
-+}
-+
-+# (3b) Determine offset range info using vmlinux.o.map.
-+#
-+# If we do not know an addend for the object's section, we are interested in
-+# anything within that section.
-+#
-+# Determine the top-level section that the object's section was included in
-+# during the final link. This is the section name offset range data will be
-+# associated with for this object.
-+#
-+# The remainder of the processing of the current object record follows the
-+# procedure outlined in (3a).
-+#
-+ARGIND == 3 && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
-+ osect = $1;
-+ if (!(osect in sect_addend))
-+ next;
-+
-+ # We need to work with the main section.
-+ sect = sect_in[osect];
-+
-+ # Turn the address into an offset from the section base.
-+ soff = $2;
-+ sub(addr_prefix, "0x", soff);
-+ soff = strtonum(soff) + sect_addend[osect];
-+ eoff = soff + strtonum($3);
-+
-+ # Determine which (if any) built-in modules the object belongs to.
-+ mod = get_module_info($4);
-+
-+ # If we are processing a built-in module:
-+ # - If the current object is within the same module, we update its
-+ # entry by extending the range and move on
-+ # - Otherwise:
-+ # + If we are still processing within the same main section, we
-+ # validate the end offset against the start offset of the
-+ # current object (e.g. .rodata.str1.[18] objects are often
-+ # listed with an incorrect size in the linker map)
-+ # + Otherwise, we validate the end offset against the section
-+ # size
-+ if (mod_name) {
-+ if (mod == mod_name) {
-+ mod_eoff = eoff;
-+ update_entry(mod_sect, mod_name, mod_soff, eoff);
-+
-+ next;
-+ } else if (sect == sect_in[mod_sect]) {
-+ if (mod_eoff > soff)
-+ update_entry(mod_sect, mod_name, mod_soff, soff);
-+ } else {
-+ v = sect_size[sect_in[mod_sect]];
-+ if (mod_eoff > v)
-+ update_entry(mod_sect, mod_name, mod_soff, v);
-+ }
-+ }
-+
-+ mod_name = mod;
-+
-+ # If we encountered an object that is not part of a built-in module, we
-+ # do not need to record any data.
-+ if (!mod)
-+ next;
-+
-+ # At this point, we encountered the start of a new built-in module.
-+ mod_name = mod;
-+ mod_soff = soff;
-+ mod_eoff = eoff;
-+ mod_sect = osect;
-+ update_entry(osect, mod, soff, mod_eoff);
-+
-+ next;
-+}
-+
-+# (4) Generate the output.
-+#
-+# Anchor records are added for each section that contains offset range data
-+# records. They are added at an adjusted section base address (base << 1) to
-+# ensure they come first in the second records (see update_entry() above for
-+# more information).
-+#
-+# All entries are sorted by (adjusted) address to ensure that the output can be
-+# parsed in strict ascending address order.
-+#
-+END {
-+ for (sect in count) {
-+ if (sect in sect_anchor)
-+ entries[sect_base[sect] * 2] = sect_anchor[sect];
-+ }
-+
-+ n = asorti(entries, indices);
-+ for (i = 1; i <= n; i++)
-+ print entries[indices[i]];
-+}
-diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
-index f48d72d22dc2a..d7e6cd7781256 100644
---- a/scripts/mod/modpost.c
-+++ b/scripts/mod/modpost.c
-@@ -733,6 +733,7 @@ static const char *const section_white_list[] =
- ".comment*",
- ".debug*",
- ".zdebug*", /* Compressed debug sections. */
-+ ".ctf", /* Type info */
- ".GCC.command.line", /* record-gcc-switches */
- ".mdebug*", /* alpha, score, mips etc. */
- ".pdr", /* alpha, score, mips etc. */
-diff --git a/scripts/modules_builtin.c b/scripts/modules_builtin.c
-new file mode 100644
-index 0000000000000..df52932a4417b
---- /dev/null
-+++ b/scripts/modules_builtin.c
-@@ -0,0 +1,200 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * A simple modules_builtin reader.
-+ *
-+ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
-+ *
-+ * This program is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ */
-+
-+#include <errno.h>
-+#include <stdio.h>
-+#include <stdlib.h>
-+#include <string.h>
-+
-+#include "modules_builtin.h"
-+
-+/*
-+ * Read a modules.builtin.objs file and translate it into a stream of
-+ * name / module-name pairs.
-+ */
-+
-+/*
-+ * Construct a modules.builtin.objs iterator.
-+ */
-+struct modules_builtin_iter *
-+modules_builtin_iter_new(const char *modules_builtin_file)
-+{
-+ struct modules_builtin_iter *i;
-+
-+ i = calloc(1, sizeof(struct modules_builtin_iter));
-+ if (i == NULL)
-+ return NULL;
-+
-+ i->f = fopen(modules_builtin_file, "r");
-+
-+ if (i->f == NULL) {
-+ fprintf(stderr, "Cannot open builtin module file %s: %s\n",
-+ modules_builtin_file, strerror(errno));
-+ return NULL;
-+ }
-+
-+ return i;
-+}
-+
-+/*
-+ * Iterate, returning a new null-terminated array of object file names, and a
-+ * new dynamically-allocated module name. (The module name passed in is freed.)
-+ *
-+ * The array of object file names should be freed by the caller: the strings it
-+ * points to are owned by the iterator, and should not be freed.
-+ */
-+
-+char ** __attribute__((__nonnull__))
-+modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name)
-+{
-+ size_t npaths = 1;
-+ char **module_paths;
-+ char *last_slash;
-+ char *last_dot;
-+ char *trailing_linefeed;
-+ char *object_name = i->line;
-+ char *dash;
-+ int composite = 0;
-+
-+ /*
-+ * Read in all module entries, computing the suffixless, pathless name
-+ * of the module and building the next arrayful of object file names for
-+ * return.
-+ *
-+ * Modules can consist of multiple files: in this case, the portion
-+ * before the colon is the path to the module (as before): the portion
-+ * after the colon is a space-separated list of files that should be
-+ * considered part of this module. In this case, the portion before the
-+ * name is an "object file" that does not actually exist: it is merged
-+ * into built-in.a without ever being written out.
-+ *
-+ * All module names have - translated to _, to match what is done to the
-+ * names of the same things when built as modules.
-+ */
-+
-+ /*
-+ * Reinvocation of exhausted iterator. Return NULL, once.
-+ */
-+retry:
-+ if (getline(&i->line, &i->line_size, i->f) < 0) {
-+ if (ferror(i->f)) {
-+ fprintf(stderr, "Error reading from modules_builtin file:"
-+ " %s\n", strerror(errno));
-+ exit(1);
-+ }
-+ rewind(i->f);
-+ return NULL;
-+ }
-+
-+ if (i->line[0] == '\0')
-+ goto retry;
-+
-+ trailing_linefeed = strchr(i->line, '\n');
-+ if (trailing_linefeed != NULL)
-+ *trailing_linefeed = '\0';
-+
-+ /*
-+ * Slice the line in two at the colon, if any. If there is anything
-+ * past the ': ', this is a composite module. (We allow for no colon
-+ * for robustness, even though one should always be present.)
-+ */
-+ if (strchr(i->line, ':') != NULL) {
-+ char *name_start;
-+
-+ object_name = strchr(i->line, ':');
-+ *object_name = '\0';
-+ object_name++;
-+ name_start = object_name + strspn(object_name, " \n");
-+ if (*name_start != '\0') {
-+ composite = 1;
-+ object_name = name_start;
-+ }
-+ }
-+
-+ /*
-+ * Figure out the module name.
-+ */
-+ last_slash = strrchr(i->line, '/');
-+ last_slash = (!last_slash) ? i->line :
-+ last_slash + 1;
-+ free(*module_name);
-+ *module_name = strdup(last_slash);
-+ dash = *module_name;
-+
-+ while (dash != NULL) {
-+ dash = strchr(dash, '-');
-+ if (dash != NULL)
-+ *dash = '_';
-+ }
-+
-+ last_dot = strrchr(*module_name, '.');
-+ if (last_dot != NULL)
-+ *last_dot = '\0';
-+
-+ /*
-+ * Multifile separator? Object file names explicitly stated:
-+ * slice them up and shuffle them in.
-+ *
-+ * The array size may be an overestimate if any object file
-+ * names start or end with spaces (very unlikely) but cannot be
-+ * an underestimate. (Check for it anyway.)
-+ */
-+ if (composite) {
-+ char *one_object;
-+
-+ for (npaths = 0, one_object = object_name;
-+ one_object != NULL;
-+ npaths++, one_object = strchr(one_object + 1, ' '));
-+ }
-+
-+ module_paths = malloc((npaths + 1) * sizeof(char *));
-+ if (!module_paths) {
-+ fprintf(stderr, "%s: out of memory on module %s\n", __func__,
-+ *module_name);
-+ exit(1);
-+ }
-+
-+ if (composite) {
-+ char *one_object;
-+ size_t i = 0;
-+
-+ while ((one_object = strsep(&object_name, " ")) != NULL) {
-+ if (i >= npaths) {
-+ fprintf(stderr, "%s: num_objs overflow on module "
-+ "%s: this is a bug.\n", __func__,
-+ *module_name);
-+ exit(1);
-+ }
-+
-+ module_paths[i++] = one_object;
-+ }
-+ } else
-+ module_paths[0] = i->line; /* untransformed module name */
-+
-+ module_paths[npaths] = NULL;
-+
-+ return module_paths;
-+}
-+
-+/*
-+ * Free an iterator. Can be called while iteration is underway, so even
-+ * state that is freed at the end of iteration must be freed here too.
-+ */
-+void
-+modules_builtin_iter_free(struct modules_builtin_iter *i)
-+{
-+ if (i == NULL)
-+ return;
-+ fclose(i->f);
-+ free(i->line);
-+ free(i);
-+}
-diff --git a/scripts/modules_builtin.h b/scripts/modules_builtin.h
-new file mode 100644
-index 0000000000000..5138792b42ef0
---- /dev/null
-+++ b/scripts/modules_builtin.h
-@@ -0,0 +1,48 @@
-+/* SPDX-License-Identifier: GPL-2.0 */
-+/*
-+ * A simple modules.builtin.objs reader.
-+ *
-+ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
-+ *
-+ * This program is free software; you can redistribute it and/or modify
-+ * it under the terms of the GNU General Public License as published by
-+ * the Free Software Foundation; either version 2 of the License, or
-+ * (at your option) any later version.
-+ */
-+
-+#ifndef _LINUX_MODULES_BUILTIN_H
-+#define _LINUX_MODULES_BUILTIN_H
-+
-+#include <stdio.h>
-+#include <stddef.h>
-+
-+/*
-+ * modules.builtin.objs iteration state.
-+ */
-+struct modules_builtin_iter {
-+ FILE *f;
-+ char *line;
-+ size_t line_size;
-+};
-+
-+/*
-+ * Construct a modules_builtin.objs iterator.
-+ */
-+struct modules_builtin_iter *
-+modules_builtin_iter_new(const char *modules_builtin_file);
-+
-+/*
-+ * Iterate, returning a new null-terminated array of object file names, and a
-+ * new dynamically-allocated module name. (The module name passed in is freed.)
-+ *
-+ * The array of object file names should be freed by the caller: the strings it
-+ * points to are owned by the iterator, and should not be freed.
-+ */
-+
-+char ** __attribute__((__nonnull__))
-+modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name);
-+
-+void
-+modules_builtin_iter_free(struct modules_builtin_iter *i);
-+
-+#endif
-diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
-index c52d517b93647..8f75906a96314 100644
---- a/scripts/package/kernel.spec
-+++ b/scripts/package/kernel.spec
-@@ -53,12 +53,18 @@ patch -p1 < %{SOURCE2}
-
- %build
- %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
-+%if %{with_ctf}
-+%{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release} ctf
-+%endif
-
- %install
- mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
- cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
- # DEPMOD=true makes depmod no-op. We do not package depmod-generated files.
- %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} DEPMOD=true modules_install
-+%if %{with_ctf}
-+%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} ctf_install
-+%endif
- %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
- cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
- cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
-diff --git a/scripts/package/mkspec b/scripts/package/mkspec
-index ce201bfa8377c..aeb43c7ab1229 100755
---- a/scripts/package/mkspec
-+++ b/scripts/package/mkspec
-@@ -21,10 +21,16 @@ else
- echo '%define with_devel 0'
- fi
-
-+if grep -q CONFIG_CTF=y include/config/auto.conf; then
-+echo '%define with_ctf %{?_without_ctf: 0} %{?!_without_ctf: 1}'
-+else
-+echo '%define with_ctf 0'
-+fi
- cat<<EOF
- %define ARCH ${ARCH}
- %define KERNELRELEASE ${KERNELRELEASE}
- %define pkg_release $("${srctree}/init/build-version")
-+
- EOF
-
- cat "${srctree}/scripts/package/kernel.spec"
-diff --git a/scripts/remove-ctf-lds.awk b/scripts/remove-ctf-lds.awk
-new file mode 100644
-index 0000000000000..5d94d6ee99227
---- /dev/null
-+++ b/scripts/remove-ctf-lds.awk
-@@ -0,0 +1,12 @@
-+# SPDX-License-Identifier: GPL-2.0
-+# See Makefile.vmlinux_o
-+
-+BEGIN {
-+ discards = 0; p = 0
-+}
-+
-+/^====/ { p = 1; next; }
-+p && /\.ctf/ { next; }
-+p && !discards && /DISCARD/ { sub(/\} *$/, " *(.ctf) }"); discards = 1 }
-+p && /^\}/ && !discards { print " /DISCARD/ : { *(.ctf) }"; }
-+p { print $0; }
-diff --git a/scripts/verify_builtin_ranges.awk b/scripts/verify_builtin_ranges.awk
-new file mode 100755
-index 0000000000000..f513841da83e1
---- /dev/null
-+++ b/scripts/verify_builtin_ranges.awk
-@@ -0,0 +1,356 @@
-+#!/usr/bin/gawk -f
-+# SPDX-License-Identifier: GPL-2.0
-+# verify_builtin_ranges.awk: Verify address range data for builtin modules
-+# Written by Kris Van Hees <kris.van.hees@oracle.com>
-+#
-+# Usage: verify_builtin_ranges.awk modules.builtin.ranges System.map \
-+# modules.builtin vmlinux.map vmlinux.o.map \
-+# [ <build-dir> ]
-+#
-+
-+# Return the module name(s) (if any) associated with the given object.
-+#
-+# If we have seen this object before, return information from the cache.
-+# Otherwise, retrieve it from the corresponding .cmd file.
-+#
-+function get_module_info(fn, mod, obj, s) {
-+ if (fn in omod)
-+ return omod[fn];
-+
-+ if (match(fn, /\/[^/]+$/) == 0)
-+ return "";
-+
-+ obj = fn;
-+ mod = "";
-+ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
-+ if (getline s <fn == 1) {
-+ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
-+ mod = substr(s, RSTART + 16, RLENGTH - 16);
-+ gsub(/['"]/, "", mod);
-+ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
-+ mod = substr(s, RSTART + 13, RLENGTH - 13);
-+ } else {
-+ print "ERROR: Failed to read: " fn "\n\n" \
-+ " Invalid kernel build directory (" kdir ")\n" \
-+ " or its content does not match " ARGV[1] >"/dev/stderr";
-+ close(fn);
-+ total = 0;
-+ exit(1);
-+ }
-+ close(fn);
-+
-+ # A single module (common case) also reflects objects that are not part
-+ # of a module. Some of those objects have names that are also a module
-+ # name (e.g. core). We check the associated module file name, and if
-+ # they do not match, the object is not part of a module.
-+ if (mod !~ / /) {
-+ if (!(mod in mods))
-+ mod = "";
-+ }
-+
-+ gsub(/([^/ ]*\/)+/, "", mod);
-+ gsub(/-/, "_", mod);
-+
-+ # At this point, mod is a single (valid) module name, or a list of
-+ # module names (that do not need validation).
-+ omod[obj] = mod;
-+
-+ return mod;
-+}
-+
-+# Return a representative integer value for a given hexadecimal address.
-+#
-+# Since all kernel addresses fall within the same memory region, we can safely
-+# strip off the first 6 hex digits before performing the hex-to-dec conversion,
-+# thereby avoiding integer overflows.
-+#
-+function addr2val(val) {
-+ sub(/^0x/, "", val);
-+ if (length(val) == 16)
-+ val = substr(val, 5);
-+ return strtonum("0x" val);
-+}
-+
-+# Determine the kernel build directory to use (default is .).
-+#
-+BEGIN {
-+ if (ARGC > 6) {
-+ kdir = ARGV[ARGC - 1];
-+ ARGV[ARGC - 1] = "";
-+ } else
-+ kdir = ".";
-+}
-+
-+# (1) Load the built-in module address range data.
-+#
-+ARGIND == 1 {
-+ ranges[FNR] = $0;
-+ rcnt++;
-+ next;
-+}
-+
-+# (2) Annotate System.map symbols with module names.
-+#
-+ARGIND == 2 {
-+ addr = addr2val($1);
-+ name = $3;
-+
-+ while (addr >= mod_eaddr) {
-+ if (sect_symb) {
-+ if (sect_symb != name)
-+ next;
-+
-+ sect_base = addr - sect_off;
-+ if (dbg)
-+ printf "[%s] BASE (%s) %016x - %016x = %016x\n", sect_name, sect_symb, addr, sect_off, sect_base >"/dev/stderr";
-+ sect_symb = 0;
-+ }
-+
-+ if (++ridx > rcnt)
-+ break;
-+
-+ $0 = ranges[ridx];
-+ sub(/-/, " ");
-+ if ($4 != "=") {
-+ sub(/-/, " ");
-+ mod_saddr = strtonum("0x" $2) + sect_base;
-+ mod_eaddr = strtonum("0x" $3) + sect_base;
-+ $1 = $2 = $3 = "";
-+ sub(/^ +/, "");
-+ mod_name = $0;
-+
-+ if (dbg)
-+ printf "[%s] %s from %016x to %016x\n", sect_name, mod_name, mod_saddr, mod_eaddr >"/dev/stderr";
-+ } else {
-+ sect_name = $1;
-+ sect_off = strtonum("0x" $2);
-+ sect_symb = $5;
-+ }
-+ }
-+
-+ idx = addr"-"name;
-+ if (addr >= mod_saddr && addr < mod_eaddr)
-+ sym2mod[idx] = mod_name;
-+
-+ next;
-+}
-+
-+# Once we are done annotating the System.map, we no longer need the ranges data.
-+#
-+FNR == 1 && ARGIND == 3 {
-+ delete ranges;
-+}
-+
-+# (3) Build a lookup map of built-in module names.
-+#
-+# Lines from modules.builtin will be like:
-+# kernel/crypto/lzo-rle.ko
-+# and we record the object name "crypto/lzo-rle".
-+#
-+ARGIND == 3 {
-+ sub(/kernel\//, ""); # strip off "kernel/" prefix
-+ sub(/\.ko$/, ""); # strip off .ko suffix
-+
-+ mods[$1] = 1;
-+ next;
-+}
-+
-+# (4) Get a list of symbols (per object).
-+#
-+# Symbols by object are read from vmlinux.map, with fallback to vmlinux.o.map
-+# if vmlinux is found to have inked in vmlinux.o.
-+#
-+
-+# If we were able to get the data we need from vmlinux.map, there is no need to
-+# process vmlinux.o.map.
-+#
-+FNR == 1 && ARGIND == 5 && total > 0 {
-+ if (dbg)
-+ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
-+ exit;
-+}
-+
-+# First determine whether we are dealing with a GNU ld or LLVM lld linker map.
-+#
-+ARGIND >= 4 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
-+ map_is_lld = 1;
-+ next;
-+}
-+
-+# (LLD) Convert a section record fronm lld format to ld format.
-+#
-+ARGIND >= 4 && map_is_lld && NF == 5 && /[0-9] [^ ]/ {
-+ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
-+}
-+
-+# (LLD) Convert an object record from lld format to ld format.
-+#
-+ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /:\(\./ {
-+ gsub(/\)/, "");
-+ sub(/:\(/, " ");
-+ sub(/ vmlinux\.a\(/, " ");
-+ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
-+}
-+
-+# (LLD) Convert a symbol record from lld format to ld format.
-+#
-+ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /^[A-Za-z_][A-Za-z0-9_]*$/ {
-+ $0 = " 0x" $1 " " $5;
-+}
-+
-+# (LLD) We do not need any other ldd linker map records.
-+#
-+ARGIND >= 4 && map_is_lld && /^[0-9a-f]{16} / {
-+ next;
-+}
-+
-+# Handle section records with long section names (spilling onto a 2nd line).
-+#
-+ARGIND >= 4 && !map_is_lld && NF == 1 && /^[^ ]/ {
-+ s = $0;
-+ getline;
-+ $0 = s " " $0;
-+}
-+
-+# Next section - previous one is done.
-+#
-+ARGIND >= 4 && /^[^ ]/ {
-+ sect = 0;
-+}
-+
-+# Get the (top level) section name.
-+#
-+ARGIND >= 4 && /^[^ ]/ && $2 ~ /^0x/ && $3 ~ /^0x/ {
-+ # Empty section or per-CPU section - ignore.
-+ if (NF < 3 || $1 ~ /\.percpu/) {
-+ sect = 0;
-+ next;
-+ }
-+
-+ sect = $1;
-+
-+ next;
-+}
-+
-+# If we are not currently in a section we care about, ignore records.
-+#
-+!sect {
-+ next;
-+}
-+
-+# Handle object records with long section names (spilling onto a 2nd line).
-+#
-+ARGIND >= 4 && /^ [^ \*]/ && NF == 1 {
-+ # If the section name is long, the remainder of the entry is found on
-+ # the next line.
-+ s = $0;
-+ getline;
-+ $0 = s " " $0;
-+}
-+
-+# If the object is vmlinux.o, we need to consult vmlinux.o.map for per-object
-+# symbol information
-+#
-+ARGIND == 4 && /^ [^ ]/ && NF == 4 {
-+ idx = sect":"$1;
-+ if (!(idx in sect_addend)) {
-+ sect_addend[idx] = addr2val($2);
-+ if (dbg)
-+ printf "ADDEND %s = %016x\n", idx, sect_addend[idx] >"/dev/stderr";
-+ }
-+ if ($4 == "vmlinux.o") {
-+ need_o_map = 1;
-+ next;
-+ }
-+}
-+
-+# If data from vmlinux.o.map is needed, we only process section and object
-+# records from vmlinux.map to determine which section we need to pay attention
-+# to in vmlinux.o.map. So skip everything else from vmlinux.map.
-+#
-+ARGIND == 4 && need_o_map {
-+ next;
-+}
-+
-+# Get module information for the current object.
-+#
-+ARGIND >= 4 && /^ [^ ]/ && NF == 4 {
-+ msect = $1;
-+ mod_name = get_module_info($4);
-+ mod_eaddr = addr2val($2) + addr2val($3);
-+
-+ next;
-+}
-+
-+# Process a symbol record.
-+#
-+# Evaluate the module information obtained from vmlinux.map (or vmlinux.o.map)
-+# as follows:
-+# - For all symbols in a given object:
-+# - If the symbol is annotated with the same module name(s) that the object
-+# belongs to, count it as a match.
-+# - Otherwise:
-+# - If the symbol is known to have duplicates of which at least one is
-+# in a built-in module, disregard it.
-+# - If the symbol us not annotated with any module name(s) AND the
-+# object belongs to built-in modules, count it as missing.
-+# - Otherwise, count it as a mismatch.
-+#
-+ARGIND >= 4 && /^ / && NF == 2 && $1 ~ /^0x/ {
-+ idx = sect":"msect;
-+ if (!(idx in sect_addend))
-+ next;
-+
-+ addr = addr2val($1);
-+
-+ # Handle the rare but annoying case where a 0-size symbol is placed at
-+ # the byte *after* the module range. Based on vmlinux.map it will be
-+ # considered part of the current object, but it falls just beyond the
-+ # module address range. Unfortunately, its address could be at the
-+ # start of another built-in module, so the only safe thing to do is to
-+ # ignore it.
-+ if (mod_name && addr == mod_eaddr)
-+ next;
-+
-+ # If we are processing vmlinux.o.map, we need to apply the base address
-+ # of the section to the relative address on the record.
-+ #
-+ if (ARGIND == 5)
-+ addr += sect_addend[idx];
-+
-+ idx = addr"-"$2;
-+ mod = "";
-+ if (idx in sym2mod) {
-+ mod = sym2mod[idx];
-+ if (sym2mod[idx] == mod_name) {
-+ mod_matches++;
-+ matches++;
-+ } else if (mod_name == "") {
-+ print $2 " in " sym2mod[idx] " (should NOT be)";
-+ mismatches++;
-+ } else {
-+ print $2 " in " sym2mod[idx] " (should be " mod_name ")";
-+ mismatches++;
-+ }
-+ } else if (mod_name != "") {
-+ print $2 " should be in " mod_name;
-+ missing++;
-+ } else
-+ matches++;
-+
-+ total++;
-+
-+ next;
-+}
-+
-+# Issue the comparison report.
-+#
-+END {
-+ if (total) {
-+ printf "Verification of %s:\n", ARGV[1];
-+ printf " Correct matches: %6d (%d%% of total)\n", matches, 100 * matches / total;
-+ printf " Module matches: %6d (%d%% of matches)\n", mod_matches, 100 * mod_matches / matches;
-+ printf " Mismatches: %6d (%d%% of total)\n", mismatches, 100 * mismatches / total;
-+ printf " Missing: %6d (%d%% of total)\n", missing, 100 * missing / total;
-+ }
-+}
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-05 13:58 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-05 13:58 UTC (permalink / raw
To: gentoo-commits
commit: c7e567fb7f29fa11e8063bdf16407bafdf75ed1e
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Thu Sep 5 13:58:06 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Thu Sep 5 13:58:06 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=c7e567fb
parisc: Delay write-protection until mark_rodata_ro() call
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +++
1710_parisc-Delay-write-protection.patch | 61 ++++++++++++++++++++++++++++++++
2 files changed, 65 insertions(+)
diff --git a/0000_README b/0000_README
index 21f04f84..d179ade8 100644
--- a/0000_README
+++ b/0000_README
@@ -83,6 +83,10 @@ Patch: 1700_sparc-address-warray-bound-warnings.patch
From: https://github.com/KSPP/linux/issues/109
Desc: Address -Warray-bounds warnings
+Patch: 1710_parisc-Delay-write-protection.patch
+From: https://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
+Desc: parisc: Delay write-protection until mark_rodata_ro() call
+
Patch: 1730_parisc-Disable-prctl.patch
From: https://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
Desc: prctl: Temporarily disable prctl(PR_SET_MDWE) on parisc
diff --git a/1710_parisc-Delay-write-protection.patch b/1710_parisc-Delay-write-protection.patch
new file mode 100644
index 00000000..efdd4c27
--- /dev/null
+++ b/1710_parisc-Delay-write-protection.patch
@@ -0,0 +1,61 @@
+From 213aa670153ed675a007c1f35c5db544b0fefc94 Mon Sep 17 00:00:00 2001
+From: Helge Deller <deller@gmx.de>
+Date: Sat, 31 Aug 2024 14:02:06 +0200
+Subject: parisc: Delay write-protection until mark_rodata_ro() call
+
+Do not write-protect the kernel read-only and __ro_after_init sections
+earlier than before mark_rodata_ro() is called. This fixes a boot issue on
+parisc which is triggered by commit 91a1d97ef482 ("jump_label,module: Don't
+alloc static_key_mod for __ro_after_init keys"). That commit may modify
+static key contents in the __ro_after_init section at bootup, so this
+section needs to be writable at least until mark_rodata_ro() is called.
+
+Signed-off-by: Helge Deller <deller@gmx.de>
+Reported-by: matoro <matoro_mailinglist_kernel@matoro.tk>
+Reported-by: Christoph Biedl <linux-kernel.bfrz@manchmal.in-ulm.de>
+Tested-by: Christoph Biedl <linux-kernel.bfrz@manchmal.in-ulm.de>
+Link: https://lore.kernel.org/linux-parisc/096cad5aada514255cd7b0b9dbafc768@matoro.tk/#r
+Fixes: 91a1d97ef482 ("jump_label,module: Don't alloc static_key_mod for __ro_after_init keys")
+Cc: stable@vger.kernel.org # v6.10+
+---
+ arch/parisc/mm/init.c | 16 +++++++++++-----
+ 1 file changed, 11 insertions(+), 5 deletions(-)
+
+diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
+index 34d91cb8b25905..96970fa75e4ac9 100644
+--- a/arch/parisc/mm/init.c
++++ b/arch/parisc/mm/init.c
+@@ -459,7 +459,6 @@ void free_initmem(void)
+ unsigned long kernel_end = (unsigned long)&_end;
+
+ /* Remap kernel text and data, but do not touch init section yet. */
+- kernel_set_to_readonly = true;
+ map_pages(init_end, __pa(init_end), kernel_end - init_end,
+ PAGE_KERNEL, 0);
+
+@@ -493,11 +492,18 @@ void free_initmem(void)
+ #ifdef CONFIG_STRICT_KERNEL_RWX
+ void mark_rodata_ro(void)
+ {
+- /* rodata memory was already mapped with KERNEL_RO access rights by
+- pagetable_init() and map_pages(). No need to do additional stuff here */
+- unsigned long roai_size = __end_ro_after_init - __start_ro_after_init;
++ unsigned long start = (unsigned long) &__start_rodata;
++ unsigned long end = (unsigned long) &__end_rodata;
++
++ pr_info("Write protecting the kernel read-only data: %luk\n",
++ (end - start) >> 10);
++
++ kernel_set_to_readonly = true;
++ map_pages(start, __pa(start), end - start, PAGE_KERNEL, 0);
+
+- pr_info("Write protected read-only-after-init data: %luk\n", roai_size >> 10);
++ /* force the kernel to see the new page table entries */
++ flush_cache_all();
++ flush_tlb_all();
+ }
+ #endif
+
+--
+cgit 1.2.3-korg
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-04 14:06 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-04 14:06 UTC (permalink / raw
To: gentoo-commits
commit: 090e7ec1c8858bc2901ddad77f9cb6cd62721fc2
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Sep 4 14:05:29 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Sep 4 14:05:29 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=090e7ec1
Remove .gitignore section from dtrace patch
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
2995_dtrace-6.10_p1.patch | 35 -----------------------------------
1 file changed, 35 deletions(-)
diff --git a/2995_dtrace-6.10_p1.patch b/2995_dtrace-6.10_p1.patch
index 6e03cbf6..97983060 100644
--- a/2995_dtrace-6.10_p1.patch
+++ b/2995_dtrace-6.10_p1.patch
@@ -1,38 +1,3 @@
-diff --git a/.gitignore b/.gitignore
-index c59dc60ba62ef..6722f45561f3a 100644
---- a/.gitignore
-+++ b/.gitignore
-@@ -16,6 +16,7 @@
- *.bin
- *.bz2
- *.c.[012]*.*
-+*.ctf
- *.dt.yaml
- *.dtb
- *.dtbo
-@@ -54,6 +55,7 @@
- Module.symvers
- dtbs-list
- modules.order
-+objects.builtin
-
- #
- # Top-level generic files
-@@ -64,12 +66,13 @@ modules.order
- /vmlinux.32
- /vmlinux.map
- /vmlinux.symvers
-+/vmlinux.ctfa
- /vmlinux-gdb.py
- /vmlinuz
- /System.map
- /Module.markers
- /modules.builtin
--/modules.builtin.modinfo
-+/modules.builtin.*
- /modules.nsdeps
-
- #
diff --git a/Documentation/dontdiff b/Documentation/dontdiff
index 3c399f132e2db..75b9655e57914 100644
--- a/Documentation/dontdiff
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-04 13:51 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-04 13:51 UTC (permalink / raw
To: gentoo-commits
commit: da7a9b74230d2b2d4e158cc04234651235bb173c
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Sep 4 13:50:43 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Sep 4 13:50:43 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=da7a9b74
Update README
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 ++++
1 file changed, 4 insertions(+)
diff --git a/0000_README b/0000_README
index f658d7dc..21f04f84 100644
--- a/0000_README
+++ b/0000_README
@@ -71,6 +71,10 @@ Patch: 1006_linux-6.10.7.patch
From: https://www.kernel.org
Desc: Linux 6.10.7
+Patch: 1007_linux-6.10.8.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.8
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
^ permalink raw reply related [flat|nested] 37+ messages in thread
* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-04 13:50 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-04 13:50 UTC (permalink / raw
To: gentoo-commits
commit: 94737e9422147d7840950af0a7890faafbb1f337
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Sep 4 13:49:42 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Sep 4 13:49:42 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=94737e94
dtrace patch thanks to Sam
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
2995_dtrace-6.10_p1.patch | 2390 +++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 2394 insertions(+)
diff --git a/0000_README b/0000_README
index 82c9265b..f658d7dc 100644
--- a/0000_README
+++ b/0000_README
@@ -111,6 +111,10 @@ Patch: 2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
From: https://lore.kernel.org/bpf/
Desc: libbpf: workaround -Wmaybe-uninitialized false positive
+Patch: 2995_dtrace-6.10_p1.patch
+From: https://github.com/thesamesam/linux/tree/dtrace-sam/v2/6.10
+Desc: dtrace patch 6.10_p1
+
Patch: 3000_Support-printing-firmware-info.patch
From: https://bugs.gentoo.org/732852
Desc: Print firmware info (Reqs CONFIG_GENTOO_PRINT_FIRMWARE_INFO). Thanks to Georgy Yakovlev
diff --git a/2995_dtrace-6.10_p1.patch b/2995_dtrace-6.10_p1.patch
new file mode 100644
index 00000000..6e03cbf6
--- /dev/null
+++ b/2995_dtrace-6.10_p1.patch
@@ -0,0 +1,2390 @@
+diff --git a/.gitignore b/.gitignore
+index c59dc60ba62ef..6722f45561f3a 100644
+--- a/.gitignore
++++ b/.gitignore
+@@ -16,6 +16,7 @@
+ *.bin
+ *.bz2
+ *.c.[012]*.*
++*.ctf
+ *.dt.yaml
+ *.dtb
+ *.dtbo
+@@ -54,6 +55,7 @@
+ Module.symvers
+ dtbs-list
+ modules.order
++objects.builtin
+
+ #
+ # Top-level generic files
+@@ -64,12 +66,13 @@ modules.order
+ /vmlinux.32
+ /vmlinux.map
+ /vmlinux.symvers
++/vmlinux.ctfa
+ /vmlinux-gdb.py
+ /vmlinuz
+ /System.map
+ /Module.markers
+ /modules.builtin
+-/modules.builtin.modinfo
++/modules.builtin.*
+ /modules.nsdeps
+
+ #
+diff --git a/Documentation/dontdiff b/Documentation/dontdiff
+index 3c399f132e2db..75b9655e57914 100644
+--- a/Documentation/dontdiff
++++ b/Documentation/dontdiff
+@@ -179,7 +179,7 @@ mkutf8data
+ modpost
+ modules-only.symvers
+ modules.builtin
+-modules.builtin.modinfo
++modules.builtin.*
+ modules.nsdeps
+ modules.order
+ modversions.h*
+diff --git a/Documentation/kbuild/kbuild.rst b/Documentation/kbuild/kbuild.rst
+index 9c8d1d046ea56..79e104ffee715 100644
+--- a/Documentation/kbuild/kbuild.rst
++++ b/Documentation/kbuild/kbuild.rst
+@@ -17,6 +17,11 @@ modules.builtin
+ This file lists all modules that are built into the kernel. This is used
+ by modprobe to not fail when trying to load something builtin.
+
++modules.builtin.objs
++-----------------------
++This file contains object mapping of modules that are built into the kernel
++to their corresponding object files used to build the module.
++
+ modules.builtin.modinfo
+ -----------------------
+ This file contains modinfo from all modules that are built into the kernel.
+diff --git a/Documentation/process/changes.rst b/Documentation/process/changes.rst
+index 5685d7bfe4d0f..8db62fe4dadff 100644
+--- a/Documentation/process/changes.rst
++++ b/Documentation/process/changes.rst
+@@ -63,9 +63,13 @@ cpio any cpio --version
+ GNU tar 1.28 tar --version
+ gtags (optional) 6.6.5 gtags --version
+ mkimage (optional) 2017.01 mkimage --version
++GNU AWK (optional) 5.1.0 gawk --version
++GNU C\ [#f2]_ 12.0 gcc --version
++binutils\ [#f2]_ 2.36 ld -v
+ ====================== =============== ========================================
+
+ .. [#f1] Sphinx is needed only to build the Kernel documentation
++.. [#f2] These are needed at build-time when CONFIG_CTF is enabled
+
+ Kernel compilation
+ ******************
+@@ -198,6 +202,12 @@ platforms. The tool is available via the ``u-boot-tools`` package or can be
+ built from the U-Boot source code. See the instructions at
+ https://docs.u-boot.org/en/latest/build/tools.html#building-tools-for-linux
+
++GNU AWK
++-------
++
++GNU AWK is needed if you want kernel builds to generate address range data for
++builtin modules (CONFIG_BUILTIN_MODULE_RANGES).
++
+ System utilities
+ ****************
+
+diff --git a/Makefile b/Makefile
+index ab77d171e268d..425dd4d723155 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1024,6 +1024,7 @@ include-$(CONFIG_UBSAN) += scripts/Makefile.ubsan
+ include-$(CONFIG_KCOV) += scripts/Makefile.kcov
+ include-$(CONFIG_RANDSTRUCT) += scripts/Makefile.randstruct
+ include-$(CONFIG_GCC_PLUGINS) += scripts/Makefile.gcc-plugins
++include-$(CONFIG_CTF) += scripts/Makefile.ctfa-toplevel
+
+ include $(addprefix $(srctree)/, $(include-y))
+
+@@ -1151,7 +1152,11 @@ PHONY += vmlinux_o
+ vmlinux_o: vmlinux.a $(KBUILD_VMLINUX_LIBS)
+ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.vmlinux_o
+
+-vmlinux.o modules.builtin.modinfo modules.builtin: vmlinux_o
++MODULES_BUILTIN := modules.builtin.modinfo
++MODULES_BUILTIN += modules.builtin
++MODULES_BUILTIN += modules.builtin.objs
++
++vmlinux.o $(MODULES_BUILTIN): vmlinux_o
+ @:
+
+ PHONY += vmlinux
+@@ -1490,9 +1495,10 @@ endif # CONFIG_MODULES
+
+ # Directories & files removed with 'make clean'
+ CLEAN_FILES += vmlinux.symvers modules-only.symvers \
+- modules.builtin modules.builtin.modinfo modules.nsdeps \
++ modules.builtin modules.builtin.* modules.nsdeps \
+ compile_commands.json rust/test \
+- rust-project.json .vmlinux.objs .vmlinux.export.c
++ rust-project.json .vmlinux.objs .vmlinux.export.c \
++ vmlinux.ctfa
+
+ # Directories & files removed with 'make mrproper'
+ MRPROPER_FILES += include/config include/generated \
+@@ -1586,6 +1592,8 @@ help:
+ @echo ' (requires a recent binutils and recent build (System.map))'
+ @echo ' dir/file.ko - Build module including final link'
+ @echo ' modules_prepare - Set up for building external modules'
++ @echo ' ctf - Generate CTF type information, installed by make ctf_install'
++ @echo ' ctf_install - Install CTF to INSTALL_MOD_PATH (default: /)'
+ @echo ' tags/TAGS - Generate tags file for editors'
+ @echo ' cscope - Generate cscope index'
+ @echo ' gtags - Generate GNU GLOBAL index'
+@@ -1942,7 +1950,7 @@ clean: $(clean-dirs)
+ $(call cmd,rmfiles)
+ @find $(or $(KBUILD_EXTMOD), .) $(RCS_FIND_IGNORE) \
+ \( -name '*.[aios]' -o -name '*.rsi' -o -name '*.ko' -o -name '.*.cmd' \
+- -o -name '*.ko.*' \
++ -o -name '*.ko.*' -o -name '*.ctf' \
+ -o -name '*.dtb' -o -name '*.dtbo' \
+ -o -name '*.dtb.S' -o -name '*.dtbo.S' \
+ -o -name '*.dt.yaml' -o -name 'dtbs-list' \
+diff --git a/arch/arm/vdso/Makefile b/arch/arm/vdso/Makefile
+index 01067a2bc43b7..d2193b8dfad83 100644
+--- a/arch/arm/vdso/Makefile
++++ b/arch/arm/vdso/Makefile
+@@ -14,6 +14,10 @@ obj-vdso := $(addprefix $(obj)/, $(obj-vdso))
+ ccflags-y := -fPIC -fno-common -fno-builtin -fno-stack-protector
+ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO32
+
++# CTF in the vDSO would introduce a new section, which would
++# expand the vDSO to more than a page.
++ccflags-y += $(call cc-option,-gctf0)
++
+ ldflags-$(CONFIG_CPU_ENDIAN_BE8) := --be8
+ ldflags-y := -Bsymbolic --no-undefined -soname=linux-vdso.so.1 \
+ -z max-page-size=4096 -shared $(ldflags-y) \
+diff --git a/arch/arm64/kernel/vdso/Makefile b/arch/arm64/kernel/vdso/Makefile
+index d63930c828397..6e84d3822cfe3 100644
+--- a/arch/arm64/kernel/vdso/Makefile
++++ b/arch/arm64/kernel/vdso/Makefile
+@@ -33,6 +33,10 @@ ldflags-y += -T
+ ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
+ ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
++# CTF in the vDSO would introduce a new section, which would
++# expand the vDSO to more than a page.
++ccflags-y += $(call cc-option,-gctf0)
++
+ # -Wmissing-prototypes and -Wmissing-declarations are removed from
+ # the CFLAGS of vgettimeofday.c to make possible to build the
+ # kernel with CONFIG_WERROR enabled.
+diff --git a/arch/loongarch/vdso/Makefile b/arch/loongarch/vdso/Makefile
+index d724d46b07c84..fbedb95223ae1 100644
+--- a/arch/loongarch/vdso/Makefile
++++ b/arch/loongarch/vdso/Makefile
+@@ -21,7 +21,8 @@ cflags-vdso := $(ccflags-vdso) \
+ -O2 -g -fno-strict-aliasing -fno-common -fno-builtin \
+ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
+ $(call cc-option, -fno-asynchronous-unwind-tables) \
+- $(call cc-option, -fno-stack-protector)
++ $(call cc-option, -fno-stack-protector) \
++ $(call cc-option,-gctf0)
+ aflags-vdso := $(ccflags-vdso) \
+ -D__ASSEMBLY__ -Wa,-gdwarf-2
+
+diff --git a/arch/mips/vdso/Makefile b/arch/mips/vdso/Makefile
+index b289b2c1b2946..6c8d777525f9b 100644
+--- a/arch/mips/vdso/Makefile
++++ b/arch/mips/vdso/Makefile
+@@ -30,7 +30,8 @@ cflags-vdso := $(ccflags-vdso) \
+ -O3 -g -fPIC -fno-strict-aliasing -fno-common -fno-builtin -G 0 \
+ -mrelax-pic-calls $(call cc-option, -mexplicit-relocs) \
+ -fno-stack-protector -fno-jump-tables -DDISABLE_BRANCH_PROFILING \
+- $(call cc-option, -fno-asynchronous-unwind-tables)
++ $(call cc-option, -fno-asynchronous-unwind-tables) \
++ $(call cc-option,-gctf0)
+ aflags-vdso := $(ccflags-vdso) \
+ -D__ASSEMBLY__ -Wa,-gdwarf-2
+
+diff --git a/arch/sparc/vdso/Makefile b/arch/sparc/vdso/Makefile
+index 243dbfc4609d8..e4f3e47074e9d 100644
+--- a/arch/sparc/vdso/Makefile
++++ b/arch/sparc/vdso/Makefile
+@@ -44,7 +44,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ CFL := $(PROFILING) -mcmodel=medlow -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
+- -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
++ $(call cc-option,-gctf0) -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ SPARC_REG_CFLAGS = -ffixed-g4 -ffixed-g5 -fcall-used-g5 -fcall-used-g7
+
+diff --git a/arch/x86/entry/vdso/Makefile b/arch/x86/entry/vdso/Makefile
+index 215a1b202a918..2fa1613a06275 100644
+--- a/arch/x86/entry/vdso/Makefile
++++ b/arch/x86/entry/vdso/Makefile
+@@ -54,6 +54,7 @@ $(obj)/vdso-image-%.c: $(obj)/vdso%.so.dbg $(obj)/vdso%.so $(obj)/vdso2c FORCE
+ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+ -fno-omit-frame-pointer -foptimize-sibling-calls \
++ $(call cc-option,-gctf0) \
+ -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
+
+ ifdef CONFIG_MITIGATION_RETPOLINE
+@@ -131,6 +132,7 @@ KBUILD_CFLAGS_32 += -m32 -msoft-float -mregparm=0 -fpic
+ KBUILD_CFLAGS_32 += -fno-stack-protector
+ KBUILD_CFLAGS_32 += $(call cc-option, -foptimize-sibling-calls)
+ KBUILD_CFLAGS_32 += -fno-omit-frame-pointer
++KBUILD_CFLAGS_32 += $(call cc-option,-gctf0)
+ KBUILD_CFLAGS_32 += -DDISABLE_BRANCH_PROFILING
+
+ ifdef CONFIG_MITIGATION_RETPOLINE
+diff --git a/arch/x86/um/vdso/Makefile b/arch/x86/um/vdso/Makefile
+index 6a77ea6434ffd..6db233b5edd75 100644
+--- a/arch/x86/um/vdso/Makefile
++++ b/arch/x86/um/vdso/Makefile
+@@ -40,7 +40,7 @@ $(obj)/%.so: $(obj)/%.so.dbg FORCE
+ #
+ CFL := $(PROFILING) -mcmodel=small -fPIC -O2 -fasynchronous-unwind-tables -m64 \
+ $(filter -g%,$(KBUILD_CFLAGS)) -fno-stack-protector \
+- -fno-omit-frame-pointer -foptimize-sibling-calls
++ -fno-omit-frame-pointer -foptimize-sibling-calls $(call cc-option,-gctf0)
+
+ $(vobjs): KBUILD_CFLAGS += $(CFL)
+
+diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
+index f00a8e18f389f..2e307c0824574 100644
+--- a/include/asm-generic/vmlinux.lds.h
++++ b/include/asm-generic/vmlinux.lds.h
+@@ -1014,6 +1014,7 @@
+ *(.discard.*) \
+ *(.export_symbol) \
+ *(.modinfo) \
++ *(.ctf) \
+ /* ld.bfd warns about .gnu.version* even when not emitted */ \
+ *(.gnu.version*) \
+
+diff --git a/include/linux/module.h b/include/linux/module.h
+index 330ffb59efe51..ec828908470c9 100644
+--- a/include/linux/module.h
++++ b/include/linux/module.h
+@@ -180,7 +180,9 @@ extern void cleanup_module(void);
+ #ifdef MODULE
+ #define MODULE_FILE
+ #else
+-#define MODULE_FILE MODULE_INFO(file, KBUILD_MODFILE);
++#define MODULE_FILE \
++ MODULE_INFO(file, KBUILD_MODFILE); \
++ MODULE_INFO(objs, KBUILD_MODOBJS);
+ #endif
+
+ /*
+diff --git a/init/Kconfig b/init/Kconfig
+index 9684e5d2b81c6..c1b00b2e4a43d 100644
+--- a/init/Kconfig
++++ b/init/Kconfig
+@@ -111,6 +111,12 @@ config PAHOLE_VERSION
+ int
+ default $(shell,$(srctree)/scripts/pahole-version.sh $(PAHOLE))
+
++config HAVE_CTF_TOOLCHAIN
++ def_bool $(cc-option,-gctf) && $(ld-option,-lbfd -liberty -lctf -lbfd -liberty -lz -ldl -lc -o /dev/null)
++ depends on CC_IS_GCC
++ help
++ GCC and binutils support CTF generation.
++
+ config CONSTRUCTORS
+ bool
+
+diff --git a/lib/Kconfig b/lib/Kconfig
+index b0a76dff5c182..61d0be30b3562 100644
+--- a/lib/Kconfig
++++ b/lib/Kconfig
+@@ -633,6 +633,16 @@ config DIMLIB
+ #
+ config LIBFDT
+ bool
++#
++# CTF support is select'ed if needed
++#
++config CTF
++ bool "Compact Type Format generation"
++ depends on HAVE_CTF_TOOLCHAIN
++ help
++ Emit a compact, compressed description of the kernel's datatypes and
++ global variables into the vmlinux.ctfa archive (for in-tree modules)
++ or into .ctf sections in kernel modules (for out-of-tree modules).
+
+ config OID_REGISTRY
+ tristate
+diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
+index 59b6765d86b8f..dab7e6983eace 100644
+--- a/lib/Kconfig.debug
++++ b/lib/Kconfig.debug
+@@ -571,6 +571,21 @@ config VMLINUX_MAP
+ pieces of code get eliminated with
+ CONFIG_LD_DEAD_CODE_DATA_ELIMINATION.
+
++config BUILTIN_MODULE_RANGES
++ bool "Generate address range information for builtin modules"
++ depends on !LTO
++ depends on VMLINUX_MAP
++ help
++ When modules are built into the kernel, there will be no module name
++ associated with its symbols in /proc/kallsyms. Tracers may want to
++ identify symbols by module name and symbol name regardless of whether
++ the module is configured as loadable or not.
++
++ This option generates modules.builtin.ranges in the build tree with
++ offset ranges (per ELF section) for the module(s) they belong to.
++ It also records an anchor symbol to determine the load address of the
++ section.
++
+ config DEBUG_FORCE_WEAK_PER_CPU
+ bool "Force weak per-cpu definitions"
+ depends on DEBUG_KERNEL
+diff --git a/scripts/.gitignore b/scripts/.gitignore
+index 3dbb8bb2457bc..11339fa922abd 100644
+--- a/scripts/.gitignore
++++ b/scripts/.gitignore
+@@ -11,3 +11,4 @@
+ /sorttable
+ /target.json
+ /unifdef
++y!/Makefile.ctf
+diff --git a/scripts/Makefile b/scripts/Makefile
+index fe56eeef09dd4..8e7eb174d3154 100644
+--- a/scripts/Makefile
++++ b/scripts/Makefile
+@@ -54,6 +54,7 @@ targets += module.lds
+
+ subdir-$(CONFIG_GCC_PLUGINS) += gcc-plugins
+ subdir-$(CONFIG_MODVERSIONS) += genksyms
++subdir-$(CONFIG_CTF) += ctf
+ subdir-$(CONFIG_SECURITY_SELINUX) += selinux
+
+ # Let clean descend into subdirs
+diff --git a/scripts/Makefile.ctfa b/scripts/Makefile.ctfa
+new file mode 100644
+index 0000000000000..2b10de139dce5
+--- /dev/null
++++ b/scripts/Makefile.ctfa
+@@ -0,0 +1,92 @@
++# SPDX-License-Identifier: GPL-2.0-only
++# ===========================================================================
++# Module CTF/CTFA generation
++# ===========================================================================
++
++include include/config/auto.conf
++include $(srctree)/scripts/Kbuild.include
++
++# CTF is already present in every object file if CONFIG_CTF is enabled.
++# vmlinux.lds.h strips it out of the finished kernel, but if nothing is done
++# it will be deduplicated into module .ko's. For out-of-tree module builds,
++# this is what we want, but for in-tree modules we can save substantial
++# space by deduplicating it against all the core kernel types as well. So
++# split the CTF out of in-tree module .ko's into separate .ctf files so that
++# it doesn't take up space in the modules on disk, and let the specialized
++# ctfarchive tool consume it and all the CTF in the vmlinux.o files when
++# 'make ctf' is invoked, and use the same machinery that the linker uses to
++# do CTF deduplication to emit vmlinux.ctfa containing the deduplicated CTF.
++
++# Nothing special needs to be done if CTF is turned off or if a standalone
++# module is being built.
++module-ctf-postlink = mv $(1).tmp $(1)
++
++ifdef CONFIG_CTF
++
++# This is quite tricky. The CTF machinery needs to be told about all the
++# built-in objects as well as all the external modules -- but Makefile.modfinal
++# only knows about the latter. So the toplevel makefile emits the names of the
++# built-in objects into a temporary file, which is then catted and its contents
++# used as prerequisites by this rule.
++#
++# We write the names of the object files to be scanned for CTF content into a
++# file, then use that, to avoid hitting command-line length limits.
++
++ifeq ($(KBUILD_EXTMOD),)
++ctf-modules := $(shell find . -name '*.ko.ctf' -print)
++quiet_cmd_ctfa_raw = CTFARAW
++ cmd_ctfa_raw = scripts/ctf/ctfarchive $@ .tmp_objects.builtin modules.builtin.objs $(ctf-filelist)
++ctf-builtins := .tmp_objects.builtin
++ctf-filelist := .tmp_ctf.filelist
++ctf-filelist-raw := .tmp_ctf.filelist.raw
++
++define module-ctf-postlink =
++ $(OBJCOPY) --only-section=.ctf $(1).tmp $(1).ctf && \
++ $(OBJCOPY) --remove-section=.ctf $(1).tmp $(1) && rm -f $(1).tmp
++endef
++
++# Split a list up like shell xargs does.
++define xargs =
++$(1) $(wordlist 1,1024,$(2))
++$(if $(word 1025,$(2)),$(call xargs,$(1),$(wordlist 1025,$(words $(2)),$(2))))
++endef
++
++$(ctf-filelist-raw): $(ctf-builtins) $(ctf-modules)
++ @rm -f $(ctf-filelist-raw);
++ $(call xargs,@printf "%s\n" >> $(ctf-filelist-raw),$^)
++ @touch $(ctf-filelist-raw)
++
++$(ctf-filelist): $(ctf-filelist-raw)
++ @rm -f $(ctf-filelist);
++ @cat $(ctf-filelist-raw) | while read -r obj; do \
++ case $$obj in \
++ $(ctf-builtins)) cat $$obj >> $(ctf-filelist);; \
++ *.a) ar t $$obj > $(ctf-filelist);; \
++ *.builtin) cat $$obj >> $(ctf-filelist);; \
++ *) echo "$$obj" >> $(ctf-filelist);; \
++ esac; \
++ done
++ @touch $(ctf-filelist)
++
++# The raw CTF depends on the output CTF file list, and that depends
++# on the .ko files for the modules.
++.tmp_vmlinux.ctfa.raw: $(ctf-filelist) FORCE
++ $(call if_changed,ctfa_raw)
++
++quiet_cmd_ctfa = CTFA
++ cmd_ctfa = { echo 'int main () { return 0; } ' | \
++ gcc -x c -c -o $<.stub -; \
++ $(OBJCOPY) '--remove-section=.*' --add-section=.ctf=$< \
++ $<.stub $@; }
++
++# The CTF itself is an ELF executable with one section: the CTF. This lets
++# objdump work on it, at minimal size cost.
++vmlinux.ctfa: .tmp_vmlinux.ctfa.raw FORCE
++ $(call if_changed,ctfa)
++
++targets += vmlinux.ctfa
++
++endif # KBUILD_EXTMOD
++
++endif # !CONFIG_CTF
++
+diff --git a/scripts/Makefile.ctfa-toplevel b/scripts/Makefile.ctfa-toplevel
+new file mode 100644
+index 0000000000000..210bef3854e9b
+--- /dev/null
++++ b/scripts/Makefile.ctfa-toplevel
+@@ -0,0 +1,54 @@
++# SPDX-License-Identifier: GPL-2.0-only
++# ===========================================================================
++# CTF rules for the top-level makefile only
++# ===========================================================================
++
++KBUILD_CFLAGS += $(call cc-option,-gctf)
++KBUILD_LDFLAGS += $(call ld-option, --ctf-variables)
++
++ifeq ($(KBUILD_EXTMOD),)
++
++# CTF generation for in-tree code (modules, built-in and not, and core kernel)
++
++# This contains all the object files that are built directly into the
++# kernel (including built-in modules), for consumption by ctfarchive in
++# Makefile.modfinal.
++# This is made doubly annoying by the presence of '.o' files which are actually
++# thin ar archives, and the need to support file(1) versions too old to
++# recognize them as archives at all. (So we assume that everything that is notr
++# an ELF object is an archive.)
++ifeq ($(SRCARCH),x86)
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),bzImage) FORCE
++else
++ifeq ($(SRCARCH),arm64)
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),Image) FORCE
++else
++.tmp_objects.builtin: $(vmlinux-dirs) $(if $(KBUILD_BUILTIN),vmlinux) FORCE
++endif
++endif
++ @echo $(KBUILD_VMLINUX_OBJS) | \
++ tr " " "\n" | grep "\.o$$" | xargs -r file | \
++ grep ELF | cut -d: -f1 > .tmp_objects.builtin
++ @for archive in $$(echo $(KBUILD_VMLINUX_OBJS) |\
++ tr " " "\n" | xargs -r file | grep -v ELF | cut -d: -f1); do \
++ $(AR) t "$$archive" >> .tmp_objects.builtin; \
++ done
++
++ctf: vmlinux.ctfa
++PHONY += ctf ctf_install
++
++# Making CTF needs the builtin files. We need to force everything to be
++# built if not already done, since we need the .o files for the machinery
++# above to work.
++vmlinux.ctfa: KBUILD_BUILTIN := 1
++vmlinux.ctfa: modules.builtin.objs .tmp_objects.builtin
++ $(Q)$(MAKE) -f $(srctree)/scripts/Makefile.modfinal vmlinux.ctfa
++
++ctf_install:
++ $(Q)mkdir -p $(MODLIB)/kernel
++ @ln -sf $(abspath $(srctree)) $(MODLIB)/source
++ $(Q)cp -f $(objtree)/vmlinux.ctfa $(MODLIB)/kernel
++
++CLEAN_FILES += vmlinux.ctfa
++
++endif
+diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
+index 7f8ec77bf35c9..97b0ea2eee9d4 100644
+--- a/scripts/Makefile.lib
++++ b/scripts/Makefile.lib
+@@ -118,6 +118,8 @@ modname-multi = $(sort $(foreach m,$(multi-obj-ym),\
+ __modname = $(or $(modname-multi),$(basetarget))
+
+ modname = $(subst $(space),:,$(__modname))
++modname-objs = $($(modname)-objs) $($(modname)-y) $($(modname)-Y)
++modname-objs-prefixed = $(sort $(strip $(addprefix $(obj)/, $(modname-objs))))
+ modfile = $(addprefix $(obj)/,$(__modname))
+
+ # target with $(obj)/ and its suffix stripped
+@@ -131,7 +133,8 @@ name-fix = $(call stringify,$(call name-fix-token,$1))
+ basename_flags = -DKBUILD_BASENAME=$(call name-fix,$(basetarget))
+ modname_flags = -DKBUILD_MODNAME=$(call name-fix,$(modname)) \
+ -D__KBUILD_MODNAME=kmod_$(call name-fix-token,$(modname))
+-modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile))
++modfile_flags = -DKBUILD_MODFILE=$(call stringify,$(modfile)) \
++ -DKBUILD_MODOBJS=$(call stringify,$(modfile).o:$(subst $(space),|,$(modname-objs-prefixed)))
+
+ _c_flags = $(filter-out $(CFLAGS_REMOVE_$(target-stem).o), \
+ $(filter-out $(ccflags-remove-y), \
+@@ -238,7 +241,7 @@ modkern_rustflags = \
+
+ modkern_aflags = $(if $(part-of-module), \
+ $(KBUILD_AFLAGS_MODULE) $(AFLAGS_MODULE), \
+- $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL))
++ $(KBUILD_AFLAGS_KERNEL) $(AFLAGS_KERNEL) $(modfile_flags))
+
+ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ -include $(srctree)/include/linux/compiler_types.h \
+@@ -248,7 +251,7 @@ c_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ rust_flags = $(_rust_flags) $(modkern_rustflags) @$(objtree)/include/generated/rustc_cfg
+
+ a_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+- $(_a_flags) $(modkern_aflags)
++ $(_a_flags) $(modkern_aflags) $(modname_flags)
+
+ cpp_flags = -Wp,-MMD,$(depfile) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) \
+ $(_cpp_flags)
+diff --git a/scripts/Makefile.modfinal b/scripts/Makefile.modfinal
+index 3bec9043e4f38..06807e403d162 100644
+--- a/scripts/Makefile.modfinal
++++ b/scripts/Makefile.modfinal
+@@ -30,11 +30,16 @@ quiet_cmd_cc_o_c = CC [M] $@
+ %.mod.o: %.mod.c FORCE
+ $(call if_changed_dep,cc_o_c)
+
++# for module-ctf-postlink
++include $(srctree)/scripts/Makefile.ctfa
++
+ quiet_cmd_ld_ko_o = LD [M] $@
+ cmd_ld_ko_o += \
+ $(LD) -r $(KBUILD_LDFLAGS) \
+ $(KBUILD_LDFLAGS_MODULE) $(LDFLAGS_MODULE) \
+- -T scripts/module.lds -o $@ $(filter %.o, $^)
++ -T scripts/module.lds $(LDFLAGS_$(modname)) -o $@.tmp \
++ $(filter %.o, $^) && \
++ $(call module-ctf-postlink,$@) \
+
+ quiet_cmd_btf_ko = BTF [M] $@
+ cmd_btf_ko = \
+diff --git a/scripts/Makefile.modinst b/scripts/Makefile.modinst
+index 0afd75472679f..e668469ce098c 100644
+--- a/scripts/Makefile.modinst
++++ b/scripts/Makefile.modinst
+@@ -30,10 +30,12 @@ $(MODLIB)/modules.order: modules.order FORCE
+ quiet_cmd_install_modorder = INSTALL $@
+ cmd_install_modorder = sed 's:^\(.*\)\.o$$:kernel/\1.ko:' $< > $@
+
+-# Install modules.builtin(.modinfo) even when CONFIG_MODULES is disabled.
+-install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo)
++# Install modules.builtin(.modinfo,.ranges,.objs) even when CONFIG_MODULES is disabled.
++install-y += $(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.objs)
+
+-$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo): $(MODLIB)/%: % FORCE
++install-$(CONFIG_BUILTIN_MODULE_RANGES) += $(MODLIB)/modules.builtin.ranges
++
++$(addprefix $(MODLIB)/, modules.builtin modules.builtin.modinfo modules.builtin.ranges modules.builtin.objs): $(MODLIB)/%: % FORCE
+ $(call cmd,install)
+
+ endif
+diff --git a/scripts/Makefile.vmlinux b/scripts/Makefile.vmlinux
+index 49946cb968440..7e8b703799c85 100644
+--- a/scripts/Makefile.vmlinux
++++ b/scripts/Makefile.vmlinux
+@@ -33,6 +33,24 @@ targets += vmlinux
+ vmlinux: scripts/link-vmlinux.sh vmlinux.o $(KBUILD_LDS) FORCE
+ +$(call if_changed_dep,link_vmlinux)
+
++# module.builtin.ranges
++# ---------------------------------------------------------------------------
++ifdef CONFIG_BUILTIN_MODULE_RANGES
++__default: modules.builtin.ranges
++
++quiet_cmd_modules_builtin_ranges = GEN $@
++ cmd_modules_builtin_ranges = $(real-prereqs) > $@
++
++targets += modules.builtin.ranges
++modules.builtin.ranges: $(srctree)/scripts/generate_builtin_ranges.awk \
++ modules.builtin vmlinux.map vmlinux.o.map FORCE
++ $(call if_changed,modules_builtin_ranges)
++
++vmlinux.map: vmlinux
++ @:
++
++endif
++
+ # Add FORCE to the prequisites of a target to force it to be always rebuilt.
+ # ---------------------------------------------------------------------------
+
+diff --git a/scripts/Makefile.vmlinux_o b/scripts/Makefile.vmlinux_o
+index 6de297916ce68..48ba44ce3b64b 100644
+--- a/scripts/Makefile.vmlinux_o
++++ b/scripts/Makefile.vmlinux_o
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0-only
+
+ PHONY := __default
+-__default: vmlinux.o modules.builtin.modinfo modules.builtin
++__default: vmlinux.o modules.builtin.modinfo modules.builtin modules.builtin.objs
+
+ include include/config/auto.conf
+ include $(srctree)/scripts/Kbuild.include
+@@ -27,6 +27,18 @@ ifdef CONFIG_LTO_CLANG
+ initcalls-lds := .tmp_initcalls.lds
+ endif
+
++# Generate a linker script to delete CTF sections
++# -----------------------------------------------
++
++quiet_cmd_gen_remove_ctf.lds = GEN $@
++ cmd_gen_remove_ctf.lds = \
++ $(LD) -r --verbose | awk -f $(real-prereqs) > $@
++
++.tmp_remove-ctf.lds: $(srctree)/scripts/remove-ctf-lds.awk FORCE
++ $(call if_changed,gen_remove_ctf.lds)
++
++targets := .tmp_remove-ctf.lds
++
+ # objtool for vmlinux.o
+ # ---------------------------------------------------------------------------
+ #
+@@ -42,13 +54,18 @@ vmlinux-objtool-args-$(CONFIG_NOINSTR_VALIDATION) += --noinstr \
+
+ objtool-args = $(vmlinux-objtool-args-y) --link
+
+-# Link of vmlinux.o used for section mismatch analysis
++# Link of vmlinux.o used for section mismatch analysis: we also strip the CTF
++# section out at this stage, since ctfarchive gets it from the underlying object
++# files and linking it further is a waste of time.
+ # ---------------------------------------------------------------------------
+
++vmlinux-o-ld-args-$(CONFIG_BUILTIN_MODULE_RANGES) += -Map=$@.map
++
+ quiet_cmd_ld_vmlinux.o = LD $@
+ cmd_ld_vmlinux.o = \
+ $(LD) ${KBUILD_LDFLAGS} -r -o $@ \
+- $(addprefix -T , $(initcalls-lds)) \
++ $(vmlinux-o-ld-args-y) \
++ $(addprefix -T , $(initcalls-lds)) -T .tmp_remove-ctf.lds \
+ --whole-archive vmlinux.a --no-whole-archive \
+ --start-group $(KBUILD_VMLINUX_LIBS) --end-group \
+ $(cmd_objtool)
+@@ -58,7 +75,7 @@ define rule_ld_vmlinux.o
+ $(call cmd,gen_objtooldep)
+ endef
+
+-vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) FORCE
++vmlinux.o: $(initcalls-lds) vmlinux.a $(KBUILD_VMLINUX_LIBS) .tmp_remove-ctf.lds FORCE
+ $(call if_changed_rule,ld_vmlinux.o)
+
+ targets += vmlinux.o
+@@ -87,6 +104,19 @@ targets += modules.builtin
+ modules.builtin: modules.builtin.modinfo FORCE
+ $(call if_changed,modules_builtin)
+
++# module.builtin.objs
++# ---------------------------------------------------------------------------
++quiet_cmd_modules_builtin_objs = GEN $@
++ cmd_modules_builtin_objs = \
++ tr '\0' '\n' < $< | \
++ sed -n 's/^[[:alnum:]:_]*\.objs=//p' | \
++ tr ' ' '\n' | uniq | sed -e 's|:|: |' -e 's:|: :g' | \
++ tr -s ' ' > $@
++
++targets += modules.builtin.objs
++modules.builtin.objs: modules.builtin.modinfo FORCE
++ $(call if_changed,modules_builtin_objs)
++
+ # Add FORCE to the prequisites of a target to force it to be always rebuilt.
+ # ---------------------------------------------------------------------------
+
+diff --git a/scripts/ctf/.gitignore b/scripts/ctf/.gitignore
+new file mode 100644
+index 0000000000000..6a0eb1c3ceeab
+--- /dev/null
++++ b/scripts/ctf/.gitignore
+@@ -0,0 +1 @@
++ctfarchive
+diff --git a/scripts/ctf/Makefile b/scripts/ctf/Makefile
+new file mode 100644
+index 0000000000000..3b83f93bb9f9a
+--- /dev/null
++++ b/scripts/ctf/Makefile
+@@ -0,0 +1,5 @@
++ifdef CONFIG_CTF
++hostprogs-always-y := ctfarchive
++ctfarchive-objs := ctfarchive.o modules_builtin.o
++HOSTLDLIBS_ctfarchive := -lctf
++endif
+diff --git a/scripts/ctf/ctfarchive.c b/scripts/ctf/ctfarchive.c
+new file mode 100644
+index 0000000000000..92cc4912ed0ee
+--- /dev/null
++++ b/scripts/ctf/ctfarchive.c
+@@ -0,0 +1,413 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * ctfmerge.c: Read in CTF extracted from generated object files from a
++ * specified directory and generate a CTF archive whose members are the
++ * deduplicated CTF derived from those object files, split up by kernel
++ * module.
++ *
++ * Copyright (c) 2019, 2023, Oracle and/or its affiliates.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#define _GNU_SOURCE 1
++#include <errno.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <string.h>
++#include <ctf-api.h>
++#include "modules_builtin.h"
++
++static ctf_file_t *output;
++
++static int private_ctf_link_add_ctf(ctf_file_t *fp,
++ const char *name)
++{
++#if !defined (CTF_LINK_FINAL)
++ return ctf_link_add_ctf(fp, NULL, name);
++#else
++ /* Non-upstreamed, erroneously-broken API. */
++ return ctf_link_add_ctf(fp, NULL, name, NULL, 0);
++#endif
++}
++
++/*
++ * Add a file to the link.
++ */
++static void add_to_link(const char *fn)
++{
++ if (private_ctf_link_add_ctf(output, fn) < 0)
++ {
++ fprintf(stderr, "Cannot add CTF file %s: %s\n", fn,
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++}
++
++struct from_to
++{
++ char *from;
++ char *to;
++};
++
++/*
++ * The world's stupidest hash table of FROM -> TO.
++ */
++static struct from_to **from_tos[256];
++static size_t alloc_from_tos[256];
++static size_t num_from_tos[256];
++
++static unsigned char from_to_hash(const char *from)
++{
++ unsigned char hval = 0;
++
++ const char *p;
++ for (p = from; *p; p++)
++ hval += *p;
++
++ return hval;
++}
++
++/*
++ * Note that we will need to add a CU mapping later on.
++ *
++ * Present purely to work around a binutils bug that stops
++ * ctf_link_add_cu_mapping() working right when called repeatedly
++ * with the same FROM.
++ */
++static int add_cu_mapping(const char *from, const char *to)
++{
++ ssize_t i, j;
++
++ i = from_to_hash(from);
++
++ for (j = 0; j < num_from_tos[i]; j++)
++ if (strcmp(from, from_tos[i][j]->from) == 0) {
++ char *tmp;
++
++ free(from_tos[i][j]->to);
++ tmp = strdup(to);
++ if (!tmp)
++ goto oom;
++ from_tos[i][j]->to = tmp;
++ return 0;
++ }
++
++ if (num_from_tos[i] >= alloc_from_tos[i]) {
++ struct from_to **tmp;
++ if (alloc_from_tos[i] < 16)
++ alloc_from_tos[i] = 16;
++ else
++ alloc_from_tos[i] *= 2;
++
++ tmp = realloc(from_tos[i], alloc_from_tos[i] * sizeof(struct from_to *));
++ if (!tmp)
++ goto oom;
++
++ from_tos[i] = tmp;
++ }
++
++ j = num_from_tos[i];
++ from_tos[i][j] = malloc(sizeof(struct from_to));
++ if (from_tos[i][j] == NULL)
++ goto oom;
++ from_tos[i][j]->from = strdup(from);
++ from_tos[i][j]->to = strdup(to);
++ if (!from_tos[i][j]->from || !from_tos[i][j]->to)
++ goto oom;
++ num_from_tos[i]++;
++
++ return 0;
++ oom:
++ fprintf(stderr,
++ "out of memory in add_cu_mapping\n");
++ exit(1);
++}
++
++/*
++ * Finally tell binutils to add all the CU mappings, with duplicate FROMs
++ * replaced with the most recent one.
++ */
++static void commit_cu_mappings(void)
++{
++ ssize_t i, j;
++
++ for (i = 0; i < 256; i++)
++ for (j = 0; j < num_from_tos[i]; j++)
++ ctf_link_add_cu_mapping(output, from_tos[i][j]->from,
++ from_tos[i][j]->to);
++}
++
++/*
++ * Add a CU mapping to the link.
++ *
++ * CU mappings for built-in modules are added by suck_in_modules, below: here,
++ * we only want to add mappings for names ending in '.ko.ctf', i.e. external
++ * modules, which appear only in the filelist (since they are not built-in).
++ * The pathnames are stripped off because modules don't have any, and hyphens
++ * are translated into underscores.
++ */
++static void add_cu_mappings(const char *fn)
++{
++ const char *last_slash;
++ const char *modname = fn;
++ char *dynmodname = NULL;
++ char *dash;
++ size_t n;
++
++ last_slash = strrchr(modname, '/');
++ if (last_slash)
++ last_slash++;
++ else
++ last_slash = modname;
++ modname = last_slash;
++ if (strchr(modname, '-') != NULL)
++ {
++ dynmodname = strdup(last_slash);
++ dash = dynmodname;
++ while (dash != NULL) {
++ dash = strchr(dash, '-');
++ if (dash != NULL)
++ *dash = '_';
++ }
++ modname = dynmodname;
++ }
++
++ n = strlen(modname);
++ if (strcmp(modname + n - strlen(".ko.ctf"), ".ko.ctf") == 0) {
++ char *mod;
++
++ n -= strlen(".ko.ctf");
++ mod = strndup(modname, n);
++ add_cu_mapping(fn, mod);
++ free(mod);
++ }
++ free(dynmodname);
++}
++
++/*
++ * Add the passed names as mappings to "vmlinux".
++ */
++static void add_builtins(const char *fn)
++{
++ if (add_cu_mapping(fn, "vmlinux") < 0)
++ {
++ fprintf(stderr, "Cannot add CTF CU mapping from %s to \"vmlinux\"\n",
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++}
++
++/*
++ * Do something with a file, line by line.
++ */
++static void suck_in_lines(const char *filename, void (*func)(const char *line))
++{
++ FILE *f;
++ char *line = NULL;
++ size_t line_size = 0;
++
++ f = fopen(filename, "r");
++ if (f == NULL) {
++ fprintf(stderr, "Cannot open %s: %s\n", filename,
++ strerror(errno));
++ exit(1);
++ }
++
++ while (getline(&line, &line_size, f) >= 0) {
++ size_t len = strlen(line);
++
++ if (len == 0)
++ continue;
++
++ if (line[len-1] == '\n')
++ line[len-1] = '\0';
++
++ func(line);
++ }
++ free(line);
++
++ if (ferror(f)) {
++ fprintf(stderr, "Error reading from %s: %s\n", filename,
++ strerror(errno));
++ exit(1);
++ }
++
++ fclose(f);
++}
++
++/*
++ * Pull in modules.builtin.objs and turn it into CU mappings.
++ */
++static void suck_in_modules(const char *modules_builtin_name)
++{
++ struct modules_builtin_iter *i;
++ char *module_name = NULL;
++ char **paths;
++
++ i = modules_builtin_iter_new(modules_builtin_name);
++ if (i == NULL) {
++ fprintf(stderr, "Cannot iterate over builtin module file.\n");
++ exit(1);
++ }
++
++ while ((paths = modules_builtin_iter_next(i, &module_name)) != NULL) {
++ size_t j;
++
++ for (j = 0; paths[j] != NULL; j++) {
++ char *alloc = NULL;
++ char *path = paths[j];
++ /*
++ * If the name doesn't start in ./, add it, to match the names
++ * passed to add_builtins.
++ */
++ if (strncmp(paths[j], "./", 2) != 0) {
++ char *p;
++ if ((alloc = malloc(strlen(paths[j]) + 3)) == NULL) {
++ fprintf(stderr, "Cannot allocate memory for "
++ "builtin module object name %s.\n",
++ paths[j]);
++ exit(1);
++ }
++ p = alloc;
++ p = stpcpy(p, "./");
++ p = stpcpy(p, paths[j]);
++ path = alloc;
++ }
++ if (add_cu_mapping(path, module_name) < 0) {
++ fprintf(stderr, "Cannot add path -> module mapping for "
++ "%s -> %s: %s\n", path, module_name,
++ ctf_errmsg(ctf_errno(output)));
++ exit(1);
++ }
++ free (alloc);
++ }
++ free(paths);
++ }
++ free(module_name);
++ modules_builtin_iter_free(i);
++}
++
++/*
++ * Strip the leading .ctf. off all the module names: transform the default name
++ * from _CTF_SECTION into shared_ctf, and chop any trailing .ctf off (since that
++ * derives from the intermediate file used to keep the CTF out of the final
++ * module).
++ */
++static char *transform_module_names(ctf_file_t *fp __attribute__((__unused__)),
++ const char *name,
++ void *arg __attribute__((__unused__)))
++{
++ if (strcmp(name, ".ctf") == 0)
++ return strdup("shared_ctf");
++
++ if (strncmp(name, ".ctf", 4) == 0) {
++ size_t n = strlen (name);
++ if (strcmp(name + n - 4, ".ctf") == 0)
++ n -= 4;
++ return strndup(name + 4, n - 4);
++ }
++ return NULL;
++}
++
++int main(int argc, char *argv[])
++{
++ int err;
++ const char *output_file;
++ unsigned char *file_data = NULL;
++ size_t file_size;
++ FILE *fp;
++
++ if (argc != 5) {
++ fprintf(stderr, "Syntax: ctfarchive output-file objects.builtin modules.builtin\n");
++ fprintf(stderr, " filelist\n");
++ exit(1);
++ }
++
++ output_file = argv[1];
++
++ /*
++ * First pull in the input files and add them to the link.
++ */
++
++ output = ctf_create(&err);
++ if (!output) {
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ ctf_errmsg(err));
++ return 1;
++ }
++
++ suck_in_lines(argv[4], add_to_link);
++
++ /*
++ * Make sure that, even if all their types are shared, all modules have
++ * a ctf member that can be used as a child of the shared CTF.
++ */
++ suck_in_lines(argv[4], add_cu_mappings);
++
++ /*
++ * Then pull in the builtin objects list and add them as
++ * mappings to "vmlinux".
++ */
++
++ suck_in_lines(argv[2], add_builtins);
++
++ /*
++ * Finally, pull in the object -> module mapping and add it
++ * as appropriate mappings.
++ */
++ suck_in_modules(argv[3]);
++
++ /*
++ * Commit the added CU mappings.
++ */
++ commit_cu_mappings();
++
++ /*
++ * Arrange to fix up the module names.
++ */
++ ctf_link_set_memb_name_changer(output, transform_module_names, NULL);
++
++ /*
++ * Do the link.
++ */
++ if (ctf_link(output, CTF_LINK_SHARE_DUPLICATED |
++ CTF_LINK_EMPTY_CU_MAPPINGS) < 0)
++ goto ctf_err;
++
++ /*
++ * Write the output.
++ */
++
++ file_data = ctf_link_write(output, &file_size, 4096);
++ if (!file_data)
++ goto ctf_err;
++
++ fp = fopen(output_file, "w");
++ if (!fp)
++ goto err;
++
++ while ((err = fwrite(file_data, file_size, 1, fp)) == 0);
++ if (ferror(fp)) {
++ errno = ferror(fp);
++ goto err;
++ }
++ if (fclose(fp) < 0)
++ goto err;
++ free(file_data);
++ ctf_file_close(output);
++
++ return 0;
++err:
++ free(file_data);
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ strerror(errno));
++ return 1;
++ctf_err:
++ fprintf(stderr, "Cannot create output CTF archive: %s\n",
++ ctf_errmsg(ctf_errno(output)));
++ return 1;
++}
+diff --git a/scripts/ctf/modules_builtin.c b/scripts/ctf/modules_builtin.c
+new file mode 100644
+index 0000000000000..10af2bbc80e0c
+--- /dev/null
++++ b/scripts/ctf/modules_builtin.c
+@@ -0,0 +1,2 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++#include "../modules_builtin.c"
+diff --git a/scripts/ctf/modules_builtin.h b/scripts/ctf/modules_builtin.h
+new file mode 100644
+index 0000000000000..5e0299e5600c2
+--- /dev/null
++++ b/scripts/ctf/modules_builtin.h
+@@ -0,0 +1,2 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++#include "../modules_builtin.h"
+diff --git a/scripts/generate_builtin_ranges.awk b/scripts/generate_builtin_ranges.awk
+new file mode 100755
+index 0000000000000..51ae0458ffbdd
+--- /dev/null
++++ b/scripts/generate_builtin_ranges.awk
+@@ -0,0 +1,516 @@
++#!/usr/bin/gawk -f
++# SPDX-License-Identifier: GPL-2.0
++# generate_builtin_ranges.awk: Generate address range data for builtin modules
++# Written by Kris Van Hees <kris.van.hees@oracle.com>
++#
++# Usage: generate_builtin_ranges.awk modules.builtin vmlinux.map \
++# vmlinux.o.map [ <build-dir> ] > modules.builtin.ranges
++#
++
++# Return the module name(s) (if any) associated with the given object.
++#
++# If we have seen this object before, return information from the cache.
++# Otherwise, retrieve it from the corresponding .cmd file.
++#
++function get_module_info(fn, mod, obj, s) {
++ if (fn in omod)
++ return omod[fn];
++
++ if (match(fn, /\/[^/]+$/) == 0)
++ return "";
++
++ obj = fn;
++ mod = "";
++ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
++ if (getline s <fn == 1) {
++ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
++ mod = substr(s, RSTART + 16, RLENGTH - 16);
++ gsub(/['"]/, "", mod);
++ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
++ mod = substr(s, RSTART + 13, RLENGTH - 13);
++ }
++ close(fn);
++
++ # A single module (common case) also reflects objects that are not part
++ # of a module. Some of those objects have names that are also a module
++ # name (e.g. core). We check the associated module file name, and if
++ # they do not match, the object is not part of a module.
++ if (mod !~ / /) {
++ if (!(mod in mods))
++ mod = "";
++ }
++
++ gsub(/([^/ ]*\/)+/, "", mod);
++ gsub(/-/, "_", mod);
++
++ # At this point, mod is a single (valid) module name, or a list of
++ # module names (that do not need validation).
++ omod[obj] = mod;
++
++ return mod;
++}
++
++# Update the ranges entry for the given module 'mod' in section 'osect'.
++#
++# We use a modified absolute start address (soff + base) as index because we
++# may need to insert an anchor record later that must be at the start of the
++# section data, and the first module may very well start at the same address.
++# So, we use (addr << 1) + 1 to allow a possible anchor record to be placed at
++# (addr << 1). This is safe because the index is only used to sort the entries
++# before writing them out.
++#
++function update_entry(osect, mod, soff, eoff, sect, idx) {
++ sect = sect_in[osect];
++ idx = (soff + sect_base[osect]) * 2 + 1;
++ entries[idx] = sprintf("%s %08x-%08x %s", sect, soff, eoff, mod);
++ count[sect]++;
++}
++
++# Determine the kernel build directory to use (default is .).
++#
++BEGIN {
++ if (ARGC > 4) {
++ kdir = ARGV[ARGC - 1];
++ ARGV[ARGC - 1] = "";
++ } else
++ kdir = ".";
++}
++
++# (1) Build a lookup map of built-in module names.
++#
++# The first file argument is used as input (modules.builtin).
++#
++# Lines will be like:
++# kernel/crypto/lzo-rle.ko
++# and we record the object name "crypto/lzo-rle".
++#
++ARGIND == 1 {
++ sub(/kernel\//, ""); # strip off "kernel/" prefix
++ sub(/\.ko$/, ""); # strip off .ko suffix
++
++ mods[$1] = 1;
++ next;
++}
++
++# (2) Collect address information for each section.
++#
++# The second file argument is used as input (vmlinux.map).
++#
++# We collect the base address of the section in order to convert all addresses
++# in the section into offset values.
++#
++# We collect the address of the anchor (or first symbol in the section if there
++# is no explicit anchor) to allow users of the range data to calculate address
++# ranges based on the actual load address of the section in the running kernel.
++#
++# We collect the start address of any sub-section (section included in the top
++# level section being processed). This is needed when the final linking was
++# done using vmlinux.a because then the list of objects contained in each
++# section is to be obtained from vmlinux.o.map. The offset of the sub-section
++# is recorded here, to be used as an addend when processing vmlinux.o.map
++# later.
++#
++
++# Both GNU ld and LLVM lld linker map format are supported by converting LLVM
++# lld linker map records into equivalent GNU ld linker map records.
++#
++# The first record of the vmlinux.map file provides enough information to know
++# which format we are dealing with.
++#
++ARGIND == 2 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
++ map_is_lld = 1;
++ if (dbg)
++ printf "NOTE: %s uses LLVM lld linker map format\n", FILENAME >"/dev/stderr";
++ next;
++}
++
++# (LLD) Convert a section record fronm lld format to ld format.
++#
++# lld: ffffffff82c00000 2c00000 2493c0 8192 .data
++# ->
++# ld: .data 0xffffffff82c00000 0x2493c0 load address 0x0000000002c00000
++#
++ARGIND == 2 && map_is_lld && NF == 5 && /[0-9] [^ ]+$/ {
++ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
++}
++
++# (LLD) Convert an anchor record from lld format to ld format.
++#
++# lld: ffffffff81000000 1000000 0 1 _text = .
++# ->
++# ld: 0xffffffff81000000 _text = .
++#
++ARGIND == 2 && map_is_lld && !anchor && NF == 7 && raw_addr == "0x"$1 && $6 == "=" && $7 == "." {
++ $0 = " 0x"$1 " " $5 " = .";
++}
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++# lld: 11480 11480 1f07 16 vmlinux.a(arch/x86/events/amd/uncore.o):(.text)
++# ->
++# ld: .text 0x0000000000011480 0x1f07 arch/x86/events/amd/uncore.o
++#
++ARGIND == 2 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
++ gsub(/\)/, "");
++ sub(/ vmlinux\.a\(/, " ");
++ sub(/:\(/, " ");
++ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (LLD) Convert a symbol record from lld format to ld format.
++#
++# We only care about these while processing a section for which no anchor has
++# been determined yet.
++#
++# lld: ffffffff82a859a4 2a859a4 0 1 btf_ksym_iter_id
++# ->
++# ld: 0xffffffff82a859a4 btf_ksym_iter_id
++#
++ARGIND == 2 && map_is_lld && sect && !anchor && NF == 5 && $5 ~ /^[_A-Za-z][_A-Za-z0-9]*$/ {
++ $0 = " 0x"$1 " " $5;
++}
++
++# (LLD) We do not need any other ldd linker map records.
++#
++ARGIND == 2 && map_is_lld && /^[0-9a-f]{16} / {
++ next;
++}
++
++# (LD) Section records with just the section name at the start of the line
++# need to have the next line pulled in to determine whether it is a
++# loadable section. If it is, the next line will contains a hex value
++# as first and second items.
++#
++ARGIND == 2 && !map_is_lld && NF == 1 && /^[^ ]/ {
++ s = $0;
++ getline;
++ if ($1 !~ /^0x/ || $2 !~ /^0x/)
++ next;
++
++ $0 = s " " $0;
++}
++
++# (LD) Object records with just the section name denote records with a long
++# section name for which the remainder of the record can be found on the
++# next line.
++#
++# (This is also needed for vmlinux.o.map, when used.)
++#
++ARGIND >= 2 && !map_is_lld && NF == 1 && /^ [^ \*]/ {
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# Beginning a new section - done with the previous one (if any).
++#
++ARGIND == 2 && /^[^ ]/ {
++ sect = 0;
++}
++
++# Process a loadable section (we only care about .-sections).
++#
++# Record the section name and its base address.
++# We also record the raw (non-stripped) address of the section because it can
++# be used to identify an anchor record.
++#
++# Note:
++# Since some AWK implementations cannot handle large integers, we strip off the
++# first 4 hex digits from the address. This is safe because the kernel space
++# is not large enough for addresses to extend into those digits. The portion
++# to strip off is stored in addr_prefix as a regexp, so further clauses can
++# perform a simple substitution to do the address stripping.
++#
++ARGIND == 2 && /^\./ {
++ # Explicitly ignore a few sections that are not relevant here.
++ if ($1 ~ /^\.orc_/ || $1 ~ /_sites$/ || $1 ~ /\.percpu/)
++ next;
++
++ # Sections with a 0-address can be ignored as well.
++ if ($2 ~ /^0x0+$/)
++ next;
++
++ raw_addr = $2;
++ addr_prefix = "^" substr($2, 1, 6);
++ base = $2;
++ sub(addr_prefix, "0x", base);
++ base = strtonum(base);
++ sect = $1;
++ anchor = 0;
++ sect_base[sect] = base;
++ sect_size[sect] = strtonum($3);
++
++ if (dbg)
++ printf "[%s] BASE %016x\n", sect, base >"/dev/stderr";
++
++ next;
++}
++
++# If we are not in a section we care about, we ignore the record.
++#
++ARGIND == 2 && !sect {
++ next;
++}
++
++# Record the first anchor symbol for the current section.
++#
++# An anchor record for the section bears the same raw address as the section
++# record.
++#
++ARGIND == 2 && !anchor && NF == 4 && raw_addr == $1 && $3 == "=" && $4 == "." {
++ anchor = sprintf("%s %08x-%08x = %s", sect, 0, 0, $2);
++ sect_anchor[sect] = anchor;
++
++ if (dbg)
++ printf "[%s] ANCHOR %016x = %s (.)\n", sect, 0, $2 >"/dev/stderr";
++
++ next;
++}
++
++# If no anchor record was found for the current section, use the first symbol
++# in the section as anchor.
++#
++ARGIND == 2 && !anchor && NF == 2 && $1 ~ /^0x/ && $2 !~ /^0x/ {
++ addr = $1;
++ sub(addr_prefix, "0x", addr);
++ addr = strtonum(addr) - base;
++ anchor = sprintf("%s %08x-%08x = %s", sect, addr, addr, $2);
++ sect_anchor[sect] = anchor;
++
++ if (dbg)
++ printf "[%s] ANCHOR %016x = %s\n", sect, addr, $2 >"/dev/stderr";
++
++ next;
++}
++
++# The first occurrence of a section name in an object record establishes the
++# addend (often 0) for that section. This information is needed to handle
++# sections that get combined in the final linking of vmlinux (e.g. .head.text
++# getting included at the start of .text).
++#
++# If the section does not have a base yet, use the base of the encapsulating
++# section.
++#
++ARGIND == 2 && sect && NF == 4 && /^ [^ \*]/ && !($1 in sect_addend) {
++ if (!($1 in sect_base)) {
++ sect_base[$1] = base;
++
++ if (dbg)
++ printf "[%s] BASE %016x\n", $1, base >"/dev/stderr";
++ }
++
++ addr = $2;
++ sub(addr_prefix, "0x", addr);
++ addr = strtonum(addr);
++ sect_addend[$1] = addr - sect_base[$1];
++ sect_in[$1] = sect;
++
++ if (dbg)
++ printf "[%s] ADDEND %016x - %016x = %016x\n", $1, addr, base, sect_addend[$1] >"/dev/stderr";
++
++ # If the object is vmlinux.o then we will need vmlinux.o.map to get the
++ # actual offsets of objects.
++ if ($4 == "vmlinux.o")
++ need_o_map = 1;
++}
++
++# (3) Collect offset ranges (relative to the section base address) for built-in
++# modules.
++#
++# If the final link was done using the actual objects, vmlinux.map contains all
++# the information we need (see section (3a)).
++# If linking was done using vmlinux.a as intermediary, we will need to process
++# vmlinux.o.map (see section (3b)).
++
++# (3a) Determine offset range info using vmlinux.map.
++#
++# Since we are already processing vmlinux.map, the top level section that is
++# being processed is already known. If we do not have a base address for it,
++# we do not need to process records for it.
++#
++# Given the object name, we determine the module(s) (if any) that the current
++# object is associated with.
++#
++# If we were already processing objects for a (list of) module(s):
++# - If the current object belongs to the same module(s), update the range data
++# to include the current object.
++# - Otherwise, ensure that the end offset of the range is valid.
++#
++# If the current object does not belong to a built-in module, ignore it.
++#
++# If it does, we add a new built-in module offset range record.
++#
++ARGIND == 2 && !need_o_map && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
++ if (!(sect in sect_base))
++ next;
++
++ # Turn the address into an offset from the section base.
++ soff = $2;
++ sub(addr_prefix, "0x", soff);
++ soff = strtonum(soff) - sect_base[sect];
++ eoff = soff + strtonum($3);
++
++ # Determine which (if any) built-in modules the object belongs to.
++ mod = get_module_info($4);
++
++ # If we are processing a built-in module:
++ # - If the current object is within the same module, we update its
++ # entry by extending the range and move on
++ # - Otherwise:
++ # + If we are still processing within the same main section, we
++ # validate the end offset against the start offset of the
++ # current object (e.g. .rodata.str1.[18] objects are often
++ # listed with an incorrect size in the linker map)
++ # + Otherwise, we validate the end offset against the section
++ # size
++ if (mod_name) {
++ if (mod == mod_name) {
++ mod_eoff = eoff;
++ update_entry(mod_sect, mod_name, mod_soff, eoff);
++
++ next;
++ } else if (sect == sect_in[mod_sect]) {
++ if (mod_eoff > soff)
++ update_entry(mod_sect, mod_name, mod_soff, soff);
++ } else {
++ v = sect_size[sect_in[mod_sect]];
++ if (mod_eoff > v)
++ update_entry(mod_sect, mod_name, mod_soff, v);
++ }
++ }
++
++ mod_name = mod;
++
++ # If we encountered an object that is not part of a built-in module, we
++ # do not need to record any data.
++ if (!mod)
++ next;
++
++ # At this point, we encountered the start of a new built-in module.
++ mod_name = mod;
++ mod_soff = soff;
++ mod_eoff = eoff;
++ mod_sect = $1;
++ update_entry($1, mod, soff, mod_eoff);
++
++ next;
++}
++
++# If we do not need to parse the vmlinux.o.map file, we are done.
++#
++ARGIND == 3 && !need_o_map {
++ if (dbg)
++ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
++ exit;
++}
++
++# (3) Collect offset ranges (relative to the section base address) for built-in
++# modules.
++#
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++ARGIND == 3 && map_is_lld && NF == 5 && $5 ~ /:\(/ {
++ gsub(/\)/, "");
++ sub(/:\(/, " ");
++
++ sect = $6;
++ if (!(sect in sect_addend))
++ next;
++
++ sub(/ vmlinux\.a\(/, " ");
++ $0 = " "sect " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (3b) Determine offset range info using vmlinux.o.map.
++#
++# If we do not know an addend for the object's section, we are interested in
++# anything within that section.
++#
++# Determine the top-level section that the object's section was included in
++# during the final link. This is the section name offset range data will be
++# associated with for this object.
++#
++# The remainder of the processing of the current object record follows the
++# procedure outlined in (3a).
++#
++ARGIND == 3 && /^ [^ ]/ && NF == 4 && $3 != "0x0" {
++ osect = $1;
++ if (!(osect in sect_addend))
++ next;
++
++ # We need to work with the main section.
++ sect = sect_in[osect];
++
++ # Turn the address into an offset from the section base.
++ soff = $2;
++ sub(addr_prefix, "0x", soff);
++ soff = strtonum(soff) + sect_addend[osect];
++ eoff = soff + strtonum($3);
++
++ # Determine which (if any) built-in modules the object belongs to.
++ mod = get_module_info($4);
++
++ # If we are processing a built-in module:
++ # - If the current object is within the same module, we update its
++ # entry by extending the range and move on
++ # - Otherwise:
++ # + If we are still processing within the same main section, we
++ # validate the end offset against the start offset of the
++ # current object (e.g. .rodata.str1.[18] objects are often
++ # listed with an incorrect size in the linker map)
++ # + Otherwise, we validate the end offset against the section
++ # size
++ if (mod_name) {
++ if (mod == mod_name) {
++ mod_eoff = eoff;
++ update_entry(mod_sect, mod_name, mod_soff, eoff);
++
++ next;
++ } else if (sect == sect_in[mod_sect]) {
++ if (mod_eoff > soff)
++ update_entry(mod_sect, mod_name, mod_soff, soff);
++ } else {
++ v = sect_size[sect_in[mod_sect]];
++ if (mod_eoff > v)
++ update_entry(mod_sect, mod_name, mod_soff, v);
++ }
++ }
++
++ mod_name = mod;
++
++ # If we encountered an object that is not part of a built-in module, we
++ # do not need to record any data.
++ if (!mod)
++ next;
++
++ # At this point, we encountered the start of a new built-in module.
++ mod_name = mod;
++ mod_soff = soff;
++ mod_eoff = eoff;
++ mod_sect = osect;
++ update_entry(osect, mod, soff, mod_eoff);
++
++ next;
++}
++
++# (4) Generate the output.
++#
++# Anchor records are added for each section that contains offset range data
++# records. They are added at an adjusted section base address (base << 1) to
++# ensure they come first in the second records (see update_entry() above for
++# more information).
++#
++# All entries are sorted by (adjusted) address to ensure that the output can be
++# parsed in strict ascending address order.
++#
++END {
++ for (sect in count) {
++ if (sect in sect_anchor)
++ entries[sect_base[sect] * 2] = sect_anchor[sect];
++ }
++
++ n = asorti(entries, indices);
++ for (i = 1; i <= n; i++)
++ print entries[indices[i]];
++}
+diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
+index f48d72d22dc2a..d7e6cd7781256 100644
+--- a/scripts/mod/modpost.c
++++ b/scripts/mod/modpost.c
+@@ -733,6 +733,7 @@ static const char *const section_white_list[] =
+ ".comment*",
+ ".debug*",
+ ".zdebug*", /* Compressed debug sections. */
++ ".ctf", /* Type info */
+ ".GCC.command.line", /* record-gcc-switches */
+ ".mdebug*", /* alpha, score, mips etc. */
+ ".pdr", /* alpha, score, mips etc. */
+diff --git a/scripts/modules_builtin.c b/scripts/modules_builtin.c
+new file mode 100644
+index 0000000000000..df52932a4417b
+--- /dev/null
++++ b/scripts/modules_builtin.c
+@@ -0,0 +1,200 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * A simple modules_builtin reader.
++ *
++ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#include <errno.h>
++#include <stdio.h>
++#include <stdlib.h>
++#include <string.h>
++
++#include "modules_builtin.h"
++
++/*
++ * Read a modules.builtin.objs file and translate it into a stream of
++ * name / module-name pairs.
++ */
++
++/*
++ * Construct a modules.builtin.objs iterator.
++ */
++struct modules_builtin_iter *
++modules_builtin_iter_new(const char *modules_builtin_file)
++{
++ struct modules_builtin_iter *i;
++
++ i = calloc(1, sizeof(struct modules_builtin_iter));
++ if (i == NULL)
++ return NULL;
++
++ i->f = fopen(modules_builtin_file, "r");
++
++ if (i->f == NULL) {
++ fprintf(stderr, "Cannot open builtin module file %s: %s\n",
++ modules_builtin_file, strerror(errno));
++ return NULL;
++ }
++
++ return i;
++}
++
++/*
++ * Iterate, returning a new null-terminated array of object file names, and a
++ * new dynamically-allocated module name. (The module name passed in is freed.)
++ *
++ * The array of object file names should be freed by the caller: the strings it
++ * points to are owned by the iterator, and should not be freed.
++ */
++
++char ** __attribute__((__nonnull__))
++modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name)
++{
++ size_t npaths = 1;
++ char **module_paths;
++ char *last_slash;
++ char *last_dot;
++ char *trailing_linefeed;
++ char *object_name = i->line;
++ char *dash;
++ int composite = 0;
++
++ /*
++ * Read in all module entries, computing the suffixless, pathless name
++ * of the module and building the next arrayful of object file names for
++ * return.
++ *
++ * Modules can consist of multiple files: in this case, the portion
++ * before the colon is the path to the module (as before): the portion
++ * after the colon is a space-separated list of files that should be
++ * considered part of this module. In this case, the portion before the
++ * name is an "object file" that does not actually exist: it is merged
++ * into built-in.a without ever being written out.
++ *
++ * All module names have - translated to _, to match what is done to the
++ * names of the same things when built as modules.
++ */
++
++ /*
++ * Reinvocation of exhausted iterator. Return NULL, once.
++ */
++retry:
++ if (getline(&i->line, &i->line_size, i->f) < 0) {
++ if (ferror(i->f)) {
++ fprintf(stderr, "Error reading from modules_builtin file:"
++ " %s\n", strerror(errno));
++ exit(1);
++ }
++ rewind(i->f);
++ return NULL;
++ }
++
++ if (i->line[0] == '\0')
++ goto retry;
++
++ trailing_linefeed = strchr(i->line, '\n');
++ if (trailing_linefeed != NULL)
++ *trailing_linefeed = '\0';
++
++ /*
++ * Slice the line in two at the colon, if any. If there is anything
++ * past the ': ', this is a composite module. (We allow for no colon
++ * for robustness, even though one should always be present.)
++ */
++ if (strchr(i->line, ':') != NULL) {
++ char *name_start;
++
++ object_name = strchr(i->line, ':');
++ *object_name = '\0';
++ object_name++;
++ name_start = object_name + strspn(object_name, " \n");
++ if (*name_start != '\0') {
++ composite = 1;
++ object_name = name_start;
++ }
++ }
++
++ /*
++ * Figure out the module name.
++ */
++ last_slash = strrchr(i->line, '/');
++ last_slash = (!last_slash) ? i->line :
++ last_slash + 1;
++ free(*module_name);
++ *module_name = strdup(last_slash);
++ dash = *module_name;
++
++ while (dash != NULL) {
++ dash = strchr(dash, '-');
++ if (dash != NULL)
++ *dash = '_';
++ }
++
++ last_dot = strrchr(*module_name, '.');
++ if (last_dot != NULL)
++ *last_dot = '\0';
++
++ /*
++ * Multifile separator? Object file names explicitly stated:
++ * slice them up and shuffle them in.
++ *
++ * The array size may be an overestimate if any object file
++ * names start or end with spaces (very unlikely) but cannot be
++ * an underestimate. (Check for it anyway.)
++ */
++ if (composite) {
++ char *one_object;
++
++ for (npaths = 0, one_object = object_name;
++ one_object != NULL;
++ npaths++, one_object = strchr(one_object + 1, ' '));
++ }
++
++ module_paths = malloc((npaths + 1) * sizeof(char *));
++ if (!module_paths) {
++ fprintf(stderr, "%s: out of memory on module %s\n", __func__,
++ *module_name);
++ exit(1);
++ }
++
++ if (composite) {
++ char *one_object;
++ size_t i = 0;
++
++ while ((one_object = strsep(&object_name, " ")) != NULL) {
++ if (i >= npaths) {
++ fprintf(stderr, "%s: num_objs overflow on module "
++ "%s: this is a bug.\n", __func__,
++ *module_name);
++ exit(1);
++ }
++
++ module_paths[i++] = one_object;
++ }
++ } else
++ module_paths[0] = i->line; /* untransformed module name */
++
++ module_paths[npaths] = NULL;
++
++ return module_paths;
++}
++
++/*
++ * Free an iterator. Can be called while iteration is underway, so even
++ * state that is freed at the end of iteration must be freed here too.
++ */
++void
++modules_builtin_iter_free(struct modules_builtin_iter *i)
++{
++ if (i == NULL)
++ return;
++ fclose(i->f);
++ free(i->line);
++ free(i);
++}
+diff --git a/scripts/modules_builtin.h b/scripts/modules_builtin.h
+new file mode 100644
+index 0000000000000..5138792b42ef0
+--- /dev/null
++++ b/scripts/modules_builtin.h
+@@ -0,0 +1,48 @@
++/* SPDX-License-Identifier: GPL-2.0 */
++/*
++ * A simple modules.builtin.objs reader.
++ *
++ * (C) 2014, 2022 Oracle, Inc. All rights reserved.
++ *
++ * This program is free software; you can redistribute it and/or modify
++ * it under the terms of the GNU General Public License as published by
++ * the Free Software Foundation; either version 2 of the License, or
++ * (at your option) any later version.
++ */
++
++#ifndef _LINUX_MODULES_BUILTIN_H
++#define _LINUX_MODULES_BUILTIN_H
++
++#include <stdio.h>
++#include <stddef.h>
++
++/*
++ * modules.builtin.objs iteration state.
++ */
++struct modules_builtin_iter {
++ FILE *f;
++ char *line;
++ size_t line_size;
++};
++
++/*
++ * Construct a modules_builtin.objs iterator.
++ */
++struct modules_builtin_iter *
++modules_builtin_iter_new(const char *modules_builtin_file);
++
++/*
++ * Iterate, returning a new null-terminated array of object file names, and a
++ * new dynamically-allocated module name. (The module name passed in is freed.)
++ *
++ * The array of object file names should be freed by the caller: the strings it
++ * points to are owned by the iterator, and should not be freed.
++ */
++
++char ** __attribute__((__nonnull__))
++modules_builtin_iter_next(struct modules_builtin_iter *i, char **module_name);
++
++void
++modules_builtin_iter_free(struct modules_builtin_iter *i);
++
++#endif
+diff --git a/scripts/package/kernel.spec b/scripts/package/kernel.spec
+index c52d517b93647..8f75906a96314 100644
+--- a/scripts/package/kernel.spec
++++ b/scripts/package/kernel.spec
+@@ -53,12 +53,18 @@ patch -p1 < %{SOURCE2}
+
+ %build
+ %{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release}
++%if %{with_ctf}
++%{make} %{makeflags} KERNELRELEASE=%{KERNELRELEASE} KBUILD_BUILD_VERSION=%{release} ctf
++%endif
+
+ %install
+ mkdir -p %{buildroot}/lib/modules/%{KERNELRELEASE}
+ cp $(%{make} %{makeflags} -s image_name) %{buildroot}/lib/modules/%{KERNELRELEASE}/vmlinuz
+ # DEPMOD=true makes depmod no-op. We do not package depmod-generated files.
+ %{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} DEPMOD=true modules_install
++%if %{with_ctf}
++%{make} %{makeflags} INSTALL_MOD_PATH=%{buildroot} ctf_install
++%endif
+ %{make} %{makeflags} INSTALL_HDR_PATH=%{buildroot}/usr headers_install
+ cp System.map %{buildroot}/lib/modules/%{KERNELRELEASE}
+ cp .config %{buildroot}/lib/modules/%{KERNELRELEASE}/config
+diff --git a/scripts/package/mkspec b/scripts/package/mkspec
+index ce201bfa8377c..aeb43c7ab1229 100755
+--- a/scripts/package/mkspec
++++ b/scripts/package/mkspec
+@@ -21,10 +21,16 @@ else
+ echo '%define with_devel 0'
+ fi
+
++if grep -q CONFIG_CTF=y include/config/auto.conf; then
++echo '%define with_ctf %{?_without_ctf: 0} %{?!_without_ctf: 1}'
++else
++echo '%define with_ctf 0'
++fi
+ cat<<EOF
+ %define ARCH ${ARCH}
+ %define KERNELRELEASE ${KERNELRELEASE}
+ %define pkg_release $("${srctree}/init/build-version")
++
+ EOF
+
+ cat "${srctree}/scripts/package/kernel.spec"
+diff --git a/scripts/remove-ctf-lds.awk b/scripts/remove-ctf-lds.awk
+new file mode 100644
+index 0000000000000..5d94d6ee99227
+--- /dev/null
++++ b/scripts/remove-ctf-lds.awk
+@@ -0,0 +1,12 @@
++# SPDX-License-Identifier: GPL-2.0
++# See Makefile.vmlinux_o
++
++BEGIN {
++ discards = 0; p = 0
++}
++
++/^====/ { p = 1; next; }
++p && /\.ctf/ { next; }
++p && !discards && /DISCARD/ { sub(/\} *$/, " *(.ctf) }"); discards = 1 }
++p && /^\}/ && !discards { print " /DISCARD/ : { *(.ctf) }"; }
++p { print $0; }
+diff --git a/scripts/verify_builtin_ranges.awk b/scripts/verify_builtin_ranges.awk
+new file mode 100755
+index 0000000000000..f513841da83e1
+--- /dev/null
++++ b/scripts/verify_builtin_ranges.awk
+@@ -0,0 +1,356 @@
++#!/usr/bin/gawk -f
++# SPDX-License-Identifier: GPL-2.0
++# verify_builtin_ranges.awk: Verify address range data for builtin modules
++# Written by Kris Van Hees <kris.van.hees@oracle.com>
++#
++# Usage: verify_builtin_ranges.awk modules.builtin.ranges System.map \
++# modules.builtin vmlinux.map vmlinux.o.map \
++# [ <build-dir> ]
++#
++
++# Return the module name(s) (if any) associated with the given object.
++#
++# If we have seen this object before, return information from the cache.
++# Otherwise, retrieve it from the corresponding .cmd file.
++#
++function get_module_info(fn, mod, obj, s) {
++ if (fn in omod)
++ return omod[fn];
++
++ if (match(fn, /\/[^/]+$/) == 0)
++ return "";
++
++ obj = fn;
++ mod = "";
++ fn = kdir "/" substr(fn, 1, RSTART) "." substr(fn, RSTART + 1) ".cmd";
++ if (getline s <fn == 1) {
++ if (match(s, /DKBUILD_MODFILE=['"]+[^'"]+/) > 0) {
++ mod = substr(s, RSTART + 16, RLENGTH - 16);
++ gsub(/['"]/, "", mod);
++ } else if (match(s, /RUST_MODFILE=[^ ]+/) > 0)
++ mod = substr(s, RSTART + 13, RLENGTH - 13);
++ } else {
++ print "ERROR: Failed to read: " fn "\n\n" \
++ " Invalid kernel build directory (" kdir ")\n" \
++ " or its content does not match " ARGV[1] >"/dev/stderr";
++ close(fn);
++ total = 0;
++ exit(1);
++ }
++ close(fn);
++
++ # A single module (common case) also reflects objects that are not part
++ # of a module. Some of those objects have names that are also a module
++ # name (e.g. core). We check the associated module file name, and if
++ # they do not match, the object is not part of a module.
++ if (mod !~ / /) {
++ if (!(mod in mods))
++ mod = "";
++ }
++
++ gsub(/([^/ ]*\/)+/, "", mod);
++ gsub(/-/, "_", mod);
++
++ # At this point, mod is a single (valid) module name, or a list of
++ # module names (that do not need validation).
++ omod[obj] = mod;
++
++ return mod;
++}
++
++# Return a representative integer value for a given hexadecimal address.
++#
++# Since all kernel addresses fall within the same memory region, we can safely
++# strip off the first 6 hex digits before performing the hex-to-dec conversion,
++# thereby avoiding integer overflows.
++#
++function addr2val(val) {
++ sub(/^0x/, "", val);
++ if (length(val) == 16)
++ val = substr(val, 5);
++ return strtonum("0x" val);
++}
++
++# Determine the kernel build directory to use (default is .).
++#
++BEGIN {
++ if (ARGC > 6) {
++ kdir = ARGV[ARGC - 1];
++ ARGV[ARGC - 1] = "";
++ } else
++ kdir = ".";
++}
++
++# (1) Load the built-in module address range data.
++#
++ARGIND == 1 {
++ ranges[FNR] = $0;
++ rcnt++;
++ next;
++}
++
++# (2) Annotate System.map symbols with module names.
++#
++ARGIND == 2 {
++ addr = addr2val($1);
++ name = $3;
++
++ while (addr >= mod_eaddr) {
++ if (sect_symb) {
++ if (sect_symb != name)
++ next;
++
++ sect_base = addr - sect_off;
++ if (dbg)
++ printf "[%s] BASE (%s) %016x - %016x = %016x\n", sect_name, sect_symb, addr, sect_off, sect_base >"/dev/stderr";
++ sect_symb = 0;
++ }
++
++ if (++ridx > rcnt)
++ break;
++
++ $0 = ranges[ridx];
++ sub(/-/, " ");
++ if ($4 != "=") {
++ sub(/-/, " ");
++ mod_saddr = strtonum("0x" $2) + sect_base;
++ mod_eaddr = strtonum("0x" $3) + sect_base;
++ $1 = $2 = $3 = "";
++ sub(/^ +/, "");
++ mod_name = $0;
++
++ if (dbg)
++ printf "[%s] %s from %016x to %016x\n", sect_name, mod_name, mod_saddr, mod_eaddr >"/dev/stderr";
++ } else {
++ sect_name = $1;
++ sect_off = strtonum("0x" $2);
++ sect_symb = $5;
++ }
++ }
++
++ idx = addr"-"name;
++ if (addr >= mod_saddr && addr < mod_eaddr)
++ sym2mod[idx] = mod_name;
++
++ next;
++}
++
++# Once we are done annotating the System.map, we no longer need the ranges data.
++#
++FNR == 1 && ARGIND == 3 {
++ delete ranges;
++}
++
++# (3) Build a lookup map of built-in module names.
++#
++# Lines from modules.builtin will be like:
++# kernel/crypto/lzo-rle.ko
++# and we record the object name "crypto/lzo-rle".
++#
++ARGIND == 3 {
++ sub(/kernel\//, ""); # strip off "kernel/" prefix
++ sub(/\.ko$/, ""); # strip off .ko suffix
++
++ mods[$1] = 1;
++ next;
++}
++
++# (4) Get a list of symbols (per object).
++#
++# Symbols by object are read from vmlinux.map, with fallback to vmlinux.o.map
++# if vmlinux is found to have inked in vmlinux.o.
++#
++
++# If we were able to get the data we need from vmlinux.map, there is no need to
++# process vmlinux.o.map.
++#
++FNR == 1 && ARGIND == 5 && total > 0 {
++ if (dbg)
++ printf "Note: %s is not needed.\n", FILENAME >"/dev/stderr";
++ exit;
++}
++
++# First determine whether we are dealing with a GNU ld or LLVM lld linker map.
++#
++ARGIND >= 4 && FNR == 1 && NF == 7 && $1 == "VMA" && $7 == "Symbol" {
++ map_is_lld = 1;
++ next;
++}
++
++# (LLD) Convert a section record fronm lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && /[0-9] [^ ]/ {
++ $0 = $5 " 0x"$1 " 0x"$3 " load address 0x"$2;
++}
++
++# (LLD) Convert an object record from lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /:\(\./ {
++ gsub(/\)/, "");
++ sub(/:\(/, " ");
++ sub(/ vmlinux\.a\(/, " ");
++ $0 = " "$6 " 0x"$1 " 0x"$3 " " $5;
++}
++
++# (LLD) Convert a symbol record from lld format to ld format.
++#
++ARGIND >= 4 && map_is_lld && NF == 5 && $5 ~ /^[A-Za-z_][A-Za-z0-9_]*$/ {
++ $0 = " 0x" $1 " " $5;
++}
++
++# (LLD) We do not need any other ldd linker map records.
++#
++ARGIND >= 4 && map_is_lld && /^[0-9a-f]{16} / {
++ next;
++}
++
++# Handle section records with long section names (spilling onto a 2nd line).
++#
++ARGIND >= 4 && !map_is_lld && NF == 1 && /^[^ ]/ {
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# Next section - previous one is done.
++#
++ARGIND >= 4 && /^[^ ]/ {
++ sect = 0;
++}
++
++# Get the (top level) section name.
++#
++ARGIND >= 4 && /^[^ ]/ && $2 ~ /^0x/ && $3 ~ /^0x/ {
++ # Empty section or per-CPU section - ignore.
++ if (NF < 3 || $1 ~ /\.percpu/) {
++ sect = 0;
++ next;
++ }
++
++ sect = $1;
++
++ next;
++}
++
++# If we are not currently in a section we care about, ignore records.
++#
++!sect {
++ next;
++}
++
++# Handle object records with long section names (spilling onto a 2nd line).
++#
++ARGIND >= 4 && /^ [^ \*]/ && NF == 1 {
++ # If the section name is long, the remainder of the entry is found on
++ # the next line.
++ s = $0;
++ getline;
++ $0 = s " " $0;
++}
++
++# If the object is vmlinux.o, we need to consult vmlinux.o.map for per-object
++# symbol information
++#
++ARGIND == 4 && /^ [^ ]/ && NF == 4 {
++ idx = sect":"$1;
++ if (!(idx in sect_addend)) {
++ sect_addend[idx] = addr2val($2);
++ if (dbg)
++ printf "ADDEND %s = %016x\n", idx, sect_addend[idx] >"/dev/stderr";
++ }
++ if ($4 == "vmlinux.o") {
++ need_o_map = 1;
++ next;
++ }
++}
++
++# If data from vmlinux.o.map is needed, we only process section and object
++# records from vmlinux.map to determine which section we need to pay attention
++# to in vmlinux.o.map. So skip everything else from vmlinux.map.
++#
++ARGIND == 4 && need_o_map {
++ next;
++}
++
++# Get module information for the current object.
++#
++ARGIND >= 4 && /^ [^ ]/ && NF == 4 {
++ msect = $1;
++ mod_name = get_module_info($4);
++ mod_eaddr = addr2val($2) + addr2val($3);
++
++ next;
++}
++
++# Process a symbol record.
++#
++# Evaluate the module information obtained from vmlinux.map (or vmlinux.o.map)
++# as follows:
++# - For all symbols in a given object:
++# - If the symbol is annotated with the same module name(s) that the object
++# belongs to, count it as a match.
++# - Otherwise:
++# - If the symbol is known to have duplicates of which at least one is
++# in a built-in module, disregard it.
++# - If the symbol us not annotated with any module name(s) AND the
++# object belongs to built-in modules, count it as missing.
++# - Otherwise, count it as a mismatch.
++#
++ARGIND >= 4 && /^ / && NF == 2 && $1 ~ /^0x/ {
++ idx = sect":"msect;
++ if (!(idx in sect_addend))
++ next;
++
++ addr = addr2val($1);
++
++ # Handle the rare but annoying case where a 0-size symbol is placed at
++ # the byte *after* the module range. Based on vmlinux.map it will be
++ # considered part of the current object, but it falls just beyond the
++ # module address range. Unfortunately, its address could be at the
++ # start of another built-in module, so the only safe thing to do is to
++ # ignore it.
++ if (mod_name && addr == mod_eaddr)
++ next;
++
++ # If we are processing vmlinux.o.map, we need to apply the base address
++ # of the section to the relative address on the record.
++ #
++ if (ARGIND == 5)
++ addr += sect_addend[idx];
++
++ idx = addr"-"$2;
++ mod = "";
++ if (idx in sym2mod) {
++ mod = sym2mod[idx];
++ if (sym2mod[idx] == mod_name) {
++ mod_matches++;
++ matches++;
++ } else if (mod_name == "") {
++ print $2 " in " sym2mod[idx] " (should NOT be)";
++ mismatches++;
++ } else {
++ print $2 " in " sym2mod[idx] " (should be " mod_name ")";
++ mismatches++;
++ }
++ } else if (mod_name != "") {
++ print $2 " should be in " mod_name;
++ missing++;
++ } else
++ matches++;
++
++ total++;
++
++ next;
++}
++
++# Issue the comparison report.
++#
++END {
++ if (total) {
++ printf "Verification of %s:\n", ARGV[1];
++ printf " Correct matches: %6d (%d%% of total)\n", matches, 100 * matches / total;
++ printf " Module matches: %6d (%d%% of matches)\n", mod_matches, 100 * mod_matches / matches;
++ printf " Mismatches: %6d (%d%% of total)\n", mismatches, 100 * mismatches / total;
++ printf " Missing: %6d (%d%% of total)\n", missing, 100 * missing / total;
++ }
++}
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-09-04 13:50 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-09-04 13:50 UTC (permalink / raw
To: gentoo-commits
commit: 1dac9a861cfca1e7fbacf1065567d710ab7ca580
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Sep 4 13:48:09 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Sep 4 13:48:09 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=1dac9a86
Linuxpatch 6.10.8
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
1007_linux-6.10.8.patch | 6428 +++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 6428 insertions(+)
diff --git a/1007_linux-6.10.8.patch b/1007_linux-6.10.8.patch
new file mode 100644
index 00000000..6758e614
--- /dev/null
+++ b/1007_linux-6.10.8.patch
@@ -0,0 +1,6428 @@
+diff --git a/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml b/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml
+index 783c27591e564..c39affb5f9983 100644
+--- a/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml
++++ b/Documentation/devicetree/bindings/usb/microchip,usb2514.yaml
+@@ -10,7 +10,7 @@ maintainers:
+ - Fabio Estevam <festevam@gmail.com>
+
+ allOf:
+- - $ref: usb-hcd.yaml#
++ - $ref: usb-device.yaml#
+
+ properties:
+ compatible:
+@@ -35,6 +35,13 @@ required:
+ - compatible
+ - reg
+
++patternProperties:
++ "^.*@[0-9a-f]{1,2}$":
++ description: The hard wired USB devices
++ type: object
++ $ref: /schemas/usb/usb-device.yaml
++ additionalProperties: true
++
+ unevaluatedProperties: false
+
+ examples:
+diff --git a/Makefile b/Makefile
+index ab77d171e268d..2e5ac6ab3d476 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 7
++SUBLEVEL = 8
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi
+index 52a0f6ee426f9..bcf4d9c870ec9 100644
+--- a/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi
++++ b/arch/arm/boot/dts/nxp/imx/imx6dl-yapp43-common.dtsi
+@@ -274,24 +274,24 @@ leds: led-controller@30 {
+
+ led@0 {
+ chan-name = "R";
+- led-cur = /bits/ 8 <0x20>;
+- max-cur = /bits/ 8 <0x60>;
++ led-cur = /bits/ 8 <0x6e>;
++ max-cur = /bits/ 8 <0xc8>;
+ reg = <0>;
+ color = <LED_COLOR_ID_RED>;
+ };
+
+ led@1 {
+ chan-name = "G";
+- led-cur = /bits/ 8 <0x20>;
+- max-cur = /bits/ 8 <0x60>;
++ led-cur = /bits/ 8 <0xbe>;
++ max-cur = /bits/ 8 <0xc8>;
+ reg = <1>;
+ color = <LED_COLOR_ID_GREEN>;
+ };
+
+ led@2 {
+ chan-name = "B";
+- led-cur = /bits/ 8 <0x20>;
+- max-cur = /bits/ 8 <0x60>;
++ led-cur = /bits/ 8 <0xbe>;
++ max-cur = /bits/ 8 <0xc8>;
+ reg = <2>;
+ color = <LED_COLOR_ID_BLUE>;
+ };
+diff --git a/arch/arm/boot/dts/ti/omap/omap3-n900.dts b/arch/arm/boot/dts/ti/omap/omap3-n900.dts
+index 07c5b963af78a..4bde3342bb959 100644
+--- a/arch/arm/boot/dts/ti/omap/omap3-n900.dts
++++ b/arch/arm/boot/dts/ti/omap/omap3-n900.dts
+@@ -781,7 +781,7 @@ accelerometer@1d {
+
+ mount-matrix = "-1", "0", "0",
+ "0", "1", "0",
+- "0", "0", "1";
++ "0", "0", "-1";
+ };
+
+ cam1: camera@3e {
+diff --git a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+index e5d3901f29136..e1f59bdcae497 100644
+--- a/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
++++ b/arch/arm64/boot/dts/freescale/imx8mp-beacon-kit.dts
+@@ -211,13 +211,12 @@ sound-wm8962 {
+
+ simple-audio-card,cpu {
+ sound-dai = <&sai3>;
++ frame-master;
++ bitclock-master;
+ };
+
+ simple-audio-card,codec {
+ sound-dai = <&wm8962>;
+- clocks = <&clk IMX8MP_CLK_IPP_DO_CLKO1>;
+- frame-master;
+- bitclock-master;
+ };
+ };
+ };
+@@ -499,10 +498,9 @@ &pcie_phy {
+ &sai3 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_sai3>;
+- assigned-clocks = <&clk IMX8MP_CLK_SAI3>,
+- <&clk IMX8MP_AUDIO_PLL2> ;
+- assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL2_OUT>;
+- assigned-clock-rates = <12288000>, <361267200>;
++ assigned-clocks = <&clk IMX8MP_CLK_SAI3>;
++ assigned-clock-parents = <&clk IMX8MP_AUDIO_PLL1_OUT>;
++ assigned-clock-rates = <12288000>;
+ fsl,sai-mclk-direction-output;
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
+index eb3f4cfb69863..ad77a96c5617b 100644
+--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
++++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352-mba93xxla.dts
+@@ -438,7 +438,7 @@ &usdhc2 {
+ pinctrl-0 = <&pinctrl_usdhc2_hs>, <&pinctrl_usdhc2_gpio>;
+ pinctrl-1 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>;
+ pinctrl-2 = <&pinctrl_usdhc2_uhs>, <&pinctrl_usdhc2_gpio>;
+- cd-gpios = <&gpio3 00 GPIO_ACTIVE_LOW>;
++ cd-gpios = <&gpio3 0 GPIO_ACTIVE_LOW>;
+ vmmc-supply = <®_usdhc2_vmmc>;
+ bus-width = <4>;
+ no-sdio;
+diff --git a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
+index 9d2328c185c90..fe951f86a96bd 100644
+--- a/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
++++ b/arch/arm64/boot/dts/freescale/imx93-tqma9352.dtsi
+@@ -19,7 +19,7 @@ reserved-memory {
+ linux,cma {
+ compatible = "shared-dma-pool";
+ reusable;
+- alloc-ranges = <0 0x60000000 0 0x40000000>;
++ alloc-ranges = <0 0x80000000 0 0x40000000>;
+ size = <0 0x10000000>;
+ linux,cma-default;
+ };
+diff --git a/arch/arm64/boot/dts/freescale/imx93.dtsi b/arch/arm64/boot/dts/freescale/imx93.dtsi
+index 4a3f42355cb8f..a0993022c102d 100644
+--- a/arch/arm64/boot/dts/freescale/imx93.dtsi
++++ b/arch/arm64/boot/dts/freescale/imx93.dtsi
+@@ -1105,7 +1105,7 @@ eqos: ethernet@428a0000 {
+ <&clk IMX93_CLK_SYS_PLL_PFD0_DIV2>;
+ assigned-clock-rates = <100000000>, <250000000>;
+ intf_mode = <&wakeupmix_gpr 0x28>;
+- snps,clk-csr = <0>;
++ snps,clk-csr = <6>;
+ nvmem-cells = <ð_mac2>;
+ nvmem-cell-names = "mac-address";
+ status = "disabled";
+diff --git a/arch/arm64/boot/dts/qcom/ipq5332.dtsi b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
+index 770d9c2fb4562..e3064568f0221 100644
+--- a/arch/arm64/boot/dts/qcom/ipq5332.dtsi
++++ b/arch/arm64/boot/dts/qcom/ipq5332.dtsi
+@@ -321,8 +321,8 @@ usb: usb@8af8800 {
+ reg = <0x08af8800 0x400>;
+
+ interrupts = <GIC_SPI 62 IRQ_TYPE_LEVEL_HIGH>,
+- <GIC_SPI 53 IRQ_TYPE_EDGE_BOTH>,
+- <GIC_SPI 52 IRQ_TYPE_EDGE_BOTH>;
++ <GIC_SPI 53 IRQ_TYPE_LEVEL_HIGH>,
++ <GIC_SPI 52 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "pwr_event",
+ "dp_hs_phy_irq",
+ "dm_hs_phy_irq";
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+index b063dd28149e7..7d03316c279df 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+@@ -648,7 +648,7 @@ &pcie4 {
+ };
+
+ &pcie4_phy {
+- vdda-phy-supply = <&vreg_l3j_0p8>;
++ vdda-phy-supply = <&vreg_l3i_0p8>;
+ vdda-pll-supply = <&vreg_l3e_1p2>;
+
+ status = "okay";
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+index df3577fcd93c9..2d7dedb7e30f2 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+@@ -459,7 +459,7 @@ &pcie4 {
+ };
+
+ &pcie4_phy {
+- vdda-phy-supply = <&vreg_l3j_0p8>;
++ vdda-phy-supply = <&vreg_l3i_0p8>;
+ vdda-pll-supply = <&vreg_l3e_1p2>;
+
+ status = "okay";
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100.dtsi b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+index 05e4d491ec18c..36c398e5fe501 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100.dtsi
++++ b/arch/arm64/boot/dts/qcom/x1e80100.dtsi
+@@ -2756,7 +2756,7 @@ pcie6a: pci@1bf8000 {
+
+ dma-coherent;
+
+- linux,pci-domain = <7>;
++ linux,pci-domain = <6>;
+ num-lanes = <2>;
+
+ interrupts = <GIC_SPI 773 IRQ_TYPE_LEVEL_HIGH>,
+@@ -2814,6 +2814,7 @@ &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+ "link_down";
+
+ power-domains = <&gcc GCC_PCIE_6A_GDSC>;
++ required-opps = <&rpmhpd_opp_nom>;
+
+ phys = <&pcie6a_phy>;
+ phy-names = "pciephy";
+@@ -2877,7 +2878,7 @@ pcie4: pci@1c08000 {
+
+ dma-coherent;
+
+- linux,pci-domain = <5>;
++ linux,pci-domain = <4>;
+ num-lanes = <2>;
+
+ interrupts = <GIC_SPI 141 IRQ_TYPE_LEVEL_HIGH>,
+@@ -2935,6 +2936,7 @@ &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+ "link_down";
+
+ power-domains = <&gcc GCC_PCIE_4_GDSC>;
++ required-opps = <&rpmhpd_opp_nom>;
+
+ phys = <&pcie4_phy>;
+ phy-names = "pciephy";
+diff --git a/arch/loongarch/include/asm/dma-direct.h b/arch/loongarch/include/asm/dma-direct.h
+deleted file mode 100644
+index 75ccd808a2af3..0000000000000
+--- a/arch/loongarch/include/asm/dma-direct.h
++++ /dev/null
+@@ -1,11 +0,0 @@
+-/* SPDX-License-Identifier: GPL-2.0 */
+-/*
+- * Copyright (C) 2020-2022 Loongson Technology Corporation Limited
+- */
+-#ifndef _LOONGARCH_DMA_DIRECT_H
+-#define _LOONGARCH_DMA_DIRECT_H
+-
+-dma_addr_t phys_to_dma(struct device *dev, phys_addr_t paddr);
+-phys_addr_t dma_to_phys(struct device *dev, dma_addr_t daddr);
+-
+-#endif /* _LOONGARCH_DMA_DIRECT_H */
+diff --git a/arch/loongarch/kernel/fpu.S b/arch/loongarch/kernel/fpu.S
+index 69a85f2479fba..6ab640101457c 100644
+--- a/arch/loongarch/kernel/fpu.S
++++ b/arch/loongarch/kernel/fpu.S
+@@ -530,6 +530,10 @@ SYM_FUNC_END(_restore_lasx_context)
+
+ #ifdef CONFIG_CPU_HAS_LBT
+ STACK_FRAME_NON_STANDARD _restore_fp
++#ifdef CONFIG_CPU_HAS_LSX
+ STACK_FRAME_NON_STANDARD _restore_lsx
++#endif
++#ifdef CONFIG_CPU_HAS_LASX
+ STACK_FRAME_NON_STANDARD _restore_lasx
+ #endif
++#endif
+diff --git a/arch/loongarch/kvm/switch.S b/arch/loongarch/kvm/switch.S
+index 80e988985a6ad..0c292f8184927 100644
+--- a/arch/loongarch/kvm/switch.S
++++ b/arch/loongarch/kvm/switch.S
+@@ -277,6 +277,10 @@ SYM_DATA(kvm_enter_guest_size, .quad kvm_enter_guest_end - kvm_enter_guest)
+
+ #ifdef CONFIG_CPU_HAS_LBT
+ STACK_FRAME_NON_STANDARD kvm_restore_fpu
++#ifdef CONFIG_CPU_HAS_LSX
+ STACK_FRAME_NON_STANDARD kvm_restore_lsx
++#endif
++#ifdef CONFIG_CPU_HAS_LASX
+ STACK_FRAME_NON_STANDARD kvm_restore_lasx
+ #endif
++#endif
+diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
+index d310b525fbf00..eeba2d26d1cb9 100644
+--- a/drivers/bluetooth/btnxpuart.c
++++ b/drivers/bluetooth/btnxpuart.c
+@@ -29,6 +29,7 @@
+ #define BTNXPUART_CHECK_BOOT_SIGNATURE 3
+ #define BTNXPUART_SERDEV_OPEN 4
+ #define BTNXPUART_IR_IN_PROGRESS 5
++#define BTNXPUART_FW_DOWNLOAD_ABORT 6
+
+ /* NXP HW err codes */
+ #define BTNXPUART_IR_HW_ERR 0xb0
+@@ -159,6 +160,7 @@ struct btnxpuart_dev {
+ u8 fw_name[MAX_FW_FILE_NAME_LEN];
+ u32 fw_dnld_v1_offset;
+ u32 fw_v1_sent_bytes;
++ u32 fw_dnld_v3_offset;
+ u32 fw_v3_offset_correction;
+ u32 fw_v1_expected_len;
+ u32 boot_reg_offset;
+@@ -436,6 +438,23 @@ static bool ps_wakeup(struct btnxpuart_dev *nxpdev)
+ return false;
+ }
+
++static void ps_cleanup(struct btnxpuart_dev *nxpdev)
++{
++ struct ps_data *psdata = &nxpdev->psdata;
++ u8 ps_state;
++
++ mutex_lock(&psdata->ps_lock);
++ ps_state = psdata->ps_state;
++ mutex_unlock(&psdata->ps_lock);
++
++ if (ps_state != PS_STATE_AWAKE)
++ ps_control(psdata->hdev, PS_STATE_AWAKE);
++
++ ps_cancel_timer(nxpdev);
++ cancel_work_sync(&psdata->work);
++ mutex_destroy(&psdata->ps_lock);
++}
++
+ static int send_ps_cmd(struct hci_dev *hdev, void *data)
+ {
+ struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+@@ -566,6 +585,7 @@ static int nxp_download_firmware(struct hci_dev *hdev)
+ nxpdev->fw_v1_sent_bytes = 0;
+ nxpdev->fw_v1_expected_len = HDR_LEN;
+ nxpdev->boot_reg_offset = 0;
++ nxpdev->fw_dnld_v3_offset = 0;
+ nxpdev->fw_v3_offset_correction = 0;
+ nxpdev->baudrate_changed = false;
+ nxpdev->timeout_changed = false;
+@@ -580,14 +600,23 @@ static int nxp_download_firmware(struct hci_dev *hdev)
+ !test_bit(BTNXPUART_FW_DOWNLOADING,
+ &nxpdev->tx_state),
+ msecs_to_jiffies(60000));
++
++ release_firmware(nxpdev->fw);
++ memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name));
++
+ if (err == 0) {
+- bt_dev_err(hdev, "FW Download Timeout.");
++ bt_dev_err(hdev, "FW Download Timeout. offset: %d",
++ nxpdev->fw_dnld_v1_offset ?
++ nxpdev->fw_dnld_v1_offset :
++ nxpdev->fw_dnld_v3_offset);
+ return -ETIMEDOUT;
+ }
++ if (test_bit(BTNXPUART_FW_DOWNLOAD_ABORT, &nxpdev->tx_state)) {
++ bt_dev_err(hdev, "FW Download Aborted");
++ return -EINTR;
++ }
+
+ serdev_device_set_flow_control(nxpdev->serdev, true);
+- release_firmware(nxpdev->fw);
+- memset(nxpdev->fw_name, 0, sizeof(nxpdev->fw_name));
+
+ /* Allow the downloaded FW to initialize */
+ msleep(1200);
+@@ -998,8 +1027,9 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
+ goto free_skb;
+ }
+
+- serdev_device_write_buf(nxpdev->serdev, nxpdev->fw->data + offset -
+- nxpdev->fw_v3_offset_correction, len);
++ nxpdev->fw_dnld_v3_offset = offset - nxpdev->fw_v3_offset_correction;
++ serdev_device_write_buf(nxpdev->serdev, nxpdev->fw->data +
++ nxpdev->fw_dnld_v3_offset, len);
+
+ free_skb:
+ kfree_skb(skb);
+@@ -1294,7 +1324,6 @@ static int btnxpuart_close(struct hci_dev *hdev)
+ {
+ struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+
+- ps_wakeup(nxpdev);
+ serdev_device_close(nxpdev->serdev);
+ skb_queue_purge(&nxpdev->txq);
+ kfree_skb(nxpdev->rx_skb);
+@@ -1429,16 +1458,22 @@ static void nxp_serdev_remove(struct serdev_device *serdev)
+ struct btnxpuart_dev *nxpdev = serdev_device_get_drvdata(serdev);
+ struct hci_dev *hdev = nxpdev->hdev;
+
+- /* Restore FW baudrate to fw_init_baudrate if changed.
+- * This will ensure FW baudrate is in sync with
+- * driver baudrate in case this driver is re-inserted.
+- */
+- if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
+- nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
+- nxp_set_baudrate_cmd(hdev, NULL);
++ if (is_fw_downloading(nxpdev)) {
++ set_bit(BTNXPUART_FW_DOWNLOAD_ABORT, &nxpdev->tx_state);
++ clear_bit(BTNXPUART_FW_DOWNLOADING, &nxpdev->tx_state);
++ wake_up_interruptible(&nxpdev->check_boot_sign_wait_q);
++ wake_up_interruptible(&nxpdev->fw_dnld_done_wait_q);
++ } else {
++ /* Restore FW baudrate to fw_init_baudrate if changed.
++ * This will ensure FW baudrate is in sync with
++ * driver baudrate in case this driver is re-inserted.
++ */
++ if (nxpdev->current_baudrate != nxpdev->fw_init_baudrate) {
++ nxpdev->new_baudrate = nxpdev->fw_init_baudrate;
++ nxp_set_baudrate_cmd(hdev, NULL);
++ }
+ }
+-
+- ps_cancel_timer(nxpdev);
++ ps_cleanup(nxpdev);
+ hci_unregister_dev(hdev);
+ hci_free_dev(hdev);
+ }
+diff --git a/drivers/char/tpm/tpm_ibmvtpm.c b/drivers/char/tpm/tpm_ibmvtpm.c
+index d3989b257f422..1e5b107d1f3bd 100644
+--- a/drivers/char/tpm/tpm_ibmvtpm.c
++++ b/drivers/char/tpm/tpm_ibmvtpm.c
+@@ -698,6 +698,10 @@ static int tpm_ibmvtpm_probe(struct vio_dev *vio_dev,
+ rc = tpm2_get_cc_attrs_tbl(chip);
+ if (rc)
+ goto init_irq_cleanup;
++
++ rc = tpm2_sessions_init(chip);
++ if (rc)
++ goto init_irq_cleanup;
+ }
+
+ return tpm_chip_register(chip);
+diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
+index 66b73c308ce67..b7318669485e4 100644
+--- a/drivers/cpufreq/amd-pstate-ut.c
++++ b/drivers/cpufreq/amd-pstate-ut.c
+@@ -160,14 +160,17 @@ static void amd_pstate_ut_check_perf(u32 index)
+ lowest_perf = AMD_CPPC_LOWEST_PERF(cap1);
+ }
+
+- if ((highest_perf != READ_ONCE(cpudata->highest_perf)) ||
+- (nominal_perf != READ_ONCE(cpudata->nominal_perf)) ||
++ if (highest_perf != READ_ONCE(cpudata->highest_perf) && !cpudata->hw_prefcore) {
++ pr_err("%s cpu%d highest=%d %d highest perf doesn't match\n",
++ __func__, cpu, highest_perf, cpudata->highest_perf);
++ goto skip_test;
++ }
++ if ((nominal_perf != READ_ONCE(cpudata->nominal_perf)) ||
+ (lowest_nonlinear_perf != READ_ONCE(cpudata->lowest_nonlinear_perf)) ||
+ (lowest_perf != READ_ONCE(cpudata->lowest_perf))) {
+ amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
+- pr_err("%s cpu%d highest=%d %d nominal=%d %d lowest_nonlinear=%d %d lowest=%d %d, they should be equal!\n",
+- __func__, cpu, highest_perf, cpudata->highest_perf,
+- nominal_perf, cpudata->nominal_perf,
++ pr_err("%s cpu%d nominal=%d %d lowest_nonlinear=%d %d lowest=%d %d, they should be equal!\n",
++ __func__, cpu, nominal_perf, cpudata->nominal_perf,
+ lowest_nonlinear_perf, cpudata->lowest_nonlinear_perf,
+ lowest_perf, cpudata->lowest_perf);
+ goto skip_test;
+diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
+index 67c4a6a0ef124..6f59403c91e03 100644
+--- a/drivers/cpufreq/amd-pstate.c
++++ b/drivers/cpufreq/amd-pstate.c
+@@ -329,7 +329,7 @@ static inline int pstate_enable(bool enable)
+ return 0;
+
+ for_each_present_cpu(cpu) {
+- unsigned long logical_id = topology_logical_die_id(cpu);
++ unsigned long logical_id = topology_logical_package_id(cpu);
+
+ if (test_bit(logical_id, &logical_proc_id_mask))
+ continue;
+diff --git a/drivers/dma/dw-edma/dw-hdma-v0-core.c b/drivers/dma/dw-edma/dw-hdma-v0-core.c
+index 10e8f0715114f..e3f8db4fe909a 100644
+--- a/drivers/dma/dw-edma/dw-hdma-v0-core.c
++++ b/drivers/dma/dw-edma/dw-hdma-v0-core.c
+@@ -17,8 +17,8 @@ enum dw_hdma_control {
+ DW_HDMA_V0_CB = BIT(0),
+ DW_HDMA_V0_TCB = BIT(1),
+ DW_HDMA_V0_LLP = BIT(2),
+- DW_HDMA_V0_LIE = BIT(3),
+- DW_HDMA_V0_RIE = BIT(4),
++ DW_HDMA_V0_LWIE = BIT(3),
++ DW_HDMA_V0_RWIE = BIT(4),
+ DW_HDMA_V0_CCS = BIT(8),
+ DW_HDMA_V0_LLE = BIT(9),
+ };
+@@ -195,25 +195,14 @@ static void dw_hdma_v0_write_ll_link(struct dw_edma_chunk *chunk,
+ static void dw_hdma_v0_core_write_chunk(struct dw_edma_chunk *chunk)
+ {
+ struct dw_edma_burst *child;
+- struct dw_edma_chan *chan = chunk->chan;
+ u32 control = 0, i = 0;
+- int j;
+
+ if (chunk->cb)
+ control = DW_HDMA_V0_CB;
+
+- j = chunk->bursts_alloc;
+- list_for_each_entry(child, &chunk->burst->list, list) {
+- j--;
+- if (!j) {
+- control |= DW_HDMA_V0_LIE;
+- if (!(chan->dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+- control |= DW_HDMA_V0_RIE;
+- }
+-
++ list_for_each_entry(child, &chunk->burst->list, list)
+ dw_hdma_v0_write_ll_data(chunk, i++, control, child->sz,
+ child->sar, child->dar);
+- }
+
+ control = DW_HDMA_V0_LLP | DW_HDMA_V0_TCB;
+ if (!chunk->cb)
+@@ -247,10 +236,11 @@ static void dw_hdma_v0_core_start(struct dw_edma_chunk *chunk, bool first)
+ if (first) {
+ /* Enable engine */
+ SET_CH_32(dw, chan->dir, chan->id, ch_en, BIT(0));
+- /* Interrupt enable&unmask - done, abort */
+- tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup) |
+- HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK |
+- HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN;
++ /* Interrupt unmask - stop, abort */
++ tmp = GET_CH_32(dw, chan->dir, chan->id, int_setup);
++ tmp &= ~(HDMA_V0_STOP_INT_MASK | HDMA_V0_ABORT_INT_MASK);
++ /* Interrupt enable - stop, abort */
++ tmp |= HDMA_V0_LOCAL_STOP_INT_EN | HDMA_V0_LOCAL_ABORT_INT_EN;
+ if (!(dw->chip->flags & DW_EDMA_CHIP_LOCAL))
+ tmp |= HDMA_V0_REMOTE_STOP_INT_EN | HDMA_V0_REMOTE_ABORT_INT_EN;
+ SET_CH_32(dw, chan->dir, chan->id, int_setup, tmp);
+diff --git a/drivers/dma/dw/core.c b/drivers/dma/dw/core.c
+index 5f7d690e3dbae..b341a6f1b0438 100644
+--- a/drivers/dma/dw/core.c
++++ b/drivers/dma/dw/core.c
+@@ -16,6 +16,7 @@
+ #include <linux/init.h>
+ #include <linux/interrupt.h>
+ #include <linux/io.h>
++#include <linux/log2.h>
+ #include <linux/mm.h>
+ #include <linux/module.h>
+ #include <linux/slab.h>
+@@ -621,12 +622,10 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+ struct dw_desc *prev;
+ struct dw_desc *first;
+ u32 ctllo, ctlhi;
+- u8 m_master = dwc->dws.m_master;
+- u8 lms = DWC_LLP_LMS(m_master);
++ u8 lms = DWC_LLP_LMS(dwc->dws.m_master);
+ dma_addr_t reg;
+ unsigned int reg_width;
+ unsigned int mem_width;
+- unsigned int data_width = dw->pdata->data_width[m_master];
+ unsigned int i;
+ struct scatterlist *sg;
+ size_t total_len = 0;
+@@ -660,7 +659,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+ mem = sg_dma_address(sg);
+ len = sg_dma_len(sg);
+
+- mem_width = __ffs(data_width | mem | len);
++ mem_width = __ffs(sconfig->src_addr_width | mem | len);
+
+ slave_sg_todev_fill_desc:
+ desc = dwc_desc_get(dwc);
+@@ -720,7 +719,7 @@ dwc_prep_slave_sg(struct dma_chan *chan, struct scatterlist *sgl,
+ lli_write(desc, sar, reg);
+ lli_write(desc, dar, mem);
+ lli_write(desc, ctlhi, ctlhi);
+- mem_width = __ffs(data_width | mem);
++ mem_width = __ffs(sconfig->dst_addr_width | mem);
+ lli_write(desc, ctllo, ctllo | DWC_CTLL_DST_WIDTH(mem_width));
+ desc->len = dlen;
+
+@@ -780,17 +779,93 @@ bool dw_dma_filter(struct dma_chan *chan, void *param)
+ }
+ EXPORT_SYMBOL_GPL(dw_dma_filter);
+
++static int dwc_verify_p_buswidth(struct dma_chan *chan)
++{
++ struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
++ struct dw_dma *dw = to_dw_dma(chan->device);
++ u32 reg_width, max_width;
++
++ if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
++ reg_width = dwc->dma_sconfig.dst_addr_width;
++ else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM)
++ reg_width = dwc->dma_sconfig.src_addr_width;
++ else /* DMA_MEM_TO_MEM */
++ return 0;
++
++ max_width = dw->pdata->data_width[dwc->dws.p_master];
++
++ /* Fall-back to 1-byte transfer width if undefined */
++ if (reg_width == DMA_SLAVE_BUSWIDTH_UNDEFINED)
++ reg_width = DMA_SLAVE_BUSWIDTH_1_BYTE;
++ else if (!is_power_of_2(reg_width) || reg_width > max_width)
++ return -EINVAL;
++ else /* bus width is valid */
++ return 0;
++
++ /* Update undefined addr width value */
++ if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV)
++ dwc->dma_sconfig.dst_addr_width = reg_width;
++ else /* DMA_DEV_TO_MEM */
++ dwc->dma_sconfig.src_addr_width = reg_width;
++
++ return 0;
++}
++
++static int dwc_verify_m_buswidth(struct dma_chan *chan)
++{
++ struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
++ struct dw_dma *dw = to_dw_dma(chan->device);
++ u32 reg_width, reg_burst, mem_width;
++
++ mem_width = dw->pdata->data_width[dwc->dws.m_master];
++
++ /*
++ * It's possible to have a data portion locked in the DMA FIFO in case
++ * of the channel suspension. Subsequent channel disabling will cause
++ * that data silent loss. In order to prevent that maintain the src and
++ * dst transfer widths coherency by means of the relation:
++ * (CTLx.SRC_TR_WIDTH * CTLx.SRC_MSIZE >= CTLx.DST_TR_WIDTH)
++ * Look for the details in the commit message that brings this change.
++ *
++ * Note the DMA configs utilized in the calculations below must have
++ * been verified to have correct values by this method call.
++ */
++ if (dwc->dma_sconfig.direction == DMA_MEM_TO_DEV) {
++ reg_width = dwc->dma_sconfig.dst_addr_width;
++ if (mem_width < reg_width)
++ return -EINVAL;
++
++ dwc->dma_sconfig.src_addr_width = mem_width;
++ } else if (dwc->dma_sconfig.direction == DMA_DEV_TO_MEM) {
++ reg_width = dwc->dma_sconfig.src_addr_width;
++ reg_burst = rounddown_pow_of_two(dwc->dma_sconfig.src_maxburst);
++
++ dwc->dma_sconfig.dst_addr_width = min(mem_width, reg_width * reg_burst);
++ }
++
++ return 0;
++}
++
+ static int dwc_config(struct dma_chan *chan, struct dma_slave_config *sconfig)
+ {
+ struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+ struct dw_dma *dw = to_dw_dma(chan->device);
++ int ret;
+
+ memcpy(&dwc->dma_sconfig, sconfig, sizeof(*sconfig));
+
+ dwc->dma_sconfig.src_maxburst =
+- clamp(dwc->dma_sconfig.src_maxburst, 0U, dwc->max_burst);
++ clamp(dwc->dma_sconfig.src_maxburst, 1U, dwc->max_burst);
+ dwc->dma_sconfig.dst_maxburst =
+- clamp(dwc->dma_sconfig.dst_maxburst, 0U, dwc->max_burst);
++ clamp(dwc->dma_sconfig.dst_maxburst, 1U, dwc->max_burst);
++
++ ret = dwc_verify_p_buswidth(chan);
++ if (ret)
++ return ret;
++
++ ret = dwc_verify_m_buswidth(chan);
++ if (ret)
++ return ret;
+
+ dw->encode_maxburst(dwc, &dwc->dma_sconfig.src_maxburst);
+ dw->encode_maxburst(dwc, &dwc->dma_sconfig.dst_maxburst);
+diff --git a/drivers/dma/ti/omap-dma.c b/drivers/dma/ti/omap-dma.c
+index b9e0e22383b72..984fbec2c4bae 100644
+--- a/drivers/dma/ti/omap-dma.c
++++ b/drivers/dma/ti/omap-dma.c
+@@ -1186,10 +1186,10 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_cyclic(
+ d->dev_addr = dev_addr;
+ d->fi = burst;
+ d->es = es;
++ d->sglen = 1;
+ d->sg[0].addr = buf_addr;
+ d->sg[0].en = period_len / es_bytes[es];
+ d->sg[0].fn = buf_len / period_len;
+- d->sglen = 1;
+
+ d->ccr = c->ccr;
+ if (dir == DMA_DEV_TO_MEM)
+@@ -1258,10 +1258,10 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_memcpy(
+ d->dev_addr = src;
+ d->fi = 0;
+ d->es = data_type;
++ d->sglen = 1;
+ d->sg[0].en = len / BIT(data_type);
+ d->sg[0].fn = 1;
+ d->sg[0].addr = dest;
+- d->sglen = 1;
+ d->ccr = c->ccr;
+ d->ccr |= CCR_DST_AMODE_POSTINC | CCR_SRC_AMODE_POSTINC;
+
+@@ -1309,6 +1309,7 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_interleaved(
+ if (data_type > CSDP_DATA_TYPE_32)
+ data_type = CSDP_DATA_TYPE_32;
+
++ d->sglen = 1;
+ sg = &d->sg[0];
+ d->dir = DMA_MEM_TO_MEM;
+ d->dev_addr = xt->src_start;
+@@ -1316,7 +1317,6 @@ static struct dma_async_tx_descriptor *omap_dma_prep_dma_interleaved(
+ sg->en = xt->sgl[0].size / BIT(data_type);
+ sg->fn = xt->numf;
+ sg->addr = xt->dst_start;
+- d->sglen = 1;
+ d->ccr = c->ccr;
+
+ src_icg = dmaengine_get_src_icg(xt, &xt->sgl[0]);
+diff --git a/drivers/firmware/microchip/mpfs-auto-update.c b/drivers/firmware/microchip/mpfs-auto-update.c
+index 835a19a7a3a09..4a95fbbf4733e 100644
+--- a/drivers/firmware/microchip/mpfs-auto-update.c
++++ b/drivers/firmware/microchip/mpfs-auto-update.c
+@@ -153,7 +153,7 @@ static enum fw_upload_err mpfs_auto_update_poll_complete(struct fw_upload *fw_up
+ */
+ ret = wait_for_completion_timeout(&priv->programming_complete,
+ msecs_to_jiffies(AUTO_UPDATE_TIMEOUT_MS));
+- if (ret)
++ if (!ret)
+ return FW_UPLOAD_ERR_TIMEOUT;
+
+ return FW_UPLOAD_ERR_NONE;
+diff --git a/drivers/firmware/qcom/qcom_scm-smc.c b/drivers/firmware/qcom/qcom_scm-smc.c
+index 16cf88acfa8ee..0a2a2c794d0ed 100644
+--- a/drivers/firmware/qcom/qcom_scm-smc.c
++++ b/drivers/firmware/qcom/qcom_scm-smc.c
+@@ -71,7 +71,7 @@ int scm_get_wq_ctx(u32 *wq_ctx, u32 *flags, u32 *more_pending)
+ struct arm_smccc_res get_wq_res;
+ struct arm_smccc_args get_wq_ctx = {0};
+
+- get_wq_ctx.args[0] = ARM_SMCCC_CALL_VAL(ARM_SMCCC_STD_CALL,
++ get_wq_ctx.args[0] = ARM_SMCCC_CALL_VAL(ARM_SMCCC_FAST_CALL,
+ ARM_SMCCC_SMC_64, ARM_SMCCC_OWNER_SIP,
+ SCM_SMC_FNID(QCOM_SCM_SVC_WAITQ, QCOM_SCM_WAITQ_GET_WQ_CTX));
+
+diff --git a/drivers/firmware/sysfb.c b/drivers/firmware/sysfb.c
+index 921f61507ae83..02a07d3d0d40a 100644
+--- a/drivers/firmware/sysfb.c
++++ b/drivers/firmware/sysfb.c
+@@ -39,6 +39,8 @@ static struct platform_device *pd;
+ static DEFINE_MUTEX(disable_lock);
+ static bool disabled;
+
++static struct device *sysfb_parent_dev(const struct screen_info *si);
++
+ static bool sysfb_unregister(void)
+ {
+ if (IS_ERR_OR_NULL(pd))
+@@ -52,6 +54,7 @@ static bool sysfb_unregister(void)
+
+ /**
+ * sysfb_disable() - disable the Generic System Framebuffers support
++ * @dev: the device to check if non-NULL
+ *
+ * This disables the registration of system framebuffer devices that match the
+ * generic drivers that make use of the system framebuffer set up by firmware.
+@@ -61,17 +64,21 @@ static bool sysfb_unregister(void)
+ * Context: The function can sleep. A @disable_lock mutex is acquired to serialize
+ * against sysfb_init(), that registers a system framebuffer device.
+ */
+-void sysfb_disable(void)
++void sysfb_disable(struct device *dev)
+ {
++ struct screen_info *si = &screen_info;
++
+ mutex_lock(&disable_lock);
+- sysfb_unregister();
+- disabled = true;
++ if (!dev || dev == sysfb_parent_dev(si)) {
++ sysfb_unregister();
++ disabled = true;
++ }
+ mutex_unlock(&disable_lock);
+ }
+ EXPORT_SYMBOL_GPL(sysfb_disable);
+
+ #if defined(CONFIG_PCI)
+-static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
++static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+ {
+ /*
+ * TODO: Try to integrate this code into the PCI subsystem
+@@ -87,13 +94,13 @@ static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+ return true;
+ }
+ #else
+-static __init bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
++static bool sysfb_pci_dev_is_enabled(struct pci_dev *pdev)
+ {
+ return false;
+ }
+ #endif
+
+-static __init struct device *sysfb_parent_dev(const struct screen_info *si)
++static struct device *sysfb_parent_dev(const struct screen_info *si)
+ {
+ struct pci_dev *pdev;
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+index 0e31bdb4b7cb6..f1b08893765cf 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_discovery.c
+@@ -256,19 +256,21 @@ static int amdgpu_discovery_read_binary_from_mem(struct amdgpu_device *adev,
+ u32 msg;
+ int i, ret = 0;
+
+- /* It can take up to a second for IFWI init to complete on some dGPUs,
+- * but generally it should be in the 60-100ms range. Normally this starts
+- * as soon as the device gets power so by the time the OS loads this has long
+- * completed. However, when a card is hotplugged via e.g., USB4, we need to
+- * wait for this to complete. Once the C2PMSG is updated, we can
+- * continue.
+- */
++ if (!amdgpu_sriov_vf(adev)) {
++ /* It can take up to a second for IFWI init to complete on some dGPUs,
++ * but generally it should be in the 60-100ms range. Normally this starts
++ * as soon as the device gets power so by the time the OS loads this has long
++ * completed. However, when a card is hotplugged via e.g., USB4, we need to
++ * wait for this to complete. Once the C2PMSG is updated, we can
++ * continue.
++ */
+
+- for (i = 0; i < 1000; i++) {
+- msg = RREG32(mmMP0_SMN_C2PMSG_33);
+- if (msg & 0x80000000)
+- break;
+- usleep_range(1000, 1100);
++ for (i = 0; i < 1000; i++) {
++ msg = RREG32(mmMP0_SMN_C2PMSG_33);
++ if (msg & 0x80000000)
++ break;
++ msleep(1);
++ }
+ }
+
+ vram_size = (uint64_t)RREG32(mmRCC_CONFIG_MEMSIZE) << 20;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+index 06f0a6534a94f..88ffb15e25ccc 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.c
+@@ -212,6 +212,8 @@ int amdgpu_ring_init(struct amdgpu_device *adev, struct amdgpu_ring *ring,
+ */
+ if (ring->funcs->type == AMDGPU_RING_TYPE_KIQ)
+ sched_hw_submission = max(sched_hw_submission, 256);
++ if (ring->funcs->type == AMDGPU_RING_TYPE_MES)
++ sched_hw_submission = 8;
+ else if (ring == &adev->sdma.instance[0].page)
+ sched_hw_submission = 256;
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+index 32d4519541c6b..e1a66d585f5e9 100644
+--- a/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/mes_v11_0.c
+@@ -163,7 +163,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
+ const char *op_str, *misc_op_str;
+ unsigned long flags;
+ u64 status_gpu_addr;
+- u32 status_offset;
++ u32 seq, status_offset;
+ u64 *status_ptr;
+ signed long r;
+ int ret;
+@@ -191,6 +191,13 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
+ if (r)
+ goto error_unlock_free;
+
++ seq = ++ring->fence_drv.sync_seq;
++ r = amdgpu_fence_wait_polling(ring,
++ seq - ring->fence_drv.num_fences_mask,
++ timeout);
++ if (r < 1)
++ goto error_undo;
++
+ api_status = (struct MES_API_STATUS *)((char *)pkt + api_status_off);
+ api_status->api_completion_fence_addr = status_gpu_addr;
+ api_status->api_completion_fence_value = 1;
+@@ -203,8 +210,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
+ mes_status_pkt.header.dwsize = API_FRAME_SIZE_IN_DWORDS;
+ mes_status_pkt.api_status.api_completion_fence_addr =
+ ring->fence_drv.gpu_addr;
+- mes_status_pkt.api_status.api_completion_fence_value =
+- ++ring->fence_drv.sync_seq;
++ mes_status_pkt.api_status.api_completion_fence_value = seq;
+
+ amdgpu_ring_write_multiple(ring, &mes_status_pkt,
+ sizeof(mes_status_pkt) / 4);
+@@ -224,7 +230,7 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
+ dev_dbg(adev->dev, "MES msg=%d was emitted\n",
+ x_pkt->header.opcode);
+
+- r = amdgpu_fence_wait_polling(ring, ring->fence_drv.sync_seq, timeout);
++ r = amdgpu_fence_wait_polling(ring, seq, timeout);
+ if (r < 1 || !*status_ptr) {
+
+ if (misc_op_str)
+@@ -247,6 +253,10 @@ static int mes_v11_0_submit_pkt_and_poll_completion(struct amdgpu_mes *mes,
+ amdgpu_device_wb_free(adev, status_offset);
+ return 0;
+
++error_undo:
++ dev_err(adev->dev, "MES ring buffer is full.\n");
++ amdgpu_ring_undo(ring);
++
+ error_unlock_free:
+ spin_unlock_irqrestore(&mes->ring_lock, flags);
+
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+index 311c62d2d1ebb..70e45d980bb93 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+@@ -28,6 +28,7 @@
+ #include <drm/drm_blend.h>
+ #include <drm/drm_gem_atomic_helper.h>
+ #include <drm/drm_plane_helper.h>
++#include <drm/drm_gem_framebuffer_helper.h>
+ #include <drm/drm_fourcc.h>
+
+ #include "amdgpu.h"
+@@ -854,10 +855,14 @@ static int amdgpu_dm_plane_helper_prepare_fb(struct drm_plane *plane,
+ }
+
+ afb = to_amdgpu_framebuffer(new_state->fb);
+- obj = new_state->fb->obj[0];
++ obj = drm_gem_fb_get_obj(new_state->fb, 0);
++ if (!obj) {
++ DRM_ERROR("Failed to get obj from framebuffer\n");
++ return -EINVAL;
++ }
++
+ rbo = gem_to_amdgpu_bo(obj);
+ adev = amdgpu_ttm_adev(rbo->tbo.bdev);
+-
+ r = amdgpu_bo_reserve(rbo, true);
+ if (r) {
+ dev_err(adev->dev, "fail to reserve bo (%d)\n", r);
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+index 06409133b09b1..95f690b70c057 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+@@ -2215,8 +2215,9 @@ static int smu_bump_power_profile_mode(struct smu_context *smu,
+ }
+
+ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
+- enum amd_dpm_forced_level level,
+- bool skip_display_settings)
++ enum amd_dpm_forced_level level,
++ bool skip_display_settings,
++ bool force_update)
+ {
+ int ret = 0;
+ int index = 0;
+@@ -2245,7 +2246,7 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
+ }
+ }
+
+- if (smu_dpm_ctx->dpm_level != level) {
++ if (force_update || smu_dpm_ctx->dpm_level != level) {
+ ret = smu_asic_set_performance_level(smu, level);
+ if (ret) {
+ dev_err(smu->adev->dev, "Failed to set performance level!");
+@@ -2256,13 +2257,12 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
+ smu_dpm_ctx->dpm_level = level;
+ }
+
+- if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
+- smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
++ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
+ index = fls(smu->workload_mask);
+ index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
+ workload[0] = smu->workload_setting[index];
+
+- if (smu->power_profile_mode != workload[0])
++ if (force_update || smu->power_profile_mode != workload[0])
+ smu_bump_power_profile_mode(smu, workload, 0);
+ }
+
+@@ -2283,11 +2283,13 @@ static int smu_handle_task(struct smu_context *smu,
+ ret = smu_pre_display_config_changed(smu);
+ if (ret)
+ return ret;
+- ret = smu_adjust_power_state_dynamic(smu, level, false);
++ ret = smu_adjust_power_state_dynamic(smu, level, false, false);
+ break;
+ case AMD_PP_TASK_COMPLETE_INIT:
++ ret = smu_adjust_power_state_dynamic(smu, level, true, true);
++ break;
+ case AMD_PP_TASK_READJUST_POWER_STATE:
+- ret = smu_adjust_power_state_dynamic(smu, level, true);
++ ret = smu_adjust_power_state_dynamic(smu, level, true, false);
+ break;
+ default:
+ break;
+@@ -2334,8 +2336,7 @@ static int smu_switch_power_profile(void *handle,
+ workload[0] = smu->workload_setting[index];
+ }
+
+- if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
+- smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
++ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
+ smu_bump_power_profile_mode(smu, workload, 0);
+
+ return 0;
+diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
+index 9c9e060476c72..8ea00c8ee74a3 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp.c
++++ b/drivers/gpu/drm/i915/display/intel_dp.c
+@@ -5860,6 +5860,18 @@ intel_dp_detect(struct drm_connector *connector,
+ else
+ status = connector_status_disconnected;
+
++ if (status != connector_status_disconnected &&
++ !intel_dp_mst_verify_dpcd_state(intel_dp))
++ /*
++ * This requires retrying detection for instance to re-enable
++ * the MST mode that got reset via a long HPD pulse. The retry
++ * will happen either via the hotplug handler's retry logic,
++ * ensured by setting the connector here to SST/disconnected,
++ * or via a userspace connector probing in response to the
++ * hotplug uevent sent when removing the MST connectors.
++ */
++ status = connector_status_disconnected;
++
+ if (status == connector_status_disconnected) {
+ memset(&intel_dp->compliance, 0, sizeof(intel_dp->compliance));
+ memset(intel_connector->dp.dsc_dpcd, 0, sizeof(intel_connector->dp.dsc_dpcd));
+diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.c b/drivers/gpu/drm/i915/display/intel_dp_mst.c
+index 715d2f59f5652..de141744e1c35 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp_mst.c
++++ b/drivers/gpu/drm/i915/display/intel_dp_mst.c
+@@ -1986,3 +1986,43 @@ bool intel_dp_mst_crtc_needs_modeset(struct intel_atomic_state *state,
+
+ return false;
+ }
++
++/*
++ * intel_dp_mst_verify_dpcd_state - verify the MST SW enabled state wrt. the DPCD
++ * @intel_dp: DP port object
++ *
++ * Verify if @intel_dp's MST enabled SW state matches the corresponding DPCD
++ * state. A long HPD pulse - not long enough to be detected as a disconnected
++ * state - could've reset the DPCD state, which requires tearing
++ * down/recreating the MST topology.
++ *
++ * Returns %true if the SW MST enabled and DPCD states match, %false
++ * otherwise.
++ */
++bool intel_dp_mst_verify_dpcd_state(struct intel_dp *intel_dp)
++{
++ struct intel_display *display = to_intel_display(intel_dp);
++ struct intel_connector *connector = intel_dp->attached_connector;
++ struct intel_digital_port *dig_port = dp_to_dig_port(intel_dp);
++ struct intel_encoder *encoder = &dig_port->base;
++ int ret;
++ u8 val;
++
++ if (!intel_dp->is_mst)
++ return true;
++
++ ret = drm_dp_dpcd_readb(intel_dp->mst_mgr.aux, DP_MSTM_CTRL, &val);
++
++ /* Adjust the expected register value for SST + SideBand. */
++ if (ret < 0 || val != (DP_MST_EN | DP_UP_REQ_EN | DP_UPSTREAM_IS_SRC)) {
++ drm_dbg_kms(display->drm,
++ "[CONNECTOR:%d:%s][ENCODER:%d:%s] MST mode got reset, removing topology (ret=%d, ctrl=0x%02x)\n",
++ connector->base.base.id, connector->base.name,
++ encoder->base.base.id, encoder->base.name,
++ ret, val);
++
++ return false;
++ }
++
++ return true;
++}
+diff --git a/drivers/gpu/drm/i915/display/intel_dp_mst.h b/drivers/gpu/drm/i915/display/intel_dp_mst.h
+index 8ca1d599091c6..9e4c7679f1c3a 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp_mst.h
++++ b/drivers/gpu/drm/i915/display/intel_dp_mst.h
+@@ -27,5 +27,6 @@ int intel_dp_mst_atomic_check_link(struct intel_atomic_state *state,
+ struct intel_link_bw_limits *limits);
+ bool intel_dp_mst_crtc_needs_modeset(struct intel_atomic_state *state,
+ struct intel_crtc *crtc);
++bool intel_dp_mst_verify_dpcd_state(struct intel_dp *intel_dp);
+
+ #endif /* __INTEL_DP_MST_H__ */
+diff --git a/drivers/gpu/drm/i915/display/vlv_dsi.c b/drivers/gpu/drm/i915/display/vlv_dsi.c
+index ee9923c7b1158..b674b8d157080 100644
+--- a/drivers/gpu/drm/i915/display/vlv_dsi.c
++++ b/drivers/gpu/drm/i915/display/vlv_dsi.c
+@@ -1869,7 +1869,6 @@ static const struct dmi_system_id vlv_dsi_dmi_quirk_table[] = {
+ /* Lenovo Yoga Tab 3 Pro YT3-X90F */
+ .matches = {
+ DMI_MATCH(DMI_SYS_VENDOR, "Intel Corporation"),
+- DMI_MATCH(DMI_PRODUCT_NAME, "CHERRYVIEW D1 PLATFORM"),
+ DMI_MATCH(DMI_PRODUCT_VERSION, "Blade3-10A-001"),
+ },
+ .driver_data = (void *)vlv_dsi_lenovo_yoga_tab3_backlight_fixup,
+diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
+index 0132403b8159f..d0f55ec15ab0a 100644
+--- a/drivers/gpu/drm/v3d/v3d_sched.c
++++ b/drivers/gpu/drm/v3d/v3d_sched.c
+@@ -134,6 +134,8 @@ v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue)
+ struct v3d_stats *local_stats = &file->stats[queue];
+ u64 now = local_clock();
+
++ preempt_disable();
++
+ write_seqcount_begin(&local_stats->lock);
+ local_stats->start_ns = now;
+ write_seqcount_end(&local_stats->lock);
+@@ -141,6 +143,8 @@ v3d_job_start_stats(struct v3d_job *job, enum v3d_queue queue)
+ write_seqcount_begin(&global_stats->lock);
+ global_stats->start_ns = now;
+ write_seqcount_end(&global_stats->lock);
++
++ preempt_enable();
+ }
+
+ static void
+@@ -162,8 +166,10 @@ v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue)
+ struct v3d_stats *local_stats = &file->stats[queue];
+ u64 now = local_clock();
+
++ preempt_disable();
+ v3d_stats_update(local_stats, now);
+ v3d_stats_update(global_stats, now);
++ preempt_enable();
+ }
+
+ static struct dma_fence *v3d_bin_job_run(struct drm_sched_job *sched_job)
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+index 717d624e9a052..890a66a2361f4 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_blit.c
+@@ -27,6 +27,8 @@
+ **************************************************************************/
+
+ #include "vmwgfx_drv.h"
++
++#include "vmwgfx_bo.h"
+ #include <linux/highmem.h>
+
+ /*
+@@ -420,13 +422,105 @@ static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
+ return 0;
+ }
+
++static void *map_external(struct vmw_bo *bo, struct iosys_map *map)
++{
++ struct vmw_private *vmw =
++ container_of(bo->tbo.bdev, struct vmw_private, bdev);
++ void *ptr = NULL;
++ int ret;
++
++ if (bo->tbo.base.import_attach) {
++ ret = dma_buf_vmap(bo->tbo.base.dma_buf, map);
++ if (ret) {
++ drm_dbg_driver(&vmw->drm,
++ "Wasn't able to map external bo!\n");
++ goto out;
++ }
++ ptr = map->vaddr;
++ } else {
++ ptr = vmw_bo_map_and_cache(bo);
++ }
++
++out:
++ return ptr;
++}
++
++static void unmap_external(struct vmw_bo *bo, struct iosys_map *map)
++{
++ if (bo->tbo.base.import_attach)
++ dma_buf_vunmap(bo->tbo.base.dma_buf, map);
++ else
++ vmw_bo_unmap(bo);
++}
++
++static int vmw_external_bo_copy(struct vmw_bo *dst, u32 dst_offset,
++ u32 dst_stride, struct vmw_bo *src,
++ u32 src_offset, u32 src_stride,
++ u32 width_in_bytes, u32 height,
++ struct vmw_diff_cpy *diff)
++{
++ struct vmw_private *vmw =
++ container_of(dst->tbo.bdev, struct vmw_private, bdev);
++ size_t dst_size = dst->tbo.resource->size;
++ size_t src_size = src->tbo.resource->size;
++ struct iosys_map dst_map = {0};
++ struct iosys_map src_map = {0};
++ int ret, i;
++ int x_in_bytes;
++ u8 *vsrc;
++ u8 *vdst;
++
++ vsrc = map_external(src, &src_map);
++ if (!vsrc) {
++ drm_dbg_driver(&vmw->drm, "Wasn't able to map src\n");
++ ret = -ENOMEM;
++ goto out;
++ }
++
++ vdst = map_external(dst, &dst_map);
++ if (!vdst) {
++ drm_dbg_driver(&vmw->drm, "Wasn't able to map dst\n");
++ ret = -ENOMEM;
++ goto out;
++ }
++
++ vsrc += src_offset;
++ vdst += dst_offset;
++ if (src_stride == dst_stride) {
++ dst_size -= dst_offset;
++ src_size -= src_offset;
++ memcpy(vdst, vsrc,
++ min(dst_stride * height, min(dst_size, src_size)));
++ } else {
++ WARN_ON(dst_stride < width_in_bytes);
++ for (i = 0; i < height; ++i) {
++ memcpy(vdst, vsrc, width_in_bytes);
++ vsrc += src_stride;
++ vdst += dst_stride;
++ }
++ }
++
++ x_in_bytes = (dst_offset % dst_stride);
++ diff->rect.x1 = x_in_bytes / diff->cpp;
++ diff->rect.y1 = ((dst_offset - x_in_bytes) / dst_stride);
++ diff->rect.x2 = diff->rect.x1 + width_in_bytes / diff->cpp;
++ diff->rect.y2 = diff->rect.y1 + height;
++
++ ret = 0;
++out:
++ unmap_external(src, &src_map);
++ unmap_external(dst, &dst_map);
++
++ return ret;
++}
++
+ /**
+ * vmw_bo_cpu_blit - in-kernel cpu blit.
+ *
+- * @dst: Destination buffer object.
++ * @vmw_dst: Destination buffer object.
+ * @dst_offset: Destination offset of blit start in bytes.
+ * @dst_stride: Destination stride in bytes.
+- * @src: Source buffer object.
++ * @vmw_src: Source buffer object.
+ * @src_offset: Source offset of blit start in bytes.
+ * @src_stride: Source stride in bytes.
+ * @w: Width of blit.
+@@ -444,13 +538,15 @@ static int vmw_bo_cpu_blit_line(struct vmw_bo_blit_line_data *d,
+ * Neither of the buffer objects may be placed in PCI memory
+ * (Fixed memory in TTM terminology) when using this function.
+ */
+-int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
++int vmw_bo_cpu_blit(struct vmw_bo *vmw_dst,
+ u32 dst_offset, u32 dst_stride,
+- struct ttm_buffer_object *src,
++ struct vmw_bo *vmw_src,
+ u32 src_offset, u32 src_stride,
+ u32 w, u32 h,
+ struct vmw_diff_cpy *diff)
+ {
++ struct ttm_buffer_object *src = &vmw_src->tbo;
++ struct ttm_buffer_object *dst = &vmw_dst->tbo;
+ struct ttm_operation_ctx ctx = {
+ .interruptible = false,
+ .no_wait_gpu = false
+@@ -460,6 +556,11 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
+ int ret = 0;
+ struct page **dst_pages = NULL;
+ struct page **src_pages = NULL;
++ bool src_external = (src->ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
++ bool dst_external = (dst->ttm->page_flags & TTM_TT_FLAG_EXTERNAL) != 0;
++
++ if (WARN_ON(dst == src))
++ return -EINVAL;
+
+ /* Buffer objects need to be either pinned or reserved: */
+ if (!(dst->pin_count))
+@@ -479,6 +580,11 @@ int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
+ return ret;
+ }
+
++ if (src_external || dst_external)
++ return vmw_external_bo_copy(vmw_dst, dst_offset, dst_stride,
++ vmw_src, src_offset, src_stride,
++ w, h, diff);
++
+ if (!src->ttm->pages && src->ttm->sg) {
+ src_pages = kvmalloc_array(src->ttm->num_pages,
+ sizeof(struct page *), GFP_KERNEL);
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+index f42ebc4a7c225..a0e433fbcba67 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+@@ -360,6 +360,8 @@ void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size)
+ void *virtual;
+ int ret;
+
++ atomic_inc(&vbo->map_count);
++
+ virtual = ttm_kmap_obj_virtual(&vbo->map, ¬_used);
+ if (virtual)
+ return virtual;
+@@ -383,11 +385,17 @@ void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size)
+ */
+ void vmw_bo_unmap(struct vmw_bo *vbo)
+ {
++ int map_count;
++
+ if (vbo->map.bo == NULL)
+ return;
+
+- ttm_bo_kunmap(&vbo->map);
+- vbo->map.bo = NULL;
++ map_count = atomic_dec_return(&vbo->map_count);
++
++ if (!map_count) {
++ ttm_bo_kunmap(&vbo->map);
++ vbo->map.bo = NULL;
++ }
+ }
+
+
+@@ -421,6 +429,7 @@ static int vmw_bo_init(struct vmw_private *dev_priv,
+ vmw_bo->tbo.priority = 3;
+ vmw_bo->res_tree = RB_ROOT;
+ xa_init(&vmw_bo->detached_resources);
++ atomic_set(&vmw_bo->map_count, 0);
+
+ params->size = ALIGN(params->size, PAGE_SIZE);
+ drm_gem_private_object_init(vdev, &vmw_bo->tbo.base, params->size);
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+index 62b4342d5f7c5..43b5439ec9f76 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+@@ -71,6 +71,8 @@ struct vmw_bo_params {
+ * @map: Kmap object for semi-persistent mappings
+ * @res_tree: RB tree of resources using this buffer object as a backing MOB
+ * @res_prios: Eviction priority counts for attached resources
++ * @map_count: The number of currently active maps. Will differ from the
++ * cpu_writers because it includes kernel maps.
+ * @cpu_writers: Number of synccpu write grabs. Protected by reservation when
+ * increased. May be decreased without reservation.
+ * @dx_query_ctx: DX context if this buffer object is used as a DX query MOB
+@@ -90,6 +92,7 @@ struct vmw_bo {
+ u32 res_prios[TTM_MAX_BO_PRIORITY];
+ struct xarray detached_resources;
+
++ atomic_t map_count;
+ atomic_t cpu_writers;
+ /* Not ref-counted. Protected by binding_mutex */
+ struct vmw_resource *dx_query_ctx;
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+index 32f50e5958097..3f4719b3c2681 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+@@ -1353,9 +1353,9 @@ void vmw_diff_memcpy(struct vmw_diff_cpy *diff, u8 *dest, const u8 *src,
+
+ void vmw_memcpy(struct vmw_diff_cpy *diff, u8 *dest, const u8 *src, size_t n);
+
+-int vmw_bo_cpu_blit(struct ttm_buffer_object *dst,
++int vmw_bo_cpu_blit(struct vmw_bo *dst,
+ u32 dst_offset, u32 dst_stride,
+- struct ttm_buffer_object *src,
++ struct vmw_bo *src,
+ u32 src_offset, u32 src_stride,
+ u32 w, u32 h,
+ struct vmw_diff_cpy *diff);
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+index 5453f7cf0e2d7..fab155a68054a 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+@@ -502,7 +502,7 @@ static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty)
+ container_of(dirty->unit, typeof(*stdu), base);
+ s32 width, height;
+ s32 src_pitch, dst_pitch;
+- struct ttm_buffer_object *src_bo, *dst_bo;
++ struct vmw_bo *src_bo, *dst_bo;
+ u32 src_offset, dst_offset;
+ struct vmw_diff_cpy diff = VMW_CPU_BLIT_DIFF_INITIALIZER(stdu->cpp);
+
+@@ -517,11 +517,11 @@ static void vmw_stdu_bo_cpu_commit(struct vmw_kms_dirty *dirty)
+
+ /* Assume we are blitting from Guest (bo) to Host (display_srf) */
+ src_pitch = stdu->display_srf->metadata.base_size.width * stdu->cpp;
+- src_bo = &stdu->display_srf->res.guest_memory_bo->tbo;
++ src_bo = stdu->display_srf->res.guest_memory_bo;
+ src_offset = ddirty->top * src_pitch + ddirty->left * stdu->cpp;
+
+ dst_pitch = ddirty->pitch;
+- dst_bo = &ddirty->buf->tbo;
++ dst_bo = ddirty->buf;
+ dst_offset = ddirty->fb_top * dst_pitch + ddirty->fb_left * stdu->cpp;
+
+ (void) vmw_bo_cpu_blit(dst_bo, dst_offset, dst_pitch,
+@@ -1170,7 +1170,7 @@ vmw_stdu_bo_populate_update_cpu(struct vmw_du_update_plane *update, void *cmd,
+ struct vmw_diff_cpy diff = VMW_CPU_BLIT_DIFF_INITIALIZER(0);
+ struct vmw_stdu_update_gb_image *cmd_img = cmd;
+ struct vmw_stdu_update *cmd_update;
+- struct ttm_buffer_object *src_bo, *dst_bo;
++ struct vmw_bo *src_bo, *dst_bo;
+ u32 src_offset, dst_offset;
+ s32 src_pitch, dst_pitch;
+ s32 width, height;
+@@ -1184,11 +1184,11 @@ vmw_stdu_bo_populate_update_cpu(struct vmw_du_update_plane *update, void *cmd,
+
+ diff.cpp = stdu->cpp;
+
+- dst_bo = &stdu->display_srf->res.guest_memory_bo->tbo;
++ dst_bo = stdu->display_srf->res.guest_memory_bo;
+ dst_pitch = stdu->display_srf->metadata.base_size.width * stdu->cpp;
+ dst_offset = bb->y1 * dst_pitch + bb->x1 * stdu->cpp;
+
+- src_bo = &vfbbo->buffer->tbo;
++ src_bo = vfbbo->buffer;
+ src_pitch = update->vfb->base.pitches[0];
+ src_offset = bo_update->fb_top * src_pitch + bo_update->fb_left *
+ stdu->cpp;
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+index 8ae6a761c9003..1625b30d99700 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+@@ -2283,9 +2283,11 @@ int vmw_dumb_create(struct drm_file *file_priv,
+ /*
+ * Without mob support we're just going to use raw memory buffer
+ * because we wouldn't be able to support full surface coherency
+- * without mobs
++ * without mobs. There also no reason to support surface coherency
++ * without 3d (i.e. gpu usage on the host) because then all the
++ * contents is going to be rendered guest side.
+ */
+- if (!dev_priv->has_mob) {
++ if (!dev_priv->has_mob || !vmw_supports_3d(dev_priv)) {
+ int cpp = DIV_ROUND_UP(args->bpp, 8);
+
+ switch (cpp) {
+diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
+index 7cdc03dc40ed9..96835ffa5734e 100644
+--- a/drivers/gpu/drm/xe/display/xe_display.c
++++ b/drivers/gpu/drm/xe/display/xe_display.c
+@@ -302,7 +302,28 @@ static bool suspend_to_idle(void)
+ return false;
+ }
+
+-void xe_display_pm_suspend(struct xe_device *xe)
++static void xe_display_flush_cleanup_work(struct xe_device *xe)
++{
++ struct intel_crtc *crtc;
++
++ for_each_intel_crtc(&xe->drm, crtc) {
++ struct drm_crtc_commit *commit;
++
++ spin_lock(&crtc->base.commit_lock);
++ commit = list_first_entry_or_null(&crtc->base.commit_list,
++ struct drm_crtc_commit, commit_entry);
++ if (commit)
++ drm_crtc_commit_get(commit);
++ spin_unlock(&crtc->base.commit_lock);
++
++ if (commit) {
++ wait_for_completion(&commit->cleanup_done);
++ drm_crtc_commit_put(commit);
++ }
++ }
++}
++
++void xe_display_pm_suspend(struct xe_device *xe, bool runtime)
+ {
+ bool s2idle = suspend_to_idle();
+ if (!xe->info.enable_display)
+@@ -316,7 +337,10 @@ void xe_display_pm_suspend(struct xe_device *xe)
+ if (has_display(xe))
+ drm_kms_helper_poll_disable(&xe->drm);
+
+- intel_display_driver_suspend(xe);
++ if (!runtime)
++ intel_display_driver_suspend(xe);
++
++ xe_display_flush_cleanup_work(xe);
+
+ intel_dp_mst_suspend(xe);
+
+@@ -352,7 +376,7 @@ void xe_display_pm_resume_early(struct xe_device *xe)
+ intel_power_domains_resume(xe);
+ }
+
+-void xe_display_pm_resume(struct xe_device *xe)
++void xe_display_pm_resume(struct xe_device *xe, bool runtime)
+ {
+ if (!xe->info.enable_display)
+ return;
+@@ -367,7 +391,8 @@ void xe_display_pm_resume(struct xe_device *xe)
+
+ /* MST sideband requires HPD interrupts enabled */
+ intel_dp_mst_resume(xe);
+- intel_display_driver_resume(xe);
++ if (!runtime)
++ intel_display_driver_resume(xe);
+
+ intel_hpd_poll_disable(xe);
+ if (has_display(xe))
+diff --git a/drivers/gpu/drm/xe/display/xe_display.h b/drivers/gpu/drm/xe/display/xe_display.h
+index 710e56180b52d..93d1f779b9788 100644
+--- a/drivers/gpu/drm/xe/display/xe_display.h
++++ b/drivers/gpu/drm/xe/display/xe_display.h
+@@ -34,10 +34,10 @@ void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir);
+ void xe_display_irq_reset(struct xe_device *xe);
+ void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt);
+
+-void xe_display_pm_suspend(struct xe_device *xe);
++void xe_display_pm_suspend(struct xe_device *xe, bool runtime);
+ void xe_display_pm_suspend_late(struct xe_device *xe);
+ void xe_display_pm_resume_early(struct xe_device *xe);
+-void xe_display_pm_resume(struct xe_device *xe);
++void xe_display_pm_resume(struct xe_device *xe, bool runtime);
+
+ #else
+
+@@ -63,10 +63,10 @@ static inline void xe_display_irq_enable(struct xe_device *xe, u32 gu_misc_iir)
+ static inline void xe_display_irq_reset(struct xe_device *xe) {}
+ static inline void xe_display_irq_postinstall(struct xe_device *xe, struct xe_gt *gt) {}
+
+-static inline void xe_display_pm_suspend(struct xe_device *xe) {}
++static inline void xe_display_pm_suspend(struct xe_device *xe, bool runtime) {}
+ static inline void xe_display_pm_suspend_late(struct xe_device *xe) {}
+ static inline void xe_display_pm_resume_early(struct xe_device *xe) {}
+-static inline void xe_display_pm_resume(struct xe_device *xe) {}
++static inline void xe_display_pm_resume(struct xe_device *xe, bool runtime) {}
+
+ #endif /* CONFIG_DRM_XE_DISPLAY */
+ #endif /* _XE_DISPLAY_H_ */
+diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
+index 2ae4420e29353..ba7013f82c8b6 100644
+--- a/drivers/gpu/drm/xe/xe_exec_queue.c
++++ b/drivers/gpu/drm/xe/xe_exec_queue.c
+@@ -67,7 +67,7 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
+ q->fence_irq = >->fence_irq[hwe->class];
+ q->ring_ops = gt->ring_ops[hwe->class];
+ q->ops = gt->exec_queue_ops;
+- INIT_LIST_HEAD(&q->compute.link);
++ INIT_LIST_HEAD(&q->lr.link);
+ INIT_LIST_HEAD(&q->multi_gt_link);
+
+ q->sched_props.timeslice_us = hwe->eclass->sched_props.timeslice_us;
+@@ -631,8 +631,7 @@ int xe_exec_queue_create_ioctl(struct drm_device *dev, void *data,
+ return PTR_ERR(q);
+
+ if (xe_vm_in_preempt_fence_mode(vm)) {
+- q->compute.context = dma_fence_context_alloc(1);
+- spin_lock_init(&q->compute.lock);
++ q->lr.context = dma_fence_context_alloc(1);
+
+ err = xe_vm_add_compute_exec_queue(vm, q);
+ if (XE_IOCTL_DBG(xe, err))
+diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
+index f0c40e8ad80a1..a5aa43942d8cf 100644
+--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
++++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
+@@ -115,19 +115,17 @@ struct xe_exec_queue {
+ enum xe_exec_queue_priority priority;
+ } sched_props;
+
+- /** @compute: compute exec queue state */
++ /** @lr: long-running exec queue state */
+ struct {
+- /** @compute.pfence: preemption fence */
++ /** @lr.pfence: preemption fence */
+ struct dma_fence *pfence;
+- /** @compute.context: preemption fence context */
++ /** @lr.context: preemption fence context */
+ u64 context;
+- /** @compute.seqno: preemption fence seqno */
++ /** @lr.seqno: preemption fence seqno */
+ u32 seqno;
+- /** @compute.link: link into VM's list of exec queues */
++ /** @lr.link: link into VM's list of exec queues */
+ struct list_head link;
+- /** @compute.lock: preemption fences lock */
+- spinlock_t lock;
+- } compute;
++ } lr;
+
+ /** @ops: submission backend exec queue operations */
+ const struct xe_exec_queue_ops *ops;
+diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
+index d37f1dea9f8b8..bb815dbde63a6 100644
+--- a/drivers/gpu/drm/xe/xe_hwmon.c
++++ b/drivers/gpu/drm/xe/xe_hwmon.c
+@@ -443,7 +443,7 @@ static int xe_hwmon_pcode_write_i1(struct xe_gt *gt, u32 uval)
+ {
+ return xe_pcode_write(gt, PCODE_MBOX(PCODE_POWER_SETUP,
+ POWER_SETUP_SUBCOMMAND_WRITE_I1, 0),
+- uval);
++ (uval & POWER_SETUP_I1_DATA_MASK));
+ }
+
+ static int xe_hwmon_power_curr_crit_read(struct xe_hwmon *hwmon, int channel,
+diff --git a/drivers/gpu/drm/xe/xe_pm.c b/drivers/gpu/drm/xe/xe_pm.c
+index 37fbeda12d3bd..cf80679ceb701 100644
+--- a/drivers/gpu/drm/xe/xe_pm.c
++++ b/drivers/gpu/drm/xe/xe_pm.c
+@@ -91,17 +91,17 @@ int xe_pm_suspend(struct xe_device *xe)
+ for_each_gt(gt, xe, id)
+ xe_gt_suspend_prepare(gt);
+
++ xe_display_pm_suspend(xe, false);
++
+ /* FIXME: Super racey... */
+ err = xe_bo_evict_all(xe);
+ if (err)
+ goto err;
+
+- xe_display_pm_suspend(xe);
+-
+ for_each_gt(gt, xe, id) {
+ err = xe_gt_suspend(gt);
+ if (err) {
+- xe_display_pm_resume(xe);
++ xe_display_pm_resume(xe, false);
+ goto err;
+ }
+ }
+@@ -151,11 +151,11 @@ int xe_pm_resume(struct xe_device *xe)
+
+ xe_irq_resume(xe);
+
+- xe_display_pm_resume(xe);
+-
+ for_each_gt(gt, xe, id)
+ xe_gt_resume(gt);
+
++ xe_display_pm_resume(xe, false);
++
+ err = xe_bo_restore_user(xe);
+ if (err)
+ goto err;
+@@ -363,6 +363,8 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
+ mutex_unlock(&xe->mem_access.vram_userfault.lock);
+
+ if (xe->d3cold.allowed) {
++ xe_display_pm_suspend(xe, true);
++
+ err = xe_bo_evict_all(xe);
+ if (err)
+ goto out;
+@@ -375,7 +377,12 @@ int xe_pm_runtime_suspend(struct xe_device *xe)
+ }
+
+ xe_irq_suspend(xe);
++
++ if (xe->d3cold.allowed)
++ xe_display_pm_suspend_late(xe);
+ out:
++ if (err)
++ xe_display_pm_resume(xe, true);
+ lock_map_release(&xe_pm_runtime_lockdep_map);
+ xe_pm_write_callback_task(xe, NULL);
+ return err;
+@@ -411,6 +418,8 @@ int xe_pm_runtime_resume(struct xe_device *xe)
+ if (err)
+ goto out;
+
++ xe_display_pm_resume_early(xe);
++
+ /*
+ * This only restores pinned memory which is the memory
+ * required for the GT(s) to resume.
+@@ -426,6 +435,7 @@ int xe_pm_runtime_resume(struct xe_device *xe)
+ xe_gt_resume(gt);
+
+ if (xe->d3cold.allowed && xe->d3cold.power_lost) {
++ xe_display_pm_resume(xe, true);
+ err = xe_bo_restore_user(xe);
+ if (err)
+ goto out;
+diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c
+index 5b243b7feb59d..c453f45328b1c 100644
+--- a/drivers/gpu/drm/xe/xe_preempt_fence.c
++++ b/drivers/gpu/drm/xe/xe_preempt_fence.c
+@@ -128,8 +128,9 @@ xe_preempt_fence_arm(struct xe_preempt_fence *pfence, struct xe_exec_queue *q,
+ {
+ list_del_init(&pfence->link);
+ pfence->q = xe_exec_queue_get(q);
++ spin_lock_init(&pfence->lock);
+ dma_fence_init(&pfence->base, &preempt_fence_ops,
+- &q->compute.lock, context, seqno);
++ &pfence->lock, context, seqno);
+
+ return &pfence->base;
+ }
+diff --git a/drivers/gpu/drm/xe/xe_preempt_fence_types.h b/drivers/gpu/drm/xe/xe_preempt_fence_types.h
+index b54b5c29b5331..312c3372a49f9 100644
+--- a/drivers/gpu/drm/xe/xe_preempt_fence_types.h
++++ b/drivers/gpu/drm/xe/xe_preempt_fence_types.h
+@@ -25,6 +25,8 @@ struct xe_preempt_fence {
+ struct xe_exec_queue *q;
+ /** @preempt_work: work struct which issues preemption */
+ struct work_struct preempt_work;
++ /** @lock: dma-fence fence lock */
++ spinlock_t lock;
+ /** @error: preempt fence is in error state */
+ int error;
+ };
+diff --git a/drivers/gpu/drm/xe/xe_vm.c b/drivers/gpu/drm/xe/xe_vm.c
+index 4aa3943e6f292..fd5612cc6f19b 100644
+--- a/drivers/gpu/drm/xe/xe_vm.c
++++ b/drivers/gpu/drm/xe/xe_vm.c
+@@ -83,10 +83,10 @@ static bool preempt_fences_waiting(struct xe_vm *vm)
+ lockdep_assert_held(&vm->lock);
+ xe_vm_assert_held(vm);
+
+- list_for_each_entry(q, &vm->preempt.exec_queues, compute.link) {
+- if (!q->compute.pfence ||
+- (q->compute.pfence && test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
+- &q->compute.pfence->flags))) {
++ list_for_each_entry(q, &vm->preempt.exec_queues, lr.link) {
++ if (!q->lr.pfence ||
++ test_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT,
++ &q->lr.pfence->flags)) {
+ return true;
+ }
+ }
+@@ -129,14 +129,14 @@ static int wait_for_existing_preempt_fences(struct xe_vm *vm)
+
+ xe_vm_assert_held(vm);
+
+- list_for_each_entry(q, &vm->preempt.exec_queues, compute.link) {
+- if (q->compute.pfence) {
+- long timeout = dma_fence_wait(q->compute.pfence, false);
++ list_for_each_entry(q, &vm->preempt.exec_queues, lr.link) {
++ if (q->lr.pfence) {
++ long timeout = dma_fence_wait(q->lr.pfence, false);
+
+ if (timeout < 0)
+ return -ETIME;
+- dma_fence_put(q->compute.pfence);
+- q->compute.pfence = NULL;
++ dma_fence_put(q->lr.pfence);
++ q->lr.pfence = NULL;
+ }
+ }
+
+@@ -148,7 +148,7 @@ static bool xe_vm_is_idle(struct xe_vm *vm)
+ struct xe_exec_queue *q;
+
+ xe_vm_assert_held(vm);
+- list_for_each_entry(q, &vm->preempt.exec_queues, compute.link) {
++ list_for_each_entry(q, &vm->preempt.exec_queues, lr.link) {
+ if (!xe_exec_queue_is_idle(q))
+ return false;
+ }
+@@ -161,17 +161,17 @@ static void arm_preempt_fences(struct xe_vm *vm, struct list_head *list)
+ struct list_head *link;
+ struct xe_exec_queue *q;
+
+- list_for_each_entry(q, &vm->preempt.exec_queues, compute.link) {
++ list_for_each_entry(q, &vm->preempt.exec_queues, lr.link) {
+ struct dma_fence *fence;
+
+ link = list->next;
+ xe_assert(vm->xe, link != list);
+
+ fence = xe_preempt_fence_arm(to_preempt_fence_from_link(link),
+- q, q->compute.context,
+- ++q->compute.seqno);
+- dma_fence_put(q->compute.pfence);
+- q->compute.pfence = fence;
++ q, q->lr.context,
++ ++q->lr.seqno);
++ dma_fence_put(q->lr.pfence);
++ q->lr.pfence = fence;
+ }
+ }
+
+@@ -191,10 +191,10 @@ static int add_preempt_fences(struct xe_vm *vm, struct xe_bo *bo)
+ if (err)
+ goto out_unlock;
+
+- list_for_each_entry(q, &vm->preempt.exec_queues, compute.link)
+- if (q->compute.pfence) {
++ list_for_each_entry(q, &vm->preempt.exec_queues, lr.link)
++ if (q->lr.pfence) {
+ dma_resv_add_fence(bo->ttm.base.resv,
+- q->compute.pfence,
++ q->lr.pfence,
+ DMA_RESV_USAGE_BOOKKEEP);
+ }
+
+@@ -211,10 +211,10 @@ static void resume_and_reinstall_preempt_fences(struct xe_vm *vm,
+ lockdep_assert_held(&vm->lock);
+ xe_vm_assert_held(vm);
+
+- list_for_each_entry(q, &vm->preempt.exec_queues, compute.link) {
++ list_for_each_entry(q, &vm->preempt.exec_queues, lr.link) {
+ q->ops->resume(q);
+
+- drm_gpuvm_resv_add_fence(&vm->gpuvm, exec, q->compute.pfence,
++ drm_gpuvm_resv_add_fence(&vm->gpuvm, exec, q->lr.pfence,
+ DMA_RESV_USAGE_BOOKKEEP, DMA_RESV_USAGE_BOOKKEEP);
+ }
+ }
+@@ -238,16 +238,16 @@ int xe_vm_add_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
+ if (err)
+ goto out_up_write;
+
+- pfence = xe_preempt_fence_create(q, q->compute.context,
+- ++q->compute.seqno);
++ pfence = xe_preempt_fence_create(q, q->lr.context,
++ ++q->lr.seqno);
+ if (!pfence) {
+ err = -ENOMEM;
+ goto out_fini;
+ }
+
+- list_add(&q->compute.link, &vm->preempt.exec_queues);
++ list_add(&q->lr.link, &vm->preempt.exec_queues);
+ ++vm->preempt.num_exec_queues;
+- q->compute.pfence = pfence;
++ q->lr.pfence = pfence;
+
+ down_read(&vm->userptr.notifier_lock);
+
+@@ -284,12 +284,12 @@ void xe_vm_remove_compute_exec_queue(struct xe_vm *vm, struct xe_exec_queue *q)
+ return;
+
+ down_write(&vm->lock);
+- list_del(&q->compute.link);
++ list_del(&q->lr.link);
+ --vm->preempt.num_exec_queues;
+- if (q->compute.pfence) {
+- dma_fence_enable_sw_signaling(q->compute.pfence);
+- dma_fence_put(q->compute.pfence);
+- q->compute.pfence = NULL;
++ if (q->lr.pfence) {
++ dma_fence_enable_sw_signaling(q->lr.pfence);
++ dma_fence_put(q->lr.pfence);
++ q->lr.pfence = NULL;
+ }
+ up_write(&vm->lock);
+ }
+@@ -325,7 +325,7 @@ static void xe_vm_kill(struct xe_vm *vm)
+ vm->flags |= XE_VM_FLAG_BANNED;
+ trace_xe_vm_kill(vm);
+
+- list_for_each_entry(q, &vm->preempt.exec_queues, compute.link)
++ list_for_each_entry(q, &vm->preempt.exec_queues, lr.link)
+ q->ops->kill(q);
+ xe_vm_unlock(vm);
+
+diff --git a/drivers/hwmon/pt5161l.c b/drivers/hwmon/pt5161l.c
+index b0d58a26d499d..a9f0b23f9e76e 100644
+--- a/drivers/hwmon/pt5161l.c
++++ b/drivers/hwmon/pt5161l.c
+@@ -427,7 +427,7 @@ static int pt5161l_read(struct device *dev, enum hwmon_sensor_types type,
+ struct pt5161l_data *data = dev_get_drvdata(dev);
+ int ret;
+ u8 buf[8];
+- long adc_code;
++ u32 adc_code;
+
+ switch (attr) {
+ case hwmon_temp_input:
+@@ -449,7 +449,7 @@ static int pt5161l_read(struct device *dev, enum hwmon_sensor_types type,
+
+ adc_code = buf[3] << 24 | buf[2] << 16 | buf[1] << 8 | buf[0];
+ if (adc_code == 0 || adc_code >= 0x3ff) {
+- dev_dbg(dev, "Invalid adc_code %lx\n", adc_code);
++ dev_dbg(dev, "Invalid adc_code %x\n", adc_code);
+ return -EIO;
+ }
+
+diff --git a/drivers/iommu/io-pgtable-arm-v7s.c b/drivers/iommu/io-pgtable-arm-v7s.c
+index 75f244a3e12df..06ffc683b28fe 100644
+--- a/drivers/iommu/io-pgtable-arm-v7s.c
++++ b/drivers/iommu/io-pgtable-arm-v7s.c
+@@ -552,9 +552,8 @@ static int arm_v7s_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+ paddr >= (1ULL << data->iop.cfg.oas)))
+ return -ERANGE;
+
+- /* If no access, then nothing to do */
+ if (!(prot & (IOMMU_READ | IOMMU_WRITE)))
+- return 0;
++ return -EINVAL;
+
+ while (pgcount--) {
+ ret = __arm_v7s_map(data, iova, paddr, pgsize, prot, 1, data->pgd,
+diff --git a/drivers/iommu/io-pgtable-arm.c b/drivers/iommu/io-pgtable-arm.c
+index 3d23b924cec16..07c9b90eab2ed 100644
+--- a/drivers/iommu/io-pgtable-arm.c
++++ b/drivers/iommu/io-pgtable-arm.c
+@@ -495,9 +495,8 @@ static int arm_lpae_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+ if (WARN_ON(iaext || paddr >> cfg->oas))
+ return -ERANGE;
+
+- /* If no access, then nothing to do */
+ if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
+- return 0;
++ return -EINVAL;
+
+ prot = arm_lpae_prot_to_pte(data, iommu_prot);
+ ret = __arm_lpae_map(data, iova, paddr, pgsize, pgcount, prot, lvl,
+diff --git a/drivers/iommu/io-pgtable-dart.c b/drivers/iommu/io-pgtable-dart.c
+index ad28031e1e93d..c004640640ee5 100644
+--- a/drivers/iommu/io-pgtable-dart.c
++++ b/drivers/iommu/io-pgtable-dart.c
+@@ -245,9 +245,8 @@ static int dart_map_pages(struct io_pgtable_ops *ops, unsigned long iova,
+ if (WARN_ON(paddr >> cfg->oas))
+ return -ERANGE;
+
+- /* If no access, then nothing to do */
+ if (!(iommu_prot & (IOMMU_READ | IOMMU_WRITE)))
+- return 0;
++ return -EINVAL;
+
+ tbl = dart_get_table(data, iova);
+
+diff --git a/drivers/iommu/iommufd/ioas.c b/drivers/iommu/iommufd/ioas.c
+index 7422482765481..157a89b993e43 100644
+--- a/drivers/iommu/iommufd/ioas.c
++++ b/drivers/iommu/iommufd/ioas.c
+@@ -213,6 +213,10 @@ int iommufd_ioas_map(struct iommufd_ucmd *ucmd)
+ if (cmd->iova >= ULONG_MAX || cmd->length >= ULONG_MAX)
+ return -EOVERFLOW;
+
++ if (!(cmd->flags &
++ (IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)))
++ return -EINVAL;
++
+ ioas = iommufd_get_ioas(ucmd->ictx, cmd->ioas_id);
+ if (IS_ERR(ioas))
+ return PTR_ERR(ioas);
+@@ -253,6 +257,10 @@ int iommufd_ioas_copy(struct iommufd_ucmd *ucmd)
+ cmd->dst_iova >= ULONG_MAX)
+ return -EOVERFLOW;
+
++ if (!(cmd->flags &
++ (IOMMU_IOAS_MAP_WRITEABLE | IOMMU_IOAS_MAP_READABLE)))
++ return -EINVAL;
++
+ src_ioas = iommufd_get_ioas(ucmd->ictx, cmd->src_ioas_id);
+ if (IS_ERR(src_ioas))
+ return PTR_ERR(src_ioas);
+diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
+index b257504a85347..60db34095a255 100644
+--- a/drivers/net/bonding/bond_main.c
++++ b/drivers/net/bonding/bond_main.c
+@@ -427,6 +427,8 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
+ struct netlink_ext_ack *extack)
+ {
+ struct net_device *bond_dev = xs->xso.dev;
++ struct net_device *real_dev;
++ netdevice_tracker tracker;
+ struct bond_ipsec *ipsec;
+ struct bonding *bond;
+ struct slave *slave;
+@@ -438,74 +440,80 @@ static int bond_ipsec_add_sa(struct xfrm_state *xs,
+ rcu_read_lock();
+ bond = netdev_priv(bond_dev);
+ slave = rcu_dereference(bond->curr_active_slave);
+- if (!slave) {
+- rcu_read_unlock();
+- return -ENODEV;
++ real_dev = slave ? slave->dev : NULL;
++ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
++ rcu_read_unlock();
++ if (!real_dev) {
++ err = -ENODEV;
++ goto out;
+ }
+
+- if (!slave->dev->xfrmdev_ops ||
+- !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+- netif_is_bond_master(slave->dev)) {
++ if (!real_dev->xfrmdev_ops ||
++ !real_dev->xfrmdev_ops->xdo_dev_state_add ||
++ netif_is_bond_master(real_dev)) {
+ NL_SET_ERR_MSG_MOD(extack, "Slave does not support ipsec offload");
+- rcu_read_unlock();
+- return -EINVAL;
++ err = -EINVAL;
++ goto out;
+ }
+
+- ipsec = kmalloc(sizeof(*ipsec), GFP_ATOMIC);
++ ipsec = kmalloc(sizeof(*ipsec), GFP_KERNEL);
+ if (!ipsec) {
+- rcu_read_unlock();
+- return -ENOMEM;
++ err = -ENOMEM;
++ goto out;
+ }
+- xs->xso.real_dev = slave->dev;
+
+- err = slave->dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
++ xs->xso.real_dev = real_dev;
++ err = real_dev->xfrmdev_ops->xdo_dev_state_add(xs, extack);
+ if (!err) {
+ ipsec->xs = xs;
+ INIT_LIST_HEAD(&ipsec->list);
+- spin_lock_bh(&bond->ipsec_lock);
++ mutex_lock(&bond->ipsec_lock);
+ list_add(&ipsec->list, &bond->ipsec_list);
+- spin_unlock_bh(&bond->ipsec_lock);
++ mutex_unlock(&bond->ipsec_lock);
+ } else {
+ kfree(ipsec);
+ }
+- rcu_read_unlock();
++out:
++ netdev_put(real_dev, &tracker);
+ return err;
+ }
+
+ static void bond_ipsec_add_sa_all(struct bonding *bond)
+ {
+ struct net_device *bond_dev = bond->dev;
++ struct net_device *real_dev;
+ struct bond_ipsec *ipsec;
+ struct slave *slave;
+
+- rcu_read_lock();
+- slave = rcu_dereference(bond->curr_active_slave);
+- if (!slave)
+- goto out;
++ slave = rtnl_dereference(bond->curr_active_slave);
++ real_dev = slave ? slave->dev : NULL;
++ if (!real_dev)
++ return;
+
+- if (!slave->dev->xfrmdev_ops ||
+- !slave->dev->xfrmdev_ops->xdo_dev_state_add ||
+- netif_is_bond_master(slave->dev)) {
+- spin_lock_bh(&bond->ipsec_lock);
++ mutex_lock(&bond->ipsec_lock);
++ if (!real_dev->xfrmdev_ops ||
++ !real_dev->xfrmdev_ops->xdo_dev_state_add ||
++ netif_is_bond_master(real_dev)) {
+ if (!list_empty(&bond->ipsec_list))
+- slave_warn(bond_dev, slave->dev,
++ slave_warn(bond_dev, real_dev,
+ "%s: no slave xdo_dev_state_add\n",
+ __func__);
+- spin_unlock_bh(&bond->ipsec_lock);
+ goto out;
+ }
+
+- spin_lock_bh(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+- ipsec->xs->xso.real_dev = slave->dev;
+- if (slave->dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
+- slave_warn(bond_dev, slave->dev, "%s: failed to add SA\n", __func__);
++ /* If new state is added before ipsec_lock acquired */
++ if (ipsec->xs->xso.real_dev == real_dev)
++ continue;
++
++ ipsec->xs->xso.real_dev = real_dev;
++ if (real_dev->xfrmdev_ops->xdo_dev_state_add(ipsec->xs, NULL)) {
++ slave_warn(bond_dev, real_dev, "%s: failed to add SA\n", __func__);
+ ipsec->xs->xso.real_dev = NULL;
+ }
+ }
+- spin_unlock_bh(&bond->ipsec_lock);
+ out:
+- rcu_read_unlock();
++ mutex_unlock(&bond->ipsec_lock);
+ }
+
+ /**
+@@ -515,6 +523,8 @@ static void bond_ipsec_add_sa_all(struct bonding *bond)
+ static void bond_ipsec_del_sa(struct xfrm_state *xs)
+ {
+ struct net_device *bond_dev = xs->xso.dev;
++ struct net_device *real_dev;
++ netdevice_tracker tracker;
+ struct bond_ipsec *ipsec;
+ struct bonding *bond;
+ struct slave *slave;
+@@ -525,6 +535,9 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
+ rcu_read_lock();
+ bond = netdev_priv(bond_dev);
+ slave = rcu_dereference(bond->curr_active_slave);
++ real_dev = slave ? slave->dev : NULL;
++ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
++ rcu_read_unlock();
+
+ if (!slave)
+ goto out;
+@@ -532,18 +545,19 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
+ if (!xs->xso.real_dev)
+ goto out;
+
+- WARN_ON(xs->xso.real_dev != slave->dev);
++ WARN_ON(xs->xso.real_dev != real_dev);
+
+- if (!slave->dev->xfrmdev_ops ||
+- !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+- netif_is_bond_master(slave->dev)) {
+- slave_warn(bond_dev, slave->dev, "%s: no slave xdo_dev_state_delete\n", __func__);
++ if (!real_dev->xfrmdev_ops ||
++ !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
++ netif_is_bond_master(real_dev)) {
++ slave_warn(bond_dev, real_dev, "%s: no slave xdo_dev_state_delete\n", __func__);
+ goto out;
+ }
+
+- slave->dev->xfrmdev_ops->xdo_dev_state_delete(xs);
++ real_dev->xfrmdev_ops->xdo_dev_state_delete(xs);
+ out:
+- spin_lock_bh(&bond->ipsec_lock);
++ netdev_put(real_dev, &tracker);
++ mutex_lock(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ if (ipsec->xs == xs) {
+ list_del(&ipsec->list);
+@@ -551,40 +565,72 @@ static void bond_ipsec_del_sa(struct xfrm_state *xs)
+ break;
+ }
+ }
+- spin_unlock_bh(&bond->ipsec_lock);
+- rcu_read_unlock();
++ mutex_unlock(&bond->ipsec_lock);
+ }
+
+ static void bond_ipsec_del_sa_all(struct bonding *bond)
+ {
+ struct net_device *bond_dev = bond->dev;
++ struct net_device *real_dev;
+ struct bond_ipsec *ipsec;
+ struct slave *slave;
+
+- rcu_read_lock();
+- slave = rcu_dereference(bond->curr_active_slave);
+- if (!slave) {
+- rcu_read_unlock();
++ slave = rtnl_dereference(bond->curr_active_slave);
++ real_dev = slave ? slave->dev : NULL;
++ if (!real_dev)
+ return;
+- }
+
+- spin_lock_bh(&bond->ipsec_lock);
++ mutex_lock(&bond->ipsec_lock);
+ list_for_each_entry(ipsec, &bond->ipsec_list, list) {
+ if (!ipsec->xs->xso.real_dev)
+ continue;
+
+- if (!slave->dev->xfrmdev_ops ||
+- !slave->dev->xfrmdev_ops->xdo_dev_state_delete ||
+- netif_is_bond_master(slave->dev)) {
+- slave_warn(bond_dev, slave->dev,
++ if (!real_dev->xfrmdev_ops ||
++ !real_dev->xfrmdev_ops->xdo_dev_state_delete ||
++ netif_is_bond_master(real_dev)) {
++ slave_warn(bond_dev, real_dev,
+ "%s: no slave xdo_dev_state_delete\n",
+ __func__);
+ } else {
+- slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
++ real_dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
++ if (real_dev->xfrmdev_ops->xdo_dev_state_free)
++ real_dev->xfrmdev_ops->xdo_dev_state_free(ipsec->xs);
+ }
+ }
+- spin_unlock_bh(&bond->ipsec_lock);
++ mutex_unlock(&bond->ipsec_lock);
++}
++
++static void bond_ipsec_free_sa(struct xfrm_state *xs)
++{
++ struct net_device *bond_dev = xs->xso.dev;
++ struct net_device *real_dev;
++ netdevice_tracker tracker;
++ struct bonding *bond;
++ struct slave *slave;
++
++ if (!bond_dev)
++ return;
++
++ rcu_read_lock();
++ bond = netdev_priv(bond_dev);
++ slave = rcu_dereference(bond->curr_active_slave);
++ real_dev = slave ? slave->dev : NULL;
++ netdev_hold(real_dev, &tracker, GFP_ATOMIC);
+ rcu_read_unlock();
++
++ if (!slave)
++ goto out;
++
++ if (!xs->xso.real_dev)
++ goto out;
++
++ WARN_ON(xs->xso.real_dev != real_dev);
++
++ if (real_dev && real_dev->xfrmdev_ops &&
++ real_dev->xfrmdev_ops->xdo_dev_state_free)
++ real_dev->xfrmdev_ops->xdo_dev_state_free(xs);
++out:
++ netdev_put(real_dev, &tracker);
+ }
+
+ /**
+@@ -627,6 +673,7 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+ static const struct xfrmdev_ops bond_xfrmdev_ops = {
+ .xdo_dev_state_add = bond_ipsec_add_sa,
+ .xdo_dev_state_delete = bond_ipsec_del_sa,
++ .xdo_dev_state_free = bond_ipsec_free_sa,
+ .xdo_dev_offload_ok = bond_ipsec_offload_ok,
+ };
+ #endif /* CONFIG_XFRM_OFFLOAD */
+@@ -5877,7 +5924,7 @@ void bond_setup(struct net_device *bond_dev)
+ /* set up xfrm device ops (only supported in active-backup right now) */
+ bond_dev->xfrmdev_ops = &bond_xfrmdev_ops;
+ INIT_LIST_HEAD(&bond->ipsec_list);
+- spin_lock_init(&bond->ipsec_lock);
++ mutex_init(&bond->ipsec_lock);
+ #endif /* CONFIG_XFRM_OFFLOAD */
+
+ /* don't acquire bond device's netif_tx_lock when transmitting */
+@@ -5926,6 +5973,10 @@ static void bond_uninit(struct net_device *bond_dev)
+ __bond_release_one(bond_dev, slave->dev, true, true);
+ netdev_info(bond_dev, "Released all slaves\n");
+
++#ifdef CONFIG_XFRM_OFFLOAD
++ mutex_destroy(&bond->ipsec_lock);
++#endif /* CONFIG_XFRM_OFFLOAD */
++
+ bond_set_slave_arr(bond, NULL, NULL);
+
+ list_del_rcu(&bond->bond_list);
+diff --git a/drivers/net/ethernet/microsoft/mana/hw_channel.c b/drivers/net/ethernet/microsoft/mana/hw_channel.c
+index bbc4f9e16c989..0a868679d342e 100644
+--- a/drivers/net/ethernet/microsoft/mana/hw_channel.c
++++ b/drivers/net/ethernet/microsoft/mana/hw_channel.c
+@@ -52,9 +52,33 @@ static int mana_hwc_verify_resp_msg(const struct hwc_caller_ctx *caller_ctx,
+ return 0;
+ }
+
++static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
++ struct hwc_work_request *req)
++{
++ struct device *dev = hwc_rxq->hwc->dev;
++ struct gdma_sge *sge;
++ int err;
++
++ sge = &req->sge;
++ sge->address = (u64)req->buf_sge_addr;
++ sge->mem_key = hwc_rxq->msg_buf->gpa_mkey;
++ sge->size = req->buf_len;
++
++ memset(&req->wqe_req, 0, sizeof(struct gdma_wqe_request));
++ req->wqe_req.sgl = sge;
++ req->wqe_req.num_sge = 1;
++ req->wqe_req.client_data_unit = 0;
++
++ err = mana_gd_post_and_ring(hwc_rxq->gdma_wq, &req->wqe_req, NULL);
++ if (err)
++ dev_err(dev, "Failed to post WQE on HWC RQ: %d\n", err);
++ return err;
++}
++
+ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
+- const struct gdma_resp_hdr *resp_msg)
++ struct hwc_work_request *rx_req)
+ {
++ const struct gdma_resp_hdr *resp_msg = rx_req->buf_va;
+ struct hwc_caller_ctx *ctx;
+ int err;
+
+@@ -62,6 +86,7 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
+ hwc->inflight_msg_res.map)) {
+ dev_err(hwc->dev, "hwc_rx: invalid msg_id = %u\n",
+ resp_msg->response.hwc_msg_id);
++ mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+ return;
+ }
+
+@@ -75,30 +100,13 @@ static void mana_hwc_handle_resp(struct hw_channel_context *hwc, u32 resp_len,
+ memcpy(ctx->output_buf, resp_msg, resp_len);
+ out:
+ ctx->error = err;
+- complete(&ctx->comp_event);
+-}
+-
+-static int mana_hwc_post_rx_wqe(const struct hwc_wq *hwc_rxq,
+- struct hwc_work_request *req)
+-{
+- struct device *dev = hwc_rxq->hwc->dev;
+- struct gdma_sge *sge;
+- int err;
+-
+- sge = &req->sge;
+- sge->address = (u64)req->buf_sge_addr;
+- sge->mem_key = hwc_rxq->msg_buf->gpa_mkey;
+- sge->size = req->buf_len;
+
+- memset(&req->wqe_req, 0, sizeof(struct gdma_wqe_request));
+- req->wqe_req.sgl = sge;
+- req->wqe_req.num_sge = 1;
+- req->wqe_req.client_data_unit = 0;
++ /* Must post rx wqe before complete(), otherwise the next rx may
++ * hit no_wqe error.
++ */
++ mana_hwc_post_rx_wqe(hwc->rxq, rx_req);
+
+- err = mana_gd_post_and_ring(hwc_rxq->gdma_wq, &req->wqe_req, NULL);
+- if (err)
+- dev_err(dev, "Failed to post WQE on HWC RQ: %d\n", err);
+- return err;
++ complete(&ctx->comp_event);
+ }
+
+ static void mana_hwc_init_event_handler(void *ctx, struct gdma_queue *q_self,
+@@ -235,14 +243,12 @@ static void mana_hwc_rx_event_handler(void *ctx, u32 gdma_rxq_id,
+ return;
+ }
+
+- mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, resp);
++ mana_hwc_handle_resp(hwc, rx_oob->tx_oob_data_size, rx_req);
+
+- /* Do no longer use 'resp', because the buffer is posted to the HW
+- * in the below mana_hwc_post_rx_wqe().
++ /* Can no longer use 'resp', because the buffer is posted to the HW
++ * in mana_hwc_handle_resp() above.
+ */
+ resp = NULL;
+-
+- mana_hwc_post_rx_wqe(hwc_rxq, rx_req);
+ }
+
+ static void mana_hwc_tx_event_handler(void *ctx, u32 gdma_txq_id,
+diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
+index 0696faf60013e..2e94d10348cce 100644
+--- a/drivers/net/gtp.c
++++ b/drivers/net/gtp.c
+@@ -1653,7 +1653,7 @@ static struct sock *gtp_encap_enable_socket(int fd, int type,
+ sock = sockfd_lookup(fd, &err);
+ if (!sock) {
+ pr_debug("gtp socket fd=%d not found\n", fd);
+- return NULL;
++ return ERR_PTR(err);
+ }
+
+ sk = sock->sk;
+diff --git a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+index fa339791223b8..ba9e656037a20 100644
+--- a/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
++++ b/drivers/net/wireless/intel/iwlwifi/fw/acpi.c
+@@ -724,22 +724,25 @@ int iwl_acpi_get_wgds_table(struct iwl_fw_runtime *fwrt)
+ entry = &wifi_pkg->package.elements[entry_idx];
+ entry_idx++;
+ if (entry->type != ACPI_TYPE_INTEGER ||
+- entry->integer.value > num_profiles) {
++ entry->integer.value > num_profiles ||
++ entry->integer.value <
++ rev_data[idx].min_profiles) {
+ ret = -EINVAL;
+ goto out_free;
+ }
+- num_profiles = entry->integer.value;
+
+ /*
+- * this also validates >= min_profiles since we
+- * otherwise wouldn't have gotten the data when
+- * looking up in ACPI
++ * Check to see if we received package count
++ * same as max # of profiles
+ */
+ if (wifi_pkg->package.count !=
+ hdr_size + profile_size * num_profiles) {
+ ret = -EINVAL;
+ goto out_free;
+ }
++
++ /* Number of valid profiles */
++ num_profiles = entry->integer.value;
+ }
+ goto read_table;
+ }
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+index d343432474db0..1380ae5155f35 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/ops.c
+@@ -1190,10 +1190,12 @@ static void iwl_mvm_trig_link_selection(struct wiphy *wiphy,
+ struct iwl_mvm *mvm =
+ container_of(wk, struct iwl_mvm, trig_link_selection_wk);
+
++ mutex_lock(&mvm->mutex);
+ ieee80211_iterate_active_interfaces(mvm->hw,
+ IEEE80211_IFACE_ITER_NORMAL,
+ iwl_mvm_find_link_selection_vif,
+ NULL);
++ mutex_unlock(&mvm->mutex);
+ }
+
+ static struct iwl_op_mode *
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+index e975f5ff17b5d..7615c91a55c62 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/scan.c
+@@ -1659,6 +1659,17 @@ iwl_mvm_umac_scan_cfg_channels_v7(struct iwl_mvm *mvm,
+ cfg->v2.channel_num = channels[i]->hw_value;
+ if (cfg80211_channel_is_psc(channels[i]))
+ cfg->flags = 0;
++
++ if (band == NL80211_BAND_6GHZ) {
++ /* 6 GHz channels should only appear in a scan request
++ * that has scan_6ghz set. The only exception is MLO
++ * scan, which has to be passive.
++ */
++ WARN_ON_ONCE(cfg->flags != 0);
++ cfg->flags =
++ cpu_to_le32(IWL_UHB_CHAN_CFG_FLAG_FORCE_PASSIVE);
++ }
++
+ cfg->v2.iter_count = 1;
+ cfg->v2.iter_interval = 0;
+ if (version < 17)
+diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+index 155eb0fab12a4..bf35c92f91d7e 100644
+--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
++++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+@@ -4363,11 +4363,27 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
+ if (ISSUPP_ADHOC_ENABLED(adapter->fw_cap_info))
+ wiphy->interface_modes |= BIT(NL80211_IFTYPE_ADHOC);
+
+- wiphy->bands[NL80211_BAND_2GHZ] = &mwifiex_band_2ghz;
+- if (adapter->config_bands & BAND_A)
+- wiphy->bands[NL80211_BAND_5GHZ] = &mwifiex_band_5ghz;
+- else
++ wiphy->bands[NL80211_BAND_2GHZ] = devm_kmemdup(adapter->dev,
++ &mwifiex_band_2ghz,
++ sizeof(mwifiex_band_2ghz),
++ GFP_KERNEL);
++ if (!wiphy->bands[NL80211_BAND_2GHZ]) {
++ ret = -ENOMEM;
++ goto err;
++ }
++
++ if (adapter->config_bands & BAND_A) {
++ wiphy->bands[NL80211_BAND_5GHZ] = devm_kmemdup(adapter->dev,
++ &mwifiex_band_5ghz,
++ sizeof(mwifiex_band_5ghz),
++ GFP_KERNEL);
++ if (!wiphy->bands[NL80211_BAND_5GHZ]) {
++ ret = -ENOMEM;
++ goto err;
++ }
++ } else {
+ wiphy->bands[NL80211_BAND_5GHZ] = NULL;
++ }
+
+ if (adapter->drcs_enabled && ISSUPP_DRCS_ENABLED(adapter->fw_cap_info))
+ wiphy->iface_combinations = &mwifiex_iface_comb_ap_sta_drcs;
+@@ -4461,8 +4477,7 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
+ if (ret < 0) {
+ mwifiex_dbg(adapter, ERROR,
+ "%s: wiphy_register failed: %d\n", __func__, ret);
+- wiphy_free(wiphy);
+- return ret;
++ goto err;
+ }
+
+ if (!adapter->regd) {
+@@ -4504,4 +4519,9 @@ int mwifiex_register_cfg80211(struct mwifiex_adapter *adapter)
+
+ adapter->wiphy = wiphy;
+ return ret;
++
++err:
++ wiphy_free(wiphy);
++
++ return ret;
+ }
+diff --git a/drivers/net/wireless/silabs/wfx/sta.c b/drivers/net/wireless/silabs/wfx/sta.c
+index a904602f02ce2..5930ff49c43ea 100644
+--- a/drivers/net/wireless/silabs/wfx/sta.c
++++ b/drivers/net/wireless/silabs/wfx/sta.c
+@@ -352,8 +352,11 @@ static int wfx_set_mfp_ap(struct wfx_vif *wvif)
+
+ ptr = (u16 *)cfg80211_find_ie(WLAN_EID_RSN, skb->data + ieoffset,
+ skb->len - ieoffset);
+- if (unlikely(!ptr))
++ if (!ptr) {
++ /* No RSN IE is fine in open networks */
++ ret = 0;
+ goto free_skb;
++ }
+
+ ptr += pairwise_cipher_suite_count_offset;
+ if (WARN_ON(ptr > (u16 *)skb_tail_pointer(skb)))
+diff --git a/drivers/nfc/pn533/pn533.c b/drivers/nfc/pn533/pn533.c
+index b19c39dcfbd93..e2bc67300a915 100644
+--- a/drivers/nfc/pn533/pn533.c
++++ b/drivers/nfc/pn533/pn533.c
+@@ -1723,6 +1723,11 @@ static int pn533_start_poll(struct nfc_dev *nfc_dev,
+ }
+
+ pn533_poll_create_mod_list(dev, im_protocols, tm_protocols);
++ if (!dev->poll_mod_count) {
++ nfc_err(dev->dev,
++ "Poll mod list is empty\n");
++ return -EINVAL;
++ }
+
+ /* Do not always start polling from the same modulation */
+ get_random_bytes(&rand_mod, sizeof(rand_mod));
+diff --git a/drivers/of/platform.c b/drivers/of/platform.c
+index 389d4ea6bfc15..ef622d41eb5b2 100644
+--- a/drivers/of/platform.c
++++ b/drivers/of/platform.c
+@@ -592,7 +592,7 @@ static int __init of_platform_default_populate_init(void)
+ * This can happen for example on DT systems that do EFI
+ * booting and may provide a GOP handle to the EFI stub.
+ */
+- sysfb_disable();
++ sysfb_disable(NULL);
+ of_platform_device_create(node, NULL, NULL);
+ of_node_put(node);
+ }
+diff --git a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
+index 0b9a59d5b8f02..adc6394626ce8 100644
+--- a/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
++++ b/drivers/phy/freescale/phy-fsl-imx8mq-usb.c
+@@ -176,7 +176,7 @@ static void imx8m_get_phy_tuning_data(struct imx8mq_usb_phy *imx_phy)
+ imx_phy->comp_dis_tune =
+ phy_comp_dis_tune_from_property(imx_phy->comp_dis_tune);
+
+- if (device_property_read_u32(dev, "fsl,pcs-tx-deemph-3p5db-attenuation-db",
++ if (device_property_read_u32(dev, "fsl,phy-pcs-tx-deemph-3p5db-attenuation-db",
+ &imx_phy->pcs_tx_deemph_3p5db))
+ imx_phy->pcs_tx_deemph_3p5db = PHY_TUNE_DEFAULT;
+ else
+diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+index 8fcdcb193d241..e99cbcc378908 100644
+--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
++++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+@@ -1008,8 +1008,8 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_serdes_tbl[] = {
+ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_ln_shrd_tbl[] = {
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RXCLK_DIV2_CTRL, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_DFE_DAC_ENABLE1, 0x88),
+- QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH1, 0x00),
+- QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH2, 0x1f),
++ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH1, 0x02),
++ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_TX_ADAPT_POST_THRESH2, 0x0d),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B0, 0xd4),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B1, 0x12),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MODE_RATE_0_1_B2, 0xdb),
+@@ -1026,6 +1026,7 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_ln_shrd_tbl[] = {
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH4_RATE3, 0x1f),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH5_RATE3, 0x1f),
+ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_MARG_COARSE_THRESH6_RATE3, 0x1f),
++ QMP_PHY_INIT_CFG(QSERDES_V6_LN_SHRD_RX_SUMMER_CAL_SPD_MODE, 0x5b),
+ };
+
+ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_tx_tbl[] = {
+@@ -1049,12 +1050,15 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_rx_tbl[] = {
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_1, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_2, 0x01),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_3, 0x45),
+- QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0b),
++ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0a, 1),
++ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_VGA_CAL_MAN_VAL, 0x0b, 2),
++ QMP_PHY_INIT_CFG(QSERDES_V6_20_VGA_CAL_CNTRL1, 0x00),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_GM_CAL, 0x0d),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_EQU_ADAPTOR_CNTRL4, 0x0b),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_SIGDET_ENABLES, 0x1c),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_PHPRE_CTRL, 0x20),
+- QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38),
++ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x3a, 1),
++ QMP_PHY_INIT_CFG_LANE(QSERDES_V6_20_RX_DFE_CTLE_POST_CAL_OFFSET, 0x38, 2),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_Q_PI_INTRINSIC_BIAS_RATE32, 0x39),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B0, 0x14),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE2_B1, 0xb3),
+@@ -1070,6 +1074,7 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_rx_tbl[] = {
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B4, 0x4b),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B5, 0x76),
+ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_MODE_RATE3_B6, 0xff),
++ QMP_PHY_INIT_CFG(QSERDES_V6_20_RX_TX_ADPT_CTRL, 0x10),
+ };
+
+ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_tbl[] = {
+@@ -1077,6 +1082,8 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_tbl[] = {
+ QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_RX_SIGDET_LVL, 0xcc),
+ QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_EQ_CONFIG4, 0x00),
+ QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_EQ_CONFIG5, 0x22),
++ QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_TX_RX_CONFIG1, 0x04),
++ QMP_PHY_INIT_CFG(QPHY_V6_20_PCS_TX_RX_CONFIG2, 0x02),
+ };
+
+ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_misc_tbl[] = {
+@@ -1087,11 +1094,13 @@ static const struct qmp_phy_init_tbl x1e80100_qmp_gen4x2_pcie_pcs_misc_tbl[] = {
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_PRE_GAIN, 0x2e),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG1, 0x03),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG3, 0x28),
++ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G3_RXEQEVAL_TIME, 0x27),
++ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_RXEQEVAL_TIME, 0x27),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_TX_RX_CONFIG, 0xc0),
+ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_POWER_STATE_CONFIG2, 0x1d),
+- QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG5, 0x0f),
+- QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G3_FOM_EQ_CONFIG5, 0xf2),
+- QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0xf2),
++ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_RX_MARGINING_CONFIG5, 0x18),
++ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G3_FOM_EQ_CONFIG5, 0x7a),
++ QMP_PHY_INIT_CFG(QPHY_PCIE_V6_20_PCS_G4_FOM_EQ_CONFIG5, 0x8a),
+ };
+
+ static const struct qmp_phy_init_tbl sm8250_qmp_pcie_serdes_tbl[] = {
+diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c
+index f2bff7f25f05a..d7d12cf3011a2 100644
+--- a/drivers/phy/xilinx/phy-zynqmp.c
++++ b/drivers/phy/xilinx/phy-zynqmp.c
+@@ -166,6 +166,24 @@
+ /* Timeout values */
+ #define TIMEOUT_US 1000
+
++/* Lane 0/1/2/3 offset */
++#define DIG_8(n) ((0x4000 * (n)) + 0x1074)
++#define ILL13(n) ((0x4000 * (n)) + 0x1994)
++#define DIG_10(n) ((0x4000 * (n)) + 0x107c)
++#define RST_DLY(n) ((0x4000 * (n)) + 0x19a4)
++#define BYP_15(n) ((0x4000 * (n)) + 0x1038)
++#define BYP_12(n) ((0x4000 * (n)) + 0x102c)
++#define MISC3(n) ((0x4000 * (n)) + 0x19ac)
++#define EQ11(n) ((0x4000 * (n)) + 0x1978)
++
++static u32 save_reg_address[] = {
++ /* Lane 0/1/2/3 Register */
++ DIG_8(0), ILL13(0), DIG_10(0), RST_DLY(0), BYP_15(0), BYP_12(0), MISC3(0), EQ11(0),
++ DIG_8(1), ILL13(1), DIG_10(1), RST_DLY(1), BYP_15(1), BYP_12(1), MISC3(1), EQ11(1),
++ DIG_8(2), ILL13(2), DIG_10(2), RST_DLY(2), BYP_15(2), BYP_12(2), MISC3(2), EQ11(2),
++ DIG_8(3), ILL13(3), DIG_10(3), RST_DLY(3), BYP_15(3), BYP_12(3), MISC3(3), EQ11(3),
++};
++
+ struct xpsgtr_dev;
+
+ /**
+@@ -214,6 +232,7 @@ struct xpsgtr_phy {
+ * @tx_term_fix: fix for GT issue
+ * @saved_icm_cfg0: stored value of ICM CFG0 register
+ * @saved_icm_cfg1: stored value of ICM CFG1 register
++ * @saved_regs: registers to be saved/restored during suspend/resume
+ */
+ struct xpsgtr_dev {
+ struct device *dev;
+@@ -226,6 +245,7 @@ struct xpsgtr_dev {
+ bool tx_term_fix;
+ unsigned int saved_icm_cfg0;
+ unsigned int saved_icm_cfg1;
++ u32 *saved_regs;
+ };
+
+ /*
+@@ -299,6 +319,32 @@ static inline void xpsgtr_clr_set_phy(struct xpsgtr_phy *gtr_phy,
+ writel((readl(addr) & ~clr) | set, addr);
+ }
+
++/**
++ * xpsgtr_save_lane_regs - Saves registers on suspend
++ * @gtr_dev: pointer to phy controller context structure
++ */
++static void xpsgtr_save_lane_regs(struct xpsgtr_dev *gtr_dev)
++{
++ int i;
++
++ for (i = 0; i < ARRAY_SIZE(save_reg_address); i++)
++ gtr_dev->saved_regs[i] = xpsgtr_read(gtr_dev,
++ save_reg_address[i]);
++}
++
++/**
++ * xpsgtr_restore_lane_regs - Restores registers on resume
++ * @gtr_dev: pointer to phy controller context structure
++ */
++static void xpsgtr_restore_lane_regs(struct xpsgtr_dev *gtr_dev)
++{
++ int i;
++
++ for (i = 0; i < ARRAY_SIZE(save_reg_address); i++)
++ xpsgtr_write(gtr_dev, save_reg_address[i],
++ gtr_dev->saved_regs[i]);
++}
++
+ /*
+ * Hardware Configuration
+ */
+@@ -839,6 +885,8 @@ static int xpsgtr_runtime_suspend(struct device *dev)
+ gtr_dev->saved_icm_cfg0 = xpsgtr_read(gtr_dev, ICM_CFG0);
+ gtr_dev->saved_icm_cfg1 = xpsgtr_read(gtr_dev, ICM_CFG1);
+
++ xpsgtr_save_lane_regs(gtr_dev);
++
+ return 0;
+ }
+
+@@ -849,6 +897,8 @@ static int xpsgtr_runtime_resume(struct device *dev)
+ unsigned int i;
+ bool skip_phy_init;
+
++ xpsgtr_restore_lane_regs(gtr_dev);
++
+ icm_cfg0 = xpsgtr_read(gtr_dev, ICM_CFG0);
+ icm_cfg1 = xpsgtr_read(gtr_dev, ICM_CFG1);
+
+@@ -994,6 +1044,12 @@ static int xpsgtr_probe(struct platform_device *pdev)
+ return ret;
+ }
+
++ gtr_dev->saved_regs = devm_kmalloc(gtr_dev->dev,
++ sizeof(save_reg_address),
++ GFP_KERNEL);
++ if (!gtr_dev->saved_regs)
++ return -ENOMEM;
++
+ return 0;
+ }
+
+diff --git a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
+index b7921b59eb7b1..54301fbba524a 100644
+--- a/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
++++ b/drivers/pinctrl/mediatek/pinctrl-mtk-common-v2.c
+@@ -709,32 +709,35 @@ static int mtk_pinconf_bias_set_rsel(struct mtk_pinctrl *hw,
+ {
+ int err, rsel_val;
+
+- if (!pullup && arg == MTK_DISABLE)
+- return 0;
+-
+ if (hw->rsel_si_unit) {
+ /* find pin rsel_index from pin_rsel array*/
+ err = mtk_hw_pin_rsel_lookup(hw, desc, pullup, arg, &rsel_val);
+ if (err)
+- goto out;
++ return err;
+ } else {
+- if (arg < MTK_PULL_SET_RSEL_000 ||
+- arg > MTK_PULL_SET_RSEL_111) {
+- err = -EINVAL;
+- goto out;
+- }
++ if (arg < MTK_PULL_SET_RSEL_000 || arg > MTK_PULL_SET_RSEL_111)
++ return -EINVAL;
+
+ rsel_val = arg - MTK_PULL_SET_RSEL_000;
+ }
+
+- err = mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_RSEL, rsel_val);
+- if (err)
+- goto out;
++ return mtk_hw_set_value(hw, desc, PINCTRL_PIN_REG_RSEL, rsel_val);
++}
+
+- err = mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, MTK_ENABLE);
++static int mtk_pinconf_bias_set_pu_pd_rsel(struct mtk_pinctrl *hw,
++ const struct mtk_pin_desc *desc,
++ u32 pullup, u32 arg)
++{
++ u32 enable = arg == MTK_DISABLE ? MTK_DISABLE : MTK_ENABLE;
++ int err;
+
+-out:
+- return err;
++ if (arg != MTK_DISABLE) {
++ err = mtk_pinconf_bias_set_rsel(hw, desc, pullup, arg);
++ if (err)
++ return err;
++ }
++
++ return mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, enable);
+ }
+
+ int mtk_pinconf_bias_set_combo(struct mtk_pinctrl *hw,
+@@ -750,22 +753,22 @@ int mtk_pinconf_bias_set_combo(struct mtk_pinctrl *hw,
+ try_all_type = MTK_PULL_TYPE_MASK;
+
+ if (try_all_type & MTK_PULL_RSEL_TYPE) {
+- err = mtk_pinconf_bias_set_rsel(hw, desc, pullup, arg);
++ err = mtk_pinconf_bias_set_pu_pd_rsel(hw, desc, pullup, arg);
+ if (!err)
+- return err;
++ return 0;
+ }
+
+ if (try_all_type & MTK_PULL_PU_PD_TYPE) {
+ err = mtk_pinconf_bias_set_pu_pd(hw, desc, pullup, arg);
+ if (!err)
+- return err;
++ return 0;
+ }
+
+ if (try_all_type & MTK_PULL_PULLSEL_TYPE) {
+ err = mtk_pinconf_bias_set_pullsel_pullen(hw, desc,
+ pullup, arg);
+ if (!err)
+- return err;
++ return 0;
+ }
+
+ if (try_all_type & MTK_PULL_PUPD_R1R0_TYPE)
+@@ -803,9 +806,9 @@ static int mtk_rsel_get_si_unit(struct mtk_pinctrl *hw,
+ return 0;
+ }
+
+-static int mtk_pinconf_bias_get_rsel(struct mtk_pinctrl *hw,
+- const struct mtk_pin_desc *desc,
+- u32 *pullup, u32 *enable)
++static int mtk_pinconf_bias_get_pu_pd_rsel(struct mtk_pinctrl *hw,
++ const struct mtk_pin_desc *desc,
++ u32 *pullup, u32 *enable)
+ {
+ int pu, pd, rsel, err;
+
+@@ -939,22 +942,22 @@ int mtk_pinconf_bias_get_combo(struct mtk_pinctrl *hw,
+ try_all_type = MTK_PULL_TYPE_MASK;
+
+ if (try_all_type & MTK_PULL_RSEL_TYPE) {
+- err = mtk_pinconf_bias_get_rsel(hw, desc, pullup, enable);
++ err = mtk_pinconf_bias_get_pu_pd_rsel(hw, desc, pullup, enable);
+ if (!err)
+- return err;
++ return 0;
+ }
+
+ if (try_all_type & MTK_PULL_PU_PD_TYPE) {
+ err = mtk_pinconf_bias_get_pu_pd(hw, desc, pullup, enable);
+ if (!err)
+- return err;
++ return 0;
+ }
+
+ if (try_all_type & MTK_PULL_PULLSEL_TYPE) {
+ err = mtk_pinconf_bias_get_pullsel_pullen(hw, desc,
+ pullup, enable);
+ if (!err)
+- return err;
++ return 0;
+ }
+
+ if (try_all_type & MTK_PULL_PUPD_R1R0_TYPE)
+diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
+index 6a74619786300..7b7b8601d01a1 100644
+--- a/drivers/pinctrl/pinctrl-rockchip.c
++++ b/drivers/pinctrl/pinctrl-rockchip.c
+@@ -3800,7 +3800,7 @@ static struct rockchip_pin_bank rk3328_pin_banks[] = {
+ PIN_BANK_IOMUX_FLAGS(0, 32, "gpio0", 0, 0, 0, 0),
+ PIN_BANK_IOMUX_FLAGS(1, 32, "gpio1", 0, 0, 0, 0),
+ PIN_BANK_IOMUX_FLAGS(2, 32, "gpio2", 0,
+- 0,
++ IOMUX_WIDTH_2BIT,
+ IOMUX_WIDTH_3BIT,
+ 0),
+ PIN_BANK_IOMUX_FLAGS(3, 32, "gpio3",
+diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
+index 4c6bfabb6bd7d..4da3c3f422b69 100644
+--- a/drivers/pinctrl/pinctrl-single.c
++++ b/drivers/pinctrl/pinctrl-single.c
+@@ -345,6 +345,8 @@ static int pcs_get_function(struct pinctrl_dev *pctldev, unsigned pin,
+ return -ENOTSUPP;
+ fselector = setting->func;
+ function = pinmux_generic_get_function(pctldev, fselector);
++ if (!function)
++ return -EINVAL;
+ *func = function->data;
+ if (!(*func)) {
+ dev_err(pcs->dev, "%s could not find function%i\n",
+diff --git a/drivers/pinctrl/qcom/pinctrl-x1e80100.c b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+index e30e938403574..65ed933f05ce1 100644
+--- a/drivers/pinctrl/qcom/pinctrl-x1e80100.c
++++ b/drivers/pinctrl/qcom/pinctrl-x1e80100.c
+@@ -1805,26 +1805,29 @@ static const struct msm_pingroup x1e80100_groups[] = {
+ [235] = PINGROUP(235, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
+ [236] = PINGROUP(236, aon_cci, qdss_gpio, _, _, _, _, _, _, _),
+ [237] = PINGROUP(237, _, _, _, _, _, _, _, _, _),
+- [238] = UFS_RESET(ufs_reset, 0x1f9000),
+- [239] = SDC_QDSD_PINGROUP(sdc2_clk, 0x1f2000, 14, 6),
+- [240] = SDC_QDSD_PINGROUP(sdc2_cmd, 0x1f2000, 11, 3),
+- [241] = SDC_QDSD_PINGROUP(sdc2_data, 0x1f2000, 9, 0),
++ [238] = UFS_RESET(ufs_reset, 0xf9000),
++ [239] = SDC_QDSD_PINGROUP(sdc2_clk, 0xf2000, 14, 6),
++ [240] = SDC_QDSD_PINGROUP(sdc2_cmd, 0xf2000, 11, 3),
++ [241] = SDC_QDSD_PINGROUP(sdc2_data, 0xf2000, 9, 0),
+ };
+
+ static const struct msm_gpio_wakeirq_map x1e80100_pdc_map[] = {
+ { 0, 72 }, { 2, 70 }, { 3, 71 }, { 6, 123 }, { 7, 67 }, { 11, 85 },
+- { 15, 68 }, { 18, 122 }, { 19, 69 }, { 21, 158 }, { 23, 143 }, { 26, 129 },
+- { 27, 144 }, { 28, 77 }, { 29, 78 }, { 30, 92 }, { 32, 145 }, { 33, 115 },
+- { 34, 130 }, { 35, 146 }, { 36, 147 }, { 39, 80 }, { 43, 148 }, { 47, 149 },
+- { 51, 79 }, { 53, 89 }, { 59, 87 }, { 64, 90 }, { 65, 106 }, { 66, 142 },
+- { 67, 88 }, { 71, 91 }, { 75, 152 }, { 79, 153 }, { 80, 125 }, { 81, 128 },
+- { 84, 137 }, { 85, 155 }, { 87, 156 }, { 91, 157 }, { 92, 138 }, { 94, 140 },
+- { 95, 141 }, { 113, 84 }, { 121, 73 }, { 123, 74 }, { 129, 76 }, { 131, 82 },
+- { 134, 83 }, { 141, 93 }, { 144, 94 }, { 147, 96 }, { 148, 97 }, { 150, 102 },
+- { 151, 103 }, { 153, 104 }, { 156, 105 }, { 157, 107 }, { 163, 98 }, { 166, 112 },
+- { 172, 99 }, { 181, 101 }, { 184, 116 }, { 193, 40 }, { 193, 117 }, { 196, 108 },
+- { 203, 133 }, { 212, 120 }, { 213, 150 }, { 214, 121 }, { 215, 118 }, { 217, 109 },
+- { 220, 110 }, { 221, 111 }, { 222, 124 }, { 224, 131 }, { 225, 132 },
++ { 13, 86 }, { 15, 68 }, { 18, 122 }, { 19, 69 }, { 21, 158 }, { 23, 143 },
++ { 24, 126 }, { 26, 129 }, { 27, 144 }, { 28, 77 }, { 29, 78 }, { 30, 92 },
++ { 31, 159 }, { 32, 145 }, { 33, 115 }, { 34, 130 }, { 35, 146 }, { 36, 147 },
++ { 38, 113 }, { 39, 80 }, { 43, 148 }, { 47, 149 }, { 51, 79 }, { 53, 89 },
++ { 55, 81 }, { 59, 87 }, { 64, 90 }, { 65, 106 }, { 66, 142 }, { 67, 88 },
++ { 68, 151 }, { 71, 91 }, { 75, 152 }, { 79, 153 }, { 80, 125 }, { 81, 128 },
++ { 83, 154 }, { 84, 137 }, { 85, 155 }, { 87, 156 }, { 91, 157 }, { 92, 138 },
++ { 93, 139 }, { 94, 140 }, { 95, 141 }, { 113, 84 }, { 121, 73 }, { 123, 74 },
++ { 125, 75 }, { 129, 76 }, { 131, 82 }, { 134, 83 }, { 141, 93 }, { 144, 94 },
++ { 145, 95 }, { 147, 96 }, { 148, 97 }, { 150, 102 }, { 151, 103 }, { 153, 104 },
++ { 154, 100 }, { 156, 105 }, { 157, 107 }, { 163, 98 }, { 166, 112 }, { 172, 99 },
++ { 175, 114 }, { 181, 101 }, { 184, 116 }, { 193, 117 }, { 196, 108 }, { 203, 133 },
++ { 208, 134 }, { 212, 120 }, { 213, 150 }, { 214, 121 }, { 215, 118 }, { 217, 109 },
++ { 219, 119 }, { 220, 110 }, { 221, 111 }, { 222, 124 }, { 224, 131 }, { 225, 132 },
++ { 228, 135 }, { 230, 136 }, { 232, 162 },
+ };
+
+ static const struct msm_pinctrl_soc_data x1e80100_pinctrl = {
+diff --git a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+index 9609eb1ecc3d8..7637de7452b91 100644
+--- a/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
++++ b/drivers/pinctrl/starfive/pinctrl-starfive-jh7110.c
+@@ -795,12 +795,12 @@ static int jh7110_irq_set_type(struct irq_data *d, unsigned int trigger)
+ case IRQ_TYPE_LEVEL_HIGH:
+ irq_type = 0; /* 0: level triggered */
+ edge_both = 0; /* 0: ignored */
+- polarity = mask; /* 1: high level */
++ polarity = 0; /* 0: high level */
+ break;
+ case IRQ_TYPE_LEVEL_LOW:
+ irq_type = 0; /* 0: level triggered */
+ edge_both = 0; /* 0: ignored */
+- polarity = 0; /* 0: low level */
++ polarity = mask; /* 1: low level */
+ break;
+ default:
+ return -EINVAL;
+diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
+index 44c6301f5f174..5b3681b9100c1 100644
+--- a/drivers/power/supply/qcom_battmgr.c
++++ b/drivers/power/supply/qcom_battmgr.c
+@@ -1384,12 +1384,16 @@ static int qcom_battmgr_probe(struct auxiliary_device *adev,
+ "failed to register wireless charing power supply\n");
+ }
+
+- battmgr->client = devm_pmic_glink_register_client(dev,
+- PMIC_GLINK_OWNER_BATTMGR,
+- qcom_battmgr_callback,
+- qcom_battmgr_pdr_notify,
+- battmgr);
+- return PTR_ERR_OR_ZERO(battmgr->client);
++ battmgr->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_BATTMGR,
++ qcom_battmgr_callback,
++ qcom_battmgr_pdr_notify,
++ battmgr);
++ if (IS_ERR(battmgr->client))
++ return PTR_ERR(battmgr->client);
++
++ pmic_glink_client_register(battmgr->client);
++
++ return 0;
+ }
+
+ static const struct auxiliary_device_id qcom_battmgr_id_table[] = {
+diff --git a/drivers/scsi/aacraid/comminit.c b/drivers/scsi/aacraid/comminit.c
+index bd99c5492b7d4..0f64b02443037 100644
+--- a/drivers/scsi/aacraid/comminit.c
++++ b/drivers/scsi/aacraid/comminit.c
+@@ -642,6 +642,7 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
+
+ if (aac_comm_init(dev)<0){
+ kfree(dev->queues);
++ dev->queues = NULL;
+ return NULL;
+ }
+ /*
+@@ -649,6 +650,7 @@ struct aac_dev *aac_init_adapter(struct aac_dev *dev)
+ */
+ if (aac_fib_setup(dev) < 0) {
+ kfree(dev->queues);
++ dev->queues = NULL;
+ return NULL;
+ }
+
+diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
+index 6b64af7d49273..7d2a294ebc3d7 100644
+--- a/drivers/scsi/sd.c
++++ b/drivers/scsi/sd.c
+@@ -1711,13 +1711,15 @@ static int sd_sync_cache(struct scsi_disk *sdkp)
+ (sshdr.asc == 0x74 && sshdr.ascq == 0x71)) /* drive is password locked */
+ /* this is no error here */
+ return 0;
++
+ /*
+- * This drive doesn't support sync and there's not much
+- * we can do because this is called during shutdown
+- * or suspend so just return success so those operations
+- * can proceed.
++ * If a format is in progress or if the drive does not
++ * support sync, there is not much we can do because
++ * this is called during shutdown or suspend so just
++ * return success so those operations can proceed.
+ */
+- if (sshdr.sense_key == ILLEGAL_REQUEST)
++ if ((sshdr.asc == 0x04 && sshdr.ascq == 0x04) ||
++ sshdr.sense_key == ILLEGAL_REQUEST)
+ return 0;
+ }
+
+diff --git a/drivers/soc/qcom/cmd-db.c b/drivers/soc/qcom/cmd-db.c
+index d845726620175..ae66c2623d250 100644
+--- a/drivers/soc/qcom/cmd-db.c
++++ b/drivers/soc/qcom/cmd-db.c
+@@ -349,7 +349,7 @@ static int cmd_db_dev_probe(struct platform_device *pdev)
+ return -EINVAL;
+ }
+
+- cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WB);
++ cmd_db_header = memremap(rmem->base, rmem->size, MEMREMAP_WC);
+ if (!cmd_db_header) {
+ ret = -ENOMEM;
+ cmd_db_header = NULL;
+diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
+index 9ebc0ba359477..9606222993fd7 100644
+--- a/drivers/soc/qcom/pmic_glink.c
++++ b/drivers/soc/qcom/pmic_glink.c
+@@ -66,15 +66,14 @@ static void _devm_pmic_glink_release_client(struct device *dev, void *res)
+ spin_unlock_irqrestore(&pg->client_lock, flags);
+ }
+
+-struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
+- unsigned int id,
+- void (*cb)(const void *, size_t, void *),
+- void (*pdr)(void *, int),
+- void *priv)
++struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev,
++ unsigned int id,
++ void (*cb)(const void *, size_t, void *),
++ void (*pdr)(void *, int),
++ void *priv)
+ {
+ struct pmic_glink_client *client;
+ struct pmic_glink *pg = dev_get_drvdata(dev->parent);
+- unsigned long flags;
+
+ client = devres_alloc(_devm_pmic_glink_release_client, sizeof(*client), GFP_KERNEL);
+ if (!client)
+@@ -85,6 +84,18 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
+ client->cb = cb;
+ client->pdr_notify = pdr;
+ client->priv = priv;
++ INIT_LIST_HEAD(&client->node);
++
++ devres_add(dev, client);
++
++ return client;
++}
++EXPORT_SYMBOL_GPL(devm_pmic_glink_client_alloc);
++
++void pmic_glink_client_register(struct pmic_glink_client *client)
++{
++ struct pmic_glink *pg = client->pg;
++ unsigned long flags;
+
+ mutex_lock(&pg->state_lock);
+ spin_lock_irqsave(&pg->client_lock, flags);
+@@ -95,17 +106,22 @@ struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
+ spin_unlock_irqrestore(&pg->client_lock, flags);
+ mutex_unlock(&pg->state_lock);
+
+- devres_add(dev, client);
+-
+- return client;
+ }
+-EXPORT_SYMBOL_GPL(devm_pmic_glink_register_client);
++EXPORT_SYMBOL_GPL(pmic_glink_client_register);
+
+ int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len)
+ {
+ struct pmic_glink *pg = client->pg;
++ int ret;
+
+- return rpmsg_send(pg->ept, data, len);
++ mutex_lock(&pg->state_lock);
++ if (!pg->ept)
++ ret = -ECONNRESET;
++ else
++ ret = rpmsg_send(pg->ept, data, len);
++ mutex_unlock(&pg->state_lock);
++
++ return ret;
+ }
+ EXPORT_SYMBOL_GPL(pmic_glink_send);
+
+@@ -175,7 +191,7 @@ static void pmic_glink_state_notify_clients(struct pmic_glink *pg)
+ if (pg->pdr_state == SERVREG_SERVICE_STATE_UP && pg->ept)
+ new_state = SERVREG_SERVICE_STATE_UP;
+ } else {
+- if (pg->pdr_state == SERVREG_SERVICE_STATE_UP && pg->ept)
++ if (pg->pdr_state == SERVREG_SERVICE_STATE_DOWN || !pg->ept)
+ new_state = SERVREG_SERVICE_STATE_DOWN;
+ }
+
+diff --git a/drivers/soc/qcom/pmic_glink_altmode.c b/drivers/soc/qcom/pmic_glink_altmode.c
+index b3808fc24c695..d9c299330894a 100644
+--- a/drivers/soc/qcom/pmic_glink_altmode.c
++++ b/drivers/soc/qcom/pmic_glink_altmode.c
+@@ -520,12 +520,17 @@ static int pmic_glink_altmode_probe(struct auxiliary_device *adev,
+ return ret;
+ }
+
+- altmode->client = devm_pmic_glink_register_client(dev,
+- altmode->owner_id,
+- pmic_glink_altmode_callback,
+- pmic_glink_altmode_pdr_notify,
+- altmode);
+- return PTR_ERR_OR_ZERO(altmode->client);
++ altmode->client = devm_pmic_glink_client_alloc(dev,
++ altmode->owner_id,
++ pmic_glink_altmode_callback,
++ pmic_glink_altmode_pdr_notify,
++ altmode);
++ if (IS_ERR(altmode->client))
++ return PTR_ERR(altmode->client);
++
++ pmic_glink_client_register(altmode->client);
++
++ return 0;
+ }
+
+ static const struct auxiliary_device_id pmic_glink_altmode_id_table[] = {
+diff --git a/drivers/soundwire/stream.c b/drivers/soundwire/stream.c
+index 4e9e7d2a942d8..00191b1d22601 100644
+--- a/drivers/soundwire/stream.c
++++ b/drivers/soundwire/stream.c
+@@ -1286,18 +1286,18 @@ struct sdw_dpn_prop *sdw_get_slave_dpn_prop(struct sdw_slave *slave,
+ unsigned int port_num)
+ {
+ struct sdw_dpn_prop *dpn_prop;
+- u8 num_ports;
++ unsigned long mask;
+ int i;
+
+ if (direction == SDW_DATA_DIR_TX) {
+- num_ports = hweight32(slave->prop.source_ports);
++ mask = slave->prop.source_ports;
+ dpn_prop = slave->prop.src_dpn_prop;
+ } else {
+- num_ports = hweight32(slave->prop.sink_ports);
++ mask = slave->prop.sink_ports;
+ dpn_prop = slave->prop.sink_dpn_prop;
+ }
+
+- for (i = 0; i < num_ports; i++) {
++ for_each_set_bit(i, &mask, 32) {
+ if (dpn_prop[i].num == port_num)
+ return &dpn_prop[i];
+ }
+diff --git a/drivers/usb/cdns3/cdnsp-gadget.h b/drivers/usb/cdns3/cdnsp-gadget.h
+index dbee6f0852777..84887dfea7635 100644
+--- a/drivers/usb/cdns3/cdnsp-gadget.h
++++ b/drivers/usb/cdns3/cdnsp-gadget.h
+@@ -811,6 +811,7 @@ struct cdnsp_stream_info {
+ * generate Missed Service Error Event.
+ * Set skip flag when receive a Missed Service Error Event and
+ * process the missed tds on the endpoint ring.
++ * @wa1_nop_trb: hold pointer to NOP trb.
+ */
+ struct cdnsp_ep {
+ struct usb_ep endpoint;
+@@ -838,6 +839,8 @@ struct cdnsp_ep {
+ #define EP_UNCONFIGURED BIT(7)
+
+ bool skip;
++ union cdnsp_trb *wa1_nop_trb;
++
+ };
+
+ /**
+diff --git a/drivers/usb/cdns3/cdnsp-ring.c b/drivers/usb/cdns3/cdnsp-ring.c
+index 02f297f5637d7..dbd83d321bca0 100644
+--- a/drivers/usb/cdns3/cdnsp-ring.c
++++ b/drivers/usb/cdns3/cdnsp-ring.c
+@@ -402,7 +402,7 @@ static u64 cdnsp_get_hw_deq(struct cdnsp_device *pdev,
+ struct cdnsp_stream_ctx *st_ctx;
+ struct cdnsp_ep *pep;
+
+- pep = &pdev->eps[stream_id];
++ pep = &pdev->eps[ep_index];
+
+ if (pep->ep_state & EP_HAS_STREAMS) {
+ st_ctx = &pep->stream_info.stream_ctx_array[stream_id];
+@@ -1904,6 +1904,23 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq)
+ if (ret)
+ return ret;
+
++ /*
++ * workaround 1: STOP EP command on LINK TRB with TC bit set to 1
++ * causes that internal cycle bit can have incorrect state after
++ * command complete. In consequence empty transfer ring can be
++ * incorrectly detected when EP is resumed.
++ * NOP TRB before LINK TRB avoid such scenario. STOP EP command is
++ * then on NOP TRB and internal cycle bit is not changed and have
++ * correct value.
++ */
++ if (pep->wa1_nop_trb) {
++ field = le32_to_cpu(pep->wa1_nop_trb->trans_event.flags);
++ field ^= TRB_CYCLE;
++
++ pep->wa1_nop_trb->trans_event.flags = cpu_to_le32(field);
++ pep->wa1_nop_trb = NULL;
++ }
++
+ /*
+ * Don't give the first TRB to the hardware (by toggling the cycle bit)
+ * until we've finished creating all the other TRBs. The ring's cycle
+@@ -1999,6 +2016,17 @@ int cdnsp_queue_bulk_tx(struct cdnsp_device *pdev, struct cdnsp_request *preq)
+ send_addr = addr;
+ }
+
++ if (cdnsp_trb_is_link(ring->enqueue + 1)) {
++ field = TRB_TYPE(TRB_TR_NOOP) | TRB_IOC;
++ if (!ring->cycle_state)
++ field |= TRB_CYCLE;
++
++ pep->wa1_nop_trb = ring->enqueue;
++
++ cdnsp_queue_trb(pdev, ring, 0, 0x0, 0x0,
++ TRB_INTR_TARGET(0), field);
++ }
++
+ cdnsp_check_trb_math(preq, enqd_len);
+ ret = cdnsp_giveback_first_trb(pdev, pep, preq->request.stream_id,
+ start_cycle, start_trb);
+diff --git a/drivers/usb/class/cdc-acm.c b/drivers/usb/class/cdc-acm.c
+index 0e7439dba8fe8..0c1b69d944ca4 100644
+--- a/drivers/usb/class/cdc-acm.c
++++ b/drivers/usb/class/cdc-acm.c
+@@ -1761,6 +1761,9 @@ static const struct usb_device_id acm_ids[] = {
+ { USB_DEVICE(0x11ca, 0x0201), /* VeriFone Mx870 Gadget Serial */
+ .driver_info = SINGLE_RX_URB,
+ },
++ { USB_DEVICE(0x1901, 0x0006), /* GE Healthcare Patient Monitor UI Controller */
++ .driver_info = DISABLE_ECHO, /* DISABLE ECHO in termios flag */
++ },
+ { USB_DEVICE(0x1965, 0x0018), /* Uniden UBC125XLT */
+ .driver_info = NO_UNION_NORMAL, /* has no union descriptor */
+ },
+diff --git a/drivers/usb/core/sysfs.c b/drivers/usb/core/sysfs.c
+index d83231d6736ac..61b6d978892c7 100644
+--- a/drivers/usb/core/sysfs.c
++++ b/drivers/usb/core/sysfs.c
+@@ -670,6 +670,7 @@ static int add_power_attributes(struct device *dev)
+
+ static void remove_power_attributes(struct device *dev)
+ {
++ sysfs_unmerge_group(&dev->kobj, &usb3_hardware_lpm_attr_group);
+ sysfs_unmerge_group(&dev->kobj, &usb2_hardware_lpm_attr_group);
+ sysfs_unmerge_group(&dev->kobj, &power_attr_group);
+ }
+diff --git a/drivers/usb/dwc3/core.c b/drivers/usb/dwc3/core.c
+index cb82557678ddd..31df6fdc233ef 100644
+--- a/drivers/usb/dwc3/core.c
++++ b/drivers/usb/dwc3/core.c
+@@ -559,9 +559,17 @@ int dwc3_event_buffers_setup(struct dwc3 *dwc)
+ void dwc3_event_buffers_cleanup(struct dwc3 *dwc)
+ {
+ struct dwc3_event_buffer *evt;
++ u32 reg;
+
+ if (!dwc->ev_buf)
+ return;
++ /*
++ * Exynos platforms may not be able to access event buffer if the
++ * controller failed to halt on dwc3_core_exit().
++ */
++ reg = dwc3_readl(dwc->regs, DWC3_DSTS);
++ if (!(reg & DWC3_DSTS_DEVCTRLHLT))
++ return;
+
+ evt = dwc->ev_buf;
+
+diff --git a/drivers/usb/dwc3/dwc3-omap.c b/drivers/usb/dwc3/dwc3-omap.c
+index d5c77db4daa92..2a11fc0ee84f1 100644
+--- a/drivers/usb/dwc3/dwc3-omap.c
++++ b/drivers/usb/dwc3/dwc3-omap.c
+@@ -522,11 +522,13 @@ static int dwc3_omap_probe(struct platform_device *pdev)
+ if (ret) {
+ dev_err(dev, "failed to request IRQ #%d --> %d\n",
+ omap->irq, ret);
+- goto err1;
++ goto err2;
+ }
+ dwc3_omap_enable_irqs(omap);
+ return 0;
+
++err2:
++ of_platform_depopulate(dev);
+ err1:
+ pm_runtime_put_sync(dev);
+ pm_runtime_disable(dev);
+diff --git a/drivers/usb/dwc3/dwc3-st.c b/drivers/usb/dwc3/dwc3-st.c
+index 211360eee95a0..c8c7cd0c17969 100644
+--- a/drivers/usb/dwc3/dwc3-st.c
++++ b/drivers/usb/dwc3/dwc3-st.c
+@@ -219,10 +219,8 @@ static int st_dwc3_probe(struct platform_device *pdev)
+ dwc3_data->regmap = regmap;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "syscfg-reg");
+- if (!res) {
+- ret = -ENXIO;
+- goto undo_platform_dev_alloc;
+- }
++ if (!res)
++ return -ENXIO;
+
+ dwc3_data->syscfg_reg_off = res->start;
+
+@@ -233,8 +231,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
+ devm_reset_control_get_exclusive(dev, "powerdown");
+ if (IS_ERR(dwc3_data->rstc_pwrdn)) {
+ dev_err(&pdev->dev, "could not get power controller\n");
+- ret = PTR_ERR(dwc3_data->rstc_pwrdn);
+- goto undo_platform_dev_alloc;
++ return PTR_ERR(dwc3_data->rstc_pwrdn);
+ }
+
+ /* Manage PowerDown */
+@@ -269,7 +266,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
+ if (!child_pdev) {
+ dev_err(dev, "failed to find dwc3 core device\n");
+ ret = -ENODEV;
+- goto err_node_put;
++ goto depopulate;
+ }
+
+ dwc3_data->dr_mode = usb_get_dr_mode(&child_pdev->dev);
+@@ -285,6 +282,7 @@ static int st_dwc3_probe(struct platform_device *pdev)
+ ret = st_dwc3_drd_init(dwc3_data);
+ if (ret) {
+ dev_err(dev, "drd initialisation failed\n");
++ of_platform_depopulate(dev);
+ goto undo_softreset;
+ }
+
+@@ -294,14 +292,14 @@ static int st_dwc3_probe(struct platform_device *pdev)
+ platform_set_drvdata(pdev, dwc3_data);
+ return 0;
+
++depopulate:
++ of_platform_depopulate(dev);
+ err_node_put:
+ of_node_put(child);
+ undo_softreset:
+ reset_control_assert(dwc3_data->rstc_rst);
+ undo_powerdown:
+ reset_control_assert(dwc3_data->rstc_pwrdn);
+-undo_platform_dev_alloc:
+- platform_device_put(pdev);
+ return ret;
+ }
+
+diff --git a/drivers/usb/dwc3/dwc3-xilinx.c b/drivers/usb/dwc3/dwc3-xilinx.c
+index 6095f4dee6ceb..c9eafb6f3bdc2 100644
+--- a/drivers/usb/dwc3/dwc3-xilinx.c
++++ b/drivers/usb/dwc3/dwc3-xilinx.c
+@@ -298,9 +298,14 @@ static int dwc3_xlnx_probe(struct platform_device *pdev)
+ goto err_pm_set_suspended;
+
+ pm_suspend_ignore_children(dev, false);
+- return pm_runtime_resume_and_get(dev);
++ ret = pm_runtime_resume_and_get(dev);
++ if (ret < 0)
++ goto err_pm_set_suspended;
++
++ return 0;
+
+ err_pm_set_suspended:
++ of_platform_depopulate(dev);
+ pm_runtime_set_suspended(dev);
+
+ err_clk_put:
+diff --git a/drivers/usb/dwc3/ep0.c b/drivers/usb/dwc3/ep0.c
+index d96ffbe520397..c9533a99e47c8 100644
+--- a/drivers/usb/dwc3/ep0.c
++++ b/drivers/usb/dwc3/ep0.c
+@@ -232,7 +232,8 @@ void dwc3_ep0_stall_and_restart(struct dwc3 *dwc)
+ /* stall is always issued on EP0 */
+ dep = dwc->eps[0];
+ __dwc3_gadget_ep_set_halt(dep, 1, false);
+- dep->flags = DWC3_EP_ENABLED;
++ dep->flags &= DWC3_EP_RESOURCE_ALLOCATED;
++ dep->flags |= DWC3_EP_ENABLED;
+ dwc->delayed_status = false;
+
+ if (!list_empty(&dep->pending_list)) {
+diff --git a/drivers/usb/gadget/function/uvc_video.c b/drivers/usb/gadget/function/uvc_video.c
+index d41f5f31dadd5..a9edd60fbbf77 100644
+--- a/drivers/usb/gadget/function/uvc_video.c
++++ b/drivers/usb/gadget/function/uvc_video.c
+@@ -753,6 +753,7 @@ int uvcg_video_enable(struct uvc_video *video)
+ video->req_int_count = 0;
+
+ uvc_video_ep_queue_initial_requests(video);
++ queue_work(video->async_wq, &video->pump);
+
+ return ret;
+ }
+diff --git a/drivers/usb/serial/option.c b/drivers/usb/serial/option.c
+index 311040f9b9352..176f38750ad58 100644
+--- a/drivers/usb/serial/option.c
++++ b/drivers/usb/serial/option.c
+@@ -619,6 +619,8 @@ static void option_instat_callback(struct urb *urb);
+
+ /* MeiG Smart Technology products */
+ #define MEIGSMART_VENDOR_ID 0x2dee
++/* MeiG Smart SRM825L based on Qualcomm 315 */
++#define MEIGSMART_PRODUCT_SRM825L 0x4d22
+ /* MeiG Smart SLM320 based on UNISOC UIS8910 */
+ #define MEIGSMART_PRODUCT_SLM320 0x4d41
+
+@@ -2366,6 +2368,9 @@ static const struct usb_device_id option_ids[] = {
+ { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, TOZED_PRODUCT_LT70C, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(UNISOC_VENDOR_ID, LUAT_PRODUCT_AIR720U, 0xff, 0, 0) },
+ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SLM320, 0xff, 0, 0) },
++ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x30) },
++ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x40) },
++ { USB_DEVICE_AND_INTERFACE_INFO(MEIGSMART_VENDOR_ID, MEIGSMART_PRODUCT_SRM825L, 0xff, 0xff, 0x60) },
+ { } /* Terminating entry */
+ };
+ MODULE_DEVICE_TABLE(usb, option_ids);
+diff --git a/drivers/usb/typec/mux/fsa4480.c b/drivers/usb/typec/mux/fsa4480.c
+index cd235339834b0..f71dba8bf07c9 100644
+--- a/drivers/usb/typec/mux/fsa4480.c
++++ b/drivers/usb/typec/mux/fsa4480.c
+@@ -274,7 +274,7 @@ static int fsa4480_probe(struct i2c_client *client)
+ return dev_err_probe(dev, PTR_ERR(fsa->regmap), "failed to initialize regmap\n");
+
+ ret = regmap_read(fsa->regmap, FSA4480_DEVICE_ID, &val);
+- if (ret || !val)
++ if (ret)
+ return dev_err_probe(dev, -ENODEV, "FSA4480 not found\n");
+
+ dev_dbg(dev, "Found FSA4480 v%lu.%lu (Vendor ID = %lu)\n",
+diff --git a/drivers/usb/typec/ucsi/ucsi_glink.c b/drivers/usb/typec/ucsi/ucsi_glink.c
+index 2fa973afe4e68..2fc4e06937d87 100644
+--- a/drivers/usb/typec/ucsi/ucsi_glink.c
++++ b/drivers/usb/typec/ucsi/ucsi_glink.c
+@@ -72,6 +72,9 @@ struct pmic_glink_ucsi {
+
+ struct work_struct notify_work;
+ struct work_struct register_work;
++ spinlock_t state_lock;
++ bool ucsi_registered;
++ bool pd_running;
+
+ u8 read_buf[UCSI_BUF_SIZE];
+ };
+@@ -271,8 +274,20 @@ static void pmic_glink_ucsi_notify(struct work_struct *work)
+ static void pmic_glink_ucsi_register(struct work_struct *work)
+ {
+ struct pmic_glink_ucsi *ucsi = container_of(work, struct pmic_glink_ucsi, register_work);
++ unsigned long flags;
++ bool pd_running;
+
+- ucsi_register(ucsi->ucsi);
++ spin_lock_irqsave(&ucsi->state_lock, flags);
++ pd_running = ucsi->pd_running;
++ spin_unlock_irqrestore(&ucsi->state_lock, flags);
++
++ if (!ucsi->ucsi_registered && pd_running) {
++ ucsi_register(ucsi->ucsi);
++ ucsi->ucsi_registered = true;
++ } else if (ucsi->ucsi_registered && !pd_running) {
++ ucsi_unregister(ucsi->ucsi);
++ ucsi->ucsi_registered = false;
++ }
+ }
+
+ static void pmic_glink_ucsi_callback(const void *data, size_t len, void *priv)
+@@ -296,11 +311,12 @@ static void pmic_glink_ucsi_callback(const void *data, size_t len, void *priv)
+ static void pmic_glink_ucsi_pdr_notify(void *priv, int state)
+ {
+ struct pmic_glink_ucsi *ucsi = priv;
++ unsigned long flags;
+
+- if (state == SERVREG_SERVICE_STATE_UP)
+- schedule_work(&ucsi->register_work);
+- else if (state == SERVREG_SERVICE_STATE_DOWN)
+- ucsi_unregister(ucsi->ucsi);
++ spin_lock_irqsave(&ucsi->state_lock, flags);
++ ucsi->pd_running = (state == SERVREG_SERVICE_STATE_UP);
++ spin_unlock_irqrestore(&ucsi->state_lock, flags);
++ schedule_work(&ucsi->register_work);
+ }
+
+ static void pmic_glink_ucsi_destroy(void *data)
+@@ -348,6 +364,7 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev,
+ init_completion(&ucsi->read_ack);
+ init_completion(&ucsi->write_ack);
+ init_completion(&ucsi->sync_ack);
++ spin_lock_init(&ucsi->state_lock);
+ mutex_init(&ucsi->lock);
+
+ ucsi->ucsi = ucsi_create(dev, &pmic_glink_ucsi_ops);
+@@ -395,12 +412,16 @@ static int pmic_glink_ucsi_probe(struct auxiliary_device *adev,
+ ucsi->port_orientation[port] = desc;
+ }
+
+- ucsi->client = devm_pmic_glink_register_client(dev,
+- PMIC_GLINK_OWNER_USBC,
+- pmic_glink_ucsi_callback,
+- pmic_glink_ucsi_pdr_notify,
+- ucsi);
+- return PTR_ERR_OR_ZERO(ucsi->client);
++ ucsi->client = devm_pmic_glink_client_alloc(dev, PMIC_GLINK_OWNER_USBC,
++ pmic_glink_ucsi_callback,
++ pmic_glink_ucsi_pdr_notify,
++ ucsi);
++ if (IS_ERR(ucsi->client))
++ return PTR_ERR(ucsi->client);
++
++ pmic_glink_client_register(ucsi->client);
++
++ return 0;
+ }
+
+ static void pmic_glink_ucsi_remove(struct auxiliary_device *adev)
+diff --git a/drivers/video/aperture.c b/drivers/video/aperture.c
+index 561be8feca96c..2b5a1e666e9b2 100644
+--- a/drivers/video/aperture.c
++++ b/drivers/video/aperture.c
+@@ -293,7 +293,7 @@ int aperture_remove_conflicting_devices(resource_size_t base, resource_size_t si
+ * ask for this, so let's assume that a real driver for the display
+ * was already probed and prevent sysfb to register devices later.
+ */
+- sysfb_disable();
++ sysfb_disable(NULL);
+
+ aperture_detach_devices(base, size);
+
+@@ -346,15 +346,10 @@ EXPORT_SYMBOL(__aperture_remove_legacy_vga_devices);
+ */
+ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *name)
+ {
+- bool primary = false;
+ resource_size_t base, size;
+ int bar, ret = 0;
+
+- if (pdev == vga_default_device())
+- primary = true;
+-
+- if (primary)
+- sysfb_disable();
++ sysfb_disable(&pdev->dev);
+
+ for (bar = 0; bar < PCI_STD_NUM_BARS; ++bar) {
+ if (!(pci_resource_flags(pdev, bar) & IORESOURCE_MEM))
+@@ -370,7 +365,7 @@ int aperture_remove_conflicting_pci_devices(struct pci_dev *pdev, const char *na
+ * that consumes the VGA framebuffer I/O range. Remove this
+ * device as well.
+ */
+- if (primary)
++ if (pdev == vga_default_device())
+ ret = __aperture_remove_legacy_vga_devices(pdev);
+
+ return ret;
+diff --git a/fs/afs/inode.c b/fs/afs/inode.c
+index 3acf5e0500728..a95e77670b494 100644
+--- a/fs/afs/inode.c
++++ b/fs/afs/inode.c
+@@ -695,13 +695,18 @@ static void afs_setattr_edit_file(struct afs_operation *op)
+ {
+ struct afs_vnode_param *vp = &op->file[0];
+ struct afs_vnode *vnode = vp->vnode;
++ struct inode *inode = &vnode->netfs.inode;
+
+ if (op->setattr.attr->ia_valid & ATTR_SIZE) {
+ loff_t size = op->setattr.attr->ia_size;
+- loff_t i_size = op->setattr.old_i_size;
++ loff_t old = op->setattr.old_i_size;
++
++ /* Note: inode->i_size was updated by afs_apply_status() inside
++ * the I/O and callback locks.
++ */
+
+- if (size != i_size) {
+- truncate_setsize(&vnode->netfs.inode, size);
++ if (size != old) {
++ truncate_pagecache(inode, size);
+ netfs_resize_file(&vnode->netfs, size, true);
+ fscache_resize_cookie(afs_vnode_cache(vnode), size);
+ }
+diff --git a/fs/attr.c b/fs/attr.c
+index 960a310581ebb..0dbf43b6555c8 100644
+--- a/fs/attr.c
++++ b/fs/attr.c
+@@ -489,9 +489,17 @@ int notify_change(struct mnt_idmap *idmap, struct dentry *dentry,
+ error = security_inode_setattr(idmap, dentry, attr);
+ if (error)
+ return error;
+- error = try_break_deleg(inode, delegated_inode);
+- if (error)
+- return error;
++
++ /*
++ * If ATTR_DELEG is set, then these attributes are being set on
++ * behalf of the holder of a write delegation. We want to avoid
++ * breaking the delegation in this case.
++ */
++ if (!(ia_valid & ATTR_DELEG)) {
++ error = try_break_deleg(inode, delegated_inode);
++ if (error)
++ return error;
++ }
+
+ if (inode->i_op->setattr)
+ error = inode->i_op->setattr(idmap, dentry, attr);
+diff --git a/fs/backing-file.c b/fs/backing-file.c
+index afb557446c27c..8860dac58c37e 100644
+--- a/fs/backing-file.c
++++ b/fs/backing-file.c
+@@ -303,13 +303,16 @@ ssize_t backing_file_splice_write(struct pipe_inode_info *pipe,
+ if (WARN_ON_ONCE(!(out->f_mode & FMODE_BACKING)))
+ return -EIO;
+
++ if (!out->f_op->splice_write)
++ return -EINVAL;
++
+ ret = file_remove_privs(ctx->user_file);
+ if (ret)
+ return ret;
+
+ old_cred = override_creds(ctx->cred);
+ file_start_write(out);
+- ret = iter_file_splice_write(pipe, out, ppos, len, flags);
++ ret = out->f_op->splice_write(pipe, out, ppos, len, flags);
+ file_end_write(out);
+ revert_creds(old_cred);
+
+diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
+index b799701454a96..7d35f0e1bc764 100644
+--- a/fs/binfmt_elf_fdpic.c
++++ b/fs/binfmt_elf_fdpic.c
+@@ -592,6 +592,9 @@ static int create_elf_fdpic_tables(struct linux_binprm *bprm,
+
+ if (bprm->have_execfd)
+ nitems++;
++#ifdef ELF_HWCAP2
++ nitems++;
++#endif
+
+ csp = sp;
+ sp -= nitems * 2 * sizeof(unsigned long);
+diff --git a/fs/btrfs/bio.c b/fs/btrfs/bio.c
+index e3a57196b0ee0..bb4ae84fa64c6 100644
+--- a/fs/btrfs/bio.c
++++ b/fs/btrfs/bio.c
+@@ -668,7 +668,6 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
+ {
+ struct btrfs_inode *inode = bbio->inode;
+ struct btrfs_fs_info *fs_info = bbio->fs_info;
+- struct btrfs_bio *orig_bbio = bbio;
+ struct bio *bio = &bbio->bio;
+ u64 logical = bio->bi_iter.bi_sector << SECTOR_SHIFT;
+ u64 length = bio->bi_iter.bi_size;
+@@ -706,7 +705,7 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
+ bbio->saved_iter = bio->bi_iter;
+ ret = btrfs_lookup_bio_sums(bbio);
+ if (ret)
+- goto fail_put_bio;
++ goto fail;
+ }
+
+ if (btrfs_op(bio) == BTRFS_MAP_WRITE) {
+@@ -740,13 +739,13 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
+
+ ret = btrfs_bio_csum(bbio);
+ if (ret)
+- goto fail_put_bio;
++ goto fail;
+ } else if (use_append ||
+ (btrfs_is_zoned(fs_info) && inode &&
+ inode->flags & BTRFS_INODE_NODATASUM)) {
+ ret = btrfs_alloc_dummy_sum(bbio);
+ if (ret)
+- goto fail_put_bio;
++ goto fail;
+ }
+ }
+
+@@ -754,12 +753,23 @@ static bool btrfs_submit_chunk(struct btrfs_bio *bbio, int mirror_num)
+ done:
+ return map_length == length;
+
+-fail_put_bio:
+- if (map_length < length)
+- btrfs_cleanup_bio(bbio);
+ fail:
+ btrfs_bio_counter_dec(fs_info);
+- btrfs_bio_end_io(orig_bbio, ret);
++ /*
++ * We have split the original bbio, now we have to end both the current
++ * @bbio and remaining one, as the remaining one will never be submitted.
++ */
++ if (map_length < length) {
++ struct btrfs_bio *remaining = bbio->private;
++
++ ASSERT(bbio->bio.bi_pool == &btrfs_clone_bioset);
++ ASSERT(remaining);
++
++ remaining->bio.bi_status = ret;
++ btrfs_orig_bbio_end_io(remaining);
++ }
++ bbio->bio.bi_status = ret;
++ btrfs_orig_bbio_end_io(bbio);
+ /* Do not submit another chunk */
+ return true;
+ }
+diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
+index 29d6ca3b874ec..3faf2181d1ee8 100644
+--- a/fs/btrfs/qgroup.c
++++ b/fs/btrfs/qgroup.c
+@@ -4100,6 +4100,8 @@ static int try_flush_qgroup(struct btrfs_root *root)
+ return 0;
+ }
+
++ btrfs_run_delayed_iputs(root->fs_info);
++ btrfs_wait_on_delayed_iputs(root->fs_info);
+ ret = btrfs_start_delalloc_snapshot(root, true);
+ if (ret < 0)
+ goto out;
+diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
+index 249ddfbb1b03e..6b64cf6065598 100644
+--- a/fs/ceph/inode.c
++++ b/fs/ceph/inode.c
+@@ -697,6 +697,7 @@ void ceph_evict_inode(struct inode *inode)
+
+ percpu_counter_dec(&mdsc->metric.total_inodes);
+
++ netfs_wait_for_outstanding_io(inode);
+ truncate_inode_pages_final(&inode->i_data);
+ if (inode->i_state & I_PINNING_NETFS_WB)
+ ceph_fscache_unuse_cookie(inode, true);
+diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c
+index 9b53883e5caf8..37afe20248409 100644
+--- a/fs/erofs/zutil.c
++++ b/fs/erofs/zutil.c
+@@ -111,7 +111,8 @@ int z_erofs_gbuf_growsize(unsigned int nrpages)
+ out:
+ if (i < z_erofs_gbuf_count && tmp_pages) {
+ for (j = 0; j < nrpages; ++j)
+- if (tmp_pages[j] && tmp_pages[j] != gbuf->pages[j])
++ if (tmp_pages[j] && (j >= gbuf->nrpages ||
++ tmp_pages[j] != gbuf->pages[j]))
+ __free_page(tmp_pages[j]);
+ kfree(tmp_pages);
+ }
+diff --git a/fs/netfs/io.c b/fs/netfs/io.c
+index f3abc5dfdbc0c..c96431d3da6d8 100644
+--- a/fs/netfs/io.c
++++ b/fs/netfs/io.c
+@@ -313,6 +313,7 @@ static bool netfs_rreq_perform_resubmissions(struct netfs_io_request *rreq)
+ netfs_reset_subreq_iter(rreq, subreq);
+ netfs_read_from_server(rreq, subreq);
+ } else if (test_bit(NETFS_SREQ_SHORT_IO, &subreq->flags)) {
++ netfs_reset_subreq_iter(rreq, subreq);
+ netfs_rreq_short_read(rreq, subreq);
+ }
+ }
+diff --git a/fs/netfs/misc.c b/fs/netfs/misc.c
+index 172808e83ca81..a46bf569303fc 100644
+--- a/fs/netfs/misc.c
++++ b/fs/netfs/misc.c
+@@ -97,10 +97,22 @@ EXPORT_SYMBOL(netfs_clear_inode_writeback);
+ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
+ {
+ struct netfs_folio *finfo;
++ struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+ size_t flen = folio_size(folio);
+
+ kenter("{%lx},%zx,%zx", folio->index, offset, length);
+
++ if (offset == 0 && length == flen) {
++ unsigned long long i_size = i_size_read(&ctx->inode);
++ unsigned long long fpos = folio_pos(folio), end;
++
++ end = umin(fpos + flen, i_size);
++ if (fpos < i_size && end > ctx->zero_point)
++ ctx->zero_point = end;
++ }
++
++ folio_wait_private_2(folio); /* [DEPRECATED] */
++
+ if (!folio_test_private(folio))
+ return;
+
+@@ -113,18 +125,34 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
+ /* We have a partially uptodate page from a streaming write. */
+ unsigned int fstart = finfo->dirty_offset;
+ unsigned int fend = fstart + finfo->dirty_len;
+- unsigned int end = offset + length;
++ unsigned int iend = offset + length;
+
+ if (offset >= fend)
+ return;
+- if (end <= fstart)
++ if (iend <= fstart)
++ return;
++
++ /* The invalidation region overlaps the data. If the region
++ * covers the start of the data, we either move along the start
++ * or just erase the data entirely.
++ */
++ if (offset <= fstart) {
++ if (iend >= fend)
++ goto erase_completely;
++ /* Move the start of the data. */
++ finfo->dirty_len = fend - iend;
++ finfo->dirty_offset = offset;
++ return;
++ }
++
++ /* Reduce the length of the data if the invalidation region
++ * covers the tail part.
++ */
++ if (iend >= fend) {
++ finfo->dirty_len = offset - fstart;
+ return;
+- if (offset <= fstart && end >= fend)
+- goto erase_completely;
+- if (offset <= fstart && end > fstart)
+- goto reduce_len;
+- if (offset > fstart && end >= fend)
+- goto move_start;
++ }
++
+ /* A partial write was split. The caller has already zeroed
+ * it, so just absorb the hole.
+ */
+@@ -137,12 +165,6 @@ void netfs_invalidate_folio(struct folio *folio, size_t offset, size_t length)
+ folio_clear_uptodate(folio);
+ kfree(finfo);
+ return;
+-reduce_len:
+- finfo->dirty_len = offset + length - finfo->dirty_offset;
+- return;
+-move_start:
+- finfo->dirty_len -= offset - finfo->dirty_offset;
+- finfo->dirty_offset = offset;
+ }
+ EXPORT_SYMBOL(netfs_invalidate_folio);
+
+@@ -159,12 +181,20 @@ bool netfs_release_folio(struct folio *folio, gfp_t gfp)
+ struct netfs_inode *ctx = netfs_inode(folio_inode(folio));
+ unsigned long long end;
+
+- end = folio_pos(folio) + folio_size(folio);
++ if (folio_test_dirty(folio))
++ return false;
++
++ end = umin(folio_pos(folio) + folio_size(folio), i_size_read(&ctx->inode));
+ if (end > ctx->zero_point)
+ ctx->zero_point = end;
+
+ if (folio_test_private(folio))
+ return false;
++ if (unlikely(folio_test_private_2(folio))) { /* [DEPRECATED] */
++ if (current_is_kswapd() || !(gfp & __GFP_FS))
++ return false;
++ folio_wait_private_2(folio);
++ }
+ fscache_note_page_release(netfs_i_cookie(ctx));
+ return true;
+ }
+diff --git a/fs/netfs/write_collect.c b/fs/netfs/write_collect.c
+index 488147439fe0f..a2b697b4aa401 100644
+--- a/fs/netfs/write_collect.c
++++ b/fs/netfs/write_collect.c
+@@ -33,6 +33,7 @@
+ int netfs_folio_written_back(struct folio *folio)
+ {
+ enum netfs_folio_trace why = netfs_folio_trace_clear;
++ struct netfs_inode *ictx = netfs_inode(folio->mapping->host);
+ struct netfs_folio *finfo;
+ struct netfs_group *group = NULL;
+ int gcount = 0;
+@@ -41,6 +42,12 @@ int netfs_folio_written_back(struct folio *folio)
+ /* Streaming writes cannot be redirtied whilst under writeback,
+ * so discard the streaming record.
+ */
++ unsigned long long fend;
++
++ fend = folio_pos(folio) + finfo->dirty_offset + finfo->dirty_len;
++ if (fend > ictx->zero_point)
++ ictx->zero_point = fend;
++
+ folio_detach_private(folio);
+ group = finfo->netfs_group;
+ gcount++;
+diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
+index a20c2c9d7d457..a366fb1c1b9b4 100644
+--- a/fs/nfsd/nfs4state.c
++++ b/fs/nfsd/nfs4state.c
+@@ -2789,15 +2789,18 @@ static int nfs4_show_open(struct seq_file *s, struct nfs4_stid *st)
+ deny & NFS4_SHARE_ACCESS_READ ? "r" : "-",
+ deny & NFS4_SHARE_ACCESS_WRITE ? "w" : "-");
+
+- spin_lock(&nf->fi_lock);
+- file = find_any_file_locked(nf);
+- if (file) {
+- nfs4_show_superblock(s, file);
+- seq_puts(s, ", ");
+- nfs4_show_fname(s, file);
+- seq_puts(s, ", ");
+- }
+- spin_unlock(&nf->fi_lock);
++ if (nf) {
++ spin_lock(&nf->fi_lock);
++ file = find_any_file_locked(nf);
++ if (file) {
++ nfs4_show_superblock(s, file);
++ seq_puts(s, ", ");
++ nfs4_show_fname(s, file);
++ seq_puts(s, ", ");
++ }
++ spin_unlock(&nf->fi_lock);
++ } else
++ seq_puts(s, "closed, ");
+ nfs4_show_owner(s, oo);
+ if (st->sc_status & SC_STATUS_ADMIN_REVOKED)
+ seq_puts(s, ", admin-revoked");
+@@ -3075,9 +3078,9 @@ nfsd4_cb_getattr_release(struct nfsd4_callback *cb)
+ struct nfs4_delegation *dp =
+ container_of(ncf, struct nfs4_delegation, dl_cb_fattr);
+
+- nfs4_put_stid(&dp->dl_stid);
+ clear_bit(CB_GETATTR_BUSY, &ncf->ncf_cb_flags);
+ wake_up_bit(&ncf->ncf_cb_flags, CB_GETATTR_BUSY);
++ nfs4_put_stid(&dp->dl_stid);
+ }
+
+ static const struct nfsd4_callback_ops nfsd4_cb_recall_any_ops = {
+@@ -8812,7 +8815,7 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
+ /**
+ * nfsd4_deleg_getattr_conflict - Recall if GETATTR causes conflict
+ * @rqstp: RPC transaction context
+- * @inode: file to be checked for a conflict
++ * @dentry: dentry of inode to be checked for a conflict
+ * @modified: return true if file was modified
+ * @size: new size of file if modified is true
+ *
+@@ -8827,16 +8830,16 @@ nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
+ * code is returned.
+ */
+ __be32
+-nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
++nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct dentry *dentry,
+ bool *modified, u64 *size)
+ {
+ __be32 status;
+ struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
+ struct file_lock_context *ctx;
+ struct file_lease *fl;
+- struct nfs4_delegation *dp;
+ struct iattr attrs;
+ struct nfs4_cb_fattr *ncf;
++ struct inode *inode = d_inode(dentry);
+
+ *modified = false;
+ ctx = locks_inode_context(inode);
+@@ -8856,17 +8859,26 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
+ */
+ if (type == F_RDLCK)
+ break;
+- goto break_lease;
++
++ nfsd_stats_wdeleg_getattr_inc(nn);
++ spin_unlock(&ctx->flc_lock);
++
++ status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
++ if (status != nfserr_jukebox ||
++ !nfsd_wait_for_delegreturn(rqstp, inode))
++ return status;
++ return 0;
+ }
+ if (type == F_WRLCK) {
+- dp = fl->c.flc_owner;
++ struct nfs4_delegation *dp = fl->c.flc_owner;
++
+ if (dp->dl_recall.cb_clp == *(rqstp->rq_lease_breaker)) {
+ spin_unlock(&ctx->flc_lock);
+ return 0;
+ }
+-break_lease:
+ nfsd_stats_wdeleg_getattr_inc(nn);
+ dp = fl->c.flc_owner;
++ refcount_inc(&dp->dl_stid.sc_count);
+ ncf = &dp->dl_cb_fattr;
+ nfs4_cb_getattr(&dp->dl_cb_fattr);
+ spin_unlock(&ctx->flc_lock);
+@@ -8876,27 +8888,37 @@ nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp, struct inode *inode,
+ /* Recall delegation only if client didn't respond */
+ status = nfserrno(nfsd_open_break_lease(inode, NFSD_MAY_READ));
+ if (status != nfserr_jukebox ||
+- !nfsd_wait_for_delegreturn(rqstp, inode))
++ !nfsd_wait_for_delegreturn(rqstp, inode)) {
++ nfs4_put_stid(&dp->dl_stid);
+ return status;
++ }
+ }
+ if (!ncf->ncf_file_modified &&
+ (ncf->ncf_initial_cinfo != ncf->ncf_cb_change ||
+ ncf->ncf_cur_fsize != ncf->ncf_cb_fsize))
+ ncf->ncf_file_modified = true;
+ if (ncf->ncf_file_modified) {
++ int err;
++
+ /*
+ * Per section 10.4.3 of RFC 8881, the server would
+ * not update the file's metadata with the client's
+ * modified size
+ */
+ attrs.ia_mtime = attrs.ia_ctime = current_time(inode);
+- attrs.ia_valid = ATTR_MTIME | ATTR_CTIME;
+- setattr_copy(&nop_mnt_idmap, inode, &attrs);
+- mark_inode_dirty(inode);
++ attrs.ia_valid = ATTR_MTIME | ATTR_CTIME | ATTR_DELEG;
++ inode_lock(inode);
++ err = notify_change(&nop_mnt_idmap, dentry, &attrs, NULL);
++ inode_unlock(inode);
++ if (err) {
++ nfs4_put_stid(&dp->dl_stid);
++ return nfserrno(err);
++ }
+ ncf->ncf_cur_fsize = ncf->ncf_cb_fsize;
+ *size = ncf->ncf_cur_fsize;
+ *modified = true;
+ }
++ nfs4_put_stid(&dp->dl_stid);
+ return 0;
+ }
+ break;
+diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
+index c7bfd2180e3f2..0869062280ccc 100644
+--- a/fs/nfsd/nfs4xdr.c
++++ b/fs/nfsd/nfs4xdr.c
+@@ -3545,6 +3545,9 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ args.dentry = dentry;
+ args.ignore_crossmnt = (ignore_crossmnt != 0);
+ args.acl = NULL;
++#ifdef CONFIG_NFSD_V4_SECURITY_LABEL
++ args.context = NULL;
++#endif
+
+ /*
+ * Make a local copy of the attribute bitmap that can be modified.
+@@ -3562,7 +3565,7 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ }
+ args.size = 0;
+ if (attrmask[0] & (FATTR4_WORD0_CHANGE | FATTR4_WORD0_SIZE)) {
+- status = nfsd4_deleg_getattr_conflict(rqstp, d_inode(dentry),
++ status = nfsd4_deleg_getattr_conflict(rqstp, dentry,
+ &file_modified, &size);
+ if (status)
+ goto out;
+@@ -3617,7 +3620,6 @@ nfsd4_encode_fattr4(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+ args.contextsupport = false;
+
+ #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
+- args.context = NULL;
+ if ((attrmask[2] & FATTR4_WORD2_SECURITY_LABEL) ||
+ attrmask[0] & FATTR4_WORD0_SUPPORTED_ATTRS) {
+ if (exp->ex_flags & NFSEXP_SECURITY_LABEL)
+diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
+index ffc217099d191..ec4559ecd193b 100644
+--- a/fs/nfsd/state.h
++++ b/fs/nfsd/state.h
+@@ -781,5 +781,5 @@ static inline bool try_to_expire_client(struct nfs4_client *clp)
+ }
+
+ extern __be32 nfsd4_deleg_getattr_conflict(struct svc_rqst *rqstp,
+- struct inode *inode, bool *file_modified, u64 *size);
++ struct dentry *dentry, bool *file_modified, u64 *size);
+ #endif /* NFSD4_STATE_H */
+diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
+index 0a271b9fbc622..1e4da268de3b4 100644
+--- a/fs/smb/client/cifsglob.h
++++ b/fs/smb/client/cifsglob.h
+@@ -254,7 +254,6 @@ struct cifs_open_info_data {
+ struct smb_rqst {
+ struct kvec *rq_iov; /* array of kvecs */
+ unsigned int rq_nvec; /* number of kvecs in array */
+- size_t rq_iter_size; /* Amount of data in ->rq_iter */
+ struct iov_iter rq_iter; /* Data iterator */
+ struct xarray rq_buffer; /* Page buffer for encryption */
+ };
+diff --git a/fs/smb/client/cifssmb.c b/fs/smb/client/cifssmb.c
+index 595c4b673707e..6dce70f172082 100644
+--- a/fs/smb/client/cifssmb.c
++++ b/fs/smb/client/cifssmb.c
+@@ -1713,7 +1713,6 @@ cifs_async_writev(struct cifs_io_subrequest *wdata)
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 2;
+ rqst.rq_iter = wdata->subreq.io_iter;
+- rqst.rq_iter_size = iov_iter_count(&wdata->subreq.io_iter);
+
+ cifs_dbg(FYI, "async write at %llu %zu bytes\n",
+ wdata->subreq.start, wdata->subreq.len);
+diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
+index 7fe59235f0901..f44f5f2494006 100644
+--- a/fs/smb/client/smb2ops.c
++++ b/fs/smb/client/smb2ops.c
+@@ -3287,6 +3287,7 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
+ struct inode *inode = file_inode(file);
+ struct cifsFileInfo *cfile = file->private_data;
+ struct file_zero_data_information fsctl_buf;
++ unsigned long long end = offset + len, i_size, remote_i_size;
+ long rc;
+ unsigned int xid;
+ __u8 set_sparse = 1;
+@@ -3318,6 +3319,27 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
+ (char *)&fsctl_buf,
+ sizeof(struct file_zero_data_information),
+ CIFSMaxBufSize, NULL, NULL);
++
++ if (rc)
++ goto unlock;
++
++ /* If there's dirty data in the buffer that would extend the EOF if it
++ * were written, then we need to move the EOF marker over to the lower
++ * of the high end of the hole and the proposed EOF. The problem is
++ * that we locally hole-punch the tail of the dirty data, the proposed
++ * EOF update will end up in the wrong place.
++ */
++ i_size = i_size_read(inode);
++ remote_i_size = netfs_inode(inode)->remote_i_size;
++ if (end > remote_i_size && i_size > remote_i_size) {
++ unsigned long long extend_to = umin(end, i_size);
++ rc = SMB2_set_eof(xid, tcon, cfile->fid.persistent_fid,
++ cfile->fid.volatile_fid, cfile->pid, extend_to);
++ if (rc >= 0)
++ netfs_inode(inode)->remote_i_size = extend_to;
++ }
++
++unlock:
+ filemap_invalidate_unlock(inode->i_mapping);
+ out:
+ inode_unlock(inode);
+@@ -4428,7 +4450,6 @@ smb3_init_transform_rq(struct TCP_Server_Info *server, int num_rqst,
+ }
+ iov_iter_xarray(&new->rq_iter, ITER_SOURCE,
+ buffer, 0, size);
+- new->rq_iter_size = size;
+ }
+ }
+
+@@ -4474,7 +4495,6 @@ decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
+ rqst.rq_nvec = 2;
+ if (iter) {
+ rqst.rq_iter = *iter;
+- rqst.rq_iter_size = iov_iter_count(iter);
+ iter_size = iov_iter_count(iter);
+ }
+
+diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
+index 4cd5c33be2a1a..d262e70100c9c 100644
+--- a/fs/smb/client/smb2pdu.c
++++ b/fs/smb/client/smb2pdu.c
+@@ -4435,7 +4435,7 @@ smb2_new_read_req(void **buf, unsigned int *total_len,
+ * If we want to do a RDMA write, fill in and append
+ * smbd_buffer_descriptor_v1 to the end of read request
+ */
+- if (smb3_use_rdma_offload(io_parms)) {
++ if (rdata && smb3_use_rdma_offload(io_parms)) {
+ struct smbd_buffer_descriptor_v1 *v1;
+ bool need_invalidate = server->dialect == SMB30_PROT_ID;
+
+@@ -4517,7 +4517,6 @@ smb2_readv_callback(struct mid_q_entry *mid)
+
+ if (rdata->got_bytes) {
+ rqst.rq_iter = rdata->subreq.io_iter;
+- rqst.rq_iter_size = iov_iter_count(&rdata->subreq.io_iter);
+ }
+
+ WARN_ONCE(rdata->server != mid->server,
+@@ -4969,7 +4968,6 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
+ rqst.rq_iov = iov;
+ rqst.rq_nvec = 1;
+ rqst.rq_iter = wdata->subreq.io_iter;
+- rqst.rq_iter_size = iov_iter_count(&rqst.rq_iter);
+ if (test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags))
+ smb2_set_replay(server, &rqst);
+ #ifdef CONFIG_CIFS_SMB_DIRECT
+diff --git a/include/linux/fs.h b/include/linux/fs.h
+index 36b9e87439221..5f07c1c377df6 100644
+--- a/include/linux/fs.h
++++ b/include/linux/fs.h
+@@ -208,6 +208,7 @@ typedef int (dio_iodone_t)(struct kiocb *iocb, loff_t offset,
+ #define ATTR_OPEN (1 << 15) /* Truncating from open(O_TRUNC) */
+ #define ATTR_TIMES_SET (1 << 16)
+ #define ATTR_TOUCH (1 << 17)
++#define ATTR_DELEG (1 << 18) /* Delegated attrs. Don't break write delegations */
+
+ /*
+ * Whiteout is represented by a char device. The following constants define the
+diff --git a/include/linux/soc/qcom/pmic_glink.h b/include/linux/soc/qcom/pmic_glink.h
+index fd124aa18c81a..7cddf10277528 100644
+--- a/include/linux/soc/qcom/pmic_glink.h
++++ b/include/linux/soc/qcom/pmic_glink.h
+@@ -23,10 +23,11 @@ struct pmic_glink_hdr {
+
+ int pmic_glink_send(struct pmic_glink_client *client, void *data, size_t len);
+
+-struct pmic_glink_client *devm_pmic_glink_register_client(struct device *dev,
+- unsigned int id,
+- void (*cb)(const void *, size_t, void *),
+- void (*pdr)(void *, int),
+- void *priv);
++struct pmic_glink_client *devm_pmic_glink_client_alloc(struct device *dev,
++ unsigned int id,
++ void (*cb)(const void *, size_t, void *),
++ void (*pdr)(void *, int),
++ void *priv);
++void pmic_glink_client_register(struct pmic_glink_client *client);
+
+ #endif
+diff --git a/include/linux/sysfb.h b/include/linux/sysfb.h
+index c9cb657dad08a..bef5f06a91de6 100644
+--- a/include/linux/sysfb.h
++++ b/include/linux/sysfb.h
+@@ -58,11 +58,11 @@ struct efifb_dmi_info {
+
+ #ifdef CONFIG_SYSFB
+
+-void sysfb_disable(void);
++void sysfb_disable(struct device *dev);
+
+ #else /* CONFIG_SYSFB */
+
+-static inline void sysfb_disable(void)
++static inline void sysfb_disable(struct device *dev)
+ {
+ }
+
+diff --git a/include/net/bonding.h b/include/net/bonding.h
+index b61fb1aa3a56b..8bb5f016969f1 100644
+--- a/include/net/bonding.h
++++ b/include/net/bonding.h
+@@ -260,7 +260,7 @@ struct bonding {
+ #ifdef CONFIG_XFRM_OFFLOAD
+ struct list_head ipsec_list;
+ /* protecting ipsec_list */
+- spinlock_t ipsec_lock;
++ struct mutex ipsec_lock;
+ #endif /* CONFIG_XFRM_OFFLOAD */
+ struct bpf_prog *xdp_prog;
+ };
+diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h
+index 9b09acac538ee..522f1da8b747a 100644
+--- a/include/net/busy_poll.h
++++ b/include/net/busy_poll.h
+@@ -68,7 +68,7 @@ static inline bool sk_can_busy_loop(struct sock *sk)
+ static inline unsigned long busy_loop_current_time(void)
+ {
+ #ifdef CONFIG_NET_RX_BUSY_POLL
+- return (unsigned long)(local_clock() >> 10);
++ return (unsigned long)(ktime_get_ns() >> 10);
+ #else
+ return 0;
+ #endif
+diff --git a/include/net/netfilter/nf_tables_ipv4.h b/include/net/netfilter/nf_tables_ipv4.h
+index 60a7d0ce30804..fcf967286e37c 100644
+--- a/include/net/netfilter/nf_tables_ipv4.h
++++ b/include/net/netfilter/nf_tables_ipv4.h
+@@ -19,7 +19,7 @@ static inline void nft_set_pktinfo_ipv4(struct nft_pktinfo *pkt)
+ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
+ {
+ struct iphdr *iph, _iph;
+- u32 len, thoff;
++ u32 len, thoff, skb_len;
+
+ iph = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb),
+ sizeof(*iph), &_iph);
+@@ -30,8 +30,10 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
+ return -1;
+
+ len = iph_totlen(pkt->skb, iph);
+- thoff = skb_network_offset(pkt->skb) + (iph->ihl * 4);
+- if (pkt->skb->len < len)
++ thoff = iph->ihl * 4;
++ skb_len = pkt->skb->len - skb_network_offset(pkt->skb);
++
++ if (skb_len < len)
+ return -1;
+ else if (len < thoff)
+ return -1;
+@@ -40,7 +42,7 @@ static inline int __nft_set_pktinfo_ipv4_validate(struct nft_pktinfo *pkt)
+
+ pkt->flags = NFT_PKTINFO_L4PROTO;
+ pkt->tprot = iph->protocol;
+- pkt->thoff = thoff;
++ pkt->thoff = skb_network_offset(pkt->skb) + thoff;
+ pkt->fragoff = ntohs(iph->frag_off) & IP_OFFSET;
+
+ return 0;
+diff --git a/include/net/netfilter/nf_tables_ipv6.h b/include/net/netfilter/nf_tables_ipv6.h
+index 467d59b9e5334..a0633eeaec977 100644
+--- a/include/net/netfilter/nf_tables_ipv6.h
++++ b/include/net/netfilter/nf_tables_ipv6.h
+@@ -31,8 +31,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
+ struct ipv6hdr *ip6h, _ip6h;
+ unsigned int thoff = 0;
+ unsigned short frag_off;
++ u32 pkt_len, skb_len;
+ int protohdr;
+- u32 pkt_len;
+
+ ip6h = skb_header_pointer(pkt->skb, skb_network_offset(pkt->skb),
+ sizeof(*ip6h), &_ip6h);
+@@ -43,7 +43,8 @@ static inline int __nft_set_pktinfo_ipv6_validate(struct nft_pktinfo *pkt)
+ return -1;
+
+ pkt_len = ntohs(ip6h->payload_len);
+- if (pkt_len + sizeof(*ip6h) > pkt->skb->len)
++ skb_len = pkt->skb->len - skb_network_offset(pkt->skb);
++ if (pkt_len + sizeof(*ip6h) > skb_len)
+ return -1;
+
+ protohdr = ipv6_find_hdr(pkt->skb, &thoff, -1, &frag_off, &flags);
+diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
+index 1af2bd56af44a..bdfa30b38321b 100644
+--- a/io_uring/kbuf.c
++++ b/io_uring/kbuf.c
+@@ -129,7 +129,7 @@ static int io_provided_buffers_select(struct io_kiocb *req, size_t *len,
+
+ iov[0].iov_base = buf;
+ iov[0].iov_len = *len;
+- return 0;
++ return 1;
+ }
+
+ static struct io_uring_buf *io_ring_head_to_buf(struct io_uring_buf_ring *br,
+diff --git a/mm/truncate.c b/mm/truncate.c
+index e99085bf3d34d..a2af7f088407f 100644
+--- a/mm/truncate.c
++++ b/mm/truncate.c
+@@ -174,7 +174,7 @@ static void truncate_cleanup_folio(struct folio *folio)
+ if (folio_mapped(folio))
+ unmap_mapping_folio(folio);
+
+- if (folio_has_private(folio))
++ if (folio_needs_release(folio))
+ folio_invalidate(folio, 0, folio_size(folio));
+
+ /*
+@@ -235,7 +235,7 @@ bool truncate_inode_partial_folio(struct folio *folio, loff_t start, loff_t end)
+ */
+ folio_zero_range(folio, offset, length);
+
+- if (folio_has_private(folio))
++ if (folio_needs_release(folio))
+ folio_invalidate(folio, offset, length);
+ if (!folio_test_large(folio))
+ return true;
+diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
+index b488d0742c966..9493966cf389f 100644
+--- a/net/bluetooth/hci_core.c
++++ b/net/bluetooth/hci_core.c
+@@ -2431,10 +2431,16 @@ static int hci_suspend_notifier(struct notifier_block *nb, unsigned long action,
+ /* To avoid a potential race with hci_unregister_dev. */
+ hci_dev_hold(hdev);
+
+- if (action == PM_SUSPEND_PREPARE)
++ switch (action) {
++ case PM_HIBERNATION_PREPARE:
++ case PM_SUSPEND_PREPARE:
+ ret = hci_suspend_dev(hdev);
+- else if (action == PM_POST_SUSPEND)
++ break;
++ case PM_POST_HIBERNATION:
++ case PM_POST_SUSPEND:
+ ret = hci_resume_dev(hdev);
++ break;
++ }
+
+ if (ret)
+ bt_dev_err(hdev, "Suspend notifier action (%lu) failed: %d",
+diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c
+index 4c27a360c2948..dc91921da4ea0 100644
+--- a/net/core/net-sysfs.c
++++ b/net/core/net-sysfs.c
+@@ -235,7 +235,7 @@ static ssize_t speed_show(struct device *dev,
+ if (!rtnl_trylock())
+ return restart_syscall();
+
+- if (netif_running(netdev) && netif_device_present(netdev)) {
++ if (netif_running(netdev)) {
+ struct ethtool_link_ksettings cmd;
+
+ if (!__ethtool_get_link_ksettings(netdev, &cmd))
+diff --git a/net/core/pktgen.c b/net/core/pktgen.c
+index ea55a758a475a..197a50ef8e2e1 100644
+--- a/net/core/pktgen.c
++++ b/net/core/pktgen.c
+@@ -3654,7 +3654,7 @@ static int pktgen_thread_worker(void *arg)
+ struct pktgen_dev *pkt_dev = NULL;
+ int cpu = t->cpu;
+
+- WARN_ON(smp_processor_id() != cpu);
++ WARN_ON_ONCE(smp_processor_id() != cpu);
+
+ init_waitqueue_head(&t->queue);
+ complete(&t->start_done);
+@@ -3989,6 +3989,7 @@ static int __net_init pg_net_init(struct net *net)
+ goto remove;
+ }
+
++ cpus_read_lock();
+ for_each_online_cpu(cpu) {
+ int err;
+
+@@ -3997,6 +3998,7 @@ static int __net_init pg_net_init(struct net *net)
+ pr_warn("Cannot create thread for cpu %d (%d)\n",
+ cpu, err);
+ }
++ cpus_read_unlock();
+
+ if (list_empty(&pn->pktgen_threads)) {
+ pr_err("Initialization failed for all threads\n");
+diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
+index fcc3dbef8b503..f99fd564d0ee5 100644
+--- a/net/ethtool/ioctl.c
++++ b/net/ethtool/ioctl.c
+@@ -441,6 +441,9 @@ int __ethtool_get_link_ksettings(struct net_device *dev,
+ if (!dev->ethtool_ops->get_link_ksettings)
+ return -EOPNOTSUPP;
+
++ if (!netif_device_present(dev))
++ return -ENODEV;
++
+ memset(link_ksettings, 0, sizeof(*link_ksettings));
+ return dev->ethtool_ops->get_link_ksettings(dev, link_ksettings);
+ }
+diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
+index ec6911034138f..2edbd5b181e29 100644
+--- a/net/ipv4/tcp.c
++++ b/net/ipv4/tcp.c
+@@ -4573,6 +4573,13 @@ int tcp_abort(struct sock *sk, int err)
+ /* Don't race with userspace socket closes such as tcp_close. */
+ lock_sock(sk);
+
++ /* Avoid closing the same socket twice. */
++ if (sk->sk_state == TCP_CLOSE) {
++ if (!has_current_bpf_ctx())
++ release_sock(sk);
++ return -ENOENT;
++ }
++
+ if (sk->sk_state == TCP_LISTEN) {
+ tcp_set_state(sk, TCP_CLOSE);
+ inet_csk_listen_stop(sk);
+@@ -4582,16 +4589,13 @@ int tcp_abort(struct sock *sk, int err)
+ local_bh_disable();
+ bh_lock_sock(sk);
+
+- if (!sock_flag(sk, SOCK_DEAD)) {
+- if (tcp_need_reset(sk->sk_state))
+- tcp_send_active_reset(sk, GFP_ATOMIC,
+- SK_RST_REASON_NOT_SPECIFIED);
+- tcp_done_with_error(sk, err);
+- }
++ if (tcp_need_reset(sk->sk_state))
++ tcp_send_active_reset(sk, GFP_ATOMIC,
++ SK_RST_REASON_NOT_SPECIFIED);
++ tcp_done_with_error(sk, err);
+
+ bh_unlock_sock(sk);
+ local_bh_enable();
+- tcp_write_queue_purge(sk);
+ if (!has_current_bpf_ctx())
+ release_sock(sk);
+ return 0;
+diff --git a/net/mptcp/fastopen.c b/net/mptcp/fastopen.c
+index ad28da655f8bc..a29ff901df758 100644
+--- a/net/mptcp/fastopen.c
++++ b/net/mptcp/fastopen.c
+@@ -68,12 +68,12 @@ void __mptcp_fastopen_gen_msk_ackseq(struct mptcp_sock *msk, struct mptcp_subflo
+ skb = skb_peek_tail(&sk->sk_receive_queue);
+ if (skb) {
+ WARN_ON_ONCE(MPTCP_SKB_CB(skb)->end_seq);
+- pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx", sk,
++ pr_debug("msk %p moving seq %llx -> %llx end_seq %llx -> %llx\n", sk,
+ MPTCP_SKB_CB(skb)->map_seq, MPTCP_SKB_CB(skb)->map_seq + msk->ack_seq,
+ MPTCP_SKB_CB(skb)->end_seq, MPTCP_SKB_CB(skb)->end_seq + msk->ack_seq);
+ MPTCP_SKB_CB(skb)->map_seq += msk->ack_seq;
+ MPTCP_SKB_CB(skb)->end_seq += msk->ack_seq;
+ }
+
+- pr_debug("msk=%p ack_seq=%llx", msk, msk->ack_seq);
++ pr_debug("msk=%p ack_seq=%llx\n", msk, msk->ack_seq);
+ }
+diff --git a/net/mptcp/options.c b/net/mptcp/options.c
+index ac2f1a54cc43a..370c3836b7712 100644
+--- a/net/mptcp/options.c
++++ b/net/mptcp/options.c
+@@ -117,7 +117,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ mp_opt->suboptions |= OPTION_MPTCP_CSUMREQD;
+ ptr += 2;
+ }
+- pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u",
++ pr_debug("MP_CAPABLE version=%x, flags=%x, optlen=%d sndr=%llu, rcvr=%llu len=%d csum=%u\n",
+ version, flags, opsize, mp_opt->sndr_key,
+ mp_opt->rcvr_key, mp_opt->data_len, mp_opt->csum);
+ break;
+@@ -131,7 +131,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ ptr += 4;
+ mp_opt->nonce = get_unaligned_be32(ptr);
+ ptr += 4;
+- pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u",
++ pr_debug("MP_JOIN bkup=%u, id=%u, token=%u, nonce=%u\n",
+ mp_opt->backup, mp_opt->join_id,
+ mp_opt->token, mp_opt->nonce);
+ } else if (opsize == TCPOLEN_MPTCP_MPJ_SYNACK) {
+@@ -142,19 +142,19 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ ptr += 8;
+ mp_opt->nonce = get_unaligned_be32(ptr);
+ ptr += 4;
+- pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u",
++ pr_debug("MP_JOIN bkup=%u, id=%u, thmac=%llu, nonce=%u\n",
+ mp_opt->backup, mp_opt->join_id,
+ mp_opt->thmac, mp_opt->nonce);
+ } else if (opsize == TCPOLEN_MPTCP_MPJ_ACK) {
+ mp_opt->suboptions |= OPTION_MPTCP_MPJ_ACK;
+ ptr += 2;
+ memcpy(mp_opt->hmac, ptr, MPTCPOPT_HMAC_LEN);
+- pr_debug("MP_JOIN hmac");
++ pr_debug("MP_JOIN hmac\n");
+ }
+ break;
+
+ case MPTCPOPT_DSS:
+- pr_debug("DSS");
++ pr_debug("DSS\n");
+ ptr++;
+
+ /* we must clear 'mpc_map' be able to detect MP_CAPABLE
+@@ -169,7 +169,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ mp_opt->ack64 = (flags & MPTCP_DSS_ACK64) != 0;
+ mp_opt->use_ack = (flags & MPTCP_DSS_HAS_ACK);
+
+- pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d",
++ pr_debug("data_fin=%d dsn64=%d use_map=%d ack64=%d use_ack=%d\n",
+ mp_opt->data_fin, mp_opt->dsn64,
+ mp_opt->use_map, mp_opt->ack64,
+ mp_opt->use_ack);
+@@ -207,7 +207,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ ptr += 4;
+ }
+
+- pr_debug("data_ack=%llu", mp_opt->data_ack);
++ pr_debug("data_ack=%llu\n", mp_opt->data_ack);
+ }
+
+ if (mp_opt->use_map) {
+@@ -231,7 +231,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ ptr += 2;
+ }
+
+- pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
++ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n",
+ mp_opt->data_seq, mp_opt->subflow_seq,
+ mp_opt->data_len, !!(mp_opt->suboptions & OPTION_MPTCP_CSUMREQD),
+ mp_opt->csum);
+@@ -293,7 +293,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ mp_opt->ahmac = get_unaligned_be64(ptr);
+ ptr += 8;
+ }
+- pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d",
++ pr_debug("ADD_ADDR%s: id=%d, ahmac=%llu, echo=%d, port=%d\n",
+ (mp_opt->addr.family == AF_INET6) ? "6" : "",
+ mp_opt->addr.id, mp_opt->ahmac, mp_opt->echo, ntohs(mp_opt->addr.port));
+ break;
+@@ -309,7 +309,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ mp_opt->rm_list.nr = opsize - TCPOLEN_MPTCP_RM_ADDR_BASE;
+ for (i = 0; i < mp_opt->rm_list.nr; i++)
+ mp_opt->rm_list.ids[i] = *ptr++;
+- pr_debug("RM_ADDR: rm_list_nr=%d", mp_opt->rm_list.nr);
++ pr_debug("RM_ADDR: rm_list_nr=%d\n", mp_opt->rm_list.nr);
+ break;
+
+ case MPTCPOPT_MP_PRIO:
+@@ -318,7 +318,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+
+ mp_opt->suboptions |= OPTION_MPTCP_PRIO;
+ mp_opt->backup = *ptr++ & MPTCP_PRIO_BKUP;
+- pr_debug("MP_PRIO: prio=%d", mp_opt->backup);
++ pr_debug("MP_PRIO: prio=%d\n", mp_opt->backup);
+ break;
+
+ case MPTCPOPT_MP_FASTCLOSE:
+@@ -329,7 +329,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ mp_opt->rcvr_key = get_unaligned_be64(ptr);
+ ptr += 8;
+ mp_opt->suboptions |= OPTION_MPTCP_FASTCLOSE;
+- pr_debug("MP_FASTCLOSE: recv_key=%llu", mp_opt->rcvr_key);
++ pr_debug("MP_FASTCLOSE: recv_key=%llu\n", mp_opt->rcvr_key);
+ break;
+
+ case MPTCPOPT_RST:
+@@ -343,7 +343,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ flags = *ptr++;
+ mp_opt->reset_transient = flags & MPTCP_RST_TRANSIENT;
+ mp_opt->reset_reason = *ptr;
+- pr_debug("MP_RST: transient=%u reason=%u",
++ pr_debug("MP_RST: transient=%u reason=%u\n",
+ mp_opt->reset_transient, mp_opt->reset_reason);
+ break;
+
+@@ -354,7 +354,7 @@ static void mptcp_parse_option(const struct sk_buff *skb,
+ ptr += 2;
+ mp_opt->suboptions |= OPTION_MPTCP_FAIL;
+ mp_opt->fail_seq = get_unaligned_be64(ptr);
+- pr_debug("MP_FAIL: data_seq=%llu", mp_opt->fail_seq);
++ pr_debug("MP_FAIL: data_seq=%llu\n", mp_opt->fail_seq);
+ break;
+
+ default:
+@@ -417,7 +417,7 @@ bool mptcp_syn_options(struct sock *sk, const struct sk_buff *skb,
+ *size = TCPOLEN_MPTCP_MPC_SYN;
+ return true;
+ } else if (subflow->request_join) {
+- pr_debug("remote_token=%u, nonce=%u", subflow->remote_token,
++ pr_debug("remote_token=%u, nonce=%u\n", subflow->remote_token,
+ subflow->local_nonce);
+ opts->suboptions = OPTION_MPTCP_MPJ_SYN;
+ opts->join_id = subflow->local_id;
+@@ -500,7 +500,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
+ *size = TCPOLEN_MPTCP_MPC_ACK;
+ }
+
+- pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d",
++ pr_debug("subflow=%p, local_key=%llu, remote_key=%llu map_len=%d\n",
+ subflow, subflow->local_key, subflow->remote_key,
+ data_len);
+
+@@ -509,7 +509,7 @@ static bool mptcp_established_options_mp(struct sock *sk, struct sk_buff *skb,
+ opts->suboptions = OPTION_MPTCP_MPJ_ACK;
+ memcpy(opts->hmac, subflow->hmac, MPTCPOPT_HMAC_LEN);
+ *size = TCPOLEN_MPTCP_MPJ_ACK;
+- pr_debug("subflow=%p", subflow);
++ pr_debug("subflow=%p\n", subflow);
+
+ /* we can use the full delegate action helper only from BH context
+ * If we are in process context - sk is flushing the backlog at
+@@ -675,7 +675,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
+
+ *size = len;
+ if (drop_other_suboptions) {
+- pr_debug("drop other suboptions");
++ pr_debug("drop other suboptions\n");
+ opts->suboptions = 0;
+
+ /* note that e.g. DSS could have written into the memory
+@@ -695,7 +695,7 @@ static bool mptcp_established_options_add_addr(struct sock *sk, struct sk_buff *
+ } else {
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_ECHOADDTX);
+ }
+- pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d",
++ pr_debug("addr_id=%d, ahmac=%llu, echo=%d, port=%d\n",
+ opts->addr.id, opts->ahmac, echo, ntohs(opts->addr.port));
+
+ return true;
+@@ -726,7 +726,7 @@ static bool mptcp_established_options_rm_addr(struct sock *sk,
+ opts->rm_list = rm_list;
+
+ for (i = 0; i < opts->rm_list.nr; i++)
+- pr_debug("rm_list_ids[%d]=%d", i, opts->rm_list.ids[i]);
++ pr_debug("rm_list_ids[%d]=%d\n", i, opts->rm_list.ids[i]);
+ MPTCP_ADD_STATS(sock_net(sk), MPTCP_MIB_RMADDRTX, opts->rm_list.nr);
+ return true;
+ }
+@@ -752,7 +752,7 @@ static bool mptcp_established_options_mp_prio(struct sock *sk,
+ opts->suboptions |= OPTION_MPTCP_PRIO;
+ opts->backup = subflow->request_bkup;
+
+- pr_debug("prio=%d", opts->backup);
++ pr_debug("prio=%d\n", opts->backup);
+
+ return true;
+ }
+@@ -794,7 +794,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk,
+ opts->suboptions |= OPTION_MPTCP_FASTCLOSE;
+ opts->rcvr_key = READ_ONCE(msk->remote_key);
+
+- pr_debug("FASTCLOSE key=%llu", opts->rcvr_key);
++ pr_debug("FASTCLOSE key=%llu\n", opts->rcvr_key);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX);
+ return true;
+ }
+@@ -816,7 +816,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk,
+ opts->suboptions |= OPTION_MPTCP_FAIL;
+ opts->fail_seq = subflow->map_seq;
+
+- pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq);
++ pr_debug("MP_FAIL fail_seq=%llu\n", opts->fail_seq);
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX);
+
+ return true;
+@@ -904,7 +904,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+ opts->csum_reqd = subflow_req->csum_reqd;
+ opts->allow_join_id0 = subflow_req->allow_join_id0;
+ *size = TCPOLEN_MPTCP_MPC_SYNACK;
+- pr_debug("subflow_req=%p, local_key=%llu",
++ pr_debug("subflow_req=%p, local_key=%llu\n",
+ subflow_req, subflow_req->local_key);
+ return true;
+ } else if (subflow_req->mp_join) {
+@@ -913,7 +913,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+ opts->join_id = subflow_req->local_id;
+ opts->thmac = subflow_req->thmac;
+ opts->nonce = subflow_req->local_nonce;
+- pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u",
++ pr_debug("req=%p, bkup=%u, id=%u, thmac=%llu, nonce=%u\n",
+ subflow_req, opts->backup, opts->join_id,
+ opts->thmac, opts->nonce);
+ *size = TCPOLEN_MPTCP_MPJ_SYNACK;
+diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
+index 3e6e0f5510bb1..37f6dbcd8434d 100644
+--- a/net/mptcp/pm.c
++++ b/net/mptcp/pm.c
+@@ -19,7 +19,7 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
+ {
+ u8 add_addr = READ_ONCE(msk->pm.addr_signal);
+
+- pr_debug("msk=%p, local_id=%d, echo=%d", msk, addr->id, echo);
++ pr_debug("msk=%p, local_id=%d, echo=%d\n", msk, addr->id, echo);
+
+ lockdep_assert_held(&msk->pm.lock);
+
+@@ -45,7 +45,7 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
+ {
+ u8 rm_addr = READ_ONCE(msk->pm.addr_signal);
+
+- pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
++ pr_debug("msk=%p, rm_list_nr=%d\n", msk, rm_list->nr);
+
+ if (rm_addr) {
+ MPTCP_ADD_STATS(sock_net((struct sock *)msk),
+@@ -66,7 +66,7 @@ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int
+ {
+ struct mptcp_pm_data *pm = &msk->pm;
+
+- pr_debug("msk=%p, token=%u side=%d", msk, READ_ONCE(msk->token), server_side);
++ pr_debug("msk=%p, token=%u side=%d\n", msk, READ_ONCE(msk->token), server_side);
+
+ WRITE_ONCE(pm->server_side, server_side);
+ mptcp_event(MPTCP_EVENT_CREATED, msk, ssk, GFP_ATOMIC);
+@@ -90,7 +90,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
+
+ subflows_max = mptcp_pm_get_subflows_max(msk);
+
+- pr_debug("msk=%p subflows=%d max=%d allow=%d", msk, pm->subflows,
++ pr_debug("msk=%p subflows=%d max=%d allow=%d\n", msk, pm->subflows,
+ subflows_max, READ_ONCE(pm->accept_subflow));
+
+ /* try to avoid acquiring the lock below */
+@@ -114,7 +114,7 @@ bool mptcp_pm_allow_new_subflow(struct mptcp_sock *msk)
+ static bool mptcp_pm_schedule_work(struct mptcp_sock *msk,
+ enum mptcp_pm_status new_status)
+ {
+- pr_debug("msk=%p status=%x new=%lx", msk, msk->pm.status,
++ pr_debug("msk=%p status=%x new=%lx\n", msk, msk->pm.status,
+ BIT(new_status));
+ if (msk->pm.status & BIT(new_status))
+ return false;
+@@ -129,7 +129,7 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
+ struct mptcp_pm_data *pm = &msk->pm;
+ bool announce = false;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ spin_lock_bh(&pm->lock);
+
+@@ -153,14 +153,14 @@ void mptcp_pm_fully_established(struct mptcp_sock *msk, const struct sock *ssk)
+
+ void mptcp_pm_connection_closed(struct mptcp_sock *msk)
+ {
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+ }
+
+ void mptcp_pm_subflow_established(struct mptcp_sock *msk)
+ {
+ struct mptcp_pm_data *pm = &msk->pm;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ if (!READ_ONCE(pm->work_pending))
+ return;
+@@ -212,7 +212,7 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
+ struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+ struct mptcp_pm_data *pm = &msk->pm;
+
+- pr_debug("msk=%p remote_id=%d accept=%d", msk, addr->id,
++ pr_debug("msk=%p remote_id=%d accept=%d\n", msk, addr->id,
+ READ_ONCE(pm->accept_addr));
+
+ mptcp_event_addr_announced(ssk, addr);
+@@ -226,7 +226,9 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
+ } else {
+ __MPTCP_INC_STATS(sock_net((struct sock *)msk), MPTCP_MIB_ADDADDRDROP);
+ }
+- } else if (!READ_ONCE(pm->accept_addr)) {
++ /* id0 should not have a different address */
++ } else if ((addr->id == 0 && !mptcp_pm_nl_is_init_remote_addr(msk, addr)) ||
++ (addr->id > 0 && !READ_ONCE(pm->accept_addr))) {
+ mptcp_pm_announce_addr(msk, addr, true);
+ mptcp_pm_add_addr_send_ack(msk);
+ } else if (mptcp_pm_schedule_work(msk, MPTCP_PM_ADD_ADDR_RECEIVED)) {
+@@ -243,7 +245,7 @@ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
+ {
+ struct mptcp_pm_data *pm = &msk->pm;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ spin_lock_bh(&pm->lock);
+
+@@ -267,7 +269,7 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
+ struct mptcp_pm_data *pm = &msk->pm;
+ u8 i;
+
+- pr_debug("msk=%p remote_ids_nr=%d", msk, rm_list->nr);
++ pr_debug("msk=%p remote_ids_nr=%d\n", msk, rm_list->nr);
+
+ for (i = 0; i < rm_list->nr; i++)
+ mptcp_event_addr_removed(msk, rm_list->ids[i]);
+@@ -299,19 +301,19 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq)
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+ struct mptcp_sock *msk = mptcp_sk(subflow->conn);
+
+- pr_debug("fail_seq=%llu", fail_seq);
++ pr_debug("fail_seq=%llu\n", fail_seq);
+
+ if (!READ_ONCE(msk->allow_infinite_fallback))
+ return;
+
+ if (!subflow->fail_tout) {
+- pr_debug("send MP_FAIL response and infinite map");
++ pr_debug("send MP_FAIL response and infinite map\n");
+
+ subflow->send_mp_fail = 1;
+ subflow->send_infinite_map = 1;
+ tcp_send_ack(sk);
+ } else {
+- pr_debug("MP_FAIL response received");
++ pr_debug("MP_FAIL response received\n");
+ WRITE_ONCE(subflow->fail_tout, 0);
+ }
+ }
+diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
+index 3e4ad801786f2..f891bc714668c 100644
+--- a/net/mptcp/pm_netlink.c
++++ b/net/mptcp/pm_netlink.c
+@@ -130,12 +130,15 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
+ {
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_addr_info cur;
+- struct sock_common *skc;
+
+ list_for_each_entry(subflow, list, node) {
+- skc = (struct sock_common *)mptcp_subflow_tcp_sock(subflow);
++ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+
+- remote_address(skc, &cur);
++ if (!((1 << inet_sk_state_load(ssk)) &
++ (TCPF_ESTABLISHED | TCPF_SYN_SENT | TCPF_SYN_RECV)))
++ continue;
++
++ remote_address((struct sock_common *)ssk, &cur);
+ if (mptcp_addresses_equal(&cur, daddr, daddr->port))
+ return true;
+ }
+@@ -287,7 +290,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
+ struct mptcp_sock *msk = entry->sock;
+ struct sock *sk = (struct sock *)msk;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ if (!msk)
+ return;
+@@ -306,7 +309,7 @@ static void mptcp_pm_add_timer(struct timer_list *timer)
+ spin_lock_bh(&msk->pm.lock);
+
+ if (!mptcp_pm_should_add_signal_addr(msk)) {
+- pr_debug("retransmit ADD_ADDR id=%d", entry->addr.id);
++ pr_debug("retransmit ADD_ADDR id=%d\n", entry->addr.id);
+ mptcp_pm_announce_addr(msk, &entry->addr, false);
+ mptcp_pm_add_addr_send_ack(msk);
+ entry->retrans_times++;
+@@ -387,7 +390,7 @@ void mptcp_pm_free_anno_list(struct mptcp_sock *msk)
+ struct sock *sk = (struct sock *)msk;
+ LIST_HEAD(free_list);
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ spin_lock_bh(&msk->pm.lock);
+ list_splice_init(&msk->pm.anno_list, &free_list);
+@@ -473,7 +476,7 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+ bool slow;
+
+- pr_debug("send ack for %s",
++ pr_debug("send ack for %s\n",
+ prio ? "mp_prio" : (mptcp_pm_should_add_signal(msk) ? "add_addr" : "rm_addr"));
+
+ slow = lock_sock_fast(ssk);
+@@ -585,6 +588,11 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+
+ __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+ msk->pm.add_addr_signaled++;
++
++ /* Special case for ID0: set the correct ID */
++ if (local.addr.id == msk->mpc_endpoint_id)
++ local.addr.id = 0;
++
+ mptcp_pm_announce_addr(msk, &local.addr, false);
+ mptcp_pm_nl_addr_send_ack(msk);
+
+@@ -607,8 +615,14 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+
+ fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+
+- msk->pm.local_addr_used++;
+ __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
++
++ /* Special case for ID0: set the correct ID */
++ if (local.addr.id == msk->mpc_endpoint_id)
++ local.addr.id = 0;
++ else /* local_addr_used is not decr for ID 0 */
++ msk->pm.local_addr_used++;
++
+ nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
+ if (nr == 0)
+ continue;
+@@ -708,7 +722,7 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
+ add_addr_accept_max = mptcp_pm_get_add_addr_accept_max(msk);
+ subflows_max = mptcp_pm_get_subflows_max(msk);
+
+- pr_debug("accepted %d:%d remote family %d",
++ pr_debug("accepted %d:%d remote family %d\n",
+ msk->pm.add_addr_accepted, add_addr_accept_max,
+ msk->pm.remote.family);
+
+@@ -737,13 +751,24 @@ static void mptcp_pm_nl_add_addr_received(struct mptcp_sock *msk)
+ spin_lock_bh(&msk->pm.lock);
+
+ if (sf_created) {
+- msk->pm.add_addr_accepted++;
++ /* add_addr_accepted is not decr for ID 0 */
++ if (remote.id)
++ msk->pm.add_addr_accepted++;
+ if (msk->pm.add_addr_accepted >= add_addr_accept_max ||
+ msk->pm.subflows >= subflows_max)
+ WRITE_ONCE(msk->pm.accept_addr, false);
+ }
+ }
+
++bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
++ const struct mptcp_addr_info *remote)
++{
++ struct mptcp_addr_info mpc_remote;
++
++ remote_address((struct sock_common *)msk, &mpc_remote);
++ return mptcp_addresses_equal(&mpc_remote, remote, remote->port);
++}
++
+ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
+ {
+ struct mptcp_subflow_context *subflow;
+@@ -755,9 +780,12 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk)
+ !mptcp_pm_should_rm_signal(msk))
+ return;
+
+- subflow = list_first_entry_or_null(&msk->conn_list, typeof(*subflow), node);
+- if (subflow)
+- mptcp_pm_send_ack(msk, subflow, false, false);
++ mptcp_for_each_subflow(msk, subflow) {
++ if (__mptcp_subflow_active(subflow)) {
++ mptcp_pm_send_ack(msk, subflow, false, false);
++ break;
++ }
++ }
+ }
+
+ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+@@ -767,7 +795,7 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+ {
+ struct mptcp_subflow_context *subflow;
+
+- pr_debug("bkup=%d", bkup);
++ pr_debug("bkup=%d\n", bkup);
+
+ mptcp_for_each_subflow(msk, subflow) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
+@@ -790,11 +818,6 @@ int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk,
+ return -EINVAL;
+ }
+
+-static bool mptcp_local_id_match(const struct mptcp_sock *msk, u8 local_id, u8 id)
+-{
+- return local_id == id || (!local_id && msk->mpc_endpoint_id == id);
+-}
+-
+ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
+ const struct mptcp_rm_list *rm_list,
+ enum linux_mptcp_mib_field rm_type)
+@@ -803,7 +826,7 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
+ struct sock *sk = (struct sock *)msk;
+ u8 i;
+
+- pr_debug("%s rm_list_nr %d",
++ pr_debug("%s rm_list_nr %d\n",
+ rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow", rm_list->nr);
+
+ msk_owned_by_me(msk);
+@@ -827,12 +850,14 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
+ int how = RCV_SHUTDOWN | SEND_SHUTDOWN;
+ u8 id = subflow_get_local_id(subflow);
+
++ if (inet_sk_state_load(ssk) == TCP_CLOSE)
++ continue;
+ if (rm_type == MPTCP_MIB_RMADDR && remote_id != rm_id)
+ continue;
+- if (rm_type == MPTCP_MIB_RMSUBFLOW && !mptcp_local_id_match(msk, id, rm_id))
++ if (rm_type == MPTCP_MIB_RMSUBFLOW && id != rm_id)
+ continue;
+
+- pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u",
++ pr_debug(" -> %s rm_list_ids[%d]=%u local_id=%u remote_id=%u mpc_id=%u\n",
+ rm_type == MPTCP_MIB_RMADDR ? "address" : "subflow",
+ i, rm_id, id, remote_id, msk->mpc_endpoint_id);
+ spin_unlock_bh(&msk->pm.lock);
+@@ -889,7 +914,7 @@ void mptcp_pm_nl_work(struct mptcp_sock *msk)
+
+ spin_lock_bh(&msk->pm.lock);
+
+- pr_debug("msk=%p status=%x", msk, pm->status);
++ pr_debug("msk=%p status=%x\n", msk, pm->status);
+ if (pm->status & BIT(MPTCP_PM_ADD_ADDR_RECEIVED)) {
+ pm->status &= ~BIT(MPTCP_PM_ADD_ADDR_RECEIVED);
+ mptcp_pm_nl_add_addr_received(msk);
+@@ -1307,20 +1332,27 @@ static struct pm_nl_pernet *genl_info_pm_nl(struct genl_info *info)
+ return pm_nl_get_pernet(genl_info_net(info));
+ }
+
+-static int mptcp_nl_add_subflow_or_signal_addr(struct net *net)
++static int mptcp_nl_add_subflow_or_signal_addr(struct net *net,
++ struct mptcp_addr_info *addr)
+ {
+ struct mptcp_sock *msk;
+ long s_slot = 0, s_num = 0;
+
+ while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+ struct sock *sk = (struct sock *)msk;
++ struct mptcp_addr_info mpc_addr;
+
+ if (!READ_ONCE(msk->fully_established) ||
+ mptcp_pm_is_userspace(msk))
+ goto next;
+
++ /* if the endp linked to the init sf is re-added with a != ID */
++ mptcp_local_address((struct sock_common *)msk, &mpc_addr);
++
+ lock_sock(sk);
+ spin_lock_bh(&msk->pm.lock);
++ if (mptcp_addresses_equal(addr, &mpc_addr, addr->port))
++ msk->mpc_endpoint_id = addr->id;
+ mptcp_pm_create_subflow_or_signal_addr(msk);
+ spin_unlock_bh(&msk->pm.lock);
+ release_sock(sk);
+@@ -1393,7 +1425,7 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
+ goto out_free;
+ }
+
+- mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk));
++ mptcp_nl_add_subflow_or_signal_addr(sock_net(skb->sk), &entry->addr);
+ return 0;
+
+ out_free:
+@@ -1438,6 +1470,12 @@ static bool remove_anno_list_by_saddr(struct mptcp_sock *msk,
+ return false;
+ }
+
++static u8 mptcp_endp_get_local_id(struct mptcp_sock *msk,
++ const struct mptcp_addr_info *addr)
++{
++ return msk->mpc_endpoint_id == addr->id ? 0 : addr->id;
++}
++
+ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr,
+ bool force)
+@@ -1445,7 +1483,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+ struct mptcp_rm_list list = { .nr = 0 };
+ bool ret;
+
+- list.ids[list.nr++] = addr->id;
++ list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
+
+ ret = remove_anno_list_by_saddr(msk, addr);
+ if (ret || force) {
+@@ -1472,13 +1510,11 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+ const struct mptcp_pm_addr_entry *entry)
+ {
+ const struct mptcp_addr_info *addr = &entry->addr;
+- struct mptcp_rm_list list = { .nr = 0 };
++ struct mptcp_rm_list list = { .nr = 1 };
+ long s_slot = 0, s_num = 0;
+ struct mptcp_sock *msk;
+
+- pr_debug("remove_id=%d", addr->id);
+-
+- list.ids[list.nr++] = addr->id;
++ pr_debug("remove_id=%d\n", addr->id);
+
+ while ((msk = mptcp_token_iter_next(net, &s_slot, &s_num)) != NULL) {
+ struct sock *sk = (struct sock *)msk;
+@@ -1497,6 +1533,7 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+ mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
+ !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
+
++ list.ids[0] = mptcp_endp_get_local_id(msk, addr);
+ if (remove_subflow) {
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_pm_nl_rm_subflow_received(msk, &list);
+@@ -1509,6 +1546,8 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+ spin_unlock_bh(&msk->pm.lock);
+ }
+
++ if (msk->mpc_endpoint_id == entry->addr.id)
++ msk->mpc_endpoint_id = 0;
+ release_sock(sk);
+
+ next:
+@@ -1603,6 +1642,7 @@ int mptcp_pm_nl_del_addr_doit(struct sk_buff *skb, struct genl_info *info)
+ return ret;
+ }
+
++/* Called from the userspace PM only */
+ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
+ {
+ struct mptcp_rm_list alist = { .nr = 0 };
+@@ -1631,6 +1671,7 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
+ }
+ }
+
++/* Called from the in-kernel PM only */
+ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
+ struct list_head *rm_list)
+ {
+@@ -1640,11 +1681,11 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
+ list_for_each_entry(entry, rm_list, list) {
+ if (slist.nr < MPTCP_RM_IDS_MAX &&
+ lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
+- slist.ids[slist.nr++] = entry->addr.id;
++ slist.ids[slist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
+
+ if (alist.nr < MPTCP_RM_IDS_MAX &&
+ remove_anno_list_by_saddr(msk, &entry->addr))
+- alist.ids[alist.nr++] = entry->addr.id;
++ alist.ids[alist.nr++] = mptcp_endp_get_local_id(msk, &entry->addr);
+ }
+
+ spin_lock_bh(&msk->pm.lock);
+@@ -1941,7 +1982,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
+ {
+ struct mptcp_rm_list list = { .nr = 0 };
+
+- list.ids[list.nr++] = addr->id;
++ list.ids[list.nr++] = mptcp_endp_get_local_id(msk, addr);
+
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_pm_nl_rm_subflow_received(msk, &list);
+diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
+index ff8292d0cf4e6..4c8c21d3c3f7c 100644
+--- a/net/mptcp/protocol.c
++++ b/net/mptcp/protocol.c
+@@ -139,7 +139,7 @@ static bool mptcp_try_coalesce(struct sock *sk, struct sk_buff *to,
+ !skb_try_coalesce(to, from, &fragstolen, &delta))
+ return false;
+
+- pr_debug("colesced seq %llx into %llx new len %d new end seq %llx",
++ pr_debug("colesced seq %llx into %llx new len %d new end seq %llx\n",
+ MPTCP_SKB_CB(from)->map_seq, MPTCP_SKB_CB(to)->map_seq,
+ to->len, MPTCP_SKB_CB(from)->end_seq);
+ MPTCP_SKB_CB(to)->end_seq = MPTCP_SKB_CB(from)->end_seq;
+@@ -217,7 +217,7 @@ static void mptcp_data_queue_ofo(struct mptcp_sock *msk, struct sk_buff *skb)
+ end_seq = MPTCP_SKB_CB(skb)->end_seq;
+ max_seq = atomic64_read(&msk->rcv_wnd_sent);
+
+- pr_debug("msk=%p seq=%llx limit=%llx empty=%d", msk, seq, max_seq,
++ pr_debug("msk=%p seq=%llx limit=%llx empty=%d\n", msk, seq, max_seq,
+ RB_EMPTY_ROOT(&msk->out_of_order_queue));
+ if (after64(end_seq, max_seq)) {
+ /* out of window */
+@@ -643,7 +643,7 @@ static bool __mptcp_move_skbs_from_subflow(struct mptcp_sock *msk,
+ }
+ }
+
+- pr_debug("msk=%p ssk=%p", msk, ssk);
++ pr_debug("msk=%p ssk=%p\n", msk, ssk);
+ tp = tcp_sk(ssk);
+ do {
+ u32 map_remaining, offset;
+@@ -724,7 +724,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
+ u64 end_seq;
+
+ p = rb_first(&msk->out_of_order_queue);
+- pr_debug("msk=%p empty=%d", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
++ pr_debug("msk=%p empty=%d\n", msk, RB_EMPTY_ROOT(&msk->out_of_order_queue));
+ while (p) {
+ skb = rb_to_skb(p);
+ if (after64(MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq))
+@@ -746,7 +746,7 @@ static bool __mptcp_ofo_queue(struct mptcp_sock *msk)
+ int delta = msk->ack_seq - MPTCP_SKB_CB(skb)->map_seq;
+
+ /* skip overlapping data, if any */
+- pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d",
++ pr_debug("uncoalesced seq=%llx ack seq=%llx delta=%d\n",
+ MPTCP_SKB_CB(skb)->map_seq, msk->ack_seq,
+ delta);
+ MPTCP_SKB_CB(skb)->offset += delta;
+@@ -1240,7 +1240,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
+ size_t copy;
+ int i;
+
+- pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u",
++ pr_debug("msk=%p ssk=%p sending dfrag at seq=%llu len=%u already sent=%u\n",
+ msk, ssk, dfrag->data_seq, dfrag->data_len, info->sent);
+
+ if (WARN_ON_ONCE(info->sent > info->limit ||
+@@ -1341,7 +1341,7 @@ static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk,
+ mpext->use_map = 1;
+ mpext->dsn64 = 1;
+
+- pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d",
++ pr_debug("data_seq=%llu subflow_seq=%u data_len=%u dsn64=%d\n",
+ mpext->data_seq, mpext->subflow_seq, mpext->data_len,
+ mpext->dsn64);
+
+@@ -1892,7 +1892,7 @@ static int mptcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len)
+ if (!msk->first_pending)
+ WRITE_ONCE(msk->first_pending, dfrag);
+ }
+- pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d", msk,
++ pr_debug("msk=%p dfrag at seq=%llu len=%u sent=%u new=%d\n", msk,
+ dfrag->data_seq, dfrag->data_len, dfrag->already_sent,
+ !dfrag_collapsed);
+
+@@ -2248,7 +2248,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ }
+ }
+
+- pr_debug("block timeout %ld", timeo);
++ pr_debug("block timeout %ld\n", timeo);
+ sk_wait_data(sk, &timeo, NULL);
+ }
+
+@@ -2264,7 +2264,7 @@ static int mptcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len,
+ }
+ }
+
+- pr_debug("msk=%p rx queue empty=%d:%d copied=%d",
++ pr_debug("msk=%p rx queue empty=%d:%d copied=%d\n",
+ msk, skb_queue_empty_lockless(&sk->sk_receive_queue),
+ skb_queue_empty(&msk->receive_queue), copied);
+ if (!(flags & MSG_PEEK))
+@@ -2326,7 +2326,7 @@ struct sock *mptcp_subflow_get_retrans(struct mptcp_sock *msk)
+ continue;
+ }
+
+- if (subflow->backup) {
++ if (subflow->backup || subflow->request_bkup) {
+ if (!backup)
+ backup = ssk;
+ continue;
+@@ -2508,6 +2508,12 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+ void mptcp_close_ssk(struct sock *sk, struct sock *ssk,
+ struct mptcp_subflow_context *subflow)
+ {
++ /* The first subflow can already be closed and still in the list */
++ if (subflow->close_event_done)
++ return;
++
++ subflow->close_event_done = true;
++
+ if (sk->sk_state == TCP_ESTABLISHED)
+ mptcp_event(MPTCP_EVENT_SUB_CLOSED, mptcp_sk(sk), ssk, GFP_KERNEL);
+
+@@ -2533,8 +2539,11 @@ static void __mptcp_close_subflow(struct sock *sk)
+
+ mptcp_for_each_subflow_safe(msk, subflow, tmp) {
+ struct sock *ssk = mptcp_subflow_tcp_sock(subflow);
++ int ssk_state = inet_sk_state_load(ssk);
+
+- if (inet_sk_state_load(ssk) != TCP_CLOSE)
++ if (ssk_state != TCP_CLOSE &&
++ (ssk_state != TCP_CLOSE_WAIT ||
++ inet_sk_state_load(sk) != TCP_ESTABLISHED))
+ continue;
+
+ /* 'subflow_data_ready' will re-sched once rx queue is empty */
+@@ -2714,7 +2723,7 @@ static void mptcp_mp_fail_no_response(struct mptcp_sock *msk)
+ if (!ssk)
+ return;
+
+- pr_debug("MP_FAIL doesn't respond, reset the subflow");
++ pr_debug("MP_FAIL doesn't respond, reset the subflow\n");
+
+ slow = lock_sock_fast(ssk);
+ mptcp_subflow_reset(ssk);
+@@ -2888,7 +2897,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
+ break;
+ default:
+ if (__mptcp_check_fallback(mptcp_sk(sk))) {
+- pr_debug("Fallback");
++ pr_debug("Fallback\n");
+ ssk->sk_shutdown |= how;
+ tcp_shutdown(ssk, how);
+
+@@ -2898,7 +2907,7 @@ void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how)
+ WRITE_ONCE(mptcp_sk(sk)->snd_una, mptcp_sk(sk)->snd_nxt);
+ mptcp_schedule_work(sk);
+ } else {
+- pr_debug("Sending DATA_FIN on subflow %p", ssk);
++ pr_debug("Sending DATA_FIN on subflow %p\n", ssk);
+ tcp_send_ack(ssk);
+ if (!mptcp_rtx_timer_pending(sk))
+ mptcp_reset_rtx_timer(sk);
+@@ -2964,7 +2973,7 @@ static void mptcp_check_send_data_fin(struct sock *sk)
+ struct mptcp_subflow_context *subflow;
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+- pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu",
++ pr_debug("msk=%p snd_data_fin_enable=%d pending=%d snd_nxt=%llu write_seq=%llu\n",
+ msk, msk->snd_data_fin_enable, !!mptcp_send_head(sk),
+ msk->snd_nxt, msk->write_seq);
+
+@@ -2988,7 +2997,7 @@ static void __mptcp_wr_shutdown(struct sock *sk)
+ {
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+- pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d",
++ pr_debug("msk=%p snd_data_fin_enable=%d shutdown=%x state=%d pending=%d\n",
+ msk, msk->snd_data_fin_enable, sk->sk_shutdown, sk->sk_state,
+ !!mptcp_send_head(sk));
+
+@@ -3003,7 +3012,7 @@ static void __mptcp_destroy_sock(struct sock *sk)
+ {
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ might_sleep();
+
+@@ -3111,7 +3120,7 @@ bool __mptcp_close(struct sock *sk, long timeout)
+ mptcp_set_state(sk, TCP_CLOSE);
+
+ sock_hold(sk);
+- pr_debug("msk=%p state=%d", sk, sk->sk_state);
++ pr_debug("msk=%p state=%d\n", sk, sk->sk_state);
+ if (msk->token)
+ mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL);
+
+@@ -3543,7 +3552,7 @@ static int mptcp_get_port(struct sock *sk, unsigned short snum)
+ {
+ struct mptcp_sock *msk = mptcp_sk(sk);
+
+- pr_debug("msk=%p, ssk=%p", msk, msk->first);
++ pr_debug("msk=%p, ssk=%p\n", msk, msk->first);
+ if (WARN_ON_ONCE(!msk->first))
+ return -EINVAL;
+
+@@ -3560,7 +3569,7 @@ void mptcp_finish_connect(struct sock *ssk)
+ sk = subflow->conn;
+ msk = mptcp_sk(sk);
+
+- pr_debug("msk=%p, token=%u", sk, subflow->token);
++ pr_debug("msk=%p, token=%u\n", sk, subflow->token);
+
+ subflow->map_seq = subflow->iasn;
+ subflow->map_subflow_seq = 1;
+@@ -3589,7 +3598,7 @@ bool mptcp_finish_join(struct sock *ssk)
+ struct sock *parent = (void *)msk;
+ bool ret = true;
+
+- pr_debug("msk=%p, subflow=%p", msk, subflow);
++ pr_debug("msk=%p, subflow=%p\n", msk, subflow);
+
+ /* mptcp socket already closing? */
+ if (!mptcp_is_fully_established(parent)) {
+@@ -3635,7 +3644,7 @@ bool mptcp_finish_join(struct sock *ssk)
+
+ static void mptcp_shutdown(struct sock *sk, int how)
+ {
+- pr_debug("sk=%p, how=%d", sk, how);
++ pr_debug("sk=%p, how=%d\n", sk, how);
+
+ if ((how & SEND_SHUTDOWN) && mptcp_close_state(sk))
+ __mptcp_wr_shutdown(sk);
+@@ -3856,7 +3865,7 @@ static int mptcp_listen(struct socket *sock, int backlog)
+ struct sock *ssk;
+ int err;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ lock_sock(sk);
+
+@@ -3895,7 +3904,7 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
+ struct mptcp_sock *msk = mptcp_sk(sock->sk);
+ struct sock *ssk, *newsk;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ /* Buggy applications can call accept on socket states other then LISTEN
+ * but no need to allocate the first subflow just to error out.
+@@ -3904,12 +3913,12 @@ static int mptcp_stream_accept(struct socket *sock, struct socket *newsock,
+ if (!ssk)
+ return -EINVAL;
+
+- pr_debug("ssk=%p, listener=%p", ssk, mptcp_subflow_ctx(ssk));
++ pr_debug("ssk=%p, listener=%p\n", ssk, mptcp_subflow_ctx(ssk));
+ newsk = inet_csk_accept(ssk, arg);
+ if (!newsk)
+ return arg->err;
+
+- pr_debug("newsk=%p, subflow is mptcp=%d", newsk, sk_is_mptcp(newsk));
++ pr_debug("newsk=%p, subflow is mptcp=%d\n", newsk, sk_is_mptcp(newsk));
+ if (sk_is_mptcp(newsk)) {
+ struct mptcp_subflow_context *subflow;
+ struct sock *new_mptcp_sock;
+@@ -4002,7 +4011,7 @@ static __poll_t mptcp_poll(struct file *file, struct socket *sock,
+ sock_poll_wait(file, sock, wait);
+
+ state = inet_sk_state_load(sk);
+- pr_debug("msk=%p state=%d flags=%lx", msk, state, msk->flags);
++ pr_debug("msk=%p state=%d flags=%lx\n", msk, state, msk->flags);
+ if (state == TCP_LISTEN) {
+ struct sock *ssk = READ_ONCE(msk->first);
+
+diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
+index c7c846805c4e1..0241b0dbab3ca 100644
+--- a/net/mptcp/protocol.h
++++ b/net/mptcp/protocol.h
+@@ -519,7 +519,8 @@ struct mptcp_subflow_context {
+ stale : 1, /* unable to snd/rcv data, do not use for xmit */
+ valid_csum_seen : 1, /* at least one csum validated */
+ is_mptfo : 1, /* subflow is doing TFO */
+- __unused : 10;
++ close_event_done : 1, /* has done the post-closed part */
++ __unused : 9;
+ bool data_avail;
+ bool scheduled;
+ u32 remote_nonce;
+@@ -987,6 +988,8 @@ void mptcp_pm_add_addr_received(const struct sock *ssk,
+ void mptcp_pm_add_addr_echoed(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr);
+ void mptcp_pm_add_addr_send_ack(struct mptcp_sock *msk);
++bool mptcp_pm_nl_is_init_remote_addr(struct mptcp_sock *msk,
++ const struct mptcp_addr_info *remote);
+ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk);
+ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk,
+ const struct mptcp_rm_list *rm_list);
+@@ -1172,7 +1175,7 @@ static inline bool mptcp_check_fallback(const struct sock *sk)
+ static inline void __mptcp_do_fallback(struct mptcp_sock *msk)
+ {
+ if (__mptcp_check_fallback(msk)) {
+- pr_debug("TCP fallback already done (msk=%p)", msk);
++ pr_debug("TCP fallback already done (msk=%p)\n", msk);
+ return;
+ }
+ set_bit(MPTCP_FALLBACK_DONE, &msk->flags);
+@@ -1208,7 +1211,7 @@ static inline void mptcp_do_fallback(struct sock *ssk)
+ }
+ }
+
+-#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a)
++#define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)\n", __func__, a)
+
+ static inline bool mptcp_check_infinite_map(struct sk_buff *skb)
+ {
+diff --git a/net/mptcp/sched.c b/net/mptcp/sched.c
+index 4a7fd0508ad28..78ed508ebc1b8 100644
+--- a/net/mptcp/sched.c
++++ b/net/mptcp/sched.c
+@@ -86,7 +86,7 @@ int mptcp_register_scheduler(struct mptcp_sched_ops *sched)
+ list_add_tail_rcu(&sched->list, &mptcp_sched_list);
+ spin_unlock(&mptcp_sched_list_lock);
+
+- pr_debug("%s registered", sched->name);
++ pr_debug("%s registered\n", sched->name);
+ return 0;
+ }
+
+@@ -118,7 +118,7 @@ int mptcp_init_sched(struct mptcp_sock *msk,
+ if (msk->sched->init)
+ msk->sched->init(msk);
+
+- pr_debug("sched=%s", msk->sched->name);
++ pr_debug("sched=%s\n", msk->sched->name);
+
+ return 0;
+ }
+diff --git a/net/mptcp/sockopt.c b/net/mptcp/sockopt.c
+index f9a4fb17b5b78..499bd002ceb89 100644
+--- a/net/mptcp/sockopt.c
++++ b/net/mptcp/sockopt.c
+@@ -873,7 +873,7 @@ int mptcp_setsockopt(struct sock *sk, int level, int optname,
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sock *ssk;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ if (level == SOL_SOCKET)
+ return mptcp_setsockopt_sol_socket(msk, optname, optval, optlen);
+@@ -1453,7 +1453,7 @@ int mptcp_getsockopt(struct sock *sk, int level, int optname,
+ struct mptcp_sock *msk = mptcp_sk(sk);
+ struct sock *ssk;
+
+- pr_debug("msk=%p", msk);
++ pr_debug("msk=%p\n", msk);
+
+ /* @@ the meaning of setsockopt() when the socket is connected and
+ * there are multiple subflows is not yet defined. It is up to the
+diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
+index c330946384ba0..fc813d538a5a2 100644
+--- a/net/mptcp/subflow.c
++++ b/net/mptcp/subflow.c
+@@ -39,7 +39,7 @@ static void subflow_req_destructor(struct request_sock *req)
+ {
+ struct mptcp_subflow_request_sock *subflow_req = mptcp_subflow_rsk(req);
+
+- pr_debug("subflow_req=%p", subflow_req);
++ pr_debug("subflow_req=%p\n", subflow_req);
+
+ if (subflow_req->msk)
+ sock_put((struct sock *)subflow_req->msk);
+@@ -146,7 +146,7 @@ static int subflow_check_req(struct request_sock *req,
+ struct mptcp_options_received mp_opt;
+ bool opt_mp_capable, opt_mp_join;
+
+- pr_debug("subflow_req=%p, listener=%p", subflow_req, listener);
++ pr_debug("subflow_req=%p, listener=%p\n", subflow_req, listener);
+
+ #ifdef CONFIG_TCP_MD5SIG
+ /* no MPTCP if MD5SIG is enabled on this socket or we may run out of
+@@ -221,7 +221,7 @@ static int subflow_check_req(struct request_sock *req,
+ }
+
+ if (subflow_use_different_sport(subflow_req->msk, sk_listener)) {
+- pr_debug("syn inet_sport=%d %d",
++ pr_debug("syn inet_sport=%d %d\n",
+ ntohs(inet_sk(sk_listener)->inet_sport),
+ ntohs(inet_sk((struct sock *)subflow_req->msk)->inet_sport));
+ if (!mptcp_pm_sport_in_anno_list(subflow_req->msk, sk_listener)) {
+@@ -243,7 +243,7 @@ static int subflow_check_req(struct request_sock *req,
+ subflow_init_req_cookie_join_save(subflow_req, skb);
+ }
+
+- pr_debug("token=%u, remote_nonce=%u msk=%p", subflow_req->token,
++ pr_debug("token=%u, remote_nonce=%u msk=%p\n", subflow_req->token,
+ subflow_req->remote_nonce, subflow_req->msk);
+ }
+
+@@ -527,7 +527,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
+ subflow->rel_write_seq = 1;
+ subflow->conn_finished = 1;
+ subflow->ssn_offset = TCP_SKB_CB(skb)->seq;
+- pr_debug("subflow=%p synack seq=%x", subflow, subflow->ssn_offset);
++ pr_debug("subflow=%p synack seq=%x\n", subflow, subflow->ssn_offset);
+
+ mptcp_get_options(skb, &mp_opt);
+ if (subflow->request_mptcp) {
+@@ -559,7 +559,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
+ subflow->thmac = mp_opt.thmac;
+ subflow->remote_nonce = mp_opt.nonce;
+ WRITE_ONCE(subflow->remote_id, mp_opt.join_id);
+- pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d",
++ pr_debug("subflow=%p, thmac=%llu, remote_nonce=%u backup=%d\n",
+ subflow, subflow->thmac, subflow->remote_nonce,
+ subflow->backup);
+
+@@ -585,7 +585,7 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
+
+ if (subflow_use_different_dport(msk, sk)) {
+- pr_debug("synack inet_dport=%d %d",
++ pr_debug("synack inet_dport=%d %d\n",
+ ntohs(inet_sk(sk)->inet_dport),
+ ntohs(inet_sk(parent)->inet_dport));
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINPORTSYNACKRX);
+@@ -655,7 +655,7 @@ static int subflow_v4_conn_request(struct sock *sk, struct sk_buff *skb)
+ {
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+
+- pr_debug("subflow=%p", subflow);
++ pr_debug("subflow=%p\n", subflow);
+
+ /* Never answer to SYNs sent to broadcast or multicast */
+ if (skb_rtable(skb)->rt_flags & (RTCF_BROADCAST | RTCF_MULTICAST))
+@@ -686,7 +686,7 @@ static int subflow_v6_conn_request(struct sock *sk, struct sk_buff *skb)
+ {
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk);
+
+- pr_debug("subflow=%p", subflow);
++ pr_debug("subflow=%p\n", subflow);
+
+ if (skb->protocol == htons(ETH_P_IP))
+ return subflow_v4_conn_request(sk, skb);
+@@ -807,7 +807,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
+ struct mptcp_sock *owner;
+ struct sock *child;
+
+- pr_debug("listener=%p, req=%p, conn=%p", listener, req, listener->conn);
++ pr_debug("listener=%p, req=%p, conn=%p\n", listener, req, listener->conn);
+
+ /* After child creation we must look for MPC even when options
+ * are not parsed
+@@ -898,7 +898,7 @@ static struct sock *subflow_syn_recv_sock(const struct sock *sk,
+ ctx->conn = (struct sock *)owner;
+
+ if (subflow_use_different_sport(owner, sk)) {
+- pr_debug("ack inet_sport=%d %d",
++ pr_debug("ack inet_sport=%d %d\n",
+ ntohs(inet_sk(sk)->inet_sport),
+ ntohs(inet_sk((struct sock *)owner)->inet_sport));
+ if (!mptcp_pm_sport_in_anno_list(owner, sk)) {
+@@ -961,7 +961,7 @@ enum mapping_status {
+
+ static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn)
+ {
+- pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d",
++ pr_debug("Bad mapping: ssn=%d map_seq=%d map_data_len=%d\n",
+ ssn, subflow->map_subflow_seq, subflow->map_data_len);
+ }
+
+@@ -1121,7 +1121,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
+
+ data_len = mpext->data_len;
+ if (data_len == 0) {
+- pr_debug("infinite mapping received");
++ pr_debug("infinite mapping received\n");
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX);
+ subflow->map_data_len = 0;
+ return MAPPING_INVALID;
+@@ -1133,7 +1133,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
+ if (data_len == 1) {
+ bool updated = mptcp_update_rcv_data_fin(msk, mpext->data_seq,
+ mpext->dsn64);
+- pr_debug("DATA_FIN with no payload seq=%llu", mpext->data_seq);
++ pr_debug("DATA_FIN with no payload seq=%llu\n", mpext->data_seq);
+ if (subflow->map_valid) {
+ /* A DATA_FIN might arrive in a DSS
+ * option before the previous mapping
+@@ -1159,7 +1159,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
+ data_fin_seq &= GENMASK_ULL(31, 0);
+
+ mptcp_update_rcv_data_fin(msk, data_fin_seq, mpext->dsn64);
+- pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d",
++ pr_debug("DATA_FIN with mapping seq=%llu dsn64=%d\n",
+ data_fin_seq, mpext->dsn64);
+
+ /* Adjust for DATA_FIN using 1 byte of sequence space */
+@@ -1205,7 +1205,7 @@ static enum mapping_status get_mapping_status(struct sock *ssk,
+ if (unlikely(subflow->map_csum_reqd != csum_reqd))
+ return MAPPING_INVALID;
+
+- pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u",
++ pr_debug("new map seq=%llu subflow_seq=%u data_len=%u csum=%d:%u\n",
+ subflow->map_seq, subflow->map_subflow_seq,
+ subflow->map_data_len, subflow->map_csum_reqd,
+ subflow->map_data_csum);
+@@ -1240,7 +1240,7 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
+ avail_len = skb->len - offset;
+ incr = limit >= avail_len ? avail_len + fin : limit;
+
+- pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
++ pr_debug("discarding=%d len=%d offset=%d seq=%d\n", incr, skb->len,
+ offset, subflow->map_subflow_seq);
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
+ tcp_sk(ssk)->copied_seq += incr;
+@@ -1255,12 +1255,16 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
+ /* sched mptcp worker to remove the subflow if no more data is pending */
+ static void subflow_sched_work_if_closed(struct mptcp_sock *msk, struct sock *ssk)
+ {
+- if (likely(ssk->sk_state != TCP_CLOSE))
++ struct sock *sk = (struct sock *)msk;
++
++ if (likely(ssk->sk_state != TCP_CLOSE &&
++ (ssk->sk_state != TCP_CLOSE_WAIT ||
++ inet_sk_state_load(sk) != TCP_ESTABLISHED)))
+ return;
+
+ if (skb_queue_empty(&ssk->sk_receive_queue) &&
+ !test_and_set_bit(MPTCP_WORK_CLOSE_SUBFLOW, &msk->flags))
+- mptcp_schedule_work((struct sock *)msk);
++ mptcp_schedule_work(sk);
+ }
+
+ static bool subflow_can_fallback(struct mptcp_subflow_context *subflow)
+@@ -1337,7 +1341,7 @@ static bool subflow_check_data_avail(struct sock *ssk)
+
+ old_ack = READ_ONCE(msk->ack_seq);
+ ack_seq = mptcp_subflow_get_mapped_dsn(subflow);
+- pr_debug("msk ack_seq=%llx subflow ack_seq=%llx", old_ack,
++ pr_debug("msk ack_seq=%llx subflow ack_seq=%llx\n", old_ack,
+ ack_seq);
+ if (unlikely(before64(ack_seq, old_ack))) {
+ mptcp_subflow_discard_data(ssk, skb, old_ack - ack_seq);
+@@ -1409,7 +1413,7 @@ bool mptcp_subflow_data_available(struct sock *sk)
+ subflow->map_valid = 0;
+ WRITE_ONCE(subflow->data_avail, false);
+
+- pr_debug("Done with mapping: seq=%u data_len=%u",
++ pr_debug("Done with mapping: seq=%u data_len=%u\n",
+ subflow->map_subflow_seq,
+ subflow->map_data_len);
+ }
+@@ -1519,7 +1523,7 @@ void mptcpv6_handle_mapped(struct sock *sk, bool mapped)
+
+ target = mapped ? &subflow_v6m_specific : subflow_default_af_ops(sk);
+
+- pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d",
++ pr_debug("subflow=%p family=%d ops=%p target=%p mapped=%d\n",
+ subflow, sk->sk_family, icsk->icsk_af_ops, target, mapped);
+
+ if (likely(icsk->icsk_af_ops == target))
+@@ -1612,7 +1616,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc,
+ goto failed;
+
+ mptcp_crypto_key_sha(subflow->remote_key, &remote_token, NULL);
+- pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d", msk,
++ pr_debug("msk=%p remote_token=%u local_id=%d remote_id=%d\n", msk,
+ remote_token, local_id, remote_id);
+ subflow->remote_token = remote_token;
+ WRITE_ONCE(subflow->remote_id, remote_id);
+@@ -1747,7 +1751,7 @@ int mptcp_subflow_create_socket(struct sock *sk, unsigned short family,
+ SOCK_INODE(sf)->i_gid = SOCK_INODE(sk->sk_socket)->i_gid;
+
+ subflow = mptcp_subflow_ctx(sf->sk);
+- pr_debug("subflow=%p", subflow);
++ pr_debug("subflow=%p\n", subflow);
+
+ *new_sock = sf;
+ sock_hold(sk);
+@@ -1776,7 +1780,7 @@ static struct mptcp_subflow_context *subflow_create_ctx(struct sock *sk,
+ INIT_LIST_HEAD(&ctx->node);
+ INIT_LIST_HEAD(&ctx->delegated_node);
+
+- pr_debug("subflow=%p", ctx);
++ pr_debug("subflow=%p\n", ctx);
+
+ ctx->tcp_sock = sk;
+ WRITE_ONCE(ctx->local_id, -1);
+@@ -1927,7 +1931,7 @@ static int subflow_ulp_init(struct sock *sk)
+ goto out;
+ }
+
+- pr_debug("subflow=%p, family=%d", ctx, sk->sk_family);
++ pr_debug("subflow=%p, family=%d\n", ctx, sk->sk_family);
+
+ tp->is_mptcp = 1;
+ ctx->icsk_af_ops = icsk->icsk_af_ops;
+diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c
+index 2389747256793..19a49af5a9e52 100644
+--- a/net/sched/sch_fq.c
++++ b/net/sched/sch_fq.c
+@@ -663,7 +663,9 @@ static struct sk_buff *fq_dequeue(struct Qdisc *sch)
+ pband = &q->band_flows[q->band_nr];
+ pband->credit = min(pband->credit + pband->quantum,
+ pband->quantum);
+- goto begin;
++ if (pband->credit > 0)
++ goto begin;
++ retry = 0;
+ }
+ if (q->time_next_delayed_flow != ~0ULL)
+ qdisc_watchdog_schedule_range_ns(&q->watchdog,
+diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c
+index 5adf0c0a6c1ac..7d315a18612ba 100644
+--- a/net/sctp/sm_statefuns.c
++++ b/net/sctp/sm_statefuns.c
+@@ -2260,12 +2260,6 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
+ }
+ }
+
+- /* Update socket peer label if first association. */
+- if (security_sctp_assoc_request(new_asoc, chunk->head_skb ?: chunk->skb)) {
+- sctp_association_free(new_asoc);
+- return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
+- }
+-
+ /* Set temp so that it won't be added into hashtable */
+ new_asoc->temp = 1;
+
+@@ -2274,6 +2268,22 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook(
+ */
+ action = sctp_tietags_compare(new_asoc, asoc);
+
++ /* In cases C and E the association doesn't enter the ESTABLISHED
++ * state, so there is no need to call security_sctp_assoc_request().
++ */
++ switch (action) {
++ case 'A': /* Association restart. */
++ case 'B': /* Collision case B. */
++ case 'D': /* Collision case D. */
++ /* Update socket peer label if first association. */
++ if (security_sctp_assoc_request((struct sctp_association *)asoc,
++ chunk->head_skb ?: chunk->skb)) {
++ sctp_association_free(new_asoc);
++ return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands);
++ }
++ break;
++ }
++
+ switch (action) {
+ case 'A': /* Association restart. */
+ retval = sctp_sf_do_dupcook_a(net, ep, asoc, chunk, commands,
+diff --git a/security/apparmor/policy_unpack_test.c b/security/apparmor/policy_unpack_test.c
+index 5c9bde25e56df..2b8003eb4f463 100644
+--- a/security/apparmor/policy_unpack_test.c
++++ b/security/apparmor/policy_unpack_test.c
+@@ -80,14 +80,14 @@ static struct aa_ext *build_aa_ext_struct(struct policy_unpack_fixture *puf,
+ *(buf + 1) = strlen(TEST_U32_NAME) + 1;
+ strscpy(buf + 3, TEST_U32_NAME, e->end - (void *)(buf + 3));
+ *(buf + 3 + strlen(TEST_U32_NAME) + 1) = AA_U32;
+- *((u32 *)(buf + 3 + strlen(TEST_U32_NAME) + 2)) = TEST_U32_DATA;
++ *((__le32 *)(buf + 3 + strlen(TEST_U32_NAME) + 2)) = cpu_to_le32(TEST_U32_DATA);
+
+ buf = e->start + TEST_NAMED_U64_BUF_OFFSET;
+ *buf = AA_NAME;
+ *(buf + 1) = strlen(TEST_U64_NAME) + 1;
+ strscpy(buf + 3, TEST_U64_NAME, e->end - (void *)(buf + 3));
+ *(buf + 3 + strlen(TEST_U64_NAME) + 1) = AA_U64;
+- *((u64 *)(buf + 3 + strlen(TEST_U64_NAME) + 2)) = TEST_U64_DATA;
++ *((__le64 *)(buf + 3 + strlen(TEST_U64_NAME) + 2)) = cpu_to_le64(TEST_U64_DATA);
+
+ buf = e->start + TEST_NAMED_BLOB_BUF_OFFSET;
+ *buf = AA_NAME;
+@@ -103,7 +103,7 @@ static struct aa_ext *build_aa_ext_struct(struct policy_unpack_fixture *puf,
+ *(buf + 1) = strlen(TEST_ARRAY_NAME) + 1;
+ strscpy(buf + 3, TEST_ARRAY_NAME, e->end - (void *)(buf + 3));
+ *(buf + 3 + strlen(TEST_ARRAY_NAME) + 1) = AA_ARRAY;
+- *((u16 *)(buf + 3 + strlen(TEST_ARRAY_NAME) + 2)) = TEST_ARRAY_SIZE;
++ *((__le16 *)(buf + 3 + strlen(TEST_ARRAY_NAME) + 2)) = cpu_to_le16(TEST_ARRAY_SIZE);
+
+ return e;
+ }
+diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
+index bfa61e005aace..400eca4ad0fb6 100644
+--- a/security/selinux/hooks.c
++++ b/security/selinux/hooks.c
+@@ -6660,8 +6660,8 @@ static int selinux_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen
+ */
+ static int selinux_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
+ {
+- return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX,
+- ctx, ctxlen, 0);
++ return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SELINUX,
++ ctx, ctxlen, 0, NULL);
+ }
+
+ static int selinux_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
+diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
+index c1fe422cfbe19..081129be5b62c 100644
+--- a/security/smack/smack_lsm.c
++++ b/security/smack/smack_lsm.c
+@@ -4874,8 +4874,8 @@ static int smack_inode_notifysecctx(struct inode *inode, void *ctx, u32 ctxlen)
+
+ static int smack_inode_setsecctx(struct dentry *dentry, void *ctx, u32 ctxlen)
+ {
+- return __vfs_setxattr_noperm(&nop_mnt_idmap, dentry, XATTR_NAME_SMACK,
+- ctx, ctxlen, 0);
++ return __vfs_setxattr_locked(&nop_mnt_idmap, dentry, XATTR_NAME_SMACK,
++ ctx, ctxlen, 0, NULL);
+ }
+
+ static int smack_inode_getsecctx(struct inode *inode, void **ctx, u32 *ctxlen)
+diff --git a/sound/core/seq/seq_clientmgr.c b/sound/core/seq/seq_clientmgr.c
+index 42a7051410501..e115fe1836349 100644
+--- a/sound/core/seq/seq_clientmgr.c
++++ b/sound/core/seq/seq_clientmgr.c
+@@ -537,6 +537,9 @@ static struct snd_seq_client *get_event_dest_client(struct snd_seq_event *event,
+ return NULL;
+ if (! dest->accept_input)
+ goto __not_avail;
++ if (snd_seq_ev_is_ump(event))
++ return dest; /* ok - no filter checks */
++
+ if ((dest->filter & SNDRV_SEQ_FILTER_USE_EVENT) &&
+ ! test_bit(event->type, dest->event_filter))
+ goto __not_avail;
+diff --git a/sound/pci/hda/cs35l56_hda.c b/sound/pci/hda/cs35l56_hda.c
+index e134ede6c5aa5..357fd59aa49e4 100644
+--- a/sound/pci/hda/cs35l56_hda.c
++++ b/sound/pci/hda/cs35l56_hda.c
+@@ -980,7 +980,7 @@ int cs35l56_hda_common_probe(struct cs35l56_hda *cs35l56, int hid, int id)
+ goto err;
+ }
+
+- cs35l56->base.cal_index = cs35l56->index;
++ cs35l56->base.cal_index = -1;
+
+ cs35l56_init_cs_dsp(&cs35l56->base, &cs35l56->cs_dsp);
+ cs35l56->cs_dsp.client_ops = &cs35l56_hda_client_ops;
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index c9d76bca99232..1a7b7e790fca9 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -10221,6 +10221,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x103c, 0x8c15, "HP Spectre x360 2-in-1 Laptop 14-eu0xxx", ALC245_FIXUP_HP_SPECTRE_X360_EU0XXX),
+ SND_PCI_QUIRK(0x103c, 0x8c16, "HP Spectre 16", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8c17, "HP Spectre 16", ALC287_FIXUP_CS35L41_I2C_2),
++ SND_PCI_QUIRK(0x103c, 0x8c21, "HP Pavilion Plus Laptop 14-ey0XXX", ALC245_FIXUP_HP_X360_MUTE_LEDS),
+ SND_PCI_QUIRK(0x103c, 0x8c46, "HP EliteBook 830 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8c47, "HP EliteBook 840 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8c48, "HP EliteBook 860 G11", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+@@ -10259,6 +10260,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x103c, 0x8ca2, "HP ZBook Power", ALC236_FIXUP_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8ca4, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
+ SND_PCI_QUIRK(0x103c, 0x8ca7, "HP ZBook Fury", ALC245_FIXUP_CS35L41_SPI_2_HP_GPIO_LED),
++ SND_PCI_QUIRK(0x103c, 0x8cbd, "HP Pavilion Aero Laptop 13-bg0xxx", ALC245_FIXUP_HP_X360_MUTE_LEDS),
+ SND_PCI_QUIRK(0x103c, 0x8cdd, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8cde, "HP Spectre", ALC287_FIXUP_CS35L41_I2C_2),
+ SND_PCI_QUIRK(0x103c, 0x8cdf, "HP SnowWhite", ALC287_FIXUP_CS35L41_I2C_2_HP_GPIO_LED),
+diff --git a/sound/soc/amd/acp/acp-legacy-mach.c b/sound/soc/amd/acp/acp-legacy-mach.c
+index 47c3b5f167f59..0d529e32e552b 100644
+--- a/sound/soc/amd/acp/acp-legacy-mach.c
++++ b/sound/soc/amd/acp/acp-legacy-mach.c
+@@ -227,6 +227,8 @@ static const struct platform_device_id board_ids[] = {
+ },
+ { }
+ };
++MODULE_DEVICE_TABLE(platform, board_ids);
++
+ static struct platform_driver acp_asoc_audio = {
+ .driver = {
+ .pm = &snd_soc_pm_ops,
+diff --git a/sound/soc/codecs/cs-amp-lib-test.c b/sound/soc/codecs/cs-amp-lib-test.c
+index 15f991b2e16e2..8169ec88a8ba8 100644
+--- a/sound/soc/codecs/cs-amp-lib-test.c
++++ b/sound/soc/codecs/cs-amp-lib-test.c
+@@ -38,6 +38,7 @@ static void cs_amp_lib_test_init_dummy_cal_blob(struct kunit *test, int num_amps
+ {
+ struct cs_amp_lib_test_priv *priv = test->priv;
+ unsigned int blob_size;
++ int i;
+
+ blob_size = offsetof(struct cirrus_amp_efi_data, data) +
+ sizeof(struct cirrus_amp_cal_data) * num_amps;
+@@ -49,6 +50,14 @@ static void cs_amp_lib_test_init_dummy_cal_blob(struct kunit *test, int num_amps
+ priv->cal_blob->count = num_amps;
+
+ get_random_bytes(priv->cal_blob->data, sizeof(struct cirrus_amp_cal_data) * num_amps);
++
++ /* Ensure all timestamps are non-zero to mark the entry valid. */
++ for (i = 0; i < num_amps; i++)
++ priv->cal_blob->data[i].calTime[0] |= 1;
++
++ /* Ensure that all UIDs are non-zero and unique. */
++ for (i = 0; i < num_amps; i++)
++ *(u8 *)&priv->cal_blob->data[i].calTarget[0] = i + 1;
+ }
+
+ static u64 cs_amp_lib_test_get_target_uid(struct kunit *test)
+diff --git a/sound/soc/codecs/cs-amp-lib.c b/sound/soc/codecs/cs-amp-lib.c
+index 605964af8afad..51b128c806718 100644
+--- a/sound/soc/codecs/cs-amp-lib.c
++++ b/sound/soc/codecs/cs-amp-lib.c
+@@ -182,6 +182,10 @@ static int _cs_amp_get_efi_calibration_data(struct device *dev, u64 target_uid,
+ for (i = 0; i < efi_data->count; ++i) {
+ u64 cal_target = cs_amp_cal_target_u64(&efi_data->data[i]);
+
++ /* Skip empty entries */
++ if (!efi_data->data[i].calTime[0] && !efi_data->data[i].calTime[1])
++ continue;
++
+ /* Skip entries with unpopulated silicon ID */
+ if (cal_target == 0)
+ continue;
+@@ -193,7 +197,8 @@ static int _cs_amp_get_efi_calibration_data(struct device *dev, u64 target_uid,
+ }
+ }
+
+- if (!cal && (amp_index >= 0) && (amp_index < efi_data->count)) {
++ if (!cal && (amp_index >= 0) && (amp_index < efi_data->count) &&
++ (efi_data->data[amp_index].calTime[0] || efi_data->data[amp_index].calTime[1])) {
+ u64 cal_target = cs_amp_cal_target_u64(&efi_data->data[amp_index]);
+
+ /*
+diff --git a/sound/soc/sof/amd/acp-dsp-offset.h b/sound/soc/sof/amd/acp-dsp-offset.h
+index 59afbe2e0f420..072b703f9b3f3 100644
+--- a/sound/soc/sof/amd/acp-dsp-offset.h
++++ b/sound/soc/sof/amd/acp-dsp-offset.h
+@@ -76,13 +76,15 @@
+ #define DSP_SW_INTR_CNTL_OFFSET 0x0
+ #define DSP_SW_INTR_STAT_OFFSET 0x4
+ #define DSP_SW_INTR_TRIG_OFFSET 0x8
+-#define ACP_ERROR_STATUS 0x18C4
++#define ACP3X_ERROR_STATUS 0x18C4
++#define ACP6X_ERROR_STATUS 0x1A4C
+ #define ACP3X_AXI2DAGB_SEM_0 0x1880
+ #define ACP5X_AXI2DAGB_SEM_0 0x1884
+ #define ACP6X_AXI2DAGB_SEM_0 0x1874
+
+ /* ACP common registers to report errors related to I2S & SoundWire interfaces */
+-#define ACP_SW0_I2S_ERROR_REASON 0x18B4
++#define ACP3X_SW_I2S_ERROR_REASON 0x18C8
++#define ACP6X_SW0_I2S_ERROR_REASON 0x18B4
+ #define ACP_SW1_I2S_ERROR_REASON 0x1A50
+
+ /* Registers from ACP_SHA block */
+diff --git a/sound/soc/sof/amd/acp.c b/sound/soc/sof/amd/acp.c
+index 74fd5f2b148b8..85b58c8ccd0da 100644
+--- a/sound/soc/sof/amd/acp.c
++++ b/sound/soc/sof/amd/acp.c
+@@ -92,6 +92,7 @@ static int config_dma_channel(struct acp_dev_data *adata, unsigned int ch,
+ unsigned int idx, unsigned int dscr_count)
+ {
+ struct snd_sof_dev *sdev = adata->dev;
++ const struct sof_amd_acp_desc *desc = get_chip_info(sdev->pdata);
+ unsigned int val, status;
+ int ret;
+
+@@ -102,7 +103,7 @@ static int config_dma_channel(struct acp_dev_data *adata, unsigned int ch,
+ val & (1 << ch), ACP_REG_POLL_INTERVAL,
+ ACP_REG_POLL_TIMEOUT_US);
+ if (ret < 0) {
+- status = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_ERROR_STATUS);
++ status = snd_sof_dsp_read(sdev, ACP_DSP_BAR, desc->acp_error_stat);
+ val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, ACP_DMA_ERR_STS_0 + ch * sizeof(u32));
+
+ dev_err(sdev->dev, "ACP_DMA_ERR_STS :0x%x ACP_ERROR_STATUS :0x%x\n", val, status);
+@@ -263,6 +264,17 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr,
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_STRT_ADDR, start_addr);
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_DESTINATION_ADDR, dest_addr);
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_MSG_LENGTH, image_length);
++
++ /* psp_send_cmd only required for vangogh platform (rev - 5) */
++ if (desc->rev == 5 && !(adata->quirks && adata->quirks->skip_iram_dram_size_mod)) {
++ /* Modify IRAM and DRAM size */
++ ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | IRAM_DRAM_FENCE_2);
++ if (ret)
++ return ret;
++ ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | MBOX_ISREADY_FLAG);
++ if (ret)
++ return ret;
++ }
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SHA_DMA_CMD, ACP_SHA_RUN);
+
+ ret = snd_sof_dsp_read_poll_timeout(sdev, ACP_DSP_BAR, ACP_SHA_TRANSFER_BYTE_CNT,
+@@ -280,17 +292,6 @@ int configure_and_run_sha_dma(struct acp_dev_data *adata, void *image_addr,
+ return ret;
+ }
+
+- /* psp_send_cmd only required for vangogh platform (rev - 5) */
+- if (desc->rev == 5 && !(adata->quirks && adata->quirks->skip_iram_dram_size_mod)) {
+- /* Modify IRAM and DRAM size */
+- ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | IRAM_DRAM_FENCE_2);
+- if (ret)
+- return ret;
+- ret = psp_send_cmd(adata, MBOX_ACP_IRAM_DRAM_FENCE_COMMAND | MBOX_ISREADY_FLAG);
+- if (ret)
+- return ret;
+- }
+-
+ ret = snd_sof_dsp_read_poll_timeout(sdev, ACP_DSP_BAR, ACP_SHA_DSP_FW_QUALIFIER,
+ fw_qualifier, fw_qualifier & DSP_FW_RUN_ENABLE,
+ ACP_REG_POLL_INTERVAL, ACP_DMA_COMPLETE_TIMEOUT_US);
+@@ -402,9 +403,11 @@ static irqreturn_t acp_irq_handler(int irq, void *dev_id)
+
+ if (val & ACP_ERROR_IRQ_MASK) {
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->ext_intr_stat, ACP_ERROR_IRQ_MASK);
+- snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + ACP_SW0_I2S_ERROR_REASON, 0);
+- snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + ACP_SW1_I2S_ERROR_REASON, 0);
+- snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + ACP_ERROR_STATUS, 0);
++ snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->acp_sw0_i2s_err_reason, 0);
++ /* ACP_SW1_I2S_ERROR_REASON is newly added register from rmb platform onwards */
++ if (desc->rev >= 6)
++ snd_sof_dsp_write(sdev, ACP_DSP_BAR, ACP_SW1_I2S_ERROR_REASON, 0);
++ snd_sof_dsp_write(sdev, ACP_DSP_BAR, desc->acp_error_stat, 0);
+ irq_flag = 1;
+ }
+
+@@ -430,6 +433,7 @@ static int acp_power_on(struct snd_sof_dev *sdev)
+ const struct sof_amd_acp_desc *desc = get_chip_info(sdev->pdata);
+ unsigned int base = desc->pgfsm_base;
+ unsigned int val;
++ unsigned int acp_pgfsm_status_mask, acp_pgfsm_cntl_mask;
+ int ret;
+
+ val = snd_sof_dsp_read(sdev, ACP_DSP_BAR, base + PGFSM_STATUS_OFFSET);
+@@ -437,9 +441,23 @@ static int acp_power_on(struct snd_sof_dev *sdev)
+ if (val == ACP_POWERED_ON)
+ return 0;
+
+- if (val & ACP_PGFSM_STATUS_MASK)
++ switch (desc->rev) {
++ case 3:
++ case 5:
++ acp_pgfsm_status_mask = ACP3X_PGFSM_STATUS_MASK;
++ acp_pgfsm_cntl_mask = ACP3X_PGFSM_CNTL_POWER_ON_MASK;
++ break;
++ case 6:
++ acp_pgfsm_status_mask = ACP6X_PGFSM_STATUS_MASK;
++ acp_pgfsm_cntl_mask = ACP6X_PGFSM_CNTL_POWER_ON_MASK;
++ break;
++ default:
++ return -EINVAL;
++ }
++
++ if (val & acp_pgfsm_status_mask)
+ snd_sof_dsp_write(sdev, ACP_DSP_BAR, base + PGFSM_CONTROL_OFFSET,
+- ACP_PGFSM_CNTL_POWER_ON_MASK);
++ acp_pgfsm_cntl_mask);
+
+ ret = snd_sof_dsp_read_poll_timeout(sdev, ACP_DSP_BAR, base + PGFSM_STATUS_OFFSET, val,
+ !val, ACP_REG_POLL_INTERVAL, ACP_REG_POLL_TIMEOUT_US);
+diff --git a/sound/soc/sof/amd/acp.h b/sound/soc/sof/amd/acp.h
+index 87e79d500865a..61b28df8c9081 100644
+--- a/sound/soc/sof/amd/acp.h
++++ b/sound/soc/sof/amd/acp.h
+@@ -25,8 +25,11 @@
+ #define ACP_REG_POLL_TIMEOUT_US 2000
+ #define ACP_DMA_COMPLETE_TIMEOUT_US 5000
+
+-#define ACP_PGFSM_CNTL_POWER_ON_MASK 0x01
+-#define ACP_PGFSM_STATUS_MASK 0x03
++#define ACP3X_PGFSM_CNTL_POWER_ON_MASK 0x01
++#define ACP3X_PGFSM_STATUS_MASK 0x03
++#define ACP6X_PGFSM_CNTL_POWER_ON_MASK 0x07
++#define ACP6X_PGFSM_STATUS_MASK 0x0F
++
+ #define ACP_POWERED_ON 0x00
+ #define ACP_ASSERT_RESET 0x01
+ #define ACP_RELEASE_RESET 0x00
+@@ -203,6 +206,8 @@ struct sof_amd_acp_desc {
+ u32 probe_reg_offset;
+ u32 reg_start_addr;
+ u32 reg_end_addr;
++ u32 acp_error_stat;
++ u32 acp_sw0_i2s_err_reason;
+ u32 sdw_max_link_count;
+ u64 sdw_acpi_dev_addr;
+ };
+diff --git a/sound/soc/sof/amd/pci-acp63.c b/sound/soc/sof/amd/pci-acp63.c
+index fc89844473657..986f5928caedd 100644
+--- a/sound/soc/sof/amd/pci-acp63.c
++++ b/sound/soc/sof/amd/pci-acp63.c
+@@ -35,6 +35,8 @@ static const struct sof_amd_acp_desc acp63_chip_info = {
+ .ext_intr_cntl = ACP6X_EXTERNAL_INTR_CNTL,
+ .ext_intr_stat = ACP6X_EXT_INTR_STAT,
+ .ext_intr_stat1 = ACP6X_EXT_INTR_STAT1,
++ .acp_error_stat = ACP6X_ERROR_STATUS,
++ .acp_sw0_i2s_err_reason = ACP6X_SW0_I2S_ERROR_REASON,
+ .dsp_intr_base = ACP6X_DSP_SW_INTR_BASE,
+ .sram_pte_offset = ACP6X_SRAM_PTE_OFFSET,
+ .hw_semaphore_offset = ACP6X_AXI2DAGB_SEM_0,
+diff --git a/sound/soc/sof/amd/pci-rmb.c b/sound/soc/sof/amd/pci-rmb.c
+index 4bc30951f8b0d..a366f904e6f31 100644
+--- a/sound/soc/sof/amd/pci-rmb.c
++++ b/sound/soc/sof/amd/pci-rmb.c
+@@ -33,6 +33,8 @@ static const struct sof_amd_acp_desc rembrandt_chip_info = {
+ .pgfsm_base = ACP6X_PGFSM_BASE,
+ .ext_intr_stat = ACP6X_EXT_INTR_STAT,
+ .dsp_intr_base = ACP6X_DSP_SW_INTR_BASE,
++ .acp_error_stat = ACP6X_ERROR_STATUS,
++ .acp_sw0_i2s_err_reason = ACP6X_SW0_I2S_ERROR_REASON,
+ .sram_pte_offset = ACP6X_SRAM_PTE_OFFSET,
+ .hw_semaphore_offset = ACP6X_AXI2DAGB_SEM_0,
+ .fusion_dsp_offset = ACP6X_DSP_FUSION_RUNSTALL,
+diff --git a/sound/soc/sof/amd/pci-rn.c b/sound/soc/sof/amd/pci-rn.c
+index e08875bdfa8b1..2b7c53470ce82 100644
+--- a/sound/soc/sof/amd/pci-rn.c
++++ b/sound/soc/sof/amd/pci-rn.c
+@@ -33,6 +33,8 @@ static const struct sof_amd_acp_desc renoir_chip_info = {
+ .pgfsm_base = ACP3X_PGFSM_BASE,
+ .ext_intr_stat = ACP3X_EXT_INTR_STAT,
+ .dsp_intr_base = ACP3X_DSP_SW_INTR_BASE,
++ .acp_error_stat = ACP3X_ERROR_STATUS,
++ .acp_sw0_i2s_err_reason = ACP3X_SW_I2S_ERROR_REASON,
+ .sram_pte_offset = ACP3X_SRAM_PTE_OFFSET,
+ .hw_semaphore_offset = ACP3X_AXI2DAGB_SEM_0,
+ .acp_clkmux_sel = ACP3X_CLKMUX_SEL,
+diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
+index 5f7d5a5ba89b0..d79bd5fc08db5 100644
+--- a/tools/testing/selftests/iommu/iommufd.c
++++ b/tools/testing/selftests/iommu/iommufd.c
+@@ -803,7 +803,7 @@ TEST_F(iommufd_ioas, copy_area)
+ {
+ struct iommu_ioas_copy copy_cmd = {
+ .size = sizeof(copy_cmd),
+- .flags = IOMMU_IOAS_MAP_FIXED_IOVA,
++ .flags = IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE,
+ .dst_ioas_id = self->ioas_id,
+ .src_ioas_id = self->ioas_id,
+ .length = PAGE_SIZE,
+@@ -1296,7 +1296,7 @@ TEST_F(iommufd_ioas, copy_sweep)
+ {
+ struct iommu_ioas_copy copy_cmd = {
+ .size = sizeof(copy_cmd),
+- .flags = IOMMU_IOAS_MAP_FIXED_IOVA,
++ .flags = IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE,
+ .src_ioas_id = self->ioas_id,
+ .dst_iova = MOCK_APERTURE_START,
+ .length = MOCK_PAGE_SIZE,
+@@ -1586,7 +1586,7 @@ TEST_F(iommufd_mock_domain, user_copy)
+ };
+ struct iommu_ioas_copy copy_cmd = {
+ .size = sizeof(copy_cmd),
+- .flags = IOMMU_IOAS_MAP_FIXED_IOVA,
++ .flags = IOMMU_IOAS_MAP_FIXED_IOVA | IOMMU_IOAS_MAP_WRITEABLE,
+ .dst_ioas_id = self->ioas_id,
+ .dst_iova = MOCK_APERTURE_START,
+ .length = BUFFER_SIZE,
+diff --git a/tools/testing/selftests/net/forwarding/local_termination.sh b/tools/testing/selftests/net/forwarding/local_termination.sh
+index 4b364cdf3ef0c..656b1a82d1dca 100755
+--- a/tools/testing/selftests/net/forwarding/local_termination.sh
++++ b/tools/testing/selftests/net/forwarding/local_termination.sh
+@@ -284,6 +284,10 @@ bridge()
+ cleanup()
+ {
+ pre_cleanup
++
++ ip link set $h2 down
++ ip link set $h1 down
++
+ vrf_cleanup
+ }
+
+diff --git a/tools/testing/selftests/net/forwarding/no_forwarding.sh b/tools/testing/selftests/net/forwarding/no_forwarding.sh
+index af3b398d13f01..9e677aa64a06a 100755
+--- a/tools/testing/selftests/net/forwarding/no_forwarding.sh
++++ b/tools/testing/selftests/net/forwarding/no_forwarding.sh
+@@ -233,6 +233,9 @@ cleanup()
+ {
+ pre_cleanup
+
++ ip link set dev $swp2 down
++ ip link set dev $swp1 down
++
+ h2_destroy
+ h1_destroy
+
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+index ed30c0ed55e7a..c0ba79a8ad6da 100755
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+@@ -1112,26 +1112,26 @@ chk_csum_nr()
+
+ print_check "sum"
+ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtDataCsumErr")
+- if [ "$count" != "$csum_ns1" ]; then
++ if [ -n "$count" ] && [ "$count" != "$csum_ns1" ]; then
+ extra_msg+=" ns1=$count"
+ fi
+ if [ -z "$count" ]; then
+ print_skip
+ elif { [ "$count" != $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 0 ]; } ||
+- { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then
++ { [ "$count" -lt $csum_ns1 ] && [ $allow_multi_errors_ns1 -eq 1 ]; }; then
+ fail_test "got $count data checksum error[s] expected $csum_ns1"
+ else
+ print_ok
+ fi
+ print_check "csum"
+ count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtDataCsumErr")
+- if [ "$count" != "$csum_ns2" ]; then
++ if [ -n "$count" ] && [ "$count" != "$csum_ns2" ]; then
+ extra_msg+=" ns2=$count"
+ fi
+ if [ -z "$count" ]; then
+ print_skip
+ elif { [ "$count" != $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 0 ]; } ||
+- { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then
++ { [ "$count" -lt $csum_ns2 ] && [ $allow_multi_errors_ns2 -eq 1 ]; }; then
+ fail_test "got $count data checksum error[s] expected $csum_ns2"
+ else
+ print_ok
+@@ -1169,13 +1169,13 @@ chk_fail_nr()
+
+ print_check "ftx"
+ count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPFailTx")
+- if [ "$count" != "$fail_tx" ]; then
++ if [ -n "$count" ] && [ "$count" != "$fail_tx" ]; then
+ extra_msg+=",tx=$count"
+ fi
+ if [ -z "$count" ]; then
+ print_skip
+ elif { [ "$count" != "$fail_tx" ] && [ $allow_tx_lost -eq 0 ]; } ||
+- { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then
++ { [ "$count" -gt "$fail_tx" ] && [ $allow_tx_lost -eq 1 ]; }; then
+ fail_test "got $count MP_FAIL[s] TX expected $fail_tx"
+ else
+ print_ok
+@@ -1183,13 +1183,13 @@ chk_fail_nr()
+
+ print_check "failrx"
+ count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPFailRx")
+- if [ "$count" != "$fail_rx" ]; then
++ if [ -n "$count" ] && [ "$count" != "$fail_rx" ]; then
+ extra_msg+=",rx=$count"
+ fi
+ if [ -z "$count" ]; then
+ print_skip
+ elif { [ "$count" != "$fail_rx" ] && [ $allow_rx_lost -eq 0 ]; } ||
+- { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then
++ { [ "$count" -gt "$fail_rx" ] && [ $allow_rx_lost -eq 1 ]; }; then
+ fail_test "got $count MP_FAIL[s] RX expected $fail_rx"
+ else
+ print_ok
+@@ -3429,14 +3429,12 @@ userspace_tests()
+ "signal"
+ userspace_pm_chk_get_addr "${ns1}" "10" "id 10 flags signal 10.0.2.1"
+ userspace_pm_chk_get_addr "${ns1}" "20" "id 20 flags signal 10.0.3.1"
+- userspace_pm_rm_addr $ns1 10
+ userspace_pm_rm_sf $ns1 "::ffff:10.0.2.1" $MPTCP_LIB_EVENT_SUB_ESTABLISHED
+ userspace_pm_chk_dump_addr "${ns1}" \
+- "id 20 flags signal 10.0.3.1" "after rm_addr 10"
++ "id 20 flags signal 10.0.3.1" "after rm_sf 10"
+ userspace_pm_rm_addr $ns1 20
+- userspace_pm_rm_sf $ns1 10.0.3.1 $MPTCP_LIB_EVENT_SUB_ESTABLISHED
+ userspace_pm_chk_dump_addr "${ns1}" "" "after rm_addr 20"
+- chk_rm_nr 2 2 invert
++ chk_rm_nr 1 1 invert
+ chk_mptcp_info subflows 0 subflows 0
+ chk_subflows_total 1 1
+ kill_events_pids
+@@ -3460,12 +3458,11 @@ userspace_tests()
+ "id 20 flags subflow 10.0.3.2" \
+ "subflow"
+ userspace_pm_chk_get_addr "${ns2}" "20" "id 20 flags subflow 10.0.3.2"
+- userspace_pm_rm_addr $ns2 20
+ userspace_pm_rm_sf $ns2 10.0.3.2 $MPTCP_LIB_EVENT_SUB_ESTABLISHED
+ userspace_pm_chk_dump_addr "${ns2}" \
+ "" \
+- "after rm_addr 20"
+- chk_rm_nr 1 1
++ "after rm_sf 20"
++ chk_rm_nr 0 1
+ chk_mptcp_info subflows 0 subflows 0
+ chk_subflows_total 1 1
+ kill_events_pids
+@@ -3575,27 +3572,28 @@ endpoint_tests()
+
+ if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT &&
+ mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+- pm_nl_set_limits $ns1 0 2
+- pm_nl_set_limits $ns2 0 2
++ pm_nl_set_limits $ns1 0 3
++ pm_nl_set_limits $ns2 0 3
++ pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
+ pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
+- test_linkfail=4 speed=20 \
++ test_linkfail=4 speed=5 \
+ run_tests $ns1 $ns2 10.0.1.1 &
+ local tests_pid=$!
+
+ wait_mpj $ns2
+ pm_nl_check_endpoint "creation" \
+ $ns2 10.0.2.2 id 2 flags subflow dev ns2eth2
+- chk_subflow_nr "before delete" 2
++ chk_subflow_nr "before delete id 2" 2
+ chk_mptcp_info subflows 1 subflows 1
+
+ pm_nl_del_endpoint $ns2 2 10.0.2.2
+ sleep 0.5
+- chk_subflow_nr "after delete" 1
++ chk_subflow_nr "after delete id 2" 1
+ chk_mptcp_info subflows 0 subflows 0
+
+ pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
+ wait_mpj $ns2
+- chk_subflow_nr "after re-add" 2
++ chk_subflow_nr "after re-add id 2" 2
+ chk_mptcp_info subflows 1 subflows 1
+
+ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
+@@ -3610,10 +3608,23 @@ endpoint_tests()
+ chk_subflow_nr "after no reject" 3
+ chk_mptcp_info subflows 2 subflows 2
+
++ local i
++ for i in $(seq 3); do
++ pm_nl_del_endpoint $ns2 1 10.0.1.2
++ sleep 0.5
++ chk_subflow_nr "after delete id 0 ($i)" 2
++ chk_mptcp_info subflows 2 subflows 2 # only decr for additional sf
++
++ pm_nl_add_endpoint $ns2 10.0.1.2 id 1 dev ns2eth1 flags subflow
++ wait_mpj $ns2
++ chk_subflow_nr "after re-add id 0 ($i)" 3
++ chk_mptcp_info subflows 3 subflows 3
++ done
++
+ mptcp_lib_kill_wait $tests_pid
+
+- chk_join_nr 3 3 3
+- chk_rm_nr 1 1
++ chk_join_nr 6 6 6
++ chk_rm_nr 4 4
+ fi
+ }
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-29 16:48 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-29 16:48 UTC (permalink / raw
To: gentoo-commits
commit: ef27e3d3833a5fc6966eba377d74239c139c169e
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Thu Aug 29 16:48:11 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Thu Aug 29 16:48:11 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=ef27e3d3
Linux patch 6.10.7
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1006_linux-6.10.7.patch | 12217 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 12221 insertions(+)
diff --git a/0000_README b/0000_README
index 75bbf8b4..82c9265b 100644
--- a/0000_README
+++ b/0000_README
@@ -67,6 +67,10 @@ Patch: 1005_linux-6.10.6.patch
From: https://www.kernel.org
Desc: Linux 6.10.6
+Patch: 1006_linux-6.10.7.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.7
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1006_linux-6.10.7.patch b/1006_linux-6.10.7.patch
new file mode 100644
index 00000000..00a04ca2
--- /dev/null
+++ b/1006_linux-6.10.7.patch
@@ -0,0 +1,12217 @@
+diff --git a/Documentation/ABI/testing/sysfs-devices-system-cpu b/Documentation/ABI/testing/sysfs-devices-system-cpu
+index e7e160954e798..0579860b55299 100644
+--- a/Documentation/ABI/testing/sysfs-devices-system-cpu
++++ b/Documentation/ABI/testing/sysfs-devices-system-cpu
+@@ -562,7 +562,8 @@ Description: Control Symmetric Multi Threading (SMT)
+ ================ =========================================
+
+ If control status is "forceoff" or "notsupported" writes
+- are rejected.
++ are rejected. Note that enabling SMT on PowerPC skips
++ offline cores.
+
+ What: /sys/devices/system/cpu/cpuX/power/energy_perf_bias
+ Date: March 2019
+diff --git a/Makefile b/Makefile
+index 361a70264e1fb..ab77d171e268d 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 6
++SUBLEVEL = 7
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+@@ -1986,7 +1986,7 @@ nsdeps: modules
+ quiet_cmd_gen_compile_commands = GEN $@
+ cmd_gen_compile_commands = $(PYTHON3) $< -a $(AR) -o $@ $(filter-out $<, $(real-prereqs))
+
+-$(extmod_prefix)compile_commands.json: scripts/clang-tools/gen_compile_commands.py \
++$(extmod_prefix)compile_commands.json: $(srctree)/scripts/clang-tools/gen_compile_commands.py \
+ $(if $(KBUILD_EXTMOD),, vmlinux.a $(KBUILD_VMLINUX_LIBS)) \
+ $(if $(CONFIG_MODULES), $(MODORDER)) FORCE
+ $(call if_changed,gen_compile_commands)
+diff --git a/arch/arm64/kernel/acpi_numa.c b/arch/arm64/kernel/acpi_numa.c
+index e51535a5f939a..ccbff21ce1faf 100644
+--- a/arch/arm64/kernel/acpi_numa.c
++++ b/arch/arm64/kernel/acpi_numa.c
+@@ -27,7 +27,7 @@
+
+ #include <asm/numa.h>
+
+-static int acpi_early_node_map[NR_CPUS] __initdata = { NUMA_NO_NODE };
++static int acpi_early_node_map[NR_CPUS] __initdata = { [0 ... NR_CPUS - 1] = NUMA_NO_NODE };
+
+ int __init acpi_numa_get_nid(unsigned int cpu)
+ {
+diff --git a/arch/arm64/kernel/setup.c b/arch/arm64/kernel/setup.c
+index a096e2451044d..b22d28ec80284 100644
+--- a/arch/arm64/kernel/setup.c
++++ b/arch/arm64/kernel/setup.c
+@@ -355,9 +355,6 @@ void __init __no_sanitize_address setup_arch(char **cmdline_p)
+ smp_init_cpus();
+ smp_build_mpidr_hash();
+
+- /* Init percpu seeds for random tags after cpus are set up. */
+- kasan_init_sw_tags();
+-
+ #ifdef CONFIG_ARM64_SW_TTBR0_PAN
+ /*
+ * Make sure init_thread_info.ttbr0 always generates translation
+diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
+index 5de85dccc09cd..05688f6a275f1 100644
+--- a/arch/arm64/kernel/smp.c
++++ b/arch/arm64/kernel/smp.c
+@@ -469,6 +469,8 @@ void __init smp_prepare_boot_cpu(void)
+ init_gic_priority_masking();
+
+ kasan_init_hw_tags();
++ /* Init percpu seeds for random tags after cpus are set up. */
++ kasan_init_sw_tags();
+ }
+
+ /*
+diff --git a/arch/arm64/kvm/sys_regs.c b/arch/arm64/kvm/sys_regs.c
+index 22b45a15d0688..33d866ca8f655 100644
+--- a/arch/arm64/kvm/sys_regs.c
++++ b/arch/arm64/kvm/sys_regs.c
+@@ -33,6 +33,7 @@
+ #include <trace/events/kvm.h>
+
+ #include "sys_regs.h"
++#include "vgic/vgic.h"
+
+ #include "trace.h"
+
+@@ -428,6 +429,11 @@ static bool access_gic_sgi(struct kvm_vcpu *vcpu,
+ {
+ bool g1;
+
++ if (!kvm_has_gicv3(vcpu->kvm)) {
++ kvm_inject_undefined(vcpu);
++ return false;
++ }
++
+ if (!p->is_write)
+ return read_from_write_only(vcpu, p, r);
+
+diff --git a/arch/arm64/kvm/vgic/vgic-debug.c b/arch/arm64/kvm/vgic/vgic-debug.c
+index bcbc8c986b1d6..980fbe4fd82cb 100644
+--- a/arch/arm64/kvm/vgic/vgic-debug.c
++++ b/arch/arm64/kvm/vgic/vgic-debug.c
+@@ -84,7 +84,7 @@ static void iter_unmark_lpis(struct kvm *kvm)
+ struct vgic_irq *irq;
+ unsigned long intid;
+
+- xa_for_each(&dist->lpi_xa, intid, irq) {
++ xa_for_each_marked(&dist->lpi_xa, intid, irq, LPI_XA_MARK_DEBUG_ITER) {
+ xa_clear_mark(&dist->lpi_xa, intid, LPI_XA_MARK_DEBUG_ITER);
+ vgic_put_irq(kvm, irq);
+ }
+diff --git a/arch/arm64/kvm/vgic/vgic.h b/arch/arm64/kvm/vgic/vgic.h
+index 03d356a123771..55e3b7108dc9b 100644
+--- a/arch/arm64/kvm/vgic/vgic.h
++++ b/arch/arm64/kvm/vgic/vgic.h
+@@ -346,4 +346,11 @@ void vgic_v4_configure_vsgis(struct kvm *kvm);
+ void vgic_v4_get_vlpi_state(struct vgic_irq *irq, bool *val);
+ int vgic_v4_request_vpe_irq(struct kvm_vcpu *vcpu, int irq);
+
++static inline bool kvm_has_gicv3(struct kvm *kvm)
++{
++ return (static_branch_unlikely(&kvm_vgic_global_state.gicv3_cpuif) &&
++ irqchip_in_kernel(kvm) &&
++ kvm->arch.vgic.vgic_model == KVM_DEV_TYPE_ARM_VGIC_V3);
++}
++
+ #endif
+diff --git a/arch/mips/kernel/cpu-probe.c b/arch/mips/kernel/cpu-probe.c
+index bda7f193baab9..af7412549e6ea 100644
+--- a/arch/mips/kernel/cpu-probe.c
++++ b/arch/mips/kernel/cpu-probe.c
+@@ -1724,12 +1724,16 @@ static inline void cpu_probe_loongson(struct cpuinfo_mips *c, unsigned int cpu)
+ c->ases |= (MIPS_ASE_LOONGSON_MMI | MIPS_ASE_LOONGSON_CAM |
+ MIPS_ASE_LOONGSON_EXT | MIPS_ASE_LOONGSON_EXT2);
+ c->ases &= ~MIPS_ASE_VZ; /* VZ of Loongson-3A2000/3000 is incomplete */
++ change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER,
++ LOONGSON_CONF6_INTIMER);
+ break;
+ case PRID_IMP_LOONGSON_64G:
+ __cpu_name[cpu] = "ICT Loongson-3";
+ set_elf_platform(cpu, "loongson3a");
+ set_isa(c, MIPS_CPU_ISA_M64R2);
+ decode_cpucfg(c);
++ change_c0_config6(LOONGSON_CONF6_EXTIMER | LOONGSON_CONF6_INTIMER,
++ LOONGSON_CONF6_INTIMER);
+ break;
+ default:
+ panic("Unknown Loongson Processor ID!");
+diff --git a/arch/powerpc/include/asm/topology.h b/arch/powerpc/include/asm/topology.h
+index f4e6f2dd04b73..16bacfe8c7a2c 100644
+--- a/arch/powerpc/include/asm/topology.h
++++ b/arch/powerpc/include/asm/topology.h
+@@ -145,6 +145,7 @@ static inline int cpu_to_coregroup_id(int cpu)
+
+ #ifdef CONFIG_HOTPLUG_SMT
+ #include <linux/cpu_smt.h>
++#include <linux/cpumask.h>
+ #include <asm/cputhreads.h>
+
+ static inline bool topology_is_primary_thread(unsigned int cpu)
+@@ -156,6 +157,18 @@ static inline bool topology_smt_thread_allowed(unsigned int cpu)
+ {
+ return cpu_thread_in_core(cpu) < cpu_smt_num_threads;
+ }
++
++#define topology_is_core_online topology_is_core_online
++static inline bool topology_is_core_online(unsigned int cpu)
++{
++ int i, first_cpu = cpu_first_thread_sibling(cpu);
++
++ for (i = first_cpu; i < first_cpu + threads_per_core; ++i) {
++ if (cpu_online(i))
++ return true;
++ }
++ return false;
++}
+ #endif
+
+ #endif /* __KERNEL__ */
+diff --git a/arch/riscv/kernel/traps.c b/arch/riscv/kernel/traps.c
+index 05a16b1f0aee8..51ebfd23e0076 100644
+--- a/arch/riscv/kernel/traps.c
++++ b/arch/riscv/kernel/traps.c
+@@ -319,6 +319,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
+
+ regs->epc += 4;
+ regs->orig_a0 = regs->a0;
++ regs->a0 = -ENOSYS;
+
+ riscv_v_vstate_discard(regs);
+
+@@ -328,8 +329,7 @@ void do_trap_ecall_u(struct pt_regs *regs)
+
+ if (syscall >= 0 && syscall < NR_syscalls)
+ syscall_handler(regs, syscall);
+- else if (syscall != -1)
+- regs->a0 = -ENOSYS;
++
+ /*
+ * Ultimately, this value will get limited by KSTACK_OFFSET_MAX(),
+ * so the maximum stack offset is 1k bytes (10 bits).
+diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
+index 7e25606f858aa..c5c66f53971af 100644
+--- a/arch/riscv/mm/init.c
++++ b/arch/riscv/mm/init.c
+@@ -931,7 +931,7 @@ static void __init create_kernel_page_table(pgd_t *pgdir,
+ PMD_SIZE, PAGE_KERNEL_EXEC);
+
+ /* Map the data in RAM */
+- end_va = kernel_map.virt_addr + XIP_OFFSET + kernel_map.size;
++ end_va = kernel_map.virt_addr + kernel_map.size;
+ for (va = kernel_map.virt_addr + XIP_OFFSET; va < end_va; va += PMD_SIZE)
+ create_pgd_mapping(pgdir, va,
+ kernel_map.phys_addr + (va - (kernel_map.virt_addr + XIP_OFFSET)),
+@@ -1100,7 +1100,7 @@ asmlinkage void __init setup_vm(uintptr_t dtb_pa)
+
+ phys_ram_base = CONFIG_PHYS_RAM_BASE;
+ kernel_map.phys_addr = (uintptr_t)CONFIG_PHYS_RAM_BASE;
+- kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_sdata);
++ kernel_map.size = (uintptr_t)(&_end) - (uintptr_t)(&_start);
+
+ kernel_map.va_kernel_xip_pa_offset = kernel_map.virt_addr - kernel_map.xiprom;
+ #else
+diff --git a/arch/s390/boot/startup.c b/arch/s390/boot/startup.c
+index 5a36d5538dae8..6d88f241dd43a 100644
+--- a/arch/s390/boot/startup.c
++++ b/arch/s390/boot/startup.c
+@@ -161,7 +161,7 @@ static void kaslr_adjust_relocs(unsigned long min_addr, unsigned long max_addr,
+ loc = (long)*reloc + phys_offset;
+ if (loc < min_addr || loc > max_addr)
+ error("64-bit relocation outside of kernel!\n");
+- *(u64 *)loc += offset - __START_KERNEL;
++ *(u64 *)loc += offset;
+ }
+ }
+
+@@ -176,7 +176,7 @@ static void kaslr_adjust_got(unsigned long offset)
+ */
+ for (entry = (u64 *)vmlinux.got_start; entry < (u64 *)vmlinux.got_end; entry++) {
+ if (*entry)
+- *entry += offset - __START_KERNEL;
++ *entry += offset;
+ }
+ }
+
+@@ -251,7 +251,7 @@ static unsigned long setup_kernel_memory_layout(unsigned long kernel_size)
+ vmemmap_size = SECTION_ALIGN_UP(pages) * sizeof(struct page);
+
+ /* choose kernel address space layout: 4 or 3 levels. */
+- BUILD_BUG_ON(!IS_ALIGNED(__START_KERNEL, THREAD_SIZE));
++ BUILD_BUG_ON(!IS_ALIGNED(TEXT_OFFSET, THREAD_SIZE));
+ BUILD_BUG_ON(!IS_ALIGNED(__NO_KASLR_START_KERNEL, THREAD_SIZE));
+ BUILD_BUG_ON(__NO_KASLR_END_KERNEL > _REGION1_SIZE);
+ vsize = get_vmem_size(ident_map_size, vmemmap_size, vmalloc_size, _REGION3_SIZE);
+@@ -378,31 +378,25 @@ static void kaslr_adjust_vmlinux_info(long offset)
+ #endif
+ }
+
+-static void fixup_vmlinux_info(void)
+-{
+- vmlinux.entry -= __START_KERNEL;
+- kaslr_adjust_vmlinux_info(-__START_KERNEL);
+-}
+-
+ void startup_kernel(void)
+ {
+- unsigned long kernel_size = vmlinux.image_size + vmlinux.bss_size;
+- unsigned long nokaslr_offset_phys, kaslr_large_page_offset;
+- unsigned long amode31_lma = 0;
++ unsigned long vmlinux_size = vmlinux.image_size + vmlinux.bss_size;
++ unsigned long nokaslr_text_lma, text_lma = 0, amode31_lma = 0;
++ unsigned long kernel_size = TEXT_OFFSET + vmlinux_size;
++ unsigned long kaslr_large_page_offset;
+ unsigned long max_physmem_end;
+ unsigned long asce_limit;
+ unsigned long safe_addr;
+ psw_t psw;
+
+- fixup_vmlinux_info();
+ setup_lpp();
+
+ /*
+ * Non-randomized kernel physical start address must be _SEGMENT_SIZE
+ * aligned (see blow).
+ */
+- nokaslr_offset_phys = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
+- safe_addr = PAGE_ALIGN(nokaslr_offset_phys + kernel_size);
++ nokaslr_text_lma = ALIGN(mem_safe_offset(), _SEGMENT_SIZE);
++ safe_addr = PAGE_ALIGN(nokaslr_text_lma + vmlinux_size);
+
+ /*
+ * Reserve decompressor memory together with decompression heap,
+@@ -446,16 +440,27 @@ void startup_kernel(void)
+ */
+ kaslr_large_page_offset = __kaslr_offset & ~_SEGMENT_MASK;
+ if (kaslr_enabled()) {
+- unsigned long end = ident_map_size - kaslr_large_page_offset;
++ unsigned long size = vmlinux_size + kaslr_large_page_offset;
+
+- __kaslr_offset_phys = randomize_within_range(kernel_size, _SEGMENT_SIZE, 0, end);
++ text_lma = randomize_within_range(size, _SEGMENT_SIZE, TEXT_OFFSET, ident_map_size);
+ }
+- if (!__kaslr_offset_phys)
+- __kaslr_offset_phys = nokaslr_offset_phys;
+- __kaslr_offset_phys |= kaslr_large_page_offset;
++ if (!text_lma)
++ text_lma = nokaslr_text_lma;
++ text_lma |= kaslr_large_page_offset;
++
++ /*
++ * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region is
++ * never accessed via the kernel image mapping as per the linker script:
++ *
++ * . = TEXT_OFFSET;
++ *
++ * Therefore, this region could be used for something else and does
++ * not need to be reserved. See how it is skipped in setup_vmem().
++ */
++ __kaslr_offset_phys = text_lma - TEXT_OFFSET;
+ kaslr_adjust_vmlinux_info(__kaslr_offset_phys);
+- physmem_reserve(RR_VMLINUX, __kaslr_offset_phys, kernel_size);
+- deploy_kernel((void *)__kaslr_offset_phys);
++ physmem_reserve(RR_VMLINUX, text_lma, vmlinux_size);
++ deploy_kernel((void *)text_lma);
+
+ /* vmlinux decompression is done, shrink reserved low memory */
+ physmem_reserve(RR_DECOMPRESSOR, 0, (unsigned long)_decompressor_end);
+@@ -474,7 +479,7 @@ void startup_kernel(void)
+ if (kaslr_enabled())
+ amode31_lma = randomize_within_range(vmlinux.amode31_size, PAGE_SIZE, 0, SZ_2G);
+ if (!amode31_lma)
+- amode31_lma = __kaslr_offset_phys - vmlinux.amode31_size;
++ amode31_lma = text_lma - vmlinux.amode31_size;
+ physmem_reserve(RR_AMODE31, amode31_lma, vmlinux.amode31_size);
+
+ /*
+@@ -490,8 +495,8 @@ void startup_kernel(void)
+ * - copy_bootdata() must follow setup_vmem() to propagate changes
+ * to bootdata made by setup_vmem()
+ */
+- clear_bss_section(__kaslr_offset_phys);
+- kaslr_adjust_relocs(__kaslr_offset_phys, __kaslr_offset_phys + vmlinux.image_size,
++ clear_bss_section(text_lma);
++ kaslr_adjust_relocs(text_lma, text_lma + vmlinux.image_size,
+ __kaslr_offset, __kaslr_offset_phys);
+ kaslr_adjust_got(__kaslr_offset);
+ setup_vmem(__kaslr_offset, __kaslr_offset + kernel_size, asce_limit);
+diff --git a/arch/s390/boot/vmem.c b/arch/s390/boot/vmem.c
+index 40cfce2687c43..3d4dae9905cd8 100644
+--- a/arch/s390/boot/vmem.c
++++ b/arch/s390/boot/vmem.c
+@@ -89,7 +89,7 @@ static void kasan_populate_shadow(unsigned long kernel_start, unsigned long kern
+ }
+ memgap_start = end;
+ }
+- kasan_populate(kernel_start, kernel_end, POPULATE_KASAN_MAP_SHADOW);
++ kasan_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KASAN_MAP_SHADOW);
+ kasan_populate(0, (unsigned long)__identity_va(0), POPULATE_KASAN_ZERO_SHADOW);
+ kasan_populate(AMODE31_START, AMODE31_END, POPULATE_KASAN_ZERO_SHADOW);
+ if (IS_ENABLED(CONFIG_KASAN_VMALLOC)) {
+@@ -466,7 +466,17 @@ void setup_vmem(unsigned long kernel_start, unsigned long kernel_end, unsigned l
+ (unsigned long)__identity_va(end),
+ POPULATE_IDENTITY);
+ }
+- pgtable_populate(kernel_start, kernel_end, POPULATE_KERNEL);
++
++ /*
++ * [kernel_start..kernel_start + TEXT_OFFSET] region is never
++ * accessed as per the linker script:
++ *
++ * . = TEXT_OFFSET;
++ *
++ * Therefore, skip mapping TEXT_OFFSET bytes to prevent access to
++ * [__kaslr_offset_phys..__kaslr_offset_phys + TEXT_OFFSET] region.
++ */
++ pgtable_populate(kernel_start + TEXT_OFFSET, kernel_end, POPULATE_KERNEL);
+ pgtable_populate(AMODE31_START, AMODE31_END, POPULATE_DIRECT);
+ pgtable_populate(__abs_lowcore, __abs_lowcore + sizeof(struct lowcore),
+ POPULATE_ABS_LOWCORE);
+diff --git a/arch/s390/boot/vmlinux.lds.S b/arch/s390/boot/vmlinux.lds.S
+index a750711d44c86..66670212a3611 100644
+--- a/arch/s390/boot/vmlinux.lds.S
++++ b/arch/s390/boot/vmlinux.lds.S
+@@ -109,7 +109,12 @@ SECTIONS
+ #ifdef CONFIG_KERNEL_UNCOMPRESSED
+ . = ALIGN(PAGE_SIZE);
+ . += AMODE31_SIZE; /* .amode31 section */
+- . = ALIGN(1 << 20); /* _SEGMENT_SIZE */
++
++ /*
++ * Make sure the location counter is not less than TEXT_OFFSET.
++ * _SEGMENT_SIZE is not available, use ALIGN(1 << 20) instead.
++ */
++ . = MAX(TEXT_OFFSET, ALIGN(1 << 20));
+ #else
+ . = ALIGN(8);
+ #endif
+diff --git a/arch/s390/include/asm/page.h b/arch/s390/include/asm/page.h
+index 224ff9d433ead..8cac1a737424d 100644
+--- a/arch/s390/include/asm/page.h
++++ b/arch/s390/include/asm/page.h
+@@ -276,8 +276,9 @@ static inline unsigned long virt_to_pfn(const void *kaddr)
+ #define AMODE31_SIZE (3 * PAGE_SIZE)
+
+ #define KERNEL_IMAGE_SIZE (512 * 1024 * 1024)
+-#define __START_KERNEL 0x100000
+ #define __NO_KASLR_START_KERNEL CONFIG_KERNEL_IMAGE_BASE
+ #define __NO_KASLR_END_KERNEL (__NO_KASLR_START_KERNEL + KERNEL_IMAGE_SIZE)
+
++#define TEXT_OFFSET 0x100000
++
+ #endif /* _S390_PAGE_H */
+diff --git a/arch/s390/include/asm/uv.h b/arch/s390/include/asm/uv.h
+index 0e7bd3873907f..b2e2f9a4163c5 100644
+--- a/arch/s390/include/asm/uv.h
++++ b/arch/s390/include/asm/uv.h
+@@ -442,7 +442,10 @@ static inline int share(unsigned long addr, u16 cmd)
+
+ if (!uv_call(0, (u64)&uvcb))
+ return 0;
+- return -EINVAL;
++ pr_err("%s UVC failed (rc: 0x%x, rrc: 0x%x), possible hypervisor bug.\n",
++ uvcb.header.cmd == UVC_CMD_SET_SHARED_ACCESS ? "Share" : "Unshare",
++ uvcb.header.rc, uvcb.header.rrc);
++ panic("System security cannot be guaranteed unless the system panics now.\n");
+ }
+
+ /*
+diff --git a/arch/s390/kernel/vmlinux.lds.S b/arch/s390/kernel/vmlinux.lds.S
+index a1ce3925ec719..52bd969b28283 100644
+--- a/arch/s390/kernel/vmlinux.lds.S
++++ b/arch/s390/kernel/vmlinux.lds.S
+@@ -39,7 +39,7 @@ PHDRS {
+
+ SECTIONS
+ {
+- . = __START_KERNEL;
++ . = TEXT_OFFSET;
+ .text : {
+ _stext = .; /* Start of text section */
+ _text = .; /* Text and read-only data */
+diff --git a/arch/s390/kvm/kvm-s390.h b/arch/s390/kvm/kvm-s390.h
+index bf8534218af3d..e680c6bf0c9d9 100644
+--- a/arch/s390/kvm/kvm-s390.h
++++ b/arch/s390/kvm/kvm-s390.h
+@@ -267,7 +267,12 @@ static inline unsigned long kvm_s390_get_gfn_end(struct kvm_memslots *slots)
+
+ static inline u32 kvm_s390_get_gisa_desc(struct kvm *kvm)
+ {
+- u32 gd = virt_to_phys(kvm->arch.gisa_int.origin);
++ u32 gd;
++
++ if (!kvm->arch.gisa_int.origin)
++ return 0;
++
++ gd = virt_to_phys(kvm->arch.gisa_int.origin);
+
+ if (gd && sclp.has_gisaf)
+ gd |= GISA_FORMAT1;
+diff --git a/arch/s390/tools/relocs.c b/arch/s390/tools/relocs.c
+index a74dbd5c9896a..30a732c808f35 100644
+--- a/arch/s390/tools/relocs.c
++++ b/arch/s390/tools/relocs.c
+@@ -280,7 +280,7 @@ static int do_reloc(struct section *sec, Elf_Rel *rel)
+ case R_390_GOTOFF64:
+ break;
+ case R_390_64:
+- add_reloc(&relocs64, offset - ehdr.e_entry);
++ add_reloc(&relocs64, offset);
+ break;
+ default:
+ die("Unsupported relocation type: %d\n", r_type);
+diff --git a/block/blk-mq-tag.c b/block/blk-mq-tag.c
+index cc57e2dd9a0bb..2cafcf11ee8be 100644
+--- a/block/blk-mq-tag.c
++++ b/block/blk-mq-tag.c
+@@ -38,6 +38,7 @@ static void blk_mq_update_wake_batch(struct blk_mq_tags *tags,
+ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
+ {
+ unsigned int users;
++ unsigned long flags;
+ struct blk_mq_tags *tags = hctx->tags;
+
+ /*
+@@ -56,11 +57,11 @@ void __blk_mq_tag_busy(struct blk_mq_hw_ctx *hctx)
+ return;
+ }
+
+- spin_lock_irq(&tags->lock);
++ spin_lock_irqsave(&tags->lock, flags);
+ users = tags->active_queues + 1;
+ WRITE_ONCE(tags->active_queues, users);
+ blk_mq_update_wake_batch(tags, users);
+- spin_unlock_irq(&tags->lock);
++ spin_unlock_irqrestore(&tags->lock, flags);
+ }
+
+ /*
+diff --git a/drivers/acpi/acpica/acevents.h b/drivers/acpi/acpica/acevents.h
+index 2133085deda77..1c5218b79fc2a 100644
+--- a/drivers/acpi/acpica/acevents.h
++++ b/drivers/acpi/acpica/acevents.h
+@@ -188,13 +188,9 @@ acpi_ev_detach_region(union acpi_operand_object *region_obj,
+ u8 acpi_ns_is_locked);
+
+ void
+-acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
++acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth,
+ acpi_adr_space_type space_id, u32 function);
+
+-void
+-acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *node,
+- acpi_adr_space_type space_id);
+-
+ acpi_status
+ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function);
+
+diff --git a/drivers/acpi/acpica/evregion.c b/drivers/acpi/acpica/evregion.c
+index dc6004daf624b..cf53b9535f18e 100644
+--- a/drivers/acpi/acpica/evregion.c
++++ b/drivers/acpi/acpica/evregion.c
+@@ -20,6 +20,10 @@ extern u8 acpi_gbl_default_address_spaces[];
+
+ /* Local prototypes */
+
++static void
++acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node,
++ acpi_adr_space_type space_id);
++
+ static acpi_status
+ acpi_ev_reg_run(acpi_handle obj_handle,
+ u32 level, void *context, void **return_value);
+@@ -61,6 +65,7 @@ acpi_status acpi_ev_initialize_op_regions(void)
+ acpi_gbl_default_address_spaces
+ [i])) {
+ acpi_ev_execute_reg_methods(acpi_gbl_root_node,
++ ACPI_UINT32_MAX,
+ acpi_gbl_default_address_spaces
+ [i], ACPI_REG_CONNECT);
+ }
+@@ -668,6 +673,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function)
+ * FUNCTION: acpi_ev_execute_reg_methods
+ *
+ * PARAMETERS: node - Namespace node for the device
++ * max_depth - Depth to which search for _REG
+ * space_id - The address space ID
+ * function - Passed to _REG: On (1) or Off (0)
+ *
+@@ -679,7 +685,7 @@ acpi_ev_execute_reg_method(union acpi_operand_object *region_obj, u32 function)
+ ******************************************************************************/
+
+ void
+-acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
++acpi_ev_execute_reg_methods(struct acpi_namespace_node *node, u32 max_depth,
+ acpi_adr_space_type space_id, u32 function)
+ {
+ struct acpi_reg_walk_info info;
+@@ -713,7 +719,7 @@ acpi_ev_execute_reg_methods(struct acpi_namespace_node *node,
+ * regions and _REG methods. (i.e. handlers must be installed for all
+ * regions of this Space ID before we can run any _REG methods)
+ */
+- (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, ACPI_UINT32_MAX,
++ (void)acpi_ns_walk_namespace(ACPI_TYPE_ANY, node, max_depth,
+ ACPI_NS_WALK_UNLOCK, acpi_ev_reg_run, NULL,
+ &info, NULL);
+
+@@ -814,7 +820,7 @@ acpi_ev_reg_run(acpi_handle obj_handle,
+ *
+ ******************************************************************************/
+
+-void
++static void
+ acpi_ev_execute_orphan_reg_method(struct acpi_namespace_node *device_node,
+ acpi_adr_space_type space_id)
+ {
+diff --git a/drivers/acpi/acpica/evxfregn.c b/drivers/acpi/acpica/evxfregn.c
+index 624361a5f34d8..95f78383bbdba 100644
+--- a/drivers/acpi/acpica/evxfregn.c
++++ b/drivers/acpi/acpica/evxfregn.c
+@@ -85,7 +85,8 @@ acpi_install_address_space_handler_internal(acpi_handle device,
+ /* Run all _REG methods for this address space */
+
+ if (run_reg) {
+- acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT);
++ acpi_ev_execute_reg_methods(node, ACPI_UINT32_MAX, space_id,
++ ACPI_REG_CONNECT);
+ }
+
+ unlock_and_exit:
+@@ -263,6 +264,7 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler)
+ * FUNCTION: acpi_execute_reg_methods
+ *
+ * PARAMETERS: device - Handle for the device
++ * max_depth - Depth to which search for _REG
+ * space_id - The address space ID
+ *
+ * RETURN: Status
+@@ -271,7 +273,8 @@ ACPI_EXPORT_SYMBOL(acpi_remove_address_space_handler)
+ *
+ ******************************************************************************/
+ acpi_status
+-acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
++acpi_execute_reg_methods(acpi_handle device, u32 max_depth,
++ acpi_adr_space_type space_id)
+ {
+ struct acpi_namespace_node *node;
+ acpi_status status;
+@@ -296,7 +299,8 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
+
+ /* Run all _REG methods for this address space */
+
+- acpi_ev_execute_reg_methods(node, space_id, ACPI_REG_CONNECT);
++ acpi_ev_execute_reg_methods(node, max_depth, space_id,
++ ACPI_REG_CONNECT);
+ } else {
+ status = AE_BAD_PARAMETER;
+ }
+@@ -306,57 +310,3 @@ acpi_execute_reg_methods(acpi_handle device, acpi_adr_space_type space_id)
+ }
+
+ ACPI_EXPORT_SYMBOL(acpi_execute_reg_methods)
+-
+-/*******************************************************************************
+- *
+- * FUNCTION: acpi_execute_orphan_reg_method
+- *
+- * PARAMETERS: device - Handle for the device
+- * space_id - The address space ID
+- *
+- * RETURN: Status
+- *
+- * DESCRIPTION: Execute an "orphan" _REG method that appears under an ACPI
+- * device. This is a _REG method that has no corresponding region
+- * within the device's scope.
+- *
+- ******************************************************************************/
+-acpi_status
+-acpi_execute_orphan_reg_method(acpi_handle device, acpi_adr_space_type space_id)
+-{
+- struct acpi_namespace_node *node;
+- acpi_status status;
+-
+- ACPI_FUNCTION_TRACE(acpi_execute_orphan_reg_method);
+-
+- /* Parameter validation */
+-
+- if (!device) {
+- return_ACPI_STATUS(AE_BAD_PARAMETER);
+- }
+-
+- status = acpi_ut_acquire_mutex(ACPI_MTX_NAMESPACE);
+- if (ACPI_FAILURE(status)) {
+- return_ACPI_STATUS(status);
+- }
+-
+- /* Convert and validate the device handle */
+-
+- node = acpi_ns_validate_handle(device);
+- if (node) {
+-
+- /*
+- * If an "orphan" _REG method is present in the device's scope
+- * for the given address space ID, run it.
+- */
+-
+- acpi_ev_execute_orphan_reg_method(node, space_id);
+- } else {
+- status = AE_BAD_PARAMETER;
+- }
+-
+- (void)acpi_ut_release_mutex(ACPI_MTX_NAMESPACE);
+- return_ACPI_STATUS(status);
+-}
+-
+-ACPI_EXPORT_SYMBOL(acpi_execute_orphan_reg_method)
+diff --git a/drivers/acpi/ec.c b/drivers/acpi/ec.c
+index 299ec653388ce..38d2f6e6b12b4 100644
+--- a/drivers/acpi/ec.c
++++ b/drivers/acpi/ec.c
+@@ -1487,12 +1487,13 @@ static bool install_gpio_irq_event_handler(struct acpi_ec *ec)
+ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
+ bool call_reg)
+ {
+- acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle;
+ acpi_status status;
+
+ acpi_ec_start(ec, false);
+
+ if (!test_bit(EC_FLAGS_EC_HANDLER_INSTALLED, &ec->flags)) {
++ acpi_handle scope_handle = ec == first_ec ? ACPI_ROOT_OBJECT : ec->handle;
++
+ acpi_ec_enter_noirq(ec);
+ status = acpi_install_address_space_handler_no_reg(scope_handle,
+ ACPI_ADR_SPACE_EC,
+@@ -1506,10 +1507,7 @@ static int ec_install_handlers(struct acpi_ec *ec, struct acpi_device *device,
+ }
+
+ if (call_reg && !test_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags)) {
+- acpi_execute_reg_methods(scope_handle, ACPI_ADR_SPACE_EC);
+- if (scope_handle != ec->handle)
+- acpi_execute_orphan_reg_method(ec->handle, ACPI_ADR_SPACE_EC);
+-
++ acpi_execute_reg_methods(ec->handle, ACPI_UINT32_MAX, ACPI_ADR_SPACE_EC);
+ set_bit(EC_FLAGS_EC_REG_CALLED, &ec->flags);
+ }
+
+@@ -1724,6 +1722,12 @@ static void acpi_ec_remove(struct acpi_device *device)
+ }
+ }
+
++void acpi_ec_register_opregions(struct acpi_device *adev)
++{
++ if (first_ec && first_ec->handle != adev->handle)
++ acpi_execute_reg_methods(adev->handle, 1, ACPI_ADR_SPACE_EC);
++}
++
+ static acpi_status
+ ec_parse_io_ports(struct acpi_resource *resource, void *context)
+ {
+diff --git a/drivers/acpi/internal.h b/drivers/acpi/internal.h
+index 601b670356e50..aadd4c218b320 100644
+--- a/drivers/acpi/internal.h
++++ b/drivers/acpi/internal.h
+@@ -223,6 +223,7 @@ int acpi_ec_add_query_handler(struct acpi_ec *ec, u8 query_bit,
+ acpi_handle handle, acpi_ec_query_func func,
+ void *data);
+ void acpi_ec_remove_query_handler(struct acpi_ec *ec, u8 query_bit);
++void acpi_ec_register_opregions(struct acpi_device *adev);
+
+ #ifdef CONFIG_PM_SLEEP
+ void acpi_ec_flush_work(void);
+diff --git a/drivers/acpi/scan.c b/drivers/acpi/scan.c
+index 503773707e012..cdc5a74092c77 100644
+--- a/drivers/acpi/scan.c
++++ b/drivers/acpi/scan.c
+@@ -2264,6 +2264,8 @@ static int acpi_bus_attach(struct acpi_device *device, void *first_pass)
+ if (device->handler)
+ goto ok;
+
++ acpi_ec_register_opregions(device);
++
+ if (!device->flags.initialized) {
+ device->flags.power_manageable =
+ device->power.states[ACPI_STATE_D0].flags.valid;
+diff --git a/drivers/acpi/video_detect.c b/drivers/acpi/video_detect.c
+index 2cc3821b2b16e..ff6f260433a11 100644
+--- a/drivers/acpi/video_detect.c
++++ b/drivers/acpi/video_detect.c
+@@ -54,6 +54,8 @@ static void acpi_video_parse_cmdline(void)
+ acpi_backlight_cmdline = acpi_backlight_nvidia_wmi_ec;
+ if (!strcmp("apple_gmux", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_apple_gmux;
++ if (!strcmp("dell_uart", acpi_video_backlight_string))
++ acpi_backlight_cmdline = acpi_backlight_dell_uart;
+ if (!strcmp("none", acpi_video_backlight_string))
+ acpi_backlight_cmdline = acpi_backlight_none;
+ }
+@@ -805,6 +807,21 @@ static const struct dmi_system_id video_detect_dmi_table[] = {
+ },
+ },
+
++ /*
++ * Dell AIO (All in Ones) which advertise an UART attached backlight
++ * controller board in their ACPI tables (and may even have one), but
++ * which need native backlight control nevertheless.
++ */
++ {
++ /* https://bugzilla.redhat.com/show_bug.cgi?id=2303936 */
++ .callback = video_detect_force_native,
++ /* Dell OptiPlex 7760 AIO */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "Dell Inc."),
++ DMI_MATCH(DMI_PRODUCT_NAME, "OptiPlex 7760 AIO"),
++ },
++ },
++
+ /*
+ * Models which have nvidia-ec-wmi support, but should not use it.
+ * Note this indicates a likely firmware bug on these models and should
+@@ -902,6 +919,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
+ static DEFINE_MUTEX(init_mutex);
+ static bool nvidia_wmi_ec_present;
+ static bool apple_gmux_present;
++ static bool dell_uart_present;
+ static bool native_available;
+ static bool init_done;
+ static long video_caps;
+@@ -916,6 +934,7 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
+ &video_caps, NULL);
+ nvidia_wmi_ec_present = nvidia_wmi_ec_supported();
+ apple_gmux_present = apple_gmux_detect(NULL, NULL);
++ dell_uart_present = acpi_dev_present("DELL0501", NULL, -1);
+ init_done = true;
+ }
+ if (native)
+@@ -946,6 +965,9 @@ enum acpi_backlight_type __acpi_video_get_backlight_type(bool native, bool *auto
+ if (apple_gmux_present)
+ return acpi_backlight_apple_gmux;
+
++ if (dell_uart_present)
++ return acpi_backlight_dell_uart;
++
+ /* Use ACPI video if available, except when native should be preferred. */
+ if ((video_caps & ACPI_VIDEO_BACKLIGHT) &&
+ !(native_available && prefer_native_over_acpi_video()))
+diff --git a/drivers/ata/pata_macio.c b/drivers/ata/pata_macio.c
+index 3cb455a32d926..99fc5d9d95d7a 100644
+--- a/drivers/ata/pata_macio.c
++++ b/drivers/ata/pata_macio.c
+@@ -208,6 +208,19 @@ static const char* macio_ata_names[] = {
+ /* Don't let a DMA segment go all the way to 64K */
+ #define MAX_DBDMA_SEG 0xff00
+
++#ifdef CONFIG_PAGE_SIZE_64KB
++/*
++ * The SCSI core requires the segment size to cover at least a page, so
++ * for 64K page size kernels it must be at least 64K. However the
++ * hardware can't handle 64K, so pata_macio_qc_prep() will split large
++ * requests. To handle the split requests the tablesize must be halved.
++ */
++#define PATA_MACIO_MAX_SEGMENT_SIZE SZ_64K
++#define PATA_MACIO_SG_TABLESIZE (MAX_DCMDS / 2)
++#else
++#define PATA_MACIO_MAX_SEGMENT_SIZE MAX_DBDMA_SEG
++#define PATA_MACIO_SG_TABLESIZE MAX_DCMDS
++#endif
+
+ /*
+ * Wait 1s for disk to answer on IDE bus after a hard reset
+@@ -912,16 +925,10 @@ static int pata_macio_do_resume(struct pata_macio_priv *priv)
+
+ static const struct scsi_host_template pata_macio_sht = {
+ __ATA_BASE_SHT(DRV_NAME),
+- .sg_tablesize = MAX_DCMDS,
++ .sg_tablesize = PATA_MACIO_SG_TABLESIZE,
+ /* We may not need that strict one */
+ .dma_boundary = ATA_DMA_BOUNDARY,
+- /*
+- * The SCSI core requires the segment size to cover at least a page, so
+- * for 64K page size kernels this must be at least 64K. However the
+- * hardware can't handle 64K, so pata_macio_qc_prep() will split large
+- * requests.
+- */
+- .max_segment_size = SZ_64K,
++ .max_segment_size = PATA_MACIO_MAX_SEGMENT_SIZE,
+ .device_configure = pata_macio_device_configure,
+ .sdev_groups = ata_common_sdev_groups,
+ .can_queue = ATA_DEF_QUEUE,
+diff --git a/drivers/atm/idt77252.c b/drivers/atm/idt77252.c
+index e7f713cd70d3f..a876024d8a05f 100644
+--- a/drivers/atm/idt77252.c
++++ b/drivers/atm/idt77252.c
+@@ -1118,8 +1118,8 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe)
+ rpp->len += skb->len;
+
+ if (stat & SAR_RSQE_EPDU) {
++ unsigned int len, truesize;
+ unsigned char *l1l2;
+- unsigned int len;
+
+ l1l2 = (unsigned char *) ((unsigned long) skb->data + skb->len - 6);
+
+@@ -1189,14 +1189,15 @@ dequeue_rx(struct idt77252_dev *card, struct rsq_entry *rsqe)
+ ATM_SKB(skb)->vcc = vcc;
+ __net_timestamp(skb);
+
++ truesize = skb->truesize;
+ vcc->push(vcc, skb);
+ atomic_inc(&vcc->stats->rx);
+
+- if (skb->truesize > SAR_FB_SIZE_3)
++ if (truesize > SAR_FB_SIZE_3)
+ add_rx_skb(card, 3, SAR_FB_SIZE_3, 1);
+- else if (skb->truesize > SAR_FB_SIZE_2)
++ else if (truesize > SAR_FB_SIZE_2)
+ add_rx_skb(card, 2, SAR_FB_SIZE_2, 1);
+- else if (skb->truesize > SAR_FB_SIZE_1)
++ else if (truesize > SAR_FB_SIZE_1)
+ add_rx_skb(card, 1, SAR_FB_SIZE_1, 1);
+ else
+ add_rx_skb(card, 0, SAR_FB_SIZE_0, 1);
+diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
+index 93900c37349c1..c084dc88d3d91 100644
+--- a/drivers/bluetooth/btintel.c
++++ b/drivers/bluetooth/btintel.c
+@@ -2876,9 +2876,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
+ INTEL_ROM_LEGACY_NO_WBS_SUPPORT))
+ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
+ &hdev->quirks);
+- if (ver.hw_variant == 0x08 && ver.fw_variant == 0x22)
+- set_bit(HCI_QUIRK_VALID_LE_STATES,
+- &hdev->quirks);
+
+ err = btintel_legacy_rom_setup(hdev, &ver);
+ break;
+@@ -2887,7 +2884,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
+ case 0x12: /* ThP */
+ case 0x13: /* HrP */
+ case 0x14: /* CcP */
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+ fallthrough;
+ case 0x0c: /* WsP */
+ /* Apply the device specific HCI quirks
+@@ -2979,9 +2975,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
+ /* These variants don't seem to support LE Coded PHY */
+ set_bit(HCI_QUIRK_BROKEN_LE_CODED, &hdev->quirks);
+
+- /* Set Valid LE States quirk */
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+-
+ /* Setup MSFT Extension support */
+ btintel_set_msft_opcode(hdev, ver.hw_variant);
+
+@@ -3003,9 +2996,6 @@ static int btintel_setup_combined(struct hci_dev *hdev)
+ */
+ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
+
+- /* Apply LE States quirk from solar onwards */
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+-
+ /* Setup MSFT Extension support */
+ btintel_set_msft_opcode(hdev,
+ INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
+diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
+index b8120b98a2395..1fd3b7073ab90 100644
+--- a/drivers/bluetooth/btintel_pcie.c
++++ b/drivers/bluetooth/btintel_pcie.c
+@@ -1182,9 +1182,6 @@ static int btintel_pcie_setup(struct hci_dev *hdev)
+ */
+ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
+
+- /* Apply LE States quirk from solar onwards */
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+-
+ /* Setup MSFT Extension support */
+ btintel_set_msft_opcode(hdev,
+ INTEL_HW_VARIANT(ver_tlv.cnvi_bt));
+diff --git a/drivers/bluetooth/btmtksdio.c b/drivers/bluetooth/btmtksdio.c
+index 8ded9ef8089a2..bc4700ed3b782 100644
+--- a/drivers/bluetooth/btmtksdio.c
++++ b/drivers/bluetooth/btmtksdio.c
+@@ -1144,9 +1144,6 @@ static int btmtksdio_setup(struct hci_dev *hdev)
+ }
+ }
+
+- /* Valid LE States quirk for MediaTek 7921 */
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+-
+ break;
+ case 0x7663:
+ case 0x7668:
+diff --git a/drivers/bluetooth/btrtl.c b/drivers/bluetooth/btrtl.c
+index 4f1e37b4f7802..bfcb41a57655f 100644
+--- a/drivers/bluetooth/btrtl.c
++++ b/drivers/bluetooth/btrtl.c
+@@ -1287,7 +1287,6 @@ void btrtl_set_quirks(struct hci_dev *hdev, struct btrtl_device_info *btrtl_dev)
+ case CHIP_ID_8852C:
+ case CHIP_ID_8851B:
+ case CHIP_ID_8852BT:
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
+
+ /* RTL8852C needs to transmit mSBC data continuously without
+diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
+index 789c492df6fa2..0927f51867c26 100644
+--- a/drivers/bluetooth/btusb.c
++++ b/drivers/bluetooth/btusb.c
+@@ -4545,8 +4545,8 @@ static int btusb_probe(struct usb_interface *intf,
+ if (id->driver_info & BTUSB_WIDEBAND_SPEECH)
+ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED, &hdev->quirks);
+
+- if (id->driver_info & BTUSB_VALID_LE_STATES)
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
++ if (!(id->driver_info & BTUSB_VALID_LE_STATES))
++ set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
+
+ if (id->driver_info & BTUSB_DIGIANSWER) {
+ data->cmdreq_type = USB_TYPE_VENDOR;
+diff --git a/drivers/bluetooth/hci_qca.c b/drivers/bluetooth/hci_qca.c
+index 9a0bc86f9aace..34c36f0f781ea 100644
+--- a/drivers/bluetooth/hci_qca.c
++++ b/drivers/bluetooth/hci_qca.c
+@@ -2408,8 +2408,8 @@ static int qca_serdev_probe(struct serdev_device *serdev)
+ set_bit(HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
+ &hdev->quirks);
+
+- if (data->capabilities & QCA_CAP_VALID_LE_STATES)
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
++ if (!(data->capabilities & QCA_CAP_VALID_LE_STATES))
++ set_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks);
+ }
+
+ return 0;
+diff --git a/drivers/bluetooth/hci_vhci.c b/drivers/bluetooth/hci_vhci.c
+index 28750a40f0ed5..b652d68f0ee14 100644
+--- a/drivers/bluetooth/hci_vhci.c
++++ b/drivers/bluetooth/hci_vhci.c
+@@ -425,8 +425,6 @@ static int __vhci_create_device(struct vhci_data *data, __u8 opcode)
+ if (opcode & 0x80)
+ set_bit(HCI_QUIRK_RAW_DEVICE, &hdev->quirks);
+
+- set_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks);
+-
+ if (hci_register_dev(hdev) < 0) {
+ BT_ERR("Can't register HCI device");
+ hci_free_dev(hdev);
+diff --git a/drivers/char/xillybus/xillyusb.c b/drivers/char/xillybus/xillyusb.c
+index 5a5afa14ca8cb..45771b1a3716a 100644
+--- a/drivers/char/xillybus/xillyusb.c
++++ b/drivers/char/xillybus/xillyusb.c
+@@ -50,6 +50,7 @@ MODULE_LICENSE("GPL v2");
+ static const char xillyname[] = "xillyusb";
+
+ static unsigned int fifo_buf_order;
++static struct workqueue_struct *wakeup_wq;
+
+ #define USB_VENDOR_ID_XILINX 0x03fd
+ #define USB_VENDOR_ID_ALTERA 0x09fb
+@@ -569,10 +570,6 @@ static void cleanup_dev(struct kref *kref)
+ * errors if executed. The mechanism relies on that xdev->error is assigned
+ * a non-zero value by report_io_error() prior to queueing wakeup_all(),
+ * which prevents bulk_in_work() from calling process_bulk_in().
+- *
+- * The fact that wakeup_all() and bulk_in_work() are queued on the same
+- * workqueue makes their concurrent execution very unlikely, however the
+- * kernel's API doesn't seem to ensure this strictly.
+ */
+
+ static void wakeup_all(struct work_struct *work)
+@@ -627,7 +624,7 @@ static void report_io_error(struct xillyusb_dev *xdev,
+
+ if (do_once) {
+ kref_get(&xdev->kref); /* xdev is used by work item */
+- queue_work(xdev->workq, &xdev->wakeup_workitem);
++ queue_work(wakeup_wq, &xdev->wakeup_workitem);
+ }
+ }
+
+@@ -1906,6 +1903,13 @@ static const struct file_operations xillyusb_fops = {
+
+ static int xillyusb_setup_base_eps(struct xillyusb_dev *xdev)
+ {
++ struct usb_device *udev = xdev->udev;
++
++ /* Verify that device has the two fundamental bulk in/out endpoints */
++ if (usb_pipe_type_check(udev, usb_sndbulkpipe(udev, MSG_EP_NUM)) ||
++ usb_pipe_type_check(udev, usb_rcvbulkpipe(udev, IN_EP_NUM)))
++ return -ENODEV;
++
+ xdev->msg_ep = endpoint_alloc(xdev, MSG_EP_NUM | USB_DIR_OUT,
+ bulk_out_work, 1, 2);
+ if (!xdev->msg_ep)
+@@ -1935,14 +1939,15 @@ static int setup_channels(struct xillyusb_dev *xdev,
+ __le16 *chandesc,
+ int num_channels)
+ {
+- struct xillyusb_channel *chan;
++ struct usb_device *udev = xdev->udev;
++ struct xillyusb_channel *chan, *new_channels;
+ int i;
+
+ chan = kcalloc(num_channels, sizeof(*chan), GFP_KERNEL);
+ if (!chan)
+ return -ENOMEM;
+
+- xdev->channels = chan;
++ new_channels = chan;
+
+ for (i = 0; i < num_channels; i++, chan++) {
+ unsigned int in_desc = le16_to_cpu(*chandesc++);
+@@ -1971,6 +1976,15 @@ static int setup_channels(struct xillyusb_dev *xdev,
+ */
+
+ if ((out_desc & 0x80) && i < 14) { /* Entry is valid */
++ if (usb_pipe_type_check(udev,
++ usb_sndbulkpipe(udev, i + 2))) {
++ dev_err(xdev->dev,
++ "Missing BULK OUT endpoint %d\n",
++ i + 2);
++ kfree(new_channels);
++ return -ENODEV;
++ }
++
+ chan->writable = 1;
+ chan->out_synchronous = !!(out_desc & 0x40);
+ chan->out_seekable = !!(out_desc & 0x20);
+@@ -1980,6 +1994,7 @@ static int setup_channels(struct xillyusb_dev *xdev,
+ }
+ }
+
++ xdev->channels = new_channels;
+ return 0;
+ }
+
+@@ -2096,9 +2111,11 @@ static int xillyusb_discovery(struct usb_interface *interface)
+ * just after responding with the IDT, there is no reason for any
+ * work item to be running now. To be sure that xdev->channels
+ * is updated on anything that might run in parallel, flush the
+- * workqueue, which rarely does anything.
++ * device's workqueue and the wakeup work item. This rarely
++ * does anything.
+ */
+ flush_workqueue(xdev->workq);
++ flush_work(&xdev->wakeup_workitem);
+
+ xdev->num_channels = num_channels;
+
+@@ -2258,6 +2275,10 @@ static int __init xillyusb_init(void)
+ {
+ int rc = 0;
+
++ wakeup_wq = alloc_workqueue(xillyname, 0, 0);
++ if (!wakeup_wq)
++ return -ENOMEM;
++
+ if (LOG2_INITIAL_FIFO_BUF_SIZE > PAGE_SHIFT)
+ fifo_buf_order = LOG2_INITIAL_FIFO_BUF_SIZE - PAGE_SHIFT;
+ else
+@@ -2265,12 +2286,17 @@ static int __init xillyusb_init(void)
+
+ rc = usb_register(&xillyusb_driver);
+
++ if (rc)
++ destroy_workqueue(wakeup_wq);
++
+ return rc;
+ }
+
+ static void __exit xillyusb_exit(void)
+ {
+ usb_deregister(&xillyusb_driver);
++
++ destroy_workqueue(wakeup_wq);
+ }
+
+ module_init(xillyusb_init);
+diff --git a/drivers/gpio/gpio-mlxbf3.c b/drivers/gpio/gpio-mlxbf3.c
+index d5906d419b0ab..10ea71273c891 100644
+--- a/drivers/gpio/gpio-mlxbf3.c
++++ b/drivers/gpio/gpio-mlxbf3.c
+@@ -39,6 +39,8 @@
+ #define MLXBF_GPIO_CAUSE_OR_EVTEN0 0x14
+ #define MLXBF_GPIO_CAUSE_OR_CLRCAUSE 0x18
+
++#define MLXBF_GPIO_CLR_ALL_INTS GENMASK(31, 0)
++
+ struct mlxbf3_gpio_context {
+ struct gpio_chip gc;
+
+@@ -82,6 +84,8 @@ static void mlxbf3_gpio_irq_disable(struct irq_data *irqd)
+ val = readl(gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0);
+ val &= ~BIT(offset);
+ writel(val, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0);
++
++ writel(BIT(offset), gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE);
+ raw_spin_unlock_irqrestore(&gs->gc.bgpio_lock, flags);
+
+ gpiochip_disable_irq(gc, offset);
+@@ -253,6 +257,15 @@ static int mlxbf3_gpio_probe(struct platform_device *pdev)
+ return 0;
+ }
+
++static void mlxbf3_gpio_shutdown(struct platform_device *pdev)
++{
++ struct mlxbf3_gpio_context *gs = platform_get_drvdata(pdev);
++
++ /* Disable and clear all interrupts */
++ writel(0, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_EVTEN0);
++ writel(MLXBF_GPIO_CLR_ALL_INTS, gs->gpio_cause_io + MLXBF_GPIO_CAUSE_OR_CLRCAUSE);
++}
++
+ static const struct acpi_device_id mlxbf3_gpio_acpi_match[] = {
+ { "MLNXBF33", 0 },
+ {}
+@@ -265,6 +278,7 @@ static struct platform_driver mlxbf3_gpio_driver = {
+ .acpi_match_table = mlxbf3_gpio_acpi_match,
+ },
+ .probe = mlxbf3_gpio_probe,
++ .shutdown = mlxbf3_gpio_shutdown,
+ };
+ module_platform_driver(mlxbf3_gpio_driver);
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+index 13eb2bc69e342..936c98a13a240 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+@@ -1057,6 +1057,9 @@ static int amdgpu_cs_patch_ibs(struct amdgpu_cs_parser *p,
+ r = amdgpu_ring_parse_cs(ring, p, job, ib);
+ if (r)
+ return r;
++
++ if (ib->sa_bo)
++ ib->gpu_addr = amdgpu_sa_bo_gpu_addr(ib->sa_bo);
+ } else {
+ ib->ptr = (uint32_t *)kptr;
+ r = amdgpu_ring_patch_cs_in_place(ring, p, job, ib);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+index 5cb33ac99f708..c43d1b6e5d66b 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ctx.c
+@@ -685,16 +685,24 @@ int amdgpu_ctx_ioctl(struct drm_device *dev, void *data,
+
+ switch (args->in.op) {
+ case AMDGPU_CTX_OP_ALLOC_CTX:
++ if (args->in.flags)
++ return -EINVAL;
+ r = amdgpu_ctx_alloc(adev, fpriv, filp, priority, &id);
+ args->out.alloc.ctx_id = id;
+ break;
+ case AMDGPU_CTX_OP_FREE_CTX:
++ if (args->in.flags)
++ return -EINVAL;
+ r = amdgpu_ctx_free(fpriv, id);
+ break;
+ case AMDGPU_CTX_OP_QUERY_STATE:
++ if (args->in.flags)
++ return -EINVAL;
+ r = amdgpu_ctx_query(adev, fpriv, id, &args->out);
+ break;
+ case AMDGPU_CTX_OP_QUERY_STATE2:
++ if (args->in.flags)
++ return -EINVAL;
+ r = amdgpu_ctx_query2(adev, fpriv, id, &args->out);
+ break;
+ case AMDGPU_CTX_OP_GET_STABLE_PSTATE:
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+index 8e8afbd237bcd..9aff579c6abf5 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+@@ -166,6 +166,9 @@ static ssize_t ta_if_load_debugfs_write(struct file *fp, const char *buf, size_t
+ if (ret)
+ return -EFAULT;
+
++ if (ta_bin_len > PSP_1_MEG)
++ return -EINVAL;
++
+ copy_pos += sizeof(uint32_t);
+
+ ta_bin = kzalloc(ta_bin_len, GFP_KERNEL);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+index 677eb141554e0..ceb3f1e4ed1dc 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.c
+@@ -151,6 +151,10 @@ int amdgpu_vcn_sw_init(struct amdgpu_device *adev)
+ }
+ }
+
++ /* from vcn4 and above, only unified queue is used */
++ adev->vcn.using_unified_queue =
++ amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0);
++
+ hdr = (const struct common_firmware_header *)adev->vcn.fw[0]->data;
+ adev->vcn.fw_version = le32_to_cpu(hdr->ucode_version);
+
+@@ -279,18 +283,6 @@ int amdgpu_vcn_sw_fini(struct amdgpu_device *adev)
+ return 0;
+ }
+
+-/* from vcn4 and above, only unified queue is used */
+-static bool amdgpu_vcn_using_unified_queue(struct amdgpu_ring *ring)
+-{
+- struct amdgpu_device *adev = ring->adev;
+- bool ret = false;
+-
+- if (amdgpu_ip_version(adev, UVD_HWIP, 0) >= IP_VERSION(4, 0, 0))
+- ret = true;
+-
+- return ret;
+-}
+-
+ bool amdgpu_vcn_is_disabled_vcn(struct amdgpu_device *adev, enum vcn_ring_type type, uint32_t vcn_instance)
+ {
+ bool ret = false;
+@@ -401,7 +393,9 @@ static void amdgpu_vcn_idle_work_handler(struct work_struct *work)
+ for (i = 0; i < adev->vcn.num_enc_rings; ++i)
+ fence[j] += amdgpu_fence_count_emitted(&adev->vcn.inst[j].ring_enc[i]);
+
+- if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
++ /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
++ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
++ !adev->vcn.using_unified_queue) {
+ struct dpg_pause_state new_state;
+
+ if (fence[j] ||
+@@ -447,7 +441,9 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
+ amdgpu_device_ip_set_powergating_state(adev, AMD_IP_BLOCK_TYPE_VCN,
+ AMD_PG_STATE_UNGATE);
+
+- if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
++ /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
++ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
++ !adev->vcn.using_unified_queue) {
+ struct dpg_pause_state new_state;
+
+ if (ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC) {
+@@ -473,8 +469,12 @@ void amdgpu_vcn_ring_begin_use(struct amdgpu_ring *ring)
+
+ void amdgpu_vcn_ring_end_use(struct amdgpu_ring *ring)
+ {
++ struct amdgpu_device *adev = ring->adev;
++
++ /* Only set DPG pause for VCN3 or below, VCN4 and above will be handled by FW */
+ if (ring->adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG &&
+- ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC)
++ ring->funcs->type == AMDGPU_RING_TYPE_VCN_ENC &&
++ !adev->vcn.using_unified_queue)
+ atomic_dec(&ring->adev->vcn.inst[ring->me].dpg_enc_submission_cnt);
+
+ atomic_dec(&ring->adev->vcn.total_submission_cnt);
+@@ -728,12 +728,11 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
+ struct amdgpu_job *job;
+ struct amdgpu_ib *ib;
+ uint64_t addr = AMDGPU_GPU_PAGE_ALIGN(ib_msg->gpu_addr);
+- bool sq = amdgpu_vcn_using_unified_queue(ring);
+ uint32_t *ib_checksum;
+ uint32_t ib_pack_in_dw;
+ int i, r;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ ib_size_dw += 8;
+
+ r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
+@@ -746,7 +745,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
+ ib->length_dw = 0;
+
+ /* single queue headers */
+- if (sq) {
++ if (adev->vcn.using_unified_queue) {
+ ib_pack_in_dw = sizeof(struct amdgpu_vcn_decode_buffer) / sizeof(uint32_t)
+ + 4 + 2; /* engine info + decoding ib in dw */
+ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, ib_pack_in_dw, false);
+@@ -765,7 +764,7 @@ static int amdgpu_vcn_dec_sw_send_msg(struct amdgpu_ring *ring,
+ for (i = ib->length_dw; i < ib_size_dw; ++i)
+ ib->ptr[i] = 0x0;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, ib_pack_in_dw);
+
+ r = amdgpu_job_submit_direct(job, ring, &f);
+@@ -855,15 +854,15 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
+ struct dma_fence **fence)
+ {
+ unsigned int ib_size_dw = 16;
++ struct amdgpu_device *adev = ring->adev;
+ struct amdgpu_job *job;
+ struct amdgpu_ib *ib;
+ struct dma_fence *f = NULL;
+ uint32_t *ib_checksum = NULL;
+ uint64_t addr;
+- bool sq = amdgpu_vcn_using_unified_queue(ring);
+ int i, r;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ ib_size_dw += 8;
+
+ r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
+@@ -877,7 +876,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
+
+ ib->length_dw = 0;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
+
+ ib->ptr[ib->length_dw++] = 0x00000018;
+@@ -899,7 +898,7 @@ static int amdgpu_vcn_enc_get_create_msg(struct amdgpu_ring *ring, uint32_t hand
+ for (i = ib->length_dw; i < ib_size_dw; ++i)
+ ib->ptr[i] = 0x0;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
+
+ r = amdgpu_job_submit_direct(job, ring, &f);
+@@ -922,15 +921,15 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
+ struct dma_fence **fence)
+ {
+ unsigned int ib_size_dw = 16;
++ struct amdgpu_device *adev = ring->adev;
+ struct amdgpu_job *job;
+ struct amdgpu_ib *ib;
+ struct dma_fence *f = NULL;
+ uint32_t *ib_checksum = NULL;
+ uint64_t addr;
+- bool sq = amdgpu_vcn_using_unified_queue(ring);
+ int i, r;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ ib_size_dw += 8;
+
+ r = amdgpu_job_alloc_with_ib(ring->adev, NULL, NULL,
+@@ -944,7 +943,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
+
+ ib->length_dw = 0;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ ib_checksum = amdgpu_vcn_unified_ring_ib_header(ib, 0x11, true);
+
+ ib->ptr[ib->length_dw++] = 0x00000018;
+@@ -966,7 +965,7 @@ static int amdgpu_vcn_enc_get_destroy_msg(struct amdgpu_ring *ring, uint32_t han
+ for (i = ib->length_dw; i < ib_size_dw; ++i)
+ ib->ptr[i] = 0x0;
+
+- if (sq)
++ if (adev->vcn.using_unified_queue)
+ amdgpu_vcn_unified_ring_ib_checksum(&ib_checksum, 0x11);
+
+ r = amdgpu_job_submit_direct(job, ring, &f);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+index 9f06def236fdc..1a5439abd1a04 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vcn.h
+@@ -329,6 +329,7 @@ struct amdgpu_vcn {
+
+ uint16_t inst_mask;
+ uint8_t num_inst_per_aid;
++ bool using_unified_queue;
+ };
+
+ struct amdgpu_fw_shared_rb_ptrs_struct {
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+index ef3e42f6b8411..63f84ef6dfcf2 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v2_0.c
+@@ -543,11 +543,11 @@ void jpeg_v2_0_dec_ring_emit_ib(struct amdgpu_ring *ring,
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
++ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
++ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
+
+ amdgpu_ring_write(ring, PACKETJ(mmUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+index d66af11aa66c7..d24d06f6d682a 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.c
+@@ -23,6 +23,7 @@
+
+ #include "amdgpu.h"
+ #include "amdgpu_jpeg.h"
++#include "amdgpu_cs.h"
+ #include "soc15.h"
+ #include "soc15d.h"
+ #include "jpeg_v4_0_3.h"
+@@ -773,11 +774,15 @@ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,
+
+ amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
++
++ if (ring->funcs->parse_cs)
++ amdgpu_ring_write(ring, 0);
++ else
++ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
+
+ amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JPEG_VMID_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+- amdgpu_ring_write(ring, (vmid | (vmid << 4)));
++ amdgpu_ring_write(ring, (vmid | (vmid << 4) | (vmid << 8)));
+
+ amdgpu_ring_write(ring, PACKETJ(regUVD_LMI_JRBC_IB_64BIT_BAR_LOW_INTERNAL_OFFSET,
+ 0, 0, PACKETJ_TYPE0));
+@@ -1063,6 +1068,7 @@ static const struct amdgpu_ring_funcs jpeg_v4_0_3_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v4_0_3_dec_ring_get_rptr,
+ .get_wptr = jpeg_v4_0_3_dec_ring_get_wptr,
+ .set_wptr = jpeg_v4_0_3_dec_ring_set_wptr,
++ .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+@@ -1227,3 +1233,56 @@ static void jpeg_v4_0_3_set_ras_funcs(struct amdgpu_device *adev)
+ {
+ adev->jpeg.ras = &jpeg_v4_0_3_ras;
+ }
++
++/**
++ * jpeg_v4_0_3_dec_ring_parse_cs - command submission parser
++ *
++ * @parser: Command submission parser context
++ * @job: the job to parse
++ * @ib: the IB to parse
++ *
++ * Parse the command stream, return -EINVAL for invalid packet,
++ * 0 otherwise
++ */
++int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
++ struct amdgpu_job *job,
++ struct amdgpu_ib *ib)
++{
++ uint32_t i, reg, res, cond, type;
++ struct amdgpu_device *adev = parser->adev;
++
++ for (i = 0; i < ib->length_dw ; i += 2) {
++ reg = CP_PACKETJ_GET_REG(ib->ptr[i]);
++ res = CP_PACKETJ_GET_RES(ib->ptr[i]);
++ cond = CP_PACKETJ_GET_COND(ib->ptr[i]);
++ type = CP_PACKETJ_GET_TYPE(ib->ptr[i]);
++
++ if (res) /* only support 0 at the moment */
++ return -EINVAL;
++
++ switch (type) {
++ case PACKETJ_TYPE0:
++ if (cond != PACKETJ_CONDITION_CHECK0 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) {
++ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
++ return -EINVAL;
++ }
++ break;
++ case PACKETJ_TYPE3:
++ if (cond != PACKETJ_CONDITION_CHECK3 || reg < JPEG_REG_RANGE_START || reg > JPEG_REG_RANGE_END) {
++ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
++ return -EINVAL;
++ }
++ break;
++ case PACKETJ_TYPE6:
++ if (ib->ptr[i] == CP_PACKETJ_NOP)
++ continue;
++ dev_err(adev->dev, "Invalid packet [0x%08x]!\n", ib->ptr[i]);
++ return -EINVAL;
++ default:
++ dev_err(adev->dev, "Unknown packet type %d !\n", type);
++ return -EINVAL;
++ }
++ }
++
++ return 0;
++}
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
+index 747a3e5f68564..71c54b294e157 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v4_0_3.h
+@@ -46,6 +46,9 @@
+
+ #define JRBC_DEC_EXTERNAL_REG_WRITE_ADDR 0x18000
+
++#define JPEG_REG_RANGE_START 0x4000
++#define JPEG_REG_RANGE_END 0x41c2
++
+ extern const struct amdgpu_ip_block_version jpeg_v4_0_3_ip_block;
+
+ void jpeg_v4_0_3_dec_ring_emit_ib(struct amdgpu_ring *ring,
+@@ -62,5 +65,7 @@ void jpeg_v4_0_3_dec_ring_insert_end(struct amdgpu_ring *ring);
+ void jpeg_v4_0_3_dec_ring_emit_wreg(struct amdgpu_ring *ring, uint32_t reg, uint32_t val);
+ void jpeg_v4_0_3_dec_ring_emit_reg_wait(struct amdgpu_ring *ring, uint32_t reg,
+ uint32_t val, uint32_t mask);
+-
++int jpeg_v4_0_3_dec_ring_parse_cs(struct amdgpu_cs_parser *parser,
++ struct amdgpu_job *job,
++ struct amdgpu_ib *ib);
+ #endif /* __JPEG_V4_0_3_H__ */
+diff --git a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+index 64c856bfe0cbb..90299f66a4445 100644
+--- a/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/jpeg_v5_0_0.c
+@@ -523,6 +523,7 @@ static const struct amdgpu_ring_funcs jpeg_v5_0_0_dec_ring_vm_funcs = {
+ .get_rptr = jpeg_v5_0_0_dec_ring_get_rptr,
+ .get_wptr = jpeg_v5_0_0_dec_ring_get_wptr,
+ .set_wptr = jpeg_v5_0_0_dec_ring_set_wptr,
++ .parse_cs = jpeg_v4_0_3_dec_ring_parse_cs,
+ .emit_frame_size =
+ SOC15_FLUSH_GPU_TLB_NUM_WREG * 6 +
+ SOC15_FLUSH_GPU_TLB_NUM_REG_WAIT * 8 +
+diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+index af1e90159ce36..2e72d445415f9 100644
+--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
++++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+@@ -176,14 +176,16 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
+ DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
+ ring->doorbell_index, ring->wptr << 2);
+ WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
+- /* SDMA seems to miss doorbells sometimes when powergating kicks in.
+- * Updating the wptr directly will wake it. This is only safe because
+- * we disallow gfxoff in begin_use() and then allow it again in end_use().
+- */
+- WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
+- lower_32_bits(ring->wptr << 2));
+- WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
+- upper_32_bits(ring->wptr << 2));
++ if (amdgpu_ip_version(adev, SDMA0_HWIP, 0) == IP_VERSION(5, 2, 1)) {
++ /* SDMA seems to miss doorbells sometimes when powergating kicks in.
++ * Updating the wptr directly will wake it. This is only safe because
++ * we disallow gfxoff in begin_use() and then allow it again in end_use().
++ */
++ WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
++ lower_32_bits(ring->wptr << 2));
++ WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
++ upper_32_bits(ring->wptr << 2));
++ }
+ } else {
+ DRM_DEBUG("Not using doorbell -- "
+ "mmSDMA%i_GFX_RB_WPTR == 0x%08x "
+diff --git a/drivers/gpu/drm/amd/amdgpu/soc15d.h b/drivers/gpu/drm/amd/amdgpu/soc15d.h
+index 2357ff39323f0..e74e1983da53a 100644
+--- a/drivers/gpu/drm/amd/amdgpu/soc15d.h
++++ b/drivers/gpu/drm/amd/amdgpu/soc15d.h
+@@ -76,6 +76,12 @@
+ ((cond & 0xF) << 24) | \
+ ((type & 0xF) << 28))
+
++#define CP_PACKETJ_NOP 0x60000000
++#define CP_PACKETJ_GET_REG(x) ((x) & 0x3FFFF)
++#define CP_PACKETJ_GET_RES(x) (((x) >> 18) & 0x3F)
++#define CP_PACKETJ_GET_COND(x) (((x) >> 24) & 0xF)
++#define CP_PACKETJ_GET_TYPE(x) (((x) >> 28) & 0xF)
++
+ /* Packet 3 types */
+ #define PACKET3_NOP 0x10
+ #define PACKET3_SET_BASE 0x11
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+index 836bf9ba620d1..8d4ad15b8e171 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+@@ -2724,6 +2724,9 @@ static int dm_suspend(void *handle)
+
+ hpd_rx_irq_work_suspend(dm);
+
++ if (adev->dm.dc->caps.ips_support)
++ dc_allow_idle_optimizations(adev->dm.dc, true);
++
+ dc_set_power_state(dm->dc, DC_ACPI_CM_POWER_STATE_D3);
+ dc_dmub_srv_set_power_state(dm->dc->ctx->dmub_srv, DC_ACPI_CM_POWER_STATE_D3);
+
+@@ -6559,12 +6562,34 @@ static const struct attribute_group amdgpu_group = {
+ .attrs = amdgpu_attrs
+ };
+
++static bool
++amdgpu_dm_should_create_sysfs(struct amdgpu_dm_connector *amdgpu_dm_connector)
++{
++ if (amdgpu_dm_abm_level >= 0)
++ return false;
++
++ if (amdgpu_dm_connector->base.connector_type != DRM_MODE_CONNECTOR_eDP)
++ return false;
++
++ /* check for OLED panels */
++ if (amdgpu_dm_connector->bl_idx >= 0) {
++ struct drm_device *drm = amdgpu_dm_connector->base.dev;
++ struct amdgpu_display_manager *dm = &drm_to_adev(drm)->dm;
++ struct amdgpu_dm_backlight_caps *caps;
++
++ caps = &dm->backlight_caps[amdgpu_dm_connector->bl_idx];
++ if (caps->aux_support)
++ return false;
++ }
++
++ return true;
++}
++
+ static void amdgpu_dm_connector_unregister(struct drm_connector *connector)
+ {
+ struct amdgpu_dm_connector *amdgpu_dm_connector = to_amdgpu_dm_connector(connector);
+
+- if (connector->connector_type == DRM_MODE_CONNECTOR_eDP &&
+- amdgpu_dm_abm_level < 0)
++ if (amdgpu_dm_should_create_sysfs(amdgpu_dm_connector))
+ sysfs_remove_group(&connector->kdev->kobj, &amdgpu_group);
+
+ drm_dp_aux_unregister(&amdgpu_dm_connector->dm_dp_aux.aux);
+@@ -6671,8 +6696,7 @@ amdgpu_dm_connector_late_register(struct drm_connector *connector)
+ to_amdgpu_dm_connector(connector);
+ int r;
+
+- if (connector->connector_type == DRM_MODE_CONNECTOR_eDP &&
+- amdgpu_dm_abm_level < 0) {
++ if (amdgpu_dm_should_create_sysfs(amdgpu_dm_connector)) {
+ r = sysfs_create_group(&connector->kdev->kobj,
+ &amdgpu_group);
+ if (r)
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+index 3306684e805ac..872f994dd356e 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+@@ -3605,7 +3605,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
+ (int)hubp->curs_attr.width || pos_cpy.x
+ <= (int)hubp->curs_attr.width +
+ pipe_ctx->plane_state->src_rect.x) {
+- pos_cpy.x = temp_x + viewport_width;
++ pos_cpy.x = 2 * viewport_width - temp_x;
+ }
+ }
+ } else {
+@@ -3698,7 +3698,7 @@ void dcn10_set_cursor_position(struct pipe_ctx *pipe_ctx)
+ (int)hubp->curs_attr.width || pos_cpy.x
+ <= (int)hubp->curs_attr.width +
+ pipe_ctx->plane_state->src_rect.x) {
+- pos_cpy.x = 2 * viewport_width - temp_x;
++ pos_cpy.x = temp_x + viewport_width;
+ }
+ }
+ } else {
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+index 9a3cc0514a36e..8e0588b1cf305 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+@@ -1778,6 +1778,9 @@ static bool dcn321_resource_construct(
+ dc->caps.color.mpc.ogam_rom_caps.hlg = 0;
+ dc->caps.color.mpc.ocsc = 1;
+
++ /* Use pipe context based otg sync logic */
++ dc->config.use_pipe_ctx_sync_logic = true;
++
+ dc->config.dc_mode_clk_limit_support = true;
+ dc->config.enable_windowed_mpo_odm = true;
+ /* read VBIOS LTTPR caps */
+diff --git a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+index 92b03073acdd5..555428606e127 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
++++ b/drivers/gpu/drm/i915/display/intel_dp_hdcp.c
+@@ -39,7 +39,9 @@ static u32 transcoder_to_stream_enc_status(enum transcoder cpu_transcoder)
+ static void intel_dp_hdcp_wait_for_cp_irq(struct intel_connector *connector,
+ int timeout)
+ {
+- struct intel_hdcp *hdcp = &connector->hdcp;
++ struct intel_digital_port *dig_port = intel_attached_dig_port(connector);
++ struct intel_dp *dp = &dig_port->dp;
++ struct intel_hdcp *hdcp = &dp->attached_connector->hdcp;
+ long ret;
+
+ #define C (hdcp->cp_irq_count_cached != atomic_read(&hdcp->cp_irq_count))
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+index 697ad4a640516..a6c5e3bc9bf15 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+@@ -1179,8 +1179,6 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
+
+ cstate->num_mixers = num_lm;
+
+- dpu_enc->connector = conn_state->connector;
+-
+ for (i = 0; i < dpu_enc->num_phys_encs; i++) {
+ struct dpu_encoder_phys *phys = dpu_enc->phys_encs[i];
+
+@@ -1277,6 +1275,8 @@ static void dpu_encoder_virt_atomic_enable(struct drm_encoder *drm_enc,
+
+ dpu_enc->commit_done_timedout = false;
+
++ dpu_enc->connector = drm_atomic_get_new_connector_for_encoder(state, drm_enc);
++
+ cur_mode = &dpu_enc->base.crtc->state->adjusted_mode;
+
+ dpu_enc->wide_bus_en = dpu_encoder_is_widebus_enabled(drm_enc);
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+index 9b72977feafa4..e61b5681f3bbd 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+@@ -308,8 +308,8 @@ static const u32 wb2_formats_rgb_yuv[] = {
+ { \
+ .maxdwnscale = SSPP_UNITY_SCALE, \
+ .maxupscale = SSPP_UNITY_SCALE, \
+- .format_list = plane_formats_yuv, \
+- .num_formats = ARRAY_SIZE(plane_formats_yuv), \
++ .format_list = plane_formats, \
++ .num_formats = ARRAY_SIZE(plane_formats), \
+ .virt_format_list = plane_formats, \
+ .virt_num_formats = ARRAY_SIZE(plane_formats), \
+ }
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+index e2adc937ea63b..935ff6fd172c4 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_kms.h
+@@ -31,24 +31,14 @@
+ * @fmt: Pointer to format string
+ */
+ #define DPU_DEBUG(fmt, ...) \
+- do { \
+- if (drm_debug_enabled(DRM_UT_KMS)) \
+- DRM_DEBUG(fmt, ##__VA_ARGS__); \
+- else \
+- pr_debug(fmt, ##__VA_ARGS__); \
+- } while (0)
++ DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)
+
+ /**
+ * DPU_DEBUG_DRIVER - macro for hardware driver logging
+ * @fmt: Pointer to format string
+ */
+ #define DPU_DEBUG_DRIVER(fmt, ...) \
+- do { \
+- if (drm_debug_enabled(DRM_UT_DRIVER)) \
+- DRM_ERROR(fmt, ##__VA_ARGS__); \
+- else \
+- pr_debug(fmt, ##__VA_ARGS__); \
+- } while (0)
++ DRM_DEBUG_DRIVER(fmt, ##__VA_ARGS__)
+
+ #define DPU_ERROR(fmt, ...) pr_err("[dpu error]" fmt, ##__VA_ARGS__)
+ #define DPU_ERROR_RATELIMITED(fmt, ...) pr_err_ratelimited("[dpu error]" fmt, ##__VA_ARGS__)
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+index 1c3a2657450c6..c31d283d1c6c1 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_plane.c
+@@ -680,6 +680,9 @@ static int dpu_plane_prepare_fb(struct drm_plane *plane,
+ new_state->fb, &layout);
+ if (ret) {
+ DPU_ERROR_PLANE(pdpu, "failed to get format layout, %d\n", ret);
++ if (pstate->aspace)
++ msm_framebuffer_cleanup(new_state->fb, pstate->aspace,
++ pstate->needs_dirtyfb);
+ return ret;
+ }
+
+@@ -743,10 +746,9 @@ static int dpu_plane_atomic_check_pipe(struct dpu_plane *pdpu,
+ min_src_size = MSM_FORMAT_IS_YUV(fmt) ? 2 : 1;
+
+ if (MSM_FORMAT_IS_YUV(fmt) &&
+- (!pipe->sspp->cap->sblk->scaler_blk.len ||
+- !pipe->sspp->cap->sblk->csc_blk.len)) {
++ !pipe->sspp->cap->sblk->csc_blk.len) {
+ DPU_DEBUG_PLANE(pdpu,
+- "plane doesn't have scaler/csc for yuv\n");
++ "plane doesn't have csc for yuv\n");
+ return -EINVAL;
+ }
+
+@@ -863,6 +865,10 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
+
+ max_linewidth = pdpu->catalog->caps->max_linewidth;
+
++ drm_rect_rotate(&pipe_cfg->src_rect,
++ new_plane_state->fb->width, new_plane_state->fb->height,
++ new_plane_state->rotation);
++
+ if ((drm_rect_width(&pipe_cfg->src_rect) > max_linewidth) ||
+ _dpu_plane_calc_clk(&crtc_state->adjusted_mode, pipe_cfg) > max_mdp_clk_rate) {
+ /*
+@@ -912,6 +918,14 @@ static int dpu_plane_atomic_check(struct drm_plane *plane,
+ r_pipe_cfg->dst_rect.x1 = pipe_cfg->dst_rect.x2;
+ }
+
++ drm_rect_rotate_inv(&pipe_cfg->src_rect,
++ new_plane_state->fb->width, new_plane_state->fb->height,
++ new_plane_state->rotation);
++ if (r_pipe->sspp)
++ drm_rect_rotate_inv(&r_pipe_cfg->src_rect,
++ new_plane_state->fb->width, new_plane_state->fb->height,
++ new_plane_state->rotation);
++
+ ret = dpu_plane_atomic_check_pipe(pdpu, pipe, pipe_cfg, fmt, &crtc_state->adjusted_mode);
+ if (ret)
+ return ret;
+diff --git a/drivers/gpu/drm/msm/dp/dp_ctrl.c b/drivers/gpu/drm/msm/dp/dp_ctrl.c
+index 7bc8a9f0657a9..f342fc5ae41ec 100644
+--- a/drivers/gpu/drm/msm/dp/dp_ctrl.c
++++ b/drivers/gpu/drm/msm/dp/dp_ctrl.c
+@@ -1286,6 +1286,8 @@ static int dp_ctrl_link_train(struct dp_ctrl_private *ctrl,
+ link_info.rate = ctrl->link->link_params.rate;
+ link_info.capabilities = DP_LINK_CAP_ENHANCED_FRAMING;
+
++ dp_link_reset_phy_params_vx_px(ctrl->link);
++
+ dp_aux_link_configure(ctrl->aux, &link_info);
+
+ if (drm_dp_max_downspread(dpcd))
+diff --git a/drivers/gpu/drm/msm/dp/dp_panel.c b/drivers/gpu/drm/msm/dp/dp_panel.c
+index 07db8f37cd06a..017fb8cc8ab67 100644
+--- a/drivers/gpu/drm/msm/dp/dp_panel.c
++++ b/drivers/gpu/drm/msm/dp/dp_panel.c
+@@ -90,22 +90,22 @@ static int dp_panel_read_dpcd(struct dp_panel *dp_panel)
+ static u32 dp_panel_get_supported_bpp(struct dp_panel *dp_panel,
+ u32 mode_edid_bpp, u32 mode_pclk_khz)
+ {
+- struct dp_link_info *link_info;
++ const struct dp_link_info *link_info;
+ const u32 max_supported_bpp = 30, min_supported_bpp = 18;
+- u32 bpp = 0, data_rate_khz = 0;
++ u32 bpp, data_rate_khz;
+
+- bpp = min_t(u32, mode_edid_bpp, max_supported_bpp);
++ bpp = min(mode_edid_bpp, max_supported_bpp);
+
+ link_info = &dp_panel->link_info;
+ data_rate_khz = link_info->num_lanes * link_info->rate * 8;
+
+- while (bpp > min_supported_bpp) {
++ do {
+ if (mode_pclk_khz * bpp <= data_rate_khz)
+- break;
++ return bpp;
+ bpp -= 6;
+- }
++ } while (bpp > min_supported_bpp);
+
+- return bpp;
++ return min_supported_bpp;
+ }
+
+ static int dp_panel_update_modes(struct drm_connector *connector,
+@@ -442,8 +442,9 @@ int dp_panel_init_panel_info(struct dp_panel *dp_panel)
+ drm_mode->clock);
+ drm_dbg_dp(panel->drm_dev, "bpp = %d\n", dp_panel->dp_mode.bpp);
+
+- dp_panel->dp_mode.bpp = max_t(u32, 18,
+- min_t(u32, dp_panel->dp_mode.bpp, 30));
++ dp_panel->dp_mode.bpp = dp_panel_get_mode_bpp(dp_panel, dp_panel->dp_mode.bpp,
++ dp_panel->dp_mode.drm_mode.clock);
++
+ drm_dbg_dp(panel->drm_dev, "updated bpp = %d\n",
+ dp_panel->dp_mode.bpp);
+
+diff --git a/drivers/gpu/drm/msm/msm_mdss.c b/drivers/gpu/drm/msm/msm_mdss.c
+index fab6ad4e5107c..ec75274178028 100644
+--- a/drivers/gpu/drm/msm/msm_mdss.c
++++ b/drivers/gpu/drm/msm/msm_mdss.c
+@@ -577,7 +577,7 @@ static const struct msm_mdss_data sc7180_data = {
+ .ubwc_enc_version = UBWC_2_0,
+ .ubwc_dec_version = UBWC_2_0,
+ .ubwc_static = 0x1e,
+- .highest_bank_bit = 0x3,
++ .highest_bank_bit = 0x1,
+ .reg_bus_bw = 76800,
+ };
+
+diff --git a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+index adc60b25f8e6c..0af01a0ec6016 100644
+--- a/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
++++ b/drivers/gpu/drm/nouveau/nvkm/core/firmware.c
+@@ -205,7 +205,8 @@ nvkm_firmware_dtor(struct nvkm_firmware *fw)
+ break;
+ case NVKM_FIRMWARE_IMG_DMA:
+ nvkm_memory_unref(&memory);
+- dma_free_coherent(fw->device->dev, sg_dma_len(&fw->mem.sgl), fw->img, fw->phys);
++ dma_free_noncoherent(fw->device->dev, sg_dma_len(&fw->mem.sgl),
++ fw->img, fw->phys, DMA_TO_DEVICE);
+ break;
+ case NVKM_FIRMWARE_IMG_SGT:
+ nvkm_memory_unref(&memory);
+@@ -236,10 +237,12 @@ nvkm_firmware_ctor(const struct nvkm_firmware_func *func, const char *name,
+ break;
+ case NVKM_FIRMWARE_IMG_DMA: {
+ dma_addr_t addr;
+-
+ len = ALIGN(fw->len, PAGE_SIZE);
+
+- fw->img = dma_alloc_coherent(fw->device->dev, len, &addr, GFP_KERNEL);
++ fw->img = dma_alloc_noncoherent(fw->device->dev,
++ len, &addr,
++ DMA_TO_DEVICE,
++ GFP_KERNEL);
+ if (fw->img) {
+ memcpy(fw->img, src, fw->len);
+ fw->phys = addr;
+diff --git a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+index 80a480b121746..a1c8545f1249a 100644
+--- a/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
++++ b/drivers/gpu/drm/nouveau/nvkm/falcon/fw.c
+@@ -89,6 +89,12 @@ nvkm_falcon_fw_boot(struct nvkm_falcon_fw *fw, struct nvkm_subdev *user,
+ nvkm_falcon_fw_dtor_sigs(fw);
+ }
+
++ /* after last write to the img, sync dma mappings */
++ dma_sync_single_for_device(fw->fw.device->dev,
++ fw->fw.phys,
++ sg_dma_len(&fw->fw.mem.sgl),
++ DMA_TO_DEVICE);
++
+ FLCNFW_DBG(fw, "resetting");
+ fw->func->reset(fw);
+
+diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
+index 30d5366d62883..0132403b8159f 100644
+--- a/drivers/gpu/drm/v3d/v3d_sched.c
++++ b/drivers/gpu/drm/v3d/v3d_sched.c
+@@ -315,7 +315,7 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
+ struct v3d_dev *v3d = job->base.v3d;
+ struct drm_device *dev = &v3d->drm;
+ struct dma_fence *fence;
+- int i, csd_cfg0_reg, csd_cfg_reg_count;
++ int i, csd_cfg0_reg;
+
+ v3d->csd_job = job;
+
+@@ -335,9 +335,17 @@ v3d_csd_job_run(struct drm_sched_job *sched_job)
+ v3d_switch_perfmon(v3d, &job->base);
+
+ csd_cfg0_reg = V3D_CSD_QUEUED_CFG0(v3d->ver);
+- csd_cfg_reg_count = v3d->ver < 71 ? 6 : 7;
+- for (i = 1; i <= csd_cfg_reg_count; i++)
++ for (i = 1; i <= 6; i++)
+ V3D_CORE_WRITE(0, csd_cfg0_reg + 4 * i, job->args.cfg[i]);
++
++ /* Although V3D 7.1 has an eighth configuration register, we are not
++ * using it. Therefore, make sure it remains unused.
++ *
++ * XXX: Set the CFG7 register
++ */
++ if (v3d->ver >= 71)
++ V3D_CORE_WRITE(0, V3D_V7_CSD_QUEUED_CFG7, 0);
++
+ /* CFG0 write kicks off the job. */
+ V3D_CORE_WRITE(0, csd_cfg0_reg, job->args.cfg[0]);
+
+diff --git a/drivers/gpu/drm/xe/display/xe_display.c b/drivers/gpu/drm/xe/display/xe_display.c
+index 0de0566e5b394..7cdc03dc40ed9 100644
+--- a/drivers/gpu/drm/xe/display/xe_display.c
++++ b/drivers/gpu/drm/xe/display/xe_display.c
+@@ -134,7 +134,7 @@ static void xe_display_fini_noirq(struct drm_device *dev, void *dummy)
+ return;
+
+ intel_display_driver_remove_noirq(xe);
+- intel_power_domains_driver_remove(xe);
++ intel_opregion_cleanup(xe);
+ }
+
+ int xe_display_init_noirq(struct xe_device *xe)
+@@ -160,8 +160,10 @@ int xe_display_init_noirq(struct xe_device *xe)
+ intel_display_device_info_runtime_init(xe);
+
+ err = intel_display_driver_probe_noirq(xe);
+- if (err)
++ if (err) {
++ intel_opregion_cleanup(xe);
+ return err;
++ }
+
+ return drmm_add_action_or_reset(&xe->drm, xe_display_fini_noirq, NULL);
+ }
+diff --git a/drivers/gpu/drm/xe/xe_device.c b/drivers/gpu/drm/xe/xe_device.c
+index 5ef9b50a20d01..a1cbdafbff75e 100644
+--- a/drivers/gpu/drm/xe/xe_device.c
++++ b/drivers/gpu/drm/xe/xe_device.c
+@@ -551,7 +551,9 @@ int xe_device_probe(struct xe_device *xe)
+ if (err)
+ return err;
+
+- xe_mmio_probe_tiles(xe);
++ err = xe_mmio_probe_tiles(xe);
++ if (err)
++ return err;
+
+ xe_ttm_sys_mgr_init(xe);
+
+diff --git a/drivers/gpu/drm/xe/xe_exec_queue.c b/drivers/gpu/drm/xe/xe_exec_queue.c
+index 395de93579fa6..2ae4420e29353 100644
+--- a/drivers/gpu/drm/xe/xe_exec_queue.c
++++ b/drivers/gpu/drm/xe/xe_exec_queue.c
+@@ -96,17 +96,11 @@ static struct xe_exec_queue *__xe_exec_queue_alloc(struct xe_device *xe,
+ }
+ }
+
+- if (xe_exec_queue_is_parallel(q)) {
+- q->parallel.composite_fence_ctx = dma_fence_context_alloc(1);
+- q->parallel.composite_fence_seqno = XE_FENCE_INITIAL_SEQNO;
+- }
+-
+ return q;
+ }
+
+ static int __xe_exec_queue_init(struct xe_exec_queue *q)
+ {
+- struct xe_device *xe = gt_to_xe(q->gt);
+ int i, err;
+
+ for (i = 0; i < q->width; ++i) {
+@@ -119,17 +113,6 @@ static int __xe_exec_queue_init(struct xe_exec_queue *q)
+ if (err)
+ goto err_lrc;
+
+- /*
+- * Normally the user vm holds an rpm ref to keep the device
+- * awake, and the context holds a ref for the vm, however for
+- * some engines we use the kernels migrate vm underneath which offers no
+- * such rpm ref, or we lack a vm. Make sure we keep a ref here, so we
+- * can perform GuC CT actions when needed. Caller is expected to have
+- * already grabbed the rpm ref outside any sensitive locks.
+- */
+- if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm))
+- xe_pm_runtime_get_noresume(xe);
+-
+ return 0;
+
+ err_lrc:
+@@ -216,8 +199,6 @@ void xe_exec_queue_fini(struct xe_exec_queue *q)
+
+ for (i = 0; i < q->width; ++i)
+ xe_lrc_finish(q->lrc + i);
+- if (!(q->flags & EXEC_QUEUE_FLAG_PERMANENT) && (q->flags & EXEC_QUEUE_FLAG_VM || !q->vm))
+- xe_pm_runtime_put(gt_to_xe(q->gt));
+ __xe_exec_queue_free(q);
+ }
+
+diff --git a/drivers/gpu/drm/xe/xe_exec_queue_types.h b/drivers/gpu/drm/xe/xe_exec_queue_types.h
+index ee78d497d838a..f0c40e8ad80a1 100644
+--- a/drivers/gpu/drm/xe/xe_exec_queue_types.h
++++ b/drivers/gpu/drm/xe/xe_exec_queue_types.h
+@@ -103,16 +103,6 @@ struct xe_exec_queue {
+ struct xe_guc_exec_queue *guc;
+ };
+
+- /**
+- * @parallel: parallel submission state
+- */
+- struct {
+- /** @parallel.composite_fence_ctx: context composite fence */
+- u64 composite_fence_ctx;
+- /** @parallel.composite_fence_seqno: seqno for composite fence */
+- u32 composite_fence_seqno;
+- } parallel;
+-
+ /** @sched_props: scheduling properties */
+ struct {
+ /** @sched_props.timeslice_us: timeslice period in micro-seconds */
+diff --git a/drivers/gpu/drm/xe/xe_gt_pagefault.c b/drivers/gpu/drm/xe/xe_gt_pagefault.c
+index fa9e9853c53ba..67e8efcaa93f1 100644
+--- a/drivers/gpu/drm/xe/xe_gt_pagefault.c
++++ b/drivers/gpu/drm/xe/xe_gt_pagefault.c
+@@ -402,6 +402,18 @@ static void pf_queue_work_func(struct work_struct *w)
+
+ static void acc_queue_work_func(struct work_struct *w);
+
++static void pagefault_fini(void *arg)
++{
++ struct xe_gt *gt = arg;
++ struct xe_device *xe = gt_to_xe(gt);
++
++ if (!xe->info.has_usm)
++ return;
++
++ destroy_workqueue(gt->usm.acc_wq);
++ destroy_workqueue(gt->usm.pf_wq);
++}
++
+ int xe_gt_pagefault_init(struct xe_gt *gt)
+ {
+ struct xe_device *xe = gt_to_xe(gt);
+@@ -429,10 +441,12 @@ int xe_gt_pagefault_init(struct xe_gt *gt)
+ gt->usm.acc_wq = alloc_workqueue("xe_gt_access_counter_work_queue",
+ WQ_UNBOUND | WQ_HIGHPRI,
+ NUM_ACC_QUEUE);
+- if (!gt->usm.acc_wq)
++ if (!gt->usm.acc_wq) {
++ destroy_workqueue(gt->usm.pf_wq);
+ return -ENOMEM;
++ }
+
+- return 0;
++ return devm_add_action_or_reset(xe->drm.dev, pagefault_fini, gt);
+ }
+
+ void xe_gt_pagefault_reset(struct xe_gt *gt)
+diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
+index 0f42971ff0a83..e48285c81bf57 100644
+--- a/drivers/gpu/drm/xe/xe_guc_submit.c
++++ b/drivers/gpu/drm/xe/xe_guc_submit.c
+@@ -35,6 +35,7 @@
+ #include "xe_macros.h"
+ #include "xe_map.h"
+ #include "xe_mocs.h"
++#include "xe_pm.h"
+ #include "xe_ring_ops_types.h"
+ #include "xe_sched_job.h"
+ #include "xe_trace.h"
+@@ -916,8 +917,9 @@ guc_exec_queue_timedout_job(struct drm_sched_job *drm_job)
+ return DRM_GPU_SCHED_STAT_NOMINAL;
+ }
+
+- drm_notice(&xe->drm, "Timedout job: seqno=%u, guc_id=%d, flags=0x%lx",
+- xe_sched_job_seqno(job), q->guc->id, q->flags);
++ drm_notice(&xe->drm, "Timedout job: seqno=%u, lrc_seqno=%u, guc_id=%d, flags=0x%lx",
++ xe_sched_job_seqno(job), xe_sched_job_lrc_seqno(job),
++ q->guc->id, q->flags);
+ xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_KERNEL,
+ "Kernel-submitted job timed out\n");
+ xe_gt_WARN(q->gt, q->flags & EXEC_QUEUE_FLAG_VM && !exec_queue_killed(q),
+@@ -1011,6 +1013,7 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
+ struct xe_exec_queue *q = ge->q;
+ struct xe_guc *guc = exec_queue_to_guc(q);
+
++ xe_pm_runtime_get(guc_to_xe(guc));
+ trace_xe_exec_queue_destroy(q);
+
+ if (xe_exec_queue_is_lr(q))
+@@ -1021,6 +1024,7 @@ static void __guc_exec_queue_fini_async(struct work_struct *w)
+
+ kfree(ge);
+ xe_exec_queue_fini(q);
++ xe_pm_runtime_put(guc_to_xe(guc));
+ }
+
+ static void guc_exec_queue_fini_async(struct xe_exec_queue *q)
+diff --git a/drivers/gpu/drm/xe/xe_hw_fence.c b/drivers/gpu/drm/xe/xe_hw_fence.c
+index f872ef1031272..35c0063a831af 100644
+--- a/drivers/gpu/drm/xe/xe_hw_fence.c
++++ b/drivers/gpu/drm/xe/xe_hw_fence.c
+@@ -208,23 +208,58 @@ static struct xe_hw_fence *to_xe_hw_fence(struct dma_fence *fence)
+ return container_of(fence, struct xe_hw_fence, dma);
+ }
+
+-struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx,
+- struct iosys_map seqno_map)
++/**
++ * xe_hw_fence_alloc() - Allocate an hw fence.
++ *
++ * Allocate but don't initialize an hw fence.
++ *
++ * Return: Pointer to the allocated fence or
++ * negative error pointer on error.
++ */
++struct dma_fence *xe_hw_fence_alloc(void)
+ {
+- struct xe_hw_fence *fence;
++ struct xe_hw_fence *hw_fence = fence_alloc();
+
+- fence = fence_alloc();
+- if (!fence)
++ if (!hw_fence)
+ return ERR_PTR(-ENOMEM);
+
+- fence->ctx = ctx;
+- fence->seqno_map = seqno_map;
+- INIT_LIST_HEAD(&fence->irq_link);
++ return &hw_fence->dma;
++}
+
+- dma_fence_init(&fence->dma, &xe_hw_fence_ops, &ctx->irq->lock,
+- ctx->dma_fence_ctx, ctx->next_seqno++);
++/**
++ * xe_hw_fence_free() - Free an hw fence.
++ * @fence: Pointer to the fence to free.
++ *
++ * Frees an hw fence that hasn't yet been
++ * initialized.
++ */
++void xe_hw_fence_free(struct dma_fence *fence)
++{
++ fence_free(&fence->rcu);
++}
+
+- trace_xe_hw_fence_create(fence);
++/**
++ * xe_hw_fence_init() - Initialize an hw fence.
++ * @fence: Pointer to the fence to initialize.
++ * @ctx: Pointer to the struct xe_hw_fence_ctx fence context.
++ * @seqno_map: Pointer to the map into where the seqno is blitted.
++ *
++ * Initializes a pre-allocated hw fence.
++ * After initialization, the fence is subject to normal
++ * dma-fence refcounting.
++ */
++void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx,
++ struct iosys_map seqno_map)
++{
++ struct xe_hw_fence *hw_fence =
++ container_of(fence, typeof(*hw_fence), dma);
++
++ hw_fence->ctx = ctx;
++ hw_fence->seqno_map = seqno_map;
++ INIT_LIST_HEAD(&hw_fence->irq_link);
++
++ dma_fence_init(fence, &xe_hw_fence_ops, &ctx->irq->lock,
++ ctx->dma_fence_ctx, ctx->next_seqno++);
+
+- return fence;
++ trace_xe_hw_fence_create(hw_fence);
+ }
+diff --git a/drivers/gpu/drm/xe/xe_hw_fence.h b/drivers/gpu/drm/xe/xe_hw_fence.h
+index cfe5fd603787e..f13a1c4982c73 100644
+--- a/drivers/gpu/drm/xe/xe_hw_fence.h
++++ b/drivers/gpu/drm/xe/xe_hw_fence.h
+@@ -24,7 +24,10 @@ void xe_hw_fence_ctx_init(struct xe_hw_fence_ctx *ctx, struct xe_gt *gt,
+ struct xe_hw_fence_irq *irq, const char *name);
+ void xe_hw_fence_ctx_finish(struct xe_hw_fence_ctx *ctx);
+
+-struct xe_hw_fence *xe_hw_fence_create(struct xe_hw_fence_ctx *ctx,
+- struct iosys_map seqno_map);
++struct dma_fence *xe_hw_fence_alloc(void);
+
++void xe_hw_fence_free(struct dma_fence *fence);
++
++void xe_hw_fence_init(struct dma_fence *fence, struct xe_hw_fence_ctx *ctx,
++ struct iosys_map seqno_map);
+ #endif
+diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
+index d7bf7bc9dc145..995f47eb365c3 100644
+--- a/drivers/gpu/drm/xe/xe_lrc.c
++++ b/drivers/gpu/drm/xe/xe_lrc.c
+@@ -901,10 +901,54 @@ u32 xe_lrc_seqno_ggtt_addr(struct xe_lrc *lrc)
+ return __xe_lrc_seqno_ggtt_addr(lrc);
+ }
+
++/**
++ * xe_lrc_alloc_seqno_fence() - Allocate an lrc seqno fence.
++ *
++ * Allocate but don't initialize an lrc seqno fence.
++ *
++ * Return: Pointer to the allocated fence or
++ * negative error pointer on error.
++ */
++struct dma_fence *xe_lrc_alloc_seqno_fence(void)
++{
++ return xe_hw_fence_alloc();
++}
++
++/**
++ * xe_lrc_free_seqno_fence() - Free an lrc seqno fence.
++ * @fence: Pointer to the fence to free.
++ *
++ * Frees an lrc seqno fence that hasn't yet been
++ * initialized.
++ */
++void xe_lrc_free_seqno_fence(struct dma_fence *fence)
++{
++ xe_hw_fence_free(fence);
++}
++
++/**
++ * xe_lrc_init_seqno_fence() - Initialize an lrc seqno fence.
++ * @lrc: Pointer to the lrc.
++ * @fence: Pointer to the fence to initialize.
++ *
++ * Initializes a pre-allocated lrc seqno fence.
++ * After initialization, the fence is subject to normal
++ * dma-fence refcounting.
++ */
++void xe_lrc_init_seqno_fence(struct xe_lrc *lrc, struct dma_fence *fence)
++{
++ xe_hw_fence_init(fence, &lrc->fence_ctx, __xe_lrc_seqno_map(lrc));
++}
++
+ struct dma_fence *xe_lrc_create_seqno_fence(struct xe_lrc *lrc)
+ {
+- return &xe_hw_fence_create(&lrc->fence_ctx,
+- __xe_lrc_seqno_map(lrc))->dma;
++ struct dma_fence *fence = xe_lrc_alloc_seqno_fence();
++
++ if (IS_ERR(fence))
++ return fence;
++
++ xe_lrc_init_seqno_fence(lrc, fence);
++ return fence;
+ }
+
+ s32 xe_lrc_seqno(struct xe_lrc *lrc)
+diff --git a/drivers/gpu/drm/xe/xe_lrc.h b/drivers/gpu/drm/xe/xe_lrc.h
+index d32fa31faa2cf..f57c5836dab87 100644
+--- a/drivers/gpu/drm/xe/xe_lrc.h
++++ b/drivers/gpu/drm/xe/xe_lrc.h
+@@ -38,6 +38,9 @@ void xe_lrc_write_ctx_reg(struct xe_lrc *lrc, int reg_nr, u32 val);
+ u64 xe_lrc_descriptor(struct xe_lrc *lrc);
+
+ u32 xe_lrc_seqno_ggtt_addr(struct xe_lrc *lrc);
++struct dma_fence *xe_lrc_alloc_seqno_fence(void);
++void xe_lrc_free_seqno_fence(struct dma_fence *fence);
++void xe_lrc_init_seqno_fence(struct xe_lrc *lrc, struct dma_fence *fence);
+ struct dma_fence *xe_lrc_create_seqno_fence(struct xe_lrc *lrc);
+ s32 xe_lrc_seqno(struct xe_lrc *lrc);
+
+diff --git a/drivers/gpu/drm/xe/xe_mmio.c b/drivers/gpu/drm/xe/xe_mmio.c
+index 334637511e750..beb4e276ba845 100644
+--- a/drivers/gpu/drm/xe/xe_mmio.c
++++ b/drivers/gpu/drm/xe/xe_mmio.c
+@@ -254,6 +254,21 @@ static int xe_mmio_tile_vram_size(struct xe_tile *tile, u64 *vram_size,
+ return xe_force_wake_put(gt_to_fw(gt), XE_FW_GT);
+ }
+
++static void vram_fini(void *arg)
++{
++ struct xe_device *xe = arg;
++ struct xe_tile *tile;
++ int id;
++
++ if (xe->mem.vram.mapping)
++ iounmap(xe->mem.vram.mapping);
++
++ xe->mem.vram.mapping = NULL;
++
++ for_each_tile(tile, xe, id)
++ tile->mem.vram.mapping = NULL;
++}
++
+ int xe_mmio_probe_vram(struct xe_device *xe)
+ {
+ struct xe_tile *tile;
+@@ -330,10 +345,21 @@ int xe_mmio_probe_vram(struct xe_device *xe)
+ drm_info(&xe->drm, "Available VRAM: %pa, %pa\n", &xe->mem.vram.io_start,
+ &available_size);
+
+- return 0;
++ return devm_add_action_or_reset(xe->drm.dev, vram_fini, xe);
+ }
+
+-void xe_mmio_probe_tiles(struct xe_device *xe)
++static void tiles_fini(void *arg)
++{
++ struct xe_device *xe = arg;
++ struct xe_tile *tile;
++ int id;
++
++ for_each_tile(tile, xe, id)
++ if (tile != xe_device_get_root_tile(xe))
++ tile->mmio.regs = NULL;
++}
++
++int xe_mmio_probe_tiles(struct xe_device *xe)
+ {
+ size_t tile_mmio_size = SZ_16M, tile_mmio_ext_size = xe->info.tile_mmio_ext_size;
+ u8 id, tile_count = xe->info.tile_count;
+@@ -384,15 +410,18 @@ void xe_mmio_probe_tiles(struct xe_device *xe)
+ regs += tile_mmio_ext_size;
+ }
+ }
++
++ return devm_add_action_or_reset(xe->drm.dev, tiles_fini, xe);
+ }
+
+-static void mmio_fini(struct drm_device *drm, void *arg)
++static void mmio_fini(void *arg)
+ {
+ struct xe_device *xe = arg;
++ struct xe_tile *root_tile = xe_device_get_root_tile(xe);
+
+ pci_iounmap(to_pci_dev(xe->drm.dev), xe->mmio.regs);
+- if (xe->mem.vram.mapping)
+- iounmap(xe->mem.vram.mapping);
++ xe->mmio.regs = NULL;
++ root_tile->mmio.regs = NULL;
+ }
+
+ int xe_mmio_init(struct xe_device *xe)
+@@ -417,7 +446,7 @@ int xe_mmio_init(struct xe_device *xe)
+ root_tile->mmio.size = SZ_16M;
+ root_tile->mmio.regs = xe->mmio.regs;
+
+- return drmm_add_action_or_reset(&xe->drm, mmio_fini, xe);
++ return devm_add_action_or_reset(xe->drm.dev, mmio_fini, xe);
+ }
+
+ u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg)
+diff --git a/drivers/gpu/drm/xe/xe_mmio.h b/drivers/gpu/drm/xe/xe_mmio.h
+index a3cd7b3036c73..a929d090bb2f1 100644
+--- a/drivers/gpu/drm/xe/xe_mmio.h
++++ b/drivers/gpu/drm/xe/xe_mmio.h
+@@ -21,7 +21,7 @@ struct xe_device;
+ #define LMEM_BAR 2
+
+ int xe_mmio_init(struct xe_device *xe);
+-void xe_mmio_probe_tiles(struct xe_device *xe);
++int xe_mmio_probe_tiles(struct xe_device *xe);
+
+ u8 xe_mmio_read8(struct xe_gt *gt, struct xe_reg reg);
+ u16 xe_mmio_read16(struct xe_gt *gt, struct xe_reg reg);
+diff --git a/drivers/gpu/drm/xe/xe_ring_ops.c b/drivers/gpu/drm/xe/xe_ring_ops.c
+index aca7a9af6e846..c59c4373aefad 100644
+--- a/drivers/gpu/drm/xe/xe_ring_ops.c
++++ b/drivers/gpu/drm/xe/xe_ring_ops.c
+@@ -380,7 +380,7 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,
+
+ dw[i++] = MI_ARB_ON_OFF | MI_ARB_DISABLE; /* Enabled again below */
+
+- i = emit_bb_start(job->batch_addr[0], BIT(8), dw, i);
++ i = emit_bb_start(job->ptrs[0].batch_addr, BIT(8), dw, i);
+
+ if (!IS_SRIOV_VF(gt_to_xe(job->q->gt))) {
+ /* XXX: Do we need this? Leaving for now. */
+@@ -389,7 +389,7 @@ static void emit_migration_job_gen12(struct xe_sched_job *job,
+ dw[i++] = preparser_disable(false);
+ }
+
+- i = emit_bb_start(job->batch_addr[1], BIT(8), dw, i);
++ i = emit_bb_start(job->ptrs[1].batch_addr, BIT(8), dw, i);
+
+ dw[i++] = MI_FLUSH_DW | MI_INVALIDATE_TLB | job->migrate_flush_flags |
+ MI_FLUSH_DW_OP_STOREDW | MI_FLUSH_IMM_DW;
+@@ -411,8 +411,8 @@ static void emit_job_gen12_gsc(struct xe_sched_job *job)
+ xe_gt_assert(gt, job->q->width <= 1); /* no parallel submission for GSCCS */
+
+ __emit_job_gen12_simple(job, job->q->lrc,
+- job->batch_addr[0],
+- xe_sched_job_seqno(job));
++ job->ptrs[0].batch_addr,
++ xe_sched_job_lrc_seqno(job));
+ }
+
+ static void emit_job_gen12_copy(struct xe_sched_job *job)
+@@ -421,14 +421,14 @@ static void emit_job_gen12_copy(struct xe_sched_job *job)
+
+ if (xe_sched_job_is_migration(job->q)) {
+ emit_migration_job_gen12(job, job->q->lrc,
+- xe_sched_job_seqno(job));
++ xe_sched_job_lrc_seqno(job));
+ return;
+ }
+
+ for (i = 0; i < job->q->width; ++i)
+ __emit_job_gen12_simple(job, job->q->lrc + i,
+- job->batch_addr[i],
+- xe_sched_job_seqno(job));
++ job->ptrs[i].batch_addr,
++ xe_sched_job_lrc_seqno(job));
+ }
+
+ static void emit_job_gen12_video(struct xe_sched_job *job)
+@@ -438,8 +438,8 @@ static void emit_job_gen12_video(struct xe_sched_job *job)
+ /* FIXME: Not doing parallel handshake for now */
+ for (i = 0; i < job->q->width; ++i)
+ __emit_job_gen12_video(job, job->q->lrc + i,
+- job->batch_addr[i],
+- xe_sched_job_seqno(job));
++ job->ptrs[i].batch_addr,
++ xe_sched_job_lrc_seqno(job));
+ }
+
+ static void emit_job_gen12_render_compute(struct xe_sched_job *job)
+@@ -448,8 +448,8 @@ static void emit_job_gen12_render_compute(struct xe_sched_job *job)
+
+ for (i = 0; i < job->q->width; ++i)
+ __emit_job_gen12_render_compute(job, job->q->lrc + i,
+- job->batch_addr[i],
+- xe_sched_job_seqno(job));
++ job->ptrs[i].batch_addr,
++ xe_sched_job_lrc_seqno(job));
+ }
+
+ static const struct xe_ring_ops ring_ops_gen12_gsc = {
+diff --git a/drivers/gpu/drm/xe/xe_sched_job.c b/drivers/gpu/drm/xe/xe_sched_job.c
+index cd8a2fba54389..2b064680abb96 100644
+--- a/drivers/gpu/drm/xe/xe_sched_job.c
++++ b/drivers/gpu/drm/xe/xe_sched_job.c
+@@ -6,7 +6,7 @@
+ #include "xe_sched_job.h"
+
+ #include <drm/xe_drm.h>
+-#include <linux/dma-fence-array.h>
++#include <linux/dma-fence-chain.h>
+ #include <linux/slab.h>
+
+ #include "xe_device.h"
+@@ -29,7 +29,7 @@ int __init xe_sched_job_module_init(void)
+ xe_sched_job_slab =
+ kmem_cache_create("xe_sched_job",
+ sizeof(struct xe_sched_job) +
+- sizeof(u64), 0,
++ sizeof(struct xe_job_ptrs), 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!xe_sched_job_slab)
+ return -ENOMEM;
+@@ -37,7 +37,7 @@ int __init xe_sched_job_module_init(void)
+ xe_sched_job_parallel_slab =
+ kmem_cache_create("xe_sched_job_parallel",
+ sizeof(struct xe_sched_job) +
+- sizeof(u64) *
++ sizeof(struct xe_job_ptrs) *
+ XE_HW_ENGINE_MAX_INSTANCE, 0,
+ SLAB_HWCACHE_ALIGN, NULL);
+ if (!xe_sched_job_parallel_slab) {
+@@ -79,26 +79,33 @@ static struct xe_device *job_to_xe(struct xe_sched_job *job)
+ return gt_to_xe(job->q->gt);
+ }
+
++/* Free unused pre-allocated fences */
++static void xe_sched_job_free_fences(struct xe_sched_job *job)
++{
++ int i;
++
++ for (i = 0; i < job->q->width; ++i) {
++ struct xe_job_ptrs *ptrs = &job->ptrs[i];
++
++ if (ptrs->lrc_fence)
++ xe_lrc_free_seqno_fence(ptrs->lrc_fence);
++ if (ptrs->chain_fence)
++ dma_fence_chain_free(ptrs->chain_fence);
++ }
++}
++
+ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
+ u64 *batch_addr)
+ {
+- struct xe_sched_job *job;
+- struct dma_fence **fences;
+ bool is_migration = xe_sched_job_is_migration(q);
++ struct xe_sched_job *job;
+ int err;
+- int i, j;
++ int i;
+ u32 width;
+
+ /* only a kernel context can submit a vm-less job */
+ XE_WARN_ON(!q->vm && !(q->flags & EXEC_QUEUE_FLAG_KERNEL));
+
+- /* Migration and kernel engines have their own locking */
+- if (!(q->flags & (EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_VM))) {
+- lockdep_assert_held(&q->vm->lock);
+- if (!xe_vm_in_lr_mode(q->vm))
+- xe_vm_assert_held(q->vm);
+- }
+-
+ job = job_alloc(xe_exec_queue_is_parallel(q) || is_migration);
+ if (!job)
+ return ERR_PTR(-ENOMEM);
+@@ -111,44 +118,25 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
+ if (err)
+ goto err_free;
+
+- if (!xe_exec_queue_is_parallel(q)) {
+- job->fence = xe_lrc_create_seqno_fence(q->lrc);
+- if (IS_ERR(job->fence)) {
+- err = PTR_ERR(job->fence);
+- goto err_sched_job;
+- }
+- } else {
+- struct dma_fence_array *cf;
++ for (i = 0; i < q->width; ++i) {
++ struct dma_fence *fence = xe_lrc_alloc_seqno_fence();
++ struct dma_fence_chain *chain;
+
+- fences = kmalloc_array(q->width, sizeof(*fences), GFP_KERNEL);
+- if (!fences) {
+- err = -ENOMEM;
++ if (IS_ERR(fence)) {
++ err = PTR_ERR(fence);
+ goto err_sched_job;
+ }
++ job->ptrs[i].lrc_fence = fence;
+
+- for (j = 0; j < q->width; ++j) {
+- fences[j] = xe_lrc_create_seqno_fence(q->lrc + j);
+- if (IS_ERR(fences[j])) {
+- err = PTR_ERR(fences[j]);
+- goto err_fences;
+- }
+- }
++ if (i + 1 == q->width)
++ continue;
+
+- cf = dma_fence_array_create(q->width, fences,
+- q->parallel.composite_fence_ctx,
+- q->parallel.composite_fence_seqno++,
+- false);
+- if (!cf) {
+- --q->parallel.composite_fence_seqno;
++ chain = dma_fence_chain_alloc();
++ if (!chain) {
+ err = -ENOMEM;
+- goto err_fences;
++ goto err_sched_job;
+ }
+-
+- /* Sanity check */
+- for (j = 0; j < q->width; ++j)
+- xe_assert(job_to_xe(job), cf->base.seqno == fences[j]->seqno);
+-
+- job->fence = &cf->base;
++ job->ptrs[i].chain_fence = chain;
+ }
+
+ width = q->width;
+@@ -156,23 +144,14 @@ struct xe_sched_job *xe_sched_job_create(struct xe_exec_queue *q,
+ width = 2;
+
+ for (i = 0; i < width; ++i)
+- job->batch_addr[i] = batch_addr[i];
+-
+- /* All other jobs require a VM to be open which has a ref */
+- if (unlikely(q->flags & EXEC_QUEUE_FLAG_KERNEL))
+- xe_pm_runtime_get_noresume(job_to_xe(job));
+- xe_device_assert_mem_access(job_to_xe(job));
++ job->ptrs[i].batch_addr = batch_addr[i];
+
++ xe_pm_runtime_get_noresume(job_to_xe(job));
+ trace_xe_sched_job_create(job);
+ return job;
+
+-err_fences:
+- for (j = j - 1; j >= 0; --j) {
+- --q->lrc[j].fence_ctx.next_seqno;
+- dma_fence_put(fences[j]);
+- }
+- kfree(fences);
+ err_sched_job:
++ xe_sched_job_free_fences(job);
+ drm_sched_job_cleanup(&job->drm);
+ err_free:
+ xe_exec_queue_put(q);
+@@ -191,36 +170,43 @@ void xe_sched_job_destroy(struct kref *ref)
+ {
+ struct xe_sched_job *job =
+ container_of(ref, struct xe_sched_job, refcount);
++ struct xe_device *xe = job_to_xe(job);
++ struct xe_exec_queue *q = job->q;
+
+- if (unlikely(job->q->flags & EXEC_QUEUE_FLAG_KERNEL))
+- xe_pm_runtime_put(job_to_xe(job));
+- xe_exec_queue_put(job->q);
++ xe_sched_job_free_fences(job);
+ dma_fence_put(job->fence);
+ drm_sched_job_cleanup(&job->drm);
+ job_free(job);
++ xe_exec_queue_put(q);
++ xe_pm_runtime_put(xe);
+ }
+
+-void xe_sched_job_set_error(struct xe_sched_job *job, int error)
++/* Set the error status under the fence to avoid racing with signaling */
++static bool xe_fence_set_error(struct dma_fence *fence, int error)
+ {
+- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &job->fence->flags))
+- return;
++ unsigned long irq_flags;
++ bool signaled;
+
+- dma_fence_set_error(job->fence, error);
++ spin_lock_irqsave(fence->lock, irq_flags);
++ signaled = test_bit(DMA_FENCE_FLAG_SIGNALED_BIT, &fence->flags);
++ if (!signaled)
++ dma_fence_set_error(fence, error);
++ spin_unlock_irqrestore(fence->lock, irq_flags);
+
+- if (dma_fence_is_array(job->fence)) {
+- struct dma_fence_array *array =
+- to_dma_fence_array(job->fence);
+- struct dma_fence **child = array->fences;
+- unsigned int nchild = array->num_fences;
++ return signaled;
++}
++
++void xe_sched_job_set_error(struct xe_sched_job *job, int error)
++{
++ if (xe_fence_set_error(job->fence, error))
++ return;
+
+- do {
+- struct dma_fence *current_fence = *child++;
++ if (dma_fence_is_chain(job->fence)) {
++ struct dma_fence *iter;
+
+- if (test_bit(DMA_FENCE_FLAG_SIGNALED_BIT,
+- ¤t_fence->flags))
+- continue;
+- dma_fence_set_error(current_fence, error);
+- } while (--nchild);
++ dma_fence_chain_for_each(iter, job->fence)
++ xe_fence_set_error(dma_fence_chain_contained(iter),
++ error);
+ }
+
+ trace_xe_sched_job_set_error(job);
+@@ -233,9 +219,9 @@ bool xe_sched_job_started(struct xe_sched_job *job)
+ {
+ struct xe_lrc *lrc = job->q->lrc;
+
+- return !__dma_fence_is_later(xe_sched_job_seqno(job),
++ return !__dma_fence_is_later(xe_sched_job_lrc_seqno(job),
+ xe_lrc_start_seqno(lrc),
+- job->fence->ops);
++ dma_fence_chain_contained(job->fence)->ops);
+ }
+
+ bool xe_sched_job_completed(struct xe_sched_job *job)
+@@ -247,14 +233,26 @@ bool xe_sched_job_completed(struct xe_sched_job *job)
+ * parallel handshake is done.
+ */
+
+- return !__dma_fence_is_later(xe_sched_job_seqno(job), xe_lrc_seqno(lrc),
+- job->fence->ops);
++ return !__dma_fence_is_later(xe_sched_job_lrc_seqno(job),
++ xe_lrc_seqno(lrc),
++ dma_fence_chain_contained(job->fence)->ops);
+ }
+
+ void xe_sched_job_arm(struct xe_sched_job *job)
+ {
+ struct xe_exec_queue *q = job->q;
++ struct dma_fence *fence, *prev;
+ struct xe_vm *vm = q->vm;
++ u64 seqno = 0;
++ int i;
++
++ /* Migration and kernel engines have their own locking */
++ if (IS_ENABLED(CONFIG_LOCKDEP) &&
++ !(q->flags & (EXEC_QUEUE_FLAG_KERNEL | EXEC_QUEUE_FLAG_VM))) {
++ lockdep_assert_held(&q->vm->lock);
++ if (!xe_vm_in_lr_mode(q->vm))
++ xe_vm_assert_held(q->vm);
++ }
+
+ if (vm && !xe_sched_job_is_migration(q) && !xe_vm_in_lr_mode(vm) &&
+ (vm->batch_invalidate_tlb || vm->tlb_flush_seqno != q->tlb_flush_seqno)) {
+@@ -263,6 +261,27 @@ void xe_sched_job_arm(struct xe_sched_job *job)
+ job->ring_ops_flush_tlb = true;
+ }
+
++ /* Arm the pre-allocated fences */
++ for (i = 0; i < q->width; prev = fence, ++i) {
++ struct dma_fence_chain *chain;
++
++ fence = job->ptrs[i].lrc_fence;
++ xe_lrc_init_seqno_fence(&q->lrc[i], fence);
++ job->ptrs[i].lrc_fence = NULL;
++ if (!i) {
++ job->lrc_seqno = fence->seqno;
++ continue;
++ } else {
++ xe_assert(gt_to_xe(q->gt), job->lrc_seqno == fence->seqno);
++ }
++
++ chain = job->ptrs[i - 1].chain_fence;
++ dma_fence_chain_init(chain, prev, fence, seqno++);
++ job->ptrs[i - 1].chain_fence = NULL;
++ fence = &chain->base;
++ }
++
++ job->fence = fence;
+ drm_sched_job_arm(&job->drm);
+ }
+
+@@ -322,7 +341,8 @@ xe_sched_job_snapshot_capture(struct xe_sched_job *job)
+
+ snapshot->batch_addr_len = q->width;
+ for (i = 0; i < q->width; i++)
+- snapshot->batch_addr[i] = xe_device_uncanonicalize_addr(xe, job->batch_addr[i]);
++ snapshot->batch_addr[i] =
++ xe_device_uncanonicalize_addr(xe, job->ptrs[i].batch_addr);
+
+ return snapshot;
+ }
+diff --git a/drivers/gpu/drm/xe/xe_sched_job.h b/drivers/gpu/drm/xe/xe_sched_job.h
+index c75018f4660dc..f362e28455dbf 100644
+--- a/drivers/gpu/drm/xe/xe_sched_job.h
++++ b/drivers/gpu/drm/xe/xe_sched_job.h
+@@ -70,7 +70,12 @@ to_xe_sched_job(struct drm_sched_job *drm)
+
+ static inline u32 xe_sched_job_seqno(struct xe_sched_job *job)
+ {
+- return job->fence->seqno;
++ return job->fence ? job->fence->seqno : 0;
++}
++
++static inline u32 xe_sched_job_lrc_seqno(struct xe_sched_job *job)
++{
++ return job->lrc_seqno;
+ }
+
+ static inline void
+diff --git a/drivers/gpu/drm/xe/xe_sched_job_types.h b/drivers/gpu/drm/xe/xe_sched_job_types.h
+index 5e12724219fdd..0d3f76fb05cea 100644
+--- a/drivers/gpu/drm/xe/xe_sched_job_types.h
++++ b/drivers/gpu/drm/xe/xe_sched_job_types.h
+@@ -11,6 +11,20 @@
+ #include <drm/gpu_scheduler.h>
+
+ struct xe_exec_queue;
++struct dma_fence;
++struct dma_fence_chain;
++
++/**
++ * struct xe_job_ptrs - Per hw engine instance data
++ */
++struct xe_job_ptrs {
++ /** @lrc_fence: Pre-allocated uinitialized lrc fence.*/
++ struct dma_fence *lrc_fence;
++ /** @chain_fence: Pre-allocated ninitialized fence chain node. */
++ struct dma_fence_chain *chain_fence;
++ /** @batch_addr: Batch buffer address. */
++ u64 batch_addr;
++};
+
+ /**
+ * struct xe_sched_job - XE schedule job (batch buffer tracking)
+@@ -37,12 +51,14 @@ struct xe_sched_job {
+ /** @user_fence.value: write back value */
+ u64 value;
+ } user_fence;
++ /** @lrc_seqno: LRC seqno */
++ u32 lrc_seqno;
+ /** @migrate_flush_flags: Additional flush flags for migration jobs */
+ u32 migrate_flush_flags;
+ /** @ring_ops_flush_tlb: The ring ops need to flush TLB before payload. */
+ bool ring_ops_flush_tlb;
+- /** @batch_addr: batch buffer address of job */
+- u64 batch_addr[];
++ /** @ptrs: per instance pointers. */
++ struct xe_job_ptrs ptrs[];
+ };
+
+ struct xe_sched_job_snapshot {
+diff --git a/drivers/gpu/drm/xe/xe_trace.h b/drivers/gpu/drm/xe/xe_trace.h
+index 2d56cfc09e421..e4cba64474e6d 100644
+--- a/drivers/gpu/drm/xe/xe_trace.h
++++ b/drivers/gpu/drm/xe/xe_trace.h
+@@ -254,6 +254,7 @@ DECLARE_EVENT_CLASS(xe_sched_job,
+
+ TP_STRUCT__entry(
+ __field(u32, seqno)
++ __field(u32, lrc_seqno)
+ __field(u16, guc_id)
+ __field(u32, guc_state)
+ __field(u32, flags)
+@@ -264,17 +265,19 @@ DECLARE_EVENT_CLASS(xe_sched_job,
+
+ TP_fast_assign(
+ __entry->seqno = xe_sched_job_seqno(job);
++ __entry->lrc_seqno = xe_sched_job_lrc_seqno(job);
+ __entry->guc_id = job->q->guc->id;
+ __entry->guc_state =
+ atomic_read(&job->q->guc->state);
+ __entry->flags = job->q->flags;
+- __entry->error = job->fence->error;
++ __entry->error = job->fence ? job->fence->error : 0;
+ __entry->fence = job->fence;
+- __entry->batch_addr = (u64)job->batch_addr[0];
++ __entry->batch_addr = (u64)job->ptrs[0].batch_addr;
+ ),
+
+- TP_printk("fence=%p, seqno=%u, guc_id=%d, batch_addr=0x%012llx, guc_state=0x%x, flags=0x%x, error=%d",
+- __entry->fence, __entry->seqno, __entry->guc_id,
++ TP_printk("fence=%p, seqno=%u, lrc_seqno=%u, guc_id=%d, batch_addr=0x%012llx, guc_state=0x%x, flags=0x%x, error=%d",
++ __entry->fence, __entry->seqno,
++ __entry->lrc_seqno, __entry->guc_id,
+ __entry->batch_addr, __entry->guc_state,
+ __entry->flags, __entry->error)
+ );
+diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
+index 20de97ce0f5ee..d84740be96426 100644
+--- a/drivers/hid/wacom_wac.c
++++ b/drivers/hid/wacom_wac.c
+@@ -1924,12 +1924,14 @@ static void wacom_map_usage(struct input_dev *input, struct hid_usage *usage,
+ int fmax = field->logical_maximum;
+ unsigned int equivalent_usage = wacom_equivalent_usage(usage->hid);
+ int resolution_code = code;
+- int resolution = hidinput_calc_abs_res(field, resolution_code);
++ int resolution;
+
+ if (equivalent_usage == HID_DG_TWIST) {
+ resolution_code = ABS_RZ;
+ }
+
++ resolution = hidinput_calc_abs_res(field, resolution_code);
++
+ if (equivalent_usage == HID_GD_X) {
+ fmin += features->offset_left;
+ fmax -= features->offset_right;
+diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
+index 365e37bba0f33..06e836e3e8773 100644
+--- a/drivers/i2c/busses/i2c-qcom-geni.c
++++ b/drivers/i2c/busses/i2c-qcom-geni.c
+@@ -986,8 +986,10 @@ static int __maybe_unused geni_i2c_runtime_resume(struct device *dev)
+ return ret;
+
+ ret = clk_prepare_enable(gi2c->core_clk);
+- if (ret)
++ if (ret) {
++ geni_icc_disable(&gi2c->se);
+ return ret;
++ }
+
+ ret = geni_se_resources_on(&gi2c->se);
+ if (ret) {
+diff --git a/drivers/i2c/busses/i2c-tegra.c b/drivers/i2c/busses/i2c-tegra.c
+index 85b31edc558df..1df5b42041427 100644
+--- a/drivers/i2c/busses/i2c-tegra.c
++++ b/drivers/i2c/busses/i2c-tegra.c
+@@ -1802,9 +1802,9 @@ static int tegra_i2c_probe(struct platform_device *pdev)
+ * domain.
+ *
+ * VI I2C device shouldn't be marked as IRQ-safe because VI I2C won't
+- * be used for atomic transfers.
++ * be used for atomic transfers. ACPI device is not IRQ safe also.
+ */
+- if (!IS_VI(i2c_dev))
++ if (!IS_VI(i2c_dev) && !has_acpi_companion(i2c_dev->dev))
+ pm_runtime_irq_safe(i2c_dev->dev);
+
+ pm_runtime_enable(i2c_dev->dev);
+diff --git a/drivers/input/input-mt.c b/drivers/input/input-mt.c
+index 14b53dac1253b..6b04a674f832a 100644
+--- a/drivers/input/input-mt.c
++++ b/drivers/input/input-mt.c
+@@ -46,6 +46,9 @@ int input_mt_init_slots(struct input_dev *dev, unsigned int num_slots,
+ return 0;
+ if (mt)
+ return mt->num_slots != num_slots ? -EINVAL : 0;
++ /* Arbitrary limit for avoiding too large memory allocation. */
++ if (num_slots > 1024)
++ return -EINVAL;
+
+ mt = kzalloc(struct_size(mt, slots, num_slots), GFP_KERNEL);
+ if (!mt)
+diff --git a/drivers/input/serio/i8042-acpipnpio.h b/drivers/input/serio/i8042-acpipnpio.h
+index 5b50475ec4140..e9eb9554dd7bd 100644
+--- a/drivers/input/serio/i8042-acpipnpio.h
++++ b/drivers/input/serio/i8042-acpipnpio.h
+@@ -83,6 +83,7 @@ static inline void i8042_write_command(int val)
+ #define SERIO_QUIRK_KBDRESET BIT(12)
+ #define SERIO_QUIRK_DRITEK BIT(13)
+ #define SERIO_QUIRK_NOPNP BIT(14)
++#define SERIO_QUIRK_FORCENORESTORE BIT(15)
+
+ /* Quirk table for different mainboards. Options similar or identical to i8042
+ * module parameters.
+@@ -1149,18 +1150,10 @@ static const struct dmi_system_id i8042_dmi_quirk_table[] __initconst = {
+ SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
+ },
+ {
+- /*
+- * Setting SERIO_QUIRK_NOMUX or SERIO_QUIRK_RESET_ALWAYS makes
+- * the keyboard very laggy for ~5 seconds after boot and
+- * sometimes also after resume.
+- * However both are required for the keyboard to not fail
+- * completely sometimes after boot or resume.
+- */
+ .matches = {
+ DMI_MATCH(DMI_BOARD_NAME, "N150CU"),
+ },
+- .driver_data = (void *)(SERIO_QUIRK_NOMUX | SERIO_QUIRK_RESET_ALWAYS |
+- SERIO_QUIRK_NOLOOP | SERIO_QUIRK_NOPNP)
++ .driver_data = (void *)(SERIO_QUIRK_FORCENORESTORE)
+ },
+ {
+ .matches = {
+@@ -1685,6 +1678,8 @@ static void __init i8042_check_quirks(void)
+ if (quirks & SERIO_QUIRK_NOPNP)
+ i8042_nopnp = true;
+ #endif
++ if (quirks & SERIO_QUIRK_FORCENORESTORE)
++ i8042_forcenorestore = true;
+ }
+ #else
+ static inline void i8042_check_quirks(void) {}
+@@ -1718,7 +1713,7 @@ static int __init i8042_platform_init(void)
+
+ i8042_check_quirks();
+
+- pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
++ pr_debug("Active quirks (empty means none):%s%s%s%s%s%s%s%s%s%s%s%s%s%s\n",
+ i8042_nokbd ? " nokbd" : "",
+ i8042_noaux ? " noaux" : "",
+ i8042_nomux ? " nomux" : "",
+@@ -1738,10 +1733,11 @@ static int __init i8042_platform_init(void)
+ "",
+ #endif
+ #ifdef CONFIG_PNP
+- i8042_nopnp ? " nopnp" : "");
++ i8042_nopnp ? " nopnp" : "",
+ #else
+- "");
++ "",
+ #endif
++ i8042_forcenorestore ? " forcenorestore" : "");
+
+ retval = i8042_pnp_init();
+ if (retval)
+diff --git a/drivers/input/serio/i8042.c b/drivers/input/serio/i8042.c
+index 9fbb8d31575ae..2233d93f90e81 100644
+--- a/drivers/input/serio/i8042.c
++++ b/drivers/input/serio/i8042.c
+@@ -115,6 +115,10 @@ module_param_named(nopnp, i8042_nopnp, bool, 0);
+ MODULE_PARM_DESC(nopnp, "Do not use PNP to detect controller settings");
+ #endif
+
++static bool i8042_forcenorestore;
++module_param_named(forcenorestore, i8042_forcenorestore, bool, 0);
++MODULE_PARM_DESC(forcenorestore, "Force no restore on s3 resume, copying s2idle behaviour");
++
+ #define DEBUG
+ #ifdef DEBUG
+ static bool i8042_debug;
+@@ -1232,7 +1236,7 @@ static int i8042_pm_suspend(struct device *dev)
+ {
+ int i;
+
+- if (pm_suspend_via_firmware())
++ if (!i8042_forcenorestore && pm_suspend_via_firmware())
+ i8042_controller_reset(true);
+
+ /* Set up serio interrupts for system wakeup. */
+@@ -1248,7 +1252,7 @@ static int i8042_pm_suspend(struct device *dev)
+
+ static int i8042_pm_resume_noirq(struct device *dev)
+ {
+- if (!pm_resume_via_firmware())
++ if (i8042_forcenorestore || !pm_resume_via_firmware())
+ i8042_interrupt(0, NULL);
+
+ return 0;
+@@ -1271,7 +1275,7 @@ static int i8042_pm_resume(struct device *dev)
+ * not restore the controller state to whatever it had been at boot
+ * time, so we do not need to do anything.
+ */
+- if (!pm_suspend_via_firmware())
++ if (i8042_forcenorestore || !pm_suspend_via_firmware())
+ return 0;
+
+ /*
+diff --git a/drivers/iommu/io-pgfault.c b/drivers/iommu/io-pgfault.c
+index 06d78fcc79fdb..f2c87c695a17c 100644
+--- a/drivers/iommu/io-pgfault.c
++++ b/drivers/iommu/io-pgfault.c
+@@ -192,6 +192,7 @@ void iommu_report_device_fault(struct device *dev, struct iopf_fault *evt)
+ report_partial_fault(iopf_param, fault);
+ iopf_put_dev_fault_param(iopf_param);
+ /* A request that is not the last does not need to be ack'd */
++ return;
+ }
+
+ /*
+diff --git a/drivers/iommu/iommufd/device.c b/drivers/iommu/iommufd/device.c
+index 873630c111c1f..e333793e88eb7 100644
+--- a/drivers/iommu/iommufd/device.c
++++ b/drivers/iommu/iommufd/device.c
+@@ -525,7 +525,7 @@ iommufd_device_do_replace(struct iommufd_device *idev,
+ err_unresv:
+ if (hwpt_is_paging(hwpt))
+ iommufd_group_remove_reserved_iova(igroup,
+- to_hwpt_paging(old_hwpt));
++ to_hwpt_paging(hwpt));
+ err_unlock:
+ mutex_unlock(&idev->igroup->lock);
+ return ERR_PTR(rc);
+diff --git a/drivers/md/dm-ioctl.c b/drivers/md/dm-ioctl.c
+index c2c07bfa64719..f299ff393a6a2 100644
+--- a/drivers/md/dm-ioctl.c
++++ b/drivers/md/dm-ioctl.c
+@@ -1181,8 +1181,26 @@ static int do_resume(struct dm_ioctl *param)
+ suspend_flags &= ~DM_SUSPEND_LOCKFS_FLAG;
+ if (param->flags & DM_NOFLUSH_FLAG)
+ suspend_flags |= DM_SUSPEND_NOFLUSH_FLAG;
+- if (!dm_suspended_md(md))
+- dm_suspend(md, suspend_flags);
++ if (!dm_suspended_md(md)) {
++ r = dm_suspend(md, suspend_flags);
++ if (r) {
++ down_write(&_hash_lock);
++ hc = dm_get_mdptr(md);
++ if (hc && !hc->new_map) {
++ hc->new_map = new_map;
++ new_map = NULL;
++ } else {
++ r = -ENXIO;
++ }
++ up_write(&_hash_lock);
++ if (new_map) {
++ dm_sync_table(md);
++ dm_table_destroy(new_map);
++ }
++ dm_put(md);
++ return r;
++ }
++ }
+
+ old_size = dm_get_size(md);
+ old_map = dm_swap_table(md, new_map);
+diff --git a/drivers/md/dm.c b/drivers/md/dm.c
+index 13037d6a6f62a..6e15ac4e0845c 100644
+--- a/drivers/md/dm.c
++++ b/drivers/md/dm.c
+@@ -2594,7 +2594,7 @@ static int dm_wait_for_bios_completion(struct mapped_device *md, unsigned int ta
+ break;
+
+ if (signal_pending_state(task_state, current)) {
+- r = -EINTR;
++ r = -ERESTARTSYS;
+ break;
+ }
+
+@@ -2619,7 +2619,7 @@ static int dm_wait_for_completion(struct mapped_device *md, unsigned int task_st
+ break;
+
+ if (signal_pending_state(task_state, current)) {
+- r = -EINTR;
++ r = -ERESTARTSYS;
+ break;
+ }
+
+diff --git a/drivers/md/persistent-data/dm-space-map-metadata.c b/drivers/md/persistent-data/dm-space-map-metadata.c
+index 04698fd03e606..d48c4fafc7798 100644
+--- a/drivers/md/persistent-data/dm-space-map-metadata.c
++++ b/drivers/md/persistent-data/dm-space-map-metadata.c
+@@ -277,7 +277,7 @@ static void sm_metadata_destroy(struct dm_space_map *sm)
+ {
+ struct sm_metadata *smm = container_of(sm, struct sm_metadata, sm);
+
+- kfree(smm);
++ kvfree(smm);
+ }
+
+ static int sm_metadata_get_nr_blocks(struct dm_space_map *sm, dm_block_t *count)
+@@ -772,7 +772,7 @@ struct dm_space_map *dm_sm_metadata_init(void)
+ {
+ struct sm_metadata *smm;
+
+- smm = kmalloc(sizeof(*smm), GFP_KERNEL);
++ smm = kvmalloc(sizeof(*smm), GFP_KERNEL);
+ if (!smm)
+ return ERR_PTR(-ENOMEM);
+
+diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
+index 5ea57b6748c53..687bd374cde89 100644
+--- a/drivers/md/raid1.c
++++ b/drivers/md/raid1.c
+@@ -617,6 +617,12 @@ static int choose_first_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+ return -1;
+ }
+
++static bool rdev_in_recovery(struct md_rdev *rdev, struct r1bio *r1_bio)
++{
++ return !test_bit(In_sync, &rdev->flags) &&
++ rdev->recovery_offset < r1_bio->sector + r1_bio->sectors;
++}
++
+ static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+ int *max_sectors)
+ {
+@@ -635,6 +641,7 @@ static int choose_bb_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+
+ rdev = conf->mirrors[disk].rdev;
+ if (!rdev || test_bit(Faulty, &rdev->flags) ||
++ rdev_in_recovery(rdev, r1_bio) ||
+ test_bit(WriteMostly, &rdev->flags))
+ continue;
+
+@@ -673,7 +680,8 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+
+ rdev = conf->mirrors[disk].rdev;
+ if (!rdev || test_bit(Faulty, &rdev->flags) ||
+- !test_bit(WriteMostly, &rdev->flags))
++ !test_bit(WriteMostly, &rdev->flags) ||
++ rdev_in_recovery(rdev, r1_bio))
+ continue;
+
+ /* there are no bad blocks, we can use this disk */
+@@ -733,9 +741,7 @@ static bool rdev_readable(struct md_rdev *rdev, struct r1bio *r1_bio)
+ if (!rdev || test_bit(Faulty, &rdev->flags))
+ return false;
+
+- /* still in recovery */
+- if (!test_bit(In_sync, &rdev->flags) &&
+- rdev->recovery_offset < r1_bio->sector + r1_bio->sectors)
++ if (rdev_in_recovery(rdev, r1_bio))
+ return false;
+
+ /* don't read from slow disk unless have to */
+diff --git a/drivers/misc/fastrpc.c b/drivers/misc/fastrpc.c
+index a7a2bcedb37e4..5680856c0fb82 100644
+--- a/drivers/misc/fastrpc.c
++++ b/drivers/misc/fastrpc.c
+@@ -2087,16 +2087,6 @@ static int fastrpc_req_mem_map(struct fastrpc_user *fl, char __user *argp)
+ return err;
+ }
+
+-static int is_attach_rejected(struct fastrpc_user *fl)
+-{
+- /* Check if the device node is non-secure */
+- if (!fl->is_secure_dev) {
+- dev_dbg(&fl->cctx->rpdev->dev, "untrusted app trying to attach to privileged DSP PD\n");
+- return -EACCES;
+- }
+- return 0;
+-}
+-
+ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
+ unsigned long arg)
+ {
+@@ -2109,19 +2099,13 @@ static long fastrpc_device_ioctl(struct file *file, unsigned int cmd,
+ err = fastrpc_invoke(fl, argp);
+ break;
+ case FASTRPC_IOCTL_INIT_ATTACH:
+- err = is_attach_rejected(fl);
+- if (!err)
+- err = fastrpc_init_attach(fl, ROOT_PD);
++ err = fastrpc_init_attach(fl, ROOT_PD);
+ break;
+ case FASTRPC_IOCTL_INIT_ATTACH_SNS:
+- err = is_attach_rejected(fl);
+- if (!err)
+- err = fastrpc_init_attach(fl, SENSORS_PD);
++ err = fastrpc_init_attach(fl, SENSORS_PD);
+ break;
+ case FASTRPC_IOCTL_INIT_CREATE_STATIC:
+- err = is_attach_rejected(fl);
+- if (!err)
+- err = fastrpc_init_create_static_process(fl, argp);
++ err = fastrpc_init_create_static_process(fl, argp);
+ break;
+ case FASTRPC_IOCTL_INIT_CREATE:
+ err = fastrpc_init_create_process(fl, argp);
+diff --git a/drivers/mmc/core/mmc_test.c b/drivers/mmc/core/mmc_test.c
+index 8f7f587a0025b..b7f627a9fdeab 100644
+--- a/drivers/mmc/core/mmc_test.c
++++ b/drivers/mmc/core/mmc_test.c
+@@ -3125,13 +3125,13 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,
+ test->buffer = kzalloc(BUFFER_SIZE, GFP_KERNEL);
+ #ifdef CONFIG_HIGHMEM
+ test->highmem = alloc_pages(GFP_KERNEL | __GFP_HIGHMEM, BUFFER_ORDER);
++ if (!test->highmem) {
++ count = -ENOMEM;
++ goto free_test_buffer;
++ }
+ #endif
+
+-#ifdef CONFIG_HIGHMEM
+- if (test->buffer && test->highmem) {
+-#else
+ if (test->buffer) {
+-#endif
+ mutex_lock(&mmc_test_lock);
+ mmc_test_run(test, testcase);
+ mutex_unlock(&mmc_test_lock);
+@@ -3139,6 +3139,7 @@ static ssize_t mtf_test_write(struct file *file, const char __user *buf,
+
+ #ifdef CONFIG_HIGHMEM
+ __free_pages(test->highmem, BUFFER_ORDER);
++free_test_buffer:
+ #endif
+ kfree(test->buffer);
+ kfree(test);
+diff --git a/drivers/mmc/host/dw_mmc.c b/drivers/mmc/host/dw_mmc.c
+index 8e2d676b92399..a4f813ea177a8 100644
+--- a/drivers/mmc/host/dw_mmc.c
++++ b/drivers/mmc/host/dw_mmc.c
+@@ -3293,6 +3293,10 @@ int dw_mci_probe(struct dw_mci *host)
+ host->biu_clk = devm_clk_get(host->dev, "biu");
+ if (IS_ERR(host->biu_clk)) {
+ dev_dbg(host->dev, "biu clock not available\n");
++ ret = PTR_ERR(host->biu_clk);
++ if (ret == -EPROBE_DEFER)
++ return ret;
++
+ } else {
+ ret = clk_prepare_enable(host->biu_clk);
+ if (ret) {
+@@ -3304,6 +3308,10 @@ int dw_mci_probe(struct dw_mci *host)
+ host->ciu_clk = devm_clk_get(host->dev, "ciu");
+ if (IS_ERR(host->ciu_clk)) {
+ dev_dbg(host->dev, "ciu clock not available\n");
++ ret = PTR_ERR(host->ciu_clk);
++ if (ret == -EPROBE_DEFER)
++ goto err_clk_biu;
++
+ host->bus_hz = host->pdata->bus_hz;
+ } else {
+ ret = clk_prepare_enable(host->ciu_clk);
+diff --git a/drivers/mmc/host/mtk-sd.c b/drivers/mmc/host/mtk-sd.c
+index a94835b8ab939..e386f78e32679 100644
+--- a/drivers/mmc/host/mtk-sd.c
++++ b/drivers/mmc/host/mtk-sd.c
+@@ -1230,7 +1230,7 @@ static bool msdc_cmd_done(struct msdc_host *host, int events,
+ }
+
+ if (!sbc_error && !(events & MSDC_INT_CMDRDY)) {
+- if (events & MSDC_INT_CMDTMO ||
++ if ((events & MSDC_INT_CMDTMO && !host->hs400_tuning) ||
+ (!mmc_op_tuning(cmd->opcode) && !host->hs400_tuning))
+ /*
+ * should not clear fifo/interrupt as the tune data
+@@ -1323,9 +1323,9 @@ static void msdc_start_command(struct msdc_host *host,
+ static void msdc_cmd_next(struct msdc_host *host,
+ struct mmc_request *mrq, struct mmc_command *cmd)
+ {
+- if ((cmd->error &&
+- !(cmd->error == -EILSEQ &&
+- (mmc_op_tuning(cmd->opcode) || host->hs400_tuning))) ||
++ if ((cmd->error && !host->hs400_tuning &&
++ !(cmd->error == -EILSEQ &&
++ mmc_op_tuning(cmd->opcode))) ||
+ (mrq->sbc && mrq->sbc->error))
+ msdc_request_done(host, mrq);
+ else if (cmd == mrq->sbc)
+diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
+index 2ed0da0684906..b257504a85347 100644
+--- a/drivers/net/bonding/bond_main.c
++++ b/drivers/net/bonding/bond_main.c
+@@ -582,7 +582,6 @@ static void bond_ipsec_del_sa_all(struct bonding *bond)
+ } else {
+ slave->dev->xfrmdev_ops->xdo_dev_state_delete(ipsec->xs);
+ }
+- ipsec->xs->xso.real_dev = NULL;
+ }
+ spin_unlock_bh(&bond->ipsec_lock);
+ rcu_read_unlock();
+@@ -599,34 +598,30 @@ static bool bond_ipsec_offload_ok(struct sk_buff *skb, struct xfrm_state *xs)
+ struct net_device *real_dev;
+ struct slave *curr_active;
+ struct bonding *bond;
+- int err;
++ bool ok = false;
+
+ bond = netdev_priv(bond_dev);
+ rcu_read_lock();
+ curr_active = rcu_dereference(bond->curr_active_slave);
++ if (!curr_active)
++ goto out;
+ real_dev = curr_active->dev;
+
+- if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP) {
+- err = false;
++ if (BOND_MODE(bond) != BOND_MODE_ACTIVEBACKUP)
+ goto out;
+- }
+
+- if (!xs->xso.real_dev) {
+- err = false;
++ if (!xs->xso.real_dev)
+ goto out;
+- }
+
+ if (!real_dev->xfrmdev_ops ||
+ !real_dev->xfrmdev_ops->xdo_dev_offload_ok ||
+- netif_is_bond_master(real_dev)) {
+- err = false;
++ netif_is_bond_master(real_dev))
+ goto out;
+- }
+
+- err = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
++ ok = real_dev->xfrmdev_ops->xdo_dev_offload_ok(skb, xs);
+ out:
+ rcu_read_unlock();
+- return err;
++ return ok;
+ }
+
+ static const struct xfrmdev_ops bond_xfrmdev_ops = {
+diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c
+index bc80fb6397dcd..95d59a18c0223 100644
+--- a/drivers/net/bonding/bond_options.c
++++ b/drivers/net/bonding/bond_options.c
+@@ -936,7 +936,7 @@ static int bond_option_active_slave_set(struct bonding *bond,
+ /* check to see if we are clearing active */
+ if (!slave_dev) {
+ netdev_dbg(bond->dev, "Clearing current active slave\n");
+- RCU_INIT_POINTER(bond->curr_active_slave, NULL);
++ bond_change_active_slave(bond, NULL);
+ bond_select_active_slave(bond);
+ } else {
+ struct slave *old_active = rtnl_dereference(bond->curr_active_slave);
+diff --git a/drivers/net/dsa/microchip/ksz_ptp.c b/drivers/net/dsa/microchip/ksz_ptp.c
+index 1fe105913c758..beb969f391be5 100644
+--- a/drivers/net/dsa/microchip/ksz_ptp.c
++++ b/drivers/net/dsa/microchip/ksz_ptp.c
+@@ -266,7 +266,6 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
+ struct ksz_port *prt;
+ struct dsa_port *dp;
+ bool tag_en = false;
+- int ret;
+
+ dsa_switch_for_each_user_port(dp, dev->ds) {
+ prt = &dev->ports[dp->index];
+@@ -277,9 +276,7 @@ static int ksz_ptp_enable_mode(struct ksz_device *dev)
+ }
+
+ if (tag_en) {
+- ret = ptp_schedule_worker(ptp_data->clock, 0);
+- if (ret)
+- return ret;
++ ptp_schedule_worker(ptp_data->clock, 0);
+ } else {
+ ptp_cancel_worker_sync(ptp_data->clock);
+ }
+diff --git a/drivers/net/dsa/mv88e6xxx/global1_atu.c b/drivers/net/dsa/mv88e6xxx/global1_atu.c
+index ce3b3690c3c05..c47f068f56b32 100644
+--- a/drivers/net/dsa/mv88e6xxx/global1_atu.c
++++ b/drivers/net/dsa/mv88e6xxx/global1_atu.c
+@@ -457,7 +457,8 @@ static irqreturn_t mv88e6xxx_g1_atu_prob_irq_thread_fn(int irq, void *dev_id)
+ trace_mv88e6xxx_atu_full_violation(chip->dev, spid,
+ entry.portvec, entry.mac,
+ fid);
+- chip->ports[spid].atu_full_violation++;
++ if (spid < ARRAY_SIZE(chip->ports))
++ chip->ports[spid].atu_full_violation++;
+ }
+
+ return IRQ_HANDLED;
+diff --git a/drivers/net/dsa/ocelot/felix.c b/drivers/net/dsa/ocelot/felix.c
+index 61e95487732dc..f5d26e724ae65 100644
+--- a/drivers/net/dsa/ocelot/felix.c
++++ b/drivers/net/dsa/ocelot/felix.c
+@@ -528,7 +528,9 @@ static int felix_tag_8021q_setup(struct dsa_switch *ds)
+ * so we need to be careful that there are no extra frames to be
+ * dequeued over MMIO, since we would never know to discard them.
+ */
++ ocelot_lock_xtr_grp_bh(ocelot, 0);
+ ocelot_drain_cpu_queue(ocelot, 0);
++ ocelot_unlock_xtr_grp_bh(ocelot, 0);
+
+ return 0;
+ }
+@@ -1504,6 +1506,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
+ int port = xmit_work->dp->index;
+ int retries = 10;
+
++ ocelot_lock_inj_grp(ocelot, 0);
++
+ do {
+ if (ocelot_can_inject(ocelot, 0))
+ break;
+@@ -1512,6 +1516,7 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
+ } while (--retries);
+
+ if (!retries) {
++ ocelot_unlock_inj_grp(ocelot, 0);
+ dev_err(ocelot->dev, "port %d failed to inject skb\n",
+ port);
+ ocelot_port_purge_txtstamp_skb(ocelot, port, skb);
+@@ -1521,6 +1526,8 @@ static void felix_port_deferred_xmit(struct kthread_work *work)
+
+ ocelot_port_inject_frame(ocelot, port, 0, rew_op, skb);
+
++ ocelot_unlock_inj_grp(ocelot, 0);
++
+ consume_skb(skb);
+ kfree(xmit_work);
+ }
+@@ -1671,6 +1678,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
+ if (!felix->info->quirk_no_xtr_irq)
+ return false;
+
++ ocelot_lock_xtr_grp(ocelot, grp);
++
+ while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
+ struct sk_buff *skb;
+ unsigned int type;
+@@ -1707,6 +1716,8 @@ static bool felix_check_xtr_pkt(struct ocelot *ocelot)
+ ocelot_drain_cpu_queue(ocelot, 0);
+ }
+
++ ocelot_unlock_xtr_grp(ocelot, grp);
++
+ return true;
+ }
+
+diff --git a/drivers/net/dsa/vitesse-vsc73xx-core.c b/drivers/net/dsa/vitesse-vsc73xx-core.c
+index 4b031fefcec68..56bb77dbd28a2 100644
+--- a/drivers/net/dsa/vitesse-vsc73xx-core.c
++++ b/drivers/net/dsa/vitesse-vsc73xx-core.c
+@@ -38,6 +38,10 @@
+ #define VSC73XX_BLOCK_ARBITER 0x5 /* Only subblock 0 */
+ #define VSC73XX_BLOCK_SYSTEM 0x7 /* Only subblock 0 */
+
++/* MII Block subblock */
++#define VSC73XX_BLOCK_MII_INTERNAL 0x0 /* Internal MDIO subblock */
++#define VSC73XX_BLOCK_MII_EXTERNAL 0x1 /* External MDIO subblock */
++
+ #define CPU_PORT 6 /* CPU port */
+
+ /* MAC Block registers */
+@@ -196,6 +200,8 @@
+ #define VSC73XX_MII_CMD 0x1
+ #define VSC73XX_MII_DATA 0x2
+
++#define VSC73XX_MII_STAT_BUSY BIT(3)
++
+ /* Arbiter block 5 registers */
+ #define VSC73XX_ARBEMPTY 0x0c
+ #define VSC73XX_ARBDISC 0x0e
+@@ -270,6 +276,7 @@
+ #define IS_739X(a) (IS_7395(a) || IS_7398(a))
+
+ #define VSC73XX_POLL_SLEEP_US 1000
++#define VSC73XX_MDIO_POLL_SLEEP_US 5
+ #define VSC73XX_POLL_TIMEOUT_US 10000
+
+ struct vsc73xx_counter {
+@@ -487,6 +494,22 @@ static int vsc73xx_detect(struct vsc73xx *vsc)
+ return 0;
+ }
+
++static int vsc73xx_mdio_busy_check(struct vsc73xx *vsc)
++{
++ int ret, err;
++ u32 val;
++
++ ret = read_poll_timeout(vsc73xx_read, err,
++ err < 0 || !(val & VSC73XX_MII_STAT_BUSY),
++ VSC73XX_MDIO_POLL_SLEEP_US,
++ VSC73XX_POLL_TIMEOUT_US, false, vsc,
++ VSC73XX_BLOCK_MII, VSC73XX_BLOCK_MII_INTERNAL,
++ VSC73XX_MII_STAT, &val);
++ if (ret)
++ return ret;
++ return err;
++}
++
+ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
+ {
+ struct vsc73xx *vsc = ds->priv;
+@@ -494,12 +517,20 @@ static int vsc73xx_phy_read(struct dsa_switch *ds, int phy, int regnum)
+ u32 val;
+ int ret;
+
++ ret = vsc73xx_mdio_busy_check(vsc);
++ if (ret)
++ return ret;
++
+ /* Setting bit 26 means "read" */
+ cmd = BIT(26) | (phy << 21) | (regnum << 16);
+ ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+ if (ret)
+ return ret;
+- msleep(2);
++
++ ret = vsc73xx_mdio_busy_check(vsc);
++ if (ret)
++ return ret;
++
+ ret = vsc73xx_read(vsc, VSC73XX_BLOCK_MII, 0, 2, &val);
+ if (ret)
+ return ret;
+@@ -523,6 +554,10 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
+ u32 cmd;
+ int ret;
+
++ ret = vsc73xx_mdio_busy_check(vsc);
++ if (ret)
++ return ret;
++
+ /* It was found through tedious experiments that this router
+ * chip really hates to have it's PHYs reset. They
+ * never recover if that happens: autonegotiation stops
+@@ -534,7 +569,7 @@ static int vsc73xx_phy_write(struct dsa_switch *ds, int phy, int regnum,
+ return 0;
+ }
+
+- cmd = (phy << 21) | (regnum << 16);
++ cmd = (phy << 21) | (regnum << 16) | val;
+ ret = vsc73xx_write(vsc, VSC73XX_BLOCK_MII, 0, 1, cmd);
+ if (ret)
+ return ret;
+@@ -817,6 +852,11 @@ static void vsc73xx_mac_link_up(struct phylink_config *config,
+
+ if (duplex == DUPLEX_FULL)
+ val |= VSC73XX_MAC_CFG_FDX;
++ else
++ /* In datasheet description ("Port Mode Procedure" in 5.6.2)
++ * this bit is configured only for half duplex.
++ */
++ val |= VSC73XX_MAC_CFG_WEXC_DIS;
+
+ /* This routine is described in the datasheet (below ARBDISC register
+ * description)
+@@ -827,7 +867,6 @@ static void vsc73xx_mac_link_up(struct phylink_config *config,
+ get_random_bytes(&seed, 1);
+ val |= seed << VSC73XX_MAC_CFG_SEED_OFFSET;
+ val |= VSC73XX_MAC_CFG_SEED_LOAD;
+- val |= VSC73XX_MAC_CFG_WEXC_DIS;
+ vsc73xx_write(vsc, VSC73XX_BLOCK_MAC, port, VSC73XX_MAC_CFG, val);
+
+ /* Flow control for the PHY facing ports:
+diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+index 345681d5007e3..f88b641533fcc 100644
+--- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
++++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c
+@@ -297,11 +297,6 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons,
+ * redirect is coming from a frame received by the
+ * bnxt_en driver.
+ */
+- rx_buf = &rxr->rx_buf_ring[cons];
+- mapping = rx_buf->mapping - bp->rx_dma_offset;
+- dma_unmap_page_attrs(&pdev->dev, mapping,
+- BNXT_RX_PAGE_SIZE, bp->rx_dir,
+- DMA_ATTR_WEAK_ORDERING);
+
+ /* if we are unable to allocate a new buffer, abort and reuse */
+ if (bnxt_alloc_rx_data(bp, rxr, rxr->rx_prod, GFP_ATOMIC)) {
+diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+index 786ceae344887..dd9e68465e697 100644
+--- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
++++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c
+@@ -1244,7 +1244,8 @@ static u64 hash_filter_ntuple(struct ch_filter_specification *fs,
+ * in the Compressed Filter Tuple.
+ */
+ if (tp->vlan_shift >= 0 && fs->mask.ivlan)
+- ntuple |= (FT_VLAN_VLD_F | fs->val.ivlan) << tp->vlan_shift;
++ ntuple |= (u64)(FT_VLAN_VLD_F |
++ fs->val.ivlan) << tp->vlan_shift;
+
+ if (tp->port_shift >= 0 && fs->mask.iport)
+ ntuple |= (u64)fs->val.iport << tp->port_shift;
+diff --git a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+index a71f848adc054..a293b08f36d46 100644
+--- a/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
++++ b/drivers/net/ethernet/freescale/dpaa2/dpaa2-switch.c
+@@ -2638,13 +2638,14 @@ static int dpaa2_switch_refill_bp(struct ethsw_core *ethsw)
+
+ static int dpaa2_switch_seed_bp(struct ethsw_core *ethsw)
+ {
+- int *count, i;
++ int *count, ret, i;
+
+ for (i = 0; i < DPAA2_ETHSW_NUM_BUFS; i += BUFS_PER_CMD) {
++ ret = dpaa2_switch_add_bufs(ethsw, ethsw->bpid);
+ count = ðsw->buf_count;
+- *count += dpaa2_switch_add_bufs(ethsw, ethsw->bpid);
++ *count += ret;
+
+- if (unlikely(*count < BUFS_PER_CMD))
++ if (unlikely(ret < BUFS_PER_CMD))
+ return -ENOMEM;
+ }
+
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+index a5fc0209d628e..4cbc4d069a1f3 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c
+@@ -5724,6 +5724,9 @@ static int hns3_reset_notify_uninit_enet(struct hnae3_handle *handle)
+ struct net_device *netdev = handle->kinfo.netdev;
+ struct hns3_nic_priv *priv = netdev_priv(netdev);
+
++ if (!test_bit(HNS3_NIC_STATE_DOWN, &priv->state))
++ hns3_nic_net_stop(netdev);
++
+ if (!test_and_clear_bit(HNS3_NIC_STATE_INITED, &priv->state)) {
+ netdev_warn(netdev, "already uninitialized\n");
+ return 0;
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+index 82574ce0194fb..465f0d5822837 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c
+@@ -2653,8 +2653,17 @@ static int hclge_cfg_mac_speed_dup_h(struct hnae3_handle *handle, int speed,
+ {
+ struct hclge_vport *vport = hclge_get_vport(handle);
+ struct hclge_dev *hdev = vport->back;
++ int ret;
++
++ ret = hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num);
++
++ if (ret)
++ return ret;
+
+- return hclge_cfg_mac_speed_dup(hdev, speed, duplex, lane_num);
++ hdev->hw.mac.req_speed = speed;
++ hdev->hw.mac.req_duplex = duplex;
++
++ return 0;
+ }
+
+ static int hclge_set_autoneg_en(struct hclge_dev *hdev, bool enable)
+@@ -2956,17 +2965,20 @@ static int hclge_mac_init(struct hclge_dev *hdev)
+ if (!test_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
+ hdev->hw.mac.duplex = HCLGE_MAC_FULL;
+
+- ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.speed,
+- hdev->hw.mac.duplex, hdev->hw.mac.lane_num);
+- if (ret)
+- return ret;
+-
+ if (hdev->hw.mac.support_autoneg) {
+ ret = hclge_set_autoneg_en(hdev, hdev->hw.mac.autoneg);
+ if (ret)
+ return ret;
+ }
+
++ if (!hdev->hw.mac.autoneg) {
++ ret = hclge_cfg_mac_speed_dup_hw(hdev, hdev->hw.mac.req_speed,
++ hdev->hw.mac.req_duplex,
++ hdev->hw.mac.lane_num);
++ if (ret)
++ return ret;
++ }
++
+ mac->link = 0;
+
+ if (mac->user_fec_mode & BIT(HNAE3_FEC_USER_DEF)) {
+@@ -11516,8 +11528,8 @@ static void hclge_reset_done(struct hnae3_ae_dev *ae_dev)
+ dev_err(&hdev->pdev->dev, "fail to rebuild, ret=%d\n", ret);
+
+ hdev->reset_type = HNAE3_NONE_RESET;
+- clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state);
+- up(&hdev->reset_sem);
++ if (test_and_clear_bit(HCLGE_STATE_RST_HANDLING, &hdev->state))
++ up(&hdev->reset_sem);
+ }
+
+ static void hclge_clear_resetting_state(struct hclge_dev *hdev)
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+index 85fb11de43a12..80079657afebe 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c
+@@ -191,6 +191,9 @@ static void hclge_mac_adjust_link(struct net_device *netdev)
+ if (ret)
+ netdev_err(netdev, "failed to adjust link.\n");
+
++ hdev->hw.mac.req_speed = (u32)speed;
++ hdev->hw.mac.req_duplex = (u8)duplex;
++
+ ret = hclge_cfg_flowctrl(hdev);
+ if (ret)
+ netdev_err(netdev, "failed to configure flow control.\n");
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+index 3735d2fed11f7..094a7c7b55921 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c
+@@ -1747,8 +1747,8 @@ static void hclgevf_reset_done(struct hnae3_ae_dev *ae_dev)
+ ret);
+
+ hdev->reset_type = HNAE3_NONE_RESET;
+- clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state);
+- up(&hdev->reset_sem);
++ if (test_and_clear_bit(HCLGEVF_STATE_RST_HANDLING, &hdev->state))
++ up(&hdev->reset_sem);
+ }
+
+ static u32 hclgevf_get_fw_version(struct hnae3_handle *handle)
+diff --git a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+index 13e6790d3cae7..afcf64dab48a1 100644
+--- a/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
++++ b/drivers/net/ethernet/intel/ice/devlink/devlink_port.c
+@@ -337,7 +337,7 @@ int ice_devlink_create_pf_port(struct ice_pf *pf)
+ return -EIO;
+
+ attrs.flavour = DEVLINK_PORT_FLAVOUR_PHYSICAL;
+- attrs.phys.port_number = pf->hw.bus.func;
++ attrs.phys.port_number = pf->hw.pf_id;
+
+ /* As FW supports only port split options for whole device,
+ * set port split options only for first PF.
+@@ -399,7 +399,7 @@ int ice_devlink_create_vf_port(struct ice_vf *vf)
+ return -EINVAL;
+
+ attrs.flavour = DEVLINK_PORT_FLAVOUR_PCI_VF;
+- attrs.pci_vf.pf = pf->hw.bus.func;
++ attrs.pci_vf.pf = pf->hw.pf_id;
+ attrs.pci_vf.vf = vf->vf_id;
+
+ ice_devlink_set_switch_id(pf, &attrs.switch_id);
+diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
+index 1facf179a96fd..f448d3a845642 100644
+--- a/drivers/net/ethernet/intel/ice/ice_base.c
++++ b/drivers/net/ethernet/intel/ice/ice_base.c
+@@ -512,6 +512,25 @@ static void ice_xsk_pool_fill_cb(struct ice_rx_ring *ring)
+ xsk_pool_fill_cb(ring->xsk_pool, &desc);
+ }
+
++/**
++ * ice_get_frame_sz - calculate xdp_buff::frame_sz
++ * @rx_ring: the ring being configured
++ *
++ * Return frame size based on underlying PAGE_SIZE
++ */
++static unsigned int ice_get_frame_sz(struct ice_rx_ring *rx_ring)
++{
++ unsigned int frame_sz;
++
++#if (PAGE_SIZE >= 8192)
++ frame_sz = rx_ring->rx_buf_len;
++#else
++ frame_sz = ice_rx_pg_size(rx_ring) / 2;
++#endif
++
++ return frame_sz;
++}
++
+ /**
+ * ice_vsi_cfg_rxq - Configure an Rx queue
+ * @ring: the ring being configured
+@@ -576,7 +595,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
+ }
+ }
+
+- xdp_init_buff(&ring->xdp, ice_rx_pg_size(ring) / 2, &ring->xdp_rxq);
++ xdp_init_buff(&ring->xdp, ice_get_frame_sz(ring), &ring->xdp_rxq);
+ ring->xdp.data = NULL;
+ ring->xdp_ext.pkt_ctx = &ring->pkt_ctx;
+ err = ice_setup_rx_ctx(ring);
+diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
+index 8d25b69812698..c9bc3f1add5d3 100644
+--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
++++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
+@@ -521,30 +521,6 @@ int ice_setup_rx_ring(struct ice_rx_ring *rx_ring)
+ return -ENOMEM;
+ }
+
+-/**
+- * ice_rx_frame_truesize
+- * @rx_ring: ptr to Rx ring
+- * @size: size
+- *
+- * calculate the truesize with taking into the account PAGE_SIZE of
+- * underlying arch
+- */
+-static unsigned int
+-ice_rx_frame_truesize(struct ice_rx_ring *rx_ring, const unsigned int size)
+-{
+- unsigned int truesize;
+-
+-#if (PAGE_SIZE < 8192)
+- truesize = ice_rx_pg_size(rx_ring) / 2; /* Must be power-of-2 */
+-#else
+- truesize = rx_ring->rx_offset ?
+- SKB_DATA_ALIGN(rx_ring->rx_offset + size) +
+- SKB_DATA_ALIGN(sizeof(struct skb_shared_info)) :
+- SKB_DATA_ALIGN(size);
+-#endif
+- return truesize;
+-}
+-
+ /**
+ * ice_run_xdp - Executes an XDP program on initialized xdp_buff
+ * @rx_ring: Rx ring
+@@ -837,16 +813,15 @@ ice_can_reuse_rx_page(struct ice_rx_buf *rx_buf)
+ if (!dev_page_is_reusable(page))
+ return false;
+
+-#if (PAGE_SIZE < 8192)
+ /* if we are only owner of page we can reuse it */
+ if (unlikely(rx_buf->pgcnt - pagecnt_bias > 1))
+ return false;
+-#else
++#if (PAGE_SIZE >= 8192)
+ #define ICE_LAST_OFFSET \
+- (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_2048)
++ (SKB_WITH_OVERHEAD(PAGE_SIZE) - ICE_RXBUF_3072)
+ if (rx_buf->page_offset > ICE_LAST_OFFSET)
+ return false;
+-#endif /* PAGE_SIZE < 8192) */
++#endif /* PAGE_SIZE >= 8192) */
+
+ /* If we have drained the page fragment pool we need to update
+ * the pagecnt_bias and page count so that we fully restock the
+@@ -949,12 +924,7 @@ ice_get_rx_buf(struct ice_rx_ring *rx_ring, const unsigned int size,
+ struct ice_rx_buf *rx_buf;
+
+ rx_buf = &rx_ring->rx_buf[ntc];
+- rx_buf->pgcnt =
+-#if (PAGE_SIZE < 8192)
+- page_count(rx_buf->page);
+-#else
+- 0;
+-#endif
++ rx_buf->pgcnt = page_count(rx_buf->page);
+ prefetchw(rx_buf->page);
+
+ if (!size)
+@@ -1160,11 +1130,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
+ bool failure;
+ u32 first;
+
+- /* Frame size depend on rx_ring setup when PAGE_SIZE=4K */
+-#if (PAGE_SIZE < 8192)
+- xdp->frame_sz = ice_rx_frame_truesize(rx_ring, 0);
+-#endif
+-
+ xdp_prog = READ_ONCE(rx_ring->xdp_prog);
+ if (xdp_prog) {
+ xdp_ring = rx_ring->xdp_ring;
+@@ -1223,10 +1188,6 @@ int ice_clean_rx_irq(struct ice_rx_ring *rx_ring, int budget)
+ hard_start = page_address(rx_buf->page) + rx_buf->page_offset -
+ offset;
+ xdp_prepare_buff(xdp, hard_start, offset, size, !!offset);
+-#if (PAGE_SIZE > 4096)
+- /* At larger PAGE_SIZE, frame_sz depend on len size */
+- xdp->frame_sz = ice_rx_frame_truesize(rx_ring, size);
+-#endif
+ xdp_buff_clear_frags_flag(xdp);
+ } else if (ice_add_xdp_frag(rx_ring, xdp, rx_buf, size)) {
+ break;
+diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c
+index fce2930ae6af7..b6aa449aa56af 100644
+--- a/drivers/net/ethernet/intel/igb/igb_main.c
++++ b/drivers/net/ethernet/intel/igb/igb_main.c
+@@ -4809,6 +4809,7 @@ static void igb_set_rx_buffer_len(struct igb_adapter *adapter,
+
+ #if (PAGE_SIZE < 8192)
+ if (adapter->max_frame_size > IGB_MAX_FRAME_BUILD_SKB ||
++ IGB_2K_TOO_SMALL_WITH_PADDING ||
+ rd32(E1000_RCTL) & E1000_RCTL_SBP)
+ set_ring_uses_large_buffer(rx_ring);
+ #endif
+diff --git a/drivers/net/ethernet/intel/igc/igc_defines.h b/drivers/net/ethernet/intel/igc/igc_defines.h
+index 5f92b3c7c3d4a..511384f3ec5cb 100644
+--- a/drivers/net/ethernet/intel/igc/igc_defines.h
++++ b/drivers/net/ethernet/intel/igc/igc_defines.h
+@@ -404,6 +404,12 @@
+ #define IGC_DTXMXPKTSZ_TSN 0x19 /* 1600 bytes of max TX DMA packet size */
+ #define IGC_DTXMXPKTSZ_DEFAULT 0x98 /* 9728-byte Jumbo frames */
+
++/* Retry Buffer Control */
++#define IGC_RETX_CTL 0x041C
++#define IGC_RETX_CTL_WATERMARK_MASK 0xF
++#define IGC_RETX_CTL_QBVFULLTH_SHIFT 8 /* QBV Retry Buffer Full Threshold */
++#define IGC_RETX_CTL_QBVFULLEN 0x1000 /* Enable QBV Retry Buffer Full Threshold */
++
+ /* Transmit Scheduling Latency */
+ /* Latency between transmission scheduling (LaunchTime) and the time
+ * the packet is transmitted to the network in nanosecond.
+diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
+index 33069880c86c0..3041f8142324f 100644
+--- a/drivers/net/ethernet/intel/igc/igc_main.c
++++ b/drivers/net/ethernet/intel/igc/igc_main.c
+@@ -6319,12 +6319,16 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
+ if (!validate_schedule(adapter, qopt))
+ return -EINVAL;
+
++ igc_ptp_read(adapter, &now);
++
++ if (igc_tsn_is_taprio_activated_by_user(adapter) &&
++ is_base_time_past(qopt->base_time, &now))
++ adapter->qbv_config_change_errors++;
++
+ adapter->cycle_time = qopt->cycle_time;
+ adapter->base_time = qopt->base_time;
+ adapter->taprio_offload_enable = true;
+
+- igc_ptp_read(adapter, &now);
+-
+ for (n = 0; n < qopt->num_entries; n++) {
+ struct tc_taprio_sched_entry *e = &qopt->entries[n];
+
+diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.c b/drivers/net/ethernet/intel/igc/igc_tsn.c
+index 22cefb1eeedfa..d68fa7f3d5f07 100644
+--- a/drivers/net/ethernet/intel/igc/igc_tsn.c
++++ b/drivers/net/ethernet/intel/igc/igc_tsn.c
+@@ -49,12 +49,19 @@ static unsigned int igc_tsn_new_flags(struct igc_adapter *adapter)
+ return new_flags;
+ }
+
++static bool igc_tsn_is_tx_mode_in_tsn(struct igc_adapter *adapter)
++{
++ struct igc_hw *hw = &adapter->hw;
++
++ return !!(rd32(IGC_TQAVCTRL) & IGC_TQAVCTRL_TRANSMIT_MODE_TSN);
++}
++
+ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter)
+ {
+ struct igc_hw *hw = &adapter->hw;
+ u16 txoffset;
+
+- if (!is_any_launchtime(adapter))
++ if (!igc_tsn_is_tx_mode_in_tsn(adapter))
+ return;
+
+ switch (adapter->link_speed) {
+@@ -78,6 +85,23 @@ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter)
+ wr32(IGC_GTXOFFSET, txoffset);
+ }
+
++static void igc_tsn_restore_retx_default(struct igc_adapter *adapter)
++{
++ struct igc_hw *hw = &adapter->hw;
++ u32 retxctl;
++
++ retxctl = rd32(IGC_RETX_CTL) & IGC_RETX_CTL_WATERMARK_MASK;
++ wr32(IGC_RETX_CTL, retxctl);
++}
++
++bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter)
++{
++ struct igc_hw *hw = &adapter->hw;
++
++ return (rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) &&
++ adapter->taprio_offload_enable;
++}
++
+ /* Returns the TSN specific registers to their default values after
+ * the adapter is reset.
+ */
+@@ -91,6 +115,9 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
+ wr32(IGC_TXPBS, I225_TXPBSIZE_DEFAULT);
+ wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_DEFAULT);
+
++ if (igc_is_device_id_i226(hw))
++ igc_tsn_restore_retx_default(adapter);
++
+ tqavctrl = rd32(IGC_TQAVCTRL);
+ tqavctrl &= ~(IGC_TQAVCTRL_TRANSMIT_MODE_TSN |
+ IGC_TQAVCTRL_ENHANCED_QAV | IGC_TQAVCTRL_FUTSCDDIS);
+@@ -111,6 +138,25 @@ static int igc_tsn_disable_offload(struct igc_adapter *adapter)
+ return 0;
+ }
+
++/* To partially fix i226 HW errata, reduce MAC internal buffering from 192 Bytes
++ * to 88 Bytes by setting RETX_CTL register using the recommendation from:
++ * a) Ethernet Controller I225/I226 Specification Update Rev 2.1
++ * Item 9: TSN: Packet Transmission Might Cross the Qbv Window
++ * b) I225/6 SW User Manual Rev 1.2.4: Section 8.11.5 Retry Buffer Control
++ */
++static void igc_tsn_set_retx_qbvfullthreshold(struct igc_adapter *adapter)
++{
++ struct igc_hw *hw = &adapter->hw;
++ u32 retxctl, watermark;
++
++ retxctl = rd32(IGC_RETX_CTL);
++ watermark = retxctl & IGC_RETX_CTL_WATERMARK_MASK;
++ /* Set QBVFULLTH value using watermark and set QBVFULLEN */
++ retxctl |= (watermark << IGC_RETX_CTL_QBVFULLTH_SHIFT) |
++ IGC_RETX_CTL_QBVFULLEN;
++ wr32(IGC_RETX_CTL, retxctl);
++}
++
+ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
+ {
+ struct igc_hw *hw = &adapter->hw;
+@@ -123,6 +169,9 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
+ wr32(IGC_DTXMXPKTSZ, IGC_DTXMXPKTSZ_TSN);
+ wr32(IGC_TXPBS, IGC_TXPBSIZE_TSN);
+
++ if (igc_is_device_id_i226(hw))
++ igc_tsn_set_retx_qbvfullthreshold(adapter);
++
+ for (i = 0; i < adapter->num_tx_queues; i++) {
+ struct igc_ring *ring = adapter->tx_ring[i];
+ u32 txqctl = 0;
+@@ -262,14 +311,6 @@ static int igc_tsn_enable_offload(struct igc_adapter *adapter)
+ s64 n = div64_s64(ktime_sub_ns(systim, base_time), cycle);
+
+ base_time = ktime_add_ns(base_time, (n + 1) * cycle);
+-
+- /* Increase the counter if scheduling into the past while
+- * Gate Control List (GCL) is running.
+- */
+- if ((rd32(IGC_BASET_H) || rd32(IGC_BASET_L)) &&
+- (adapter->tc_setup_type == TC_SETUP_QDISC_TAPRIO) &&
+- (adapter->qbv_count > 1))
+- adapter->qbv_config_change_errors++;
+ } else {
+ if (igc_is_device_id_i226(hw)) {
+ ktime_t adjust_time, expires_time;
+@@ -331,15 +372,22 @@ int igc_tsn_reset(struct igc_adapter *adapter)
+ return err;
+ }
+
+-int igc_tsn_offload_apply(struct igc_adapter *adapter)
++static bool igc_tsn_will_tx_mode_change(struct igc_adapter *adapter)
+ {
+- struct igc_hw *hw = &adapter->hw;
++ bool any_tsn_enabled = !!(igc_tsn_new_flags(adapter) &
++ IGC_FLAG_TSN_ANY_ENABLED);
+
+- /* Per I225/6 HW Design Section 7.5.2.1, transmit mode
+- * cannot be changed dynamically. Require reset the adapter.
++ return (any_tsn_enabled && !igc_tsn_is_tx_mode_in_tsn(adapter)) ||
++ (!any_tsn_enabled && igc_tsn_is_tx_mode_in_tsn(adapter));
++}
++
++int igc_tsn_offload_apply(struct igc_adapter *adapter)
++{
++ /* Per I225/6 HW Design Section 7.5.2.1 guideline, if tx mode change
++ * from legacy->tsn or tsn->legacy, then reset adapter is needed.
+ */
+ if (netif_running(adapter->netdev) &&
+- (igc_is_device_id_i225(hw) || !adapter->qbv_count)) {
++ igc_tsn_will_tx_mode_change(adapter)) {
+ schedule_work(&adapter->reset_task);
+ return 0;
+ }
+diff --git a/drivers/net/ethernet/intel/igc/igc_tsn.h b/drivers/net/ethernet/intel/igc/igc_tsn.h
+index b53e6af560b73..98ec845a86bf0 100644
+--- a/drivers/net/ethernet/intel/igc/igc_tsn.h
++++ b/drivers/net/ethernet/intel/igc/igc_tsn.h
+@@ -7,5 +7,6 @@
+ int igc_tsn_offload_apply(struct igc_adapter *adapter);
+ int igc_tsn_reset(struct igc_adapter *adapter);
+ void igc_tsn_adjust_txtime_offset(struct igc_adapter *adapter);
++bool igc_tsn_is_taprio_activated_by_user(struct igc_adapter *adapter);
+
+ #endif /* _IGC_BASE_H */
+diff --git a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+index 3e09d22858147..daf4b951e9059 100644
+--- a/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
++++ b/drivers/net/ethernet/marvell/octeontx2/af/rvu_cpt.c
+@@ -632,7 +632,9 @@ int rvu_mbox_handler_cpt_inline_ipsec_cfg(struct rvu *rvu,
+ return ret;
+ }
+
+-static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
++static bool validate_and_update_reg_offset(struct rvu *rvu,
++ struct cpt_rd_wr_reg_msg *req,
++ u64 *reg_offset)
+ {
+ u64 offset = req->reg_offset;
+ int blkaddr, num_lfs, lf;
+@@ -663,6 +665,11 @@ static bool is_valid_offset(struct rvu *rvu, struct cpt_rd_wr_reg_msg *req)
+ if (lf < 0)
+ return false;
+
++ /* Translate local LF's offset to global CPT LF's offset to
++ * access LFX register.
++ */
++ *reg_offset = (req->reg_offset & 0xFF000) + (lf << 3);
++
+ return true;
+ } else if (!(req->hdr.pcifunc & RVU_PFVF_FUNC_MASK)) {
+ /* Registers that can be accessed from PF */
+@@ -697,7 +704,7 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
+ struct cpt_rd_wr_reg_msg *rsp)
+ {
+ u64 offset = req->reg_offset;
+- int blkaddr, lf;
++ int blkaddr;
+
+ blkaddr = validate_and_get_cpt_blkaddr(req->blkaddr);
+ if (blkaddr < 0)
+@@ -708,18 +715,10 @@ int rvu_mbox_handler_cpt_rd_wr_register(struct rvu *rvu,
+ !is_cpt_vf(rvu, req->hdr.pcifunc))
+ return CPT_AF_ERR_ACCESS_DENIED;
+
+- if (!is_valid_offset(rvu, req))
++ if (!validate_and_update_reg_offset(rvu, req, &offset))
+ return CPT_AF_ERR_ACCESS_DENIED;
+
+- /* Translate local LF used by VFs to global CPT LF */
+- lf = rvu_get_lf(rvu, &rvu->hw->block[blkaddr], req->hdr.pcifunc,
+- (offset & 0xFFF) >> 3);
+-
+- /* Translate local LF's offset to global CPT LF's offset */
+- offset &= 0xFF000;
+- offset += lf << 3;
+-
+- rsp->reg_offset = offset;
++ rsp->reg_offset = req->reg_offset;
+ rsp->ret_val = req->ret_val;
+ rsp->is_write = req->is_write;
+
+diff --git a/drivers/net/ethernet/mediatek/mtk_wed.c b/drivers/net/ethernet/mediatek/mtk_wed.c
+index 61334a71058c7..e212a4ba92751 100644
+--- a/drivers/net/ethernet/mediatek/mtk_wed.c
++++ b/drivers/net/ethernet/mediatek/mtk_wed.c
+@@ -2666,14 +2666,15 @@ mtk_wed_setup_tc_block_cb(enum tc_setup_type type, void *type_data, void *cb_pri
+ {
+ struct mtk_wed_flow_block_priv *priv = cb_priv;
+ struct flow_cls_offload *cls = type_data;
+- struct mtk_wed_hw *hw = priv->hw;
++ struct mtk_wed_hw *hw = NULL;
+
+- if (!tc_can_offload(priv->dev))
++ if (!priv || !tc_can_offload(priv->dev))
+ return -EOPNOTSUPP;
+
+ if (type != TC_SETUP_CLSFLOWER)
+ return -EOPNOTSUPP;
+
++ hw = priv->hw;
+ return mtk_flow_offload_cmd(hw->eth, cls, hw->index);
+ }
+
+@@ -2729,6 +2730,7 @@ mtk_wed_setup_tc_block(struct mtk_wed_hw *hw, struct net_device *dev,
+ flow_block_cb_remove(block_cb, f);
+ list_del(&block_cb->driver_list);
+ kfree(block_cb->cb_priv);
++ block_cb->cb_priv = NULL;
+ }
+ return 0;
+ default:
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+index 22918b2ef7f12..09433b91be176 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en/reporter_tx.c
+@@ -146,7 +146,9 @@ static int mlx5e_tx_reporter_timeout_recover(void *ctx)
+ return err;
+ }
+
++ mutex_lock(&priv->state_lock);
+ err = mlx5e_safe_reopen_channels(priv);
++ mutex_unlock(&priv->state_lock);
+ if (!err) {
+ to_ctx->status = 1; /* all channels recovered */
+ return err;
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+index 3eccdadc03578..773624bb2c5d5 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_fs_ethtool.c
+@@ -734,7 +734,7 @@ mlx5e_ethtool_flow_replace(struct mlx5e_priv *priv,
+ if (num_tuples <= 0) {
+ netdev_warn(priv->netdev, "%s: flow is not valid %d\n",
+ __func__, num_tuples);
+- return num_tuples;
++ return num_tuples < 0 ? num_tuples : -EINVAL;
+ }
+
+ eth_ft = get_flow_table(priv, fs, num_tuples);
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+index eedbcba226894..409f525f1703c 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c
+@@ -3005,15 +3005,18 @@ int mlx5e_update_tx_netdev_queues(struct mlx5e_priv *priv)
+ static void mlx5e_set_default_xps_cpumasks(struct mlx5e_priv *priv,
+ struct mlx5e_params *params)
+ {
+- struct mlx5_core_dev *mdev = priv->mdev;
+- int num_comp_vectors, ix, irq;
+-
+- num_comp_vectors = mlx5_comp_vectors_max(mdev);
++ int ix;
+
+ for (ix = 0; ix < params->num_channels; ix++) {
++ int num_comp_vectors, irq, vec_ix;
++ struct mlx5_core_dev *mdev;
++
++ mdev = mlx5_sd_ch_ix_get_dev(priv->mdev, ix);
++ num_comp_vectors = mlx5_comp_vectors_max(mdev);
+ cpumask_clear(priv->scratchpad.cpumask);
++ vec_ix = mlx5_sd_ch_ix_get_vec_ix(mdev, ix);
+
+- for (irq = ix; irq < num_comp_vectors; irq += params->num_channels) {
++ for (irq = vec_ix; irq < num_comp_vectors; irq += params->num_channels) {
+ int cpu = mlx5_comp_vector_get_cpu(mdev, irq);
+
+ cpumask_set_cpu(cpu, priv->scratchpad.cpumask);
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
+index 234cd00f71a1c..b7d4b1a2baf2e 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/ipsec_fs_roce.c
+@@ -386,7 +386,8 @@ static int ipsec_fs_roce_tx_mpv_create(struct mlx5_core_dev *mdev,
+ return -EOPNOTSUPP;
+
+ peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp);
+- if (!peer_priv) {
++ if (!peer_priv || !peer_priv->ipsec) {
++ mlx5_core_err(mdev, "IPsec not supported on master device\n");
+ err = -EOPNOTSUPP;
+ goto release_peer;
+ }
+@@ -455,7 +456,8 @@ static int ipsec_fs_roce_rx_mpv_create(struct mlx5_core_dev *mdev,
+ return -EOPNOTSUPP;
+
+ peer_priv = mlx5_devcom_get_next_peer_data(*ipsec_roce->devcom, &tmp);
+- if (!peer_priv) {
++ if (!peer_priv || !peer_priv->ipsec) {
++ mlx5_core_err(mdev, "IPsec not supported on master device\n");
+ err = -EOPNOTSUPP;
+ goto release_peer;
+ }
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+index f6deb5a3f8202..eeb0b7ea05f12 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/lib/sd.c
+@@ -126,7 +126,7 @@ static bool mlx5_sd_is_supported(struct mlx5_core_dev *dev, u8 host_buses)
+ }
+
+ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm,
+- u8 *host_buses, u8 *sd_group)
++ u8 *host_buses)
+ {
+ u32 out[MLX5_ST_SZ_DW(mpir_reg)];
+ int err;
+@@ -135,10 +135,6 @@ static int mlx5_query_sd(struct mlx5_core_dev *dev, bool *sdm,
+ if (err)
+ return err;
+
+- err = mlx5_query_nic_vport_sd_group(dev, sd_group);
+- if (err)
+- return err;
+-
+ *sdm = MLX5_GET(mpir_reg, out, sdm);
+ *host_buses = MLX5_GET(mpir_reg, out, host_buses);
+
+@@ -166,19 +162,23 @@ static int sd_init(struct mlx5_core_dev *dev)
+ if (mlx5_core_is_ecpf(dev))
+ return 0;
+
++ err = mlx5_query_nic_vport_sd_group(dev, &sd_group);
++ if (err)
++ return err;
++
++ if (!sd_group)
++ return 0;
++
+ if (!MLX5_CAP_MCAM_REG(dev, mpir))
+ return 0;
+
+- err = mlx5_query_sd(dev, &sdm, &host_buses, &sd_group);
++ err = mlx5_query_sd(dev, &sdm, &host_buses);
+ if (err)
+ return err;
+
+ if (!sdm)
+ return 0;
+
+- if (!sd_group)
+- return 0;
+-
+ group_id = mlx5_sd_group_id(dev, sd_group);
+
+ if (!mlx5_sd_is_supported(dev, host_buses)) {
+diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
+index bc94e75a7aebd..e7777700ee18a 100644
+--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
++++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige.h
+@@ -40,6 +40,7 @@
+ */
+ #define MLXBF_GIGE_BCAST_MAC_FILTER_IDX 0
+ #define MLXBF_GIGE_LOCAL_MAC_FILTER_IDX 1
++#define MLXBF_GIGE_MAX_FILTER_IDX 3
+
+ /* Define for broadcast MAC literal */
+ #define BCAST_MAC_ADDR 0xFFFFFFFFFFFF
+@@ -175,6 +176,13 @@ enum mlxbf_gige_res {
+ int mlxbf_gige_mdio_probe(struct platform_device *pdev,
+ struct mlxbf_gige *priv);
+ void mlxbf_gige_mdio_remove(struct mlxbf_gige *priv);
++
++void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv);
++void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv);
++void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv,
++ unsigned int index);
++void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv,
++ unsigned int index);
+ void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
+ unsigned int index, u64 dmac);
+ void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv,
+diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+index b157f0f1c5a88..385a56ac73481 100644
+--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
++++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_main.c
+@@ -168,6 +168,10 @@ static int mlxbf_gige_open(struct net_device *netdev)
+ if (err)
+ goto napi_deinit;
+
++ mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_BCAST_MAC_FILTER_IDX);
++ mlxbf_gige_enable_mac_rx_filter(priv, MLXBF_GIGE_LOCAL_MAC_FILTER_IDX);
++ mlxbf_gige_enable_multicast_rx(priv);
++
+ /* Set bits in INT_EN that we care about */
+ int_en = MLXBF_GIGE_INT_EN_HW_ACCESS_ERROR |
+ MLXBF_GIGE_INT_EN_TX_CHECKSUM_INPUTS |
+@@ -379,6 +383,7 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
+ void __iomem *plu_base;
+ void __iomem *base;
+ int addr, phy_irq;
++ unsigned int i;
+ int err;
+
+ base = devm_platform_ioremap_resource(pdev, MLXBF_GIGE_RES_MAC);
+@@ -423,6 +428,11 @@ static int mlxbf_gige_probe(struct platform_device *pdev)
+ priv->rx_q_entries = MLXBF_GIGE_DEFAULT_RXQ_SZ;
+ priv->tx_q_entries = MLXBF_GIGE_DEFAULT_TXQ_SZ;
+
++ for (i = 0; i <= MLXBF_GIGE_MAX_FILTER_IDX; i++)
++ mlxbf_gige_disable_mac_rx_filter(priv, i);
++ mlxbf_gige_disable_multicast_rx(priv);
++ mlxbf_gige_disable_promisc(priv);
++
+ /* Write initial MAC address to hardware */
+ mlxbf_gige_initial_mac(priv);
+
+diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
+index 98a8681c21b9c..4d14cb13fd64e 100644
+--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
++++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_regs.h
+@@ -62,6 +62,8 @@
+ #define MLXBF_GIGE_TX_STATUS_DATA_FIFO_FULL BIT(1)
+ #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_START 0x0520
+ #define MLXBF_GIGE_RX_MAC_FILTER_DMAC_RANGE_END 0x0528
++#define MLXBF_GIGE_RX_MAC_FILTER_GENERAL 0x0530
++#define MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST BIT(1)
+ #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC 0x0540
+ #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_DISC_EN BIT(0)
+ #define MLXBF_GIGE_RX_MAC_FILTER_COUNT_PASS 0x0548
+diff --git a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
+index 6999843584934..eb62620b63c7f 100644
+--- a/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
++++ b/drivers/net/ethernet/mellanox/mlxbf_gige/mlxbf_gige_rx.c
+@@ -11,15 +11,31 @@
+ #include "mlxbf_gige.h"
+ #include "mlxbf_gige_regs.h"
+
+-void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
+- unsigned int index, u64 dmac)
++void mlxbf_gige_enable_multicast_rx(struct mlxbf_gige *priv)
+ {
+ void __iomem *base = priv->base;
+- u64 control;
++ u64 data;
+
+- /* Write destination MAC to specified MAC RX filter */
+- writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER +
+- (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE));
++ data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
++ data |= MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST;
++ writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
++}
++
++void mlxbf_gige_disable_multicast_rx(struct mlxbf_gige *priv)
++{
++ void __iomem *base = priv->base;
++ u64 data;
++
++ data = readq(base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
++ data &= ~MLXBF_GIGE_RX_MAC_FILTER_EN_MULTICAST;
++ writeq(data, base + MLXBF_GIGE_RX_MAC_FILTER_GENERAL);
++}
++
++void mlxbf_gige_enable_mac_rx_filter(struct mlxbf_gige *priv,
++ unsigned int index)
++{
++ void __iomem *base = priv->base;
++ u64 control;
+
+ /* Enable MAC receive filter mask for specified index */
+ control = readq(base + MLXBF_GIGE_CONTROL);
+@@ -27,6 +43,28 @@ void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
+ writeq(control, base + MLXBF_GIGE_CONTROL);
+ }
+
++void mlxbf_gige_disable_mac_rx_filter(struct mlxbf_gige *priv,
++ unsigned int index)
++{
++ void __iomem *base = priv->base;
++ u64 control;
++
++ /* Disable MAC receive filter mask for specified index */
++ control = readq(base + MLXBF_GIGE_CONTROL);
++ control &= ~(MLXBF_GIGE_CONTROL_EN_SPECIFIC_MAC << index);
++ writeq(control, base + MLXBF_GIGE_CONTROL);
++}
++
++void mlxbf_gige_set_mac_rx_filter(struct mlxbf_gige *priv,
++ unsigned int index, u64 dmac)
++{
++ void __iomem *base = priv->base;
++
++ /* Write destination MAC to specified MAC RX filter */
++ writeq(dmac, base + MLXBF_GIGE_RX_MAC_FILTER +
++ (index * MLXBF_GIGE_RX_MAC_FILTER_STRIDE));
++}
++
+ void mlxbf_gige_get_mac_rx_filter(struct mlxbf_gige *priv,
+ unsigned int index, u64 *dmac)
+ {
+diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
+index ad7ae7ba2b8fc..482b9cd369508 100644
+--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
+@@ -599,7 +599,11 @@ static void mana_get_rxbuf_cfg(int mtu, u32 *datasize, u32 *alloc_size,
+ else
+ *headroom = XDP_PACKET_HEADROOM;
+
+- *alloc_size = mtu + MANA_RXBUF_PAD + *headroom;
++ *alloc_size = SKB_DATA_ALIGN(mtu + MANA_RXBUF_PAD + *headroom);
++
++ /* Using page pool in this case, so alloc_size is PAGE_SIZE */
++ if (*alloc_size < PAGE_SIZE)
++ *alloc_size = PAGE_SIZE;
+
+ *datasize = mtu + ETH_HLEN;
+ }
+@@ -1773,7 +1777,6 @@ static void mana_poll_rx_cq(struct mana_cq *cq)
+ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
+ {
+ struct mana_cq *cq = context;
+- u8 arm_bit;
+ int w;
+
+ WARN_ON_ONCE(cq->gdma_cq != gdma_queue);
+@@ -1784,16 +1787,23 @@ static int mana_cq_handler(void *context, struct gdma_queue *gdma_queue)
+ mana_poll_tx_cq(cq);
+
+ w = cq->work_done;
+-
+- if (w < cq->budget &&
+- napi_complete_done(&cq->napi, w)) {
+- arm_bit = SET_ARM_BIT;
+- } else {
+- arm_bit = 0;
++ cq->work_done_since_doorbell += w;
++
++ if (w < cq->budget) {
++ mana_gd_ring_cq(gdma_queue, SET_ARM_BIT);
++ cq->work_done_since_doorbell = 0;
++ napi_complete_done(&cq->napi, w);
++ } else if (cq->work_done_since_doorbell >
++ cq->gdma_cq->queue_size / COMP_ENTRY_SIZE * 4) {
++ /* MANA hardware requires at least one doorbell ring every 8
++ * wraparounds of CQ even if there is no need to arm the CQ.
++ * This driver rings the doorbell as soon as we have exceeded
++ * 4 wraparounds.
++ */
++ mana_gd_ring_cq(gdma_queue, 0);
++ cq->work_done_since_doorbell = 0;
+ }
+
+- mana_gd_ring_cq(gdma_queue, arm_bit);
+-
+ return w;
+ }
+
+diff --git a/drivers/net/ethernet/mscc/ocelot.c b/drivers/net/ethernet/mscc/ocelot.c
+index ed2fb44500b0c..f4e027a6fe955 100644
+--- a/drivers/net/ethernet/mscc/ocelot.c
++++ b/drivers/net/ethernet/mscc/ocelot.c
+@@ -1099,6 +1099,48 @@ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb,
+ }
+ EXPORT_SYMBOL(ocelot_ptp_rx_timestamp);
+
++void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp)
++ __acquires(&ocelot->inj_lock)
++{
++ spin_lock(&ocelot->inj_lock);
++}
++EXPORT_SYMBOL_GPL(ocelot_lock_inj_grp);
++
++void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp)
++ __releases(&ocelot->inj_lock)
++{
++ spin_unlock(&ocelot->inj_lock);
++}
++EXPORT_SYMBOL_GPL(ocelot_unlock_inj_grp);
++
++void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp)
++ __acquires(&ocelot->inj_lock)
++{
++ spin_lock(&ocelot->inj_lock);
++}
++EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp);
++
++void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp)
++ __releases(&ocelot->inj_lock)
++{
++ spin_unlock(&ocelot->inj_lock);
++}
++EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp);
++
++void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp)
++ __acquires(&ocelot->xtr_lock)
++{
++ spin_lock_bh(&ocelot->xtr_lock);
++}
++EXPORT_SYMBOL_GPL(ocelot_lock_xtr_grp_bh);
++
++void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp)
++ __releases(&ocelot->xtr_lock)
++{
++ spin_unlock_bh(&ocelot->xtr_lock);
++}
++EXPORT_SYMBOL_GPL(ocelot_unlock_xtr_grp_bh);
++
+ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb)
+ {
+ u64 timestamp, src_port, len;
+@@ -1109,6 +1151,8 @@ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **nskb)
+ u32 val, *buf;
+ int err;
+
++ lockdep_assert_held(&ocelot->xtr_lock);
++
+ err = ocelot_xtr_poll_xfh(ocelot, grp, xfh);
+ if (err)
+ return err;
+@@ -1184,6 +1228,8 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp)
+ {
+ u32 val = ocelot_read(ocelot, QS_INJ_STATUS);
+
++ lockdep_assert_held(&ocelot->inj_lock);
++
+ if (!(val & QS_INJ_STATUS_FIFO_RDY(BIT(grp))))
+ return false;
+ if (val & QS_INJ_STATUS_WMARK_REACHED(BIT(grp)))
+@@ -1193,28 +1239,55 @@ bool ocelot_can_inject(struct ocelot *ocelot, int grp)
+ }
+ EXPORT_SYMBOL(ocelot_can_inject);
+
+-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag)
++/**
++ * ocelot_ifh_set_basic - Set basic information in Injection Frame Header
++ * @ifh: Pointer to Injection Frame Header memory
++ * @ocelot: Switch private data structure
++ * @port: Egress port number
++ * @rew_op: Egress rewriter operation for PTP
++ * @skb: Pointer to socket buffer (packet)
++ *
++ * Populate the Injection Frame Header with basic information for this skb: the
++ * analyzer bypass bit, destination port, VLAN info, egress rewriter info.
++ */
++void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
++ u32 rew_op, struct sk_buff *skb)
+ {
++ struct ocelot_port *ocelot_port = ocelot->ports[port];
++ struct net_device *dev = skb->dev;
++ u64 vlan_tci, tag_type;
++ int qos_class;
++
++ ocelot_xmit_get_vlan_info(skb, ocelot_port->bridge, &vlan_tci,
++ &tag_type);
++
++ qos_class = netdev_get_num_tc(dev) ?
++ netdev_get_prio_tc_map(dev, skb->priority) : skb->priority;
++
++ memset(ifh, 0, OCELOT_TAG_LEN);
+ ocelot_ifh_set_bypass(ifh, 1);
++ ocelot_ifh_set_src(ifh, BIT_ULL(ocelot->num_phys_ports));
+ ocelot_ifh_set_dest(ifh, BIT_ULL(port));
+- ocelot_ifh_set_tag_type(ifh, IFH_TAG_TYPE_C);
+- if (vlan_tag)
+- ocelot_ifh_set_vlan_tci(ifh, vlan_tag);
++ ocelot_ifh_set_qos_class(ifh, qos_class);
++ ocelot_ifh_set_tag_type(ifh, tag_type);
++ ocelot_ifh_set_vlan_tci(ifh, vlan_tci);
+ if (rew_op)
+ ocelot_ifh_set_rew_op(ifh, rew_op);
+ }
+-EXPORT_SYMBOL(ocelot_ifh_port_set);
++EXPORT_SYMBOL(ocelot_ifh_set_basic);
+
+ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
+ u32 rew_op, struct sk_buff *skb)
+ {
+- u32 ifh[OCELOT_TAG_LEN / 4] = {0};
++ u32 ifh[OCELOT_TAG_LEN / 4];
+ unsigned int i, count, last;
+
++ lockdep_assert_held(&ocelot->inj_lock);
++
+ ocelot_write_rix(ocelot, QS_INJ_CTRL_GAP_SIZE(1) |
+ QS_INJ_CTRL_SOF, QS_INJ_CTRL, grp);
+
+- ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));
++ ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
+
+ for (i = 0; i < OCELOT_TAG_LEN / 4; i++)
+ ocelot_write_rix(ocelot, ifh[i], QS_INJ_WR, grp);
+@@ -1247,6 +1320,8 @@ EXPORT_SYMBOL(ocelot_port_inject_frame);
+
+ void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp)
+ {
++ lockdep_assert_held(&ocelot->xtr_lock);
++
+ while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp))
+ ocelot_read_rix(ocelot, QS_XTR_RD, grp);
+ }
+@@ -2929,6 +3004,8 @@ int ocelot_init(struct ocelot *ocelot)
+ mutex_init(&ocelot->fwd_domain_lock);
+ spin_lock_init(&ocelot->ptp_clock_lock);
+ spin_lock_init(&ocelot->ts_id_lock);
++ spin_lock_init(&ocelot->inj_lock);
++ spin_lock_init(&ocelot->xtr_lock);
+
+ ocelot->owq = alloc_ordered_workqueue("ocelot-owq", 0);
+ if (!ocelot->owq)
+diff --git a/drivers/net/ethernet/mscc/ocelot_fdma.c b/drivers/net/ethernet/mscc/ocelot_fdma.c
+index 312a468321544..00326ae8c708b 100644
+--- a/drivers/net/ethernet/mscc/ocelot_fdma.c
++++ b/drivers/net/ethernet/mscc/ocelot_fdma.c
+@@ -665,8 +665,7 @@ static int ocelot_fdma_prepare_skb(struct ocelot *ocelot, int port, u32 rew_op,
+
+ ifh = skb_push(skb, OCELOT_TAG_LEN);
+ skb_put(skb, ETH_FCS_LEN);
+- memset(ifh, 0, OCELOT_TAG_LEN);
+- ocelot_ifh_port_set(ifh, port, rew_op, skb_vlan_tag_get(skb));
++ ocelot_ifh_set_basic(ifh, ocelot, port, rew_op, skb);
+
+ return 0;
+ }
+diff --git a/drivers/net/ethernet/mscc/ocelot_vsc7514.c b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+index 993212c3a7da6..c09dd2e3343cb 100644
+--- a/drivers/net/ethernet/mscc/ocelot_vsc7514.c
++++ b/drivers/net/ethernet/mscc/ocelot_vsc7514.c
+@@ -51,6 +51,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
+ struct ocelot *ocelot = arg;
+ int grp = 0, err;
+
++ ocelot_lock_xtr_grp(ocelot, grp);
++
+ while (ocelot_read(ocelot, QS_XTR_DATA_PRESENT) & BIT(grp)) {
+ struct sk_buff *skb;
+
+@@ -69,6 +71,8 @@ static irqreturn_t ocelot_xtr_irq_handler(int irq, void *arg)
+ if (err < 0)
+ ocelot_drain_cpu_queue(ocelot, 0);
+
++ ocelot_unlock_xtr_grp(ocelot, grp);
++
+ return IRQ_HANDLED;
+ }
+
+diff --git a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+index ec54b18c5fe73..a5e9b779c44d0 100644
+--- a/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
++++ b/drivers/net/ethernet/wangxun/ngbe/ngbe_mdio.c
+@@ -124,8 +124,12 @@ static int ngbe_phylink_init(struct wx *wx)
+ MAC_SYM_PAUSE | MAC_ASYM_PAUSE;
+ config->mac_managed_pm = true;
+
+- phy_mode = PHY_INTERFACE_MODE_RGMII_ID;
+- __set_bit(PHY_INTERFACE_MODE_RGMII_ID, config->supported_interfaces);
++ /* The MAC only has add the Tx delay and it can not be modified.
++ * So just disable TX delay in PHY, and it is does not matter to
++ * internal phy.
++ */
++ phy_mode = PHY_INTERFACE_MODE_RGMII_RXID;
++ __set_bit(PHY_INTERFACE_MODE_RGMII_RXID, config->supported_interfaces);
+
+ phylink = phylink_create(config, NULL, phy_mode, &ngbe_mac_ops);
+ if (IS_ERR(phylink))
+diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet.h b/drivers/net/ethernet/xilinx/xilinx_axienet.h
+index fa5500decc960..09c9f9787180b 100644
+--- a/drivers/net/ethernet/xilinx/xilinx_axienet.h
++++ b/drivers/net/ethernet/xilinx/xilinx_axienet.h
+@@ -160,16 +160,17 @@
+ #define XAE_RCW1_OFFSET 0x00000404 /* Rx Configuration Word 1 */
+ #define XAE_TC_OFFSET 0x00000408 /* Tx Configuration */
+ #define XAE_FCC_OFFSET 0x0000040C /* Flow Control Configuration */
+-#define XAE_EMMC_OFFSET 0x00000410 /* EMAC mode configuration */
+-#define XAE_PHYC_OFFSET 0x00000414 /* RGMII/SGMII configuration */
++#define XAE_EMMC_OFFSET 0x00000410 /* MAC speed configuration */
++#define XAE_PHYC_OFFSET 0x00000414 /* RX Max Frame Configuration */
+ #define XAE_ID_OFFSET 0x000004F8 /* Identification register */
+-#define XAE_MDIO_MC_OFFSET 0x00000500 /* MII Management Config */
+-#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MII Management Control */
+-#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MII Management Write Data */
+-#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MII Management Read Data */
++#define XAE_MDIO_MC_OFFSET 0x00000500 /* MDIO Setup */
++#define XAE_MDIO_MCR_OFFSET 0x00000504 /* MDIO Control */
++#define XAE_MDIO_MWD_OFFSET 0x00000508 /* MDIO Write Data */
++#define XAE_MDIO_MRD_OFFSET 0x0000050C /* MDIO Read Data */
+ #define XAE_UAW0_OFFSET 0x00000700 /* Unicast address word 0 */
+ #define XAE_UAW1_OFFSET 0x00000704 /* Unicast address word 1 */
+-#define XAE_FMI_OFFSET 0x00000708 /* Filter Mask Index */
++#define XAE_FMI_OFFSET 0x00000708 /* Frame Filter Control */
++#define XAE_FFE_OFFSET 0x0000070C /* Frame Filter Enable */
+ #define XAE_AF0_OFFSET 0x00000710 /* Address Filter 0 */
+ #define XAE_AF1_OFFSET 0x00000714 /* Address Filter 1 */
+
+@@ -308,7 +309,7 @@
+ */
+ #define XAE_UAW1_UNICASTADDR_MASK 0x0000FFFF
+
+-/* Bit masks for Axi Ethernet FMI register */
++/* Bit masks for Axi Ethernet FMC register */
+ #define XAE_FMI_PM_MASK 0x80000000 /* Promis. mode enable */
+ #define XAE_FMI_IND_MASK 0x00000003 /* Index Mask */
+
+diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+index fa510f4e26008..559c0d60d9483 100644
+--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
++++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+@@ -432,7 +432,7 @@ static int netdev_set_mac_address(struct net_device *ndev, void *p)
+ */
+ static void axienet_set_multicast_list(struct net_device *ndev)
+ {
+- int i;
++ int i = 0;
+ u32 reg, af0reg, af1reg;
+ struct axienet_local *lp = netdev_priv(ndev);
+
+@@ -450,7 +450,10 @@ static void axienet_set_multicast_list(struct net_device *ndev)
+ } else if (!netdev_mc_empty(ndev)) {
+ struct netdev_hw_addr *ha;
+
+- i = 0;
++ reg = axienet_ior(lp, XAE_FMI_OFFSET);
++ reg &= ~XAE_FMI_PM_MASK;
++ axienet_iow(lp, XAE_FMI_OFFSET, reg);
++
+ netdev_for_each_mc_addr(ha, ndev) {
+ if (i >= XAE_MULTICAST_CAM_TABLE_NUM)
+ break;
+@@ -469,6 +472,7 @@ static void axienet_set_multicast_list(struct net_device *ndev)
+ axienet_iow(lp, XAE_FMI_OFFSET, reg);
+ axienet_iow(lp, XAE_AF0_OFFSET, af0reg);
+ axienet_iow(lp, XAE_AF1_OFFSET, af1reg);
++ axienet_iow(lp, XAE_FFE_OFFSET, 1);
+ i++;
+ }
+ } else {
+@@ -476,18 +480,15 @@ static void axienet_set_multicast_list(struct net_device *ndev)
+ reg &= ~XAE_FMI_PM_MASK;
+
+ axienet_iow(lp, XAE_FMI_OFFSET, reg);
+-
+- for (i = 0; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
+- reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
+- reg |= i;
+-
+- axienet_iow(lp, XAE_FMI_OFFSET, reg);
+- axienet_iow(lp, XAE_AF0_OFFSET, 0);
+- axienet_iow(lp, XAE_AF1_OFFSET, 0);
+- }
+-
+ dev_info(&ndev->dev, "Promiscuous mode disabled.\n");
+ }
++
++ for (; i < XAE_MULTICAST_CAM_TABLE_NUM; i++) {
++ reg = axienet_ior(lp, XAE_FMI_OFFSET) & 0xFFFFFF00;
++ reg |= i;
++ axienet_iow(lp, XAE_FMI_OFFSET, reg);
++ axienet_iow(lp, XAE_FFE_OFFSET, 0);
++ }
+ }
+
+ /**
+diff --git a/drivers/net/gtp.c b/drivers/net/gtp.c
+index 427b91aca50d3..0696faf60013e 100644
+--- a/drivers/net/gtp.c
++++ b/drivers/net/gtp.c
+@@ -1269,6 +1269,9 @@ static netdev_tx_t gtp_dev_xmit(struct sk_buff *skb, struct net_device *dev)
+ if (skb_cow_head(skb, dev->needed_headroom))
+ goto tx_err;
+
++ if (!pskb_inet_may_pull(skb))
++ goto tx_err;
++
+ skb_reset_inner_headers(skb);
+
+ /* PDP context lookups in gtp_build_skb_*() need rcu read-side lock. */
+diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
+index a7c7a868c14ce..fca9f7e510b41 100644
+--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
++++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
+@@ -124,6 +124,60 @@ static void ath12k_hal_tx_cmd_ext_desc_setup(struct ath12k_base *ab,
+ HAL_TX_MSDU_EXT_INFO1_ENCRYPT_TYPE);
+ }
+
++static void ath12k_dp_tx_move_payload(struct sk_buff *skb,
++ unsigned long delta,
++ bool head)
++{
++ unsigned long len = skb->len;
++
++ if (head) {
++ skb_push(skb, delta);
++ memmove(skb->data, skb->data + delta, len);
++ skb_trim(skb, len);
++ } else {
++ skb_put(skb, delta);
++ memmove(skb->data + delta, skb->data, len);
++ skb_pull(skb, delta);
++ }
++}
++
++static int ath12k_dp_tx_align_payload(struct ath12k_base *ab,
++ struct sk_buff **pskb)
++{
++ u32 iova_mask = ab->hw_params->iova_mask;
++ unsigned long offset, delta1, delta2;
++ struct sk_buff *skb2, *skb = *pskb;
++ unsigned int headroom = skb_headroom(skb);
++ int tailroom = skb_tailroom(skb);
++ int ret = 0;
++
++ offset = (unsigned long)skb->data & iova_mask;
++ delta1 = offset;
++ delta2 = iova_mask - offset + 1;
++
++ if (headroom >= delta1) {
++ ath12k_dp_tx_move_payload(skb, delta1, true);
++ } else if (tailroom >= delta2) {
++ ath12k_dp_tx_move_payload(skb, delta2, false);
++ } else {
++ skb2 = skb_realloc_headroom(skb, iova_mask);
++ if (!skb2) {
++ ret = -ENOMEM;
++ goto out;
++ }
++
++ dev_kfree_skb_any(skb);
++
++ offset = (unsigned long)skb2->data & iova_mask;
++ if (offset)
++ ath12k_dp_tx_move_payload(skb2, offset, true);
++ *pskb = skb2;
++ }
++
++out:
++ return ret;
++}
++
+ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
+ struct sk_buff *skb)
+ {
+@@ -145,6 +199,7 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
+ u8 ring_selector, ring_map = 0;
+ bool tcl_ring_retry;
+ bool msdu_ext_desc = false;
++ u32 iova_mask = ab->hw_params->iova_mask;
+
+ if (test_bit(ATH12K_FLAG_CRASH_FLUSH, &ar->ab->dev_flags))
+ return -ESHUTDOWN;
+@@ -240,6 +295,23 @@ int ath12k_dp_tx(struct ath12k *ar, struct ath12k_vif *arvif,
+ goto fail_remove_tx_buf;
+ }
+
++ if (iova_mask &&
++ (unsigned long)skb->data & iova_mask) {
++ ret = ath12k_dp_tx_align_payload(ab, &skb);
++ if (ret) {
++ ath12k_warn(ab, "failed to align TX buffer %d\n", ret);
++ /* don't bail out, give original buffer
++ * a chance even unaligned.
++ */
++ goto map;
++ }
++
++ /* hdr is pointing to a wrong place after alignment,
++ * so refresh it for later use.
++ */
++ hdr = (void *)skb->data;
++ }
++map:
+ ti.paddr = dma_map_single(ab->dev, skb->data, skb->len, DMA_TO_DEVICE);
+ if (dma_mapping_error(ab->dev, ti.paddr)) {
+ atomic_inc(&ab->soc_stats.tx_err.misc_fail);
+diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
+index bff8cf97a18c6..2a92147d15fa1 100644
+--- a/drivers/net/wireless/ath/ath12k/hw.c
++++ b/drivers/net/wireless/ath/ath12k/hw.c
+@@ -922,6 +922,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
+ .supports_sta_ps = false,
+
+ .acpi_guid = NULL,
++
++ .iova_mask = 0,
+ },
+ {
+ .name = "wcn7850 hw2.0",
+@@ -997,6 +999,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
+ .supports_sta_ps = true,
+
+ .acpi_guid = &wcn7850_uuid,
++
++ .iova_mask = ATH12K_PCIE_MAX_PAYLOAD_SIZE - 1,
+ },
+ {
+ .name = "qcn9274 hw2.0",
+@@ -1067,6 +1071,8 @@ static const struct ath12k_hw_params ath12k_hw_params[] = {
+ .supports_sta_ps = false,
+
+ .acpi_guid = NULL,
++
++ .iova_mask = 0,
+ },
+ };
+
+diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
+index 2a314cfc8cb84..400bda17e02f6 100644
+--- a/drivers/net/wireless/ath/ath12k/hw.h
++++ b/drivers/net/wireless/ath/ath12k/hw.h
+@@ -96,6 +96,8 @@
+ #define ATH12K_M3_FILE "m3.bin"
+ #define ATH12K_REGDB_FILE_NAME "regdb.bin"
+
++#define ATH12K_PCIE_MAX_PAYLOAD_SIZE 128
++
+ enum ath12k_hw_rate_cck {
+ ATH12K_HW_RATE_CCK_LP_11M = 0,
+ ATH12K_HW_RATE_CCK_LP_5_5M,
+@@ -214,6 +216,8 @@ struct ath12k_hw_params {
+ bool supports_sta_ps;
+
+ const guid_t *acpi_guid;
++
++ u32 iova_mask;
+ };
+
+ struct ath12k_hw_ops {
+diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
+index ead37a4e002a2..8474e25d2ac64 100644
+--- a/drivers/net/wireless/ath/ath12k/mac.c
++++ b/drivers/net/wireless/ath/ath12k/mac.c
+@@ -8737,6 +8737,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
+
+ hw->vif_data_size = sizeof(struct ath12k_vif);
+ hw->sta_data_size = sizeof(struct ath12k_sta);
++ hw->extra_tx_headroom = ab->hw_params->iova_mask;
+
+ wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_CQM_RSSI_LIST);
+ wiphy_ext_feature_set(wiphy, NL80211_EXT_FEATURE_STA_TX_PWR);
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+index 5fe0e671ecb36..826b768196e28 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmfmac/cfg80211.c
+@@ -4320,9 +4320,16 @@ brcmf_pmksa_v3_op(struct brcmf_if *ifp, struct cfg80211_pmksa *pmksa,
+ /* Single PMK operation */
+ pmk_op->count = cpu_to_le16(1);
+ length += sizeof(struct brcmf_pmksa_v3);
+- memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN);
+- memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN);
+- pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN;
++ if (pmksa->bssid)
++ memcpy(pmk_op->pmk[0].bssid, pmksa->bssid, ETH_ALEN);
++ if (pmksa->pmkid) {
++ memcpy(pmk_op->pmk[0].pmkid, pmksa->pmkid, WLAN_PMKID_LEN);
++ pmk_op->pmk[0].pmkid_len = WLAN_PMKID_LEN;
++ }
++ if (pmksa->ssid && pmksa->ssid_len) {
++ memcpy(pmk_op->pmk[0].ssid.SSID, pmksa->ssid, pmksa->ssid_len);
++ pmk_op->pmk[0].ssid.SSID_len = pmksa->ssid_len;
++ }
+ pmk_op->pmk[0].time_left = cpu_to_le32(alive ? BRCMF_PMKSA_NO_EXPIRY : 0);
+ }
+
+diff --git a/drivers/nvme/host/core.c b/drivers/nvme/host/core.c
+index 782090ce0bc10..d973d063bbf50 100644
+--- a/drivers/nvme/host/core.c
++++ b/drivers/nvme/host/core.c
+@@ -4522,7 +4522,6 @@ void nvme_stop_ctrl(struct nvme_ctrl *ctrl)
+ {
+ nvme_mpath_stop(ctrl);
+ nvme_auth_stop(ctrl);
+- nvme_stop_keep_alive(ctrl);
+ nvme_stop_failfast_work(ctrl);
+ flush_work(&ctrl->async_event_work);
+ cancel_work_sync(&ctrl->fw_act_work);
+@@ -4558,6 +4557,7 @@ EXPORT_SYMBOL_GPL(nvme_start_ctrl);
+
+ void nvme_uninit_ctrl(struct nvme_ctrl *ctrl)
+ {
++ nvme_stop_keep_alive(ctrl);
+ nvme_hwmon_exit(ctrl);
+ nvme_fault_inject_fini(&ctrl->fault_inject);
+ dev_pm_qos_hide_latency_tolerance(ctrl->device);
+diff --git a/drivers/platform/surface/aggregator/controller.c b/drivers/platform/surface/aggregator/controller.c
+index 7fc602e01487d..7e89f547999b2 100644
+--- a/drivers/platform/surface/aggregator/controller.c
++++ b/drivers/platform/surface/aggregator/controller.c
+@@ -1354,7 +1354,8 @@ void ssam_controller_destroy(struct ssam_controller *ctrl)
+ if (ctrl->state == SSAM_CONTROLLER_UNINITIALIZED)
+ return;
+
+- WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED);
++ WARN_ON(ctrl->state != SSAM_CONTROLLER_STOPPED &&
++ ctrl->state != SSAM_CONTROLLER_INITIALIZED);
+
+ /*
+ * Note: New events could still have been received after the previous
+diff --git a/drivers/platform/x86/dell/Kconfig b/drivers/platform/x86/dell/Kconfig
+index 195a8bf532cc6..de0bfd8f4b66e 100644
+--- a/drivers/platform/x86/dell/Kconfig
++++ b/drivers/platform/x86/dell/Kconfig
+@@ -148,6 +148,7 @@ config DELL_SMO8800
+ config DELL_UART_BACKLIGHT
+ tristate "Dell AIO UART Backlight driver"
+ depends on ACPI
++ depends on ACPI_VIDEO
+ depends on BACKLIGHT_CLASS_DEVICE
+ depends on SERIAL_DEV_BUS
+ help
+diff --git a/drivers/platform/x86/dell/dell-uart-backlight.c b/drivers/platform/x86/dell/dell-uart-backlight.c
+index 87d2a20b4cb3d..3995f90add456 100644
+--- a/drivers/platform/x86/dell/dell-uart-backlight.c
++++ b/drivers/platform/x86/dell/dell-uart-backlight.c
+@@ -20,6 +20,7 @@
+ #include <linux/string.h>
+ #include <linux/types.h>
+ #include <linux/wait.h>
++#include <acpi/video.h>
+ #include "../serdev_helpers.h"
+
+ /* The backlight controller must respond within 1 second */
+@@ -332,10 +333,17 @@ struct serdev_device_driver dell_uart_bl_serdev_driver = {
+
+ static int dell_uart_bl_pdev_probe(struct platform_device *pdev)
+ {
++ enum acpi_backlight_type bl_type;
+ struct serdev_device *serdev;
+ struct device *ctrl_dev;
+ int ret;
+
++ bl_type = acpi_video_get_backlight_type();
++ if (bl_type != acpi_backlight_dell_uart) {
++ dev_dbg(&pdev->dev, "Not loading (ACPI backlight type = %d)\n", bl_type);
++ return -ENODEV;
++ }
++
+ ctrl_dev = get_serdev_controller("DELL0501", NULL, 0, "serial0");
+ if (IS_ERR(ctrl_dev))
+ return PTR_ERR(ctrl_dev);
+diff --git a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+index 7fa360073f6ef..4045823071091 100644
+--- a/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
++++ b/drivers/platform/x86/intel/speed_select_if/isst_tpmi_core.c
+@@ -1549,8 +1549,7 @@ int tpmi_sst_dev_add(struct auxiliary_device *auxdev)
+ goto unlock_free;
+ }
+
+- ret = sst_main(auxdev, &pd_info[i]);
+- if (ret) {
++ if (sst_main(auxdev, &pd_info[i])) {
+ /*
+ * This entry is not valid, hardware can partially
+ * populate dies. In this case MMIO will have 0xFFs.
+diff --git a/drivers/pmdomain/imx/imx93-pd.c b/drivers/pmdomain/imx/imx93-pd.c
+index 1e94b499c19bc..d750a7dc58d21 100644
+--- a/drivers/pmdomain/imx/imx93-pd.c
++++ b/drivers/pmdomain/imx/imx93-pd.c
+@@ -20,6 +20,7 @@
+ #define FUNC_STAT_PSW_STAT_MASK BIT(0)
+ #define FUNC_STAT_RST_STAT_MASK BIT(2)
+ #define FUNC_STAT_ISO_STAT_MASK BIT(4)
++#define FUNC_STAT_SSAR_STAT_MASK BIT(8)
+
+ struct imx93_power_domain {
+ struct generic_pm_domain genpd;
+@@ -50,7 +51,7 @@ static int imx93_pd_on(struct generic_pm_domain *genpd)
+ writel(val, addr + MIX_SLICE_SW_CTRL_OFF);
+
+ ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val,
+- !(val & FUNC_STAT_ISO_STAT_MASK), 1, 10000);
++ !(val & FUNC_STAT_SSAR_STAT_MASK), 1, 10000);
+ if (ret) {
+ dev_err(domain->dev, "pd_on timeout: name: %s, stat: %x\n", genpd->name, val);
+ return ret;
+@@ -72,7 +73,7 @@ static int imx93_pd_off(struct generic_pm_domain *genpd)
+ writel(val, addr + MIX_SLICE_SW_CTRL_OFF);
+
+ ret = readl_poll_timeout(addr + MIX_FUNC_STAT_OFF, val,
+- val & FUNC_STAT_PSW_STAT_MASK, 1, 1000);
++ val & FUNC_STAT_PSW_STAT_MASK, 1, 10000);
+ if (ret) {
+ dev_err(domain->dev, "pd_off timeout: name: %s, stat: %x\n", genpd->name, val);
+ return ret;
+diff --git a/drivers/pmdomain/imx/scu-pd.c b/drivers/pmdomain/imx/scu-pd.c
+index 05841b0bf7f30..01d465d88f60d 100644
+--- a/drivers/pmdomain/imx/scu-pd.c
++++ b/drivers/pmdomain/imx/scu-pd.c
+@@ -223,11 +223,6 @@ static const struct imx_sc_pd_range imx8qxp_scu_pd_ranges[] = {
+ { "lvds1-pwm", IMX_SC_R_LVDS_1_PWM_0, 1, false, 0 },
+ { "lvds1-lpi2c", IMX_SC_R_LVDS_1_I2C_0, 2, true, 0 },
+
+- { "mipi1", IMX_SC_R_MIPI_1, 1, 0 },
+- { "mipi1-pwm0", IMX_SC_R_MIPI_1_PWM_0, 1, 0 },
+- { "mipi1-i2c", IMX_SC_R_MIPI_1_I2C_0, 2, 1 },
+- { "lvds1", IMX_SC_R_LVDS_1, 1, 0 },
+-
+ /* DC SS */
+ { "dc0", IMX_SC_R_DC_0, 1, false, 0 },
+ { "dc0-pll", IMX_SC_R_DC_0_PLL_0, 2, true, 0 },
+diff --git a/drivers/s390/block/dasd.c b/drivers/s390/block/dasd.c
+index 0a97cfedd7060..42a4a996defbe 100644
+--- a/drivers/s390/block/dasd.c
++++ b/drivers/s390/block/dasd.c
+@@ -1601,9 +1601,15 @@ static int dasd_ese_needs_format(struct dasd_block *block, struct irb *irb)
+ if (!sense)
+ return 0;
+
+- return !!(sense[1] & SNS1_NO_REC_FOUND) ||
+- !!(sense[1] & SNS1_FILE_PROTECTED) ||
+- scsw_cstat(&irb->scsw) == SCHN_STAT_INCORR_LEN;
++ if (sense[1] & SNS1_NO_REC_FOUND)
++ return 1;
++
++ if ((sense[1] & SNS1_INV_TRACK_FORMAT) &&
++ scsw_is_tm(&irb->scsw) &&
++ !(sense[2] & SNS2_ENV_DATA_PRESENT))
++ return 1;
++
++ return 0;
+ }
+
+ static int dasd_ese_oos_cond(u8 *sense)
+@@ -1624,7 +1630,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
+ struct dasd_device *device;
+ unsigned long now;
+ int nrf_suppressed = 0;
+- int fp_suppressed = 0;
++ int it_suppressed = 0;
+ struct request *req;
+ u8 *sense = NULL;
+ int expires;
+@@ -1679,8 +1685,9 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
+ */
+ sense = dasd_get_sense(irb);
+ if (sense) {
+- fp_suppressed = (sense[1] & SNS1_FILE_PROTECTED) &&
+- test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
++ it_suppressed = (sense[1] & SNS1_INV_TRACK_FORMAT) &&
++ !(sense[2] & SNS2_ENV_DATA_PRESENT) &&
++ test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags);
+ nrf_suppressed = (sense[1] & SNS1_NO_REC_FOUND) &&
+ test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
+
+@@ -1695,7 +1702,7 @@ void dasd_int_handler(struct ccw_device *cdev, unsigned long intparm,
+ return;
+ }
+ }
+- if (!(fp_suppressed || nrf_suppressed))
++ if (!(it_suppressed || nrf_suppressed))
+ device->discipline->dump_sense_dbf(device, irb, "int");
+
+ if (device->features & DASD_FEATURE_ERPLOG)
+@@ -2459,14 +2466,17 @@ static int _dasd_sleep_on_queue(struct list_head *ccw_queue, int interruptible)
+ rc = 0;
+ list_for_each_entry_safe(cqr, n, ccw_queue, blocklist) {
+ /*
+- * In some cases the 'File Protected' or 'Incorrect Length'
+- * error might be expected and error recovery would be
+- * unnecessary in these cases. Check if the according suppress
+- * bit is set.
++ * In some cases certain errors might be expected and
++ * error recovery would be unnecessary in these cases.
++ * Check if the according suppress bit is set.
+ */
+ sense = dasd_get_sense(&cqr->irb);
+- if (sense && sense[1] & SNS1_FILE_PROTECTED &&
+- test_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags))
++ if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) &&
++ !(sense[2] & SNS2_ENV_DATA_PRESENT) &&
++ test_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags))
++ continue;
++ if (sense && (sense[1] & SNS1_NO_REC_FOUND) &&
++ test_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags))
+ continue;
+ if (scsw_cstat(&cqr->irb.scsw) == 0x40 &&
+ test_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags))
+diff --git a/drivers/s390/block/dasd_3990_erp.c b/drivers/s390/block/dasd_3990_erp.c
+index bbbacfc386f28..d0aa267462c50 100644
+--- a/drivers/s390/block/dasd_3990_erp.c
++++ b/drivers/s390/block/dasd_3990_erp.c
+@@ -1386,14 +1386,8 @@ dasd_3990_erp_file_prot(struct dasd_ccw_req * erp)
+
+ struct dasd_device *device = erp->startdev;
+
+- /*
+- * In some cases the 'File Protected' error might be expected and
+- * log messages shouldn't be written then.
+- * Check if the according suppress bit is set.
+- */
+- if (!test_bit(DASD_CQR_SUPPRESS_FP, &erp->flags))
+- dev_err(&device->cdev->dev,
+- "Accessing the DASD failed because of a hardware error\n");
++ dev_err(&device->cdev->dev,
++ "Accessing the DASD failed because of a hardware error\n");
+
+ return dasd_3990_erp_cleanup(erp, DASD_CQR_FAILED);
+
+diff --git a/drivers/s390/block/dasd_eckd.c b/drivers/s390/block/dasd_eckd.c
+index a76c6af9ea638..a47443d3cc366 100644
+--- a/drivers/s390/block/dasd_eckd.c
++++ b/drivers/s390/block/dasd_eckd.c
+@@ -2274,6 +2274,7 @@ dasd_eckd_analysis_ccw(struct dasd_device *device)
+ cqr->status = DASD_CQR_FILLED;
+ /* Set flags to suppress output for expected errors */
+ set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
++ set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags);
+
+ return cqr;
+ }
+@@ -2555,7 +2556,6 @@ dasd_eckd_build_check_tcw(struct dasd_device *base, struct format_data_t *fdata,
+ cqr->buildclk = get_tod_clock();
+ cqr->status = DASD_CQR_FILLED;
+ /* Set flags to suppress output for expected errors */
+- set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
+ set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags);
+
+ return cqr;
+@@ -4129,8 +4129,6 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_cmd_single(
+
+ /* Set flags to suppress output for expected errors */
+ if (dasd_eckd_is_ese(basedev)) {
+- set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
+- set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags);
+ set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
+ }
+
+@@ -4632,9 +4630,8 @@ static struct dasd_ccw_req *dasd_eckd_build_cp_tpm_track(
+
+ /* Set flags to suppress output for expected errors */
+ if (dasd_eckd_is_ese(basedev)) {
+- set_bit(DASD_CQR_SUPPRESS_FP, &cqr->flags);
+- set_bit(DASD_CQR_SUPPRESS_IL, &cqr->flags);
+ set_bit(DASD_CQR_SUPPRESS_NRF, &cqr->flags);
++ set_bit(DASD_CQR_SUPPRESS_IT, &cqr->flags);
+ }
+
+ return cqr;
+@@ -5779,36 +5776,32 @@ static void dasd_eckd_dump_sense(struct dasd_device *device,
+ {
+ u8 *sense = dasd_get_sense(irb);
+
+- if (scsw_is_tm(&irb->scsw)) {
+- /*
+- * In some cases the 'File Protected' or 'Incorrect Length'
+- * error might be expected and log messages shouldn't be written
+- * then. Check if the according suppress bit is set.
+- */
+- if (sense && (sense[1] & SNS1_FILE_PROTECTED) &&
+- test_bit(DASD_CQR_SUPPRESS_FP, &req->flags))
+- return;
+- if (scsw_cstat(&irb->scsw) == 0x40 &&
+- test_bit(DASD_CQR_SUPPRESS_IL, &req->flags))
+- return;
++ /*
++ * In some cases certain errors might be expected and
++ * log messages shouldn't be written then.
++ * Check if the according suppress bit is set.
++ */
++ if (sense && (sense[1] & SNS1_INV_TRACK_FORMAT) &&
++ !(sense[2] & SNS2_ENV_DATA_PRESENT) &&
++ test_bit(DASD_CQR_SUPPRESS_IT, &req->flags))
++ return;
+
+- dasd_eckd_dump_sense_tcw(device, req, irb);
+- } else {
+- /*
+- * In some cases the 'Command Reject' or 'No Record Found'
+- * error might be expected and log messages shouldn't be
+- * written then. Check if the according suppress bit is set.
+- */
+- if (sense && sense[0] & SNS0_CMD_REJECT &&
+- test_bit(DASD_CQR_SUPPRESS_CR, &req->flags))
+- return;
++ if (sense && sense[0] & SNS0_CMD_REJECT &&
++ test_bit(DASD_CQR_SUPPRESS_CR, &req->flags))
++ return;
+
+- if (sense && sense[1] & SNS1_NO_REC_FOUND &&
+- test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags))
+- return;
++ if (sense && sense[1] & SNS1_NO_REC_FOUND &&
++ test_bit(DASD_CQR_SUPPRESS_NRF, &req->flags))
++ return;
+
++ if (scsw_cstat(&irb->scsw) == 0x40 &&
++ test_bit(DASD_CQR_SUPPRESS_IL, &req->flags))
++ return;
++
++ if (scsw_is_tm(&irb->scsw))
++ dasd_eckd_dump_sense_tcw(device, req, irb);
++ else
+ dasd_eckd_dump_sense_ccw(device, req, irb);
+- }
+ }
+
+ static int dasd_eckd_reload_device(struct dasd_device *device)
+diff --git a/drivers/s390/block/dasd_genhd.c b/drivers/s390/block/dasd_genhd.c
+index 4533dd055ca8e..23d6e638f381d 100644
+--- a/drivers/s390/block/dasd_genhd.c
++++ b/drivers/s390/block/dasd_genhd.c
+@@ -41,7 +41,6 @@ int dasd_gendisk_alloc(struct dasd_block *block)
+ */
+ .max_segment_size = PAGE_SIZE,
+ .seg_boundary_mask = PAGE_SIZE - 1,
+- .dma_alignment = PAGE_SIZE - 1,
+ .max_segments = USHRT_MAX,
+ };
+ struct gendisk *gdp;
+diff --git a/drivers/s390/block/dasd_int.h b/drivers/s390/block/dasd_int.h
+index e5f40536b4254..81cfb5c89681b 100644
+--- a/drivers/s390/block/dasd_int.h
++++ b/drivers/s390/block/dasd_int.h
+@@ -196,7 +196,7 @@ struct dasd_ccw_req {
+ * The following flags are used to suppress output of certain errors.
+ */
+ #define DASD_CQR_SUPPRESS_NRF 4 /* Suppress 'No Record Found' error */
+-#define DASD_CQR_SUPPRESS_FP 5 /* Suppress 'File Protected' error*/
++#define DASD_CQR_SUPPRESS_IT 5 /* Suppress 'Invalid Track' error*/
+ #define DASD_CQR_SUPPRESS_IL 6 /* Suppress 'Incorrect Length' error */
+ #define DASD_CQR_SUPPRESS_CR 7 /* Suppress 'Command Reject' error */
+
+diff --git a/drivers/s390/crypto/ap_bus.c b/drivers/s390/crypto/ap_bus.c
+index 898865be0dad9..99fadfb4cd9f2 100644
+--- a/drivers/s390/crypto/ap_bus.c
++++ b/drivers/s390/crypto/ap_bus.c
+@@ -971,11 +971,16 @@ int ap_driver_register(struct ap_driver *ap_drv, struct module *owner,
+ char *name)
+ {
+ struct device_driver *drv = &ap_drv->driver;
++ int rc;
+
+ drv->bus = &ap_bus_type;
+ drv->owner = owner;
+ drv->name = name;
+- return driver_register(drv);
++ rc = driver_register(drv);
++
++ ap_check_bindings_complete();
++
++ return rc;
+ }
+ EXPORT_SYMBOL(ap_driver_register);
+
+diff --git a/drivers/spi/spi-cadence-quadspi.c b/drivers/spi/spi-cadence-quadspi.c
+index 05ebb03d319fc..d4607cb89c484 100644
+--- a/drivers/spi/spi-cadence-quadspi.c
++++ b/drivers/spi/spi-cadence-quadspi.c
+@@ -2000,13 +2000,25 @@ static int cqspi_runtime_resume(struct device *dev)
+ static int cqspi_suspend(struct device *dev)
+ {
+ struct cqspi_st *cqspi = dev_get_drvdata(dev);
++ int ret;
+
+- return spi_controller_suspend(cqspi->host);
++ ret = spi_controller_suspend(cqspi->host);
++ if (ret)
++ return ret;
++
++ return pm_runtime_force_suspend(dev);
+ }
+
+ static int cqspi_resume(struct device *dev)
+ {
+ struct cqspi_st *cqspi = dev_get_drvdata(dev);
++ int ret;
++
++ ret = pm_runtime_force_resume(dev);
++ if (ret) {
++ dev_err(dev, "pm_runtime_force_resume failed on resume\n");
++ return ret;
++ }
+
+ return spi_controller_resume(cqspi->host);
+ }
+diff --git a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h
+index 961c612880833..aad860e54d3a7 100644
+--- a/drivers/staging/media/atomisp/pci/ia_css_stream_public.h
++++ b/drivers/staging/media/atomisp/pci/ia_css_stream_public.h
+@@ -27,12 +27,16 @@
+ #include "ia_css_prbs.h"
+ #include "ia_css_input_port.h"
+
+-/* Input modes, these enumerate all supported input modes.
+- * Note that not all ISP modes support all input modes.
++/*
++ * Input modes, these enumerate all supported input modes.
++ * This enum is part of the atomisp firmware ABI and must
++ * NOT be changed!
++ * Note that not all ISP modes support all input modes.
+ */
+ enum ia_css_input_mode {
+ IA_CSS_INPUT_MODE_SENSOR, /** data from sensor */
+ IA_CSS_INPUT_MODE_FIFO, /** data from input-fifo */
++ IA_CSS_INPUT_MODE_TPG, /** data from test-pattern generator */
+ IA_CSS_INPUT_MODE_PRBS, /** data from pseudo-random bit stream */
+ IA_CSS_INPUT_MODE_MEMORY, /** data from a frame in memory */
+ IA_CSS_INPUT_MODE_BUFFERED_SENSOR /** data is sent through mipi buffer */
+diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h
+index bef2b8c5132ba..419aba9b0e49e 100644
+--- a/drivers/staging/media/atomisp/pci/sh_css_internal.h
++++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h
+@@ -341,7 +341,14 @@ struct sh_css_sp_input_formatter_set {
+
+ #define IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT (3)
+
+-/* SP configuration information */
++/*
++ * SP configuration information
++ *
++ * This struct is part of the atomisp firmware ABI and is directly copied
++ * to ISP DRAM by sh_css_store_sp_group_to_ddr()
++ *
++ * Do NOT change this struct's layout or remove seemingly unused fields!
++ */
+ struct sh_css_sp_config {
+ u8 no_isp_sync; /* Signal host immediately after start */
+ u8 enable_raw_pool_locking; /** Enable Raw Buffer Locking for HALv3 Support */
+@@ -351,6 +358,10 @@ struct sh_css_sp_config {
+ host (true) or when they are passed to the preview/video pipe
+ (false). */
+
++ /*
++ * Note the fields below are only used on the ISP2400 not on the ISP2401,
++ * sh_css_store_sp_group_to_ddr() skip copying these when run on the ISP2401.
++ */
+ struct {
+ u8 a_changed;
+ u8 b_changed;
+@@ -360,11 +371,13 @@ struct sh_css_sp_config {
+ } input_formatter;
+
+ sync_generator_cfg_t sync_gen;
++ tpg_cfg_t tpg;
+ prbs_cfg_t prbs;
+ input_system_cfg_t input_circuit;
+ u8 input_circuit_cfg_changed;
+- u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT];
+- u8 enable_isys_event_queue;
++ u32 mipi_sizes_for_check[N_CSI_PORTS][IA_CSS_MIPI_SIZE_CHECK_MAX_NOF_ENTRIES_PER_PORT];
++ /* These last 2 fields are used on both the ISP2400 and the ISP2401 */
++ u8 enable_isys_event_queue;
+ u8 disable_cont_vf;
+ };
+
+diff --git a/drivers/thermal/gov_bang_bang.c b/drivers/thermal/gov_bang_bang.c
+index acb52c9ee10f1..daed67d19efb8 100644
+--- a/drivers/thermal/gov_bang_bang.c
++++ b/drivers/thermal/gov_bang_bang.c
+@@ -13,6 +13,28 @@
+
+ #include "thermal_core.h"
+
++static void bang_bang_set_instance_target(struct thermal_instance *instance,
++ unsigned int target)
++{
++ if (instance->target != 0 && instance->target != 1 &&
++ instance->target != THERMAL_NO_TARGET)
++ pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n",
++ instance->target, instance->name);
++
++ /*
++ * Enable the fan when the trip is crossed on the way up and disable it
++ * when the trip is crossed on the way down.
++ */
++ instance->target = target;
++ instance->initialized = true;
++
++ dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target);
++
++ mutex_lock(&instance->cdev->lock);
++ __thermal_cdev_update(instance->cdev);
++ mutex_unlock(&instance->cdev->lock);
++}
++
+ /**
+ * bang_bang_control - controls devices associated with the given zone
+ * @tz: thermal_zone_device
+@@ -54,41 +76,60 @@ static void bang_bang_control(struct thermal_zone_device *tz,
+ tz->temperature, trip->hysteresis);
+
+ list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
+- if (instance->trip != trip)
+- continue;
++ if (instance->trip == trip)
++ bang_bang_set_instance_target(instance, crossed_up);
++ }
++}
++
++static void bang_bang_manage(struct thermal_zone_device *tz)
++{
++ const struct thermal_trip_desc *td;
++ struct thermal_instance *instance;
+
+- if (instance->target == THERMAL_NO_TARGET)
+- instance->target = 0;
++ /* If the code below has run already, nothing needs to be done. */
++ if (tz->governor_data)
++ return;
+
+- if (instance->target != 0 && instance->target != 1) {
+- pr_debug("Unexpected state %ld of thermal instance %s in bang-bang\n",
+- instance->target, instance->name);
++ for_each_trip_desc(tz, td) {
++ const struct thermal_trip *trip = &td->trip;
+
+- instance->target = 1;
+- }
++ if (tz->temperature >= td->threshold ||
++ trip->temperature == THERMAL_TEMP_INVALID ||
++ trip->type == THERMAL_TRIP_CRITICAL ||
++ trip->type == THERMAL_TRIP_HOT)
++ continue;
+
+ /*
+- * Enable the fan when the trip is crossed on the way up and
+- * disable it when the trip is crossed on the way down.
++ * If the initial cooling device state is "on", but the zone
++ * temperature is not above the trip point, the core will not
++ * call bang_bang_control() until the zone temperature reaches
++ * the trip point temperature which may be never. In those
++ * cases, set the initial state of the cooling device to 0.
+ */
+- if (instance->target == 0 && crossed_up)
+- instance->target = 1;
+- else if (instance->target == 1 && !crossed_up)
+- instance->target = 0;
+-
+- dev_dbg(&instance->cdev->device, "target=%ld\n", instance->target);
+-
+- mutex_lock(&instance->cdev->lock);
+- instance->cdev->updated = false; /* cdev needs update */
+- mutex_unlock(&instance->cdev->lock);
++ list_for_each_entry(instance, &tz->thermal_instances, tz_node) {
++ if (!instance->initialized && instance->trip == trip)
++ bang_bang_set_instance_target(instance, 0);
++ }
+ }
+
+- list_for_each_entry(instance, &tz->thermal_instances, tz_node)
+- thermal_cdev_update(instance->cdev);
++ tz->governor_data = (void *)true;
++}
++
++static void bang_bang_update_tz(struct thermal_zone_device *tz,
++ enum thermal_notify_event reason)
++{
++ /*
++ * Let bang_bang_manage() know that it needs to walk trips after binding
++ * a new cdev and after system resume.
++ */
++ if (reason == THERMAL_TZ_BIND_CDEV || reason == THERMAL_TZ_RESUME)
++ tz->governor_data = NULL;
+ }
+
+ static struct thermal_governor thermal_gov_bang_bang = {
+ .name = "bang_bang",
+ .trip_crossed = bang_bang_control,
++ .manage = bang_bang_manage,
++ .update_tz = bang_bang_update_tz,
+ };
+ THERMAL_GOVERNOR_DECLARE(thermal_gov_bang_bang);
+diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
+index f2d31bc48f529..b8d889ef4fa5e 100644
+--- a/drivers/thermal/thermal_core.c
++++ b/drivers/thermal/thermal_core.c
+@@ -1715,7 +1715,8 @@ static void thermal_zone_device_resume(struct work_struct *work)
+ tz->suspended = false;
+
+ thermal_zone_device_init(tz);
+- __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
++ thermal_governor_update_tz(tz, THERMAL_TZ_RESUME);
++ __thermal_zone_device_update(tz, THERMAL_TZ_RESUME);
+
+ complete(&tz->resume);
+ tz->resuming = false;
+diff --git a/drivers/thermal/thermal_debugfs.c b/drivers/thermal/thermal_debugfs.c
+index 9424472291570..6d55f5fc4ca0f 100644
+--- a/drivers/thermal/thermal_debugfs.c
++++ b/drivers/thermal/thermal_debugfs.c
+@@ -178,11 +178,11 @@ struct thermal_debugfs {
+ void thermal_debug_init(void)
+ {
+ d_root = debugfs_create_dir("thermal", NULL);
+- if (!d_root)
++ if (IS_ERR(d_root))
+ return;
+
+ d_cdev = debugfs_create_dir("cooling_devices", d_root);
+- if (!d_cdev)
++ if (IS_ERR(d_cdev))
+ return;
+
+ d_tz = debugfs_create_dir("thermal_zones", d_root);
+@@ -202,7 +202,7 @@ static struct thermal_debugfs *thermal_debugfs_add_id(struct dentry *d, int id)
+ snprintf(ids, IDSLENGTH, "%d", id);
+
+ thermal_dbg->d_top = debugfs_create_dir(ids, d);
+- if (!thermal_dbg->d_top) {
++ if (IS_ERR(thermal_dbg->d_top)) {
+ kfree(thermal_dbg);
+ return NULL;
+ }
+diff --git a/drivers/thermal/thermal_of.c b/drivers/thermal/thermal_of.c
+index aa34b6e82e268..1f252692815a1 100644
+--- a/drivers/thermal/thermal_of.c
++++ b/drivers/thermal/thermal_of.c
+@@ -125,7 +125,7 @@ static int thermal_of_populate_trip(struct device_node *np,
+ static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *ntrips)
+ {
+ struct thermal_trip *tt;
+- struct device_node *trips, *trip;
++ struct device_node *trips;
+ int ret, count;
+
+ trips = of_get_child_by_name(np, "trips");
+@@ -150,7 +150,7 @@ static struct thermal_trip *thermal_of_trips_init(struct device_node *np, int *n
+ *ntrips = count;
+
+ count = 0;
+- for_each_child_of_node(trips, trip) {
++ for_each_child_of_node_scoped(trips, trip) {
+ ret = thermal_of_populate_trip(trip, &tt[count++]);
+ if (ret)
+ goto out_kfree;
+@@ -184,14 +184,14 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int
+ * Search for each thermal zone, a defined sensor
+ * corresponding to the one passed as parameter
+ */
+- for_each_available_child_of_node(np, tz) {
++ for_each_available_child_of_node_scoped(np, child) {
+
+ int count, i;
+
+- count = of_count_phandle_with_args(tz, "thermal-sensors",
++ count = of_count_phandle_with_args(child, "thermal-sensors",
+ "#thermal-sensor-cells");
+ if (count <= 0) {
+- pr_err("%pOFn: missing thermal sensor\n", tz);
++ pr_err("%pOFn: missing thermal sensor\n", child);
+ tz = ERR_PTR(-EINVAL);
+ goto out;
+ }
+@@ -200,18 +200,19 @@ static struct device_node *of_thermal_zone_find(struct device_node *sensor, int
+
+ int ret;
+
+- ret = of_parse_phandle_with_args(tz, "thermal-sensors",
++ ret = of_parse_phandle_with_args(child, "thermal-sensors",
+ "#thermal-sensor-cells",
+ i, &sensor_specs);
+ if (ret < 0) {
+- pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", tz, ret);
++ pr_err("%pOFn: Failed to read thermal-sensors cells: %d\n", child, ret);
+ tz = ERR_PTR(ret);
+ goto out;
+ }
+
+ if ((sensor == sensor_specs.np) && id == (sensor_specs.args_count ?
+ sensor_specs.args[0] : 0)) {
+- pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, tz);
++ pr_debug("sensor %pOFn id=%d belongs to %pOFn\n", sensor, id, child);
++ tz = no_free_ptr(child);
+ goto out;
+ }
+ }
+@@ -491,7 +492,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
+ trips = thermal_of_trips_init(np, &ntrips);
+ if (IS_ERR(trips)) {
+ pr_err("Failed to find trip points for %pOFn id=%d\n", sensor, id);
+- return ERR_CAST(trips);
++ ret = PTR_ERR(trips);
++ goto out_of_node_put;
+ }
+
+ ret = thermal_of_monitor_init(np, &delay, &pdelay);
+@@ -519,6 +521,7 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
+ goto out_kfree_trips;
+ }
+
++ of_node_put(np);
+ kfree(trips);
+
+ ret = thermal_zone_device_enable(tz);
+@@ -533,6 +536,8 @@ static struct thermal_zone_device *thermal_of_zone_register(struct device_node *
+
+ out_kfree_trips:
+ kfree(trips);
++out_of_node_put:
++ of_node_put(np);
+
+ return ERR_PTR(ret);
+ }
+diff --git a/drivers/thunderbolt/switch.c b/drivers/thunderbolt/switch.c
+index 326433df5880e..6a2116cbb06f9 100644
+--- a/drivers/thunderbolt/switch.c
++++ b/drivers/thunderbolt/switch.c
+@@ -3392,6 +3392,7 @@ void tb_switch_remove(struct tb_switch *sw)
+ tb_switch_remove(port->remote->sw);
+ port->remote = NULL;
+ } else if (port->xdomain) {
++ port->xdomain->is_unplugged = true;
+ tb_xdomain_remove(port->xdomain);
+ port->xdomain = NULL;
+ }
+diff --git a/drivers/tty/serial/8250/8250_omap.c b/drivers/tty/serial/8250/8250_omap.c
+index 1af9aed99c651..afef1dd4ddf49 100644
+--- a/drivers/tty/serial/8250/8250_omap.c
++++ b/drivers/tty/serial/8250/8250_omap.c
+@@ -27,7 +27,6 @@
+ #include <linux/pm_wakeirq.h>
+ #include <linux/dma-mapping.h>
+ #include <linux/sys_soc.h>
+-#include <linux/pm_domain.h>
+
+ #include "8250.h"
+
+@@ -119,12 +118,6 @@
+ #define UART_OMAP_TO_L 0x26
+ #define UART_OMAP_TO_H 0x27
+
+-/*
+- * Copy of the genpd flags for the console.
+- * Only used if console suspend is disabled
+- */
+-static unsigned int genpd_flags_console;
+-
+ struct omap8250_priv {
+ void __iomem *membase;
+ int line;
+@@ -1655,7 +1648,6 @@ static int omap8250_suspend(struct device *dev)
+ {
+ struct omap8250_priv *priv = dev_get_drvdata(dev);
+ struct uart_8250_port *up = serial8250_get_port(priv->line);
+- struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain);
+ int err = 0;
+
+ serial8250_suspend_port(priv->line);
+@@ -1666,19 +1658,8 @@ static int omap8250_suspend(struct device *dev)
+ if (!device_may_wakeup(dev))
+ priv->wer = 0;
+ serial_out(up, UART_OMAP_WER, priv->wer);
+- if (uart_console(&up->port)) {
+- if (console_suspend_enabled)
+- err = pm_runtime_force_suspend(dev);
+- else {
+- /*
+- * The pd shall not be powered-off (no console suspend).
+- * Make copy of genpd flags before to set it always on.
+- * The original value is restored during the resume.
+- */
+- genpd_flags_console = genpd->flags;
+- genpd->flags |= GENPD_FLAG_ALWAYS_ON;
+- }
+- }
++ if (uart_console(&up->port) && console_suspend_enabled)
++ err = pm_runtime_force_suspend(dev);
+ flush_work(&priv->qos_work);
+
+ return err;
+@@ -1688,16 +1669,12 @@ static int omap8250_resume(struct device *dev)
+ {
+ struct omap8250_priv *priv = dev_get_drvdata(dev);
+ struct uart_8250_port *up = serial8250_get_port(priv->line);
+- struct generic_pm_domain *genpd = pd_to_genpd(dev->pm_domain);
+ int err;
+
+ if (uart_console(&up->port) && console_suspend_enabled) {
+- if (console_suspend_enabled) {
+- err = pm_runtime_force_resume(dev);
+- if (err)
+- return err;
+- } else
+- genpd->flags = genpd_flags_console;
++ err = pm_runtime_force_resume(dev);
++ if (err)
++ return err;
+ }
+
+ serial8250_resume_port(priv->line);
+diff --git a/drivers/tty/serial/atmel_serial.c b/drivers/tty/serial/atmel_serial.c
+index 0a90964d6d107..09b246c9e389e 100644
+--- a/drivers/tty/serial/atmel_serial.c
++++ b/drivers/tty/serial/atmel_serial.c
+@@ -2514,7 +2514,7 @@ static const struct uart_ops atmel_pops = {
+ };
+
+ static const struct serial_rs485 atmel_rs485_supported = {
+- .flags = SER_RS485_ENABLED | SER_RS485_RTS_AFTER_SEND | SER_RS485_RX_DURING_TX,
++ .flags = SER_RS485_ENABLED | SER_RS485_RTS_ON_SEND | SER_RS485_RX_DURING_TX,
+ .delay_rts_before_send = 1,
+ .delay_rts_after_send = 1,
+ };
+diff --git a/drivers/tty/serial/fsl_lpuart.c b/drivers/tty/serial/fsl_lpuart.c
+index 615291ea9b5e9..77efa7ee6eda2 100644
+--- a/drivers/tty/serial/fsl_lpuart.c
++++ b/drivers/tty/serial/fsl_lpuart.c
+@@ -2923,6 +2923,7 @@ static int lpuart_probe(struct platform_device *pdev)
+ pm_runtime_set_autosuspend_delay(&pdev->dev, UART_AUTOSUSPEND_TIMEOUT);
+ pm_runtime_set_active(&pdev->dev);
+ pm_runtime_enable(&pdev->dev);
++ pm_runtime_mark_last_busy(&pdev->dev);
+
+ ret = lpuart_global_reset(sport);
+ if (ret)
+diff --git a/drivers/tty/vt/conmakehash.c b/drivers/tty/vt/conmakehash.c
+index 82d9db68b2ce8..a931fcde7ad98 100644
+--- a/drivers/tty/vt/conmakehash.c
++++ b/drivers/tty/vt/conmakehash.c
+@@ -11,8 +11,6 @@
+ * Copyright (C) 1995-1997 H. Peter Anvin
+ */
+
+-#include <libgen.h>
+-#include <linux/limits.h>
+ #include <stdio.h>
+ #include <stdlib.h>
+ #include <sysexits.h>
+@@ -79,7 +77,6 @@ int main(int argc, char *argv[])
+ {
+ FILE *ctbl;
+ const char *tblname;
+- char base_tblname[PATH_MAX];
+ char buffer[65536];
+ int fontlen;
+ int i, nuni, nent;
+@@ -245,20 +242,15 @@ int main(int argc, char *argv[])
+ for ( i = 0 ; i < fontlen ; i++ )
+ nuni += unicount[i];
+
+- strncpy(base_tblname, tblname, PATH_MAX);
+- base_tblname[PATH_MAX - 1] = 0;
+ printf("\
+ /*\n\
+- * Do not edit this file; it was automatically generated by\n\
+- *\n\
+- * conmakehash %s > [this file]\n\
+- *\n\
++ * Automatically generated file; Do not edit.\n\
+ */\n\
+ \n\
+ #include <linux/types.h>\n\
+ \n\
+ u8 dfont_unicount[%d] = \n\
+-{\n\t", basename(base_tblname), fontlen);
++{\n\t", fontlen);
+
+ for ( i = 0 ; i < fontlen ; i++ )
+ {
+diff --git a/drivers/usb/host/xhci-mem.c b/drivers/usb/host/xhci-mem.c
+index 3100219d6496d..f591ddd086627 100644
+--- a/drivers/usb/host/xhci-mem.c
++++ b/drivers/usb/host/xhci-mem.c
+@@ -1877,7 +1877,7 @@ void xhci_mem_cleanup(struct xhci_hcd *xhci)
+
+ cancel_delayed_work_sync(&xhci->cmd_timer);
+
+- for (i = 0; i < xhci->max_interrupters; i++) {
++ for (i = 0; xhci->interrupters && i < xhci->max_interrupters; i++) {
+ if (xhci->interrupters[i]) {
+ xhci_remove_interrupter(xhci, xhci->interrupters[i]);
+ xhci_free_interrupter(xhci, xhci->interrupters[i]);
+diff --git a/drivers/usb/host/xhci.c b/drivers/usb/host/xhci.c
+index 0a8cf6c17f827..efdf4c228b8c0 100644
+--- a/drivers/usb/host/xhci.c
++++ b/drivers/usb/host/xhci.c
+@@ -2837,7 +2837,7 @@ static int xhci_configure_endpoint(struct xhci_hcd *xhci,
+ xhci->num_active_eps);
+ return -ENOMEM;
+ }
+- if ((xhci->quirks & XHCI_SW_BW_CHECKING) &&
++ if ((xhci->quirks & XHCI_SW_BW_CHECKING) && !ctx_change &&
+ xhci_reserve_bandwidth(xhci, virt_dev, command->in_ctx)) {
+ if ((xhci->quirks & XHCI_EP_LIMIT_QUIRK))
+ xhci_free_host_resources(xhci, ctrl_ctx);
+@@ -4200,8 +4200,10 @@ static int xhci_setup_device(struct usb_hcd *hcd, struct usb_device *udev,
+ mutex_unlock(&xhci->mutex);
+ ret = xhci_disable_slot(xhci, udev->slot_id);
+ xhci_free_virt_device(xhci, udev->slot_id);
+- if (!ret)
+- xhci_alloc_dev(hcd, udev);
++ if (!ret) {
++ if (xhci_alloc_dev(hcd, udev) == 1)
++ xhci_setup_addressable_virt_dev(xhci, udev);
++ }
+ kfree(command->completion);
+ kfree(command);
+ return -EPROTO;
+diff --git a/drivers/usb/misc/usb-ljca.c b/drivers/usb/misc/usb-ljca.c
+index 2d30fc1be3066..1a8d5e80b9aec 100644
+--- a/drivers/usb/misc/usb-ljca.c
++++ b/drivers/usb/misc/usb-ljca.c
+@@ -169,6 +169,7 @@ static const struct acpi_device_id ljca_gpio_hids[] = {
+ { "INTC1096" },
+ { "INTC100B" },
+ { "INTC10D1" },
++ { "INTC10B5" },
+ {},
+ };
+
+diff --git a/drivers/usb/typec/tcpm/tcpm.c b/drivers/usb/typec/tcpm/tcpm.c
+index 5d4da962acc87..ea388e793f882 100644
+--- a/drivers/usb/typec/tcpm/tcpm.c
++++ b/drivers/usb/typec/tcpm/tcpm.c
+@@ -5630,7 +5630,6 @@ static void run_state_machine(struct tcpm_port *port)
+ break;
+ case PORT_RESET:
+ tcpm_reset_port(port);
+- port->pd_events = 0;
+ if (port->self_powered)
+ tcpm_set_cc(port, TYPEC_CC_OPEN);
+ else
+diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
+index 6cc80fb10da23..5eb06fccc32e5 100644
+--- a/fs/btrfs/delayed-ref.c
++++ b/fs/btrfs/delayed-ref.c
+@@ -1169,6 +1169,73 @@ btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 byt
+ return find_ref_head(delayed_refs, bytenr, false);
+ }
+
++static int find_comp(struct btrfs_delayed_ref_node *entry, u64 root, u64 parent)
++{
++ int type = parent ? BTRFS_SHARED_BLOCK_REF_KEY : BTRFS_TREE_BLOCK_REF_KEY;
++
++ if (type < entry->type)
++ return -1;
++ if (type > entry->type)
++ return 1;
++
++ if (type == BTRFS_TREE_BLOCK_REF_KEY) {
++ if (root < entry->ref_root)
++ return -1;
++ if (root > entry->ref_root)
++ return 1;
++ } else {
++ if (parent < entry->parent)
++ return -1;
++ if (parent > entry->parent)
++ return 1;
++ }
++ return 0;
++}
++
++/*
++ * Check to see if a given root/parent reference is attached to the head. This
++ * only checks for BTRFS_ADD_DELAYED_REF references that match, as that
++ * indicates the reference exists for the given root or parent. This is for
++ * tree blocks only.
++ *
++ * @head: the head of the bytenr we're searching.
++ * @root: the root objectid of the reference if it is a normal reference.
++ * @parent: the parent if this is a shared backref.
++ */
++bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
++ u64 root, u64 parent)
++{
++ struct rb_node *node;
++ bool found = false;
++
++ lockdep_assert_held(&head->mutex);
++
++ spin_lock(&head->lock);
++ node = head->ref_tree.rb_root.rb_node;
++ while (node) {
++ struct btrfs_delayed_ref_node *entry;
++ int ret;
++
++ entry = rb_entry(node, struct btrfs_delayed_ref_node, ref_node);
++ ret = find_comp(entry, root, parent);
++ if (ret < 0) {
++ node = node->rb_left;
++ } else if (ret > 0) {
++ node = node->rb_right;
++ } else {
++ /*
++ * We only want to count ADD actions, as drops mean the
++ * ref doesn't exist.
++ */
++ if (entry->action == BTRFS_ADD_DELAYED_REF)
++ found = true;
++ break;
++ }
++ }
++ spin_unlock(&head->lock);
++ return found;
++}
++
+ void __cold btrfs_delayed_ref_exit(void)
+ {
+ kmem_cache_destroy(btrfs_delayed_ref_head_cachep);
+diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
+index 04b180ebe1fe0..1d11a1a6f9cb1 100644
+--- a/fs/btrfs/delayed-ref.h
++++ b/fs/btrfs/delayed-ref.h
+@@ -389,6 +389,8 @@ int btrfs_delayed_refs_rsv_refill(struct btrfs_fs_info *fs_info,
+ void btrfs_migrate_to_delayed_refs_rsv(struct btrfs_fs_info *fs_info,
+ u64 num_bytes);
+ bool btrfs_check_space_for_delayed_refs(struct btrfs_fs_info *fs_info);
++bool btrfs_find_delayed_tree_ref(struct btrfs_delayed_ref_head *head,
++ u64 root, u64 parent);
+
+ static inline u64 btrfs_delayed_ref_owner(struct btrfs_delayed_ref_node *node)
+ {
+diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
+index 844b677d054ec..8bf980123c5c5 100644
+--- a/fs/btrfs/extent-tree.c
++++ b/fs/btrfs/extent-tree.c
+@@ -5387,23 +5387,62 @@ static int check_ref_exists(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 bytenr, u64 parent,
+ int level)
+ {
++ struct btrfs_delayed_ref_root *delayed_refs;
++ struct btrfs_delayed_ref_head *head;
+ struct btrfs_path *path;
+ struct btrfs_extent_inline_ref *iref;
+ int ret;
++ bool exists = false;
+
+ path = btrfs_alloc_path();
+ if (!path)
+ return -ENOMEM;
+-
++again:
+ ret = lookup_extent_backref(trans, path, &iref, bytenr,
+ root->fs_info->nodesize, parent,
+ btrfs_root_id(root), level, 0);
++ if (ret != -ENOENT) {
++ /*
++ * If we get 0 then we found our reference, return 1, else
++ * return the error if it's not -ENOENT;
++ */
++ btrfs_free_path(path);
++ return (ret < 0 ) ? ret : 1;
++ }
++
++ /*
++ * We could have a delayed ref with this reference, so look it up while
++ * we're holding the path open to make sure we don't race with the
++ * delayed ref running.
++ */
++ delayed_refs = &trans->transaction->delayed_refs;
++ spin_lock(&delayed_refs->lock);
++ head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
++ if (!head)
++ goto out;
++ if (!mutex_trylock(&head->mutex)) {
++ /*
++ * We're contended, means that the delayed ref is running, get a
++ * reference and wait for the ref head to be complete and then
++ * try again.
++ */
++ refcount_inc(&head->refs);
++ spin_unlock(&delayed_refs->lock);
++
++ btrfs_release_path(path);
++
++ mutex_lock(&head->mutex);
++ mutex_unlock(&head->mutex);
++ btrfs_put_delayed_ref_head(head);
++ goto again;
++ }
++
++ exists = btrfs_find_delayed_tree_ref(head, root->root_key.objectid, parent);
++ mutex_unlock(&head->mutex);
++out:
++ spin_unlock(&delayed_refs->lock);
+ btrfs_free_path(path);
+- if (ret == -ENOENT)
+- return 0;
+- if (ret < 0)
+- return ret;
+- return 1;
++ return exists ? 1 : 0;
+ }
+
+ /*
+diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
+index 0486b1f911248..3bad7c0be1f10 100644
+--- a/fs/btrfs/extent_io.c
++++ b/fs/btrfs/extent_io.c
+@@ -1420,6 +1420,13 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
+ free_extent_map(em);
+ em = NULL;
+
++ /*
++ * Although the PageDirty bit might be cleared before entering
++ * this function, subpage dirty bit is not cleared.
++ * So clear subpage dirty bit here so next time we won't submit
++ * page for range already written to disk.
++ */
++ btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
+ btrfs_set_range_writeback(inode, cur, cur + iosize - 1);
+ if (!PageWriteback(page)) {
+ btrfs_err(inode->root->fs_info,
+@@ -1427,13 +1434,6 @@ static noinline_for_stack int __extent_writepage_io(struct btrfs_inode *inode,
+ page->index, cur, end);
+ }
+
+- /*
+- * Although the PageDirty bit is cleared before entering this
+- * function, subpage dirty bit is not cleared.
+- * So clear subpage dirty bit here so next time we won't submit
+- * page for range already written to disk.
+- */
+- btrfs_folio_clear_dirty(fs_info, page_folio(page), cur, iosize);
+
+ submit_extent_page(bio_ctrl, disk_bytenr, page, iosize,
+ cur - page_offset(page));
+diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
+index b4c9a6aa118cd..6853f043c2c14 100644
+--- a/fs/btrfs/extent_map.c
++++ b/fs/btrfs/extent_map.c
+@@ -1065,8 +1065,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
+ return 0;
+
+ /*
+- * We want to be fast because we can be called from any path trying to
+- * allocate memory, so if the lock is busy we don't want to spend time
++ * We want to be fast so if the lock is busy we don't want to spend time
+ * waiting for it - either some task is about to do IO for the inode or
+ * we may have another task shrinking extent maps, here in this code, so
+ * skip this inode.
+@@ -1109,9 +1108,7 @@ static long btrfs_scan_inode(struct btrfs_inode *inode, struct btrfs_em_shrink_c
+ /*
+ * Stop if we need to reschedule or there's contention on the
+ * lock. This is to avoid slowing other tasks trying to take the
+- * lock and because the shrinker might be called during a memory
+- * allocation path and we want to avoid taking a very long time
+- * and slowing down all sorts of tasks.
++ * lock.
+ */
+ if (need_resched() || rwlock_needbreak(&tree->lock))
+ break;
+@@ -1139,12 +1136,7 @@ static long btrfs_scan_root(struct btrfs_root *root, struct btrfs_em_shrink_ctx
+ if (ctx->scanned >= ctx->nr_to_scan)
+ break;
+
+- /*
+- * We may be called from memory allocation paths, so we don't
+- * want to take too much time and slowdown tasks.
+- */
+- if (need_resched())
+- break;
++ cond_resched();
+
+ inode = btrfs_find_first_inode(root, min_ino);
+ }
+@@ -1202,14 +1194,12 @@ long btrfs_free_extent_maps(struct btrfs_fs_info *fs_info, long nr_to_scan)
+ ctx.last_ino);
+ }
+
+- /*
+- * We may be called from memory allocation paths, so we don't want to
+- * take too much time and slowdown tasks, so stop if we need reschedule.
+- */
+- while (ctx.scanned < ctx.nr_to_scan && !need_resched()) {
++ while (ctx.scanned < ctx.nr_to_scan) {
+ struct btrfs_root *root;
+ unsigned long count;
+
++ cond_resched();
++
+ spin_lock(&fs_info->fs_roots_radix_lock);
+ count = radix_tree_gang_lookup(&fs_info->fs_roots_radix,
+ (void **)&root,
+diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
+index 62c3dea9572ab..1926a228d0ba0 100644
+--- a/fs/btrfs/free-space-cache.c
++++ b/fs/btrfs/free-space-cache.c
+@@ -2698,15 +2698,16 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
+ u64 offset = bytenr - block_group->start;
+ u64 to_free, to_unusable;
+ int bg_reclaim_threshold = 0;
+- bool initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
++ bool initial;
+ u64 reclaimable_unusable;
+
+- WARN_ON(!initial && offset + size > block_group->zone_capacity);
++ spin_lock(&block_group->lock);
+
++ initial = ((size == block_group->length) && (block_group->alloc_offset == 0));
++ WARN_ON(!initial && offset + size > block_group->zone_capacity);
+ if (!initial)
+ bg_reclaim_threshold = READ_ONCE(sinfo->bg_reclaim_threshold);
+
+- spin_lock(&ctl->tree_lock);
+ if (!used)
+ to_free = size;
+ else if (initial)
+@@ -2719,7 +2720,9 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
+ to_free = offset + size - block_group->alloc_offset;
+ to_unusable = size - to_free;
+
++ spin_lock(&ctl->tree_lock);
+ ctl->free_space += to_free;
++ spin_unlock(&ctl->tree_lock);
+ /*
+ * If the block group is read-only, we should account freed space into
+ * bytes_readonly.
+@@ -2728,11 +2731,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
+ block_group->zone_unusable += to_unusable;
+ WARN_ON(block_group->zone_unusable > block_group->length);
+ }
+- spin_unlock(&ctl->tree_lock);
+ if (!used) {
+- spin_lock(&block_group->lock);
+ block_group->alloc_offset -= size;
+- spin_unlock(&block_group->lock);
+ }
+
+ reclaimable_unusable = block_group->zone_unusable -
+@@ -2746,6 +2746,8 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
+ btrfs_mark_bg_to_reclaim(block_group);
+ }
+
++ spin_unlock(&block_group->lock);
++
+ return 0;
+ }
+
+diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
+index 3dd4a48479a9e..d1a04c0c576ed 100644
+--- a/fs/btrfs/send.c
++++ b/fs/btrfs/send.c
+@@ -6158,25 +6158,51 @@ static int send_write_or_clone(struct send_ctx *sctx,
+ u64 offset = key->offset;
+ u64 end;
+ u64 bs = sctx->send_root->fs_info->sectorsize;
++ struct btrfs_file_extent_item *ei;
++ u64 disk_byte;
++ u64 data_offset;
++ u64 num_bytes;
++ struct btrfs_inode_info info = { 0 };
+
+ end = min_t(u64, btrfs_file_extent_end(path), sctx->cur_inode_size);
+ if (offset >= end)
+ return 0;
+
+- if (clone_root && IS_ALIGNED(end, bs)) {
+- struct btrfs_file_extent_item *ei;
+- u64 disk_byte;
+- u64 data_offset;
++ num_bytes = end - offset;
+
+- ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
+- struct btrfs_file_extent_item);
+- disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
+- data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
+- ret = clone_range(sctx, path, clone_root, disk_byte,
+- data_offset, offset, end - offset);
+- } else {
+- ret = send_extent_data(sctx, path, offset, end - offset);
+- }
++ if (!clone_root)
++ goto write_data;
++
++ if (IS_ALIGNED(end, bs))
++ goto clone_data;
++
++ /*
++ * If the extent end is not aligned, we can clone if the extent ends at
++ * the i_size of the inode and the clone range ends at the i_size of the
++ * source inode, otherwise the clone operation fails with -EINVAL.
++ */
++ if (end != sctx->cur_inode_size)
++ goto write_data;
++
++ ret = get_inode_info(clone_root->root, clone_root->ino, &info);
++ if (ret < 0)
++ return ret;
++
++ if (clone_root->offset + num_bytes == info.size)
++ goto clone_data;
++
++write_data:
++ ret = send_extent_data(sctx, path, offset, num_bytes);
++ sctx->cur_inode_next_write_offset = end;
++ return ret;
++
++clone_data:
++ ei = btrfs_item_ptr(path->nodes[0], path->slots[0],
++ struct btrfs_file_extent_item);
++ disk_byte = btrfs_file_extent_disk_bytenr(path->nodes[0], ei);
++ data_offset = btrfs_file_extent_offset(path->nodes[0], ei);
++ ret = clone_range(sctx, path, clone_root, disk_byte, data_offset, offset,
++ num_bytes);
+ sctx->cur_inode_next_write_offset = end;
+ return ret;
+ }
+diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
+index f05cce7c8b8d1..03107c01b2875 100644
+--- a/fs/btrfs/super.c
++++ b/fs/btrfs/super.c
+@@ -28,6 +28,7 @@
+ #include <linux/btrfs.h>
+ #include <linux/security.h>
+ #include <linux/fs_parser.h>
++#include <linux/swap.h>
+ #include "messages.h"
+ #include "delayed-inode.h"
+ #include "ctree.h"
+@@ -2386,7 +2387,13 @@ static long btrfs_nr_cached_objects(struct super_block *sb, struct shrink_contro
+
+ trace_btrfs_extent_map_shrinker_count(fs_info, nr);
+
+- return nr;
++ /*
++ * Only report the real number for DEBUG builds, as there are reports of
++ * serious performance degradation caused by too frequent shrinks.
++ */
++ if (IS_ENABLED(CONFIG_BTRFS_DEBUG))
++ return nr;
++ return 0;
+ }
+
+ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_control *sc)
+@@ -2394,6 +2401,15 @@ static long btrfs_free_cached_objects(struct super_block *sb, struct shrink_cont
+ const long nr_to_scan = min_t(unsigned long, LONG_MAX, sc->nr_to_scan);
+ struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
++ /*
++ * We may be called from any task trying to allocate memory and we don't
++ * want to slow it down with scanning and dropping extent maps. It would
++ * also cause heavy lock contention if many tasks concurrently enter
++ * here. Therefore only allow kswapd tasks to scan and drop extent maps.
++ */
++ if (!current_is_kswapd())
++ return 0;
++
+ return btrfs_free_extent_maps(fs_info, nr_to_scan);
+ }
+
+diff --git a/fs/btrfs/tree-checker.c b/fs/btrfs/tree-checker.c
+index a2c3651a3d8fc..897e19790522d 100644
+--- a/fs/btrfs/tree-checker.c
++++ b/fs/btrfs/tree-checker.c
+@@ -551,9 +551,10 @@ static int check_dir_item(struct extent_buffer *leaf,
+
+ /* dir type check */
+ dir_type = btrfs_dir_ftype(leaf, di);
+- if (unlikely(dir_type >= BTRFS_FT_MAX)) {
++ if (unlikely(dir_type <= BTRFS_FT_UNKNOWN ||
++ dir_type >= BTRFS_FT_MAX)) {
+ dir_item_err(leaf, slot,
+- "invalid dir item type, have %u expect [0, %u)",
++ "invalid dir item type, have %u expect (0, %u)",
+ dir_type, BTRFS_FT_MAX);
+ return -EUCLEAN;
+ }
+@@ -1717,6 +1718,72 @@ static int check_raid_stripe_extent(const struct extent_buffer *leaf,
+ return 0;
+ }
+
++static int check_dev_extent_item(const struct extent_buffer *leaf,
++ const struct btrfs_key *key,
++ int slot,
++ struct btrfs_key *prev_key)
++{
++ struct btrfs_dev_extent *de;
++ const u32 sectorsize = leaf->fs_info->sectorsize;
++
++ de = btrfs_item_ptr(leaf, slot, struct btrfs_dev_extent);
++ /* Basic fixed member checks. */
++ if (unlikely(btrfs_dev_extent_chunk_tree(leaf, de) !=
++ BTRFS_CHUNK_TREE_OBJECTID)) {
++ generic_err(leaf, slot,
++ "invalid dev extent chunk tree id, has %llu expect %llu",
++ btrfs_dev_extent_chunk_tree(leaf, de),
++ BTRFS_CHUNK_TREE_OBJECTID);
++ return -EUCLEAN;
++ }
++ if (unlikely(btrfs_dev_extent_chunk_objectid(leaf, de) !=
++ BTRFS_FIRST_CHUNK_TREE_OBJECTID)) {
++ generic_err(leaf, slot,
++ "invalid dev extent chunk objectid, has %llu expect %llu",
++ btrfs_dev_extent_chunk_objectid(leaf, de),
++ BTRFS_FIRST_CHUNK_TREE_OBJECTID);
++ return -EUCLEAN;
++ }
++ /* Alignment check. */
++ if (unlikely(!IS_ALIGNED(key->offset, sectorsize))) {
++ generic_err(leaf, slot,
++ "invalid dev extent key.offset, has %llu not aligned to %u",
++ key->offset, sectorsize);
++ return -EUCLEAN;
++ }
++ if (unlikely(!IS_ALIGNED(btrfs_dev_extent_chunk_offset(leaf, de),
++ sectorsize))) {
++ generic_err(leaf, slot,
++ "invalid dev extent chunk offset, has %llu not aligned to %u",
++ btrfs_dev_extent_chunk_objectid(leaf, de),
++ sectorsize);
++ return -EUCLEAN;
++ }
++ if (unlikely(!IS_ALIGNED(btrfs_dev_extent_length(leaf, de),
++ sectorsize))) {
++ generic_err(leaf, slot,
++ "invalid dev extent length, has %llu not aligned to %u",
++ btrfs_dev_extent_length(leaf, de), sectorsize);
++ return -EUCLEAN;
++ }
++ /* Overlap check with previous dev extent. */
++ if (slot && prev_key->objectid == key->objectid &&
++ prev_key->type == key->type) {
++ struct btrfs_dev_extent *prev_de;
++ u64 prev_len;
++
++ prev_de = btrfs_item_ptr(leaf, slot - 1, struct btrfs_dev_extent);
++ prev_len = btrfs_dev_extent_length(leaf, prev_de);
++ if (unlikely(prev_key->offset + prev_len > key->offset)) {
++ generic_err(leaf, slot,
++ "dev extent overlap, prev offset %llu len %llu current offset %llu",
++ prev_key->objectid, prev_len, key->offset);
++ return -EUCLEAN;
++ }
++ }
++ return 0;
++}
++
+ /*
+ * Common point to switch the item-specific validation.
+ */
+@@ -1753,6 +1820,9 @@ static enum btrfs_tree_block_status check_leaf_item(struct extent_buffer *leaf,
+ case BTRFS_DEV_ITEM_KEY:
+ ret = check_dev_item(leaf, key, slot);
+ break;
++ case BTRFS_DEV_EXTENT_KEY:
++ ret = check_dev_extent_item(leaf, key, slot, prev_key);
++ break;
+ case BTRFS_INODE_ITEM_KEY:
+ ret = check_inode_item(leaf, key, slot);
+ break;
+diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
+index 8c16bc5250ef5..73b5a07bf94de 100644
+--- a/fs/ceph/addr.c
++++ b/fs/ceph/addr.c
+@@ -498,6 +498,11 @@ const struct netfs_request_ops ceph_netfs_ops = {
+ };
+
+ #ifdef CONFIG_CEPH_FSCACHE
++static void ceph_set_page_fscache(struct page *page)
++{
++ folio_start_private_2(page_folio(page)); /* [DEPRECATED] */
++}
++
+ static void ceph_fscache_write_terminated(void *priv, ssize_t error, bool was_async)
+ {
+ struct inode *inode = priv;
+@@ -515,6 +520,10 @@ static void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, b
+ ceph_fscache_write_terminated, inode, true, caching);
+ }
+ #else
++static inline void ceph_set_page_fscache(struct page *page)
++{
++}
++
+ static inline void ceph_fscache_write_to_cache(struct inode *inode, u64 off, u64 len, bool caching)
+ {
+ }
+@@ -706,6 +715,8 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
+ len = wlen;
+
+ set_page_writeback(page);
++ if (caching)
++ ceph_set_page_fscache(page);
+ ceph_fscache_write_to_cache(inode, page_off, len, caching);
+
+ if (IS_ENCRYPTED(inode)) {
+@@ -789,6 +800,8 @@ static int ceph_writepage(struct page *page, struct writeback_control *wbc)
+ return AOP_WRITEPAGE_ACTIVATE;
+ }
+
++ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
++
+ err = writepage_nounlock(page, wbc);
+ if (err == -ERESTARTSYS) {
+ /* direct memory reclaimer was killed by SIGKILL. return 0
+@@ -1062,7 +1075,8 @@ static int ceph_writepages_start(struct address_space *mapping,
+ unlock_page(page);
+ break;
+ }
+- if (PageWriteback(page)) {
++ if (PageWriteback(page) ||
++ PagePrivate2(page) /* [DEPRECATED] */) {
+ if (wbc->sync_mode == WB_SYNC_NONE) {
+ doutc(cl, "%p under writeback\n", page);
+ unlock_page(page);
+@@ -1070,6 +1084,7 @@ static int ceph_writepages_start(struct address_space *mapping,
+ }
+ doutc(cl, "waiting on writeback %p\n", page);
+ wait_on_page_writeback(page);
++ folio_wait_private_2(page_folio(page)); /* [DEPRECATED] */
+ }
+
+ if (!clear_page_dirty_for_io(page)) {
+@@ -1254,6 +1269,8 @@ static int ceph_writepages_start(struct address_space *mapping,
+ }
+
+ set_page_writeback(page);
++ if (caching)
++ ceph_set_page_fscache(page);
+ len += thp_size(page);
+ }
+ ceph_fscache_write_to_cache(inode, offset, len, caching);
+diff --git a/fs/file.c b/fs/file.c
+index a11e59b5d6026..655338effe9c7 100644
+--- a/fs/file.c
++++ b/fs/file.c
+@@ -46,27 +46,23 @@ static void free_fdtable_rcu(struct rcu_head *rcu)
+ #define BITBIT_NR(nr) BITS_TO_LONGS(BITS_TO_LONGS(nr))
+ #define BITBIT_SIZE(nr) (BITBIT_NR(nr) * sizeof(long))
+
++#define fdt_words(fdt) ((fdt)->max_fds / BITS_PER_LONG) // words in ->open_fds
+ /*
+ * Copy 'count' fd bits from the old table to the new table and clear the extra
+ * space if any. This does not copy the file pointers. Called with the files
+ * spinlock held for write.
+ */
+-static void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
+- unsigned int count)
++static inline void copy_fd_bitmaps(struct fdtable *nfdt, struct fdtable *ofdt,
++ unsigned int copy_words)
+ {
+- unsigned int cpy, set;
+-
+- cpy = count / BITS_PER_BYTE;
+- set = (nfdt->max_fds - count) / BITS_PER_BYTE;
+- memcpy(nfdt->open_fds, ofdt->open_fds, cpy);
+- memset((char *)nfdt->open_fds + cpy, 0, set);
+- memcpy(nfdt->close_on_exec, ofdt->close_on_exec, cpy);
+- memset((char *)nfdt->close_on_exec + cpy, 0, set);
+-
+- cpy = BITBIT_SIZE(count);
+- set = BITBIT_SIZE(nfdt->max_fds) - cpy;
+- memcpy(nfdt->full_fds_bits, ofdt->full_fds_bits, cpy);
+- memset((char *)nfdt->full_fds_bits + cpy, 0, set);
++ unsigned int nwords = fdt_words(nfdt);
++
++ bitmap_copy_and_extend(nfdt->open_fds, ofdt->open_fds,
++ copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
++ bitmap_copy_and_extend(nfdt->close_on_exec, ofdt->close_on_exec,
++ copy_words * BITS_PER_LONG, nwords * BITS_PER_LONG);
++ bitmap_copy_and_extend(nfdt->full_fds_bits, ofdt->full_fds_bits,
++ copy_words, nwords);
+ }
+
+ /*
+@@ -84,7 +80,7 @@ static void copy_fdtable(struct fdtable *nfdt, struct fdtable *ofdt)
+ memcpy(nfdt->fd, ofdt->fd, cpy);
+ memset((char *)nfdt->fd + cpy, 0, set);
+
+- copy_fd_bitmaps(nfdt, ofdt, ofdt->max_fds);
++ copy_fd_bitmaps(nfdt, ofdt, fdt_words(ofdt));
+ }
+
+ /*
+@@ -379,7 +375,7 @@ struct files_struct *dup_fd(struct files_struct *oldf, unsigned int max_fds, int
+ open_files = sane_fdtable_size(old_fdt, max_fds);
+ }
+
+- copy_fd_bitmaps(new_fdt, old_fdt, open_files);
++ copy_fd_bitmaps(new_fdt, old_fdt, open_files / BITS_PER_LONG);
+
+ old_fds = old_fdt->fd;
+ new_fds = new_fdt->fd;
+diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
+index 9eb191b5c4de1..7146038b2fe7d 100644
+--- a/fs/fuse/dev.c
++++ b/fs/fuse/dev.c
+@@ -1618,9 +1618,11 @@ static int fuse_notify_store(struct fuse_conn *fc, unsigned int size,
+
+ this_num = min_t(unsigned, num, PAGE_SIZE - offset);
+ err = fuse_copy_page(cs, &page, offset, this_num, 0);
+- if (!err && offset == 0 &&
+- (this_num == PAGE_SIZE || file_size == end))
++ if (!PageUptodate(page) && !err && offset == 0 &&
++ (this_num == PAGE_SIZE || file_size == end)) {
++ zero_user_segment(page, this_num, PAGE_SIZE);
+ SetPageUptodate(page);
++ }
+ unlock_page(page);
+ put_page(page);
+
+diff --git a/fs/inode.c b/fs/inode.c
+index 3a41f83a4ba55..f5add7222c98e 100644
+--- a/fs/inode.c
++++ b/fs/inode.c
+@@ -486,6 +486,39 @@ static void inode_lru_list_del(struct inode *inode)
+ this_cpu_dec(nr_unused);
+ }
+
++static void inode_pin_lru_isolating(struct inode *inode)
++{
++ lockdep_assert_held(&inode->i_lock);
++ WARN_ON(inode->i_state & (I_LRU_ISOLATING | I_FREEING | I_WILL_FREE));
++ inode->i_state |= I_LRU_ISOLATING;
++}
++
++static void inode_unpin_lru_isolating(struct inode *inode)
++{
++ spin_lock(&inode->i_lock);
++ WARN_ON(!(inode->i_state & I_LRU_ISOLATING));
++ inode->i_state &= ~I_LRU_ISOLATING;
++ smp_mb();
++ wake_up_bit(&inode->i_state, __I_LRU_ISOLATING);
++ spin_unlock(&inode->i_lock);
++}
++
++static void inode_wait_for_lru_isolating(struct inode *inode)
++{
++ spin_lock(&inode->i_lock);
++ if (inode->i_state & I_LRU_ISOLATING) {
++ DEFINE_WAIT_BIT(wq, &inode->i_state, __I_LRU_ISOLATING);
++ wait_queue_head_t *wqh;
++
++ wqh = bit_waitqueue(&inode->i_state, __I_LRU_ISOLATING);
++ spin_unlock(&inode->i_lock);
++ __wait_on_bit(wqh, &wq, bit_wait, TASK_UNINTERRUPTIBLE);
++ spin_lock(&inode->i_lock);
++ WARN_ON(inode->i_state & I_LRU_ISOLATING);
++ }
++ spin_unlock(&inode->i_lock);
++}
++
+ /**
+ * inode_sb_list_add - add inode to the superblock list of inodes
+ * @inode: inode to add
+@@ -655,6 +688,8 @@ static void evict(struct inode *inode)
+
+ inode_sb_list_del(inode);
+
++ inode_wait_for_lru_isolating(inode);
++
+ /*
+ * Wait for flusher thread to be done with the inode so that filesystem
+ * does not start destroying it while writeback is still running. Since
+@@ -843,7 +878,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
+ * be under pressure before the cache inside the highmem zone.
+ */
+ if (inode_has_buffers(inode) || !mapping_empty(&inode->i_data)) {
+- __iget(inode);
++ inode_pin_lru_isolating(inode);
+ spin_unlock(&inode->i_lock);
+ spin_unlock(lru_lock);
+ if (remove_inode_buffers(inode)) {
+@@ -855,7 +890,7 @@ static enum lru_status inode_lru_isolate(struct list_head *item,
+ __count_vm_events(PGINODESTEAL, reap);
+ mm_account_reclaimed_pages(reap);
+ }
+- iput(inode);
++ inode_unpin_lru_isolating(inode);
+ spin_lock(lru_lock);
+ return LRU_RETRY;
+ }
+diff --git a/fs/libfs.c b/fs/libfs.c
+index b635ee5adbcce..65279e53fbf27 100644
+--- a/fs/libfs.c
++++ b/fs/libfs.c
+@@ -450,6 +450,14 @@ void simple_offset_destroy(struct offset_ctx *octx)
+ mtree_destroy(&octx->mt);
+ }
+
++static int offset_dir_open(struct inode *inode, struct file *file)
++{
++ struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
++
++ file->private_data = (void *)ctx->next_offset;
++ return 0;
++}
++
+ /**
+ * offset_dir_llseek - Advance the read position of a directory descriptor
+ * @file: an open directory whose position is to be updated
+@@ -463,6 +471,9 @@ void simple_offset_destroy(struct offset_ctx *octx)
+ */
+ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
+ {
++ struct inode *inode = file->f_inode;
++ struct offset_ctx *ctx = inode->i_op->get_offset_ctx(inode);
++
+ switch (whence) {
+ case SEEK_CUR:
+ offset += file->f_pos;
+@@ -476,7 +487,8 @@ static loff_t offset_dir_llseek(struct file *file, loff_t offset, int whence)
+ }
+
+ /* In this case, ->private_data is protected by f_pos_lock */
+- file->private_data = NULL;
++ if (!offset)
++ file->private_data = (void *)ctx->next_offset;
+ return vfs_setpos(file, offset, LONG_MAX);
+ }
+
+@@ -507,7 +519,7 @@ static bool offset_dir_emit(struct dir_context *ctx, struct dentry *dentry)
+ inode->i_ino, fs_umode_to_dtype(inode->i_mode));
+ }
+
+-static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
++static void offset_iterate_dir(struct inode *inode, struct dir_context *ctx, long last_index)
+ {
+ struct offset_ctx *octx = inode->i_op->get_offset_ctx(inode);
+ struct dentry *dentry;
+@@ -515,17 +527,21 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+ while (true) {
+ dentry = offset_find_next(octx, ctx->pos);
+ if (!dentry)
+- return ERR_PTR(-ENOENT);
++ return;
++
++ if (dentry2offset(dentry) >= last_index) {
++ dput(dentry);
++ return;
++ }
+
+ if (!offset_dir_emit(ctx, dentry)) {
+ dput(dentry);
+- break;
++ return;
+ }
+
+ ctx->pos = dentry2offset(dentry) + 1;
+ dput(dentry);
+ }
+- return NULL;
+ }
+
+ /**
+@@ -552,22 +568,19 @@ static void *offset_iterate_dir(struct inode *inode, struct dir_context *ctx)
+ static int offset_readdir(struct file *file, struct dir_context *ctx)
+ {
+ struct dentry *dir = file->f_path.dentry;
++ long last_index = (long)file->private_data;
+
+ lockdep_assert_held(&d_inode(dir)->i_rwsem);
+
+ if (!dir_emit_dots(file, ctx))
+ return 0;
+
+- /* In this case, ->private_data is protected by f_pos_lock */
+- if (ctx->pos == DIR_OFFSET_MIN)
+- file->private_data = NULL;
+- else if (file->private_data == ERR_PTR(-ENOENT))
+- return 0;
+- file->private_data = offset_iterate_dir(d_inode(dir), ctx);
++ offset_iterate_dir(d_inode(dir), ctx, last_index);
+ return 0;
+ }
+
+ const struct file_operations simple_offset_dir_operations = {
++ .open = offset_dir_open,
+ .llseek = offset_dir_llseek,
+ .iterate_shared = offset_readdir,
+ .read = generic_read_dir,
+diff --git a/fs/locks.c b/fs/locks.c
+index 9afb16e0683ff..e45cad40f8b6b 100644
+--- a/fs/locks.c
++++ b/fs/locks.c
+@@ -2984,7 +2984,7 @@ static int __init filelock_init(void)
+ filelock_cache = kmem_cache_create("file_lock_cache",
+ sizeof(struct file_lock), 0, SLAB_PANIC, NULL);
+
+- filelease_cache = kmem_cache_create("file_lock_cache",
++ filelease_cache = kmem_cache_create("file_lease_cache",
+ sizeof(struct file_lease), 0, SLAB_PANIC, NULL);
+
+ for_each_possible_cpu(i) {
+diff --git a/fs/netfs/buffered_read.c b/fs/netfs/buffered_read.c
+index 4c0401dbbfcfa..9aa045e2ab0ae 100644
+--- a/fs/netfs/buffered_read.c
++++ b/fs/netfs/buffered_read.c
+@@ -466,7 +466,7 @@ int netfs_write_begin(struct netfs_inode *ctx,
+ if (!netfs_is_cache_enabled(ctx) &&
+ netfs_skip_folio_read(folio, pos, len, false)) {
+ netfs_stat(&netfs_n_rh_write_zskip);
+- goto have_folio;
++ goto have_folio_no_wait;
+ }
+
+ rreq = netfs_alloc_request(mapping, file,
+@@ -507,6 +507,12 @@ int netfs_write_begin(struct netfs_inode *ctx,
+ netfs_put_request(rreq, false, netfs_rreq_trace_put_return);
+
+ have_folio:
++ if (test_bit(NETFS_ICTX_USE_PGPRIV2, &ctx->flags)) {
++ ret = folio_wait_private_2_killable(folio);
++ if (ret < 0)
++ goto error;
++ }
++have_folio_no_wait:
+ *_folio = folio;
+ kleave(" = 0");
+ return 0;
+diff --git a/fs/netfs/buffered_write.c b/fs/netfs/buffered_write.c
+index ecbc99ec7d367..18055c1e01835 100644
+--- a/fs/netfs/buffered_write.c
++++ b/fs/netfs/buffered_write.c
+@@ -184,7 +184,7 @@ ssize_t netfs_perform_write(struct kiocb *iocb, struct iov_iter *iter,
+ unsigned int bdp_flags = (iocb->ki_flags & IOCB_NOWAIT) ? BDP_ASYNC : 0;
+ ssize_t written = 0, ret, ret2;
+ loff_t i_size, pos = iocb->ki_pos, from, to;
+- size_t max_chunk = PAGE_SIZE << MAX_PAGECACHE_ORDER;
++ size_t max_chunk = mapping_max_folio_size(mapping);
+ bool maybe_trouble = false;
+
+ if (unlikely(test_bit(NETFS_ICTX_WRITETHROUGH, &ctx->flags) ||
+diff --git a/fs/netfs/fscache_cookie.c b/fs/netfs/fscache_cookie.c
+index 4d1e8bf4c615f..431a1905fcb4c 100644
+--- a/fs/netfs/fscache_cookie.c
++++ b/fs/netfs/fscache_cookie.c
+@@ -741,6 +741,10 @@ static void fscache_cookie_state_machine(struct fscache_cookie *cookie)
+ spin_lock(&cookie->lock);
+ }
+ if (test_bit(FSCACHE_COOKIE_DO_LRU_DISCARD, &cookie->flags)) {
++ if (atomic_read(&cookie->n_accesses) != 0)
++ /* still being accessed: postpone it */
++ break;
++
+ __fscache_set_cookie_state(cookie,
+ FSCACHE_COOKIE_STATE_LRU_DISCARDING);
+ wake = true;
+diff --git a/fs/netfs/io.c b/fs/netfs/io.c
+index c7576481c321d..f3abc5dfdbc0c 100644
+--- a/fs/netfs/io.c
++++ b/fs/netfs/io.c
+@@ -98,6 +98,146 @@ static void netfs_rreq_completed(struct netfs_io_request *rreq, bool was_async)
+ netfs_put_request(rreq, was_async, netfs_rreq_trace_put_complete);
+ }
+
++/*
++ * [DEPRECATED] Deal with the completion of writing the data to the cache. We
++ * have to clear the PG_fscache bits on the folios involved and release the
++ * caller's ref.
++ *
++ * May be called in softirq mode and we inherit a ref from the caller.
++ */
++static void netfs_rreq_unmark_after_write(struct netfs_io_request *rreq,
++ bool was_async)
++{
++ struct netfs_io_subrequest *subreq;
++ struct folio *folio;
++ pgoff_t unlocked = 0;
++ bool have_unlocked = false;
++
++ rcu_read_lock();
++
++ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
++ XA_STATE(xas, &rreq->mapping->i_pages, subreq->start / PAGE_SIZE);
++
++ xas_for_each(&xas, folio, (subreq->start + subreq->len - 1) / PAGE_SIZE) {
++ if (xas_retry(&xas, folio))
++ continue;
++
++ /* We might have multiple writes from the same huge
++ * folio, but we mustn't unlock a folio more than once.
++ */
++ if (have_unlocked && folio->index <= unlocked)
++ continue;
++ unlocked = folio_next_index(folio) - 1;
++ trace_netfs_folio(folio, netfs_folio_trace_end_copy);
++ folio_end_private_2(folio);
++ have_unlocked = true;
++ }
++ }
++
++ rcu_read_unlock();
++ netfs_rreq_completed(rreq, was_async);
++}
++
++static void netfs_rreq_copy_terminated(void *priv, ssize_t transferred_or_error,
++ bool was_async) /* [DEPRECATED] */
++{
++ struct netfs_io_subrequest *subreq = priv;
++ struct netfs_io_request *rreq = subreq->rreq;
++
++ if (IS_ERR_VALUE(transferred_or_error)) {
++ netfs_stat(&netfs_n_rh_write_failed);
++ trace_netfs_failure(rreq, subreq, transferred_or_error,
++ netfs_fail_copy_to_cache);
++ } else {
++ netfs_stat(&netfs_n_rh_write_done);
++ }
++
++ trace_netfs_sreq(subreq, netfs_sreq_trace_write_term);
++
++ /* If we decrement nr_copy_ops to 0, the ref belongs to us. */
++ if (atomic_dec_and_test(&rreq->nr_copy_ops))
++ netfs_rreq_unmark_after_write(rreq, was_async);
++
++ netfs_put_subrequest(subreq, was_async, netfs_sreq_trace_put_terminated);
++}
++
++/*
++ * [DEPRECATED] Perform any outstanding writes to the cache. We inherit a ref
++ * from the caller.
++ */
++static void netfs_rreq_do_write_to_cache(struct netfs_io_request *rreq)
++{
++ struct netfs_cache_resources *cres = &rreq->cache_resources;
++ struct netfs_io_subrequest *subreq, *next, *p;
++ struct iov_iter iter;
++ int ret;
++
++ trace_netfs_rreq(rreq, netfs_rreq_trace_copy);
++
++ /* We don't want terminating writes trying to wake us up whilst we're
++ * still going through the list.
++ */
++ atomic_inc(&rreq->nr_copy_ops);
++
++ list_for_each_entry_safe(subreq, p, &rreq->subrequests, rreq_link) {
++ if (!test_bit(NETFS_SREQ_COPY_TO_CACHE, &subreq->flags)) {
++ list_del_init(&subreq->rreq_link);
++ netfs_put_subrequest(subreq, false,
++ netfs_sreq_trace_put_no_copy);
++ }
++ }
++
++ list_for_each_entry(subreq, &rreq->subrequests, rreq_link) {
++ /* Amalgamate adjacent writes */
++ while (!list_is_last(&subreq->rreq_link, &rreq->subrequests)) {
++ next = list_next_entry(subreq, rreq_link);
++ if (next->start != subreq->start + subreq->len)
++ break;
++ subreq->len += next->len;
++ list_del_init(&next->rreq_link);
++ netfs_put_subrequest(next, false,
++ netfs_sreq_trace_put_merged);
++ }
++
++ ret = cres->ops->prepare_write(cres, &subreq->start, &subreq->len,
++ subreq->len, rreq->i_size, true);
++ if (ret < 0) {
++ trace_netfs_failure(rreq, subreq, ret, netfs_fail_prepare_write);
++ trace_netfs_sreq(subreq, netfs_sreq_trace_write_skip);
++ continue;
++ }
++
++ iov_iter_xarray(&iter, ITER_SOURCE, &rreq->mapping->i_pages,
++ subreq->start, subreq->len);
++
++ atomic_inc(&rreq->nr_copy_ops);
++ netfs_stat(&netfs_n_rh_write);
++ netfs_get_subrequest(subreq, netfs_sreq_trace_get_copy_to_cache);
++ trace_netfs_sreq(subreq, netfs_sreq_trace_write);
++ cres->ops->write(cres, subreq->start, &iter,
++ netfs_rreq_copy_terminated, subreq);
++ }
++
++ /* If we decrement nr_copy_ops to 0, the usage ref belongs to us. */
++ if (atomic_dec_and_test(&rreq->nr_copy_ops))
++ netfs_rreq_unmark_after_write(rreq, false);
++}
++
++static void netfs_rreq_write_to_cache_work(struct work_struct *work) /* [DEPRECATED] */
++{
++ struct netfs_io_request *rreq =
++ container_of(work, struct netfs_io_request, work);
++
++ netfs_rreq_do_write_to_cache(rreq);
++}
++
++static void netfs_rreq_write_to_cache(struct netfs_io_request *rreq) /* [DEPRECATED] */
++{
++ rreq->work.func = netfs_rreq_write_to_cache_work;
++ if (!queue_work(system_unbound_wq, &rreq->work))
++ BUG();
++}
++
+ /*
+ * Handle a short read.
+ */
+@@ -275,6 +415,10 @@ static void netfs_rreq_assess(struct netfs_io_request *rreq, bool was_async)
+ clear_bit_unlock(NETFS_RREQ_IN_PROGRESS, &rreq->flags);
+ wake_up_bit(&rreq->flags, NETFS_RREQ_IN_PROGRESS);
+
++ if (test_bit(NETFS_RREQ_COPY_TO_CACHE, &rreq->flags) &&
++ test_bit(NETFS_RREQ_USE_PGPRIV2, &rreq->flags))
++ return netfs_rreq_write_to_cache(rreq);
++
+ netfs_rreq_completed(rreq, was_async);
+ }
+
+diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
+index d4bcc7da700c6..0a271b9fbc622 100644
+--- a/fs/smb/client/cifsglob.h
++++ b/fs/smb/client/cifsglob.h
+@@ -290,7 +290,7 @@ struct smb_version_operations {
+ int (*check_receive)(struct mid_q_entry *, struct TCP_Server_Info *,
+ bool);
+ void (*add_credits)(struct TCP_Server_Info *server,
+- const struct cifs_credits *credits,
++ struct cifs_credits *credits,
+ const int optype);
+ void (*set_credits)(struct TCP_Server_Info *, const int);
+ int * (*get_credits_field)(struct TCP_Server_Info *, const int);
+@@ -550,8 +550,8 @@ struct smb_version_operations {
+ size_t *, struct cifs_credits *);
+ /* adjust previously taken mtu credits to request size */
+ int (*adjust_credits)(struct TCP_Server_Info *server,
+- struct cifs_credits *credits,
+- const unsigned int payload_size);
++ struct cifs_io_subrequest *subreq,
++ unsigned int /*enum smb3_rw_credits_trace*/ trace);
+ /* check if we need to issue closedir */
+ bool (*dir_needs_close)(struct cifsFileInfo *);
+ long (*fallocate)(struct file *, struct cifs_tcon *, int, loff_t,
+@@ -848,6 +848,9 @@ static inline void cifs_server_unlock(struct TCP_Server_Info *server)
+ struct cifs_credits {
+ unsigned int value;
+ unsigned int instance;
++ unsigned int in_flight_check;
++ unsigned int rreq_debug_id;
++ unsigned int rreq_debug_index;
+ };
+
+ static inline unsigned int
+@@ -873,7 +876,7 @@ has_credits(struct TCP_Server_Info *server, int *credits, int num_credits)
+ }
+
+ static inline void
+-add_credits(struct TCP_Server_Info *server, const struct cifs_credits *credits,
++add_credits(struct TCP_Server_Info *server, struct cifs_credits *credits,
+ const int optype)
+ {
+ server->ops->add_credits(server, credits, optype);
+@@ -897,11 +900,11 @@ set_credits(struct TCP_Server_Info *server, const int val)
+ }
+
+ static inline int
+-adjust_credits(struct TCP_Server_Info *server, struct cifs_credits *credits,
+- const unsigned int payload_size)
++adjust_credits(struct TCP_Server_Info *server, struct cifs_io_subrequest *subreq,
++ unsigned int /* enum smb3_rw_credits_trace */ trace)
+ {
+ return server->ops->adjust_credits ?
+- server->ops->adjust_credits(server, credits, payload_size) : 0;
++ server->ops->adjust_credits(server, subreq, trace) : 0;
+ }
+
+ static inline __le64
+diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
+index 04ec1b9737a89..b202eac6584e1 100644
+--- a/fs/smb/client/file.c
++++ b/fs/smb/client/file.c
+@@ -80,6 +80,16 @@ static void cifs_prepare_write(struct netfs_io_subrequest *subreq)
+ return netfs_prepare_write_failed(subreq);
+ }
+
++ wdata->credits.rreq_debug_id = subreq->rreq->debug_id;
++ wdata->credits.rreq_debug_index = subreq->debug_index;
++ wdata->credits.in_flight_check = 1;
++ trace_smb3_rw_credits(wdata->rreq->debug_id,
++ wdata->subreq.debug_index,
++ wdata->credits.value,
++ server->credits, server->in_flight,
++ wdata->credits.value,
++ cifs_trace_rw_credits_write_prepare);
++
+ #ifdef CONFIG_CIFS_SMB_DIRECT
+ if (server->smbd_conn)
+ subreq->max_nr_segs = server->smbd_conn->max_frmr_depth;
+@@ -101,7 +111,7 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq)
+ goto fail;
+ }
+
+- rc = adjust_credits(wdata->server, &wdata->credits, wdata->subreq.len);
++ rc = adjust_credits(wdata->server, wdata, cifs_trace_rw_credits_issue_write_adjust);
+ if (rc)
+ goto fail;
+
+@@ -163,7 +173,18 @@ static bool cifs_clamp_length(struct netfs_io_subrequest *subreq)
+ return false;
+ }
+
++ rdata->credits.in_flight_check = 1;
++ rdata->credits.rreq_debug_id = rreq->debug_id;
++ rdata->credits.rreq_debug_index = subreq->debug_index;
++
++ trace_smb3_rw_credits(rdata->rreq->debug_id,
++ rdata->subreq.debug_index,
++ rdata->credits.value,
++ server->credits, server->in_flight, 0,
++ cifs_trace_rw_credits_read_submit);
++
+ subreq->len = min_t(size_t, subreq->len, rsize);
++
+ #ifdef CONFIG_CIFS_SMB_DIRECT
+ if (server->smbd_conn)
+ subreq->max_nr_segs = server->smbd_conn->max_frmr_depth;
+@@ -294,7 +315,20 @@ static void cifs_free_subrequest(struct netfs_io_subrequest *subreq)
+ #endif
+ }
+
+- add_credits_and_wake_if(rdata->server, &rdata->credits, 0);
++ if (rdata->credits.value != 0) {
++ trace_smb3_rw_credits(rdata->rreq->debug_id,
++ rdata->subreq.debug_index,
++ rdata->credits.value,
++ rdata->server ? rdata->server->credits : 0,
++ rdata->server ? rdata->server->in_flight : 0,
++ -rdata->credits.value,
++ cifs_trace_rw_credits_free_subreq);
++ if (rdata->server)
++ add_credits_and_wake_if(rdata->server, &rdata->credits, 0);
++ else
++ rdata->credits.value = 0;
++ }
++
+ if (rdata->have_xid)
+ free_xid(rdata->xid);
+ }
+@@ -2719,6 +2753,7 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
+ struct inode *inode = file->f_mapping->host;
+ struct cifsInodeInfo *cinode = CIFS_I(inode);
+ struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
++ struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+ ssize_t rc;
+
+ rc = netfs_start_io_write(inode);
+@@ -2735,12 +2770,16 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
+ if (rc <= 0)
+ goto out;
+
+- if (!cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
++ if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) &&
++ (cifs_find_lock_conflict(cfile, iocb->ki_pos, iov_iter_count(from),
+ server->vals->exclusive_lock_type, 0,
+- NULL, CIFS_WRITE_OP))
+- rc = netfs_buffered_write_iter_locked(iocb, from, NULL);
+- else
++ NULL, CIFS_WRITE_OP))) {
+ rc = -EACCES;
++ goto out;
++ }
++
++ rc = netfs_buffered_write_iter_locked(iocb, from, NULL);
++
+ out:
+ up_read(&cinode->lock_sem);
+ netfs_end_io_write(inode);
+@@ -2872,9 +2911,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
+ if (!CIFS_CACHE_READ(cinode))
+ return netfs_unbuffered_read_iter(iocb, to);
+
+- if (cap_unix(tcon->ses) &&
+- (CIFS_UNIX_FCNTL_CAP & le64_to_cpu(tcon->fsUnixInfo.Capability)) &&
+- ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0)) {
++ if ((cifs_sb->mnt_cifs_flags & CIFS_MOUNT_NOPOSIXBRL) == 0) {
+ if (iocb->ki_flags & IOCB_DIRECT)
+ return netfs_unbuffered_read_iter(iocb, to);
+ return netfs_buffered_read_iter(iocb, to);
+diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
+index 689d8a506d459..48c27581ec511 100644
+--- a/fs/smb/client/reparse.c
++++ b/fs/smb/client/reparse.c
+@@ -378,6 +378,8 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
+ u32 plen, struct cifs_sb_info *cifs_sb,
+ bool unicode, struct cifs_open_info_data *data)
+ {
++ struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
++
+ data->reparse.buf = buf;
+
+ /* See MS-FSCC 2.1.2 */
+@@ -394,12 +396,13 @@ int parse_reparse_point(struct reparse_data_buffer *buf,
+ case IO_REPARSE_TAG_LX_FIFO:
+ case IO_REPARSE_TAG_LX_CHR:
+ case IO_REPARSE_TAG_LX_BLK:
+- return 0;
++ break;
+ default:
+- cifs_dbg(VFS, "%s: unhandled reparse tag: 0x%08x\n",
+- __func__, le32_to_cpu(buf->ReparseTag));
+- return -EOPNOTSUPP;
++ cifs_tcon_dbg(VFS | ONCE, "unhandled reparse tag: 0x%08x\n",
++ le32_to_cpu(buf->ReparseTag));
++ break;
+ }
++ return 0;
+ }
+
+ int smb2_parse_reparse_point(struct cifs_sb_info *cifs_sb,
+diff --git a/fs/smb/client/smb1ops.c b/fs/smb/client/smb1ops.c
+index 212ec6f66ec65..e1f2feb56f45f 100644
+--- a/fs/smb/client/smb1ops.c
++++ b/fs/smb/client/smb1ops.c
+@@ -108,7 +108,7 @@ cifs_find_mid(struct TCP_Server_Info *server, char *buffer)
+
+ static void
+ cifs_add_credits(struct TCP_Server_Info *server,
+- const struct cifs_credits *credits, const int optype)
++ struct cifs_credits *credits, const int optype)
+ {
+ spin_lock(&server->req_lock);
+ server->credits += credits->value;
+diff --git a/fs/smb/client/smb2ops.c b/fs/smb/client/smb2ops.c
+index c8e536540895a..7fe59235f0901 100644
+--- a/fs/smb/client/smb2ops.c
++++ b/fs/smb/client/smb2ops.c
+@@ -66,7 +66,7 @@ change_conf(struct TCP_Server_Info *server)
+
+ static void
+ smb2_add_credits(struct TCP_Server_Info *server,
+- const struct cifs_credits *credits, const int optype)
++ struct cifs_credits *credits, const int optype)
+ {
+ int *val, rc = -1;
+ int scredits, in_flight;
+@@ -94,7 +94,21 @@ smb2_add_credits(struct TCP_Server_Info *server,
+ server->conn_id, server->hostname, *val,
+ add, server->in_flight);
+ }
+- WARN_ON_ONCE(server->in_flight == 0);
++ if (credits->in_flight_check > 1) {
++ pr_warn_once("rreq R=%08x[%x] Credits not in flight\n",
++ credits->rreq_debug_id, credits->rreq_debug_index);
++ } else {
++ credits->in_flight_check = 2;
++ }
++ if (WARN_ON_ONCE(server->in_flight == 0)) {
++ pr_warn_once("rreq R=%08x[%x] Zero in_flight\n",
++ credits->rreq_debug_id, credits->rreq_debug_index);
++ trace_smb3_rw_credits(credits->rreq_debug_id,
++ credits->rreq_debug_index,
++ credits->value,
++ server->credits, server->in_flight, 0,
++ cifs_trace_rw_credits_zero_in_flight);
++ }
+ server->in_flight--;
+ if (server->in_flight == 0 &&
+ ((optype & CIFS_OP_MASK) != CIFS_NEG_OP) &&
+@@ -283,16 +297,23 @@ smb2_wait_mtu_credits(struct TCP_Server_Info *server, size_t size,
+
+ static int
+ smb2_adjust_credits(struct TCP_Server_Info *server,
+- struct cifs_credits *credits,
+- const unsigned int payload_size)
++ struct cifs_io_subrequest *subreq,
++ unsigned int /*enum smb3_rw_credits_trace*/ trace)
+ {
+- int new_val = DIV_ROUND_UP(payload_size, SMB2_MAX_BUFFER_SIZE);
++ struct cifs_credits *credits = &subreq->credits;
++ int new_val = DIV_ROUND_UP(subreq->subreq.len, SMB2_MAX_BUFFER_SIZE);
+ int scredits, in_flight;
+
+ if (!credits->value || credits->value == new_val)
+ return 0;
+
+ if (credits->value < new_val) {
++ trace_smb3_rw_credits(subreq->rreq->debug_id,
++ subreq->subreq.debug_index,
++ credits->value,
++ server->credits, server->in_flight,
++ new_val - credits->value,
++ cifs_trace_rw_credits_no_adjust_up);
+ trace_smb3_too_many_credits(server->CurrentMid,
+ server->conn_id, server->hostname, 0, credits->value - new_val, 0);
+ cifs_server_dbg(VFS, "request has less credits (%d) than required (%d)",
+@@ -308,6 +329,12 @@ smb2_adjust_credits(struct TCP_Server_Info *server,
+ in_flight = server->in_flight;
+ spin_unlock(&server->req_lock);
+
++ trace_smb3_rw_credits(subreq->rreq->debug_id,
++ subreq->subreq.debug_index,
++ credits->value,
++ server->credits, server->in_flight,
++ new_val - credits->value,
++ cifs_trace_rw_credits_old_session);
+ trace_smb3_reconnect_detected(server->CurrentMid,
+ server->conn_id, server->hostname, scredits,
+ credits->value - new_val, in_flight);
+@@ -316,6 +343,11 @@ smb2_adjust_credits(struct TCP_Server_Info *server,
+ return -EAGAIN;
+ }
+
++ trace_smb3_rw_credits(subreq->rreq->debug_id,
++ subreq->subreq.debug_index,
++ credits->value,
++ server->credits, server->in_flight,
++ new_val - credits->value, trace);
+ server->credits += credits->value - new_val;
+ scredits = server->credits;
+ in_flight = server->in_flight;
+diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
+index 896147ba6660e..4cd5c33be2a1a 100644
+--- a/fs/smb/client/smb2pdu.c
++++ b/fs/smb/client/smb2pdu.c
+@@ -4505,8 +4505,15 @@ smb2_readv_callback(struct mid_q_entry *mid)
+ struct TCP_Server_Info *server = rdata->server;
+ struct smb2_hdr *shdr =
+ (struct smb2_hdr *)rdata->iov[0].iov_base;
+- struct cifs_credits credits = { .value = 0, .instance = 0 };
++ struct cifs_credits credits = {
++ .value = 0,
++ .instance = 0,
++ .rreq_debug_id = rdata->rreq->debug_id,
++ .rreq_debug_index = rdata->subreq.debug_index,
++ };
+ struct smb_rqst rqst = { .rq_iov = &rdata->iov[1], .rq_nvec = 1 };
++ unsigned int rreq_debug_id = rdata->rreq->debug_id;
++ unsigned int subreq_debug_index = rdata->subreq.debug_index;
+
+ if (rdata->got_bytes) {
+ rqst.rq_iter = rdata->subreq.io_iter;
+@@ -4590,10 +4597,16 @@ smb2_readv_callback(struct mid_q_entry *mid)
+ if (rdata->subreq.start < rdata->subreq.rreq->i_size)
+ rdata->result = 0;
+ }
++ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, rdata->credits.value,
++ server->credits, server->in_flight,
++ 0, cifs_trace_rw_credits_read_response_clear);
+ rdata->credits.value = 0;
+ INIT_WORK(&rdata->subreq.work, smb2_readv_worker);
+ queue_work(cifsiod_wq, &rdata->subreq.work);
+ release_mid(mid);
++ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
++ server->credits, server->in_flight,
++ credits.value, cifs_trace_rw_credits_read_response_add);
+ add_credits(server, &credits, 0);
+ }
+
+@@ -4650,7 +4663,7 @@ smb2_async_readv(struct cifs_io_subrequest *rdata)
+ min_t(int, server->max_credits -
+ server->credits, credit_request));
+
+- rc = adjust_credits(server, &rdata->credits, rdata->subreq.len);
++ rc = adjust_credits(server, rdata, cifs_trace_rw_credits_call_readv_adjust);
+ if (rc)
+ goto async_readv_out;
+
+@@ -4769,7 +4782,14 @@ smb2_writev_callback(struct mid_q_entry *mid)
+ struct cifs_tcon *tcon = tlink_tcon(wdata->req->cfile->tlink);
+ struct TCP_Server_Info *server = wdata->server;
+ struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf;
+- struct cifs_credits credits = { .value = 0, .instance = 0 };
++ struct cifs_credits credits = {
++ .value = 0,
++ .instance = 0,
++ .rreq_debug_id = wdata->rreq->debug_id,
++ .rreq_debug_index = wdata->subreq.debug_index,
++ };
++ unsigned int rreq_debug_id = wdata->rreq->debug_id;
++ unsigned int subreq_debug_index = wdata->subreq.debug_index;
+ ssize_t result = 0;
+ size_t written;
+
+@@ -4840,9 +4860,15 @@ smb2_writev_callback(struct mid_q_entry *mid)
+ tcon->tid, tcon->ses->Suid,
+ wdata->subreq.start, wdata->subreq.len);
+
++ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, wdata->credits.value,
++ server->credits, server->in_flight,
++ 0, cifs_trace_rw_credits_write_response_clear);
+ wdata->credits.value = 0;
+ cifs_write_subrequest_terminated(wdata, result ?: written, true);
+ release_mid(mid);
++ trace_smb3_rw_credits(rreq_debug_id, subreq_debug_index, 0,
++ server->credits, server->in_flight,
++ credits.value, cifs_trace_rw_credits_write_response_add);
+ add_credits(server, &credits, 0);
+ }
+
+@@ -4972,7 +4998,7 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
+ min_t(int, server->max_credits -
+ server->credits, credit_request));
+
+- rc = adjust_credits(server, &wdata->credits, io_parms->length);
++ rc = adjust_credits(server, wdata, cifs_trace_rw_credits_call_writev_adjust);
+ if (rc)
+ goto async_writev_out;
+
+@@ -4997,6 +5023,12 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
+ cifs_small_buf_release(req);
+ out:
+ if (rc) {
++ trace_smb3_rw_credits(wdata->rreq->debug_id,
++ wdata->subreq.debug_index,
++ wdata->credits.value,
++ server->credits, server->in_flight,
++ -(int)wdata->credits.value,
++ cifs_trace_rw_credits_write_response_clear);
+ add_credits_and_wake_if(wdata->server, &wdata->credits, 0);
+ cifs_write_subrequest_terminated(wdata, rc, true);
+ }
+diff --git a/fs/smb/client/trace.h b/fs/smb/client/trace.h
+index 36d47ce596317..36d5295c2a6f9 100644
+--- a/fs/smb/client/trace.h
++++ b/fs/smb/client/trace.h
+@@ -20,6 +20,22 @@
+ /*
+ * Specify enums for tracing information.
+ */
++#define smb3_rw_credits_traces \
++ EM(cifs_trace_rw_credits_call_readv_adjust, "rd-call-adj") \
++ EM(cifs_trace_rw_credits_call_writev_adjust, "wr-call-adj") \
++ EM(cifs_trace_rw_credits_free_subreq, "free-subreq") \
++ EM(cifs_trace_rw_credits_issue_read_adjust, "rd-issu-adj") \
++ EM(cifs_trace_rw_credits_issue_write_adjust, "wr-issu-adj") \
++ EM(cifs_trace_rw_credits_no_adjust_up, "no-adj-up ") \
++ EM(cifs_trace_rw_credits_old_session, "old-session") \
++ EM(cifs_trace_rw_credits_read_response_add, "rd-resp-add") \
++ EM(cifs_trace_rw_credits_read_response_clear, "rd-resp-clr") \
++ EM(cifs_trace_rw_credits_read_submit, "rd-submit ") \
++ EM(cifs_trace_rw_credits_write_prepare, "wr-prepare ") \
++ EM(cifs_trace_rw_credits_write_response_add, "wr-resp-add") \
++ EM(cifs_trace_rw_credits_write_response_clear, "wr-resp-clr") \
++ E_(cifs_trace_rw_credits_zero_in_flight, "ZERO-IN-FLT")
++
+ #define smb3_tcon_ref_traces \
+ EM(netfs_trace_tcon_ref_dec_dfs_refer, "DEC DfsRef") \
+ EM(netfs_trace_tcon_ref_free, "FRE ") \
+@@ -59,7 +75,8 @@
+ #define EM(a, b) a,
+ #define E_(a, b) a
+
+-enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
++enum smb3_rw_credits_trace { smb3_rw_credits_traces } __mode(byte);
++enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
+
+ #undef EM
+ #undef E_
+@@ -71,6 +88,7 @@ enum smb3_tcon_ref_trace { smb3_tcon_ref_traces } __mode(byte);
+ #define EM(a, b) TRACE_DEFINE_ENUM(a);
+ #define E_(a, b) TRACE_DEFINE_ENUM(a);
+
++smb3_rw_credits_traces;
+ smb3_tcon_ref_traces;
+
+ #undef EM
+@@ -1316,6 +1334,41 @@ TRACE_EVENT(smb3_tcon_ref,
+ __entry->ref)
+ );
+
++TRACE_EVENT(smb3_rw_credits,
++ TP_PROTO(unsigned int rreq_debug_id,
++ unsigned int subreq_debug_index,
++ unsigned int subreq_credits,
++ unsigned int server_credits,
++ int server_in_flight,
++ int credit_change,
++ enum smb3_rw_credits_trace trace),
++ TP_ARGS(rreq_debug_id, subreq_debug_index, subreq_credits,
++ server_credits, server_in_flight, credit_change, trace),
++ TP_STRUCT__entry(
++ __field(unsigned int, rreq_debug_id)
++ __field(unsigned int, subreq_debug_index)
++ __field(unsigned int, subreq_credits)
++ __field(unsigned int, server_credits)
++ __field(int, in_flight)
++ __field(int, credit_change)
++ __field(enum smb3_rw_credits_trace, trace)
++ ),
++ TP_fast_assign(
++ __entry->rreq_debug_id = rreq_debug_id;
++ __entry->subreq_debug_index = subreq_debug_index;
++ __entry->subreq_credits = subreq_credits;
++ __entry->server_credits = server_credits;
++ __entry->in_flight = server_in_flight;
++ __entry->credit_change = credit_change;
++ __entry->trace = trace;
++ ),
++ TP_printk("R=%08x[%x] %s cred=%u chg=%d pool=%u ifl=%d",
++ __entry->rreq_debug_id, __entry->subreq_debug_index,
++ __print_symbolic(__entry->trace, smb3_rw_credits_traces),
++ __entry->subreq_credits, __entry->credit_change,
++ __entry->server_credits, __entry->in_flight)
++ );
++
+
+ #undef EM
+ #undef E_
+diff --git a/fs/smb/client/transport.c b/fs/smb/client/transport.c
+index 012b9bd069952..adfe0d0587010 100644
+--- a/fs/smb/client/transport.c
++++ b/fs/smb/client/transport.c
+@@ -988,10 +988,10 @@ static void
+ cifs_compound_callback(struct mid_q_entry *mid)
+ {
+ struct TCP_Server_Info *server = mid->server;
+- struct cifs_credits credits;
+-
+- credits.value = server->ops->get_credits(mid);
+- credits.instance = server->reconnect_instance;
++ struct cifs_credits credits = {
++ .value = server->ops->get_credits(mid),
++ .instance = server->reconnect_instance,
++ };
+
+ add_credits(server, &credits, mid->optype);
+
+diff --git a/fs/smb/server/connection.c b/fs/smb/server/connection.c
+index 09e1e7771592f..7889df8112b4e 100644
+--- a/fs/smb/server/connection.c
++++ b/fs/smb/server/connection.c
+@@ -165,11 +165,43 @@ void ksmbd_all_conn_set_status(u64 sess_id, u32 status)
+ up_read(&conn_list_lock);
+ }
+
+-void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id)
++void ksmbd_conn_wait_idle(struct ksmbd_conn *conn)
+ {
+ wait_event(conn->req_running_q, atomic_read(&conn->req_running) < 2);
+ }
+
++int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id)
++{
++ struct ksmbd_conn *conn;
++ int rc, retry_count = 0, max_timeout = 120;
++ int rcount = 1;
++
++retry_idle:
++ if (retry_count >= max_timeout)
++ return -EIO;
++
++ down_read(&conn_list_lock);
++ list_for_each_entry(conn, &conn_list, conns_list) {
++ if (conn->binding || xa_load(&conn->sessions, sess_id)) {
++ if (conn == curr_conn)
++ rcount = 2;
++ if (atomic_read(&conn->req_running) >= rcount) {
++ rc = wait_event_timeout(conn->req_running_q,
++ atomic_read(&conn->req_running) < rcount,
++ HZ);
++ if (!rc) {
++ up_read(&conn_list_lock);
++ retry_count++;
++ goto retry_idle;
++ }
++ }
++ }
++ }
++ up_read(&conn_list_lock);
++
++ return 0;
++}
++
+ int ksmbd_conn_write(struct ksmbd_work *work)
+ {
+ struct ksmbd_conn *conn = work->conn;
+diff --git a/fs/smb/server/connection.h b/fs/smb/server/connection.h
+index 0e04cf8b1d896..b93e5437793e0 100644
+--- a/fs/smb/server/connection.h
++++ b/fs/smb/server/connection.h
+@@ -145,7 +145,8 @@ extern struct list_head conn_list;
+ extern struct rw_semaphore conn_list_lock;
+
+ bool ksmbd_conn_alive(struct ksmbd_conn *conn);
+-void ksmbd_conn_wait_idle(struct ksmbd_conn *conn, u64 sess_id);
++void ksmbd_conn_wait_idle(struct ksmbd_conn *conn);
++int ksmbd_conn_wait_idle_sess_id(struct ksmbd_conn *curr_conn, u64 sess_id);
+ struct ksmbd_conn *ksmbd_conn_alloc(void);
+ void ksmbd_conn_free(struct ksmbd_conn *conn);
+ bool ksmbd_conn_lookup_dialect(struct ksmbd_conn *c);
+diff --git a/fs/smb/server/mgmt/user_session.c b/fs/smb/server/mgmt/user_session.c
+index aec0a7a124052..dac5f984f1754 100644
+--- a/fs/smb/server/mgmt/user_session.c
++++ b/fs/smb/server/mgmt/user_session.c
+@@ -310,6 +310,7 @@ void destroy_previous_session(struct ksmbd_conn *conn,
+ {
+ struct ksmbd_session *prev_sess;
+ struct ksmbd_user *prev_user;
++ int err;
+
+ down_write(&sessions_table_lock);
+ down_write(&conn->session_lock);
+@@ -324,8 +325,15 @@ void destroy_previous_session(struct ksmbd_conn *conn,
+ memcmp(user->passkey, prev_user->passkey, user->passkey_sz))
+ goto out;
+
++ ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_RECONNECT);
++ err = ksmbd_conn_wait_idle_sess_id(conn, id);
++ if (err) {
++ ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE);
++ goto out;
++ }
+ ksmbd_destroy_file_table(&prev_sess->file_table);
+ prev_sess->state = SMB2_SESSION_EXPIRED;
++ ksmbd_all_conn_set_status(id, KSMBD_SESS_NEED_NEGOTIATE);
+ out:
+ up_write(&conn->session_lock);
+ up_write(&sessions_table_lock);
+diff --git a/fs/smb/server/smb2pdu.c b/fs/smb/server/smb2pdu.c
+index 840c71c66b30b..8cfdf0d1a186e 100644
+--- a/fs/smb/server/smb2pdu.c
++++ b/fs/smb/server/smb2pdu.c
+@@ -2210,7 +2210,7 @@ int smb2_session_logoff(struct ksmbd_work *work)
+ ksmbd_conn_unlock(conn);
+
+ ksmbd_close_session_fds(work);
+- ksmbd_conn_wait_idle(conn, sess_id);
++ ksmbd_conn_wait_idle(conn);
+
+ /*
+ * Re-lookup session to validate if session is deleted
+@@ -4406,7 +4406,8 @@ int smb2_query_dir(struct ksmbd_work *work)
+ rsp->OutputBufferLength = cpu_to_le32(0);
+ rsp->Buffer[0] = 0;
+ rc = ksmbd_iov_pin_rsp(work, (void *)rsp,
+- sizeof(struct smb2_query_directory_rsp));
++ offsetof(struct smb2_query_directory_rsp, Buffer)
++ + 1);
+ if (rc)
+ goto err_out;
+ } else {
+diff --git a/include/acpi/acpixf.h b/include/acpi/acpixf.h
+index 80dc36f9d5274..9f1c1d225e32c 100644
+--- a/include/acpi/acpixf.h
++++ b/include/acpi/acpixf.h
+@@ -660,12 +660,9 @@ ACPI_EXTERNAL_RETURN_STATUS(acpi_status
+ void *context))
+ ACPI_EXTERNAL_RETURN_STATUS(acpi_status
+ acpi_execute_reg_methods(acpi_handle device,
++ u32 nax_depth,
+ acpi_adr_space_type
+ space_id))
+-ACPI_EXTERNAL_RETURN_STATUS(acpi_status
+- acpi_execute_orphan_reg_method(acpi_handle device,
+- acpi_adr_space_type
+- space_id))
+ ACPI_EXTERNAL_RETURN_STATUS(acpi_status
+ acpi_remove_address_space_handler(acpi_handle
+ device,
+diff --git a/include/acpi/video.h b/include/acpi/video.h
+index 3d538d4178abb..044c463138df8 100644
+--- a/include/acpi/video.h
++++ b/include/acpi/video.h
+@@ -50,6 +50,7 @@ enum acpi_backlight_type {
+ acpi_backlight_native,
+ acpi_backlight_nvidia_wmi_ec,
+ acpi_backlight_apple_gmux,
++ acpi_backlight_dell_uart,
+ };
+
+ #if IS_ENABLED(CONFIG_ACPI_VIDEO)
+diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
+index 70bf1004076b2..f00a8e18f389f 100644
+--- a/include/asm-generic/vmlinux.lds.h
++++ b/include/asm-generic/vmlinux.lds.h
+@@ -451,30 +451,11 @@
+ #endif
+ #endif
+
+-/*
+- * Some symbol definitions will not exist yet during the first pass of the
+- * link, but are guaranteed to exist in the final link. Provide preliminary
+- * definitions that will be superseded in the final link to avoid having to
+- * rely on weak external linkage, which requires a GOT when used in position
+- * independent code.
+- */
+-#define PRELIMINARY_SYMBOL_DEFINITIONS \
+- PROVIDE(kallsyms_addresses = .); \
+- PROVIDE(kallsyms_offsets = .); \
+- PROVIDE(kallsyms_names = .); \
+- PROVIDE(kallsyms_num_syms = .); \
+- PROVIDE(kallsyms_relative_base = .); \
+- PROVIDE(kallsyms_token_table = .); \
+- PROVIDE(kallsyms_token_index = .); \
+- PROVIDE(kallsyms_markers = .); \
+- PROVIDE(kallsyms_seqs_of_names = .);
+-
+ /*
+ * Read only Data
+ */
+ #define RO_DATA(align) \
+ . = ALIGN((align)); \
+- PRELIMINARY_SYMBOL_DEFINITIONS \
+ .rodata : AT(ADDR(.rodata) - LOAD_OFFSET) { \
+ __start_rodata = .; \
+ *(.rodata) *(.rodata.*) \
+diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h
+index 8c4768c44a01b..d3b66d77df7a3 100644
+--- a/include/linux/bitmap.h
++++ b/include/linux/bitmap.h
+@@ -270,6 +270,18 @@ static inline void bitmap_copy_clear_tail(unsigned long *dst,
+ dst[nbits / BITS_PER_LONG] &= BITMAP_LAST_WORD_MASK(nbits);
+ }
+
++static inline void bitmap_copy_and_extend(unsigned long *to,
++ const unsigned long *from,
++ unsigned int count, unsigned int size)
++{
++ unsigned int copy = BITS_TO_LONGS(count);
++
++ memcpy(to, from, copy * sizeof(long));
++ if (count % BITS_PER_LONG)
++ to[copy - 1] &= BITMAP_LAST_WORD_MASK(count);
++ memset(to + copy, 0, bitmap_size(size) - copy * sizeof(long));
++}
++
+ /*
+ * On 32-bit systems bitmaps are represented as u32 arrays internally. On LE64
+ * machines the order of hi and lo parts of numbers match the bitmap structure.
+diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
+index ff2a6cdb1fa3f..5db4a3f354804 100644
+--- a/include/linux/bpf_verifier.h
++++ b/include/linux/bpf_verifier.h
+@@ -846,8 +846,8 @@ static inline u32 type_flag(u32 type)
+ /* only use after check_attach_btf_id() */
+ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
+ {
+- return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ?
+- prog->aux->dst_prog->type : prog->type;
++ return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->saved_dst_prog_type) ?
++ prog->aux->saved_dst_prog_type : prog->type;
+ }
+
+ static inline bool bpf_prog_check_recur(const struct bpf_prog *prog)
+diff --git a/include/linux/dsa/ocelot.h b/include/linux/dsa/ocelot.h
+index dca2969015d80..6fbfbde68a37c 100644
+--- a/include/linux/dsa/ocelot.h
++++ b/include/linux/dsa/ocelot.h
+@@ -5,6 +5,8 @@
+ #ifndef _NET_DSA_TAG_OCELOT_H
+ #define _NET_DSA_TAG_OCELOT_H
+
++#include <linux/if_bridge.h>
++#include <linux/if_vlan.h>
+ #include <linux/kthread.h>
+ #include <linux/packing.h>
+ #include <linux/skbuff.h>
+@@ -273,4 +275,49 @@ static inline u32 ocelot_ptp_rew_op(struct sk_buff *skb)
+ return rew_op;
+ }
+
++/**
++ * ocelot_xmit_get_vlan_info: Determine VLAN_TCI and TAG_TYPE for injected frame
++ * @skb: Pointer to socket buffer
++ * @br: Pointer to bridge device that the port is under, if any
++ * @vlan_tci:
++ * @tag_type:
++ *
++ * If the port is under a VLAN-aware bridge, remove the VLAN header from the
++ * payload and move it into the DSA tag, which will make the switch classify
++ * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
++ * which is the pvid of standalone ports (OCELOT_STANDALONE_PVID), although not
++ * of VLAN-unaware bridge ports (that would be ocelot_vlan_unaware_pvid()).
++ * Anyway, VID 0 is fine because it is stripped on egress for these port modes,
++ * and source address learning is not performed for packets injected from the
++ * CPU anyway, so it doesn't matter that the VID is "wrong".
++ */
++static inline void ocelot_xmit_get_vlan_info(struct sk_buff *skb,
++ struct net_device *br,
++ u64 *vlan_tci, u64 *tag_type)
++{
++ struct vlan_ethhdr *hdr;
++ u16 proto, tci;
++
++ if (!br || !br_vlan_enabled(br)) {
++ *vlan_tci = 0;
++ *tag_type = IFH_TAG_TYPE_C;
++ return;
++ }
++
++ hdr = (struct vlan_ethhdr *)skb_mac_header(skb);
++ br_vlan_get_proto(br, &proto);
++
++ if (ntohs(hdr->h_vlan_proto) == proto) {
++ vlan_remove_tag(skb, &tci);
++ *vlan_tci = tci;
++ } else {
++ rcu_read_lock();
++ br_vlan_get_pvid_rcu(br, &tci);
++ rcu_read_unlock();
++ *vlan_tci = tci;
++ }
++
++ *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
++}
++
+ #endif
+diff --git a/include/linux/fs.h b/include/linux/fs.h
+index 93ac1a859d699..36b9e87439221 100644
+--- a/include/linux/fs.h
++++ b/include/linux/fs.h
+@@ -2370,6 +2370,9 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
+ *
+ * I_PINNING_FSCACHE_WB Inode is pinning an fscache object for writeback.
+ *
++ * I_LRU_ISOLATING Inode is pinned being isolated from LRU without holding
++ * i_count.
++ *
+ * Q: What is the difference between I_WILL_FREE and I_FREEING?
+ */
+ #define I_DIRTY_SYNC (1 << 0)
+@@ -2393,6 +2396,8 @@ static inline void kiocb_clone(struct kiocb *kiocb, struct kiocb *kiocb_src,
+ #define I_DONTCACHE (1 << 16)
+ #define I_SYNC_QUEUED (1 << 17)
+ #define I_PINNING_NETFS_WB (1 << 18)
++#define __I_LRU_ISOLATING 19
++#define I_LRU_ISOLATING (1 << __I_LRU_ISOLATING)
+
+ #define I_DIRTY_INODE (I_DIRTY_SYNC | I_DIRTY_DATASYNC)
+ #define I_DIRTY (I_DIRTY_INODE | I_DIRTY_PAGES)
+diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
+index 8120d1976188c..18cf440866d9f 100644
+--- a/include/linux/hugetlb.h
++++ b/include/linux/hugetlb.h
+@@ -967,10 +967,37 @@ static inline bool htlb_allow_alloc_fallback(int reason)
+ static inline spinlock_t *huge_pte_lockptr(struct hstate *h,
+ struct mm_struct *mm, pte_t *pte)
+ {
+- if (huge_page_size(h) == PMD_SIZE)
++ const unsigned long size = huge_page_size(h);
++
++ VM_WARN_ON(size == PAGE_SIZE);
++
++ /*
++ * hugetlb must use the exact same PT locks as core-mm page table
++ * walkers would. When modifying a PTE table, hugetlb must take the
++ * PTE PT lock, when modifying a PMD table, hugetlb must take the PMD
++ * PT lock etc.
++ *
++ * The expectation is that any hugetlb folio smaller than a PMD is
++ * always mapped into a single PTE table and that any hugetlb folio
++ * smaller than a PUD (but at least as big as a PMD) is always mapped
++ * into a single PMD table.
++ *
++ * If that does not hold for an architecture, then that architecture
++ * must disable split PT locks such that all *_lockptr() functions
++ * will give us the same result: the per-MM PT lock.
++ *
++ * Note that with e.g., CONFIG_PGTABLE_LEVELS=2 where
++ * PGDIR_SIZE==P4D_SIZE==PUD_SIZE==PMD_SIZE, we'd use pud_lockptr()
++ * and core-mm would use pmd_lockptr(). However, in such configurations
++ * split PMD locks are disabled -- they don't make sense on a single
++ * PGDIR page table -- and the end result is the same.
++ */
++ if (size >= PUD_SIZE)
++ return pud_lockptr(mm, (pud_t *) pte);
++ else if (size >= PMD_SIZE || IS_ENABLED(CONFIG_HIGHPTE))
+ return pmd_lockptr(mm, (pmd_t *) pte);
+- VM_BUG_ON(huge_page_size(h) == PAGE_SIZE);
+- return &mm->page_table_lock;
++ /* pte_alloc_huge() only applies with !CONFIG_HIGHPTE */
++ return ptep_lockptr(mm, pte);
+ }
+
+ #ifndef hugepages_supported
+diff --git a/include/linux/io_uring_types.h b/include/linux/io_uring_types.h
+index 7abdc09271245..b18e998c8b887 100644
+--- a/include/linux/io_uring_types.h
++++ b/include/linux/io_uring_types.h
+@@ -410,7 +410,7 @@ struct io_ring_ctx {
+ spinlock_t napi_lock; /* napi_list lock */
+
+ /* napi busy poll default timeout */
+- unsigned int napi_busy_poll_to;
++ ktime_t napi_busy_poll_dt;
+ bool napi_prefer_busy_poll;
+ bool napi_enabled;
+
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index b58bad248eefd..f32177152921e 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -2960,6 +2960,13 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
+ return ptlock_ptr(page_ptdesc(pmd_page(*pmd)));
+ }
+
++static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
++{
++ BUILD_BUG_ON(IS_ENABLED(CONFIG_HIGHPTE));
++ BUILD_BUG_ON(MAX_PTRS_PER_PTE * sizeof(pte_t) > PAGE_SIZE);
++ return ptlock_ptr(virt_to_ptdesc(pte));
++}
++
+ static inline bool ptlock_init(struct ptdesc *ptdesc)
+ {
+ /*
+@@ -2984,6 +2991,10 @@ static inline spinlock_t *pte_lockptr(struct mm_struct *mm, pmd_t *pmd)
+ {
+ return &mm->page_table_lock;
+ }
++static inline spinlock_t *ptep_lockptr(struct mm_struct *mm, pte_t *pte)
++{
++ return &mm->page_table_lock;
++}
+ static inline void ptlock_cache_init(void) {}
+ static inline bool ptlock_init(struct ptdesc *ptdesc) { return true; }
+ static inline void ptlock_free(struct ptdesc *ptdesc) {}
+diff --git a/include/linux/panic.h b/include/linux/panic.h
+index 6717b15e798c3..556b4e2ad9aa5 100644
+--- a/include/linux/panic.h
++++ b/include/linux/panic.h
+@@ -16,6 +16,7 @@ extern void oops_enter(void);
+ extern void oops_exit(void);
+ extern bool oops_may_print(void);
+
++extern bool panic_triggering_all_cpu_backtrace;
+ extern int panic_timeout;
+ extern unsigned long panic_print;
+ extern int panic_on_oops;
+diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
+index 18cd0c0c73d93..207f0c83c8e97 100644
+--- a/include/linux/pgalloc_tag.h
++++ b/include/linux/pgalloc_tag.h
+@@ -43,6 +43,18 @@ static inline void put_page_tag_ref(union codetag_ref *ref)
+ page_ext_put(page_ext_from_codetag_ref(ref));
+ }
+
++static inline void clear_page_tag_ref(struct page *page)
++{
++ if (mem_alloc_profiling_enabled()) {
++ union codetag_ref *ref = get_page_tag_ref(page);
++
++ if (ref) {
++ set_codetag_empty(ref);
++ put_page_tag_ref(ref);
++ }
++ }
++}
++
+ static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
+ unsigned int nr)
+ {
+@@ -126,6 +138,7 @@ static inline void pgalloc_tag_sub_pages(struct alloc_tag *tag, unsigned int nr)
+
+ static inline union codetag_ref *get_page_tag_ref(struct page *page) { return NULL; }
+ static inline void put_page_tag_ref(union codetag_ref *ref) {}
++static inline void clear_page_tag_ref(struct page *page) {}
+ static inline void pgalloc_tag_add(struct page *page, struct task_struct *task,
+ unsigned int nr) {}
+ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr) {}
+diff --git a/include/linux/thermal.h b/include/linux/thermal.h
+index f1155c0439c4b..13f88317b81bf 100644
+--- a/include/linux/thermal.h
++++ b/include/linux/thermal.h
+@@ -55,6 +55,7 @@ enum thermal_notify_event {
+ THERMAL_TZ_BIND_CDEV, /* Cooling dev is bind to the thermal zone */
+ THERMAL_TZ_UNBIND_CDEV, /* Cooling dev is unbind from the thermal zone */
+ THERMAL_INSTANCE_WEIGHT_CHANGED, /* Thermal instance weight changed */
++ THERMAL_TZ_RESUME, /* Thermal zone is resuming after system sleep */
+ };
+
+ /**
+diff --git a/include/net/af_vsock.h b/include/net/af_vsock.h
+index 535701efc1e5c..24d970f7a4fa2 100644
+--- a/include/net/af_vsock.h
++++ b/include/net/af_vsock.h
+@@ -230,8 +230,12 @@ struct vsock_tap {
+ int vsock_add_tap(struct vsock_tap *vt);
+ int vsock_remove_tap(struct vsock_tap *vt);
+ void vsock_deliver_tap(struct sk_buff *build_skb(void *opaque), void *opaque);
++int __vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
++ int flags);
+ int vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ int flags);
++int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
++ size_t len, int flags);
+ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+ size_t len, int flags);
+
+diff --git a/include/net/bluetooth/hci.h b/include/net/bluetooth/hci.h
+index e372a88e8c3f6..d1d073089f384 100644
+--- a/include/net/bluetooth/hci.h
++++ b/include/net/bluetooth/hci.h
+@@ -206,14 +206,17 @@ enum {
+ */
+ HCI_QUIRK_WIDEBAND_SPEECH_SUPPORTED,
+
+- /* When this quirk is set, the controller has validated that
+- * LE states reported through the HCI_LE_READ_SUPPORTED_STATES are
+- * valid. This mechanism is necessary as many controllers have
+- * been seen has having trouble initiating a connectable
+- * advertisement despite the state combination being reported as
+- * supported.
++ /* When this quirk is set, the LE states reported through the
++ * HCI_LE_READ_SUPPORTED_STATES are invalid/broken.
++ *
++ * This mechanism is necessary as many controllers have been seen has
++ * having trouble initiating a connectable advertisement despite the
++ * state combination being reported as supported.
++ *
++ * This quirk can be set before hci_register_dev is called or
++ * during the hdev->setup vendor callback.
+ */
+- HCI_QUIRK_VALID_LE_STATES,
++ HCI_QUIRK_BROKEN_LE_STATES,
+
+ /* When this quirk is set, then erroneous data reporting
+ * is ignored. This is mainly due to the fact that the HCI
+diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
+index b15f51ae3bfd9..c97ff64c9189f 100644
+--- a/include/net/bluetooth/hci_core.h
++++ b/include/net/bluetooth/hci_core.h
+@@ -826,7 +826,7 @@ extern struct mutex hci_cb_list_lock;
+ } while (0)
+
+ #define hci_dev_le_state_simultaneous(hdev) \
+- (test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) && \
++ (!test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) && \
+ (hdev->le_states[4] & 0x08) && /* Central */ \
+ (hdev->le_states[4] & 0x40) && /* Peripheral */ \
+ (hdev->le_states[3] & 0x10)) /* Simultaneous */
+diff --git a/include/net/kcm.h b/include/net/kcm.h
+index 90279e5e09a5c..441e993be634c 100644
+--- a/include/net/kcm.h
++++ b/include/net/kcm.h
+@@ -70,6 +70,7 @@ struct kcm_sock {
+ struct work_struct tx_work;
+ struct list_head wait_psock_list;
+ struct sk_buff *seq_skb;
++ struct mutex tx_mutex;
+ u32 tx_stopped : 1;
+
+ /* Don't use bit fields here, these are set under different locks */
+diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
+index f207a6e1042ae..9bdb1fdc7c51b 100644
+--- a/include/net/mana/mana.h
++++ b/include/net/mana/mana.h
+@@ -274,6 +274,7 @@ struct mana_cq {
+ /* NAPI data */
+ struct napi_struct napi;
+ int work_done;
++ int work_done_since_doorbell;
+ int budget;
+ };
+
+diff --git a/include/scsi/scsi_cmnd.h b/include/scsi/scsi_cmnd.h
+index 45c40d200154d..8ecfb94049db5 100644
+--- a/include/scsi/scsi_cmnd.h
++++ b/include/scsi/scsi_cmnd.h
+@@ -234,7 +234,7 @@ static inline sector_t scsi_get_lba(struct scsi_cmnd *scmd)
+
+ static inline unsigned int scsi_logical_block_count(struct scsi_cmnd *scmd)
+ {
+- unsigned int shift = ilog2(scmd->device->sector_size) - SECTOR_SHIFT;
++ unsigned int shift = ilog2(scmd->device->sector_size);
+
+ return blk_rq_bytes(scsi_cmd_to_rq(scmd)) >> shift;
+ }
+diff --git a/include/soc/mscc/ocelot.h b/include/soc/mscc/ocelot.h
+index 1e1b40f4e664e..846132ca5503d 100644
+--- a/include/soc/mscc/ocelot.h
++++ b/include/soc/mscc/ocelot.h
+@@ -813,6 +813,9 @@ struct ocelot {
+ const u32 *const *map;
+ struct list_head stats_regions;
+
++ spinlock_t inj_lock;
++ spinlock_t xtr_lock;
++
+ u32 pool_size[OCELOT_SB_NUM][OCELOT_SB_POOL_NUM];
+ int packet_buffer_size;
+ int num_frame_refs;
+@@ -966,10 +969,17 @@ void __ocelot_target_write_ix(struct ocelot *ocelot, enum ocelot_target target,
+ u32 val, u32 reg, u32 offset);
+
+ /* Packet I/O */
++void ocelot_lock_inj_grp(struct ocelot *ocelot, int grp);
++void ocelot_unlock_inj_grp(struct ocelot *ocelot, int grp);
++void ocelot_lock_xtr_grp(struct ocelot *ocelot, int grp);
++void ocelot_unlock_xtr_grp(struct ocelot *ocelot, int grp);
++void ocelot_lock_xtr_grp_bh(struct ocelot *ocelot, int grp);
++void ocelot_unlock_xtr_grp_bh(struct ocelot *ocelot, int grp);
+ bool ocelot_can_inject(struct ocelot *ocelot, int grp);
+ void ocelot_port_inject_frame(struct ocelot *ocelot, int port, int grp,
+ u32 rew_op, struct sk_buff *skb);
+-void ocelot_ifh_port_set(void *ifh, int port, u32 rew_op, u32 vlan_tag);
++void ocelot_ifh_set_basic(void *ifh, struct ocelot *ocelot, int port,
++ u32 rew_op, struct sk_buff *skb);
+ int ocelot_xtr_poll_frame(struct ocelot *ocelot, int grp, struct sk_buff **skb);
+ void ocelot_drain_cpu_queue(struct ocelot *ocelot, int grp);
+ void ocelot_ptp_rx_timestamp(struct ocelot *ocelot, struct sk_buff *skb,
+diff --git a/include/trace/events/netfs.h b/include/trace/events/netfs.h
+index da23484268dfc..24ec3434d32ee 100644
+--- a/include/trace/events/netfs.h
++++ b/include/trace/events/netfs.h
+@@ -145,6 +145,7 @@
+ EM(netfs_folio_trace_clear_g, "clear-g") \
+ EM(netfs_folio_trace_clear_s, "clear-s") \
+ EM(netfs_folio_trace_copy_to_cache, "mark-copy") \
++ EM(netfs_folio_trace_end_copy, "end-copy") \
+ EM(netfs_folio_trace_filled_gaps, "filled-gaps") \
+ EM(netfs_folio_trace_kill, "kill") \
+ EM(netfs_folio_trace_kill_cc, "kill-cc") \
+diff --git a/include/uapi/misc/fastrpc.h b/include/uapi/misc/fastrpc.h
+index 91583690bddc5..f33d914d8f469 100644
+--- a/include/uapi/misc/fastrpc.h
++++ b/include/uapi/misc/fastrpc.h
+@@ -8,14 +8,11 @@
+ #define FASTRPC_IOCTL_ALLOC_DMA_BUFF _IOWR('R', 1, struct fastrpc_alloc_dma_buf)
+ #define FASTRPC_IOCTL_FREE_DMA_BUFF _IOWR('R', 2, __u32)
+ #define FASTRPC_IOCTL_INVOKE _IOWR('R', 3, struct fastrpc_invoke)
+-/* This ioctl is only supported with secure device nodes */
+ #define FASTRPC_IOCTL_INIT_ATTACH _IO('R', 4)
+ #define FASTRPC_IOCTL_INIT_CREATE _IOWR('R', 5, struct fastrpc_init_create)
+ #define FASTRPC_IOCTL_MMAP _IOWR('R', 6, struct fastrpc_req_mmap)
+ #define FASTRPC_IOCTL_MUNMAP _IOWR('R', 7, struct fastrpc_req_munmap)
+-/* This ioctl is only supported with secure device nodes */
+ #define FASTRPC_IOCTL_INIT_ATTACH_SNS _IO('R', 8)
+-/* This ioctl is only supported with secure device nodes */
+ #define FASTRPC_IOCTL_INIT_CREATE_STATIC _IOWR('R', 9, struct fastrpc_init_create_static)
+ #define FASTRPC_IOCTL_MEM_MAP _IOWR('R', 10, struct fastrpc_mem_map)
+ #define FASTRPC_IOCTL_MEM_UNMAP _IOWR('R', 11, struct fastrpc_mem_unmap)
+diff --git a/init/Kconfig b/init/Kconfig
+index d8a971b804d32..9684e5d2b81c6 100644
+--- a/init/Kconfig
++++ b/init/Kconfig
+@@ -1789,24 +1789,6 @@ config KALLSYMS_ABSOLUTE_PERCPU
+ depends on KALLSYMS
+ default X86_64 && SMP
+
+-config KALLSYMS_BASE_RELATIVE
+- bool
+- depends on KALLSYMS
+- default y
+- help
+- Instead of emitting them as absolute values in the native word size,
+- emit the symbol references in the kallsyms table as 32-bit entries,
+- each containing a relative value in the range [base, base + U32_MAX]
+- or, when KALLSYMS_ABSOLUTE_PERCPU is in effect, each containing either
+- an absolute value in the range [0, S32_MAX] or a relative value in the
+- range [base, base + S32_MAX], where base is the lowest relative symbol
+- address encountered in the image.
+-
+- On 64-bit builds, this reduces the size of the address table by 50%,
+- but more importantly, it results in entries whose values are build
+- time constants, and no relocation pass is required at runtime to fix
+- up the entries based on the runtime load address of the kernel.
+-
+ # end of the "standard kernel features (expert users)" menu
+
+ config ARCH_HAS_MEMBARRIER_CALLBACKS
+@@ -1924,12 +1906,15 @@ config RUST
+ config RUSTC_VERSION_TEXT
+ string
+ depends on RUST
+- default $(shell,command -v $(RUSTC) >/dev/null 2>&1 && $(RUSTC) --version || echo n)
++ default "$(shell,$(RUSTC) --version 2>/dev/null)"
+
+ config BINDGEN_VERSION_TEXT
+ string
+ depends on RUST
+- default $(shell,command -v $(BINDGEN) >/dev/null 2>&1 && $(BINDGEN) --version || echo n)
++ # The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0
++ # (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when
++ # the minimum version is upgraded past that (0.69.1 already fixed the issue).
++ default "$(shell,$(BINDGEN) --version workaround-for-0.69.0 2>/dev/null)"
+
+ #
+ # Place an empty function call at each tracepoint site. Can be
+diff --git a/io_uring/io_uring.h b/io_uring/io_uring.h
+index 726e6367af4d3..af46d03d58847 100644
+--- a/io_uring/io_uring.h
++++ b/io_uring/io_uring.h
+@@ -43,7 +43,7 @@ struct io_wait_queue {
+ ktime_t timeout;
+
+ #ifdef CONFIG_NET_RX_BUSY_POLL
+- unsigned int napi_busy_poll_to;
++ ktime_t napi_busy_poll_dt;
+ bool napi_prefer_busy_poll;
+ #endif
+ };
+diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
+index c95dc1736dd93..1af2bd56af44a 100644
+--- a/io_uring/kbuf.c
++++ b/io_uring/kbuf.c
+@@ -218,10 +218,13 @@ static int io_ring_buffers_peek(struct io_kiocb *req, struct buf_sel_arg *arg,
+
+ buf = io_ring_head_to_buf(br, head, bl->mask);
+ if (arg->max_len) {
+- int needed;
++ u32 len = READ_ONCE(buf->len);
++ size_t needed;
+
+- needed = (arg->max_len + buf->len - 1) / buf->len;
+- needed = min(needed, PEEK_MAX_IMPORT);
++ if (unlikely(!len))
++ return -ENOBUFS;
++ needed = (arg->max_len + len - 1) / len;
++ needed = min_not_zero(needed, (size_t) PEEK_MAX_IMPORT);
+ if (nr_avail > needed)
+ nr_avail = needed;
+ }
+diff --git a/io_uring/napi.c b/io_uring/napi.c
+index 080d10e0e0afd..ab5d68d4440c4 100644
+--- a/io_uring/napi.c
++++ b/io_uring/napi.c
+@@ -33,6 +33,12 @@ static struct io_napi_entry *io_napi_hash_find(struct hlist_head *hash_list,
+ return NULL;
+ }
+
++static inline ktime_t net_to_ktime(unsigned long t)
++{
++ /* napi approximating usecs, reverse busy_loop_current_time */
++ return ns_to_ktime(t << 10);
++}
++
+ void __io_napi_add(struct io_ring_ctx *ctx, struct socket *sock)
+ {
+ struct hlist_head *hash_list;
+@@ -102,14 +108,14 @@ static inline void io_napi_remove_stale(struct io_ring_ctx *ctx, bool is_stale)
+ __io_napi_remove_stale(ctx);
+ }
+
+-static inline bool io_napi_busy_loop_timeout(unsigned long start_time,
+- unsigned long bp_usec)
++static inline bool io_napi_busy_loop_timeout(ktime_t start_time,
++ ktime_t bp)
+ {
+- if (bp_usec) {
+- unsigned long end_time = start_time + bp_usec;
+- unsigned long now = busy_loop_current_time();
++ if (bp) {
++ ktime_t end_time = ktime_add(start_time, bp);
++ ktime_t now = net_to_ktime(busy_loop_current_time());
+
+- return time_after(now, end_time);
++ return ktime_after(now, end_time);
+ }
+
+ return true;
+@@ -124,7 +130,8 @@ static bool io_napi_busy_loop_should_end(void *data,
+ return true;
+ if (io_should_wake(iowq) || io_has_work(iowq->ctx))
+ return true;
+- if (io_napi_busy_loop_timeout(start_time, iowq->napi_busy_poll_to))
++ if (io_napi_busy_loop_timeout(net_to_ktime(start_time),
++ iowq->napi_busy_poll_dt))
+ return true;
+
+ return false;
+@@ -181,10 +188,12 @@ static void io_napi_blocking_busy_loop(struct io_ring_ctx *ctx,
+ */
+ void io_napi_init(struct io_ring_ctx *ctx)
+ {
++ u64 sys_dt = READ_ONCE(sysctl_net_busy_poll) * NSEC_PER_USEC;
++
+ INIT_LIST_HEAD(&ctx->napi_list);
+ spin_lock_init(&ctx->napi_lock);
+ ctx->napi_prefer_busy_poll = false;
+- ctx->napi_busy_poll_to = READ_ONCE(sysctl_net_busy_poll);
++ ctx->napi_busy_poll_dt = ns_to_ktime(sys_dt);
+ }
+
+ /*
+@@ -217,7 +226,7 @@ void io_napi_free(struct io_ring_ctx *ctx)
+ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+ {
+ const struct io_uring_napi curr = {
+- .busy_poll_to = ctx->napi_busy_poll_to,
++ .busy_poll_to = ktime_to_us(ctx->napi_busy_poll_dt),
+ .prefer_busy_poll = ctx->napi_prefer_busy_poll
+ };
+ struct io_uring_napi napi;
+@@ -232,7 +241,7 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+ if (copy_to_user(arg, &curr, sizeof(curr)))
+ return -EFAULT;
+
+- WRITE_ONCE(ctx->napi_busy_poll_to, napi.busy_poll_to);
++ WRITE_ONCE(ctx->napi_busy_poll_dt, napi.busy_poll_to * NSEC_PER_USEC);
+ WRITE_ONCE(ctx->napi_prefer_busy_poll, !!napi.prefer_busy_poll);
+ WRITE_ONCE(ctx->napi_enabled, true);
+ return 0;
+@@ -249,14 +258,14 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+ {
+ const struct io_uring_napi curr = {
+- .busy_poll_to = ctx->napi_busy_poll_to,
++ .busy_poll_to = ktime_to_us(ctx->napi_busy_poll_dt),
+ .prefer_busy_poll = ctx->napi_prefer_busy_poll
+ };
+
+ if (arg && copy_to_user(arg, &curr, sizeof(curr)))
+ return -EFAULT;
+
+- WRITE_ONCE(ctx->napi_busy_poll_to, 0);
++ WRITE_ONCE(ctx->napi_busy_poll_dt, 0);
+ WRITE_ONCE(ctx->napi_prefer_busy_poll, false);
+ WRITE_ONCE(ctx->napi_enabled, false);
+ return 0;
+@@ -275,23 +284,20 @@ int io_unregister_napi(struct io_ring_ctx *ctx, void __user *arg)
+ void __io_napi_adjust_timeout(struct io_ring_ctx *ctx, struct io_wait_queue *iowq,
+ struct timespec64 *ts)
+ {
+- unsigned int poll_to = READ_ONCE(ctx->napi_busy_poll_to);
++ ktime_t poll_dt = READ_ONCE(ctx->napi_busy_poll_dt);
+
+ if (ts) {
+ struct timespec64 poll_to_ts;
+
+- poll_to_ts = ns_to_timespec64(1000 * (s64)poll_to);
++ poll_to_ts = ns_to_timespec64(ktime_to_ns(poll_dt));
+ if (timespec64_compare(ts, &poll_to_ts) < 0) {
+ s64 poll_to_ns = timespec64_to_ns(ts);
+- if (poll_to_ns > 0) {
+- u64 val = poll_to_ns + 999;
+- do_div(val, (s64) 1000);
+- poll_to = val;
+- }
++ if (poll_to_ns > 0)
++ poll_dt = ns_to_ktime(poll_to_ns);
+ }
+ }
+
+- iowq->napi_busy_poll_to = poll_to;
++ iowq->napi_busy_poll_dt = poll_dt;
+ }
+
+ /*
+@@ -305,7 +311,7 @@ void __io_napi_busy_loop(struct io_ring_ctx *ctx, struct io_wait_queue *iowq)
+ {
+ iowq->napi_prefer_busy_poll = READ_ONCE(ctx->napi_prefer_busy_poll);
+
+- if (!(ctx->flags & IORING_SETUP_SQPOLL) && ctx->napi_enabled)
++ if (!(ctx->flags & IORING_SETUP_SQPOLL))
+ io_napi_blocking_busy_loop(ctx, iowq);
+ }
+
+@@ -320,7 +326,7 @@ int io_napi_sqpoll_busy_poll(struct io_ring_ctx *ctx)
+ LIST_HEAD(napi_list);
+ bool is_stale = false;
+
+- if (!READ_ONCE(ctx->napi_busy_poll_to))
++ if (!READ_ONCE(ctx->napi_busy_poll_dt))
+ return 0;
+ if (list_empty_careful(&ctx->napi_list))
+ return 0;
+diff --git a/io_uring/napi.h b/io_uring/napi.h
+index 6fc0393d0dbef..341d010cf66bc 100644
+--- a/io_uring/napi.h
++++ b/io_uring/napi.h
+@@ -55,7 +55,7 @@ static inline void io_napi_add(struct io_kiocb *req)
+ struct io_ring_ctx *ctx = req->ctx;
+ struct socket *sock;
+
+- if (!READ_ONCE(ctx->napi_busy_poll_to))
++ if (!READ_ONCE(ctx->napi_enabled))
+ return;
+
+ sock = sock_from_file(req->file);
+diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
+index a8845cc299fec..521bd7efae038 100644
+--- a/kernel/bpf/verifier.c
++++ b/kernel/bpf/verifier.c
+@@ -16881,8 +16881,9 @@ static bool stacksafe(struct bpf_verifier_env *env, struct bpf_func_state *old,
+ spi = i / BPF_REG_SIZE;
+
+ if (exact != NOT_EXACT &&
+- old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
+- cur->stack[spi].slot_type[i % BPF_REG_SIZE])
++ (i >= cur->allocated_stack ||
++ old->stack[spi].slot_type[i % BPF_REG_SIZE] !=
++ cur->stack[spi].slot_type[i % BPF_REG_SIZE]))
+ return false;
+
+ if (!(old->stack[spi].spilled_ptr.live & REG_LIVE_READ)
+diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
+index 5e468db958104..fc1c6236460d2 100644
+--- a/kernel/cgroup/cpuset.c
++++ b/kernel/cgroup/cpuset.c
+@@ -1940,6 +1940,8 @@ static int update_parent_effective_cpumask(struct cpuset *cs, int cmd,
+ part_error = PERR_CPUSEMPTY;
+ goto write_error;
+ }
++ /* Check newmask again, whether cpus are available for parent/cs */
++ nocpu |= tasks_nocpu_error(parent, cs, newmask);
+
+ /*
+ * partcmd_update with newmask:
+@@ -2472,7 +2474,8 @@ static int update_cpumask(struct cpuset *cs, struct cpuset *trialcs,
+ */
+ if (!*buf) {
+ cpumask_clear(trialcs->cpus_allowed);
+- cpumask_clear(trialcs->effective_xcpus);
++ if (cpumask_empty(trialcs->exclusive_cpus))
++ cpumask_clear(trialcs->effective_xcpus);
+ } else {
+ retval = cpulist_parse(buf, trialcs->cpus_allowed);
+ if (retval < 0)
+diff --git a/kernel/cpu.c b/kernel/cpu.c
+index 3d2bf1d50a0c4..6dee328bfe6fd 100644
+--- a/kernel/cpu.c
++++ b/kernel/cpu.c
+@@ -2679,6 +2679,16 @@ int cpuhp_smt_disable(enum cpuhp_smt_control ctrlval)
+ return ret;
+ }
+
++/**
++ * Check if the core a CPU belongs to is online
++ */
++#if !defined(topology_is_core_online)
++static inline bool topology_is_core_online(unsigned int cpu)
++{
++ return true;
++}
++#endif
++
+ int cpuhp_smt_enable(void)
+ {
+ int cpu, ret = 0;
+@@ -2689,7 +2699,7 @@ int cpuhp_smt_enable(void)
+ /* Skip online CPUs and CPUs on offline nodes */
+ if (cpu_online(cpu) || !node_online(cpu_to_node(cpu)))
+ continue;
+- if (!cpu_smt_thread_allowed(cpu))
++ if (!cpu_smt_thread_allowed(cpu) || !topology_is_core_online(cpu))
+ continue;
+ ret = _cpu_up(cpu, 0, CPUHP_ONLINE);
+ if (ret)
+diff --git a/kernel/events/core.c b/kernel/events/core.c
+index b2a6aec118f3a..7891d5a75526a 100644
+--- a/kernel/events/core.c
++++ b/kernel/events/core.c
+@@ -9708,7 +9708,8 @@ static int __perf_event_overflow(struct perf_event *event,
+
+ ret = __perf_event_account_interrupt(event, throttle);
+
+- if (event->prog && !bpf_overflow_handler(event, data, regs))
++ if (event->prog && event->prog->type == BPF_PROG_TYPE_PERF_EVENT &&
++ !bpf_overflow_handler(event, data, regs))
+ return ret;
+
+ /*
+diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
+index 98b9622d372e4..a9a0ca605d4a8 100644
+--- a/kernel/kallsyms.c
++++ b/kernel/kallsyms.c
+@@ -148,9 +148,6 @@ static unsigned int get_symbol_offset(unsigned long pos)
+
+ unsigned long kallsyms_sym_address(int idx)
+ {
+- if (!IS_ENABLED(CONFIG_KALLSYMS_BASE_RELATIVE))
+- return kallsyms_addresses[idx];
+-
+ /* values are unsigned offsets if --absolute-percpu is not in effect */
+ if (!IS_ENABLED(CONFIG_KALLSYMS_ABSOLUTE_PERCPU))
+ return kallsyms_relative_base + (u32)kallsyms_offsets[idx];
+@@ -163,38 +160,6 @@ unsigned long kallsyms_sym_address(int idx)
+ return kallsyms_relative_base - 1 - kallsyms_offsets[idx];
+ }
+
+-static void cleanup_symbol_name(char *s)
+-{
+- char *res;
+-
+- if (!IS_ENABLED(CONFIG_LTO_CLANG))
+- return;
+-
+- /*
+- * LLVM appends various suffixes for local functions and variables that
+- * must be promoted to global scope as part of LTO. This can break
+- * hooking of static functions with kprobes. '.' is not a valid
+- * character in an identifier in C. Suffixes only in LLVM LTO observed:
+- * - foo.llvm.[0-9a-f]+
+- */
+- res = strstr(s, ".llvm.");
+- if (res)
+- *res = '\0';
+-
+- return;
+-}
+-
+-static int compare_symbol_name(const char *name, char *namebuf)
+-{
+- /* The kallsyms_seqs_of_names is sorted based on names after
+- * cleanup_symbol_name() (see scripts/kallsyms.c) if clang lto is enabled.
+- * To ensure correct bisection in kallsyms_lookup_names(), do
+- * cleanup_symbol_name(namebuf) before comparing name and namebuf.
+- */
+- cleanup_symbol_name(namebuf);
+- return strcmp(name, namebuf);
+-}
+-
+ static unsigned int get_symbol_seq(int index)
+ {
+ unsigned int i, seq = 0;
+@@ -222,7 +187,7 @@ static int kallsyms_lookup_names(const char *name,
+ seq = get_symbol_seq(mid);
+ off = get_symbol_offset(seq);
+ kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
+- ret = compare_symbol_name(name, namebuf);
++ ret = strcmp(name, namebuf);
+ if (ret > 0)
+ low = mid + 1;
+ else if (ret < 0)
+@@ -239,7 +204,7 @@ static int kallsyms_lookup_names(const char *name,
+ seq = get_symbol_seq(low - 1);
+ off = get_symbol_offset(seq);
+ kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
+- if (compare_symbol_name(name, namebuf))
++ if (strcmp(name, namebuf))
+ break;
+ low--;
+ }
+@@ -251,7 +216,7 @@ static int kallsyms_lookup_names(const char *name,
+ seq = get_symbol_seq(high + 1);
+ off = get_symbol_offset(seq);
+ kallsyms_expand_symbol(off, namebuf, ARRAY_SIZE(namebuf));
+- if (compare_symbol_name(name, namebuf))
++ if (strcmp(name, namebuf))
+ break;
+ high++;
+ }
+@@ -325,7 +290,7 @@ static unsigned long get_symbol_pos(unsigned long addr,
+ unsigned long symbol_start = 0, symbol_end = 0;
+ unsigned long i, low, high, mid;
+
+- /* Do a binary search on the sorted kallsyms_addresses array. */
++ /* Do a binary search on the sorted kallsyms_offsets array. */
+ low = 0;
+ high = kallsyms_num_syms;
+
+@@ -410,8 +375,7 @@ static int kallsyms_lookup_buildid(unsigned long addr,
+ if (modbuildid)
+ *modbuildid = NULL;
+
+- ret = strlen(namebuf);
+- goto found;
++ return strlen(namebuf);
+ }
+
+ /* See if it's in a module or a BPF JITed image. */
+@@ -425,8 +389,6 @@ static int kallsyms_lookup_buildid(unsigned long addr,
+ ret = ftrace_mod_address_lookup(addr, symbolsize,
+ offset, modname, namebuf);
+
+-found:
+- cleanup_symbol_name(namebuf);
+ return ret;
+ }
+
+@@ -453,8 +415,6 @@ const char *kallsyms_lookup(unsigned long addr,
+
+ int lookup_symbol_name(unsigned long addr, char *symname)
+ {
+- int res;
+-
+ symname[0] = '\0';
+ symname[KSYM_NAME_LEN - 1] = '\0';
+
+@@ -465,16 +425,10 @@ int lookup_symbol_name(unsigned long addr, char *symname)
+ /* Grab name */
+ kallsyms_expand_symbol(get_symbol_offset(pos),
+ symname, KSYM_NAME_LEN);
+- goto found;
++ return 0;
+ }
+ /* See if it's in a module. */
+- res = lookup_module_symbol_name(addr, symname);
+- if (res)
+- return res;
+-
+-found:
+- cleanup_symbol_name(symname);
+- return 0;
++ return lookup_module_symbol_name(addr, symname);
+ }
+
+ /* Look up a kernel symbol and return it in a text buffer. */
+diff --git a/kernel/kallsyms_internal.h b/kernel/kallsyms_internal.h
+index 85480274fc8fb..9633782f82500 100644
+--- a/kernel/kallsyms_internal.h
++++ b/kernel/kallsyms_internal.h
+@@ -4,12 +4,6 @@
+
+ #include <linux/types.h>
+
+-/*
+- * These will be re-linked against their real values during the second link
+- * stage. Preliminary values must be provided in the linker script using the
+- * PROVIDE() directive so that the first link stage can complete successfully.
+- */
+-extern const unsigned long kallsyms_addresses[];
+ extern const int kallsyms_offsets[];
+ extern const u8 kallsyms_names[];
+
+diff --git a/kernel/kallsyms_selftest.c b/kernel/kallsyms_selftest.c
+index 2f84896a7bcbd..873f7c445488c 100644
+--- a/kernel/kallsyms_selftest.c
++++ b/kernel/kallsyms_selftest.c
+@@ -187,31 +187,11 @@ static void test_perf_kallsyms_lookup_name(void)
+ stat.min, stat.max, div_u64(stat.sum, stat.real_cnt));
+ }
+
+-static bool match_cleanup_name(const char *s, const char *name)
+-{
+- char *p;
+- int len;
+-
+- if (!IS_ENABLED(CONFIG_LTO_CLANG))
+- return false;
+-
+- p = strstr(s, ".llvm.");
+- if (!p)
+- return false;
+-
+- len = strlen(name);
+- if (p - s != len)
+- return false;
+-
+- return !strncmp(s, name, len);
+-}
+-
+ static int find_symbol(void *data, const char *name, unsigned long addr)
+ {
+ struct test_stat *stat = (struct test_stat *)data;
+
+- if (strcmp(name, stat->name) == 0 ||
+- (!stat->perf && match_cleanup_name(name, stat->name))) {
++ if (!strcmp(name, stat->name)) {
+ stat->real_cnt++;
+ stat->addr = addr;
+
+diff --git a/kernel/panic.c b/kernel/panic.c
+index 8bff183d6180e..30342568e935f 100644
+--- a/kernel/panic.c
++++ b/kernel/panic.c
+@@ -63,6 +63,8 @@ unsigned long panic_on_taint;
+ bool panic_on_taint_nousertaint = false;
+ static unsigned int warn_limit __read_mostly;
+
++bool panic_triggering_all_cpu_backtrace;
++
+ int panic_timeout = CONFIG_PANIC_TIMEOUT;
+ EXPORT_SYMBOL_GPL(panic_timeout);
+
+@@ -252,8 +254,12 @@ void check_panic_on_warn(const char *origin)
+ */
+ static void panic_other_cpus_shutdown(bool crash_kexec)
+ {
+- if (panic_print & PANIC_PRINT_ALL_CPU_BT)
++ if (panic_print & PANIC_PRINT_ALL_CPU_BT) {
++ /* Temporary allow non-panic CPUs to write their backtraces. */
++ panic_triggering_all_cpu_backtrace = true;
+ trigger_all_cpu_backtrace();
++ panic_triggering_all_cpu_backtrace = false;
++ }
+
+ /*
+ * Note that smp_send_stop() is the usual SMP shutdown function,
+diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
+index dddb15f48d595..c5d844f727f63 100644
+--- a/kernel/printk/printk.c
++++ b/kernel/printk/printk.c
+@@ -2316,7 +2316,7 @@ asmlinkage int vprintk_emit(int facility, int level,
+ * non-panic CPUs are generating any messages, they will be
+ * silently dropped.
+ */
+- if (other_cpu_in_panic())
++ if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace)
+ return 0;
+
+ if (level == LOGLEVEL_SCHED) {
+diff --git a/kernel/trace/trace.c b/kernel/trace/trace.c
+index 578a49ff5c32e..cb507860163d0 100644
+--- a/kernel/trace/trace.c
++++ b/kernel/trace/trace.c
+@@ -7956,7 +7956,7 @@ tracing_buffers_read(struct file *filp, char __user *ubuf,
+ trace_access_unlock(iter->cpu_file);
+
+ if (ret < 0) {
+- if (trace_empty(iter)) {
++ if (trace_empty(iter) && !iter->closed) {
+ if ((filp->f_flags & O_NONBLOCK))
+ return -EAGAIN;
+
+diff --git a/kernel/vmcore_info.c b/kernel/vmcore_info.c
+index 1d5eadd9dd61c..8b4f8cc2e0ec0 100644
+--- a/kernel/vmcore_info.c
++++ b/kernel/vmcore_info.c
+@@ -216,12 +216,8 @@ static int __init crash_save_vmcoreinfo_init(void)
+ VMCOREINFO_SYMBOL(kallsyms_num_syms);
+ VMCOREINFO_SYMBOL(kallsyms_token_table);
+ VMCOREINFO_SYMBOL(kallsyms_token_index);
+-#ifdef CONFIG_KALLSYMS_BASE_RELATIVE
+ VMCOREINFO_SYMBOL(kallsyms_offsets);
+ VMCOREINFO_SYMBOL(kallsyms_relative_base);
+-#else
+- VMCOREINFO_SYMBOL(kallsyms_addresses);
+-#endif /* CONFIG_KALLSYMS_BASE_RELATIVE */
+ #endif /* CONFIG_KALLSYMS */
+
+ arch_crash_save_vmcoreinfo();
+diff --git a/kernel/workqueue.c b/kernel/workqueue.c
+index f98247ec99c20..c970eec25c5a0 100644
+--- a/kernel/workqueue.c
++++ b/kernel/workqueue.c
+@@ -896,7 +896,7 @@ static struct worker_pool *get_work_pool(struct work_struct *work)
+
+ static unsigned long shift_and_mask(unsigned long v, u32 shift, u32 bits)
+ {
+- return (v >> shift) & ((1 << bits) - 1);
++ return (v >> shift) & ((1U << bits) - 1);
+ }
+
+ static void work_offqd_unpack(struct work_offq_data *offqd, unsigned long data)
+@@ -4190,7 +4190,6 @@ static bool start_flush_work(struct work_struct *work, struct wq_barrier *barr,
+ static bool __flush_work(struct work_struct *work, bool from_cancel)
+ {
+ struct wq_barrier barr;
+- unsigned long data;
+
+ if (WARN_ON(!wq_online))
+ return false;
+@@ -4208,29 +4207,35 @@ static bool __flush_work(struct work_struct *work, bool from_cancel)
+ * was queued on a BH workqueue, we also know that it was running in the
+ * BH context and thus can be busy-waited.
+ */
+- data = *work_data_bits(work);
+- if (from_cancel &&
+- !WARN_ON_ONCE(data & WORK_STRUCT_PWQ) && (data & WORK_OFFQ_BH)) {
+- /*
+- * On RT, prevent a live lock when %current preempted soft
+- * interrupt processing or prevents ksoftirqd from running by
+- * keeping flipping BH. If the BH work item runs on a different
+- * CPU then this has no effect other than doing the BH
+- * disable/enable dance for nothing. This is copied from
+- * kernel/softirq.c::tasklet_unlock_spin_wait().
+- */
+- while (!try_wait_for_completion(&barr.done)) {
+- if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
+- local_bh_disable();
+- local_bh_enable();
+- } else {
+- cpu_relax();
++ if (from_cancel) {
++ unsigned long data = *work_data_bits(work);
++
++ if (!WARN_ON_ONCE(data & WORK_STRUCT_PWQ) &&
++ (data & WORK_OFFQ_BH)) {
++ /*
++ * On RT, prevent a live lock when %current preempted
++ * soft interrupt processing or prevents ksoftirqd from
++ * running by keeping flipping BH. If the BH work item
++ * runs on a different CPU then this has no effect other
++ * than doing the BH disable/enable dance for nothing.
++ * This is copied from
++ * kernel/softirq.c::tasklet_unlock_spin_wait().
++ */
++ while (!try_wait_for_completion(&barr.done)) {
++ if (IS_ENABLED(CONFIG_PREEMPT_RT)) {
++ local_bh_disable();
++ local_bh_enable();
++ } else {
++ cpu_relax();
++ }
+ }
++ goto out_destroy;
+ }
+- } else {
+- wait_for_completion(&barr.done);
+ }
+
++ wait_for_completion(&barr.done);
++
++out_destroy:
+ destroy_work_on_stack(&barr.work);
+ return true;
+ }
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 5f32a196a612e..4d9c1277e5e4d 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -1672,7 +1672,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
+ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+ if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+ spin_unlock(vmf->ptl);
+- goto out;
++ return 0;
+ }
+
+ pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+@@ -1715,22 +1715,16 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
+ if (!migrate_misplaced_folio(folio, vma, target_nid)) {
+ flags |= TNF_MIGRATED;
+ nid = target_nid;
+- } else {
+- flags |= TNF_MIGRATE_FAIL;
+- vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+- if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
+- spin_unlock(vmf->ptl);
+- goto out;
+- }
+- goto out_map;
+- }
+-
+-out:
+- if (nid != NUMA_NO_NODE)
+ task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
++ return 0;
++ }
+
+- return 0;
+-
++ flags |= TNF_MIGRATE_FAIL;
++ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
++ if (unlikely(!pmd_same(oldpmd, *vmf->pmd))) {
++ spin_unlock(vmf->ptl);
++ return 0;
++ }
+ out_map:
+ /* Restore the PMD */
+ pmd = pmd_modify(oldpmd, vma->vm_page_prot);
+@@ -1740,7 +1734,10 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
+ set_pmd_at(vma->vm_mm, haddr, vmf->pmd, pmd);
+ update_mmu_cache_pmd(vma, vmf->address, vmf->pmd);
+ spin_unlock(vmf->ptl);
+- goto out;
++
++ if (nid != NUMA_NO_NODE)
++ task_numa_fault(last_cpupid, nid, HPAGE_PMD_NR, flags);
++ return 0;
+ }
+
+ /*
+diff --git a/mm/memcontrol.c b/mm/memcontrol.c
+index 88c7a0861017c..332f190bf3d6b 100644
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@ -5282,9 +5282,12 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of,
+ buf = endp + 1;
+
+ cfd = simple_strtoul(buf, &endp, 10);
+- if ((*endp != ' ') && (*endp != '\0'))
++ if (*endp == '\0')
++ buf = endp;
++ else if (*endp == ' ')
++ buf = endp + 1;
++ else
+ return -EINVAL;
+- buf = endp + 1;
+
+ event = kzalloc(sizeof(*event), GFP_KERNEL);
+ if (!event)
+diff --git a/mm/memory-failure.c b/mm/memory-failure.c
+index d3c830e817e35..7e2e454142bcd 100644
+--- a/mm/memory-failure.c
++++ b/mm/memory-failure.c
+@@ -2406,7 +2406,7 @@ struct memory_failure_entry {
+ struct memory_failure_cpu {
+ DECLARE_KFIFO(fifo, struct memory_failure_entry,
+ MEMORY_FAILURE_FIFO_SIZE);
+- spinlock_t lock;
++ raw_spinlock_t lock;
+ struct work_struct work;
+ };
+
+@@ -2432,20 +2432,22 @@ void memory_failure_queue(unsigned long pfn, int flags)
+ {
+ struct memory_failure_cpu *mf_cpu;
+ unsigned long proc_flags;
++ bool buffer_overflow;
+ struct memory_failure_entry entry = {
+ .pfn = pfn,
+ .flags = flags,
+ };
+
+ mf_cpu = &get_cpu_var(memory_failure_cpu);
+- spin_lock_irqsave(&mf_cpu->lock, proc_flags);
+- if (kfifo_put(&mf_cpu->fifo, entry))
++ raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags);
++ buffer_overflow = !kfifo_put(&mf_cpu->fifo, entry);
++ if (!buffer_overflow)
+ schedule_work_on(smp_processor_id(), &mf_cpu->work);
+- else
++ raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
++ put_cpu_var(memory_failure_cpu);
++ if (buffer_overflow)
+ pr_err("buffer overflow when queuing memory failure at %#lx\n",
+ pfn);
+- spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
+- put_cpu_var(memory_failure_cpu);
+ }
+ EXPORT_SYMBOL_GPL(memory_failure_queue);
+
+@@ -2458,9 +2460,9 @@ static void memory_failure_work_func(struct work_struct *work)
+
+ mf_cpu = container_of(work, struct memory_failure_cpu, work);
+ for (;;) {
+- spin_lock_irqsave(&mf_cpu->lock, proc_flags);
++ raw_spin_lock_irqsave(&mf_cpu->lock, proc_flags);
+ gotten = kfifo_get(&mf_cpu->fifo, &entry);
+- spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
++ raw_spin_unlock_irqrestore(&mf_cpu->lock, proc_flags);
+ if (!gotten)
+ break;
+ if (entry.flags & MF_SOFT_OFFLINE)
+@@ -2490,7 +2492,7 @@ static int __init memory_failure_init(void)
+
+ for_each_possible_cpu(cpu) {
+ mf_cpu = &per_cpu(memory_failure_cpu, cpu);
+- spin_lock_init(&mf_cpu->lock);
++ raw_spin_lock_init(&mf_cpu->lock);
+ INIT_KFIFO(mf_cpu->fifo);
+ INIT_WORK(&mf_cpu->work, memory_failure_work_func);
+ }
+diff --git a/mm/memory.c b/mm/memory.c
+index 755ffe082e217..72d00a38585d0 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -5155,7 +5155,7 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
+
+ if (unlikely(!pte_same(old_pte, vmf->orig_pte))) {
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+- goto out;
++ return 0;
+ }
+
+ pte = pte_modify(old_pte, vma->vm_page_prot);
+@@ -5218,23 +5218,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
+ if (!migrate_misplaced_folio(folio, vma, target_nid)) {
+ nid = target_nid;
+ flags |= TNF_MIGRATED;
+- } else {
+- flags |= TNF_MIGRATE_FAIL;
+- vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
+- vmf->address, &vmf->ptl);
+- if (unlikely(!vmf->pte))
+- goto out;
+- if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
+- pte_unmap_unlock(vmf->pte, vmf->ptl);
+- goto out;
+- }
+- goto out_map;
++ task_numa_fault(last_cpupid, nid, nr_pages, flags);
++ return 0;
+ }
+
+-out:
+- if (nid != NUMA_NO_NODE)
+- task_numa_fault(last_cpupid, nid, nr_pages, flags);
+- return 0;
++ flags |= TNF_MIGRATE_FAIL;
++ vmf->pte = pte_offset_map_lock(vma->vm_mm, vmf->pmd,
++ vmf->address, &vmf->ptl);
++ if (unlikely(!vmf->pte))
++ return 0;
++ if (unlikely(!pte_same(ptep_get(vmf->pte), vmf->orig_pte))) {
++ pte_unmap_unlock(vmf->pte, vmf->ptl);
++ return 0;
++ }
+ out_map:
+ /*
+ * Make it present again, depending on how arch implements
+@@ -5247,7 +5243,10 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
+ numa_rebuild_single_mapping(vmf, vma, vmf->address, vmf->pte,
+ writable);
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+- goto out;
++
++ if (nid != NUMA_NO_NODE)
++ task_numa_fault(last_cpupid, nid, nr_pages, flags);
++ return 0;
+ }
+
+ static inline vm_fault_t create_huge_pmd(struct vm_fault *vmf)
+diff --git a/mm/mm_init.c b/mm/mm_init.c
+index 3ec04933f7fd8..2addc701790ae 100644
+--- a/mm/mm_init.c
++++ b/mm/mm_init.c
+@@ -2293,6 +2293,8 @@ void __init init_cma_reserved_pageblock(struct page *page)
+
+ set_pageblock_migratetype(page, MIGRATE_CMA);
+ set_page_refcounted(page);
++ /* pages were reserved and not allocated */
++ clear_page_tag_ref(page);
+ __free_pages(page, pageblock_order);
+
+ adjust_managed_page_count(page, pageblock_nr_pages);
+@@ -2505,15 +2507,7 @@ void __init memblock_free_pages(struct page *page, unsigned long pfn,
+ }
+
+ /* pages were reserved and not allocated */
+- if (mem_alloc_profiling_enabled()) {
+- union codetag_ref *ref = get_page_tag_ref(page);
+-
+- if (ref) {
+- set_codetag_empty(ref);
+- put_page_tag_ref(ref);
+- }
+- }
+-
++ clear_page_tag_ref(page);
+ __free_pages_core(page, order);
+ }
+
+diff --git a/mm/mseal.c b/mm/mseal.c
+index bf783bba8ed0b..15bba28acc005 100644
+--- a/mm/mseal.c
++++ b/mm/mseal.c
+@@ -40,9 +40,17 @@ static bool can_modify_vma(struct vm_area_struct *vma)
+
+ static bool is_madv_discard(int behavior)
+ {
+- return behavior &
+- (MADV_FREE | MADV_DONTNEED | MADV_DONTNEED_LOCKED |
+- MADV_REMOVE | MADV_DONTFORK | MADV_WIPEONFORK);
++ switch (behavior) {
++ case MADV_FREE:
++ case MADV_DONTNEED:
++ case MADV_DONTNEED_LOCKED:
++ case MADV_REMOVE:
++ case MADV_DONTFORK:
++ case MADV_WIPEONFORK:
++ return true;
++ }
++
++ return false;
+ }
+
+ static bool is_ro_anon(struct vm_area_struct *vma)
+diff --git a/mm/page_alloc.c b/mm/page_alloc.c
+index df2c442f1c47b..b50060405d947 100644
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -287,7 +287,7 @@ EXPORT_SYMBOL(nr_online_nodes);
+
+ static bool page_contains_unaccepted(struct page *page, unsigned int order);
+ static void accept_page(struct page *page, unsigned int order);
+-static bool try_to_accept_memory(struct zone *zone, unsigned int order);
++static bool cond_accept_memory(struct zone *zone, unsigned int order);
+ static inline bool has_unaccepted_memory(void);
+ static bool __free_unaccepted(struct page *page);
+
+@@ -3059,9 +3059,6 @@ static inline long __zone_watermark_unusable_free(struct zone *z,
+ if (!(alloc_flags & ALLOC_CMA))
+ unusable_free += zone_page_state(z, NR_FREE_CMA_PAGES);
+ #endif
+-#ifdef CONFIG_UNACCEPTED_MEMORY
+- unusable_free += zone_page_state(z, NR_UNACCEPTED);
+-#endif
+
+ return unusable_free;
+ }
+@@ -3355,6 +3352,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
+ }
+ }
+
++ cond_accept_memory(zone, order);
++
+ /*
+ * Detect whether the number of free pages is below high
+ * watermark. If so, we will decrease pcp->high and free
+@@ -3380,10 +3379,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
+ gfp_mask)) {
+ int ret;
+
+- if (has_unaccepted_memory()) {
+- if (try_to_accept_memory(zone, order))
+- goto try_this_zone;
+- }
++ if (cond_accept_memory(zone, order))
++ goto try_this_zone;
+
+ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+ /*
+@@ -3437,10 +3434,8 @@ get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags,
+
+ return page;
+ } else {
+- if (has_unaccepted_memory()) {
+- if (try_to_accept_memory(zone, order))
+- goto try_this_zone;
+- }
++ if (cond_accept_memory(zone, order))
++ goto try_this_zone;
+
+ #ifdef CONFIG_DEFERRED_STRUCT_PAGE_INIT
+ /* Try again if zone has deferred pages */
+@@ -5811,14 +5806,7 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
+
+ void free_reserved_page(struct page *page)
+ {
+- if (mem_alloc_profiling_enabled()) {
+- union codetag_ref *ref = get_page_tag_ref(page);
+-
+- if (ref) {
+- set_codetag_empty(ref);
+- put_page_tag_ref(ref);
+- }
+- }
++ clear_page_tag_ref(page);
+ ClearPageReserved(page);
+ init_page_count(page);
+ __free_page(page);
+@@ -6933,9 +6921,6 @@ static bool try_to_accept_memory_one(struct zone *zone)
+ struct page *page;
+ bool last;
+
+- if (list_empty(&zone->unaccepted_pages))
+- return false;
+-
+ spin_lock_irqsave(&zone->lock, flags);
+ page = list_first_entry_or_null(&zone->unaccepted_pages,
+ struct page, lru);
+@@ -6961,23 +6946,29 @@ static bool try_to_accept_memory_one(struct zone *zone)
+ return true;
+ }
+
+-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
++static bool cond_accept_memory(struct zone *zone, unsigned int order)
+ {
+ long to_accept;
+- int ret = false;
++ bool ret = false;
++
++ if (!has_unaccepted_memory())
++ return false;
++
++ if (list_empty(&zone->unaccepted_pages))
++ return false;
+
+ /* How much to accept to get to high watermark? */
+ to_accept = high_wmark_pages(zone) -
+ (zone_page_state(zone, NR_FREE_PAGES) -
+- __zone_watermark_unusable_free(zone, order, 0));
++ __zone_watermark_unusable_free(zone, order, 0) -
++ zone_page_state(zone, NR_UNACCEPTED));
+
+- /* Accept at least one page */
+- do {
++ while (to_accept > 0) {
+ if (!try_to_accept_memory_one(zone))
+ break;
+ ret = true;
+ to_accept -= MAX_ORDER_NR_PAGES;
+- } while (to_accept > 0);
++ }
+
+ return ret;
+ }
+@@ -7020,7 +7011,7 @@ static void accept_page(struct page *page, unsigned int order)
+ {
+ }
+
+-static bool try_to_accept_memory(struct zone *zone, unsigned int order)
++static bool cond_accept_memory(struct zone *zone, unsigned int order)
+ {
+ return false;
+ }
+diff --git a/mm/vmalloc.c b/mm/vmalloc.c
+index e34ea860153f2..881e497137e5d 100644
+--- a/mm/vmalloc.c
++++ b/mm/vmalloc.c
+@@ -3583,15 +3583,8 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
+ page = alloc_pages_noprof(alloc_gfp, order);
+ else
+ page = alloc_pages_node_noprof(nid, alloc_gfp, order);
+- if (unlikely(!page)) {
+- if (!nofail)
+- break;
+-
+- /* fall back to the zero order allocations */
+- alloc_gfp |= __GFP_NOFAIL;
+- order = 0;
+- continue;
+- }
++ if (unlikely(!page))
++ break;
+
+ /*
+ * Higher order allocations must be able to be treated as
+diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
+index 6ecb110bf46bc..b488d0742c966 100644
+--- a/net/bluetooth/hci_core.c
++++ b/net/bluetooth/hci_core.c
+@@ -3674,19 +3674,19 @@ static void hci_sched_le(struct hci_dev *hdev)
+ {
+ struct hci_chan *chan;
+ struct sk_buff *skb;
+- int quote, cnt, tmp;
++ int quote, *cnt, tmp;
+
+ BT_DBG("%s", hdev->name);
+
+ if (!hci_conn_num(hdev, LE_LINK))
+ return;
+
+- cnt = hdev->le_pkts ? hdev->le_cnt : hdev->acl_cnt;
++ cnt = hdev->le_pkts ? &hdev->le_cnt : &hdev->acl_cnt;
+
+- __check_timeout(hdev, cnt, LE_LINK);
++ __check_timeout(hdev, *cnt, LE_LINK);
+
+- tmp = cnt;
+- while (cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) {
++ tmp = *cnt;
++ while (*cnt && (chan = hci_chan_sent(hdev, LE_LINK, "e))) {
+ u32 priority = (skb_peek(&chan->data_q))->priority;
+ while (quote-- && (skb = skb_peek(&chan->data_q))) {
+ BT_DBG("chan %p skb %p len %d priority %u", chan, skb,
+@@ -3701,7 +3701,7 @@ static void hci_sched_le(struct hci_dev *hdev)
+ hci_send_frame(hdev, skb);
+ hdev->le_last_tx = jiffies;
+
+- cnt--;
++ (*cnt)--;
+ chan->sent++;
+ chan->conn->sent++;
+
+@@ -3711,12 +3711,7 @@ static void hci_sched_le(struct hci_dev *hdev)
+ }
+ }
+
+- if (hdev->le_pkts)
+- hdev->le_cnt = cnt;
+- else
+- hdev->acl_cnt = cnt;
+-
+- if (cnt != tmp)
++ if (*cnt != tmp)
+ hci_prio_recalculate(hdev, LE_LINK);
+ }
+
+diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
+index a78f6d706cd43..59d9086db75fe 100644
+--- a/net/bluetooth/hci_event.c
++++ b/net/bluetooth/hci_event.c
+@@ -5921,7 +5921,7 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev,
+ * while we have an existing one in peripheral role.
+ */
+ if (hdev->conn_hash.le_num_peripheral > 0 &&
+- (!test_bit(HCI_QUIRK_VALID_LE_STATES, &hdev->quirks) ||
++ (test_bit(HCI_QUIRK_BROKEN_LE_STATES, &hdev->quirks) ||
+ !(hdev->le_states[3] & 0x10)))
+ return NULL;
+
+diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c
+index 80f220b7e19d5..ad4793ea052df 100644
+--- a/net/bluetooth/mgmt.c
++++ b/net/bluetooth/mgmt.c
+@@ -3457,6 +3457,10 @@ static int pair_device(struct sock *sk, struct hci_dev *hdev, void *data,
+ * will be kept and this function does nothing.
+ */
+ p = hci_conn_params_add(hdev, &cp->addr.bdaddr, addr_type);
++ if (!p) {
++ err = -EIO;
++ goto unlock;
++ }
+
+ if (p->auto_connect == HCI_AUTO_CONN_EXPLICIT)
+ p->auto_connect = HCI_AUTO_CONN_DISABLED;
+diff --git a/net/bluetooth/smp.c b/net/bluetooth/smp.c
+index 1e7ea3a4b7ef3..4f9fdf400584e 100644
+--- a/net/bluetooth/smp.c
++++ b/net/bluetooth/smp.c
+@@ -914,7 +914,7 @@ static int tk_request(struct l2cap_conn *conn, u8 remote_oob, u8 auth,
+ * Confirms and the responder Enters the passkey.
+ */
+ if (smp->method == OVERLAP) {
+- if (hcon->role == HCI_ROLE_MASTER)
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ smp->method = CFM_PASSKEY;
+ else
+ smp->method = REQ_PASSKEY;
+@@ -964,7 +964,7 @@ static u8 smp_confirm(struct smp_chan *smp)
+
+ smp_send_cmd(smp->conn, SMP_CMD_PAIRING_CONFIRM, sizeof(cp), &cp);
+
+- if (conn->hcon->out)
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
+ else
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+@@ -980,7 +980,8 @@ static u8 smp_random(struct smp_chan *smp)
+ int ret;
+
+ bt_dev_dbg(conn->hcon->hdev, "conn %p %s", conn,
+- conn->hcon->out ? "initiator" : "responder");
++ test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" :
++ "responder");
+
+ ret = smp_c1(smp->tk, smp->rrnd, smp->preq, smp->prsp,
+ hcon->init_addr_type, &hcon->init_addr,
+@@ -994,7 +995,7 @@ static u8 smp_random(struct smp_chan *smp)
+ return SMP_CONFIRM_FAILED;
+ }
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ u8 stk[16];
+ __le64 rand = 0;
+ __le16 ediv = 0;
+@@ -1256,14 +1257,15 @@ static void smp_distribute_keys(struct smp_chan *smp)
+ rsp = (void *) &smp->prsp[1];
+
+ /* The responder sends its keys first */
+- if (hcon->out && (smp->remote_key_dist & KEY_DIST_MASK)) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags) &&
++ (smp->remote_key_dist & KEY_DIST_MASK)) {
+ smp_allow_key_dist(smp);
+ return;
+ }
+
+ req = (void *) &smp->preq[1];
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ keydist = &rsp->init_key_dist;
+ *keydist &= req->init_key_dist;
+ } else {
+@@ -1432,7 +1434,7 @@ static int sc_mackey_and_ltk(struct smp_chan *smp, u8 mackey[16], u8 ltk[16])
+ struct hci_conn *hcon = smp->conn->hcon;
+ u8 *na, *nb, a[7], b[7];
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ na = smp->prnd;
+ nb = smp->rrnd;
+ } else {
+@@ -1460,7 +1462,7 @@ static void sc_dhkey_check(struct smp_chan *smp)
+ a[6] = hcon->init_addr_type;
+ b[6] = hcon->resp_addr_type;
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ local_addr = a;
+ remote_addr = b;
+ memcpy(io_cap, &smp->preq[1], 3);
+@@ -1539,7 +1541,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
+ /* The round is only complete when the initiator
+ * receives pairing random.
+ */
+- if (!hcon->out) {
++ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+ sizeof(smp->prnd), smp->prnd);
+ if (smp->passkey_round == 20)
+@@ -1567,7 +1569,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
+
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+ sizeof(smp->prnd), smp->prnd);
+ return 0;
+@@ -1578,7 +1580,7 @@ static u8 sc_passkey_round(struct smp_chan *smp, u8 smp_op)
+ case SMP_CMD_PUBLIC_KEY:
+ default:
+ /* Initiating device starts the round */
+- if (!hcon->out)
++ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ return 0;
+
+ bt_dev_dbg(hdev, "Starting passkey round %u",
+@@ -1623,7 +1625,7 @@ static int sc_user_reply(struct smp_chan *smp, u16 mgmt_op, __le32 passkey)
+ }
+
+ /* Initiator sends DHKey check first */
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ sc_dhkey_check(smp);
+ SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+ } else if (test_and_clear_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags)) {
+@@ -1746,7 +1748,7 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
+ struct smp_cmd_pairing rsp, *req = (void *) skb->data;
+ struct l2cap_chan *chan = conn->smp;
+ struct hci_dev *hdev = conn->hcon->hdev;
+- struct smp_chan *smp;
++ struct smp_chan *smp = chan->data;
+ u8 key_size, auth, sec_level;
+ int ret;
+
+@@ -1755,16 +1757,14 @@ static u8 smp_cmd_pairing_req(struct l2cap_conn *conn, struct sk_buff *skb)
+ if (skb->len < sizeof(*req))
+ return SMP_INVALID_PARAMS;
+
+- if (conn->hcon->role != HCI_ROLE_SLAVE)
++ if (smp && test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ return SMP_CMD_NOTSUPP;
+
+- if (!chan->data)
++ if (!smp) {
+ smp = smp_chan_create(conn);
+- else
+- smp = chan->data;
+-
+- if (!smp)
+- return SMP_UNSPECIFIED;
++ if (!smp)
++ return SMP_UNSPECIFIED;
++ }
+
+ /* We didn't start the pairing, so match remote */
+ auth = req->auth_req & AUTH_REQ_MASK(hdev);
+@@ -1946,7 +1946,7 @@ static u8 smp_cmd_pairing_rsp(struct l2cap_conn *conn, struct sk_buff *skb)
+ if (skb->len < sizeof(*rsp))
+ return SMP_INVALID_PARAMS;
+
+- if (conn->hcon->role != HCI_ROLE_MASTER)
++ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ return SMP_CMD_NOTSUPP;
+
+ skb_pull(skb, sizeof(*rsp));
+@@ -2041,7 +2041,7 @@ static u8 sc_check_confirm(struct smp_chan *smp)
+ if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
+ return sc_passkey_round(smp, SMP_CMD_PAIRING_CONFIRM);
+
+- if (conn->hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
+ smp->prnd);
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+@@ -2063,7 +2063,7 @@ static int fixup_sc_false_positive(struct smp_chan *smp)
+ u8 auth;
+
+ /* The issue is only observed when we're in responder role */
+- if (hcon->out)
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ return SMP_UNSPECIFIED;
+
+ if (hci_dev_test_flag(hdev, HCI_SC_ONLY)) {
+@@ -2099,7 +2099,8 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
+ struct hci_dev *hdev = hcon->hdev;
+
+ bt_dev_dbg(hdev, "conn %p %s", conn,
+- hcon->out ? "initiator" : "responder");
++ test_bit(SMP_FLAG_INITIATOR, &smp->flags) ? "initiator" :
++ "responder");
+
+ if (skb->len < sizeof(smp->pcnf))
+ return SMP_INVALID_PARAMS;
+@@ -2121,7 +2122,7 @@ static u8 smp_cmd_pairing_confirm(struct l2cap_conn *conn, struct sk_buff *skb)
+ return ret;
+ }
+
+- if (conn->hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM, sizeof(smp->prnd),
+ smp->prnd);
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RANDOM);
+@@ -2156,7 +2157,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
+ if (!test_bit(SMP_FLAG_SC, &smp->flags))
+ return smp_random(smp);
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ pkax = smp->local_pk;
+ pkbx = smp->remote_pk;
+ na = smp->prnd;
+@@ -2169,7 +2170,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
+ }
+
+ if (smp->method == REQ_OOB) {
+- if (!hcon->out)
++ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+ sizeof(smp->prnd), smp->prnd);
+ SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+@@ -2180,7 +2181,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
+ if (smp->method == REQ_PASSKEY || smp->method == DSP_PASSKEY)
+ return sc_passkey_round(smp, SMP_CMD_PAIRING_RANDOM);
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ u8 cfm[16];
+
+ err = smp_f4(smp->tfm_cmac, smp->remote_pk, smp->local_pk,
+@@ -2221,7 +2222,7 @@ static u8 smp_cmd_pairing_random(struct l2cap_conn *conn, struct sk_buff *skb)
+ return SMP_UNSPECIFIED;
+
+ if (smp->method == REQ_OOB) {
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ sc_dhkey_check(smp);
+ SMP_ALLOW_CMD(smp, SMP_CMD_DHKEY_CHECK);
+ }
+@@ -2295,10 +2296,27 @@ bool smp_sufficient_security(struct hci_conn *hcon, u8 sec_level,
+ return false;
+ }
+
++static void smp_send_pairing_req(struct smp_chan *smp, __u8 auth)
++{
++ struct smp_cmd_pairing cp;
++
++ if (smp->conn->hcon->type == ACL_LINK)
++ build_bredr_pairing_cmd(smp, &cp, NULL);
++ else
++ build_pairing_cmd(smp->conn, &cp, NULL, auth);
++
++ smp->preq[0] = SMP_CMD_PAIRING_REQ;
++ memcpy(&smp->preq[1], &cp, sizeof(cp));
++
++ smp_send_cmd(smp->conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
++ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
++
++ set_bit(SMP_FLAG_INITIATOR, &smp->flags);
++}
++
+ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
+ {
+ struct smp_cmd_security_req *rp = (void *) skb->data;
+- struct smp_cmd_pairing cp;
+ struct hci_conn *hcon = conn->hcon;
+ struct hci_dev *hdev = hcon->hdev;
+ struct smp_chan *smp;
+@@ -2347,16 +2365,20 @@ static u8 smp_cmd_security_req(struct l2cap_conn *conn, struct sk_buff *skb)
+
+ skb_pull(skb, sizeof(*rp));
+
+- memset(&cp, 0, sizeof(cp));
+- build_pairing_cmd(conn, &cp, NULL, auth);
++ smp_send_pairing_req(smp, auth);
+
+- smp->preq[0] = SMP_CMD_PAIRING_REQ;
+- memcpy(&smp->preq[1], &cp, sizeof(cp));
++ return 0;
++}
+
+- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
+- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
++static void smp_send_security_req(struct smp_chan *smp, __u8 auth)
++{
++ struct smp_cmd_security_req cp;
+
+- return 0;
++ cp.auth_req = auth;
++ smp_send_cmd(smp->conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
++ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ);
++
++ clear_bit(SMP_FLAG_INITIATOR, &smp->flags);
+ }
+
+ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
+@@ -2427,23 +2449,11 @@ int smp_conn_security(struct hci_conn *hcon, __u8 sec_level)
+ authreq |= SMP_AUTH_MITM;
+ }
+
+- if (hcon->role == HCI_ROLE_MASTER) {
+- struct smp_cmd_pairing cp;
+-
+- build_pairing_cmd(conn, &cp, NULL, authreq);
+- smp->preq[0] = SMP_CMD_PAIRING_REQ;
+- memcpy(&smp->preq[1], &cp, sizeof(cp));
+-
+- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(cp), &cp);
+- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
+- } else {
+- struct smp_cmd_security_req cp;
+- cp.auth_req = authreq;
+- smp_send_cmd(conn, SMP_CMD_SECURITY_REQ, sizeof(cp), &cp);
+- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_REQ);
+- }
++ if (hcon->role == HCI_ROLE_MASTER)
++ smp_send_pairing_req(smp, authreq);
++ else
++ smp_send_security_req(smp, authreq);
+
+- set_bit(SMP_FLAG_INITIATOR, &smp->flags);
+ ret = 0;
+
+ unlock:
+@@ -2694,8 +2704,6 @@ static int smp_cmd_sign_info(struct l2cap_conn *conn, struct sk_buff *skb)
+
+ static u8 sc_select_method(struct smp_chan *smp)
+ {
+- struct l2cap_conn *conn = smp->conn;
+- struct hci_conn *hcon = conn->hcon;
+ struct smp_cmd_pairing *local, *remote;
+ u8 local_mitm, remote_mitm, local_io, remote_io, method;
+
+@@ -2708,7 +2716,7 @@ static u8 sc_select_method(struct smp_chan *smp)
+ * the "struct smp_cmd_pairing" from them we need to skip the
+ * first byte which contains the opcode.
+ */
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ local = (void *) &smp->preq[1];
+ remote = (void *) &smp->prsp[1];
+ } else {
+@@ -2777,7 +2785,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
+ /* Non-initiating device sends its public key after receiving
+ * the key from the initiating device.
+ */
+- if (!hcon->out) {
++ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ err = sc_send_public_key(smp);
+ if (err)
+ return err;
+@@ -2839,7 +2847,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
+ }
+
+ if (smp->method == REQ_OOB) {
+- if (hcon->out)
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ smp_send_cmd(conn, SMP_CMD_PAIRING_RANDOM,
+ sizeof(smp->prnd), smp->prnd);
+
+@@ -2848,7 +2856,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
+ return 0;
+ }
+
+- if (hcon->out)
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_CONFIRM);
+
+ if (smp->method == REQ_PASSKEY) {
+@@ -2863,7 +2871,7 @@ static int smp_cmd_public_key(struct l2cap_conn *conn, struct sk_buff *skb)
+ /* The Initiating device waits for the non-initiating device to
+ * send the confirm value.
+ */
+- if (conn->hcon->out)
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags))
+ return 0;
+
+ err = smp_f4(smp->tfm_cmac, smp->local_pk, smp->remote_pk, smp->prnd,
+@@ -2897,7 +2905,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
+ a[6] = hcon->init_addr_type;
+ b[6] = hcon->resp_addr_type;
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ local_addr = a;
+ remote_addr = b;
+ memcpy(io_cap, &smp->prsp[1], 3);
+@@ -2922,7 +2930,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
+ if (crypto_memneq(check->e, e, 16))
+ return SMP_DHKEY_CHECK_FAILED;
+
+- if (!hcon->out) {
++ if (!test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ if (test_bit(SMP_FLAG_WAIT_USER, &smp->flags)) {
+ set_bit(SMP_FLAG_DHKEY_PENDING, &smp->flags);
+ return 0;
+@@ -2934,7 +2942,7 @@ static int smp_cmd_dhkey_check(struct l2cap_conn *conn, struct sk_buff *skb)
+
+ sc_add_ltk(smp);
+
+- if (hcon->out) {
++ if (test_bit(SMP_FLAG_INITIATOR, &smp->flags)) {
+ hci_le_start_enc(hcon, 0, 0, smp->tk, smp->enc_key_size);
+ hcon->enc_key_size = smp->enc_key_size;
+ }
+@@ -3083,7 +3091,6 @@ static void bredr_pairing(struct l2cap_chan *chan)
+ struct l2cap_conn *conn = chan->conn;
+ struct hci_conn *hcon = conn->hcon;
+ struct hci_dev *hdev = hcon->hdev;
+- struct smp_cmd_pairing req;
+ struct smp_chan *smp;
+
+ bt_dev_dbg(hdev, "chan %p", chan);
+@@ -3135,14 +3142,7 @@ static void bredr_pairing(struct l2cap_chan *chan)
+
+ bt_dev_dbg(hdev, "starting SMP over BR/EDR");
+
+- /* Prepare and send the BR/EDR SMP Pairing Request */
+- build_bredr_pairing_cmd(smp, &req, NULL);
+-
+- smp->preq[0] = SMP_CMD_PAIRING_REQ;
+- memcpy(&smp->preq[1], &req, sizeof(req));
+-
+- smp_send_cmd(conn, SMP_CMD_PAIRING_REQ, sizeof(req), &req);
+- SMP_ALLOW_CMD(smp, SMP_CMD_PAIRING_RSP);
++ smp_send_pairing_req(smp, 0x00);
+ }
+
+ static void smp_resume_cb(struct l2cap_chan *chan)
+diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c
+index bf30c50b56895..a9e1b56f854d4 100644
+--- a/net/bridge/br_netfilter_hooks.c
++++ b/net/bridge/br_netfilter_hooks.c
+@@ -619,8 +619,12 @@ static unsigned int br_nf_local_in(void *priv,
+ if (likely(nf_ct_is_confirmed(ct)))
+ return NF_ACCEPT;
+
++ if (WARN_ON_ONCE(refcount_read(&nfct->use) != 1)) {
++ nf_reset_ct(skb);
++ return NF_ACCEPT;
++ }
++
+ WARN_ON_ONCE(skb_shared(skb));
+- WARN_ON_ONCE(refcount_read(&nfct->use) != 1);
+
+ /* We can't call nf_confirm here, it would create a dependency
+ * on nf_conntrack module.
+diff --git a/net/dsa/tag_ocelot.c b/net/dsa/tag_ocelot.c
+index e0e4300bfbd3f..bf6608fc6be70 100644
+--- a/net/dsa/tag_ocelot.c
++++ b/net/dsa/tag_ocelot.c
+@@ -8,40 +8,6 @@
+ #define OCELOT_NAME "ocelot"
+ #define SEVILLE_NAME "seville"
+
+-/* If the port is under a VLAN-aware bridge, remove the VLAN header from the
+- * payload and move it into the DSA tag, which will make the switch classify
+- * the packet to the bridge VLAN. Otherwise, leave the classified VLAN at zero,
+- * which is the pvid of standalone and VLAN-unaware bridge ports.
+- */
+-static void ocelot_xmit_get_vlan_info(struct sk_buff *skb, struct dsa_port *dp,
+- u64 *vlan_tci, u64 *tag_type)
+-{
+- struct net_device *br = dsa_port_bridge_dev_get(dp);
+- struct vlan_ethhdr *hdr;
+- u16 proto, tci;
+-
+- if (!br || !br_vlan_enabled(br)) {
+- *vlan_tci = 0;
+- *tag_type = IFH_TAG_TYPE_C;
+- return;
+- }
+-
+- hdr = skb_vlan_eth_hdr(skb);
+- br_vlan_get_proto(br, &proto);
+-
+- if (ntohs(hdr->h_vlan_proto) == proto) {
+- vlan_remove_tag(skb, &tci);
+- *vlan_tci = tci;
+- } else {
+- rcu_read_lock();
+- br_vlan_get_pvid_rcu(br, &tci);
+- rcu_read_unlock();
+- *vlan_tci = tci;
+- }
+-
+- *tag_type = (proto != ETH_P_8021Q) ? IFH_TAG_TYPE_S : IFH_TAG_TYPE_C;
+-}
+-
+ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
+ __be32 ifh_prefix, void **ifh)
+ {
+@@ -53,7 +19,8 @@ static void ocelot_xmit_common(struct sk_buff *skb, struct net_device *netdev,
+ u32 rew_op = 0;
+ u64 qos_class;
+
+- ocelot_xmit_get_vlan_info(skb, dp, &vlan_tci, &tag_type);
++ ocelot_xmit_get_vlan_info(skb, dsa_port_bridge_dev_get(dp), &vlan_tci,
++ &tag_type);
+
+ qos_class = netdev_get_num_tc(netdev) ?
+ netdev_get_prio_tc_map(netdev, skb->priority) : skb->priority;
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+index ecd521108559f..2c52f6dcbd290 100644
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -238,9 +238,14 @@ static void tcp_measure_rcv_mss(struct sock *sk, const struct sk_buff *skb)
+ */
+ if (unlikely(len != icsk->icsk_ack.rcv_mss)) {
+ u64 val = (u64)skb->len << TCP_RMEM_TO_WIN_SCALE;
++ u8 old_ratio = tcp_sk(sk)->scaling_ratio;
+
+ do_div(val, skb->truesize);
+ tcp_sk(sk)->scaling_ratio = val ? val : 1;
++
++ if (old_ratio != tcp_sk(sk)->scaling_ratio)
++ WRITE_ONCE(tcp_sk(sk)->window_clamp,
++ tcp_win_from_space(sk, sk->sk_rcvbuf));
+ }
+ icsk->icsk_ack.rcv_mss = min_t(unsigned int, len,
+ tcp_sk(sk)->advmss);
+@@ -754,7 +759,8 @@ void tcp_rcv_space_adjust(struct sock *sk)
+ * <prev RTT . ><current RTT .. ><next RTT .... >
+ */
+
+- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) {
++ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
++ !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+ u64 rcvwin, grow;
+ int rcvbuf;
+
+@@ -770,22 +776,12 @@ void tcp_rcv_space_adjust(struct sock *sk)
+
+ rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
+- if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
+- if (rcvbuf > sk->sk_rcvbuf) {
+- WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+-
+- /* Make the window clamp follow along. */
+- WRITE_ONCE(tp->window_clamp,
+- tcp_win_from_space(sk, rcvbuf));
+- }
+- } else {
+- /* Make the window clamp follow along while being bounded
+- * by SO_RCVBUF.
+- */
+- int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf));
++ if (rcvbuf > sk->sk_rcvbuf) {
++ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+
+- if (clamp > tp->window_clamp)
+- WRITE_ONCE(tp->window_clamp, clamp);
++ /* Make the window clamp follow along. */
++ WRITE_ONCE(tp->window_clamp,
++ tcp_win_from_space(sk, rcvbuf));
+ }
+ }
+ tp->rcvq_space.space = copied;
+diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
+index a541659b6562b..8f8f93716ff85 100644
+--- a/net/ipv4/tcp_ipv4.c
++++ b/net/ipv4/tcp_ipv4.c
+@@ -95,6 +95,8 @@ EXPORT_SYMBOL(tcp_hashinfo);
+
+ static DEFINE_PER_CPU(struct sock *, ipv4_tcp_sk);
+
++static DEFINE_MUTEX(tcp_exit_batch_mutex);
++
+ static u32 tcp_v4_init_seq(const struct sk_buff *skb)
+ {
+ return secure_tcp_seq(ip_hdr(skb)->daddr,
+@@ -3509,6 +3511,16 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
+ {
+ struct net *net;
+
++ /* make sure concurrent calls to tcp_sk_exit_batch from net_cleanup_work
++ * and failed setup_net error unwinding path are serialized.
++ *
++ * tcp_twsk_purge() handles twsk in any dead netns, not just those in
++ * net_exit_list, the thread that dismantles a particular twsk must
++ * do so without other thread progressing to refcount_dec_and_test() of
++ * tcp_death_row.tw_refcount.
++ */
++ mutex_lock(&tcp_exit_batch_mutex);
++
+ tcp_twsk_purge(net_exit_list);
+
+ list_for_each_entry(net, net_exit_list, exit_list) {
+@@ -3516,6 +3528,8 @@ static void __net_exit tcp_sk_exit_batch(struct list_head *net_exit_list)
+ WARN_ON_ONCE(!refcount_dec_and_test(&net->ipv4.tcp_death_row.tw_refcount));
+ tcp_fastopen_ctx_destroy(net);
+ }
++
++ mutex_unlock(&tcp_exit_batch_mutex);
+ }
+
+ static struct pernet_operations __net_initdata tcp_sk_ops = {
+diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
+index ee9af921556a7..5b54f4f32b1cd 100644
+--- a/net/ipv4/udp_offload.c
++++ b/net/ipv4/udp_offload.c
+@@ -279,7 +279,8 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
+ return ERR_PTR(-EINVAL);
+
+ if (unlikely(skb_checksum_start(gso_skb) !=
+- skb_transport_header(gso_skb)))
++ skb_transport_header(gso_skb) &&
++ !(skb_shinfo(gso_skb)->gso_type & SKB_GSO_FRAGLIST)))
+ return ERR_PTR(-EINVAL);
+
+ if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
+diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
+index 784424ac41477..c49344d8311ab 100644
+--- a/net/ipv6/ip6_output.c
++++ b/net/ipv6/ip6_output.c
+@@ -70,11 +70,15 @@ static int ip6_finish_output2(struct net *net, struct sock *sk, struct sk_buff *
+
+ /* Be paranoid, rather than too clever. */
+ if (unlikely(hh_len > skb_headroom(skb)) && dev->header_ops) {
++ /* Make sure idev stays alive */
++ rcu_read_lock();
+ skb = skb_expand_head(skb, hh_len);
+ if (!skb) {
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
++ rcu_read_unlock();
+ return -ENOMEM;
+ }
++ rcu_read_unlock();
+ }
+
+ hdr = ipv6_hdr(skb);
+@@ -283,11 +287,15 @@ int ip6_xmit(const struct sock *sk, struct sk_buff *skb, struct flowi6 *fl6,
+ head_room += opt->opt_nflen + opt->opt_flen;
+
+ if (unlikely(head_room > skb_headroom(skb))) {
++ /* Make sure idev stays alive */
++ rcu_read_lock();
+ skb = skb_expand_head(skb, head_room);
+ if (!skb) {
+ IP6_INC_STATS(net, idev, IPSTATS_MIB_OUTDISCARDS);
++ rcu_read_unlock();
+ return -ENOBUFS;
+ }
++ rcu_read_unlock();
+ }
+
+ if (opt) {
+@@ -1953,6 +1961,7 @@ int ip6_send_skb(struct sk_buff *skb)
+ struct rt6_info *rt = dst_rt6_info(skb_dst(skb));
+ int err;
+
++ rcu_read_lock();
+ err = ip6_local_out(net, skb->sk, skb);
+ if (err) {
+ if (err > 0)
+@@ -1962,6 +1971,7 @@ int ip6_send_skb(struct sk_buff *skb)
+ IPSTATS_MIB_OUTDISCARDS);
+ }
+
++ rcu_read_unlock();
+ return err;
+ }
+
+diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c
+index 9dee0c1279554..87dfb565a9f81 100644
+--- a/net/ipv6/ip6_tunnel.c
++++ b/net/ipv6/ip6_tunnel.c
+@@ -1507,7 +1507,8 @@ static void ip6_tnl_link_config(struct ip6_tnl *t)
+ tdev = __dev_get_by_index(t->net, p->link);
+
+ if (tdev) {
+- dev->hard_header_len = tdev->hard_header_len + t_hlen;
++ dev->needed_headroom = tdev->hard_header_len +
++ tdev->needed_headroom + t_hlen;
+ mtu = min_t(unsigned int, tdev->mtu, IP6_MAX_MTU);
+
+ mtu = mtu - t_hlen;
+@@ -1731,7 +1732,9 @@ ip6_tnl_siocdevprivate(struct net_device *dev, struct ifreq *ifr,
+ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
+ {
+ struct ip6_tnl *tnl = netdev_priv(dev);
++ int t_hlen;
+
++ t_hlen = tnl->hlen + sizeof(struct ipv6hdr);
+ if (tnl->parms.proto == IPPROTO_IPV6) {
+ if (new_mtu < IPV6_MIN_MTU)
+ return -EINVAL;
+@@ -1740,10 +1743,10 @@ int ip6_tnl_change_mtu(struct net_device *dev, int new_mtu)
+ return -EINVAL;
+ }
+ if (tnl->parms.proto == IPPROTO_IPV6 || tnl->parms.proto == 0) {
+- if (new_mtu > IP6_MAX_MTU - dev->hard_header_len)
++ if (new_mtu > IP6_MAX_MTU - dev->hard_header_len - t_hlen)
+ return -EINVAL;
+ } else {
+- if (new_mtu > IP_MAX_MTU - dev->hard_header_len)
++ if (new_mtu > IP_MAX_MTU - dev->hard_header_len - t_hlen)
+ return -EINVAL;
+ }
+ WRITE_ONCE(dev->mtu, new_mtu);
+@@ -1887,12 +1890,11 @@ ip6_tnl_dev_init_gen(struct net_device *dev)
+ t_hlen = t->hlen + sizeof(struct ipv6hdr);
+
+ dev->type = ARPHRD_TUNNEL6;
+- dev->hard_header_len = LL_MAX_HEADER + t_hlen;
+ dev->mtu = ETH_DATA_LEN - t_hlen;
+ if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT))
+ dev->mtu -= 8;
+ dev->min_mtu = ETH_MIN_MTU;
+- dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len;
++ dev->max_mtu = IP6_MAX_MTU - dev->hard_header_len - t_hlen;
+
+ netdev_hold(dev, &t->dev_tracker, GFP_KERNEL);
+ netdev_lockdep_set_classes(dev);
+diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c
+index 5e1b50c6a44d2..3e9779ed7daec 100644
+--- a/net/ipv6/netfilter/nf_conntrack_reasm.c
++++ b/net/ipv6/netfilter/nf_conntrack_reasm.c
+@@ -154,6 +154,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user,
+ };
+ struct inet_frag_queue *q;
+
++ if (!(ipv6_addr_type(&hdr->daddr) & (IPV6_ADDR_MULTICAST |
++ IPV6_ADDR_LINKLOCAL)))
++ key.iif = 0;
++
+ q = inet_frag_find(nf_frag->fqdir, &key);
+ if (!q)
+ return NULL;
+diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c
+index b7bf34a5eb37a..1235307020075 100644
+--- a/net/iucv/iucv.c
++++ b/net/iucv/iucv.c
+@@ -86,13 +86,15 @@ struct device *iucv_alloc_device(const struct attribute_group **attrs,
+ {
+ struct device *dev;
+ va_list vargs;
++ char buf[20];
+ int rc;
+
+ dev = kzalloc(sizeof(*dev), GFP_KERNEL);
+ if (!dev)
+ goto out_error;
+ va_start(vargs, fmt);
+- rc = dev_set_name(dev, fmt, vargs);
++ vsnprintf(buf, sizeof(buf), fmt, vargs);
++ rc = dev_set_name(dev, "%s", buf);
+ va_end(vargs);
+ if (rc)
+ goto out_error;
+diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c
+index 2f191e50d4fc9..d4118c796290e 100644
+--- a/net/kcm/kcmsock.c
++++ b/net/kcm/kcmsock.c
+@@ -755,6 +755,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+ !(msg->msg_flags & MSG_MORE) : !!(msg->msg_flags & MSG_EOR);
+ int err = -EPIPE;
+
++ mutex_lock(&kcm->tx_mutex);
+ lock_sock(sk);
+
+ /* Per tcp_sendmsg this should be in poll */
+@@ -926,6 +927,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+ KCM_STATS_ADD(kcm->stats.tx_bytes, copied);
+
+ release_sock(sk);
++ mutex_unlock(&kcm->tx_mutex);
+ return copied;
+
+ out_error:
+@@ -951,6 +953,7 @@ static int kcm_sendmsg(struct socket *sock, struct msghdr *msg, size_t len)
+ sk->sk_write_space(sk);
+
+ release_sock(sk);
++ mutex_unlock(&kcm->tx_mutex);
+ return err;
+ }
+
+@@ -1204,6 +1207,7 @@ static void init_kcm_sock(struct kcm_sock *kcm, struct kcm_mux *mux)
+ spin_unlock_bh(&mux->lock);
+
+ INIT_WORK(&kcm->tx_work, kcm_tx_work);
++ mutex_init(&kcm->tx_mutex);
+
+ spin_lock_bh(&mux->rx_lock);
+ kcm_rcv_ready(kcm);
+diff --git a/net/mctp/test/route-test.c b/net/mctp/test/route-test.c
+index 77e5dd4222580..8551dab1d1e69 100644
+--- a/net/mctp/test/route-test.c
++++ b/net/mctp/test/route-test.c
+@@ -366,7 +366,7 @@ static void mctp_test_route_input_sk(struct kunit *test)
+
+ skb2 = skb_recv_datagram(sock->sk, MSG_DONTWAIT, &rc);
+ KUNIT_EXPECT_NOT_ERR_OR_NULL(test, skb2);
+- KUNIT_EXPECT_EQ(test, skb->len, 1);
++ KUNIT_EXPECT_EQ(test, skb2->len, 1);
+
+ skb_free_datagram(sock->sk, skb2);
+
+diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c
+index 3ae46b545d2c2..2d3efb405437d 100644
+--- a/net/mptcp/diag.c
++++ b/net/mptcp/diag.c
+@@ -94,7 +94,7 @@ static size_t subflow_get_info_size(const struct sock *sk)
+ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_RELWRITE_SEQ */
+ nla_total_size_64bit(8) + /* MPTCP_SUBFLOW_ATTR_MAP_SEQ */
+ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_MAP_SFSEQ */
+- nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
++ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_SSN_OFFSET */
+ nla_total_size(2) + /* MPTCP_SUBFLOW_ATTR_MAP_DATALEN */
+ nla_total_size(4) + /* MPTCP_SUBFLOW_ATTR_FLAGS */
+ nla_total_size(1) + /* MPTCP_SUBFLOW_ATTR_ID_REM */
+diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
+index 23bb89c94e90d..3e6e0f5510bb1 100644
+--- a/net/mptcp/pm.c
++++ b/net/mptcp/pm.c
+@@ -60,16 +60,6 @@ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_
+ return 0;
+ }
+
+-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list)
+-{
+- pr_debug("msk=%p, rm_list_nr=%d", msk, rm_list->nr);
+-
+- spin_lock_bh(&msk->pm.lock);
+- mptcp_pm_nl_rm_subflow_received(msk, rm_list);
+- spin_unlock_bh(&msk->pm.lock);
+- return 0;
+-}
+-
+ /* path manager event handlers */
+
+ void mptcp_pm_new_connection(struct mptcp_sock *msk, const struct sock *ssk, int server_side)
+@@ -444,9 +434,6 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id
+ *flags = 0;
+ *ifindex = 0;
+
+- if (!id)
+- return 0;
+-
+ if (mptcp_pm_is_userspace(msk))
+ return mptcp_userspace_pm_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
+ return mptcp_pm_nl_get_flags_and_ifindex_by_id(msk, id, flags, ifindex);
+diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
+index 4cae2aa7be5cb..3e4ad801786f2 100644
+--- a/net/mptcp/pm_netlink.c
++++ b/net/mptcp/pm_netlink.c
+@@ -143,11 +143,13 @@ static bool lookup_subflow_by_daddr(const struct list_head *list,
+ return false;
+ }
+
+-static struct mptcp_pm_addr_entry *
++static bool
+ select_local_address(const struct pm_nl_pernet *pernet,
+- const struct mptcp_sock *msk)
++ const struct mptcp_sock *msk,
++ struct mptcp_pm_addr_entry *new_entry)
+ {
+- struct mptcp_pm_addr_entry *entry, *ret = NULL;
++ struct mptcp_pm_addr_entry *entry;
++ bool found = false;
+
+ msk_owned_by_me(msk);
+
+@@ -159,17 +161,21 @@ select_local_address(const struct pm_nl_pernet *pernet,
+ if (!test_bit(entry->addr.id, msk->pm.id_avail_bitmap))
+ continue;
+
+- ret = entry;
++ *new_entry = *entry;
++ found = true;
+ break;
+ }
+ rcu_read_unlock();
+- return ret;
++
++ return found;
+ }
+
+-static struct mptcp_pm_addr_entry *
+-select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
++static bool
++select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk,
++ struct mptcp_pm_addr_entry *new_entry)
+ {
+- struct mptcp_pm_addr_entry *entry, *ret = NULL;
++ struct mptcp_pm_addr_entry *entry;
++ bool found = false;
+
+ rcu_read_lock();
+ /* do not keep any additional per socket state, just signal
+@@ -184,11 +190,13 @@ select_signal_address(struct pm_nl_pernet *pernet, const struct mptcp_sock *msk)
+ if (!(entry->flags & MPTCP_PM_ADDR_FLAG_SIGNAL))
+ continue;
+
+- ret = entry;
++ *new_entry = *entry;
++ found = true;
+ break;
+ }
+ rcu_read_unlock();
+- return ret;
++
++ return found;
+ }
+
+ unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk)
+@@ -512,9 +520,10 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
+
+ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+ {
+- struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL;
+ struct sock *sk = (struct sock *)msk;
++ struct mptcp_pm_addr_entry local;
+ unsigned int add_addr_signal_max;
++ bool signal_and_subflow = false;
+ unsigned int local_addr_max;
+ struct pm_nl_pernet *pernet;
+ unsigned int subflows_max;
+@@ -565,23 +574,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+ if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
+ return;
+
+- local = select_signal_address(pernet, msk);
+- if (!local)
++ if (!select_signal_address(pernet, msk, &local))
+ goto subflow;
+
+ /* If the alloc fails, we are on memory pressure, not worth
+ * continuing, and trying to create subflows.
+ */
+- if (!mptcp_pm_alloc_anno_list(msk, &local->addr))
++ if (!mptcp_pm_alloc_anno_list(msk, &local.addr))
+ return;
+
+- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
++ __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
+ msk->pm.add_addr_signaled++;
+- mptcp_pm_announce_addr(msk, &local->addr, false);
++ mptcp_pm_announce_addr(msk, &local.addr, false);
+ mptcp_pm_nl_addr_send_ack(msk);
+
+- if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
+- signal_and_subflow = local;
++ if (local.flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
++ signal_and_subflow = true;
+ }
+
+ subflow:
+@@ -592,26 +600,22 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+ bool fullmesh;
+ int i, nr;
+
+- if (signal_and_subflow) {
+- local = signal_and_subflow;
+- signal_and_subflow = NULL;
+- } else {
+- local = select_local_address(pernet, msk);
+- if (!local)
+- break;
+- }
++ if (signal_and_subflow)
++ signal_and_subflow = false;
++ else if (!select_local_address(pernet, msk, &local))
++ break;
+
+- fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
++ fullmesh = !!(local.flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+
+ msk->pm.local_addr_used++;
+- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+- nr = fill_remote_addresses_vec(msk, &local->addr, fullmesh, addrs);
++ __clear_bit(local.addr.id, msk->pm.id_avail_bitmap);
++ nr = fill_remote_addresses_vec(msk, &local.addr, fullmesh, addrs);
+ if (nr == 0)
+ continue;
+
+ spin_unlock_bh(&msk->pm.lock);
+ for (i = 0; i < nr; i++)
+- __mptcp_subflow_connect(sk, &local->addr, &addrs[i]);
++ __mptcp_subflow_connect(sk, &local.addr, &addrs[i]);
+ spin_lock_bh(&msk->pm.lock);
+ }
+ mptcp_pm_nl_check_work_pending(msk);
+@@ -636,6 +640,7 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
+ {
+ struct sock *sk = (struct sock *)msk;
+ struct mptcp_pm_addr_entry *entry;
++ struct mptcp_addr_info mpc_addr;
+ struct pm_nl_pernet *pernet;
+ unsigned int subflows_max;
+ int i = 0;
+@@ -643,6 +648,8 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
+ pernet = pm_nl_get_pernet_from_msk(msk);
+ subflows_max = mptcp_pm_get_subflows_max(msk);
+
++ mptcp_local_address((struct sock_common *)msk, &mpc_addr);
++
+ rcu_read_lock();
+ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
+ if (!(entry->flags & MPTCP_PM_ADDR_FLAG_FULLMESH))
+@@ -653,7 +660,13 @@ static unsigned int fill_local_addresses_vec(struct mptcp_sock *msk,
+
+ if (msk->pm.subflows < subflows_max) {
+ msk->pm.subflows++;
+- addrs[i++] = entry->addr;
++ addrs[i] = entry->addr;
++
++ /* Special case for ID0: set the correct ID */
++ if (mptcp_addresses_equal(&entry->addr, &mpc_addr, entry->addr.port))
++ addrs[i].id = 0;
++
++ i++;
+ }
+ }
+ rcu_read_unlock();
+@@ -829,25 +842,27 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk,
+ mptcp_close_ssk(sk, ssk, subflow);
+ spin_lock_bh(&msk->pm.lock);
+
+- removed = true;
++ removed |= subflow->request_join;
+ if (rm_type == MPTCP_MIB_RMSUBFLOW)
+ __MPTCP_INC_STATS(sock_net(sk), rm_type);
+ }
+- if (rm_type == MPTCP_MIB_RMSUBFLOW)
+- __set_bit(rm_id ? rm_id : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap);
+- else if (rm_type == MPTCP_MIB_RMADDR)
++
++ if (rm_type == MPTCP_MIB_RMADDR)
+ __MPTCP_INC_STATS(sock_net(sk), rm_type);
++
+ if (!removed)
+ continue;
+
+ if (!mptcp_pm_is_kernel(msk))
+ continue;
+
+- if (rm_type == MPTCP_MIB_RMADDR) {
+- msk->pm.add_addr_accepted--;
+- WRITE_ONCE(msk->pm.accept_addr, true);
+- } else if (rm_type == MPTCP_MIB_RMSUBFLOW) {
+- msk->pm.local_addr_used--;
++ if (rm_type == MPTCP_MIB_RMADDR && rm_id &&
++ !WARN_ON_ONCE(msk->pm.add_addr_accepted == 0)) {
++ /* Note: if the subflow has been closed before, this
++ * add_addr_accepted counter will not be decremented.
++ */
++ if (--msk->pm.add_addr_accepted < mptcp_pm_get_add_addr_accept_max(msk))
++ WRITE_ONCE(msk->pm.accept_addr, true);
+ }
+ }
+ }
+@@ -857,8 +872,8 @@ static void mptcp_pm_nl_rm_addr_received(struct mptcp_sock *msk)
+ mptcp_pm_nl_rm_addr_or_subflow(msk, &msk->pm.rm_list_rx, MPTCP_MIB_RMADDR);
+ }
+
+-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
+- const struct mptcp_rm_list *rm_list)
++static void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
++ const struct mptcp_rm_list *rm_list)
+ {
+ mptcp_pm_nl_rm_addr_or_subflow(msk, rm_list, MPTCP_MIB_RMSUBFLOW);
+ }
+@@ -1393,6 +1408,10 @@ int mptcp_pm_nl_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int
+ struct sock *sk = (struct sock *)msk;
+ struct net *net = sock_net(sk);
+
++ /* No entries with ID 0 */
++ if (id == 0)
++ return 0;
++
+ rcu_read_lock();
+ entry = __lookup_addr_by_id(pm_nl_get_pernet(net), id);
+ if (entry) {
+@@ -1431,13 +1450,24 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+ ret = remove_anno_list_by_saddr(msk, addr);
+ if (ret || force) {
+ spin_lock_bh(&msk->pm.lock);
+- msk->pm.add_addr_signaled -= ret;
++ if (ret) {
++ __set_bit(addr->id, msk->pm.id_avail_bitmap);
++ msk->pm.add_addr_signaled--;
++ }
+ mptcp_pm_remove_addr(msk, &list);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+ return ret;
+ }
+
++static void __mark_subflow_endp_available(struct mptcp_sock *msk, u8 id)
++{
++ /* If it was marked as used, and not ID 0, decrement local_addr_used */
++ if (!__test_and_set_bit(id ? : msk->mpc_endpoint_id, msk->pm.id_avail_bitmap) &&
++ id && !WARN_ON_ONCE(msk->pm.local_addr_used == 0))
++ msk->pm.local_addr_used--;
++}
++
+ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+ const struct mptcp_pm_addr_entry *entry)
+ {
+@@ -1466,8 +1496,19 @@ static int mptcp_nl_remove_subflow_and_signal_addr(struct net *net,
+ remove_subflow = lookup_subflow_by_saddr(&msk->conn_list, addr);
+ mptcp_pm_remove_anno_addr(msk, addr, remove_subflow &&
+ !(entry->flags & MPTCP_PM_ADDR_FLAG_IMPLICIT));
+- if (remove_subflow)
+- mptcp_pm_remove_subflow(msk, &list);
++
++ if (remove_subflow) {
++ spin_lock_bh(&msk->pm.lock);
++ mptcp_pm_nl_rm_subflow_received(msk, &list);
++ spin_unlock_bh(&msk->pm.lock);
++ }
++
++ if (entry->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW) {
++ spin_lock_bh(&msk->pm.lock);
++ __mark_subflow_endp_available(msk, list.ids[0]);
++ spin_unlock_bh(&msk->pm.lock);
++ }
++
+ release_sock(sk);
+
+ next:
+@@ -1502,6 +1543,7 @@ static int mptcp_nl_remove_id_zero_address(struct net *net,
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_pm_remove_addr(msk, &list);
+ mptcp_pm_nl_rm_subflow_received(msk, &list);
++ __mark_subflow_endp_available(msk, 0);
+ spin_unlock_bh(&msk->pm.lock);
+ release_sock(sk);
+
+@@ -1605,14 +1647,17 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
+ alist.ids[alist.nr++] = entry->addr.id;
+ }
+
++ spin_lock_bh(&msk->pm.lock);
+ if (alist.nr) {
+- spin_lock_bh(&msk->pm.lock);
+ msk->pm.add_addr_signaled -= alist.nr;
+ mptcp_pm_remove_addr(msk, &alist);
+- spin_unlock_bh(&msk->pm.lock);
+ }
+ if (slist.nr)
+- mptcp_pm_remove_subflow(msk, &slist);
++ mptcp_pm_nl_rm_subflow_received(msk, &slist);
++ /* Reset counters: maybe some subflows have been removed before */
++ bitmap_fill(msk->pm.id_avail_bitmap, MPTCP_PM_MAX_ADDR_ID + 1);
++ msk->pm.local_addr_used = 0;
++ spin_unlock_bh(&msk->pm.lock);
+ }
+
+ static void mptcp_nl_remove_addrs_list(struct net *net,
+@@ -1900,6 +1945,7 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk,
+
+ spin_lock_bh(&msk->pm.lock);
+ mptcp_pm_nl_rm_subflow_received(msk, &list);
++ __mark_subflow_endp_available(msk, list.ids[0]);
+ mptcp_pm_create_subflow_or_signal_addr(msk);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
+index 8357046732f71..c7c846805c4e1 100644
+--- a/net/mptcp/protocol.h
++++ b/net/mptcp/protocol.h
+@@ -1021,7 +1021,6 @@ int mptcp_pm_announce_addr(struct mptcp_sock *msk,
+ const struct mptcp_addr_info *addr,
+ bool echo);
+ int mptcp_pm_remove_addr(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
+-int mptcp_pm_remove_subflow(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list);
+ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list);
+
+ void mptcp_free_local_addr_list(struct mptcp_sock *msk);
+@@ -1128,8 +1127,6 @@ static inline u8 subflow_get_local_id(const struct mptcp_subflow_context *subflo
+
+ void __init mptcp_pm_nl_init(void);
+ void mptcp_pm_nl_work(struct mptcp_sock *msk);
+-void mptcp_pm_nl_rm_subflow_received(struct mptcp_sock *msk,
+- const struct mptcp_rm_list *rm_list);
+ unsigned int mptcp_pm_get_add_addr_signal_max(const struct mptcp_sock *msk);
+ unsigned int mptcp_pm_get_add_addr_accept_max(const struct mptcp_sock *msk);
+ unsigned int mptcp_pm_get_subflows_max(const struct mptcp_sock *msk);
+diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c
+index 6eef15648b7b0..b0f1991719324 100644
+--- a/net/netfilter/nf_flow_table_inet.c
++++ b/net/netfilter/nf_flow_table_inet.c
+@@ -17,6 +17,9 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb,
+
+ switch (skb->protocol) {
+ case htons(ETH_P_8021Q):
++ if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth)))
++ return NF_ACCEPT;
++
+ veth = (struct vlan_ethhdr *)skb_mac_header(skb);
+ proto = veth->h_vlan_encapsulated_proto;
+ break;
+diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c
+index c2c005234dcd3..98edcaa37b38d 100644
+--- a/net/netfilter/nf_flow_table_ip.c
++++ b/net/netfilter/nf_flow_table_ip.c
+@@ -281,6 +281,9 @@ static bool nf_flow_skb_encap_protocol(struct sk_buff *skb, __be16 proto,
+
+ switch (skb->protocol) {
+ case htons(ETH_P_8021Q):
++ if (!pskb_may_pull(skb, skb_mac_offset(skb) + sizeof(*veth)))
++ return false;
++
+ veth = (struct vlan_ethhdr *)skb_mac_header(skb);
+ if (veth->h_vlan_encapsulated_proto == proto) {
+ *offset += VLAN_HLEN;
+diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c
+index a010b25076ca0..3d46372b538e5 100644
+--- a/net/netfilter/nf_flow_table_offload.c
++++ b/net/netfilter/nf_flow_table_offload.c
+@@ -841,8 +841,8 @@ static int nf_flow_offload_tuple(struct nf_flowtable *flowtable,
+ struct list_head *block_cb_list)
+ {
+ struct flow_cls_offload cls_flow = {};
++ struct netlink_ext_ack extack = {};
+ struct flow_block_cb *block_cb;
+- struct netlink_ext_ack extack;
+ __be16 proto = ETH_P_ALL;
+ int err, i = 0;
+
+diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c
+index 91cc3a81ba8f1..41d7faeb101cf 100644
+--- a/net/netfilter/nf_tables_api.c
++++ b/net/netfilter/nf_tables_api.c
+@@ -7977,6 +7977,19 @@ static int nf_tables_dump_obj(struct sk_buff *skb, struct netlink_callback *cb)
+ return skb->len;
+ }
+
++static int nf_tables_dumpreset_obj(struct sk_buff *skb,
++ struct netlink_callback *cb)
++{
++ struct nftables_pernet *nft_net = nft_pernet(sock_net(skb->sk));
++ int ret;
++
++ mutex_lock(&nft_net->commit_mutex);
++ ret = nf_tables_dump_obj(skb, cb);
++ mutex_unlock(&nft_net->commit_mutex);
++
++ return ret;
++}
++
+ static int nf_tables_dump_obj_start(struct netlink_callback *cb)
+ {
+ struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
+@@ -7993,12 +8006,18 @@ static int nf_tables_dump_obj_start(struct netlink_callback *cb)
+ if (nla[NFTA_OBJ_TYPE])
+ ctx->type = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
+
+- if (NFNL_MSG_TYPE(cb->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
+- ctx->reset = true;
+-
+ return 0;
+ }
+
++static int nf_tables_dumpreset_obj_start(struct netlink_callback *cb)
++{
++ struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
++
++ ctx->reset = true;
++
++ return nf_tables_dump_obj_start(cb);
++}
++
+ static int nf_tables_dump_obj_done(struct netlink_callback *cb)
+ {
+ struct nft_obj_dump_ctx *ctx = (void *)cb->ctx;
+@@ -8009,8 +8028,9 @@ static int nf_tables_dump_obj_done(struct netlink_callback *cb)
+ }
+
+ /* called with rcu_read_lock held */
+-static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
+- const struct nlattr * const nla[])
++static struct sk_buff *
++nf_tables_getobj_single(u32 portid, const struct nfnl_info *info,
++ const struct nlattr * const nla[], bool reset)
+ {
+ struct netlink_ext_ack *extack = info->extack;
+ u8 genmask = nft_genmask_cur(info->net);
+@@ -8019,72 +8039,109 @@ static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
+ struct net *net = info->net;
+ struct nft_object *obj;
+ struct sk_buff *skb2;
+- bool reset = false;
+ u32 objtype;
+ int err;
+
+- if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
+- struct netlink_dump_control c = {
+- .start = nf_tables_dump_obj_start,
+- .dump = nf_tables_dump_obj,
+- .done = nf_tables_dump_obj_done,
+- .module = THIS_MODULE,
+- .data = (void *)nla,
+- };
+-
+- return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+- }
+-
+ if (!nla[NFTA_OBJ_NAME] ||
+ !nla[NFTA_OBJ_TYPE])
+- return -EINVAL;
++ return ERR_PTR(-EINVAL);
+
+ table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask, 0);
+ if (IS_ERR(table)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]);
+- return PTR_ERR(table);
++ return ERR_CAST(table);
+ }
+
+ objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE]));
+ obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask);
+ if (IS_ERR(obj)) {
+ NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]);
+- return PTR_ERR(obj);
++ return ERR_CAST(obj);
+ }
+
+ skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_ATOMIC);
+ if (!skb2)
+- return -ENOMEM;
++ return ERR_PTR(-ENOMEM);
+
+- if (NFNL_MSG_TYPE(info->nlh->nlmsg_type) == NFT_MSG_GETOBJ_RESET)
+- reset = true;
++ err = nf_tables_fill_obj_info(skb2, net, portid,
++ info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
++ family, table, obj, reset);
++ if (err < 0) {
++ kfree_skb(skb2);
++ return ERR_PTR(err);
++ }
+
+- if (reset) {
+- const struct nftables_pernet *nft_net;
+- char *buf;
++ return skb2;
++}
+
+- nft_net = nft_pernet(net);
+- buf = kasprintf(GFP_ATOMIC, "%s:%u", table->name, nft_net->base_seq);
++static int nf_tables_getobj(struct sk_buff *skb, const struct nfnl_info *info,
++ const struct nlattr * const nla[])
++{
++ u32 portid = NETLINK_CB(skb).portid;
++ struct sk_buff *skb2;
+
+- audit_log_nfcfg(buf,
+- family,
+- 1,
+- AUDIT_NFT_OP_OBJ_RESET,
+- GFP_ATOMIC);
+- kfree(buf);
++ if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
++ struct netlink_dump_control c = {
++ .start = nf_tables_dump_obj_start,
++ .dump = nf_tables_dump_obj,
++ .done = nf_tables_dump_obj_done,
++ .module = THIS_MODULE,
++ .data = (void *)nla,
++ };
++
++ return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
+ }
+
+- err = nf_tables_fill_obj_info(skb2, net, NETLINK_CB(skb).portid,
+- info->nlh->nlmsg_seq, NFT_MSG_NEWOBJ, 0,
+- family, table, obj, reset);
+- if (err < 0)
+- goto err_fill_obj_info;
++ skb2 = nf_tables_getobj_single(portid, info, nla, false);
++ if (IS_ERR(skb2))
++ return PTR_ERR(skb2);
+
+- return nfnetlink_unicast(skb2, net, NETLINK_CB(skb).portid);
++ return nfnetlink_unicast(skb2, info->net, portid);
++}
+
+-err_fill_obj_info:
+- kfree_skb(skb2);
+- return err;
++static int nf_tables_getobj_reset(struct sk_buff *skb,
++ const struct nfnl_info *info,
++ const struct nlattr * const nla[])
++{
++ struct nftables_pernet *nft_net = nft_pernet(info->net);
++ u32 portid = NETLINK_CB(skb).portid;
++ struct net *net = info->net;
++ struct sk_buff *skb2;
++ char *buf;
++
++ if (info->nlh->nlmsg_flags & NLM_F_DUMP) {
++ struct netlink_dump_control c = {
++ .start = nf_tables_dumpreset_obj_start,
++ .dump = nf_tables_dumpreset_obj,
++ .done = nf_tables_dump_obj_done,
++ .module = THIS_MODULE,
++ .data = (void *)nla,
++ };
++
++ return nft_netlink_dump_start_rcu(info->sk, skb, info->nlh, &c);
++ }
++
++ if (!try_module_get(THIS_MODULE))
++ return -EINVAL;
++ rcu_read_unlock();
++ mutex_lock(&nft_net->commit_mutex);
++ skb2 = nf_tables_getobj_single(portid, info, nla, true);
++ mutex_unlock(&nft_net->commit_mutex);
++ rcu_read_lock();
++ module_put(THIS_MODULE);
++
++ if (IS_ERR(skb2))
++ return PTR_ERR(skb2);
++
++ buf = kasprintf(GFP_ATOMIC, "%.*s:%u",
++ nla_len(nla[NFTA_OBJ_TABLE]),
++ (char *)nla_data(nla[NFTA_OBJ_TABLE]),
++ nft_net->base_seq);
++ audit_log_nfcfg(buf, info->nfmsg->nfgen_family, 1,
++ AUDIT_NFT_OP_OBJ_RESET, GFP_ATOMIC);
++ kfree(buf);
++
++ return nfnetlink_unicast(skb2, net, portid);
+ }
+
+ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj)
+@@ -9367,7 +9424,7 @@ static const struct nfnl_callback nf_tables_cb[NFT_MSG_MAX] = {
+ .policy = nft_obj_policy,
+ },
+ [NFT_MSG_GETOBJ_RESET] = {
+- .call = nf_tables_getobj,
++ .call = nf_tables_getobj_reset,
+ .type = NFNL_CB_RCU,
+ .attr_count = NFTA_OBJ_MAX,
+ .policy = nft_obj_policy,
+diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c
+index 4abf660c7baff..932b3ddb34f13 100644
+--- a/net/netfilter/nfnetlink.c
++++ b/net/netfilter/nfnetlink.c
+@@ -427,8 +427,10 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
+
+ nfnl_unlock(subsys_id);
+
+- if (nlh->nlmsg_flags & NLM_F_ACK)
++ if (nlh->nlmsg_flags & NLM_F_ACK) {
++ memset(&extack, 0, sizeof(extack));
+ nfnl_err_add(&err_list, nlh, 0, &extack);
++ }
+
+ while (skb->len >= nlmsg_total_size(0)) {
+ int msglen, type;
+@@ -577,6 +579,7 @@ static void nfnetlink_rcv_batch(struct sk_buff *skb, struct nlmsghdr *nlh,
+ ss->abort(net, oskb, NFNL_ABORT_NONE);
+ netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL);
+ } else if (nlh->nlmsg_flags & NLM_F_ACK) {
++ memset(&extack, 0, sizeof(extack));
+ nfnl_err_add(&err_list, nlh, 0, &extack);
+ }
+ } else {
+diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c
+index 55e28e1da66ec..e0716da256bf5 100644
+--- a/net/netfilter/nfnetlink_queue.c
++++ b/net/netfilter/nfnetlink_queue.c
+@@ -820,10 +820,41 @@ static bool nf_ct_drop_unconfirmed(const struct nf_queue_entry *entry)
+ {
+ #if IS_ENABLED(CONFIG_NF_CONNTRACK)
+ static const unsigned long flags = IPS_CONFIRMED | IPS_DYING;
+- const struct nf_conn *ct = (void *)skb_nfct(entry->skb);
++ struct nf_conn *ct = (void *)skb_nfct(entry->skb);
++ unsigned long status;
++ unsigned int use;
+
+- if (ct && ((ct->status & flags) == IPS_DYING))
++ if (!ct)
++ return false;
++
++ status = READ_ONCE(ct->status);
++ if ((status & flags) == IPS_DYING)
+ return true;
++
++ if (status & IPS_CONFIRMED)
++ return false;
++
++ /* in some cases skb_clone() can occur after initial conntrack
++ * pickup, but conntrack assumes exclusive skb->_nfct ownership for
++ * unconfirmed entries.
++ *
++ * This happens for br_netfilter and with ip multicast routing.
++ * We can't be solved with serialization here because one clone could
++ * have been queued for local delivery.
++ */
++ use = refcount_read(&ct->ct_general.use);
++ if (likely(use == 1))
++ return false;
++
++ /* Can't decrement further? Exclusive ownership. */
++ if (!refcount_dec_not_one(&ct->ct_general.use))
++ return false;
++
++ skb_set_nfct(entry->skb, 0);
++ /* No nf_ct_put(): we already decremented .use and it cannot
++ * drop down to 0.
++ */
++ return true;
+ #endif
+ return false;
+ }
+diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c
+index 291ed2026367e..eab0dc66bee6b 100644
+--- a/net/netfilter/nft_counter.c
++++ b/net/netfilter/nft_counter.c
+@@ -107,11 +107,16 @@ static void nft_counter_reset(struct nft_counter_percpu_priv *priv,
+ struct nft_counter *total)
+ {
+ struct nft_counter *this_cpu;
++ seqcount_t *myseq;
+
+ local_bh_disable();
+ this_cpu = this_cpu_ptr(priv->counter);
++ myseq = this_cpu_ptr(&nft_counter_seq);
++
++ write_seqcount_begin(myseq);
+ this_cpu->packets -= total->packets;
+ this_cpu->bytes -= total->bytes;
++ write_seqcount_end(myseq);
+ local_bh_enable();
+ }
+
+@@ -265,7 +270,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr,
+ struct nft_counter *this_cpu;
+ seqcount_t *myseq;
+
+- preempt_disable();
++ local_bh_disable();
+ this_cpu = this_cpu_ptr(priv->counter);
+ myseq = this_cpu_ptr(&nft_counter_seq);
+
+@@ -273,7 +278,7 @@ static void nft_counter_offload_stats(struct nft_expr *expr,
+ this_cpu->packets += stats->pkts;
+ this_cpu->bytes += stats->bytes;
+ write_seqcount_end(myseq);
+- preempt_enable();
++ local_bh_enable();
+ }
+
+ void nft_counter_init_seqcount(void)
+diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c
+index 99d72543abd3a..78d9961fcd446 100644
+--- a/net/openvswitch/datapath.c
++++ b/net/openvswitch/datapath.c
+@@ -2706,7 +2706,7 @@ static struct pernet_operations ovs_net_ops = {
+ };
+
+ static const char * const ovs_drop_reasons[] = {
+-#define S(x) (#x),
++#define S(x) [(x) & ~SKB_DROP_REASON_SUBSYS_MASK] = (#x),
+ OVS_DROP_REASONS(S)
+ #undef S
+ };
+diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c
+index edc72962ae63a..0f8d581438c39 100644
+--- a/net/sched/sch_netem.c
++++ b/net/sched/sch_netem.c
+@@ -446,12 +446,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ struct netem_sched_data *q = qdisc_priv(sch);
+ /* We don't fill cb now as skb_unshare() may invalidate it */
+ struct netem_skb_cb *cb;
+- struct sk_buff *skb2;
++ struct sk_buff *skb2 = NULL;
+ struct sk_buff *segs = NULL;
+ unsigned int prev_len = qdisc_pkt_len(skb);
+ int count = 1;
+- int rc = NET_XMIT_SUCCESS;
+- int rc_drop = NET_XMIT_DROP;
+
+ /* Do not fool qdisc_drop_all() */
+ skb->prev = NULL;
+@@ -480,19 +478,11 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ skb_orphan_partial(skb);
+
+ /*
+- * If we need to duplicate packet, then re-insert at top of the
+- * qdisc tree, since parent queuer expects that only one
+- * skb will be queued.
++ * If we need to duplicate packet, then clone it before
++ * original is modified.
+ */
+- if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) {
+- struct Qdisc *rootq = qdisc_root_bh(sch);
+- u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
+-
+- q->duplicate = 0;
+- rootq->enqueue(skb2, rootq, to_free);
+- q->duplicate = dupsave;
+- rc_drop = NET_XMIT_SUCCESS;
+- }
++ if (count > 1)
++ skb2 = skb_clone(skb, GFP_ATOMIC);
+
+ /*
+ * Randomized packet corruption.
+@@ -504,7 +494,8 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ if (skb_is_gso(skb)) {
+ skb = netem_segment(skb, sch, to_free);
+ if (!skb)
+- return rc_drop;
++ goto finish_segs;
++
+ segs = skb->next;
+ skb_mark_not_on_list(skb);
+ qdisc_skb_cb(skb)->pkt_len = skb->len;
+@@ -530,7 +521,24 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ /* re-link segs, so that qdisc_drop_all() frees them all */
+ skb->next = segs;
+ qdisc_drop_all(skb, sch, to_free);
+- return rc_drop;
++ if (skb2)
++ __qdisc_drop(skb2, to_free);
++ return NET_XMIT_DROP;
++ }
++
++ /*
++ * If doing duplication then re-insert at top of the
++ * qdisc tree, since parent queuer expects that only one
++ * skb will be queued.
++ */
++ if (skb2) {
++ struct Qdisc *rootq = qdisc_root_bh(sch);
++ u32 dupsave = q->duplicate; /* prevent duplicating a dup... */
++
++ q->duplicate = 0;
++ rootq->enqueue(skb2, rootq, to_free);
++ q->duplicate = dupsave;
++ skb2 = NULL;
+ }
+
+ qdisc_qstats_backlog_inc(sch, skb);
+@@ -601,9 +609,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch,
+ }
+
+ finish_segs:
++ if (skb2)
++ __qdisc_drop(skb2, to_free);
++
+ if (segs) {
+ unsigned int len, last_len;
+- int nb;
++ int rc, nb;
+
+ len = skb ? skb->len : 0;
+ nb = skb ? 1 : 0;
+diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c
+index 4b040285aa78c..0ff9b2dd86bac 100644
+--- a/net/vmw_vsock/af_vsock.c
++++ b/net/vmw_vsock/af_vsock.c
+@@ -1270,25 +1270,28 @@ static int vsock_dgram_connect(struct socket *sock,
+ return err;
+ }
+
++int __vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
++ size_t len, int flags)
++{
++ struct sock *sk = sock->sk;
++ struct vsock_sock *vsk = vsock_sk(sk);
++
++ return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
++}
++
+ int vsock_dgram_recvmsg(struct socket *sock, struct msghdr *msg,
+ size_t len, int flags)
+ {
+ #ifdef CONFIG_BPF_SYSCALL
++ struct sock *sk = sock->sk;
+ const struct proto *prot;
+-#endif
+- struct vsock_sock *vsk;
+- struct sock *sk;
+
+- sk = sock->sk;
+- vsk = vsock_sk(sk);
+-
+-#ifdef CONFIG_BPF_SYSCALL
+ prot = READ_ONCE(sk->sk_prot);
+ if (prot != &vsock_proto)
+ return prot->recvmsg(sk, msg, len, flags, NULL);
+ #endif
+
+- return vsk->transport->dgram_dequeue(vsk, msg, len, flags);
++ return __vsock_dgram_recvmsg(sock, msg, len, flags);
+ }
+ EXPORT_SYMBOL_GPL(vsock_dgram_recvmsg);
+
+@@ -2174,15 +2177,12 @@ static int __vsock_seqpacket_recvmsg(struct sock *sk, struct msghdr *msg,
+ }
+
+ int
+-vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+- int flags)
++__vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
++ int flags)
+ {
+ struct sock *sk;
+ struct vsock_sock *vsk;
+ const struct vsock_transport *transport;
+-#ifdef CONFIG_BPF_SYSCALL
+- const struct proto *prot;
+-#endif
+ int err;
+
+ sk = sock->sk;
+@@ -2233,14 +2233,6 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ goto out;
+ }
+
+-#ifdef CONFIG_BPF_SYSCALL
+- prot = READ_ONCE(sk->sk_prot);
+- if (prot != &vsock_proto) {
+- release_sock(sk);
+- return prot->recvmsg(sk, msg, len, flags, NULL);
+- }
+-#endif
+-
+ if (sk->sk_type == SOCK_STREAM)
+ err = __vsock_stream_recvmsg(sk, msg, len, flags);
+ else
+@@ -2250,6 +2242,22 @@ vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ release_sock(sk);
+ return err;
+ }
++
++int
++vsock_connectible_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
++ int flags)
++{
++#ifdef CONFIG_BPF_SYSCALL
++ struct sock *sk = sock->sk;
++ const struct proto *prot;
++
++ prot = READ_ONCE(sk->sk_prot);
++ if (prot != &vsock_proto)
++ return prot->recvmsg(sk, msg, len, flags, NULL);
++#endif
++
++ return __vsock_connectible_recvmsg(sock, msg, len, flags);
++}
+ EXPORT_SYMBOL_GPL(vsock_connectible_recvmsg);
+
+ static int vsock_set_rcvlowat(struct sock *sk, int val)
+diff --git a/net/vmw_vsock/vsock_bpf.c b/net/vmw_vsock/vsock_bpf.c
+index a3c97546ab84a..c42c5cc18f324 100644
+--- a/net/vmw_vsock/vsock_bpf.c
++++ b/net/vmw_vsock/vsock_bpf.c
+@@ -64,9 +64,9 @@ static int __vsock_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int
+ int err;
+
+ if (sk->sk_type == SOCK_STREAM || sk->sk_type == SOCK_SEQPACKET)
+- err = vsock_connectible_recvmsg(sock, msg, len, flags);
++ err = __vsock_connectible_recvmsg(sock, msg, len, flags);
+ else if (sk->sk_type == SOCK_DGRAM)
+- err = vsock_dgram_recvmsg(sock, msg, len, flags);
++ err = __vsock_dgram_recvmsg(sock, msg, len, flags);
+ else
+ err = -EPROTOTYPE;
+
+diff --git a/scripts/kallsyms.c b/scripts/kallsyms.c
+index 47978efe4797c..839d9c49f28ce 100644
+--- a/scripts/kallsyms.c
++++ b/scripts/kallsyms.c
+@@ -5,8 +5,7 @@
+ * This software may be used and distributed according to the terms
+ * of the GNU General Public License, incorporated herein by reference.
+ *
+- * Usage: kallsyms [--all-symbols] [--absolute-percpu]
+- * [--base-relative] [--lto-clang] in.map > out.S
++ * Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S
+ *
+ * Table compression uses all the unused char codes on the symbols and
+ * maps these to the most used substrings (tokens). For instance, it might
+@@ -63,8 +62,6 @@ static struct sym_entry **table;
+ static unsigned int table_size, table_cnt;
+ static int all_symbols;
+ static int absolute_percpu;
+-static int base_relative;
+-static int lto_clang;
+
+ static int token_profit[0x10000];
+
+@@ -75,8 +72,7 @@ static unsigned char best_table_len[256];
+
+ static void usage(void)
+ {
+- fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] "
+- "[--base-relative] [--lto-clang] in.map > out.S\n");
++ fprintf(stderr, "Usage: kallsyms [--all-symbols] [--absolute-percpu] in.map > out.S\n");
+ exit(1);
+ }
+
+@@ -259,12 +255,6 @@ static void shrink_table(void)
+ }
+ }
+ table_cnt = pos;
+-
+- /* When valid symbol is not registered, exit to error */
+- if (!table_cnt) {
+- fprintf(stderr, "No valid symbol.\n");
+- exit(1);
+- }
+ }
+
+ static void read_map(const char *in)
+@@ -352,25 +342,6 @@ static int symbol_absolute(const struct sym_entry *s)
+ return s->percpu_absolute;
+ }
+
+-static void cleanup_symbol_name(char *s)
+-{
+- char *p;
+-
+- /*
+- * ASCII[.] = 2e
+- * ASCII[0-9] = 30,39
+- * ASCII[A-Z] = 41,5a
+- * ASCII[_] = 5f
+- * ASCII[a-z] = 61,7a
+- *
+- * As above, replacing the first '.' in ".llvm." with '\0' does not
+- * affect the main sorting, but it helps us with subsorting.
+- */
+- p = strstr(s, ".llvm.");
+- if (p)
+- *p = '\0';
+-}
+-
+ static int compare_names(const void *a, const void *b)
+ {
+ int ret;
+@@ -497,58 +468,43 @@ static void write_src(void)
+ printf("\t.short\t%d\n", best_idx[i]);
+ printf("\n");
+
+- if (!base_relative)
+- output_label("kallsyms_addresses");
+- else
+- output_label("kallsyms_offsets");
++ output_label("kallsyms_offsets");
+
+ for (i = 0; i < table_cnt; i++) {
+- if (base_relative) {
+- /*
+- * Use the offset relative to the lowest value
+- * encountered of all relative symbols, and emit
+- * non-relocatable fixed offsets that will be fixed
+- * up at runtime.
+- */
++ /*
++ * Use the offset relative to the lowest value
++ * encountered of all relative symbols, and emit
++ * non-relocatable fixed offsets that will be fixed
++ * up at runtime.
++ */
+
+- long long offset;
+- int overflow;
+-
+- if (!absolute_percpu) {
+- offset = table[i]->addr - relative_base;
+- overflow = (offset < 0 || offset > UINT_MAX);
+- } else if (symbol_absolute(table[i])) {
+- offset = table[i]->addr;
+- overflow = (offset < 0 || offset > INT_MAX);
+- } else {
+- offset = relative_base - table[i]->addr - 1;
+- overflow = (offset < INT_MIN || offset >= 0);
+- }
+- if (overflow) {
+- fprintf(stderr, "kallsyms failure: "
+- "%s symbol value %#llx out of range in relative mode\n",
+- symbol_absolute(table[i]) ? "absolute" : "relative",
+- table[i]->addr);
+- exit(EXIT_FAILURE);
+- }
+- printf("\t.long\t%#x /* %s */\n", (int)offset, table[i]->sym);
+- } else if (!symbol_absolute(table[i])) {
+- output_address(table[i]->addr);
++ long long offset;
++ int overflow;
++
++ if (!absolute_percpu) {
++ offset = table[i]->addr - relative_base;
++ overflow = (offset < 0 || offset > UINT_MAX);
++ } else if (symbol_absolute(table[i])) {
++ offset = table[i]->addr;
++ overflow = (offset < 0 || offset > INT_MAX);
+ } else {
+- printf("\tPTR\t%#llx\n", table[i]->addr);
++ offset = relative_base - table[i]->addr - 1;
++ overflow = (offset < INT_MIN || offset >= 0);
++ }
++ if (overflow) {
++ fprintf(stderr, "kallsyms failure: "
++ "%s symbol value %#llx out of range in relative mode\n",
++ symbol_absolute(table[i]) ? "absolute" : "relative",
++ table[i]->addr);
++ exit(EXIT_FAILURE);
+ }
++ printf("\t.long\t%#x /* %s */\n", (int)offset, table[i]->sym);
+ }
+ printf("\n");
+
+- if (base_relative) {
+- output_label("kallsyms_relative_base");
+- output_address(relative_base);
+- printf("\n");
+- }
+-
+- if (lto_clang)
+- for (i = 0; i < table_cnt; i++)
+- cleanup_symbol_name((char *)table[i]->sym);
++ output_label("kallsyms_relative_base");
++ output_address(relative_base);
++ printf("\n");
+
+ sort_symbols_by_name();
+ output_label("kallsyms_seqs_of_names");
+@@ -826,8 +782,6 @@ int main(int argc, char **argv)
+ static const struct option long_options[] = {
+ {"all-symbols", no_argument, &all_symbols, 1},
+ {"absolute-percpu", no_argument, &absolute_percpu, 1},
+- {"base-relative", no_argument, &base_relative, 1},
+- {"lto-clang", no_argument, <o_clang, 1},
+ {},
+ };
+
+@@ -847,8 +801,7 @@ int main(int argc, char **argv)
+ if (absolute_percpu)
+ make_percpus_absolute();
+ sort_symbols();
+- if (base_relative)
+- record_relative_base();
++ record_relative_base();
+ optimize_token_table();
+ write_src();
+
+diff --git a/scripts/link-vmlinux.sh b/scripts/link-vmlinux.sh
+index 518c70b8db507..070a319140e89 100755
+--- a/scripts/link-vmlinux.sh
++++ b/scripts/link-vmlinux.sh
+@@ -45,7 +45,6 @@ info()
+
+ # Link of vmlinux
+ # ${1} - output file
+-# ${2}, ${3}, ... - optional extra .o files
+ vmlinux_link()
+ {
+ local output=${1}
+@@ -90,7 +89,7 @@ vmlinux_link()
+ ldflags="${ldflags} ${wl}--script=${objtree}/${KBUILD_LDS}"
+
+ # The kallsyms linking does not need debug symbols included.
+- if [ "$output" != "${output#.tmp_vmlinux.kallsyms}" ] ; then
++ if [ -n "${strip_debug}" ] ; then
+ ldflags="${ldflags} ${wl}--strip-debug"
+ fi
+
+@@ -101,15 +100,15 @@ vmlinux_link()
+ ${ld} ${ldflags} -o ${output} \
+ ${wl}--whole-archive ${objs} ${wl}--no-whole-archive \
+ ${wl}--start-group ${libs} ${wl}--end-group \
+- $@ ${ldlibs}
++ ${kallsymso} ${btf_vmlinux_bin_o} ${ldlibs}
+ }
+
+ # generate .BTF typeinfo from DWARF debuginfo
+ # ${1} - vmlinux image
+-# ${2} - file to dump raw BTF data into
+ gen_btf()
+ {
+ local pahole_ver
++ local btf_data=${1}.btf.o
+
+ if ! [ -x "$(command -v ${PAHOLE})" ]; then
+ echo >&2 "BTF: ${1}: pahole (${PAHOLE}) is not available"
+@@ -122,18 +121,16 @@ gen_btf()
+ return 1
+ fi
+
+- vmlinux_link ${1}
+-
+- info "BTF" ${2}
++ info BTF "${btf_data}"
+ LLVM_OBJCOPY="${OBJCOPY}" ${PAHOLE} -J ${PAHOLE_FLAGS} ${1}
+
+- # Create ${2} which contains just .BTF section but no symbols. Add
++ # Create ${btf_data} which contains just .BTF section but no symbols. Add
+ # SHF_ALLOC because .BTF will be part of the vmlinux image. --strip-all
+ # deletes all symbols including __start_BTF and __stop_BTF, which will
+ # be redefined in the linker script. Add 2>/dev/null to suppress GNU
+ # objcopy warnings: "empty loadable segment detected at ..."
+ ${OBJCOPY} --only-section=.BTF --set-section-flags .BTF=alloc,readonly \
+- --strip-all ${1} ${2} 2>/dev/null
++ --strip-all ${1} "${btf_data}" 2>/dev/null
+ # Change e_type to ET_REL so that it can be used to link final vmlinux.
+ # GNU ld 2.35+ and lld do not allow an ET_EXEC input.
+ if is_enabled CONFIG_CPU_BIG_ENDIAN; then
+@@ -141,10 +138,12 @@ gen_btf()
+ else
+ et_rel='\1\0'
+ fi
+- printf "${et_rel}" | dd of=${2} conv=notrunc bs=1 seek=16 status=none
++ printf "${et_rel}" | dd of="${btf_data}" conv=notrunc bs=1 seek=16 status=none
++
++ btf_vmlinux_bin_o=${btf_data}
+ }
+
+-# Create ${2} .S file with all symbols from the ${1} object file
++# Create ${2}.o file with all symbols from the ${1} object file
+ kallsyms()
+ {
+ local kallsymopt;
+@@ -157,35 +156,23 @@ kallsyms()
+ kallsymopt="${kallsymopt} --absolute-percpu"
+ fi
+
+- if is_enabled CONFIG_KALLSYMS_BASE_RELATIVE; then
+- kallsymopt="${kallsymopt} --base-relative"
+- fi
++ info KSYMS "${2}.S"
++ scripts/kallsyms ${kallsymopt} "${1}" > "${2}.S"
+
+- if is_enabled CONFIG_LTO_CLANG; then
+- kallsymopt="${kallsymopt} --lto-clang"
+- fi
++ info AS "${2}.o"
++ ${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \
++ ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} -c -o "${2}.o" "${2}.S"
+
+- info KSYMS ${2}
+- scripts/kallsyms ${kallsymopt} ${1} > ${2}
++ kallsymso=${2}.o
+ }
+
+-# Perform one step in kallsyms generation, including temporary linking of
+-# vmlinux.
+-kallsyms_step()
++# Perform kallsyms for the given temporary vmlinux.
++sysmap_and_kallsyms()
+ {
+- kallsymso_prev=${kallsymso}
+- kallsyms_vmlinux=.tmp_vmlinux.kallsyms${1}
+- kallsymso=${kallsyms_vmlinux}.o
+- kallsyms_S=${kallsyms_vmlinux}.S
++ mksysmap "${1}" "${1}.syms"
++ kallsyms "${1}.syms" "${1}.kallsyms"
+
+- vmlinux_link ${kallsyms_vmlinux} "${kallsymso_prev}" ${btf_vmlinux_bin_o}
+- mksysmap ${kallsyms_vmlinux} ${kallsyms_vmlinux}.syms
+- kallsyms ${kallsyms_vmlinux}.syms ${kallsyms_S}
+-
+- info AS ${kallsymso}
+- ${CC} ${NOSTDINC_FLAGS} ${LINUXINCLUDE} ${KBUILD_CPPFLAGS} \
+- ${KBUILD_AFLAGS} ${KBUILD_AFLAGS_KERNEL} \
+- -c -o ${kallsymso} ${kallsyms_S}
++ kallsyms_sysmap=${1}.syms
+ }
+
+ # Create map file with all symbols from ${1}
+@@ -223,26 +210,41 @@ fi
+
+ ${MAKE} -f "${srctree}/scripts/Makefile.build" obj=init init/version-timestamp.o
+
+-btf_vmlinux_bin_o=""
++btf_vmlinux_bin_o=
++kallsymso=
++strip_debug=
++
++if is_enabled CONFIG_KALLSYMS; then
++ truncate -s0 .tmp_vmlinux.kallsyms0.syms
++ kallsyms .tmp_vmlinux.kallsyms0.syms .tmp_vmlinux0.kallsyms
++fi
++
++if is_enabled CONFIG_KALLSYMS || is_enabled CONFIG_DEBUG_INFO_BTF; then
++
++ # The kallsyms linking does not need debug symbols, but the BTF does.
++ if ! is_enabled CONFIG_DEBUG_INFO_BTF; then
++ strip_debug=1
++ fi
++
++ vmlinux_link .tmp_vmlinux1
++fi
++
+ if is_enabled CONFIG_DEBUG_INFO_BTF; then
+- btf_vmlinux_bin_o=.btf.vmlinux.bin.o
+- if ! gen_btf .tmp_vmlinux.btf $btf_vmlinux_bin_o ; then
++ if ! gen_btf .tmp_vmlinux1; then
+ echo >&2 "Failed to generate BTF for vmlinux"
+ echo >&2 "Try to disable CONFIG_DEBUG_INFO_BTF"
+ exit 1
+ fi
+ fi
+
+-kallsymso=""
+-kallsymso_prev=""
+-kallsyms_vmlinux=""
+ if is_enabled CONFIG_KALLSYMS; then
+
+ # kallsyms support
+ # Generate section listing all symbols and add it into vmlinux
+- # It's a three step process:
++ # It's a four step process:
++ # 0) Generate a dummy __kallsyms with empty symbol list.
+ # 1) Link .tmp_vmlinux.kallsyms1 so it has all symbols and sections,
+- # but __kallsyms is empty.
++ # with a dummy __kallsyms.
+ # Running kallsyms on that gives us .tmp_kallsyms1.o with
+ # the right size
+ # 2) Link .tmp_vmlinux.kallsyms2 so it now has a __kallsyms section of
+@@ -261,19 +263,25 @@ if is_enabled CONFIG_KALLSYMS; then
+ # a) Verify that the System.map from vmlinux matches the map from
+ # ${kallsymso}.
+
+- kallsyms_step 1
+- kallsyms_step 2
++ # The kallsyms linking does not need debug symbols included.
++ strip_debug=1
++
++ sysmap_and_kallsyms .tmp_vmlinux1
++ size1=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})
+
+- # step 3
+- size1=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso_prev})
++ vmlinux_link .tmp_vmlinux2
++ sysmap_and_kallsyms .tmp_vmlinux2
+ size2=$(${CONFIG_SHELL} "${srctree}/scripts/file-size.sh" ${kallsymso})
+
+ if [ $size1 -ne $size2 ] || [ -n "${KALLSYMS_EXTRA_PASS}" ]; then
+- kallsyms_step 3
++ vmlinux_link .tmp_vmlinux3
++ sysmap_and_kallsyms .tmp_vmlinux3
+ fi
+ fi
+
+-vmlinux_link vmlinux "${kallsymso}" ${btf_vmlinux_bin_o}
++strip_debug=
++
++vmlinux_link vmlinux
+
+ # fill in BTF IDs
+ if is_enabled CONFIG_DEBUG_INFO_BTF && is_enabled CONFIG_BPF; then
+@@ -293,7 +301,7 @@ fi
+
+ # step a (see comment above)
+ if is_enabled CONFIG_KALLSYMS; then
+- if ! cmp -s System.map ${kallsyms_vmlinux}.syms; then
++ if ! cmp -s System.map "${kallsyms_sysmap}"; then
+ echo >&2 Inconsistent kallsyms data
+ echo >&2 'Try "make KALLSYMS_EXTRA_PASS=1" as a workaround'
+ exit 1
+diff --git a/scripts/rust_is_available.sh b/scripts/rust_is_available.sh
+index 117018946b577..a6fdcf13e0e53 100755
+--- a/scripts/rust_is_available.sh
++++ b/scripts/rust_is_available.sh
+@@ -129,8 +129,12 @@ fi
+ # Check that the Rust bindings generator is suitable.
+ #
+ # Non-stable and distributions' versions may have a version suffix, e.g. `-dev`.
++#
++# The dummy parameter `workaround-for-0.69.0` is required to support 0.69.0
++# (https://github.com/rust-lang/rust-bindgen/pull/2678). It can be removed when
++# the minimum version is upgraded past that (0.69.1 already fixed the issue).
+ rust_bindings_generator_output=$( \
+- LC_ALL=C "$BINDGEN" --version 2>/dev/null
++ LC_ALL=C "$BINDGEN" --version workaround-for-0.69.0 2>/dev/null
+ ) || rust_bindings_generator_code=$?
+ if [ -n "$rust_bindings_generator_code" ]; then
+ echo >&2 "***"
+diff --git a/security/keys/trusted-keys/trusted_dcp.c b/security/keys/trusted-keys/trusted_dcp.c
+index b5f81a05be367..4edc5bbbcda3c 100644
+--- a/security/keys/trusted-keys/trusted_dcp.c
++++ b/security/keys/trusted-keys/trusted_dcp.c
+@@ -186,20 +186,21 @@ static int do_aead_crypto(u8 *in, u8 *out, size_t len, u8 *key, u8 *nonce,
+ return ret;
+ }
+
+-static int decrypt_blob_key(u8 *key)
++static int decrypt_blob_key(u8 *encrypted_key, u8 *plain_key)
+ {
+- return do_dcp_crypto(key, key, false);
++ return do_dcp_crypto(encrypted_key, plain_key, false);
+ }
+
+-static int encrypt_blob_key(u8 *key)
++static int encrypt_blob_key(u8 *plain_key, u8 *encrypted_key)
+ {
+- return do_dcp_crypto(key, key, true);
++ return do_dcp_crypto(plain_key, encrypted_key, true);
+ }
+
+ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob)
+ {
+ struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob;
+ int blen, ret;
++ u8 plain_blob_key[AES_KEYSIZE_128];
+
+ blen = calc_blob_len(p->key_len);
+ if (blen > MAX_BLOB_SIZE)
+@@ -207,30 +208,36 @@ static int trusted_dcp_seal(struct trusted_key_payload *p, char *datablob)
+
+ b->fmt_version = DCP_BLOB_VERSION;
+ get_random_bytes(b->nonce, AES_KEYSIZE_128);
+- get_random_bytes(b->blob_key, AES_KEYSIZE_128);
++ get_random_bytes(plain_blob_key, AES_KEYSIZE_128);
+
+- ret = do_aead_crypto(p->key, b->payload, p->key_len, b->blob_key,
++ ret = do_aead_crypto(p->key, b->payload, p->key_len, plain_blob_key,
+ b->nonce, true);
+ if (ret) {
+ pr_err("Unable to encrypt blob payload: %i\n", ret);
+- return ret;
++ goto out;
+ }
+
+- ret = encrypt_blob_key(b->blob_key);
++ ret = encrypt_blob_key(plain_blob_key, b->blob_key);
+ if (ret) {
+ pr_err("Unable to encrypt blob key: %i\n", ret);
+- return ret;
++ goto out;
+ }
+
+- b->payload_len = get_unaligned_le32(&p->key_len);
++ put_unaligned_le32(p->key_len, &b->payload_len);
+ p->blob_len = blen;
+- return 0;
++ ret = 0;
++
++out:
++ memzero_explicit(plain_blob_key, sizeof(plain_blob_key));
++
++ return ret;
+ }
+
+ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)
+ {
+ struct dcp_blob_fmt *b = (struct dcp_blob_fmt *)p->blob;
+ int blen, ret;
++ u8 plain_blob_key[AES_KEYSIZE_128];
+
+ if (b->fmt_version != DCP_BLOB_VERSION) {
+ pr_err("DCP blob has bad version: %i, expected %i\n",
+@@ -248,14 +255,14 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)
+ goto out;
+ }
+
+- ret = decrypt_blob_key(b->blob_key);
++ ret = decrypt_blob_key(b->blob_key, plain_blob_key);
+ if (ret) {
+ pr_err("Unable to decrypt blob key: %i\n", ret);
+ goto out;
+ }
+
+ ret = do_aead_crypto(b->payload, p->key, p->key_len + DCP_BLOB_AUTHLEN,
+- b->blob_key, b->nonce, false);
++ plain_blob_key, b->nonce, false);
+ if (ret) {
+ pr_err("Unwrap of DCP payload failed: %i\n", ret);
+ goto out;
+@@ -263,6 +270,8 @@ static int trusted_dcp_unseal(struct trusted_key_payload *p, char *datablob)
+
+ ret = 0;
+ out:
++ memzero_explicit(plain_blob_key, sizeof(plain_blob_key));
++
+ return ret;
+ }
+
+diff --git a/security/selinux/avc.c b/security/selinux/avc.c
+index 32eb67fb3e42c..b49c44869dc46 100644
+--- a/security/selinux/avc.c
++++ b/security/selinux/avc.c
+@@ -330,12 +330,12 @@ static int avc_add_xperms_decision(struct avc_node *node,
+ {
+ struct avc_xperms_decision_node *dest_xpd;
+
+- node->ae.xp_node->xp.len++;
+ dest_xpd = avc_xperms_decision_alloc(src->used);
+ if (!dest_xpd)
+ return -ENOMEM;
+ avc_copy_xperms_decision(&dest_xpd->xpd, src);
+ list_add(&dest_xpd->xpd_list, &node->ae.xp_node->xpd_head);
++ node->ae.xp_node->xp.len++;
+ return 0;
+ }
+
+@@ -907,7 +907,11 @@ static int avc_update_node(u32 event, u32 perms, u8 driver, u8 xperm, u32 ssid,
+ node->ae.avd.auditdeny &= ~perms;
+ break;
+ case AVC_CALLBACK_ADD_XPERMS:
+- avc_add_xperms_decision(node, xpd);
++ rc = avc_add_xperms_decision(node, xpd);
++ if (rc) {
++ avc_node_kill(node);
++ goto out_unlock;
++ }
+ break;
+ }
+ avc_node_replace(node, orig);
+diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
+index 55c78c318ccd7..bfa61e005aace 100644
+--- a/security/selinux/hooks.c
++++ b/security/selinux/hooks.c
+@@ -3852,7 +3852,17 @@ static int selinux_file_mprotect(struct vm_area_struct *vma,
+ if (default_noexec &&
+ (prot & PROT_EXEC) && !(vma->vm_flags & VM_EXEC)) {
+ int rc = 0;
+- if (vma_is_initial_heap(vma)) {
++ /*
++ * We don't use the vma_is_initial_heap() helper as it has
++ * a history of problems and is currently broken on systems
++ * where there is no heap, e.g. brk == start_brk. Before
++ * replacing the conditional below with vma_is_initial_heap(),
++ * or something similar, please ensure that the logic is the
++ * same as what we have below or you have tested every possible
++ * corner case you can think to test.
++ */
++ if (vma->vm_start >= vma->vm_mm->start_brk &&
++ vma->vm_end <= vma->vm_mm->brk) {
+ rc = avc_has_perm(sid, sid, SECCLASS_PROCESS,
+ PROCESS__EXECHEAP, NULL);
+ } else if (!vma->vm_file && (vma_is_initial_stack(vma) ||
+diff --git a/sound/core/timer.c b/sound/core/timer.c
+index d104adc75a8b0..71a07c1662f5c 100644
+--- a/sound/core/timer.c
++++ b/sound/core/timer.c
+@@ -547,7 +547,7 @@ static int snd_timer_start1(struct snd_timer_instance *timeri,
+ /* check the actual time for the start tick;
+ * bail out as error if it's way too low (< 100us)
+ */
+- if (start) {
++ if (start && !(timer->hw.flags & SNDRV_TIMER_HW_SLAVE)) {
+ if ((u64)snd_timer_hw_resolution(timer) * ticks < 100000)
+ return -EINVAL;
+ }
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index 3840565ef8b02..c9d76bca99232 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -583,7 +583,6 @@ static void alc_shutup_pins(struct hda_codec *codec)
+ switch (codec->core.vendor_id) {
+ case 0x10ec0236:
+ case 0x10ec0256:
+- case 0x10ec0257:
+ case 0x19e58326:
+ case 0x10ec0283:
+ case 0x10ec0285:
+diff --git a/sound/pci/hda/tas2781_hda_i2c.c b/sound/pci/hda/tas2781_hda_i2c.c
+index fdee6592c502d..9e88d39eac1e2 100644
+--- a/sound/pci/hda/tas2781_hda_i2c.c
++++ b/sound/pci/hda/tas2781_hda_i2c.c
+@@ -2,10 +2,12 @@
+ //
+ // TAS2781 HDA I2C driver
+ //
+-// Copyright 2023 Texas Instruments, Inc.
++// Copyright 2023 - 2024 Texas Instruments, Inc.
+ //
+ // Author: Shenghao Ding <shenghao-ding@ti.com>
++// Current maintainer: Baojun Xu <baojun.xu@ti.com>
+
++#include <asm/unaligned.h>
+ #include <linux/acpi.h>
+ #include <linux/crc8.h>
+ #include <linux/crc32.h>
+@@ -519,20 +521,22 @@ static void tas2781_apply_calib(struct tasdevice_priv *tas_priv)
+ static const unsigned char rgno_array[CALIB_MAX] = {
+ 0x74, 0x0c, 0x14, 0x70, 0x7c,
+ };
+- unsigned char *data;
++ int offset = 0;
+ int i, j, rc;
++ __be32 data;
+
+ for (i = 0; i < tas_priv->ndev; i++) {
+- data = tas_priv->cali_data.data +
+- i * TASDEVICE_SPEAKER_CALIBRATION_SIZE;
+ for (j = 0; j < CALIB_MAX; j++) {
++ data = cpu_to_be32(
++ *(uint32_t *)&tas_priv->cali_data.data[offset]);
+ rc = tasdevice_dev_bulk_write(tas_priv, i,
+ TASDEVICE_REG(0, page_array[j], rgno_array[j]),
+- &(data[4 * j]), 4);
++ (unsigned char *)&data, 4);
+ if (rc < 0)
+ dev_err(tas_priv->dev,
+ "chn %d calib %d bulk_wr err = %d\n",
+ i, j, rc);
++ offset += 4;
+ }
+ }
+ }
+diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
+index f13a8d63a019a..aaa6a515d0f8a 100644
+--- a/sound/usb/quirks-table.h
++++ b/sound/usb/quirks-table.h
+@@ -273,6 +273,7 @@ YAMAHA_DEVICE(0x105a, NULL),
+ YAMAHA_DEVICE(0x105b, NULL),
+ YAMAHA_DEVICE(0x105c, NULL),
+ YAMAHA_DEVICE(0x105d, NULL),
++YAMAHA_DEVICE(0x1718, "P-125"),
+ {
+ USB_DEVICE(0x0499, 0x1503),
+ .driver_info = (unsigned long) & (const struct snd_usb_audio_quirk) {
+diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
+index ea063a14cdd8f..e7b68c67852e9 100644
+--- a/sound/usb/quirks.c
++++ b/sound/usb/quirks.c
+@@ -2221,6 +2221,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
+ QUIRK_FLAG_GENERIC_IMPLICIT_FB),
+ DEVICE_FLG(0x2b53, 0x0031, /* Fiero SC-01 (firmware v1.1.0) */
+ QUIRK_FLAG_GENERIC_IMPLICIT_FB),
++ DEVICE_FLG(0x2d95, 0x8021, /* VIVO USB-C-XE710 HEADSET */
++ QUIRK_FLAG_CTL_MSG_DELAY_1M),
+ DEVICE_FLG(0x30be, 0x0101, /* Schiit Hel */
+ QUIRK_FLAG_IGNORE_CTL_ERROR),
+ DEVICE_FLG(0x413c, 0xa506, /* Dell AE515 sound bar */
+diff --git a/tools/perf/tests/vmlinux-kallsyms.c b/tools/perf/tests/vmlinux-kallsyms.c
+index e30fd55f8e51d..cd3b480d20bd6 100644
+--- a/tools/perf/tests/vmlinux-kallsyms.c
++++ b/tools/perf/tests/vmlinux-kallsyms.c
+@@ -26,7 +26,6 @@ static bool is_ignored_symbol(const char *name, char type)
+ * when --all-symbols is specified so exclude them to get a
+ * stable symbol list.
+ */
+- "kallsyms_addresses",
+ "kallsyms_offsets",
+ "kallsyms_relative_base",
+ "kallsyms_num_syms",
+diff --git a/tools/testing/selftests/bpf/progs/iters.c b/tools/testing/selftests/bpf/progs/iters.c
+index fe65e0952a1e0..179bfe25dbc61 100644
+--- a/tools/testing/selftests/bpf/progs/iters.c
++++ b/tools/testing/selftests/bpf/progs/iters.c
+@@ -1434,4 +1434,58 @@ int iter_arr_with_actual_elem_count(const void *ctx)
+ return sum;
+ }
+
++__u32 upper, select_n, result;
++__u64 global;
++
++static __noinline bool nest_2(char *str)
++{
++ /* some insns (including branch insns) to ensure stacksafe() is triggered
++ * in nest_2(). This way, stacksafe() can compare frame associated with nest_1().
++ */
++ if (str[0] == 't')
++ return true;
++ if (str[1] == 'e')
++ return true;
++ if (str[2] == 's')
++ return true;
++ if (str[3] == 't')
++ return true;
++ return false;
++}
++
++static __noinline bool nest_1(int n)
++{
++ /* case 0: allocate stack, case 1: no allocate stack */
++ switch (n) {
++ case 0: {
++ char comm[16];
++
++ if (bpf_get_current_comm(comm, 16))
++ return false;
++ return nest_2(comm);
++ }
++ case 1:
++ return nest_2((char *)&global);
++ default:
++ return false;
++ }
++}
++
++SEC("raw_tp")
++__success
++int iter_subprog_check_stacksafe(const void *ctx)
++{
++ long i;
++
++ bpf_for(i, 0, upper) {
++ if (!nest_1(select_n)) {
++ result = 1;
++ return 0;
++ }
++ }
++
++ result = 2;
++ return 0;
++}
++
+ char _license[] SEC("license") = "GPL";
+diff --git a/tools/testing/selftests/core/close_range_test.c b/tools/testing/selftests/core/close_range_test.c
+index 991c473e38593..12b4eb9d04347 100644
+--- a/tools/testing/selftests/core/close_range_test.c
++++ b/tools/testing/selftests/core/close_range_test.c
+@@ -589,4 +589,39 @@ TEST(close_range_cloexec_unshare_syzbot)
+ EXPECT_EQ(close(fd3), 0);
+ }
+
++TEST(close_range_bitmap_corruption)
++{
++ pid_t pid;
++ int status;
++ struct __clone_args args = {
++ .flags = CLONE_FILES,
++ .exit_signal = SIGCHLD,
++ };
++
++ /* get the first 128 descriptors open */
++ for (int i = 2; i < 128; i++)
++ EXPECT_GE(dup2(0, i), 0);
++
++ /* get descriptor table shared */
++ pid = sys_clone3(&args, sizeof(args));
++ ASSERT_GE(pid, 0);
++
++ if (pid == 0) {
++ /* unshare and truncate descriptor table down to 64 */
++ if (sys_close_range(64, ~0U, CLOSE_RANGE_UNSHARE))
++ exit(EXIT_FAILURE);
++
++ ASSERT_EQ(fcntl(64, F_GETFD), -1);
++ /* ... and verify that the range 64..127 is not
++ stuck "fully used" according to secondary bitmap */
++ EXPECT_EQ(dup(0), 64)
++ exit(EXIT_FAILURE);
++ exit(EXIT_SUCCESS);
++ }
++
++ EXPECT_EQ(waitpid(pid, &status, 0), pid);
++ EXPECT_EQ(true, WIFEXITED(status));
++ EXPECT_EQ(0, WEXITSTATUS(status));
++}
++
+ TEST_HARNESS_MAIN
+diff --git a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
+index 877cd6df94a10..fe905a7f34b3c 100755
+--- a/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
++++ b/tools/testing/selftests/drivers/net/mlxsw/ethtool_lanes.sh
+@@ -2,6 +2,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+
+ lib_dir=$(dirname $0)/../../../net/forwarding
++ethtool_lib_dir=$(dirname $0)/../hw
+
+ ALL_TESTS="
+ autoneg
+@@ -11,7 +12,7 @@ ALL_TESTS="
+ NUM_NETIFS=2
+ : ${TIMEOUT:=30000} # ms
+ source $lib_dir/lib.sh
+-source $lib_dir/ethtool_lib.sh
++source $ethtool_lib_dir/ethtool_lib.sh
+
+ setup_prepare()
+ {
+diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
+index 478cd26f62fdd..1285b82fbd8a2 100644
+--- a/tools/testing/selftests/mm/Makefile
++++ b/tools/testing/selftests/mm/Makefile
+@@ -51,7 +51,9 @@ TEST_GEN_FILES += madv_populate
+ TEST_GEN_FILES += map_fixed_noreplace
+ TEST_GEN_FILES += map_hugetlb
+ TEST_GEN_FILES += map_populate
++ifneq (,$(filter $(ARCH),arm64 riscv riscv64 x86 x86_64))
+ TEST_GEN_FILES += memfd_secret
++endif
+ TEST_GEN_FILES += migration
+ TEST_GEN_FILES += mkdirty
+ TEST_GEN_FILES += mlock-random-test
+diff --git a/tools/testing/selftests/mm/run_vmtests.sh b/tools/testing/selftests/mm/run_vmtests.sh
+index 3157204b90476..1c7cdfd29fcc8 100755
+--- a/tools/testing/selftests/mm/run_vmtests.sh
++++ b/tools/testing/selftests/mm/run_vmtests.sh
+@@ -367,8 +367,11 @@ CATEGORY="hmm" run_test bash ./test_hmm.sh smoke
+ # MADV_POPULATE_READ and MADV_POPULATE_WRITE tests
+ CATEGORY="madv_populate" run_test ./madv_populate
+
++if [ -x ./memfd_secret ]
++then
+ (echo 0 | sudo tee /proc/sys/kernel/yama/ptrace_scope 2>&1) | tap_prefix
+ CATEGORY="memfd_secret" run_test ./memfd_secret
++fi
+
+ # KSM KSM_MERGE_TIME_HUGE_PAGES test with size of 100
+ CATEGORY="ksm" run_test ./ksm_tests -H -s 100
+diff --git a/tools/testing/selftests/net/af_unix/msg_oob.c b/tools/testing/selftests/net/af_unix/msg_oob.c
+index 16d0c172eaebe..535eb2c3d7d1c 100644
+--- a/tools/testing/selftests/net/af_unix/msg_oob.c
++++ b/tools/testing/selftests/net/af_unix/msg_oob.c
+@@ -209,7 +209,7 @@ static void __sendpair(struct __test_metadata *_metadata,
+
+ static void __recvpair(struct __test_metadata *_metadata,
+ FIXTURE_DATA(msg_oob) *self,
+- const void *expected_buf, int expected_len,
++ const char *expected_buf, int expected_len,
+ int buf_len, int flags)
+ {
+ int i, ret[2], recv_errno[2], expected_errno = 0;
+diff --git a/tools/testing/selftests/net/lib.sh b/tools/testing/selftests/net/lib.sh
+index 9155c914c064f..93de05fedd91a 100644
+--- a/tools/testing/selftests/net/lib.sh
++++ b/tools/testing/selftests/net/lib.sh
+@@ -128,25 +128,18 @@ slowwait_for_counter()
+ cleanup_ns()
+ {
+ local ns=""
+- local errexit=0
+ local ret=0
+
+- # disable errexit temporary
+- if [[ $- =~ "e" ]]; then
+- errexit=1
+- set +e
+- fi
+-
+ for ns in "$@"; do
+ [ -z "${ns}" ] && continue
+- ip netns delete "${ns}" &> /dev/null
++ ip netns pids "${ns}" 2> /dev/null | xargs -r kill || true
++ ip netns delete "${ns}" &> /dev/null || true
+ if ! busywait $BUSYWAIT_TIMEOUT ip netns list \| grep -vq "^$ns$" &> /dev/null; then
+ echo "Warn: Failed to remove namespace $ns"
+ ret=1
+ fi
+ done
+
+- [ $errexit -eq 1 ] && set -e
+ return $ret
+ }
+
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+index a3293043c85dd..ed30c0ed55e7a 100755
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+@@ -436,9 +436,10 @@ reset_with_tcp_filter()
+ local ns="${!1}"
+ local src="${2}"
+ local target="${3}"
++ local chain="${4:-INPUT}"
+
+ if ! ip netns exec "${ns}" ${iptables} \
+- -A INPUT \
++ -A "${chain}" \
+ -s "${src}" \
+ -p tcp \
+ -j "${target}"; then
+@@ -3058,6 +3059,7 @@ fullmesh_tests()
+ pm_nl_set_limits $ns1 1 3
+ pm_nl_set_limits $ns2 1 3
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
++ pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,fullmesh
+ fullmesh=1 speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 3 3 3
+@@ -3571,10 +3573,10 @@ endpoint_tests()
+ mptcp_lib_kill_wait $tests_pid
+ fi
+
+- if reset "delete and re-add" &&
++ if reset_with_tcp_filter "delete and re-add" ns2 10.0.3.2 REJECT OUTPUT &&
+ mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+- pm_nl_set_limits $ns1 1 1
+- pm_nl_set_limits $ns2 1 1
++ pm_nl_set_limits $ns1 0 2
++ pm_nl_set_limits $ns2 0 2
+ pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
+ test_linkfail=4 speed=20 \
+ run_tests $ns1 $ns2 10.0.1.1 &
+@@ -3591,11 +3593,27 @@ endpoint_tests()
+ chk_subflow_nr "after delete" 1
+ chk_mptcp_info subflows 0 subflows 0
+
+- pm_nl_add_endpoint $ns2 10.0.2.2 dev ns2eth2 flags subflow
++ pm_nl_add_endpoint $ns2 10.0.2.2 id 2 dev ns2eth2 flags subflow
+ wait_mpj $ns2
+ chk_subflow_nr "after re-add" 2
+ chk_mptcp_info subflows 1 subflows 1
++
++ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
++ wait_attempt_fail $ns2
++ chk_subflow_nr "after new reject" 2
++ chk_mptcp_info subflows 1 subflows 1
++
++ ip netns exec "${ns2}" ${iptables} -D OUTPUT -s "10.0.3.2" -p tcp -j REJECT
++ pm_nl_del_endpoint $ns2 3 10.0.3.2
++ pm_nl_add_endpoint $ns2 10.0.3.2 id 3 flags subflow
++ wait_mpj $ns2
++ chk_subflow_nr "after no reject" 3
++ chk_mptcp_info subflows 2 subflows 2
++
+ mptcp_lib_kill_wait $tests_pid
++
++ chk_join_nr 3 3 3
++ chk_rm_nr 1 1
+ fi
+ }
+
+diff --git a/tools/testing/selftests/net/udpgro.sh b/tools/testing/selftests/net/udpgro.sh
+index 11a1ebda564fd..d5ffd8c9172e1 100755
+--- a/tools/testing/selftests/net/udpgro.sh
++++ b/tools/testing/selftests/net/udpgro.sh
+@@ -7,8 +7,6 @@ source net_helper.sh
+
+ readonly PEER_NS="ns-peer-$(mktemp -u XXXXXX)"
+
+-BPF_FILE="xdp_dummy.bpf.o"
+-
+ # set global exit status, but never reset nonzero one.
+ check_err()
+ {
+@@ -38,7 +36,7 @@ cfg_veth() {
+ ip -netns "${PEER_NS}" addr add dev veth1 192.168.1.1/24
+ ip -netns "${PEER_NS}" addr add dev veth1 2001:db8::1/64 nodad
+ ip -netns "${PEER_NS}" link set dev veth1 up
+- ip -n "${PEER_NS}" link set veth1 xdp object ${BPF_FILE} section xdp
++ ip netns exec "${PEER_NS}" ethtool -K veth1 gro on
+ }
+
+ run_one() {
+@@ -46,17 +44,19 @@ run_one() {
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local -r rx_args=${all#*rx}
++ local ret=0
+
+ cfg_veth
+
+- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} && \
+- echo "ok" || \
+- echo "failed" &
++ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} &
++ local PID1=$!
+
+ wait_local_port_listen ${PEER_NS} 8000 udp
+ ./udpgso_bench_tx ${tx_args}
+- ret=$?
+- wait $(jobs -p)
++ check_err $?
++ wait ${PID1}
++ check_err $?
++ [ "$ret" -eq 0 ] && echo "ok" || echo "failed"
+ return $ret
+ }
+
+@@ -73,6 +73,7 @@ run_one_nat() {
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local -r rx_args=${all#*rx}
++ local ret=0
+
+ if [[ ${tx_args} = *-4* ]]; then
+ ipt_cmd=iptables
+@@ -93,16 +94,17 @@ run_one_nat() {
+ # ... so that GRO will match the UDP_GRO enabled socket, but packets
+ # will land on the 'plain' one
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -G ${family} -b ${addr1} -n 0 &
+- pid=$!
+- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} && \
+- echo "ok" || \
+- echo "failed"&
++ local PID1=$!
++ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${family} -b ${addr2%/*} ${rx_args} &
++ local PID2=$!
+
+ wait_local_port_listen "${PEER_NS}" 8000 udp
+ ./udpgso_bench_tx ${tx_args}
+- ret=$?
+- kill -INT $pid
+- wait $(jobs -p)
++ check_err $?
++ kill -INT ${PID1}
++ wait ${PID2}
++ check_err $?
++ [ "$ret" -eq 0 ] && echo "ok" || echo "failed"
+ return $ret
+ }
+
+@@ -111,20 +113,26 @@ run_one_2sock() {
+ local -r all="$@"
+ local -r tx_args=${all%rx*}
+ local -r rx_args=${all#*rx}
++ local ret=0
+
+ cfg_veth
+
+ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 1000 -R 10 ${rx_args} -p 12345 &
+- ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} && \
+- echo "ok" || \
+- echo "failed" &
++ local PID1=$!
++ ip netns exec "${PEER_NS}" ./udpgso_bench_rx -C 2000 -R 10 ${rx_args} &
++ local PID2=$!
+
+ wait_local_port_listen "${PEER_NS}" 12345 udp
+ ./udpgso_bench_tx ${tx_args} -p 12345
++ check_err $?
+ wait_local_port_listen "${PEER_NS}" 8000 udp
+ ./udpgso_bench_tx ${tx_args}
+- ret=$?
+- wait $(jobs -p)
++ check_err $?
++ wait ${PID1}
++ check_err $?
++ wait ${PID2}
++ check_err $?
++ [ "$ret" -eq 0 ] && echo "ok" || echo "failed"
+ return $ret
+ }
+
+@@ -196,11 +204,6 @@ run_all() {
+ return $ret
+ }
+
+-if [ ! -f ${BPF_FILE} ]; then
+- echo "Missing ${BPF_FILE}. Run 'make' first"
+- exit -1
+-fi
+-
+ if [[ $# -eq 0 ]]; then
+ run_all
+ elif [[ $1 == "__subprocess" ]]; then
+diff --git a/tools/testing/selftests/tc-testing/tdc.py b/tools/testing/selftests/tc-testing/tdc.py
+index ee349187636fc..4f255cec0c22e 100755
+--- a/tools/testing/selftests/tc-testing/tdc.py
++++ b/tools/testing/selftests/tc-testing/tdc.py
+@@ -143,7 +143,6 @@ class PluginMgr:
+ except Exception as ee:
+ print('exception {} in call to pre_case for {} plugin'.
+ format(ee, pgn_inst.__class__))
+- print('test_ordinal is {}'.format(test_ordinal))
+ print('testid is {}'.format(caseinfo['id']))
+ raise
+
+diff --git a/tools/tracing/rtla/src/osnoise_top.c b/tools/tracing/rtla/src/osnoise_top.c
+index 07ba55d4ec06f..de33ea5005b6b 100644
+--- a/tools/tracing/rtla/src/osnoise_top.c
++++ b/tools/tracing/rtla/src/osnoise_top.c
+@@ -640,8 +640,10 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params)
+ return NULL;
+
+ tool->data = osnoise_alloc_top(nr_cpus);
+- if (!tool->data)
+- goto out_err;
++ if (!tool->data) {
++ osnoise_destroy_tool(tool);
++ return NULL;
++ }
+
+ tool->params = params;
+
+@@ -649,11 +651,6 @@ struct osnoise_tool *osnoise_init_top(struct osnoise_top_params *params)
+ osnoise_top_handler, NULL);
+
+ return tool;
+-
+-out_err:
+- osnoise_free_top(tool->data);
+- osnoise_destroy_tool(tool);
+- return NULL;
+ }
+
+ static int stop_tracing;
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-19 10:23 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-19 10:23 UTC (permalink / raw
To: gentoo-commits
commit: 9ea6291b7fa333834b62299defaeaa1444daf91f
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Mon Aug 19 10:22:56 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Mon Aug 19 10:22:56 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=9ea6291b
Linux patch 6.10.6
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1005_linux-6.10.6.patch | 1626 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 1630 insertions(+)
diff --git a/0000_README b/0000_README
index b1582141..75bbf8b4 100644
--- a/0000_README
+++ b/0000_README
@@ -63,6 +63,10 @@ Patch: 1004_linux-6.10.5.patch
From: https://www.kernel.org
Desc: Linux 6.10.5
+Patch: 1005_linux-6.10.6.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.6
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1005_linux-6.10.6.patch b/1005_linux-6.10.6.patch
new file mode 100644
index 00000000..f226d534
--- /dev/null
+++ b/1005_linux-6.10.6.patch
@@ -0,0 +1,1626 @@
+diff --git a/Makefile b/Makefile
+index f9badb79ae8f4e..361a70264e1fb0 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 5
++SUBLEVEL = 6
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/loongarch/include/uapi/asm/unistd.h b/arch/loongarch/include/uapi/asm/unistd.h
+index fcb668984f0336..b344b1f917153b 100644
+--- a/arch/loongarch/include/uapi/asm/unistd.h
++++ b/arch/loongarch/include/uapi/asm/unistd.h
+@@ -1,4 +1,5 @@
+ /* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
++#define __ARCH_WANT_NEW_STAT
+ #define __ARCH_WANT_SYS_CLONE
+ #define __ARCH_WANT_SYS_CLONE3
+
+diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
+index 076fbeadce0153..4e084760110396 100644
+--- a/drivers/ata/libata-scsi.c
++++ b/drivers/ata/libata-scsi.c
+@@ -941,8 +941,19 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc)
+ &sense_key, &asc, &ascq);
+ ata_scsi_set_sense(qc->dev, cmd, sense_key, asc, ascq);
+ } else {
+- /* ATA PASS-THROUGH INFORMATION AVAILABLE */
+- ata_scsi_set_sense(qc->dev, cmd, RECOVERED_ERROR, 0, 0x1D);
++ /*
++ * ATA PASS-THROUGH INFORMATION AVAILABLE
++ *
++ * Note: we are supposed to call ata_scsi_set_sense(), which
++ * respects the D_SENSE bit, instead of unconditionally
++ * generating the sense data in descriptor format. However,
++ * because hdparm, hddtemp, and udisks incorrectly assume sense
++ * data in descriptor format, without even looking at the
++ * RESPONSE CODE field in the returned sense data (to see which
++ * format the returned sense data is in), we are stuck with
++ * being bug compatible with older kernels.
++ */
++ scsi_build_sense(cmd, 1, RECOVERED_ERROR, 0, 0x1D);
+ }
+ }
+
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+index 964bb6d0a38331..836bf9ba620d19 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+@@ -2944,6 +2944,7 @@ static int dm_resume(void *handle)
+
+ commit_params.streams = dc_state->streams;
+ commit_params.stream_count = dc_state->stream_count;
++ dc_exit_ips_for_hw_access(dm->dc);
+ WARN_ON(!dc_commit_streams(dm->dc, &commit_params));
+
+ dm_gpureset_commit_state(dm->cached_dc_state, dm);
+@@ -3016,7 +3017,8 @@ static int dm_resume(void *handle)
+ emulated_link_detect(aconnector->dc_link);
+ } else {
+ mutex_lock(&dm->dc_lock);
+- dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD);
++ dc_exit_ips_for_hw_access(dm->dc);
++ dc_link_detect(aconnector->dc_link, DETECT_REASON_RESUMEFROMS3S4);
+ mutex_unlock(&dm->dc_lock);
+ }
+
+@@ -3352,6 +3354,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector)
+ enum dc_connection_type new_connection_type = dc_connection_none;
+ struct amdgpu_device *adev = drm_to_adev(dev);
+ struct dm_connector_state *dm_con_state = to_dm_connector_state(connector->state);
++ struct dc *dc = aconnector->dc_link->ctx->dc;
+ bool ret = false;
+
+ if (adev->dm.disable_hpd_irq)
+@@ -3386,6 +3389,7 @@ static void handle_hpd_irq_helper(struct amdgpu_dm_connector *aconnector)
+ drm_kms_helper_connector_hotplug_event(connector);
+ } else {
+ mutex_lock(&adev->dm.dc_lock);
++ dc_exit_ips_for_hw_access(dc);
+ ret = dc_link_detect(aconnector->dc_link, DETECT_REASON_HPD);
+ mutex_unlock(&adev->dm.dc_lock);
+ if (ret) {
+@@ -3445,6 +3449,7 @@ static void handle_hpd_rx_irq(void *param)
+ bool has_left_work = false;
+ int idx = dc_link->link_index;
+ struct hpd_rx_irq_offload_work_queue *offload_wq = &adev->dm.hpd_rx_offload_wq[idx];
++ struct dc *dc = aconnector->dc_link->ctx->dc;
+
+ memset(&hpd_irq_data, 0, sizeof(hpd_irq_data));
+
+@@ -3534,6 +3539,7 @@ static void handle_hpd_rx_irq(void *param)
+ bool ret = false;
+
+ mutex_lock(&adev->dm.dc_lock);
++ dc_exit_ips_for_hw_access(dc);
+ ret = dc_link_detect(dc_link, DETECT_REASON_HPDRX);
+ mutex_unlock(&adev->dm.dc_lock);
+
+@@ -4640,6 +4646,7 @@ static int amdgpu_dm_initialize_drm_device(struct amdgpu_device *adev)
+ bool ret = false;
+
+ mutex_lock(&dm->dc_lock);
++ dc_exit_ips_for_hw_access(dm->dc);
+ ret = dc_link_detect(link, DETECT_REASON_BOOT);
+ mutex_unlock(&dm->dc_lock);
+
+@@ -8948,7 +8955,8 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state,
+
+ memset(&position, 0, sizeof(position));
+ mutex_lock(&dm->dc_lock);
+- dc_stream_set_cursor_position(dm_old_crtc_state->stream, &position);
++ dc_exit_ips_for_hw_access(dm->dc);
++ dc_stream_program_cursor_position(dm_old_crtc_state->stream, &position);
+ mutex_unlock(&dm->dc_lock);
+ }
+
+@@ -9017,6 +9025,7 @@ static void amdgpu_dm_commit_streams(struct drm_atomic_state *state,
+
+ dm_enable_per_frame_crtc_master_sync(dc_state);
+ mutex_lock(&dm->dc_lock);
++ dc_exit_ips_for_hw_access(dm->dc);
+ WARN_ON(!dc_commit_streams(dm->dc, ¶ms));
+
+ /* Allow idle optimization when vblank count is 0 for display off */
+@@ -9382,6 +9391,7 @@ static void amdgpu_dm_atomic_commit_tail(struct drm_atomic_state *state)
+
+
+ mutex_lock(&dm->dc_lock);
++ dc_exit_ips_for_hw_access(dm->dc);
+ dc_update_planes_and_stream(dm->dc,
+ dummy_updates,
+ status->plane_count,
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+index bb4e5ab7edc6e4..b50010ed763327 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+@@ -1594,171 +1594,109 @@ static bool is_dsc_common_config_possible(struct dc_stream_state *stream,
+ return bw_range->max_target_bpp_x16 && bw_range->min_target_bpp_x16;
+ }
+
+-#if defined(CONFIG_DRM_AMD_DC_FP)
+-static bool dp_get_link_current_set_bw(struct drm_dp_aux *aux, uint32_t *cur_link_bw)
+-{
+- uint32_t total_data_bw_efficiency_x10000 = 0;
+- uint32_t link_rate_per_lane_kbps = 0;
+- enum dc_link_rate link_rate;
+- union lane_count_set lane_count;
+- u8 dp_link_encoding;
+- u8 link_bw_set = 0;
+-
+- *cur_link_bw = 0;
+-
+- if (drm_dp_dpcd_read(aux, DP_MAIN_LINK_CHANNEL_CODING_SET, &dp_link_encoding, 1) != 1 ||
+- drm_dp_dpcd_read(aux, DP_LANE_COUNT_SET, &lane_count.raw, 1) != 1 ||
+- drm_dp_dpcd_read(aux, DP_LINK_BW_SET, &link_bw_set, 1) != 1)
+- return false;
+-
+- switch (dp_link_encoding) {
+- case DP_8b_10b_ENCODING:
+- link_rate = link_bw_set;
+- link_rate_per_lane_kbps = link_rate * LINK_RATE_REF_FREQ_IN_KHZ * BITS_PER_DP_BYTE;
+- total_data_bw_efficiency_x10000 = DATA_EFFICIENCY_8b_10b_x10000;
+- total_data_bw_efficiency_x10000 /= 100;
+- total_data_bw_efficiency_x10000 *= DATA_EFFICIENCY_8b_10b_FEC_EFFICIENCY_x100;
+- break;
+- case DP_128b_132b_ENCODING:
+- switch (link_bw_set) {
+- case DP_LINK_BW_10:
+- link_rate = LINK_RATE_UHBR10;
+- break;
+- case DP_LINK_BW_13_5:
+- link_rate = LINK_RATE_UHBR13_5;
+- break;
+- case DP_LINK_BW_20:
+- link_rate = LINK_RATE_UHBR20;
+- break;
+- default:
+- return false;
+- }
+-
+- link_rate_per_lane_kbps = link_rate * 10000;
+- total_data_bw_efficiency_x10000 = DATA_EFFICIENCY_128b_132b_x10000;
+- break;
+- default:
+- return false;
+- }
+-
+- *cur_link_bw = link_rate_per_lane_kbps * lane_count.bits.LANE_COUNT_SET / 10000 * total_data_bw_efficiency_x10000;
+- return true;
+-}
+-#endif
+-
+ enum dc_status dm_dp_mst_is_port_support_mode(
+ struct amdgpu_dm_connector *aconnector,
+ struct dc_stream_state *stream)
+ {
+-#if defined(CONFIG_DRM_AMD_DC_FP)
+- int branch_max_throughput_mps = 0;
++ int pbn, branch_max_throughput_mps = 0;
+ struct dc_link_settings cur_link_settings;
+- uint32_t end_to_end_bw_in_kbps = 0;
+- uint32_t root_link_bw_in_kbps = 0;
+- uint32_t virtual_channel_bw_in_kbps = 0;
++ unsigned int end_to_end_bw_in_kbps = 0;
++ unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0;
+ struct dc_dsc_bw_range bw_range = {0};
+ struct dc_dsc_config_options dsc_options = {0};
+- uint32_t stream_kbps;
+
+- /* DSC unnecessary case
+- * Check if timing could be supported within end-to-end BW
++ /*
++ * Consider the case with the depth of the mst topology tree is equal or less than 2
++ * A. When dsc bitstream can be transmitted along the entire path
++ * 1. dsc is possible between source and branch/leaf device (common dsc params is possible), AND
++ * 2. dsc passthrough supported at MST branch, or
++ * 3. dsc decoding supported at leaf MST device
++ * Use maximum dsc compression as bw constraint
++ * B. When dsc bitstream cannot be transmitted along the entire path
++ * Use native bw as bw constraint
+ */
+- stream_kbps =
+- dc_bandwidth_in_kbps_from_timing(&stream->timing,
+- dc_link_get_highest_encoding_format(stream->link));
+- cur_link_settings = stream->link->verified_link_cap;
+- root_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, &cur_link_settings);
+- virtual_channel_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn);
+-
+- /* pick the end to end bw bottleneck */
+- end_to_end_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps);
+-
+- if (stream_kbps <= end_to_end_bw_in_kbps) {
+- DRM_DEBUG_DRIVER("No DSC needed. End-to-end bw sufficient.");
+- return DC_OK;
+- }
+-
+- /*DSC necessary case*/
+- if (!aconnector->dsc_aux)
+- return DC_FAIL_BANDWIDTH_VALIDATE;
+-
+- if (is_dsc_common_config_possible(stream, &bw_range)) {
+-
+- /*capable of dsc passthough. dsc bitstream along the entire path*/
+- if (aconnector->mst_output_port->passthrough_aux) {
+- if (bw_range.min_kbps > end_to_end_bw_in_kbps) {
+- DRM_DEBUG_DRIVER("DSC passthrough. Max dsc compression can't fit into end-to-end bw\n");
++ if (is_dsc_common_config_possible(stream, &bw_range) &&
++ (aconnector->mst_output_port->passthrough_aux ||
++ aconnector->dsc_aux == &aconnector->mst_output_port->aux)) {
++ cur_link_settings = stream->link->verified_link_cap;
++ upper_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, &cur_link_settings);
++ down_link_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn);
++
++ /* pick the end to end bw bottleneck */
++ end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps, down_link_bw_in_kbps);
++
++ if (end_to_end_bw_in_kbps < bw_range.min_kbps) {
++ DRM_DEBUG_DRIVER("maximum dsc compression cannot fit into end-to-end bandwidth\n");
+ return DC_FAIL_BANDWIDTH_VALIDATE;
+- }
+- } else {
+- /*dsc bitstream decoded at the dp last link*/
+- struct drm_dp_mst_port *immediate_upstream_port = NULL;
+- uint32_t end_link_bw = 0;
+-
+- /*Get last DP link BW capability*/
+- if (dp_get_link_current_set_bw(&aconnector->mst_output_port->aux, &end_link_bw)) {
+- if (stream_kbps > end_link_bw) {
+- DRM_DEBUG_DRIVER("DSC decode at last link. Mode required bw can't fit into available bw\n");
+- return DC_FAIL_BANDWIDTH_VALIDATE;
+- }
+- }
+-
+- /*Get virtual channel bandwidth between source and the link before the last link*/
+- if (aconnector->mst_output_port->parent->port_parent)
+- immediate_upstream_port = aconnector->mst_output_port->parent->port_parent;
++ }
+
+- if (immediate_upstream_port) {
+- virtual_channel_bw_in_kbps = kbps_from_pbn(immediate_upstream_port->full_pbn);
+- virtual_channel_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps);
+- if (bw_range.min_kbps > virtual_channel_bw_in_kbps) {
+- DRM_DEBUG_DRIVER("DSC decode at last link. Max dsc compression can't fit into MST available bw\n");
+- return DC_FAIL_BANDWIDTH_VALIDATE;
+- }
++ if (end_to_end_bw_in_kbps < bw_range.stream_kbps) {
++ dc_dsc_get_default_config_option(stream->link->dc, &dsc_options);
++ dsc_options.max_target_bpp_limit_override_x16 = aconnector->base.display_info.max_dsc_bpp * 16;
++ if (dc_dsc_compute_config(stream->sink->ctx->dc->res_pool->dscs[0],
++ &stream->sink->dsc_caps.dsc_dec_caps,
++ &dsc_options,
++ end_to_end_bw_in_kbps,
++ &stream->timing,
++ dc_link_get_highest_encoding_format(stream->link),
++ &stream->timing.dsc_cfg)) {
++ stream->timing.flags.DSC = 1;
++ DRM_DEBUG_DRIVER("end-to-end bandwidth require dsc and dsc config found\n");
++ } else {
++ DRM_DEBUG_DRIVER("end-to-end bandwidth require dsc but dsc config not found\n");
++ return DC_FAIL_BANDWIDTH_VALIDATE;
+ }
+ }
+-
+- /*Confirm if we can obtain dsc config*/
+- dc_dsc_get_default_config_option(stream->link->dc, &dsc_options);
+- dsc_options.max_target_bpp_limit_override_x16 = aconnector->base.display_info.max_dsc_bpp * 16;
+- if (dc_dsc_compute_config(stream->sink->ctx->dc->res_pool->dscs[0],
+- &stream->sink->dsc_caps.dsc_dec_caps,
+- &dsc_options,
+- end_to_end_bw_in_kbps,
+- &stream->timing,
+- dc_link_get_highest_encoding_format(stream->link),
+- &stream->timing.dsc_cfg)) {
+- stream->timing.flags.DSC = 1;
+- DRM_DEBUG_DRIVER("Require dsc and dsc config found\n");
+- } else {
+- DRM_DEBUG_DRIVER("Require dsc but can't find appropriate dsc config\n");
++ } else {
++ /* Check if mode could be supported within max slot
++ * number of current mst link and full_pbn of mst links.
++ */
++ int pbn_div, slot_num, max_slot_num;
++ enum dc_link_encoding_format link_encoding;
++ uint32_t stream_kbps =
++ dc_bandwidth_in_kbps_from_timing(&stream->timing,
++ dc_link_get_highest_encoding_format(stream->link));
++
++ pbn = kbps_to_peak_pbn(stream_kbps);
++ pbn_div = dm_mst_get_pbn_divider(stream->link);
++ slot_num = DIV_ROUND_UP(pbn, pbn_div);
++
++ link_encoding = dc_link_get_highest_encoding_format(stream->link);
++ if (link_encoding == DC_LINK_ENCODING_DP_8b_10b)
++ max_slot_num = 63;
++ else if (link_encoding == DC_LINK_ENCODING_DP_128b_132b)
++ max_slot_num = 64;
++ else {
++ DRM_DEBUG_DRIVER("Invalid link encoding format\n");
+ return DC_FAIL_BANDWIDTH_VALIDATE;
+ }
+
+- /* check is mst dsc output bandwidth branch_overall_throughput_0_mps */
+- switch (stream->timing.pixel_encoding) {
+- case PIXEL_ENCODING_RGB:
+- case PIXEL_ENCODING_YCBCR444:
+- branch_max_throughput_mps =
+- aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_0_mps;
+- break;
+- case PIXEL_ENCODING_YCBCR422:
+- case PIXEL_ENCODING_YCBCR420:
+- branch_max_throughput_mps =
+- aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_1_mps;
+- break;
+- default:
+- break;
++ if (slot_num > max_slot_num ||
++ pbn > aconnector->mst_output_port->full_pbn) {
++ DRM_DEBUG_DRIVER("Mode can not be supported within mst links!");
++ return DC_FAIL_BANDWIDTH_VALIDATE;
+ }
++ }
+
+- if (branch_max_throughput_mps != 0 &&
+- ((stream->timing.pix_clk_100hz / 10) > branch_max_throughput_mps * 1000)) {
+- DRM_DEBUG_DRIVER("DSC is required but max throughput mps fails");
+- return DC_FAIL_BANDWIDTH_VALIDATE;
+- }
+- } else {
+- DRM_DEBUG_DRIVER("DSC is required but can't find common dsc config.");
+- return DC_FAIL_BANDWIDTH_VALIDATE;
++ /* check is mst dsc output bandwidth branch_overall_throughput_0_mps */
++ switch (stream->timing.pixel_encoding) {
++ case PIXEL_ENCODING_RGB:
++ case PIXEL_ENCODING_YCBCR444:
++ branch_max_throughput_mps =
++ aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_0_mps;
++ break;
++ case PIXEL_ENCODING_YCBCR422:
++ case PIXEL_ENCODING_YCBCR420:
++ branch_max_throughput_mps =
++ aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_1_mps;
++ break;
++ default:
++ break;
+ }
+-#endif
++
++ if (branch_max_throughput_mps != 0 &&
++ ((stream->timing.pix_clk_100hz / 10) > branch_max_throughput_mps * 1000))
++ return DC_FAIL_BANDWIDTH_VALIDATE;
++
+ return DC_OK;
+ }
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+index 8a4c40b4c27e4f..311c62d2d1ebbf 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_plane.c
+@@ -1254,7 +1254,7 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane,
+ /* turn off cursor */
+ if (crtc_state && crtc_state->stream) {
+ mutex_lock(&adev->dm.dc_lock);
+- dc_stream_set_cursor_position(crtc_state->stream,
++ dc_stream_program_cursor_position(crtc_state->stream,
+ &position);
+ mutex_unlock(&adev->dm.dc_lock);
+ }
+@@ -1284,11 +1284,11 @@ void amdgpu_dm_plane_handle_cursor_update(struct drm_plane *plane,
+
+ if (crtc_state->stream) {
+ mutex_lock(&adev->dm.dc_lock);
+- if (!dc_stream_set_cursor_attributes(crtc_state->stream,
++ if (!dc_stream_program_cursor_attributes(crtc_state->stream,
+ &attributes))
+ DRM_ERROR("DC failed to set cursor attributes\n");
+
+- if (!dc_stream_set_cursor_position(crtc_state->stream,
++ if (!dc_stream_program_cursor_position(crtc_state->stream,
+ &position))
+ DRM_ERROR("DC failed to set cursor position\n");
+ mutex_unlock(&adev->dm.dc_lock);
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+index 5c7e4884cac2c5..53bc991b6e6737 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc_stream.c
+@@ -266,7 +266,6 @@ bool dc_stream_set_cursor_attributes(
+ const struct dc_cursor_attributes *attributes)
+ {
+ struct dc *dc;
+- bool reset_idle_optimizations = false;
+
+ if (NULL == stream) {
+ dm_error("DC: dc_stream is NULL!\n");
+@@ -297,20 +296,36 @@ bool dc_stream_set_cursor_attributes(
+
+ stream->cursor_attributes = *attributes;
+
+- dc_z10_restore(dc);
+- /* disable idle optimizations while updating cursor */
+- if (dc->idle_optimizations_allowed) {
+- dc_allow_idle_optimizations(dc, false);
+- reset_idle_optimizations = true;
+- }
++ return true;
++}
+
+- program_cursor_attributes(dc, stream, attributes);
++bool dc_stream_program_cursor_attributes(
++ struct dc_stream_state *stream,
++ const struct dc_cursor_attributes *attributes)
++{
++ struct dc *dc;
++ bool reset_idle_optimizations = false;
+
+- /* re-enable idle optimizations if necessary */
+- if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle)
+- dc_allow_idle_optimizations(dc, true);
++ dc = stream ? stream->ctx->dc : NULL;
+
+- return true;
++ if (dc_stream_set_cursor_attributes(stream, attributes)) {
++ dc_z10_restore(dc);
++ /* disable idle optimizations while updating cursor */
++ if (dc->idle_optimizations_allowed) {
++ dc_allow_idle_optimizations(dc, false);
++ reset_idle_optimizations = true;
++ }
++
++ program_cursor_attributes(dc, stream, attributes);
++
++ /* re-enable idle optimizations if necessary */
++ if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle)
++ dc_allow_idle_optimizations(dc, true);
++
++ return true;
++ }
++
++ return false;
+ }
+
+ static void program_cursor_position(
+@@ -355,9 +370,6 @@ bool dc_stream_set_cursor_position(
+ struct dc_stream_state *stream,
+ const struct dc_cursor_position *position)
+ {
+- struct dc *dc;
+- bool reset_idle_optimizations = false;
+-
+ if (NULL == stream) {
+ dm_error("DC: dc_stream is NULL!\n");
+ return false;
+@@ -368,24 +380,46 @@ bool dc_stream_set_cursor_position(
+ return false;
+ }
+
++ stream->cursor_position = *position;
++
++
++ return true;
++}
++
++bool dc_stream_program_cursor_position(
++ struct dc_stream_state *stream,
++ const struct dc_cursor_position *position)
++{
++ struct dc *dc;
++ bool reset_idle_optimizations = false;
++ const struct dc_cursor_position *old_position;
++
++ if (!stream)
++ return false;
++
++ old_position = &stream->cursor_position;
+ dc = stream->ctx->dc;
+- dc_z10_restore(dc);
+
+- /* disable idle optimizations if enabling cursor */
+- if (dc->idle_optimizations_allowed && (!stream->cursor_position.enable || dc->debug.exit_idle_opt_for_cursor_updates)
+- && position->enable) {
+- dc_allow_idle_optimizations(dc, false);
+- reset_idle_optimizations = true;
+- }
++ if (dc_stream_set_cursor_position(stream, position)) {
++ dc_z10_restore(dc);
+
+- stream->cursor_position = *position;
++ /* disable idle optimizations if enabling cursor */
++ if (dc->idle_optimizations_allowed &&
++ (!old_position->enable || dc->debug.exit_idle_opt_for_cursor_updates) &&
++ position->enable) {
++ dc_allow_idle_optimizations(dc, false);
++ reset_idle_optimizations = true;
++ }
+
+- program_cursor_position(dc, stream, position);
+- /* re-enable idle optimizations if necessary */
+- if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle)
+- dc_allow_idle_optimizations(dc, true);
++ program_cursor_position(dc, stream, position);
++ /* re-enable idle optimizations if necessary */
++ if (reset_idle_optimizations && !dc->debug.disable_dmub_reallow_idle)
++ dc_allow_idle_optimizations(dc, true);
+
+- return true;
++ return true;
++ }
++
++ return false;
+ }
+
+ bool dc_stream_add_writeback(struct dc *dc,
+diff --git a/drivers/gpu/drm/amd/display/dc/dc_stream.h b/drivers/gpu/drm/amd/display/dc/dc_stream.h
+index e5dbbc6089a5e4..1039dfb0b071a7 100644
+--- a/drivers/gpu/drm/amd/display/dc/dc_stream.h
++++ b/drivers/gpu/drm/amd/display/dc/dc_stream.h
+@@ -470,10 +470,18 @@ bool dc_stream_set_cursor_attributes(
+ struct dc_stream_state *stream,
+ const struct dc_cursor_attributes *attributes);
+
++bool dc_stream_program_cursor_attributes(
++ struct dc_stream_state *stream,
++ const struct dc_cursor_attributes *attributes);
++
+ bool dc_stream_set_cursor_position(
+ struct dc_stream_state *stream,
+ const struct dc_cursor_position *position);
+
++bool dc_stream_program_cursor_position(
++ struct dc_stream_state *stream,
++ const struct dc_cursor_position *position);
++
+
+ bool dc_stream_adjust_vmin_vmax(struct dc *dc,
+ struct dc_stream_state *stream,
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+index 5b09d95cc5b8fc..4c470615330509 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+@@ -1041,7 +1041,7 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
+
+ /* Use copied cursor, and it's okay to not switch back */
+ cursor_attr.address.quad_part = cmd.mall.cursor_copy_dst.quad_part;
+- dc_stream_set_cursor_attributes(stream, &cursor_attr);
++ dc_stream_program_cursor_attributes(stream, &cursor_attr);
+ }
+
+ /* Enable MALL */
+diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c
+index 22d83ac18eb735..fbf58012becdf2 100644
+--- a/drivers/media/usb/dvb-usb/dvb-usb-init.c
++++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c
+@@ -23,40 +23,11 @@ static int dvb_usb_force_pid_filter_usage;
+ module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444);
+ MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0).");
+
+-static int dvb_usb_check_bulk_endpoint(struct dvb_usb_device *d, u8 endpoint)
+-{
+- if (endpoint) {
+- int ret;
+-
+- ret = usb_pipe_type_check(d->udev, usb_sndbulkpipe(d->udev, endpoint));
+- if (ret)
+- return ret;
+- ret = usb_pipe_type_check(d->udev, usb_rcvbulkpipe(d->udev, endpoint));
+- if (ret)
+- return ret;
+- }
+- return 0;
+-}
+-
+-static void dvb_usb_clear_halt(struct dvb_usb_device *d, u8 endpoint)
+-{
+- if (endpoint) {
+- usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, endpoint));
+- usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, endpoint));
+- }
+-}
+-
+ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs)
+ {
+ struct dvb_usb_adapter *adap;
+ int ret, n, o;
+
+- ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint);
+- if (ret)
+- return ret;
+- ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint_response);
+- if (ret)
+- return ret;
+ for (n = 0; n < d->props.num_adapters; n++) {
+ adap = &d->adapter[n];
+ adap->dev = d;
+@@ -132,8 +103,10 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs)
+ * when reloading the driver w/o replugging the device
+ * sometimes a timeout occurs, this helps
+ */
+- dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint);
+- dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint_response);
++ if (d->props.generic_bulk_ctrl_endpoint != 0) {
++ usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint));
++ usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint));
++ }
+
+ return 0;
+
+diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
+index 7168ff4cc62bba..a823330567ff8b 100644
+--- a/drivers/nvme/host/pci.c
++++ b/drivers/nvme/host/pci.c
+@@ -2933,6 +2933,13 @@ static unsigned long check_vendor_combination_bug(struct pci_dev *pdev)
+ return NVME_QUIRK_FORCE_NO_SIMPLE_SUSPEND;
+ }
+
++ /*
++ * NVMe SSD drops off the PCIe bus after system idle
++ * for 10 hours on a Lenovo N60z board.
++ */
++ if (dmi_match(DMI_BOARD_NAME, "LXKT-ZXEG-N6"))
++ return NVME_QUIRK_NO_APST;
++
+ return 0;
+ }
+
+diff --git a/drivers/platform/x86/Kconfig b/drivers/platform/x86/Kconfig
+index 665fa952498659..ddfccc226751f4 100644
+--- a/drivers/platform/x86/Kconfig
++++ b/drivers/platform/x86/Kconfig
+@@ -477,6 +477,7 @@ config LENOVO_YMC
+ tristate "Lenovo Yoga Tablet Mode Control"
+ depends on ACPI_WMI
+ depends on INPUT
++ depends on IDEAPAD_LAPTOP
+ select INPUT_SPARSEKMAP
+ help
+ This driver maps the Tablet Mode Control switch to SW_TABLET_MODE input
+diff --git a/drivers/platform/x86/amd/pmf/spc.c b/drivers/platform/x86/amd/pmf/spc.c
+index a3dec14c30043e..3c153fb1425e9f 100644
+--- a/drivers/platform/x86/amd/pmf/spc.c
++++ b/drivers/platform/x86/amd/pmf/spc.c
+@@ -150,36 +150,26 @@ static int amd_pmf_get_slider_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_
+ return 0;
+ }
+
+-static int amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
++static void amd_pmf_get_sensor_info(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+ {
+ struct amd_sfh_info sfh_info;
+- int ret;
++
++ /* Get the latest information from SFH */
++ in->ev_info.user_present = false;
+
+ /* Get ALS data */
+- ret = amd_get_sfh_info(&sfh_info, MT_ALS);
+- if (!ret)
++ if (!amd_get_sfh_info(&sfh_info, MT_ALS))
+ in->ev_info.ambient_light = sfh_info.ambient_light;
+ else
+- return ret;
++ dev_dbg(dev->dev, "ALS is not enabled/detected\n");
+
+ /* get HPD data */
+- ret = amd_get_sfh_info(&sfh_info, MT_HPD);
+- if (ret)
+- return ret;
+-
+- switch (sfh_info.user_present) {
+- case SFH_NOT_DETECTED:
+- in->ev_info.user_present = 0xff; /* assume no sensors connected */
+- break;
+- case SFH_USER_PRESENT:
+- in->ev_info.user_present = 1;
+- break;
+- case SFH_USER_AWAY:
+- in->ev_info.user_present = 0;
+- break;
++ if (!amd_get_sfh_info(&sfh_info, MT_HPD)) {
++ if (sfh_info.user_present == SFH_USER_PRESENT)
++ in->ev_info.user_present = true;
++ } else {
++ dev_dbg(dev->dev, "HPD is not enabled/detected\n");
+ }
+-
+- return 0;
+ }
+
+ void amd_pmf_populate_ta_inputs(struct amd_pmf_dev *dev, struct ta_pmf_enact_table *in)
+diff --git a/drivers/platform/x86/ideapad-laptop.c b/drivers/platform/x86/ideapad-laptop.c
+index fcf13d88fd6ed4..490815917adec8 100644
+--- a/drivers/platform/x86/ideapad-laptop.c
++++ b/drivers/platform/x86/ideapad-laptop.c
+@@ -125,6 +125,7 @@ struct ideapad_rfk_priv {
+
+ struct ideapad_private {
+ struct acpi_device *adev;
++ struct mutex vpc_mutex; /* protects the VPC calls */
+ struct rfkill *rfk[IDEAPAD_RFKILL_DEV_NUM];
+ struct ideapad_rfk_priv rfk_priv[IDEAPAD_RFKILL_DEV_NUM];
+ struct platform_device *platform_device;
+@@ -145,6 +146,7 @@ struct ideapad_private {
+ bool touchpad_ctrl_via_ec : 1;
+ bool ctrl_ps2_aux_port : 1;
+ bool usb_charging : 1;
++ bool ymc_ec_trigger : 1;
+ } features;
+ struct {
+ bool initialized;
+@@ -193,6 +195,12 @@ MODULE_PARM_DESC(touchpad_ctrl_via_ec,
+ "Enable registering a 'touchpad' sysfs-attribute which can be used to manually "
+ "tell the EC to enable/disable the touchpad. This may not work on all models.");
+
++static bool ymc_ec_trigger __read_mostly;
++module_param(ymc_ec_trigger, bool, 0444);
++MODULE_PARM_DESC(ymc_ec_trigger,
++ "Enable EC triggering work-around to force emitting tablet mode events. "
++ "If you need this please report this to: platform-driver-x86@vger.kernel.org");
++
+ /*
+ * shared data
+ */
+@@ -297,6 +305,8 @@ static int debugfs_status_show(struct seq_file *s, void *data)
+ struct ideapad_private *priv = s->private;
+ unsigned long value;
+
++ guard(mutex)(&priv->vpc_mutex);
++
+ if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL_MAX, &value))
+ seq_printf(s, "Backlight max: %lu\n", value);
+ if (!read_ec_data(priv->adev->handle, VPCCMD_R_BL, &value))
+@@ -415,7 +425,8 @@ static ssize_t camera_power_show(struct device *dev,
+ unsigned long result;
+ int err;
+
+- err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ err = read_ec_data(priv->adev->handle, VPCCMD_R_CAMERA, &result);
+ if (err)
+ return err;
+
+@@ -434,7 +445,8 @@ static ssize_t camera_power_store(struct device *dev,
+ if (err)
+ return err;
+
+- err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_CAMERA, state);
+ if (err)
+ return err;
+
+@@ -487,7 +499,8 @@ static ssize_t fan_mode_show(struct device *dev,
+ unsigned long result;
+ int err;
+
+- err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ err = read_ec_data(priv->adev->handle, VPCCMD_R_FAN, &result);
+ if (err)
+ return err;
+
+@@ -509,7 +522,8 @@ static ssize_t fan_mode_store(struct device *dev,
+ if (state > 4 || state == 3)
+ return -EINVAL;
+
+- err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_FAN, state);
+ if (err)
+ return err;
+
+@@ -594,7 +608,8 @@ static ssize_t touchpad_show(struct device *dev,
+ unsigned long result;
+ int err;
+
+- err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ err = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &result);
+ if (err)
+ return err;
+
+@@ -615,7 +630,8 @@ static ssize_t touchpad_store(struct device *dev,
+ if (err)
+ return err;
+
+- err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_TOUCHPAD, state);
+ if (err)
+ return err;
+
+@@ -1012,6 +1028,8 @@ static int ideapad_rfk_set(void *data, bool blocked)
+ struct ideapad_rfk_priv *priv = data;
+ int opcode = ideapad_rfk_data[priv->dev].opcode;
+
++ guard(mutex)(&priv->priv->vpc_mutex);
++
+ return write_ec_cmd(priv->priv->adev->handle, opcode, !blocked);
+ }
+
+@@ -1025,6 +1043,8 @@ static void ideapad_sync_rfk_state(struct ideapad_private *priv)
+ int i;
+
+ if (priv->features.hw_rfkill_switch) {
++ guard(mutex)(&priv->vpc_mutex);
++
+ if (read_ec_data(priv->adev->handle, VPCCMD_R_RF, &hw_blocked))
+ return;
+ hw_blocked = !hw_blocked;
+@@ -1198,8 +1218,9 @@ static void ideapad_input_novokey(struct ideapad_private *priv)
+ {
+ unsigned long long_pressed;
+
+- if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed))
+- return;
++ scoped_guard(mutex, &priv->vpc_mutex)
++ if (read_ec_data(priv->adev->handle, VPCCMD_R_NOVO, &long_pressed))
++ return;
+
+ if (long_pressed)
+ ideapad_input_report(priv, 17);
+@@ -1211,8 +1232,9 @@ static void ideapad_check_special_buttons(struct ideapad_private *priv)
+ {
+ unsigned long bit, value;
+
+- if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value))
+- return;
++ scoped_guard(mutex, &priv->vpc_mutex)
++ if (read_ec_data(priv->adev->handle, VPCCMD_R_SPECIAL_BUTTONS, &value))
++ return;
+
+ for_each_set_bit (bit, &value, 16) {
+ switch (bit) {
+@@ -1245,6 +1267,8 @@ static int ideapad_backlight_get_brightness(struct backlight_device *blightdev)
+ unsigned long now;
+ int err;
+
++ guard(mutex)(&priv->vpc_mutex);
++
+ err = read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now);
+ if (err)
+ return err;
+@@ -1257,6 +1281,8 @@ static int ideapad_backlight_update_status(struct backlight_device *blightdev)
+ struct ideapad_private *priv = bl_get_data(blightdev);
+ int err;
+
++ guard(mutex)(&priv->vpc_mutex);
++
+ err = write_ec_cmd(priv->adev->handle, VPCCMD_W_BL,
+ blightdev->props.brightness);
+ if (err)
+@@ -1334,6 +1360,8 @@ static void ideapad_backlight_notify_power(struct ideapad_private *priv)
+ if (!blightdev)
+ return;
+
++ guard(mutex)(&priv->vpc_mutex);
++
+ if (read_ec_data(priv->adev->handle, VPCCMD_R_BL_POWER, &power))
+ return;
+
+@@ -1346,7 +1374,8 @@ static void ideapad_backlight_notify_brightness(struct ideapad_private *priv)
+
+ /* if we control brightness via acpi video driver */
+ if (!priv->blightdev)
+- read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ read_ec_data(priv->adev->handle, VPCCMD_R_BL, &now);
+ else
+ backlight_force_update(priv->blightdev, BACKLIGHT_UPDATE_HOTKEY);
+ }
+@@ -1571,7 +1600,8 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_
+ int ret;
+
+ /* Without reading from EC touchpad LED doesn't switch state */
+- ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value);
++ scoped_guard(mutex, &priv->vpc_mutex)
++ ret = read_ec_data(priv->adev->handle, VPCCMD_R_TOUCHPAD, &value);
+ if (ret)
+ return;
+
+@@ -1599,16 +1629,92 @@ static void ideapad_sync_touchpad_state(struct ideapad_private *priv, bool send_
+ priv->r_touchpad_val = value;
+ }
+
++static const struct dmi_system_id ymc_ec_trigger_quirk_dmi_table[] = {
++ {
++ /* Lenovo Yoga 7 14ARB7 */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
++ DMI_MATCH(DMI_PRODUCT_NAME, "82QF"),
++ },
++ },
++ {
++ /* Lenovo Yoga 7 14ACN6 */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
++ DMI_MATCH(DMI_PRODUCT_NAME, "82N7"),
++ },
++ },
++ { }
++};
++
++static void ideapad_laptop_trigger_ec(void)
++{
++ struct ideapad_private *priv;
++ int ret;
++
++ guard(mutex)(&ideapad_shared_mutex);
++
++ priv = ideapad_shared;
++ if (!priv)
++ return;
++
++ if (!priv->features.ymc_ec_trigger)
++ return;
++
++ scoped_guard(mutex, &priv->vpc_mutex)
++ ret = write_ec_cmd(priv->adev->handle, VPCCMD_W_YMC, 1);
++ if (ret)
++ dev_warn(&priv->platform_device->dev, "Could not write YMC: %d\n", ret);
++}
++
++static int ideapad_laptop_nb_notify(struct notifier_block *nb,
++ unsigned long action, void *data)
++{
++ switch (action) {
++ case IDEAPAD_LAPTOP_YMC_EVENT:
++ ideapad_laptop_trigger_ec();
++ break;
++ }
++
++ return 0;
++}
++
++static struct notifier_block ideapad_laptop_notifier = {
++ .notifier_call = ideapad_laptop_nb_notify,
++};
++
++static BLOCKING_NOTIFIER_HEAD(ideapad_laptop_chain_head);
++
++int ideapad_laptop_register_notifier(struct notifier_block *nb)
++{
++ return blocking_notifier_chain_register(&ideapad_laptop_chain_head, nb);
++}
++EXPORT_SYMBOL_NS_GPL(ideapad_laptop_register_notifier, IDEAPAD_LAPTOP);
++
++int ideapad_laptop_unregister_notifier(struct notifier_block *nb)
++{
++ return blocking_notifier_chain_unregister(&ideapad_laptop_chain_head, nb);
++}
++EXPORT_SYMBOL_NS_GPL(ideapad_laptop_unregister_notifier, IDEAPAD_LAPTOP);
++
++void ideapad_laptop_call_notifier(unsigned long action, void *data)
++{
++ blocking_notifier_call_chain(&ideapad_laptop_chain_head, action, data);
++}
++EXPORT_SYMBOL_NS_GPL(ideapad_laptop_call_notifier, IDEAPAD_LAPTOP);
++
+ static void ideapad_acpi_notify(acpi_handle handle, u32 event, void *data)
+ {
+ struct ideapad_private *priv = data;
+ unsigned long vpc1, vpc2, bit;
+
+- if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1))
+- return;
++ scoped_guard(mutex, &priv->vpc_mutex) {
++ if (read_ec_data(handle, VPCCMD_R_VPC1, &vpc1))
++ return;
+
+- if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2))
+- return;
++ if (read_ec_data(handle, VPCCMD_R_VPC2, &vpc2))
++ return;
++ }
+
+ vpc1 = (vpc2 << 8) | vpc1;
+
+@@ -1735,6 +1841,8 @@ static void ideapad_check_features(struct ideapad_private *priv)
+ priv->features.ctrl_ps2_aux_port =
+ ctrl_ps2_aux_port || dmi_check_system(ctrl_ps2_aux_port_list);
+ priv->features.touchpad_ctrl_via_ec = touchpad_ctrl_via_ec;
++ priv->features.ymc_ec_trigger =
++ ymc_ec_trigger || dmi_check_system(ymc_ec_trigger_quirk_dmi_table);
+
+ if (!read_ec_data(handle, VPCCMD_R_FAN, &val))
+ priv->features.fan_mode = true;
+@@ -1915,6 +2023,10 @@ static int ideapad_acpi_add(struct platform_device *pdev)
+ priv->adev = adev;
+ priv->platform_device = pdev;
+
++ err = devm_mutex_init(&pdev->dev, &priv->vpc_mutex);
++ if (err)
++ return err;
++
+ ideapad_check_features(priv);
+
+ err = ideapad_sysfs_init(priv);
+@@ -1983,6 +2095,8 @@ static int ideapad_acpi_add(struct platform_device *pdev)
+ if (err)
+ goto shared_init_failed;
+
++ ideapad_laptop_register_notifier(&ideapad_laptop_notifier);
++
+ return 0;
+
+ shared_init_failed:
+@@ -2015,6 +2129,8 @@ static void ideapad_acpi_remove(struct platform_device *pdev)
+ struct ideapad_private *priv = dev_get_drvdata(&pdev->dev);
+ int i;
+
++ ideapad_laptop_unregister_notifier(&ideapad_laptop_notifier);
++
+ ideapad_shared_exit(priv);
+
+ acpi_remove_notify_handler(priv->adev->handle,
+diff --git a/drivers/platform/x86/ideapad-laptop.h b/drivers/platform/x86/ideapad-laptop.h
+index 4498a96de59769..948cc61800a950 100644
+--- a/drivers/platform/x86/ideapad-laptop.h
++++ b/drivers/platform/x86/ideapad-laptop.h
+@@ -12,6 +12,15 @@
+ #include <linux/acpi.h>
+ #include <linux/jiffies.h>
+ #include <linux/errno.h>
++#include <linux/notifier.h>
++
++enum ideapad_laptop_notifier_actions {
++ IDEAPAD_LAPTOP_YMC_EVENT,
++};
++
++int ideapad_laptop_register_notifier(struct notifier_block *nb);
++int ideapad_laptop_unregister_notifier(struct notifier_block *nb);
++void ideapad_laptop_call_notifier(unsigned long action, void *data);
+
+ enum {
+ VPCCMD_R_VPC1 = 0x10,
+diff --git a/drivers/platform/x86/lenovo-ymc.c b/drivers/platform/x86/lenovo-ymc.c
+index e1fbc35504d498..e0bbd6a14a89cb 100644
+--- a/drivers/platform/x86/lenovo-ymc.c
++++ b/drivers/platform/x86/lenovo-ymc.c
+@@ -20,32 +20,10 @@
+ #define LENOVO_YMC_QUERY_INSTANCE 0
+ #define LENOVO_YMC_QUERY_METHOD 0x01
+
+-static bool ec_trigger __read_mostly;
+-module_param(ec_trigger, bool, 0444);
+-MODULE_PARM_DESC(ec_trigger, "Enable EC triggering work-around to force emitting tablet mode events");
+-
+ static bool force;
+ module_param(force, bool, 0444);
+ MODULE_PARM_DESC(force, "Force loading on boards without a convertible DMI chassis-type");
+
+-static const struct dmi_system_id ec_trigger_quirk_dmi_table[] = {
+- {
+- /* Lenovo Yoga 7 14ARB7 */
+- .matches = {
+- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+- DMI_MATCH(DMI_PRODUCT_NAME, "82QF"),
+- },
+- },
+- {
+- /* Lenovo Yoga 7 14ACN6 */
+- .matches = {
+- DMI_MATCH(DMI_SYS_VENDOR, "LENOVO"),
+- DMI_MATCH(DMI_PRODUCT_NAME, "82N7"),
+- },
+- },
+- { }
+-};
+-
+ static const struct dmi_system_id allowed_chasis_types_dmi_table[] = {
+ {
+ .matches = {
+@@ -62,21 +40,8 @@ static const struct dmi_system_id allowed_chasis_types_dmi_table[] = {
+
+ struct lenovo_ymc_private {
+ struct input_dev *input_dev;
+- struct acpi_device *ec_acpi_dev;
+ };
+
+-static void lenovo_ymc_trigger_ec(struct wmi_device *wdev, struct lenovo_ymc_private *priv)
+-{
+- int err;
+-
+- if (!priv->ec_acpi_dev)
+- return;
+-
+- err = write_ec_cmd(priv->ec_acpi_dev->handle, VPCCMD_W_YMC, 1);
+- if (err)
+- dev_warn(&wdev->dev, "Could not write YMC: %d\n", err);
+-}
+-
+ static const struct key_entry lenovo_ymc_keymap[] = {
+ /* Laptop */
+ { KE_SW, 0x01, { .sw = { SW_TABLET_MODE, 0 } } },
+@@ -125,11 +90,9 @@ static void lenovo_ymc_notify(struct wmi_device *wdev, union acpi_object *data)
+
+ free_obj:
+ kfree(obj);
+- lenovo_ymc_trigger_ec(wdev, priv);
++ ideapad_laptop_call_notifier(IDEAPAD_LAPTOP_YMC_EVENT, &code);
+ }
+
+-static void acpi_dev_put_helper(void *p) { acpi_dev_put(p); }
+-
+ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx)
+ {
+ struct lenovo_ymc_private *priv;
+@@ -143,29 +106,10 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx)
+ return -ENODEV;
+ }
+
+- ec_trigger |= dmi_check_system(ec_trigger_quirk_dmi_table);
+-
+ priv = devm_kzalloc(&wdev->dev, sizeof(*priv), GFP_KERNEL);
+ if (!priv)
+ return -ENOMEM;
+
+- if (ec_trigger) {
+- pr_debug("Lenovo YMC enable EC triggering.\n");
+- priv->ec_acpi_dev = acpi_dev_get_first_match_dev("VPC2004", NULL, -1);
+-
+- if (!priv->ec_acpi_dev) {
+- dev_err(&wdev->dev, "Could not find EC ACPI device.\n");
+- return -ENODEV;
+- }
+- err = devm_add_action_or_reset(&wdev->dev,
+- acpi_dev_put_helper, priv->ec_acpi_dev);
+- if (err) {
+- dev_err(&wdev->dev,
+- "Could not clean up EC ACPI device: %d\n", err);
+- return err;
+- }
+- }
+-
+ input_dev = devm_input_allocate_device(&wdev->dev);
+ if (!input_dev)
+ return -ENOMEM;
+@@ -192,7 +136,6 @@ static int lenovo_ymc_probe(struct wmi_device *wdev, const void *ctx)
+ dev_set_drvdata(&wdev->dev, priv);
+
+ /* Report the state for the first time on probe */
+- lenovo_ymc_trigger_ec(wdev, priv);
+ lenovo_ymc_notify(wdev, NULL);
+ return 0;
+ }
+@@ -217,3 +160,4 @@ module_wmi_driver(lenovo_ymc_driver);
+ MODULE_AUTHOR("Gergo Koteles <soyer@irl.hu>");
+ MODULE_DESCRIPTION("Lenovo Yoga Mode Control driver");
+ MODULE_LICENSE("GPL");
++MODULE_IMPORT_NS(IDEAPAD_LAPTOP);
+diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
+index c26545d71d39a3..cd6d5bbb4b9df5 100644
+--- a/fs/binfmt_flat.c
++++ b/fs/binfmt_flat.c
+@@ -72,8 +72,10 @@
+
+ #ifdef CONFIG_BINFMT_FLAT_NO_DATA_START_OFFSET
+ #define DATA_START_OFFSET_WORDS (0)
++#define MAX_SHARED_LIBS_UPDATE (0)
+ #else
+ #define DATA_START_OFFSET_WORDS (MAX_SHARED_LIBS)
++#define MAX_SHARED_LIBS_UPDATE (MAX_SHARED_LIBS)
+ #endif
+
+ struct lib_info {
+@@ -880,7 +882,7 @@ static int load_flat_binary(struct linux_binprm *bprm)
+ return res;
+
+ /* Update data segment pointers for all libraries */
+- for (i = 0; i < MAX_SHARED_LIBS; i++) {
++ for (i = 0; i < MAX_SHARED_LIBS_UPDATE; i++) {
+ if (!libinfo.lib_list[i].loaded)
+ continue;
+ for (j = 0; j < MAX_SHARED_LIBS; j++) {
+diff --git a/fs/exec.c b/fs/exec.c
+index 40073142288f7a..0c17e59e3767b8 100644
+--- a/fs/exec.c
++++ b/fs/exec.c
+@@ -1668,6 +1668,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
+ unsigned int mode;
+ vfsuid_t vfsuid;
+ vfsgid_t vfsgid;
++ int err;
+
+ if (!mnt_may_suid(file->f_path.mnt))
+ return;
+@@ -1684,12 +1685,17 @@ static void bprm_fill_uid(struct linux_binprm *bprm, struct file *file)
+ /* Be careful if suid/sgid is set */
+ inode_lock(inode);
+
+- /* reload atomically mode/uid/gid now that lock held */
++ /* Atomically reload and check mode/uid/gid now that lock held. */
+ mode = inode->i_mode;
+ vfsuid = i_uid_into_vfsuid(idmap, inode);
+ vfsgid = i_gid_into_vfsgid(idmap, inode);
++ err = inode_permission(idmap, inode, MAY_EXEC);
+ inode_unlock(inode);
+
++ /* Did the exec bit vanish out from under us? Give up. */
++ if (err)
++ return;
++
+ /* We ignore suid/sgid if there are no mappings for them in the ns */
+ if (!vfsuid_has_mapping(bprm->cred->user_ns, vfsuid) ||
+ !vfsgid_has_mapping(bprm->cred->user_ns, vfsgid))
+diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
+index 48048fa3642766..fd1fc06359eea3 100644
+--- a/fs/f2fs/extent_cache.c
++++ b/fs/f2fs/extent_cache.c
+@@ -19,33 +19,23 @@
+ #include "node.h"
+ #include <trace/events/f2fs.h>
+
+-bool sanity_check_extent_cache(struct inode *inode)
++bool sanity_check_extent_cache(struct inode *inode, struct page *ipage)
+ {
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+- struct f2fs_inode_info *fi = F2FS_I(inode);
+- struct extent_tree *et = fi->extent_tree[EX_READ];
+- struct extent_info *ei;
+-
+- if (!et)
+- return true;
++ struct f2fs_extent *i_ext = &F2FS_INODE(ipage)->i_ext;
++ struct extent_info ei;
+
+- ei = &et->largest;
+- if (!ei->len)
+- return true;
++ get_read_extent_info(&ei, i_ext);
+
+- /* Let's drop, if checkpoint got corrupted. */
+- if (is_set_ckpt_flags(sbi, CP_ERROR_FLAG)) {
+- ei->len = 0;
+- et->largest_updated = true;
++ if (!ei.len)
+ return true;
+- }
+
+- if (!f2fs_is_valid_blkaddr(sbi, ei->blk, DATA_GENERIC_ENHANCE) ||
+- !f2fs_is_valid_blkaddr(sbi, ei->blk + ei->len - 1,
++ if (!f2fs_is_valid_blkaddr(sbi, ei.blk, DATA_GENERIC_ENHANCE) ||
++ !f2fs_is_valid_blkaddr(sbi, ei.blk + ei.len - 1,
+ DATA_GENERIC_ENHANCE)) {
+ f2fs_warn(sbi, "%s: inode (ino=%lx) extent info [%u, %u, %u] is incorrect, run fsck to fix",
+ __func__, inode->i_ino,
+- ei->blk, ei->fofs, ei->len);
++ ei.blk, ei.fofs, ei.len);
+ return false;
+ }
+ return true;
+@@ -394,24 +384,22 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
+
+ if (!__may_extent_tree(inode, EX_READ)) {
+ /* drop largest read extent */
+- if (i_ext && i_ext->len) {
++ if (i_ext->len) {
+ f2fs_wait_on_page_writeback(ipage, NODE, true, true);
+ i_ext->len = 0;
+ set_page_dirty(ipage);
+ }
+- goto out;
++ set_inode_flag(inode, FI_NO_EXTENT);
++ return;
+ }
+
+ et = __grab_extent_tree(inode, EX_READ);
+
+- if (!i_ext || !i_ext->len)
+- goto out;
+-
+ get_read_extent_info(&ei, i_ext);
+
+ write_lock(&et->lock);
+- if (atomic_read(&et->node_cnt))
+- goto unlock_out;
++ if (atomic_read(&et->node_cnt) || !ei.len)
++ goto skip;
+
+ en = __attach_extent_node(sbi, et, &ei, NULL,
+ &et->root.rb_root.rb_node, true);
+@@ -423,11 +411,13 @@ void f2fs_init_read_extent_tree(struct inode *inode, struct page *ipage)
+ list_add_tail(&en->list, &eti->extent_list);
+ spin_unlock(&eti->extent_lock);
+ }
+-unlock_out:
++skip:
++ /* Let's drop, if checkpoint got corrupted. */
++ if (f2fs_cp_error(sbi)) {
++ et->largest.len = 0;
++ et->largest_updated = true;
++ }
+ write_unlock(&et->lock);
+-out:
+- if (!F2FS_I(inode)->extent_tree[EX_READ])
+- set_inode_flag(inode, FI_NO_EXTENT);
+ }
+
+ void f2fs_init_age_extent_tree(struct inode *inode)
+diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
+index 66680159a29680..5556ab491368da 100644
+--- a/fs/f2fs/f2fs.h
++++ b/fs/f2fs/f2fs.h
+@@ -4195,7 +4195,7 @@ void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
+ /*
+ * extent_cache.c
+ */
+-bool sanity_check_extent_cache(struct inode *inode);
++bool sanity_check_extent_cache(struct inode *inode, struct page *ipage);
+ void f2fs_init_extent_tree(struct inode *inode);
+ void f2fs_drop_extent_tree(struct inode *inode);
+ void f2fs_destroy_extent_node(struct inode *inode);
+diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
+index b2951cd930d808..448c75e80b89e6 100644
+--- a/fs/f2fs/gc.c
++++ b/fs/f2fs/gc.c
+@@ -1566,6 +1566,16 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+ continue;
+ }
+
++ if (f2fs_has_inline_data(inode)) {
++ iput(inode);
++ set_sbi_flag(sbi, SBI_NEED_FSCK);
++ f2fs_err_ratelimited(sbi,
++ "inode %lx has both inline_data flag and "
++ "data block, nid=%u, ofs_in_node=%u",
++ inode->i_ino, dni.nid, ofs_in_node);
++ continue;
++ }
++
+ err = f2fs_gc_pinned_control(inode, gc_type, segno);
+ if (err == -EAGAIN) {
+ iput(inode);
+diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
+index c6b55aedc27627..ed629dabbfda43 100644
+--- a/fs/f2fs/inode.c
++++ b/fs/f2fs/inode.c
+@@ -511,16 +511,16 @@ static int do_read_inode(struct inode *inode)
+
+ init_idisk_time(inode);
+
+- /* Need all the flag bits */
+- f2fs_init_read_extent_tree(inode, node_page);
+- f2fs_init_age_extent_tree(inode);
+-
+- if (!sanity_check_extent_cache(inode)) {
++ if (!sanity_check_extent_cache(inode, node_page)) {
+ f2fs_put_page(node_page, 1);
+ f2fs_handle_error(sbi, ERROR_CORRUPTED_INODE);
+ return -EFSCORRUPTED;
+ }
+
++ /* Need all the flag bits */
++ f2fs_init_read_extent_tree(inode, node_page);
++ f2fs_init_age_extent_tree(inode);
++
+ f2fs_put_page(node_page, 1);
+
+ stat_inc_inline_xattr(inode);
+diff --git a/fs/jfs/jfs_dmap.c b/fs/jfs/jfs_dmap.c
+index cb3cda1390adb1..5713994328cbcb 100644
+--- a/fs/jfs/jfs_dmap.c
++++ b/fs/jfs/jfs_dmap.c
+@@ -1626,6 +1626,8 @@ s64 dbDiscardAG(struct inode *ip, int agno, s64 minlen)
+ } else if (rc == -ENOSPC) {
+ /* search for next smaller log2 block */
+ l2nb = BLKSTOL2(nblocks) - 1;
++ if (unlikely(l2nb < 0))
++ break;
+ nblocks = 1LL << l2nb;
+ } else {
+ /* Trim any already allocated blocks */
+diff --git a/fs/jfs/jfs_dtree.c b/fs/jfs/jfs_dtree.c
+index 031d8f570f581f..5d3127ca68a42d 100644
+--- a/fs/jfs/jfs_dtree.c
++++ b/fs/jfs/jfs_dtree.c
+@@ -834,6 +834,8 @@ int dtInsert(tid_t tid, struct inode *ip,
+ * the full page.
+ */
+ DT_GETSEARCH(ip, btstack->top, bn, mp, p, index);
++ if (p->header.freelist == 0)
++ return -EINVAL;
+
+ /*
+ * insert entry for new key
+diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
+index 4822cfd6351c27..ded451a84b773b 100644
+--- a/fs/ntfs3/frecord.c
++++ b/fs/ntfs3/frecord.c
+@@ -1896,6 +1896,47 @@ enum REPARSE_SIGN ni_parse_reparse(struct ntfs_inode *ni, struct ATTRIB *attr,
+ return REPARSE_LINK;
+ }
+
++/*
++ * fiemap_fill_next_extent_k - a copy of fiemap_fill_next_extent
++ * but it accepts kernel address for fi_extents_start
++ */
++static int fiemap_fill_next_extent_k(struct fiemap_extent_info *fieinfo,
++ u64 logical, u64 phys, u64 len, u32 flags)
++{
++ struct fiemap_extent extent;
++ struct fiemap_extent __user *dest = fieinfo->fi_extents_start;
++
++ /* only count the extents */
++ if (fieinfo->fi_extents_max == 0) {
++ fieinfo->fi_extents_mapped++;
++ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
++ }
++
++ if (fieinfo->fi_extents_mapped >= fieinfo->fi_extents_max)
++ return 1;
++
++ if (flags & FIEMAP_EXTENT_DELALLOC)
++ flags |= FIEMAP_EXTENT_UNKNOWN;
++ if (flags & FIEMAP_EXTENT_DATA_ENCRYPTED)
++ flags |= FIEMAP_EXTENT_ENCODED;
++ if (flags & (FIEMAP_EXTENT_DATA_TAIL | FIEMAP_EXTENT_DATA_INLINE))
++ flags |= FIEMAP_EXTENT_NOT_ALIGNED;
++
++ memset(&extent, 0, sizeof(extent));
++ extent.fe_logical = logical;
++ extent.fe_physical = phys;
++ extent.fe_length = len;
++ extent.fe_flags = flags;
++
++ dest += fieinfo->fi_extents_mapped;
++ memcpy(dest, &extent, sizeof(extent));
++
++ fieinfo->fi_extents_mapped++;
++ if (fieinfo->fi_extents_mapped == fieinfo->fi_extents_max)
++ return 1;
++ return (flags & FIEMAP_EXTENT_LAST) ? 1 : 0;
++}
++
+ /*
+ * ni_fiemap - Helper for file_fiemap().
+ *
+@@ -1906,6 +1947,8 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
+ __u64 vbo, __u64 len)
+ {
+ int err = 0;
++ struct fiemap_extent __user *fe_u = fieinfo->fi_extents_start;
++ struct fiemap_extent *fe_k = NULL;
+ struct ntfs_sb_info *sbi = ni->mi.sbi;
+ u8 cluster_bits = sbi->cluster_bits;
+ struct runs_tree *run;
+@@ -1953,6 +1996,18 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
+ goto out;
+ }
+
++ /*
++ * To avoid lock problems replace pointer to user memory by pointer to kernel memory.
++ */
++ fe_k = kmalloc_array(fieinfo->fi_extents_max,
++ sizeof(struct fiemap_extent),
++ GFP_NOFS | __GFP_ZERO);
++ if (!fe_k) {
++ err = -ENOMEM;
++ goto out;
++ }
++ fieinfo->fi_extents_start = fe_k;
++
+ end = vbo + len;
+ alloc_size = le64_to_cpu(attr->nres.alloc_size);
+ if (end > alloc_size)
+@@ -2041,8 +2096,9 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
+ if (vbo + dlen >= end)
+ flags |= FIEMAP_EXTENT_LAST;
+
+- err = fiemap_fill_next_extent(fieinfo, vbo, lbo, dlen,
+- flags);
++ err = fiemap_fill_next_extent_k(fieinfo, vbo, lbo, dlen,
++ flags);
++
+ if (err < 0)
+ break;
+ if (err == 1) {
+@@ -2062,7 +2118,8 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
+ if (vbo + bytes >= end)
+ flags |= FIEMAP_EXTENT_LAST;
+
+- err = fiemap_fill_next_extent(fieinfo, vbo, lbo, bytes, flags);
++ err = fiemap_fill_next_extent_k(fieinfo, vbo, lbo, bytes,
++ flags);
+ if (err < 0)
+ break;
+ if (err == 1) {
+@@ -2075,7 +2132,19 @@ int ni_fiemap(struct ntfs_inode *ni, struct fiemap_extent_info *fieinfo,
+
+ up_read(run_lock);
+
++ /*
++ * Copy to user memory out of lock
++ */
++ if (copy_to_user(fe_u, fe_k,
++ fieinfo->fi_extents_max *
++ sizeof(struct fiemap_extent))) {
++ err = -EFAULT;
++ }
++
+ out:
++ /* Restore original pointer. */
++ fieinfo->fi_extents_start = fe_u;
++ kfree(fe_k);
+ return err;
+ }
+
+diff --git a/net/core/filter.c b/net/core/filter.c
+index 110692c1dd95a5..ab0455c64e49ad 100644
+--- a/net/core/filter.c
++++ b/net/core/filter.c
+@@ -2279,12 +2279,12 @@ static int __bpf_redirect_neigh_v6(struct sk_buff *skb, struct net_device *dev,
+
+ err = bpf_out_neigh_v6(net, skb, dev, nh);
+ if (unlikely(net_xmit_eval(err)))
+- dev->stats.tx_errors++;
++ DEV_STATS_INC(dev, tx_errors);
+ else
+ ret = NET_XMIT_SUCCESS;
+ goto out_xmit;
+ out_drop:
+- dev->stats.tx_errors++;
++ DEV_STATS_INC(dev, tx_errors);
+ kfree_skb(skb);
+ out_xmit:
+ return ret;
+@@ -2385,12 +2385,12 @@ static int __bpf_redirect_neigh_v4(struct sk_buff *skb, struct net_device *dev,
+
+ err = bpf_out_neigh_v4(net, skb, dev, nh);
+ if (unlikely(net_xmit_eval(err)))
+- dev->stats.tx_errors++;
++ DEV_STATS_INC(dev, tx_errors);
+ else
+ ret = NET_XMIT_SUCCESS;
+ goto out_xmit;
+ out_drop:
+- dev->stats.tx_errors++;
++ DEV_STATS_INC(dev, tx_errors);
+ kfree_skb(skb);
+ out_xmit:
+ return ret;
+diff --git a/net/ipv4/fou_core.c b/net/ipv4/fou_core.c
+index a8494f796dca33..0abbc413e0fe51 100644
+--- a/net/ipv4/fou_core.c
++++ b/net/ipv4/fou_core.c
+@@ -433,7 +433,7 @@ static struct sk_buff *gue_gro_receive(struct sock *sk,
+
+ offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads;
+ ops = rcu_dereference(offloads[proto]);
+- if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive))
++ if (!ops || !ops->callbacks.gro_receive)
+ goto out;
+
+ pp = call_gro_receive(ops->callbacks.gro_receive, head, skb);
+diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
+index 6d821a793045ee..56cd60d33a28e7 100644
+--- a/sound/soc/codecs/cs35l56-shared.c
++++ b/sound/soc/codecs/cs35l56-shared.c
+@@ -36,6 +36,7 @@ static const struct reg_sequence cs35l56_patch[] = {
+ { CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 },
+ { CS35L56_SWIRE_DP3_CH3_INPUT, 0x00000029 },
+ { CS35L56_SWIRE_DP3_CH4_INPUT, 0x00000028 },
++ { CS35L56_IRQ1_MASK_18, 0x1f7df0ff },
+
+ /* These are not reset by a soft-reset, so patch to defaults. */
+ { CS35L56_MAIN_RENDER_USER_MUTE, 0x00000000 },
+diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
+index d1bdb0b93bda0c..8cc2d4937f3403 100644
+--- a/sound/usb/mixer.c
++++ b/sound/usb/mixer.c
+@@ -2021,6 +2021,13 @@ static int parse_audio_feature_unit(struct mixer_build *state, int unitid,
+ bmaControls = ftr->bmaControls;
+ }
+
++ if (channels > 32) {
++ usb_audio_info(state->chip,
++ "usbmixer: too many channels (%d) in unit %d\n",
++ channels, unitid);
++ return -EINVAL;
++ }
++
+ /* parse the source unit */
+ err = parse_audio_unit(state, hdr->bSourceID);
+ if (err < 0)
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-15 14:05 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-15 14:05 UTC (permalink / raw
To: gentoo-commits
commit: 9d1ed4e98b1b3b271a2fd0986f46af57dfcf7bb5
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Thu Aug 15 14:04:39 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Thu Aug 15 14:04:39 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=9d1ed4e9
BMQ Sched Patch. USE=experimental
A new CPU scheduler developed from PDS(incld). Inspired by the scheduler in zircon.
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 8 +
5020_BMQ-and-PDS-io-scheduler-v6.9-r2.patch | 11843 ++++++++++++++++++++++++++
5021_BMQ-and-PDS-gentoo-defaults.patch | 13 +
3 files changed, 11864 insertions(+)
diff --git a/0000_README b/0000_README
index 845e8cff..b1582141 100644
--- a/0000_README
+++ b/0000_README
@@ -114,3 +114,11 @@ Desc: Add Gentoo Linux support config settings and defaults.
Patch: 5010_enable-cpu-optimizations-universal.patch
From: https://github.com/graysky2/kernel_compiler_patch
Desc: Kernel >= 5.15 patch enables gcc = v11.1+ optimizations for additional CPUs.
+
+Patch: 5020_BMQ-and-PDS-io-scheduler-v6.10-r2.patch
+From: https://github.com/Frogging-Family/linux-tkg
+Desc: BMQ(BitMap Queue) Scheduler. A new CPU scheduler developed from PDS(incld). Inspired by the scheduler in zircon.
+
+Patch: 5021_BMQ-and-PDS-gentoo-defaults.patch
+From: https://gitweb.gentoo.org/proj/linux-patches.git/
+Desc: Set defaults for BMQ. default to n
diff --git a/5020_BMQ-and-PDS-io-scheduler-v6.9-r2.patch b/5020_BMQ-and-PDS-io-scheduler-v6.9-r2.patch
new file mode 100644
index 00000000..77443a4c
--- /dev/null
+++ b/5020_BMQ-and-PDS-io-scheduler-v6.9-r2.patch
@@ -0,0 +1,11843 @@
+diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
+index 7fd43947832f..a07de351a5c2 100644
+--- a/Documentation/admin-guide/sysctl/kernel.rst
++++ b/Documentation/admin-guide/sysctl/kernel.rst
+@@ -1673,3 +1673,12 @@ is 10 seconds.
+
+ The softlockup threshold is (``2 * watchdog_thresh``). Setting this
+ tunable to zero will disable lockup detection altogether.
++
++yield_type:
++===========
++
++BMQ/PDS CPU scheduler only. This determines what type of yield calls
++to sched_yield() will be performed.
++
++ 0 - No yield.
++ 1 - Requeue task. (default)
+diff --git a/Documentation/scheduler/sched-BMQ.txt b/Documentation/scheduler/sched-BMQ.txt
+new file mode 100644
+index 000000000000..05c84eec0f31
+--- /dev/null
++++ b/Documentation/scheduler/sched-BMQ.txt
+@@ -0,0 +1,110 @@
++ BitMap queue CPU Scheduler
++ --------------------------
++
++CONTENT
++========
++
++ Background
++ Design
++ Overview
++ Task policy
++ Priority management
++ BitMap Queue
++ CPU Assignment and Migration
++
++
++Background
++==========
++
++BitMap Queue CPU scheduler, referred to as BMQ from here on, is an evolution
++of previous Priority and Deadline based Skiplist multiple queue scheduler(PDS),
++and inspired by Zircon scheduler. The goal of it is to keep the scheduler code
++simple, while efficiency and scalable for interactive tasks, such as desktop,
++movie playback and gaming etc.
++
++Design
++======
++
++Overview
++--------
++
++BMQ use per CPU run queue design, each CPU(logical) has it's own run queue,
++each CPU is responsible for scheduling the tasks that are putting into it's
++run queue.
++
++The run queue is a set of priority queues. Note that these queues are fifo
++queue for non-rt tasks or priority queue for rt tasks in data structure. See
++BitMap Queue below for details. BMQ is optimized for non-rt tasks in the fact
++that most applications are non-rt tasks. No matter the queue is fifo or
++priority, In each queue is an ordered list of runnable tasks awaiting execution
++and the data structures are the same. When it is time for a new task to run,
++the scheduler simply looks the lowest numbered queueue that contains a task,
++and runs the first task from the head of that queue. And per CPU idle task is
++also in the run queue, so the scheduler can always find a task to run on from
++its run queue.
++
++Each task will assigned the same timeslice(default 4ms) when it is picked to
++start running. Task will be reinserted at the end of the appropriate priority
++queue when it uses its whole timeslice. When the scheduler selects a new task
++from the priority queue it sets the CPU's preemption timer for the remainder of
++the previous timeslice. When that timer fires the scheduler will stop execution
++on that task, select another task and start over again.
++
++If a task blocks waiting for a shared resource then it's taken out of its
++priority queue and is placed in a wait queue for the shared resource. When it
++is unblocked it will be reinserted in the appropriate priority queue of an
++eligible CPU.
++
++Task policy
++-----------
++
++BMQ supports DEADLINE, FIFO, RR, NORMAL, BATCH and IDLE task policy like the
++mainline CFS scheduler. But BMQ is heavy optimized for non-rt task, that's
++NORMAL/BATCH/IDLE policy tasks. Below is the implementation detail of each
++policy.
++
++DEADLINE
++ It is squashed as priority 0 FIFO task.
++
++FIFO/RR
++ All RT tasks share one single priority queue in BMQ run queue designed. The
++complexity of insert operation is O(n). BMQ is not designed for system runs
++with major rt policy tasks.
++
++NORMAL/BATCH/IDLE
++ BATCH and IDLE tasks are treated as the same policy. They compete CPU with
++NORMAL policy tasks, but they just don't boost. To control the priority of
++NORMAL/BATCH/IDLE tasks, simply use nice level.
++
++ISO
++ ISO policy is not supported in BMQ. Please use nice level -20 NORMAL policy
++task instead.
++
++Priority management
++-------------------
++
++RT tasks have priority from 0-99. For non-rt tasks, there are three different
++factors used to determine the effective priority of a task. The effective
++priority being what is used to determine which queue it will be in.
++
++The first factor is simply the task’s static priority. Which is assigned from
++task's nice level, within [-20, 19] in userland's point of view and [0, 39]
++internally.
++
++The second factor is the priority boost. This is a value bounded between
++[-MAX_PRIORITY_ADJ, MAX_PRIORITY_ADJ] used to offset the base priority, it is
++modified by the following cases:
++
++*When a thread has used up its entire timeslice, always deboost its boost by
++increasing by one.
++*When a thread gives up cpu control(voluntary or non-voluntary) to reschedule,
++and its switch-in time(time after last switch and run) below the thredhold
++based on its priority boost, will boost its boost by decreasing by one buti is
++capped at 0 (won’t go negative).
++
++The intent in this system is to ensure that interactive threads are serviced
++quickly. These are usually the threads that interact directly with the user
++and cause user-perceivable latency. These threads usually do little work and
++spend most of their time blocked awaiting another user event. So they get the
++priority boost from unblocking while background threads that do most of the
++processing receive the priority penalty for using their entire timeslice.
+diff --git a/fs/proc/base.c b/fs/proc/base.c
+index 72a1acd03675..e69ab1acbdbd 100644
+--- a/fs/proc/base.c
++++ b/fs/proc/base.c
+@@ -481,7 +481,7 @@ static int proc_pid_schedstat(struct seq_file *m, struct pid_namespace *ns,
+ seq_puts(m, "0 0 0\n");
+ else
+ seq_printf(m, "%llu %llu %lu\n",
+- (unsigned long long)task->se.sum_exec_runtime,
++ (unsigned long long)tsk_seruntime(task),
+ (unsigned long long)task->sched_info.run_delay,
+ task->sched_info.pcount);
+
+diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h
+index 8874f681b056..59eb72bf7d5f 100644
+--- a/include/asm-generic/resource.h
++++ b/include/asm-generic/resource.h
+@@ -23,7 +23,7 @@
+ [RLIMIT_LOCKS] = { RLIM_INFINITY, RLIM_INFINITY }, \
+ [RLIMIT_SIGPENDING] = { 0, 0 }, \
+ [RLIMIT_MSGQUEUE] = { MQ_BYTES_MAX, MQ_BYTES_MAX }, \
+- [RLIMIT_NICE] = { 0, 0 }, \
++ [RLIMIT_NICE] = { 30, 30 }, \
+ [RLIMIT_RTPRIO] = { 0, 0 }, \
+ [RLIMIT_RTTIME] = { RLIM_INFINITY, RLIM_INFINITY }, \
+ }
+diff --git a/include/linux/sched.h b/include/linux/sched.h
+index a5f4b48fca18..b775fc92142a 100644
+--- a/include/linux/sched.h
++++ b/include/linux/sched.h
+@@ -774,9 +774,13 @@ struct task_struct {
+ struct alloc_tag *alloc_tag;
+ #endif
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_ALT)
+ int on_cpu;
++#endif
++
++#ifdef CONFIG_SMP
+ struct __call_single_node wake_entry;
++#ifndef CONFIG_SCHED_ALT
+ unsigned int wakee_flips;
+ unsigned long wakee_flip_decay_ts;
+ struct task_struct *last_wakee;
+@@ -790,6 +794,7 @@ struct task_struct {
+ */
+ int recent_used_cpu;
+ int wake_cpu;
++#endif /* !CONFIG_SCHED_ALT */
+ #endif
+ int on_rq;
+
+@@ -798,6 +803,19 @@ struct task_struct {
+ int normal_prio;
+ unsigned int rt_priority;
+
++#ifdef CONFIG_SCHED_ALT
++ u64 last_ran;
++ s64 time_slice;
++ struct list_head sq_node;
++#ifdef CONFIG_SCHED_BMQ
++ int boost_prio;
++#endif /* CONFIG_SCHED_BMQ */
++#ifdef CONFIG_SCHED_PDS
++ u64 deadline;
++#endif /* CONFIG_SCHED_PDS */
++ /* sched_clock time spent running */
++ u64 sched_time;
++#else /* !CONFIG_SCHED_ALT */
+ struct sched_entity se;
+ struct sched_rt_entity rt;
+ struct sched_dl_entity dl;
+@@ -809,6 +827,7 @@ struct task_struct {
+ unsigned long core_cookie;
+ unsigned int core_occupation;
+ #endif
++#endif /* !CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_CGROUP_SCHED
+ struct task_group *sched_task_group;
+@@ -1571,6 +1590,15 @@ struct task_struct {
+ */
+ };
+
++#ifdef CONFIG_SCHED_ALT
++#define tsk_seruntime(t) ((t)->sched_time)
++/* replace the uncertian rt_timeout with 0UL */
++#define tsk_rttimeout(t) (0UL)
++#else /* CFS */
++#define tsk_seruntime(t) ((t)->se.sum_exec_runtime)
++#define tsk_rttimeout(t) ((t)->rt.timeout)
++#endif /* !CONFIG_SCHED_ALT */
++
+ #define TASK_REPORT_IDLE (TASK_REPORT + 1)
+ #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
+
+diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
+index df3aca89d4f5..1df1f7635188 100644
+--- a/include/linux/sched/deadline.h
++++ b/include/linux/sched/deadline.h
+@@ -2,6 +2,25 @@
+ #ifndef _LINUX_SCHED_DEADLINE_H
+ #define _LINUX_SCHED_DEADLINE_H
+
++#ifdef CONFIG_SCHED_ALT
++
++static inline int dl_task(struct task_struct *p)
++{
++ return 0;
++}
++
++#ifdef CONFIG_SCHED_BMQ
++#define __tsk_deadline(p) (0UL)
++#endif
++
++#ifdef CONFIG_SCHED_PDS
++#define __tsk_deadline(p) ((((u64) ((p)->prio))<<56) | (p)->deadline)
++#endif
++
++#else
++
++#define __tsk_deadline(p) ((p)->dl.deadline)
++
+ /*
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+@@ -23,6 +42,7 @@ static inline int dl_task(struct task_struct *p)
+ {
+ return dl_prio(p->prio);
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ static inline bool dl_time_before(u64 a, u64 b)
+ {
+diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
+index ab83d85e1183..e66dfb553bc5 100644
+--- a/include/linux/sched/prio.h
++++ b/include/linux/sched/prio.h
+@@ -18,6 +18,28 @@
+ #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH)
+ #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2)
+
++#ifdef CONFIG_SCHED_ALT
++
++/* Undefine MAX_PRIO and DEFAULT_PRIO */
++#undef MAX_PRIO
++#undef DEFAULT_PRIO
++
++/* +/- priority levels from the base priority */
++#ifdef CONFIG_SCHED_BMQ
++#define MAX_PRIORITY_ADJ (12)
++#endif
++
++#ifdef CONFIG_SCHED_PDS
++#define MAX_PRIORITY_ADJ (0)
++#endif
++
++#define MIN_NORMAL_PRIO (128)
++#define NORMAL_PRIO_NUM (64)
++#define MAX_PRIO (MIN_NORMAL_PRIO + NORMAL_PRIO_NUM)
++#define DEFAULT_PRIO (MAX_PRIO - MAX_PRIORITY_ADJ - NICE_WIDTH / 2)
++
++#endif /* CONFIG_SCHED_ALT */
++
+ /*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
+index b2b9e6eb9683..09bd4d8758b2 100644
+--- a/include/linux/sched/rt.h
++++ b/include/linux/sched/rt.h
+@@ -24,8 +24,10 @@ static inline bool task_is_realtime(struct task_struct *tsk)
+
+ if (policy == SCHED_FIFO || policy == SCHED_RR)
+ return true;
++#ifndef CONFIG_SCHED_ALT
+ if (policy == SCHED_DEADLINE)
+ return true;
++#endif
+ return false;
+ }
+
+diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
+index 4237daa5ac7a..3cebd93c49c8 100644
+--- a/include/linux/sched/topology.h
++++ b/include/linux/sched/topology.h
+@@ -244,7 +244,8 @@ static inline bool cpus_share_resources(int this_cpu, int that_cpu)
+
+ #endif /* !CONFIG_SMP */
+
+-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
++#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) && \
++ !defined(CONFIG_SCHED_ALT)
+ extern void rebuild_sched_domains_energy(void);
+ #else
+ static inline void rebuild_sched_domains_energy(void)
+diff --git a/init/Kconfig b/init/Kconfig
+index febdea2afc3b..5b2295d7c8e5 100644
+--- a/init/Kconfig
++++ b/init/Kconfig
+@@ -638,6 +638,7 @@ config TASK_IO_ACCOUNTING
+
+ config PSI
+ bool "Pressure stall information tracking"
++ depends on !SCHED_ALT
+ select KERNFS
+ help
+ Collect metrics that indicate how overcommitted the CPU, memory,
+@@ -803,6 +804,7 @@ menu "Scheduler features"
+ config UCLAMP_TASK
+ bool "Enable utilization clamping for RT/FAIR tasks"
+ depends on CPU_FREQ_GOV_SCHEDUTIL
++ depends on !SCHED_ALT
+ help
+ This feature enables the scheduler to track the clamped utilization
+ of each CPU based on RUNNABLE tasks scheduled on that CPU.
+@@ -849,6 +851,35 @@ config UCLAMP_BUCKETS_COUNT
+
+ If in doubt, use the default value.
+
++menuconfig SCHED_ALT
++ bool "Alternative CPU Schedulers"
++ default y
++ help
++ This feature enable alternative CPU scheduler"
++
++if SCHED_ALT
++
++choice
++ prompt "Alternative CPU Scheduler"
++ default SCHED_BMQ
++
++config SCHED_BMQ
++ bool "BMQ CPU scheduler"
++ help
++ The BitMap Queue CPU scheduler for excellent interactivity and
++ responsiveness on the desktop and solid scalability on normal
++ hardware and commodity servers.
++
++config SCHED_PDS
++ bool "PDS CPU scheduler"
++ help
++ The Priority and Deadline based Skip list multiple queue CPU
++ Scheduler.
++
++endchoice
++
++endif
++
+ endmenu
+
+ #
+@@ -914,6 +945,7 @@ config NUMA_BALANCING
+ depends on ARCH_SUPPORTS_NUMA_BALANCING
+ depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+ depends on SMP && NUMA && MIGRATION && !PREEMPT_RT
++ depends on !SCHED_ALT
+ help
+ This option adds support for automatic NUMA aware memory/task placement.
+ The mechanism is quite primitive and is based on migrating memory when
+@@ -1015,6 +1047,7 @@ config FAIR_GROUP_SCHED
+ depends on CGROUP_SCHED
+ default CGROUP_SCHED
+
++if !SCHED_ALT
+ config CFS_BANDWIDTH
+ bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
+ depends on FAIR_GROUP_SCHED
+@@ -1037,6 +1070,7 @@ config RT_GROUP_SCHED
+ realtime bandwidth for them.
+ See Documentation/scheduler/sched-rt-group.rst for more information.
+
++endif #!SCHED_ALT
+ endif #CGROUP_SCHED
+
+ config SCHED_MM_CID
+@@ -1285,6 +1319,7 @@ config CHECKPOINT_RESTORE
+
+ config SCHED_AUTOGROUP
+ bool "Automatic process group scheduling"
++ depends on !SCHED_ALT
+ select CGROUPS
+ select CGROUP_SCHED
+ select FAIR_GROUP_SCHED
+diff --git a/init/init_task.c b/init/init_task.c
+index eeb110c65fe2..9d5ac5c3af07 100644
+--- a/init/init_task.c
++++ b/init/init_task.c
+@@ -70,9 +70,15 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
+ .stack = init_stack,
+ .usage = REFCOUNT_INIT(2),
+ .flags = PF_KTHREAD,
++#ifdef CONFIG_SCHED_ALT
++ .prio = DEFAULT_PRIO,
++ .static_prio = DEFAULT_PRIO,
++ .normal_prio = DEFAULT_PRIO,
++#else
+ .prio = MAX_PRIO - 20,
+ .static_prio = MAX_PRIO - 20,
+ .normal_prio = MAX_PRIO - 20,
++#endif
+ .policy = SCHED_NORMAL,
+ .cpus_ptr = &init_task.cpus_mask,
+ .user_cpus_ptr = NULL,
+@@ -85,6 +91,16 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
+ .restart_block = {
+ .fn = do_no_restart_syscall,
+ },
++#ifdef CONFIG_SCHED_ALT
++ .sq_node = LIST_HEAD_INIT(init_task.sq_node),
++#ifdef CONFIG_SCHED_BMQ
++ .boost_prio = 0,
++#endif
++#ifdef CONFIG_SCHED_PDS
++ .deadline = 0,
++#endif
++ .time_slice = HZ,
++#else
+ .se = {
+ .group_node = LIST_HEAD_INIT(init_task.se.group_node),
+ },
+@@ -92,6 +108,7 @@ struct task_struct init_task __aligned(L1_CACHE_BYTES) = {
+ .run_list = LIST_HEAD_INIT(init_task.rt.run_list),
+ .time_slice = RR_TIMESLICE,
+ },
++#endif
+ .tasks = LIST_HEAD_INIT(init_task.tasks),
+ #ifdef CONFIG_SMP
+ .pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
+diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
+index c2f1fd95a821..41654679b1b2 100644
+--- a/kernel/Kconfig.preempt
++++ b/kernel/Kconfig.preempt
+@@ -117,7 +117,7 @@ config PREEMPT_DYNAMIC
+
+ config SCHED_CORE
+ bool "Core Scheduling for SMT"
+- depends on SCHED_SMT
++ depends on SCHED_SMT && !SCHED_ALT
+ help
+ This option permits Core Scheduling, a means of coordinated task
+ selection across SMT siblings. When enabled -- see
+diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
+index c12b9fdb22a4..f7fa31c1be91 100644
+--- a/kernel/cgroup/cpuset.c
++++ b/kernel/cgroup/cpuset.c
+@@ -846,7 +846,7 @@ static int validate_change(struct cpuset *cur, struct cpuset *trial)
+ return ret;
+ }
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_ALT)
+ /*
+ * Helper routine for generate_sched_domains().
+ * Do cpusets a, b have overlapping effective cpus_allowed masks?
+@@ -1245,7 +1245,7 @@ static void rebuild_sched_domains_locked(void)
+ /* Have scheduler rebuild the domains */
+ partition_and_rebuild_sched_domains(ndoms, doms, attr);
+ }
+-#else /* !CONFIG_SMP */
++#else /* !CONFIG_SMP || CONFIG_SCHED_ALT */
+ static void rebuild_sched_domains_locked(void)
+ {
+ }
+@@ -3301,12 +3301,15 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
+ goto out_unlock;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(task)) {
+ cs->nr_migrate_dl_tasks++;
+ cs->sum_migrate_dl_bw += task->dl.dl_bw;
+ }
++#endif
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (!cs->nr_migrate_dl_tasks)
+ goto out_success;
+
+@@ -3327,6 +3330,7 @@ static int cpuset_can_attach(struct cgroup_taskset *tset)
+ }
+
+ out_success:
++#endif
+ /*
+ * Mark attach is in progress. This makes validate_change() fail
+ * changes which zero cpus/mems_allowed.
+@@ -3350,12 +3354,14 @@ static void cpuset_cancel_attach(struct cgroup_taskset *tset)
+ if (!cs->attach_in_progress)
+ wake_up(&cpuset_attach_wq);
+
++#ifndef CONFIG_SCHED_ALT
+ if (cs->nr_migrate_dl_tasks) {
+ int cpu = cpumask_any(cs->effective_cpus);
+
+ dl_bw_free(cpu, cs->sum_migrate_dl_bw);
+ reset_migrate_dl_data(cs);
+ }
++#endif
+
+ mutex_unlock(&cpuset_mutex);
+ }
+diff --git a/kernel/delayacct.c b/kernel/delayacct.c
+index e039b0f99a0b..7fc16698a514 100644
+--- a/kernel/delayacct.c
++++ b/kernel/delayacct.c
+@@ -149,7 +149,7 @@ int delayacct_add_tsk(struct taskstats *d, struct task_struct *tsk)
+ */
+ t1 = tsk->sched_info.pcount;
+ t2 = tsk->sched_info.run_delay;
+- t3 = tsk->se.sum_exec_runtime;
++ t3 = tsk_seruntime(tsk);
+
+ d->cpu_count += t1;
+
+diff --git a/kernel/exit.c b/kernel/exit.c
+index 81fcee45d630..76076803a464 100644
+--- a/kernel/exit.c
++++ b/kernel/exit.c
+@@ -175,7 +175,7 @@ static void __exit_signal(struct task_struct *tsk)
+ sig->curr_target = next_thread(tsk);
+ }
+
+- add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
++ add_device_randomness((const void*) &tsk_seruntime(tsk),
+ sizeof(unsigned long long));
+
+ /*
+@@ -196,7 +196,7 @@ static void __exit_signal(struct task_struct *tsk)
+ sig->inblock += task_io_get_inblock(tsk);
+ sig->oublock += task_io_get_oublock(tsk);
+ task_io_accounting_add(&sig->ioac, &tsk->ioac);
+- sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
++ sig->sum_sched_runtime += tsk_seruntime(tsk);
+ sig->nr_threads--;
+ __unhash_process(tsk, group_dead);
+ write_sequnlock(&sig->stats_lock);
+diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
+index 88d08eeb8bc0..03e8793badfc 100644
+--- a/kernel/locking/rtmutex.c
++++ b/kernel/locking/rtmutex.c
+@@ -363,7 +363,7 @@ waiter_update_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
+ lockdep_assert(RB_EMPTY_NODE(&waiter->tree.entry));
+
+ waiter->tree.prio = __waiter_prio(task);
+- waiter->tree.deadline = task->dl.deadline;
++ waiter->tree.deadline = __tsk_deadline(task);
+ }
+
+ /*
+@@ -384,16 +384,20 @@ waiter_clone_prio(struct rt_mutex_waiter *waiter, struct task_struct *task)
+ * Only use with rt_waiter_node_{less,equal}()
+ */
+ #define task_to_waiter_node(p) \
+- &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
++ &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = __tsk_deadline(p) }
+ #define task_to_waiter(p) \
+ &(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
+
+ static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
+ {
++#ifdef CONFIG_SCHED_PDS
++ return (left->deadline < right->deadline);
++#else
+ if (left->prio < right->prio)
+ return 1;
+
++#ifndef CONFIG_SCHED_BMQ
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+@@ -402,16 +406,22 @@ static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
+ */
+ if (dl_prio(left->prio))
+ return dl_time_before(left->deadline, right->deadline);
++#endif
+
+ return 0;
++#endif
+ }
+
+ static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
+ {
++#ifdef CONFIG_SCHED_PDS
++ return (left->deadline == right->deadline);
++#else
+ if (left->prio != right->prio)
+ return 0;
+
++#ifndef CONFIG_SCHED_BMQ
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+@@ -420,8 +430,10 @@ static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
+ */
+ if (dl_prio(left->prio))
+ return left->deadline == right->deadline;
++#endif
+
+ return 1;
++#endif
+ }
+
+ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
+diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
+index 976092b7bd45..31d587c16ec1 100644
+--- a/kernel/sched/Makefile
++++ b/kernel/sched/Makefile
+@@ -28,7 +28,12 @@ endif
+ # These compilation units have roughly the same size and complexity - so their
+ # build parallelizes well and finishes roughly at once:
+ #
++ifdef CONFIG_SCHED_ALT
++obj-y += alt_core.o
++obj-$(CONFIG_SCHED_DEBUG) += alt_debug.o
++else
+ obj-y += core.o
+ obj-y += fair.o
++endif
+ obj-y += build_policy.o
+ obj-y += build_utility.o
+diff --git a/kernel/sched/alt_core.c b/kernel/sched/alt_core.c
+new file mode 100644
+index 000000000000..6fa0058d2649
+--- /dev/null
++++ b/kernel/sched/alt_core.c
+@@ -0,0 +1,8809 @@
++/*
++ * kernel/sched/alt_core.c
++ *
++ * Core alternative kernel scheduler code and related syscalls
++ *
++ * Copyright (C) 1991-2002 Linus Torvalds
++ *
++ * 2009-08-13 Brainfuck deadline scheduling policy by Con Kolivas deletes
++ * a whole lot of those previous things.
++ * 2017-09-06 Priority and Deadline based Skip list multiple queue kernel
++ * scheduler by Alfred Chen.
++ * 2019-02-20 BMQ(BitMap Queue) kernel scheduler by Alfred Chen.
++ */
++#include <linux/sched/clock.h>
++#include <linux/sched/cputime.h>
++#include <linux/sched/debug.h>
++#include <linux/sched/hotplug.h>
++#include <linux/sched/init.h>
++#include <linux/sched/isolation.h>
++#include <linux/sched/loadavg.h>
++#include <linux/sched/mm.h>
++#include <linux/sched/nohz.h>
++#include <linux/sched/stat.h>
++#include <linux/sched/wake_q.h>
++
++#include <linux/blkdev.h>
++#include <linux/context_tracking.h>
++#include <linux/cpuset.h>
++#include <linux/delayacct.h>
++#include <linux/init_task.h>
++#include <linux/kcov.h>
++#include <linux/kprobes.h>
++#include <linux/nmi.h>
++#include <linux/rseq.h>
++#include <linux/scs.h>
++
++#include <uapi/linux/sched/types.h>
++
++#include <asm/irq_regs.h>
++#include <asm/switch_to.h>
++
++#define CREATE_TRACE_POINTS
++#include <trace/events/sched.h>
++#include <trace/events/ipi.h>
++#undef CREATE_TRACE_POINTS
++
++#include "sched.h"
++#include "smp.h"
++
++#include "pelt.h"
++
++#include "../../io_uring/io-wq.h"
++#include "../smpboot.h"
++
++EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu);
++EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask);
++
++/*
++ * Export tracepoints that act as a bare tracehook (ie: have no trace event
++ * associated with them) to allow external modules to probe them.
++ */
++EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
++
++#ifdef CONFIG_SCHED_DEBUG
++#define sched_feat(x) (1)
++/*
++ * Print a warning if need_resched is set for the given duration (if
++ * LATENCY_WARN is enabled).
++ *
++ * If sysctl_resched_latency_warn_once is set, only one warning will be shown
++ * per boot.
++ */
++__read_mostly int sysctl_resched_latency_warn_ms = 100;
++__read_mostly int sysctl_resched_latency_warn_once = 1;
++#else
++#define sched_feat(x) (0)
++#endif /* CONFIG_SCHED_DEBUG */
++
++#define ALT_SCHED_VERSION "v6.10-r2"
++
++/* rt_prio(prio) defined in include/linux/sched/rt.h */
++#define rt_task(p) rt_prio((p)->prio)
++#define rt_policy(policy) ((policy) == SCHED_FIFO || (policy) == SCHED_RR)
++#define task_has_rt_policy(p) (rt_policy((p)->policy))
++
++#define STOP_PRIO (MAX_RT_PRIO - 1)
++
++/*
++ * Time slice
++ * (default: 4 msec, units: nanoseconds)
++ */
++unsigned int sysctl_sched_base_slice __read_mostly = (4 << 20);
++
++#include "alt_core.h"
++#include "alt_topology.h"
++
++struct affinity_context {
++ const struct cpumask *new_mask;
++ struct cpumask *user_mask;
++ unsigned int flags;
++};
++
++/* Reschedule if less than this many μs left */
++#define RESCHED_NS (100 << 10)
++
++/**
++ * sched_yield_type - Type of sched_yield() will be performed.
++ * 0: No yield.
++ * 1: Requeue task. (default)
++ */
++int sched_yield_type __read_mostly = 1;
++
++#ifdef CONFIG_SMP
++cpumask_t sched_rq_pending_mask ____cacheline_aligned_in_smp;
++
++DEFINE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
++DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_llc_mask);
++DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_topo_end_mask);
++
++#ifdef CONFIG_SCHED_SMT
++DEFINE_STATIC_KEY_FALSE(sched_smt_present);
++EXPORT_SYMBOL_GPL(sched_smt_present);
++
++cpumask_t sched_smt_mask ____cacheline_aligned_in_smp;
++#endif
++
++/*
++ * Keep a unique ID per domain (we use the first CPUs number in the cpumask of
++ * the domain), this allows us to quickly tell if two cpus are in the same cache
++ * domain, see cpus_share_cache().
++ */
++DEFINE_PER_CPU(int, sd_llc_id);
++#endif /* CONFIG_SMP */
++
++static DEFINE_MUTEX(sched_hotcpu_mutex);
++
++DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
++
++#ifndef prepare_arch_switch
++# define prepare_arch_switch(next) do { } while (0)
++#endif
++#ifndef finish_arch_post_lock_switch
++# define finish_arch_post_lock_switch() do { } while (0)
++#endif
++
++static cpumask_t sched_preempt_mask[SCHED_QUEUE_BITS + 2] ____cacheline_aligned_in_smp;
++
++cpumask_t *const sched_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS - 1];
++cpumask_t *const sched_sg_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS];
++cpumask_t *const sched_pcore_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS];
++cpumask_t *const sched_ecore_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS + 1];
++
++/* task function */
++static inline const struct cpumask *task_user_cpus(struct task_struct *p)
++{
++ if (!p->user_cpus_ptr)
++ return cpu_possible_mask; /* &init_task.cpus_mask */
++ return p->user_cpus_ptr;
++}
++
++/* sched_queue related functions */
++static inline void sched_queue_init(struct sched_queue *q)
++{
++ int i;
++
++ bitmap_zero(q->bitmap, SCHED_QUEUE_BITS);
++ for(i = 0; i < SCHED_LEVELS; i++)
++ INIT_LIST_HEAD(&q->heads[i]);
++}
++
++/*
++ * Init idle task and put into queue structure of rq
++ * IMPORTANT: may be called multiple times for a single cpu
++ */
++static inline void sched_queue_init_idle(struct sched_queue *q,
++ struct task_struct *idle)
++{
++ INIT_LIST_HEAD(&q->heads[IDLE_TASK_SCHED_PRIO]);
++ list_add_tail(&idle->sq_node, &q->heads[IDLE_TASK_SCHED_PRIO]);
++ idle->on_rq = TASK_ON_RQ_QUEUED;
++}
++
++#define CLEAR_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
++ if (low < pr && pr <= high) \
++ cpumask_clear_cpu(cpu, sched_preempt_mask + pr);
++
++#define SET_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
++ if (low < pr && pr <= high) \
++ cpumask_set_cpu(cpu, sched_preempt_mask + pr);
++
++static atomic_t sched_prio_record = ATOMIC_INIT(0);
++
++/* water mark related functions */
++static inline void update_sched_preempt_mask(struct rq *rq)
++{
++ int prio = find_first_bit(rq->queue.bitmap, SCHED_QUEUE_BITS);
++ int last_prio = rq->prio;
++ int cpu, pr;
++
++ if (prio == last_prio)
++ return;
++
++ rq->prio = prio;
++#ifdef CONFIG_SCHED_PDS
++ rq->prio_idx = sched_prio2idx(rq->prio, rq);
++#endif
++ cpu = cpu_of(rq);
++ pr = atomic_read(&sched_prio_record);
++
++ if (prio < last_prio) {
++ if (IDLE_TASK_SCHED_PRIO == last_prio) {
++ rq->clear_idle_mask_func(cpu, sched_idle_mask);
++ last_prio -= 2;
++ }
++ CLEAR_CACHED_PREEMPT_MASK(pr, prio, last_prio, cpu);
++
++ return;
++ }
++ /* last_prio < prio */
++ if (IDLE_TASK_SCHED_PRIO == prio) {
++ rq->set_idle_mask_func(cpu, sched_idle_mask);
++ prio -= 2;
++ }
++ SET_CACHED_PREEMPT_MASK(pr, last_prio, prio, cpu);
++}
++
++/*
++ * Serialization rules:
++ *
++ * Lock order:
++ *
++ * p->pi_lock
++ * rq->lock
++ * hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
++ *
++ * rq1->lock
++ * rq2->lock where: rq1 < rq2
++ *
++ * Regular state:
++ *
++ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
++ * local CPU's rq->lock, it optionally removes the task from the runqueue and
++ * always looks at the local rq data structures to find the most eligible task
++ * to run next.
++ *
++ * Task enqueue is also under rq->lock, possibly taken from another CPU.
++ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
++ * the local CPU to avoid bouncing the runqueue state around [ see
++ * ttwu_queue_wakelist() ]
++ *
++ * Task wakeup, specifically wakeups that involve migration, are horribly
++ * complicated to avoid having to take two rq->locks.
++ *
++ * Special state:
++ *
++ * System-calls and anything external will use task_rq_lock() which acquires
++ * both p->pi_lock and rq->lock. As a consequence the state they change is
++ * stable while holding either lock:
++ *
++ * - sched_setaffinity()/
++ * set_cpus_allowed_ptr(): p->cpus_ptr, p->nr_cpus_allowed
++ * - set_user_nice(): p->se.load, p->*prio
++ * - __sched_setscheduler(): p->sched_class, p->policy, p->*prio,
++ * p->se.load, p->rt_priority,
++ * p->dl.dl_{runtime, deadline, period, flags, bw, density}
++ * - sched_setnuma(): p->numa_preferred_nid
++ * - sched_move_task(): p->sched_task_group
++ * - uclamp_update_active() p->uclamp*
++ *
++ * p->state <- TASK_*:
++ *
++ * is changed locklessly using set_current_state(), __set_current_state() or
++ * set_special_state(), see their respective comments, or by
++ * try_to_wake_up(). This latter uses p->pi_lock to serialize against
++ * concurrent self.
++ *
++ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
++ *
++ * is set by activate_task() and cleared by deactivate_task(), under
++ * rq->lock. Non-zero indicates the task is runnable, the special
++ * ON_RQ_MIGRATING state is used for migration without holding both
++ * rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
++ *
++ * p->on_cpu <- { 0, 1 }:
++ *
++ * is set by prepare_task() and cleared by finish_task() such that it will be
++ * set before p is scheduled-in and cleared after p is scheduled-out, both
++ * under rq->lock. Non-zero indicates the task is running on its CPU.
++ *
++ * [ The astute reader will observe that it is possible for two tasks on one
++ * CPU to have ->on_cpu = 1 at the same time. ]
++ *
++ * task_cpu(p): is changed by set_task_cpu(), the rules are:
++ *
++ * - Don't call set_task_cpu() on a blocked task:
++ *
++ * We don't care what CPU we're not running on, this simplifies hotplug,
++ * the CPU assignment of blocked tasks isn't required to be valid.
++ *
++ * - for try_to_wake_up(), called under p->pi_lock:
++ *
++ * This allows try_to_wake_up() to only take one rq->lock, see its comment.
++ *
++ * - for migration called under rq->lock:
++ * [ see task_on_rq_migrating() in task_rq_lock() ]
++ *
++ * o move_queued_task()
++ * o detach_task()
++ *
++ * - for migration called under double_rq_lock():
++ *
++ * o __migrate_swap_task()
++ * o push_rt_task() / pull_rt_task()
++ * o push_dl_task() / pull_dl_task()
++ * o dl_task_offline_migration()
++ *
++ */
++
++/*
++ * Context: p->pi_lock
++ */
++static inline struct rq *__task_access_lock(struct task_struct *p, raw_spinlock_t **plock)
++{
++ struct rq *rq;
++ for (;;) {
++ rq = task_rq(p);
++ if (p->on_cpu || task_on_rq_queued(p)) {
++ raw_spin_lock(&rq->lock);
++ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
++ *plock = &rq->lock;
++ return rq;
++ }
++ raw_spin_unlock(&rq->lock);
++ } else if (task_on_rq_migrating(p)) {
++ do {
++ cpu_relax();
++ } while (unlikely(task_on_rq_migrating(p)));
++ } else {
++ *plock = NULL;
++ return rq;
++ }
++ }
++}
++
++static inline void __task_access_unlock(struct task_struct *p, raw_spinlock_t *lock)
++{
++ if (NULL != lock)
++ raw_spin_unlock(lock);
++}
++
++static inline struct rq *
++task_access_lock_irqsave(struct task_struct *p, raw_spinlock_t **plock, unsigned long *flags)
++{
++ struct rq *rq;
++ for (;;) {
++ rq = task_rq(p);
++ if (p->on_cpu || task_on_rq_queued(p)) {
++ raw_spin_lock_irqsave(&rq->lock, *flags);
++ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
++ *plock = &rq->lock;
++ return rq;
++ }
++ raw_spin_unlock_irqrestore(&rq->lock, *flags);
++ } else if (task_on_rq_migrating(p)) {
++ do {
++ cpu_relax();
++ } while (unlikely(task_on_rq_migrating(p)));
++ } else {
++ raw_spin_lock_irqsave(&p->pi_lock, *flags);
++ if (likely(!p->on_cpu && !p->on_rq && rq == task_rq(p))) {
++ *plock = &p->pi_lock;
++ return rq;
++ }
++ raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
++ }
++ }
++}
++
++static inline void
++task_access_unlock_irqrestore(struct task_struct *p, raw_spinlock_t *lock, unsigned long *flags)
++{
++ raw_spin_unlock_irqrestore(lock, *flags);
++}
++
++/*
++ * __task_rq_lock - lock the rq @p resides on.
++ */
++struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ lockdep_assert_held(&p->pi_lock);
++
++ for (;;) {
++ rq = task_rq(p);
++ raw_spin_lock(&rq->lock);
++ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
++ return rq;
++ raw_spin_unlock(&rq->lock);
++
++ while (unlikely(task_on_rq_migrating(p)))
++ cpu_relax();
++ }
++}
++
++/*
++ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
++ */
++struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(p->pi_lock)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ for (;;) {
++ raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
++ rq = task_rq(p);
++ raw_spin_lock(&rq->lock);
++ /*
++ * move_queued_task() task_rq_lock()
++ *
++ * ACQUIRE (rq->lock)
++ * [S] ->on_rq = MIGRATING [L] rq = task_rq()
++ * WMB (__set_task_cpu()) ACQUIRE (rq->lock);
++ * [S] ->cpu = new_cpu [L] task_rq()
++ * [L] ->on_rq
++ * RELEASE (rq->lock)
++ *
++ * If we observe the old CPU in task_rq_lock(), the acquire of
++ * the old rq->lock will fully serialize against the stores.
++ *
++ * If we observe the new CPU in task_rq_lock(), the address
++ * dependency headed by '[L] rq = task_rq()' and the acquire
++ * will pair with the WMB to ensure we then also see migrating.
++ */
++ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
++ return rq;
++ }
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
++
++ while (unlikely(task_on_rq_migrating(p)))
++ cpu_relax();
++ }
++}
++
++static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock_irqsave(&rq->lock, rf->flags);
++}
++
++static inline void rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
++}
++
++DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
++ rq_lock_irqsave(_T->lock, &_T->rf),
++ rq_unlock_irqrestore(_T->lock, &_T->rf),
++ struct rq_flags rf)
++
++void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
++{
++ raw_spinlock_t *lock;
++
++ /* Matches synchronize_rcu() in __sched_core_enable() */
++ preempt_disable();
++
++ for (;;) {
++ lock = __rq_lockp(rq);
++ raw_spin_lock_nested(lock, subclass);
++ if (likely(lock == __rq_lockp(rq))) {
++ /* preempt_count *MUST* be > 1 */
++ preempt_enable_no_resched();
++ return;
++ }
++ raw_spin_unlock(lock);
++ }
++}
++
++void raw_spin_rq_unlock(struct rq *rq)
++{
++ raw_spin_unlock(rq_lockp(rq));
++}
++
++/*
++ * RQ-clock updating methods:
++ */
++
++static void update_rq_clock_task(struct rq *rq, s64 delta)
++{
++/*
++ * In theory, the compile should just see 0 here, and optimize out the call
++ * to sched_rt_avg_update. But I don't trust it...
++ */
++ s64 __maybe_unused steal = 0, irq_delta = 0;
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
++
++ /*
++ * Since irq_time is only updated on {soft,}irq_exit, we might run into
++ * this case when a previous update_rq_clock() happened inside a
++ * {soft,}irq region.
++ *
++ * When this happens, we stop ->clock_task and only update the
++ * prev_irq_time stamp to account for the part that fit, so that a next
++ * update will consume the rest. This ensures ->clock_task is
++ * monotonic.
++ *
++ * It does however cause some slight miss-attribution of {soft,}irq
++ * time, a more accurate solution would be to update the irq_time using
++ * the current rq->clock timestamp, except that would require using
++ * atomic ops.
++ */
++ if (irq_delta > delta)
++ irq_delta = delta;
++
++ rq->prev_irq_time += irq_delta;
++ delta -= irq_delta;
++ delayacct_irq(rq->curr, irq_delta);
++#endif
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ if (static_key_false((¶virt_steal_rq_enabled))) {
++ steal = paravirt_steal_clock(cpu_of(rq));
++ steal -= rq->prev_steal_time_rq;
++
++ if (unlikely(steal > delta))
++ steal = delta;
++
++ rq->prev_steal_time_rq += steal;
++ delta -= steal;
++ }
++#endif
++
++ rq->clock_task += delta;
++
++#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
++ if ((irq_delta + steal))
++ update_irq_load_avg(rq, irq_delta + steal);
++#endif
++}
++
++static inline void update_rq_clock(struct rq *rq)
++{
++ s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
++
++ if (unlikely(delta <= 0))
++ return;
++ rq->clock += delta;
++ sched_update_rq_clock(rq);
++ update_rq_clock_task(rq, delta);
++}
++
++/*
++ * RQ Load update routine
++ */
++#define RQ_LOAD_HISTORY_BITS (sizeof(s32) * 8ULL)
++#define RQ_UTIL_SHIFT (8)
++#define RQ_LOAD_HISTORY_TO_UTIL(l) (((l) >> (RQ_LOAD_HISTORY_BITS - 1 - RQ_UTIL_SHIFT)) & 0xff)
++
++#define LOAD_BLOCK(t) ((t) >> 17)
++#define LOAD_HALF_BLOCK(t) ((t) >> 16)
++#define BLOCK_MASK(t) ((t) & ((0x01 << 18) - 1))
++#define LOAD_BLOCK_BIT(b) (1UL << (RQ_LOAD_HISTORY_BITS - 1 - (b)))
++#define CURRENT_LOAD_BIT LOAD_BLOCK_BIT(0)
++
++static inline void rq_load_update(struct rq *rq)
++{
++ u64 time = rq->clock;
++ u64 delta = min(LOAD_BLOCK(time) - LOAD_BLOCK(rq->load_stamp), RQ_LOAD_HISTORY_BITS - 1);
++ u64 prev = !!(rq->load_history & CURRENT_LOAD_BIT);
++ u64 curr = !!rq->nr_running;
++
++ if (delta) {
++ rq->load_history = rq->load_history >> delta;
++
++ if (delta < RQ_UTIL_SHIFT) {
++ rq->load_block += (~BLOCK_MASK(rq->load_stamp)) * prev;
++ if (!!LOAD_HALF_BLOCK(rq->load_block) ^ curr)
++ rq->load_history ^= LOAD_BLOCK_BIT(delta);
++ }
++
++ rq->load_block = BLOCK_MASK(time) * prev;
++ } else {
++ rq->load_block += (time - rq->load_stamp) * prev;
++ }
++ if (prev ^ curr)
++ rq->load_history ^= CURRENT_LOAD_BIT;
++ rq->load_stamp = time;
++}
++
++unsigned long rq_load_util(struct rq *rq, unsigned long max)
++{
++ return RQ_LOAD_HISTORY_TO_UTIL(rq->load_history) * (max >> RQ_UTIL_SHIFT);
++}
++
++#ifdef CONFIG_SMP
++unsigned long sched_cpu_util(int cpu)
++{
++ return rq_load_util(cpu_rq(cpu), arch_scale_cpu_capacity(cpu));
++}
++#endif /* CONFIG_SMP */
++
++#ifdef CONFIG_CPU_FREQ
++/**
++ * cpufreq_update_util - Take a note about CPU utilization changes.
++ * @rq: Runqueue to carry out the update for.
++ * @flags: Update reason flags.
++ *
++ * This function is called by the scheduler on the CPU whose utilization is
++ * being updated.
++ *
++ * It can only be called from RCU-sched read-side critical sections.
++ *
++ * The way cpufreq is currently arranged requires it to evaluate the CPU
++ * performance state (frequency/voltage) on a regular basis to prevent it from
++ * being stuck in a completely inadequate performance level for too long.
++ * That is not guaranteed to happen if the updates are only triggered from CFS
++ * and DL, though, because they may not be coming in if only RT tasks are
++ * active all the time (or there are RT tasks only).
++ *
++ * As a workaround for that issue, this function is called periodically by the
++ * RT sched class to trigger extra cpufreq updates to prevent it from stalling,
++ * but that really is a band-aid. Going forward it should be replaced with
++ * solutions targeted more specifically at RT tasks.
++ */
++static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
++{
++ struct update_util_data *data;
++
++#ifdef CONFIG_SMP
++ rq_load_update(rq);
++#endif
++ data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, cpu_of(rq)));
++ if (data)
++ data->func(data, rq_clock(rq), flags);
++}
++#else
++static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
++{
++#ifdef CONFIG_SMP
++ rq_load_update(rq);
++#endif
++}
++#endif /* CONFIG_CPU_FREQ */
++
++#ifdef CONFIG_NO_HZ_FULL
++/*
++ * Tick may be needed by tasks in the runqueue depending on their policy and
++ * requirements. If tick is needed, lets send the target an IPI to kick it out
++ * of nohz mode if necessary.
++ */
++static inline void sched_update_tick_dependency(struct rq *rq)
++{
++ int cpu = cpu_of(rq);
++
++ if (!tick_nohz_full_cpu(cpu))
++ return;
++
++ if (rq->nr_running < 2)
++ tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
++ else
++ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
++}
++#else /* !CONFIG_NO_HZ_FULL */
++static inline void sched_update_tick_dependency(struct rq *rq) { }
++#endif
++
++bool sched_task_on_rq(struct task_struct *p)
++{
++ return task_on_rq_queued(p);
++}
++
++unsigned long get_wchan(struct task_struct *p)
++{
++ unsigned long ip = 0;
++ unsigned int state;
++
++ if (!p || p == current)
++ return 0;
++
++ /* Only get wchan if task is blocked and we can keep it that way. */
++ raw_spin_lock_irq(&p->pi_lock);
++ state = READ_ONCE(p->__state);
++ smp_rmb(); /* see try_to_wake_up() */
++ if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq)
++ ip = __get_wchan(p);
++ raw_spin_unlock_irq(&p->pi_lock);
++
++ return ip;
++}
++
++/*
++ * Add/Remove/Requeue task to/from the runqueue routines
++ * Context: rq->lock
++ */
++#define __SCHED_DEQUEUE_TASK(p, rq, flags, func) \
++ sched_info_dequeue(rq, p); \
++ \
++ __list_del_entry(&p->sq_node); \
++ if (p->sq_node.prev == p->sq_node.next) { \
++ clear_bit(sched_idx2prio(p->sq_node.next - &rq->queue.heads[0], rq), \
++ rq->queue.bitmap); \
++ func; \
++ }
++
++#define __SCHED_ENQUEUE_TASK(p, rq, flags, func) \
++ sched_info_enqueue(rq, p); \
++ { \
++ int idx, prio; \
++ TASK_SCHED_PRIO_IDX(p, rq, idx, prio); \
++ list_add_tail(&p->sq_node, &rq->queue.heads[idx]); \
++ if (list_is_first(&p->sq_node, &rq->queue.heads[idx])) { \
++ set_bit(prio, rq->queue.bitmap); \
++ func; \
++ } \
++ }
++
++static inline void dequeue_task(struct task_struct *p, struct rq *rq, int flags)
++{
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++
++ /*printk(KERN_INFO "sched: dequeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: dequeue task reside on cpu%d from cpu%d\n",
++ task_cpu(p), cpu_of(rq));
++#endif
++
++ __SCHED_DEQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
++ --rq->nr_running;
++#ifdef CONFIG_SMP
++ if (1 == rq->nr_running)
++ cpumask_clear_cpu(cpu_of(rq), &sched_rq_pending_mask);
++#endif
++
++ sched_update_tick_dependency(rq);
++}
++
++static inline void enqueue_task(struct task_struct *p, struct rq *rq, int flags)
++{
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++
++ /*printk(KERN_INFO "sched: enqueue(%d) %px %d\n", cpu_of(rq), p, p->prio);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: enqueue task reside on cpu%d to cpu%d\n",
++ task_cpu(p), cpu_of(rq));
++#endif
++
++ __SCHED_ENQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
++ ++rq->nr_running;
++#ifdef CONFIG_SMP
++ if (2 == rq->nr_running)
++ cpumask_set_cpu(cpu_of(rq), &sched_rq_pending_mask);
++#endif
++
++ sched_update_tick_dependency(rq);
++}
++
++static inline void requeue_task(struct task_struct *p, struct rq *rq)
++{
++ struct list_head *node = &p->sq_node;
++ int deq_idx, idx, prio;
++
++ TASK_SCHED_PRIO_IDX(p, rq, idx, prio);
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++ /*printk(KERN_INFO "sched: requeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: cpu[%d] requeue task reside on cpu%d\n",
++ cpu_of(rq), task_cpu(p));
++#endif
++ if (list_is_last(node, &rq->queue.heads[idx]))
++ return;
++
++ __list_del_entry(node);
++ if (node->prev == node->next && (deq_idx = node->next - &rq->queue.heads[0]) != idx)
++ clear_bit(sched_idx2prio(deq_idx, rq), rq->queue.bitmap);
++
++ list_add_tail(node, &rq->queue.heads[idx]);
++ if (list_is_first(node, &rq->queue.heads[idx]))
++ set_bit(prio, rq->queue.bitmap);
++ update_sched_preempt_mask(rq);
++}
++
++/*
++ * cmpxchg based fetch_or, macro so it works for different integer types
++ */
++#define fetch_or(ptr, mask) \
++ ({ \
++ typeof(ptr) _ptr = (ptr); \
++ typeof(mask) _mask = (mask); \
++ typeof(*_ptr) _val = *_ptr; \
++ \
++ do { \
++ } while (!try_cmpxchg(_ptr, &_val, _val | _mask)); \
++ _val; \
++})
++
++#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
++/*
++ * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
++ * this avoids any races wrt polling state changes and thereby avoids
++ * spurious IPIs.
++ */
++static inline bool set_nr_and_not_polling(struct task_struct *p)
++{
++ struct thread_info *ti = task_thread_info(p);
++ return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
++}
++
++/*
++ * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
++ *
++ * If this returns true, then the idle task promises to call
++ * sched_ttwu_pending() and reschedule soon.
++ */
++static bool set_nr_if_polling(struct task_struct *p)
++{
++ struct thread_info *ti = task_thread_info(p);
++ typeof(ti->flags) val = READ_ONCE(ti->flags);
++
++ do {
++ if (!(val & _TIF_POLLING_NRFLAG))
++ return false;
++ if (val & _TIF_NEED_RESCHED)
++ return true;
++ } while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
++
++ return true;
++}
++
++#else
++static inline bool set_nr_and_not_polling(struct task_struct *p)
++{
++ set_tsk_need_resched(p);
++ return true;
++}
++
++#ifdef CONFIG_SMP
++static inline bool set_nr_if_polling(struct task_struct *p)
++{
++ return false;
++}
++#endif
++#endif
++
++static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
++{
++ struct wake_q_node *node = &task->wake_q;
++
++ /*
++ * Atomically grab the task, if ->wake_q is !nil already it means
++ * it's already queued (either by us or someone else) and will get the
++ * wakeup due to that.
++ *
++ * In order to ensure that a pending wakeup will observe our pending
++ * state, even in the failed case, an explicit smp_mb() must be used.
++ */
++ smp_mb__before_atomic();
++ if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
++ return false;
++
++ /*
++ * The head is context local, there can be no concurrency.
++ */
++ *head->lastp = node;
++ head->lastp = &node->next;
++ return true;
++}
++
++/**
++ * wake_q_add() - queue a wakeup for 'later' waking.
++ * @head: the wake_q_head to add @task to
++ * @task: the task to queue for 'later' wakeup
++ *
++ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
++ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
++ * instantly.
++ *
++ * This function must be used as-if it were wake_up_process(); IOW the task
++ * must be ready to be woken at this location.
++ */
++void wake_q_add(struct wake_q_head *head, struct task_struct *task)
++{
++ if (__wake_q_add(head, task))
++ get_task_struct(task);
++}
++
++/**
++ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
++ * @head: the wake_q_head to add @task to
++ * @task: the task to queue for 'later' wakeup
++ *
++ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
++ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
++ * instantly.
++ *
++ * This function must be used as-if it were wake_up_process(); IOW the task
++ * must be ready to be woken at this location.
++ *
++ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
++ * that already hold reference to @task can call the 'safe' version and trust
++ * wake_q to do the right thing depending whether or not the @task is already
++ * queued for wakeup.
++ */
++void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
++{
++ if (!__wake_q_add(head, task))
++ put_task_struct(task);
++}
++
++void wake_up_q(struct wake_q_head *head)
++{
++ struct wake_q_node *node = head->first;
++
++ while (node != WAKE_Q_TAIL) {
++ struct task_struct *task;
++
++ task = container_of(node, struct task_struct, wake_q);
++ /* task can safely be re-inserted now: */
++ node = node->next;
++ task->wake_q.next = NULL;
++
++ /*
++ * wake_up_process() executes a full barrier, which pairs with
++ * the queueing in wake_q_add() so as not to miss wakeups.
++ */
++ wake_up_process(task);
++ put_task_struct(task);
++ }
++}
++
++/*
++ * resched_curr - mark rq's current task 'to be rescheduled now'.
++ *
++ * On UP this means the setting of the need_resched flag, on SMP it
++ * might also involve a cross-CPU call to trigger the scheduler on
++ * the target CPU.
++ */
++static inline void resched_curr(struct rq *rq)
++{
++ struct task_struct *curr = rq->curr;
++ int cpu;
++
++ lockdep_assert_held(&rq->lock);
++
++ if (test_tsk_need_resched(curr))
++ return;
++
++ cpu = cpu_of(rq);
++ if (cpu == smp_processor_id()) {
++ set_tsk_need_resched(curr);
++ set_preempt_need_resched();
++ return;
++ }
++
++ if (set_nr_and_not_polling(curr))
++ smp_send_reschedule(cpu);
++ else
++ trace_sched_wake_idle_without_ipi(cpu);
++}
++
++void resched_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ if (cpu_online(cpu) || cpu == smp_processor_id())
++ resched_curr(cpu_rq(cpu));
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++}
++
++#ifdef CONFIG_SMP
++#ifdef CONFIG_NO_HZ_COMMON
++/*
++ * This routine will record that the CPU is going idle with tick stopped.
++ * This info will be used in performing idle load balancing in the future.
++ */
++void nohz_balance_enter_idle(int cpu) {}
++
++/*
++ * In the semi idle case, use the nearest busy CPU for migrating timers
++ * from an idle CPU. This is good for power-savings.
++ *
++ * We don't do similar optimization for completely idle system, as
++ * selecting an idle CPU will add more delays to the timers than intended
++ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
++ */
++int get_nohz_timer_target(void)
++{
++ int i, cpu = smp_processor_id(), default_cpu = -1;
++ struct cpumask *mask;
++ const struct cpumask *hk_mask;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
++ if (!idle_cpu(cpu))
++ return cpu;
++ default_cpu = cpu;
++ }
++
++ hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
++
++ for (mask = per_cpu(sched_cpu_topo_masks, cpu);
++ mask < per_cpu(sched_cpu_topo_end_mask, cpu); mask++)
++ for_each_cpu_and(i, mask, hk_mask)
++ if (!idle_cpu(i))
++ return i;
++
++ if (default_cpu == -1)
++ default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
++ cpu = default_cpu;
++
++ return cpu;
++}
++
++/*
++ * When add_timer_on() enqueues a timer into the timer wheel of an
++ * idle CPU then this timer might expire before the next timer event
++ * which is scheduled to wake up that CPU. In case of a completely
++ * idle system the next event might even be infinite time into the
++ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
++ * leaves the inner idle loop so the newly added timer is taken into
++ * account when the CPU goes back to idle and evaluates the timer
++ * wheel for the next timer event.
++ */
++static inline void wake_up_idle_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (cpu == smp_processor_id())
++ return;
++
++ /*
++ * Set TIF_NEED_RESCHED and send an IPI if in the non-polling
++ * part of the idle loop. This forces an exit from the idle loop
++ * and a round trip to schedule(). Now this could be optimized
++ * because a simple new idle loop iteration is enough to
++ * re-evaluate the next tick. Provided some re-ordering of tick
++ * nohz functions that would need to follow TIF_NR_POLLING
++ * clearing:
++ *
++ * - On most archs, a simple fetch_or on ti::flags with a
++ * "0" value would be enough to know if an IPI needs to be sent.
++ *
++ * - x86 needs to perform a last need_resched() check between
++ * monitor and mwait which doesn't take timers into account.
++ * There a dedicated TIF_TIMER flag would be required to
++ * fetch_or here and be checked along with TIF_NEED_RESCHED
++ * before mwait().
++ *
++ * However, remote timer enqueue is not such a frequent event
++ * and testing of the above solutions didn't appear to report
++ * much benefits.
++ */
++ if (set_nr_and_not_polling(rq->idle))
++ smp_send_reschedule(cpu);
++ else
++ trace_sched_wake_idle_without_ipi(cpu);
++}
++
++static inline bool wake_up_full_nohz_cpu(int cpu)
++{
++ /*
++ * We just need the target to call irq_exit() and re-evaluate
++ * the next tick. The nohz full kick at least implies that.
++ * If needed we can still optimize that later with an
++ * empty IRQ.
++ */
++ if (cpu_is_offline(cpu))
++ return true; /* Don't try to wake offline CPUs. */
++ if (tick_nohz_full_cpu(cpu)) {
++ if (cpu != smp_processor_id() ||
++ tick_nohz_tick_stopped())
++ tick_nohz_full_kick_cpu(cpu);
++ return true;
++ }
++
++ return false;
++}
++
++void wake_up_nohz_cpu(int cpu)
++{
++ if (!wake_up_full_nohz_cpu(cpu))
++ wake_up_idle_cpu(cpu);
++}
++
++static void nohz_csd_func(void *info)
++{
++ struct rq *rq = info;
++ int cpu = cpu_of(rq);
++ unsigned int flags;
++
++ /*
++ * Release the rq::nohz_csd.
++ */
++ flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
++ WARN_ON(!(flags & NOHZ_KICK_MASK));
++
++ rq->idle_balance = idle_cpu(cpu);
++ if (rq->idle_balance && !need_resched()) {
++ rq->nohz_idle_balance = flags;
++ raise_softirq_irqoff(SCHED_SOFTIRQ);
++ }
++}
++
++#endif /* CONFIG_NO_HZ_COMMON */
++#endif /* CONFIG_SMP */
++
++static inline void wakeup_preempt(struct rq *rq)
++{
++ if (sched_rq_first_task(rq) != rq->curr)
++ resched_curr(rq);
++}
++
++static __always_inline
++int __task_state_match(struct task_struct *p, unsigned int state)
++{
++ if (READ_ONCE(p->__state) & state)
++ return 1;
++
++ if (READ_ONCE(p->saved_state) & state)
++ return -1;
++
++ return 0;
++}
++
++static __always_inline
++int task_state_match(struct task_struct *p, unsigned int state)
++{
++ /*
++ * Serialize against current_save_and_set_rtlock_wait_state(),
++ * current_restore_rtlock_saved_state(), and __refrigerator().
++ */
++ guard(raw_spinlock_irq)(&p->pi_lock);
++
++ return __task_state_match(p, state);
++}
++
++/*
++ * wait_task_inactive - wait for a thread to unschedule.
++ *
++ * Wait for the thread to block in any of the states set in @match_state.
++ * If it changes, i.e. @p might have woken up, then return zero. When we
++ * succeed in waiting for @p to be off its CPU, we return a positive number
++ * (its total switch count). If a second call a short while later returns the
++ * same number, the caller can be sure that @p has remained unscheduled the
++ * whole time.
++ *
++ * The caller must ensure that the task *will* unschedule sometime soon,
++ * else this function might spin for a *long* time. This function can't
++ * be called with interrupts off, or it may introduce deadlock with
++ * smp_call_function() if an IPI is sent by the same process we are
++ * waiting to become inactive.
++ */
++unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
++{
++ unsigned long flags;
++ int running, queued, match;
++ unsigned long ncsw;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ for (;;) {
++ rq = task_rq(p);
++
++ /*
++ * If the task is actively running on another CPU
++ * still, just relax and busy-wait without holding
++ * any locks.
++ *
++ * NOTE! Since we don't hold any locks, it's not
++ * even sure that "rq" stays as the right runqueue!
++ * But we don't care, since this will return false
++ * if the runqueue has changed and p is actually now
++ * running somewhere else!
++ */
++ while (task_on_cpu(p)) {
++ if (!task_state_match(p, match_state))
++ return 0;
++ cpu_relax();
++ }
++
++ /*
++ * Ok, time to look more closely! We need the rq
++ * lock now, to be *sure*. If we're wrong, we'll
++ * just go back and repeat.
++ */
++ task_access_lock_irqsave(p, &lock, &flags);
++ trace_sched_wait_task(p);
++ running = task_on_cpu(p);
++ queued = p->on_rq;
++ ncsw = 0;
++ if ((match = __task_state_match(p, match_state))) {
++ /*
++ * When matching on p->saved_state, consider this task
++ * still queued so it will wait.
++ */
++ if (match < 0)
++ queued = 1;
++ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
++ }
++ task_access_unlock_irqrestore(p, lock, &flags);
++
++ /*
++ * If it changed from the expected state, bail out now.
++ */
++ if (unlikely(!ncsw))
++ break;
++
++ /*
++ * Was it really running after all now that we
++ * checked with the proper locks actually held?
++ *
++ * Oops. Go back and try again..
++ */
++ if (unlikely(running)) {
++ cpu_relax();
++ continue;
++ }
++
++ /*
++ * It's not enough that it's not actively running,
++ * it must be off the runqueue _entirely_, and not
++ * preempted!
++ *
++ * So if it was still runnable (but just not actively
++ * running right now), it's preempted, and we should
++ * yield - it could be a while.
++ */
++ if (unlikely(queued)) {
++ ktime_t to = NSEC_PER_SEC / HZ;
++
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
++ continue;
++ }
++
++ /*
++ * Ahh, all good. It wasn't running, and it wasn't
++ * runnable, which means that it will never become
++ * running in the future either. We're all done!
++ */
++ break;
++ }
++
++ return ncsw;
++}
++
++#ifdef CONFIG_SCHED_HRTICK
++/*
++ * Use HR-timers to deliver accurate preemption points.
++ */
++
++static void hrtick_clear(struct rq *rq)
++{
++ if (hrtimer_active(&rq->hrtick_timer))
++ hrtimer_cancel(&rq->hrtick_timer);
++}
++
++/*
++ * High-resolution timer tick.
++ * Runs from hardirq context with interrupts disabled.
++ */
++static enum hrtimer_restart hrtick(struct hrtimer *timer)
++{
++ struct rq *rq = container_of(timer, struct rq, hrtick_timer);
++
++ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
++
++ raw_spin_lock(&rq->lock);
++ resched_curr(rq);
++ raw_spin_unlock(&rq->lock);
++
++ return HRTIMER_NORESTART;
++}
++
++/*
++ * Use hrtick when:
++ * - enabled by features
++ * - hrtimer is actually high res
++ */
++static inline int hrtick_enabled(struct rq *rq)
++{
++ /**
++ * Alt schedule FW doesn't support sched_feat yet
++ if (!sched_feat(HRTICK))
++ return 0;
++ */
++ if (!cpu_active(cpu_of(rq)))
++ return 0;
++ return hrtimer_is_hres_active(&rq->hrtick_timer);
++}
++
++#ifdef CONFIG_SMP
++
++static void __hrtick_restart(struct rq *rq)
++{
++ struct hrtimer *timer = &rq->hrtick_timer;
++ ktime_t time = rq->hrtick_time;
++
++ hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
++}
++
++/*
++ * called from hardirq (IPI) context
++ */
++static void __hrtick_start(void *arg)
++{
++ struct rq *rq = arg;
++
++ raw_spin_lock(&rq->lock);
++ __hrtick_restart(rq);
++ raw_spin_unlock(&rq->lock);
++}
++
++/*
++ * Called to set the hrtick timer state.
++ *
++ * called with rq->lock held and irqs disabled
++ */
++static inline void hrtick_start(struct rq *rq, u64 delay)
++{
++ struct hrtimer *timer = &rq->hrtick_timer;
++ s64 delta;
++
++ /*
++ * Don't schedule slices shorter than 10000ns, that just
++ * doesn't make sense and can cause timer DoS.
++ */
++ delta = max_t(s64, delay, 10000LL);
++
++ rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
++
++ if (rq == this_rq())
++ __hrtick_restart(rq);
++ else
++ smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
++}
++
++#else
++/*
++ * Called to set the hrtick timer state.
++ *
++ * called with rq->lock held and irqs disabled
++ */
++static inline void hrtick_start(struct rq *rq, u64 delay)
++{
++ /*
++ * Don't schedule slices shorter than 10000ns, that just
++ * doesn't make sense. Rely on vruntime for fairness.
++ */
++ delay = max_t(u64, delay, 10000LL);
++ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
++ HRTIMER_MODE_REL_PINNED_HARD);
++}
++#endif /* CONFIG_SMP */
++
++static void hrtick_rq_init(struct rq *rq)
++{
++#ifdef CONFIG_SMP
++ INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
++#endif
++
++ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
++ rq->hrtick_timer.function = hrtick;
++}
++#else /* CONFIG_SCHED_HRTICK */
++static inline int hrtick_enabled(struct rq *rq)
++{
++ return 0;
++}
++
++static inline void hrtick_clear(struct rq *rq)
++{
++}
++
++static inline void hrtick_rq_init(struct rq *rq)
++{
++}
++#endif /* CONFIG_SCHED_HRTICK */
++
++static inline int __normal_prio(int policy, int rt_prio, int static_prio)
++{
++ return rt_policy(policy) ? (MAX_RT_PRIO - 1 - rt_prio) : static_prio;
++}
++
++/*
++ * Calculate the expected normal priority: i.e. priority
++ * without taking RT-inheritance into account. Might be
++ * boosted by interactivity modifiers. Changes upon fork,
++ * setprio syscalls, and whenever the interactivity
++ * estimator recalculates.
++ */
++static inline int normal_prio(struct task_struct *p)
++{
++ return __normal_prio(p->policy, p->rt_priority, p->static_prio);
++}
++
++/*
++ * Calculate the current priority, i.e. the priority
++ * taken into account by the scheduler. This value might
++ * be boosted by RT tasks as it will be RT if the task got
++ * RT-boosted. If not then it returns p->normal_prio.
++ */
++static int effective_prio(struct task_struct *p)
++{
++ p->normal_prio = normal_prio(p);
++ /*
++ * If we are RT tasks or we were boosted to RT priority,
++ * keep the priority unchanged. Otherwise, update priority
++ * to the normal priority:
++ */
++ if (!rt_prio(p->prio))
++ return p->normal_prio;
++ return p->prio;
++}
++
++/*
++ * activate_task - move a task to the runqueue.
++ *
++ * Context: rq->lock
++ */
++static void activate_task(struct task_struct *p, struct rq *rq)
++{
++ enqueue_task(p, rq, ENQUEUE_WAKEUP);
++
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
++ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
++
++ /*
++ * If in_iowait is set, the code below may not trigger any cpufreq
++ * utilization updates, so do it here explicitly with the IOWAIT flag
++ * passed.
++ */
++ cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT * p->in_iowait);
++}
++
++/*
++ * deactivate_task - remove a task from the runqueue.
++ *
++ * Context: rq->lock
++ */
++static inline void deactivate_task(struct task_struct *p, struct rq *rq)
++{
++ WRITE_ONCE(p->on_rq, 0);
++ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
++
++ dequeue_task(p, rq, DEQUEUE_SLEEP);
++
++ cpufreq_update_util(rq, 0);
++}
++
++static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
++{
++#ifdef CONFIG_SMP
++ /*
++ * After ->cpu is set up to a new value, task_access_lock(p, ...) can be
++ * successfully executed on another CPU. We must ensure that updates of
++ * per-task data have been completed by this moment.
++ */
++ smp_wmb();
++
++ WRITE_ONCE(task_thread_info(p)->cpu, cpu);
++#endif
++}
++
++#define SCA_CHECK 0x01
++#define SCA_USER 0x08
++
++#ifdef CONFIG_SMP
++
++void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
++{
++#ifdef CONFIG_SCHED_DEBUG
++ unsigned int state = READ_ONCE(p->__state);
++
++ /*
++ * We should never call set_task_cpu() on a blocked task,
++ * ttwu() will sort out the placement.
++ */
++ WARN_ON_ONCE(state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq);
++
++#ifdef CONFIG_LOCKDEP
++ /*
++ * The caller should hold either p->pi_lock or rq->lock, when changing
++ * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
++ *
++ * sched_move_task() holds both and thus holding either pins the cgroup,
++ * see task_group().
++ */
++ WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
++ lockdep_is_held(&task_rq(p)->lock)));
++#endif
++ /*
++ * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
++ */
++ WARN_ON_ONCE(!cpu_online(new_cpu));
++
++ WARN_ON_ONCE(is_migration_disabled(p));
++#endif
++ trace_sched_migrate_task(p, new_cpu);
++
++ if (task_cpu(p) != new_cpu)
++ {
++ rseq_migrate(p);
++ perf_event_task_migrate(p);
++ }
++
++ __set_task_cpu(p, new_cpu);
++}
++
++#define MDF_FORCE_ENABLED 0x80
++
++static void
++__do_set_cpus_ptr(struct task_struct *p, const struct cpumask *new_mask)
++{
++ /*
++ * This here violates the locking rules for affinity, since we're only
++ * supposed to change these variables while holding both rq->lock and
++ * p->pi_lock.
++ *
++ * HOWEVER, it magically works, because ttwu() is the only code that
++ * accesses these variables under p->pi_lock and only does so after
++ * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
++ * before finish_task().
++ *
++ * XXX do further audits, this smells like something putrid.
++ */
++ SCHED_WARN_ON(!p->on_cpu);
++ p->cpus_ptr = new_mask;
++}
++
++void migrate_disable(void)
++{
++ struct task_struct *p = current;
++ int cpu;
++
++ if (p->migration_disabled) {
++ p->migration_disabled++;
++ return;
++ }
++
++ guard(preempt)();
++ cpu = smp_processor_id();
++ if (cpumask_test_cpu(cpu, &p->cpus_mask)) {
++ cpu_rq(cpu)->nr_pinned++;
++ p->migration_disabled = 1;
++ p->migration_flags &= ~MDF_FORCE_ENABLED;
++
++ /*
++ * Violates locking rules! see comment in __do_set_cpus_ptr().
++ */
++ if (p->cpus_ptr == &p->cpus_mask)
++ __do_set_cpus_ptr(p, cpumask_of(cpu));
++ }
++}
++EXPORT_SYMBOL_GPL(migrate_disable);
++
++void migrate_enable(void)
++{
++ struct task_struct *p = current;
++
++ if (0 == p->migration_disabled)
++ return;
++
++ if (p->migration_disabled > 1) {
++ p->migration_disabled--;
++ return;
++ }
++
++ if (WARN_ON_ONCE(!p->migration_disabled))
++ return;
++
++ /*
++ * Ensure stop_task runs either before or after this, and that
++ * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
++ */
++ guard(preempt)();
++ /*
++ * Assumption: current should be running on allowed cpu
++ */
++ WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &p->cpus_mask));
++ if (p->cpus_ptr != &p->cpus_mask)
++ __do_set_cpus_ptr(p, &p->cpus_mask);
++ /*
++ * Mustn't clear migration_disabled() until cpus_ptr points back at the
++ * regular cpus_mask, otherwise things that race (eg.
++ * select_fallback_rq) get confused.
++ */
++ barrier();
++ p->migration_disabled = 0;
++ this_rq()->nr_pinned--;
++}
++EXPORT_SYMBOL_GPL(migrate_enable);
++
++static inline bool rq_has_pinned_tasks(struct rq *rq)
++{
++ return rq->nr_pinned;
++}
++
++/*
++ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
++ * __set_cpus_allowed_ptr() and select_fallback_rq().
++ */
++static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
++{
++ /* When not in the task's cpumask, no point in looking further. */
++ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
++ return false;
++
++ /* migrate_disabled() must be allowed to finish. */
++ if (is_migration_disabled(p))
++ return cpu_online(cpu);
++
++ /* Non kernel threads are not allowed during either online or offline. */
++ if (!(p->flags & PF_KTHREAD))
++ return cpu_active(cpu) && task_cpu_possible(cpu, p);
++
++ /* KTHREAD_IS_PER_CPU is always allowed. */
++ if (kthread_is_per_cpu(p))
++ return cpu_online(cpu);
++
++ /* Regular kernel threads don't get to stay during offline. */
++ if (cpu_dying(cpu))
++ return false;
++
++ /* But are allowed during online. */
++ return cpu_online(cpu);
++}
++
++/*
++ * This is how migration works:
++ *
++ * 1) we invoke migration_cpu_stop() on the target CPU using
++ * stop_one_cpu().
++ * 2) stopper starts to run (implicitly forcing the migrated thread
++ * off the CPU)
++ * 3) it checks whether the migrated task is still in the wrong runqueue.
++ * 4) if it's in the wrong runqueue then the migration thread removes
++ * it and puts it into the right queue.
++ * 5) stopper completes and stop_one_cpu() returns and the migration
++ * is done.
++ */
++
++/*
++ * move_queued_task - move a queued task to new rq.
++ *
++ * Returns (locked) new rq. Old rq's lock is released.
++ */
++struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
++{
++ int src_cpu;
++
++ lockdep_assert_held(&rq->lock);
++
++ src_cpu = cpu_of(rq);
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
++ dequeue_task(p, rq, 0);
++ set_task_cpu(p, new_cpu);
++ raw_spin_unlock(&rq->lock);
++
++ rq = cpu_rq(new_cpu);
++
++ raw_spin_lock(&rq->lock);
++ WARN_ON_ONCE(task_cpu(p) != new_cpu);
++
++ sched_mm_cid_migrate_to(rq, p, src_cpu);
++
++ sched_task_sanity_check(p, rq);
++ enqueue_task(p, rq, 0);
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
++ wakeup_preempt(rq);
++
++ return rq;
++}
++
++struct migration_arg {
++ struct task_struct *task;
++ int dest_cpu;
++};
++
++/*
++ * Move (not current) task off this CPU, onto the destination CPU. We're doing
++ * this because either it can't run here any more (set_cpus_allowed()
++ * away from this CPU, or CPU going down), or because we're
++ * attempting to rebalance this task on exec (sched_exec).
++ *
++ * So we race with normal scheduler movements, but that's OK, as long
++ * as the task is no longer on this CPU.
++ */
++static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
++{
++ /* Affinity changed (again). */
++ if (!is_cpu_allowed(p, dest_cpu))
++ return rq;
++
++ return move_queued_task(rq, p, dest_cpu);
++}
++
++/*
++ * migration_cpu_stop - this will be executed by a highprio stopper thread
++ * and performs thread migration by bumping thread off CPU then
++ * 'pushing' onto another runqueue.
++ */
++static int migration_cpu_stop(void *data)
++{
++ struct migration_arg *arg = data;
++ struct task_struct *p = arg->task;
++ struct rq *rq = this_rq();
++ unsigned long flags;
++
++ /*
++ * The original target CPU might have gone down and we might
++ * be on another CPU but it doesn't matter.
++ */
++ local_irq_save(flags);
++ /*
++ * We need to explicitly wake pending tasks before running
++ * __migrate_task() such that we will not miss enforcing cpus_ptr
++ * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
++ */
++ flush_smp_call_function_queue();
++
++ raw_spin_lock(&p->pi_lock);
++ raw_spin_lock(&rq->lock);
++ /*
++ * If task_rq(p) != rq, it cannot be migrated here, because we're
++ * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
++ * we're holding p->pi_lock.
++ */
++ if (task_rq(p) == rq && task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ rq = __migrate_task(rq, p, arg->dest_cpu);
++ }
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ return 0;
++}
++
++static inline void
++set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx)
++{
++ cpumask_copy(&p->cpus_mask, ctx->new_mask);
++ p->nr_cpus_allowed = cpumask_weight(ctx->new_mask);
++
++ /*
++ * Swap in a new user_cpus_ptr if SCA_USER flag set
++ */
++ if (ctx->flags & SCA_USER)
++ swap(p->user_cpus_ptr, ctx->user_mask);
++}
++
++static void
++__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
++{
++ lockdep_assert_held(&p->pi_lock);
++ set_cpus_allowed_common(p, ctx);
++}
++
++/*
++ * Used for kthread_bind() and select_fallback_rq(), in both cases the user
++ * affinity (if any) should be destroyed too.
++ */
++void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .user_mask = NULL,
++ .flags = SCA_USER, /* clear the user requested mask */
++ };
++ union cpumask_rcuhead {
++ cpumask_t cpumask;
++ struct rcu_head rcu;
++ };
++
++ __do_set_cpus_allowed(p, &ac);
++
++ /*
++ * Because this is called with p->pi_lock held, it is not possible
++ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
++ * kfree_rcu().
++ */
++ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
++}
++
++static cpumask_t *alloc_user_cpus_ptr(int node)
++{
++ /*
++ * See do_set_cpus_allowed() above for the rcu_head usage.
++ */
++ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
++
++ return kmalloc_node(size, GFP_KERNEL, node);
++}
++
++int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
++ int node)
++{
++ cpumask_t *user_mask;
++ unsigned long flags;
++
++ /*
++ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
++ * may differ by now due to racing.
++ */
++ dst->user_cpus_ptr = NULL;
++
++ /*
++ * This check is racy and losing the race is a valid situation.
++ * It is not worth the extra overhead of taking the pi_lock on
++ * every fork/clone.
++ */
++ if (data_race(!src->user_cpus_ptr))
++ return 0;
++
++ user_mask = alloc_user_cpus_ptr(node);
++ if (!user_mask)
++ return -ENOMEM;
++
++ /*
++ * Use pi_lock to protect content of user_cpus_ptr
++ *
++ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
++ * do_set_cpus_allowed().
++ */
++ raw_spin_lock_irqsave(&src->pi_lock, flags);
++ if (src->user_cpus_ptr) {
++ swap(dst->user_cpus_ptr, user_mask);
++ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
++ }
++ raw_spin_unlock_irqrestore(&src->pi_lock, flags);
++
++ if (unlikely(user_mask))
++ kfree(user_mask);
++
++ return 0;
++}
++
++static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
++{
++ struct cpumask *user_mask = NULL;
++
++ swap(p->user_cpus_ptr, user_mask);
++
++ return user_mask;
++}
++
++void release_user_cpus_ptr(struct task_struct *p)
++{
++ kfree(clear_user_cpus_ptr(p));
++}
++
++#endif
++
++/**
++ * task_curr - is this task currently executing on a CPU?
++ * @p: the task in question.
++ *
++ * Return: 1 if the task is currently executing. 0 otherwise.
++ */
++inline int task_curr(const struct task_struct *p)
++{
++ return cpu_curr(task_cpu(p)) == p;
++}
++
++#ifdef CONFIG_SMP
++/***
++ * kick_process - kick a running thread to enter/exit the kernel
++ * @p: the to-be-kicked thread
++ *
++ * Cause a process which is running on another CPU to enter
++ * kernel-mode, without any delay. (to get signals handled.)
++ *
++ * NOTE: this function doesn't have to take the runqueue lock,
++ * because all it wants to ensure is that the remote task enters
++ * the kernel. If the IPI races and the task has been migrated
++ * to another CPU then no harm is done and the purpose has been
++ * achieved as well.
++ */
++void kick_process(struct task_struct *p)
++{
++ guard(preempt)();
++ int cpu = task_cpu(p);
++
++ if ((cpu != smp_processor_id()) && task_curr(p))
++ smp_send_reschedule(cpu);
++}
++EXPORT_SYMBOL_GPL(kick_process);
++
++/*
++ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
++ *
++ * A few notes on cpu_active vs cpu_online:
++ *
++ * - cpu_active must be a subset of cpu_online
++ *
++ * - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
++ * see __set_cpus_allowed_ptr(). At this point the newly online
++ * CPU isn't yet part of the sched domains, and balancing will not
++ * see it.
++ *
++ * - on cpu-down we clear cpu_active() to mask the sched domains and
++ * avoid the load balancer to place new tasks on the to be removed
++ * CPU. Existing tasks will remain running there and will be taken
++ * off.
++ *
++ * This means that fallback selection must not select !active CPUs.
++ * And can assume that any active CPU must be online. Conversely
++ * select_task_rq() below may allow selection of !active CPUs in order
++ * to satisfy the above rules.
++ */
++static int select_fallback_rq(int cpu, struct task_struct *p)
++{
++ int nid = cpu_to_node(cpu);
++ const struct cpumask *nodemask = NULL;
++ enum { cpuset, possible, fail } state = cpuset;
++ int dest_cpu;
++
++ /*
++ * If the node that the CPU is on has been offlined, cpu_to_node()
++ * will return -1. There is no CPU on the node, and we should
++ * select the CPU on the other node.
++ */
++ if (nid != -1) {
++ nodemask = cpumask_of_node(nid);
++
++ /* Look for allowed, online CPU in same node. */
++ for_each_cpu(dest_cpu, nodemask) {
++ if (is_cpu_allowed(p, dest_cpu))
++ return dest_cpu;
++ }
++ }
++
++ for (;;) {
++ /* Any allowed, online CPU? */
++ for_each_cpu(dest_cpu, p->cpus_ptr) {
++ if (!is_cpu_allowed(p, dest_cpu))
++ continue;
++ goto out;
++ }
++
++ /* No more Mr. Nice Guy. */
++ switch (state) {
++ case cpuset:
++ if (cpuset_cpus_allowed_fallback(p)) {
++ state = possible;
++ break;
++ }
++ fallthrough;
++ case possible:
++ /*
++ * XXX When called from select_task_rq() we only
++ * hold p->pi_lock and again violate locking order.
++ *
++ * More yuck to audit.
++ */
++ do_set_cpus_allowed(p, task_cpu_possible_mask(p));
++ state = fail;
++ break;
++
++ case fail:
++ BUG();
++ break;
++ }
++ }
++
++out:
++ if (state != cpuset) {
++ /*
++ * Don't tell them about moving exiting tasks or
++ * kernel threads (both mm NULL), since they never
++ * leave kernel.
++ */
++ if (p->mm && printk_ratelimit()) {
++ printk_deferred("process %d (%s) no longer affine to cpu%d\n",
++ task_pid_nr(p), p->comm, cpu);
++ }
++ }
++
++ return dest_cpu;
++}
++
++static inline void
++sched_preempt_mask_flush(cpumask_t *mask, int prio, int ref)
++{
++ int cpu;
++
++ cpumask_copy(mask, sched_preempt_mask + ref);
++ if (prio < ref) {
++ for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) {
++ if (prio < cpu_rq(cpu)->prio)
++ cpumask_set_cpu(cpu, mask);
++ }
++ } else {
++ for_each_cpu_andnot(cpu, mask, sched_idle_mask) {
++ if (prio >= cpu_rq(cpu)->prio)
++ cpumask_clear_cpu(cpu, mask);
++ }
++ }
++}
++
++static inline int
++preempt_mask_check(cpumask_t *preempt_mask, cpumask_t *allow_mask, int prio)
++{
++ cpumask_t *mask = sched_preempt_mask + prio;
++ int pr = atomic_read(&sched_prio_record);
++
++ if (pr != prio && SCHED_QUEUE_BITS - 1 != prio) {
++ sched_preempt_mask_flush(mask, prio, pr);
++ atomic_set(&sched_prio_record, prio);
++ }
++
++ return cpumask_and(preempt_mask, allow_mask, mask);
++}
++
++__read_mostly idle_select_func_t idle_select_func ____cacheline_aligned_in_smp = cpumask_and;
++
++static inline int select_task_rq(struct task_struct *p)
++{
++ cpumask_t allow_mask, mask;
++
++ if (unlikely(!cpumask_and(&allow_mask, p->cpus_ptr, cpu_active_mask)))
++ return select_fallback_rq(task_cpu(p), p);
++
++ if (idle_select_func(&mask, &allow_mask, sched_idle_mask) ||
++ preempt_mask_check(&mask, &allow_mask, task_sched_prio(p)))
++ return best_mask_cpu(task_cpu(p), &mask);
++
++ return best_mask_cpu(task_cpu(p), &allow_mask);
++}
++
++void sched_set_stop_task(int cpu, struct task_struct *stop)
++{
++ static struct lock_class_key stop_pi_lock;
++ struct sched_param stop_param = { .sched_priority = STOP_PRIO };
++ struct sched_param start_param = { .sched_priority = 0 };
++ struct task_struct *old_stop = cpu_rq(cpu)->stop;
++
++ if (stop) {
++ /*
++ * Make it appear like a SCHED_FIFO task, its something
++ * userspace knows about and won't get confused about.
++ *
++ * Also, it will make PI more or less work without too
++ * much confusion -- but then, stop work should not
++ * rely on PI working anyway.
++ */
++ sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param);
++
++ /*
++ * The PI code calls rt_mutex_setprio() with ->pi_lock held to
++ * adjust the effective priority of a task. As a result,
++ * rt_mutex_setprio() can trigger (RT) balancing operations,
++ * which can then trigger wakeups of the stop thread to push
++ * around the current task.
++ *
++ * The stop task itself will never be part of the PI-chain, it
++ * never blocks, therefore that ->pi_lock recursion is safe.
++ * Tell lockdep about this by placing the stop->pi_lock in its
++ * own class.
++ */
++ lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
++ }
++
++ cpu_rq(cpu)->stop = stop;
++
++ if (old_stop) {
++ /*
++ * Reset it back to a normal scheduling policy so that
++ * it can die in pieces.
++ */
++ sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param);
++ }
++}
++
++static int affine_move_task(struct rq *rq, struct task_struct *p, int dest_cpu,
++ raw_spinlock_t *lock, unsigned long irq_flags)
++ __releases(rq->lock)
++ __releases(p->pi_lock)
++{
++ /* Can the task run on the task's current CPU? If so, we're done */
++ if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
++ if (p->migration_disabled) {
++ if (likely(p->cpus_ptr != &p->cpus_mask))
++ __do_set_cpus_ptr(p, &p->cpus_mask);
++ p->migration_disabled = 0;
++ p->migration_flags |= MDF_FORCE_ENABLED;
++ /* When p is migrate_disabled, rq->lock should be held */
++ rq->nr_pinned--;
++ }
++
++ if (task_on_cpu(p) || READ_ONCE(p->__state) == TASK_WAKING) {
++ struct migration_arg arg = { p, dest_cpu };
++
++ /* Need help from migration thread: drop lock and wait. */
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
++ return 0;
++ }
++ if (task_on_rq_queued(p)) {
++ /*
++ * OK, since we're going to drop the lock immediately
++ * afterwards anyway.
++ */
++ update_rq_clock(rq);
++ rq = move_queued_task(rq, p, dest_cpu);
++ lock = &rq->lock;
++ }
++ }
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ return 0;
++}
++
++static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
++ struct affinity_context *ctx,
++ struct rq *rq,
++ raw_spinlock_t *lock,
++ unsigned long irq_flags)
++{
++ const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
++ const struct cpumask *cpu_valid_mask = cpu_active_mask;
++ bool kthread = p->flags & PF_KTHREAD;
++ int dest_cpu;
++ int ret = 0;
++
++ if (kthread || is_migration_disabled(p)) {
++ /*
++ * Kernel threads are allowed on online && !active CPUs,
++ * however, during cpu-hot-unplug, even these might get pushed
++ * away if not KTHREAD_IS_PER_CPU.
++ *
++ * Specifically, migration_disabled() tasks must not fail the
++ * cpumask_any_and_distribute() pick below, esp. so on
++ * SCA_MIGRATE_ENABLE, otherwise we'll not call
++ * set_cpus_allowed_common() and actually reset p->cpus_ptr.
++ */
++ cpu_valid_mask = cpu_online_mask;
++ }
++
++ if (!kthread && !cpumask_subset(ctx->new_mask, cpu_allowed_mask)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ /*
++ * Must re-check here, to close a race against __kthread_bind(),
++ * sched_setaffinity() is not guaranteed to observe the flag.
++ */
++ if ((ctx->flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
++ goto out;
++
++ dest_cpu = cpumask_any_and(cpu_valid_mask, ctx->new_mask);
++ if (dest_cpu >= nr_cpu_ids) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ __do_set_cpus_allowed(p, ctx);
++
++ return affine_move_task(rq, p, dest_cpu, lock, irq_flags);
++
++out:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++
++ return ret;
++}
++
++/*
++ * Change a given task's CPU affinity. Migrate the thread to a
++ * is removed from the allowed bitmask.
++ *
++ * NOTE: the caller must have a valid reference to the task, the
++ * task must not exit() & deallocate itself prematurely. The
++ * call is not atomic; no spinlocks may be held.
++ */
++static int __set_cpus_allowed_ptr(struct task_struct *p,
++ struct affinity_context *ctx)
++{
++ unsigned long irq_flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
++ rq = __task_access_lock(p, &lock);
++ /*
++ * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
++ * flags are set.
++ */
++ if (p->user_cpus_ptr &&
++ !(ctx->flags & SCA_USER) &&
++ cpumask_and(rq->scratch_mask, ctx->new_mask, p->user_cpus_ptr))
++ ctx->new_mask = rq->scratch_mask;
++
++
++ return __set_cpus_allowed_ptr_locked(p, ctx, rq, lock, irq_flags);
++}
++
++int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .flags = 0,
++ };
++
++ return __set_cpus_allowed_ptr(p, &ac);
++}
++EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
++
++/*
++ * Change a given task's CPU affinity to the intersection of its current
++ * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
++ * If user_cpus_ptr is defined, use it as the basis for restricting CPU
++ * affinity or use cpu_online_mask instead.
++ *
++ * If the resulting mask is empty, leave the affinity unchanged and return
++ * -EINVAL.
++ */
++static int restrict_cpus_allowed_ptr(struct task_struct *p,
++ struct cpumask *new_mask,
++ const struct cpumask *subset_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .flags = 0,
++ };
++ unsigned long irq_flags;
++ raw_spinlock_t *lock;
++ struct rq *rq;
++ int err;
++
++ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
++ rq = __task_access_lock(p, &lock);
++
++ if (!cpumask_and(new_mask, task_user_cpus(p), subset_mask)) {
++ err = -EINVAL;
++ goto err_unlock;
++ }
++
++ return __set_cpus_allowed_ptr_locked(p, &ac, rq, lock, irq_flags);
++
++err_unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ return err;
++}
++
++/*
++ * Restrict the CPU affinity of task @p so that it is a subset of
++ * task_cpu_possible_mask() and point @p->user_cpus_ptr to a copy of the
++ * old affinity mask. If the resulting mask is empty, we warn and walk
++ * up the cpuset hierarchy until we find a suitable mask.
++ */
++void force_compatible_cpus_allowed_ptr(struct task_struct *p)
++{
++ cpumask_var_t new_mask;
++ const struct cpumask *override_mask = task_cpu_possible_mask(p);
++
++ alloc_cpumask_var(&new_mask, GFP_KERNEL);
++
++ /*
++ * __migrate_task() can fail silently in the face of concurrent
++ * offlining of the chosen destination CPU, so take the hotplug
++ * lock to ensure that the migration succeeds.
++ */
++ cpus_read_lock();
++ if (!cpumask_available(new_mask))
++ goto out_set_mask;
++
++ if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
++ goto out_free_mask;
++
++ /*
++ * We failed to find a valid subset of the affinity mask for the
++ * task, so override it based on its cpuset hierarchy.
++ */
++ cpuset_cpus_allowed(p, new_mask);
++ override_mask = new_mask;
++
++out_set_mask:
++ if (printk_ratelimit()) {
++ printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
++ task_pid_nr(p), p->comm,
++ cpumask_pr_args(override_mask));
++ }
++
++ WARN_ON(set_cpus_allowed_ptr(p, override_mask));
++out_free_mask:
++ cpus_read_unlock();
++ free_cpumask_var(new_mask);
++}
++
++static int
++__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
++
++/*
++ * Restore the affinity of a task @p which was previously restricted by a
++ * call to force_compatible_cpus_allowed_ptr().
++ *
++ * It is the caller's responsibility to serialise this with any calls to
++ * force_compatible_cpus_allowed_ptr(@p).
++ */
++void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
++{
++ struct affinity_context ac = {
++ .new_mask = task_user_cpus(p),
++ .flags = 0,
++ };
++ int ret;
++
++ /*
++ * Try to restore the old affinity mask with __sched_setaffinity().
++ * Cpuset masking will be done there too.
++ */
++ ret = __sched_setaffinity(p, &ac);
++ WARN_ON_ONCE(ret);
++}
++
++#else /* CONFIG_SMP */
++
++static inline int select_task_rq(struct task_struct *p)
++{
++ return 0;
++}
++
++static inline int
++__set_cpus_allowed_ptr(struct task_struct *p,
++ struct affinity_context *ctx)
++{
++ return set_cpus_allowed_ptr(p, ctx->new_mask);
++}
++
++static inline bool rq_has_pinned_tasks(struct rq *rq)
++{
++ return false;
++}
++
++static inline cpumask_t *alloc_user_cpus_ptr(int node)
++{
++ return NULL;
++}
++
++#endif /* !CONFIG_SMP */
++
++static void
++ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq;
++
++ if (!schedstat_enabled())
++ return;
++
++ rq = this_rq();
++
++#ifdef CONFIG_SMP
++ if (cpu == rq->cpu) {
++ __schedstat_inc(rq->ttwu_local);
++ __schedstat_inc(p->stats.nr_wakeups_local);
++ } else {
++ /** Alt schedule FW ToDo:
++ * How to do ttwu_wake_remote
++ */
++ }
++#endif /* CONFIG_SMP */
++
++ __schedstat_inc(rq->ttwu_count);
++ __schedstat_inc(p->stats.nr_wakeups);
++}
++
++/*
++ * Mark the task runnable.
++ */
++static inline void ttwu_do_wakeup(struct task_struct *p)
++{
++ WRITE_ONCE(p->__state, TASK_RUNNING);
++ trace_sched_wakeup(p);
++}
++
++static inline void
++ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
++{
++ if (p->sched_contributes_to_load)
++ rq->nr_uninterruptible--;
++
++ if (
++#ifdef CONFIG_SMP
++ !(wake_flags & WF_MIGRATED) &&
++#endif
++ p->in_iowait) {
++ delayacct_blkio_end(p);
++ atomic_dec(&task_rq(p)->nr_iowait);
++ }
++
++ activate_task(p, rq);
++ wakeup_preempt(rq);
++
++ ttwu_do_wakeup(p);
++}
++
++/*
++ * Consider @p being inside a wait loop:
++ *
++ * for (;;) {
++ * set_current_state(TASK_UNINTERRUPTIBLE);
++ *
++ * if (CONDITION)
++ * break;
++ *
++ * schedule();
++ * }
++ * __set_current_state(TASK_RUNNING);
++ *
++ * between set_current_state() and schedule(). In this case @p is still
++ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
++ * an atomic manner.
++ *
++ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
++ * then schedule() must still happen and p->state can be changed to
++ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
++ * need to do a full wakeup with enqueue.
++ *
++ * Returns: %true when the wakeup is done,
++ * %false otherwise.
++ */
++static int ttwu_runnable(struct task_struct *p, int wake_flags)
++{
++ struct rq *rq;
++ raw_spinlock_t *lock;
++ int ret = 0;
++
++ rq = __task_access_lock(p, &lock);
++ if (task_on_rq_queued(p)) {
++ if (!task_on_cpu(p)) {
++ /*
++ * When on_rq && !on_cpu the task is preempted, see if
++ * it should preempt the task that is current now.
++ */
++ update_rq_clock(rq);
++ wakeup_preempt(rq);
++ }
++ ttwu_do_wakeup(p);
++ ret = 1;
++ }
++ __task_access_unlock(p, lock);
++
++ return ret;
++}
++
++#ifdef CONFIG_SMP
++void sched_ttwu_pending(void *arg)
++{
++ struct llist_node *llist = arg;
++ struct rq *rq = this_rq();
++ struct task_struct *p, *t;
++ struct rq_flags rf;
++
++ if (!llist)
++ return;
++
++ rq_lock_irqsave(rq, &rf);
++ update_rq_clock(rq);
++
++ llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
++ if (WARN_ON_ONCE(p->on_cpu))
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++
++ if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
++ set_task_cpu(p, cpu_of(rq));
++
++ ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0);
++ }
++
++ /*
++ * Must be after enqueueing at least once task such that
++ * idle_cpu() does not observe a false-negative -- if it does,
++ * it is possible for select_idle_siblings() to stack a number
++ * of tasks on this CPU during that window.
++ *
++ * It is ok to clear ttwu_pending when another task pending.
++ * We will receive IPI after local irq enabled and then enqueue it.
++ * Since now nr_running > 0, idle_cpu() will always get correct result.
++ */
++ WRITE_ONCE(rq->ttwu_pending, 0);
++ rq_unlock_irqrestore(rq, &rf);
++}
++
++/*
++ * Prepare the scene for sending an IPI for a remote smp_call
++ *
++ * Returns true if the caller can proceed with sending the IPI.
++ * Returns false otherwise.
++ */
++bool call_function_single_prep_ipi(int cpu)
++{
++ if (set_nr_if_polling(cpu_rq(cpu)->idle)) {
++ trace_sched_wake_idle_without_ipi(cpu);
++ return false;
++ }
++
++ return true;
++}
++
++/*
++ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
++ * necessary. The wakee CPU on receipt of the IPI will queue the task
++ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
++ * of the wakeup instead of the waker.
++ */
++static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
++
++ WRITE_ONCE(rq->ttwu_pending, 1);
++ __smp_call_single_queue(cpu, &p->wake_entry.llist);
++}
++
++static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
++{
++ /*
++ * Do not complicate things with the async wake_list while the CPU is
++ * in hotplug state.
++ */
++ if (!cpu_active(cpu))
++ return false;
++
++ /* Ensure the task will still be allowed to run on the CPU. */
++ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
++ return false;
++
++ /*
++ * If the CPU does not share cache, then queue the task on the
++ * remote rqs wakelist to avoid accessing remote data.
++ */
++ if (!cpus_share_cache(smp_processor_id(), cpu))
++ return true;
++
++ if (cpu == smp_processor_id())
++ return false;
++
++ /*
++ * If the wakee cpu is idle, or the task is descheduling and the
++ * only running task on the CPU, then use the wakelist to offload
++ * the task activation to the idle (or soon-to-be-idle) CPU as
++ * the current CPU is likely busy. nr_running is checked to
++ * avoid unnecessary task stacking.
++ *
++ * Note that we can only get here with (wakee) p->on_rq=0,
++ * p->on_cpu can be whatever, we've done the dequeue, so
++ * the wakee has been accounted out of ->nr_running.
++ */
++ if (!cpu_rq(cpu)->nr_running)
++ return true;
++
++ return false;
++}
++
++static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ if (__is_defined(ALT_SCHED_TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
++ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
++ __ttwu_queue_wakelist(p, cpu, wake_flags);
++ return true;
++ }
++
++ return false;
++}
++
++void wake_up_if_idle(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ guard(rcu)();
++ if (is_idle_task(rcu_dereference(rq->curr))) {
++ guard(raw_spinlock_irqsave)(&rq->lock);
++ if (is_idle_task(rq->curr))
++ resched_curr(rq);
++ }
++}
++
++extern struct static_key_false sched_asym_cpucapacity;
++
++static __always_inline bool sched_asym_cpucap_active(void)
++{
++ return static_branch_unlikely(&sched_asym_cpucapacity);
++}
++
++bool cpus_equal_capacity(int this_cpu, int that_cpu)
++{
++ if (!sched_asym_cpucap_active())
++ return true;
++
++ if (this_cpu == that_cpu)
++ return true;
++
++ return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu);
++}
++
++bool cpus_share_cache(int this_cpu, int that_cpu)
++{
++ if (this_cpu == that_cpu)
++ return true;
++
++ return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
++}
++#else /* !CONFIG_SMP */
++
++static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ return false;
++}
++
++#endif /* CONFIG_SMP */
++
++static inline void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (ttwu_queue_wakelist(p, cpu, wake_flags))
++ return;
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++ ttwu_do_activate(rq, p, wake_flags);
++ raw_spin_unlock(&rq->lock);
++}
++
++/*
++ * Invoked from try_to_wake_up() to check whether the task can be woken up.
++ *
++ * The caller holds p::pi_lock if p != current or has preemption
++ * disabled when p == current.
++ *
++ * The rules of saved_state:
++ *
++ * The related locking code always holds p::pi_lock when updating
++ * p::saved_state, which means the code is fully serialized in both cases.
++ *
++ * For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
++ * No other bits set. This allows to distinguish all wakeup scenarios.
++ *
++ * For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
++ * allows us to prevent early wakeup of tasks before they can be run on
++ * asymmetric ISA architectures (eg ARMv9).
++ */
++static __always_inline
++bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
++{
++ int match;
++
++ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
++ WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
++ state != TASK_RTLOCK_WAIT);
++ }
++
++ *success = !!(match = __task_state_match(p, state));
++
++ /*
++ * Saved state preserves the task state across blocking on
++ * an RT lock or TASK_FREEZABLE tasks. If the state matches,
++ * set p::saved_state to TASK_RUNNING, but do not wake the task
++ * because it waits for a lock wakeup or __thaw_task(). Also
++ * indicate success because from the regular waker's point of
++ * view this has succeeded.
++ *
++ * After acquiring the lock the task will restore p::__state
++ * from p::saved_state which ensures that the regular
++ * wakeup is not lost. The restore will also set
++ * p::saved_state to TASK_RUNNING so any further tests will
++ * not result in false positives vs. @success
++ */
++ if (match < 0)
++ p->saved_state = TASK_RUNNING;
++
++ return match > 0;
++}
++
++/*
++ * Notes on Program-Order guarantees on SMP systems.
++ *
++ * MIGRATION
++ *
++ * The basic program-order guarantee on SMP systems is that when a task [t]
++ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
++ * execution on its new CPU [c1].
++ *
++ * For migration (of runnable tasks) this is provided by the following means:
++ *
++ * A) UNLOCK of the rq(c0)->lock scheduling out task t
++ * B) migration for t is required to synchronize *both* rq(c0)->lock and
++ * rq(c1)->lock (if not at the same time, then in that order).
++ * C) LOCK of the rq(c1)->lock scheduling in task
++ *
++ * Transitivity guarantees that B happens after A and C after B.
++ * Note: we only require RCpc transitivity.
++ * Note: the CPU doing B need not be c0 or c1
++ *
++ * Example:
++ *
++ * CPU0 CPU1 CPU2
++ *
++ * LOCK rq(0)->lock
++ * sched-out X
++ * sched-in Y
++ * UNLOCK rq(0)->lock
++ *
++ * LOCK rq(0)->lock // orders against CPU0
++ * dequeue X
++ * UNLOCK rq(0)->lock
++ *
++ * LOCK rq(1)->lock
++ * enqueue X
++ * UNLOCK rq(1)->lock
++ *
++ * LOCK rq(1)->lock // orders against CPU2
++ * sched-out Z
++ * sched-in X
++ * UNLOCK rq(1)->lock
++ *
++ *
++ * BLOCKING -- aka. SLEEP + WAKEUP
++ *
++ * For blocking we (obviously) need to provide the same guarantee as for
++ * migration. However the means are completely different as there is no lock
++ * chain to provide order. Instead we do:
++ *
++ * 1) smp_store_release(X->on_cpu, 0) -- finish_task()
++ * 2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
++ *
++ * Example:
++ *
++ * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule)
++ *
++ * LOCK rq(0)->lock LOCK X->pi_lock
++ * dequeue X
++ * sched-out X
++ * smp_store_release(X->on_cpu, 0);
++ *
++ * smp_cond_load_acquire(&X->on_cpu, !VAL);
++ * X->state = WAKING
++ * set_task_cpu(X,2)
++ *
++ * LOCK rq(2)->lock
++ * enqueue X
++ * X->state = RUNNING
++ * UNLOCK rq(2)->lock
++ *
++ * LOCK rq(2)->lock // orders against CPU1
++ * sched-out Z
++ * sched-in X
++ * UNLOCK rq(2)->lock
++ *
++ * UNLOCK X->pi_lock
++ * UNLOCK rq(0)->lock
++ *
++ *
++ * However; for wakeups there is a second guarantee we must provide, namely we
++ * must observe the state that lead to our wakeup. That is, not only must our
++ * task observe its own prior state, it must also observe the stores prior to
++ * its wakeup.
++ *
++ * This means that any means of doing remote wakeups must order the CPU doing
++ * the wakeup against the CPU the task is going to end up running on. This,
++ * however, is already required for the regular Program-Order guarantee above,
++ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
++ *
++ */
++
++/**
++ * try_to_wake_up - wake up a thread
++ * @p: the thread to be awakened
++ * @state: the mask of task states that can be woken
++ * @wake_flags: wake modifier flags (WF_*)
++ *
++ * Conceptually does:
++ *
++ * If (@state & @p->state) @p->state = TASK_RUNNING.
++ *
++ * If the task was not queued/runnable, also place it back on a runqueue.
++ *
++ * This function is atomic against schedule() which would dequeue the task.
++ *
++ * It issues a full memory barrier before accessing @p->state, see the comment
++ * with set_current_state().
++ *
++ * Uses p->pi_lock to serialize against concurrent wake-ups.
++ *
++ * Relies on p->pi_lock stabilizing:
++ * - p->sched_class
++ * - p->cpus_ptr
++ * - p->sched_task_group
++ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
++ *
++ * Tries really hard to only take one task_rq(p)->lock for performance.
++ * Takes rq->lock in:
++ * - ttwu_runnable() -- old rq, unavoidable, see comment there;
++ * - ttwu_queue() -- new rq, for enqueue of the task;
++ * - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
++ *
++ * As a consequence we race really badly with just about everything. See the
++ * many memory barriers and their comments for details.
++ *
++ * Return: %true if @p->state changes (an actual wakeup was done),
++ * %false otherwise.
++ */
++int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
++{
++ guard(preempt)();
++ int cpu, success = 0;
++
++ if (p == current) {
++ /*
++ * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
++ * == smp_processor_id()'. Together this means we can special
++ * case the whole 'p->on_rq && ttwu_runnable()' case below
++ * without taking any locks.
++ *
++ * In particular:
++ * - we rely on Program-Order guarantees for all the ordering,
++ * - we're serialized against set_special_state() by virtue of
++ * it disabling IRQs (this allows not taking ->pi_lock).
++ */
++ if (!ttwu_state_match(p, state, &success))
++ goto out;
++
++ trace_sched_waking(p);
++ ttwu_do_wakeup(p);
++ goto out;
++ }
++
++ /*
++ * If we are going to wake up a thread waiting for CONDITION we
++ * need to ensure that CONDITION=1 done by the caller can not be
++ * reordered with p->state check below. This pairs with smp_store_mb()
++ * in set_current_state() that the waiting thread does.
++ */
++ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
++ smp_mb__after_spinlock();
++ if (!ttwu_state_match(p, state, &success))
++ break;
++
++ trace_sched_waking(p);
++
++ /*
++ * Ensure we load p->on_rq _after_ p->state, otherwise it would
++ * be possible to, falsely, observe p->on_rq == 0 and get stuck
++ * in smp_cond_load_acquire() below.
++ *
++ * sched_ttwu_pending() try_to_wake_up()
++ * STORE p->on_rq = 1 LOAD p->state
++ * UNLOCK rq->lock
++ *
++ * __schedule() (switch to task 'p')
++ * LOCK rq->lock smp_rmb();
++ * smp_mb__after_spinlock();
++ * UNLOCK rq->lock
++ *
++ * [task p]
++ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
++ *
++ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
++ * __schedule(). See the comment for smp_mb__after_spinlock().
++ *
++ * A similar smp_rmb() lives in __task_needs_rq_lock().
++ */
++ smp_rmb();
++ if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
++ break;
++
++#ifdef CONFIG_SMP
++ /*
++ * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
++ * possible to, falsely, observe p->on_cpu == 0.
++ *
++ * One must be running (->on_cpu == 1) in order to remove oneself
++ * from the runqueue.
++ *
++ * __schedule() (switch to task 'p') try_to_wake_up()
++ * STORE p->on_cpu = 1 LOAD p->on_rq
++ * UNLOCK rq->lock
++ *
++ * __schedule() (put 'p' to sleep)
++ * LOCK rq->lock smp_rmb();
++ * smp_mb__after_spinlock();
++ * STORE p->on_rq = 0 LOAD p->on_cpu
++ *
++ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
++ * __schedule(). See the comment for smp_mb__after_spinlock().
++ *
++ * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
++ * schedule()'s deactivate_task() has 'happened' and p will no longer
++ * care about it's own p->state. See the comment in __schedule().
++ */
++ smp_acquire__after_ctrl_dep();
++
++ /*
++ * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
++ * == 0), which means we need to do an enqueue, change p->state to
++ * TASK_WAKING such that we can unlock p->pi_lock before doing the
++ * enqueue, such as ttwu_queue_wakelist().
++ */
++ WRITE_ONCE(p->__state, TASK_WAKING);
++
++ /*
++ * If the owning (remote) CPU is still in the middle of schedule() with
++ * this task as prev, considering queueing p on the remote CPUs wake_list
++ * which potentially sends an IPI instead of spinning on p->on_cpu to
++ * let the waker make forward progress. This is safe because IRQs are
++ * disabled and the IPI will deliver after on_cpu is cleared.
++ *
++ * Ensure we load task_cpu(p) after p->on_cpu:
++ *
++ * set_task_cpu(p, cpu);
++ * STORE p->cpu = @cpu
++ * __schedule() (switch to task 'p')
++ * LOCK rq->lock
++ * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
++ * STORE p->on_cpu = 1 LOAD p->cpu
++ *
++ * to ensure we observe the correct CPU on which the task is currently
++ * scheduling.
++ */
++ if (smp_load_acquire(&p->on_cpu) &&
++ ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
++ break;
++
++ /*
++ * If the owning (remote) CPU is still in the middle of schedule() with
++ * this task as prev, wait until it's done referencing the task.
++ *
++ * Pairs with the smp_store_release() in finish_task().
++ *
++ * This ensures that tasks getting woken will be fully ordered against
++ * their previous state and preserve Program Order.
++ */
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++
++ sched_task_ttwu(p);
++
++ if ((wake_flags & WF_CURRENT_CPU) &&
++ cpumask_test_cpu(smp_processor_id(), p->cpus_ptr))
++ cpu = smp_processor_id();
++ else
++ cpu = select_task_rq(p);
++
++ if (cpu != task_cpu(p)) {
++ if (p->in_iowait) {
++ delayacct_blkio_end(p);
++ atomic_dec(&task_rq(p)->nr_iowait);
++ }
++
++ wake_flags |= WF_MIGRATED;
++ set_task_cpu(p, cpu);
++ }
++#else
++ sched_task_ttwu(p);
++
++ cpu = task_cpu(p);
++#endif /* CONFIG_SMP */
++
++ ttwu_queue(p, cpu, wake_flags);
++ }
++out:
++ if (success)
++ ttwu_stat(p, task_cpu(p), wake_flags);
++
++ return success;
++}
++
++static bool __task_needs_rq_lock(struct task_struct *p)
++{
++ unsigned int state = READ_ONCE(p->__state);
++
++ /*
++ * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
++ * the task is blocked. Make sure to check @state since ttwu() can drop
++ * locks at the end, see ttwu_queue_wakelist().
++ */
++ if (state == TASK_RUNNING || state == TASK_WAKING)
++ return true;
++
++ /*
++ * Ensure we load p->on_rq after p->__state, otherwise it would be
++ * possible to, falsely, observe p->on_rq == 0.
++ *
++ * See try_to_wake_up() for a longer comment.
++ */
++ smp_rmb();
++ if (p->on_rq)
++ return true;
++
++#ifdef CONFIG_SMP
++ /*
++ * Ensure the task has finished __schedule() and will not be referenced
++ * anymore. Again, see try_to_wake_up() for a longer comment.
++ */
++ smp_rmb();
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++#endif
++
++ return false;
++}
++
++/**
++ * task_call_func - Invoke a function on task in fixed state
++ * @p: Process for which the function is to be invoked, can be @current.
++ * @func: Function to invoke.
++ * @arg: Argument to function.
++ *
++ * Fix the task in it's current state by avoiding wakeups and or rq operations
++ * and call @func(@arg) on it. This function can use ->on_rq and task_curr()
++ * to work out what the state is, if required. Given that @func can be invoked
++ * with a runqueue lock held, it had better be quite lightweight.
++ *
++ * Returns:
++ * Whatever @func returns
++ */
++int task_call_func(struct task_struct *p, task_call_f func, void *arg)
++{
++ struct rq *rq = NULL;
++ struct rq_flags rf;
++ int ret;
++
++ raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
++
++ if (__task_needs_rq_lock(p))
++ rq = __task_rq_lock(p, &rf);
++
++ /*
++ * At this point the task is pinned; either:
++ * - blocked and we're holding off wakeups (pi->lock)
++ * - woken, and we're holding off enqueue (rq->lock)
++ * - queued, and we're holding off schedule (rq->lock)
++ * - running, and we're holding off de-schedule (rq->lock)
++ *
++ * The called function (@func) can use: task_curr(), p->on_rq and
++ * p->__state to differentiate between these states.
++ */
++ ret = func(p, arg);
++
++ if (rq)
++ __task_rq_unlock(rq, &rf);
++
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
++ return ret;
++}
++
++/**
++ * cpu_curr_snapshot - Return a snapshot of the currently running task
++ * @cpu: The CPU on which to snapshot the task.
++ *
++ * Returns the task_struct pointer of the task "currently" running on
++ * the specified CPU. If the same task is running on that CPU throughout,
++ * the return value will be a pointer to that task's task_struct structure.
++ * If the CPU did any context switches even vaguely concurrently with the
++ * execution of this function, the return value will be a pointer to the
++ * task_struct structure of a randomly chosen task that was running on
++ * that CPU somewhere around the time that this function was executing.
++ *
++ * If the specified CPU was offline, the return value is whatever it
++ * is, perhaps a pointer to the task_struct structure of that CPU's idle
++ * task, but there is no guarantee. Callers wishing a useful return
++ * value must take some action to ensure that the specified CPU remains
++ * online throughout.
++ *
++ * This function executes full memory barriers before and after fetching
++ * the pointer, which permits the caller to confine this function's fetch
++ * with respect to the caller's accesses to other shared variables.
++ */
++struct task_struct *cpu_curr_snapshot(int cpu)
++{
++ struct task_struct *t;
++
++ smp_mb(); /* Pairing determined by caller's synchronization design. */
++ t = rcu_dereference(cpu_curr(cpu));
++ smp_mb(); /* Pairing determined by caller's synchronization design. */
++ return t;
++}
++
++/**
++ * wake_up_process - Wake up a specific process
++ * @p: The process to be woken up.
++ *
++ * Attempt to wake up the nominated process and move it to the set of runnable
++ * processes.
++ *
++ * Return: 1 if the process was woken up, 0 if it was already running.
++ *
++ * This function executes a full memory barrier before accessing the task state.
++ */
++int wake_up_process(struct task_struct *p)
++{
++ return try_to_wake_up(p, TASK_NORMAL, 0);
++}
++EXPORT_SYMBOL(wake_up_process);
++
++int wake_up_state(struct task_struct *p, unsigned int state)
++{
++ return try_to_wake_up(p, state, 0);
++}
++
++/*
++ * Perform scheduler related setup for a newly forked process p.
++ * p is forked by current.
++ *
++ * __sched_fork() is basic setup used by init_idle() too:
++ */
++static inline void __sched_fork(unsigned long clone_flags, struct task_struct *p)
++{
++ p->on_rq = 0;
++ p->on_cpu = 0;
++ p->utime = 0;
++ p->stime = 0;
++ p->sched_time = 0;
++
++#ifdef CONFIG_SCHEDSTATS
++ /* Even if schedstat is disabled, there should not be garbage */
++ memset(&p->stats, 0, sizeof(p->stats));
++#endif
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++ INIT_HLIST_HEAD(&p->preempt_notifiers);
++#endif
++
++#ifdef CONFIG_COMPACTION
++ p->capture_control = NULL;
++#endif
++#ifdef CONFIG_SMP
++ p->wake_entry.u_flags = CSD_TYPE_TTWU;
++#endif
++ init_sched_mm_cid(p);
++}
++
++/*
++ * fork()/clone()-time setup:
++ */
++int sched_fork(unsigned long clone_flags, struct task_struct *p)
++{
++ __sched_fork(clone_flags, p);
++ /*
++ * We mark the process as NEW here. This guarantees that
++ * nobody will actually run it, and a signal or other external
++ * event cannot wake it up and insert it on the runqueue either.
++ */
++ p->__state = TASK_NEW;
++
++ /*
++ * Make sure we do not leak PI boosting priority to the child.
++ */
++ p->prio = current->normal_prio;
++
++ /*
++ * Revert to default priority/policy on fork if requested.
++ */
++ if (unlikely(p->sched_reset_on_fork)) {
++ if (task_has_rt_policy(p)) {
++ p->policy = SCHED_NORMAL;
++ p->static_prio = NICE_TO_PRIO(0);
++ p->rt_priority = 0;
++ } else if (PRIO_TO_NICE(p->static_prio) < 0)
++ p->static_prio = NICE_TO_PRIO(0);
++
++ p->prio = p->normal_prio = p->static_prio;
++
++ /*
++ * We don't need the reset flag anymore after the fork. It has
++ * fulfilled its duty:
++ */
++ p->sched_reset_on_fork = 0;
++ }
++
++#ifdef CONFIG_SCHED_INFO
++ if (unlikely(sched_info_on()))
++ memset(&p->sched_info, 0, sizeof(p->sched_info));
++#endif
++ init_task_preempt_count(p);
++
++ return 0;
++}
++
++void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
++{
++ unsigned long flags;
++ struct rq *rq;
++
++ /*
++ * Because we're not yet on the pid-hash, p->pi_lock isn't strictly
++ * required yet, but lockdep gets upset if rules are violated.
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ /*
++ * Share the timeslice between parent and child, thus the
++ * total amount of pending timeslices in the system doesn't change,
++ * resulting in more scheduling fairness.
++ */
++ rq = this_rq();
++ raw_spin_lock(&rq->lock);
++
++ rq->curr->time_slice /= 2;
++ p->time_slice = rq->curr->time_slice;
++#ifdef CONFIG_SCHED_HRTICK
++ hrtick_start(rq, rq->curr->time_slice);
++#endif
++
++ if (p->time_slice < RESCHED_NS) {
++ p->time_slice = sysctl_sched_base_slice;
++ resched_curr(rq);
++ }
++ sched_task_fork(p, rq);
++ raw_spin_unlock(&rq->lock);
++
++ rseq_migrate(p);
++ /*
++ * We're setting the CPU for the first time, we don't migrate,
++ * so use __set_task_cpu().
++ */
++ __set_task_cpu(p, smp_processor_id());
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++
++void sched_post_fork(struct task_struct *p)
++{
++}
++
++#ifdef CONFIG_SCHEDSTATS
++
++DEFINE_STATIC_KEY_FALSE(sched_schedstats);
++
++static void set_schedstats(bool enabled)
++{
++ if (enabled)
++ static_branch_enable(&sched_schedstats);
++ else
++ static_branch_disable(&sched_schedstats);
++}
++
++void force_schedstat_enabled(void)
++{
++ if (!schedstat_enabled()) {
++ pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
++ static_branch_enable(&sched_schedstats);
++ }
++}
++
++static int __init setup_schedstats(char *str)
++{
++ int ret = 0;
++ if (!str)
++ goto out;
++
++ if (!strcmp(str, "enable")) {
++ set_schedstats(true);
++ ret = 1;
++ } else if (!strcmp(str, "disable")) {
++ set_schedstats(false);
++ ret = 1;
++ }
++out:
++ if (!ret)
++ pr_warn("Unable to parse schedstats=\n");
++
++ return ret;
++}
++__setup("schedstats=", setup_schedstats);
++
++#ifdef CONFIG_PROC_SYSCTL
++static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
++ size_t *lenp, loff_t *ppos)
++{
++ struct ctl_table t;
++ int err;
++ int state = static_branch_likely(&sched_schedstats);
++
++ if (write && !capable(CAP_SYS_ADMIN))
++ return -EPERM;
++
++ t = *table;
++ t.data = &state;
++ err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
++ if (err < 0)
++ return err;
++ if (write)
++ set_schedstats(state);
++ return err;
++}
++
++static struct ctl_table sched_core_sysctls[] = {
++ {
++ .procname = "sched_schedstats",
++ .data = NULL,
++ .maxlen = sizeof(unsigned int),
++ .mode = 0644,
++ .proc_handler = sysctl_schedstats,
++ .extra1 = SYSCTL_ZERO,
++ .extra2 = SYSCTL_ONE,
++ },
++};
++static int __init sched_core_sysctl_init(void)
++{
++ register_sysctl_init("kernel", sched_core_sysctls);
++ return 0;
++}
++late_initcall(sched_core_sysctl_init);
++#endif /* CONFIG_PROC_SYSCTL */
++#endif /* CONFIG_SCHEDSTATS */
++
++/*
++ * wake_up_new_task - wake up a newly created task for the first time.
++ *
++ * This function will do some initial scheduler statistics housekeeping
++ * that must be done for every newly created context, then puts the task
++ * on the runqueue and wakes it.
++ */
++void wake_up_new_task(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ WRITE_ONCE(p->__state, TASK_RUNNING);
++ rq = cpu_rq(select_task_rq(p));
++#ifdef CONFIG_SMP
++ rseq_migrate(p);
++ /*
++ * Fork balancing, do it here and not earlier because:
++ * - cpus_ptr can change in the fork path
++ * - any previously selected CPU might disappear through hotplug
++ *
++ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
++ * as we're not fully set-up yet.
++ */
++ __set_task_cpu(p, cpu_of(rq));
++#endif
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++
++ activate_task(p, rq);
++ trace_sched_wakeup_new(p);
++ wakeup_preempt(rq);
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++
++static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
++
++void preempt_notifier_inc(void)
++{
++ static_branch_inc(&preempt_notifier_key);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_inc);
++
++void preempt_notifier_dec(void)
++{
++ static_branch_dec(&preempt_notifier_key);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_dec);
++
++/**
++ * preempt_notifier_register - tell me when current is being preempted & rescheduled
++ * @notifier: notifier struct to register
++ */
++void preempt_notifier_register(struct preempt_notifier *notifier)
++{
++ if (!static_branch_unlikely(&preempt_notifier_key))
++ WARN(1, "registering preempt_notifier while notifiers disabled\n");
++
++ hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_register);
++
++/**
++ * preempt_notifier_unregister - no longer interested in preemption notifications
++ * @notifier: notifier struct to unregister
++ *
++ * This is *not* safe to call from within a preemption notifier.
++ */
++void preempt_notifier_unregister(struct preempt_notifier *notifier)
++{
++ hlist_del(¬ifier->link);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
++
++static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_in(notifier, raw_smp_processor_id());
++}
++
++static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++ if (static_branch_unlikely(&preempt_notifier_key))
++ __fire_sched_in_preempt_notifiers(curr);
++}
++
++static void
++__fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_out(notifier, next);
++}
++
++static __always_inline void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++ if (static_branch_unlikely(&preempt_notifier_key))
++ __fire_sched_out_preempt_notifiers(curr, next);
++}
++
++#else /* !CONFIG_PREEMPT_NOTIFIERS */
++
++static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++}
++
++static inline void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++}
++
++#endif /* CONFIG_PREEMPT_NOTIFIERS */
++
++static inline void prepare_task(struct task_struct *next)
++{
++ /*
++ * Claim the task as running, we do this before switching to it
++ * such that any running task will have this set.
++ *
++ * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
++ * its ordering comment.
++ */
++ WRITE_ONCE(next->on_cpu, 1);
++}
++
++static inline void finish_task(struct task_struct *prev)
++{
++#ifdef CONFIG_SMP
++ /*
++ * This must be the very last reference to @prev from this CPU. After
++ * p->on_cpu is cleared, the task can be moved to a different CPU. We
++ * must ensure this doesn't happen until the switch is completely
++ * finished.
++ *
++ * In particular, the load of prev->state in finish_task_switch() must
++ * happen before this.
++ *
++ * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
++ */
++ smp_store_release(&prev->on_cpu, 0);
++#else
++ prev->on_cpu = 0;
++#endif
++}
++
++#ifdef CONFIG_SMP
++
++static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++ void (*func)(struct rq *rq);
++ struct balance_callback *next;
++
++ lockdep_assert_held(&rq->lock);
++
++ while (head) {
++ func = (void (*)(struct rq *))head->func;
++ next = head->next;
++ head->next = NULL;
++ head = next;
++
++ func(rq);
++ }
++}
++
++static void balance_push(struct rq *rq);
++
++/*
++ * balance_push_callback is a right abuse of the callback interface and plays
++ * by significantly different rules.
++ *
++ * Where the normal balance_callback's purpose is to be ran in the same context
++ * that queued it (only later, when it's safe to drop rq->lock again),
++ * balance_push_callback is specifically targeted at __schedule().
++ *
++ * This abuse is tolerated because it places all the unlikely/odd cases behind
++ * a single test, namely: rq->balance_callback == NULL.
++ */
++struct balance_callback balance_push_callback = {
++ .next = NULL,
++ .func = balance_push,
++};
++
++static inline struct balance_callback *
++__splice_balance_callbacks(struct rq *rq, bool split)
++{
++ struct balance_callback *head = rq->balance_callback;
++
++ if (likely(!head))
++ return NULL;
++
++ lockdep_assert_rq_held(rq);
++ /*
++ * Must not take balance_push_callback off the list when
++ * splice_balance_callbacks() and balance_callbacks() are not
++ * in the same rq->lock section.
++ *
++ * In that case it would be possible for __schedule() to interleave
++ * and observe the list empty.
++ */
++ if (split && head == &balance_push_callback)
++ head = NULL;
++ else
++ rq->balance_callback = NULL;
++
++ return head;
++}
++
++static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
++{
++ return __splice_balance_callbacks(rq, true);
++}
++
++static void __balance_callbacks(struct rq *rq)
++{
++ do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
++}
++
++static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++ unsigned long flags;
++
++ if (unlikely(head)) {
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ do_balance_callbacks(rq, head);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++ }
++}
++
++#else
++
++static inline void __balance_callbacks(struct rq *rq)
++{
++}
++
++static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
++{
++ return NULL;
++}
++
++static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++}
++
++#endif
++
++static inline void
++prepare_lock_switch(struct rq *rq, struct task_struct *next)
++{
++ /*
++ * Since the runqueue lock will be released by the next
++ * task (which is an invalid locking op but in the case
++ * of the scheduler it's an obvious special-case), so we
++ * do an early lockdep release here:
++ */
++ spin_release(&rq->lock.dep_map, _THIS_IP_);
++#ifdef CONFIG_DEBUG_SPINLOCK
++ /* this is a valid case when another task releases the spinlock */
++ rq->lock.owner = next;
++#endif
++}
++
++static inline void finish_lock_switch(struct rq *rq)
++{
++ /*
++ * If we are tracking spinlock dependencies then we have to
++ * fix up the runqueue lock - which gets 'carried over' from
++ * prev into current:
++ */
++ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
++ __balance_callbacks(rq);
++ raw_spin_unlock_irq(&rq->lock);
++}
++
++/*
++ * NOP if the arch has not defined these:
++ */
++
++#ifndef prepare_arch_switch
++# define prepare_arch_switch(next) do { } while (0)
++#endif
++
++#ifndef finish_arch_post_lock_switch
++# define finish_arch_post_lock_switch() do { } while (0)
++#endif
++
++static inline void kmap_local_sched_out(void)
++{
++#ifdef CONFIG_KMAP_LOCAL
++ if (unlikely(current->kmap_ctrl.idx))
++ __kmap_local_sched_out();
++#endif
++}
++
++static inline void kmap_local_sched_in(void)
++{
++#ifdef CONFIG_KMAP_LOCAL
++ if (unlikely(current->kmap_ctrl.idx))
++ __kmap_local_sched_in();
++#endif
++}
++
++/**
++ * prepare_task_switch - prepare to switch tasks
++ * @rq: the runqueue preparing to switch
++ * @next: the task we are going to switch to.
++ *
++ * This is called with the rq lock held and interrupts off. It must
++ * be paired with a subsequent finish_task_switch after the context
++ * switch.
++ *
++ * prepare_task_switch sets up locking and calls architecture specific
++ * hooks.
++ */
++static inline void
++prepare_task_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ kcov_prepare_switch(prev);
++ sched_info_switch(rq, prev, next);
++ perf_event_task_sched_out(prev, next);
++ rseq_preempt(prev);
++ fire_sched_out_preempt_notifiers(prev, next);
++ kmap_local_sched_out();
++ prepare_task(next);
++ prepare_arch_switch(next);
++}
++
++/**
++ * finish_task_switch - clean up after a task-switch
++ * @rq: runqueue associated with task-switch
++ * @prev: the thread we just switched away from.
++ *
++ * finish_task_switch must be called after the context switch, paired
++ * with a prepare_task_switch call before the context switch.
++ * finish_task_switch will reconcile locking set up by prepare_task_switch,
++ * and do any other architecture-specific cleanup actions.
++ *
++ * Note that we may have delayed dropping an mm in context_switch(). If
++ * so, we finish that here outside of the runqueue lock. (Doing it
++ * with the lock held can cause deadlocks; see schedule() for
++ * details.)
++ *
++ * The context switch have flipped the stack from under us and restored the
++ * local variables which were saved when this task called schedule() in the
++ * past. prev == current is still correct but we need to recalculate this_rq
++ * because prev may have moved to another CPU.
++ */
++static struct rq *finish_task_switch(struct task_struct *prev)
++ __releases(rq->lock)
++{
++ struct rq *rq = this_rq();
++ struct mm_struct *mm = rq->prev_mm;
++ unsigned int prev_state;
++
++ /*
++ * The previous task will have left us with a preempt_count of 2
++ * because it left us after:
++ *
++ * schedule()
++ * preempt_disable(); // 1
++ * __schedule()
++ * raw_spin_lock_irq(&rq->lock) // 2
++ *
++ * Also, see FORK_PREEMPT_COUNT.
++ */
++ if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
++ "corrupted preempt_count: %s/%d/0x%x\n",
++ current->comm, current->pid, preempt_count()))
++ preempt_count_set(FORK_PREEMPT_COUNT);
++
++ rq->prev_mm = NULL;
++
++ /*
++ * A task struct has one reference for the use as "current".
++ * If a task dies, then it sets TASK_DEAD in tsk->state and calls
++ * schedule one last time. The schedule call will never return, and
++ * the scheduled task must drop that reference.
++ *
++ * We must observe prev->state before clearing prev->on_cpu (in
++ * finish_task), otherwise a concurrent wakeup can get prev
++ * running on another CPU and we could rave with its RUNNING -> DEAD
++ * transition, resulting in a double drop.
++ */
++ prev_state = READ_ONCE(prev->__state);
++ vtime_task_switch(prev);
++ perf_event_task_sched_in(prev, current);
++ finish_task(prev);
++ tick_nohz_task_switch();
++ finish_lock_switch(rq);
++ finish_arch_post_lock_switch();
++ kcov_finish_switch(current);
++ /*
++ * kmap_local_sched_out() is invoked with rq::lock held and
++ * interrupts disabled. There is no requirement for that, but the
++ * sched out code does not have an interrupt enabled section.
++ * Restoring the maps on sched in does not require interrupts being
++ * disabled either.
++ */
++ kmap_local_sched_in();
++
++ fire_sched_in_preempt_notifiers(current);
++ /*
++ * When switching through a kernel thread, the loop in
++ * membarrier_{private,global}_expedited() may have observed that
++ * kernel thread and not issued an IPI. It is therefore possible to
++ * schedule between user->kernel->user threads without passing though
++ * switch_mm(). Membarrier requires a barrier after storing to
++ * rq->curr, before returning to userspace, so provide them here:
++ *
++ * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
++ * provided by mmdrop(),
++ * - a sync_core for SYNC_CORE.
++ */
++ if (mm) {
++ membarrier_mm_sync_core_before_usermode(mm);
++ mmdrop_sched(mm);
++ }
++ if (unlikely(prev_state == TASK_DEAD)) {
++ /* Task is done with its stack. */
++ put_task_stack(prev);
++
++ put_task_struct_rcu_user(prev);
++ }
++
++ return rq;
++}
++
++/**
++ * schedule_tail - first thing a freshly forked thread must call.
++ * @prev: the thread we just switched away from.
++ */
++asmlinkage __visible void schedule_tail(struct task_struct *prev)
++ __releases(rq->lock)
++{
++ /*
++ * New tasks start with FORK_PREEMPT_COUNT, see there and
++ * finish_task_switch() for details.
++ *
++ * finish_task_switch() will drop rq->lock() and lower preempt_count
++ * and the preempt_enable() will end up enabling preemption (on
++ * PREEMPT_COUNT kernels).
++ */
++
++ finish_task_switch(prev);
++ preempt_enable();
++
++ if (current->set_child_tid)
++ put_user(task_pid_vnr(current), current->set_child_tid);
++
++ calculate_sigpending();
++}
++
++/*
++ * context_switch - switch to the new MM and the new thread's register state.
++ */
++static __always_inline struct rq *
++context_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ prepare_task_switch(rq, prev, next);
++
++ /*
++ * For paravirt, this is coupled with an exit in switch_to to
++ * combine the page table reload and the switch backend into
++ * one hypercall.
++ */
++ arch_start_context_switch(prev);
++
++ /*
++ * kernel -> kernel lazy + transfer active
++ * user -> kernel lazy + mmgrab() active
++ *
++ * kernel -> user switch + mmdrop() active
++ * user -> user switch
++ *
++ * switch_mm_cid() needs to be updated if the barriers provided
++ * by context_switch() are modified.
++ */
++ if (!next->mm) { // to kernel
++ enter_lazy_tlb(prev->active_mm, next);
++
++ next->active_mm = prev->active_mm;
++ if (prev->mm) // from user
++ mmgrab(prev->active_mm);
++ else
++ prev->active_mm = NULL;
++ } else { // to user
++ membarrier_switch_mm(rq, prev->active_mm, next->mm);
++ /*
++ * sys_membarrier() requires an smp_mb() between setting
++ * rq->curr / membarrier_switch_mm() and returning to userspace.
++ *
++ * The below provides this either through switch_mm(), or in
++ * case 'prev->active_mm == next->mm' through
++ * finish_task_switch()'s mmdrop().
++ */
++ switch_mm_irqs_off(prev->active_mm, next->mm, next);
++ lru_gen_use_mm(next->mm);
++
++ if (!prev->mm) { // from kernel
++ /* will mmdrop() in finish_task_switch(). */
++ rq->prev_mm = prev->active_mm;
++ prev->active_mm = NULL;
++ }
++ }
++
++ /* switch_mm_cid() requires the memory barriers above. */
++ switch_mm_cid(rq, prev, next);
++
++ prepare_lock_switch(rq, next);
++
++ /* Here we just switch the register state and the stack. */
++ switch_to(prev, next, prev);
++ barrier();
++
++ return finish_task_switch(prev);
++}
++
++/*
++ * nr_running, nr_uninterruptible and nr_context_switches:
++ *
++ * externally visible scheduler statistics: current number of runnable
++ * threads, total number of context switches performed since bootup.
++ */
++unsigned int nr_running(void)
++{
++ unsigned int i, sum = 0;
++
++ for_each_online_cpu(i)
++ sum += cpu_rq(i)->nr_running;
++
++ return sum;
++}
++
++/*
++ * Check if only the current task is running on the CPU.
++ *
++ * Caution: this function does not check that the caller has disabled
++ * preemption, thus the result might have a time-of-check-to-time-of-use
++ * race. The caller is responsible to use it correctly, for example:
++ *
++ * - from a non-preemptible section (of course)
++ *
++ * - from a thread that is bound to a single CPU
++ *
++ * - in a loop with very short iterations (e.g. a polling loop)
++ */
++bool single_task_running(void)
++{
++ return raw_rq()->nr_running == 1;
++}
++EXPORT_SYMBOL(single_task_running);
++
++unsigned long long nr_context_switches_cpu(int cpu)
++{
++ return cpu_rq(cpu)->nr_switches;
++}
++
++unsigned long long nr_context_switches(void)
++{
++ int i;
++ unsigned long long sum = 0;
++
++ for_each_possible_cpu(i)
++ sum += cpu_rq(i)->nr_switches;
++
++ return sum;
++}
++
++/*
++ * Consumers of these two interfaces, like for example the cpuidle menu
++ * governor, are using nonsensical data. Preferring shallow idle state selection
++ * for a CPU that has IO-wait which might not even end up running the task when
++ * it does become runnable.
++ */
++
++unsigned int nr_iowait_cpu(int cpu)
++{
++ return atomic_read(&cpu_rq(cpu)->nr_iowait);
++}
++
++/*
++ * IO-wait accounting, and how it's mostly bollocks (on SMP).
++ *
++ * The idea behind IO-wait account is to account the idle time that we could
++ * have spend running if it were not for IO. That is, if we were to improve the
++ * storage performance, we'd have a proportional reduction in IO-wait time.
++ *
++ * This all works nicely on UP, where, when a task blocks on IO, we account
++ * idle time as IO-wait, because if the storage were faster, it could've been
++ * running and we'd not be idle.
++ *
++ * This has been extended to SMP, by doing the same for each CPU. This however
++ * is broken.
++ *
++ * Imagine for instance the case where two tasks block on one CPU, only the one
++ * CPU will have IO-wait accounted, while the other has regular idle. Even
++ * though, if the storage were faster, both could've ran at the same time,
++ * utilising both CPUs.
++ *
++ * This means, that when looking globally, the current IO-wait accounting on
++ * SMP is a lower bound, by reason of under accounting.
++ *
++ * Worse, since the numbers are provided per CPU, they are sometimes
++ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
++ * associated with any one particular CPU, it can wake to another CPU than it
++ * blocked on. This means the per CPU IO-wait number is meaningless.
++ *
++ * Task CPU affinities can make all that even more 'interesting'.
++ */
++
++unsigned int nr_iowait(void)
++{
++ unsigned int i, sum = 0;
++
++ for_each_possible_cpu(i)
++ sum += nr_iowait_cpu(i);
++
++ return sum;
++}
++
++#ifdef CONFIG_SMP
++
++/*
++ * sched_exec - execve() is a valuable balancing opportunity, because at
++ * this point the task has the smallest effective memory and cache
++ * footprint.
++ */
++void sched_exec(void)
++{
++}
++
++#endif
++
++DEFINE_PER_CPU(struct kernel_stat, kstat);
++DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
++
++EXPORT_PER_CPU_SYMBOL(kstat);
++EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
++
++static inline void update_curr(struct rq *rq, struct task_struct *p)
++{
++ s64 ns = rq->clock_task - p->last_ran;
++
++ p->sched_time += ns;
++ cgroup_account_cputime(p, ns);
++ account_group_exec_runtime(p, ns);
++
++ p->time_slice -= ns;
++ p->last_ran = rq->clock_task;
++}
++
++/*
++ * Return accounted runtime for the task.
++ * Return separately the current's pending runtime that have not been
++ * accounted yet.
++ */
++unsigned long long task_sched_runtime(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++ u64 ns;
++
++#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
++ /*
++ * 64-bit doesn't need locks to atomically read a 64-bit value.
++ * So we have a optimization chance when the task's delta_exec is 0.
++ * Reading ->on_cpu is racy, but this is ok.
++ *
++ * If we race with it leaving CPU, we'll take a lock. So we're correct.
++ * If we race with it entering CPU, unaccounted time is 0. This is
++ * indistinguishable from the read occurring a few cycles earlier.
++ * If we see ->on_cpu without ->on_rq, the task is leaving, and has
++ * been accounted, so we're correct here as well.
++ */
++ if (!p->on_cpu || !task_on_rq_queued(p))
++ return tsk_seruntime(p);
++#endif
++
++ rq = task_access_lock_irqsave(p, &lock, &flags);
++ /*
++ * Must be ->curr _and_ ->on_rq. If dequeued, we would
++ * project cycles that may never be accounted to this
++ * thread, breaking clock_gettime().
++ */
++ if (p == rq->curr && task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ update_curr(rq, p);
++ }
++ ns = tsk_seruntime(p);
++ task_access_unlock_irqrestore(p, lock, &flags);
++
++ return ns;
++}
++
++/* This manages tasks that have run out of timeslice during a scheduler_tick */
++static inline void scheduler_task_tick(struct rq *rq)
++{
++ struct task_struct *p = rq->curr;
++
++ if (is_idle_task(p))
++ return;
++
++ update_curr(rq, p);
++ cpufreq_update_util(rq, 0);
++
++ /*
++ * Tasks have less than RESCHED_NS of time slice left they will be
++ * rescheduled.
++ */
++ if (p->time_slice >= RESCHED_NS)
++ return;
++ set_tsk_need_resched(p);
++ set_preempt_need_resched();
++}
++
++#ifdef CONFIG_SCHED_DEBUG
++static u64 cpu_resched_latency(struct rq *rq)
++{
++ int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
++ u64 resched_latency, now = rq_clock(rq);
++ static bool warned_once;
++
++ if (sysctl_resched_latency_warn_once && warned_once)
++ return 0;
++
++ if (!need_resched() || !latency_warn_ms)
++ return 0;
++
++ if (system_state == SYSTEM_BOOTING)
++ return 0;
++
++ if (!rq->last_seen_need_resched_ns) {
++ rq->last_seen_need_resched_ns = now;
++ rq->ticks_without_resched = 0;
++ return 0;
++ }
++
++ rq->ticks_without_resched++;
++ resched_latency = now - rq->last_seen_need_resched_ns;
++ if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC)
++ return 0;
++
++ warned_once = true;
++
++ return resched_latency;
++}
++
++static int __init setup_resched_latency_warn_ms(char *str)
++{
++ long val;
++
++ if ((kstrtol(str, 0, &val))) {
++ pr_warn("Unable to set resched_latency_warn_ms\n");
++ return 1;
++ }
++
++ sysctl_resched_latency_warn_ms = val;
++ return 1;
++}
++__setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
++#else
++static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
++#endif /* CONFIG_SCHED_DEBUG */
++
++/*
++ * This function gets called by the timer code, with HZ frequency.
++ * We call it with interrupts disabled.
++ */
++void sched_tick(void)
++{
++ int cpu __maybe_unused = smp_processor_id();
++ struct rq *rq = cpu_rq(cpu);
++ struct task_struct *curr = rq->curr;
++ u64 resched_latency;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ arch_scale_freq_tick();
++
++ sched_clock_tick();
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++
++ scheduler_task_tick(rq);
++ if (sched_feat(LATENCY_WARN))
++ resched_latency = cpu_resched_latency(rq);
++ calc_global_load_tick(rq);
++
++ task_tick_mm_cid(rq, rq->curr);
++
++ raw_spin_unlock(&rq->lock);
++
++ if (sched_feat(LATENCY_WARN) && resched_latency)
++ resched_latency_warn(cpu, resched_latency);
++
++ perf_event_task_tick();
++
++ if (curr->flags & PF_WQ_WORKER)
++ wq_worker_tick(curr);
++}
++
++#ifdef CONFIG_NO_HZ_FULL
++
++struct tick_work {
++ int cpu;
++ atomic_t state;
++ struct delayed_work work;
++};
++/* Values for ->state, see diagram below. */
++#define TICK_SCHED_REMOTE_OFFLINE 0
++#define TICK_SCHED_REMOTE_OFFLINING 1
++#define TICK_SCHED_REMOTE_RUNNING 2
++
++/*
++ * State diagram for ->state:
++ *
++ *
++ * TICK_SCHED_REMOTE_OFFLINE
++ * | ^
++ * | |
++ * | | sched_tick_remote()
++ * | |
++ * | |
++ * +--TICK_SCHED_REMOTE_OFFLINING
++ * | ^
++ * | |
++ * sched_tick_start() | | sched_tick_stop()
++ * | |
++ * V |
++ * TICK_SCHED_REMOTE_RUNNING
++ *
++ *
++ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
++ * and sched_tick_start() are happy to leave the state in RUNNING.
++ */
++
++static struct tick_work __percpu *tick_work_cpu;
++
++static void sched_tick_remote(struct work_struct *work)
++{
++ struct delayed_work *dwork = to_delayed_work(work);
++ struct tick_work *twork = container_of(dwork, struct tick_work, work);
++ int cpu = twork->cpu;
++ struct rq *rq = cpu_rq(cpu);
++ int os;
++
++ /*
++ * Handle the tick only if it appears the remote CPU is running in full
++ * dynticks mode. The check is racy by nature, but missing a tick or
++ * having one too much is no big deal because the scheduler tick updates
++ * statistics and checks timeslices in a time-independent way, regardless
++ * of when exactly it is running.
++ */
++ if (tick_nohz_tick_stopped_cpu(cpu)) {
++ guard(raw_spinlock_irqsave)(&rq->lock);
++ struct task_struct *curr = rq->curr;
++
++ if (cpu_online(cpu)) {
++ update_rq_clock(rq);
++
++ if (!is_idle_task(curr)) {
++ /*
++ * Make sure the next tick runs within a
++ * reasonable amount of time.
++ */
++ u64 delta = rq_clock_task(rq) - curr->last_ran;
++ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
++ }
++ scheduler_task_tick(rq);
++
++ calc_load_nohz_remote(rq);
++ }
++ }
++
++ /*
++ * Run the remote tick once per second (1Hz). This arbitrary
++ * frequency is large enough to avoid overload but short enough
++ * to keep scheduler internal stats reasonably up to date. But
++ * first update state to reflect hotplug activity if required.
++ */
++ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
++ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
++ if (os == TICK_SCHED_REMOTE_RUNNING)
++ queue_delayed_work(system_unbound_wq, dwork, HZ);
++}
++
++static void sched_tick_start(int cpu)
++{
++ int os;
++ struct tick_work *twork;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ return;
++
++ WARN_ON_ONCE(!tick_work_cpu);
++
++ twork = per_cpu_ptr(tick_work_cpu, cpu);
++ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
++ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
++ if (os == TICK_SCHED_REMOTE_OFFLINE) {
++ twork->cpu = cpu;
++ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
++ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
++ }
++}
++
++#ifdef CONFIG_HOTPLUG_CPU
++static void sched_tick_stop(int cpu)
++{
++ struct tick_work *twork;
++ int os;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ return;
++
++ WARN_ON_ONCE(!tick_work_cpu);
++
++ twork = per_cpu_ptr(tick_work_cpu, cpu);
++ /* There cannot be competing actions, but don't rely on stop-machine. */
++ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
++ WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
++ /* Don't cancel, as this would mess up the state machine. */
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
++int __init sched_tick_offload_init(void)
++{
++ tick_work_cpu = alloc_percpu(struct tick_work);
++ BUG_ON(!tick_work_cpu);
++ return 0;
++}
++
++#else /* !CONFIG_NO_HZ_FULL */
++static inline void sched_tick_start(int cpu) { }
++static inline void sched_tick_stop(int cpu) { }
++#endif
++
++#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
++ defined(CONFIG_PREEMPT_TRACER))
++/*
++ * If the value passed in is equal to the current preempt count
++ * then we just disabled preemption. Start timing the latency.
++ */
++static inline void preempt_latency_start(int val)
++{
++ if (preempt_count() == val) {
++ unsigned long ip = get_lock_parent_ip();
++#ifdef CONFIG_DEBUG_PREEMPT
++ current->preempt_disable_ip = ip;
++#endif
++ trace_preempt_off(CALLER_ADDR0, ip);
++ }
++}
++
++void preempt_count_add(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
++ return;
++#endif
++ __preempt_count_add(val);
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Spinlock count overflowing soon?
++ */
++ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
++ PREEMPT_MASK - 10);
++#endif
++ preempt_latency_start(val);
++}
++EXPORT_SYMBOL(preempt_count_add);
++NOKPROBE_SYMBOL(preempt_count_add);
++
++/*
++ * If the value passed in equals to the current preempt count
++ * then we just enabled preemption. Stop timing the latency.
++ */
++static inline void preempt_latency_stop(int val)
++{
++ if (preempt_count() == val)
++ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
++}
++
++void preempt_count_sub(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
++ return;
++ /*
++ * Is the spinlock portion underflowing?
++ */
++ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
++ !(preempt_count() & PREEMPT_MASK)))
++ return;
++#endif
++
++ preempt_latency_stop(val);
++ __preempt_count_sub(val);
++}
++EXPORT_SYMBOL(preempt_count_sub);
++NOKPROBE_SYMBOL(preempt_count_sub);
++
++#else
++static inline void preempt_latency_start(int val) { }
++static inline void preempt_latency_stop(int val) { }
++#endif
++
++static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ return p->preempt_disable_ip;
++#else
++ return 0;
++#endif
++}
++
++/*
++ * Print scheduling while atomic bug:
++ */
++static noinline void __schedule_bug(struct task_struct *prev)
++{
++ /* Save this before calling printk(), since that will clobber it */
++ unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
++
++ if (oops_in_progress)
++ return;
++
++ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
++ prev->comm, prev->pid, preempt_count());
++
++ debug_show_held_locks(prev);
++ print_modules();
++ if (irqs_disabled())
++ print_irqtrace_events(prev);
++ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
++ pr_err("Preemption disabled at:");
++ print_ip_sym(KERN_ERR, preempt_disable_ip);
++ }
++ check_panic_on_warn("scheduling while atomic");
++
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++
++/*
++ * Various schedule()-time debugging checks and statistics:
++ */
++static inline void schedule_debug(struct task_struct *prev, bool preempt)
++{
++#ifdef CONFIG_SCHED_STACK_END_CHECK
++ if (task_stack_end_corrupted(prev))
++ panic("corrupted stack end detected inside scheduler\n");
++
++ if (task_scs_end_corrupted(prev))
++ panic("corrupted shadow stack detected inside scheduler\n");
++#endif
++
++#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
++ if (!preempt && READ_ONCE(prev->__state) && prev->non_block_count) {
++ printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
++ prev->comm, prev->pid, prev->non_block_count);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++ }
++#endif
++
++ if (unlikely(in_atomic_preempt_off())) {
++ __schedule_bug(prev);
++ preempt_count_set(PREEMPT_DISABLED);
++ }
++ rcu_sleep_check();
++ SCHED_WARN_ON(ct_state() == CONTEXT_USER);
++
++ profile_hit(SCHED_PROFILING, __builtin_return_address(0));
++
++ schedstat_inc(this_rq()->sched_count);
++}
++
++#ifdef ALT_SCHED_DEBUG
++static void alt_sched_debug(void)
++{
++ printk(KERN_INFO "sched: pending: 0x%04lx, idle: 0x%04lx, sg_idle: 0x%04lx,"
++ " ecore_idle: 0x%04lx\n",
++ sched_rq_pending_mask.bits[0],
++ sched_idle_mask->bits[0],
++ sched_pcore_idle_mask->bits[0],
++ sched_ecore_idle_mask->bits[0]);
++}
++#else
++inline void alt_sched_debug(void) {}
++#endif
++
++#ifdef CONFIG_SMP
++
++#ifdef CONFIG_PREEMPT_RT
++#define SCHED_NR_MIGRATE_BREAK 8
++#else
++#define SCHED_NR_MIGRATE_BREAK 32
++#endif
++
++const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
++
++/*
++ * Migrate pending tasks in @rq to @dest_cpu
++ */
++static inline int
++migrate_pending_tasks(struct rq *rq, struct rq *dest_rq, const int dest_cpu)
++{
++ struct task_struct *p, *skip = rq->curr;
++ int nr_migrated = 0;
++ int nr_tries = min(rq->nr_running / 2, sysctl_sched_nr_migrate);
++
++ /* WA to check rq->curr is still on rq */
++ if (!task_on_rq_queued(skip))
++ return 0;
++
++ while (skip != rq->idle && nr_tries &&
++ (p = sched_rq_next_task(skip, rq)) != rq->idle) {
++ skip = sched_rq_next_task(p, rq);
++ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) {
++ __SCHED_DEQUEUE_TASK(p, rq, 0, );
++ set_task_cpu(p, dest_cpu);
++ sched_task_sanity_check(p, dest_rq);
++ sched_mm_cid_migrate_to(dest_rq, p, cpu_of(rq));
++ __SCHED_ENQUEUE_TASK(p, dest_rq, 0, );
++ nr_migrated++;
++ }
++ nr_tries--;
++ }
++
++ return nr_migrated;
++}
++
++static inline int take_other_rq_tasks(struct rq *rq, int cpu)
++{
++ cpumask_t *topo_mask, *end_mask, chk;
++
++ if (unlikely(!rq->online))
++ return 0;
++
++ if (cpumask_empty(&sched_rq_pending_mask))
++ return 0;
++
++ topo_mask = per_cpu(sched_cpu_topo_masks, cpu);
++ end_mask = per_cpu(sched_cpu_topo_end_mask, cpu);
++ do {
++ int i;
++
++ if (!cpumask_and(&chk, &sched_rq_pending_mask, topo_mask))
++ continue;
++
++ for_each_cpu_wrap(i, &chk, cpu) {
++ int nr_migrated;
++ struct rq *src_rq;
++
++ src_rq = cpu_rq(i);
++ if (!do_raw_spin_trylock(&src_rq->lock))
++ continue;
++ spin_acquire(&src_rq->lock.dep_map,
++ SINGLE_DEPTH_NESTING, 1, _RET_IP_);
++
++ if ((nr_migrated = migrate_pending_tasks(src_rq, rq, cpu))) {
++ src_rq->nr_running -= nr_migrated;
++ if (src_rq->nr_running < 2)
++ cpumask_clear_cpu(i, &sched_rq_pending_mask);
++
++ spin_release(&src_rq->lock.dep_map, _RET_IP_);
++ do_raw_spin_unlock(&src_rq->lock);
++
++ rq->nr_running += nr_migrated;
++ if (rq->nr_running > 1)
++ cpumask_set_cpu(cpu, &sched_rq_pending_mask);
++
++ update_sched_preempt_mask(rq);
++ cpufreq_update_util(rq, 0);
++
++ return 1;
++ }
++
++ spin_release(&src_rq->lock.dep_map, _RET_IP_);
++ do_raw_spin_unlock(&src_rq->lock);
++ }
++ } while (++topo_mask < end_mask);
++
++ return 0;
++}
++#endif
++
++static inline void time_slice_expired(struct task_struct *p, struct rq *rq)
++{
++ p->time_slice = sysctl_sched_base_slice;
++
++ sched_task_renew(p, rq);
++
++ if (SCHED_FIFO != p->policy && task_on_rq_queued(p))
++ requeue_task(p, rq);
++}
++
++/*
++ * Timeslices below RESCHED_NS are considered as good as expired as there's no
++ * point rescheduling when there's so little time left.
++ */
++static inline void check_curr(struct task_struct *p, struct rq *rq)
++{
++ if (unlikely(rq->idle == p))
++ return;
++
++ update_curr(rq, p);
++
++ if (p->time_slice < RESCHED_NS)
++ time_slice_expired(p, rq);
++}
++
++static inline struct task_struct *
++choose_next_task(struct rq *rq, int cpu)
++{
++ struct task_struct *next = sched_rq_first_task(rq);
++
++ if (next == rq->idle) {
++#ifdef CONFIG_SMP
++ if (!take_other_rq_tasks(rq, cpu)) {
++ if (likely(rq->balance_func && rq->online))
++ rq->balance_func(rq, cpu);
++#endif /* CONFIG_SMP */
++
++ schedstat_inc(rq->sched_goidle);
++ /*printk(KERN_INFO "sched: choose_next_task(%d) idle %px\n", cpu, next);*/
++ return next;
++#ifdef CONFIG_SMP
++ }
++ next = sched_rq_first_task(rq);
++#endif
++ }
++#ifdef CONFIG_HIGH_RES_TIMERS
++ hrtick_start(rq, next->time_slice);
++#endif
++ /*printk(KERN_INFO "sched: choose_next_task(%d) next %px\n", cpu, next);*/
++ return next;
++}
++
++/*
++ * Constants for the sched_mode argument of __schedule().
++ *
++ * The mode argument allows RT enabled kernels to differentiate a
++ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
++ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
++ * optimize the AND operation out and just check for zero.
++ */
++#define SM_NONE 0x0
++#define SM_PREEMPT 0x1
++#define SM_RTLOCK_WAIT 0x2
++
++#ifndef CONFIG_PREEMPT_RT
++# define SM_MASK_PREEMPT (~0U)
++#else
++# define SM_MASK_PREEMPT SM_PREEMPT
++#endif
++
++/*
++ * schedule() is the main scheduler function.
++ *
++ * The main means of driving the scheduler and thus entering this function are:
++ *
++ * 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
++ *
++ * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
++ * paths. For example, see arch/x86/entry_64.S.
++ *
++ * To drive preemption between tasks, the scheduler sets the flag in timer
++ * interrupt handler sched_tick().
++ *
++ * 3. Wakeups don't really cause entry into schedule(). They add a
++ * task to the run-queue and that's it.
++ *
++ * Now, if the new task added to the run-queue preempts the current
++ * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
++ * called on the nearest possible occasion:
++ *
++ * - If the kernel is preemptible (CONFIG_PREEMPTION=y):
++ *
++ * - in syscall or exception context, at the next outmost
++ * preempt_enable(). (this might be as soon as the wake_up()'s
++ * spin_unlock()!)
++ *
++ * - in IRQ context, return from interrupt-handler to
++ * preemptible context
++ *
++ * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
++ * then at the next:
++ *
++ * - cond_resched() call
++ * - explicit schedule() call
++ * - return from syscall or exception to user-space
++ * - return from interrupt-handler to user-space
++ *
++ * WARNING: must be called with preemption disabled!
++ */
++static void __sched notrace __schedule(unsigned int sched_mode)
++{
++ struct task_struct *prev, *next;
++ unsigned long *switch_count;
++ unsigned long prev_state;
++ struct rq *rq;
++ int cpu;
++
++ cpu = smp_processor_id();
++ rq = cpu_rq(cpu);
++ prev = rq->curr;
++
++ schedule_debug(prev, !!sched_mode);
++
++ /* by passing sched_feat(HRTICK) checking which Alt schedule FW doesn't support */
++ hrtick_clear(rq);
++
++ local_irq_disable();
++ rcu_note_context_switch(!!sched_mode);
++
++ /*
++ * Make sure that signal_pending_state()->signal_pending() below
++ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
++ * done by the caller to avoid the race with signal_wake_up():
++ *
++ * __set_current_state(@state) signal_wake_up()
++ * schedule() set_tsk_thread_flag(p, TIF_SIGPENDING)
++ * wake_up_state(p, state)
++ * LOCK rq->lock LOCK p->pi_state
++ * smp_mb__after_spinlock() smp_mb__after_spinlock()
++ * if (signal_pending_state()) if (p->state & @state)
++ *
++ * Also, the membarrier system call requires a full memory barrier
++ * after coming from user-space, before storing to rq->curr; this
++ * barrier matches a full barrier in the proximity of the membarrier
++ * system call exit.
++ */
++ raw_spin_lock(&rq->lock);
++ smp_mb__after_spinlock();
++
++ update_rq_clock(rq);
++
++ switch_count = &prev->nivcsw;
++ /*
++ * We must load prev->state once (task_struct::state is volatile), such
++ * that we form a control dependency vs deactivate_task() below.
++ */
++ prev_state = READ_ONCE(prev->__state);
++ if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
++ if (signal_pending_state(prev_state, prev)) {
++ WRITE_ONCE(prev->__state, TASK_RUNNING);
++ } else {
++ prev->sched_contributes_to_load =
++ (prev_state & TASK_UNINTERRUPTIBLE) &&
++ !(prev_state & TASK_NOLOAD) &&
++ !(prev_state & TASK_FROZEN);
++
++ if (prev->sched_contributes_to_load)
++ rq->nr_uninterruptible++;
++
++ /*
++ * __schedule() ttwu()
++ * prev_state = prev->state; if (p->on_rq && ...)
++ * if (prev_state) goto out;
++ * p->on_rq = 0; smp_acquire__after_ctrl_dep();
++ * p->state = TASK_WAKING
++ *
++ * Where __schedule() and ttwu() have matching control dependencies.
++ *
++ * After this, schedule() must not care about p->state any more.
++ */
++ sched_task_deactivate(prev, rq);
++ deactivate_task(prev, rq);
++
++ if (prev->in_iowait) {
++ atomic_inc(&rq->nr_iowait);
++ delayacct_blkio_start();
++ }
++ }
++ switch_count = &prev->nvcsw;
++ }
++
++ check_curr(prev, rq);
++
++ next = choose_next_task(rq, cpu);
++ clear_tsk_need_resched(prev);
++ clear_preempt_need_resched();
++#ifdef CONFIG_SCHED_DEBUG
++ rq->last_seen_need_resched_ns = 0;
++#endif
++
++ if (likely(prev != next)) {
++ next->last_ran = rq->clock_task;
++
++ /*printk(KERN_INFO "sched: %px -> %px\n", prev, next);*/
++ rq->nr_switches++;
++ /*
++ * RCU users of rcu_dereference(rq->curr) may not see
++ * changes to task_struct made by pick_next_task().
++ */
++ RCU_INIT_POINTER(rq->curr, next);
++ /*
++ * The membarrier system call requires each architecture
++ * to have a full memory barrier after updating
++ * rq->curr, before returning to user-space.
++ *
++ * Here are the schemes providing that barrier on the
++ * various architectures:
++ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC,
++ * RISC-V. switch_mm() relies on membarrier_arch_switch_mm()
++ * on PowerPC and on RISC-V.
++ * - finish_lock_switch() for weakly-ordered
++ * architectures where spin_unlock is a full barrier,
++ * - switch_to() for arm64 (weakly-ordered, spin_unlock
++ * is a RELEASE barrier),
++ *
++ * The barrier matches a full barrier in the proximity of
++ * the membarrier system call entry.
++ *
++ * On RISC-V, this barrier pairing is also needed for the
++ * SYNC_CORE command when switching between processes, cf.
++ * the inline comments in membarrier_arch_switch_mm().
++ */
++ ++*switch_count;
++
++ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
++
++ /* Also unlocks the rq: */
++ rq = context_switch(rq, prev, next);
++
++ cpu = cpu_of(rq);
++ } else {
++ __balance_callbacks(rq);
++ raw_spin_unlock_irq(&rq->lock);
++ }
++}
++
++void __noreturn do_task_dead(void)
++{
++ /* Causes final put_task_struct in finish_task_switch(): */
++ set_special_state(TASK_DEAD);
++
++ /* Tell freezer to ignore us: */
++ current->flags |= PF_NOFREEZE;
++
++ __schedule(SM_NONE);
++ BUG();
++
++ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
++ for (;;)
++ cpu_relax();
++}
++
++static inline void sched_submit_work(struct task_struct *tsk)
++{
++ static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
++ unsigned int task_flags;
++
++ /*
++ * Establish LD_WAIT_CONFIG context to ensure none of the code called
++ * will use a blocking primitive -- which would lead to recursion.
++ */
++ lock_map_acquire_try(&sched_map);
++
++ task_flags = tsk->flags;
++ /*
++ * If a worker goes to sleep, notify and ask workqueue whether it
++ * wants to wake up a task to maintain concurrency.
++ */
++ if (task_flags & PF_WQ_WORKER)
++ wq_worker_sleeping(tsk);
++ else if (task_flags & PF_IO_WORKER)
++ io_wq_worker_sleeping(tsk);
++
++ /*
++ * spinlock and rwlock must not flush block requests. This will
++ * deadlock if the callback attempts to acquire a lock which is
++ * already acquired.
++ */
++ SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
++
++ /*
++ * If we are going to sleep and we have plugged IO queued,
++ * make sure to submit it to avoid deadlocks.
++ */
++ blk_flush_plug(tsk->plug, true);
++
++ lock_map_release(&sched_map);
++}
++
++static void sched_update_worker(struct task_struct *tsk)
++{
++ if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
++ if (tsk->flags & PF_BLOCK_TS)
++ blk_plug_invalidate_ts(tsk);
++ if (tsk->flags & PF_WQ_WORKER)
++ wq_worker_running(tsk);
++ else if (tsk->flags & PF_IO_WORKER)
++ io_wq_worker_running(tsk);
++ }
++}
++
++static __always_inline void __schedule_loop(unsigned int sched_mode)
++{
++ do {
++ preempt_disable();
++ __schedule(sched_mode);
++ sched_preempt_enable_no_resched();
++ } while (need_resched());
++}
++
++asmlinkage __visible void __sched schedule(void)
++{
++ struct task_struct *tsk = current;
++
++#ifdef CONFIG_RT_MUTEXES
++ lockdep_assert(!tsk->sched_rt_mutex);
++#endif
++
++ if (!task_is_running(tsk))
++ sched_submit_work(tsk);
++ __schedule_loop(SM_NONE);
++ sched_update_worker(tsk);
++}
++EXPORT_SYMBOL(schedule);
++
++/*
++ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
++ * state (have scheduled out non-voluntarily) by making sure that all
++ * tasks have either left the run queue or have gone into user space.
++ * As idle tasks do not do either, they must not ever be preempted
++ * (schedule out non-voluntarily).
++ *
++ * schedule_idle() is similar to schedule_preempt_disable() except that it
++ * never enables preemption because it does not call sched_submit_work().
++ */
++void __sched schedule_idle(void)
++{
++ /*
++ * As this skips calling sched_submit_work(), which the idle task does
++ * regardless because that function is a nop when the task is in a
++ * TASK_RUNNING state, make sure this isn't used someplace that the
++ * current task can be in any other state. Note, idle is always in the
++ * TASK_RUNNING state.
++ */
++ WARN_ON_ONCE(current->__state);
++ do {
++ __schedule(SM_NONE);
++ } while (need_resched());
++}
++
++#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK)
++asmlinkage __visible void __sched schedule_user(void)
++{
++ /*
++ * If we come here after a random call to set_need_resched(),
++ * or we have been woken up remotely but the IPI has not yet arrived,
++ * we haven't yet exited the RCU idle mode. Do it here manually until
++ * we find a better solution.
++ *
++ * NB: There are buggy callers of this function. Ideally we
++ * should warn if prev_state != CONTEXT_USER, but that will trigger
++ * too frequently to make sense yet.
++ */
++ enum ctx_state prev_state = exception_enter();
++ schedule();
++ exception_exit(prev_state);
++}
++#endif
++
++/**
++ * schedule_preempt_disabled - called with preemption disabled
++ *
++ * Returns with preemption disabled. Note: preempt_count must be 1
++ */
++void __sched schedule_preempt_disabled(void)
++{
++ sched_preempt_enable_no_resched();
++ schedule();
++ preempt_disable();
++}
++
++#ifdef CONFIG_PREEMPT_RT
++void __sched notrace schedule_rtlock(void)
++{
++ __schedule_loop(SM_RTLOCK_WAIT);
++}
++NOKPROBE_SYMBOL(schedule_rtlock);
++#endif
++
++static void __sched notrace preempt_schedule_common(void)
++{
++ do {
++ /*
++ * Because the function tracer can trace preempt_count_sub()
++ * and it also uses preempt_enable/disable_notrace(), if
++ * NEED_RESCHED is set, the preempt_enable_notrace() called
++ * by the function tracer will call this function again and
++ * cause infinite recursion.
++ *
++ * Preemption must be disabled here before the function
++ * tracer can trace. Break up preempt_disable() into two
++ * calls. One to disable preemption without fear of being
++ * traced. The other to still record the preemption latency,
++ * which can also be traced by the function tracer.
++ */
++ preempt_disable_notrace();
++ preempt_latency_start(1);
++ __schedule(SM_PREEMPT);
++ preempt_latency_stop(1);
++ preempt_enable_no_resched_notrace();
++
++ /*
++ * Check again in case we missed a preemption opportunity
++ * between schedule and now.
++ */
++ } while (need_resched());
++}
++
++#ifdef CONFIG_PREEMPTION
++/*
++ * This is the entry point to schedule() from in-kernel preemption
++ * off of preempt_enable.
++ */
++asmlinkage __visible void __sched notrace preempt_schedule(void)
++{
++ /*
++ * If there is a non-zero preempt_count or interrupts are disabled,
++ * we do not want to preempt the current task. Just return..
++ */
++ if (likely(!preemptible()))
++ return;
++
++ preempt_schedule_common();
++}
++NOKPROBE_SYMBOL(preempt_schedule);
++EXPORT_SYMBOL(preempt_schedule);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#ifndef preempt_schedule_dynamic_enabled
++#define preempt_schedule_dynamic_enabled preempt_schedule
++#define preempt_schedule_dynamic_disabled NULL
++#endif
++DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
++EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
++void __sched notrace dynamic_preempt_schedule(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
++ return;
++ preempt_schedule();
++}
++NOKPROBE_SYMBOL(dynamic_preempt_schedule);
++EXPORT_SYMBOL(dynamic_preempt_schedule);
++#endif
++#endif
++
++/**
++ * preempt_schedule_notrace - preempt_schedule called by tracing
++ *
++ * The tracing infrastructure uses preempt_enable_notrace to prevent
++ * recursion and tracing preempt enabling caused by the tracing
++ * infrastructure itself. But as tracing can happen in areas coming
++ * from userspace or just about to enter userspace, a preempt enable
++ * can occur before user_exit() is called. This will cause the scheduler
++ * to be called when the system is still in usermode.
++ *
++ * To prevent this, the preempt_enable_notrace will use this function
++ * instead of preempt_schedule() to exit user context if needed before
++ * calling the scheduler.
++ */
++asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
++{
++ enum ctx_state prev_ctx;
++
++ if (likely(!preemptible()))
++ return;
++
++ do {
++ /*
++ * Because the function tracer can trace preempt_count_sub()
++ * and it also uses preempt_enable/disable_notrace(), if
++ * NEED_RESCHED is set, the preempt_enable_notrace() called
++ * by the function tracer will call this function again and
++ * cause infinite recursion.
++ *
++ * Preemption must be disabled here before the function
++ * tracer can trace. Break up preempt_disable() into two
++ * calls. One to disable preemption without fear of being
++ * traced. The other to still record the preemption latency,
++ * which can also be traced by the function tracer.
++ */
++ preempt_disable_notrace();
++ preempt_latency_start(1);
++ /*
++ * Needs preempt disabled in case user_exit() is traced
++ * and the tracer calls preempt_enable_notrace() causing
++ * an infinite recursion.
++ */
++ prev_ctx = exception_enter();
++ __schedule(SM_PREEMPT);
++ exception_exit(prev_ctx);
++
++ preempt_latency_stop(1);
++ preempt_enable_no_resched_notrace();
++ } while (need_resched());
++}
++EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#ifndef preempt_schedule_notrace_dynamic_enabled
++#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace
++#define preempt_schedule_notrace_dynamic_disabled NULL
++#endif
++DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
++EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
++void __sched notrace dynamic_preempt_schedule_notrace(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
++ return;
++ preempt_schedule_notrace();
++}
++NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
++EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
++#endif
++#endif
++
++#endif /* CONFIG_PREEMPTION */
++
++/*
++ * This is the entry point to schedule() from kernel preemption
++ * off of irq context.
++ * Note, that this is called and return with irqs disabled. This will
++ * protect us against recursive calling from irq.
++ */
++asmlinkage __visible void __sched preempt_schedule_irq(void)
++{
++ enum ctx_state prev_state;
++
++ /* Catch callers which need to be fixed */
++ BUG_ON(preempt_count() || !irqs_disabled());
++
++ prev_state = exception_enter();
++
++ do {
++ preempt_disable();
++ local_irq_enable();
++ __schedule(SM_PREEMPT);
++ local_irq_disable();
++ sched_preempt_enable_no_resched();
++ } while (need_resched());
++
++ exception_exit(prev_state);
++}
++
++int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
++ void *key)
++{
++ WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
++ return try_to_wake_up(curr->private, mode, wake_flags);
++}
++EXPORT_SYMBOL(default_wake_function);
++
++static inline void check_task_changed(struct task_struct *p, struct rq *rq)
++{
++ /* Trigger resched if task sched_prio has been modified. */
++ if (task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ requeue_task(p, rq);
++ wakeup_preempt(rq);
++ }
++}
++
++static void __setscheduler_prio(struct task_struct *p, int prio)
++{
++ p->prio = prio;
++}
++
++#ifdef CONFIG_RT_MUTEXES
++
++/*
++ * Would be more useful with typeof()/auto_type but they don't mix with
++ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
++ * name such that if someone were to implement this function we get to compare
++ * notes.
++ */
++#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
++
++void rt_mutex_pre_schedule(void)
++{
++ lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
++ sched_submit_work(current);
++}
++
++void rt_mutex_schedule(void)
++{
++ lockdep_assert(current->sched_rt_mutex);
++ __schedule_loop(SM_NONE);
++}
++
++void rt_mutex_post_schedule(void)
++{
++ sched_update_worker(current);
++ lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
++}
++
++static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
++{
++ if (pi_task)
++ prio = min(prio, pi_task->prio);
++
++ return prio;
++}
++
++static inline int rt_effective_prio(struct task_struct *p, int prio)
++{
++ struct task_struct *pi_task = rt_mutex_get_top_task(p);
++
++ return __rt_effective_prio(pi_task, prio);
++}
++
++/*
++ * rt_mutex_setprio - set the current priority of a task
++ * @p: task to boost
++ * @pi_task: donor task
++ *
++ * This function changes the 'effective' priority of a task. It does
++ * not touch ->normal_prio like __setscheduler().
++ *
++ * Used by the rt_mutex code to implement priority inheritance
++ * logic. Call site only calls if the priority of the task changed.
++ */
++void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
++{
++ int prio;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ /* XXX used to be waiter->prio, not waiter->task->prio */
++ prio = __rt_effective_prio(pi_task, p->normal_prio);
++
++ /*
++ * If nothing changed; bail early.
++ */
++ if (p->pi_top_task == pi_task && prio == p->prio)
++ return;
++
++ rq = __task_access_lock(p, &lock);
++ /*
++ * Set under pi_lock && rq->lock, such that the value can be used under
++ * either lock.
++ *
++ * Note that there is loads of tricky to make this pointer cache work
++ * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
++ * ensure a task is de-boosted (pi_task is set to NULL) before the
++ * task is allowed to run again (and can exit). This ensures the pointer
++ * points to a blocked task -- which guarantees the task is present.
++ */
++ p->pi_top_task = pi_task;
++
++ /*
++ * For FIFO/RR we only need to set prio, if that matches we're done.
++ */
++ if (prio == p->prio)
++ goto out_unlock;
++
++ /*
++ * Idle task boosting is a nono in general. There is one
++ * exception, when PREEMPT_RT and NOHZ is active:
++ *
++ * The idle task calls get_next_timer_interrupt() and holds
++ * the timer wheel base->lock on the CPU and another CPU wants
++ * to access the timer (probably to cancel it). We can safely
++ * ignore the boosting request, as the idle CPU runs this code
++ * with interrupts disabled and will complete the lock
++ * protected section without being interrupted. So there is no
++ * real need to boost.
++ */
++ if (unlikely(p == rq->idle)) {
++ WARN_ON(p != rq->curr);
++ WARN_ON(p->pi_blocked_on);
++ goto out_unlock;
++ }
++
++ trace_sched_pi_setprio(p, pi_task);
++
++ __setscheduler_prio(p, prio);
++
++ check_task_changed(p, rq);
++out_unlock:
++ /* Avoid rq from going away on us: */
++ preempt_disable();
++
++ if (task_on_rq_queued(p))
++ __balance_callbacks(rq);
++ __task_access_unlock(p, lock);
++
++ preempt_enable();
++}
++#else
++static inline int rt_effective_prio(struct task_struct *p, int prio)
++{
++ return prio;
++}
++#endif
++
++void set_user_nice(struct task_struct *p, long nice)
++{
++ unsigned long flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
++ return;
++ /*
++ * We have to be careful, if called from sys_setpriority(),
++ * the task might be in the middle of scheduling on another CPU.
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ rq = __task_access_lock(p, &lock);
++
++ p->static_prio = NICE_TO_PRIO(nice);
++ /*
++ * The RT priorities are set via sched_setscheduler(), but we still
++ * allow the 'normal' nice value to be set - but as expected
++ * it won't have any effect on scheduling until the task is
++ * not SCHED_NORMAL/SCHED_BATCH:
++ */
++ if (task_has_rt_policy(p))
++ goto out_unlock;
++
++ p->prio = effective_prio(p);
++
++ check_task_changed(p, rq);
++out_unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++EXPORT_SYMBOL(set_user_nice);
++
++/*
++ * is_nice_reduction - check if nice value is an actual reduction
++ *
++ * Similar to can_nice() but does not perform a capability check.
++ *
++ * @p: task
++ * @nice: nice value
++ */
++static bool is_nice_reduction(const struct task_struct *p, const int nice)
++{
++ /* Convert nice value [19,-20] to rlimit style value [1,40]: */
++ int nice_rlim = nice_to_rlimit(nice);
++
++ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));
++}
++
++/*
++ * can_nice - check if a task can reduce its nice value
++ * @p: task
++ * @nice: nice value
++ */
++int can_nice(const struct task_struct *p, const int nice)
++{
++ return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);
++}
++
++#ifdef __ARCH_WANT_SYS_NICE
++
++/*
++ * sys_nice - change the priority of the current process.
++ * @increment: priority increment
++ *
++ * sys_setpriority is a more generic, but much slower function that
++ * does similar things.
++ */
++SYSCALL_DEFINE1(nice, int, increment)
++{
++ long nice, retval;
++
++ /*
++ * Setpriority might change our priority at the same moment.
++ * We don't have to worry. Conceptually one call occurs first
++ * and we have a single winner.
++ */
++
++ increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
++ nice = task_nice(current) + increment;
++
++ nice = clamp_val(nice, MIN_NICE, MAX_NICE);
++ if (increment < 0 && !can_nice(current, nice))
++ return -EPERM;
++
++ retval = security_task_setnice(current, nice);
++ if (retval)
++ return retval;
++
++ set_user_nice(current, nice);
++ return 0;
++}
++
++#endif
++
++/**
++ * task_prio - return the priority value of a given task.
++ * @p: the task in question.
++ *
++ * Return: The priority value as seen by users in /proc.
++ *
++ * sched policy return value kernel prio user prio/nice
++ *
++ * (BMQ)normal, batch, idle[0 ... 53] [100 ... 139] 0/[-20 ... 19]/[-7 ... 7]
++ * (PDS)normal, batch, idle[0 ... 39] 100 0/[-20 ... 19]
++ * fifo, rr [-1 ... -100] [99 ... 0] [0 ... 99]
++ */
++int task_prio(const struct task_struct *p)
++{
++ return (p->prio < MAX_RT_PRIO) ? p->prio - MAX_RT_PRIO :
++ task_sched_prio_normal(p, task_rq(p));
++}
++
++/**
++ * idle_cpu - is a given CPU idle currently?
++ * @cpu: the processor in question.
++ *
++ * Return: 1 if the CPU is currently idle. 0 otherwise.
++ */
++int idle_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (rq->curr != rq->idle)
++ return 0;
++
++ if (rq->nr_running)
++ return 0;
++
++#ifdef CONFIG_SMP
++ if (rq->ttwu_pending)
++ return 0;
++#endif
++
++ return 1;
++}
++
++/**
++ * idle_task - return the idle task for a given CPU.
++ * @cpu: the processor in question.
++ *
++ * Return: The idle task for the cpu @cpu.
++ */
++struct task_struct *idle_task(int cpu)
++{
++ return cpu_rq(cpu)->idle;
++}
++
++/**
++ * find_process_by_pid - find a process with a matching PID value.
++ * @pid: the pid in question.
++ *
++ * The task of @pid, if found. %NULL otherwise.
++ */
++static inline struct task_struct *find_process_by_pid(pid_t pid)
++{
++ return pid ? find_task_by_vpid(pid) : current;
++}
++
++static struct task_struct *find_get_task(pid_t pid)
++{
++ struct task_struct *p;
++ guard(rcu)();
++
++ p = find_process_by_pid(pid);
++ if (likely(p))
++ get_task_struct(p);
++
++ return p;
++}
++
++DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
++ find_get_task(pid), pid_t pid)
++
++/*
++ * sched_setparam() passes in -1 for its policy, to let the functions
++ * it calls know not to change it.
++ */
++#define SETPARAM_POLICY -1
++
++static void __setscheduler_params(struct task_struct *p,
++ const struct sched_attr *attr)
++{
++ int policy = attr->sched_policy;
++
++ if (policy == SETPARAM_POLICY)
++ policy = p->policy;
++
++ p->policy = policy;
++
++ /*
++ * allow normal nice value to be set, but will not have any
++ * effect on scheduling until the task not SCHED_NORMAL/
++ * SCHED_BATCH
++ */
++ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
++
++ /*
++ * __sched_setscheduler() ensures attr->sched_priority == 0 when
++ * !rt_policy. Always setting this ensures that things like
++ * getparam()/getattr() don't report silly values for !rt tasks.
++ */
++ p->rt_priority = attr->sched_priority;
++ p->normal_prio = normal_prio(p);
++}
++
++/*
++ * check the target process has a UID that matches the current process's
++ */
++static bool check_same_owner(struct task_struct *p)
++{
++ const struct cred *cred = current_cred(), *pcred;
++ guard(rcu)();
++
++ pcred = __task_cred(p);
++ return (uid_eq(cred->euid, pcred->euid) ||
++ uid_eq(cred->euid, pcred->uid));
++}
++
++/*
++ * Allow unprivileged RT tasks to decrease priority.
++ * Only issue a capable test if needed and only once to avoid an audit
++ * event on permitted non-privileged operations:
++ */
++static int user_check_sched_setscheduler(struct task_struct *p,
++ const struct sched_attr *attr,
++ int policy, int reset_on_fork)
++{
++ if (rt_policy(policy)) {
++ unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
++
++ /* Can't set/change the rt policy: */
++ if (policy != p->policy && !rlim_rtprio)
++ goto req_priv;
++
++ /* Can't increase priority: */
++ if (attr->sched_priority > p->rt_priority &&
++ attr->sched_priority > rlim_rtprio)
++ goto req_priv;
++ }
++
++ /* Can't change other user's priorities: */
++ if (!check_same_owner(p))
++ goto req_priv;
++
++ /* Normal users shall not reset the sched_reset_on_fork flag: */
++ if (p->sched_reset_on_fork && !reset_on_fork)
++ goto req_priv;
++
++ return 0;
++
++req_priv:
++ if (!capable(CAP_SYS_NICE))
++ return -EPERM;
++
++ return 0;
++}
++
++static int __sched_setscheduler(struct task_struct *p,
++ const struct sched_attr *attr,
++ bool user, bool pi)
++{
++ const struct sched_attr dl_squash_attr = {
++ .size = sizeof(struct sched_attr),
++ .sched_policy = SCHED_FIFO,
++ .sched_nice = 0,
++ .sched_priority = 99,
++ };
++ int oldpolicy = -1, policy = attr->sched_policy;
++ int retval, newprio;
++ struct balance_callback *head;
++ unsigned long flags;
++ struct rq *rq;
++ int reset_on_fork;
++ raw_spinlock_t *lock;
++
++ /* The pi code expects interrupts enabled */
++ BUG_ON(pi && in_interrupt());
++
++ /*
++ * Alt schedule FW supports SCHED_DEADLINE by squash it as prio 0 SCHED_FIFO
++ */
++ if (unlikely(SCHED_DEADLINE == policy)) {
++ attr = &dl_squash_attr;
++ policy = attr->sched_policy;
++ }
++recheck:
++ /* Double check policy once rq lock held */
++ if (policy < 0) {
++ reset_on_fork = p->sched_reset_on_fork;
++ policy = oldpolicy = p->policy;
++ } else {
++ reset_on_fork = !!(attr->sched_flags & SCHED_RESET_ON_FORK);
++
++ if (policy > SCHED_IDLE)
++ return -EINVAL;
++ }
++
++ if (attr->sched_flags & ~(SCHED_FLAG_ALL))
++ return -EINVAL;
++
++ /*
++ * Valid priorities for SCHED_FIFO and SCHED_RR are
++ * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL and
++ * SCHED_BATCH and SCHED_IDLE is 0.
++ */
++ if (attr->sched_priority < 0 ||
++ (p->mm && attr->sched_priority > MAX_RT_PRIO - 1) ||
++ (!p->mm && attr->sched_priority > MAX_RT_PRIO - 1))
++ return -EINVAL;
++ if ((SCHED_RR == policy || SCHED_FIFO == policy) !=
++ (attr->sched_priority != 0))
++ return -EINVAL;
++
++ if (user) {
++ retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork);
++ if (retval)
++ return retval;
++
++ retval = security_task_setscheduler(p);
++ if (retval)
++ return retval;
++ }
++
++ /*
++ * Make sure no PI-waiters arrive (or leave) while we are
++ * changing the priority of the task:
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++
++ /*
++ * To be able to change p->policy safely, task_access_lock()
++ * must be called.
++ * IF use task_access_lock() here:
++ * For the task p which is not running, reading rq->stop is
++ * racy but acceptable as ->stop doesn't change much.
++ * An enhancemnet can be made to read rq->stop saftly.
++ */
++ rq = __task_access_lock(p, &lock);
++
++ /*
++ * Changing the policy of the stop threads its a very bad idea
++ */
++ if (p == rq->stop) {
++ retval = -EINVAL;
++ goto unlock;
++ }
++
++ /*
++ * If not changing anything there's no need to proceed further:
++ */
++ if (unlikely(policy == p->policy)) {
++ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
++ goto change;
++ if (!rt_policy(policy) &&
++ NICE_TO_PRIO(attr->sched_nice) != p->static_prio)
++ goto change;
++
++ p->sched_reset_on_fork = reset_on_fork;
++ retval = 0;
++ goto unlock;
++ }
++change:
++
++ /* Re-check policy now with rq lock held */
++ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
++ policy = oldpolicy = -1;
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ goto recheck;
++ }
++
++ p->sched_reset_on_fork = reset_on_fork;
++
++ newprio = __normal_prio(policy, attr->sched_priority, NICE_TO_PRIO(attr->sched_nice));
++ if (pi) {
++ /*
++ * Take priority boosted tasks into account. If the new
++ * effective priority is unchanged, we just store the new
++ * normal parameters and do not touch the scheduler class and
++ * the runqueue. This will be done when the task deboost
++ * itself.
++ */
++ newprio = rt_effective_prio(p, newprio);
++ }
++
++ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
++ __setscheduler_params(p, attr);
++ __setscheduler_prio(p, newprio);
++ }
++
++ check_task_changed(p, rq);
++
++ /* Avoid rq from going away on us: */
++ preempt_disable();
++ head = splice_balance_callbacks(rq);
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ if (pi)
++ rt_mutex_adjust_pi(p);
++
++ /* Run balance callbacks after we've adjusted the PI chain: */
++ balance_callbacks(rq, head);
++ preempt_enable();
++
++ return 0;
++
++unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ return retval;
++}
++
++static int _sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param, bool check)
++{
++ struct sched_attr attr = {
++ .sched_policy = policy,
++ .sched_priority = param->sched_priority,
++ .sched_nice = PRIO_TO_NICE(p->static_prio),
++ };
++
++ /* Fixup the legacy SCHED_RESET_ON_FORK hack. */
++ if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
++ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
++ policy &= ~SCHED_RESET_ON_FORK;
++ attr.sched_policy = policy;
++ }
++
++ return __sched_setscheduler(p, &attr, check, true);
++}
++
++/**
++ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * Use sched_set_fifo(), read its comment.
++ *
++ * Return: 0 on success. An error code otherwise.
++ *
++ * NOTE that the task may be already dead.
++ */
++int sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return _sched_setscheduler(p, policy, param, true);
++}
++
++int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
++{
++ return __sched_setscheduler(p, attr, true, true);
++}
++
++int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
++{
++ return __sched_setscheduler(p, attr, false, true);
++}
++EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
++
++/**
++ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * Just like sched_setscheduler, only don't bother checking if the
++ * current context has permission. For example, this is needed in
++ * stop_machine(): we create temporary high priority worker threads,
++ * but our caller might not have that capability.
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++int sched_setscheduler_nocheck(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return _sched_setscheduler(p, policy, param, false);
++}
++
++/*
++ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
++ * incapable of resource management, which is the one thing an OS really should
++ * be doing.
++ *
++ * This is of course the reason it is limited to privileged users only.
++ *
++ * Worse still; it is fundamentally impossible to compose static priority
++ * workloads. You cannot take two correctly working static prio workloads
++ * and smash them together and still expect them to work.
++ *
++ * For this reason 'all' FIFO tasks the kernel creates are basically at:
++ *
++ * MAX_RT_PRIO / 2
++ *
++ * The administrator _MUST_ configure the system, the kernel simply doesn't
++ * know enough information to make a sensible choice.
++ */
++void sched_set_fifo(struct task_struct *p)
++{
++ struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
++ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_fifo);
++
++/*
++ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
++ */
++void sched_set_fifo_low(struct task_struct *p)
++{
++ struct sched_param sp = { .sched_priority = 1 };
++ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_fifo_low);
++
++void sched_set_normal(struct task_struct *p, int nice)
++{
++ struct sched_attr attr = {
++ .sched_policy = SCHED_NORMAL,
++ .sched_nice = nice,
++ };
++ WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_normal);
++
++static int
++do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
++{
++ struct sched_param lparam;
++
++ if (!param || pid < 0)
++ return -EINVAL;
++ if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
++ return -EFAULT;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ return sched_setscheduler(p, policy, &lparam);
++}
++
++/*
++ * Mimics kernel/events/core.c perf_copy_attr().
++ */
++static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
++{
++ u32 size;
++ int ret;
++
++ /* Zero the full structure, so that a short copy will be nice: */
++ memset(attr, 0, sizeof(*attr));
++
++ ret = get_user(size, &uattr->size);
++ if (ret)
++ return ret;
++
++ /* ABI compatibility quirk: */
++ if (!size)
++ size = SCHED_ATTR_SIZE_VER0;
++
++ if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
++ goto err_size;
++
++ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
++ if (ret) {
++ if (ret == -E2BIG)
++ goto err_size;
++ return ret;
++ }
++
++ /*
++ * XXX: Do we want to be lenient like existing syscalls; or do we want
++ * to be strict and return an error on out-of-bounds values?
++ */
++ attr->sched_nice = clamp(attr->sched_nice, -20, 19);
++
++ /* sched/core.c uses zero here but we already know ret is zero */
++ return 0;
++
++err_size:
++ put_user(sizeof(*attr), &uattr->size);
++ return -E2BIG;
++}
++
++/**
++ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
++ * @pid: the pid in question.
++ * @policy: new policy.
++ *
++ * Return: 0 on success. An error code otherwise.
++ * @param: structure containing the new RT priority.
++ */
++SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
++{
++ if (policy < 0)
++ return -EINVAL;
++
++ return do_sched_setscheduler(pid, policy, param);
++}
++
++/**
++ * sys_sched_setparam - set/change the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the new RT priority.
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
++{
++ return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
++}
++
++static void get_params(struct task_struct *p, struct sched_attr *attr)
++{
++ if (task_has_rt_policy(p))
++ attr->sched_priority = p->rt_priority;
++ else
++ attr->sched_nice = task_nice(p);
++}
++
++/**
++ * sys_sched_setattr - same as above, but with extended sched_attr
++ * @pid: the pid in question.
++ * @uattr: structure containing the extended parameters.
++ */
++SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
++ unsigned int, flags)
++{
++ struct sched_attr attr;
++ int retval;
++
++ if (!uattr || pid < 0 || flags)
++ return -EINVAL;
++
++ retval = sched_copy_attr(uattr, &attr);
++ if (retval)
++ return retval;
++
++ if ((int)attr.sched_policy < 0)
++ return -EINVAL;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
++ get_params(p, &attr);
++
++ return sched_setattr(p, &attr);
++}
++
++/**
++ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
++ * @pid: the pid in question.
++ *
++ * Return: On success, the policy of the thread. Otherwise, a negative error
++ * code.
++ */
++SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
++{
++ struct task_struct *p;
++ int retval = -EINVAL;
++
++ if (pid < 0)
++ return -ESRCH;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (!retval)
++ retval = p->policy;
++
++ return retval;
++}
++
++/**
++ * sys_sched_getscheduler - get the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the RT priority.
++ *
++ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
++ * code.
++ */
++SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
++{
++ struct sched_param lp = { .sched_priority = 0 };
++ struct task_struct *p;
++
++ if (!param || pid < 0)
++ return -EINVAL;
++
++ scoped_guard (rcu) {
++ int retval;
++
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -EINVAL;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ if (task_has_rt_policy(p))
++ lp.sched_priority = p->rt_priority;
++ }
++
++ /*
++ * This one might sleep, we cannot do it with a spinlock held ...
++ */
++ return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
++}
++
++/*
++ * Copy the kernel size attribute structure (which might be larger
++ * than what user-space knows about) to user-space.
++ *
++ * Note that all cases are valid: user-space buffer can be larger or
++ * smaller than the kernel-space buffer. The usual case is that both
++ * have the same size.
++ */
++static int
++sched_attr_copy_to_user(struct sched_attr __user *uattr,
++ struct sched_attr *kattr,
++ unsigned int usize)
++{
++ unsigned int ksize = sizeof(*kattr);
++
++ if (!access_ok(uattr, usize))
++ return -EFAULT;
++
++ /*
++ * sched_getattr() ABI forwards and backwards compatibility:
++ *
++ * If usize == ksize then we just copy everything to user-space and all is good.
++ *
++ * If usize < ksize then we only copy as much as user-space has space for,
++ * this keeps ABI compatibility as well. We skip the rest.
++ *
++ * If usize > ksize then user-space is using a newer version of the ABI,
++ * which part the kernel doesn't know about. Just ignore it - tooling can
++ * detect the kernel's knowledge of attributes from the attr->size value
++ * which is set to ksize in this case.
++ */
++ kattr->size = min(usize, ksize);
++
++ if (copy_to_user(uattr, kattr, kattr->size))
++ return -EFAULT;
++
++ return 0;
++}
++
++/**
++ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
++ * @pid: the pid in question.
++ * @uattr: structure containing the extended parameters.
++ * @usize: sizeof(attr) for fwd/bwd comp.
++ * @flags: for future extension.
++ */
++SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
++ unsigned int, usize, unsigned int, flags)
++{
++ struct sched_attr kattr = { };
++ struct task_struct *p;
++ int retval;
++
++ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
++ usize < SCHED_ATTR_SIZE_VER0 || flags)
++ return -EINVAL;
++
++ scoped_guard (rcu) {
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ kattr.sched_policy = p->policy;
++ if (p->sched_reset_on_fork)
++ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
++ get_params(p, &kattr);
++ kattr.sched_flags &= SCHED_FLAG_ALL;
++
++#ifdef CONFIG_UCLAMP_TASK
++ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
++ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
++#endif
++ }
++
++ return sched_attr_copy_to_user(uattr, &kattr, usize);
++}
++
++#ifdef CONFIG_SMP
++int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
++{
++ return 0;
++}
++#endif
++
++static int
++__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
++{
++ int retval;
++ cpumask_var_t cpus_allowed, new_mask;
++
++ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
++ return -ENOMEM;
++
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
++ retval = -ENOMEM;
++ goto out_free_cpus_allowed;
++ }
++
++ cpuset_cpus_allowed(p, cpus_allowed);
++ cpumask_and(new_mask, ctx->new_mask, cpus_allowed);
++
++ ctx->new_mask = new_mask;
++ ctx->flags |= SCA_CHECK;
++
++ retval = __set_cpus_allowed_ptr(p, ctx);
++ if (retval)
++ goto out_free_new_mask;
++
++ cpuset_cpus_allowed(p, cpus_allowed);
++ if (!cpumask_subset(new_mask, cpus_allowed)) {
++ /*
++ * We must have raced with a concurrent cpuset
++ * update. Just reset the cpus_allowed to the
++ * cpuset's cpus_allowed
++ */
++ cpumask_copy(new_mask, cpus_allowed);
++
++ /*
++ * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr()
++ * will restore the previous user_cpus_ptr value.
++ *
++ * In the unlikely event a previous user_cpus_ptr exists,
++ * we need to further restrict the mask to what is allowed
++ * by that old user_cpus_ptr.
++ */
++ if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) {
++ bool empty = !cpumask_and(new_mask, new_mask,
++ ctx->user_mask);
++
++ if (WARN_ON_ONCE(empty))
++ cpumask_copy(new_mask, cpus_allowed);
++ }
++ __set_cpus_allowed_ptr(p, ctx);
++ retval = -EINVAL;
++ }
++
++out_free_new_mask:
++ free_cpumask_var(new_mask);
++out_free_cpus_allowed:
++ free_cpumask_var(cpus_allowed);
++ return retval;
++}
++
++long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
++{
++ struct affinity_context ac;
++ struct cpumask *user_mask;
++ int retval;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ if (p->flags & PF_NO_SETAFFINITY)
++ return -EINVAL;
++
++ if (!check_same_owner(p)) {
++ guard(rcu)();
++ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
++ return -EPERM;
++ }
++
++ retval = security_task_setscheduler(p);
++ if (retval)
++ return retval;
++
++ /*
++ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
++ * alloc_user_cpus_ptr() returns NULL.
++ */
++ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
++ if (user_mask) {
++ cpumask_copy(user_mask, in_mask);
++ } else if (IS_ENABLED(CONFIG_SMP)) {
++ return -ENOMEM;
++ }
++
++ ac = (struct affinity_context){
++ .new_mask = in_mask,
++ .user_mask = user_mask,
++ .flags = SCA_USER,
++ };
++
++ retval = __sched_setaffinity(p, &ac);
++ kfree(ac.user_mask);
++
++ return retval;
++}
++
++static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
++ struct cpumask *new_mask)
++{
++ if (len < cpumask_size())
++ cpumask_clear(new_mask);
++ else if (len > cpumask_size())
++ len = cpumask_size();
++
++ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
++}
++
++/**
++ * sys_sched_setaffinity - set the CPU affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to the new CPU mask
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ cpumask_var_t new_mask;
++ int retval;
++
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
++ if (retval == 0)
++ retval = sched_setaffinity(pid, new_mask);
++ free_cpumask_var(new_mask);
++ return retval;
++}
++
++long sched_getaffinity(pid_t pid, cpumask_t *mask)
++{
++ struct task_struct *p;
++ int retval;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ guard(raw_spinlock_irqsave)(&p->pi_lock);
++ cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
++
++ return retval;
++}
++
++/**
++ * sys_sched_getaffinity - get the CPU affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to hold the current CPU mask
++ *
++ * Return: size of CPU mask copied to user_mask_ptr on success. An
++ * error code otherwise.
++ */
++SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ int ret;
++ cpumask_var_t mask;
++
++ if ((len * BITS_PER_BYTE) < nr_cpu_ids)
++ return -EINVAL;
++ if (len & (sizeof(unsigned long)-1))
++ return -EINVAL;
++
++ if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ ret = sched_getaffinity(pid, mask);
++ if (ret == 0) {
++ unsigned int retlen = min(len, cpumask_size());
++
++ if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen))
++ ret = -EFAULT;
++ else
++ ret = retlen;
++ }
++ free_cpumask_var(mask);
++
++ return ret;
++}
++
++static void do_sched_yield(void)
++{
++ struct rq *rq;
++ struct rq_flags rf;
++ struct task_struct *p;
++
++ if (!sched_yield_type)
++ return;
++
++ rq = this_rq_lock_irq(&rf);
++
++ schedstat_inc(rq->yld_count);
++
++ p = current;
++ if (rt_task(p)) {
++ if (task_on_rq_queued(p))
++ requeue_task(p, rq);
++ } else if (rq->nr_running > 1) {
++ do_sched_yield_type_1(p, rq);
++ if (task_on_rq_queued(p))
++ requeue_task(p, rq);
++ }
++
++ preempt_disable();
++ raw_spin_unlock_irq(&rq->lock);
++ sched_preempt_enable_no_resched();
++
++ schedule();
++}
++
++/**
++ * sys_sched_yield - yield the current processor to other threads.
++ *
++ * This function yields the current CPU to other tasks. If there are no
++ * other threads running on this CPU then this function will return.
++ *
++ * Return: 0.
++ */
++SYSCALL_DEFINE0(sched_yield)
++{
++ do_sched_yield();
++ return 0;
++}
++
++#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
++int __sched __cond_resched(void)
++{
++ if (should_resched(0)) {
++ preempt_schedule_common();
++ return 1;
++ }
++ /*
++ * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
++ * whether the current CPU is in an RCU read-side critical section,
++ * so the tick can report quiescent states even for CPUs looping
++ * in kernel context. In contrast, in non-preemptible kernels,
++ * RCU readers leave no in-memory hints, which means that CPU-bound
++ * processes executing in kernel context might never report an
++ * RCU quiescent state. Therefore, the following code causes
++ * cond_resched() to report a quiescent state, but only when RCU
++ * is in urgent need of one.
++ */
++#ifndef CONFIG_PREEMPT_RCU
++ rcu_all_qs();
++#endif
++ return 0;
++}
++EXPORT_SYMBOL(__cond_resched);
++#endif
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#define cond_resched_dynamic_enabled __cond_resched
++#define cond_resched_dynamic_disabled ((void *)&__static_call_return0)
++DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
++EXPORT_STATIC_CALL_TRAMP(cond_resched);
++
++#define might_resched_dynamic_enabled __cond_resched
++#define might_resched_dynamic_disabled ((void *)&__static_call_return0)
++DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
++EXPORT_STATIC_CALL_TRAMP(might_resched);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
++int __sched dynamic_cond_resched(void)
++{
++ klp_sched_try_switch();
++ if (!static_branch_unlikely(&sk_dynamic_cond_resched))
++ return 0;
++ return __cond_resched();
++}
++EXPORT_SYMBOL(dynamic_cond_resched);
++
++static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
++int __sched dynamic_might_resched(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_might_resched))
++ return 0;
++ return __cond_resched();
++}
++EXPORT_SYMBOL(dynamic_might_resched);
++#endif
++#endif
++
++/*
++ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
++ * call schedule, and on return reacquire the lock.
++ *
++ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
++ * operations here to prevent schedule() from being called twice (once via
++ * spin_unlock(), once by hand).
++ */
++int __cond_resched_lock(spinlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held(lock);
++
++ if (spin_needbreak(lock) || resched) {
++ spin_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ spin_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_lock);
++
++int __cond_resched_rwlock_read(rwlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held_read(lock);
++
++ if (rwlock_needbreak(lock) || resched) {
++ read_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ read_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_rwlock_read);
++
++int __cond_resched_rwlock_write(rwlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held_write(lock);
++
++ if (rwlock_needbreak(lock) || resched) {
++ write_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ write_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_rwlock_write);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++
++#ifdef CONFIG_GENERIC_ENTRY
++#include <linux/entry-common.h>
++#endif
++
++/*
++ * SC:cond_resched
++ * SC:might_resched
++ * SC:preempt_schedule
++ * SC:preempt_schedule_notrace
++ * SC:irqentry_exit_cond_resched
++ *
++ *
++ * NONE:
++ * cond_resched <- __cond_resched
++ * might_resched <- RET0
++ * preempt_schedule <- NOP
++ * preempt_schedule_notrace <- NOP
++ * irqentry_exit_cond_resched <- NOP
++ *
++ * VOLUNTARY:
++ * cond_resched <- __cond_resched
++ * might_resched <- __cond_resched
++ * preempt_schedule <- NOP
++ * preempt_schedule_notrace <- NOP
++ * irqentry_exit_cond_resched <- NOP
++ *
++ * FULL:
++ * cond_resched <- RET0
++ * might_resched <- RET0
++ * preempt_schedule <- preempt_schedule
++ * preempt_schedule_notrace <- preempt_schedule_notrace
++ * irqentry_exit_cond_resched <- irqentry_exit_cond_resched
++ */
++
++enum {
++ preempt_dynamic_undefined = -1,
++ preempt_dynamic_none,
++ preempt_dynamic_voluntary,
++ preempt_dynamic_full,
++};
++
++int preempt_dynamic_mode = preempt_dynamic_undefined;
++
++int sched_dynamic_mode(const char *str)
++{
++ if (!strcmp(str, "none"))
++ return preempt_dynamic_none;
++
++ if (!strcmp(str, "voluntary"))
++ return preempt_dynamic_voluntary;
++
++ if (!strcmp(str, "full"))
++ return preempt_dynamic_full;
++
++ return -EINVAL;
++}
++
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled)
++#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled)
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key)
++#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key)
++#else
++#error "Unsupported PREEMPT_DYNAMIC mechanism"
++#endif
++
++static DEFINE_MUTEX(sched_dynamic_mutex);
++static bool klp_override;
++
++static void __sched_dynamic_update(int mode)
++{
++ /*
++ * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
++ * the ZERO state, which is invalid.
++ */
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(might_resched);
++ preempt_dynamic_enable(preempt_schedule);
++ preempt_dynamic_enable(preempt_schedule_notrace);
++ preempt_dynamic_enable(irqentry_exit_cond_resched);
++
++ switch (mode) {
++ case preempt_dynamic_none:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_disable(might_resched);
++ preempt_dynamic_disable(preempt_schedule);
++ preempt_dynamic_disable(preempt_schedule_notrace);
++ preempt_dynamic_disable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: none\n");
++ break;
++
++ case preempt_dynamic_voluntary:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(might_resched);
++ preempt_dynamic_disable(preempt_schedule);
++ preempt_dynamic_disable(preempt_schedule_notrace);
++ preempt_dynamic_disable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: voluntary\n");
++ break;
++
++ case preempt_dynamic_full:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_disable(might_resched);
++ preempt_dynamic_enable(preempt_schedule);
++ preempt_dynamic_enable(preempt_schedule_notrace);
++ preempt_dynamic_enable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: full\n");
++ break;
++ }
++
++ preempt_dynamic_mode = mode;
++}
++
++void sched_dynamic_update(int mode)
++{
++ mutex_lock(&sched_dynamic_mutex);
++ __sched_dynamic_update(mode);
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
++
++static int klp_cond_resched(void)
++{
++ __klp_sched_try_switch();
++ return __cond_resched();
++}
++
++void sched_dynamic_klp_enable(void)
++{
++ mutex_lock(&sched_dynamic_mutex);
++
++ klp_override = true;
++ static_call_update(cond_resched, klp_cond_resched);
++
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++void sched_dynamic_klp_disable(void)
++{
++ mutex_lock(&sched_dynamic_mutex);
++
++ klp_override = false;
++ __sched_dynamic_update(preempt_dynamic_mode);
++
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
++
++
++static int __init setup_preempt_mode(char *str)
++{
++ int mode = sched_dynamic_mode(str);
++ if (mode < 0) {
++ pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
++ return 0;
++ }
++
++ sched_dynamic_update(mode);
++ return 1;
++}
++__setup("preempt=", setup_preempt_mode);
++
++static void __init preempt_dynamic_init(void)
++{
++ if (preempt_dynamic_mode == preempt_dynamic_undefined) {
++ if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
++ sched_dynamic_update(preempt_dynamic_none);
++ } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
++ sched_dynamic_update(preempt_dynamic_voluntary);
++ } else {
++ /* Default static call setting, nothing to do */
++ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
++ preempt_dynamic_mode = preempt_dynamic_full;
++ pr_info("Dynamic Preempt: full\n");
++ }
++ }
++}
++
++#define PREEMPT_MODEL_ACCESSOR(mode) \
++ bool preempt_model_##mode(void) \
++ { \
++ WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
++ return preempt_dynamic_mode == preempt_dynamic_##mode; \
++ } \
++ EXPORT_SYMBOL_GPL(preempt_model_##mode)
++
++PREEMPT_MODEL_ACCESSOR(none);
++PREEMPT_MODEL_ACCESSOR(voluntary);
++PREEMPT_MODEL_ACCESSOR(full);
++
++#else /* !CONFIG_PREEMPT_DYNAMIC */
++
++static inline void preempt_dynamic_init(void) { }
++
++#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
++
++/**
++ * yield - yield the current processor to other threads.
++ *
++ * Do not ever use this function, there's a 99% chance you're doing it wrong.
++ *
++ * The scheduler is at all times free to pick the calling task as the most
++ * eligible task to run, if removing the yield() call from your code breaks
++ * it, it's already broken.
++ *
++ * Typical broken usage is:
++ *
++ * while (!event)
++ * yield();
++ *
++ * where one assumes that yield() will let 'the other' process run that will
++ * make event true. If the current task is a SCHED_FIFO task that will never
++ * happen. Never use yield() as a progress guarantee!!
++ *
++ * If you want to use yield() to wait for something, use wait_event().
++ * If you want to use yield() to be 'nice' for others, use cond_resched().
++ * If you still want to use yield(), do not!
++ */
++void __sched yield(void)
++{
++ set_current_state(TASK_RUNNING);
++ do_sched_yield();
++}
++EXPORT_SYMBOL(yield);
++
++/**
++ * yield_to - yield the current processor to another thread in
++ * your thread group, or accelerate that thread toward the
++ * processor it's on.
++ * @p: target task
++ * @preempt: whether task preemption is allowed or not
++ *
++ * It's the caller's job to ensure that the target task struct
++ * can't go away on us before we can do any checks.
++ *
++ * In Alt schedule FW, yield_to is not supported.
++ *
++ * Return:
++ * true (>0) if we indeed boosted the target task.
++ * false (0) if we failed to boost the target.
++ * -ESRCH if there's no task to yield to.
++ */
++int __sched yield_to(struct task_struct *p, bool preempt)
++{
++ return 0;
++}
++EXPORT_SYMBOL_GPL(yield_to);
++
++int io_schedule_prepare(void)
++{
++ int old_iowait = current->in_iowait;
++
++ current->in_iowait = 1;
++ blk_flush_plug(current->plug, true);
++ return old_iowait;
++}
++
++void io_schedule_finish(int token)
++{
++ current->in_iowait = token;
++}
++
++/*
++ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
++ * that process accounting knows that this is a task in IO wait state.
++ *
++ * But don't do that if it is a deliberate, throttling IO wait (this task
++ * has set its backing_dev_info: the queue against which it should throttle)
++ */
++
++long __sched io_schedule_timeout(long timeout)
++{
++ int token;
++ long ret;
++
++ token = io_schedule_prepare();
++ ret = schedule_timeout(timeout);
++ io_schedule_finish(token);
++
++ return ret;
++}
++EXPORT_SYMBOL(io_schedule_timeout);
++
++void __sched io_schedule(void)
++{
++ int token;
++
++ token = io_schedule_prepare();
++ schedule();
++ io_schedule_finish(token);
++}
++EXPORT_SYMBOL(io_schedule);
++
++/**
++ * sys_sched_get_priority_max - return maximum RT priority.
++ * @policy: scheduling class.
++ *
++ * Return: On success, this syscall returns the maximum
++ * rt_priority that can be used by a given scheduling class.
++ * On failure, a negative error code is returned.
++ */
++SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = MAX_RT_PRIO - 1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_IDLE:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++/**
++ * sys_sched_get_priority_min - return minimum RT priority.
++ * @policy: scheduling class.
++ *
++ * Return: On success, this syscall returns the minimum
++ * rt_priority that can be used by a given scheduling class.
++ * On failure, a negative error code is returned.
++ */
++SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = 1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_IDLE:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
++{
++ struct task_struct *p;
++ int retval;
++
++ alt_sched_debug();
++
++ if (pid < 0)
++ return -EINVAL;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -EINVAL;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ *t = ns_to_timespec64(sysctl_sched_base_slice);
++ return 0;
++}
++
++/**
++ * sys_sched_rr_get_interval - return the default timeslice of a process.
++ * @pid: pid of the process.
++ * @interval: userspace pointer to the timeslice value.
++ *
++ *
++ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
++ * an error code.
++ */
++SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
++ struct __kernel_timespec __user *, interval)
++{
++ struct timespec64 t;
++ int retval = sched_rr_get_interval(pid, &t);
++
++ if (retval == 0)
++ retval = put_timespec64(&t, interval);
++
++ return retval;
++}
++
++#ifdef CONFIG_COMPAT_32BIT_TIME
++SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
++ struct old_timespec32 __user *, interval)
++{
++ struct timespec64 t;
++ int retval = sched_rr_get_interval(pid, &t);
++
++ if (retval == 0)
++ retval = put_old_timespec32(&t, interval);
++ return retval;
++}
++#endif
++
++void sched_show_task(struct task_struct *p)
++{
++ unsigned long free = 0;
++ int ppid;
++
++ if (!try_get_task_stack(p))
++ return;
++
++ pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
++
++ if (task_is_running(p))
++ pr_cont(" running task ");
++#ifdef CONFIG_DEBUG_STACK_USAGE
++ free = stack_not_used(p);
++#endif
++ ppid = 0;
++ rcu_read_lock();
++ if (pid_alive(p))
++ ppid = task_pid_nr(rcu_dereference(p->real_parent));
++ rcu_read_unlock();
++ pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
++ free, task_pid_nr(p), task_tgid_nr(p),
++ ppid, read_task_thread_flags(p));
++
++ print_worker_info(KERN_INFO, p);
++ print_stop_info(KERN_INFO, p);
++ show_stack(p, NULL, KERN_INFO);
++ put_task_stack(p);
++}
++EXPORT_SYMBOL_GPL(sched_show_task);
++
++static inline bool
++state_filter_match(unsigned long state_filter, struct task_struct *p)
++{
++ unsigned int state = READ_ONCE(p->__state);
++
++ /* no filter, everything matches */
++ if (!state_filter)
++ return true;
++
++ /* filter, but doesn't match */
++ if (!(state & state_filter))
++ return false;
++
++ /*
++ * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
++ * TASK_KILLABLE).
++ */
++ if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD))
++ return false;
++
++ return true;
++}
++
++
++void show_state_filter(unsigned int state_filter)
++{
++ struct task_struct *g, *p;
++
++ rcu_read_lock();
++ for_each_process_thread(g, p) {
++ /*
++ * reset the NMI-timeout, listing all files on a slow
++ * console might take a lot of time:
++ * Also, reset softlockup watchdogs on all CPUs, because
++ * another CPU might be blocked waiting for us to process
++ * an IPI.
++ */
++ touch_nmi_watchdog();
++ touch_all_softlockup_watchdogs();
++ if (state_filter_match(state_filter, p))
++ sched_show_task(p);
++ }
++
++#ifdef CONFIG_SCHED_DEBUG
++ /* TODO: Alt schedule FW should support this
++ if (!state_filter)
++ sysrq_sched_debug_show();
++ */
++#endif
++ rcu_read_unlock();
++ /*
++ * Only show locks if all tasks are dumped:
++ */
++ if (!state_filter)
++ debug_show_all_locks();
++}
++
++void dump_cpu_task(int cpu)
++{
++ if (cpu == smp_processor_id() && in_hardirq()) {
++ struct pt_regs *regs;
++
++ regs = get_irq_regs();
++ if (regs) {
++ show_regs(regs);
++ return;
++ }
++ }
++
++ if (trigger_single_cpu_backtrace(cpu))
++ return;
++
++ pr_info("Task dump for CPU %d:\n", cpu);
++ sched_show_task(cpu_curr(cpu));
++}
++
++/**
++ * init_idle - set up an idle thread for a given CPU
++ * @idle: task in question
++ * @cpu: CPU the idle task belongs to
++ *
++ * NOTE: this function does not set the idle thread's NEED_RESCHED
++ * flag, to make booting more robust.
++ */
++void __init init_idle(struct task_struct *idle, int cpu)
++{
++#ifdef CONFIG_SMP
++ struct affinity_context ac = (struct affinity_context) {
++ .new_mask = cpumask_of(cpu),
++ .flags = 0,
++ };
++#endif
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ __sched_fork(0, idle);
++
++ raw_spin_lock_irqsave(&idle->pi_lock, flags);
++ raw_spin_lock(&rq->lock);
++
++ idle->last_ran = rq->clock_task;
++ idle->__state = TASK_RUNNING;
++ /*
++ * PF_KTHREAD should already be set at this point; regardless, make it
++ * look like a proper per-CPU kthread.
++ */
++ idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
++ kthread_set_per_cpu(idle, cpu);
++
++ sched_queue_init_idle(&rq->queue, idle);
++
++#ifdef CONFIG_SMP
++ /*
++ * It's possible that init_idle() gets called multiple times on a task,
++ * in that case do_set_cpus_allowed() will not do the right thing.
++ *
++ * And since this is boot we can forgo the serialisation.
++ */
++ set_cpus_allowed_common(idle, &ac);
++#endif
++
++ /* Silence PROVE_RCU */
++ rcu_read_lock();
++ __set_task_cpu(idle, cpu);
++ rcu_read_unlock();
++
++ rq->idle = idle;
++ rcu_assign_pointer(rq->curr, idle);
++ idle->on_cpu = 1;
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
++
++ /* Set the preempt count _outside_ the spinlocks! */
++ init_idle_preempt_count(idle, cpu);
++
++ ftrace_graph_init_idle_task(idle, cpu);
++ vtime_init_idle(idle, cpu);
++#ifdef CONFIG_SMP
++ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
++#endif
++}
++
++#ifdef CONFIG_SMP
++
++int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur,
++ const struct cpumask __maybe_unused *trial)
++{
++ return 1;
++}
++
++int task_can_attach(struct task_struct *p)
++{
++ int ret = 0;
++
++ /*
++ * Kthreads which disallow setaffinity shouldn't be moved
++ * to a new cpuset; we don't want to change their CPU
++ * affinity and isolating such threads by their set of
++ * allowed nodes is unnecessary. Thus, cpusets are not
++ * applicable for such threads. This prevents checking for
++ * success of set_cpus_allowed_ptr() on all attached tasks
++ * before cpus_mask may be changed.
++ */
++ if (p->flags & PF_NO_SETAFFINITY)
++ ret = -EINVAL;
++
++ return ret;
++}
++
++bool sched_smp_initialized __read_mostly;
++
++#ifdef CONFIG_HOTPLUG_CPU
++/*
++ * Ensures that the idle task is using init_mm right before its CPU goes
++ * offline.
++ */
++void idle_task_exit(void)
++{
++ struct mm_struct *mm = current->active_mm;
++
++ BUG_ON(current != this_rq()->idle);
++
++ if (mm != &init_mm) {
++ switch_mm(mm, &init_mm, current);
++ finish_arch_post_lock_switch();
++ }
++
++ /* finish_cpu(), as ran on the BP, will clean up the active_mm state */
++}
++
++static int __balance_push_cpu_stop(void *arg)
++{
++ struct task_struct *p = arg;
++ struct rq *rq = this_rq();
++ struct rq_flags rf;
++ int cpu;
++
++ raw_spin_lock_irq(&p->pi_lock);
++ rq_lock(rq, &rf);
++
++ update_rq_clock(rq);
++
++ if (task_rq(p) == rq && task_on_rq_queued(p)) {
++ cpu = select_fallback_rq(rq->cpu, p);
++ rq = __migrate_task(rq, p, cpu);
++ }
++
++ rq_unlock(rq, &rf);
++ raw_spin_unlock_irq(&p->pi_lock);
++
++ put_task_struct(p);
++
++ return 0;
++}
++
++static DEFINE_PER_CPU(struct cpu_stop_work, push_work);
++
++/*
++ * This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only
++ * effective when the hotplug motion is down.
++ */
++static void balance_push(struct rq *rq)
++{
++ struct task_struct *push_task = rq->curr;
++
++ lockdep_assert_held(&rq->lock);
++
++ /*
++ * Ensure the thing is persistent until balance_push_set(.on = false);
++ */
++ rq->balance_callback = &balance_push_callback;
++
++ /*
++ * Only active while going offline and when invoked on the outgoing
++ * CPU.
++ */
++ if (!cpu_dying(rq->cpu) || rq != this_rq())
++ return;
++
++ /*
++ * Both the cpu-hotplug and stop task are in this case and are
++ * required to complete the hotplug process.
++ */
++ if (kthread_is_per_cpu(push_task) ||
++ is_migration_disabled(push_task)) {
++
++ /*
++ * If this is the idle task on the outgoing CPU try to wake
++ * up the hotplug control thread which might wait for the
++ * last task to vanish. The rcuwait_active() check is
++ * accurate here because the waiter is pinned on this CPU
++ * and can't obviously be running in parallel.
++ *
++ * On RT kernels this also has to check whether there are
++ * pinned and scheduled out tasks on the runqueue. They
++ * need to leave the migrate disabled section first.
++ */
++ if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
++ rcuwait_active(&rq->hotplug_wait)) {
++ raw_spin_unlock(&rq->lock);
++ rcuwait_wake_up(&rq->hotplug_wait);
++ raw_spin_lock(&rq->lock);
++ }
++ return;
++ }
++
++ get_task_struct(push_task);
++ /*
++ * Temporarily drop rq->lock such that we can wake-up the stop task.
++ * Both preemption and IRQs are still disabled.
++ */
++ preempt_disable();
++ raw_spin_unlock(&rq->lock);
++ stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
++ this_cpu_ptr(&push_work));
++ preempt_enable();
++ /*
++ * At this point need_resched() is true and we'll take the loop in
++ * schedule(). The next pick is obviously going to be the stop task
++ * which kthread_is_per_cpu() and will push this task away.
++ */
++ raw_spin_lock(&rq->lock);
++}
++
++static void balance_push_set(int cpu, bool on)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct rq_flags rf;
++
++ rq_lock_irqsave(rq, &rf);
++ if (on) {
++ WARN_ON_ONCE(rq->balance_callback);
++ rq->balance_callback = &balance_push_callback;
++ } else if (rq->balance_callback == &balance_push_callback) {
++ rq->balance_callback = NULL;
++ }
++ rq_unlock_irqrestore(rq, &rf);
++}
++
++/*
++ * Invoked from a CPUs hotplug control thread after the CPU has been marked
++ * inactive. All tasks which are not per CPU kernel threads are either
++ * pushed off this CPU now via balance_push() or placed on a different CPU
++ * during wakeup. Wait until the CPU is quiescent.
++ */
++static void balance_hotplug_wait(void)
++{
++ struct rq *rq = this_rq();
++
++ rcuwait_wait_event(&rq->hotplug_wait,
++ rq->nr_running == 1 && !rq_has_pinned_tasks(rq),
++ TASK_UNINTERRUPTIBLE);
++}
++
++#else
++
++static void balance_push(struct rq *rq)
++{
++}
++
++static void balance_push_set(int cpu, bool on)
++{
++}
++
++static inline void balance_hotplug_wait(void)
++{
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
++static void set_rq_offline(struct rq *rq)
++{
++ if (rq->online) {
++ update_rq_clock(rq);
++ rq->online = false;
++ }
++}
++
++static void set_rq_online(struct rq *rq)
++{
++ if (!rq->online)
++ rq->online = true;
++}
++
++/*
++ * used to mark begin/end of suspend/resume:
++ */
++static int num_cpus_frozen;
++
++/*
++ * Update cpusets according to cpu_active mask. If cpusets are
++ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
++ * around partition_sched_domains().
++ *
++ * If we come here as part of a suspend/resume, don't touch cpusets because we
++ * want to restore it back to its original state upon resume anyway.
++ */
++static void cpuset_cpu_active(void)
++{
++ if (cpuhp_tasks_frozen) {
++ /*
++ * num_cpus_frozen tracks how many CPUs are involved in suspend
++ * resume sequence. As long as this is not the last online
++ * operation in the resume sequence, just build a single sched
++ * domain, ignoring cpusets.
++ */
++ partition_sched_domains(1, NULL, NULL);
++ if (--num_cpus_frozen)
++ return;
++ /*
++ * This is the last CPU online operation. So fall through and
++ * restore the original sched domains by considering the
++ * cpuset configurations.
++ */
++ cpuset_force_rebuild();
++ }
++
++ cpuset_update_active_cpus();
++}
++
++static int cpuset_cpu_inactive(unsigned int cpu)
++{
++ if (!cpuhp_tasks_frozen) {
++ cpuset_update_active_cpus();
++ } else {
++ num_cpus_frozen++;
++ partition_sched_domains(1, NULL, NULL);
++ }
++ return 0;
++}
++
++int sched_cpu_activate(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ /*
++ * Clear the balance_push callback and prepare to schedule
++ * regular tasks.
++ */
++ balance_push_set(cpu, false);
++
++ set_cpu_active(cpu, true);
++
++ if (sched_smp_initialized)
++ cpuset_cpu_active();
++
++ /*
++ * Put the rq online, if not already. This happens:
++ *
++ * 1) In the early boot process, because we build the real domains
++ * after all cpus have been brought up.
++ *
++ * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
++ * domains.
++ */
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ set_rq_online(rq);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++#ifdef CONFIG_SCHED_SMT
++ /*
++ * When going up, increment the number of cores with SMT present.
++ */
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) {
++ static_branch_inc_cpuslocked(&sched_smt_present);
++ cpumask_or(&sched_smt_mask, &sched_smt_mask, cpu_smt_mask(cpu));
++ }
++#endif
++
++ return 0;
++}
++
++int sched_cpu_deactivate(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++ int ret;
++
++ set_cpu_active(cpu, false);
++
++ /*
++ * From this point forward, this CPU will refuse to run any task that
++ * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively
++ * push those tasks away until this gets cleared, see
++ * sched_cpu_dying().
++ */
++ balance_push_set(cpu, true);
++
++ /*
++ * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
++ * users of this state to go away such that all new such users will
++ * observe it.
++ *
++ * Specifically, we rely on ttwu to no longer target this CPU, see
++ * ttwu_queue_cond() and is_cpu_allowed().
++ *
++ * Do sync before park smpboot threads to take care the rcu boost case.
++ */
++ synchronize_rcu();
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ set_rq_offline(rq);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++#ifdef CONFIG_SCHED_SMT
++ /*
++ * When going down, decrement the number of cores with SMT present.
++ */
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) {
++ static_branch_dec_cpuslocked(&sched_smt_present);
++ if (!static_branch_likely(&sched_smt_present))
++ cpumask_clear(sched_pcore_idle_mask);
++ cpumask_andnot(&sched_smt_mask, &sched_smt_mask, cpu_smt_mask(cpu));
++ }
++#endif
++
++ if (!sched_smp_initialized)
++ return 0;
++
++ ret = cpuset_cpu_inactive(cpu);
++ if (ret) {
++ balance_push_set(cpu, false);
++ set_cpu_active(cpu, true);
++ return ret;
++ }
++
++ return 0;
++}
++
++static void sched_rq_cpu_starting(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ rq->calc_load_update = calc_load_update;
++}
++
++int sched_cpu_starting(unsigned int cpu)
++{
++ sched_rq_cpu_starting(cpu);
++ sched_tick_start(cpu);
++ return 0;
++}
++
++#ifdef CONFIG_HOTPLUG_CPU
++
++/*
++ * Invoked immediately before the stopper thread is invoked to bring the
++ * CPU down completely. At this point all per CPU kthreads except the
++ * hotplug thread (current) and the stopper thread (inactive) have been
++ * either parked or have been unbound from the outgoing CPU. Ensure that
++ * any of those which might be on the way out are gone.
++ *
++ * If after this point a bound task is being woken on this CPU then the
++ * responsible hotplug callback has failed to do it's job.
++ * sched_cpu_dying() will catch it with the appropriate fireworks.
++ */
++int sched_cpu_wait_empty(unsigned int cpu)
++{
++ balance_hotplug_wait();
++ return 0;
++}
++
++/*
++ * Since this CPU is going 'away' for a while, fold any nr_active delta we
++ * might have. Called from the CPU stopper task after ensuring that the
++ * stopper is the last running task on the CPU, so nr_active count is
++ * stable. We need to take the teardown thread which is calling this into
++ * account, so we hand in adjust = 1 to the load calculation.
++ *
++ * Also see the comment "Global load-average calculations".
++ */
++static void calc_load_migrate(struct rq *rq)
++{
++ long delta = calc_load_fold_active(rq, 1);
++
++ if (delta)
++ atomic_long_add(delta, &calc_load_tasks);
++}
++
++static void dump_rq_tasks(struct rq *rq, const char *loglvl)
++{
++ struct task_struct *g, *p;
++ int cpu = cpu_of(rq);
++
++ lockdep_assert_held(&rq->lock);
++
++ printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
++ for_each_process_thread(g, p) {
++ if (task_cpu(p) != cpu)
++ continue;
++
++ if (!task_on_rq_queued(p))
++ continue;
++
++ printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm);
++ }
++}
++
++int sched_cpu_dying(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ /* Handle pending wakeups and then migrate everything off */
++ sched_tick_stop(cpu);
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
++ WARN(true, "Dying CPU not properly vacated!");
++ dump_rq_tasks(rq, KERN_WARNING);
++ }
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ calc_load_migrate(rq);
++ hrtick_clear(rq);
++ return 0;
++}
++#endif
++
++#ifdef CONFIG_SMP
++static void sched_init_topology_cpumask_early(void)
++{
++ int cpu;
++ cpumask_t *tmp;
++
++ for_each_possible_cpu(cpu) {
++ /* init topo masks */
++ tmp = per_cpu(sched_cpu_topo_masks, cpu);
++
++ cpumask_copy(tmp, cpu_possible_mask);
++ per_cpu(sched_cpu_llc_mask, cpu) = tmp;
++ per_cpu(sched_cpu_topo_end_mask, cpu) = ++tmp;
++ }
++}
++
++#define TOPOLOGY_CPUMASK(name, mask, last)\
++ if (cpumask_and(topo, topo, mask)) { \
++ cpumask_copy(topo, mask); \
++ printk(KERN_INFO "sched: cpu#%02d topo: 0x%08lx - "#name, \
++ cpu, (topo++)->bits[0]); \
++ } \
++ if (!last) \
++ bitmap_complement(cpumask_bits(topo), cpumask_bits(mask), \
++ nr_cpumask_bits);
++
++static void sched_init_topology_cpumask(void)
++{
++ int cpu;
++ cpumask_t *topo;
++
++ for_each_online_cpu(cpu) {
++ topo = per_cpu(sched_cpu_topo_masks, cpu);
++
++ bitmap_complement(cpumask_bits(topo), cpumask_bits(cpumask_of(cpu)),
++ nr_cpumask_bits);
++#ifdef CONFIG_SCHED_SMT
++ TOPOLOGY_CPUMASK(smt, topology_sibling_cpumask(cpu), false);
++#endif
++ TOPOLOGY_CPUMASK(cluster, topology_cluster_cpumask(cpu), false);
++
++ per_cpu(sd_llc_id, cpu) = cpumask_first(cpu_coregroup_mask(cpu));
++ per_cpu(sched_cpu_llc_mask, cpu) = topo;
++ TOPOLOGY_CPUMASK(coregroup, cpu_coregroup_mask(cpu), false);
++
++ TOPOLOGY_CPUMASK(core, topology_core_cpumask(cpu), false);
++
++ TOPOLOGY_CPUMASK(others, cpu_online_mask, true);
++
++ per_cpu(sched_cpu_topo_end_mask, cpu) = topo;
++ printk(KERN_INFO "sched: cpu#%02d llc_id = %d, llc_mask idx = %d\n",
++ cpu, per_cpu(sd_llc_id, cpu),
++ (int) (per_cpu(sched_cpu_llc_mask, cpu) -
++ per_cpu(sched_cpu_topo_masks, cpu)));
++ }
++}
++#endif
++
++void __init sched_init_smp(void)
++{
++ /* Move init over to a non-isolated CPU */
++ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
++ BUG();
++ current->flags &= ~PF_NO_SETAFFINITY;
++
++ sched_init_topology();
++ sched_init_topology_cpumask();
++
++ sched_smp_initialized = true;
++}
++
++static int __init migration_init(void)
++{
++ sched_cpu_starting(smp_processor_id());
++ return 0;
++}
++early_initcall(migration_init);
++
++#else
++void __init sched_init_smp(void)
++{
++ cpu_rq(0)->idle->time_slice = sysctl_sched_base_slice;
++}
++#endif /* CONFIG_SMP */
++
++int in_sched_functions(unsigned long addr)
++{
++ return in_lock_functions(addr) ||
++ (addr >= (unsigned long)__sched_text_start
++ && addr < (unsigned long)__sched_text_end);
++}
++
++#ifdef CONFIG_CGROUP_SCHED
++/*
++ * Default task group.
++ * Every task in system belongs to this group at bootup.
++ */
++struct task_group root_task_group;
++LIST_HEAD(task_groups);
++
++/* Cacheline aligned slab cache for task_group */
++static struct kmem_cache *task_group_cache __ro_after_init;
++#endif /* CONFIG_CGROUP_SCHED */
++
++void __init sched_init(void)
++{
++ int i;
++ struct rq *rq;
++
++ printk(KERN_INFO "sched/alt: "ALT_SCHED_NAME" CPU Scheduler "ALT_SCHED_VERSION\
++ " by Alfred Chen.\n");
++
++ wait_bit_init();
++
++#ifdef CONFIG_SMP
++ for (i = 0; i < SCHED_QUEUE_BITS; i++)
++ cpumask_copy(sched_preempt_mask + i, cpu_present_mask);
++#endif
++
++#ifdef CONFIG_CGROUP_SCHED
++ task_group_cache = KMEM_CACHE(task_group, 0);
++
++ list_add(&root_task_group.list, &task_groups);
++ INIT_LIST_HEAD(&root_task_group.children);
++ INIT_LIST_HEAD(&root_task_group.siblings);
++#endif /* CONFIG_CGROUP_SCHED */
++ for_each_possible_cpu(i) {
++ rq = cpu_rq(i);
++
++ sched_queue_init(&rq->queue);
++ rq->prio = IDLE_TASK_SCHED_PRIO;
++#ifdef CONFIG_SCHED_PDS
++ rq->prio_idx = rq->prio;
++#endif
++
++ raw_spin_lock_init(&rq->lock);
++ rq->nr_running = rq->nr_uninterruptible = 0;
++ rq->calc_load_active = 0;
++ rq->calc_load_update = jiffies + LOAD_FREQ;
++#ifdef CONFIG_SMP
++ rq->online = false;
++ rq->cpu = i;
++
++ rq->clear_idle_mask_func = cpumask_clear_cpu;
++ rq->set_idle_mask_func = cpumask_set_cpu;
++ rq->balance_func = NULL;
++ rq->active_balance_arg.active = 0;
++
++#ifdef CONFIG_NO_HZ_COMMON
++ INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
++#endif
++ rq->balance_callback = &balance_push_callback;
++#ifdef CONFIG_HOTPLUG_CPU
++ rcuwait_init(&rq->hotplug_wait);
++#endif
++#endif /* CONFIG_SMP */
++ rq->nr_switches = 0;
++
++ hrtick_rq_init(rq);
++ atomic_set(&rq->nr_iowait, 0);
++
++ zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
++ }
++#ifdef CONFIG_SMP
++ /* Set rq->online for cpu 0 */
++ cpu_rq(0)->online = true;
++#endif
++ /*
++ * The boot idle thread does lazy MMU switching as well:
++ */
++ mmgrab(&init_mm);
++ enter_lazy_tlb(&init_mm, current);
++
++ /*
++ * The idle task doesn't need the kthread struct to function, but it
++ * is dressed up as a per-CPU kthread and thus needs to play the part
++ * if we want to avoid special-casing it in code that deals with per-CPU
++ * kthreads.
++ */
++ WARN_ON(!set_kthread_struct(current));
++
++ /*
++ * Make us the idle thread. Technically, schedule() should not be
++ * called from this thread, however somewhere below it might be,
++ * but because we are the idle thread, we just pick up running again
++ * when this runqueue becomes "idle".
++ */
++ init_idle(current, smp_processor_id());
++
++ calc_load_update = jiffies + LOAD_FREQ;
++
++#ifdef CONFIG_SMP
++ idle_thread_set_boot_cpu();
++ balance_push_set(smp_processor_id(), false);
++
++ sched_init_topology_cpumask_early();
++#endif /* SMP */
++
++ preempt_dynamic_init();
++}
++
++#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
++
++void __might_sleep(const char *file, int line)
++{
++ unsigned int state = get_current_state();
++ /*
++ * Blocking primitives will set (and therefore destroy) current->state,
++ * since we will exit with TASK_RUNNING make sure we enter with it,
++ * otherwise we will destroy state.
++ */
++ WARN_ONCE(state != TASK_RUNNING && current->task_state_change,
++ "do not call blocking ops when !TASK_RUNNING; "
++ "state=%x set at [<%p>] %pS\n", state,
++ (void *)current->task_state_change,
++ (void *)current->task_state_change);
++
++ __might_resched(file, line, 0);
++}
++EXPORT_SYMBOL(__might_sleep);
++
++static void print_preempt_disable_ip(int preempt_offset, unsigned long ip)
++{
++ if (!IS_ENABLED(CONFIG_DEBUG_PREEMPT))
++ return;
++
++ if (preempt_count() == preempt_offset)
++ return;
++
++ pr_err("Preemption disabled at:");
++ print_ip_sym(KERN_ERR, ip);
++}
++
++static inline bool resched_offsets_ok(unsigned int offsets)
++{
++ unsigned int nested = preempt_count();
++
++ nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT;
++
++ return nested == offsets;
++}
++
++void __might_resched(const char *file, int line, unsigned int offsets)
++{
++ /* Ratelimiting timestamp: */
++ static unsigned long prev_jiffy;
++
++ unsigned long preempt_disable_ip;
++
++ /* WARN_ON_ONCE() by default, no rate limit required: */
++ rcu_sleep_check();
++
++ if ((resched_offsets_ok(offsets) && !irqs_disabled() &&
++ !is_idle_task(current) && !current->non_block_count) ||
++ system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
++ oops_in_progress)
++ return;
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ /* Save this before calling printk(), since that will clobber it: */
++ preempt_disable_ip = get_preempt_disable_ip(current);
++
++ pr_err("BUG: sleeping function called from invalid context at %s:%d\n",
++ file, line);
++ pr_err("in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(), current->non_block_count,
++ current->pid, current->comm);
++ pr_err("preempt_count: %x, expected: %x\n", preempt_count(),
++ offsets & MIGHT_RESCHED_PREEMPT_MASK);
++
++ if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
++ pr_err("RCU nest depth: %d, expected: %u\n",
++ rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT);
++ }
++
++ if (task_stack_end_corrupted(current))
++ pr_emerg("Thread overran stack, or stack corrupted\n");
++
++ debug_show_held_locks(current);
++ if (irqs_disabled())
++ print_irqtrace_events(current);
++
++ print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK,
++ preempt_disable_ip);
++
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL(__might_resched);
++
++void __cant_sleep(const char *file, int line, int preempt_offset)
++{
++ static unsigned long prev_jiffy;
++
++ if (irqs_disabled())
++ return;
++
++ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
++ return;
++
++ if (preempt_count() > preempt_offset)
++ return;
++
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
++ printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(),
++ current->pid, current->comm);
++
++ debug_show_held_locks(current);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL_GPL(__cant_sleep);
++
++#ifdef CONFIG_SMP
++void __cant_migrate(const char *file, int line)
++{
++ static unsigned long prev_jiffy;
++
++ if (irqs_disabled())
++ return;
++
++ if (is_migration_disabled(current))
++ return;
++
++ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
++ return;
++
++ if (preempt_count() > 0)
++ return;
++
++ if (current->migration_flags & MDF_FORCE_ENABLED)
++ return;
++
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
++ pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(), is_migration_disabled(current),
++ current->pid, current->comm);
++
++ debug_show_held_locks(current);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL_GPL(__cant_migrate);
++#endif
++#endif
++
++#ifdef CONFIG_MAGIC_SYSRQ
++void normalize_rt_tasks(void)
++{
++ struct task_struct *g, *p;
++ struct sched_attr attr = {
++ .sched_policy = SCHED_NORMAL,
++ };
++
++ read_lock(&tasklist_lock);
++ for_each_process_thread(g, p) {
++ /*
++ * Only normalize user tasks:
++ */
++ if (p->flags & PF_KTHREAD)
++ continue;
++
++ schedstat_set(p->stats.wait_start, 0);
++ schedstat_set(p->stats.sleep_start, 0);
++ schedstat_set(p->stats.block_start, 0);
++
++ if (!rt_task(p)) {
++ /*
++ * Renice negative nice level userspace
++ * tasks back to 0:
++ */
++ if (task_nice(p) < 0)
++ set_user_nice(p, 0);
++ continue;
++ }
++
++ __sched_setscheduler(p, &attr, false, false);
++ }
++ read_unlock(&tasklist_lock);
++}
++#endif /* CONFIG_MAGIC_SYSRQ */
++
++#if defined(CONFIG_KGDB_KDB)
++/*
++ * These functions are only useful for kdb.
++ *
++ * They can only be called when the whole system has been
++ * stopped - every CPU needs to be quiescent, and no scheduling
++ * activity can take place. Using them for anything else would
++ * be a serious bug, and as a result, they aren't even visible
++ * under any other configuration.
++ */
++
++/**
++ * curr_task - return the current task for a given CPU.
++ * @cpu: the processor in question.
++ *
++ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
++ *
++ * Return: The current task for @cpu.
++ */
++struct task_struct *curr_task(int cpu)
++{
++ return cpu_curr(cpu);
++}
++
++#endif /* defined(CONFIG_KGDB_KDB) */
++
++#ifdef CONFIG_CGROUP_SCHED
++static void sched_free_group(struct task_group *tg)
++{
++ kmem_cache_free(task_group_cache, tg);
++}
++
++static void sched_free_group_rcu(struct rcu_head *rhp)
++{
++ sched_free_group(container_of(rhp, struct task_group, rcu));
++}
++
++static void sched_unregister_group(struct task_group *tg)
++{
++ /*
++ * We have to wait for yet another RCU grace period to expire, as
++ * print_cfs_stats() might run concurrently.
++ */
++ call_rcu(&tg->rcu, sched_free_group_rcu);
++}
++
++/* allocate runqueue etc for a new task group */
++struct task_group *sched_create_group(struct task_group *parent)
++{
++ struct task_group *tg;
++
++ tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
++ if (!tg)
++ return ERR_PTR(-ENOMEM);
++
++ return tg;
++}
++
++void sched_online_group(struct task_group *tg, struct task_group *parent)
++{
++}
++
++/* rcu callback to free various structures associated with a task group */
++static void sched_unregister_group_rcu(struct rcu_head *rhp)
++{
++ /* Now it should be safe to free those cfs_rqs: */
++ sched_unregister_group(container_of(rhp, struct task_group, rcu));
++}
++
++void sched_destroy_group(struct task_group *tg)
++{
++ /* Wait for possible concurrent references to cfs_rqs complete: */
++ call_rcu(&tg->rcu, sched_unregister_group_rcu);
++}
++
++void sched_release_group(struct task_group *tg)
++{
++}
++
++static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
++{
++ return css ? container_of(css, struct task_group, css) : NULL;
++}
++
++static struct cgroup_subsys_state *
++cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
++{
++ struct task_group *parent = css_tg(parent_css);
++ struct task_group *tg;
++
++ if (!parent) {
++ /* This is early initialization for the top cgroup */
++ return &root_task_group.css;
++ }
++
++ tg = sched_create_group(parent);
++ if (IS_ERR(tg))
++ return ERR_PTR(-ENOMEM);
++ return &tg->css;
++}
++
++/* Expose task group only after completing cgroup initialization */
++static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++ struct task_group *parent = css_tg(css->parent);
++
++ if (parent)
++ sched_online_group(tg, parent);
++ return 0;
++}
++
++static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++
++ sched_release_group(tg);
++}
++
++static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++
++ /*
++ * Relies on the RCU grace period between css_released() and this.
++ */
++ sched_unregister_group(tg);
++}
++
++#ifdef CONFIG_RT_GROUP_SCHED
++static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
++{
++ return 0;
++}
++#endif
++
++static void cpu_cgroup_attach(struct cgroup_taskset *tset)
++{
++}
++
++#ifdef CONFIG_FAIR_GROUP_SCHED
++static DEFINE_MUTEX(shares_mutex);
++
++static int sched_group_set_shares(struct task_group *tg, unsigned long shares)
++{
++ /*
++ * We can't change the weight of the root cgroup.
++ */
++ if (&root_task_group == tg)
++ return -EINVAL;
++
++ shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
++
++ mutex_lock(&shares_mutex);
++ if (tg->shares == shares)
++ goto done;
++
++ tg->shares = shares;
++done:
++ mutex_unlock(&shares_mutex);
++ return 0;
++}
++
++static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 shareval)
++{
++ if (shareval > scale_load_down(ULONG_MAX))
++ shareval = MAX_SHARES;
++ return sched_group_set_shares(css_tg(css), scale_load(shareval));
++}
++
++static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ struct task_group *tg = css_tg(css);
++
++ return (u64) scale_load_down(tg->shares);
++}
++#endif
++
++static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, s64 cfs_quota_us)
++{
++ return 0;
++}
++
++static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 cfs_period_us)
++{
++ return 0;
++}
++
++static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 cfs_burst_us)
++{
++ return 0;
++}
++
++static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 val)
++{
++ return 0;
++}
++
++static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 rt_period_us)
++{
++ return 0;
++}
++
++static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes,
++ loff_t off)
++{
++ return nbytes;
++}
++
++static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes,
++ loff_t off)
++{
++ return nbytes;
++}
++
++static struct cftype cpu_legacy_files[] = {
++#ifdef CONFIG_FAIR_GROUP_SCHED
++ {
++ .name = "shares",
++ .read_u64 = cpu_shares_read_u64,
++ .write_u64 = cpu_shares_write_u64,
++ },
++#endif
++ {
++ .name = "cfs_quota_us",
++ .read_s64 = cpu_cfs_quota_read_s64,
++ .write_s64 = cpu_cfs_quota_write_s64,
++ },
++ {
++ .name = "cfs_period_us",
++ .read_u64 = cpu_cfs_period_read_u64,
++ .write_u64 = cpu_cfs_period_write_u64,
++ },
++ {
++ .name = "cfs_burst_us",
++ .read_u64 = cpu_cfs_burst_read_u64,
++ .write_u64 = cpu_cfs_burst_write_u64,
++ },
++ {
++ .name = "stat",
++ .seq_show = cpu_cfs_stat_show,
++ },
++ {
++ .name = "stat.local",
++ .seq_show = cpu_cfs_local_stat_show,
++ },
++ {
++ .name = "rt_runtime_us",
++ .read_s64 = cpu_rt_runtime_read,
++ .write_s64 = cpu_rt_runtime_write,
++ },
++ {
++ .name = "rt_period_us",
++ .read_u64 = cpu_rt_period_read_uint,
++ .write_u64 = cpu_rt_period_write_uint,
++ },
++ {
++ .name = "uclamp.min",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_min_show,
++ .write = cpu_uclamp_min_write,
++ },
++ {
++ .name = "uclamp.max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_max_show,
++ .write = cpu_uclamp_max_write,
++ },
++ { } /* Terminate */
++};
++
++static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft, u64 weight)
++{
++ return 0;
++}
++
++static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 nice)
++{
++ return 0;
++}
++
++static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 idle)
++{
++ return 0;
++}
++
++static int cpu_max_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static ssize_t cpu_max_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes, loff_t off)
++{
++ return nbytes;
++}
++
++static struct cftype cpu_files[] = {
++ {
++ .name = "weight",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_u64 = cpu_weight_read_u64,
++ .write_u64 = cpu_weight_write_u64,
++ },
++ {
++ .name = "weight.nice",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_s64 = cpu_weight_nice_read_s64,
++ .write_s64 = cpu_weight_nice_write_s64,
++ },
++ {
++ .name = "idle",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_s64 = cpu_idle_read_s64,
++ .write_s64 = cpu_idle_write_s64,
++ },
++ {
++ .name = "max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_max_show,
++ .write = cpu_max_write,
++ },
++ {
++ .name = "max.burst",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_u64 = cpu_cfs_burst_read_u64,
++ .write_u64 = cpu_cfs_burst_write_u64,
++ },
++ {
++ .name = "uclamp.min",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_min_show,
++ .write = cpu_uclamp_min_write,
++ },
++ {
++ .name = "uclamp.max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_max_show,
++ .write = cpu_uclamp_max_write,
++ },
++ { } /* terminate */
++};
++
++static int cpu_extra_stat_show(struct seq_file *sf,
++ struct cgroup_subsys_state *css)
++{
++ return 0;
++}
++
++static int cpu_local_stat_show(struct seq_file *sf,
++ struct cgroup_subsys_state *css)
++{
++ return 0;
++}
++
++struct cgroup_subsys cpu_cgrp_subsys = {
++ .css_alloc = cpu_cgroup_css_alloc,
++ .css_online = cpu_cgroup_css_online,
++ .css_released = cpu_cgroup_css_released,
++ .css_free = cpu_cgroup_css_free,
++ .css_extra_stat_show = cpu_extra_stat_show,
++ .css_local_stat_show = cpu_local_stat_show,
++#ifdef CONFIG_RT_GROUP_SCHED
++ .can_attach = cpu_cgroup_can_attach,
++#endif
++ .attach = cpu_cgroup_attach,
++ .legacy_cftypes = cpu_legacy_files,
++ .dfl_cftypes = cpu_files,
++ .early_init = true,
++ .threaded = true,
++};
++#endif /* CONFIG_CGROUP_SCHED */
++
++#undef CREATE_TRACE_POINTS
++
++#ifdef CONFIG_SCHED_MM_CID
++
++#
++/*
++ * @cid_lock: Guarantee forward-progress of cid allocation.
++ *
++ * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock
++ * is only used when contention is detected by the lock-free allocation so
++ * forward progress can be guaranteed.
++ */
++DEFINE_RAW_SPINLOCK(cid_lock);
++
++/*
++ * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock.
++ *
++ * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is
++ * detected, it is set to 1 to ensure that all newly coming allocations are
++ * serialized by @cid_lock until the allocation which detected contention
++ * completes and sets @use_cid_lock back to 0. This guarantees forward progress
++ * of a cid allocation.
++ */
++int use_cid_lock;
++
++/*
++ * mm_cid remote-clear implements a lock-free algorithm to clear per-mm/cpu cid
++ * concurrently with respect to the execution of the source runqueue context
++ * switch.
++ *
++ * There is one basic properties we want to guarantee here:
++ *
++ * (1) Remote-clear should _never_ mark a per-cpu cid UNSET when it is actively
++ * used by a task. That would lead to concurrent allocation of the cid and
++ * userspace corruption.
++ *
++ * Provide this guarantee by introducing a Dekker memory ordering to guarantee
++ * that a pair of loads observe at least one of a pair of stores, which can be
++ * shown as:
++ *
++ * X = Y = 0
++ *
++ * w[X]=1 w[Y]=1
++ * MB MB
++ * r[Y]=y r[X]=x
++ *
++ * Which guarantees that x==0 && y==0 is impossible. But rather than using
++ * values 0 and 1, this algorithm cares about specific state transitions of the
++ * runqueue current task (as updated by the scheduler context switch), and the
++ * per-mm/cpu cid value.
++ *
++ * Let's introduce task (Y) which has task->mm == mm and task (N) which has
++ * task->mm != mm for the rest of the discussion. There are two scheduler state
++ * transitions on context switch we care about:
++ *
++ * (TSA) Store to rq->curr with transition from (N) to (Y)
++ *
++ * (TSB) Store to rq->curr with transition from (Y) to (N)
++ *
++ * On the remote-clear side, there is one transition we care about:
++ *
++ * (TMA) cmpxchg to *pcpu_cid to set the LAZY flag
++ *
++ * There is also a transition to UNSET state which can be performed from all
++ * sides (scheduler, remote-clear). It is always performed with a cmpxchg which
++ * guarantees that only a single thread will succeed:
++ *
++ * (TMB) cmpxchg to *pcpu_cid to mark UNSET
++ *
++ * Just to be clear, what we do _not_ want to happen is a transition to UNSET
++ * when a thread is actively using the cid (property (1)).
++ *
++ * Let's looks at the relevant combinations of TSA/TSB, and TMA transitions.
++ *
++ * Scenario A) (TSA)+(TMA) (from next task perspective)
++ *
++ * CPU0 CPU1
++ *
++ * Context switch CS-1 Remote-clear
++ * - store to rq->curr: (N)->(Y) (TSA) - cmpxchg to *pcpu_id to LAZY (TMA)
++ * (implied barrier after cmpxchg)
++ * - switch_mm_cid()
++ * - memory barrier (see switch_mm_cid()
++ * comment explaining how this barrier
++ * is combined with other scheduler
++ * barriers)
++ * - mm_cid_get (next)
++ * - READ_ONCE(*pcpu_cid) - rcu_dereference(src_rq->curr)
++ *
++ * This Dekker ensures that either task (Y) is observed by the
++ * rcu_dereference() or the LAZY flag is observed by READ_ONCE(), or both are
++ * observed.
++ *
++ * If task (Y) store is observed by rcu_dereference(), it means that there is
++ * still an active task on the cpu. Remote-clear will therefore not transition
++ * to UNSET, which fulfills property (1).
++ *
++ * If task (Y) is not observed, but the lazy flag is observed by READ_ONCE(),
++ * it will move its state to UNSET, which clears the percpu cid perhaps
++ * uselessly (which is not an issue for correctness). Because task (Y) is not
++ * observed, CPU1 can move ahead to set the state to UNSET. Because moving
++ * state to UNSET is done with a cmpxchg expecting that the old state has the
++ * LAZY flag set, only one thread will successfully UNSET.
++ *
++ * If both states (LAZY flag and task (Y)) are observed, the thread on CPU0
++ * will observe the LAZY flag and transition to UNSET (perhaps uselessly), and
++ * CPU1 will observe task (Y) and do nothing more, which is fine.
++ *
++ * What we are effectively preventing with this Dekker is a scenario where
++ * neither LAZY flag nor store (Y) are observed, which would fail property (1)
++ * because this would UNSET a cid which is actively used.
++ */
++
++void sched_mm_cid_migrate_from(struct task_struct *t)
++{
++ t->migrate_from_cpu = task_cpu(t);
++}
++
++static
++int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
++ struct task_struct *t,
++ struct mm_cid *src_pcpu_cid)
++{
++ struct mm_struct *mm = t->mm;
++ struct task_struct *src_task;
++ int src_cid, last_mm_cid;
++
++ if (!mm)
++ return -1;
++
++ last_mm_cid = t->last_mm_cid;
++ /*
++ * If the migrated task has no last cid, or if the current
++ * task on src rq uses the cid, it means the source cid does not need
++ * to be moved to the destination cpu.
++ */
++ if (last_mm_cid == -1)
++ return -1;
++ src_cid = READ_ONCE(src_pcpu_cid->cid);
++ if (!mm_cid_is_valid(src_cid) || last_mm_cid != src_cid)
++ return -1;
++
++ /*
++ * If we observe an active task using the mm on this rq, it means we
++ * are not the last task to be migrated from this cpu for this mm, so
++ * there is no need to move src_cid to the destination cpu.
++ */
++ rcu_read_lock();
++ src_task = rcu_dereference(src_rq->curr);
++ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
++ rcu_read_unlock();
++ t->last_mm_cid = -1;
++ return -1;
++ }
++ rcu_read_unlock();
++
++ return src_cid;
++}
++
++static
++int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
++ struct task_struct *t,
++ struct mm_cid *src_pcpu_cid,
++ int src_cid)
++{
++ struct task_struct *src_task;
++ struct mm_struct *mm = t->mm;
++ int lazy_cid;
++
++ if (src_cid == -1)
++ return -1;
++
++ /*
++ * Attempt to clear the source cpu cid to move it to the destination
++ * cpu.
++ */
++ lazy_cid = mm_cid_set_lazy_put(src_cid);
++ if (!try_cmpxchg(&src_pcpu_cid->cid, &src_cid, lazy_cid))
++ return -1;
++
++ /*
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm matches the scheduler barrier in context_switch()
++ * between store to rq->curr and load of prev and next task's
++ * per-mm/cpu cid.
++ *
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm_cid_active matches the barrier in
++ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
++ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
++ * load of per-mm/cpu cid.
++ */
++
++ /*
++ * If we observe an active task using the mm on this rq after setting
++ * the lazy-put flag, this task will be responsible for transitioning
++ * from lazy-put flag set to MM_CID_UNSET.
++ */
++ scoped_guard (rcu) {
++ src_task = rcu_dereference(src_rq->curr);
++ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
++ rcu_read_unlock();
++ /*
++ * We observed an active task for this mm, there is therefore
++ * no point in moving this cid to the destination cpu.
++ */
++ t->last_mm_cid = -1;
++ return -1;
++ }
++ }
++
++ /*
++ * The src_cid is unused, so it can be unset.
++ */
++ if (!try_cmpxchg(&src_pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
++ return -1;
++ return src_cid;
++}
++
++/*
++ * Migration to dst cpu. Called with dst_rq lock held.
++ * Interrupts are disabled, which keeps the window of cid ownership without the
++ * source rq lock held small.
++ */
++void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu)
++{
++ struct mm_cid *src_pcpu_cid, *dst_pcpu_cid;
++ struct mm_struct *mm = t->mm;
++ int src_cid, dst_cid;
++ struct rq *src_rq;
++
++ lockdep_assert_rq_held(dst_rq);
++
++ if (!mm)
++ return;
++ if (src_cpu == -1) {
++ t->last_mm_cid = -1;
++ return;
++ }
++ /*
++ * Move the src cid if the dst cid is unset. This keeps id
++ * allocation closest to 0 in cases where few threads migrate around
++ * many cpus.
++ *
++ * If destination cid is already set, we may have to just clear
++ * the src cid to ensure compactness in frequent migrations
++ * scenarios.
++ *
++ * It is not useful to clear the src cid when the number of threads is
++ * greater or equal to the number of allowed cpus, because user-space
++ * can expect that the number of allowed cids can reach the number of
++ * allowed cpus.
++ */
++ dst_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(dst_rq));
++ dst_cid = READ_ONCE(dst_pcpu_cid->cid);
++ if (!mm_cid_is_unset(dst_cid) &&
++ atomic_read(&mm->mm_users) >= t->nr_cpus_allowed)
++ return;
++ src_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, src_cpu);
++ src_rq = cpu_rq(src_cpu);
++ src_cid = __sched_mm_cid_migrate_from_fetch_cid(src_rq, t, src_pcpu_cid);
++ if (src_cid == -1)
++ return;
++ src_cid = __sched_mm_cid_migrate_from_try_steal_cid(src_rq, t, src_pcpu_cid,
++ src_cid);
++ if (src_cid == -1)
++ return;
++ if (!mm_cid_is_unset(dst_cid)) {
++ __mm_cid_put(mm, src_cid);
++ return;
++ }
++ /* Move src_cid to dst cpu. */
++ mm_cid_snapshot_time(dst_rq, mm);
++ WRITE_ONCE(dst_pcpu_cid->cid, src_cid);
++}
++
++static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_cid,
++ int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct task_struct *t;
++ int cid, lazy_cid;
++
++ cid = READ_ONCE(pcpu_cid->cid);
++ if (!mm_cid_is_valid(cid))
++ return;
++
++ /*
++ * Clear the cpu cid if it is set to keep cid allocation compact. If
++ * there happens to be other tasks left on the source cpu using this
++ * mm, the next task using this mm will reallocate its cid on context
++ * switch.
++ */
++ lazy_cid = mm_cid_set_lazy_put(cid);
++ if (!try_cmpxchg(&pcpu_cid->cid, &cid, lazy_cid))
++ return;
++
++ /*
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm matches the scheduler barrier in context_switch()
++ * between store to rq->curr and load of prev and next task's
++ * per-mm/cpu cid.
++ *
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm_cid_active matches the barrier in
++ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
++ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
++ * load of per-mm/cpu cid.
++ */
++
++ /*
++ * If we observe an active task using the mm on this rq after setting
++ * the lazy-put flag, that task will be responsible for transitioning
++ * from lazy-put flag set to MM_CID_UNSET.
++ */
++ scoped_guard (rcu) {
++ t = rcu_dereference(rq->curr);
++ if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
++ return;
++ }
++
++ /*
++ * The cid is unused, so it can be unset.
++ * Disable interrupts to keep the window of cid ownership without rq
++ * lock small.
++ */
++ scoped_guard (irqsave) {
++ if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
++ __mm_cid_put(mm, cid);
++ }
++}
++
++static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct mm_cid *pcpu_cid;
++ struct task_struct *curr;
++ u64 rq_clock;
++
++ /*
++ * rq->clock load is racy on 32-bit but one spurious clear once in a
++ * while is irrelevant.
++ */
++ rq_clock = READ_ONCE(rq->clock);
++ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
++
++ /*
++ * In order to take care of infrequently scheduled tasks, bump the time
++ * snapshot associated with this cid if an active task using the mm is
++ * observed on this rq.
++ */
++ scoped_guard (rcu) {
++ curr = rcu_dereference(rq->curr);
++ if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
++ WRITE_ONCE(pcpu_cid->time, rq_clock);
++ return;
++ }
++ }
++
++ if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
++ return;
++ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
++}
++
++static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu,
++ int weight)
++{
++ struct mm_cid *pcpu_cid;
++ int cid;
++
++ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
++ cid = READ_ONCE(pcpu_cid->cid);
++ if (!mm_cid_is_valid(cid) || cid < weight)
++ return;
++ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
++}
++
++static void task_mm_cid_work(struct callback_head *work)
++{
++ unsigned long now = jiffies, old_scan, next_scan;
++ struct task_struct *t = current;
++ struct cpumask *cidmask;
++ struct mm_struct *mm;
++ int weight, cpu;
++
++ SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work));
++
++ work->next = work; /* Prevent double-add */
++ if (t->flags & PF_EXITING)
++ return;
++ mm = t->mm;
++ if (!mm)
++ return;
++ old_scan = READ_ONCE(mm->mm_cid_next_scan);
++ next_scan = now + msecs_to_jiffies(MM_CID_SCAN_DELAY);
++ if (!old_scan) {
++ unsigned long res;
++
++ res = cmpxchg(&mm->mm_cid_next_scan, old_scan, next_scan);
++ if (res != old_scan)
++ old_scan = res;
++ else
++ old_scan = next_scan;
++ }
++ if (time_before(now, old_scan))
++ return;
++ if (!try_cmpxchg(&mm->mm_cid_next_scan, &old_scan, next_scan))
++ return;
++ cidmask = mm_cidmask(mm);
++ /* Clear cids that were not recently used. */
++ for_each_possible_cpu(cpu)
++ sched_mm_cid_remote_clear_old(mm, cpu);
++ weight = cpumask_weight(cidmask);
++ /*
++ * Clear cids that are greater or equal to the cidmask weight to
++ * recompact it.
++ */
++ for_each_possible_cpu(cpu)
++ sched_mm_cid_remote_clear_weight(mm, cpu, weight);
++}
++
++void init_sched_mm_cid(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ int mm_users = 0;
++
++ if (mm) {
++ mm_users = atomic_read(&mm->mm_users);
++ if (mm_users == 1)
++ mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY);
++ }
++ t->cid_work.next = &t->cid_work; /* Protect against double add */
++ init_task_work(&t->cid_work, task_mm_cid_work);
++}
++
++void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
++{
++ struct callback_head *work = &curr->cid_work;
++ unsigned long now = jiffies;
++
++ if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) ||
++ work->next != work)
++ return;
++ if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan)))
++ return;
++ task_work_add(curr, work, TWA_RESUME);
++}
++
++void sched_mm_cid_exit_signals(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ guard(rq_lock_irqsave)(rq);
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 0);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ mm_cid_put(mm);
++ t->last_mm_cid = t->mm_cid = -1;
++}
++
++void sched_mm_cid_before_execve(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ guard(rq_lock_irqsave)(rq);
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 0);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ mm_cid_put(mm);
++ t->last_mm_cid = t->mm_cid = -1;
++}
++
++void sched_mm_cid_after_execve(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ scoped_guard (rq_lock_irqsave, rq) {
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 1);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
++ }
++ rseq_set_notify_resume(t);
++}
++
++void sched_mm_cid_fork(struct task_struct *t)
++{
++ WARN_ON_ONCE(!t->mm || t->mm_cid != -1);
++ t->mm_cid_active = 1;
++}
++#endif
+diff --git a/kernel/sched/alt_core.h b/kernel/sched/alt_core.h
+new file mode 100644
+index 000000000000..7b546c1bc9d0
+--- /dev/null
++++ b/kernel/sched/alt_core.h
+@@ -0,0 +1,74 @@
++#ifndef _KERNEL_SCHED_ALT_CORE_H
++#define _KERNEL_SCHED_ALT_CORE_H
++
++/*
++ * Compile time debug macro
++ * #define ALT_SCHED_DEBUG
++ */
++
++/*
++ * Task related inlined functions
++ */
++static inline bool is_migration_disabled(struct task_struct *p)
++{
++#ifdef CONFIG_SMP
++ return p->migration_disabled;
++#else
++ return false;
++#endif
++}
++
++/*
++ * RQ related inlined functions
++ */
++
++/*
++ * This routine assume that the idle task always in queue
++ */
++static inline struct task_struct *sched_rq_first_task(struct rq *rq)
++{
++ const struct list_head *head = &rq->queue.heads[sched_rq_prio_idx(rq)];
++
++ return list_first_entry(head, struct task_struct, sq_node);
++}
++
++static inline struct task_struct * sched_rq_next_task(struct task_struct *p, struct rq *rq)
++{
++ struct list_head *next = p->sq_node.next;
++
++ if (&rq->queue.heads[0] <= next && next < &rq->queue.heads[SCHED_LEVELS]) {
++ struct list_head *head;
++ unsigned long idx = next - &rq->queue.heads[0];
++
++ idx = find_next_bit(rq->queue.bitmap, SCHED_QUEUE_BITS,
++ sched_idx2prio(idx, rq) + 1);
++ head = &rq->queue.heads[sched_prio2idx(idx, rq)];
++
++ return list_first_entry(head, struct task_struct, sq_node);
++ }
++
++ return list_next_entry(p, sq_node);
++}
++
++#ifdef CONFIG_SMP
++extern cpumask_t sched_rq_pending_mask ____cacheline_aligned_in_smp;
++
++DECLARE_STATIC_KEY_FALSE(sched_smt_present);
++DECLARE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_llc_mask);
++
++extern cpumask_t sched_smt_mask ____cacheline_aligned_in_smp;
++
++extern cpumask_t *const sched_idle_mask;
++extern cpumask_t *const sched_sg_idle_mask;
++extern cpumask_t *const sched_pcore_idle_mask;
++extern cpumask_t *const sched_ecore_idle_mask;
++
++extern struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu);
++
++typedef bool (*idle_select_func_t)(struct cpumask *dstp, const struct cpumask *src1p,
++ const struct cpumask *src2p);
++
++extern idle_select_func_t idle_select_func;
++#endif
++
++#endif /* _KERNEL_SCHED_ALT_CORE_H */
+diff --git a/kernel/sched/alt_debug.c b/kernel/sched/alt_debug.c
+new file mode 100644
+index 000000000000..1dbd7eb6a434
+--- /dev/null
++++ b/kernel/sched/alt_debug.c
+@@ -0,0 +1,32 @@
++/*
++ * kernel/sched/alt_debug.c
++ *
++ * Print the alt scheduler debugging details
++ *
++ * Author: Alfred Chen
++ * Date : 2020
++ */
++#include "sched.h"
++#include "linux/sched/debug.h"
++
++/*
++ * This allows printing both to /proc/sched_debug and
++ * to the console
++ */
++#define SEQ_printf(m, x...) \
++ do { \
++ if (m) \
++ seq_printf(m, x); \
++ else \
++ pr_cont(x); \
++ } while (0)
++
++void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
++ struct seq_file *m)
++{
++ SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns),
++ get_nr_threads(p));
++}
++
++void proc_sched_set_task(struct task_struct *p)
++{}
+diff --git a/kernel/sched/alt_sched.h b/kernel/sched/alt_sched.h
+new file mode 100644
+index 000000000000..e8e61a59eae8
+--- /dev/null
++++ b/kernel/sched/alt_sched.h
+@@ -0,0 +1,989 @@
++#ifndef _KERNEL_SCHED_ALT_SCHED_H
++#define _KERNEL_SCHED_ALT_SCHED_H
++
++#include <linux/context_tracking.h>
++#include <linux/profile.h>
++#include <linux/stop_machine.h>
++#include <linux/syscalls.h>
++#include <linux/tick.h>
++
++#include <trace/events/power.h>
++#include <trace/events/sched.h>
++
++#include "../workqueue_internal.h"
++
++#include "cpupri.h"
++
++#ifdef CONFIG_CGROUP_SCHED
++/* task group related information */
++struct task_group {
++ struct cgroup_subsys_state css;
++
++ struct rcu_head rcu;
++ struct list_head list;
++
++ struct task_group *parent;
++ struct list_head siblings;
++ struct list_head children;
++#ifdef CONFIG_FAIR_GROUP_SCHED
++ unsigned long shares;
++#endif
++};
++
++extern struct task_group *sched_create_group(struct task_group *parent);
++extern void sched_online_group(struct task_group *tg,
++ struct task_group *parent);
++extern void sched_destroy_group(struct task_group *tg);
++extern void sched_release_group(struct task_group *tg);
++#endif /* CONFIG_CGROUP_SCHED */
++
++#define MIN_SCHED_NORMAL_PRIO (32)
++/*
++ * levels: RT(0-24), reserved(25-31), NORMAL(32-63), cpu idle task(64)
++ *
++ * -- BMQ --
++ * NORMAL: (lower boost range 12, NICE_WIDTH 40, higher boost range 12) / 2
++ * -- PDS --
++ * NORMAL: SCHED_EDGE_DELTA + ((NICE_WIDTH 40) / 2)
++ */
++#define SCHED_LEVELS (64 + 1)
++
++#define IDLE_TASK_SCHED_PRIO (SCHED_LEVELS - 1)
++
++#ifdef CONFIG_SCHED_DEBUG
++# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
++extern void resched_latency_warn(int cpu, u64 latency);
++#else
++# define SCHED_WARN_ON(x) ({ (void)(x), 0; })
++static inline void resched_latency_warn(int cpu, u64 latency) {}
++#endif
++
++/*
++ * Increase resolution of nice-level calculations for 64-bit architectures.
++ * The extra resolution improves shares distribution and load balancing of
++ * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
++ * hierarchies, especially on larger systems. This is not a user-visible change
++ * and does not change the user-interface for setting shares/weights.
++ *
++ * We increase resolution only if we have enough bits to allow this increased
++ * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
++ * are pretty high and the returns do not justify the increased costs.
++ *
++ * Really only required when CONFIG_FAIR_GROUP_SCHED=y is also set, but to
++ * increase coverage and consistency always enable it on 64-bit platforms.
++ */
++#ifdef CONFIG_64BIT
++# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
++# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
++# define scale_load_down(w) \
++({ \
++ unsigned long __w = (w); \
++ if (__w) \
++ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
++ __w; \
++})
++#else
++# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
++# define scale_load(w) (w)
++# define scale_load_down(w) (w)
++#endif
++
++#ifdef CONFIG_FAIR_GROUP_SCHED
++#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
++
++/*
++ * A weight of 0 or 1 can cause arithmetics problems.
++ * A weight of a cfs_rq is the sum of weights of which entities
++ * are queued on this cfs_rq, so a weight of a entity should not be
++ * too large, so as the shares value of a task group.
++ * (The default weight is 1024 - so there's no practical
++ * limitation from this.)
++ */
++#define MIN_SHARES (1UL << 1)
++#define MAX_SHARES (1UL << 18)
++#endif
++
++/*
++ * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
++ */
++#ifdef CONFIG_SCHED_DEBUG
++# define const_debug __read_mostly
++#else
++# define const_debug const
++#endif
++
++/* task_struct::on_rq states: */
++#define TASK_ON_RQ_QUEUED 1
++#define TASK_ON_RQ_MIGRATING 2
++
++static inline int task_on_rq_queued(struct task_struct *p)
++{
++ return p->on_rq == TASK_ON_RQ_QUEUED;
++}
++
++static inline int task_on_rq_migrating(struct task_struct *p)
++{
++ return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
++}
++
++/* Wake flags. The first three directly map to some SD flag value */
++#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
++#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
++#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
++
++#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
++#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
++#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
++
++#ifdef CONFIG_SMP
++static_assert(WF_EXEC == SD_BALANCE_EXEC);
++static_assert(WF_FORK == SD_BALANCE_FORK);
++static_assert(WF_TTWU == SD_BALANCE_WAKE);
++#endif
++
++#define SCHED_QUEUE_BITS (SCHED_LEVELS - 1)
++
++struct sched_queue {
++ DECLARE_BITMAP(bitmap, SCHED_QUEUE_BITS);
++ struct list_head heads[SCHED_LEVELS];
++};
++
++struct rq;
++struct cpuidle_state;
++
++struct balance_callback {
++ struct balance_callback *next;
++ void (*func)(struct rq *rq);
++};
++
++typedef void (*balance_func_t)(struct rq *rq, int cpu);
++typedef void (*set_idle_mask_func_t)(unsigned int cpu, struct cpumask *dstp);
++typedef void (*clear_idle_mask_func_t)(int cpu, struct cpumask *dstp);
++
++struct balance_arg {
++ struct task_struct *task;
++ int active;
++ cpumask_t *cpumask;
++};
++
++/*
++ * This is the main, per-CPU runqueue data structure.
++ * This data should only be modified by the local cpu.
++ */
++struct rq {
++ /* runqueue lock: */
++ raw_spinlock_t lock;
++
++ struct task_struct __rcu *curr;
++ struct task_struct *idle;
++ struct task_struct *stop;
++ struct mm_struct *prev_mm;
++
++ struct sched_queue queue ____cacheline_aligned;
++
++ int prio;
++#ifdef CONFIG_SCHED_PDS
++ int prio_idx;
++ u64 time_edge;
++#endif
++
++ /* switch count */
++ u64 nr_switches;
++
++ atomic_t nr_iowait;
++
++#ifdef CONFIG_SCHED_DEBUG
++ u64 last_seen_need_resched_ns;
++ int ticks_without_resched;
++#endif
++
++#ifdef CONFIG_MEMBARRIER
++ int membarrier_state;
++#endif
++
++ set_idle_mask_func_t set_idle_mask_func;
++ clear_idle_mask_func_t clear_idle_mask_func;
++
++#ifdef CONFIG_SMP
++ int cpu; /* cpu of this runqueue */
++ bool online;
++
++ unsigned int ttwu_pending;
++ unsigned char nohz_idle_balance;
++ unsigned char idle_balance;
++
++#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
++ struct sched_avg avg_irq;
++#endif
++
++ balance_func_t balance_func;
++ struct balance_arg active_balance_arg ____cacheline_aligned;
++ struct cpu_stop_work active_balance_work;
++
++ struct balance_callback *balance_callback;
++#ifdef CONFIG_HOTPLUG_CPU
++ struct rcuwait hotplug_wait;
++#endif
++ unsigned int nr_pinned;
++
++#endif /* CONFIG_SMP */
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ u64 prev_irq_time;
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++#ifdef CONFIG_PARAVIRT
++ u64 prev_steal_time;
++#endif /* CONFIG_PARAVIRT */
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ u64 prev_steal_time_rq;
++#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */
++
++ /* For genenal cpu load util */
++ s32 load_history;
++ u64 load_block;
++ u64 load_stamp;
++
++ /* calc_load related fields */
++ unsigned long calc_load_update;
++ long calc_load_active;
++
++ /* Ensure that all clocks are in the same cache line */
++ u64 clock ____cacheline_aligned;
++ u64 clock_task;
++
++ unsigned int nr_running;
++ unsigned long nr_uninterruptible;
++
++#ifdef CONFIG_SCHED_HRTICK
++#ifdef CONFIG_SMP
++ call_single_data_t hrtick_csd;
++#endif
++ struct hrtimer hrtick_timer;
++ ktime_t hrtick_time;
++#endif
++
++#ifdef CONFIG_SCHEDSTATS
++
++ /* latency stats */
++ struct sched_info rq_sched_info;
++ unsigned long long rq_cpu_time;
++ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
++
++ /* sys_sched_yield() stats */
++ unsigned int yld_count;
++
++ /* schedule() stats */
++ unsigned int sched_switch;
++ unsigned int sched_count;
++ unsigned int sched_goidle;
++
++ /* try_to_wake_up() stats */
++ unsigned int ttwu_count;
++ unsigned int ttwu_local;
++#endif /* CONFIG_SCHEDSTATS */
++
++#ifdef CONFIG_CPU_IDLE
++ /* Must be inspected within a rcu lock section */
++ struct cpuidle_state *idle_state;
++#endif
++
++#ifdef CONFIG_NO_HZ_COMMON
++#ifdef CONFIG_SMP
++ call_single_data_t nohz_csd;
++#endif
++ atomic_t nohz_flags;
++#endif /* CONFIG_NO_HZ_COMMON */
++
++ /* Scratch cpumask to be temporarily used under rq_lock */
++ cpumask_var_t scratch_mask;
++};
++
++extern unsigned int sysctl_sched_base_slice;
++
++extern unsigned long rq_load_util(struct rq *rq, unsigned long max);
++
++extern unsigned long calc_load_update;
++extern atomic_long_t calc_load_tasks;
++
++extern void calc_global_load_tick(struct rq *this_rq);
++extern long calc_load_fold_active(struct rq *this_rq, long adjust);
++
++DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
++#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
++#define this_rq() this_cpu_ptr(&runqueues)
++#define task_rq(p) cpu_rq(task_cpu(p))
++#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
++#define raw_rq() raw_cpu_ptr(&runqueues)
++
++#ifdef CONFIG_SMP
++#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
++void register_sched_domain_sysctl(void);
++void unregister_sched_domain_sysctl(void);
++#else
++static inline void register_sched_domain_sysctl(void)
++{
++}
++static inline void unregister_sched_domain_sysctl(void)
++{
++}
++#endif
++
++extern bool sched_smp_initialized;
++
++enum {
++#ifdef CONFIG_SCHED_SMT
++ SMT_LEVEL_SPACE_HOLDER,
++#endif
++ COREGROUP_LEVEL_SPACE_HOLDER,
++ CORE_LEVEL_SPACE_HOLDER,
++ OTHER_LEVEL_SPACE_HOLDER,
++ NR_CPU_AFFINITY_LEVELS
++};
++
++DECLARE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
++
++static inline int
++__best_mask_cpu(const cpumask_t *cpumask, const cpumask_t *mask)
++{
++ int cpu;
++
++ while ((cpu = cpumask_any_and(cpumask, mask)) >= nr_cpu_ids)
++ mask++;
++
++ return cpu;
++}
++
++static inline int best_mask_cpu(int cpu, const cpumask_t *mask)
++{
++ return __best_mask_cpu(mask, per_cpu(sched_cpu_topo_masks, cpu));
++}
++
++#endif
++
++#ifndef arch_scale_freq_tick
++static __always_inline
++void arch_scale_freq_tick(void)
++{
++}
++#endif
++
++#ifndef arch_scale_freq_capacity
++static __always_inline
++unsigned long arch_scale_freq_capacity(int cpu)
++{
++ return SCHED_CAPACITY_SCALE;
++}
++#endif
++
++static inline u64 __rq_clock_broken(struct rq *rq)
++{
++ return READ_ONCE(rq->clock);
++}
++
++static inline u64 rq_clock(struct rq *rq)
++{
++ /*
++ * Relax lockdep_assert_held() checking as in VRQ, call to
++ * sched_info_xxxx() may not held rq->lock
++ * lockdep_assert_held(&rq->lock);
++ */
++ return rq->clock;
++}
++
++static inline u64 rq_clock_task(struct rq *rq)
++{
++ /*
++ * Relax lockdep_assert_held() checking as in VRQ, call to
++ * sched_info_xxxx() may not held rq->lock
++ * lockdep_assert_held(&rq->lock);
++ */
++ return rq->clock_task;
++}
++
++/*
++ * {de,en}queue flags:
++ *
++ * DEQUEUE_SLEEP - task is no longer runnable
++ * ENQUEUE_WAKEUP - task just became runnable
++ *
++ */
++
++#define DEQUEUE_SLEEP 0x01
++
++#define ENQUEUE_WAKEUP 0x01
++
++
++/*
++ * Below are scheduler API which using in other kernel code
++ * It use the dummy rq_flags
++ * ToDo : BMQ need to support these APIs for compatibility with mainline
++ * scheduler code.
++ */
++struct rq_flags {
++ unsigned long flags;
++};
++
++struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(rq->lock);
++
++struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(p->pi_lock)
++ __acquires(rq->lock);
++
++static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock(&rq->lock);
++}
++
++static inline void
++task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
++ __releases(rq->lock)
++ __releases(p->pi_lock)
++{
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
++}
++
++static inline void
++rq_lock(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock(&rq->lock);
++}
++
++static inline void
++rq_unlock(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock(&rq->lock);
++}
++
++static inline void
++rq_lock_irq(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock_irq(&rq->lock);
++}
++
++static inline void
++rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock_irq(&rq->lock);
++}
++
++static inline struct rq *
++this_rq_lock_irq(struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ local_irq_disable();
++ rq = this_rq();
++ raw_spin_lock(&rq->lock);
++
++ return rq;
++}
++
++static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
++{
++ return &rq->lock;
++}
++
++static inline raw_spinlock_t *rq_lockp(struct rq *rq)
++{
++ return __rq_lockp(rq);
++}
++
++static inline void lockdep_assert_rq_held(struct rq *rq)
++{
++ lockdep_assert_held(__rq_lockp(rq));
++}
++
++extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
++extern void raw_spin_rq_unlock(struct rq *rq);
++
++static inline void raw_spin_rq_lock(struct rq *rq)
++{
++ raw_spin_rq_lock_nested(rq, 0);
++}
++
++static inline void raw_spin_rq_lock_irq(struct rq *rq)
++{
++ local_irq_disable();
++ raw_spin_rq_lock(rq);
++}
++
++static inline void raw_spin_rq_unlock_irq(struct rq *rq)
++{
++ raw_spin_rq_unlock(rq);
++ local_irq_enable();
++}
++
++static inline int task_current(struct rq *rq, struct task_struct *p)
++{
++ return rq->curr == p;
++}
++
++static inline bool task_on_cpu(struct task_struct *p)
++{
++ return p->on_cpu;
++}
++
++extern struct static_key_false sched_schedstats;
++
++#ifdef CONFIG_CPU_IDLE
++static inline void idle_set_state(struct rq *rq,
++ struct cpuidle_state *idle_state)
++{
++ rq->idle_state = idle_state;
++}
++
++static inline struct cpuidle_state *idle_get_state(struct rq *rq)
++{
++ WARN_ON(!rcu_read_lock_held());
++ return rq->idle_state;
++}
++#else
++static inline void idle_set_state(struct rq *rq,
++ struct cpuidle_state *idle_state)
++{
++}
++
++static inline struct cpuidle_state *idle_get_state(struct rq *rq)
++{
++ return NULL;
++}
++#endif
++
++static inline int cpu_of(const struct rq *rq)
++{
++#ifdef CONFIG_SMP
++ return rq->cpu;
++#else
++ return 0;
++#endif
++}
++
++extern void resched_cpu(int cpu);
++
++#include "stats.h"
++
++#ifdef CONFIG_NO_HZ_COMMON
++#define NOHZ_BALANCE_KICK_BIT 0
++#define NOHZ_STATS_KICK_BIT 1
++
++#define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT)
++#define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT)
++
++#define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
++
++#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
++
++/* TODO: needed?
++extern void nohz_balance_exit_idle(struct rq *rq);
++#else
++static inline void nohz_balance_exit_idle(struct rq *rq) { }
++*/
++#endif
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++struct irqtime {
++ u64 total;
++ u64 tick_delta;
++ u64 irq_start_time;
++ struct u64_stats_sync sync;
++};
++
++DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
++
++/*
++ * Returns the irqtime minus the softirq time computed by ksoftirqd.
++ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
++ * and never move forward.
++ */
++static inline u64 irq_time_read(int cpu)
++{
++ struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
++ unsigned int seq;
++ u64 total;
++
++ do {
++ seq = __u64_stats_fetch_begin(&irqtime->sync);
++ total = irqtime->total;
++ } while (__u64_stats_fetch_retry(&irqtime->sync, seq));
++
++ return total;
++}
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++
++#ifdef CONFIG_CPU_FREQ
++DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
++#endif /* CONFIG_CPU_FREQ */
++
++#ifdef CONFIG_NO_HZ_FULL
++extern int __init sched_tick_offload_init(void);
++#else
++static inline int sched_tick_offload_init(void) { return 0; }
++#endif
++
++#ifdef arch_scale_freq_capacity
++#ifndef arch_scale_freq_invariant
++#define arch_scale_freq_invariant() (true)
++#endif
++#else /* arch_scale_freq_capacity */
++#define arch_scale_freq_invariant() (false)
++#endif
++
++#ifdef CONFIG_SMP
++unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
++ unsigned long min,
++ unsigned long max);
++#endif /* CONFIG_SMP */
++
++extern void schedule_idle(void);
++
++#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
++
++/*
++ * !! For sched_setattr_nocheck() (kernel) only !!
++ *
++ * This is actually gross. :(
++ *
++ * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE
++ * tasks, but still be able to sleep. We need this on platforms that cannot
++ * atomically change clock frequency. Remove once fast switching will be
++ * available on such platforms.
++ *
++ * SUGOV stands for SchedUtil GOVernor.
++ */
++#define SCHED_FLAG_SUGOV 0x10000000
++
++#ifdef CONFIG_MEMBARRIER
++/*
++ * The scheduler provides memory barriers required by membarrier between:
++ * - prior user-space memory accesses and store to rq->membarrier_state,
++ * - store to rq->membarrier_state and following user-space memory accesses.
++ * In the same way it provides those guarantees around store to rq->curr.
++ */
++static inline void membarrier_switch_mm(struct rq *rq,
++ struct mm_struct *prev_mm,
++ struct mm_struct *next_mm)
++{
++ int membarrier_state;
++
++ if (prev_mm == next_mm)
++ return;
++
++ membarrier_state = atomic_read(&next_mm->membarrier_state);
++ if (READ_ONCE(rq->membarrier_state) == membarrier_state)
++ return;
++
++ WRITE_ONCE(rq->membarrier_state, membarrier_state);
++}
++#else
++static inline void membarrier_switch_mm(struct rq *rq,
++ struct mm_struct *prev_mm,
++ struct mm_struct *next_mm)
++{
++}
++#endif
++
++#ifdef CONFIG_NUMA
++extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
++#else
++static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
++{
++ return nr_cpu_ids;
++}
++#endif
++
++extern void swake_up_all_locked(struct swait_queue_head *q);
++extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
++
++extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++extern int preempt_dynamic_mode;
++extern int sched_dynamic_mode(const char *str);
++extern void sched_dynamic_update(int mode);
++#endif
++
++static inline void nohz_run_idle_balance(int cpu) { }
++
++static inline
++unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
++ struct task_struct *p)
++{
++ return util;
++}
++
++static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
++
++#ifdef CONFIG_SCHED_MM_CID
++
++#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */
++#define MM_CID_SCAN_DELAY 100 /* 100ms */
++
++extern raw_spinlock_t cid_lock;
++extern int use_cid_lock;
++
++extern void sched_mm_cid_migrate_from(struct task_struct *t);
++extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu);
++extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr);
++extern void init_sched_mm_cid(struct task_struct *t);
++
++static inline void __mm_cid_put(struct mm_struct *mm, int cid)
++{
++ if (cid < 0)
++ return;
++ cpumask_clear_cpu(cid, mm_cidmask(mm));
++}
++
++/*
++ * The per-mm/cpu cid can have the MM_CID_LAZY_PUT flag set or transition to
++ * the MM_CID_UNSET state without holding the rq lock, but the rq lock needs to
++ * be held to transition to other states.
++ *
++ * State transitions synchronized with cmpxchg or try_cmpxchg need to be
++ * consistent across cpus, which prevents use of this_cpu_cmpxchg.
++ */
++static inline void mm_cid_put_lazy(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ int cid;
++
++ lockdep_assert_irqs_disabled();
++ cid = __this_cpu_read(pcpu_cid->cid);
++ if (!mm_cid_is_lazy_put(cid) ||
++ !try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
++ return;
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++}
++
++static inline int mm_cid_pcpu_unset(struct mm_struct *mm)
++{
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ int cid, res;
++
++ lockdep_assert_irqs_disabled();
++ cid = __this_cpu_read(pcpu_cid->cid);
++ for (;;) {
++ if (mm_cid_is_unset(cid))
++ return MM_CID_UNSET;
++ /*
++ * Attempt transition from valid or lazy-put to unset.
++ */
++ res = cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, cid, MM_CID_UNSET);
++ if (res == cid)
++ break;
++ cid = res;
++ }
++ return cid;
++}
++
++static inline void mm_cid_put(struct mm_struct *mm)
++{
++ int cid;
++
++ lockdep_assert_irqs_disabled();
++ cid = mm_cid_pcpu_unset(mm);
++ if (cid == MM_CID_UNSET)
++ return;
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++}
++
++static inline int __mm_cid_try_get(struct mm_struct *mm)
++{
++ struct cpumask *cpumask;
++ int cid;
++
++ cpumask = mm_cidmask(mm);
++ /*
++ * Retry finding first zero bit if the mask is temporarily
++ * filled. This only happens during concurrent remote-clear
++ * which owns a cid without holding a rq lock.
++ */
++ for (;;) {
++ cid = cpumask_first_zero(cpumask);
++ if (cid < nr_cpu_ids)
++ break;
++ cpu_relax();
++ }
++ if (cpumask_test_and_set_cpu(cid, cpumask))
++ return -1;
++ return cid;
++}
++
++/*
++ * Save a snapshot of the current runqueue time of this cpu
++ * with the per-cpu cid value, allowing to estimate how recently it was used.
++ */
++static inline void mm_cid_snapshot_time(struct rq *rq, struct mm_struct *mm)
++{
++ struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(rq));
++
++ lockdep_assert_rq_held(rq);
++ WRITE_ONCE(pcpu_cid->time, rq->clock);
++}
++
++static inline int __mm_cid_get(struct rq *rq, struct mm_struct *mm)
++{
++ int cid;
++
++ /*
++ * All allocations (even those using the cid_lock) are lock-free. If
++ * use_cid_lock is set, hold the cid_lock to perform cid allocation to
++ * guarantee forward progress.
++ */
++ if (!READ_ONCE(use_cid_lock)) {
++ cid = __mm_cid_try_get(mm);
++ if (cid >= 0)
++ goto end;
++ raw_spin_lock(&cid_lock);
++ } else {
++ raw_spin_lock(&cid_lock);
++ cid = __mm_cid_try_get(mm);
++ if (cid >= 0)
++ goto unlock;
++ }
++
++ /*
++ * cid concurrently allocated. Retry while forcing following
++ * allocations to use the cid_lock to ensure forward progress.
++ */
++ WRITE_ONCE(use_cid_lock, 1);
++ /*
++ * Set use_cid_lock before allocation. Only care about program order
++ * because this is only required for forward progress.
++ */
++ barrier();
++ /*
++ * Retry until it succeeds. It is guaranteed to eventually succeed once
++ * all newcoming allocations observe the use_cid_lock flag set.
++ */
++ do {
++ cid = __mm_cid_try_get(mm);
++ cpu_relax();
++ } while (cid < 0);
++ /*
++ * Allocate before clearing use_cid_lock. Only care about
++ * program order because this is for forward progress.
++ */
++ barrier();
++ WRITE_ONCE(use_cid_lock, 0);
++unlock:
++ raw_spin_unlock(&cid_lock);
++end:
++ mm_cid_snapshot_time(rq, mm);
++ return cid;
++}
++
++static inline int mm_cid_get(struct rq *rq, struct mm_struct *mm)
++{
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ struct cpumask *cpumask;
++ int cid;
++
++ lockdep_assert_rq_held(rq);
++ cpumask = mm_cidmask(mm);
++ cid = __this_cpu_read(pcpu_cid->cid);
++ if (mm_cid_is_valid(cid)) {
++ mm_cid_snapshot_time(rq, mm);
++ return cid;
++ }
++ if (mm_cid_is_lazy_put(cid)) {
++ if (try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++ }
++ cid = __mm_cid_get(rq, mm);
++ __this_cpu_write(pcpu_cid->cid, cid);
++ return cid;
++}
++
++static inline void switch_mm_cid(struct rq *rq,
++ struct task_struct *prev,
++ struct task_struct *next)
++{
++ /*
++ * Provide a memory barrier between rq->curr store and load of
++ * {prev,next}->mm->pcpu_cid[cpu] on rq->curr->mm transition.
++ *
++ * Should be adapted if context_switch() is modified.
++ */
++ if (!next->mm) { // to kernel
++ /*
++ * user -> kernel transition does not guarantee a barrier, but
++ * we can use the fact that it performs an atomic operation in
++ * mmgrab().
++ */
++ if (prev->mm) // from user
++ smp_mb__after_mmgrab();
++ /*
++ * kernel -> kernel transition does not change rq->curr->mm
++ * state. It stays NULL.
++ */
++ } else { // to user
++ /*
++ * kernel -> user transition does not provide a barrier
++ * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
++ * Provide it here.
++ */
++ if (!prev->mm) // from kernel
++ smp_mb();
++ /*
++ * user -> user transition guarantees a memory barrier through
++ * switch_mm() when current->mm changes. If current->mm is
++ * unchanged, no barrier is needed.
++ */
++ }
++ if (prev->mm_cid_active) {
++ mm_cid_snapshot_time(rq, prev->mm);
++ mm_cid_put_lazy(prev);
++ prev->mm_cid = -1;
++ }
++ if (next->mm_cid_active)
++ next->last_mm_cid = next->mm_cid = mm_cid_get(rq, next->mm);
++}
++
++#else
++static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { }
++static inline void sched_mm_cid_migrate_from(struct task_struct *t) { }
++static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu) { }
++static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
++static inline void init_sched_mm_cid(struct task_struct *t) { }
++#endif
++
++#ifdef CONFIG_SMP
++extern struct balance_callback balance_push_callback;
++
++static inline void
++queue_balance_callback(struct rq *rq,
++ struct balance_callback *head,
++ void (*func)(struct rq *rq))
++{
++ lockdep_assert_rq_held(rq);
++
++ /*
++ * Don't (re)queue an already queued item; nor queue anything when
++ * balance_push() is active, see the comment with
++ * balance_push_callback.
++ */
++ if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
++ return;
++
++ head->func = func;
++ head->next = rq->balance_callback;
++ rq->balance_callback = head;
++}
++#endif /* CONFIG_SMP */
++
++#ifdef CONFIG_SCHED_BMQ
++#include "bmq.h"
++#endif
++#ifdef CONFIG_SCHED_PDS
++#include "pds.h"
++#endif
++
++#endif /* _KERNEL_SCHED_ALT_SCHED_H */
+diff --git a/kernel/sched/alt_topology.c b/kernel/sched/alt_topology.c
+new file mode 100644
+index 000000000000..2266138ee783
+--- /dev/null
++++ b/kernel/sched/alt_topology.c
+@@ -0,0 +1,350 @@
++#include "alt_core.h"
++#include "alt_topology.h"
++
++#ifdef CONFIG_SMP
++
++static cpumask_t sched_pcore_mask ____cacheline_aligned_in_smp;
++
++static int __init sched_pcore_mask_setup(char *str)
++{
++ if (cpulist_parse(str, &sched_pcore_mask))
++ pr_warn("sched/alt: pcore_cpus= incorrect CPU range\n");
++
++ return 0;
++}
++__setup("pcore_cpus=", sched_pcore_mask_setup);
++
++/*
++ * set/clear idle mask functions
++ */
++#ifdef CONFIG_SCHED_SMT
++static void set_idle_mask_smt(unsigned int cpu, struct cpumask *dstp)
++{
++ cpumask_set_cpu(cpu, dstp);
++ if (cpumask_subset(cpu_smt_mask(cpu), sched_idle_mask))
++ cpumask_or(sched_sg_idle_mask, sched_sg_idle_mask, cpu_smt_mask(cpu));
++}
++
++static void clear_idle_mask_smt(int cpu, struct cpumask *dstp)
++{
++ cpumask_clear_cpu(cpu, dstp);
++ cpumask_andnot(sched_sg_idle_mask, sched_sg_idle_mask, cpu_smt_mask(cpu));
++}
++#endif
++
++static void set_idle_mask_pcore(unsigned int cpu, struct cpumask *dstp)
++{
++ cpumask_set_cpu(cpu, dstp);
++ cpumask_set_cpu(cpu, sched_pcore_idle_mask);
++}
++
++static void clear_idle_mask_pcore(int cpu, struct cpumask *dstp)
++{
++ cpumask_clear_cpu(cpu, dstp);
++ cpumask_clear_cpu(cpu, sched_pcore_idle_mask);
++}
++
++static void set_idle_mask_ecore(unsigned int cpu, struct cpumask *dstp)
++{
++ cpumask_set_cpu(cpu, dstp);
++ cpumask_set_cpu(cpu, sched_ecore_idle_mask);
++}
++
++static void clear_idle_mask_ecore(int cpu, struct cpumask *dstp)
++{
++ cpumask_clear_cpu(cpu, dstp);
++ cpumask_clear_cpu(cpu, sched_ecore_idle_mask);
++}
++
++/*
++ * Idle cpu/rq selection functions
++ */
++#ifdef CONFIG_SCHED_SMT
++static bool p1_idle_select_func(struct cpumask *dstp, const struct cpumask *src1p,
++ const struct cpumask *src2p)
++{
++ return cpumask_and(dstp, src1p, src2p + 1) ||
++ cpumask_and(dstp, src1p, src2p);
++}
++#endif
++
++static bool p1p2_idle_select_func(struct cpumask *dstp, const struct cpumask *src1p,
++ const struct cpumask *src2p)
++{
++ return cpumask_and(dstp, src1p, src2p + 1) ||
++ cpumask_and(dstp, src1p, src2p + 2) ||
++ cpumask_and(dstp, src1p, src2p);
++}
++
++/* common balance functions */
++static int active_balance_cpu_stop(void *data)
++{
++ struct balance_arg *arg = data;
++ struct task_struct *p = arg->task;
++ struct rq *rq = this_rq();
++ unsigned long flags;
++ cpumask_t tmp;
++
++ local_irq_save(flags);
++
++ raw_spin_lock(&p->pi_lock);
++ raw_spin_lock(&rq->lock);
++
++ arg->active = 0;
++
++ if (task_on_rq_queued(p) && task_rq(p) == rq &&
++ cpumask_and(&tmp, p->cpus_ptr, arg->cpumask) &&
++ !is_migration_disabled(p)) {
++ int dcpu = __best_mask_cpu(&tmp, per_cpu(sched_cpu_llc_mask, cpu_of(rq)));
++ rq = move_queued_task(rq, p, dcpu);
++ }
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ return 0;
++}
++
++/* trigger_active_balance - for @rq */
++static inline int
++trigger_active_balance(struct rq *src_rq, struct rq *rq, cpumask_t *target_mask)
++{
++ struct balance_arg *arg;
++ unsigned long flags;
++ struct task_struct *p;
++ int res;
++
++ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
++ return 0;
++
++ arg = &rq->active_balance_arg;
++ res = (1 == rq->nr_running) && \
++ !is_migration_disabled((p = sched_rq_first_task(rq))) && \
++ cpumask_intersects(p->cpus_ptr, target_mask) && \
++ !arg->active;
++ if (res) {
++ arg->task = p;
++ arg->cpumask = target_mask;
++
++ arg->active = 1;
++ }
++
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ if (res) {
++ preempt_disable();
++ raw_spin_unlock(&src_rq->lock);
++
++ stop_one_cpu_nowait(cpu_of(rq), active_balance_cpu_stop, arg,
++ &rq->active_balance_work);
++
++ preempt_enable();
++ raw_spin_lock(&src_rq->lock);
++ }
++
++ return res;
++}
++
++static inline int
++ecore_source_balance(struct rq *rq, cpumask_t *single_task_mask, cpumask_t *target_mask)
++{
++ if (cpumask_andnot(single_task_mask, single_task_mask, &sched_pcore_mask)) {
++ int i, cpu = cpu_of(rq);
++
++ for_each_cpu_wrap(i, single_task_mask, cpu)
++ if (trigger_active_balance(rq, cpu_rq(i), target_mask))
++ return 1;
++ }
++
++ return 0;
++}
++
++static DEFINE_PER_CPU(struct balance_callback, active_balance_head);
++
++#ifdef CONFIG_SCHED_SMT
++static inline int
++smt_pcore_source_balance(struct rq *rq, cpumask_t *single_task_mask, cpumask_t *target_mask)
++{
++ cpumask_t smt_single_mask;
++
++ if (cpumask_and(&smt_single_mask, single_task_mask, &sched_smt_mask)) {
++ int i, cpu = cpu_of(rq);
++
++ for_each_cpu_wrap(i, &smt_single_mask, cpu) {
++ if (cpumask_subset(cpu_smt_mask(i), &smt_single_mask) &&
++ trigger_active_balance(rq, cpu_rq(i), target_mask))
++ return 1;
++ }
++ }
++
++ return 0;
++}
++
++/* smt p core balance functions */
++static inline void smt_pcore_balance(struct rq *rq)
++{
++ cpumask_t single_task_mask;
++
++ if (cpumask_andnot(&single_task_mask, cpu_active_mask, sched_idle_mask) &&
++ cpumask_andnot(&single_task_mask, &single_task_mask, &sched_rq_pending_mask) &&
++ (/* smt core group balance */
++ (static_key_count(&sched_smt_present.key) > 1 &&
++ smt_pcore_source_balance(rq, &single_task_mask, sched_sg_idle_mask)
++ ) ||
++ /* e core to idle smt core balance */
++ ecore_source_balance(rq, &single_task_mask, sched_sg_idle_mask)))
++ return;
++}
++
++static void smt_pcore_balance_func(struct rq *rq, const int cpu)
++{
++ if (cpumask_test_cpu(cpu, sched_sg_idle_mask))
++ queue_balance_callback(rq, &per_cpu(active_balance_head, cpu), smt_pcore_balance);
++}
++
++/* smt balance functions */
++static inline void smt_balance(struct rq *rq)
++{
++ cpumask_t single_task_mask;
++
++ if (cpumask_andnot(&single_task_mask, cpu_active_mask, sched_idle_mask) &&
++ cpumask_andnot(&single_task_mask, &single_task_mask, &sched_rq_pending_mask) &&
++ static_key_count(&sched_smt_present.key) > 1 &&
++ smt_pcore_source_balance(rq, &single_task_mask, sched_sg_idle_mask))
++ return;
++}
++
++static void smt_balance_func(struct rq *rq, const int cpu)
++{
++ if (cpumask_test_cpu(cpu, sched_sg_idle_mask))
++ queue_balance_callback(rq, &per_cpu(active_balance_head, cpu), smt_balance);
++}
++
++/* e core balance functions */
++static inline void ecore_balance(struct rq *rq)
++{
++ cpumask_t single_task_mask;
++
++ if (cpumask_andnot(&single_task_mask, cpu_active_mask, sched_idle_mask) &&
++ cpumask_andnot(&single_task_mask, &single_task_mask, &sched_rq_pending_mask) &&
++ /* smt occupied p core to idle e core balance */
++ smt_pcore_source_balance(rq, &single_task_mask, sched_ecore_idle_mask))
++ return;
++}
++
++static void ecore_balance_func(struct rq *rq, const int cpu)
++{
++ queue_balance_callback(rq, &per_cpu(active_balance_head, cpu), ecore_balance);
++}
++#endif /* CONFIG_SCHED_SMT */
++
++/* p core balance functions */
++static inline void pcore_balance(struct rq *rq)
++{
++ cpumask_t single_task_mask;
++
++ if (cpumask_andnot(&single_task_mask, cpu_active_mask, sched_idle_mask) &&
++ cpumask_andnot(&single_task_mask, &single_task_mask, &sched_rq_pending_mask) &&
++ /* idle e core to p core balance */
++ ecore_source_balance(rq, &single_task_mask, sched_pcore_idle_mask))
++ return;
++}
++
++static void pcore_balance_func(struct rq *rq, const int cpu)
++{
++ queue_balance_callback(rq, &per_cpu(active_balance_head, cpu), pcore_balance);
++}
++
++#ifdef ALT_SCHED_DEBUG
++#define SCHED_DEBUG_INFO(...) printk(KERN_INFO __VA_ARGS__)
++#else
++#define SCHED_DEBUG_INFO(...) do { } while(0)
++#endif
++
++#define SET_IDLE_SELECT_FUNC(func) \
++{ \
++ idle_select_func = func; \
++ printk(KERN_INFO "sched: "#func); \
++}
++
++#define SET_RQ_BALANCE_FUNC(rq, cpu, func) \
++{ \
++ rq->balance_func = func; \
++ SCHED_DEBUG_INFO("sched: cpu#%02d -> "#func, cpu); \
++}
++
++#define SET_RQ_IDLE_MASK_FUNC(rq, cpu, set_func, clear_func) \
++{ \
++ rq->set_idle_mask_func = set_func; \
++ rq->clear_idle_mask_func = clear_func; \
++ SCHED_DEBUG_INFO("sched: cpu#%02d -> "#set_func" "#clear_func, cpu); \
++}
++
++void sched_init_topology(void)
++{
++ int cpu;
++ struct rq *rq;
++ cpumask_t sched_ecore_mask = { CPU_BITS_NONE };
++ int ecore_present = 0;
++
++#ifdef CONFIG_SCHED_SMT
++ if (!cpumask_empty(&sched_smt_mask))
++ printk(KERN_INFO "sched: smt mask: 0x%08lx\n", sched_smt_mask.bits[0]);
++#endif
++
++ if (!cpumask_empty(&sched_pcore_mask)) {
++ cpumask_andnot(&sched_ecore_mask, cpu_online_mask, &sched_pcore_mask);
++ printk(KERN_INFO "sched: pcore mask: 0x%08lx, ecore mask: 0x%08lx\n",
++ sched_pcore_mask.bits[0], sched_ecore_mask.bits[0]);
++
++ ecore_present = !cpumask_empty(&sched_ecore_mask);
++ }
++
++#ifdef CONFIG_SCHED_SMT
++ /* idle select function */
++ if (cpumask_equal(&sched_smt_mask, cpu_online_mask)) {
++ SET_IDLE_SELECT_FUNC(p1_idle_select_func);
++ } else
++#endif
++ if (!cpumask_empty(&sched_pcore_mask)) {
++ SET_IDLE_SELECT_FUNC(p1p2_idle_select_func);
++ }
++
++ for_each_online_cpu(cpu) {
++ rq = cpu_rq(cpu);
++ /* take chance to reset time slice for idle tasks */
++ rq->idle->time_slice = sysctl_sched_base_slice;
++
++#ifdef CONFIG_SCHED_SMT
++ if (cpumask_weight(cpu_smt_mask(cpu)) > 1) {
++ SET_RQ_IDLE_MASK_FUNC(rq, cpu, set_idle_mask_smt, clear_idle_mask_smt);
++
++ if (cpumask_test_cpu(cpu, &sched_pcore_mask) &&
++ !cpumask_intersects(&sched_ecore_mask, &sched_smt_mask)) {
++ SET_RQ_BALANCE_FUNC(rq, cpu, smt_pcore_balance_func);
++ } else {
++ SET_RQ_BALANCE_FUNC(rq, cpu, smt_balance_func);
++ }
++
++ continue;
++ }
++#endif
++ /* !SMT or only one cpu in sg */
++ if (cpumask_test_cpu(cpu, &sched_pcore_mask)) {
++ SET_RQ_IDLE_MASK_FUNC(rq, cpu, set_idle_mask_pcore, clear_idle_mask_pcore);
++
++ if (ecore_present)
++ SET_RQ_BALANCE_FUNC(rq, cpu, pcore_balance_func);
++
++ continue;
++ }
++ if (cpumask_test_cpu(cpu, &sched_ecore_mask)) {
++ SET_RQ_IDLE_MASK_FUNC(rq, cpu, set_idle_mask_ecore, clear_idle_mask_ecore);
++#ifdef CONFIG_SCHED_SMT
++ if (cpumask_intersects(&sched_pcore_mask, &sched_smt_mask))
++ SET_RQ_BALANCE_FUNC(rq, cpu, ecore_balance_func);
++#endif
++ }
++ }
++}
++#endif /* CONFIG_SMP */
+diff --git a/kernel/sched/alt_topology.h b/kernel/sched/alt_topology.h
+new file mode 100644
+index 000000000000..076174cd2bc6
+--- /dev/null
++++ b/kernel/sched/alt_topology.h
+@@ -0,0 +1,6 @@
++#ifndef _KERNEL_SCHED_ALT_TOPOLOGY_H
++#define _KERNEL_SCHED_ALT_TOPOLOGY_H
++
++extern void sched_init_topology(void);
++
++#endif /* _KERNEL_SCHED_ALT_TOPOLOGY_H */
+diff --git a/kernel/sched/bmq.h b/kernel/sched/bmq.h
+new file mode 100644
+index 000000000000..5a7835246ec3
+--- /dev/null
++++ b/kernel/sched/bmq.h
+@@ -0,0 +1,103 @@
++#ifndef _KERNEL_SCHED_BMQ_H
++#define _KERNEL_SCHED_BMQ_H
++
++#define ALT_SCHED_NAME "BMQ"
++
++/*
++ * BMQ only routines
++ */
++static inline void boost_task(struct task_struct *p, int n)
++{
++ int limit;
++
++ switch (p->policy) {
++ case SCHED_NORMAL:
++ limit = -MAX_PRIORITY_ADJ;
++ break;
++ case SCHED_BATCH:
++ limit = 0;
++ break;
++ default:
++ return;
++ }
++
++ p->boost_prio = max(limit, p->boost_prio - n);
++}
++
++static inline void deboost_task(struct task_struct *p)
++{
++ if (p->boost_prio < MAX_PRIORITY_ADJ)
++ p->boost_prio++;
++}
++
++/*
++ * Common interfaces
++ */
++static inline void sched_timeslice_imp(const int timeslice_ms) {}
++
++/* This API is used in task_prio(), return value readed by human users */
++static inline int
++task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
++{
++ return p->prio + p->boost_prio - MIN_NORMAL_PRIO;
++}
++
++static inline int task_sched_prio(const struct task_struct *p)
++{
++ return (p->prio < MIN_NORMAL_PRIO)? (p->prio >> 2) :
++ MIN_SCHED_NORMAL_PRIO + (p->prio + p->boost_prio - MIN_NORMAL_PRIO) / 2;
++}
++
++#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
++ prio = task_sched_prio(p); \
++ idx = prio;
++
++static inline int sched_prio2idx(int prio, struct rq *rq)
++{
++ return prio;
++}
++
++static inline int sched_idx2prio(int idx, struct rq *rq)
++{
++ return idx;
++}
++
++static inline int sched_rq_prio_idx(struct rq *rq)
++{
++ return rq->prio;
++}
++
++static inline int task_running_nice(struct task_struct *p)
++{
++ return (p->prio + p->boost_prio > DEFAULT_PRIO);
++}
++
++static inline void sched_update_rq_clock(struct rq *rq) {}
++
++static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
++{
++ deboost_task(p);
++}
++
++static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq) {}
++static inline void sched_task_fork(struct task_struct *p, struct rq *rq) {}
++
++static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
++{
++ p->boost_prio = MAX_PRIORITY_ADJ;
++}
++
++static inline void sched_task_ttwu(struct task_struct *p)
++{
++ s64 delta = this_rq()->clock_task > p->last_ran;
++
++ if (likely(delta > 0))
++ boost_task(p, delta >> 22);
++}
++
++static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq)
++{
++ boost_task(p, 1);
++}
++
++#endif /* _KERNEL_SCHED_BMQ_H */
+diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
+index d9dc9ab3773f..71a25540d65e 100644
+--- a/kernel/sched/build_policy.c
++++ b/kernel/sched/build_policy.c
+@@ -42,13 +42,19 @@
+
+ #include "idle.c"
+
++#ifndef CONFIG_SCHED_ALT
+ #include "rt.c"
++#endif
+
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ # include "cpudeadline.c"
++#endif
+ # include "pelt.c"
+ #endif
+
+ #include "cputime.c"
+-#include "deadline.c"
+
++#ifndef CONFIG_SCHED_ALT
++#include "deadline.c"
++#endif
+diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
+index 80a3df49ab47..58d04aa73634 100644
+--- a/kernel/sched/build_utility.c
++++ b/kernel/sched/build_utility.c
+@@ -56,6 +56,10 @@
+
+ #include "clock.c"
+
++#ifdef CONFIG_SCHED_ALT
++# include "alt_topology.c"
++#endif
++
+ #ifdef CONFIG_CGROUP_CPUACCT
+ # include "cpuacct.c"
+ #endif
+@@ -84,7 +88,9 @@
+
+ #ifdef CONFIG_SMP
+ # include "cpupri.c"
++#ifndef CONFIG_SCHED_ALT
+ # include "stop_task.c"
++#endif
+ # include "topology.c"
+ #endif
+
+diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
+index eece6244f9d2..3075127f9e95 100644
+--- a/kernel/sched/cpufreq_schedutil.c
++++ b/kernel/sched/cpufreq_schedutil.c
+@@ -197,12 +197,17 @@ unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
+
+ static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
+ {
++#ifndef CONFIG_SCHED_ALT
+ unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
+
+ util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
+ util = max(util, boost);
+ sg_cpu->bw_min = min;
+ sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
++#else /* CONFIG_SCHED_ALT */
++ sg_cpu->bw_min = 0;
++ sg_cpu->util = rq_load_util(cpu_rq(sg_cpu->cpu), arch_scale_cpu_capacity(sg_cpu->cpu));
++#endif /* CONFIG_SCHED_ALT */
+ }
+
+ /**
+@@ -343,8 +348,10 @@ static inline bool sugov_cpu_is_busy(struct sugov_cpu *sg_cpu) { return false; }
+ */
+ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
+ {
++#ifndef CONFIG_SCHED_ALT
+ if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
+ sg_cpu->sg_policy->limits_changed = true;
++#endif
+ }
+
+ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
+@@ -676,6 +683,7 @@ static int sugov_kthread_create(struct sugov_policy *sg_policy)
+ }
+
+ ret = sched_setattr_nocheck(thread, &attr);
++
+ if (ret) {
+ kthread_stop(thread);
+ pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
+diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
+index aa48b2ec879d..3034c06528bc 100644
+--- a/kernel/sched/cputime.c
++++ b/kernel/sched/cputime.c
+@@ -126,7 +126,7 @@ void account_user_time(struct task_struct *p, u64 cputime)
+ p->utime += cputime;
+ account_group_user_time(p, cputime);
+
+- index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
++ index = task_running_nice(p) ? CPUTIME_NICE : CPUTIME_USER;
+
+ /* Add user time to cpustat. */
+ task_group_account_field(p, index, cputime);
+@@ -150,7 +150,7 @@ void account_guest_time(struct task_struct *p, u64 cputime)
+ p->gtime += cputime;
+
+ /* Add guest time to cpustat. */
+- if (task_nice(p) > 0) {
++ if (task_running_nice(p)) {
+ task_group_account_field(p, CPUTIME_NICE, cputime);
+ cpustat[CPUTIME_GUEST_NICE] += cputime;
+ } else {
+@@ -288,7 +288,7 @@ static inline u64 account_other_time(u64 max)
+ #ifdef CONFIG_64BIT
+ static inline u64 read_sum_exec_runtime(struct task_struct *t)
+ {
+- return t->se.sum_exec_runtime;
++ return tsk_seruntime(t);
+ }
+ #else
+ static u64 read_sum_exec_runtime(struct task_struct *t)
+@@ -298,7 +298,7 @@ static u64 read_sum_exec_runtime(struct task_struct *t)
+ struct rq *rq;
+
+ rq = task_rq_lock(t, &rf);
+- ns = t->se.sum_exec_runtime;
++ ns = tsk_seruntime(t);
+ task_rq_unlock(rq, t, &rf);
+
+ return ns;
+@@ -617,7 +617,7 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
+ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
+ {
+ struct task_cputime cputime = {
+- .sum_exec_runtime = p->se.sum_exec_runtime,
++ .sum_exec_runtime = tsk_seruntime(p),
+ };
+
+ if (task_cputime(p, &cputime.utime, &cputime.stime))
+diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
+index c1eb9a1afd13..d3aec989797d 100644
+--- a/kernel/sched/debug.c
++++ b/kernel/sched/debug.c
+@@ -7,6 +7,7 @@
+ * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
+ */
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * This allows printing both to /sys/kernel/debug/sched/debug and
+ * to the console
+@@ -215,6 +216,7 @@ static const struct file_operations sched_scaling_fops = {
+ };
+
+ #endif /* SMP */
++#endif /* !CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_PREEMPT_DYNAMIC
+
+@@ -278,6 +280,7 @@ static const struct file_operations sched_dynamic_fops = {
+
+ #endif /* CONFIG_PREEMPT_DYNAMIC */
+
++#ifndef CONFIG_SCHED_ALT
+ __read_mostly bool sched_debug_verbose;
+
+ #ifdef CONFIG_SMP
+@@ -332,6 +335,7 @@ static const struct file_operations sched_debug_fops = {
+ .llseek = seq_lseek,
+ .release = seq_release,
+ };
++#endif /* !CONFIG_SCHED_ALT */
+
+ static struct dentry *debugfs_sched;
+
+@@ -341,14 +345,17 @@ static __init int sched_init_debug(void)
+
+ debugfs_sched = debugfs_create_dir("sched", NULL);
+
++#ifndef CONFIG_SCHED_ALT
+ debugfs_create_file("features", 0644, debugfs_sched, NULL, &sched_feat_fops);
+ debugfs_create_file_unsafe("verbose", 0644, debugfs_sched, &sched_debug_verbose, &sched_verbose_fops);
++#endif /* !CONFIG_SCHED_ALT */
+ #ifdef CONFIG_PREEMPT_DYNAMIC
+ debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
+ #endif
+
+ debugfs_create_u32("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
+
++#ifndef CONFIG_SCHED_ALT
+ debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
+ debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
+
+@@ -373,11 +380,13 @@ static __init int sched_init_debug(void)
+ #endif
+
+ debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
++#endif /* !CONFIG_SCHED_ALT */
+
+ return 0;
+ }
+ late_initcall(sched_init_debug);
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_SMP
+
+ static cpumask_var_t sd_sysctl_cpus;
+@@ -1111,6 +1120,7 @@ void proc_sched_set_task(struct task_struct *p)
+ memset(&p->stats, 0, sizeof(p->stats));
+ #endif
+ }
++#endif /* !CONFIG_SCHED_ALT */
+
+ void resched_latency_warn(int cpu, u64 latency)
+ {
+diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
+index 6135fbe83d68..57708dc54827 100644
+--- a/kernel/sched/idle.c
++++ b/kernel/sched/idle.c
+@@ -430,6 +430,7 @@ void cpu_startup_entry(enum cpuhp_state state)
+ do_idle();
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * idle-task scheduling class.
+ */
+@@ -551,3 +552,4 @@ DEFINE_SCHED_CLASS(idle) = {
+ .switched_to = switched_to_idle,
+ .update_curr = update_curr_idle,
+ };
++#endif
+diff --git a/kernel/sched/pds.h b/kernel/sched/pds.h
+new file mode 100644
+index 000000000000..fe3099071eb7
+--- /dev/null
++++ b/kernel/sched/pds.h
+@@ -0,0 +1,139 @@
++#ifndef _KERNEL_SCHED_PDS_H
++#define _KERNEL_SCHED_PDS_H
++
++#define ALT_SCHED_NAME "PDS"
++
++static const u64 RT_MASK = ((1ULL << MIN_SCHED_NORMAL_PRIO) - 1);
++
++#define SCHED_NORMAL_PRIO_NUM (32)
++#define SCHED_EDGE_DELTA (SCHED_NORMAL_PRIO_NUM - NICE_WIDTH / 2)
++
++/* PDS assume SCHED_NORMAL_PRIO_NUM is power of 2 */
++#define SCHED_NORMAL_PRIO_MOD(x) ((x) & (SCHED_NORMAL_PRIO_NUM - 1))
++
++/* default time slice 4ms -> shift 22, 2 time slice slots -> shift 23 */
++static __read_mostly int sched_timeslice_shift = 23;
++
++/*
++ * Common interfaces
++ */
++static inline int
++task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
++{
++ u64 sched_dl = max(p->deadline, rq->time_edge);
++
++#ifdef ALT_SCHED_DEBUG
++ if (WARN_ONCE(sched_dl - rq->time_edge > NORMAL_PRIO_NUM - 1,
++ "pds: task_sched_prio_normal() delta %lld\n", sched_dl - rq->time_edge))
++ return SCHED_NORMAL_PRIO_NUM - 1;
++#endif
++
++ return sched_dl - rq->time_edge;
++}
++
++static inline int task_sched_prio(const struct task_struct *p)
++{
++ return (p->prio < MIN_NORMAL_PRIO) ? (p->prio >> 2) :
++ MIN_SCHED_NORMAL_PRIO + task_sched_prio_normal(p, task_rq(p));
++}
++
++#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
++ if (p->prio < MIN_NORMAL_PRIO) { \
++ prio = p->prio >> 2; \
++ idx = prio; \
++ } else { \
++ u64 sched_dl = max(p->deadline, rq->time_edge); \
++ prio = MIN_SCHED_NORMAL_PRIO + sched_dl - rq->time_edge; \
++ idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_dl); \
++ }
++
++static inline int sched_prio2idx(int sched_prio, struct rq *rq)
++{
++ return (IDLE_TASK_SCHED_PRIO == sched_prio || sched_prio < MIN_SCHED_NORMAL_PRIO) ?
++ sched_prio :
++ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_prio + rq->time_edge);
++}
++
++static inline int sched_idx2prio(int sched_idx, struct rq *rq)
++{
++ return (sched_idx < MIN_SCHED_NORMAL_PRIO) ?
++ sched_idx :
++ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_idx - rq->time_edge);
++}
++
++static inline int sched_rq_prio_idx(struct rq *rq)
++{
++ return rq->prio_idx;
++}
++
++static inline int task_running_nice(struct task_struct *p)
++{
++ return (p->prio > DEFAULT_PRIO);
++}
++
++static inline void sched_update_rq_clock(struct rq *rq)
++{
++ struct list_head head;
++ u64 old = rq->time_edge;
++ u64 now = rq->clock >> sched_timeslice_shift;
++ u64 prio, delta;
++ DECLARE_BITMAP(normal, SCHED_QUEUE_BITS);
++
++ if (now == old)
++ return;
++
++ rq->time_edge = now;
++ delta = min_t(u64, SCHED_NORMAL_PRIO_NUM, now - old);
++ INIT_LIST_HEAD(&head);
++
++ prio = MIN_SCHED_NORMAL_PRIO;
++ for_each_set_bit_from(prio, rq->queue.bitmap, MIN_SCHED_NORMAL_PRIO + delta)
++ list_splice_tail_init(rq->queue.heads + MIN_SCHED_NORMAL_PRIO +
++ SCHED_NORMAL_PRIO_MOD(prio + old), &head);
++
++ bitmap_shift_right(normal, rq->queue.bitmap, delta, SCHED_QUEUE_BITS);
++ if (!list_empty(&head)) {
++ u64 idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(now);
++
++ __list_splice(&head, rq->queue.heads + idx, rq->queue.heads[idx].next);
++ set_bit(MIN_SCHED_NORMAL_PRIO, normal);
++ }
++ bitmap_replace(rq->queue.bitmap, normal, rq->queue.bitmap,
++ (const unsigned long *)&RT_MASK, SCHED_QUEUE_BITS);
++
++ if (rq->prio < MIN_SCHED_NORMAL_PRIO || IDLE_TASK_SCHED_PRIO == rq->prio)
++ return;
++
++ rq->prio = max_t(u64, MIN_SCHED_NORMAL_PRIO, rq->prio - delta);
++ rq->prio_idx = sched_prio2idx(rq->prio, rq);
++}
++
++static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
++{
++ if (p->prio >= MIN_NORMAL_PRIO)
++ p->deadline = rq->time_edge + SCHED_EDGE_DELTA +
++ (p->static_prio - (MAX_PRIO - NICE_WIDTH)) / 2;
++}
++
++static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq)
++{
++ u64 max_dl = rq->time_edge + SCHED_EDGE_DELTA + NICE_WIDTH / 2 - 1;
++ if (unlikely(p->deadline > max_dl))
++ p->deadline = max_dl;
++}
++
++static inline void sched_task_fork(struct task_struct *p, struct rq *rq)
++{
++ sched_task_renew(p, rq);
++}
++
++static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
++{
++ p->time_slice = sysctl_sched_base_slice;
++ sched_task_renew(p, rq);
++}
++
++static inline void sched_task_ttwu(struct task_struct *p) {}
++static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq) {}
++
++#endif /* _KERNEL_SCHED_PDS_H */
+diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
+index ef00382de595..9b8362284b9e 100644
+--- a/kernel/sched/pelt.c
++++ b/kernel/sched/pelt.c
+@@ -266,6 +266,7 @@ ___update_load_avg(struct sched_avg *sa, unsigned long load)
+ WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * sched_entity:
+ *
+@@ -383,8 +384,9 @@ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+
+ return 0;
+ }
++#endif
+
+-#ifdef CONFIG_SCHED_HW_PRESSURE
++#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
+ /*
+ * hardware:
+ *
+diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
+index 2150062949d4..a82bff3231a4 100644
+--- a/kernel/sched/pelt.h
++++ b/kernel/sched/pelt.h
+@@ -1,13 +1,15 @@
+ #ifdef CONFIG_SMP
+ #include "sched-pelt.h"
+
++#ifndef CONFIG_SCHED_ALT
+ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
+ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
+ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
+ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
++#endif
+
+-#ifdef CONFIG_SCHED_HW_PRESSURE
++#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
+ int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity);
+
+ static inline u64 hw_load_avg(struct rq *rq)
+@@ -44,6 +46,7 @@ static inline u32 get_pelt_divider(struct sched_avg *avg)
+ return PELT_MIN_DIVIDER + avg->period_contrib;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ static inline void cfs_se_util_change(struct sched_avg *avg)
+ {
+ unsigned int enqueued;
+@@ -180,9 +183,11 @@ static inline u64 cfs_rq_clock_pelt(struct cfs_rq *cfs_rq)
+ return rq_clock_pelt(rq_of(cfs_rq));
+ }
+ #endif
++#endif /* CONFIG_SCHED_ALT */
+
+ #else
+
++#ifndef CONFIG_SCHED_ALT
+ static inline int
+ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+ {
+@@ -200,6 +205,7 @@ update_dl_rq_load_avg(u64 now, struct rq *rq, int running)
+ {
+ return 0;
+ }
++#endif
+
+ static inline int
+ update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
+diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
+index ef20c61004eb..a38785bb8048 100644
+--- a/kernel/sched/sched.h
++++ b/kernel/sched/sched.h
+@@ -5,6 +5,10 @@
+ #ifndef _KERNEL_SCHED_SCHED_H
+ #define _KERNEL_SCHED_SCHED_H
+
++#ifdef CONFIG_SCHED_ALT
++#include "alt_sched.h"
++#else
++
+ #include <linux/sched/affinity.h>
+ #include <linux/sched/autogroup.h>
+ #include <linux/sched/cpufreq.h>
+@@ -3481,4 +3485,9 @@ static inline void init_sched_mm_cid(struct task_struct *t) { }
+ extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
+ extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
++static inline int task_running_nice(struct task_struct *p)
++{
++ return (task_nice(p) > 0);
++}
++#endif /* !CONFIG_SCHED_ALT */
+ #endif /* _KERNEL_SCHED_SCHED_H */
+diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
+index 78e48f5426ee..2b31bcb9f683 100644
+--- a/kernel/sched/stats.c
++++ b/kernel/sched/stats.c
+@@ -125,8 +125,10 @@ static int show_schedstat(struct seq_file *seq, void *v)
+ } else {
+ struct rq *rq;
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ struct sched_domain *sd;
+ int dcount = 0;
++#endif
+ #endif
+ cpu = (unsigned long)(v - 2);
+ rq = cpu_rq(cpu);
+@@ -143,6 +145,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
+ seq_printf(seq, "\n");
+
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ /* domain-specific stats */
+ rcu_read_lock();
+ for_each_domain(cpu, sd) {
+@@ -170,6 +173,7 @@ static int show_schedstat(struct seq_file *seq, void *v)
+ sd->ttwu_move_balance);
+ }
+ rcu_read_unlock();
++#endif
+ #endif
+ }
+ return 0;
+diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
+index b02dfc322951..49f94ed07ce6 100644
+--- a/kernel/sched/stats.h
++++ b/kernel/sched/stats.h
+@@ -89,6 +89,7 @@ static inline void rq_sched_info_depart (struct rq *rq, unsigned long long delt
+
+ #endif /* CONFIG_SCHEDSTATS */
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_FAIR_GROUP_SCHED
+ struct sched_entity_stats {
+ struct sched_entity se;
+@@ -105,6 +106,7 @@ __schedstats_from_se(struct sched_entity *se)
+ #endif
+ return &task_of(se)->stats;
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_PSI
+ void psi_task_change(struct task_struct *task, int clear, int set);
+diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
+index a6994a1fcc90..22d542998c5c 100644
+--- a/kernel/sched/topology.c
++++ b/kernel/sched/topology.c
+@@ -3,6 +3,7 @@
+ * Scheduler topology setup/handling methods
+ */
+
++#ifndef CONFIG_SCHED_ALT
+ #include <linux/bsearch.h>
+
+ DEFINE_MUTEX(sched_domains_mutex);
+@@ -1451,8 +1452,10 @@ static void asym_cpu_capacity_scan(void)
+ */
+
+ static int default_relax_domain_level = -1;
++#endif /* CONFIG_SCHED_ALT */
+ int sched_domain_level_max;
+
++#ifndef CONFIG_SCHED_ALT
+ static int __init setup_relax_domain_level(char *str)
+ {
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+@@ -1687,6 +1690,7 @@ sd_init(struct sched_domain_topology_level *tl,
+
+ return sd;
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ /*
+ * Topology list, bottom-up.
+@@ -1723,6 +1727,7 @@ void __init set_sched_topology(struct sched_domain_topology_level *tl)
+ sched_domain_topology_saved = NULL;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_NUMA
+
+ static const struct cpumask *sd_numa_mask(int cpu)
+@@ -2789,3 +2794,28 @@ void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
+ partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
+ mutex_unlock(&sched_domains_mutex);
+ }
++#else /* CONFIG_SCHED_ALT */
++DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
++
++void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
++ struct sched_domain_attr *dattr_new)
++{}
++
++#ifdef CONFIG_NUMA
++int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
++{
++ return best_mask_cpu(cpu, cpus);
++}
++
++int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
++{
++ return cpumask_nth(cpu, cpus);
++}
++
++const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops)
++{
++ return ERR_PTR(-EOPNOTSUPP);
++}
++EXPORT_SYMBOL_GPL(sched_numa_hop_mask);
++#endif /* CONFIG_NUMA */
++#endif
+diff --git a/kernel/sysctl.c b/kernel/sysctl.c
+index e0b917328cf9..c72067bfb880 100644
+--- a/kernel/sysctl.c
++++ b/kernel/sysctl.c
+@@ -92,6 +92,10 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals);
+
+ /* Constants used for minimum and maximum */
+
++#ifdef CONFIG_SCHED_ALT
++extern int sched_yield_type;
++#endif
++
+ #ifdef CONFIG_PERF_EVENTS
+ static const int six_hundred_forty_kb = 640 * 1024;
+ #endif
+@@ -1912,6 +1916,17 @@ static struct ctl_table kern_table[] = {
+ .proc_handler = proc_dointvec,
+ },
+ #endif
++#ifdef CONFIG_SCHED_ALT
++ {
++ .procname = "yield_type",
++ .data = &sched_yield_type,
++ .maxlen = sizeof (int),
++ .mode = 0644,
++ .proc_handler = &proc_dointvec_minmax,
++ .extra1 = SYSCTL_ZERO,
++ .extra2 = SYSCTL_TWO,
++ },
++#endif
+ #if defined(CONFIG_S390) && defined(CONFIG_SMP)
+ {
+ .procname = "spin_retry",
+diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
+index b8ee320208d4..087b252383cb 100644
+--- a/kernel/time/hrtimer.c
++++ b/kernel/time/hrtimer.c
+@@ -2074,8 +2074,10 @@ long hrtimer_nanosleep(ktime_t rqtp, const enum hrtimer_mode mode,
+ int ret = 0;
+ u64 slack;
+
++#ifndef CONFIG_SCHED_ALT
+ slack = current->timer_slack_ns;
+- if (rt_task(current))
++ if (dl_task(current) || rt_task(current))
++#endif
+ slack = 0;
+
+ hrtimer_init_sleeper_on_stack(&t, clockid, mode);
+diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
+index e9c6f9d0e42c..43ee0a94abdd 100644
+--- a/kernel/time/posix-cpu-timers.c
++++ b/kernel/time/posix-cpu-timers.c
+@@ -223,7 +223,7 @@ static void task_sample_cputime(struct task_struct *p, u64 *samples)
+ u64 stime, utime;
+
+ task_cputime(p, &utime, &stime);
+- store_samples(samples, stime, utime, p->se.sum_exec_runtime);
++ store_samples(samples, stime, utime, tsk_seruntime(p));
+ }
+
+ static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
+@@ -867,6 +867,7 @@ static void collect_posix_cputimers(struct posix_cputimers *pct, u64 *samples,
+ }
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ static inline void check_dl_overrun(struct task_struct *tsk)
+ {
+ if (tsk->dl.dl_overrun) {
+@@ -874,6 +875,7 @@ static inline void check_dl_overrun(struct task_struct *tsk)
+ send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
+ }
+ }
++#endif
+
+ static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
+ {
+@@ -901,8 +903,10 @@ static void check_thread_timers(struct task_struct *tsk,
+ u64 samples[CPUCLOCK_MAX];
+ unsigned long soft;
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(tsk))
+ check_dl_overrun(tsk);
++#endif
+
+ if (expiry_cache_is_inactive(pct))
+ return;
+@@ -916,7 +920,7 @@ static void check_thread_timers(struct task_struct *tsk,
+ soft = task_rlimit(tsk, RLIMIT_RTTIME);
+ if (soft != RLIM_INFINITY) {
+ /* Task RT timeout is accounted in jiffies. RTTIME is usec */
+- unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ);
++ unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ);
+ unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
+
+ /* At the hard limit, send SIGKILL. No further action. */
+@@ -1152,8 +1156,10 @@ static inline bool fastpath_timer_check(struct task_struct *tsk)
+ return true;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(tsk) && tsk->dl.dl_overrun)
+ return true;
++#endif
+
+ return false;
+ }
+diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
+index e9c5058a8efd..8c23dc364046 100644
+--- a/kernel/trace/trace_selftest.c
++++ b/kernel/trace/trace_selftest.c
+@@ -1155,10 +1155,15 @@ static int trace_wakeup_test_thread(void *data)
+ {
+ /* Make this a -deadline thread */
+ static const struct sched_attr attr = {
++#ifdef CONFIG_SCHED_ALT
++ /* No deadline on BMQ/PDS, use RR */
++ .sched_policy = SCHED_RR,
++#else
+ .sched_policy = SCHED_DEADLINE,
+ .sched_runtime = 100000ULL,
+ .sched_deadline = 10000000ULL,
+ .sched_period = 10000000ULL
++#endif
+ };
+ struct wakeup_test_data *x = data;
+
+diff --git a/kernel/workqueue.c b/kernel/workqueue.c
+index 3fbaecfc88c2..e2e493d2316b 100644
+--- a/kernel/workqueue.c
++++ b/kernel/workqueue.c
+@@ -1248,6 +1248,7 @@ static bool kick_pool(struct worker_pool *pool)
+
+ p = worker->task;
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_SMP
+ /*
+ * Idle @worker is about to execute @work and waking up provides an
+@@ -1277,6 +1278,8 @@ static bool kick_pool(struct worker_pool *pool)
+ }
+ }
+ #endif
++#endif /* !CONFIG_SCHED_ALT */
++
+ wake_up_process(p);
+ return true;
+ }
+@@ -1405,7 +1408,11 @@ void wq_worker_running(struct task_struct *task)
+ * CPU intensive auto-detection cares about how long a work item hogged
+ * CPU without sleeping. Reset the starting timestamp on wakeup.
+ */
++#ifdef CONFIG_SCHED_ALT
++ worker->current_at = worker->task->sched_time;
++#else
+ worker->current_at = worker->task->se.sum_exec_runtime;
++#endif
+
+ WRITE_ONCE(worker->sleeping, 0);
+ }
+@@ -1490,7 +1497,11 @@ void wq_worker_tick(struct task_struct *task)
+ * We probably want to make this prettier in the future.
+ */
+ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) ||
++#ifdef CONFIG_SCHED_ALT
++ worker->task->sched_time - worker->current_at <
++#else
+ worker->task->se.sum_exec_runtime - worker->current_at <
++#endif
+ wq_cpu_intensive_thresh_us * NSEC_PER_USEC)
+ return;
+
+@@ -3176,7 +3187,11 @@ __acquires(&pool->lock)
+ worker->current_func = work->func;
+ worker->current_pwq = pwq;
+ if (worker->task)
++#ifdef CONFIG_SCHED_ALT
++ worker->current_at = worker->task->sched_time;
++#else
+ worker->current_at = worker->task->se.sum_exec_runtime;
++#endif
+ work_data = *work_data_bits(work);
+ worker->current_color = get_work_color(work_data);
+
diff --git a/5021_BMQ-and-PDS-gentoo-defaults.patch b/5021_BMQ-and-PDS-gentoo-defaults.patch
new file mode 100644
index 00000000..6dc48eec
--- /dev/null
+++ b/5021_BMQ-and-PDS-gentoo-defaults.patch
@@ -0,0 +1,13 @@
+--- a/init/Kconfig 2023-02-13 08:16:09.534315265 -0500
++++ b/init/Kconfig 2023-02-13 08:17:24.130237204 -0500
+@@ -867,8 +867,9 @@ config UCLAMP_BUCKETS_COUNT
+ If in doubt, use the default value.
+
+ menuconfig SCHED_ALT
++ depends on X86_64
+ bool "Alternative CPU Schedulers"
+- default y
++ default n
+ help
+ This feature enable alternative CPU scheduler"
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-14 15:18 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-14 15:18 UTC (permalink / raw
To: gentoo-commits
commit: 7acf5823d708e0a03078c1e068cd7b10f00c8465
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Aug 14 15:18:13 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Aug 14 15:18:13 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=7acf5823
Remove redundant patch
Removed:
2950_jump-label-fix.patch
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 ----
2950_jump-label-fix.patch | 57 -----------------------------------------------
2 files changed, 61 deletions(-)
diff --git a/0000_README b/0000_README
index 04764583..46799647 100644
--- a/0000_README
+++ b/0000_README
@@ -95,10 +95,6 @@ Patch: 2920_sign-file-patch-for-libressl.patch
From: https://bugs.gentoo.org/717166
Desc: sign-file: full functionality with modern LibreSSL
-Patch: 2950_jump-label-fix.patch
-From: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/
-Desc: jump_label: Fix a regression
-
Patch: 2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
From: https://lore.kernel.org/bpf/
Desc: libbpf: workaround -Wmaybe-uninitialized false positive
diff --git a/2950_jump-label-fix.patch b/2950_jump-label-fix.patch
deleted file mode 100644
index 1a5fdf7a..00000000
--- a/2950_jump-label-fix.patch
+++ /dev/null
@@ -1,57 +0,0 @@
-From 224fa3552029a3d14bec7acf72ded8171d551b88 Mon Sep 17 00:00:00 2001
-From: Peter Zijlstra <peterz@infradead.org>
-Date: Wed, 31 Jul 2024 12:43:21 +0200
-Subject: jump_label: Fix the fix, brown paper bags galore
-
-Per the example of:
-
- !atomic_cmpxchg(&key->enabled, 0, 1)
-
-the inverse was written as:
-
- atomic_cmpxchg(&key->enabled, 1, 0)
-
-except of course, that while !old is only true for old == 0, old is
-true for everything except old == 0.
-
-Fix it to read:
-
- atomic_cmpxchg(&key->enabled, 1, 0) == 1
-
-such that only the 1->0 transition returns true and goes on to disable
-the keys.
-
-Fixes: 83ab38ef0a0b ("jump_label: Fix concurrency issues in static_key_slow_dec()")
-Reported-by: Darrick J. Wong <djwong@kernel.org>
-Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
-Tested-by: Darrick J. Wong <djwong@kernel.org>
-Link: https://lkml.kernel.org/r/20240731105557.GY33588@noisy.programming.kicks-ass.net
----
- kernel/jump_label.c | 4 ++--
- 1 file changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/kernel/jump_label.c b/kernel/jump_label.c
-index 4ad5ed8adf9691..6dc76b590703ed 100644
---- a/kernel/jump_label.c
-+++ b/kernel/jump_label.c
-@@ -236,7 +236,7 @@ void static_key_disable_cpuslocked(struct static_key *key)
- }
-
- jump_label_lock();
-- if (atomic_cmpxchg(&key->enabled, 1, 0))
-+ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
- jump_label_update(key);
- jump_label_unlock();
- }
-@@ -289,7 +289,7 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
- return;
-
- guard(mutex)(&jump_label_mutex);
-- if (atomic_cmpxchg(&key->enabled, 1, 0))
-+ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
- jump_label_update(key);
- else
- WARN_ON_ONCE(!static_key_slow_try_dec(key));
---
-cgit 1.2.3-korg
-
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-14 14:49 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-14 14:49 UTC (permalink / raw
To: gentoo-commits
commit: 59cf1147d40237fbf00353e17a5cf22141622e1b
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Aug 14 14:49:16 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Aug 14 14:49:16 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=59cf1147
libbpf: v2 workaround -Wmaybe-uninitialized false positive
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +-
...workaround-Wmaybe-uninitialized-false-pos.patch | 47 ++++++++++++++++++----
2 files changed, 41 insertions(+), 10 deletions(-)
diff --git a/0000_README b/0000_README
index 308053b4..04764583 100644
--- a/0000_README
+++ b/0000_README
@@ -99,8 +99,8 @@ Patch: 2950_jump-label-fix.patch
From: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/
Desc: jump_label: Fix a regression
-Patch: 2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch
-From: https://lore.kernel.org/bpf/3ebbe7a4e93a5ddc3a26e2e11d329801d7c8de6b.1723217044.git.sam@gentoo.org/
+Patch: 2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
+From: https://lore.kernel.org/bpf/
Desc: libbpf: workaround -Wmaybe-uninitialized false positive
Patch: 3000_Support-printing-firmware-info.patch
diff --git a/2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch b/2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
similarity index 59%
rename from 2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch
rename to 2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
index 86de18d7..af5e117f 100644
--- a/2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch
+++ b/2990_libbpf-v2-workaround-Wmaybe-uninitialized-false-pos.patch
@@ -1,8 +1,8 @@
From git@z Thu Jan 1 00:00:00 1970
-Subject: [PATCH] libbpf: workaround -Wmaybe-uninitialized false positive
+Subject: [PATCH v2] libbpf: workaround -Wmaybe-uninitialized false positive
From: Sam James <sam@gentoo.org>
-Date: Fri, 09 Aug 2024 16:24:04 +0100
-Message-Id: <3ebbe7a4e93a5ddc3a26e2e11d329801d7c8de6b.1723217044.git.sam@gentoo.org>
+Date: Fri, 09 Aug 2024 18:26:41 +0100
+Message-Id: <8f5c3b173e4cb216322ae19ade2766940c6fbebb.1723224401.git.sam@gentoo.org>
MIME-Version: 1.0
Content-Type: text/plain; charset="utf-8"
Content-Transfer-Encoding: 8bit
@@ -37,28 +37,59 @@ here (see linked GCC bug). Suppress -Wmaybe-uninitialized accordingly.
Link: https://gcc.gnu.org/PR114952
Signed-off-by: Sam James <sam@gentoo.org>
---
- tools/lib/bpf/elf.c | 4 ++++
- 1 file changed, 4 insertions(+)
+v2: Fix Clang build.
+
+Range-diff against v1:
+1: 3ebbe7a4e93a ! 1: 8f5c3b173e4c libbpf: workaround -Wmaybe-uninitialized false positive
+ @@ tools/lib/bpf/elf.c: long elf_find_func_offset(Elf *elf, const char *binary_path
+ return ret;
+ }
+
+ ++#if !defined(__clang__)
+ +#pragma GCC diagnostic push
+ +/* https://gcc.gnu.org/PR114952 */
+ +#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+ ++#endif
+ /* Find offset of function name in ELF object specified by path. "name" matches
+ * symbol name or name@@LIB for library functions.
+ */
+ @@ tools/lib/bpf/elf.c: long elf_find_func_offset_from_file(const char *binary_path
+ elf_close(&elf_fd);
+ return ret;
+ }
+ ++#if !defined(__clang__)
+ +#pragma GCC diagnostic pop
+ ++#endif
+
+ struct symbol {
+ const char *name;
+
+ tools/lib/bpf/elf.c | 8 ++++++++
+ 1 file changed, 8 insertions(+)
diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
-index c92e02394159e..ee226bb8e1af0 100644
+index c92e02394159..7058425ca85b 100644
--- a/tools/lib/bpf/elf.c
+++ b/tools/lib/bpf/elf.c
-@@ -369,6 +369,9 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
+@@ -369,6 +369,11 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
return ret;
}
++#if !defined(__clang__)
+#pragma GCC diagnostic push
+/* https://gcc.gnu.org/PR114952 */
+#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
++#endif
/* Find offset of function name in ELF object specified by path. "name" matches
* symbol name or name@@LIB for library functions.
*/
-@@ -384,6 +387,7 @@ long elf_find_func_offset_from_file(const char *binary_path, const char *name)
+@@ -384,6 +389,9 @@ long elf_find_func_offset_from_file(const char *binary_path, const char *name)
elf_close(&elf_fd);
return ret;
}
++#if !defined(__clang__)
+#pragma GCC diagnostic pop
++#endif
struct symbol {
const char *name;
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-14 14:08 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-14 14:08 UTC (permalink / raw
To: gentoo-commits
commit: d96679025b88dd13a8f0068426bf68f8144ac048
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Tue Aug 13 17:13:24 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Tue Aug 13 17:13:24 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=d9667902
xfs: xfs_finobt_count_blocks() walks the wrong btree
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +++
1900_xfs-finobt-count-blocks-fix.patch | 55 ++++++++++++++++++++++++++++++++++
2 files changed, 59 insertions(+)
diff --git a/0000_README b/0000_README
index 8befc23c..aa55e020 100644
--- a/0000_README
+++ b/0000_README
@@ -71,6 +71,10 @@ Patch: 1730_parisc-Disable-prctl.patch
From: https://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
Desc: prctl: Temporarily disable prctl(PR_SET_MDWE) on parisc
+Patch: 1900_xfs-finobt-count-blocks-fix.patch
+From: https://lore.kernel.org/linux-xfs/20240813152530.GF6051@frogsfrogsfrogs/T/#mdc718f38912ccc1b9b53b46d9adfaeff0828b55f
+Desc: xfs: xfs_finobt_count_blocks() walks the wrong btree
+
Patch: 2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch
From: https://lore.kernel.org/linux-bluetooth/20190522070540.48895-1-marcel@holtmann.org/raw
Desc: Bluetooth: Check key sizes only when Secure Simple Pairing is enabled. See bug #686758
diff --git a/1900_xfs-finobt-count-blocks-fix.patch b/1900_xfs-finobt-count-blocks-fix.patch
new file mode 100644
index 00000000..02f60712
--- /dev/null
+++ b/1900_xfs-finobt-count-blocks-fix.patch
@@ -0,0 +1,55 @@
+xfs: xfs_finobt_count_blocks() walks the wrong btree
+
+From: Dave Chinner <dchinner@redhat.com>
+
+As a result of the factoring in commit 14dd46cf31f4 ("xfs: split
+xfs_inobt_init_cursor"), mount started taking a long time on a
+user's filesystem. For Anders, this made mount times regress from
+under a second to over 15 minutes for a filesystem with only 30
+million inodes in it.
+
+Anders bisected it down to the above commit, but even then the bug
+was not obvious. In this commit, over 20 calls to
+xfs_inobt_init_cursor() were modified, and some we modified to call
+a new function named xfs_finobt_init_cursor().
+
+If that takes you a moment to reread those function names to see
+what the rename was, then you have realised why this bug wasn't
+spotted during review. And it wasn't spotted on inspection even
+after the bisect pointed at this commit - a single missing "f" isn't
+the easiest thing for a human eye to notice....
+
+The result is that xfs_finobt_count_blocks() now incorrectly calls
+xfs_inobt_init_cursor() so it is now walking the inobt instead of
+the finobt. Hence when there are lots of allocated inodes in a
+filesystem, mount takes a -long- time run because it now walks a
+massive allocated inode btrees instead of the small, nearly empty
+free inode btrees. It also means all the finobt space reservations
+are wrong, so mount could potentially given ENOSPC on kernel
+upgrade.
+
+In hindsight, commit 14dd46cf31f4 should have been two commits - the
+first to convert the finobt callers to the new API, the second to
+modify the xfs_inobt_init_cursor() API for the inobt callers. That
+would have made the bug very obvious during review.
+
+Fixes: 14dd46cf31f4 ("xfs: split xfs_inobt_init_cursor")
+Reported-by: Anders Blomdell <anders.blomdell@gmail.com>
+Signed-off-by: Dave Chinner <dchinner@redhat.com>
+---
+ fs/xfs/libxfs/xfs_ialloc_btree.c | 2 +-
+ 1 file changed, 1 insertion(+), 1 deletion(-)
+
+diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
+index 496e2f72a85b..797d5b5f7b72 100644
+--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
++++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
+@@ -749,7 +749,7 @@ xfs_finobt_count_blocks(
+ if (error)
+ return error;
+
+- cur = xfs_inobt_init_cursor(pag, tp, agbp);
++ cur = xfs_finobt_init_cursor(pag, tp, agbp);
+ error = xfs_btree_count_blocks(cur, tree_blocks);
+ xfs_btree_del_cursor(cur, error);
+ xfs_trans_brelse(tp, agbp);
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-14 14:08 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-14 14:08 UTC (permalink / raw
To: gentoo-commits
commit: fab41ab6d1472887f05dd343aa0821750eed8c5a
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Aug 14 14:08:05 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Aug 14 14:08:05 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=fab41ab6
Linux patch 6.10.5
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1004_linux-6.10.5.patch | 11070 ++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 11074 insertions(+)
diff --git a/0000_README b/0000_README
index aa55e020..308053b4 100644
--- a/0000_README
+++ b/0000_README
@@ -59,6 +59,10 @@ Patch: 1003_linux-6.10.4.patch
From: https://www.kernel.org
Desc: Linux 6.10.4
+Patch: 1004_linux-6.10.5.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.5
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1004_linux-6.10.5.patch b/1004_linux-6.10.5.patch
new file mode 100644
index 00000000..f00971be
--- /dev/null
+++ b/1004_linux-6.10.5.patch
@@ -0,0 +1,11070 @@
+diff --git a/Documentation/admin-guide/cifs/usage.rst b/Documentation/admin-guide/cifs/usage.rst
+index fd4b56c0996f4..c09674a75a9e3 100644
+--- a/Documentation/admin-guide/cifs/usage.rst
++++ b/Documentation/admin-guide/cifs/usage.rst
+@@ -742,7 +742,7 @@ SecurityFlags Flags which control security negotiation and
+ may use NTLMSSP 0x00080
+ must use NTLMSSP 0x80080
+ seal (packet encryption) 0x00040
+- must seal (not implemented yet) 0x40040
++ must seal 0x40040
+
+ cifsFYI If set to non-zero value, additional debug information
+ will be logged to the system error log. This field
+diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
+index 2569e7f19b476..c82446cef8e21 100644
+--- a/Documentation/admin-guide/kernel-parameters.txt
++++ b/Documentation/admin-guide/kernel-parameters.txt
+@@ -4801,11 +4801,9 @@
+
+ profile= [KNL] Enable kernel profiling via /proc/profile
+ Format: [<profiletype>,]<number>
+- Param: <profiletype>: "schedule", "sleep", or "kvm"
++ Param: <profiletype>: "schedule" or "kvm"
+ [defaults to kernel profiling]
+ Param: "schedule" - profile schedule points.
+- Param: "sleep" - profile D-state sleeping (millisecs).
+- Requires CONFIG_SCHEDSTATS
+ Param: "kvm" - profile VM exits.
+ Param: <number> - step/bucket size as a power of 2 for
+ statistical time based profiling.
+diff --git a/Documentation/arch/arm64/silicon-errata.rst b/Documentation/arch/arm64/silicon-errata.rst
+index eb8af8032c315..50327c05be8d1 100644
+--- a/Documentation/arch/arm64/silicon-errata.rst
++++ b/Documentation/arch/arm64/silicon-errata.rst
+@@ -122,26 +122,50 @@ stable kernels.
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A76 | #1490853 | N/A |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A76 | #3324349 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A77 | #1491015 | N/A |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A77 | #1508412 | ARM64_ERRATUM_1508412 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A77 | #3324348 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A78 | #3324344 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A78C | #3324346,3324347| ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A710 | #2119858 | ARM64_ERRATUM_2119858 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A710 | #2054223 | ARM64_ERRATUM_2054223 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A710 | #2224489 | ARM64_ERRATUM_2224489 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A710 | #3324338 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-A715 | #2645198 | ARM64_ERRATUM_2645198 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A720 | #3456091 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-A725 | #3456106 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-X1 | #1502854 | N/A |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-X1 | #3324344 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-X1C | #3324346 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-X2 | #2119858 | ARM64_ERRATUM_2119858 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-X2 | #2224489 | ARM64_ERRATUM_2224489 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-X2 | #3324338 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-X3 | #3324335 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Cortex-X4 | #3194386 | ARM64_ERRATUM_3194386 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Cortex-X925 | #3324334 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Neoverse-N1 | #1188873,1418040| ARM64_ERRATUM_1418040 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Neoverse-N1 | #1349291 | N/A |
+@@ -150,15 +174,23 @@ stable kernels.
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Neoverse-N1 | #1542419 | ARM64_ERRATUM_1542419 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Neoverse-N1 | #3324349 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Neoverse-N2 | #2139208 | ARM64_ERRATUM_2139208 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Neoverse-N2 | #2067961 | ARM64_ERRATUM_2067961 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Neoverse-N2 | #2253138 | ARM64_ERRATUM_2253138 |
+ +----------------+-----------------+-----------------+-----------------------------+
++| ARM | Neoverse-N2 | #3324339 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
+ | ARM | Neoverse-V1 | #1619801 | N/A |
+ +----------------+-----------------+-----------------+-----------------------------+
+-| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3312417 |
++| ARM | Neoverse-V1 | #3324341 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
++| ARM | Neoverse-V2 | #3324336 | ARM64_ERRATUM_3194386 |
+++----------------+-----------------+-----------------+-----------------------------+
++| ARM | Neoverse-V3 | #3312417 | ARM64_ERRATUM_3194386 |
+ +----------------+-----------------+-----------------+-----------------------------+
+ | ARM | MMU-500 | #841119,826419 | N/A |
+ +----------------+-----------------+-----------------+-----------------------------+
+diff --git a/Documentation/hwmon/corsair-psu.rst b/Documentation/hwmon/corsair-psu.rst
+index 16db34d464dd6..7ed794087f848 100644
+--- a/Documentation/hwmon/corsair-psu.rst
++++ b/Documentation/hwmon/corsair-psu.rst
+@@ -15,11 +15,11 @@ Supported devices:
+
+ Corsair HX850i
+
+- Corsair HX1000i (Series 2022 and 2023)
++ Corsair HX1000i (Legacy and Series 2023)
+
+- Corsair HX1200i
++ Corsair HX1200i (Legacy and Series 2023)
+
+- Corsair HX1500i (Series 2022 and 2023)
++ Corsair HX1500i (Legacy and Series 2023)
+
+ Corsair RM550i
+
+diff --git a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst
+index b3c5779521d8c..2e7d0d3151a17 100644
+--- a/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst
++++ b/Documentation/userspace-api/media/v4l/pixfmt-yuv-luma.rst
+@@ -21,9 +21,9 @@ are often referred to as greyscale formats.
+
+ .. raw:: latex
+
+- \scriptsize
++ \tiny
+
+-.. tabularcolumns:: |p{3.6cm}|p{3.0cm}|p{1.3cm}|p{2.6cm}|p{1.3cm}|p{1.3cm}|p{1.3cm}|
++.. tabularcolumns:: |p{3.6cm}|p{2.4cm}|p{1.3cm}|p{1.3cm}|p{1.3cm}|p{1.3cm}|p{1.3cm}|p{1.3cm}|p{1.3cm}|
+
+ .. flat-table:: Luma-Only Image Formats
+ :header-rows: 1
+diff --git a/Makefile b/Makefile
+index aec5cc0babf8c..f9badb79ae8f4 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 4
++SUBLEVEL = 5
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig
+index 5d91259ee7b53..11bbdc15c6e5e 100644
+--- a/arch/arm64/Kconfig
++++ b/arch/arm64/Kconfig
+@@ -1067,48 +1067,44 @@ config ARM64_ERRATUM_3117295
+
+ If unsure, say Y.
+
+-config ARM64_WORKAROUND_SPECULATIVE_SSBS
+- bool
+-
+ config ARM64_ERRATUM_3194386
+- bool "Cortex-X4: 3194386: workaround for MSR SSBS not self-synchronizing"
+- select ARM64_WORKAROUND_SPECULATIVE_SSBS
+- default y
+- help
+- This option adds the workaround for ARM Cortex-X4 erratum 3194386.
++ bool "Cortex-*/Neoverse-*: workaround for MSR SSBS not self-synchronizing"
++ default y
++ help
++ This option adds the workaround for the following errata:
++
++ * ARM Cortex-A76 erratum 3324349
++ * ARM Cortex-A77 erratum 3324348
++ * ARM Cortex-A78 erratum 3324344
++ * ARM Cortex-A78C erratum 3324346
++ * ARM Cortex-A78C erratum 3324347
++ * ARM Cortex-A710 erratam 3324338
++ * ARM Cortex-A720 erratum 3456091
++ * ARM Cortex-A725 erratum 3456106
++ * ARM Cortex-X1 erratum 3324344
++ * ARM Cortex-X1C erratum 3324346
++ * ARM Cortex-X2 erratum 3324338
++ * ARM Cortex-X3 erratum 3324335
++ * ARM Cortex-X4 erratum 3194386
++ * ARM Cortex-X925 erratum 3324334
++ * ARM Neoverse-N1 erratum 3324349
++ * ARM Neoverse N2 erratum 3324339
++ * ARM Neoverse-V1 erratum 3324341
++ * ARM Neoverse V2 erratum 3324336
++ * ARM Neoverse-V3 erratum 3312417
+
+ On affected cores "MSR SSBS, #0" instructions may not affect
+ subsequent speculative instructions, which may permit unexepected
+ speculative store bypassing.
+
+- Work around this problem by placing a speculation barrier after
+- kernel changes to SSBS. The presence of the SSBS special-purpose
+- register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such
+- that userspace will use the PR_SPEC_STORE_BYPASS prctl to change
+- SSBS.
++ Work around this problem by placing a Speculation Barrier (SB) or
++ Instruction Synchronization Barrier (ISB) after kernel changes to
++ SSBS. The presence of the SSBS special-purpose register is hidden
++ from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such that userspace
++ will use the PR_SPEC_STORE_BYPASS prctl to change SSBS.
+
+ If unsure, say Y.
+
+-config ARM64_ERRATUM_3312417
+- bool "Neoverse-V3: 3312417: workaround for MSR SSBS not self-synchronizing"
+- select ARM64_WORKAROUND_SPECULATIVE_SSBS
+- default y
+- help
+- This option adds the workaround for ARM Neoverse-V3 erratum 3312417.
+-
+- On affected cores "MSR SSBS, #0" instructions may not affect
+- subsequent speculative instructions, which may permit unexepected
+- speculative store bypassing.
+-
+- Work around this problem by placing a speculation barrier after
+- kernel changes to SSBS. The presence of the SSBS special-purpose
+- register is hidden from hwcaps and EL0 reads of ID_AA64PFR1_EL1, such
+- that userspace will use the PR_SPEC_STORE_BYPASS prctl to change
+- SSBS.
+-
+- If unsure, say Y.
+-
+-
+ config CAVIUM_ERRATUM_22375
+ bool "Cavium erratum 22375, 24313"
+ default y
+diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
+index e8f4d136e5dfb..9202181fbd652 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-am62-verdin-dahlia.dtsi
+@@ -43,15 +43,6 @@ simple-audio-card,cpu {
+ sound-dai = <&mcasp0>;
+ };
+ };
+-
+- reg_usb_hub: regulator-usb-hub {
+- compatible = "regulator-fixed";
+- enable-active-high;
+- /* Verdin CTRL_SLEEP_MOCI# (SODIMM 256) */
+- gpio = <&main_gpio0 31 GPIO_ACTIVE_HIGH>;
+- regulator-boot-on;
+- regulator-name = "HUB_PWR_EN";
+- };
+ };
+
+ /* Verdin ETHs */
+@@ -193,11 +184,6 @@ &ospi0 {
+ status = "okay";
+ };
+
+-/* Do not force CTRL_SLEEP_MOCI# always enabled */
+-®_force_sleep_moci {
+- status = "disabled";
+-};
+-
+ /* Verdin SD_1 */
+ &sdhci1 {
+ status = "okay";
+@@ -218,15 +204,7 @@ &usbss1 {
+ };
+
+ &usb1 {
+- #address-cells = <1>;
+- #size-cells = <0>;
+ status = "okay";
+-
+- usb-hub@1 {
+- compatible = "usb424,2744";
+- reg = <1>;
+- vdd-supply = <®_usb_hub>;
+- };
+ };
+
+ /* Verdin CTRL_WAKE1_MICO# */
+diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
+index 359f53f3e019b..5bef31b8577be 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
+@@ -138,12 +138,6 @@ reg_1v8_eth: regulator-1v8-eth {
+ vin-supply = <®_1v8>;
+ };
+
+- /*
+- * By default we enable CTRL_SLEEP_MOCI#, this is required to have
+- * peripherals on the carrier board powered.
+- * If more granularity or power saving is required this can be disabled
+- * in the carrier board device tree files.
+- */
+ reg_force_sleep_moci: regulator-force-sleep-moci {
+ compatible = "regulator-fixed";
+ enable-active-high;
+diff --git a/arch/arm64/include/asm/cpucaps.h b/arch/arm64/include/asm/cpucaps.h
+index 7529c02639332..a6e5b07b64fd5 100644
+--- a/arch/arm64/include/asm/cpucaps.h
++++ b/arch/arm64/include/asm/cpucaps.h
+@@ -59,7 +59,7 @@ cpucap_is_possible(const unsigned int cap)
+ case ARM64_WORKAROUND_REPEAT_TLBI:
+ return IS_ENABLED(CONFIG_ARM64_WORKAROUND_REPEAT_TLBI);
+ case ARM64_WORKAROUND_SPECULATIVE_SSBS:
+- return IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS);
++ return IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386);
+ }
+
+ return true;
+diff --git a/arch/arm64/include/asm/cputype.h b/arch/arm64/include/asm/cputype.h
+index 7b32b99023a21..5fd7caea44193 100644
+--- a/arch/arm64/include/asm/cputype.h
++++ b/arch/arm64/include/asm/cputype.h
+@@ -86,9 +86,14 @@
+ #define ARM_CPU_PART_CORTEX_X2 0xD48
+ #define ARM_CPU_PART_NEOVERSE_N2 0xD49
+ #define ARM_CPU_PART_CORTEX_A78C 0xD4B
++#define ARM_CPU_PART_CORTEX_X1C 0xD4C
++#define ARM_CPU_PART_CORTEX_X3 0xD4E
+ #define ARM_CPU_PART_NEOVERSE_V2 0xD4F
++#define ARM_CPU_PART_CORTEX_A720 0xD81
+ #define ARM_CPU_PART_CORTEX_X4 0xD82
+ #define ARM_CPU_PART_NEOVERSE_V3 0xD84
++#define ARM_CPU_PART_CORTEX_X925 0xD85
++#define ARM_CPU_PART_CORTEX_A725 0xD87
+
+ #define APM_CPU_PART_XGENE 0x000
+ #define APM_CPU_VAR_POTENZA 0x00
+@@ -162,9 +167,14 @@
+ #define MIDR_CORTEX_X2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X2)
+ #define MIDR_NEOVERSE_N2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_N2)
+ #define MIDR_CORTEX_A78C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A78C)
++#define MIDR_CORTEX_X1C MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X1C)
++#define MIDR_CORTEX_X3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X3)
+ #define MIDR_NEOVERSE_V2 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V2)
++#define MIDR_CORTEX_A720 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A720)
+ #define MIDR_CORTEX_X4 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X4)
+ #define MIDR_NEOVERSE_V3 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_NEOVERSE_V3)
++#define MIDR_CORTEX_X925 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_X925)
++#define MIDR_CORTEX_A725 MIDR_CPU_MODEL(ARM_CPU_IMP_ARM, ARM_CPU_PART_CORTEX_A725)
+ #define MIDR_THUNDERX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX)
+ #define MIDR_THUNDERX_81XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_81XX)
+ #define MIDR_THUNDERX_83XX MIDR_CPU_MODEL(ARM_CPU_IMP_CAVIUM, CAVIUM_CPU_PART_THUNDERX_83XX)
+diff --git a/arch/arm64/kernel/cpu_errata.c b/arch/arm64/kernel/cpu_errata.c
+index 828be635e7e1d..f6b6b45073571 100644
+--- a/arch/arm64/kernel/cpu_errata.c
++++ b/arch/arm64/kernel/cpu_errata.c
+@@ -432,14 +432,26 @@ static const struct midr_range erratum_spec_unpriv_load_list[] = {
+ };
+ #endif
+
+-#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS
+-static const struct midr_range erratum_spec_ssbs_list[] = {
+ #ifdef CONFIG_ARM64_ERRATUM_3194386
++static const struct midr_range erratum_spec_ssbs_list[] = {
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_A76),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_A77),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_A78),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_A78C),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_A710),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_A720),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_A725),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_X1),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_X1C),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_X2),
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_X3),
+ MIDR_ALL_VERSIONS(MIDR_CORTEX_X4),
+-#endif
+-#ifdef CONFIG_ARM64_ERRATUM_3312417
++ MIDR_ALL_VERSIONS(MIDR_CORTEX_X925),
++ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N1),
++ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_N2),
++ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V1),
++ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V2),
+ MIDR_ALL_VERSIONS(MIDR_NEOVERSE_V3),
+-#endif
+ {}
+ };
+ #endif
+@@ -741,9 +753,9 @@ const struct arm64_cpu_capabilities arm64_errata[] = {
+ MIDR_FIXED(MIDR_CPU_VAR_REV(1,1), BIT(25)),
+ },
+ #endif
+-#ifdef CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS
++#ifdef CONFIG_ARM64_ERRATUM_3194386
+ {
+- .desc = "ARM errata 3194386, 3312417",
++ .desc = "SSBS not fully self-synchronizing",
+ .capability = ARM64_WORKAROUND_SPECULATIVE_SSBS,
+ ERRATA_MIDR_RANGE_LIST(erratum_spec_ssbs_list),
+ },
+diff --git a/arch/arm64/kernel/proton-pack.c b/arch/arm64/kernel/proton-pack.c
+index baca47bd443c8..da53722f95d41 100644
+--- a/arch/arm64/kernel/proton-pack.c
++++ b/arch/arm64/kernel/proton-pack.c
+@@ -567,7 +567,7 @@ static enum mitigation_state spectre_v4_enable_hw_mitigation(void)
+ * Mitigate this with an unconditional speculation barrier, as CPUs
+ * could mis-speculate branches and bypass a conditional barrier.
+ */
+- if (IS_ENABLED(CONFIG_ARM64_WORKAROUND_SPECULATIVE_SSBS))
++ if (IS_ENABLED(CONFIG_ARM64_ERRATUM_3194386))
+ spec_bar();
+
+ return SPECTRE_MITIGATED;
+diff --git a/arch/loongarch/kernel/efi.c b/arch/loongarch/kernel/efi.c
+index 000825406c1f6..2bf86aeda874c 100644
+--- a/arch/loongarch/kernel/efi.c
++++ b/arch/loongarch/kernel/efi.c
+@@ -66,6 +66,12 @@ void __init efi_runtime_init(void)
+ set_bit(EFI_RUNTIME_SERVICES, &efi.flags);
+ }
+
++bool efi_poweroff_required(void)
++{
++ return efi_enabled(EFI_RUNTIME_SERVICES) &&
++ (acpi_gbl_reduced_hardware || acpi_no_s5);
++}
++
+ unsigned long __initdata screen_info_table = EFI_INVALID_TABLE_ADDR;
+
+ #if defined(CONFIG_SYSFB) || defined(CONFIG_EFI_EARLYCON)
+diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
+index 9656e956ed135..4ecfa08ac3e1f 100644
+--- a/arch/parisc/Kconfig
++++ b/arch/parisc/Kconfig
+@@ -20,6 +20,7 @@ config PARISC
+ select ARCH_SUPPORTS_HUGETLBFS if PA20
+ select ARCH_SUPPORTS_MEMORY_FAILURE
+ select ARCH_STACKWALK
++ select ARCH_HAS_CACHE_LINE_SIZE
+ select ARCH_HAS_DEBUG_VM_PGTABLE
+ select HAVE_RELIABLE_STACKTRACE
+ select DMA_OPS
+diff --git a/arch/parisc/include/asm/cache.h b/arch/parisc/include/asm/cache.h
+index 2a60d7a72f1fa..a3f0f100f2194 100644
+--- a/arch/parisc/include/asm/cache.h
++++ b/arch/parisc/include/asm/cache.h
+@@ -20,7 +20,16 @@
+
+ #define SMP_CACHE_BYTES L1_CACHE_BYTES
+
+-#define ARCH_DMA_MINALIGN L1_CACHE_BYTES
++#ifdef CONFIG_PA20
++#define ARCH_DMA_MINALIGN 128
++#else
++#define ARCH_DMA_MINALIGN 32
++#endif
++#define ARCH_KMALLOC_MINALIGN 16 /* ldcw requires 16-byte alignment */
++
++#define arch_slab_minalign() ((unsigned)dcache_stride)
++#define cache_line_size() dcache_stride
++#define dma_get_cache_alignment cache_line_size
+
+ #define __read_mostly __section(".data..read_mostly")
+
+diff --git a/arch/parisc/net/bpf_jit_core.c b/arch/parisc/net/bpf_jit_core.c
+index 979f45d4d1fbe..06cbcd6fe87b8 100644
+--- a/arch/parisc/net/bpf_jit_core.c
++++ b/arch/parisc/net/bpf_jit_core.c
+@@ -114,7 +114,7 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog)
+ jit_data->header =
+ bpf_jit_binary_alloc(prog_size + extable_size,
+ &jit_data->image,
+- sizeof(u32),
++ sizeof(long),
+ bpf_fill_ill_insns);
+ if (!jit_data->header) {
+ prog = orig_prog;
+diff --git a/arch/x86/events/amd/core.c b/arch/x86/events/amd/core.c
+index 1fc4ce44e743c..920e3a640cadd 100644
+--- a/arch/x86/events/amd/core.c
++++ b/arch/x86/events/amd/core.c
+@@ -432,8 +432,10 @@ static void __amd_put_nb_event_constraints(struct cpu_hw_events *cpuc,
+ * be removed on one CPU at a time AND PMU is disabled
+ * when we come here
+ */
+- for (i = 0; i < x86_pmu.num_counters; i++) {
+- if (cmpxchg(nb->owners + i, event, NULL) == event)
++ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
++ struct perf_event *tmp = event;
++
++ if (try_cmpxchg(nb->owners + i, &tmp, NULL))
+ break;
+ }
+ }
+@@ -499,7 +501,7 @@ __amd_get_nb_event_constraints(struct cpu_hw_events *cpuc, struct perf_event *ev
+ * because of successive calls to x86_schedule_events() from
+ * hw_perf_group_sched_in() without hw_perf_enable()
+ */
+- for_each_set_bit(idx, c->idxmsk, x86_pmu.num_counters) {
++ for_each_set_bit(idx, c->idxmsk, x86_pmu_max_num_counters(NULL)) {
+ if (new == -1 || hwc->idx == idx)
+ /* assign free slot, prefer hwc->idx */
+ old = cmpxchg(nb->owners + idx, NULL, event);
+@@ -542,7 +544,7 @@ static struct amd_nb *amd_alloc_nb(int cpu)
+ /*
+ * initialize all possible NB constraints
+ */
+- for (i = 0; i < x86_pmu.num_counters; i++) {
++ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ __set_bit(i, nb->event_constraints[i].idxmsk);
+ nb->event_constraints[i].weight = 1;
+ }
+@@ -735,7 +737,7 @@ static void amd_pmu_check_overflow(void)
+ * counters are always enabled when this function is called and
+ * ARCH_PERFMON_EVENTSEL_INT is always set.
+ */
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+@@ -755,7 +757,7 @@ static void amd_pmu_enable_all(int added)
+
+ amd_brs_enable_all();
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ /* only activate events which are marked as active */
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+@@ -978,7 +980,7 @@ static int amd_pmu_v2_handle_irq(struct pt_regs *regs)
+ /* Clear any reserved bits set by buggy microcode */
+ status &= amd_pmu_global_cntr_mask;
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+@@ -1313,7 +1315,7 @@ static __initconst const struct x86_pmu amd_pmu = {
+ .addr_offset = amd_pmu_addr_offset,
+ .event_map = amd_pmu_event_map,
+ .max_events = ARRAY_SIZE(amd_perfmon_event_map),
+- .num_counters = AMD64_NUM_COUNTERS,
++ .cntr_mask64 = GENMASK_ULL(AMD64_NUM_COUNTERS - 1, 0),
+ .add = amd_pmu_add_event,
+ .del = amd_pmu_del_event,
+ .cntval_bits = 48,
+@@ -1412,7 +1414,7 @@ static int __init amd_core_pmu_init(void)
+ */
+ x86_pmu.eventsel = MSR_F15H_PERF_CTL;
+ x86_pmu.perfctr = MSR_F15H_PERF_CTR;
+- x86_pmu.num_counters = AMD64_NUM_COUNTERS_CORE;
++ x86_pmu.cntr_mask64 = GENMASK_ULL(AMD64_NUM_COUNTERS_CORE - 1, 0);
+
+ /* Check for Performance Monitoring v2 support */
+ if (boot_cpu_has(X86_FEATURE_PERFMON_V2)) {
+@@ -1422,9 +1424,9 @@ static int __init amd_core_pmu_init(void)
+ x86_pmu.version = 2;
+
+ /* Find the number of available Core PMCs */
+- x86_pmu.num_counters = ebx.split.num_core_pmc;
++ x86_pmu.cntr_mask64 = GENMASK_ULL(ebx.split.num_core_pmc - 1, 0);
+
+- amd_pmu_global_cntr_mask = (1ULL << x86_pmu.num_counters) - 1;
++ amd_pmu_global_cntr_mask = x86_pmu.cntr_mask64;
+
+ /* Update PMC handling functions */
+ x86_pmu.enable_all = amd_pmu_v2_enable_all;
+@@ -1452,12 +1454,12 @@ static int __init amd_core_pmu_init(void)
+ * even numbered counter that has a consecutive adjacent odd
+ * numbered counter following it.
+ */
+- for (i = 0; i < x86_pmu.num_counters - 1; i += 2)
++ for (i = 0; i < x86_pmu_max_num_counters(NULL) - 1; i += 2)
+ even_ctr_mask |= BIT_ULL(i);
+
+ pair_constraint = (struct event_constraint)
+ __EVENT_CONSTRAINT(0, even_ctr_mask, 0,
+- x86_pmu.num_counters / 2, 0,
++ x86_pmu_max_num_counters(NULL) / 2, 0,
+ PERF_X86_EVENT_PAIR);
+
+ x86_pmu.get_event_constraints = amd_get_event_constraints_f17h;
+diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
+index 5a4bfe9aea237..0bfde2ea5cb8c 100644
+--- a/arch/x86/events/amd/uncore.c
++++ b/arch/x86/events/amd/uncore.c
+@@ -162,7 +162,9 @@ static int amd_uncore_add(struct perf_event *event, int flags)
+ /* if not, take the first available counter */
+ hwc->idx = -1;
+ for (i = 0; i < pmu->num_counters; i++) {
+- if (cmpxchg(&ctx->events[i], NULL, event) == NULL) {
++ struct perf_event *tmp = NULL;
++
++ if (try_cmpxchg(&ctx->events[i], &tmp, event)) {
+ hwc->idx = i;
+ break;
+ }
+@@ -196,7 +198,9 @@ static void amd_uncore_del(struct perf_event *event, int flags)
+ event->pmu->stop(event, PERF_EF_UPDATE);
+
+ for (i = 0; i < pmu->num_counters; i++) {
+- if (cmpxchg(&ctx->events[i], event, NULL) == event)
++ struct perf_event *tmp = event;
++
++ if (try_cmpxchg(&ctx->events[i], &tmp, NULL))
+ break;
+ }
+
+diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
+index acd367c453341..83d12dd3f831a 100644
+--- a/arch/x86/events/core.c
++++ b/arch/x86/events/core.c
+@@ -189,29 +189,31 @@ static DEFINE_MUTEX(pmc_reserve_mutex);
+
+ #ifdef CONFIG_X86_LOCAL_APIC
+
+-static inline int get_possible_num_counters(void)
++static inline u64 get_possible_counter_mask(void)
+ {
+- int i, num_counters = x86_pmu.num_counters;
++ u64 cntr_mask = x86_pmu.cntr_mask64;
++ int i;
+
+ if (!is_hybrid())
+- return num_counters;
++ return cntr_mask;
+
+ for (i = 0; i < x86_pmu.num_hybrid_pmus; i++)
+- num_counters = max_t(int, num_counters, x86_pmu.hybrid_pmu[i].num_counters);
++ cntr_mask |= x86_pmu.hybrid_pmu[i].cntr_mask64;
+
+- return num_counters;
++ return cntr_mask;
+ }
+
+ static bool reserve_pmc_hardware(void)
+ {
+- int i, num_counters = get_possible_num_counters();
++ u64 cntr_mask = get_possible_counter_mask();
++ int i, end;
+
+- for (i = 0; i < num_counters; i++) {
++ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
+ if (!reserve_perfctr_nmi(x86_pmu_event_addr(i)))
+ goto perfctr_fail;
+ }
+
+- for (i = 0; i < num_counters; i++) {
++ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
+ if (!reserve_evntsel_nmi(x86_pmu_config_addr(i)))
+ goto eventsel_fail;
+ }
+@@ -219,13 +221,14 @@ static bool reserve_pmc_hardware(void)
+ return true;
+
+ eventsel_fail:
+- for (i--; i >= 0; i--)
++ end = i;
++ for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
+ release_evntsel_nmi(x86_pmu_config_addr(i));
+-
+- i = num_counters;
++ i = X86_PMC_IDX_MAX;
+
+ perfctr_fail:
+- for (i--; i >= 0; i--)
++ end = i;
++ for_each_set_bit(i, (unsigned long *)&cntr_mask, end)
+ release_perfctr_nmi(x86_pmu_event_addr(i));
+
+ return false;
+@@ -233,9 +236,10 @@ static bool reserve_pmc_hardware(void)
+
+ static void release_pmc_hardware(void)
+ {
+- int i, num_counters = get_possible_num_counters();
++ u64 cntr_mask = get_possible_counter_mask();
++ int i;
+
+- for (i = 0; i < num_counters; i++) {
++ for_each_set_bit(i, (unsigned long *)&cntr_mask, X86_PMC_IDX_MAX) {
+ release_perfctr_nmi(x86_pmu_event_addr(i));
+ release_evntsel_nmi(x86_pmu_config_addr(i));
+ }
+@@ -248,7 +252,8 @@ static void release_pmc_hardware(void) {}
+
+ #endif
+
+-bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
++bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
++ unsigned long *fixed_cntr_mask)
+ {
+ u64 val, val_fail = -1, val_new= ~0;
+ int i, reg, reg_fail = -1, ret = 0;
+@@ -259,7 +264,7 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
+ * Check to see if the BIOS enabled any of the counters, if so
+ * complain and bail.
+ */
+- for (i = 0; i < num_counters; i++) {
++ for_each_set_bit(i, cntr_mask, X86_PMC_IDX_MAX) {
+ reg = x86_pmu_config_addr(i);
+ ret = rdmsrl_safe(reg, &val);
+ if (ret)
+@@ -273,12 +278,12 @@ bool check_hw_exists(struct pmu *pmu, int num_counters, int num_counters_fixed)
+ }
+ }
+
+- if (num_counters_fixed) {
++ if (*(u64 *)fixed_cntr_mask) {
+ reg = MSR_ARCH_PERFMON_FIXED_CTR_CTRL;
+ ret = rdmsrl_safe(reg, &val);
+ if (ret)
+ goto msr_fail;
+- for (i = 0; i < num_counters_fixed; i++) {
++ for_each_set_bit(i, fixed_cntr_mask, X86_PMC_IDX_MAX) {
+ if (fixed_counter_disabled(i, pmu))
+ continue;
+ if (val & (0x03ULL << i*4)) {
+@@ -679,7 +684,7 @@ void x86_pmu_disable_all(void)
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
+ u64 val;
+
+@@ -736,7 +741,7 @@ void x86_pmu_enable_all(int added)
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
+
+ if (!test_bit(idx, cpuc->active_mask))
+@@ -975,7 +980,6 @@ EXPORT_SYMBOL_GPL(perf_assign_events);
+
+ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
+ {
+- int num_counters = hybrid(cpuc->pmu, num_counters);
+ struct event_constraint *c;
+ struct perf_event *e;
+ int n0, i, wmin, wmax, unsched = 0;
+@@ -1051,7 +1055,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
+
+ /* slow path */
+ if (i != n) {
+- int gpmax = num_counters;
++ int gpmax = x86_pmu_max_num_counters(cpuc->pmu);
+
+ /*
+ * Do not allow scheduling of more than half the available
+@@ -1072,7 +1076,7 @@ int x86_schedule_events(struct cpu_hw_events *cpuc, int n, int *assign)
+ * the extra Merge events needed by large increment events.
+ */
+ if (x86_pmu.flags & PMU_FL_PAIR) {
+- gpmax = num_counters - cpuc->n_pair;
++ gpmax -= cpuc->n_pair;
+ WARN_ON(gpmax <= 0);
+ }
+
+@@ -1157,12 +1161,10 @@ static int collect_event(struct cpu_hw_events *cpuc, struct perf_event *event,
+ */
+ static int collect_events(struct cpu_hw_events *cpuc, struct perf_event *leader, bool dogrp)
+ {
+- int num_counters = hybrid(cpuc->pmu, num_counters);
+- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+ struct perf_event *event;
+ int n, max_count;
+
+- max_count = num_counters + num_counters_fixed;
++ max_count = x86_pmu_num_counters(cpuc->pmu) + x86_pmu_num_counters_fixed(cpuc->pmu);
+
+ /* current number of events already accepted */
+ n = cpuc->n_events;
+@@ -1519,19 +1521,22 @@ static void x86_pmu_start(struct perf_event *event, int flags)
+ void perf_event_print_debug(void)
+ {
+ u64 ctrl, status, overflow, pmc_ctrl, pmc_count, prev_left, fixed;
++ unsigned long *cntr_mask, *fixed_cntr_mask;
++ struct event_constraint *pebs_constraints;
++ struct cpu_hw_events *cpuc;
+ u64 pebs, debugctl;
+- int cpu = smp_processor_id();
+- struct cpu_hw_events *cpuc = &per_cpu(cpu_hw_events, cpu);
+- int num_counters = hybrid(cpuc->pmu, num_counters);
+- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+- struct event_constraint *pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
+- unsigned long flags;
+- int idx;
++ int cpu, idx;
+
+- if (!num_counters)
+- return;
++ guard(irqsave)();
++
++ cpu = smp_processor_id();
++ cpuc = &per_cpu(cpu_hw_events, cpu);
++ cntr_mask = hybrid(cpuc->pmu, cntr_mask);
++ fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
++ pebs_constraints = hybrid(cpuc->pmu, pebs_constraints);
+
+- local_irq_save(flags);
++ if (!*(u64 *)cntr_mask)
++ return;
+
+ if (x86_pmu.version >= 2) {
+ rdmsrl(MSR_CORE_PERF_GLOBAL_CTRL, ctrl);
+@@ -1555,7 +1560,7 @@ void perf_event_print_debug(void)
+ }
+ pr_info("CPU#%d: active: %016llx\n", cpu, *(u64 *)cpuc->active_mask);
+
+- for (idx = 0; idx < num_counters; idx++) {
++ for_each_set_bit(idx, cntr_mask, X86_PMC_IDX_MAX) {
+ rdmsrl(x86_pmu_config_addr(idx), pmc_ctrl);
+ rdmsrl(x86_pmu_event_addr(idx), pmc_count);
+
+@@ -1568,7 +1573,7 @@ void perf_event_print_debug(void)
+ pr_info("CPU#%d: gen-PMC%d left: %016llx\n",
+ cpu, idx, prev_left);
+ }
+- for (idx = 0; idx < num_counters_fixed; idx++) {
++ for_each_set_bit(idx, fixed_cntr_mask, X86_PMC_IDX_MAX) {
+ if (fixed_counter_disabled(idx, cpuc->pmu))
+ continue;
+ rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
+@@ -1576,7 +1581,6 @@ void perf_event_print_debug(void)
+ pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
+ cpu, idx, pmc_count);
+ }
+- local_irq_restore(flags);
+ }
+
+ void x86_pmu_stop(struct perf_event *event, int flags)
+@@ -1682,7 +1686,7 @@ int x86_pmu_handle_irq(struct pt_regs *regs)
+ */
+ apic_write(APIC_LVTPC, APIC_DM_NMI);
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+
+@@ -2038,18 +2042,15 @@ static void _x86_pmu_read(struct perf_event *event)
+ static_call(x86_pmu_update)(event);
+ }
+
+-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
+- u64 intel_ctrl)
++void x86_pmu_show_pmu_cap(struct pmu *pmu)
+ {
+ pr_info("... version: %d\n", x86_pmu.version);
+ pr_info("... bit width: %d\n", x86_pmu.cntval_bits);
+- pr_info("... generic registers: %d\n", num_counters);
++ pr_info("... generic registers: %d\n", x86_pmu_num_counters(pmu));
+ pr_info("... value mask: %016Lx\n", x86_pmu.cntval_mask);
+ pr_info("... max period: %016Lx\n", x86_pmu.max_period);
+- pr_info("... fixed-purpose events: %lu\n",
+- hweight64((((1ULL << num_counters_fixed) - 1)
+- << INTEL_PMC_IDX_FIXED) & intel_ctrl));
+- pr_info("... event mask: %016Lx\n", intel_ctrl);
++ pr_info("... fixed-purpose events: %d\n", x86_pmu_num_counters_fixed(pmu));
++ pr_info("... event mask: %016Lx\n", hybrid(pmu, intel_ctrl));
+ }
+
+ static int __init init_hw_perf_events(void)
+@@ -2086,7 +2087,7 @@ static int __init init_hw_perf_events(void)
+ pmu_check_apic();
+
+ /* sanity check that the hardware exists or is emulated */
+- if (!check_hw_exists(&pmu, x86_pmu.num_counters, x86_pmu.num_counters_fixed))
++ if (!check_hw_exists(&pmu, x86_pmu.cntr_mask, x86_pmu.fixed_cntr_mask))
+ goto out_bad_pmu;
+
+ pr_cont("%s PMU driver.\n", x86_pmu.name);
+@@ -2097,14 +2098,14 @@ static int __init init_hw_perf_events(void)
+ quirk->func();
+
+ if (!x86_pmu.intel_ctrl)
+- x86_pmu.intel_ctrl = (1 << x86_pmu.num_counters) - 1;
++ x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
+
+ perf_events_lapic_init();
+ register_nmi_handler(NMI_LOCAL, perf_event_nmi_handler, 0, "PMI");
+
+ unconstrained = (struct event_constraint)
+- __EVENT_CONSTRAINT(0, (1ULL << x86_pmu.num_counters) - 1,
+- 0, x86_pmu.num_counters, 0, 0);
++ __EVENT_CONSTRAINT(0, x86_pmu.cntr_mask64,
++ 0, x86_pmu_num_counters(NULL), 0, 0);
+
+ x86_pmu_format_group.attrs = x86_pmu.format_attrs;
+
+@@ -2113,11 +2114,8 @@ static int __init init_hw_perf_events(void)
+
+ pmu.attr_update = x86_pmu.attr_update;
+
+- if (!is_hybrid()) {
+- x86_pmu_show_pmu_cap(x86_pmu.num_counters,
+- x86_pmu.num_counters_fixed,
+- x86_pmu.intel_ctrl);
+- }
++ if (!is_hybrid())
++ x86_pmu_show_pmu_cap(NULL);
+
+ if (!x86_pmu.read)
+ x86_pmu.read = _x86_pmu_read;
+@@ -2481,7 +2479,7 @@ void perf_clear_dirty_counters(void)
+ for_each_set_bit(i, cpuc->dirty, X86_PMC_IDX_MAX) {
+ if (i >= INTEL_PMC_IDX_FIXED) {
+ /* Metrics and fake events don't have corresponding HW counters. */
+- if ((i - INTEL_PMC_IDX_FIXED) >= hybrid(cpuc->pmu, num_counters_fixed))
++ if (!test_bit(i - INTEL_PMC_IDX_FIXED, hybrid(cpuc->pmu, fixed_cntr_mask)))
+ continue;
+
+ wrmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + (i - INTEL_PMC_IDX_FIXED), 0);
+@@ -2986,8 +2984,8 @@ void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap)
+ * base PMU holds the correct number of counters for P-cores.
+ */
+ cap->version = x86_pmu.version;
+- cap->num_counters_gp = x86_pmu.num_counters;
+- cap->num_counters_fixed = x86_pmu.num_counters_fixed;
++ cap->num_counters_gp = x86_pmu_num_counters(NULL);
++ cap->num_counters_fixed = x86_pmu_num_counters_fixed(NULL);
+ cap->bit_width_gp = x86_pmu.cntval_bits;
+ cap->bit_width_fixed = x86_pmu.cntval_bits;
+ cap->events_mask = (unsigned int)x86_pmu.events_maskl;
+diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
+index 101a21fe9c213..f25205d047e83 100644
+--- a/arch/x86/events/intel/core.c
++++ b/arch/x86/events/intel/core.c
+@@ -2874,23 +2874,23 @@ static void intel_pmu_reset(void)
+ {
+ struct debug_store *ds = __this_cpu_read(cpu_hw_events.ds);
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+- int num_counters = hybrid(cpuc->pmu, num_counters);
++ unsigned long *cntr_mask = hybrid(cpuc->pmu, cntr_mask);
++ unsigned long *fixed_cntr_mask = hybrid(cpuc->pmu, fixed_cntr_mask);
+ unsigned long flags;
+ int idx;
+
+- if (!num_counters)
++ if (!*(u64 *)cntr_mask)
+ return;
+
+ local_irq_save(flags);
+
+ pr_info("clearing PMU state on CPU#%d\n", smp_processor_id());
+
+- for (idx = 0; idx < num_counters; idx++) {
++ for_each_set_bit(idx, cntr_mask, INTEL_PMC_MAX_GENERIC) {
+ wrmsrl_safe(x86_pmu_config_addr(idx), 0ull);
+ wrmsrl_safe(x86_pmu_event_addr(idx), 0ull);
+ }
+- for (idx = 0; idx < num_counters_fixed; idx++) {
++ for_each_set_bit(idx, fixed_cntr_mask, INTEL_PMC_MAX_FIXED) {
+ if (fixed_counter_disabled(idx, cpuc->pmu))
+ continue;
+ wrmsrl_safe(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, 0ull);
+@@ -2940,8 +2940,7 @@ static void x86_pmu_handle_guest_pebs(struct pt_regs *regs,
+ !guest_pebs_idxs)
+ return;
+
+- for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs,
+- INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed) {
++ for_each_set_bit(bit, (unsigned long *)&guest_pebs_idxs, X86_PMC_IDX_MAX) {
+ event = cpuc->events[bit];
+ if (!event->attr.precise_ip)
+ continue;
+@@ -4199,7 +4198,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
+ struct perf_guest_switch_msr *arr = cpuc->guest_switch_msrs;
+ int idx;
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct perf_event *event = cpuc->events[idx];
+
+ arr[idx].msr = x86_pmu_config_addr(idx);
+@@ -4217,7 +4216,7 @@ static struct perf_guest_switch_msr *core_guest_get_msrs(int *nr, void *data)
+ arr[idx].guest &= ~ARCH_PERFMON_EVENTSEL_ENABLE;
+ }
+
+- *nr = x86_pmu.num_counters;
++ *nr = x86_pmu_max_num_counters(cpuc->pmu);
+ return arr;
+ }
+
+@@ -4232,7 +4231,7 @@ static void core_pmu_enable_all(int added)
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct hw_perf_event *hwc = &cpuc->events[idx]->hw;
+
+ if (!test_bit(idx, cpuc->active_mask) ||
+@@ -4684,13 +4683,33 @@ static void flip_smm_bit(void *data)
+ }
+ }
+
+-static void intel_pmu_check_num_counters(int *num_counters,
+- int *num_counters_fixed,
+- u64 *intel_ctrl, u64 fixed_mask);
++static void intel_pmu_check_counters_mask(u64 *cntr_mask,
++ u64 *fixed_cntr_mask,
++ u64 *intel_ctrl)
++{
++ unsigned int bit;
++
++ bit = fls64(*cntr_mask);
++ if (bit > INTEL_PMC_MAX_GENERIC) {
++ WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
++ bit, INTEL_PMC_MAX_GENERIC);
++ *cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_GENERIC - 1, 0);
++ }
++ *intel_ctrl = *cntr_mask;
++
++ bit = fls64(*fixed_cntr_mask);
++ if (bit > INTEL_PMC_MAX_FIXED) {
++ WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
++ bit, INTEL_PMC_MAX_FIXED);
++ *fixed_cntr_mask &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
++ }
++
++ *intel_ctrl |= *fixed_cntr_mask << INTEL_PMC_IDX_FIXED;
++}
+
+ static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
+- int num_counters,
+- int num_counters_fixed,
++ u64 cntr_mask,
++ u64 fixed_cntr_mask,
+ u64 intel_ctrl);
+
+ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
+@@ -4713,11 +4732,10 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
+ if (sub_bitmaps & ARCH_PERFMON_NUM_COUNTER_LEAF_BIT) {
+ cpuid_count(ARCH_PERFMON_EXT_LEAF, ARCH_PERFMON_NUM_COUNTER_LEAF,
+ &eax, &ebx, &ecx, &edx);
+- pmu->num_counters = fls(eax);
+- pmu->num_counters_fixed = fls(ebx);
++ pmu->cntr_mask64 = eax;
++ pmu->fixed_cntr_mask64 = ebx;
+ }
+
+-
+ if (!intel_pmu_broken_perf_cap()) {
+ /* Perf Metric (Bit 15) and PEBS via PT (Bit 16) are hybrid enumeration */
+ rdmsrl(MSR_IA32_PERF_CAPABILITIES, pmu->intel_cap.capabilities);
+@@ -4726,12 +4744,12 @@ static void update_pmu_cap(struct x86_hybrid_pmu *pmu)
+
+ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
+ {
+- intel_pmu_check_num_counters(&pmu->num_counters, &pmu->num_counters_fixed,
+- &pmu->intel_ctrl, (1ULL << pmu->num_counters_fixed) - 1);
+- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
++ intel_pmu_check_counters_mask(&pmu->cntr_mask64, &pmu->fixed_cntr_mask64,
++ &pmu->intel_ctrl);
++ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
+ pmu->unconstrained = (struct event_constraint)
+- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
+- 0, pmu->num_counters, 0, 0);
++ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
++ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
+
+ if (pmu->intel_cap.perf_metrics)
+ pmu->intel_ctrl |= 1ULL << GLOBAL_CTRL_EN_PERF_METRICS;
+@@ -4744,8 +4762,8 @@ static void intel_pmu_check_hybrid_pmus(struct x86_hybrid_pmu *pmu)
+ pmu->pmu.capabilities &= ~PERF_PMU_CAP_AUX_OUTPUT;
+
+ intel_pmu_check_event_constraints(pmu->event_constraints,
+- pmu->num_counters,
+- pmu->num_counters_fixed,
++ pmu->cntr_mask64,
++ pmu->fixed_cntr_mask64,
+ pmu->intel_ctrl);
+
+ intel_pmu_check_extra_regs(pmu->extra_regs);
+@@ -4806,7 +4824,7 @@ static bool init_hybrid_pmu(int cpu)
+
+ intel_pmu_check_hybrid_pmus(pmu);
+
+- if (!check_hw_exists(&pmu->pmu, pmu->num_counters, pmu->num_counters_fixed))
++ if (!check_hw_exists(&pmu->pmu, pmu->cntr_mask, pmu->fixed_cntr_mask))
+ return false;
+
+ pr_info("%s PMU driver: ", pmu->name);
+@@ -4816,8 +4834,7 @@ static bool init_hybrid_pmu(int cpu)
+
+ pr_cont("\n");
+
+- x86_pmu_show_pmu_cap(pmu->num_counters, pmu->num_counters_fixed,
+- pmu->intel_ctrl);
++ x86_pmu_show_pmu_cap(&pmu->pmu);
+
+ end:
+ cpumask_set_cpu(cpu, &pmu->supported_cpus);
+@@ -5955,29 +5972,9 @@ static const struct attribute_group *hybrid_attr_update[] = {
+
+ static struct attribute *empty_attrs;
+
+-static void intel_pmu_check_num_counters(int *num_counters,
+- int *num_counters_fixed,
+- u64 *intel_ctrl, u64 fixed_mask)
+-{
+- if (*num_counters > INTEL_PMC_MAX_GENERIC) {
+- WARN(1, KERN_ERR "hw perf events %d > max(%d), clipping!",
+- *num_counters, INTEL_PMC_MAX_GENERIC);
+- *num_counters = INTEL_PMC_MAX_GENERIC;
+- }
+- *intel_ctrl = (1ULL << *num_counters) - 1;
+-
+- if (*num_counters_fixed > INTEL_PMC_MAX_FIXED) {
+- WARN(1, KERN_ERR "hw perf events fixed %d > max(%d), clipping!",
+- *num_counters_fixed, INTEL_PMC_MAX_FIXED);
+- *num_counters_fixed = INTEL_PMC_MAX_FIXED;
+- }
+-
+- *intel_ctrl |= fixed_mask << INTEL_PMC_IDX_FIXED;
+-}
+-
+ static void intel_pmu_check_event_constraints(struct event_constraint *event_constraints,
+- int num_counters,
+- int num_counters_fixed,
++ u64 cntr_mask,
++ u64 fixed_cntr_mask,
+ u64 intel_ctrl)
+ {
+ struct event_constraint *c;
+@@ -6014,10 +6011,9 @@ static void intel_pmu_check_event_constraints(struct event_constraint *event_con
+ * generic counters
+ */
+ if (!use_fixed_pseudo_encoding(c->code))
+- c->idxmsk64 |= (1ULL << num_counters) - 1;
++ c->idxmsk64 |= cntr_mask;
+ }
+- c->idxmsk64 &=
+- ~(~0ULL << (INTEL_PMC_IDX_FIXED + num_counters_fixed));
++ c->idxmsk64 &= cntr_mask | (fixed_cntr_mask << INTEL_PMC_IDX_FIXED);
+ c->weight = hweight64(c->idxmsk64);
+ }
+ }
+@@ -6068,12 +6064,12 @@ static __always_inline int intel_pmu_init_hybrid(enum hybrid_pmu_type pmus)
+ pmu->pmu_type = intel_hybrid_pmu_type_map[bit].id;
+ pmu->name = intel_hybrid_pmu_type_map[bit].name;
+
+- pmu->num_counters = x86_pmu.num_counters;
+- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
+- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
++ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
++ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
++ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
+ pmu->unconstrained = (struct event_constraint)
+- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
+- 0, pmu->num_counters, 0, 0);
++ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
++ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
+
+ pmu->intel_cap.capabilities = x86_pmu.intel_cap.capabilities;
+ if (pmu->pmu_type & hybrid_small) {
+@@ -6186,14 +6182,14 @@ __init int intel_pmu_init(void)
+ x86_pmu = intel_pmu;
+
+ x86_pmu.version = version;
+- x86_pmu.num_counters = eax.split.num_counters;
++ x86_pmu.cntr_mask64 = GENMASK_ULL(eax.split.num_counters - 1, 0);
+ x86_pmu.cntval_bits = eax.split.bit_width;
+ x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
+
+ x86_pmu.events_maskl = ebx.full;
+ x86_pmu.events_mask_len = eax.split.mask_length;
+
+- x86_pmu.max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, x86_pmu.num_counters);
++ x86_pmu.pebs_events_mask = intel_pmu_pebs_mask(x86_pmu.cntr_mask64);
+ x86_pmu.pebs_capable = PEBS_COUNTER_MASK;
+
+ /*
+@@ -6203,12 +6199,10 @@ __init int intel_pmu_init(void)
+ if (version > 1 && version < 5) {
+ int assume = 3 * !boot_cpu_has(X86_FEATURE_HYPERVISOR);
+
+- x86_pmu.num_counters_fixed =
+- max((int)edx.split.num_counters_fixed, assume);
+-
+- fixed_mask = (1L << x86_pmu.num_counters_fixed) - 1;
++ x86_pmu.fixed_cntr_mask64 =
++ GENMASK_ULL(max((int)edx.split.num_counters_fixed, assume) - 1, 0);
+ } else if (version >= 5)
+- x86_pmu.num_counters_fixed = fls(fixed_mask);
++ x86_pmu.fixed_cntr_mask64 = fixed_mask;
+
+ if (boot_cpu_has(X86_FEATURE_PDCM)) {
+ u64 capabilities;
+@@ -6807,11 +6801,13 @@ __init int intel_pmu_init(void)
+ pmu = &x86_pmu.hybrid_pmu[X86_HYBRID_PMU_CORE_IDX];
+ intel_pmu_init_glc(&pmu->pmu);
+ if (cpu_feature_enabled(X86_FEATURE_HYBRID_CPU)) {
+- pmu->num_counters = x86_pmu.num_counters + 2;
+- pmu->num_counters_fixed = x86_pmu.num_counters_fixed + 1;
++ pmu->cntr_mask64 <<= 2;
++ pmu->cntr_mask64 |= 0x3;
++ pmu->fixed_cntr_mask64 <<= 1;
++ pmu->fixed_cntr_mask64 |= 0x1;
+ } else {
+- pmu->num_counters = x86_pmu.num_counters;
+- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
++ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
++ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
+ }
+
+ /*
+@@ -6821,15 +6817,16 @@ __init int intel_pmu_init(void)
+ * mistakenly add extra counters for P-cores. Correct the number of
+ * counters here.
+ */
+- if ((pmu->num_counters > 8) || (pmu->num_counters_fixed > 4)) {
+- pmu->num_counters = x86_pmu.num_counters;
+- pmu->num_counters_fixed = x86_pmu.num_counters_fixed;
++ if ((x86_pmu_num_counters(&pmu->pmu) > 8) || (x86_pmu_num_counters_fixed(&pmu->pmu) > 4)) {
++ pmu->cntr_mask64 = x86_pmu.cntr_mask64;
++ pmu->fixed_cntr_mask64 = x86_pmu.fixed_cntr_mask64;
+ }
+
+- pmu->max_pebs_events = min_t(unsigned, MAX_PEBS_EVENTS, pmu->num_counters);
++ pmu->pebs_events_mask = intel_pmu_pebs_mask(pmu->cntr_mask64);
+ pmu->unconstrained = (struct event_constraint)
+- __EVENT_CONSTRAINT(0, (1ULL << pmu->num_counters) - 1,
+- 0, pmu->num_counters, 0, 0);
++ __EVENT_CONSTRAINT(0, pmu->cntr_mask64,
++ 0, x86_pmu_num_counters(&pmu->pmu), 0, 0);
++
+ pmu->extra_regs = intel_glc_extra_regs;
+
+ /* Initialize Atom core specific PerfMon capabilities.*/
+@@ -6896,9 +6893,9 @@ __init int intel_pmu_init(void)
+ * The constraints may be cut according to the CPUID enumeration
+ * by inserting the EVENT_CONSTRAINT_END.
+ */
+- if (x86_pmu.num_counters_fixed > INTEL_PMC_MAX_FIXED)
+- x86_pmu.num_counters_fixed = INTEL_PMC_MAX_FIXED;
+- intel_v5_gen_event_constraints[x86_pmu.num_counters_fixed].weight = -1;
++ if (fls64(x86_pmu.fixed_cntr_mask64) > INTEL_PMC_MAX_FIXED)
++ x86_pmu.fixed_cntr_mask64 &= GENMASK_ULL(INTEL_PMC_MAX_FIXED - 1, 0);
++ intel_v5_gen_event_constraints[fls64(x86_pmu.fixed_cntr_mask64)].weight = -1;
+ x86_pmu.event_constraints = intel_v5_gen_event_constraints;
+ pr_cont("generic architected perfmon, ");
+ name = "generic_arch_v5+";
+@@ -6925,18 +6922,17 @@ __init int intel_pmu_init(void)
+ x86_pmu.attr_update = hybrid_attr_update;
+ }
+
+- intel_pmu_check_num_counters(&x86_pmu.num_counters,
+- &x86_pmu.num_counters_fixed,
+- &x86_pmu.intel_ctrl,
+- (u64)fixed_mask);
++ intel_pmu_check_counters_mask(&x86_pmu.cntr_mask64,
++ &x86_pmu.fixed_cntr_mask64,
++ &x86_pmu.intel_ctrl);
+
+ /* AnyThread may be deprecated on arch perfmon v5 or later */
+ if (x86_pmu.intel_cap.anythread_deprecated)
+ x86_pmu.format_attrs = intel_arch_formats_attr;
+
+ intel_pmu_check_event_constraints(x86_pmu.event_constraints,
+- x86_pmu.num_counters,
+- x86_pmu.num_counters_fixed,
++ x86_pmu.cntr_mask64,
++ x86_pmu.fixed_cntr_mask64,
+ x86_pmu.intel_ctrl);
+ /*
+ * Access LBR MSR may cause #GP under certain circumstances.
+diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
+index dd18320558914..9f116dfc47284 100644
+--- a/arch/x86/events/intel/cstate.c
++++ b/arch/x86/events/intel/cstate.c
+@@ -41,7 +41,7 @@
+ * MSR_CORE_C1_RES: CORE C1 Residency Counter
+ * perf code: 0x00
+ * Available model: SLM,AMT,GLM,CNL,ICX,TNT,ADL,RPL
+- * MTL,SRF,GRR
++ * MTL,SRF,GRR,ARL,LNL
+ * Scope: Core (each processor core has a MSR)
+ * MSR_CORE_C3_RESIDENCY: CORE C3 Residency Counter
+ * perf code: 0x01
+@@ -53,30 +53,31 @@
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
+ * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
+- * GRR
++ * GRR,ARL,LNL
+ * Scope: Core
+ * MSR_CORE_C7_RESIDENCY: CORE C7 Residency Counter
+ * perf code: 0x03
+ * Available model: SNB,IVB,HSW,BDW,SKL,CNL,KBL,CML,
+- * ICL,TGL,RKL,ADL,RPL,MTL
++ * ICL,TGL,RKL,ADL,RPL,MTL,ARL,LNL
+ * Scope: Core
+ * MSR_PKG_C2_RESIDENCY: Package C2 Residency Counter.
+ * perf code: 0x00
+ * Available model: SNB,IVB,HSW,BDW,SKL,KNL,GLM,CNL,
+ * KBL,CML,ICL,ICX,TGL,TNT,RKL,ADL,
+- * RPL,SPR,MTL
++ * RPL,SPR,MTL,ARL,LNL,SRF
+ * Scope: Package (physical package)
+ * MSR_PKG_C3_RESIDENCY: Package C3 Residency Counter.
+ * perf code: 0x01
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,KNL,
+ * GLM,CNL,KBL,CML,ICL,TGL,TNT,RKL,
+- * ADL,RPL,MTL
++ * ADL,RPL,MTL,ARL,LNL
+ * Scope: Package (physical package)
+ * MSR_PKG_C6_RESIDENCY: Package C6 Residency Counter.
+ * perf code: 0x02
+ * Available model: SLM,AMT,NHM,WSM,SNB,IVB,HSW,BDW,
+ * SKL,KNL,GLM,CNL,KBL,CML,ICL,ICX,
+- * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF
++ * TGL,TNT,RKL,ADL,RPL,SPR,MTL,SRF,
++ * ARL,LNL
+ * Scope: Package (physical package)
+ * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
+ * perf code: 0x03
+@@ -86,7 +87,7 @@
+ * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
+ * perf code: 0x04
+ * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
+- * ADL,RPL,MTL
++ * ADL,RPL,MTL,ARL
+ * Scope: Package (physical package)
+ * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
+ * perf code: 0x05
+@@ -95,7 +96,7 @@
+ * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
+ * perf code: 0x06
+ * Available model: HSW ULT,KBL,GLM,CNL,CML,ICL,TGL,
+- * TNT,RKL,ADL,RPL,MTL
++ * TNT,RKL,ADL,RPL,MTL,ARL,LNL
+ * Scope: Package (physical package)
+ * MSR_MODULE_C6_RES_MS: Module C6 Residency Counter.
+ * perf code: 0x00
+@@ -640,6 +641,17 @@ static const struct cstate_model adl_cstates __initconst = {
+ BIT(PERF_CSTATE_PKG_C10_RES),
+ };
+
++static const struct cstate_model lnl_cstates __initconst = {
++ .core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
++ BIT(PERF_CSTATE_CORE_C6_RES) |
++ BIT(PERF_CSTATE_CORE_C7_RES),
++
++ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
++ BIT(PERF_CSTATE_PKG_C3_RES) |
++ BIT(PERF_CSTATE_PKG_C6_RES) |
++ BIT(PERF_CSTATE_PKG_C10_RES),
++};
++
+ static const struct cstate_model slm_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
+ BIT(PERF_CSTATE_CORE_C6_RES),
+@@ -681,7 +693,8 @@ static const struct cstate_model srf_cstates __initconst = {
+ .core_events = BIT(PERF_CSTATE_CORE_C1_RES) |
+ BIT(PERF_CSTATE_CORE_C6_RES),
+
+- .pkg_events = BIT(PERF_CSTATE_PKG_C6_RES),
++ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
++ BIT(PERF_CSTATE_PKG_C6_RES),
+
+ .module_events = BIT(PERF_CSTATE_MODULE_C6_RES),
+ };
+@@ -760,6 +773,10 @@ static const struct x86_cpu_id intel_cstates_match[] __initconst = {
+ X86_MATCH_VFM(INTEL_RAPTORLAKE_S, &adl_cstates),
+ X86_MATCH_VFM(INTEL_METEORLAKE, &adl_cstates),
+ X86_MATCH_VFM(INTEL_METEORLAKE_L, &adl_cstates),
++ X86_MATCH_VFM(INTEL_ARROWLAKE, &adl_cstates),
++ X86_MATCH_VFM(INTEL_ARROWLAKE_H, &adl_cstates),
++ X86_MATCH_VFM(INTEL_ARROWLAKE_U, &adl_cstates),
++ X86_MATCH_VFM(INTEL_LUNARLAKE_M, &lnl_cstates),
+ { },
+ };
+ MODULE_DEVICE_TABLE(x86cpu, intel_cstates_match);
+diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
+index 80a4f712217b7..9212053f6f1d6 100644
+--- a/arch/x86/events/intel/ds.c
++++ b/arch/x86/events/intel/ds.c
+@@ -1137,8 +1137,7 @@ void intel_pmu_pebs_sched_task(struct perf_event_pmu_context *pmu_ctx, bool sche
+ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
+ {
+ struct debug_store *ds = cpuc->ds;
+- int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
+- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
++ int max_pebs_events = intel_pmu_max_num_pebs(cpuc->pmu);
+ u64 threshold;
+ int reserved;
+
+@@ -1146,7 +1145,7 @@ static inline void pebs_update_threshold(struct cpu_hw_events *cpuc)
+ return;
+
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL)
+- reserved = max_pebs_events + num_counters_fixed;
++ reserved = max_pebs_events + x86_pmu_max_num_counters_fixed(cpuc->pmu);
+ else
+ reserved = max_pebs_events;
+
+@@ -2161,6 +2160,7 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
+ void *base, *at, *top;
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ short error[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
++ int max_pebs_events = intel_pmu_max_num_pebs(NULL);
+ int bit, i, size;
+ u64 mask;
+
+@@ -2172,11 +2172,11 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+- mask = (1ULL << x86_pmu.max_pebs_events) - 1;
+- size = x86_pmu.max_pebs_events;
++ mask = x86_pmu.pebs_events_mask;
++ size = max_pebs_events;
+ if (x86_pmu.flags & PMU_FL_PEBS_ALL) {
+- mask |= ((1ULL << x86_pmu.num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED;
+- size = INTEL_PMC_IDX_FIXED + x86_pmu.num_counters_fixed;
++ mask |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
++ size = INTEL_PMC_IDX_FIXED + x86_pmu_max_num_counters_fixed(NULL);
+ }
+
+ if (unlikely(base >= top)) {
+@@ -2212,8 +2212,9 @@ static void intel_pmu_drain_pebs_nhm(struct pt_regs *iregs, struct perf_sample_d
+ pebs_status = p->status = cpuc->pebs_enabled;
+
+ bit = find_first_bit((unsigned long *)&pebs_status,
+- x86_pmu.max_pebs_events);
+- if (bit >= x86_pmu.max_pebs_events)
++ max_pebs_events);
++
++ if (!(x86_pmu.pebs_events_mask & (1 << bit)))
+ continue;
+
+ /*
+@@ -2271,12 +2272,10 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
+ {
+ short counts[INTEL_PMC_IDX_FIXED + MAX_FIXED_PEBS_EVENTS] = {};
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+- int max_pebs_events = hybrid(cpuc->pmu, max_pebs_events);
+- int num_counters_fixed = hybrid(cpuc->pmu, num_counters_fixed);
+ struct debug_store *ds = cpuc->ds;
+ struct perf_event *event;
+ void *base, *at, *top;
+- int bit, size;
++ int bit;
+ u64 mask;
+
+ if (!x86_pmu.pebs_active)
+@@ -2287,12 +2286,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
+
+ ds->pebs_index = ds->pebs_buffer_base;
+
+- mask = ((1ULL << max_pebs_events) - 1) |
+- (((1ULL << num_counters_fixed) - 1) << INTEL_PMC_IDX_FIXED);
+- size = INTEL_PMC_IDX_FIXED + num_counters_fixed;
++ mask = hybrid(cpuc->pmu, pebs_events_mask) |
++ (hybrid(cpuc->pmu, fixed_cntr_mask64) << INTEL_PMC_IDX_FIXED);
+
+ if (unlikely(base >= top)) {
+- intel_pmu_pebs_event_update_no_drain(cpuc, size);
++ intel_pmu_pebs_event_update_no_drain(cpuc, X86_PMC_IDX_MAX);
+ return;
+ }
+
+@@ -2302,11 +2300,11 @@ static void intel_pmu_drain_pebs_icl(struct pt_regs *iregs, struct perf_sample_d
+ pebs_status = get_pebs_status(at) & cpuc->pebs_enabled;
+ pebs_status &= mask;
+
+- for_each_set_bit(bit, (unsigned long *)&pebs_status, size)
++ for_each_set_bit(bit, (unsigned long *)&pebs_status, X86_PMC_IDX_MAX)
+ counts[bit]++;
+ }
+
+- for_each_set_bit(bit, (unsigned long *)&mask, size) {
++ for_each_set_bit(bit, (unsigned long *)&mask, X86_PMC_IDX_MAX) {
+ if (counts[bit] == 0)
+ continue;
+
+diff --git a/arch/x86/events/intel/knc.c b/arch/x86/events/intel/knc.c
+index 618001c208e81..034a1f6a457c6 100644
+--- a/arch/x86/events/intel/knc.c
++++ b/arch/x86/events/intel/knc.c
+@@ -303,7 +303,7 @@ static const struct x86_pmu knc_pmu __initconst = {
+ .apic = 1,
+ .max_period = (1ULL << 39) - 1,
+ .version = 0,
+- .num_counters = 2,
++ .cntr_mask64 = 0x3,
+ .cntval_bits = 40,
+ .cntval_mask = (1ULL << 40) - 1,
+ .get_event_constraints = x86_get_event_constraints,
+diff --git a/arch/x86/events/intel/p4.c b/arch/x86/events/intel/p4.c
+index 35936188db01b..844bc4fc4724d 100644
+--- a/arch/x86/events/intel/p4.c
++++ b/arch/x86/events/intel/p4.c
+@@ -919,7 +919,7 @@ static void p4_pmu_disable_all(void)
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct perf_event *event = cpuc->events[idx];
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+@@ -998,7 +998,7 @@ static void p4_pmu_enable_all(int added)
+ struct cpu_hw_events *cpuc = this_cpu_ptr(&cpu_hw_events);
+ int idx;
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ struct perf_event *event = cpuc->events[idx];
+ if (!test_bit(idx, cpuc->active_mask))
+ continue;
+@@ -1040,7 +1040,7 @@ static int p4_pmu_handle_irq(struct pt_regs *regs)
+
+ cpuc = this_cpu_ptr(&cpu_hw_events);
+
+- for (idx = 0; idx < x86_pmu.num_counters; idx++) {
++ for_each_set_bit(idx, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ int overflow;
+
+ if (!test_bit(idx, cpuc->active_mask)) {
+@@ -1353,7 +1353,7 @@ static __initconst const struct x86_pmu p4_pmu = {
+ * though leave it restricted at moment assuming
+ * HT is on
+ */
+- .num_counters = ARCH_P4_MAX_CCCR,
++ .cntr_mask64 = GENMASK_ULL(ARCH_P4_MAX_CCCR - 1, 0),
+ .apic = 1,
+ .cntval_bits = ARCH_P4_CNTRVAL_BITS,
+ .cntval_mask = ARCH_P4_CNTRVAL_MASK,
+@@ -1395,7 +1395,7 @@ __init int p4_pmu_init(void)
+ *
+ * Solve this by zero'ing out the registers to mimic a reset.
+ */
+- for (i = 0; i < x86_pmu.num_counters; i++) {
++ for_each_set_bit(i, x86_pmu.cntr_mask, X86_PMC_IDX_MAX) {
+ reg = x86_pmu_config_addr(i);
+ wrmsrl_safe(reg, 0ULL);
+ }
+diff --git a/arch/x86/events/intel/p6.c b/arch/x86/events/intel/p6.c
+index 408879b0c0d4e..a6cffb4f4ef52 100644
+--- a/arch/x86/events/intel/p6.c
++++ b/arch/x86/events/intel/p6.c
+@@ -214,7 +214,7 @@ static __initconst const struct x86_pmu p6_pmu = {
+ .apic = 1,
+ .max_period = (1ULL << 31) - 1,
+ .version = 0,
+- .num_counters = 2,
++ .cntr_mask64 = 0x3,
+ /*
+ * Events have 40 bits implemented. However they are designed such
+ * that bits [32-39] are sign extensions of bit 31. As such the
+diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
+index 72b022a1e16c5..745c174fc8809 100644
+--- a/arch/x86/events/perf_event.h
++++ b/arch/x86/events/perf_event.h
+@@ -684,9 +684,15 @@ struct x86_hybrid_pmu {
+ cpumask_t supported_cpus;
+ union perf_capabilities intel_cap;
+ u64 intel_ctrl;
+- int max_pebs_events;
+- int num_counters;
+- int num_counters_fixed;
++ u64 pebs_events_mask;
++ union {
++ u64 cntr_mask64;
++ unsigned long cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
++ };
++ union {
++ u64 fixed_cntr_mask64;
++ unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
++ };
+ struct event_constraint unconstrained;
+
+ u64 hw_cache_event_ids
+@@ -774,8 +780,14 @@ struct x86_pmu {
+ int (*rdpmc_index)(int index);
+ u64 (*event_map)(int);
+ int max_events;
+- int num_counters;
+- int num_counters_fixed;
++ union {
++ u64 cntr_mask64;
++ unsigned long cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
++ };
++ union {
++ u64 fixed_cntr_mask64;
++ unsigned long fixed_cntr_mask[BITS_TO_LONGS(X86_PMC_IDX_MAX)];
++ };
+ int cntval_bits;
+ u64 cntval_mask;
+ union {
+@@ -852,7 +864,7 @@ struct x86_pmu {
+ pebs_ept :1;
+ int pebs_record_size;
+ int pebs_buffer_size;
+- int max_pebs_events;
++ u64 pebs_events_mask;
+ void (*drain_pebs)(struct pt_regs *regs, struct perf_sample_data *data);
+ struct event_constraint *pebs_constraints;
+ void (*pebs_aliases)(struct perf_event *event);
+@@ -1125,8 +1137,8 @@ static inline int x86_pmu_rdpmc_index(int index)
+ return x86_pmu.rdpmc_index ? x86_pmu.rdpmc_index(index) : index;
+ }
+
+-bool check_hw_exists(struct pmu *pmu, int num_counters,
+- int num_counters_fixed);
++bool check_hw_exists(struct pmu *pmu, unsigned long *cntr_mask,
++ unsigned long *fixed_cntr_mask);
+
+ int x86_add_exclusive(unsigned int what);
+
+@@ -1197,8 +1209,27 @@ void x86_pmu_enable_event(struct perf_event *event);
+
+ int x86_pmu_handle_irq(struct pt_regs *regs);
+
+-void x86_pmu_show_pmu_cap(int num_counters, int num_counters_fixed,
+- u64 intel_ctrl);
++void x86_pmu_show_pmu_cap(struct pmu *pmu);
++
++static inline int x86_pmu_num_counters(struct pmu *pmu)
++{
++ return hweight64(hybrid(pmu, cntr_mask64));
++}
++
++static inline int x86_pmu_max_num_counters(struct pmu *pmu)
++{
++ return fls64(hybrid(pmu, cntr_mask64));
++}
++
++static inline int x86_pmu_num_counters_fixed(struct pmu *pmu)
++{
++ return hweight64(hybrid(pmu, fixed_cntr_mask64));
++}
++
++static inline int x86_pmu_max_num_counters_fixed(struct pmu *pmu)
++{
++ return fls64(hybrid(pmu, fixed_cntr_mask64));
++}
+
+ extern struct event_constraint emptyconstraint;
+
+@@ -1661,6 +1692,17 @@ static inline int is_ht_workaround_enabled(void)
+ return !!(x86_pmu.flags & PMU_FL_EXCL_ENABLED);
+ }
+
++static inline u64 intel_pmu_pebs_mask(u64 cntr_mask)
++{
++ return MAX_PEBS_EVENTS_MASK & cntr_mask;
++}
++
++static inline int intel_pmu_max_num_pebs(struct pmu *pmu)
++{
++ static_assert(MAX_PEBS_EVENTS == 32);
++ return fls((u32)hybrid(pmu, pebs_events_mask));
++}
++
+ #else /* CONFIG_CPU_SUP_INTEL */
+
+ static inline void reserve_ds_buffers(void)
+diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
+index 3e9acdaeed1ec..2fd9b0cf9a5e5 100644
+--- a/arch/x86/events/zhaoxin/core.c
++++ b/arch/x86/events/zhaoxin/core.c
+@@ -530,13 +530,13 @@ __init int zhaoxin_pmu_init(void)
+ pr_info("Version check pass!\n");
+
+ x86_pmu.version = version;
+- x86_pmu.num_counters = eax.split.num_counters;
++ x86_pmu.cntr_mask64 = GENMASK_ULL(eax.split.num_counters - 1, 0);
+ x86_pmu.cntval_bits = eax.split.bit_width;
+ x86_pmu.cntval_mask = (1ULL << eax.split.bit_width) - 1;
+ x86_pmu.events_maskl = ebx.full;
+ x86_pmu.events_mask_len = eax.split.mask_length;
+
+- x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
++ x86_pmu.fixed_cntr_mask64 = GENMASK_ULL(edx.split.num_counters_fixed - 1, 0);
+ x86_add_quirk(zhaoxin_arch_events_quirk);
+
+ switch (boot_cpu_data.x86) {
+@@ -604,13 +604,13 @@ __init int zhaoxin_pmu_init(void)
+ return -ENODEV;
+ }
+
+- x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
+- x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
++ x86_pmu.intel_ctrl = x86_pmu.cntr_mask64;
++ x86_pmu.intel_ctrl |= x86_pmu.fixed_cntr_mask64 << INTEL_PMC_IDX_FIXED;
+
+ if (x86_pmu.event_constraints) {
+ for_each_event_constraint(c, x86_pmu.event_constraints) {
+- c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+- c->weight += x86_pmu.num_counters;
++ c->idxmsk64 |= x86_pmu.cntr_mask64;
++ c->weight += x86_pmu_num_counters(NULL);
+ }
+ }
+
+diff --git a/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
+index 2f9eeb5c3069a..5dbeac48a5b93 100644
+--- a/arch/x86/include/asm/intel_ds.h
++++ b/arch/x86/include/asm/intel_ds.h
+@@ -9,6 +9,7 @@
+ /* The maximal number of PEBS events: */
+ #define MAX_PEBS_EVENTS_FMT4 8
+ #define MAX_PEBS_EVENTS 32
++#define MAX_PEBS_EVENTS_MASK GENMASK_ULL(MAX_PEBS_EVENTS - 1, 0)
+ #define MAX_FIXED_PEBS_EVENTS 16
+
+ /*
+diff --git a/arch/x86/include/asm/qspinlock.h b/arch/x86/include/asm/qspinlock.h
+index a053c12939751..68da67df304d5 100644
+--- a/arch/x86/include/asm/qspinlock.h
++++ b/arch/x86/include/asm/qspinlock.h
+@@ -66,13 +66,15 @@ static inline bool vcpu_is_preempted(long cpu)
+
+ #ifdef CONFIG_PARAVIRT
+ /*
+- * virt_spin_lock_key - enables (by default) the virt_spin_lock() hijack.
++ * virt_spin_lock_key - disables by default the virt_spin_lock() hijack.
+ *
+- * Native (and PV wanting native due to vCPU pinning) should disable this key.
+- * It is done in this backwards fashion to only have a single direction change,
+- * which removes ordering between native_pv_spin_init() and HV setup.
++ * Native (and PV wanting native due to vCPU pinning) should keep this key
++ * disabled. Native does not touch the key.
++ *
++ * When in a guest then native_pv_lock_init() enables the key first and
++ * KVM/XEN might conditionally disable it later in the boot process again.
+ */
+-DECLARE_STATIC_KEY_TRUE(virt_spin_lock_key);
++DECLARE_STATIC_KEY_FALSE(virt_spin_lock_key);
+
+ /*
+ * Shortcut for the queued_spin_lock_slowpath() function that allows
+diff --git a/arch/x86/kernel/cpu/mtrr/mtrr.c b/arch/x86/kernel/cpu/mtrr/mtrr.c
+index 767bf1c71aadd..2a2fc14955cd3 100644
+--- a/arch/x86/kernel/cpu/mtrr/mtrr.c
++++ b/arch/x86/kernel/cpu/mtrr/mtrr.c
+@@ -609,7 +609,7 @@ void mtrr_save_state(void)
+ {
+ int first_cpu;
+
+- if (!mtrr_enabled())
++ if (!mtrr_enabled() || !mtrr_state.have_fixed)
+ return;
+
+ first_cpu = cpumask_first(cpu_online_mask);
+diff --git a/arch/x86/kernel/paravirt.c b/arch/x86/kernel/paravirt.c
+index 5358d43886adc..fec3815335558 100644
+--- a/arch/x86/kernel/paravirt.c
++++ b/arch/x86/kernel/paravirt.c
+@@ -51,13 +51,12 @@ DEFINE_ASM_FUNC(pv_native_irq_enable, "sti", .noinstr.text);
+ DEFINE_ASM_FUNC(pv_native_read_cr2, "mov %cr2, %rax", .noinstr.text);
+ #endif
+
+-DEFINE_STATIC_KEY_TRUE(virt_spin_lock_key);
++DEFINE_STATIC_KEY_FALSE(virt_spin_lock_key);
+
+ void __init native_pv_lock_init(void)
+ {
+- if (IS_ENABLED(CONFIG_PARAVIRT_SPINLOCKS) &&
+- !boot_cpu_has(X86_FEATURE_HYPERVISOR))
+- static_branch_disable(&virt_spin_lock_key);
++ if (boot_cpu_has(X86_FEATURE_HYPERVISOR))
++ static_branch_enable(&virt_spin_lock_key);
+ }
+
+ static void native_tlb_remove_table(struct mmu_gather *tlb, void *table)
+diff --git a/arch/x86/mm/pti.c b/arch/x86/mm/pti.c
+index 2e69abf4f852a..bfdf5f45b1370 100644
+--- a/arch/x86/mm/pti.c
++++ b/arch/x86/mm/pti.c
+@@ -374,14 +374,14 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
+ */
+ *target_pmd = *pmd;
+
+- addr += PMD_SIZE;
++ addr = round_up(addr + 1, PMD_SIZE);
+
+ } else if (level == PTI_CLONE_PTE) {
+
+ /* Walk the page-table down to the pte level */
+ pte = pte_offset_kernel(pmd, addr);
+ if (pte_none(*pte)) {
+- addr += PAGE_SIZE;
++ addr = round_up(addr + 1, PAGE_SIZE);
+ continue;
+ }
+
+@@ -401,7 +401,7 @@ pti_clone_pgtable(unsigned long start, unsigned long end,
+ /* Clone the PTE */
+ *target_pte = *pte;
+
+- addr += PAGE_SIZE;
++ addr = round_up(addr + 1, PAGE_SIZE);
+
+ } else {
+ BUG();
+@@ -496,7 +496,7 @@ static void pti_clone_entry_text(void)
+ {
+ pti_clone_pgtable((unsigned long) __entry_text_start,
+ (unsigned long) __entry_text_end,
+- PTI_CLONE_PMD);
++ PTI_LEVEL_KERNEL_IMAGE);
+ }
+
+ /*
+diff --git a/drivers/acpi/battery.c b/drivers/acpi/battery.c
+index b379401ff1c20..44ca989f16466 100644
+--- a/drivers/acpi/battery.c
++++ b/drivers/acpi/battery.c
+@@ -678,12 +678,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev,
+ return count;
+ }
+
+-static const struct device_attribute alarm_attr = {
++static struct device_attribute alarm_attr = {
+ .attr = {.name = "alarm", .mode = 0644},
+ .show = acpi_battery_alarm_show,
+ .store = acpi_battery_alarm_store,
+ };
+
++static struct attribute *acpi_battery_attrs[] = {
++ &alarm_attr.attr,
++ NULL
++};
++ATTRIBUTE_GROUPS(acpi_battery);
++
+ /*
+ * The Battery Hooking API
+ *
+@@ -823,7 +829,10 @@ static void __exit battery_hook_exit(void)
+
+ static int sysfs_add_battery(struct acpi_battery *battery)
+ {
+- struct power_supply_config psy_cfg = { .drv_data = battery, };
++ struct power_supply_config psy_cfg = {
++ .drv_data = battery,
++ .attr_grp = acpi_battery_groups,
++ };
+ bool full_cap_broken = false;
+
+ if (!ACPI_BATTERY_CAPACITY_VALID(battery->full_charge_capacity) &&
+@@ -868,7 +877,7 @@ static int sysfs_add_battery(struct acpi_battery *battery)
+ return result;
+ }
+ battery_hook_add_battery(battery);
+- return device_create_file(&battery->bat->dev, &alarm_attr);
++ return 0;
+ }
+
+ static void sysfs_remove_battery(struct acpi_battery *battery)
+@@ -879,7 +888,6 @@ static void sysfs_remove_battery(struct acpi_battery *battery)
+ return;
+ }
+ battery_hook_remove_battery(battery);
+- device_remove_file(&battery->bat->dev, &alarm_attr);
+ power_supply_unregister(battery->bat);
+ battery->bat = NULL;
+ mutex_unlock(&battery->sysfs_lock);
+diff --git a/drivers/acpi/resource.c b/drivers/acpi/resource.c
+index b5bf8b81a050a..df5d5a554b388 100644
+--- a/drivers/acpi/resource.c
++++ b/drivers/acpi/resource.c
+@@ -524,6 +524,20 @@ static const struct dmi_system_id irq1_level_low_skip_override[] = {
+ DMI_MATCH(DMI_BOARD_NAME, "N6506MV"),
+ },
+ },
++ {
++ /* Asus Vivobook Pro N6506MU */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
++ DMI_MATCH(DMI_BOARD_NAME, "N6506MU"),
++ },
++ },
++ {
++ /* Asus Vivobook Pro N6506MJ */
++ .matches = {
++ DMI_MATCH(DMI_SYS_VENDOR, "ASUSTeK COMPUTER INC."),
++ DMI_MATCH(DMI_BOARD_NAME, "N6506MJ"),
++ },
++ },
+ {
+ /* LG Electronics 17U70P */
+ .matches = {
+diff --git a/drivers/acpi/sbs.c b/drivers/acpi/sbs.c
+index dc8164b182dcc..442c5905d43be 100644
+--- a/drivers/acpi/sbs.c
++++ b/drivers/acpi/sbs.c
+@@ -77,7 +77,6 @@ struct acpi_battery {
+ u16 spec;
+ u8 id;
+ u8 present:1;
+- u8 have_sysfs_alarm:1;
+ };
+
+ #define to_acpi_battery(x) power_supply_get_drvdata(x)
+@@ -462,12 +461,18 @@ static ssize_t acpi_battery_alarm_store(struct device *dev,
+ return count;
+ }
+
+-static const struct device_attribute alarm_attr = {
++static struct device_attribute alarm_attr = {
+ .attr = {.name = "alarm", .mode = 0644},
+ .show = acpi_battery_alarm_show,
+ .store = acpi_battery_alarm_store,
+ };
+
++static struct attribute *acpi_battery_attrs[] = {
++ &alarm_attr.attr,
++ NULL
++};
++ATTRIBUTE_GROUPS(acpi_battery);
++
+ /* --------------------------------------------------------------------------
+ Driver Interface
+ -------------------------------------------------------------------------- */
+@@ -518,7 +523,10 @@ static int acpi_battery_read(struct acpi_battery *battery)
+ static int acpi_battery_add(struct acpi_sbs *sbs, int id)
+ {
+ struct acpi_battery *battery = &sbs->battery[id];
+- struct power_supply_config psy_cfg = { .drv_data = battery, };
++ struct power_supply_config psy_cfg = {
++ .drv_data = battery,
++ .attr_grp = acpi_battery_groups,
++ };
+ int result;
+
+ battery->id = id;
+@@ -548,10 +556,6 @@ static int acpi_battery_add(struct acpi_sbs *sbs, int id)
+ goto end;
+ }
+
+- result = device_create_file(&battery->bat->dev, &alarm_attr);
+- if (result)
+- goto end;
+- battery->have_sysfs_alarm = 1;
+ end:
+ pr_info("%s [%s]: Battery Slot [%s] (battery %s)\n",
+ ACPI_SBS_DEVICE_NAME, acpi_device_bid(sbs->device),
+@@ -563,11 +567,8 @@ static void acpi_battery_remove(struct acpi_sbs *sbs, int id)
+ {
+ struct acpi_battery *battery = &sbs->battery[id];
+
+- if (battery->bat) {
+- if (battery->have_sysfs_alarm)
+- device_remove_file(&battery->bat->dev, &alarm_attr);
++ if (battery->bat)
+ power_supply_unregister(battery->bat);
+- }
+ }
+
+ static int acpi_charger_add(struct acpi_sbs *sbs)
+diff --git a/drivers/base/core.c b/drivers/base/core.c
+index 2b4c0624b7043..b5399262198a6 100644
+--- a/drivers/base/core.c
++++ b/drivers/base/core.c
+@@ -25,6 +25,7 @@
+ #include <linux/mutex.h>
+ #include <linux/pm_runtime.h>
+ #include <linux/netdevice.h>
++#include <linux/rcupdate.h>
+ #include <linux/sched/signal.h>
+ #include <linux/sched/mm.h>
+ #include <linux/string_helpers.h>
+@@ -2640,6 +2641,7 @@ static const char *dev_uevent_name(const struct kobject *kobj)
+ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
+ {
+ const struct device *dev = kobj_to_dev(kobj);
++ struct device_driver *driver;
+ int retval = 0;
+
+ /* add device node properties if present */
+@@ -2668,8 +2670,12 @@ static int dev_uevent(const struct kobject *kobj, struct kobj_uevent_env *env)
+ if (dev->type && dev->type->name)
+ add_uevent_var(env, "DEVTYPE=%s", dev->type->name);
+
+- if (dev->driver)
+- add_uevent_var(env, "DRIVER=%s", dev->driver->name);
++ /* Synchronize with module_remove_driver() */
++ rcu_read_lock();
++ driver = READ_ONCE(dev->driver);
++ if (driver)
++ add_uevent_var(env, "DRIVER=%s", driver->name);
++ rcu_read_unlock();
+
+ /* Add common DT information about the device */
+ of_device_uevent(dev, env);
+@@ -2739,11 +2745,8 @@ static ssize_t uevent_show(struct device *dev, struct device_attribute *attr,
+ if (!env)
+ return -ENOMEM;
+
+- /* Synchronize with really_probe() */
+- device_lock(dev);
+ /* let the kset specific function add its keys */
+ retval = kset->uevent_ops->uevent(&dev->kobj, env);
+- device_unlock(dev);
+ if (retval)
+ goto out;
+
+diff --git a/drivers/base/module.c b/drivers/base/module.c
+index a1b55da07127d..b0b79b9c189d4 100644
+--- a/drivers/base/module.c
++++ b/drivers/base/module.c
+@@ -7,6 +7,7 @@
+ #include <linux/errno.h>
+ #include <linux/slab.h>
+ #include <linux/string.h>
++#include <linux/rcupdate.h>
+ #include "base.h"
+
+ static char *make_driver_name(struct device_driver *drv)
+@@ -97,6 +98,9 @@ void module_remove_driver(struct device_driver *drv)
+ if (!drv)
+ return;
+
++ /* Synchronize with dev_uevent() */
++ synchronize_rcu();
++
+ sysfs_remove_link(&drv->p->kobj, "module");
+
+ if (drv->owner)
+diff --git a/drivers/base/regmap/regmap-kunit.c b/drivers/base/regmap/regmap-kunit.c
+index be32cd4e84da4..292e86f601978 100644
+--- a/drivers/base/regmap/regmap-kunit.c
++++ b/drivers/base/regmap/regmap-kunit.c
+@@ -145,9 +145,9 @@ static struct regmap *gen_regmap(struct kunit *test,
+ const struct regmap_test_param *param = test->param_value;
+ struct regmap_test_priv *priv = test->priv;
+ unsigned int *buf;
+- struct regmap *ret;
++ struct regmap *ret = ERR_PTR(-ENOMEM);
+ size_t size;
+- int i;
++ int i, error;
+ struct reg_default *defaults;
+
+ config->cache_type = param->cache;
+@@ -172,15 +172,17 @@ static struct regmap *gen_regmap(struct kunit *test,
+
+ *data = kzalloc(sizeof(**data), GFP_KERNEL);
+ if (!(*data))
+- return ERR_PTR(-ENOMEM);
++ goto out_free;
+ (*data)->vals = buf;
+
+ if (config->num_reg_defaults) {
+- defaults = kcalloc(config->num_reg_defaults,
+- sizeof(struct reg_default),
+- GFP_KERNEL);
++ defaults = kunit_kcalloc(test,
++ config->num_reg_defaults,
++ sizeof(struct reg_default),
++ GFP_KERNEL);
+ if (!defaults)
+- return ERR_PTR(-ENOMEM);
++ goto out_free;
++
+ config->reg_defaults = defaults;
+
+ for (i = 0; i < config->num_reg_defaults; i++) {
+@@ -190,12 +192,19 @@ static struct regmap *gen_regmap(struct kunit *test,
+ }
+
+ ret = regmap_init_ram(priv->dev, config, *data);
+- if (IS_ERR(ret)) {
+- kfree(buf);
+- kfree(*data);
+- } else {
+- kunit_add_action(test, regmap_exit_action, ret);
+- }
++ if (IS_ERR(ret))
++ goto out_free;
++
++ /* This calls regmap_exit() on failure, which frees buf and *data */
++ error = kunit_add_action_or_reset(test, regmap_exit_action, ret);
++ if (error)
++ ret = ERR_PTR(error);
++
++ return ret;
++
++out_free:
++ kfree(buf);
++ kfree(*data);
+
+ return ret;
+ }
+@@ -1497,9 +1506,9 @@ static struct regmap *gen_raw_regmap(struct kunit *test,
+ struct regmap_test_priv *priv = test->priv;
+ const struct regmap_test_param *param = test->param_value;
+ u16 *buf;
+- struct regmap *ret;
++ struct regmap *ret = ERR_PTR(-ENOMEM);
+ size_t size = (config->max_register + 1) * config->reg_bits / 8;
+- int i;
++ int i, error;
+ struct reg_default *defaults;
+
+ config->cache_type = param->cache;
+@@ -1515,15 +1524,16 @@ static struct regmap *gen_raw_regmap(struct kunit *test,
+
+ *data = kzalloc(sizeof(**data), GFP_KERNEL);
+ if (!(*data))
+- return ERR_PTR(-ENOMEM);
++ goto out_free;
+ (*data)->vals = (void *)buf;
+
+ config->num_reg_defaults = config->max_register + 1;
+- defaults = kcalloc(config->num_reg_defaults,
+- sizeof(struct reg_default),
+- GFP_KERNEL);
++ defaults = kunit_kcalloc(test,
++ config->num_reg_defaults,
++ sizeof(struct reg_default),
++ GFP_KERNEL);
+ if (!defaults)
+- return ERR_PTR(-ENOMEM);
++ goto out_free;
+ config->reg_defaults = defaults;
+
+ for (i = 0; i < config->num_reg_defaults; i++) {
+@@ -1536,7 +1546,8 @@ static struct regmap *gen_raw_regmap(struct kunit *test,
+ defaults[i].def = be16_to_cpu(buf[i]);
+ break;
+ default:
+- return ERR_PTR(-EINVAL);
++ ret = ERR_PTR(-EINVAL);
++ goto out_free;
+ }
+ }
+
+@@ -1548,12 +1559,19 @@ static struct regmap *gen_raw_regmap(struct kunit *test,
+ config->num_reg_defaults = 0;
+
+ ret = regmap_init_raw_ram(priv->dev, config, *data);
+- if (IS_ERR(ret)) {
+- kfree(buf);
+- kfree(*data);
+- } else {
+- kunit_add_action(test, regmap_exit_action, ret);
+- }
++ if (IS_ERR(ret))
++ goto out_free;
++
++ /* This calls regmap_exit() on failure, which frees buf and *data */
++ error = kunit_add_action_or_reset(test, regmap_exit_action, ret);
++ if (error)
++ ret = ERR_PTR(error);
++
++ return ret;
++
++out_free:
++ kfree(buf);
++ kfree(*data);
+
+ return ret;
+ }
+diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
+index 6a863328b8053..d310b525fbf00 100644
+--- a/drivers/bluetooth/btnxpuart.c
++++ b/drivers/bluetooth/btnxpuart.c
+@@ -344,7 +344,7 @@ static void ps_cancel_timer(struct btnxpuart_dev *nxpdev)
+ struct ps_data *psdata = &nxpdev->psdata;
+
+ flush_work(&psdata->work);
+- del_timer_sync(&psdata->ps_timer);
++ timer_shutdown_sync(&psdata->ps_timer);
+ }
+
+ static void ps_control(struct hci_dev *hdev, u8 ps_state)
+diff --git a/drivers/clocksource/sh_cmt.c b/drivers/clocksource/sh_cmt.c
+index 26919556ef5f0..b72b36e0abed8 100644
+--- a/drivers/clocksource/sh_cmt.c
++++ b/drivers/clocksource/sh_cmt.c
+@@ -528,6 +528,7 @@ static void sh_cmt_set_next(struct sh_cmt_channel *ch, unsigned long delta)
+ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id)
+ {
+ struct sh_cmt_channel *ch = dev_id;
++ unsigned long flags;
+
+ /* clear flags */
+ sh_cmt_write_cmcsr(ch, sh_cmt_read_cmcsr(ch) &
+@@ -558,6 +559,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id)
+
+ ch->flags &= ~FLAG_SKIPEVENT;
+
++ raw_spin_lock_irqsave(&ch->lock, flags);
++
+ if (ch->flags & FLAG_REPROGRAM) {
+ ch->flags &= ~FLAG_REPROGRAM;
+ sh_cmt_clock_event_program_verify(ch, 1);
+@@ -570,6 +573,8 @@ static irqreturn_t sh_cmt_interrupt(int irq, void *dev_id)
+
+ ch->flags &= ~FLAG_IRQCONTEXT;
+
++ raw_spin_unlock_irqrestore(&ch->lock, flags);
++
+ return IRQ_HANDLED;
+ }
+
+@@ -780,12 +785,18 @@ static int sh_cmt_clock_event_next(unsigned long delta,
+ struct clock_event_device *ced)
+ {
+ struct sh_cmt_channel *ch = ced_to_sh_cmt(ced);
++ unsigned long flags;
+
+ BUG_ON(!clockevent_state_oneshot(ced));
++
++ raw_spin_lock_irqsave(&ch->lock, flags);
++
+ if (likely(ch->flags & FLAG_IRQCONTEXT))
+ ch->next_match_value = delta - 1;
+ else
+- sh_cmt_set_next(ch, delta - 1);
++ __sh_cmt_set_next(ch, delta - 1);
++
++ raw_spin_unlock_irqrestore(&ch->lock, flags);
+
+ return 0;
+ }
+diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
+index a092b13ffbc2f..67c4a6a0ef124 100644
+--- a/drivers/cpufreq/amd-pstate.c
++++ b/drivers/cpufreq/amd-pstate.c
+@@ -304,10 +304,8 @@ static int amd_pstate_set_energy_pref_index(struct amd_cpudata *cpudata,
+ int epp = -EINVAL;
+ int ret;
+
+- if (!pref_index) {
+- pr_debug("EPP pref_index is invalid\n");
+- return -EINVAL;
+- }
++ if (!pref_index)
++ epp = cpudata->epp_default;
+
+ if (epp == -EINVAL)
+ epp = epp_values[pref_index];
+@@ -1439,7 +1437,7 @@ static int amd_pstate_epp_cpu_init(struct cpufreq_policy *policy)
+
+ policy->driver_data = cpudata;
+
+- cpudata->epp_cached = amd_pstate_get_epp(cpudata, 0);
++ cpudata->epp_cached = cpudata->epp_default = amd_pstate_get_epp(cpudata, 0);
+
+ policy->min = policy->cpuinfo.min_freq;
+ policy->max = policy->cpuinfo.max_freq;
+@@ -1766,8 +1764,13 @@ static int __init amd_pstate_init(void)
+ /* check if this machine need CPPC quirks */
+ dmi_check_system(amd_pstate_quirks_table);
+
+- switch (cppc_state) {
+- case AMD_PSTATE_UNDEFINED:
++ /*
++ * determine the driver mode from the command line or kernel config.
++ * If no command line input is provided, cppc_state will be AMD_PSTATE_UNDEFINED.
++ * command line options will override the kernel config settings.
++ */
++
++ if (cppc_state == AMD_PSTATE_UNDEFINED) {
+ /* Disable on the following configs by default:
+ * 1. Undefined platforms
+ * 2. Server platforms
+@@ -1779,15 +1782,20 @@ static int __init amd_pstate_init(void)
+ pr_info("driver load is disabled, boot with specific mode to enable this\n");
+ return -ENODEV;
+ }
+- ret = amd_pstate_set_driver(CONFIG_X86_AMD_PSTATE_DEFAULT_MODE);
+- if (ret)
+- return ret;
+- break;
++ /* get driver mode from kernel config option [1:4] */
++ cppc_state = CONFIG_X86_AMD_PSTATE_DEFAULT_MODE;
++ }
++
++ switch (cppc_state) {
+ case AMD_PSTATE_DISABLE:
++ pr_info("driver load is disabled, boot with specific mode to enable this\n");
+ return -ENODEV;
+ case AMD_PSTATE_PASSIVE:
+ case AMD_PSTATE_ACTIVE:
+ case AMD_PSTATE_GUIDED:
++ ret = amd_pstate_set_driver(cppc_state);
++ if (ret)
++ return ret;
+ break;
+ default:
+ return -EINVAL;
+@@ -1808,7 +1816,7 @@ static int __init amd_pstate_init(void)
+ /* enable amd pstate feature */
+ ret = amd_pstate_enable(true);
+ if (ret) {
+- pr_err("failed to enable with return %d\n", ret);
++ pr_err("failed to enable driver mode(%d)\n", cppc_state);
+ return ret;
+ }
+
+diff --git a/drivers/cpufreq/amd-pstate.h b/drivers/cpufreq/amd-pstate.h
+index e6a28e7f4dbf1..f80b33fa5d43a 100644
+--- a/drivers/cpufreq/amd-pstate.h
++++ b/drivers/cpufreq/amd-pstate.h
+@@ -99,6 +99,7 @@ struct amd_cpudata {
+ u32 policy;
+ u64 cppc_cap1_cached;
+ bool suspended;
++ s16 epp_default;
+ };
+
+ #endif /* _LINUX_AMD_PSTATE_H */
+diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
+index fa62367ee9290..1a9aadd4c803c 100644
+--- a/drivers/gpio/gpiolib.c
++++ b/drivers/gpio/gpiolib.c
+@@ -17,6 +17,7 @@
+ #include <linux/list.h>
+ #include <linux/lockdep.h>
+ #include <linux/module.h>
++#include <linux/nospec.h>
+ #include <linux/of.h>
+ #include <linux/pinctrl/consumer.h>
+ #include <linux/seq_file.h>
+@@ -198,7 +199,7 @@ gpio_device_get_desc(struct gpio_device *gdev, unsigned int hwnum)
+ if (hwnum >= gdev->ngpio)
+ return ERR_PTR(-EINVAL);
+
+- return &gdev->descs[hwnum];
++ return &gdev->descs[array_index_nospec(hwnum, gdev->ngpio)];
+ }
+ EXPORT_SYMBOL_GPL(gpio_device_get_desc);
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+index ee7df1d84e028..89cf9ac6da174 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+@@ -4048,6 +4048,7 @@ int amdgpu_device_init(struct amdgpu_device *adev,
+ mutex_init(&adev->grbm_idx_mutex);
+ mutex_init(&adev->mn_lock);
+ mutex_init(&adev->virt.vf_errors.lock);
++ mutex_init(&adev->virt.rlcg_reg_lock);
+ hash_init(adev->mn_hash);
+ mutex_init(&adev->psp.mutex);
+ mutex_init(&adev->notifier_lock);
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+index e4742b65032d1..4a9cec002691a 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_job.c
+@@ -262,9 +262,8 @@ amdgpu_job_prepare_job(struct drm_sched_job *sched_job,
+ struct dma_fence *fence = NULL;
+ int r;
+
+- /* Ignore soft recovered fences here */
+ r = drm_sched_entity_error(s_entity);
+- if (r && r != -ENODATA)
++ if (r)
+ goto error;
+
+ if (!fence && job->gang_submit)
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+index ca5c86e5f7cd6..8e8afbd237bcd 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_psp_ta.c
+@@ -334,7 +334,7 @@ static ssize_t ta_if_invoke_debugfs_write(struct file *fp, const char *buf, size
+
+ set_ta_context_funcs(psp, ta_type, &context);
+
+- if (!context->initialized) {
++ if (!context || !context->initialized) {
+ dev_err(adev->dev, "TA is not initialized\n");
+ ret = -EINVAL;
+ goto err_free_shared_buf;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+index 1adc81a55734d..0c4ee06451e9c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ras.c
+@@ -2172,12 +2172,15 @@ static void amdgpu_ras_interrupt_process_handler(struct work_struct *work)
+ int amdgpu_ras_interrupt_dispatch(struct amdgpu_device *adev,
+ struct ras_dispatch_if *info)
+ {
+- struct ras_manager *obj = amdgpu_ras_find_obj(adev, &info->head);
+- struct ras_ih_data *data = &obj->ih_data;
++ struct ras_manager *obj;
++ struct ras_ih_data *data;
+
++ obj = amdgpu_ras_find_obj(adev, &info->head);
+ if (!obj)
+ return -EINVAL;
+
++ data = &obj->ih_data;
++
+ if (data->inuse == 0)
+ return 0;
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+index 54ab51a4ada77..972a58f0f4924 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.c
+@@ -980,6 +980,9 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
+ scratch_reg1 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg1;
+ scratch_reg2 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg2;
+ scratch_reg3 = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->scratch_reg3;
++
++ mutex_lock(&adev->virt.rlcg_reg_lock);
++
+ if (reg_access_ctrl->spare_int)
+ spare_int = (void __iomem *)adev->rmmio + 4 * reg_access_ctrl->spare_int;
+
+@@ -1036,6 +1039,9 @@ u32 amdgpu_virt_rlcg_reg_rw(struct amdgpu_device *adev, u32 offset, u32 v, u32 f
+ }
+
+ ret = readl(scratch_reg0);
++
++ mutex_unlock(&adev->virt.rlcg_reg_lock);
++
+ return ret;
+ }
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+index 642f1fd287d83..0ec246c74570c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_virt.h
+@@ -272,6 +272,8 @@ struct amdgpu_virt {
+
+ /* the ucode id to signal the autoload */
+ uint32_t autoload_ucode_id;
++
++ struct mutex rlcg_reg_lock;
+ };
+
+ struct amdgpu_video_codec_info;
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+index 66e8a016126b8..9b748d7058b5c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm_sdma.c
+@@ -102,6 +102,11 @@ static int amdgpu_vm_sdma_prepare(struct amdgpu_vm_update_params *p,
+ if (!r)
+ r = amdgpu_sync_push_to_job(&sync, p->job);
+ amdgpu_sync_free(&sync);
++
++ if (r) {
++ p->num_dw_left = 0;
++ amdgpu_job_free(p->job);
++ }
+ return r;
+ }
+
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+index 31e500859ab01..92485251247a0 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_svm.c
+@@ -1658,7 +1658,7 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
+ start = map_start << PAGE_SHIFT;
+ end = (map_last + 1) << PAGE_SHIFT;
+ for (addr = start; !r && addr < end; ) {
+- struct hmm_range *hmm_range;
++ struct hmm_range *hmm_range = NULL;
+ unsigned long map_start_vma;
+ unsigned long map_last_vma;
+ struct vm_area_struct *vma;
+@@ -1696,7 +1696,12 @@ static int svm_range_validate_and_map(struct mm_struct *mm,
+ }
+
+ svm_range_lock(prange);
+- if (!r && amdgpu_hmm_range_get_pages_done(hmm_range)) {
++
++ /* Free backing memory of hmm_range if it was initialized
++ * Overrride return value to TRY AGAIN only if prior returns
++ * were successful
++ */
++ if (hmm_range && amdgpu_hmm_range_get_pages_done(hmm_range) && !r) {
+ pr_debug("hmm update the range, need validate again\n");
+ r = -EAGAIN;
+ }
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+index 3cdcadd41be1a..964bb6d0a3833 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm.c
+@@ -2701,7 +2701,8 @@ static int dm_suspend(void *handle)
+
+ dm->cached_dc_state = dc_state_create_copy(dm->dc->current_state);
+
+- dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false);
++ if (dm->cached_dc_state)
++ dm_gpureset_toggle_interrupts(adev, dm->cached_dc_state, false);
+
+ amdgpu_dm_commit_zero_streams(dm->dc);
+
+@@ -6788,7 +6789,8 @@ static void create_eml_sink(struct amdgpu_dm_connector *aconnector)
+ aconnector->dc_sink = aconnector->dc_link->local_sink ?
+ aconnector->dc_link->local_sink :
+ aconnector->dc_em_sink;
+- dc_sink_retain(aconnector->dc_sink);
++ if (aconnector->dc_sink)
++ dc_sink_retain(aconnector->dc_sink);
+ }
+ }
+
+@@ -7615,7 +7617,8 @@ static int amdgpu_dm_connector_get_modes(struct drm_connector *connector)
+ drm_add_modes_noedid(connector, 1920, 1080);
+ } else {
+ amdgpu_dm_connector_ddc_get_modes(connector, edid);
+- amdgpu_dm_connector_add_common_modes(encoder, connector);
++ if (encoder)
++ amdgpu_dm_connector_add_common_modes(encoder, connector);
+ amdgpu_dm_connector_add_freesync_modes(connector, edid);
+ }
+ amdgpu_dm_fbc_init(connector);
+diff --git a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+index a5e1a93ddaea2..bb4e5ab7edc6e 100644
+--- a/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
++++ b/drivers/gpu/drm/amd/display/amdgpu_dm/amdgpu_dm_mst_types.c
+@@ -182,6 +182,8 @@ amdgpu_dm_mst_connector_early_unregister(struct drm_connector *connector)
+ dc_sink_release(dc_sink);
+ aconnector->dc_sink = NULL;
+ aconnector->edid = NULL;
++ aconnector->dsc_aux = NULL;
++ port->passthrough_aux = NULL;
+ }
+
+ aconnector->mst_status = MST_STATUS_DEFAULT;
+@@ -494,6 +496,8 @@ dm_dp_mst_detect(struct drm_connector *connector,
+ dc_sink_release(aconnector->dc_sink);
+ aconnector->dc_sink = NULL;
+ aconnector->edid = NULL;
++ aconnector->dsc_aux = NULL;
++ port->passthrough_aux = NULL;
+
+ amdgpu_dm_set_mst_status(&aconnector->mst_status,
+ MST_REMOTE_EDID | MST_ALLOCATE_NEW_PAYLOAD | MST_CLEAR_ALLOCATED_PAYLOAD,
+@@ -1233,14 +1237,6 @@ static bool is_dsc_need_re_compute(
+ if (!aconnector || !aconnector->dsc_aux)
+ continue;
+
+- /*
+- * check if cached virtual MST DSC caps are available and DSC is supported
+- * as per specifications in their Virtual DPCD registers.
+- */
+- if (!(aconnector->dc_sink->dsc_caps.dsc_dec_caps.is_dsc_supported ||
+- aconnector->dc_link->dpcd_caps.dsc_caps.dsc_basic_caps.fields.dsc_support.DSC_PASSTHROUGH_SUPPORT))
+- continue;
+-
+ stream_on_link[new_stream_on_link_num] = aconnector;
+ new_stream_on_link_num++;
+
+@@ -1268,6 +1264,9 @@ static bool is_dsc_need_re_compute(
+ }
+ }
+
++ if (new_stream_on_link_num == 0)
++ return false;
++
+ /* check current_state if there stream on link but it is not in
+ * new request state
+ */
+@@ -1595,109 +1594,171 @@ static bool is_dsc_common_config_possible(struct dc_stream_state *stream,
+ return bw_range->max_target_bpp_x16 && bw_range->min_target_bpp_x16;
+ }
+
++#if defined(CONFIG_DRM_AMD_DC_FP)
++static bool dp_get_link_current_set_bw(struct drm_dp_aux *aux, uint32_t *cur_link_bw)
++{
++ uint32_t total_data_bw_efficiency_x10000 = 0;
++ uint32_t link_rate_per_lane_kbps = 0;
++ enum dc_link_rate link_rate;
++ union lane_count_set lane_count;
++ u8 dp_link_encoding;
++ u8 link_bw_set = 0;
++
++ *cur_link_bw = 0;
++
++ if (drm_dp_dpcd_read(aux, DP_MAIN_LINK_CHANNEL_CODING_SET, &dp_link_encoding, 1) != 1 ||
++ drm_dp_dpcd_read(aux, DP_LANE_COUNT_SET, &lane_count.raw, 1) != 1 ||
++ drm_dp_dpcd_read(aux, DP_LINK_BW_SET, &link_bw_set, 1) != 1)
++ return false;
++
++ switch (dp_link_encoding) {
++ case DP_8b_10b_ENCODING:
++ link_rate = link_bw_set;
++ link_rate_per_lane_kbps = link_rate * LINK_RATE_REF_FREQ_IN_KHZ * BITS_PER_DP_BYTE;
++ total_data_bw_efficiency_x10000 = DATA_EFFICIENCY_8b_10b_x10000;
++ total_data_bw_efficiency_x10000 /= 100;
++ total_data_bw_efficiency_x10000 *= DATA_EFFICIENCY_8b_10b_FEC_EFFICIENCY_x100;
++ break;
++ case DP_128b_132b_ENCODING:
++ switch (link_bw_set) {
++ case DP_LINK_BW_10:
++ link_rate = LINK_RATE_UHBR10;
++ break;
++ case DP_LINK_BW_13_5:
++ link_rate = LINK_RATE_UHBR13_5;
++ break;
++ case DP_LINK_BW_20:
++ link_rate = LINK_RATE_UHBR20;
++ break;
++ default:
++ return false;
++ }
++
++ link_rate_per_lane_kbps = link_rate * 10000;
++ total_data_bw_efficiency_x10000 = DATA_EFFICIENCY_128b_132b_x10000;
++ break;
++ default:
++ return false;
++ }
++
++ *cur_link_bw = link_rate_per_lane_kbps * lane_count.bits.LANE_COUNT_SET / 10000 * total_data_bw_efficiency_x10000;
++ return true;
++}
++#endif
++
+ enum dc_status dm_dp_mst_is_port_support_mode(
+ struct amdgpu_dm_connector *aconnector,
+ struct dc_stream_state *stream)
+ {
+- int pbn, branch_max_throughput_mps = 0;
++#if defined(CONFIG_DRM_AMD_DC_FP)
++ int branch_max_throughput_mps = 0;
+ struct dc_link_settings cur_link_settings;
+- unsigned int end_to_end_bw_in_kbps = 0;
+- unsigned int upper_link_bw_in_kbps = 0, down_link_bw_in_kbps = 0;
++ uint32_t end_to_end_bw_in_kbps = 0;
++ uint32_t root_link_bw_in_kbps = 0;
++ uint32_t virtual_channel_bw_in_kbps = 0;
+ struct dc_dsc_bw_range bw_range = {0};
+ struct dc_dsc_config_options dsc_options = {0};
++ uint32_t stream_kbps;
+
+- /*
+- * Consider the case with the depth of the mst topology tree is equal or less than 2
+- * A. When dsc bitstream can be transmitted along the entire path
+- * 1. dsc is possible between source and branch/leaf device (common dsc params is possible), AND
+- * 2. dsc passthrough supported at MST branch, or
+- * 3. dsc decoding supported at leaf MST device
+- * Use maximum dsc compression as bw constraint
+- * B. When dsc bitstream cannot be transmitted along the entire path
+- * Use native bw as bw constraint
++ /* DSC unnecessary case
++ * Check if timing could be supported within end-to-end BW
+ */
+- if (is_dsc_common_config_possible(stream, &bw_range) &&
+- (aconnector->mst_output_port->passthrough_aux ||
+- aconnector->dsc_aux == &aconnector->mst_output_port->aux)) {
+- cur_link_settings = stream->link->verified_link_cap;
+- upper_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, &cur_link_settings);
+- down_link_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn);
+-
+- /* pick the end to end bw bottleneck */
+- end_to_end_bw_in_kbps = min(upper_link_bw_in_kbps, down_link_bw_in_kbps);
+-
+- if (end_to_end_bw_in_kbps < bw_range.min_kbps) {
+- DRM_DEBUG_DRIVER("maximum dsc compression cannot fit into end-to-end bandwidth\n");
++ stream_kbps =
++ dc_bandwidth_in_kbps_from_timing(&stream->timing,
++ dc_link_get_highest_encoding_format(stream->link));
++ cur_link_settings = stream->link->verified_link_cap;
++ root_link_bw_in_kbps = dc_link_bandwidth_kbps(aconnector->dc_link, &cur_link_settings);
++ virtual_channel_bw_in_kbps = kbps_from_pbn(aconnector->mst_output_port->full_pbn);
++
++ /* pick the end to end bw bottleneck */
++ end_to_end_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps);
++
++ if (stream_kbps <= end_to_end_bw_in_kbps) {
++ DRM_DEBUG_DRIVER("No DSC needed. End-to-end bw sufficient.");
++ return DC_OK;
++ }
++
++ /*DSC necessary case*/
++ if (!aconnector->dsc_aux)
++ return DC_FAIL_BANDWIDTH_VALIDATE;
++
++ if (is_dsc_common_config_possible(stream, &bw_range)) {
++
++ /*capable of dsc passthough. dsc bitstream along the entire path*/
++ if (aconnector->mst_output_port->passthrough_aux) {
++ if (bw_range.min_kbps > end_to_end_bw_in_kbps) {
++ DRM_DEBUG_DRIVER("DSC passthrough. Max dsc compression can't fit into end-to-end bw\n");
+ return DC_FAIL_BANDWIDTH_VALIDATE;
+- }
++ }
++ } else {
++ /*dsc bitstream decoded at the dp last link*/
++ struct drm_dp_mst_port *immediate_upstream_port = NULL;
++ uint32_t end_link_bw = 0;
++
++ /*Get last DP link BW capability*/
++ if (dp_get_link_current_set_bw(&aconnector->mst_output_port->aux, &end_link_bw)) {
++ if (stream_kbps > end_link_bw) {
++ DRM_DEBUG_DRIVER("DSC decode at last link. Mode required bw can't fit into available bw\n");
++ return DC_FAIL_BANDWIDTH_VALIDATE;
++ }
++ }
+
+- if (end_to_end_bw_in_kbps < bw_range.stream_kbps) {
+- dc_dsc_get_default_config_option(stream->link->dc, &dsc_options);
+- dsc_options.max_target_bpp_limit_override_x16 = aconnector->base.display_info.max_dsc_bpp * 16;
+- if (dc_dsc_compute_config(stream->sink->ctx->dc->res_pool->dscs[0],
+- &stream->sink->dsc_caps.dsc_dec_caps,
+- &dsc_options,
+- end_to_end_bw_in_kbps,
+- &stream->timing,
+- dc_link_get_highest_encoding_format(stream->link),
+- &stream->timing.dsc_cfg)) {
+- stream->timing.flags.DSC = 1;
+- DRM_DEBUG_DRIVER("end-to-end bandwidth require dsc and dsc config found\n");
+- } else {
+- DRM_DEBUG_DRIVER("end-to-end bandwidth require dsc but dsc config not found\n");
+- return DC_FAIL_BANDWIDTH_VALIDATE;
++ /*Get virtual channel bandwidth between source and the link before the last link*/
++ if (aconnector->mst_output_port->parent->port_parent)
++ immediate_upstream_port = aconnector->mst_output_port->parent->port_parent;
++
++ if (immediate_upstream_port) {
++ virtual_channel_bw_in_kbps = kbps_from_pbn(immediate_upstream_port->full_pbn);
++ virtual_channel_bw_in_kbps = min(root_link_bw_in_kbps, virtual_channel_bw_in_kbps);
++ if (bw_range.min_kbps > virtual_channel_bw_in_kbps) {
++ DRM_DEBUG_DRIVER("DSC decode at last link. Max dsc compression can't fit into MST available bw\n");
++ return DC_FAIL_BANDWIDTH_VALIDATE;
++ }
+ }
+ }
+- } else {
+- /* Check if mode could be supported within max slot
+- * number of current mst link and full_pbn of mst links.
+- */
+- int pbn_div, slot_num, max_slot_num;
+- enum dc_link_encoding_format link_encoding;
+- uint32_t stream_kbps =
+- dc_bandwidth_in_kbps_from_timing(&stream->timing,
+- dc_link_get_highest_encoding_format(stream->link));
+-
+- pbn = kbps_to_peak_pbn(stream_kbps);
+- pbn_div = dm_mst_get_pbn_divider(stream->link);
+- slot_num = DIV_ROUND_UP(pbn, pbn_div);
+-
+- link_encoding = dc_link_get_highest_encoding_format(stream->link);
+- if (link_encoding == DC_LINK_ENCODING_DP_8b_10b)
+- max_slot_num = 63;
+- else if (link_encoding == DC_LINK_ENCODING_DP_128b_132b)
+- max_slot_num = 64;
+- else {
+- DRM_DEBUG_DRIVER("Invalid link encoding format\n");
+- return DC_FAIL_BANDWIDTH_VALIDATE;
+- }
+
+- if (slot_num > max_slot_num ||
+- pbn > aconnector->mst_output_port->full_pbn) {
+- DRM_DEBUG_DRIVER("Mode can not be supported within mst links!");
++ /*Confirm if we can obtain dsc config*/
++ dc_dsc_get_default_config_option(stream->link->dc, &dsc_options);
++ dsc_options.max_target_bpp_limit_override_x16 = aconnector->base.display_info.max_dsc_bpp * 16;
++ if (dc_dsc_compute_config(stream->sink->ctx->dc->res_pool->dscs[0],
++ &stream->sink->dsc_caps.dsc_dec_caps,
++ &dsc_options,
++ end_to_end_bw_in_kbps,
++ &stream->timing,
++ dc_link_get_highest_encoding_format(stream->link),
++ &stream->timing.dsc_cfg)) {
++ stream->timing.flags.DSC = 1;
++ DRM_DEBUG_DRIVER("Require dsc and dsc config found\n");
++ } else {
++ DRM_DEBUG_DRIVER("Require dsc but can't find appropriate dsc config\n");
+ return DC_FAIL_BANDWIDTH_VALIDATE;
+ }
+- }
+
+- /* check is mst dsc output bandwidth branch_overall_throughput_0_mps */
+- switch (stream->timing.pixel_encoding) {
+- case PIXEL_ENCODING_RGB:
+- case PIXEL_ENCODING_YCBCR444:
+- branch_max_throughput_mps =
+- aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_0_mps;
+- break;
+- case PIXEL_ENCODING_YCBCR422:
+- case PIXEL_ENCODING_YCBCR420:
+- branch_max_throughput_mps =
+- aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_1_mps;
+- break;
+- default:
+- break;
+- }
++ /* check is mst dsc output bandwidth branch_overall_throughput_0_mps */
++ switch (stream->timing.pixel_encoding) {
++ case PIXEL_ENCODING_RGB:
++ case PIXEL_ENCODING_YCBCR444:
++ branch_max_throughput_mps =
++ aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_0_mps;
++ break;
++ case PIXEL_ENCODING_YCBCR422:
++ case PIXEL_ENCODING_YCBCR420:
++ branch_max_throughput_mps =
++ aconnector->dc_sink->dsc_caps.dsc_dec_caps.branch_overall_throughput_1_mps;
++ break;
++ default:
++ break;
++ }
+
+- if (branch_max_throughput_mps != 0 &&
+- ((stream->timing.pix_clk_100hz / 10) > branch_max_throughput_mps * 1000))
++ if (branch_max_throughput_mps != 0 &&
++ ((stream->timing.pix_clk_100hz / 10) > branch_max_throughput_mps * 1000)) {
++ DRM_DEBUG_DRIVER("DSC is required but max throughput mps fails");
+ return DC_FAIL_BANDWIDTH_VALIDATE;
+-
++ }
++ } else {
++ DRM_DEBUG_DRIVER("DSC is required but can't find common dsc config.");
++ return DC_FAIL_BANDWIDTH_VALIDATE;
++ }
++#endif
+ return DC_OK;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+index 15819416a2f36..8ed599324693e 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc_resource.c
+@@ -2267,6 +2267,10 @@ void resource_log_pipe_topology_update(struct dc *dc, struct dc_state *state)
+
+ otg_master = resource_get_otg_master_for_stream(
+ &state->res_ctx, state->streams[stream_idx]);
++
++ if (!otg_master)
++ continue;
++
+ resource_log_pipe_for_stream(dc, state, otg_master, stream_idx);
+ }
+ if (state->phantom_stream_count > 0) {
+@@ -2508,6 +2512,17 @@ static void remove_hpo_dp_link_enc_from_ctx(struct resource_context *res_ctx,
+ }
+ }
+
++static int get_num_of_free_pipes(const struct resource_pool *pool, const struct dc_state *context)
++{
++ int i;
++ int count = 0;
++
++ for (i = 0; i < pool->pipe_count; i++)
++ if (resource_is_pipe_type(&context->res_ctx.pipe_ctx[i], FREE_PIPE))
++ count++;
++ return count;
++}
++
+ enum dc_status resource_add_otg_master_for_stream_output(struct dc_state *new_ctx,
+ const struct resource_pool *pool,
+ struct dc_stream_state *stream)
+@@ -2641,37 +2656,33 @@ static bool acquire_secondary_dpp_pipes_and_add_plane(
+ struct dc_state *cur_ctx,
+ struct resource_pool *pool)
+ {
+- struct pipe_ctx *opp_head_pipe, *sec_pipe, *tail_pipe;
++ struct pipe_ctx *sec_pipe, *tail_pipe;
++ struct pipe_ctx *opp_heads[MAX_PIPES];
++ int opp_head_count;
++ int i;
+
+ if (!pool->funcs->acquire_free_pipe_as_secondary_dpp_pipe) {
+ ASSERT(0);
+ return false;
+ }
+
+- opp_head_pipe = otg_master_pipe;
+- while (opp_head_pipe) {
++ opp_head_count = resource_get_opp_heads_for_otg_master(otg_master_pipe,
++ &new_ctx->res_ctx, opp_heads);
++ if (get_num_of_free_pipes(pool, new_ctx) < opp_head_count)
++ /* not enough free pipes */
++ return false;
++
++ for (i = 0; i < opp_head_count; i++) {
+ sec_pipe = pool->funcs->acquire_free_pipe_as_secondary_dpp_pipe(
+ cur_ctx,
+ new_ctx,
+ pool,
+- opp_head_pipe);
+- if (!sec_pipe) {
+- /* try tearing down MPCC combine */
+- int pipe_idx = acquire_first_split_pipe(
+- &new_ctx->res_ctx, pool,
+- otg_master_pipe->stream);
+-
+- if (pipe_idx >= 0)
+- sec_pipe = &new_ctx->res_ctx.pipe_ctx[pipe_idx];
+- }
+-
+- if (!sec_pipe)
+- return false;
+-
++ opp_heads[i]);
++ ASSERT(sec_pipe);
+ sec_pipe->plane_state = plane_state;
+
+ /* establish pipe relationship */
+- tail_pipe = get_tail_pipe(opp_head_pipe);
++ tail_pipe = get_tail_pipe(opp_heads[i]);
+ tail_pipe->bottom_pipe = sec_pipe;
+ sec_pipe->top_pipe = tail_pipe;
+ sec_pipe->bottom_pipe = NULL;
+@@ -2682,8 +2693,6 @@ static bool acquire_secondary_dpp_pipes_and_add_plane(
+ } else {
+ sec_pipe->prev_odm_pipe = NULL;
+ }
+-
+- opp_head_pipe = opp_head_pipe->next_odm_pipe;
+ }
+ return true;
+ }
+@@ -2696,6 +2705,7 @@ bool resource_append_dpp_pipes_for_plane_composition(
+ struct dc_plane_state *plane_state)
+ {
+ bool success;
++
+ if (otg_master_pipe->plane_state == NULL)
+ success = add_plane_to_opp_head_pipes(otg_master_pipe,
+ plane_state, new_ctx);
+@@ -2703,10 +2713,15 @@ bool resource_append_dpp_pipes_for_plane_composition(
+ success = acquire_secondary_dpp_pipes_and_add_plane(
+ otg_master_pipe, plane_state, new_ctx,
+ cur_ctx, pool);
+- if (success)
++ if (success) {
+ /* when appending a plane mpc slice count changes from 0 to 1 */
+ success = update_pipe_params_after_mpc_slice_count_change(
+ plane_state, new_ctx, pool);
++ if (!success)
++ resource_remove_dpp_pipes_for_plane_composition(new_ctx,
++ pool, plane_state);
++ }
++
+ return success;
+ }
+
+@@ -2716,6 +2731,7 @@ void resource_remove_dpp_pipes_for_plane_composition(
+ const struct dc_plane_state *plane_state)
+ {
+ int i;
++
+ for (i = pool->pipe_count - 1; i >= 0; i--) {
+ struct pipe_ctx *pipe_ctx = &context->res_ctx.pipe_ctx[i];
+
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_state.c b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+index 76bb05f4d6bf3..52a1cfc5feed8 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc_state.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc_state.c
+@@ -437,6 +437,19 @@ enum dc_status dc_state_remove_stream(
+ return DC_OK;
+ }
+
++static void remove_mpc_combine_for_stream(const struct dc *dc,
++ struct dc_state *new_ctx,
++ const struct dc_state *cur_ctx,
++ struct dc_stream_status *status)
++{
++ int i;
++
++ for (i = 0; i < status->plane_count; i++)
++ resource_update_pipes_for_plane_with_slice_count(
++ new_ctx, cur_ctx, dc->res_pool,
++ status->plane_states[i], 1);
++}
++
+ bool dc_state_add_plane(
+ const struct dc *dc,
+ struct dc_stream_state *stream,
+@@ -447,8 +460,12 @@ bool dc_state_add_plane(
+ struct pipe_ctx *otg_master_pipe;
+ struct dc_stream_status *stream_status = NULL;
+ bool added = false;
++ int odm_slice_count;
++ int i;
+
+ stream_status = dc_state_get_stream_status(state, stream);
++ otg_master_pipe = resource_get_otg_master_for_stream(
++ &state->res_ctx, stream);
+ if (stream_status == NULL) {
+ dm_error("Existing stream not found; failed to attach surface!\n");
+ goto out;
+@@ -456,22 +473,39 @@ bool dc_state_add_plane(
+ dm_error("Surface: can not attach plane_state %p! Maximum is: %d\n",
+ plane_state, MAX_SURFACE_NUM);
+ goto out;
++ } else if (!otg_master_pipe) {
++ goto out;
+ }
+
+- if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm)
+- /* ODM combine could prevent us from supporting more planes
+- * we will reset ODM slice count back to 1 when all planes have
+- * been removed to maximize the amount of planes supported when
+- * new planes are added.
+- */
+- resource_update_pipes_for_stream_with_slice_count(
+- state, dc->current_state, dc->res_pool, stream, 1);
++ added = resource_append_dpp_pipes_for_plane_composition(state,
++ dc->current_state, pool, otg_master_pipe, plane_state);
+
+- otg_master_pipe = resource_get_otg_master_for_stream(
+- &state->res_ctx, stream);
+- if (otg_master_pipe)
++ if (!added) {
++ /* try to remove MPC combine to free up pipes */
++ for (i = 0; i < state->stream_count; i++)
++ remove_mpc_combine_for_stream(dc, state,
++ dc->current_state,
++ &state->stream_status[i]);
+ added = resource_append_dpp_pipes_for_plane_composition(state,
+- dc->current_state, pool, otg_master_pipe, plane_state);
++ dc->current_state, pool,
++ otg_master_pipe, plane_state);
++ }
++
++ if (!added) {
++ /* try to decrease ODM slice count gradually to free up pipes */
++ odm_slice_count = resource_get_odm_slice_count(otg_master_pipe);
++ for (i = odm_slice_count - 1; i > 0; i--) {
++ resource_update_pipes_for_stream_with_slice_count(state,
++ dc->current_state, dc->res_pool, stream,
++ i);
++ added = resource_append_dpp_pipes_for_plane_composition(
++ state,
++ dc->current_state, pool,
++ otg_master_pipe, plane_state);
++ if (added)
++ break;
++ }
++ }
+
+ if (added) {
+ stream_status->plane_states[stream_status->plane_count] =
+@@ -531,15 +565,6 @@ bool dc_state_remove_plane(
+
+ stream_status->plane_states[stream_status->plane_count] = NULL;
+
+- if (stream_status->plane_count == 0 && dc->config.enable_windowed_mpo_odm)
+- /* ODM combine could prevent us from supporting more planes
+- * we will reset ODM slice count back to 1 when all planes have
+- * been removed to maximize the amount of planes supported when
+- * new planes are added.
+- */
+- resource_update_pipes_for_stream_with_slice_count(
+- state, dc->current_state, dc->res_pool, stream, 1);
+-
+ return true;
+ }
+
+diff --git a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+index 4f559a025cf00..09cf54586fd5d 100644
+--- a/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
++++ b/drivers/gpu/drm/amd/display/dc/dce/dmub_replay.c
+@@ -84,7 +84,7 @@ static void dmub_replay_enable(struct dmub_replay *dmub, bool enable, bool wait,
+
+ cmd.replay_enable.header.payload_bytes = sizeof(struct dmub_rb_cmd_replay_enable_data);
+
+- dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
++ dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
+
+ /* Below loops 1000 x 500us = 500 ms.
+ * Exit REPLAY may need to wait 1-2 frames to power up. Timeout after at
+@@ -127,7 +127,7 @@ static void dmub_replay_set_power_opt(struct dmub_replay *dmub, unsigned int pow
+ cmd.replay_set_power_opt.replay_set_power_opt_data.power_opt = power_opt;
+ cmd.replay_set_power_opt.replay_set_power_opt_data.panel_inst = panel_inst;
+
+- dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
++ dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
+ }
+
+ /*
+@@ -209,8 +209,7 @@ static bool dmub_replay_copy_settings(struct dmub_replay *dmub,
+ else
+ copy_settings_data->flags.bitfields.force_wakeup_by_tps3 = 0;
+
+-
+- dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
++ dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
+
+ return true;
+ }
+@@ -231,7 +230,7 @@ static void dmub_replay_set_coasting_vtotal(struct dmub_replay *dmub,
+ cmd.replay_set_coasting_vtotal.header.payload_bytes = sizeof(struct dmub_cmd_replay_set_coasting_vtotal_data);
+ cmd.replay_set_coasting_vtotal.replay_set_coasting_vtotal_data.coasting_vtotal = coasting_vtotal;
+
+- dm_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
++ dc_wake_and_execute_dmub_cmd(dc, &cmd, DM_DMUB_WAIT_TYPE_WAIT);
+ }
+
+ /*
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+index 0c4aef8ffe2c5..3306684e805ac 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn10/dcn10_hwseq.c
+@@ -288,6 +288,7 @@ static void dcn10_log_color_state(struct dc *dc,
+ {
+ struct dc_context *dc_ctx = dc->ctx;
+ struct resource_pool *pool = dc->res_pool;
++ bool is_gamut_remap_available = false;
+ int i;
+
+ DTN_INFO("DPP: IGAM format IGAM mode DGAM mode RGAM mode"
+@@ -300,16 +301,15 @@ static void dcn10_log_color_state(struct dc *dc,
+ struct dcn_dpp_state s = {0};
+
+ dpp->funcs->dpp_read_state(dpp, &s);
+- dpp->funcs->dpp_get_gamut_remap(dpp, &s.gamut_remap);
++ if (dpp->funcs->dpp_get_gamut_remap) {
++ dpp->funcs->dpp_get_gamut_remap(dpp, &s.gamut_remap);
++ is_gamut_remap_available = true;
++ }
+
+ if (!s.is_enabled)
+ continue;
+
+- DTN_INFO("[%2d]: %11xh %11s %9s %9s"
+- " %12s "
+- "%010lld %010lld %010lld %010lld "
+- "%010lld %010lld %010lld %010lld "
+- "%010lld %010lld %010lld %010lld",
++ DTN_INFO("[%2d]: %11xh %11s %9s %9s",
+ dpp->inst,
+ s.igam_input_format,
+ (s.igam_lut_mode == 0) ? "BypassFixed" :
+@@ -328,22 +328,27 @@ static void dcn10_log_color_state(struct dc *dc,
+ ((s.rgam_lut_mode == 2) ? "Ycc" :
+ ((s.rgam_lut_mode == 3) ? "RAM" :
+ ((s.rgam_lut_mode == 4) ? "RAM" :
+- "Unknown")))),
+- (s.gamut_remap.gamut_adjust_type == 0) ? "Bypass" :
+- ((s.gamut_remap.gamut_adjust_type == 1) ? "HW" :
+- "SW"),
+- s.gamut_remap.temperature_matrix[0].value,
+- s.gamut_remap.temperature_matrix[1].value,
+- s.gamut_remap.temperature_matrix[2].value,
+- s.gamut_remap.temperature_matrix[3].value,
+- s.gamut_remap.temperature_matrix[4].value,
+- s.gamut_remap.temperature_matrix[5].value,
+- s.gamut_remap.temperature_matrix[6].value,
+- s.gamut_remap.temperature_matrix[7].value,
+- s.gamut_remap.temperature_matrix[8].value,
+- s.gamut_remap.temperature_matrix[9].value,
+- s.gamut_remap.temperature_matrix[10].value,
+- s.gamut_remap.temperature_matrix[11].value);
++ "Unknown")))));
++ if (is_gamut_remap_available)
++ DTN_INFO(" %12s "
++ "%010lld %010lld %010lld %010lld "
++ "%010lld %010lld %010lld %010lld "
++ "%010lld %010lld %010lld %010lld",
++ (s.gamut_remap.gamut_adjust_type == 0) ? "Bypass" :
++ ((s.gamut_remap.gamut_adjust_type == 1) ? "HW" : "SW"),
++ s.gamut_remap.temperature_matrix[0].value,
++ s.gamut_remap.temperature_matrix[1].value,
++ s.gamut_remap.temperature_matrix[2].value,
++ s.gamut_remap.temperature_matrix[3].value,
++ s.gamut_remap.temperature_matrix[4].value,
++ s.gamut_remap.temperature_matrix[5].value,
++ s.gamut_remap.temperature_matrix[6].value,
++ s.gamut_remap.temperature_matrix[7].value,
++ s.gamut_remap.temperature_matrix[8].value,
++ s.gamut_remap.temperature_matrix[9].value,
++ s.gamut_remap.temperature_matrix[10].value,
++ s.gamut_remap.temperature_matrix[11].value);
++
+ DTN_INFO("\n");
+ }
+ DTN_INFO("\n");
+diff --git a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+index ed9141a67db37..5b09d95cc5b8f 100644
+--- a/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
++++ b/drivers/gpu/drm/amd/display/dc/hwss/dcn30/dcn30_hwseq.c
+@@ -919,6 +919,9 @@ bool dcn30_apply_idle_power_optimizations(struct dc *dc, bool enable)
+ stream = dc->current_state->streams[0];
+ plane = (stream ? dc->current_state->stream_status[0].plane_states[0] : NULL);
+
++ if (!stream || !plane)
++ return false;
++
+ if (stream && plane) {
+ cursor_cache_enable = stream->cursor_position.enable &&
+ plane->address.grph.cursor_cache_addr.quad_part;
+diff --git a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c
+index 3e6c7be7e2786..5302d2c9c7607 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c
++++ b/drivers/gpu/drm/amd/display/dc/link/hwss/link_hwss_hpo_fixed_vs_pe_retimer_dp.c
+@@ -165,7 +165,12 @@ static void set_hpo_fixed_vs_pe_retimer_dp_link_test_pattern(struct dc_link *lin
+ link_res->hpo_dp_link_enc->funcs->set_link_test_pattern(
+ link_res->hpo_dp_link_enc, tp_params);
+ }
++
+ link->dc->link_srv->dp_trace_source_sequence(link, DPCD_SOURCE_SEQ_AFTER_SET_SOURCE_PATTERN);
++
++ // Give retimer extra time to lock before updating DP_TRAINING_PATTERN_SET to TPS1
++ if (tp_params->dp_phy_pattern == DP_TEST_PATTERN_128b_132b_TPS1_TRAINING_MODE)
++ msleep(30);
+ }
+
+ static void set_hpo_fixed_vs_pe_retimer_dp_lane_settings(struct dc_link *link,
+diff --git a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+index b53ad18dbfbca..ec9ff5f8bdc5d 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
++++ b/drivers/gpu/drm/amd/display/dc/link/link_dpms.c
+@@ -2313,8 +2313,6 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
+
+ dc->hwss.disable_audio_stream(pipe_ctx);
+
+- edp_set_panel_assr(link, pipe_ctx, &panel_mode_dp, false);
+-
+ update_psp_stream_config(pipe_ctx, true);
+ dc->hwss.blank_stream(pipe_ctx);
+
+@@ -2368,6 +2366,7 @@ void link_set_dpms_off(struct pipe_ctx *pipe_ctx)
+ dc->hwss.disable_stream(pipe_ctx);
+ disable_link(pipe_ctx->stream->link, &pipe_ctx->link_res, pipe_ctx->stream->signal);
+ }
++ edp_set_panel_assr(link, pipe_ctx, &panel_mode_dp, false);
+
+ if (pipe_ctx->stream->timing.flags.DSC) {
+ if (dc_is_dp_signal(pipe_ctx->stream->signal))
+diff --git a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
+index 0fcf0b8530acf..564246983f37e 100644
+--- a/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
++++ b/drivers/gpu/drm/amd/display/dc/link/protocols/link_dp_irq_handler.c
+@@ -454,7 +454,8 @@ bool dp_handle_hpd_rx_irq(struct dc_link *link,
+ * If we got sink count changed it means
+ * Downstream port status changed,
+ * then DM should call DC to do the detection.
+- * NOTE: Do not handle link loss on eDP since it is internal link*/
++ * NOTE: Do not handle link loss on eDP since it is internal link
++ */
+ if ((link->connector_signal != SIGNAL_TYPE_EDP) &&
+ dp_parse_link_loss_status(
+ link,
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
+index 0a939437e19f1..6b380e037e3f8 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn20/dcn20_resource.c
+@@ -2193,10 +2193,11 @@ bool dcn20_get_dcc_compression_cap(const struct dc *dc,
+ const struct dc_dcc_surface_param *input,
+ struct dc_surface_dcc_cap *output)
+ {
+- return dc->res_pool->hubbub->funcs->get_dcc_compression_cap(
+- dc->res_pool->hubbub,
+- input,
+- output);
++ if (dc->res_pool->hubbub->funcs->get_dcc_compression_cap)
++ return dc->res_pool->hubbub->funcs->get_dcc_compression_cap(
++ dc->res_pool->hubbub, input, output);
++
++ return false;
+ }
+
+ static void dcn20_destroy_resource_pool(struct resource_pool **pool)
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+index 5fb21a0508cd9..f531ce1d2b1dc 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/amd_powerplay.c
+@@ -929,7 +929,7 @@ static int pp_dpm_switch_power_profile(void *handle,
+ enum PP_SMC_POWER_PROFILE type, bool en)
+ {
+ struct pp_hwmgr *hwmgr = handle;
+- long workload;
++ long workload[1];
+ uint32_t index;
+
+ if (!hwmgr || !hwmgr->pm_en)
+@@ -947,12 +947,12 @@ static int pp_dpm_switch_power_profile(void *handle,
+ hwmgr->workload_mask &= ~(1 << hwmgr->workload_prority[type]);
+ index = fls(hwmgr->workload_mask);
+ index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0;
+- workload = hwmgr->workload_setting[index];
++ workload[0] = hwmgr->workload_setting[index];
+ } else {
+ hwmgr->workload_mask |= (1 << hwmgr->workload_prority[type]);
+ index = fls(hwmgr->workload_mask);
+ index = index <= Workload_Policy_Max ? index - 1 : 0;
+- workload = hwmgr->workload_setting[index];
++ workload[0] = hwmgr->workload_setting[index];
+ }
+
+ if (type == PP_SMC_POWER_PROFILE_COMPUTE &&
+@@ -962,7 +962,7 @@ static int pp_dpm_switch_power_profile(void *handle,
+ }
+
+ if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL)
+- hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0);
++ hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0);
+
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
+index 1d829402cd2e2..f4bd8e9357e22 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/pp_psm.c
+@@ -269,7 +269,7 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set
+ struct pp_power_state *new_ps)
+ {
+ uint32_t index;
+- long workload;
++ long workload[1];
+
+ if (hwmgr->not_vf) {
+ if (!skip_display_settings)
+@@ -294,10 +294,10 @@ int psm_adjust_power_state_dynamic(struct pp_hwmgr *hwmgr, bool skip_display_set
+ if (hwmgr->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL) {
+ index = fls(hwmgr->workload_mask);
+ index = index > 0 && index <= Workload_Policy_Max ? index - 1 : 0;
+- workload = hwmgr->workload_setting[index];
++ workload[0] = hwmgr->workload_setting[index];
+
+- if (hwmgr->power_profile_mode != workload && hwmgr->hwmgr_func->set_power_profile_mode)
+- hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, &workload, 0);
++ if (hwmgr->power_profile_mode != workload[0] && hwmgr->hwmgr_func->set_power_profile_mode)
++ hwmgr->hwmgr_func->set_power_profile_mode(hwmgr, workload, 0);
+ }
+
+ return 0;
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+index 1fcd4451001fa..f1c369945ac5d 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu7_hwmgr.c
+@@ -2957,6 +2957,7 @@ static int smu7_update_edc_leakage_table(struct pp_hwmgr *hwmgr)
+
+ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
+ {
++ struct amdgpu_device *adev = hwmgr->adev;
+ struct smu7_hwmgr *data;
+ int result = 0;
+
+@@ -2993,40 +2994,37 @@ static int smu7_hwmgr_backend_init(struct pp_hwmgr *hwmgr)
+ /* Initalize Dynamic State Adjustment Rule Settings */
+ result = phm_initializa_dynamic_state_adjustment_rule_settings(hwmgr);
+
+- if (0 == result) {
+- struct amdgpu_device *adev = hwmgr->adev;
++ if (result)
++ goto fail;
+
+- data->is_tlu_enabled = false;
++ data->is_tlu_enabled = false;
+
+- hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
++ hwmgr->platform_descriptor.hardwareActivityPerformanceLevels =
+ SMU7_MAX_HARDWARE_POWERLEVELS;
+- hwmgr->platform_descriptor.hardwarePerformanceLevels = 2;
+- hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50;
++ hwmgr->platform_descriptor.hardwarePerformanceLevels = 2;
++ hwmgr->platform_descriptor.minimumClocksReductionPercentage = 50;
+
+- data->pcie_gen_cap = adev->pm.pcie_gen_mask;
+- if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
+- data->pcie_spc_cap = 20;
+- else
+- data->pcie_spc_cap = 16;
+- data->pcie_lane_cap = adev->pm.pcie_mlw_mask;
+-
+- hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */
+-/* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */
+- hwmgr->platform_descriptor.clockStep.engineClock = 500;
+- hwmgr->platform_descriptor.clockStep.memoryClock = 500;
+- smu7_thermal_parameter_init(hwmgr);
+- } else {
+- /* Ignore return value in here, we are cleaning up a mess. */
+- smu7_hwmgr_backend_fini(hwmgr);
+- }
++ data->pcie_gen_cap = adev->pm.pcie_gen_mask;
++ if (data->pcie_gen_cap & CAIL_PCIE_LINK_SPEED_SUPPORT_GEN3)
++ data->pcie_spc_cap = 20;
++ else
++ data->pcie_spc_cap = 16;
++ data->pcie_lane_cap = adev->pm.pcie_mlw_mask;
++
++ hwmgr->platform_descriptor.vbiosInterruptId = 0x20000400; /* IRQ_SOURCE1_SW_INT */
++ /* The true clock step depends on the frequency, typically 4.5 or 9 MHz. Here we use 5. */
++ hwmgr->platform_descriptor.clockStep.engineClock = 500;
++ hwmgr->platform_descriptor.clockStep.memoryClock = 500;
++ smu7_thermal_parameter_init(hwmgr);
+
+ result = smu7_update_edc_leakage_table(hwmgr);
+- if (result) {
+- smu7_hwmgr_backend_fini(hwmgr);
+- return result;
+- }
++ if (result)
++ goto fail;
+
+ return 0;
++fail:
++ smu7_hwmgr_backend_fini(hwmgr);
++ return result;
+ }
+
+ static int smu7_force_dpm_highest(struct pp_hwmgr *hwmgr)
+@@ -3316,8 +3314,7 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
+ const struct pp_power_state *current_ps)
+ {
+ struct amdgpu_device *adev = hwmgr->adev;
+- struct smu7_power_state *smu7_ps =
+- cast_phw_smu7_power_state(&request_ps->hardware);
++ struct smu7_power_state *smu7_ps;
+ uint32_t sclk;
+ uint32_t mclk;
+ struct PP_Clocks minimum_clocks = {0};
+@@ -3334,6 +3331,10 @@ static int smu7_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
+ uint32_t latency;
+ bool latency_allowed = false;
+
++ smu7_ps = cast_phw_smu7_power_state(&request_ps->hardware);
++ if (!smu7_ps)
++ return -EINVAL;
++
+ data->battery_state = (PP_StateUILabel_Battery ==
+ request_ps->classification.ui_label);
+ data->mclk_ignore_signal = false;
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+index b015a601b385a..eb744401e0567 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/smu8_hwmgr.c
+@@ -1065,16 +1065,18 @@ static int smu8_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
+ struct pp_power_state *prequest_ps,
+ const struct pp_power_state *pcurrent_ps)
+ {
+- struct smu8_power_state *smu8_ps =
+- cast_smu8_power_state(&prequest_ps->hardware);
+-
+- const struct smu8_power_state *smu8_current_ps =
+- cast_const_smu8_power_state(&pcurrent_ps->hardware);
+-
++ struct smu8_power_state *smu8_ps;
++ const struct smu8_power_state *smu8_current_ps;
+ struct smu8_hwmgr *data = hwmgr->backend;
+ struct PP_Clocks clocks = {0, 0, 0, 0};
+ bool force_high;
+
++ smu8_ps = cast_smu8_power_state(&prequest_ps->hardware);
++ smu8_current_ps = cast_const_smu8_power_state(&pcurrent_ps->hardware);
++
++ if (!smu8_ps || !smu8_current_ps)
++ return -EINVAL;
++
+ smu8_ps->need_dfs_bypass = true;
+
+ data->battery_state = (PP_StateUILabel_Battery == prequest_ps->classification.ui_label);
+diff --git a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+index 9f5bd998c6bff..f4acdb2267416 100644
+--- a/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
++++ b/drivers/gpu/drm/amd/pm/powerplay/hwmgr/vega10_hwmgr.c
+@@ -3259,8 +3259,7 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
+ const struct pp_power_state *current_ps)
+ {
+ struct amdgpu_device *adev = hwmgr->adev;
+- struct vega10_power_state *vega10_ps =
+- cast_phw_vega10_power_state(&request_ps->hardware);
++ struct vega10_power_state *vega10_ps;
+ uint32_t sclk;
+ uint32_t mclk;
+ struct PP_Clocks minimum_clocks = {0};
+@@ -3278,6 +3277,10 @@ static int vega10_apply_state_adjust_rules(struct pp_hwmgr *hwmgr,
+ uint32_t stable_pstate_sclk = 0, stable_pstate_mclk = 0;
+ uint32_t latency;
+
++ vega10_ps = cast_phw_vega10_power_state(&request_ps->hardware);
++ if (!vega10_ps)
++ return -EINVAL;
++
+ data->battery_state = (PP_StateUILabel_Battery ==
+ request_ps->classification.ui_label);
+
+@@ -3415,13 +3418,17 @@ static int vega10_find_dpm_states_clocks_in_dpm_table(struct pp_hwmgr *hwmgr, co
+ const struct vega10_power_state *vega10_ps =
+ cast_const_phw_vega10_power_state(states->pnew_state);
+ struct vega10_single_dpm_table *sclk_table = &(data->dpm_table.gfx_table);
+- uint32_t sclk = vega10_ps->performance_levels
+- [vega10_ps->performance_level_count - 1].gfx_clock;
+ struct vega10_single_dpm_table *mclk_table = &(data->dpm_table.mem_table);
+- uint32_t mclk = vega10_ps->performance_levels
+- [vega10_ps->performance_level_count - 1].mem_clock;
++ uint32_t sclk, mclk;
+ uint32_t i;
+
++ if (vega10_ps == NULL)
++ return -EINVAL;
++ sclk = vega10_ps->performance_levels
++ [vega10_ps->performance_level_count - 1].gfx_clock;
++ mclk = vega10_ps->performance_levels
++ [vega10_ps->performance_level_count - 1].mem_clock;
++
+ for (i = 0; i < sclk_table->count; i++) {
+ if (sclk == sclk_table->dpm_levels[i].value)
+ break;
+@@ -3728,6 +3735,9 @@ static int vega10_generate_dpm_level_enable_mask(
+ cast_const_phw_vega10_power_state(states->pnew_state);
+ int i;
+
++ if (vega10_ps == NULL)
++ return -EINVAL;
++
+ PP_ASSERT_WITH_CODE(!vega10_trim_dpm_states(hwmgr, vega10_ps),
+ "Attempt to Trim DPM States Failed!",
+ return -1);
+@@ -4995,6 +5005,8 @@ static int vega10_check_states_equal(struct pp_hwmgr *hwmgr,
+
+ vega10_psa = cast_const_phw_vega10_power_state(pstate1);
+ vega10_psb = cast_const_phw_vega10_power_state(pstate2);
++ if (vega10_psa == NULL || vega10_psb == NULL)
++ return -EINVAL;
+
+ /* If the two states don't even have the same number of performance levels
+ * they cannot be the same state.
+@@ -5128,6 +5140,8 @@ static int vega10_set_sclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+ return -EINVAL;
+
+ vega10_ps = cast_phw_vega10_power_state(&ps->hardware);
++ if (vega10_ps == NULL)
++ return -EINVAL;
+
+ vega10_ps->performance_levels
+ [vega10_ps->performance_level_count - 1].gfx_clock =
+@@ -5179,6 +5193,8 @@ static int vega10_set_mclk_od(struct pp_hwmgr *hwmgr, uint32_t value)
+ return -EINVAL;
+
+ vega10_ps = cast_phw_vega10_power_state(&ps->hardware);
++ if (vega10_ps == NULL)
++ return -EINVAL;
+
+ vega10_ps->performance_levels
+ [vega10_ps->performance_level_count - 1].mem_clock =
+@@ -5420,6 +5436,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr)
+ return;
+
+ vega10_ps = cast_phw_vega10_power_state(&ps->hardware);
++ if (vega10_ps == NULL)
++ return;
++
+ max_level = vega10_ps->performance_level_count - 1;
+
+ if (vega10_ps->performance_levels[max_level].gfx_clock !=
+@@ -5442,6 +5461,9 @@ static void vega10_odn_update_power_state(struct pp_hwmgr *hwmgr)
+
+ ps = (struct pp_power_state *)((unsigned long)(hwmgr->ps) + hwmgr->ps_size * (hwmgr->num_ps - 1));
+ vega10_ps = cast_phw_vega10_power_state(&ps->hardware);
++ if (vega10_ps == NULL)
++ return;
++
+ max_level = vega10_ps->performance_level_count - 1;
+
+ if (vega10_ps->performance_levels[max_level].gfx_clock !=
+@@ -5632,6 +5654,8 @@ static int vega10_get_performance_level(struct pp_hwmgr *hwmgr, const struct pp_
+ return -EINVAL;
+
+ vega10_ps = cast_const_phw_vega10_power_state(state);
++ if (vega10_ps == NULL)
++ return -EINVAL;
+
+ i = index > vega10_ps->performance_level_count - 1 ?
+ vega10_ps->performance_level_count - 1 : index;
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+index e1796ecf9c05c..06409133b09b1 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/amdgpu_smu.c
+@@ -2220,7 +2220,7 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
+ {
+ int ret = 0;
+ int index = 0;
+- long workload;
++ long workload[1];
+ struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
+
+ if (!skip_display_settings) {
+@@ -2260,10 +2260,10 @@ static int smu_adjust_power_state_dynamic(struct smu_context *smu,
+ smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM) {
+ index = fls(smu->workload_mask);
+ index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
+- workload = smu->workload_setting[index];
++ workload[0] = smu->workload_setting[index];
+
+- if (smu->power_profile_mode != workload)
+- smu_bump_power_profile_mode(smu, &workload, 0);
++ if (smu->power_profile_mode != workload[0])
++ smu_bump_power_profile_mode(smu, workload, 0);
+ }
+
+ return ret;
+@@ -2313,7 +2313,7 @@ static int smu_switch_power_profile(void *handle,
+ {
+ struct smu_context *smu = handle;
+ struct smu_dpm_context *smu_dpm_ctx = &(smu->smu_dpm);
+- long workload;
++ long workload[1];
+ uint32_t index;
+
+ if (!smu->pm_enabled || !smu->adev->pm.dpm_enabled)
+@@ -2326,17 +2326,17 @@ static int smu_switch_power_profile(void *handle,
+ smu->workload_mask &= ~(1 << smu->workload_prority[type]);
+ index = fls(smu->workload_mask);
+ index = index > 0 && index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
+- workload = smu->workload_setting[index];
++ workload[0] = smu->workload_setting[index];
+ } else {
+ smu->workload_mask |= (1 << smu->workload_prority[type]);
+ index = fls(smu->workload_mask);
+ index = index <= WORKLOAD_POLICY_MAX ? index - 1 : 0;
+- workload = smu->workload_setting[index];
++ workload[0] = smu->workload_setting[index];
+ }
+
+ if (smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_MANUAL &&
+ smu_dpm_ctx->dpm_level != AMD_DPM_FORCED_LEVEL_PERF_DETERMINISM)
+- smu_bump_power_profile_mode(smu, &workload, 0);
++ smu_bump_power_profile_mode(smu, workload, 0);
+
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
+index 6a4f20fccf841..7b0bc9704eacb 100644
+--- a/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
++++ b/drivers/gpu/drm/bridge/analogix/analogix_dp_reg.c
+@@ -1027,7 +1027,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
+ u32 status_reg;
+ u8 *buffer = msg->buffer;
+ unsigned int i;
+- int num_transferred = 0;
+ int ret;
+
+ /* Buffer size of AUX CH is 16 bytes */
+@@ -1079,7 +1078,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
+ reg = buffer[i];
+ writel(reg, dp->reg_base + ANALOGIX_DP_BUF_DATA_0 +
+ 4 * i);
+- num_transferred++;
+ }
+ }
+
+@@ -1127,7 +1125,6 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
+ reg = readl(dp->reg_base + ANALOGIX_DP_BUF_DATA_0 +
+ 4 * i);
+ buffer[i] = (unsigned char)reg;
+- num_transferred++;
+ }
+ }
+
+@@ -1144,7 +1141,7 @@ ssize_t analogix_dp_transfer(struct analogix_dp_device *dp,
+ (msg->request & ~DP_AUX_I2C_MOT) == DP_AUX_NATIVE_READ)
+ msg->reply = DP_AUX_NATIVE_REPLY_ACK;
+
+- return num_transferred > 0 ? num_transferred : -EBUSY;
++ return msg->size;
+
+ aux_error:
+ /* if aux err happen, reset aux */
+diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
+index 68831f4e502a2..fc2ceae61db2d 100644
+--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
++++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
+@@ -4069,6 +4069,7 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
+ if (up_req->msg.req_type == DP_CONNECTION_STATUS_NOTIFY) {
+ const struct drm_dp_connection_status_notify *conn_stat =
+ &up_req->msg.u.conn_stat;
++ bool handle_csn;
+
+ drm_dbg_kms(mgr->dev, "Got CSN: pn: %d ldps:%d ddps: %d mcs: %d ip: %d pdt: %d\n",
+ conn_stat->port_number,
+@@ -4077,6 +4078,16 @@ static int drm_dp_mst_handle_up_req(struct drm_dp_mst_topology_mgr *mgr)
+ conn_stat->message_capability_status,
+ conn_stat->input_port,
+ conn_stat->peer_device_type);
++
++ mutex_lock(&mgr->probe_lock);
++ handle_csn = mgr->mst_primary->link_address_sent;
++ mutex_unlock(&mgr->probe_lock);
++
++ if (!handle_csn) {
++ drm_dbg_kms(mgr->dev, "Got CSN before finish topology probing. Skip it.");
++ kfree(up_req);
++ goto out;
++ }
+ } else if (up_req->msg.req_type == DP_RESOURCE_STATUS_NOTIFY) {
+ const struct drm_dp_resource_status_notify *res_stat =
+ &up_req->msg.u.resource_stat;
+diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
+index 02b1235c6d619..106292d6ed268 100644
+--- a/drivers/gpu/drm/drm_atomic_uapi.c
++++ b/drivers/gpu/drm/drm_atomic_uapi.c
+@@ -1067,23 +1067,16 @@ int drm_atomic_set_property(struct drm_atomic_state *state,
+ }
+
+ if (async_flip &&
+- prop != config->prop_fb_id &&
+- prop != config->prop_in_fence_fd &&
+- prop != config->prop_fb_damage_clips) {
++ (plane_state->plane->type != DRM_PLANE_TYPE_PRIMARY ||
++ (prop != config->prop_fb_id &&
++ prop != config->prop_in_fence_fd &&
++ prop != config->prop_fb_damage_clips))) {
+ ret = drm_atomic_plane_get_property(plane, plane_state,
+ prop, &old_val);
+ ret = drm_atomic_check_prop_changes(ret, old_val, prop_value, prop);
+ break;
+ }
+
+- if (async_flip && plane_state->plane->type != DRM_PLANE_TYPE_PRIMARY) {
+- drm_dbg_atomic(prop->dev,
+- "[OBJECT:%d] Only primary planes can be changed during async flip\n",
+- obj->id);
+- ret = -EINVAL;
+- break;
+- }
+-
+ ret = drm_atomic_plane_set_property(plane,
+ plane_state, file_priv,
+ prop, prop_value);
+diff --git a/drivers/gpu/drm/drm_client_modeset.c b/drivers/gpu/drm/drm_client_modeset.c
+index 31af5cf37a099..cee5eafbfb81a 100644
+--- a/drivers/gpu/drm/drm_client_modeset.c
++++ b/drivers/gpu/drm/drm_client_modeset.c
+@@ -880,6 +880,11 @@ int drm_client_modeset_probe(struct drm_client_dev *client, unsigned int width,
+
+ kfree(modeset->mode);
+ modeset->mode = drm_mode_duplicate(dev, mode);
++ if (!modeset->mode) {
++ ret = -ENOMEM;
++ break;
++ }
++
+ drm_connector_get(connector);
+ modeset->connectors[modeset->num_connectors++] = connector;
+ modeset->x = offset->x;
+diff --git a/drivers/gpu/drm/i915/display/intel_backlight.c b/drivers/gpu/drm/i915/display/intel_backlight.c
+index 071668bfe5d14..6c3333136737e 100644
+--- a/drivers/gpu/drm/i915/display/intel_backlight.c
++++ b/drivers/gpu/drm/i915/display/intel_backlight.c
+@@ -1449,6 +1449,9 @@ bxt_setup_backlight(struct intel_connector *connector, enum pipe unused)
+
+ static int cnp_num_backlight_controllers(struct drm_i915_private *i915)
+ {
++ if (INTEL_PCH_TYPE(i915) >= PCH_MTL)
++ return 2;
++
+ if (INTEL_PCH_TYPE(i915) >= PCH_DG1)
+ return 1;
+
+diff --git a/drivers/gpu/drm/i915/display/intel_pps.c b/drivers/gpu/drm/i915/display/intel_pps.c
+index 0ccbf9a85914c..eca07436d1bcd 100644
+--- a/drivers/gpu/drm/i915/display/intel_pps.c
++++ b/drivers/gpu/drm/i915/display/intel_pps.c
+@@ -351,6 +351,9 @@ static int intel_num_pps(struct drm_i915_private *i915)
+ if (IS_GEMINILAKE(i915) || IS_BROXTON(i915))
+ return 2;
+
++ if (INTEL_PCH_TYPE(i915) >= PCH_MTL)
++ return 2;
++
+ if (INTEL_PCH_TYPE(i915) >= PCH_DG1)
+ return 1;
+
+diff --git a/drivers/gpu/drm/i915/gem/i915_gem_mman.c b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+index a2195e28b625f..cac6d4184506c 100644
+--- a/drivers/gpu/drm/i915/gem/i915_gem_mman.c
++++ b/drivers/gpu/drm/i915/gem/i915_gem_mman.c
+@@ -290,6 +290,41 @@ static vm_fault_t vm_fault_cpu(struct vm_fault *vmf)
+ return i915_error_to_vmf_fault(err);
+ }
+
++static void set_address_limits(struct vm_area_struct *area,
++ struct i915_vma *vma,
++ unsigned long obj_offset,
++ unsigned long *start_vaddr,
++ unsigned long *end_vaddr)
++{
++ unsigned long vm_start, vm_end, vma_size; /* user's memory parameters */
++ long start, end; /* memory boundaries */
++
++ /*
++ * Let's move into the ">> PAGE_SHIFT"
++ * domain to be sure not to lose bits
++ */
++ vm_start = area->vm_start >> PAGE_SHIFT;
++ vm_end = area->vm_end >> PAGE_SHIFT;
++ vma_size = vma->size >> PAGE_SHIFT;
++
++ /*
++ * Calculate the memory boundaries by considering the offset
++ * provided by the user during memory mapping and the offset
++ * provided for the partial mapping.
++ */
++ start = vm_start;
++ start -= obj_offset;
++ start += vma->gtt_view.partial.offset;
++ end = start + vma_size;
++
++ start = max_t(long, start, vm_start);
++ end = min_t(long, end, vm_end);
++
++ /* Let's move back into the "<< PAGE_SHIFT" domain */
++ *start_vaddr = (unsigned long)start << PAGE_SHIFT;
++ *end_vaddr = (unsigned long)end << PAGE_SHIFT;
++}
++
+ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
+ {
+ #define MIN_CHUNK_PAGES (SZ_1M >> PAGE_SHIFT)
+@@ -302,14 +337,18 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
+ struct i915_ggtt *ggtt = to_gt(i915)->ggtt;
+ bool write = area->vm_flags & VM_WRITE;
+ struct i915_gem_ww_ctx ww;
++ unsigned long obj_offset;
++ unsigned long start, end; /* memory boundaries */
+ intel_wakeref_t wakeref;
+ struct i915_vma *vma;
+ pgoff_t page_offset;
++ unsigned long pfn;
+ int srcu;
+ int ret;
+
+- /* We don't use vmf->pgoff since that has the fake offset */
++ obj_offset = area->vm_pgoff - drm_vma_node_start(&mmo->vma_node);
+ page_offset = (vmf->address - area->vm_start) >> PAGE_SHIFT;
++ page_offset += obj_offset;
+
+ trace_i915_gem_object_fault(obj, page_offset, true, write);
+
+@@ -402,12 +441,14 @@ static vm_fault_t vm_fault_gtt(struct vm_fault *vmf)
+ if (ret)
+ goto err_unpin;
+
++ set_address_limits(area, vma, obj_offset, &start, &end);
++
++ pfn = (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT;
++ pfn += (start - area->vm_start) >> PAGE_SHIFT;
++ pfn += obj_offset - vma->gtt_view.partial.offset;
++
+ /* Finally, remap it using the new GTT offset */
+- ret = remap_io_mapping(area,
+- area->vm_start + (vma->gtt_view.partial.offset << PAGE_SHIFT),
+- (ggtt->gmadr.start + i915_ggtt_offset(vma)) >> PAGE_SHIFT,
+- min_t(u64, vma->size, area->vm_end - area->vm_start),
+- &ggtt->iomap);
++ ret = remap_io_mapping(area, start, pfn, end - start, &ggtt->iomap);
+ if (ret)
+ goto err_fence;
+
+@@ -1084,6 +1125,8 @@ int i915_gem_fb_mmap(struct drm_i915_gem_object *obj, struct vm_area_struct *vma
+ mmo = mmap_offset_attach(obj, mmap_type, NULL);
+ if (IS_ERR(mmo))
+ return PTR_ERR(mmo);
++
++ vma->vm_pgoff += drm_vma_node_start(&mmo->vma_node);
+ }
+
+ /*
+diff --git a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+index e6f177183c0fa..5c72462d1f57e 100644
+--- a/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
++++ b/drivers/gpu/drm/i915/gem/i915_gem_ttm.c
+@@ -165,7 +165,6 @@ i915_ttm_placement_from_obj(const struct drm_i915_gem_object *obj,
+ i915_ttm_place_from_region(num_allowed ? obj->mm.placements[0] :
+ obj->mm.region, &places[0], obj->bo_offset,
+ obj->base.size, flags);
+- places[0].flags |= TTM_PL_FLAG_DESIRED;
+
+ /* Cache this on object? */
+ for (i = 0; i < num_allowed; ++i) {
+@@ -779,13 +778,16 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
+ .interruptible = true,
+ .no_wait_gpu = false,
+ };
+- int real_num_busy;
++ struct ttm_placement initial_placement;
++ struct ttm_place initial_place;
+ int ret;
+
+ /* First try only the requested placement. No eviction. */
+- real_num_busy = placement->num_placement;
+- placement->num_placement = 1;
+- ret = ttm_bo_validate(bo, placement, &ctx);
++ initial_placement.num_placement = 1;
++ memcpy(&initial_place, placement->placement, sizeof(struct ttm_place));
++ initial_place.flags |= TTM_PL_FLAG_DESIRED;
++ initial_placement.placement = &initial_place;
++ ret = ttm_bo_validate(bo, &initial_placement, &ctx);
+ if (ret) {
+ ret = i915_ttm_err_to_gem(ret);
+ /*
+@@ -800,7 +802,6 @@ static int __i915_ttm_get_pages(struct drm_i915_gem_object *obj,
+ * If the initial attempt fails, allow all accepted placements,
+ * evicting if necessary.
+ */
+- placement->num_placement = real_num_busy;
+ ret = ttm_bo_validate(bo, placement, &ctx);
+ if (ret)
+ return i915_ttm_err_to_gem(ret);
+diff --git a/drivers/gpu/drm/lima/lima_drv.c b/drivers/gpu/drm/lima/lima_drv.c
+index 739c865b556f8..10bce18b7c31c 100644
+--- a/drivers/gpu/drm/lima/lima_drv.c
++++ b/drivers/gpu/drm/lima/lima_drv.c
+@@ -501,3 +501,4 @@ module_platform_driver(lima_platform_driver);
+ MODULE_AUTHOR("Lima Project Developers");
+ MODULE_DESCRIPTION("Lima DRM Driver");
+ MODULE_LICENSE("GPL v2");
++MODULE_SOFTDEP("pre: governor_simpleondemand");
+diff --git a/drivers/gpu/drm/mgag200/mgag200_i2c.c b/drivers/gpu/drm/mgag200/mgag200_i2c.c
+index 423eb302be7eb..4caeb68f3010c 100644
+--- a/drivers/gpu/drm/mgag200/mgag200_i2c.c
++++ b/drivers/gpu/drm/mgag200/mgag200_i2c.c
+@@ -31,6 +31,8 @@
+ #include <linux/i2c.h>
+ #include <linux/pci.h>
+
++#include <drm/drm_managed.h>
++
+ #include "mgag200_drv.h"
+
+ static int mga_i2c_read_gpio(struct mga_device *mdev)
+@@ -86,7 +88,7 @@ static int mga_gpio_getscl(void *data)
+ return (mga_i2c_read_gpio(mdev) & i2c->clock) ? 1 : 0;
+ }
+
+-static void mgag200_i2c_release(void *res)
++static void mgag200_i2c_release(struct drm_device *dev, void *res)
+ {
+ struct mga_i2c_chan *i2c = res;
+
+@@ -114,7 +116,7 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c)
+ i2c->adapter.algo_data = &i2c->bit;
+
+ i2c->bit.udelay = 10;
+- i2c->bit.timeout = 2;
++ i2c->bit.timeout = usecs_to_jiffies(2200);
+ i2c->bit.data = i2c;
+ i2c->bit.setsda = mga_gpio_setsda;
+ i2c->bit.setscl = mga_gpio_setscl;
+@@ -125,5 +127,5 @@ int mgag200_i2c_init(struct mga_device *mdev, struct mga_i2c_chan *i2c)
+ if (ret)
+ return ret;
+
+- return devm_add_action_or_reset(dev->dev, mgag200_i2c_release, i2c);
++ return drmm_add_action_or_reset(dev, mgag200_i2c_release, i2c);
+ }
+diff --git a/drivers/gpu/drm/radeon/pptable.h b/drivers/gpu/drm/radeon/pptable.h
+index b7f22597ee95e..969a8fb0ee9e0 100644
+--- a/drivers/gpu/drm/radeon/pptable.h
++++ b/drivers/gpu/drm/radeon/pptable.h
+@@ -439,7 +439,7 @@ typedef struct _StateArray{
+ //how many states we have
+ UCHAR ucNumEntries;
+
+- ATOM_PPLIB_STATE_V2 states[] __counted_by(ucNumEntries);
++ ATOM_PPLIB_STATE_V2 states[] /* __counted_by(ucNumEntries) */;
+ }StateArray;
+
+
+diff --git a/drivers/gpu/drm/tests/drm_gem_shmem_test.c b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
+index 91202e40cde94..60c652782761b 100644
+--- a/drivers/gpu/drm/tests/drm_gem_shmem_test.c
++++ b/drivers/gpu/drm/tests/drm_gem_shmem_test.c
+@@ -102,6 +102,17 @@ static void drm_gem_shmem_test_obj_create_private(struct kunit *test)
+
+ sg_init_one(sgt->sgl, buf, TEST_SIZE);
+
++ /*
++ * Set the DMA mask to 64-bits and map the sgtables
++ * otherwise drm_gem_shmem_free will cause a warning
++ * on debug kernels.
++ */
++ ret = dma_set_mask(drm_dev->dev, DMA_BIT_MASK(64));
++ KUNIT_ASSERT_EQ(test, ret, 0);
++
++ ret = dma_map_sgtable(drm_dev->dev, sgt, DMA_BIDIRECTIONAL, 0);
++ KUNIT_ASSERT_EQ(test, ret, 0);
++
+ /* Init a mock DMA-BUF */
+ buf_mock.size = TEST_SIZE;
+ attach_mock.dmabuf = &buf_mock;
+diff --git a/drivers/gpu/drm/xe/regs/xe_engine_regs.h b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+index af71b87d80301..03c6d4d50a839 100644
+--- a/drivers/gpu/drm/xe/regs/xe_engine_regs.h
++++ b/drivers/gpu/drm/xe/regs/xe_engine_regs.h
+@@ -44,9 +44,10 @@
+ #define GSCCS_RING_BASE 0x11a000
+
+ #define RING_TAIL(base) XE_REG((base) + 0x30)
++#define TAIL_ADDR REG_GENMASK(20, 3)
+
+ #define RING_HEAD(base) XE_REG((base) + 0x34)
+-#define HEAD_ADDR 0x001FFFFC
++#define HEAD_ADDR REG_GENMASK(20, 2)
+
+ #define RING_START(base) XE_REG((base) + 0x38)
+
+@@ -135,7 +136,6 @@
+ #define RING_VALID_MASK 0x00000001
+ #define RING_VALID 0x00000001
+ #define STOP_RING REG_BIT(8)
+-#define TAIL_ADDR 0x001FFFF8
+
+ #define RING_CTX_TIMESTAMP(base) XE_REG((base) + 0x3a8)
+ #define CSBE_DEBUG_STATUS(base) XE_REG((base) + 0x3fc)
+diff --git a/drivers/gpu/drm/xe/xe_guc_submit.c b/drivers/gpu/drm/xe/xe_guc_submit.c
+index e4e3658e6a138..0f42971ff0a83 100644
+--- a/drivers/gpu/drm/xe/xe_guc_submit.c
++++ b/drivers/gpu/drm/xe/xe_guc_submit.c
+@@ -1429,8 +1429,8 @@ static void guc_exec_queue_stop(struct xe_guc *guc, struct xe_exec_queue *q)
+ !xe_sched_job_completed(job)) ||
+ xe_sched_invalidate_job(job, 2)) {
+ trace_xe_sched_job_ban(job);
+- xe_sched_tdr_queue_imm(&q->guc->sched);
+ set_exec_queue_banned(q);
++ xe_sched_tdr_queue_imm(&q->guc->sched);
+ }
+ }
+ }
+diff --git a/drivers/gpu/drm/xe/xe_hwmon.c b/drivers/gpu/drm/xe/xe_hwmon.c
+index 453e601ddd5e6..d37f1dea9f8b8 100644
+--- a/drivers/gpu/drm/xe/xe_hwmon.c
++++ b/drivers/gpu/drm/xe/xe_hwmon.c
+@@ -200,9 +200,10 @@ static int xe_hwmon_power_max_write(struct xe_hwmon *hwmon, int channel, long va
+ PKG_PWR_LIM_1_EN, 0, channel);
+
+ if (reg_val & PKG_PWR_LIM_1_EN) {
++ drm_warn(>_to_xe(hwmon->gt)->drm, "PL1 disable is not supported!\n");
+ ret = -EOPNOTSUPP;
+- goto unlock;
+ }
++ goto unlock;
+ }
+
+ /* Computation in 64-bits to avoid overflow. Round to nearest. */
+diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
+index 615bbc372ac62..d7bf7bc9dc145 100644
+--- a/drivers/gpu/drm/xe/xe_lrc.c
++++ b/drivers/gpu/drm/xe/xe_lrc.c
+@@ -1354,7 +1354,10 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
+ if (!snapshot)
+ return NULL;
+
+- snapshot->context_desc = lower_32_bits(xe_lrc_ggtt_addr(lrc));
++ if (lrc->bo && lrc->bo->vm)
++ xe_vm_get(lrc->bo->vm);
++
++ snapshot->context_desc = xe_lrc_ggtt_addr(lrc);
+ snapshot->head = xe_lrc_ring_head(lrc);
+ snapshot->tail.internal = lrc->ring.tail;
+ snapshot->tail.memory = xe_lrc_read_ctx_reg(lrc, CTX_RING_TAIL);
+@@ -1370,12 +1373,14 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
+ void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot)
+ {
+ struct xe_bo *bo;
++ struct xe_vm *vm;
+ struct iosys_map src;
+
+ if (!snapshot)
+ return;
+
+ bo = snapshot->lrc_bo;
++ vm = bo->vm;
+ snapshot->lrc_bo = NULL;
+
+ snapshot->lrc_snapshot = kvmalloc(snapshot->lrc_size, GFP_KERNEL);
+@@ -1395,6 +1400,8 @@ void xe_lrc_snapshot_capture_delayed(struct xe_lrc_snapshot *snapshot)
+ dma_resv_unlock(bo->ttm.base.resv);
+ put_bo:
+ xe_bo_put(bo);
++ if (vm)
++ xe_vm_put(vm);
+ }
+
+ void xe_lrc_snapshot_print(struct xe_lrc_snapshot *snapshot, struct drm_printer *p)
+@@ -1440,7 +1447,13 @@ void xe_lrc_snapshot_free(struct xe_lrc_snapshot *snapshot)
+ return;
+
+ kvfree(snapshot->lrc_snapshot);
+- if (snapshot->lrc_bo)
++ if (snapshot->lrc_bo) {
++ struct xe_vm *vm;
++
++ vm = snapshot->lrc_bo->vm;
+ xe_bo_put(snapshot->lrc_bo);
++ if (vm)
++ xe_vm_put(vm);
++ }
+ kfree(snapshot);
+ }
+diff --git a/drivers/gpu/drm/xe/xe_preempt_fence.c b/drivers/gpu/drm/xe/xe_preempt_fence.c
+index 7d50c6e89d8e7..5b243b7feb59d 100644
+--- a/drivers/gpu/drm/xe/xe_preempt_fence.c
++++ b/drivers/gpu/drm/xe/xe_preempt_fence.c
+@@ -23,11 +23,19 @@ static void preempt_fence_work_func(struct work_struct *w)
+ q->ops->suspend_wait(q);
+
+ dma_fence_signal(&pfence->base);
+- dma_fence_end_signalling(cookie);
+-
++ /*
++ * Opt for keep everything in the fence critical section. This looks really strange since we
++ * have just signalled the fence, however the preempt fences are all signalled via single
++ * global ordered-wq, therefore anything that happens in this callback can easily block
++ * progress on the entire wq, which itself may prevent other published preempt fences from
++ * ever signalling. Therefore try to keep everything here in the callback in the fence
++ * critical section. For example if something below grabs a scary lock like vm->lock,
++ * lockdep should complain since we also hold that lock whilst waiting on preempt fences to
++ * complete.
++ */
+ xe_vm_queue_rebind_worker(q->vm);
+-
+ xe_exec_queue_put(q);
++ dma_fence_end_signalling(cookie);
+ }
+
+ static const char *
+diff --git a/drivers/gpu/drm/xe/xe_rtp.c b/drivers/gpu/drm/xe/xe_rtp.c
+index fb44cc7521d8c..10326bd1bfa3b 100644
+--- a/drivers/gpu/drm/xe/xe_rtp.c
++++ b/drivers/gpu/drm/xe/xe_rtp.c
+@@ -200,7 +200,7 @@ static void rtp_mark_active(struct xe_device *xe,
+ if (first == last)
+ bitmap_set(ctx->active_entries, first, 1);
+ else
+- bitmap_set(ctx->active_entries, first, last - first + 2);
++ bitmap_set(ctx->active_entries, first, last - first + 1);
+ }
+
+ /**
+diff --git a/drivers/gpu/drm/xe/xe_sync.c b/drivers/gpu/drm/xe/xe_sync.c
+index 65f1f16282356..2bfff998458ba 100644
+--- a/drivers/gpu/drm/xe/xe_sync.c
++++ b/drivers/gpu/drm/xe/xe_sync.c
+@@ -263,7 +263,7 @@ void xe_sync_entry_cleanup(struct xe_sync_entry *sync)
+ if (sync->fence)
+ dma_fence_put(sync->fence);
+ if (sync->chain_fence)
+- dma_fence_put(&sync->chain_fence->base);
++ dma_fence_chain_free(sync->chain_fence);
+ if (sync->ufence)
+ user_fence_put(sync->ufence);
+ }
+diff --git a/drivers/hwmon/corsair-psu.c b/drivers/hwmon/corsair-psu.c
+index 2c7c92272fe39..f8f22b8a67cdf 100644
+--- a/drivers/hwmon/corsair-psu.c
++++ b/drivers/hwmon/corsair-psu.c
+@@ -875,15 +875,16 @@ static const struct hid_device_id corsairpsu_idtable[] = {
+ { HID_USB_DEVICE(0x1b1c, 0x1c04) }, /* Corsair HX650i */
+ { HID_USB_DEVICE(0x1b1c, 0x1c05) }, /* Corsair HX750i */
+ { HID_USB_DEVICE(0x1b1c, 0x1c06) }, /* Corsair HX850i */
+- { HID_USB_DEVICE(0x1b1c, 0x1c07) }, /* Corsair HX1000i Series 2022 */
+- { HID_USB_DEVICE(0x1b1c, 0x1c08) }, /* Corsair HX1200i */
++ { HID_USB_DEVICE(0x1b1c, 0x1c07) }, /* Corsair HX1000i Legacy */
++ { HID_USB_DEVICE(0x1b1c, 0x1c08) }, /* Corsair HX1200i Legacy */
+ { HID_USB_DEVICE(0x1b1c, 0x1c09) }, /* Corsair RM550i */
+ { HID_USB_DEVICE(0x1b1c, 0x1c0a) }, /* Corsair RM650i */
+ { HID_USB_DEVICE(0x1b1c, 0x1c0b) }, /* Corsair RM750i */
+ { HID_USB_DEVICE(0x1b1c, 0x1c0c) }, /* Corsair RM850i */
+ { HID_USB_DEVICE(0x1b1c, 0x1c0d) }, /* Corsair RM1000i */
+ { HID_USB_DEVICE(0x1b1c, 0x1c1e) }, /* Corsair HX1000i Series 2023 */
+- { HID_USB_DEVICE(0x1b1c, 0x1c1f) }, /* Corsair HX1500i Series 2022 and 2023 */
++ { HID_USB_DEVICE(0x1b1c, 0x1c1f) }, /* Corsair HX1500i Legacy and Series 2023 */
++ { HID_USB_DEVICE(0x1b1c, 0x1c23) }, /* Corsair HX1200i Series 2023 */
+ { },
+ };
+ MODULE_DEVICE_TABLE(hid, corsairpsu_idtable);
+diff --git a/drivers/i2c/busses/i2c-qcom-geni.c b/drivers/i2c/busses/i2c-qcom-geni.c
+index 0a8b95ce35f79..365e37bba0f33 100644
+--- a/drivers/i2c/busses/i2c-qcom-geni.c
++++ b/drivers/i2c/busses/i2c-qcom-geni.c
+@@ -990,8 +990,11 @@ static int __maybe_unused geni_i2c_runtime_resume(struct device *dev)
+ return ret;
+
+ ret = geni_se_resources_on(&gi2c->se);
+- if (ret)
++ if (ret) {
++ clk_disable_unprepare(gi2c->core_clk);
++ geni_icc_disable(&gi2c->se);
+ return ret;
++ }
+
+ enable_irq(gi2c->irq);
+ gi2c->suspended = 0;
+diff --git a/drivers/i2c/i2c-smbus.c b/drivers/i2c/i2c-smbus.c
+index 97f338b123b11..25bc7b8d98f0d 100644
+--- a/drivers/i2c/i2c-smbus.c
++++ b/drivers/i2c/i2c-smbus.c
+@@ -34,6 +34,7 @@ static int smbus_do_alert(struct device *dev, void *addrp)
+ struct i2c_client *client = i2c_verify_client(dev);
+ struct alert_data *data = addrp;
+ struct i2c_driver *driver;
++ int ret;
+
+ if (!client || client->addr != data->addr)
+ return 0;
+@@ -47,16 +48,47 @@ static int smbus_do_alert(struct device *dev, void *addrp)
+ device_lock(dev);
+ if (client->dev.driver) {
+ driver = to_i2c_driver(client->dev.driver);
+- if (driver->alert)
++ if (driver->alert) {
++ /* Stop iterating after we find the device */
+ driver->alert(client, data->type, data->data);
+- else
++ ret = -EBUSY;
++ } else {
+ dev_warn(&client->dev, "no driver alert()!\n");
+- } else
++ ret = -EOPNOTSUPP;
++ }
++ } else {
+ dev_dbg(&client->dev, "alert with no driver\n");
++ ret = -ENODEV;
++ }
++ device_unlock(dev);
++
++ return ret;
++}
++
++/* Same as above, but call back all drivers with alert handler */
++
++static int smbus_do_alert_force(struct device *dev, void *addrp)
++{
++ struct i2c_client *client = i2c_verify_client(dev);
++ struct alert_data *data = addrp;
++ struct i2c_driver *driver;
++
++ if (!client || (client->flags & I2C_CLIENT_TEN))
++ return 0;
++
++ /*
++ * Drivers should either disable alerts, or provide at least
++ * a minimal handler. Lock so the driver won't change.
++ */
++ device_lock(dev);
++ if (client->dev.driver) {
++ driver = to_i2c_driver(client->dev.driver);
++ if (driver->alert)
++ driver->alert(client, data->type, data->data);
++ }
+ device_unlock(dev);
+
+- /* Stop iterating after we find the device */
+- return -EBUSY;
++ return 0;
+ }
+
+ /*
+@@ -67,6 +99,7 @@ static irqreturn_t smbus_alert(int irq, void *d)
+ {
+ struct i2c_smbus_alert *alert = d;
+ struct i2c_client *ara;
++ unsigned short prev_addr = I2C_CLIENT_END; /* Not a valid address */
+
+ ara = alert->ara;
+
+@@ -94,8 +127,25 @@ static irqreturn_t smbus_alert(int irq, void *d)
+ data.addr, data.data);
+
+ /* Notify driver for the device which issued the alert */
+- device_for_each_child(&ara->adapter->dev, &data,
+- smbus_do_alert);
++ status = device_for_each_child(&ara->adapter->dev, &data,
++ smbus_do_alert);
++ /*
++ * If we read the same address more than once, and the alert
++ * was not handled by a driver, it won't do any good to repeat
++ * the loop because it will never terminate. Try again, this
++ * time calling the alert handlers of all devices connected to
++ * the bus, and abort the loop afterwards. If this helps, we
++ * are all set. If it doesn't, there is nothing else we can do,
++ * so we might as well abort the loop.
++ * Note: This assumes that a driver with alert handler handles
++ * the alert properly and clears it if necessary.
++ */
++ if (data.addr == prev_addr && status != -EBUSY) {
++ device_for_each_child(&ara->adapter->dev, &data,
++ smbus_do_alert_force);
++ break;
++ }
++ prev_addr = data.addr;
+ }
+
+ return IRQ_HANDLED;
+diff --git a/drivers/irqchip/irq-loongarch-cpu.c b/drivers/irqchip/irq-loongarch-cpu.c
+index 9d8f2c4060431..b35903a06902f 100644
+--- a/drivers/irqchip/irq-loongarch-cpu.c
++++ b/drivers/irqchip/irq-loongarch-cpu.c
+@@ -18,11 +18,13 @@ struct fwnode_handle *cpuintc_handle;
+
+ static u32 lpic_gsi_to_irq(u32 gsi)
+ {
++ int irq = 0;
++
+ /* Only pch irqdomain transferring is required for LoongArch. */
+ if (gsi >= GSI_MIN_PCH_IRQ && gsi <= GSI_MAX_PCH_IRQ)
+- return acpi_register_gsi(NULL, gsi, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_HIGH);
++ irq = acpi_register_gsi(NULL, gsi, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_HIGH);
+
+- return 0;
++ return (irq > 0) ? irq : 0;
+ }
+
+ static struct fwnode_handle *lpic_get_gsi_domain_id(u32 gsi)
+diff --git a/drivers/irqchip/irq-mbigen.c b/drivers/irqchip/irq-mbigen.c
+index 58881d3139792..244a8d489cac6 100644
+--- a/drivers/irqchip/irq-mbigen.c
++++ b/drivers/irqchip/irq-mbigen.c
+@@ -64,6 +64,20 @@ struct mbigen_device {
+ void __iomem *base;
+ };
+
++static inline unsigned int get_mbigen_node_offset(unsigned int nid)
++{
++ unsigned int offset = nid * MBIGEN_NODE_OFFSET;
++
++ /*
++ * To avoid touched clear register in unexpected way, we need to directly
++ * skip clear register when access to more than 10 mbigen nodes.
++ */
++ if (nid >= (REG_MBIGEN_CLEAR_OFFSET / MBIGEN_NODE_OFFSET))
++ offset += MBIGEN_NODE_OFFSET;
++
++ return offset;
++}
++
+ static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq)
+ {
+ unsigned int nid, pin;
+@@ -72,8 +86,7 @@ static inline unsigned int get_mbigen_vec_reg(irq_hw_number_t hwirq)
+ nid = hwirq / IRQS_PER_MBIGEN_NODE + 1;
+ pin = hwirq % IRQS_PER_MBIGEN_NODE;
+
+- return pin * 4 + nid * MBIGEN_NODE_OFFSET
+- + REG_MBIGEN_VEC_OFFSET;
++ return pin * 4 + get_mbigen_node_offset(nid) + REG_MBIGEN_VEC_OFFSET;
+ }
+
+ static inline void get_mbigen_type_reg(irq_hw_number_t hwirq,
+@@ -88,8 +101,7 @@ static inline void get_mbigen_type_reg(irq_hw_number_t hwirq,
+ *mask = 1 << (irq_ofst % 32);
+ ofst = irq_ofst / 32 * 4;
+
+- *addr = ofst + nid * MBIGEN_NODE_OFFSET
+- + REG_MBIGEN_TYPE_OFFSET;
++ *addr = ofst + get_mbigen_node_offset(nid) + REG_MBIGEN_TYPE_OFFSET;
+ }
+
+ static inline void get_mbigen_clear_reg(irq_hw_number_t hwirq,
+diff --git a/drivers/irqchip/irq-meson-gpio.c b/drivers/irqchip/irq-meson-gpio.c
+index 9a1791908598d..a4c3b57098ba0 100644
+--- a/drivers/irqchip/irq-meson-gpio.c
++++ b/drivers/irqchip/irq-meson-gpio.c
+@@ -178,7 +178,7 @@ struct meson_gpio_irq_controller {
+ void __iomem *base;
+ u32 channel_irqs[MAX_NUM_CHANNEL];
+ DECLARE_BITMAP(channel_map, MAX_NUM_CHANNEL);
+- spinlock_t lock;
++ raw_spinlock_t lock;
+ };
+
+ static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
+@@ -187,14 +187,14 @@ static void meson_gpio_irq_update_bits(struct meson_gpio_irq_controller *ctl,
+ unsigned long flags;
+ u32 tmp;
+
+- spin_lock_irqsave(&ctl->lock, flags);
++ raw_spin_lock_irqsave(&ctl->lock, flags);
+
+ tmp = readl_relaxed(ctl->base + reg);
+ tmp &= ~mask;
+ tmp |= val;
+ writel_relaxed(tmp, ctl->base + reg);
+
+- spin_unlock_irqrestore(&ctl->lock, flags);
++ raw_spin_unlock_irqrestore(&ctl->lock, flags);
+ }
+
+ static void meson_gpio_irq_init_dummy(struct meson_gpio_irq_controller *ctl)
+@@ -244,12 +244,12 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
+ unsigned long flags;
+ unsigned int idx;
+
+- spin_lock_irqsave(&ctl->lock, flags);
++ raw_spin_lock_irqsave(&ctl->lock, flags);
+
+ /* Find a free channel */
+ idx = find_first_zero_bit(ctl->channel_map, ctl->params->nr_channels);
+ if (idx >= ctl->params->nr_channels) {
+- spin_unlock_irqrestore(&ctl->lock, flags);
++ raw_spin_unlock_irqrestore(&ctl->lock, flags);
+ pr_err("No channel available\n");
+ return -ENOSPC;
+ }
+@@ -257,7 +257,7 @@ meson_gpio_irq_request_channel(struct meson_gpio_irq_controller *ctl,
+ /* Mark the channel as used */
+ set_bit(idx, ctl->channel_map);
+
+- spin_unlock_irqrestore(&ctl->lock, flags);
++ raw_spin_unlock_irqrestore(&ctl->lock, flags);
+
+ /*
+ * Setup the mux of the channel to route the signal of the pad
+@@ -567,7 +567,7 @@ static int meson_gpio_irq_of_init(struct device_node *node, struct device_node *
+ if (!ctl)
+ return -ENOMEM;
+
+- spin_lock_init(&ctl->lock);
++ raw_spin_lock_init(&ctl->lock);
+
+ ctl->base = of_iomap(node, 0);
+ if (!ctl->base) {
+diff --git a/drivers/irqchip/irq-riscv-aplic-msi.c b/drivers/irqchip/irq-riscv-aplic-msi.c
+index 028444af48bd5..d7773f76e5d0a 100644
+--- a/drivers/irqchip/irq-riscv-aplic-msi.c
++++ b/drivers/irqchip/irq-riscv-aplic-msi.c
+@@ -32,15 +32,10 @@ static void aplic_msi_irq_unmask(struct irq_data *d)
+ aplic_irq_unmask(d);
+ }
+
+-static void aplic_msi_irq_eoi(struct irq_data *d)
++static void aplic_msi_irq_retrigger_level(struct irq_data *d)
+ {
+ struct aplic_priv *priv = irq_data_get_irq_chip_data(d);
+
+- /*
+- * EOI handling is required only for level-triggered interrupts
+- * when APLIC is in MSI mode.
+- */
+-
+ switch (irqd_get_trigger_type(d)) {
+ case IRQ_TYPE_LEVEL_LOW:
+ case IRQ_TYPE_LEVEL_HIGH:
+@@ -59,6 +54,29 @@ static void aplic_msi_irq_eoi(struct irq_data *d)
+ }
+ }
+
++static void aplic_msi_irq_eoi(struct irq_data *d)
++{
++ /*
++ * EOI handling is required only for level-triggered interrupts
++ * when APLIC is in MSI mode.
++ */
++ aplic_msi_irq_retrigger_level(d);
++}
++
++static int aplic_msi_irq_set_type(struct irq_data *d, unsigned int type)
++{
++ int rc = aplic_irq_set_type(d, type);
++
++ if (rc)
++ return rc;
++ /*
++ * Updating sourcecfg register for level-triggered interrupts
++ * requires interrupt retriggering when APLIC is in MSI mode.
++ */
++ aplic_msi_irq_retrigger_level(d);
++ return 0;
++}
++
+ static void aplic_msi_write_msg(struct irq_data *d, struct msi_msg *msg)
+ {
+ unsigned int group_index, hart_index, guest_index, val;
+@@ -130,7 +148,7 @@ static const struct msi_domain_template aplic_msi_template = {
+ .name = "APLIC-MSI",
+ .irq_mask = aplic_msi_irq_mask,
+ .irq_unmask = aplic_msi_irq_unmask,
+- .irq_set_type = aplic_irq_set_type,
++ .irq_set_type = aplic_msi_irq_set_type,
+ .irq_eoi = aplic_msi_irq_eoi,
+ #ifdef CONFIG_SMP
+ .irq_set_affinity = irq_chip_set_affinity_parent,
+diff --git a/drivers/irqchip/irq-xilinx-intc.c b/drivers/irqchip/irq-xilinx-intc.c
+index 238d3d3449496..7e08714d507f4 100644
+--- a/drivers/irqchip/irq-xilinx-intc.c
++++ b/drivers/irqchip/irq-xilinx-intc.c
+@@ -189,7 +189,7 @@ static int __init xilinx_intc_of_init(struct device_node *intc,
+ irqc->intr_mask = 0;
+ }
+
+- if (irqc->intr_mask >> irqc->nr_irq)
++ if ((u64)irqc->intr_mask >> irqc->nr_irq)
+ pr_warn("irq-xilinx: mismatch in kind-of-intr param\n");
+
+ pr_info("irq-xilinx: %pOF: num_irq=%d, edge=0x%x\n",
+diff --git a/drivers/md/md.c b/drivers/md/md.c
+index 9c5be016e5073..a5b5801baa9e8 100644
+--- a/drivers/md/md.c
++++ b/drivers/md/md.c
+@@ -479,7 +479,6 @@ int mddev_suspend(struct mddev *mddev, bool interruptible)
+ */
+ WRITE_ONCE(mddev->suspended, mddev->suspended + 1);
+
+- del_timer_sync(&mddev->safemode_timer);
+ /* restrict memory reclaim I/O during raid array is suspend */
+ mddev->noio_flag = memalloc_noio_save();
+
+@@ -8639,12 +8638,12 @@ EXPORT_SYMBOL(md_done_sync);
+ * A return value of 'false' means that the write wasn't recorded
+ * and cannot proceed as the array is being suspend.
+ */
+-bool md_write_start(struct mddev *mddev, struct bio *bi)
++void md_write_start(struct mddev *mddev, struct bio *bi)
+ {
+ int did_change = 0;
+
+ if (bio_data_dir(bi) != WRITE)
+- return true;
++ return;
+
+ BUG_ON(mddev->ro == MD_RDONLY);
+ if (mddev->ro == MD_AUTO_READ) {
+@@ -8677,15 +8676,9 @@ bool md_write_start(struct mddev *mddev, struct bio *bi)
+ if (did_change)
+ sysfs_notify_dirent_safe(mddev->sysfs_state);
+ if (!mddev->has_superblocks)
+- return true;
++ return;
+ wait_event(mddev->sb_wait,
+- !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags) ||
+- is_md_suspended(mddev));
+- if (test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags)) {
+- percpu_ref_put(&mddev->writes_pending);
+- return false;
+- }
+- return true;
++ !test_bit(MD_SB_CHANGE_PENDING, &mddev->sb_flags));
+ }
+ EXPORT_SYMBOL(md_write_start);
+
+diff --git a/drivers/md/md.h b/drivers/md/md.h
+index ca085ecad5044..487582058f741 100644
+--- a/drivers/md/md.h
++++ b/drivers/md/md.h
+@@ -785,7 +785,7 @@ extern void md_unregister_thread(struct mddev *mddev, struct md_thread __rcu **t
+ extern void md_wakeup_thread(struct md_thread __rcu *thread);
+ extern void md_check_recovery(struct mddev *mddev);
+ extern void md_reap_sync_thread(struct mddev *mddev);
+-extern bool md_write_start(struct mddev *mddev, struct bio *bi);
++extern void md_write_start(struct mddev *mddev, struct bio *bi);
+ extern void md_write_inc(struct mddev *mddev, struct bio *bi);
+ extern void md_write_end(struct mddev *mddev);
+ extern void md_done_sync(struct mddev *mddev, int blocks, int ok);
+diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
+index 22bbd06ba6a29..5ea57b6748c53 100644
+--- a/drivers/md/raid1.c
++++ b/drivers/md/raid1.c
+@@ -1688,8 +1688,7 @@ static bool raid1_make_request(struct mddev *mddev, struct bio *bio)
+ if (bio_data_dir(bio) == READ)
+ raid1_read_request(mddev, bio, sectors, NULL);
+ else {
+- if (!md_write_start(mddev,bio))
+- return false;
++ md_write_start(mddev,bio);
+ raid1_write_request(mddev, bio, sectors);
+ }
+ return true;
+diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
+index a4556d2e46bf9..f8d7c02c6ed56 100644
+--- a/drivers/md/raid10.c
++++ b/drivers/md/raid10.c
+@@ -1836,8 +1836,7 @@ static bool raid10_make_request(struct mddev *mddev, struct bio *bio)
+ && md_flush_request(mddev, bio))
+ return true;
+
+- if (!md_write_start(mddev, bio))
+- return false;
++ md_write_start(mddev, bio);
+
+ if (unlikely(bio_op(bio) == REQ_OP_DISCARD))
+ if (!raid10_handle_discard(mddev, bio))
+diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
+index 1c6b58adec133..ff9f4751c0965 100644
+--- a/drivers/md/raid5.c
++++ b/drivers/md/raid5.c
+@@ -6097,8 +6097,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
+ ctx.do_flush = bi->bi_opf & REQ_PREFLUSH;
+ }
+
+- if (!md_write_start(mddev, bi))
+- return false;
++ md_write_start(mddev, bi);
+ /*
+ * If array is degraded, better not do chunk aligned read because
+ * later we might have to read it again in order to reconstruct
+@@ -6273,7 +6272,9 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
+ safepos = conf->reshape_safe;
+ sector_div(safepos, data_disks);
+ if (mddev->reshape_backwards) {
+- BUG_ON(writepos < reshape_sectors);
++ if (WARN_ON(writepos < reshape_sectors))
++ return MaxSector;
++
+ writepos -= reshape_sectors;
+ readpos += reshape_sectors;
+ safepos += reshape_sectors;
+@@ -6291,14 +6292,18 @@ static sector_t reshape_request(struct mddev *mddev, sector_t sector_nr, int *sk
+ * to set 'stripe_addr' which is where we will write to.
+ */
+ if (mddev->reshape_backwards) {
+- BUG_ON(conf->reshape_progress == 0);
++ if (WARN_ON(conf->reshape_progress == 0))
++ return MaxSector;
++
+ stripe_addr = writepos;
+- BUG_ON((mddev->dev_sectors &
+- ~((sector_t)reshape_sectors - 1))
+- - reshape_sectors - stripe_addr
+- != sector_nr);
++ if (WARN_ON((mddev->dev_sectors &
++ ~((sector_t)reshape_sectors - 1)) -
++ reshape_sectors - stripe_addr != sector_nr))
++ return MaxSector;
+ } else {
+- BUG_ON(writepos != sector_nr + reshape_sectors);
++ if (WARN_ON(writepos != sector_nr + reshape_sectors))
++ return MaxSector;
++
+ stripe_addr = sector_nr;
+ }
+
+diff --git a/drivers/media/i2c/ov5647.c b/drivers/media/i2c/ov5647.c
+index 7e1ecdf2485f7..0fb4d7bff9d14 100644
+--- a/drivers/media/i2c/ov5647.c
++++ b/drivers/media/i2c/ov5647.c
+@@ -1360,24 +1360,21 @@ static int ov5647_parse_dt(struct ov5647 *sensor, struct device_node *np)
+ struct v4l2_fwnode_endpoint bus_cfg = {
+ .bus_type = V4L2_MBUS_CSI2_DPHY,
+ };
+- struct device_node *ep;
++ struct device_node *ep __free(device_node) =
++ of_graph_get_endpoint_by_regs(np, 0, -1);
+ int ret;
+
+- ep = of_graph_get_endpoint_by_regs(np, 0, -1);
+ if (!ep)
+ return -EINVAL;
+
+ ret = v4l2_fwnode_endpoint_parse(of_fwnode_handle(ep), &bus_cfg);
+ if (ret)
+- goto out;
++ return ret;
+
+ sensor->clock_ncont = bus_cfg.bus.mipi_csi2.flags &
+ V4L2_MBUS_CSI2_NONCONTINUOUS_CLOCK;
+
+-out:
+- of_node_put(ep);
+-
+- return ret;
++ return 0;
+ }
+
+ static int ov5647_probe(struct i2c_client *client)
+diff --git a/drivers/media/pci/intel/ipu6/Kconfig b/drivers/media/pci/intel/ipu6/Kconfig
+index 154343080c82a..40e20f0aa5ae5 100644
+--- a/drivers/media/pci/intel/ipu6/Kconfig
++++ b/drivers/media/pci/intel/ipu6/Kconfig
+@@ -3,13 +3,14 @@ config VIDEO_INTEL_IPU6
+ depends on ACPI || COMPILE_TEST
+ depends on VIDEO_DEV
+ depends on X86 && X86_64 && HAS_DMA
++ depends on IPU_BRIDGE || !IPU_BRIDGE
++ select AUXILIARY_BUS
+ select DMA_OPS
+ select IOMMU_IOVA
+ select VIDEO_V4L2_SUBDEV_API
+ select MEDIA_CONTROLLER
+ select VIDEOBUF2_DMA_CONTIG
+ select V4L2_FWNODE
+- select IPU_BRIDGE
+ help
+ This is the 6th Gen Intel Image Processing Unit, found in Intel SoCs
+ and used for capturing images and video from camera sensors.
+diff --git a/drivers/media/platform/amphion/vdec.c b/drivers/media/platform/amphion/vdec.c
+index a57f9f4f3b876..6a38a0fa0e2d4 100644
+--- a/drivers/media/platform/amphion/vdec.c
++++ b/drivers/media/platform/amphion/vdec.c
+@@ -195,7 +195,6 @@ static int vdec_op_s_ctrl(struct v4l2_ctrl *ctrl)
+ struct vdec_t *vdec = inst->priv;
+ int ret = 0;
+
+- vpu_inst_lock(inst);
+ switch (ctrl->id) {
+ case V4L2_CID_MPEG_VIDEO_DEC_DISPLAY_DELAY_ENABLE:
+ vdec->params.display_delay_enable = ctrl->val;
+@@ -207,7 +206,6 @@ static int vdec_op_s_ctrl(struct v4l2_ctrl *ctrl)
+ ret = -EINVAL;
+ break;
+ }
+- vpu_inst_unlock(inst);
+
+ return ret;
+ }
+diff --git a/drivers/media/platform/amphion/venc.c b/drivers/media/platform/amphion/venc.c
+index 4eb57d793a9c0..16ed4d21519cd 100644
+--- a/drivers/media/platform/amphion/venc.c
++++ b/drivers/media/platform/amphion/venc.c
+@@ -518,7 +518,6 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl)
+ struct venc_t *venc = inst->priv;
+ int ret = 0;
+
+- vpu_inst_lock(inst);
+ switch (ctrl->id) {
+ case V4L2_CID_MPEG_VIDEO_H264_PROFILE:
+ venc->params.profile = ctrl->val;
+@@ -579,7 +578,6 @@ static int venc_op_s_ctrl(struct v4l2_ctrl *ctrl)
+ ret = -EINVAL;
+ break;
+ }
+- vpu_inst_unlock(inst);
+
+ return ret;
+ }
+diff --git a/drivers/media/tuners/xc2028.c b/drivers/media/tuners/xc2028.c
+index 5a967edceca93..352b8a3679b72 100644
+--- a/drivers/media/tuners/xc2028.c
++++ b/drivers/media/tuners/xc2028.c
+@@ -1361,9 +1361,16 @@ static void load_firmware_cb(const struct firmware *fw,
+ void *context)
+ {
+ struct dvb_frontend *fe = context;
+- struct xc2028_data *priv = fe->tuner_priv;
++ struct xc2028_data *priv;
+ int rc;
+
++ if (!fe) {
++ pr_warn("xc2028: No frontend in %s\n", __func__);
++ return;
++ }
++
++ priv = fe->tuner_priv;
++
+ tuner_dbg("request_firmware_nowait(): %s\n", fw ? "OK" : "error");
+ if (!fw) {
+ tuner_err("Could not load firmware %s.\n", priv->fname);
+diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
+index 51f4f653b983d..5bebe1460a9f7 100644
+--- a/drivers/media/usb/uvc/uvc_video.c
++++ b/drivers/media/usb/uvc/uvc_video.c
+@@ -214,13 +214,13 @@ static void uvc_fixup_video_ctrl(struct uvc_streaming *stream,
+ * Compute a bandwidth estimation by multiplying the frame
+ * size by the number of video frames per second, divide the
+ * result by the number of USB frames (or micro-frames for
+- * high-speed devices) per second and add the UVC header size
+- * (assumed to be 12 bytes long).
++ * high- and super-speed devices) per second and add the UVC
++ * header size (assumed to be 12 bytes long).
+ */
+ bandwidth = frame->wWidth * frame->wHeight / 8 * format->bpp;
+ bandwidth *= 10000000 / interval + 1;
+ bandwidth /= 1000;
+- if (stream->dev->udev->speed == USB_SPEED_HIGH)
++ if (stream->dev->udev->speed >= USB_SPEED_HIGH)
+ bandwidth /= 8;
+ bandwidth += 12;
+
+@@ -478,6 +478,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
+ ktime_t time;
+ u16 host_sof;
+ u16 dev_sof;
++ u32 dev_stc;
+
+ switch (data[1] & (UVC_STREAM_PTS | UVC_STREAM_SCR)) {
+ case UVC_STREAM_PTS | UVC_STREAM_SCR:
+@@ -526,6 +527,34 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
+ if (dev_sof == stream->clock.last_sof)
+ return;
+
++ dev_stc = get_unaligned_le32(&data[header_size - 6]);
++
++ /*
++ * STC (Source Time Clock) is the clock used by the camera. The UVC 1.5
++ * standard states that it "must be captured when the first video data
++ * of a video frame is put on the USB bus". This is generally understood
++ * as requiring devices to clear the payload header's SCR bit before
++ * the first packet containing video data.
++ *
++ * Most vendors follow that interpretation, but some (namely SunplusIT
++ * on some devices) always set the `UVC_STREAM_SCR` bit, fill the SCR
++ * field with 0's,and expect that the driver only processes the SCR if
++ * there is data in the packet.
++ *
++ * Ignore all the hardware timestamp information if we haven't received
++ * any data for this frame yet, the packet contains no data, and both
++ * STC and SOF are zero. This heuristics should be safe on compliant
++ * devices. This should be safe with compliant devices, as in the very
++ * unlikely case where a UVC 1.1 device would send timing information
++ * only before the first packet containing data, and both STC and SOF
++ * happen to be zero for a particular frame, we would only miss one
++ * clock sample from many and the clock recovery algorithm wouldn't
++ * suffer from this condition.
++ */
++ if (buf && buf->bytesused == 0 && len == header_size &&
++ dev_stc == 0 && dev_sof == 0)
++ return;
++
+ stream->clock.last_sof = dev_sof;
+
+ host_sof = usb_get_current_frame_number(stream->dev->udev);
+@@ -575,7 +604,7 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
+ spin_lock_irqsave(&stream->clock.lock, flags);
+
+ sample = &stream->clock.samples[stream->clock.head];
+- sample->dev_stc = get_unaligned_le32(&data[header_size - 6]);
++ sample->dev_stc = dev_stc;
+ sample->dev_sof = dev_sof;
+ sample->host_sof = host_sof;
+ sample->host_time = time;
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+index bfe4caa0c99d4..4cb79a4f24612 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-ring.c
+@@ -485,6 +485,8 @@ int mcp251xfd_ring_alloc(struct mcp251xfd_priv *priv)
+ clear_bit(MCP251XFD_FLAGS_FD_MODE, priv->flags);
+ }
+
++ tx_ring->obj_num_shift_to_u8 = BITS_PER_TYPE(tx_ring->obj_num) -
++ ilog2(tx_ring->obj_num);
+ tx_ring->obj_size = tx_obj_size;
+
+ rem = priv->rx_obj_num;
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+index e5bd57b65aafe..5b0c7890d4b44 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd-tef.c
+@@ -2,7 +2,7 @@
+ //
+ // mcp251xfd - Microchip MCP251xFD Family CAN controller driver
+ //
+-// Copyright (c) 2019, 2020, 2021 Pengutronix,
++// Copyright (c) 2019, 2020, 2021, 2023 Pengutronix,
+ // Marc Kleine-Budde <kernel@pengutronix.de>
+ //
+ // Based on:
+@@ -16,6 +16,11 @@
+
+ #include "mcp251xfd.h"
+
++static inline bool mcp251xfd_tx_fifo_sta_full(u32 fifo_sta)
++{
++ return !(fifo_sta & MCP251XFD_REG_FIFOSTA_TFNRFNIF);
++}
++
+ static inline int
+ mcp251xfd_tef_tail_get_from_chip(const struct mcp251xfd_priv *priv,
+ u8 *tef_tail)
+@@ -55,56 +60,39 @@ static int mcp251xfd_check_tef_tail(const struct mcp251xfd_priv *priv)
+ return 0;
+ }
+
+-static int
+-mcp251xfd_handle_tefif_recover(const struct mcp251xfd_priv *priv, const u32 seq)
+-{
+- const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+- u32 tef_sta;
+- int err;
+-
+- err = regmap_read(priv->map_reg, MCP251XFD_REG_TEFSTA, &tef_sta);
+- if (err)
+- return err;
+-
+- if (tef_sta & MCP251XFD_REG_TEFSTA_TEFOVIF) {
+- netdev_err(priv->ndev,
+- "Transmit Event FIFO buffer overflow.\n");
+- return -ENOBUFS;
+- }
+-
+- netdev_info(priv->ndev,
+- "Transmit Event FIFO buffer %s. (seq=0x%08x, tef_tail=0x%08x, tef_head=0x%08x, tx_head=0x%08x).\n",
+- tef_sta & MCP251XFD_REG_TEFSTA_TEFFIF ?
+- "full" : tef_sta & MCP251XFD_REG_TEFSTA_TEFNEIF ?
+- "not empty" : "empty",
+- seq, priv->tef->tail, priv->tef->head, tx_ring->head);
+-
+- /* The Sequence Number in the TEF doesn't match our tef_tail. */
+- return -EAGAIN;
+-}
+-
+ static int
+ mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
+ const struct mcp251xfd_hw_tef_obj *hw_tef_obj,
+ unsigned int *frame_len_ptr)
+ {
+ struct net_device_stats *stats = &priv->ndev->stats;
++ u32 seq, tef_tail_masked, tef_tail;
+ struct sk_buff *skb;
+- u32 seq, seq_masked, tef_tail_masked, tef_tail;
+
+- seq = FIELD_GET(MCP251XFD_OBJ_FLAGS_SEQ_MCP2518FD_MASK,
++ /* Use the MCP2517FD mask on the MCP2518FD, too. We only
++ * compare 7 bits, this is enough to detect old TEF objects.
++ */
++ seq = FIELD_GET(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK,
+ hw_tef_obj->flags);
+-
+- /* Use the MCP2517FD mask on the MCP2518FD, too. We only
+- * compare 7 bits, this should be enough to detect
+- * net-yet-completed, i.e. old TEF objects.
+- */
+- seq_masked = seq &
+- field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
+ tef_tail_masked = priv->tef->tail &
+ field_mask(MCP251XFD_OBJ_FLAGS_SEQ_MCP2517FD_MASK);
+- if (seq_masked != tef_tail_masked)
+- return mcp251xfd_handle_tefif_recover(priv, seq);
++
++ /* According to mcp2518fd erratum DS80000789E 6. the FIFOCI
++ * bits of a FIFOSTA register, here the TX FIFO tail index
++ * might be corrupted and we might process past the TEF FIFO's
++ * head into old CAN frames.
++ *
++ * Compare the sequence number of the currently processed CAN
++ * frame with the expected sequence number. Abort with
++ * -EBADMSG if an old CAN frame is detected.
++ */
++ if (seq != tef_tail_masked) {
++ netdev_dbg(priv->ndev, "%s: chip=0x%02x ring=0x%02x\n", __func__,
++ seq, tef_tail_masked);
++ stats->tx_fifo_errors++;
++
++ return -EBADMSG;
++ }
+
+ tef_tail = mcp251xfd_get_tef_tail(priv);
+ skb = priv->can.echo_skb[tef_tail];
+@@ -120,28 +108,44 @@ mcp251xfd_handle_tefif_one(struct mcp251xfd_priv *priv,
+ return 0;
+ }
+
+-static int mcp251xfd_tef_ring_update(struct mcp251xfd_priv *priv)
++static int
++mcp251xfd_get_tef_len(struct mcp251xfd_priv *priv, u8 *len_p)
+ {
+ const struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+- unsigned int new_head;
+- u8 chip_tx_tail;
++ const u8 shift = tx_ring->obj_num_shift_to_u8;
++ u8 chip_tx_tail, tail, len;
++ u32 fifo_sta;
+ int err;
+
+- err = mcp251xfd_tx_tail_get_from_chip(priv, &chip_tx_tail);
++ err = regmap_read(priv->map_reg, MCP251XFD_REG_FIFOSTA(priv->tx->fifo_nr),
++ &fifo_sta);
+ if (err)
+ return err;
+
+- /* chip_tx_tail, is the next TX-Object send by the HW.
+- * The new TEF head must be >= the old head, ...
++ if (mcp251xfd_tx_fifo_sta_full(fifo_sta)) {
++ *len_p = tx_ring->obj_num;
++ return 0;
++ }
++
++ chip_tx_tail = FIELD_GET(MCP251XFD_REG_FIFOSTA_FIFOCI_MASK, fifo_sta);
++
++ err = mcp251xfd_check_tef_tail(priv);
++ if (err)
++ return err;
++ tail = mcp251xfd_get_tef_tail(priv);
++
++ /* First shift to full u8. The subtraction works on signed
++ * values, that keeps the difference steady around the u8
++ * overflow. The right shift acts on len, which is an u8.
+ */
+- new_head = round_down(priv->tef->head, tx_ring->obj_num) + chip_tx_tail;
+- if (new_head <= priv->tef->head)
+- new_head += tx_ring->obj_num;
++ BUILD_BUG_ON(sizeof(tx_ring->obj_num) != sizeof(chip_tx_tail));
++ BUILD_BUG_ON(sizeof(tx_ring->obj_num) != sizeof(tail));
++ BUILD_BUG_ON(sizeof(tx_ring->obj_num) != sizeof(len));
+
+- /* ... but it cannot exceed the TX head. */
+- priv->tef->head = min(new_head, tx_ring->head);
++ len = (chip_tx_tail << shift) - (tail << shift);
++ *len_p = len >> shift;
+
+- return mcp251xfd_check_tef_tail(priv);
++ return 0;
+ }
+
+ static inline int
+@@ -182,13 +186,12 @@ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
+ u8 tef_tail, len, l;
+ int err, i;
+
+- err = mcp251xfd_tef_ring_update(priv);
++ err = mcp251xfd_get_tef_len(priv, &len);
+ if (err)
+ return err;
+
+ tef_tail = mcp251xfd_get_tef_tail(priv);
+- len = mcp251xfd_get_tef_len(priv);
+- l = mcp251xfd_get_tef_linear_len(priv);
++ l = mcp251xfd_get_tef_linear_len(priv, len);
+ err = mcp251xfd_tef_obj_read(priv, hw_tef_obj, tef_tail, l);
+ if (err)
+ return err;
+@@ -203,12 +206,12 @@ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
+ unsigned int frame_len = 0;
+
+ err = mcp251xfd_handle_tefif_one(priv, &hw_tef_obj[i], &frame_len);
+- /* -EAGAIN means the Sequence Number in the TEF
+- * doesn't match our tef_tail. This can happen if we
+- * read the TEF objects too early. Leave loop let the
+- * interrupt handler call us again.
++ /* -EBADMSG means we're affected by mcp2518fd erratum
++ * DS80000789E 6., i.e. the Sequence Number in the TEF
++ * doesn't match our tef_tail. Don't process any
++ * further and mark processed frames as good.
+ */
+- if (err == -EAGAIN)
++ if (err == -EBADMSG)
+ goto out_netif_wake_queue;
+ if (err)
+ return err;
+@@ -223,6 +226,8 @@ int mcp251xfd_handle_tefif(struct mcp251xfd_priv *priv)
+ struct mcp251xfd_tx_ring *tx_ring = priv->tx;
+ int offset;
+
++ ring->head += len;
++
+ /* Increment the TEF FIFO tail pointer 'len' times in
+ * a single SPI message.
+ *
+diff --git a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+index b35bfebd23f29..4628bf847bc9b 100644
+--- a/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
++++ b/drivers/net/can/spi/mcp251xfd/mcp251xfd.h
+@@ -524,6 +524,7 @@ struct mcp251xfd_tef_ring {
+
+ /* u8 obj_num equals tx_ring->obj_num */
+ /* u8 obj_size equals sizeof(struct mcp251xfd_hw_tef_obj) */
++ /* u8 obj_num_shift_to_u8 equals tx_ring->obj_num_shift_to_u8 */
+
+ union mcp251xfd_write_reg_buf irq_enable_buf;
+ struct spi_transfer irq_enable_xfer;
+@@ -542,6 +543,7 @@ struct mcp251xfd_tx_ring {
+ u8 nr;
+ u8 fifo_nr;
+ u8 obj_num;
++ u8 obj_num_shift_to_u8;
+ u8 obj_size;
+
+ struct mcp251xfd_tx_obj obj[MCP251XFD_TX_OBJ_NUM_MAX];
+@@ -861,17 +863,8 @@ static inline u8 mcp251xfd_get_tef_tail(const struct mcp251xfd_priv *priv)
+ return priv->tef->tail & (priv->tx->obj_num - 1);
+ }
+
+-static inline u8 mcp251xfd_get_tef_len(const struct mcp251xfd_priv *priv)
++static inline u8 mcp251xfd_get_tef_linear_len(const struct mcp251xfd_priv *priv, u8 len)
+ {
+- return priv->tef->head - priv->tef->tail;
+-}
+-
+-static inline u8 mcp251xfd_get_tef_linear_len(const struct mcp251xfd_priv *priv)
+-{
+- u8 len;
+-
+- len = mcp251xfd_get_tef_len(priv);
+-
+ return min_t(u8, len, priv->tx->obj_num - mcp251xfd_get_tef_tail(priv));
+ }
+
+diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c
+index ed1e6560df25e..0e663ec0c12a3 100644
+--- a/drivers/net/dsa/bcm_sf2.c
++++ b/drivers/net/dsa/bcm_sf2.c
+@@ -675,8 +675,10 @@ static int bcm_sf2_mdio_register(struct dsa_switch *ds)
+ of_remove_property(child, prop);
+
+ phydev = of_phy_find_device(child);
+- if (phydev)
++ if (phydev) {
+ phy_device_remove(phydev);
++ phy_device_free(phydev);
++ }
+ }
+
+ err = mdiobus_register(priv->user_mii_bus);
+diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
+index baa1eeb9a1b04..3103e1b32d0ba 100644
+--- a/drivers/net/dsa/microchip/ksz_common.c
++++ b/drivers/net/dsa/microchip/ksz_common.c
+@@ -2578,7 +2578,11 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
+ if (!port)
+ return MICREL_KSZ8_P1_ERRATA;
+ break;
++ case KSZ8567_CHIP_ID:
+ case KSZ9477_CHIP_ID:
++ case KSZ9567_CHIP_ID:
++ case KSZ9896_CHIP_ID:
++ case KSZ9897_CHIP_ID:
+ /* KSZ9477 Errata DS80000754C
+ *
+ * Module 4: Energy Efficient Ethernet (EEE) feature select must
+@@ -2588,6 +2592,13 @@ static u32 ksz_get_phy_flags(struct dsa_switch *ds, int port)
+ * controls. If not disabled, the PHY ports can auto-negotiate
+ * to enable EEE, and this feature can cause link drops when
+ * linked to another device supporting EEE.
++ *
++ * The same item appears in the errata for the KSZ9567, KSZ9896,
++ * and KSZ9897.
++ *
++ * A similar item appears in the errata for the KSZ8567, but
++ * provides an alternative workaround. For now, use the simple
++ * workaround of disabling the EEE feature for this device too.
+ */
+ return MICREL_NO_EEE;
+ }
+@@ -3763,6 +3774,11 @@ static int ksz_port_set_mac_address(struct dsa_switch *ds, int port,
+ return -EBUSY;
+ }
+
++ /* Need to initialize variable as the code to fill in settings may
++ * not be executed.
++ */
++ wol.wolopts = 0;
++
+ ksz_get_wol(ds, dp->index, &wol);
+ if (wol.wolopts & WAKE_MAGIC) {
+ dev_err(ds->dev,
+diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+index 23627c973e40f..a2d672a698e35 100644
+--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
++++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+@@ -7433,19 +7433,20 @@ static bool bnxt_need_reserve_rings(struct bnxt *bp)
+ int rx = bp->rx_nr_rings, stat;
+ int vnic, grp = rx;
+
+- if (hw_resc->resv_tx_rings != bp->tx_nr_rings &&
+- bp->hwrm_spec_code >= 0x10601)
+- return true;
+-
+ /* Old firmware does not need RX ring reservations but we still
+ * need to setup a default RSS map when needed. With new firmware
+ * we go through RX ring reservations first and then set up the
+ * RSS map for the successfully reserved RX rings when needed.
+ */
+- if (!BNXT_NEW_RM(bp)) {
++ if (!BNXT_NEW_RM(bp))
+ bnxt_check_rss_tbl_no_rmgr(bp);
++
++ if (hw_resc->resv_tx_rings != bp->tx_nr_rings &&
++ bp->hwrm_spec_code >= 0x10601)
++ return true;
++
++ if (!BNXT_NEW_RM(bp))
+ return false;
+- }
+
+ vnic = bnxt_get_total_vnics(bp, rx);
+
+diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+index 1248792d7fd4d..0715ea5bf13ed 100644
+--- a/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
++++ b/drivers/net/ethernet/broadcom/genet/bcmgenet_wol.c
+@@ -42,19 +42,15 @@ void bcmgenet_get_wol(struct net_device *dev, struct ethtool_wolinfo *wol)
+ struct bcmgenet_priv *priv = netdev_priv(dev);
+ struct device *kdev = &priv->pdev->dev;
+
+- if (dev->phydev) {
++ if (dev->phydev)
+ phy_ethtool_get_wol(dev->phydev, wol);
+- if (wol->supported)
+- return;
+- }
+
+- if (!device_can_wakeup(kdev)) {
+- wol->supported = 0;
+- wol->wolopts = 0;
++ /* MAC is not wake-up capable, return what the PHY does */
++ if (!device_can_wakeup(kdev))
+ return;
+- }
+
+- wol->supported = WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
++ /* Overlay MAC capabilities with that of the PHY queried before */
++ wol->supported |= WAKE_MAGIC | WAKE_MAGICSECURE | WAKE_FILTER;
+ wol->wolopts = priv->wolopts;
+ memset(wol->sopass, 0, sizeof(wol->sopass));
+
+diff --git a/drivers/net/ethernet/freescale/fec_ptp.c b/drivers/net/ethernet/freescale/fec_ptp.c
+index e32f6724f5681..2e4f3e1782a25 100644
+--- a/drivers/net/ethernet/freescale/fec_ptp.c
++++ b/drivers/net/ethernet/freescale/fec_ptp.c
+@@ -775,6 +775,9 @@ void fec_ptp_stop(struct platform_device *pdev)
+ struct net_device *ndev = platform_get_drvdata(pdev);
+ struct fec_enet_private *fep = netdev_priv(ndev);
+
++ if (fep->pps_enable)
++ fec_ptp_enable_pps(fep, 0);
++
+ cancel_delayed_work_sync(&fep->time_keep);
+ hrtimer_cancel(&fep->perout_timer);
+ if (fep->ptp_clock)
+diff --git a/drivers/net/ethernet/google/gve/gve_ethtool.c b/drivers/net/ethernet/google/gve/gve_ethtool.c
+index fe1741d482b4a..cf816ede05f69 100644
+--- a/drivers/net/ethernet/google/gve/gve_ethtool.c
++++ b/drivers/net/ethernet/google/gve/gve_ethtool.c
+@@ -492,7 +492,7 @@ static int gve_set_channels(struct net_device *netdev,
+ return -EINVAL;
+ }
+
+- if (!netif_carrier_ok(netdev)) {
++ if (!netif_running(netdev)) {
+ priv->tx_cfg.num_queues = new_tx;
+ priv->rx_cfg.num_queues = new_rx;
+ return 0;
+diff --git a/drivers/net/ethernet/google/gve/gve_main.c b/drivers/net/ethernet/google/gve/gve_main.c
+index cabf7d4bcecb8..8b14efd14a505 100644
+--- a/drivers/net/ethernet/google/gve/gve_main.c
++++ b/drivers/net/ethernet/google/gve/gve_main.c
+@@ -1511,7 +1511,7 @@ static int gve_set_xdp(struct gve_priv *priv, struct bpf_prog *prog,
+ u32 status;
+
+ old_prog = READ_ONCE(priv->xdp_prog);
+- if (!netif_carrier_ok(priv->dev)) {
++ if (!netif_running(priv->dev)) {
+ WRITE_ONCE(priv->xdp_prog, prog);
+ if (old_prog)
+ bpf_prog_put(old_prog);
+@@ -1784,7 +1784,7 @@ int gve_adjust_queues(struct gve_priv *priv,
+ rx_alloc_cfg.qcfg = &new_rx_config;
+ tx_alloc_cfg.num_rings = new_tx_config.num_queues;
+
+- if (netif_carrier_ok(priv->dev)) {
++ if (netif_running(priv->dev)) {
+ err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+ return err;
+ }
+@@ -2001,7 +2001,7 @@ static int gve_set_features(struct net_device *netdev,
+
+ if ((netdev->features & NETIF_F_LRO) != (features & NETIF_F_LRO)) {
+ netdev->features ^= NETIF_F_LRO;
+- if (netif_carrier_ok(netdev)) {
++ if (netif_running(netdev)) {
+ err = gve_adjust_config(priv, &tx_alloc_cfg, &rx_alloc_cfg);
+ if (err) {
+ /* Revert the change on error. */
+@@ -2290,7 +2290,7 @@ static int gve_reset_recovery(struct gve_priv *priv, bool was_up)
+
+ int gve_reset(struct gve_priv *priv, bool attempt_teardown)
+ {
+- bool was_up = netif_carrier_ok(priv->dev);
++ bool was_up = netif_running(priv->dev);
+ int err;
+
+ dev_info(&priv->pdev->dev, "Performing reset\n");
+@@ -2631,7 +2631,7 @@ static void gve_shutdown(struct pci_dev *pdev)
+ {
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct gve_priv *priv = netdev_priv(netdev);
+- bool was_up = netif_carrier_ok(priv->dev);
++ bool was_up = netif_running(priv->dev);
+
+ rtnl_lock();
+ if (was_up && gve_close(priv->dev)) {
+@@ -2649,7 +2649,7 @@ static int gve_suspend(struct pci_dev *pdev, pm_message_t state)
+ {
+ struct net_device *netdev = pci_get_drvdata(pdev);
+ struct gve_priv *priv = netdev_priv(netdev);
+- bool was_up = netif_carrier_ok(priv->dev);
++ bool was_up = netif_running(priv->dev);
+
+ priv->suspend_cnt++;
+ rtnl_lock();
+diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
+index 9b075dd48889e..f16d13e9ff6e3 100644
+--- a/drivers/net/ethernet/intel/ice/ice_main.c
++++ b/drivers/net/ethernet/intel/ice/ice_main.c
+@@ -560,6 +560,8 @@ ice_prepare_for_reset(struct ice_pf *pf, enum ice_reset_req reset_type)
+ if (test_bit(ICE_PREPARED_FOR_RESET, pf->state))
+ return;
+
++ synchronize_irq(pf->oicr_irq.virq);
++
+ ice_unplug_aux_dev(pf);
+
+ /* Notify VFs of impending reset */
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_lib.c b/drivers/net/ethernet/intel/idpf/idpf_lib.c
+index f1ee5584e8fa2..3ac9d7ab83f20 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_lib.c
++++ b/drivers/net/ethernet/intel/idpf/idpf_lib.c
+@@ -905,8 +905,8 @@ static void idpf_vport_stop(struct idpf_vport *vport)
+
+ vport->link_up = false;
+ idpf_vport_intr_deinit(vport);
+- idpf_vport_intr_rel(vport);
+ idpf_vport_queues_rel(vport);
++ idpf_vport_intr_rel(vport);
+ np->state = __IDPF_VPORT_DOWN;
+ }
+
+@@ -1337,9 +1337,8 @@ static void idpf_rx_init_buf_tail(struct idpf_vport *vport)
+ /**
+ * idpf_vport_open - Bring up a vport
+ * @vport: vport to bring up
+- * @alloc_res: allocate queue resources
+ */
+-static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res)
++static int idpf_vport_open(struct idpf_vport *vport)
+ {
+ struct idpf_netdev_priv *np = netdev_priv(vport->netdev);
+ struct idpf_adapter *adapter = vport->adapter;
+@@ -1352,45 +1351,43 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res)
+ /* we do not allow interface up just yet */
+ netif_carrier_off(vport->netdev);
+
+- if (alloc_res) {
+- err = idpf_vport_queues_alloc(vport);
+- if (err)
+- return err;
+- }
+-
+ err = idpf_vport_intr_alloc(vport);
+ if (err) {
+ dev_err(&adapter->pdev->dev, "Failed to allocate interrupts for vport %u: %d\n",
+ vport->vport_id, err);
+- goto queues_rel;
++ return err;
+ }
+
++ err = idpf_vport_queues_alloc(vport);
++ if (err)
++ goto intr_rel;
++
+ err = idpf_vport_queue_ids_init(vport);
+ if (err) {
+ dev_err(&adapter->pdev->dev, "Failed to initialize queue ids for vport %u: %d\n",
+ vport->vport_id, err);
+- goto intr_rel;
++ goto queues_rel;
+ }
+
+ err = idpf_vport_intr_init(vport);
+ if (err) {
+ dev_err(&adapter->pdev->dev, "Failed to initialize interrupts for vport %u: %d\n",
+ vport->vport_id, err);
+- goto intr_rel;
++ goto queues_rel;
+ }
+
+ err = idpf_rx_bufs_init_all(vport);
+ if (err) {
+ dev_err(&adapter->pdev->dev, "Failed to initialize RX buffers for vport %u: %d\n",
+ vport->vport_id, err);
+- goto intr_rel;
++ goto queues_rel;
+ }
+
+ err = idpf_queue_reg_init(vport);
+ if (err) {
+ dev_err(&adapter->pdev->dev, "Failed to initialize queue registers for vport %u: %d\n",
+ vport->vport_id, err);
+- goto intr_rel;
++ goto queues_rel;
+ }
+
+ idpf_rx_init_buf_tail(vport);
+@@ -1457,10 +1454,10 @@ static int idpf_vport_open(struct idpf_vport *vport, bool alloc_res)
+ idpf_send_map_unmap_queue_vector_msg(vport, false);
+ intr_deinit:
+ idpf_vport_intr_deinit(vport);
+-intr_rel:
+- idpf_vport_intr_rel(vport);
+ queues_rel:
+ idpf_vport_queues_rel(vport);
++intr_rel:
++ idpf_vport_intr_rel(vport);
+
+ return err;
+ }
+@@ -1541,7 +1538,7 @@ void idpf_init_task(struct work_struct *work)
+ np = netdev_priv(vport->netdev);
+ np->state = __IDPF_VPORT_DOWN;
+ if (test_and_clear_bit(IDPF_VPORT_UP_REQUESTED, vport_config->flags))
+- idpf_vport_open(vport, true);
++ idpf_vport_open(vport);
+
+ /* Spawn and return 'idpf_init_task' work queue until all the
+ * default vports are created
+@@ -1900,9 +1897,6 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
+ goto free_vport;
+ }
+
+- err = idpf_vport_queues_alloc(new_vport);
+- if (err)
+- goto free_vport;
+ if (current_state <= __IDPF_VPORT_DOWN) {
+ idpf_send_delete_queues_msg(vport);
+ } else {
+@@ -1974,17 +1968,23 @@ int idpf_initiate_soft_reset(struct idpf_vport *vport,
+
+ err = idpf_set_real_num_queues(vport);
+ if (err)
+- goto err_reset;
++ goto err_open;
+
+ if (current_state == __IDPF_VPORT_UP)
+- err = idpf_vport_open(vport, false);
++ err = idpf_vport_open(vport);
+
+ kfree(new_vport);
+
+ return err;
+
+ err_reset:
+- idpf_vport_queues_rel(new_vport);
++ idpf_send_add_queues_msg(vport, vport->num_txq, vport->num_complq,
++ vport->num_rxq, vport->num_bufq);
++
++err_open:
++ if (current_state == __IDPF_VPORT_UP)
++ idpf_vport_open(vport);
++
+ free_vport:
+ kfree(new_vport);
+
+@@ -2213,7 +2213,7 @@ static int idpf_open(struct net_device *netdev)
+ idpf_vport_ctrl_lock(netdev);
+ vport = idpf_netdev_to_vport(netdev);
+
+- err = idpf_vport_open(vport, true);
++ err = idpf_vport_open(vport);
+
+ idpf_vport_ctrl_unlock(netdev);
+
+diff --git a/drivers/net/ethernet/intel/idpf/idpf_txrx.c b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+index b023704bbbdab..20ca04320d4bd 100644
+--- a/drivers/net/ethernet/intel/idpf/idpf_txrx.c
++++ b/drivers/net/ethernet/intel/idpf/idpf_txrx.c
+@@ -3436,9 +3436,7 @@ static void idpf_vport_intr_napi_dis_all(struct idpf_vport *vport)
+ */
+ void idpf_vport_intr_rel(struct idpf_vport *vport)
+ {
+- int i, j, v_idx;
+-
+- for (v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
++ for (u32 v_idx = 0; v_idx < vport->num_q_vectors; v_idx++) {
+ struct idpf_q_vector *q_vector = &vport->q_vectors[v_idx];
+
+ kfree(q_vector->bufq);
+@@ -3449,26 +3447,6 @@ void idpf_vport_intr_rel(struct idpf_vport *vport)
+ q_vector->rx = NULL;
+ }
+
+- /* Clean up the mapping of queues to vectors */
+- for (i = 0; i < vport->num_rxq_grp; i++) {
+- struct idpf_rxq_group *rx_qgrp = &vport->rxq_grps[i];
+-
+- if (idpf_is_queue_model_split(vport->rxq_model))
+- for (j = 0; j < rx_qgrp->splitq.num_rxq_sets; j++)
+- rx_qgrp->splitq.rxq_sets[j]->rxq.q_vector = NULL;
+- else
+- for (j = 0; j < rx_qgrp->singleq.num_rxq; j++)
+- rx_qgrp->singleq.rxqs[j]->q_vector = NULL;
+- }
+-
+- if (idpf_is_queue_model_split(vport->txq_model))
+- for (i = 0; i < vport->num_txq_grp; i++)
+- vport->txq_grps[i].complq->q_vector = NULL;
+- else
+- for (i = 0; i < vport->num_txq_grp; i++)
+- for (j = 0; j < vport->txq_grps[i].num_txq; j++)
+- vport->txq_grps[i].txqs[j]->q_vector = NULL;
+-
+ kfree(vport->q_vectors);
+ vport->q_vectors = NULL;
+ }
+@@ -3636,13 +3614,15 @@ void idpf_vport_intr_update_itr_ena_irq(struct idpf_q_vector *q_vector)
+ /**
+ * idpf_vport_intr_req_irq - get MSI-X vectors from the OS for the vport
+ * @vport: main vport structure
+- * @basename: name for the vector
+ */
+-static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename)
++static int idpf_vport_intr_req_irq(struct idpf_vport *vport)
+ {
+ struct idpf_adapter *adapter = vport->adapter;
++ const char *drv_name, *if_name, *vec_name;
+ int vector, err, irq_num, vidx;
+- const char *vec_name;
++
++ drv_name = dev_driver_string(&adapter->pdev->dev);
++ if_name = netdev_name(vport->netdev);
+
+ for (vector = 0; vector < vport->num_q_vectors; vector++) {
+ struct idpf_q_vector *q_vector = &vport->q_vectors[vector];
+@@ -3659,8 +3639,8 @@ static int idpf_vport_intr_req_irq(struct idpf_vport *vport, char *basename)
+ else
+ continue;
+
+- q_vector->name = kasprintf(GFP_KERNEL, "%s-%s-%d",
+- basename, vec_name, vidx);
++ q_vector->name = kasprintf(GFP_KERNEL, "%s-%s-%s-%d", drv_name,
++ if_name, vec_name, vidx);
+
+ err = request_irq(irq_num, idpf_vport_intr_clean_queues, 0,
+ q_vector->name, q_vector);
+@@ -4170,7 +4150,6 @@ int idpf_vport_intr_alloc(struct idpf_vport *vport)
+ */
+ int idpf_vport_intr_init(struct idpf_vport *vport)
+ {
+- char *int_name;
+ int err;
+
+ err = idpf_vport_intr_init_vec_idx(vport);
+@@ -4184,11 +4163,7 @@ int idpf_vport_intr_init(struct idpf_vport *vport)
+ if (err)
+ goto unroll_vectors_alloc;
+
+- int_name = kasprintf(GFP_KERNEL, "%s-%s",
+- dev_driver_string(&vport->adapter->pdev->dev),
+- vport->netdev->name);
+-
+- err = idpf_vport_intr_req_irq(vport, int_name);
++ err = idpf_vport_intr_req_irq(vport);
+ if (err)
+ goto unroll_vectors_alloc;
+
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+index b5333da20e8a7..cdc84a27a04ed 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c
+@@ -2374,6 +2374,9 @@ static void mlx5e_handle_rx_cqe_mpwrq_shampo(struct mlx5e_rq *rq, struct mlx5_cq
+ if (likely(wi->consumed_strides < rq->mpwqe.num_strides))
+ return;
+
++ if (unlikely(!cstrides))
++ return;
++
+ wq = &rq->mpwqe.wq;
+ wqe = mlx5_wq_ll_get_wqe(wq, wqe_id);
+ mlx5_wq_ll_pop(wq, cqe->wqe_id, &wqe->next.next_wqe_index);
+diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c
+index c0ced4d315f3d..d92f640bae575 100644
+--- a/drivers/net/ethernet/mellanox/mlxsw/pci.c
++++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c
+@@ -1599,6 +1599,7 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
+ {
+ struct pci_dev *pdev = mlxsw_pci->pdev;
+ char mrsr_pl[MLXSW_REG_MRSR_LEN];
++ struct pci_dev *bridge;
+ int err;
+
+ if (!pci_reset_sbr_supported) {
+@@ -1615,6 +1616,9 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
+ sbr:
+ device_lock_assert(&pdev->dev);
+
++ bridge = pci_upstream_bridge(pdev);
++ if (bridge)
++ pci_cfg_access_lock(bridge);
+ pci_cfg_access_lock(pdev);
+ pci_save_state(pdev);
+
+@@ -1624,6 +1628,8 @@ static int mlxsw_pci_reset_at_pci_disable(struct mlxsw_pci *mlxsw_pci,
+
+ pci_restore_state(pdev);
+ pci_cfg_access_unlock(pdev);
++ if (bridge)
++ pci_cfg_access_unlock(bridge);
+
+ return err;
+ }
+diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+index 466c4002f00d4..3a7f3a8b06718 100644
+--- a/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
++++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-qcom-ethqos.c
+@@ -21,6 +21,7 @@
+ #define RGMII_IO_MACRO_CONFIG2 0x1C
+ #define RGMII_IO_MACRO_DEBUG1 0x20
+ #define EMAC_SYSTEM_LOW_POWER_DEBUG 0x28
++#define EMAC_WRAPPER_SGMII_PHY_CNTRL1 0xf4
+
+ /* RGMII_IO_MACRO_CONFIG fields */
+ #define RGMII_CONFIG_FUNC_CLK_EN BIT(30)
+@@ -79,6 +80,9 @@
+ #define ETHQOS_MAC_CTRL_SPEED_MODE BIT(14)
+ #define ETHQOS_MAC_CTRL_PORT_SEL BIT(15)
+
++/* EMAC_WRAPPER_SGMII_PHY_CNTRL1 bits */
++#define SGMII_PHY_CNTRL1_SGMII_TX_TO_RX_LOOPBACK_EN BIT(3)
++
+ #define SGMII_10M_RX_CLK_DVDR 0x31
+
+ struct ethqos_emac_por {
+@@ -95,6 +99,7 @@ struct ethqos_emac_driver_data {
+ bool has_integrated_pcs;
+ u32 dma_addr_width;
+ struct dwmac4_addrs dwmac4_addrs;
++ bool needs_sgmii_loopback;
+ };
+
+ struct qcom_ethqos {
+@@ -114,6 +119,7 @@ struct qcom_ethqos {
+ unsigned int num_por;
+ bool rgmii_config_loopback_en;
+ bool has_emac_ge_3;
++ bool needs_sgmii_loopback;
+ };
+
+ static int rgmii_readl(struct qcom_ethqos *ethqos, unsigned int offset)
+@@ -191,8 +197,22 @@ ethqos_update_link_clk(struct qcom_ethqos *ethqos, unsigned int speed)
+ clk_set_rate(ethqos->link_clk, ethqos->link_clk_rate);
+ }
+
++static void
++qcom_ethqos_set_sgmii_loopback(struct qcom_ethqos *ethqos, bool enable)
++{
++ if (!ethqos->needs_sgmii_loopback ||
++ ethqos->phy_mode != PHY_INTERFACE_MODE_2500BASEX)
++ return;
++
++ rgmii_updatel(ethqos,
++ SGMII_PHY_CNTRL1_SGMII_TX_TO_RX_LOOPBACK_EN,
++ enable ? SGMII_PHY_CNTRL1_SGMII_TX_TO_RX_LOOPBACK_EN : 0,
++ EMAC_WRAPPER_SGMII_PHY_CNTRL1);
++}
++
+ static void ethqos_set_func_clk_en(struct qcom_ethqos *ethqos)
+ {
++ qcom_ethqos_set_sgmii_loopback(ethqos, true);
+ rgmii_updatel(ethqos, RGMII_CONFIG_FUNC_CLK_EN,
+ RGMII_CONFIG_FUNC_CLK_EN, RGMII_IO_MACRO_CONFIG);
+ }
+@@ -277,6 +297,7 @@ static const struct ethqos_emac_driver_data emac_v4_0_0_data = {
+ .has_emac_ge_3 = true,
+ .link_clk_name = "phyaux",
+ .has_integrated_pcs = true,
++ .needs_sgmii_loopback = true,
+ .dma_addr_width = 36,
+ .dwmac4_addrs = {
+ .dma_chan = 0x00008100,
+@@ -674,6 +695,7 @@ static void ethqos_fix_mac_speed(void *priv, unsigned int speed, unsigned int mo
+ {
+ struct qcom_ethqos *ethqos = priv;
+
++ qcom_ethqos_set_sgmii_loopback(ethqos, false);
+ ethqos->speed = speed;
+ ethqos_update_link_clk(ethqos, speed);
+ ethqos_configure(ethqos);
+@@ -809,6 +831,7 @@ static int qcom_ethqos_probe(struct platform_device *pdev)
+ ethqos->num_por = data->num_por;
+ ethqos->rgmii_config_loopback_en = data->rgmii_config_loopback_en;
+ ethqos->has_emac_ge_3 = data->has_emac_ge_3;
++ ethqos->needs_sgmii_loopback = data->needs_sgmii_loopback;
+
+ ethqos->link_clk = devm_clk_get(dev, data->link_clk_name ?: "rgmii");
+ if (IS_ERR(ethqos->link_clk))
+diff --git a/drivers/net/pse-pd/tps23881.c b/drivers/net/pse-pd/tps23881.c
+index 98ffbb1bbf13c..2d1c2e5706f8b 100644
+--- a/drivers/net/pse-pd/tps23881.c
++++ b/drivers/net/pse-pd/tps23881.c
+@@ -5,6 +5,7 @@
+ * Copyright (c) 2023 Bootlin, Kory Maincent <kory.maincent@bootlin.com>
+ */
+
++#include <linux/bitfield.h>
+ #include <linux/delay.h>
+ #include <linux/firmware.h>
+ #include <linux/i2c.h>
+@@ -29,6 +30,8 @@
+ #define TPS23881_REG_TPON BIT(0)
+ #define TPS23881_REG_FWREV 0x41
+ #define TPS23881_REG_DEVID 0x43
++#define TPS23881_REG_DEVID_MASK 0xF0
++#define TPS23881_DEVICE_ID 0x02
+ #define TPS23881_REG_SRAM_CTRL 0x60
+ #define TPS23881_REG_SRAM_DATA 0x61
+
+@@ -750,7 +753,7 @@ static int tps23881_i2c_probe(struct i2c_client *client)
+ if (ret < 0)
+ return ret;
+
+- if (ret != 0x22) {
++ if (FIELD_GET(TPS23881_REG_DEVID_MASK, ret) != TPS23881_DEVICE_ID) {
+ dev_err(dev, "Wrong device ID\n");
+ return -ENXIO;
+ }
+diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c
+index 386d62769dedb..cfda32047cffb 100644
+--- a/drivers/net/usb/qmi_wwan.c
++++ b/drivers/net/usb/qmi_wwan.c
+@@ -201,6 +201,7 @@ static int qmimux_rx_fixup(struct usbnet *dev, struct sk_buff *skb)
+ break;
+ default:
+ /* not ip - do not know what to do */
++ kfree_skb(skbn);
+ goto skip;
+ }
+
+diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
+index 5161e7efda2cb..f32e017b62e9b 100644
+--- a/drivers/net/virtio_net.c
++++ b/drivers/net/virtio_net.c
+@@ -3257,7 +3257,11 @@ static int virtnet_set_ringparam(struct net_device *dev,
+ err = virtnet_send_tx_ctrl_coal_vq_cmd(vi, i,
+ vi->intr_coal_tx.max_usecs,
+ vi->intr_coal_tx.max_packets);
+- if (err)
++
++ /* Don't break the tx resize action if the vq coalescing is not
++ * supported. The same is true for rx resize below.
++ */
++ if (err && err != -EOPNOTSUPP)
+ return err;
+ }
+
+@@ -3272,7 +3276,7 @@ static int virtnet_set_ringparam(struct net_device *dev,
+ vi->intr_coal_rx.max_usecs,
+ vi->intr_coal_rx.max_packets);
+ mutex_unlock(&vi->rq[i].dim_lock);
+- if (err)
++ if (err && err != -EOPNOTSUPP)
+ return err;
+ }
+ }
+diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
+index 121f27284be59..1d287ed25a949 100644
+--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
++++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
+@@ -2793,6 +2793,7 @@ int ath12k_dp_rx_peer_frag_setup(struct ath12k *ar, const u8 *peer_mac, int vdev
+ peer = ath12k_peer_find(ab, vdev_id, peer_mac);
+ if (!peer) {
+ spin_unlock_bh(&ab->base_lock);
++ crypto_free_shash(tfm);
+ ath12k_warn(ab, "failed to find the peer to set up fragment info\n");
+ return -ENOENT;
+ }
+diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
+index 55fde0d33183c..f92b4ce49dfd4 100644
+--- a/drivers/net/wireless/ath/ath12k/pci.c
++++ b/drivers/net/wireless/ath/ath12k/pci.c
+@@ -1091,14 +1091,14 @@ void ath12k_pci_ext_irq_enable(struct ath12k_base *ab)
+ {
+ int i;
+
+- set_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
+-
+ for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
+ struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
+
+ napi_enable(&irq_grp->napi);
+ ath12k_pci_ext_grp_enable(irq_grp);
+ }
++
++ set_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
+ }
+
+ void ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
+diff --git a/drivers/net/wireless/realtek/rtlwifi/usb.c b/drivers/net/wireless/realtek/rtlwifi/usb.c
+index 2ea72d9e39577..4d2931e544278 100644
+--- a/drivers/net/wireless/realtek/rtlwifi/usb.c
++++ b/drivers/net/wireless/realtek/rtlwifi/usb.c
+@@ -23,6 +23,8 @@ MODULE_DESCRIPTION("USB basic driver for rtlwifi");
+
+ #define MAX_USBCTRL_VENDORREQ_TIMES 10
+
++static void _rtl_usb_cleanup_tx(struct ieee80211_hw *hw);
++
+ static void _usbctrl_vendorreq_sync(struct usb_device *udev, u8 reqtype,
+ u16 value, void *pdata, u16 len)
+ {
+@@ -285,9 +287,23 @@ static int _rtl_usb_init(struct ieee80211_hw *hw)
+ }
+ /* usb endpoint mapping */
+ err = rtlpriv->cfg->usb_interface_cfg->usb_endpoint_mapping(hw);
+- rtlusb->usb_mq_to_hwq = rtlpriv->cfg->usb_interface_cfg->usb_mq_to_hwq;
+- _rtl_usb_init_tx(hw);
+- _rtl_usb_init_rx(hw);
++ if (err)
++ return err;
++
++ rtlusb->usb_mq_to_hwq = rtlpriv->cfg->usb_interface_cfg->usb_mq_to_hwq;
++
++ err = _rtl_usb_init_tx(hw);
++ if (err)
++ return err;
++
++ err = _rtl_usb_init_rx(hw);
++ if (err)
++ goto err_out;
++
++ return 0;
++
++err_out:
++ _rtl_usb_cleanup_tx(hw);
+ return err;
+ }
+
+@@ -691,17 +707,13 @@ static int rtl_usb_start(struct ieee80211_hw *hw)
+ }
+
+ /*======================= tx =========================================*/
+-static void rtl_usb_cleanup(struct ieee80211_hw *hw)
++static void _rtl_usb_cleanup_tx(struct ieee80211_hw *hw)
+ {
+ u32 i;
+ struct sk_buff *_skb;
+ struct rtl_usb *rtlusb = rtl_usbdev(rtl_usbpriv(hw));
+ struct ieee80211_tx_info *txinfo;
+
+- /* clean up rx stuff. */
+- _rtl_usb_cleanup_rx(hw);
+-
+- /* clean up tx stuff */
+ for (i = 0; i < RTL_USB_MAX_EP_NUM; i++) {
+ while ((_skb = skb_dequeue(&rtlusb->tx_skb_queue[i]))) {
+ rtlusb->usb_tx_cleanup(hw, _skb);
+@@ -715,6 +727,12 @@ static void rtl_usb_cleanup(struct ieee80211_hw *hw)
+ usb_kill_anchored_urbs(&rtlusb->tx_submitted);
+ }
+
++static void rtl_usb_cleanup(struct ieee80211_hw *hw)
++{
++ _rtl_usb_cleanup_rx(hw);
++ _rtl_usb_cleanup_tx(hw);
++}
++
+ /* We may add some struct into struct rtl_usb later. Do deinit here. */
+ static void rtl_usb_deinit(struct ieee80211_hw *hw)
+ {
+diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
+index b36aa9a6bb3fc..312b57d7da642 100644
+--- a/drivers/net/wireless/realtek/rtw89/pci.c
++++ b/drivers/net/wireless/realtek/rtw89/pci.c
+@@ -183,14 +183,17 @@ static void rtw89_pci_sync_skb_for_device(struct rtw89_dev *rtwdev,
+ static void rtw89_pci_rxbd_info_update(struct rtw89_dev *rtwdev,
+ struct sk_buff *skb)
+ {
+- struct rtw89_pci_rxbd_info *rxbd_info;
+ struct rtw89_pci_rx_info *rx_info = RTW89_PCI_RX_SKB_CB(skb);
++ struct rtw89_pci_rxbd_info *rxbd_info;
++ __le32 info;
+
+ rxbd_info = (struct rtw89_pci_rxbd_info *)skb->data;
+- rx_info->fs = le32_get_bits(rxbd_info->dword, RTW89_PCI_RXBD_FS);
+- rx_info->ls = le32_get_bits(rxbd_info->dword, RTW89_PCI_RXBD_LS);
+- rx_info->len = le32_get_bits(rxbd_info->dword, RTW89_PCI_RXBD_WRITE_SIZE);
+- rx_info->tag = le32_get_bits(rxbd_info->dword, RTW89_PCI_RXBD_TAG);
++ info = rxbd_info->dword;
++
++ rx_info->fs = le32_get_bits(info, RTW89_PCI_RXBD_FS);
++ rx_info->ls = le32_get_bits(info, RTW89_PCI_RXBD_LS);
++ rx_info->len = le32_get_bits(info, RTW89_PCI_RXBD_WRITE_SIZE);
++ rx_info->tag = le32_get_bits(info, RTW89_PCI_RXBD_TAG);
+ }
+
+ static int rtw89_pci_validate_rx_tag(struct rtw89_dev *rtwdev,
+diff --git a/drivers/nvme/host/apple.c b/drivers/nvme/host/apple.c
+index 0cfa39361d3b6..25ecc1a005c5a 100644
+--- a/drivers/nvme/host/apple.c
++++ b/drivers/nvme/host/apple.c
+@@ -1388,7 +1388,7 @@ static void devm_apple_nvme_mempool_destroy(void *data)
+ mempool_destroy(data);
+ }
+
+-static int apple_nvme_probe(struct platform_device *pdev)
++static struct apple_nvme *apple_nvme_alloc(struct platform_device *pdev)
+ {
+ struct device *dev = &pdev->dev;
+ struct apple_nvme *anv;
+@@ -1396,7 +1396,7 @@ static int apple_nvme_probe(struct platform_device *pdev)
+
+ anv = devm_kzalloc(dev, sizeof(*anv), GFP_KERNEL);
+ if (!anv)
+- return -ENOMEM;
++ return ERR_PTR(-ENOMEM);
+
+ anv->dev = get_device(dev);
+ anv->adminq.is_adminq = true;
+@@ -1516,10 +1516,26 @@ static int apple_nvme_probe(struct platform_device *pdev)
+ goto put_dev;
+ }
+
++ return anv;
++put_dev:
++ put_device(anv->dev);
++ return ERR_PTR(ret);
++}
++
++static int apple_nvme_probe(struct platform_device *pdev)
++{
++ struct apple_nvme *anv;
++ int ret;
++
++ anv = apple_nvme_alloc(pdev);
++ if (IS_ERR(anv))
++ return PTR_ERR(anv);
++
+ anv->ctrl.admin_q = blk_mq_alloc_queue(&anv->admin_tagset, NULL, NULL);
+ if (IS_ERR(anv->ctrl.admin_q)) {
+ ret = -ENOMEM;
+- goto put_dev;
++ anv->ctrl.admin_q = NULL;
++ goto out_uninit_ctrl;
+ }
+
+ nvme_reset_ctrl(&anv->ctrl);
+@@ -1527,8 +1543,9 @@ static int apple_nvme_probe(struct platform_device *pdev)
+
+ return 0;
+
+-put_dev:
+- put_device(anv->dev);
++out_uninit_ctrl:
++ nvme_uninit_ctrl(&anv->ctrl);
++ nvme_put_ctrl(&anv->ctrl);
+ return ret;
+ }
+
+diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
+index 5a93f021ca4f1..7168ff4cc62bb 100644
+--- a/drivers/nvme/host/pci.c
++++ b/drivers/nvme/host/pci.c
+@@ -826,9 +826,9 @@ static blk_status_t nvme_map_metadata(struct nvme_dev *dev, struct request *req,
+ struct nvme_command *cmnd)
+ {
+ struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
++ struct bio_vec bv = rq_integrity_vec(req);
+
+- iod->meta_dma = dma_map_bvec(dev->dev, rq_integrity_vec(req),
+- rq_dma_dir(req), 0);
++ iod->meta_dma = dma_map_bvec(dev->dev, &bv, rq_dma_dir(req), 0);
+ if (dma_mapping_error(dev->dev, iod->meta_dma))
+ return BLK_STS_IOERR;
+ cmnd->rw.metadata = cpu_to_le64(iod->meta_dma);
+@@ -968,7 +968,7 @@ static __always_inline void nvme_pci_unmap_rq(struct request *req)
+ struct nvme_iod *iod = blk_mq_rq_to_pdu(req);
+
+ dma_unmap_page(dev->dev, iod->meta_dma,
+- rq_integrity_vec(req)->bv_len, rq_dma_dir(req));
++ rq_integrity_vec(req).bv_len, rq_dma_dir(req));
+ }
+
+ if (blk_rq_nr_phys_segments(req))
+diff --git a/drivers/platform/chrome/cros_ec_lpc.c b/drivers/platform/chrome/cros_ec_lpc.c
+index ddfbfec44f4cc..43e0914256a3c 100644
+--- a/drivers/platform/chrome/cros_ec_lpc.c
++++ b/drivers/platform/chrome/cros_ec_lpc.c
+@@ -39,6 +39,11 @@ static bool cros_ec_lpc_acpi_device_found;
+ * be used as the base port for EC mapped memory.
+ */
+ #define CROS_EC_LPC_QUIRK_REMAP_MEMORY BIT(0)
++/*
++ * Indicates that lpc_driver_data.quirk_acpi_id should be used to find
++ * the ACPI device.
++ */
++#define CROS_EC_LPC_QUIRK_ACPI_ID BIT(1)
+
+ /**
+ * struct lpc_driver_data - driver data attached to a DMI device ID to indicate
+@@ -46,10 +51,12 @@ static bool cros_ec_lpc_acpi_device_found;
+ * @quirks: a bitfield composed of quirks from CROS_EC_LPC_QUIRK_*
+ * @quirk_mmio_memory_base: The first I/O port addressing EC mapped memory (used
+ * when quirk ...REMAP_MEMORY is set.)
++ * @quirk_acpi_id: An ACPI HID to be used to find the ACPI device.
+ */
+ struct lpc_driver_data {
+ u32 quirks;
+ u16 quirk_mmio_memory_base;
++ const char *quirk_acpi_id;
+ };
+
+ /**
+@@ -374,6 +381,26 @@ static void cros_ec_lpc_acpi_notify(acpi_handle device, u32 value, void *data)
+ pm_system_wakeup();
+ }
+
++static acpi_status cros_ec_lpc_parse_device(acpi_handle handle, u32 level,
++ void *context, void **retval)
++{
++ *(struct acpi_device **)context = acpi_fetch_acpi_dev(handle);
++ return AE_CTRL_TERMINATE;
++}
++
++static struct acpi_device *cros_ec_lpc_get_device(const char *id)
++{
++ struct acpi_device *adev = NULL;
++ acpi_status status = acpi_get_devices(id, cros_ec_lpc_parse_device,
++ &adev, NULL);
++ if (ACPI_FAILURE(status)) {
++ pr_warn(DRV_NAME ": Looking for %s failed\n", id);
++ return NULL;
++ }
++
++ return adev;
++}
++
+ static int cros_ec_lpc_probe(struct platform_device *pdev)
+ {
+ struct device *dev = &pdev->dev;
+@@ -401,6 +428,16 @@ static int cros_ec_lpc_probe(struct platform_device *pdev)
+
+ if (quirks & CROS_EC_LPC_QUIRK_REMAP_MEMORY)
+ ec_lpc->mmio_memory_base = driver_data->quirk_mmio_memory_base;
++
++ if (quirks & CROS_EC_LPC_QUIRK_ACPI_ID) {
++ adev = cros_ec_lpc_get_device(driver_data->quirk_acpi_id);
++ if (!adev) {
++ dev_err(dev, "failed to get ACPI device '%s'",
++ driver_data->quirk_acpi_id);
++ return -ENODEV;
++ }
++ ACPI_COMPANION_SET(dev, adev);
++ }
+ }
+
+ /*
+@@ -661,23 +698,12 @@ static struct platform_device cros_ec_lpc_device = {
+ .name = DRV_NAME
+ };
+
+-static acpi_status cros_ec_lpc_parse_device(acpi_handle handle, u32 level,
+- void *context, void **retval)
+-{
+- *(bool *)context = true;
+- return AE_CTRL_TERMINATE;
+-}
+-
+ static int __init cros_ec_lpc_init(void)
+ {
+ int ret;
+- acpi_status status;
+ const struct dmi_system_id *dmi_match;
+
+- status = acpi_get_devices(ACPI_DRV_NAME, cros_ec_lpc_parse_device,
+- &cros_ec_lpc_acpi_device_found, NULL);
+- if (ACPI_FAILURE(status))
+- pr_warn(DRV_NAME ": Looking for %s failed\n", ACPI_DRV_NAME);
++ cros_ec_lpc_acpi_device_found = !!cros_ec_lpc_get_device(ACPI_DRV_NAME);
+
+ dmi_match = dmi_first_match(cros_ec_lpc_dmi_table);
+
+diff --git a/drivers/platform/x86/intel/ifs/runtest.c b/drivers/platform/x86/intel/ifs/runtest.c
+index 282e4bfe30da3..be3d51ed0e474 100644
+--- a/drivers/platform/x86/intel/ifs/runtest.c
++++ b/drivers/platform/x86/intel/ifs/runtest.c
+@@ -221,8 +221,8 @@ static int doscan(void *data)
+ */
+ static void ifs_test_core(int cpu, struct device *dev)
+ {
++ union ifs_status status = {};
+ union ifs_scan activate;
+- union ifs_status status;
+ unsigned long timeout;
+ struct ifs_data *ifsd;
+ int to_start, to_stop;
+diff --git a/drivers/platform/x86/intel/vbtn.c b/drivers/platform/x86/intel/vbtn.c
+index 9b7ce03ba085c..a353e830b65fd 100644
+--- a/drivers/platform/x86/intel/vbtn.c
++++ b/drivers/platform/x86/intel/vbtn.c
+@@ -7,11 +7,13 @@
+ */
+
+ #include <linux/acpi.h>
++#include <linux/cleanup.h>
+ #include <linux/dmi.h>
+ #include <linux/input.h>
+ #include <linux/input/sparse-keymap.h>
+ #include <linux/kernel.h>
+ #include <linux/module.h>
++#include <linux/mutex.h>
+ #include <linux/platform_device.h>
+ #include <linux/suspend.h>
+ #include "../dual_accel_detect.h"
+@@ -66,6 +68,7 @@ static const struct key_entry intel_vbtn_switchmap[] = {
+ };
+
+ struct intel_vbtn_priv {
++ struct mutex mutex; /* Avoid notify_handler() racing with itself */
+ struct input_dev *buttons_dev;
+ struct input_dev *switches_dev;
+ bool dual_accel;
+@@ -155,6 +158,8 @@ static void notify_handler(acpi_handle handle, u32 event, void *context)
+ bool autorelease;
+ int ret;
+
++ guard(mutex)(&priv->mutex);
++
+ if ((ke = sparse_keymap_entry_from_scancode(priv->buttons_dev, event))) {
+ if (!priv->has_buttons) {
+ dev_warn(&device->dev, "Warning: received 0x%02x button event on a device without buttons, please report this.\n",
+@@ -290,6 +295,10 @@ static int intel_vbtn_probe(struct platform_device *device)
+ return -ENOMEM;
+ dev_set_drvdata(&device->dev, priv);
+
++ err = devm_mutex_init(&device->dev, &priv->mutex);
++ if (err)
++ return err;
++
+ priv->dual_accel = dual_accel;
+ priv->has_buttons = has_buttons;
+ priv->has_switches = has_switches;
+diff --git a/drivers/power/supply/axp288_charger.c b/drivers/power/supply/axp288_charger.c
+index b5903193e2f96..ac05942e4e6ac 100644
+--- a/drivers/power/supply/axp288_charger.c
++++ b/drivers/power/supply/axp288_charger.c
+@@ -178,18 +178,18 @@ static inline int axp288_charger_set_cv(struct axp288_chrg_info *info, int cv)
+ u8 reg_val;
+ int ret;
+
+- if (cv <= CV_4100MV) {
+- reg_val = CHRG_CCCV_CV_4100MV;
+- cv = CV_4100MV;
+- } else if (cv <= CV_4150MV) {
+- reg_val = CHRG_CCCV_CV_4150MV;
+- cv = CV_4150MV;
+- } else if (cv <= CV_4200MV) {
++ if (cv >= CV_4350MV) {
++ reg_val = CHRG_CCCV_CV_4350MV;
++ cv = CV_4350MV;
++ } else if (cv >= CV_4200MV) {
+ reg_val = CHRG_CCCV_CV_4200MV;
+ cv = CV_4200MV;
++ } else if (cv >= CV_4150MV) {
++ reg_val = CHRG_CCCV_CV_4150MV;
++ cv = CV_4150MV;
+ } else {
+- reg_val = CHRG_CCCV_CV_4350MV;
+- cv = CV_4350MV;
++ reg_val = CHRG_CCCV_CV_4100MV;
++ cv = CV_4100MV;
+ }
+
+ reg_val = reg_val << CHRG_CCCV_CV_BIT_POS;
+@@ -337,8 +337,8 @@ static int axp288_charger_usb_set_property(struct power_supply *psy,
+ }
+ break;
+ case POWER_SUPPLY_PROP_CONSTANT_CHARGE_VOLTAGE:
+- scaled_val = min(val->intval, info->max_cv);
+- scaled_val = DIV_ROUND_CLOSEST(scaled_val, 1000);
++ scaled_val = DIV_ROUND_CLOSEST(val->intval, 1000);
++ scaled_val = min(scaled_val, info->max_cv);
+ ret = axp288_charger_set_cv(info, scaled_val);
+ if (ret < 0) {
+ dev_warn(&info->pdev->dev, "set charge voltage failed\n");
+diff --git a/drivers/power/supply/qcom_battmgr.c b/drivers/power/supply/qcom_battmgr.c
+index ec163d1bcd189..44c6301f5f174 100644
+--- a/drivers/power/supply/qcom_battmgr.c
++++ b/drivers/power/supply/qcom_battmgr.c
+@@ -486,7 +486,7 @@ static int qcom_battmgr_bat_get_property(struct power_supply *psy,
+ int ret;
+
+ if (!battmgr->service_up)
+- return -ENODEV;
++ return -EAGAIN;
+
+ if (battmgr->variant == QCOM_BATTMGR_SC8280XP)
+ ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp);
+@@ -683,7 +683,7 @@ static int qcom_battmgr_ac_get_property(struct power_supply *psy,
+ int ret;
+
+ if (!battmgr->service_up)
+- return -ENODEV;
++ return -EAGAIN;
+
+ ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp);
+ if (ret)
+@@ -748,7 +748,7 @@ static int qcom_battmgr_usb_get_property(struct power_supply *psy,
+ int ret;
+
+ if (!battmgr->service_up)
+- return -ENODEV;
++ return -EAGAIN;
+
+ if (battmgr->variant == QCOM_BATTMGR_SC8280XP)
+ ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp);
+@@ -867,7 +867,7 @@ static int qcom_battmgr_wls_get_property(struct power_supply *psy,
+ int ret;
+
+ if (!battmgr->service_up)
+- return -ENODEV;
++ return -EAGAIN;
+
+ if (battmgr->variant == QCOM_BATTMGR_SC8280XP)
+ ret = qcom_battmgr_bat_sc8280xp_update(battmgr, psp);
+diff --git a/drivers/power/supply/rt5033_battery.c b/drivers/power/supply/rt5033_battery.c
+index 32eafe2c00af5..7a27b262fb84a 100644
+--- a/drivers/power/supply/rt5033_battery.c
++++ b/drivers/power/supply/rt5033_battery.c
+@@ -159,6 +159,7 @@ static int rt5033_battery_probe(struct i2c_client *client)
+ return -EINVAL;
+ }
+
++ i2c_set_clientdata(client, battery);
+ psy_cfg.of_node = client->dev.of_node;
+ psy_cfg.drv_data = battery;
+
+diff --git a/drivers/s390/char/sclp_sd.c b/drivers/s390/char/sclp_sd.c
+index f9e164be7568f..944e75beb160c 100644
+--- a/drivers/s390/char/sclp_sd.c
++++ b/drivers/s390/char/sclp_sd.c
+@@ -320,8 +320,14 @@ static int sclp_sd_store_data(struct sclp_sd_data *result, u8 di)
+ &esize);
+ if (rc) {
+ /* Cancel running request if interrupted */
+- if (rc == -ERESTARTSYS)
+- sclp_sd_sync(page, SD_EQ_HALT, di, 0, 0, NULL, NULL);
++ if (rc == -ERESTARTSYS) {
++ if (sclp_sd_sync(page, SD_EQ_HALT, di, 0, 0, NULL, NULL)) {
++ pr_warn("Could not stop Store Data request - leaking at least %zu bytes\n",
++ (size_t)dsize * PAGE_SIZE);
++ data = NULL;
++ asce = 0;
++ }
++ }
+ vfree(data);
+ goto out;
+ }
+diff --git a/drivers/scsi/mpi3mr/mpi3mr_os.c b/drivers/scsi/mpi3mr/mpi3mr_os.c
+index bce639a6cca17..c051692395ccb 100644
+--- a/drivers/scsi/mpi3mr/mpi3mr_os.c
++++ b/drivers/scsi/mpi3mr/mpi3mr_os.c
+@@ -3453,6 +3453,17 @@ static int mpi3mr_prepare_sg_scmd(struct mpi3mr_ioc *mrioc,
+ scmd->sc_data_direction);
+ priv->meta_sg_valid = 1; /* To unmap meta sg DMA */
+ } else {
++ /*
++ * Some firmware versions byte-swap the REPORT ZONES command
++ * reply from ATA-ZAC devices by directly accessing in the host
++ * buffer. This does not respect the default command DMA
++ * direction and causes IOMMU page faults on some architectures
++ * with an IOMMU enforcing write mappings (e.g. AMD hosts).
++ * Avoid such issue by making the REPORT ZONES buffer mapping
++ * bi-directional.
++ */
++ if (scmd->cmnd[0] == ZBC_IN && scmd->cmnd[1] == ZI_REPORT_ZONES)
++ scmd->sc_data_direction = DMA_BIDIRECTIONAL;
+ sg_scmd = scsi_sglist(scmd);
+ sges_left = scsi_dma_map(scmd);
+ }
+diff --git a/drivers/scsi/mpt3sas/mpt3sas_base.c b/drivers/scsi/mpt3sas/mpt3sas_base.c
+index b2bcf4a27ddcd..b785a7e88b498 100644
+--- a/drivers/scsi/mpt3sas/mpt3sas_base.c
++++ b/drivers/scsi/mpt3sas/mpt3sas_base.c
+@@ -2671,6 +2671,22 @@ _base_build_zero_len_sge_ieee(struct MPT3SAS_ADAPTER *ioc, void *paddr)
+ _base_add_sg_single_ieee(paddr, sgl_flags, 0, 0, -1);
+ }
+
++static inline int _base_scsi_dma_map(struct scsi_cmnd *cmd)
++{
++ /*
++ * Some firmware versions byte-swap the REPORT ZONES command reply from
++ * ATA-ZAC devices by directly accessing in the host buffer. This does
++ * not respect the default command DMA direction and causes IOMMU page
++ * faults on some architectures with an IOMMU enforcing write mappings
++ * (e.g. AMD hosts). Avoid such issue by making the report zones buffer
++ * mapping bi-directional.
++ */
++ if (cmd->cmnd[0] == ZBC_IN && cmd->cmnd[1] == ZI_REPORT_ZONES)
++ cmd->sc_data_direction = DMA_BIDIRECTIONAL;
++
++ return scsi_dma_map(cmd);
++}
++
+ /**
+ * _base_build_sg_scmd - main sg creation routine
+ * pcie_device is unused here!
+@@ -2717,7 +2733,7 @@ _base_build_sg_scmd(struct MPT3SAS_ADAPTER *ioc,
+ sgl_flags = sgl_flags << MPI2_SGE_FLAGS_SHIFT;
+
+ sg_scmd = scsi_sglist(scmd);
+- sges_left = scsi_dma_map(scmd);
++ sges_left = _base_scsi_dma_map(scmd);
+ if (sges_left < 0)
+ return -ENOMEM;
+
+@@ -2861,7 +2877,7 @@ _base_build_sg_scmd_ieee(struct MPT3SAS_ADAPTER *ioc,
+ }
+
+ sg_scmd = scsi_sglist(scmd);
+- sges_left = scsi_dma_map(scmd);
++ sges_left = _base_scsi_dma_map(scmd);
+ if (sges_left < 0)
+ return -ENOMEM;
+
+diff --git a/drivers/scsi/sd.c b/drivers/scsi/sd.c
+index 1b7561abe05d9..6b64af7d49273 100644
+--- a/drivers/scsi/sd.c
++++ b/drivers/scsi/sd.c
+@@ -4119,6 +4119,8 @@ static int sd_resume(struct device *dev)
+ {
+ struct scsi_disk *sdkp = dev_get_drvdata(dev);
+
++ sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
++
+ if (opal_unlock_from_suspend(sdkp->opal_dev)) {
+ sd_printk(KERN_NOTICE, sdkp, "OPAL unlock failed\n");
+ return -EIO;
+@@ -4135,13 +4137,12 @@ static int sd_resume_common(struct device *dev, bool runtime)
+ if (!sdkp) /* E.g.: runtime resume at the start of sd_probe() */
+ return 0;
+
+- sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
+-
+ if (!sd_do_start_stop(sdkp->device, runtime)) {
+ sdkp->suspended = false;
+ return 0;
+ }
+
++ sd_printk(KERN_NOTICE, sdkp, "Starting disk\n");
+ ret = sd_start_stop_device(sdkp, 1);
+ if (!ret) {
+ sd_resume(dev);
+diff --git a/drivers/soc/qcom/icc-bwmon.c b/drivers/soc/qcom/icc-bwmon.c
+index ecddb60bd6650..e7851974084b6 100644
+--- a/drivers/soc/qcom/icc-bwmon.c
++++ b/drivers/soc/qcom/icc-bwmon.c
+@@ -783,9 +783,14 @@ static int bwmon_probe(struct platform_device *pdev)
+ bwmon->dev = dev;
+
+ bwmon_disable(bwmon);
+- ret = devm_request_threaded_irq(dev, bwmon->irq, bwmon_intr,
+- bwmon_intr_thread,
+- IRQF_ONESHOT, dev_name(dev), bwmon);
++
++ /*
++ * SoCs with multiple cpu-bwmon instances can end up using a shared interrupt
++ * line. Using the devm_ variant might result in the IRQ handler being executed
++ * after bwmon_disable in bwmon_remove()
++ */
++ ret = request_threaded_irq(bwmon->irq, bwmon_intr, bwmon_intr_thread,
++ IRQF_ONESHOT | IRQF_SHARED, dev_name(dev), bwmon);
+ if (ret)
+ return dev_err_probe(dev, ret, "failed to request IRQ\n");
+
+@@ -800,6 +805,7 @@ static void bwmon_remove(struct platform_device *pdev)
+ struct icc_bwmon *bwmon = platform_get_drvdata(pdev);
+
+ bwmon_disable(bwmon);
++ free_irq(bwmon->irq, bwmon);
+ }
+
+ static const struct icc_bwmon_data msm8998_bwmon_data = {
+diff --git a/drivers/spi/spi-fsl-lpspi.c b/drivers/spi/spi-fsl-lpspi.c
+index aa5ed254be46c..f2d7eedd324b7 100644
+--- a/drivers/spi/spi-fsl-lpspi.c
++++ b/drivers/spi/spi-fsl-lpspi.c
+@@ -296,7 +296,7 @@ static void fsl_lpspi_set_watermark(struct fsl_lpspi_data *fsl_lpspi)
+ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
+ {
+ struct lpspi_config config = fsl_lpspi->config;
+- unsigned int perclk_rate, scldiv;
++ unsigned int perclk_rate, scldiv, div;
+ u8 prescale;
+
+ perclk_rate = clk_get_rate(fsl_lpspi->clk_per);
+@@ -313,8 +313,10 @@ static int fsl_lpspi_set_bitrate(struct fsl_lpspi_data *fsl_lpspi)
+ return -EINVAL;
+ }
+
++ div = DIV_ROUND_UP(perclk_rate, config.speed_hz);
++
+ for (prescale = 0; prescale < 8; prescale++) {
+- scldiv = perclk_rate / config.speed_hz / (1 << prescale) - 2;
++ scldiv = div / (1 << prescale) - 2;
+ if (scldiv < 256) {
+ fsl_lpspi->config.prescale = prescale;
+ break;
+diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
+index 05e6d007f9a7f..5304728c68c20 100644
+--- a/drivers/spi/spidev.c
++++ b/drivers/spi/spidev.c
+@@ -700,6 +700,7 @@ static const struct class spidev_class = {
+ };
+
+ static const struct spi_device_id spidev_spi_ids[] = {
++ { .name = "bh2228fv" },
+ { .name = "dh2228fv" },
+ { .name = "ltc2488" },
+ { .name = "sx1301" },
+diff --git a/drivers/spmi/spmi-pmic-arb.c b/drivers/spmi/spmi-pmic-arb.c
+index 791cdc160c515..f36f57bde0771 100644
+--- a/drivers/spmi/spmi-pmic-arb.c
++++ b/drivers/spmi/spmi-pmic-arb.c
+@@ -398,7 +398,7 @@ static int pmic_arb_fmt_read_cmd(struct spmi_pmic_arb_bus *bus, u8 opc, u8 sid,
+
+ *offset = rc;
+ if (bc >= PMIC_ARB_MAX_TRANS_BYTES) {
+- dev_err(&bus->spmic->dev, "pmic-arb supports 1..%d bytes per trans, but:%zu requested",
++ dev_err(&bus->spmic->dev, "pmic-arb supports 1..%d bytes per trans, but:%zu requested\n",
+ PMIC_ARB_MAX_TRANS_BYTES, len);
+ return -EINVAL;
+ }
+@@ -477,7 +477,7 @@ static int pmic_arb_fmt_write_cmd(struct spmi_pmic_arb_bus *bus, u8 opc,
+
+ *offset = rc;
+ if (bc >= PMIC_ARB_MAX_TRANS_BYTES) {
+- dev_err(&bus->spmic->dev, "pmic-arb supports 1..%d bytes per trans, but:%zu requested",
++ dev_err(&bus->spmic->dev, "pmic-arb supports 1..%d bytes per trans, but:%zu requested\n",
+ PMIC_ARB_MAX_TRANS_BYTES, len);
+ return -EINVAL;
+ }
+@@ -1702,7 +1702,7 @@ static int spmi_pmic_arb_bus_init(struct platform_device *pdev,
+
+ index = of_property_match_string(node, "reg-names", "cnfg");
+ if (index < 0) {
+- dev_err(dev, "cnfg reg region missing");
++ dev_err(dev, "cnfg reg region missing\n");
+ return -EINVAL;
+ }
+
+@@ -1712,7 +1712,7 @@ static int spmi_pmic_arb_bus_init(struct platform_device *pdev,
+
+ index = of_property_match_string(node, "reg-names", "intr");
+ if (index < 0) {
+- dev_err(dev, "intr reg region missing");
++ dev_err(dev, "intr reg region missing\n");
+ return -EINVAL;
+ }
+
+@@ -1737,8 +1737,7 @@ static int spmi_pmic_arb_bus_init(struct platform_device *pdev,
+
+ dev_dbg(&pdev->dev, "adding irq domain for bus %d\n", bus_index);
+
+- bus->domain = irq_domain_add_tree(dev->of_node,
+- &pmic_arb_irq_domain_ops, bus);
++ bus->domain = irq_domain_add_tree(node, &pmic_arb_irq_domain_ops, bus);
+ if (!bus->domain) {
+ dev_err(&pdev->dev, "unable to create irq_domain\n");
+ return -ENOMEM;
+diff --git a/drivers/thermal/intel/intel_hfi.c b/drivers/thermal/intel/intel_hfi.c
+index a180a98bb9f15..5b18a46a10b06 100644
+--- a/drivers/thermal/intel/intel_hfi.c
++++ b/drivers/thermal/intel/intel_hfi.c
+@@ -401,10 +401,10 @@ static void hfi_disable(void)
+ * intel_hfi_online() - Enable HFI on @cpu
+ * @cpu: CPU in which the HFI will be enabled
+ *
+- * Enable the HFI to be used in @cpu. The HFI is enabled at the die/package
+- * level. The first CPU in the die/package to come online does the full HFI
++ * Enable the HFI to be used in @cpu. The HFI is enabled at the package
++ * level. The first CPU in the package to come online does the full HFI
+ * initialization. Subsequent CPUs will just link themselves to the HFI
+- * instance of their die/package.
++ * instance of their package.
+ *
+ * This function is called before enabling the thermal vector in the local APIC
+ * in order to ensure that @cpu has an associated HFI instance when it receives
+@@ -414,31 +414,31 @@ void intel_hfi_online(unsigned int cpu)
+ {
+ struct hfi_instance *hfi_instance;
+ struct hfi_cpu_info *info;
+- u16 die_id;
++ u16 pkg_id;
+
+ /* Nothing to do if hfi_instances are missing. */
+ if (!hfi_instances)
+ return;
+
+ /*
+- * Link @cpu to the HFI instance of its package/die. It does not
++ * Link @cpu to the HFI instance of its package. It does not
+ * matter whether the instance has been initialized.
+ */
+ info = &per_cpu(hfi_cpu_info, cpu);
+- die_id = topology_logical_die_id(cpu);
++ pkg_id = topology_logical_package_id(cpu);
+ hfi_instance = info->hfi_instance;
+ if (!hfi_instance) {
+- if (die_id >= max_hfi_instances)
++ if (pkg_id >= max_hfi_instances)
+ return;
+
+- hfi_instance = &hfi_instances[die_id];
++ hfi_instance = &hfi_instances[pkg_id];
+ info->hfi_instance = hfi_instance;
+ }
+
+ init_hfi_cpu_index(info);
+
+ /*
+- * Now check if the HFI instance of the package/die of @cpu has been
++ * Now check if the HFI instance of the package of @cpu has been
+ * initialized (by checking its header). In such case, all we have to
+ * do is to add @cpu to this instance's cpumask and enable the instance
+ * if needed.
+@@ -504,7 +504,7 @@ void intel_hfi_online(unsigned int cpu)
+ *
+ * On some processors, hardware remembers previous programming settings even
+ * after being reprogrammed. Thus, keep HFI enabled even if all CPUs in the
+- * die/package of @cpu are offline. See note in intel_hfi_online().
++ * package of @cpu are offline. See note in intel_hfi_online().
+ */
+ void intel_hfi_offline(unsigned int cpu)
+ {
+@@ -674,9 +674,13 @@ void __init intel_hfi_init(void)
+ if (hfi_parse_features())
+ return;
+
+- /* There is one HFI instance per die/package. */
+- max_hfi_instances = topology_max_packages() *
+- topology_max_dies_per_package();
++ /*
++ * Note: HFI resources are managed at the physical package scope.
++ * There could be platforms that enumerate packages as Linux dies.
++ * Special handling would be needed if this happens on an HFI-capable
++ * platform.
++ */
++ max_hfi_instances = topology_max_packages();
+
+ /*
+ * This allocation may fail. CPU hotplug callbacks must check
+diff --git a/drivers/tty/serial/sc16is7xx.c b/drivers/tty/serial/sc16is7xx.c
+index bf0065d1c8e9c..9547aa8f45205 100644
+--- a/drivers/tty/serial/sc16is7xx.c
++++ b/drivers/tty/serial/sc16is7xx.c
+@@ -326,6 +326,7 @@ struct sc16is7xx_one {
+ struct kthread_work reg_work;
+ struct kthread_delayed_work ms_work;
+ struct sc16is7xx_one_config config;
++ unsigned char buf[SC16IS7XX_FIFO_SIZE]; /* Rx buffer. */
+ unsigned int old_mctrl;
+ u8 old_lcr; /* Value before EFR access. */
+ bool irda_mode;
+@@ -339,7 +340,6 @@ struct sc16is7xx_port {
+ unsigned long gpio_valid_mask;
+ #endif
+ u8 mctrl_mask;
+- unsigned char buf[SC16IS7XX_FIFO_SIZE];
+ struct kthread_worker kworker;
+ struct task_struct *kworker_task;
+ struct sc16is7xx_one p[];
+@@ -591,6 +591,8 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
+ SC16IS7XX_MCR_CLKSEL_BIT,
+ prescaler == 1 ? 0 : SC16IS7XX_MCR_CLKSEL_BIT);
+
++ mutex_lock(&one->efr_lock);
++
+ /* Backup LCR and access special register set (DLL/DLH) */
+ lcr = sc16is7xx_port_read(port, SC16IS7XX_LCR_REG);
+ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG,
+@@ -605,24 +607,26 @@ static int sc16is7xx_set_baud(struct uart_port *port, int baud)
+ /* Restore LCR and access to general register set */
+ sc16is7xx_port_write(port, SC16IS7XX_LCR_REG, lcr);
+
++ mutex_unlock(&one->efr_lock);
++
+ return DIV_ROUND_CLOSEST((clk / prescaler) / 16, div);
+ }
+
+ static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen,
+ unsigned int iir)
+ {
+- struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
++ struct sc16is7xx_one *one = to_sc16is7xx_one(port, port);
+ unsigned int lsr = 0, bytes_read, i;
+ bool read_lsr = (iir == SC16IS7XX_IIR_RLSE_SRC) ? true : false;
+ u8 ch, flag;
+
+- if (unlikely(rxlen >= sizeof(s->buf))) {
++ if (unlikely(rxlen >= sizeof(one->buf))) {
+ dev_warn_ratelimited(port->dev,
+ "ttySC%i: Possible RX FIFO overrun: %d\n",
+ port->line, rxlen);
+ port->icount.buf_overrun++;
+ /* Ensure sanity of RX level */
+- rxlen = sizeof(s->buf);
++ rxlen = sizeof(one->buf);
+ }
+
+ while (rxlen) {
+@@ -635,10 +639,10 @@ static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen,
+ lsr = 0;
+
+ if (read_lsr) {
+- s->buf[0] = sc16is7xx_port_read(port, SC16IS7XX_RHR_REG);
++ one->buf[0] = sc16is7xx_port_read(port, SC16IS7XX_RHR_REG);
+ bytes_read = 1;
+ } else {
+- sc16is7xx_fifo_read(port, s->buf, rxlen);
++ sc16is7xx_fifo_read(port, one->buf, rxlen);
+ bytes_read = rxlen;
+ }
+
+@@ -671,7 +675,7 @@ static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen,
+ }
+
+ for (i = 0; i < bytes_read; ++i) {
+- ch = s->buf[i];
++ ch = one->buf[i];
+ if (uart_handle_sysrq_char(port, ch))
+ continue;
+
+@@ -689,10 +693,10 @@ static void sc16is7xx_handle_rx(struct uart_port *port, unsigned int rxlen,
+
+ static void sc16is7xx_handle_tx(struct uart_port *port)
+ {
+- struct sc16is7xx_port *s = dev_get_drvdata(port->dev);
+ struct tty_port *tport = &port->state->port;
+ unsigned long flags;
+ unsigned int txlen;
++ unsigned char *tail;
+
+ if (unlikely(port->x_char)) {
+ sc16is7xx_port_write(port, SC16IS7XX_THR_REG, port->x_char);
+@@ -717,8 +721,9 @@ static void sc16is7xx_handle_tx(struct uart_port *port)
+ txlen = 0;
+ }
+
+- txlen = uart_fifo_out(port, s->buf, txlen);
+- sc16is7xx_fifo_write(port, s->buf, txlen);
++ txlen = kfifo_out_linear_ptr(&tport->xmit_fifo, &tail, txlen);
++ sc16is7xx_fifo_write(port, tail, txlen);
++ uart_xmit_advance(port, txlen);
+
+ uart_port_lock_irqsave(port, &flags);
+ if (kfifo_len(&tport->xmit_fifo) < WAKEUP_CHARS)
+diff --git a/drivers/tty/serial/serial_core.c b/drivers/tty/serial/serial_core.c
+index 2a8006e3d6878..9967444eae10c 100644
+--- a/drivers/tty/serial/serial_core.c
++++ b/drivers/tty/serial/serial_core.c
+@@ -881,6 +881,14 @@ static int uart_set_info(struct tty_struct *tty, struct tty_port *port,
+ new_flags = (__force upf_t)new_info->flags;
+ old_custom_divisor = uport->custom_divisor;
+
++ if (!(uport->flags & UPF_FIXED_PORT)) {
++ unsigned int uartclk = new_info->baud_base * 16;
++ /* check needs to be done here before other settings made */
++ if (uartclk == 0) {
++ retval = -EINVAL;
++ goto exit;
++ }
++ }
+ if (!capable(CAP_SYS_ADMIN)) {
+ retval = -EPERM;
+ if (change_irq || change_port ||
+diff --git a/drivers/tty/vt/conmakehash.c b/drivers/tty/vt/conmakehash.c
+index dc2177fec7156..82d9db68b2ce8 100644
+--- a/drivers/tty/vt/conmakehash.c
++++ b/drivers/tty/vt/conmakehash.c
+@@ -11,6 +11,8 @@
+ * Copyright (C) 1995-1997 H. Peter Anvin
+ */
+
++#include <libgen.h>
++#include <linux/limits.h>
+ #include <stdio.h>
+ #include <stdlib.h>
+ #include <sysexits.h>
+@@ -76,8 +78,8 @@ static void addpair(int fp, int un)
+ int main(int argc, char *argv[])
+ {
+ FILE *ctbl;
+- const char *tblname, *rel_tblname;
+- const char *abs_srctree;
++ const char *tblname;
++ char base_tblname[PATH_MAX];
+ char buffer[65536];
+ int fontlen;
+ int i, nuni, nent;
+@@ -102,16 +104,6 @@ int main(int argc, char *argv[])
+ }
+ }
+
+- abs_srctree = getenv("abs_srctree");
+- if (abs_srctree && !strncmp(abs_srctree, tblname, strlen(abs_srctree)))
+- {
+- rel_tblname = tblname + strlen(abs_srctree);
+- while (*rel_tblname == '/')
+- ++rel_tblname;
+- }
+- else
+- rel_tblname = tblname;
+-
+ /* For now we assume the default font is always 256 characters. */
+ fontlen = 256;
+
+@@ -253,6 +245,8 @@ int main(int argc, char *argv[])
+ for ( i = 0 ; i < fontlen ; i++ )
+ nuni += unicount[i];
+
++ strncpy(base_tblname, tblname, PATH_MAX);
++ base_tblname[PATH_MAX - 1] = 0;
+ printf("\
+ /*\n\
+ * Do not edit this file; it was automatically generated by\n\
+@@ -264,7 +258,7 @@ int main(int argc, char *argv[])
+ #include <linux/types.h>\n\
+ \n\
+ u8 dfont_unicount[%d] = \n\
+-{\n\t", rel_tblname, fontlen);
++{\n\t", basename(base_tblname), fontlen);
+
+ for ( i = 0 ; i < fontlen ; i++ )
+ {
+diff --git a/drivers/ufs/core/ufshcd-priv.h b/drivers/ufs/core/ufshcd-priv.h
+index f42d99ce5bf1e..81d6f0cfb148b 100644
+--- a/drivers/ufs/core/ufshcd-priv.h
++++ b/drivers/ufs/core/ufshcd-priv.h
+@@ -329,6 +329,11 @@ static inline int ufshcd_rpm_get_sync(struct ufs_hba *hba)
+ return pm_runtime_get_sync(&hba->ufs_device_wlun->sdev_gendev);
+ }
+
++static inline int ufshcd_rpm_get_if_active(struct ufs_hba *hba)
++{
++ return pm_runtime_get_if_active(&hba->ufs_device_wlun->sdev_gendev);
++}
++
+ static inline int ufshcd_rpm_put_sync(struct ufs_hba *hba)
+ {
+ return pm_runtime_put_sync(&hba->ufs_device_wlun->sdev_gendev);
+diff --git a/drivers/ufs/core/ufshcd.c b/drivers/ufs/core/ufshcd.c
+index 46433ecf0c4dc..5864d65448ce5 100644
+--- a/drivers/ufs/core/ufshcd.c
++++ b/drivers/ufs/core/ufshcd.c
+@@ -4086,11 +4086,16 @@ static inline void ufshcd_add_delay_before_dme_cmd(struct ufs_hba *hba)
+ min_sleep_time_us =
+ MIN_DELAY_BEFORE_DME_CMDS_US - delta;
+ else
+- return; /* no more delay required */
++ min_sleep_time_us = 0; /* no more delay required */
+ }
+
+- /* allow sleep for extra 50us if needed */
+- usleep_range(min_sleep_time_us, min_sleep_time_us + 50);
++ if (min_sleep_time_us > 0) {
++ /* allow sleep for extra 50us if needed */
++ usleep_range(min_sleep_time_us, min_sleep_time_us + 50);
++ }
++
++ /* update the last_dme_cmd_tstamp */
++ hba->last_dme_cmd_tstamp = ktime_get();
+ }
+
+ /**
+@@ -8171,7 +8176,10 @@ static void ufshcd_update_rtc(struct ufs_hba *hba)
+ */
+ val = ts64.tv_sec - hba->dev_info.rtc_time_baseline;
+
+- ufshcd_rpm_get_sync(hba);
++ /* Skip update RTC if RPM state is not RPM_ACTIVE */
++ if (ufshcd_rpm_get_if_active(hba) <= 0)
++ return;
++
+ err = ufshcd_query_attr(hba, UPIU_QUERY_OPCODE_WRITE_ATTR, QUERY_ATTR_IDN_SECONDS_PASSED,
+ 0, 0, &val);
+ ufshcd_rpm_put_sync(hba);
+@@ -10220,9 +10228,6 @@ int ufshcd_system_restore(struct device *dev)
+ */
+ ufshcd_readl(hba, REG_UTP_TASK_REQ_LIST_BASE_H);
+
+- /* Resuming from hibernate, assume that link was OFF */
+- ufshcd_set_link_off(hba);
+-
+ return 0;
+
+ }
+diff --git a/drivers/usb/gadget/function/f_fs.c b/drivers/usb/gadget/function/f_fs.c
+index 1f21459b1188c..a7bc715bcafa9 100644
+--- a/drivers/usb/gadget/function/f_fs.c
++++ b/drivers/usb/gadget/function/f_fs.c
+@@ -3731,10 +3731,10 @@ static int ffs_func_set_alt(struct usb_function *f,
+ struct ffs_data *ffs = func->ffs;
+ int ret = 0, intf;
+
+- if (alt > MAX_ALT_SETTINGS)
+- return -EINVAL;
+-
+ if (alt != (unsigned)-1) {
++ if (alt > MAX_ALT_SETTINGS)
++ return -EINVAL;
++
+ intf = ffs_func_revmap_intf(func, interface);
+ if (intf < 0)
+ return intf;
+diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c
+index 0e38bb145e8f5..6908fdd4a83f3 100644
+--- a/drivers/usb/gadget/function/f_midi2.c
++++ b/drivers/usb/gadget/function/f_midi2.c
+@@ -642,12 +642,21 @@ static void process_ump_stream_msg(struct f_midi2_ep *ep, const u32 *data)
+ if (format)
+ return; // invalid
+ blk = (*data >> 8) & 0xff;
+- if (blk >= ep->num_blks)
+- return;
+- if (*data & UMP_STREAM_MSG_REQUEST_FB_INFO)
+- reply_ump_stream_fb_info(ep, blk);
+- if (*data & UMP_STREAM_MSG_REQUEST_FB_NAME)
+- reply_ump_stream_fb_name(ep, blk);
++ if (blk == 0xff) {
++ /* inquiry for all blocks */
++ for (blk = 0; blk < ep->num_blks; blk++) {
++ if (*data & UMP_STREAM_MSG_REQUEST_FB_INFO)
++ reply_ump_stream_fb_info(ep, blk);
++ if (*data & UMP_STREAM_MSG_REQUEST_FB_NAME)
++ reply_ump_stream_fb_name(ep, blk);
++ }
++ } else if (blk < ep->num_blks) {
++ /* only the specified block */
++ if (*data & UMP_STREAM_MSG_REQUEST_FB_INFO)
++ reply_ump_stream_fb_info(ep, blk);
++ if (*data & UMP_STREAM_MSG_REQUEST_FB_NAME)
++ reply_ump_stream_fb_name(ep, blk);
++ }
+ return;
+ }
+ }
+diff --git a/drivers/usb/gadget/function/u_audio.c b/drivers/usb/gadget/function/u_audio.c
+index 89af0feb75120..24299576972fe 100644
+--- a/drivers/usb/gadget/function/u_audio.c
++++ b/drivers/usb/gadget/function/u_audio.c
+@@ -592,16 +592,25 @@ int u_audio_start_capture(struct g_audio *audio_dev)
+ struct usb_ep *ep, *ep_fback;
+ struct uac_rtd_params *prm;
+ struct uac_params *params = &audio_dev->params;
+- int req_len, i;
++ int req_len, i, ret;
+
+ prm = &uac->c_prm;
+ dev_dbg(dev, "start capture with rate %d\n", prm->srate);
+ ep = audio_dev->out_ep;
+- config_ep_by_speed(gadget, &audio_dev->func, ep);
++ ret = config_ep_by_speed(gadget, &audio_dev->func, ep);
++ if (ret < 0) {
++ dev_err(dev, "config_ep_by_speed for out_ep failed (%d)\n", ret);
++ return ret;
++ }
++
+ req_len = ep->maxpacket;
+
+ prm->ep_enabled = true;
+- usb_ep_enable(ep);
++ ret = usb_ep_enable(ep);
++ if (ret < 0) {
++ dev_err(dev, "usb_ep_enable failed for out_ep (%d)\n", ret);
++ return ret;
++ }
+
+ for (i = 0; i < params->req_number; i++) {
+ if (!prm->reqs[i]) {
+@@ -629,9 +638,18 @@ int u_audio_start_capture(struct g_audio *audio_dev)
+ return 0;
+
+ /* Setup feedback endpoint */
+- config_ep_by_speed(gadget, &audio_dev->func, ep_fback);
++ ret = config_ep_by_speed(gadget, &audio_dev->func, ep_fback);
++ if (ret < 0) {
++ dev_err(dev, "config_ep_by_speed in_ep_fback failed (%d)\n", ret);
++ return ret; // TODO: Clean up out_ep
++ }
++
+ prm->fb_ep_enabled = true;
+- usb_ep_enable(ep_fback);
++ ret = usb_ep_enable(ep_fback);
++ if (ret < 0) {
++ dev_err(dev, "usb_ep_enable failed for in_ep_fback (%d)\n", ret);
++ return ret; // TODO: Clean up out_ep
++ }
+ req_len = ep_fback->maxpacket;
+
+ req_fback = usb_ep_alloc_request(ep_fback, GFP_ATOMIC);
+@@ -687,13 +705,17 @@ int u_audio_start_playback(struct g_audio *audio_dev)
+ struct uac_params *params = &audio_dev->params;
+ unsigned int factor;
+ const struct usb_endpoint_descriptor *ep_desc;
+- int req_len, i;
++ int req_len, i, ret;
+ unsigned int p_pktsize;
+
+ prm = &uac->p_prm;
+ dev_dbg(dev, "start playback with rate %d\n", prm->srate);
+ ep = audio_dev->in_ep;
+- config_ep_by_speed(gadget, &audio_dev->func, ep);
++ ret = config_ep_by_speed(gadget, &audio_dev->func, ep);
++ if (ret < 0) {
++ dev_err(dev, "config_ep_by_speed for in_ep failed (%d)\n", ret);
++ return ret;
++ }
+
+ ep_desc = ep->desc;
+ /*
+@@ -720,7 +742,11 @@ int u_audio_start_playback(struct g_audio *audio_dev)
+ uac->p_residue_mil = 0;
+
+ prm->ep_enabled = true;
+- usb_ep_enable(ep);
++ ret = usb_ep_enable(ep);
++ if (ret < 0) {
++ dev_err(dev, "usb_ep_enable failed for in_ep (%d)\n", ret);
++ return ret;
++ }
+
+ for (i = 0; i < params->req_number; i++) {
+ if (!prm->reqs[i]) {
+diff --git a/drivers/usb/gadget/function/u_serial.c b/drivers/usb/gadget/function/u_serial.c
+index a92eb6d909768..8962f96ae7294 100644
+--- a/drivers/usb/gadget/function/u_serial.c
++++ b/drivers/usb/gadget/function/u_serial.c
+@@ -1441,6 +1441,7 @@ void gserial_suspend(struct gserial *gser)
+ spin_lock(&port->port_lock);
+ spin_unlock(&serial_port_lock);
+ port->suspended = true;
++ port->start_delayed = true;
+ spin_unlock_irqrestore(&port->port_lock, flags);
+ }
+ EXPORT_SYMBOL_GPL(gserial_suspend);
+diff --git a/drivers/usb/gadget/udc/core.c b/drivers/usb/gadget/udc/core.c
+index 2dfae7a17b3f1..81f9140f36813 100644
+--- a/drivers/usb/gadget/udc/core.c
++++ b/drivers/usb/gadget/udc/core.c
+@@ -118,12 +118,10 @@ int usb_ep_enable(struct usb_ep *ep)
+ goto out;
+
+ /* UDC drivers can't handle endpoints with maxpacket size 0 */
+- if (usb_endpoint_maxp(ep->desc) == 0) {
+- /*
+- * We should log an error message here, but we can't call
+- * dev_err() because there's no way to find the gadget
+- * given only ep.
+- */
++ if (!ep->desc || usb_endpoint_maxp(ep->desc) == 0) {
++ WARN_ONCE(1, "%s: ep%d (%s) has %s\n", __func__, ep->address, ep->name,
++ (!ep->desc) ? "NULL descriptor" : "maxpacket 0");
++
+ ret = -EINVAL;
+ goto out;
+ }
+diff --git a/drivers/usb/serial/usb_debug.c b/drivers/usb/serial/usb_debug.c
+index 6934970f180d7..5a8869cd95d52 100644
+--- a/drivers/usb/serial/usb_debug.c
++++ b/drivers/usb/serial/usb_debug.c
+@@ -76,6 +76,11 @@ static void usb_debug_process_read_urb(struct urb *urb)
+ usb_serial_generic_process_read_urb(urb);
+ }
+
++static void usb_debug_init_termios(struct tty_struct *tty)
++{
++ tty->termios.c_lflag &= ~(ECHO | ECHONL);
++}
++
+ static struct usb_serial_driver debug_device = {
+ .driver = {
+ .owner = THIS_MODULE,
+@@ -85,6 +90,7 @@ static struct usb_serial_driver debug_device = {
+ .num_ports = 1,
+ .bulk_out_size = USB_DEBUG_MAX_PACKET_SIZE,
+ .break_ctl = usb_debug_break_ctl,
++ .init_termios = usb_debug_init_termios,
+ .process_read_urb = usb_debug_process_read_urb,
+ };
+
+@@ -96,6 +102,7 @@ static struct usb_serial_driver dbc_device = {
+ .id_table = dbc_id_table,
+ .num_ports = 1,
+ .break_ctl = usb_debug_break_ctl,
++ .init_termios = usb_debug_init_termios,
+ .process_read_urb = usb_debug_process_read_urb,
+ };
+
+diff --git a/drivers/usb/typec/mux/fsa4480.c b/drivers/usb/typec/mux/fsa4480.c
+index cb7cdf90cb0aa..cd235339834b0 100644
+--- a/drivers/usb/typec/mux/fsa4480.c
++++ b/drivers/usb/typec/mux/fsa4480.c
+@@ -13,6 +13,10 @@
+ #include <linux/usb/typec_dp.h>
+ #include <linux/usb/typec_mux.h>
+
++#define FSA4480_DEVICE_ID 0x00
++ #define FSA4480_DEVICE_ID_VENDOR_ID GENMASK(7, 6)
++ #define FSA4480_DEVICE_ID_VERSION_ID GENMASK(5, 3)
++ #define FSA4480_DEVICE_ID_REV_ID GENMASK(2, 0)
+ #define FSA4480_SWITCH_ENABLE 0x04
+ #define FSA4480_SWITCH_SELECT 0x05
+ #define FSA4480_SWITCH_STATUS1 0x07
+@@ -251,6 +255,7 @@ static int fsa4480_probe(struct i2c_client *client)
+ struct typec_switch_desc sw_desc = { };
+ struct typec_mux_desc mux_desc = { };
+ struct fsa4480 *fsa;
++ int val = 0;
+ int ret;
+
+ fsa = devm_kzalloc(dev, sizeof(*fsa), GFP_KERNEL);
+@@ -268,6 +273,15 @@ static int fsa4480_probe(struct i2c_client *client)
+ if (IS_ERR(fsa->regmap))
+ return dev_err_probe(dev, PTR_ERR(fsa->regmap), "failed to initialize regmap\n");
+
++ ret = regmap_read(fsa->regmap, FSA4480_DEVICE_ID, &val);
++ if (ret || !val)
++ return dev_err_probe(dev, -ENODEV, "FSA4480 not found\n");
++
++ dev_dbg(dev, "Found FSA4480 v%lu.%lu (Vendor ID = %lu)\n",
++ FIELD_GET(FSA4480_DEVICE_ID_VERSION_ID, val),
++ FIELD_GET(FSA4480_DEVICE_ID_REV_ID, val),
++ FIELD_GET(FSA4480_DEVICE_ID_VENDOR_ID, val));
++
+ /* Safe mode */
+ fsa->cur_enable = FSA4480_ENABLE_DEVICE | FSA4480_ENABLE_USB;
+ fsa->mode = TYPEC_STATE_SAFE;
+diff --git a/drivers/usb/usbip/vhci_hcd.c b/drivers/usb/usbip/vhci_hcd.c
+index 82650c11e4516..302a89aeb258a 100644
+--- a/drivers/usb/usbip/vhci_hcd.c
++++ b/drivers/usb/usbip/vhci_hcd.c
+@@ -745,6 +745,7 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
+ *
+ */
+ if (usb_pipedevice(urb->pipe) == 0) {
++ struct usb_device *old;
+ __u8 type = usb_pipetype(urb->pipe);
+ struct usb_ctrlrequest *ctrlreq =
+ (struct usb_ctrlrequest *) urb->setup_packet;
+@@ -755,14 +756,15 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
+ goto no_need_xmit;
+ }
+
++ old = vdev->udev;
+ switch (ctrlreq->bRequest) {
+ case USB_REQ_SET_ADDRESS:
+ /* set_address may come when a device is reset */
+ dev_info(dev, "SetAddress Request (%d) to port %d\n",
+ ctrlreq->wValue, vdev->rhport);
+
+- usb_put_dev(vdev->udev);
+ vdev->udev = usb_get_dev(urb->dev);
++ usb_put_dev(old);
+
+ spin_lock(&vdev->ud.lock);
+ vdev->ud.status = VDEV_ST_USED;
+@@ -781,8 +783,8 @@ static int vhci_urb_enqueue(struct usb_hcd *hcd, struct urb *urb, gfp_t mem_flag
+ usbip_dbg_vhci_hc(
+ "Not yet?:Get_Descriptor to device 0 (get max pipe size)\n");
+
+- usb_put_dev(vdev->udev);
+ vdev->udev = usb_get_dev(urb->dev);
++ usb_put_dev(old);
+ goto out;
+
+ default:
+@@ -1067,6 +1069,7 @@ static void vhci_shutdown_connection(struct usbip_device *ud)
+ static void vhci_device_reset(struct usbip_device *ud)
+ {
+ struct vhci_device *vdev = container_of(ud, struct vhci_device, ud);
++ struct usb_device *old = vdev->udev;
+ unsigned long flags;
+
+ spin_lock_irqsave(&ud->lock, flags);
+@@ -1074,8 +1077,8 @@ static void vhci_device_reset(struct usbip_device *ud)
+ vdev->speed = 0;
+ vdev->devid = 0;
+
+- usb_put_dev(vdev->udev);
+ vdev->udev = NULL;
++ usb_put_dev(old);
+
+ if (ud->tcp_socket) {
+ sockfd_put(ud->tcp_socket);
+diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
+index 63a53680a85cb..6b9c12acf4381 100644
+--- a/drivers/vhost/vdpa.c
++++ b/drivers/vhost/vdpa.c
+@@ -1483,13 +1483,7 @@ static vm_fault_t vhost_vdpa_fault(struct vm_fault *vmf)
+
+ notify = ops->get_vq_notification(vdpa, index);
+
+- vma->vm_page_prot = pgprot_noncached(vma->vm_page_prot);
+- if (remap_pfn_range(vma, vmf->address & PAGE_MASK,
+- PFN_DOWN(notify.addr), PAGE_SIZE,
+- vma->vm_page_prot))
+- return VM_FAULT_SIGBUS;
+-
+- return VM_FAULT_NOPAGE;
++ return vmf_insert_pfn(vma, vmf->address & PAGE_MASK, PFN_DOWN(notify.addr));
+ }
+
+ static const struct vm_operations_struct vhost_vdpa_vm_ops = {
+diff --git a/drivers/xen/privcmd.c b/drivers/xen/privcmd.c
+index 67dfa47788649..c9c620e32fa8b 100644
+--- a/drivers/xen/privcmd.c
++++ b/drivers/xen/privcmd.c
+@@ -845,7 +845,7 @@ static long privcmd_ioctl_mmap_resource(struct file *file,
+ #ifdef CONFIG_XEN_PRIVCMD_EVENTFD
+ /* Irqfd support */
+ static struct workqueue_struct *irqfd_cleanup_wq;
+-static DEFINE_MUTEX(irqfds_lock);
++static DEFINE_SPINLOCK(irqfds_lock);
+ static LIST_HEAD(irqfds_list);
+
+ struct privcmd_kernel_irqfd {
+@@ -909,9 +909,11 @@ irqfd_wakeup(wait_queue_entry_t *wait, unsigned int mode, int sync, void *key)
+ irqfd_inject(kirqfd);
+
+ if (flags & EPOLLHUP) {
+- mutex_lock(&irqfds_lock);
++ unsigned long flags;
++
++ spin_lock_irqsave(&irqfds_lock, flags);
+ irqfd_deactivate(kirqfd);
+- mutex_unlock(&irqfds_lock);
++ spin_unlock_irqrestore(&irqfds_lock, flags);
+ }
+
+ return 0;
+@@ -929,6 +931,7 @@ irqfd_poll_func(struct file *file, wait_queue_head_t *wqh, poll_table *pt)
+ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd)
+ {
+ struct privcmd_kernel_irqfd *kirqfd, *tmp;
++ unsigned long flags;
+ __poll_t events;
+ struct fd f;
+ void *dm_op;
+@@ -968,18 +971,18 @@ static int privcmd_irqfd_assign(struct privcmd_irqfd *irqfd)
+ init_waitqueue_func_entry(&kirqfd->wait, irqfd_wakeup);
+ init_poll_funcptr(&kirqfd->pt, irqfd_poll_func);
+
+- mutex_lock(&irqfds_lock);
++ spin_lock_irqsave(&irqfds_lock, flags);
+
+ list_for_each_entry(tmp, &irqfds_list, list) {
+ if (kirqfd->eventfd == tmp->eventfd) {
+ ret = -EBUSY;
+- mutex_unlock(&irqfds_lock);
++ spin_unlock_irqrestore(&irqfds_lock, flags);
+ goto error_eventfd;
+ }
+ }
+
+ list_add_tail(&kirqfd->list, &irqfds_list);
+- mutex_unlock(&irqfds_lock);
++ spin_unlock_irqrestore(&irqfds_lock, flags);
+
+ /*
+ * Check if there was an event already pending on the eventfd before we
+@@ -1011,12 +1014,13 @@ static int privcmd_irqfd_deassign(struct privcmd_irqfd *irqfd)
+ {
+ struct privcmd_kernel_irqfd *kirqfd;
+ struct eventfd_ctx *eventfd;
++ unsigned long flags;
+
+ eventfd = eventfd_ctx_fdget(irqfd->fd);
+ if (IS_ERR(eventfd))
+ return PTR_ERR(eventfd);
+
+- mutex_lock(&irqfds_lock);
++ spin_lock_irqsave(&irqfds_lock, flags);
+
+ list_for_each_entry(kirqfd, &irqfds_list, list) {
+ if (kirqfd->eventfd == eventfd) {
+@@ -1025,7 +1029,7 @@ static int privcmd_irqfd_deassign(struct privcmd_irqfd *irqfd)
+ }
+ }
+
+- mutex_unlock(&irqfds_lock);
++ spin_unlock_irqrestore(&irqfds_lock, flags);
+
+ eventfd_ctx_put(eventfd);
+
+@@ -1073,13 +1077,14 @@ static int privcmd_irqfd_init(void)
+ static void privcmd_irqfd_exit(void)
+ {
+ struct privcmd_kernel_irqfd *kirqfd, *tmp;
++ unsigned long flags;
+
+- mutex_lock(&irqfds_lock);
++ spin_lock_irqsave(&irqfds_lock, flags);
+
+ list_for_each_entry_safe(kirqfd, tmp, &irqfds_list, list)
+ irqfd_deactivate(kirqfd);
+
+- mutex_unlock(&irqfds_lock);
++ spin_unlock_irqrestore(&irqfds_lock, flags);
+
+ destroy_workqueue(irqfd_cleanup_wq);
+ }
+diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
+index 1a49b92329908..8a791b648ac53 100644
+--- a/fs/btrfs/ctree.c
++++ b/fs/btrfs/ctree.c
+@@ -321,7 +321,7 @@ int btrfs_copy_root(struct btrfs_trans_handle *trans,
+ WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
+ trans->transid != fs_info->running_transaction->transid);
+ WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
+- trans->transid != root->last_trans);
++ trans->transid != btrfs_get_root_last_trans(root));
+
+ level = btrfs_header_level(buf);
+ if (level == 0)
+@@ -551,7 +551,7 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
+ WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
+ trans->transid != fs_info->running_transaction->transid);
+ WARN_ON(test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
+- trans->transid != root->last_trans);
++ trans->transid != btrfs_get_root_last_trans(root));
+
+ level = btrfs_header_level(buf);
+
+@@ -620,10 +620,16 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
+ atomic_inc(&cow->refs);
+ rcu_assign_pointer(root->node, cow);
+
+- btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+- parent_start, last_ref);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
++ parent_start, last_ref);
+ free_extent_buffer(buf);
+ add_root_to_dirty_list(root);
++ if (ret < 0) {
++ btrfs_tree_unlock(cow);
++ free_extent_buffer(cow);
++ btrfs_abort_transaction(trans, ret);
++ return ret;
++ }
+ } else {
+ WARN_ON(trans->transid != btrfs_header_generation(parent));
+ ret = btrfs_tree_mod_log_insert_key(parent, parent_slot,
+@@ -648,8 +654,14 @@ int btrfs_force_cow_block(struct btrfs_trans_handle *trans,
+ return ret;
+ }
+ }
+- btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
+- parent_start, last_ref);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(root), buf,
++ parent_start, last_ref);
++ if (ret < 0) {
++ btrfs_tree_unlock(cow);
++ free_extent_buffer(cow);
++ btrfs_abort_transaction(trans, ret);
++ return ret;
++ }
+ }
+ if (unlock_orig)
+ btrfs_tree_unlock(buf);
+@@ -983,9 +995,13 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
+ free_extent_buffer(mid);
+
+ root_sub_used_bytes(root);
+- btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
+ /* once for the root ptr */
+ free_extent_buffer_stale(mid);
++ if (ret < 0) {
++ btrfs_abort_transaction(trans, ret);
++ goto out;
++ }
+ return 0;
+ }
+ if (btrfs_header_nritems(mid) >
+@@ -1053,10 +1069,14 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
+ goto out;
+ }
+ root_sub_used_bytes(root);
+- btrfs_free_tree_block(trans, btrfs_root_id(root), right,
+- 0, 1);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(root),
++ right, 0, 1);
+ free_extent_buffer_stale(right);
+ right = NULL;
++ if (ret < 0) {
++ btrfs_abort_transaction(trans, ret);
++ goto out;
++ }
+ } else {
+ struct btrfs_disk_key right_key;
+ btrfs_node_key(right, &right_key, 0);
+@@ -1111,9 +1131,13 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
+ goto out;
+ }
+ root_sub_used_bytes(root);
+- btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(root), mid, 0, 1);
+ free_extent_buffer_stale(mid);
+ mid = NULL;
++ if (ret < 0) {
++ btrfs_abort_transaction(trans, ret);
++ goto out;
++ }
+ } else {
+ /* update the parent key to reflect our changes */
+ struct btrfs_disk_key mid_key;
+@@ -2883,7 +2907,11 @@ static noinline int insert_new_root(struct btrfs_trans_handle *trans,
+ old = root->node;
+ ret = btrfs_tree_mod_log_insert_root(root->node, c, false);
+ if (ret < 0) {
+- btrfs_free_tree_block(trans, btrfs_root_id(root), c, 0, 1);
++ int ret2;
++
++ ret2 = btrfs_free_tree_block(trans, btrfs_root_id(root), c, 0, 1);
++ if (ret2 < 0)
++ btrfs_abort_transaction(trans, ret2);
+ btrfs_tree_unlock(c);
+ free_extent_buffer(c);
+ return ret;
+@@ -4452,9 +4480,12 @@ static noinline int btrfs_del_leaf(struct btrfs_trans_handle *trans,
+ root_sub_used_bytes(root);
+
+ atomic_inc(&leaf->refs);
+- btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(root), leaf, 0, 1);
+ free_extent_buffer_stale(leaf);
+- return 0;
++ if (ret < 0)
++ btrfs_abort_transaction(trans, ret);
++
++ return ret;
+ }
+ /*
+ * delete the item at the leaf level in path. If that empties
+diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
+index c03c58246033b..a56209d275c15 100644
+--- a/fs/btrfs/ctree.h
++++ b/fs/btrfs/ctree.h
+@@ -354,6 +354,16 @@ static inline void btrfs_set_root_last_log_commit(struct btrfs_root *root, int c
+ WRITE_ONCE(root->last_log_commit, commit_id);
+ }
+
++static inline u64 btrfs_get_root_last_trans(const struct btrfs_root *root)
++{
++ return READ_ONCE(root->last_trans);
++}
++
++static inline void btrfs_set_root_last_trans(struct btrfs_root *root, u64 transid)
++{
++ WRITE_ONCE(root->last_trans, transid);
++}
++
+ /*
+ * Structure that conveys information about an extent that is going to replace
+ * all the extents in a file range.
+@@ -447,6 +457,7 @@ struct btrfs_file_private {
+ void *filldir_buf;
+ u64 last_index;
+ struct extent_state *llseek_cached_state;
++ bool fsync_skip_inode_lock;
+ };
+
+ static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
+diff --git a/fs/btrfs/defrag.c b/fs/btrfs/defrag.c
+index 407ccec3e57ed..f664678c71d15 100644
+--- a/fs/btrfs/defrag.c
++++ b/fs/btrfs/defrag.c
+@@ -139,7 +139,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
+ if (trans)
+ transid = trans->transid;
+ else
+- transid = inode->root->last_trans;
++ transid = btrfs_get_root_last_trans(root);
+
+ defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS);
+ if (!defrag)
+diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
+index cabb558dbdaa8..3791813dc7b62 100644
+--- a/fs/btrfs/disk-io.c
++++ b/fs/btrfs/disk-io.c
+@@ -658,7 +658,7 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
+ root->state = 0;
+ RB_CLEAR_NODE(&root->rb_node);
+
+- root->last_trans = 0;
++ btrfs_set_root_last_trans(root, 0);
+ root->free_objectid = 0;
+ root->nr_delalloc_inodes = 0;
+ root->nr_ordered_extents = 0;
+@@ -1010,7 +1010,7 @@ int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
+ return ret;
+ }
+
+- log_root->last_trans = trans->transid;
++ btrfs_set_root_last_trans(log_root, trans->transid);
+ log_root->root_key.offset = btrfs_root_id(root);
+
+ inode_item = &log_root->root_item.inode;
+diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
+index b75e14f399a01..844b677d054ec 100644
+--- a/fs/btrfs/extent-tree.c
++++ b/fs/btrfs/extent-tree.c
+@@ -104,10 +104,7 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+ struct btrfs_delayed_ref_head *head;
+ struct btrfs_delayed_ref_root *delayed_refs;
+ struct btrfs_path *path;
+- struct btrfs_extent_item *ei;
+- struct extent_buffer *leaf;
+ struct btrfs_key key;
+- u32 item_size;
+ u64 num_refs;
+ u64 extent_flags;
+ u64 owner = 0;
+@@ -157,16 +154,11 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+ }
+
+ if (ret == 0) {
+- leaf = path->nodes[0];
+- item_size = btrfs_item_size(leaf, path->slots[0]);
+- if (item_size >= sizeof(*ei)) {
+- ei = btrfs_item_ptr(leaf, path->slots[0],
+- struct btrfs_extent_item);
+- num_refs = btrfs_extent_refs(leaf, ei);
+- extent_flags = btrfs_extent_flags(leaf, ei);
+- owner = btrfs_get_extent_owner_root(fs_info, leaf,
+- path->slots[0]);
+- } else {
++ struct extent_buffer *leaf = path->nodes[0];
++ struct btrfs_extent_item *ei;
++ const u32 item_size = btrfs_item_size(leaf, path->slots[0]);
++
++ if (unlikely(item_size < sizeof(*ei))) {
+ ret = -EUCLEAN;
+ btrfs_err(fs_info,
+ "unexpected extent item size, has %u expect >= %zu",
+@@ -179,6 +171,10 @@ int btrfs_lookup_extent_info(struct btrfs_trans_handle *trans,
+ goto out_free;
+ }
+
++ ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
++ num_refs = btrfs_extent_refs(leaf, ei);
++ extent_flags = btrfs_extent_flags(leaf, ei);
++ owner = btrfs_get_extent_owner_root(fs_info, leaf, path->slots[0]);
+ BUG_ON(num_refs == 0);
+ } else {
+ num_refs = 0;
+@@ -3420,10 +3416,10 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
+ return 0;
+ }
+
+-void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
+- u64 root_id,
+- struct extent_buffer *buf,
+- u64 parent, int last_ref)
++int btrfs_free_tree_block(struct btrfs_trans_handle *trans,
++ u64 root_id,
++ struct extent_buffer *buf,
++ u64 parent, int last_ref)
+ {
+ struct btrfs_fs_info *fs_info = trans->fs_info;
+ struct btrfs_block_group *bg;
+@@ -3450,11 +3446,12 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
+ btrfs_init_tree_ref(&generic_ref, btrfs_header_level(buf), 0, false);
+ btrfs_ref_tree_mod(fs_info, &generic_ref);
+ ret = btrfs_add_delayed_tree_ref(trans, &generic_ref, NULL);
+- BUG_ON(ret); /* -ENOMEM */
++ if (ret < 0)
++ return ret;
+ }
+
+ if (!last_ref)
+- return;
++ return 0;
+
+ if (btrfs_header_generation(buf) != trans->transid)
+ goto out;
+@@ -3511,6 +3508,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
+ * matter anymore.
+ */
+ clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
++ return 0;
+ }
+
+ /* Can return -ENOMEM */
+@@ -5644,7 +5642,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
+ struct walk_control *wc)
+ {
+ struct btrfs_fs_info *fs_info = root->fs_info;
+- int ret;
++ int ret = 0;
+ int level = wc->level;
+ struct extent_buffer *eb = path->nodes[level];
+ u64 parent = 0;
+@@ -5731,12 +5729,14 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
+ goto owner_mismatch;
+ }
+
+- btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent,
+- wc->refs[level] == 1);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(root), eb, parent,
++ wc->refs[level] == 1);
++ if (ret < 0)
++ btrfs_abort_transaction(trans, ret);
+ out:
+ wc->refs[level] = 0;
+ wc->flags[level] = 0;
+- return 0;
++ return ret;
+
+ owner_mismatch:
+ btrfs_err_rl(fs_info, "unexpected tree owner, have %llu expect %llu",
+diff --git a/fs/btrfs/extent-tree.h b/fs/btrfs/extent-tree.h
+index af9f8800d5aca..2ad51130c037e 100644
+--- a/fs/btrfs/extent-tree.h
++++ b/fs/btrfs/extent-tree.h
+@@ -127,10 +127,10 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
+ u64 empty_size,
+ u64 reloc_src_root,
+ enum btrfs_lock_nesting nest);
+-void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
+- u64 root_id,
+- struct extent_buffer *buf,
+- u64 parent, int last_ref);
++int btrfs_free_tree_block(struct btrfs_trans_handle *trans,
++ u64 root_id,
++ struct extent_buffer *buf,
++ u64 parent, int last_ref);
+ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root, u64 owner,
+ u64 offset, u64 ram_bytes,
+diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
+index 958155cc43a81..0486b1f911248 100644
+--- a/fs/btrfs/extent_io.c
++++ b/fs/btrfs/extent_io.c
+@@ -2246,10 +2246,8 @@ void extent_write_locked_range(struct inode *inode, struct page *locked_page,
+
+ page = find_get_page(mapping, cur >> PAGE_SHIFT);
+ ASSERT(PageLocked(page));
+- if (pages_dirty && page != locked_page) {
++ if (pages_dirty && page != locked_page)
+ ASSERT(PageDirty(page));
+- clear_page_dirty_for_io(page);
+- }
+
+ ret = __extent_writepage_io(BTRFS_I(inode), page, &bio_ctrl,
+ i_size, &nr);
+diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
+index d90138683a0a3..ca434f0cd27f0 100644
+--- a/fs/btrfs/file.c
++++ b/fs/btrfs/file.c
+@@ -1550,21 +1550,37 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
+ * So here we disable page faults in the iov_iter and then retry if we
+ * got -EFAULT, faulting in the pages before the retry.
+ */
++again:
+ from->nofault = true;
+ dio = btrfs_dio_write(iocb, from, written);
+ from->nofault = false;
+
+- /*
+- * iomap_dio_complete() will call btrfs_sync_file() if we have a dsync
+- * iocb, and that needs to lock the inode. So unlock it before calling
+- * iomap_dio_complete() to avoid a deadlock.
+- */
+- btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
+-
+- if (IS_ERR_OR_NULL(dio))
++ if (IS_ERR_OR_NULL(dio)) {
+ ret = PTR_ERR_OR_ZERO(dio);
+- else
++ } else {
++ struct btrfs_file_private stack_private = { 0 };
++ struct btrfs_file_private *private;
++ const bool have_private = (file->private_data != NULL);
++
++ if (!have_private)
++ file->private_data = &stack_private;
++
++ /*
++ * If we have a synchoronous write, we must make sure the fsync
++ * triggered by the iomap_dio_complete() call below doesn't
++ * deadlock on the inode lock - we are already holding it and we
++ * can't call it after unlocking because we may need to complete
++ * partial writes due to the input buffer (or parts of it) not
++ * being already faulted in.
++ */
++ private = file->private_data;
++ private->fsync_skip_inode_lock = true;
+ ret = iomap_dio_complete(dio);
++ private->fsync_skip_inode_lock = false;
++
++ if (!have_private)
++ file->private_data = NULL;
++ }
+
+ /* No increment (+=) because iomap returns a cumulative value. */
+ if (ret > 0)
+@@ -1591,10 +1607,12 @@ static ssize_t btrfs_direct_write(struct kiocb *iocb, struct iov_iter *from)
+ } else {
+ fault_in_iov_iter_readable(from, left);
+ prev_left = left;
+- goto relock;
++ goto again;
+ }
+ }
+
++ btrfs_inode_unlock(BTRFS_I(inode), ilock_flags);
++
+ /*
+ * If 'ret' is -ENOTBLK or we have not written all data, then it means
+ * we must fallback to buffered IO.
+@@ -1793,6 +1811,7 @@ static inline bool skip_inode_logging(const struct btrfs_log_ctx *ctx)
+ */
+ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+ {
++ struct btrfs_file_private *private = file->private_data;
+ struct dentry *dentry = file_dentry(file);
+ struct inode *inode = d_inode(dentry);
+ struct btrfs_fs_info *fs_info = inode_to_fs_info(inode);
+@@ -1802,6 +1821,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+ int ret = 0, err;
+ u64 len;
+ bool full_sync;
++ const bool skip_ilock = (private ? private->fsync_skip_inode_lock : false);
+
+ trace_btrfs_sync_file(file, datasync);
+
+@@ -1829,7 +1849,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+ if (ret)
+ goto out;
+
+- btrfs_inode_lock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
++ if (skip_ilock)
++ down_write(&BTRFS_I(inode)->i_mmap_lock);
++ else
++ btrfs_inode_lock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
+
+ atomic_inc(&root->log_batch);
+
+@@ -1853,7 +1876,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+ */
+ ret = start_ordered_ops(inode, start, end);
+ if (ret) {
+- btrfs_inode_unlock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
++ if (skip_ilock)
++ up_write(&BTRFS_I(inode)->i_mmap_lock);
++ else
++ btrfs_inode_unlock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
+ goto out;
+ }
+
+@@ -1982,7 +2008,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+ * file again, but that will end up using the synchronization
+ * inside btrfs_sync_log to keep things safe.
+ */
+- btrfs_inode_unlock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
++ if (skip_ilock)
++ up_write(&BTRFS_I(inode)->i_mmap_lock);
++ else
++ btrfs_inode_unlock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
+
+ if (ret == BTRFS_NO_LOG_SYNC) {
+ ret = btrfs_end_transaction(trans);
+@@ -2051,7 +2080,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
+
+ out_release_extents:
+ btrfs_release_log_ctx_extents(&ctx);
+- btrfs_inode_unlock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
++ if (skip_ilock)
++ up_write(&BTRFS_I(inode)->i_mmap_lock);
++ else
++ btrfs_inode_unlock(BTRFS_I(inode), BTRFS_ILOCK_MMAP);
+ goto out;
+ }
+
+diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
+index d674f2106593a..62c3dea9572ab 100644
+--- a/fs/btrfs/free-space-cache.c
++++ b/fs/btrfs/free-space-cache.c
+@@ -858,6 +858,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
+ spin_unlock(&ctl->tree_lock);
+ btrfs_err(fs_info,
+ "Duplicate entries in free space cache, dumping");
++ kmem_cache_free(btrfs_free_space_bitmap_cachep, e->bitmap);
+ kmem_cache_free(btrfs_free_space_cachep, e);
+ goto free_cache;
+ }
+diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
+index 90f2938bd743d..7ba50e133921a 100644
+--- a/fs/btrfs/free-space-tree.c
++++ b/fs/btrfs/free-space-tree.c
+@@ -1300,10 +1300,14 @@ int btrfs_delete_free_space_tree(struct btrfs_fs_info *fs_info)
+ btrfs_tree_lock(free_space_root->node);
+ btrfs_clear_buffer_dirty(trans, free_space_root->node);
+ btrfs_tree_unlock(free_space_root->node);
+- btrfs_free_tree_block(trans, btrfs_root_id(free_space_root),
+- free_space_root->node, 0, 1);
+-
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(free_space_root),
++ free_space_root->node, 0, 1);
+ btrfs_put_root(free_space_root);
++ if (ret < 0) {
++ btrfs_abort_transaction(trans, ret);
++ btrfs_end_transaction(trans);
++ return ret;
++ }
+
+ return btrfs_commit_transaction(trans);
+ }
+diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
+index efd5d6e9589e0..c1b0556e40368 100644
+--- a/fs/btrfs/ioctl.c
++++ b/fs/btrfs/ioctl.c
+@@ -719,6 +719,8 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
+ ret = btrfs_insert_root(trans, fs_info->tree_root, &key,
+ root_item);
+ if (ret) {
++ int ret2;
++
+ /*
+ * Since we don't abort the transaction in this case, free the
+ * tree block so that we don't leak space and leave the
+@@ -729,7 +731,9 @@ static noinline int create_subvol(struct mnt_idmap *idmap,
+ btrfs_tree_lock(leaf);
+ btrfs_clear_buffer_dirty(trans, leaf);
+ btrfs_tree_unlock(leaf);
+- btrfs_free_tree_block(trans, objectid, leaf, 0, 1);
++ ret2 = btrfs_free_tree_block(trans, objectid, leaf, 0, 1);
++ if (ret2 < 0)
++ btrfs_abort_transaction(trans, ret2);
+ free_extent_buffer(leaf);
+ goto out;
+ }
+diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
+index 7e46aa8a04446..b876156fcd035 100644
+--- a/fs/btrfs/print-tree.c
++++ b/fs/btrfs/print-tree.c
+@@ -14,7 +14,7 @@
+
+ struct root_name_map {
+ u64 id;
+- char name[16];
++ const char *name;
+ };
+
+ static const struct root_name_map root_map[] = {
+diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
+index 39a15cca58ca9..29d6ca3b874ec 100644
+--- a/fs/btrfs/qgroup.c
++++ b/fs/btrfs/qgroup.c
+@@ -1446,9 +1446,11 @@ int btrfs_quota_disable(struct btrfs_fs_info *fs_info)
+ btrfs_tree_lock(quota_root->node);
+ btrfs_clear_buffer_dirty(trans, quota_root->node);
+ btrfs_tree_unlock(quota_root->node);
+- btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
+- quota_root->node, 0, 1);
++ ret = btrfs_free_tree_block(trans, btrfs_root_id(quota_root),
++ quota_root->node, 0, 1);
+
++ if (ret < 0)
++ btrfs_abort_transaction(trans, ret);
+
+ out:
+ btrfs_put_root(quota_root);
+diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
+index 8b24bb5a0aa18..f2935252b981a 100644
+--- a/fs/btrfs/relocation.c
++++ b/fs/btrfs/relocation.c
+@@ -817,7 +817,7 @@ static struct btrfs_root *create_reloc_root(struct btrfs_trans_handle *trans,
+ goto abort;
+ }
+ set_bit(BTRFS_ROOT_SHAREABLE, &reloc_root->state);
+- reloc_root->last_trans = trans->transid;
++ btrfs_set_root_last_trans(reloc_root, trans->transid);
+ return reloc_root;
+ fail:
+ kfree(root_item);
+@@ -864,7 +864,7 @@ int btrfs_init_reloc_root(struct btrfs_trans_handle *trans,
+ */
+ if (root->reloc_root) {
+ reloc_root = root->reloc_root;
+- reloc_root->last_trans = trans->transid;
++ btrfs_set_root_last_trans(reloc_root, trans->transid);
+ return 0;
+ }
+
+@@ -1739,7 +1739,7 @@ static noinline_for_stack int merge_reloc_root(struct reloc_control *rc,
+ * btrfs_update_reloc_root() and update our root item
+ * appropriately.
+ */
+- reloc_root->last_trans = trans->transid;
++ btrfs_set_root_last_trans(reloc_root, trans->transid);
+ trans->block_rsv = rc->block_rsv;
+
+ replaced = 0;
+@@ -2082,7 +2082,7 @@ static int record_reloc_root_in_trans(struct btrfs_trans_handle *trans,
+ struct btrfs_root *root;
+ int ret;
+
+- if (reloc_root->last_trans == trans->transid)
++ if (btrfs_get_root_last_trans(reloc_root) == trans->transid)
+ return 0;
+
+ root = btrfs_get_fs_root(fs_info, reloc_root->root_key.offset, false);
+diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
+index 3388c836b9a56..76117bb2c726c 100644
+--- a/fs/btrfs/transaction.c
++++ b/fs/btrfs/transaction.c
+@@ -405,7 +405,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
+ int ret = 0;
+
+ if ((test_bit(BTRFS_ROOT_SHAREABLE, &root->state) &&
+- root->last_trans < trans->transid) || force) {
++ btrfs_get_root_last_trans(root) < trans->transid) || force) {
+ WARN_ON(!force && root->commit_root != root->node);
+
+ /*
+@@ -421,7 +421,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
+ smp_wmb();
+
+ spin_lock(&fs_info->fs_roots_radix_lock);
+- if (root->last_trans == trans->transid && !force) {
++ if (btrfs_get_root_last_trans(root) == trans->transid && !force) {
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+ return 0;
+ }
+@@ -429,7 +429,7 @@ static int record_root_in_trans(struct btrfs_trans_handle *trans,
+ (unsigned long)btrfs_root_id(root),
+ BTRFS_ROOT_TRANS_TAG);
+ spin_unlock(&fs_info->fs_roots_radix_lock);
+- root->last_trans = trans->transid;
++ btrfs_set_root_last_trans(root, trans->transid);
+
+ /* this is pretty tricky. We don't want to
+ * take the relocation lock in btrfs_record_root_in_trans
+@@ -491,7 +491,7 @@ int btrfs_record_root_in_trans(struct btrfs_trans_handle *trans,
+ * and barriers
+ */
+ smp_rmb();
+- if (root->last_trans == trans->transid &&
++ if (btrfs_get_root_last_trans(root) == trans->transid &&
+ !test_bit(BTRFS_ROOT_IN_TRANS_SETUP, &root->state))
+ return 0;
+
+diff --git a/fs/buffer.c b/fs/buffer.c
+index 8c19e705b9c33..645f0387dfe1d 100644
+--- a/fs/buffer.c
++++ b/fs/buffer.c
+@@ -2187,6 +2187,8 @@ static void __block_commit_write(struct folio *folio, size_t from, size_t to)
+ struct buffer_head *bh, *head;
+
+ bh = head = folio_buffers(folio);
++ if (!bh)
++ return;
+ blocksize = bh->b_size;
+
+ block_start = 0;
+diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
+index d5bd1e3a5d36c..e7a09a99837b9 100644
+--- a/fs/ext4/inline.c
++++ b/fs/ext4/inline.c
+@@ -1410,7 +1410,11 @@ int ext4_inlinedir_to_tree(struct file *dir_file,
+ hinfo->hash = EXT4_DIRENT_HASH(de);
+ hinfo->minor_hash = EXT4_DIRENT_MINOR_HASH(de);
+ } else {
+- ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
++ err = ext4fs_dirhash(dir, de->name, de->name_len, hinfo);
++ if (err) {
++ ret = err;
++ goto out;
++ }
+ }
+ if ((hinfo->hash < start_hash) ||
+ ((hinfo->hash == start_hash) &&
+diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
+index 4b0d64a76e88e..238e196338234 100644
+--- a/fs/ext4/inode.c
++++ b/fs/ext4/inode.c
+@@ -2973,6 +2973,11 @@ static int ext4_da_do_write_end(struct address_space *mapping,
+ bool disksize_changed = false;
+ loff_t new_i_size;
+
++ if (unlikely(!folio_buffers(folio))) {
++ folio_unlock(folio);
++ folio_put(folio);
++ return -EIO;
++ }
+ /*
+ * block_write_end() will mark the inode as dirty with I_DIRTY_PAGES
+ * flag, which all that's needed to trigger page writeback.
+diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
+index ae5b544ed0cc0..c8d9d85e0e871 100644
+--- a/fs/jbd2/journal.c
++++ b/fs/jbd2/journal.c
+@@ -399,6 +399,7 @@ int jbd2_journal_write_metadata_buffer(transaction_t *transaction,
+ tmp = jbd2_alloc(bh_in->b_size, GFP_NOFS);
+ if (!tmp) {
+ brelse(new_bh);
++ free_buffer_head(new_bh);
+ return -ENOMEM;
+ }
+ spin_lock(&jh_in->b_state_lock);
+diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
+index c848ebe5d08f1..0f9b4f7b56cd8 100644
+--- a/fs/nfsd/nfsctl.c
++++ b/fs/nfsd/nfsctl.c
+@@ -2053,8 +2053,7 @@ int nfsd_nl_listener_set_doit(struct sk_buff *skb, struct genl_info *info)
+ continue;
+ }
+
+- ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa,
+- SVC_SOCK_ANONYMOUS,
++ ret = svc_xprt_create_from_sa(serv, xcl_name, net, sa, 0,
+ get_current_cred());
+ /* always save the latest error */
+ if (ret < 0)
+diff --git a/fs/smb/client/cifs_debug.c b/fs/smb/client/cifs_debug.c
+index c71ae5c043060..4a20e92474b23 100644
+--- a/fs/smb/client/cifs_debug.c
++++ b/fs/smb/client/cifs_debug.c
+@@ -1072,7 +1072,7 @@ static int cifs_security_flags_proc_open(struct inode *inode, struct file *file)
+ static void
+ cifs_security_flags_handle_must_flags(unsigned int *flags)
+ {
+- unsigned int signflags = *flags & CIFSSEC_MUST_SIGN;
++ unsigned int signflags = *flags & (CIFSSEC_MUST_SIGN | CIFSSEC_MUST_SEAL);
+
+ if ((*flags & CIFSSEC_MUST_KRB5) == CIFSSEC_MUST_KRB5)
+ *flags = CIFSSEC_MUST_KRB5;
+diff --git a/fs/smb/client/cifsglob.h b/fs/smb/client/cifsglob.h
+index a865941724c02..d4bcc7da700c6 100644
+--- a/fs/smb/client/cifsglob.h
++++ b/fs/smb/client/cifsglob.h
+@@ -1901,7 +1901,7 @@ static inline bool is_replayable_error(int error)
+ #define CIFSSEC_MAY_SIGN 0x00001
+ #define CIFSSEC_MAY_NTLMV2 0x00004
+ #define CIFSSEC_MAY_KRB5 0x00008
+-#define CIFSSEC_MAY_SEAL 0x00040 /* not supported yet */
++#define CIFSSEC_MAY_SEAL 0x00040
+ #define CIFSSEC_MAY_NTLMSSP 0x00080 /* raw ntlmssp with ntlmv2 */
+
+ #define CIFSSEC_MUST_SIGN 0x01001
+@@ -1911,11 +1911,11 @@ require use of the stronger protocol */
+ #define CIFSSEC_MUST_NTLMV2 0x04004
+ #define CIFSSEC_MUST_KRB5 0x08008
+ #ifdef CONFIG_CIFS_UPCALL
+-#define CIFSSEC_MASK 0x8F08F /* flags supported if no weak allowed */
++#define CIFSSEC_MASK 0xCF0CF /* flags supported if no weak allowed */
+ #else
+-#define CIFSSEC_MASK 0x87087 /* flags supported if no weak allowed */
++#define CIFSSEC_MASK 0xC70C7 /* flags supported if no weak allowed */
+ #endif /* UPCALL */
+-#define CIFSSEC_MUST_SEAL 0x40040 /* not supported yet */
++#define CIFSSEC_MUST_SEAL 0x40040
+ #define CIFSSEC_MUST_NTLMSSP 0x80080 /* raw ntlmssp with ntlmv2 */
+
+ #define CIFSSEC_DEF (CIFSSEC_MAY_SIGN | CIFSSEC_MAY_NTLMV2 | CIFSSEC_MAY_NTLMSSP | CIFSSEC_MAY_SEAL)
+diff --git a/fs/smb/client/inode.c b/fs/smb/client/inode.c
+index 4a8aa1de95223..dd0afa23734c8 100644
+--- a/fs/smb/client/inode.c
++++ b/fs/smb/client/inode.c
+@@ -1042,13 +1042,26 @@ static int reparse_info_to_fattr(struct cifs_open_info_data *data,
+ }
+
+ rc = -EOPNOTSUPP;
+- switch ((data->reparse.tag = tag)) {
+- case 0: /* SMB1 symlink */
++ data->reparse.tag = tag;
++ if (!data->reparse.tag) {
+ if (server->ops->query_symlink) {
+ rc = server->ops->query_symlink(xid, tcon,
+ cifs_sb, full_path,
+ &data->symlink_target);
+ }
++ if (rc == -EOPNOTSUPP)
++ data->reparse.tag = IO_REPARSE_TAG_INTERNAL;
++ }
++
++ switch (data->reparse.tag) {
++ case 0: /* SMB1 symlink */
++ break;
++ case IO_REPARSE_TAG_INTERNAL:
++ rc = 0;
++ if (le32_to_cpu(data->fi.Attributes) & ATTR_DIRECTORY) {
++ cifs_create_junction_fattr(fattr, sb);
++ goto out;
++ }
+ break;
+ case IO_REPARSE_TAG_MOUNT_POINT:
+ cifs_create_junction_fattr(fattr, sb);
+diff --git a/fs/smb/client/misc.c b/fs/smb/client/misc.c
+index 07c468ddb88a8..65d4b72b4d51a 100644
+--- a/fs/smb/client/misc.c
++++ b/fs/smb/client/misc.c
+@@ -1288,6 +1288,7 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid,
+ const char *full_path,
+ bool *islink)
+ {
++ struct TCP_Server_Info *server = tcon->ses->server;
+ struct cifs_ses *ses = tcon->ses;
+ size_t len;
+ char *path;
+@@ -1304,12 +1305,12 @@ int cifs_inval_name_dfs_link_error(const unsigned int xid,
+ !is_tcon_dfs(tcon))
+ return 0;
+
+- spin_lock(&tcon->tc_lock);
+- if (!tcon->origin_fullpath) {
+- spin_unlock(&tcon->tc_lock);
++ spin_lock(&server->srv_lock);
++ if (!server->leaf_fullpath) {
++ spin_unlock(&server->srv_lock);
+ return 0;
+ }
+- spin_unlock(&tcon->tc_lock);
++ spin_unlock(&server->srv_lock);
+
+ /*
+ * Slow path - tcon is DFS and @full_path has prefix path, so attempt
+diff --git a/fs/smb/client/reparse.c b/fs/smb/client/reparse.c
+index a0ffbda907331..689d8a506d459 100644
+--- a/fs/smb/client/reparse.c
++++ b/fs/smb/client/reparse.c
+@@ -505,6 +505,10 @@ bool cifs_reparse_point_to_fattr(struct cifs_sb_info *cifs_sb,
+ }
+
+ switch (tag) {
++ case IO_REPARSE_TAG_INTERNAL:
++ if (!(fattr->cf_cifsattrs & ATTR_DIRECTORY))
++ return false;
++ fallthrough;
+ case IO_REPARSE_TAG_DFS:
+ case IO_REPARSE_TAG_DFSR:
+ case IO_REPARSE_TAG_MOUNT_POINT:
+diff --git a/fs/smb/client/reparse.h b/fs/smb/client/reparse.h
+index 6b55d1df9e2f8..2c0644bc4e65a 100644
+--- a/fs/smb/client/reparse.h
++++ b/fs/smb/client/reparse.h
+@@ -12,6 +12,12 @@
+ #include "fs_context.h"
+ #include "cifsglob.h"
+
++/*
++ * Used only by cifs.ko to ignore reparse points from files when client or
++ * server doesn't support FSCTL_GET_REPARSE_POINT.
++ */
++#define IO_REPARSE_TAG_INTERNAL ((__u32)~0U)
++
+ static inline dev_t reparse_nfs_mkdev(struct reparse_posix_data *buf)
+ {
+ u64 v = le64_to_cpu(*(__le64 *)buf->DataBuffer);
+@@ -78,10 +84,19 @@ static inline u32 reparse_mode_wsl_tag(mode_t mode)
+ static inline bool reparse_inode_match(struct inode *inode,
+ struct cifs_fattr *fattr)
+ {
++ struct cifsInodeInfo *cinode = CIFS_I(inode);
+ struct timespec64 ctime = inode_get_ctime(inode);
+
+- return (CIFS_I(inode)->cifsAttrs & ATTR_REPARSE) &&
+- CIFS_I(inode)->reparse_tag == fattr->cf_cifstag &&
++ /*
++ * Do not match reparse tags when client or server doesn't support
++ * FSCTL_GET_REPARSE_POINT. @fattr->cf_cifstag should contain correct
++ * reparse tag from query dir response but the client won't be able to
++ * read the reparse point data anyway. This spares us a revalidation.
++ */
++ if (cinode->reparse_tag != IO_REPARSE_TAG_INTERNAL &&
++ cinode->reparse_tag != fattr->cf_cifstag)
++ return false;
++ return (cinode->cifsAttrs & ATTR_REPARSE) &&
+ timespec64_equal(&ctime, &fattr->cf_ctime);
+ }
+
+diff --git a/fs/smb/client/smb2inode.c b/fs/smb/client/smb2inode.c
+index 5c02a12251c84..062b86a4936fd 100644
+--- a/fs/smb/client/smb2inode.c
++++ b/fs/smb/client/smb2inode.c
+@@ -930,6 +930,8 @@ int smb2_query_path_info(const unsigned int xid,
+
+ switch (rc) {
+ case 0:
++ rc = parse_create_response(data, cifs_sb, &out_iov[0]);
++ break;
+ case -EOPNOTSUPP:
+ /*
+ * BB TODO: When support for special files added to Samba
+diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
+index bb84a89e59059..896147ba6660e 100644
+--- a/fs/smb/client/smb2pdu.c
++++ b/fs/smb/client/smb2pdu.c
+@@ -82,6 +82,9 @@ int smb3_encryption_required(const struct cifs_tcon *tcon)
+ if (tcon->seal &&
+ (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+ return 1;
++ if (((global_secflags & CIFSSEC_MUST_SEAL) == CIFSSEC_MUST_SEAL) &&
++ (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
++ return 1;
+ return 0;
+ }
+
+diff --git a/fs/tracefs/event_inode.c b/fs/tracefs/event_inode.c
+index 5d88c184f0fc1..01e99e98457dd 100644
+--- a/fs/tracefs/event_inode.c
++++ b/fs/tracefs/event_inode.c
+@@ -112,7 +112,7 @@ static void release_ei(struct kref *ref)
+ entry->release(entry->name, ei->data);
+ }
+
+- call_rcu(&ei->rcu, free_ei_rcu);
++ call_srcu(&eventfs_srcu, &ei->rcu, free_ei_rcu);
+ }
+
+ static inline void put_ei(struct eventfs_inode *ei)
+@@ -736,7 +736,7 @@ struct eventfs_inode *eventfs_create_dir(const char *name, struct eventfs_inode
+ /* Was the parent freed? */
+ if (list_empty(&ei->list)) {
+ cleanup_ei(ei);
+- ei = NULL;
++ ei = ERR_PTR(-EBUSY);
+ }
+ return ei;
+ }
+diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
+index 7c29f4afc23d5..507a61004ed37 100644
+--- a/fs/tracefs/inode.c
++++ b/fs/tracefs/inode.c
+@@ -42,7 +42,7 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
+ struct tracefs_inode *ti;
+ unsigned long flags;
+
+- ti = kmem_cache_alloc(tracefs_inode_cachep, GFP_KERNEL);
++ ti = alloc_inode_sb(sb, tracefs_inode_cachep, GFP_KERNEL);
+ if (!ti)
+ return NULL;
+
+@@ -53,15 +53,14 @@ static struct inode *tracefs_alloc_inode(struct super_block *sb)
+ return &ti->vfs_inode;
+ }
+
+-static void tracefs_free_inode_rcu(struct rcu_head *rcu)
++static void tracefs_free_inode(struct inode *inode)
+ {
+- struct tracefs_inode *ti;
++ struct tracefs_inode *ti = get_tracefs(inode);
+
+- ti = container_of(rcu, struct tracefs_inode, rcu);
+ kmem_cache_free(tracefs_inode_cachep, ti);
+ }
+
+-static void tracefs_free_inode(struct inode *inode)
++static void tracefs_destroy_inode(struct inode *inode)
+ {
+ struct tracefs_inode *ti = get_tracefs(inode);
+ unsigned long flags;
+@@ -69,8 +68,6 @@ static void tracefs_free_inode(struct inode *inode)
+ spin_lock_irqsave(&tracefs_inode_lock, flags);
+ list_del_rcu(&ti->list);
+ spin_unlock_irqrestore(&tracefs_inode_lock, flags);
+-
+- call_rcu(&ti->rcu, tracefs_free_inode_rcu);
+ }
+
+ static ssize_t default_read_file(struct file *file, char __user *buf,
+@@ -445,6 +442,7 @@ static int tracefs_drop_inode(struct inode *inode)
+ static const struct super_operations tracefs_super_operations = {
+ .alloc_inode = tracefs_alloc_inode,
+ .free_inode = tracefs_free_inode,
++ .destroy_inode = tracefs_destroy_inode,
+ .drop_inode = tracefs_drop_inode,
+ .statfs = simple_statfs,
+ .show_options = tracefs_show_options,
+diff --git a/fs/tracefs/internal.h b/fs/tracefs/internal.h
+index f704d8348357e..d83c2a25f288e 100644
+--- a/fs/tracefs/internal.h
++++ b/fs/tracefs/internal.h
+@@ -10,10 +10,7 @@ enum {
+ };
+
+ struct tracefs_inode {
+- union {
+- struct inode vfs_inode;
+- struct rcu_head rcu;
+- };
++ struct inode vfs_inode;
+ /* The below gets initialized with memset_after(ti, 0, vfs_inode) */
+ struct list_head list;
+ unsigned long flags;
+diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
+index 558ad046972ad..bb471ec364046 100644
+--- a/fs/udf/balloc.c
++++ b/fs/udf/balloc.c
+@@ -18,6 +18,7 @@
+ #include "udfdecl.h"
+
+ #include <linux/bitops.h>
++#include <linux/overflow.h>
+
+ #include "udf_i.h"
+ #include "udf_sb.h"
+@@ -140,7 +141,6 @@ static void udf_bitmap_free_blocks(struct super_block *sb,
+ {
+ struct udf_sb_info *sbi = UDF_SB(sb);
+ struct buffer_head *bh = NULL;
+- struct udf_part_map *partmap;
+ unsigned long block;
+ unsigned long block_group;
+ unsigned long bit;
+@@ -149,19 +149,9 @@ static void udf_bitmap_free_blocks(struct super_block *sb,
+ unsigned long overflow;
+
+ mutex_lock(&sbi->s_alloc_mutex);
+- partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
+- if (bloc->logicalBlockNum + count < count ||
+- (bloc->logicalBlockNum + count) > partmap->s_partition_len) {
+- udf_debug("%u < %d || %u + %u > %u\n",
+- bloc->logicalBlockNum, 0,
+- bloc->logicalBlockNum, count,
+- partmap->s_partition_len);
+- goto error_return;
+- }
+-
++ /* We make sure this cannot overflow when mounting the filesystem */
+ block = bloc->logicalBlockNum + offset +
+ (sizeof(struct spaceBitmapDesc) << 3);
+-
+ do {
+ overflow = 0;
+ block_group = block >> (sb->s_blocksize_bits + 3);
+@@ -391,7 +381,6 @@ static void udf_table_free_blocks(struct super_block *sb,
+ uint32_t count)
+ {
+ struct udf_sb_info *sbi = UDF_SB(sb);
+- struct udf_part_map *partmap;
+ uint32_t start, end;
+ uint32_t elen;
+ struct kernel_lb_addr eloc;
+@@ -400,16 +389,6 @@ static void udf_table_free_blocks(struct super_block *sb,
+ struct udf_inode_info *iinfo;
+
+ mutex_lock(&sbi->s_alloc_mutex);
+- partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
+- if (bloc->logicalBlockNum + count < count ||
+- (bloc->logicalBlockNum + count) > partmap->s_partition_len) {
+- udf_debug("%u < %d || %u + %u > %u\n",
+- bloc->logicalBlockNum, 0,
+- bloc->logicalBlockNum, count,
+- partmap->s_partition_len);
+- goto error_return;
+- }
+-
+ iinfo = UDF_I(table);
+ udf_add_free_space(sb, sbi->s_partition, count);
+
+@@ -684,6 +663,17 @@ void udf_free_blocks(struct super_block *sb, struct inode *inode,
+ {
+ uint16_t partition = bloc->partitionReferenceNum;
+ struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
++ uint32_t blk;
++
++ if (check_add_overflow(bloc->logicalBlockNum, offset, &blk) ||
++ check_add_overflow(blk, count, &blk) ||
++ bloc->logicalBlockNum + count > map->s_partition_len) {
++ udf_debug("Invalid request to free blocks: (%d, %u), off %u, "
++ "len %u, partition len %u\n",
++ partition, bloc->logicalBlockNum, offset, count,
++ map->s_partition_len);
++ return;
++ }
+
+ if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) {
+ udf_bitmap_free_blocks(sb, map->s_uspace.s_bitmap,
+diff --git a/include/linux/blk-integrity.h b/include/linux/blk-integrity.h
+index 7428cb43952da..9fc4fed9a19f8 100644
+--- a/include/linux/blk-integrity.h
++++ b/include/linux/blk-integrity.h
+@@ -100,14 +100,13 @@ static inline bool blk_integrity_rq(struct request *rq)
+ }
+
+ /*
+- * Return the first bvec that contains integrity data. Only drivers that are
+- * limited to a single integrity segment should use this helper.
++ * Return the current bvec that contains the integrity data. bip_iter may be
++ * advanced to iterate over the integrity data.
+ */
+-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
++static inline struct bio_vec rq_integrity_vec(struct request *rq)
+ {
+- if (WARN_ON_ONCE(queue_max_integrity_segments(rq->q) > 1))
+- return NULL;
+- return rq->bio->bi_integrity->bip_vec;
++ return mp_bvec_iter_bvec(rq->bio->bi_integrity->bip_vec,
++ rq->bio->bi_integrity->bip_iter);
+ }
+ #else /* CONFIG_BLK_DEV_INTEGRITY */
+ static inline int blk_rq_count_integrity_sg(struct request_queue *q,
+@@ -167,9 +166,10 @@ static inline int blk_integrity_rq(struct request *rq)
+ return 0;
+ }
+
+-static inline struct bio_vec *rq_integrity_vec(struct request *rq)
++static inline struct bio_vec rq_integrity_vec(struct request *rq)
+ {
+- return NULL;
++ /* the optimizer will remove all calls to this function */
++ return (struct bio_vec){ };
+ }
+ #endif /* CONFIG_BLK_DEV_INTEGRITY */
+ #endif /* _LINUX_BLK_INTEGRITY_H */
+diff --git a/include/linux/fs.h b/include/linux/fs.h
+index 0283cf366c2a9..93ac1a859d699 100644
+--- a/include/linux/fs.h
++++ b/include/linux/fs.h
+@@ -629,6 +629,7 @@ struct inode {
+ umode_t i_mode;
+ unsigned short i_opflags;
+ kuid_t i_uid;
++ struct list_head i_lru; /* inode LRU list */
+ kgid_t i_gid;
+ unsigned int i_flags;
+
+@@ -690,7 +691,6 @@ struct inode {
+ u16 i_wb_frn_avg_time;
+ u16 i_wb_frn_history;
+ #endif
+- struct list_head i_lru; /* inode LRU list */
+ struct list_head i_sb_list;
+ struct list_head i_wb_list; /* backing dev writeback list */
+ union {
+diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
+index 942a587bb97e3..677aea20d3e11 100644
+--- a/include/linux/pci_ids.h
++++ b/include/linux/pci_ids.h
+@@ -2126,6 +2126,8 @@
+
+ #define PCI_VENDOR_ID_CHELSIO 0x1425
+
++#define PCI_VENDOR_ID_EDIMAX 0x1432
++
+ #define PCI_VENDOR_ID_ADLINK 0x144a
+
+ #define PCI_VENDOR_ID_SAMSUNG 0x144d
+diff --git a/include/linux/profile.h b/include/linux/profile.h
+index 04ae5ebcb637a..cb365a7518616 100644
+--- a/include/linux/profile.h
++++ b/include/linux/profile.h
+@@ -11,7 +11,6 @@
+
+ #define CPU_PROFILING 1
+ #define SCHED_PROFILING 2
+-#define SLEEP_PROFILING 3
+ #define KVM_PROFILING 4
+
+ struct proc_dir_entry;
+diff --git a/include/linux/rcupdate.h b/include/linux/rcupdate.h
+index dfd2399f2cde0..61cb3de236af1 100644
+--- a/include/linux/rcupdate.h
++++ b/include/linux/rcupdate.h
+@@ -209,7 +209,6 @@ void synchronize_rcu_tasks_rude(void);
+
+ #define rcu_note_voluntary_context_switch(t) rcu_tasks_qs(t, false)
+ void exit_tasks_rcu_start(void);
+-void exit_tasks_rcu_stop(void);
+ void exit_tasks_rcu_finish(void);
+ #else /* #ifdef CONFIG_TASKS_RCU_GENERIC */
+ #define rcu_tasks_classic_qs(t, preempt) do { } while (0)
+@@ -218,7 +217,6 @@ void exit_tasks_rcu_finish(void);
+ #define call_rcu_tasks call_rcu
+ #define synchronize_rcu_tasks synchronize_rcu
+ static inline void exit_tasks_rcu_start(void) { }
+-static inline void exit_tasks_rcu_stop(void) { }
+ static inline void exit_tasks_rcu_finish(void) { }
+ #endif /* #else #ifdef CONFIG_TASKS_RCU_GENERIC */
+
+diff --git a/include/linux/trace_events.h b/include/linux/trace_events.h
+index 9df3e2973626b..9435185c10ef7 100644
+--- a/include/linux/trace_events.h
++++ b/include/linux/trace_events.h
+@@ -880,7 +880,6 @@ do { \
+ struct perf_event;
+
+ DECLARE_PER_CPU(struct pt_regs, perf_trace_regs);
+-DECLARE_PER_CPU(int, bpf_kprobe_override);
+
+ extern int perf_trace_init(struct perf_event *event);
+ extern void perf_trace_destroy(struct perf_event *event);
+diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
+index d1d7825318c32..6c395a2600e8d 100644
+--- a/include/linux/virtio_net.h
++++ b/include/linux/virtio_net.h
+@@ -56,7 +56,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+ unsigned int thlen = 0;
+ unsigned int p_off = 0;
+ unsigned int ip_proto;
+- u64 ret, remainder, gso_size;
+
+ if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+@@ -99,16 +98,6 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+ u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+ u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
+
+- if (hdr->gso_size) {
+- gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
+- ret = div64_u64_rem(skb->len, gso_size, &remainder);
+- if (!(ret && (hdr->gso_size > needed) &&
+- ((remainder > needed) || (remainder == 0)))) {
+- return -EINVAL;
+- }
+- skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG;
+- }
+-
+ if (!pskb_may_pull(skb, needed))
+ return -EINVAL;
+
+@@ -182,6 +171,11 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+ if (gso_type != SKB_GSO_UDP_L4)
+ return -EINVAL;
+ break;
++ case SKB_GSO_TCPV4:
++ case SKB_GSO_TCPV6:
++ if (skb->csum_offset != offsetof(struct tcphdr, check))
++ return -EINVAL;
++ break;
+ }
+
+ /* Kernel has a special handling for GSO_BY_FRAGS. */
+diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
+index dc627ebf01df8..347959585deb6 100644
+--- a/include/sound/cs35l56.h
++++ b/include/sound/cs35l56.h
+@@ -267,13 +267,23 @@ struct cs35l56_base {
+ bool fw_patched;
+ bool secured;
+ bool can_hibernate;
+- bool fw_owns_asp1;
+ bool cal_data_valid;
+ s8 cal_index;
+ struct cirrus_amp_cal_data cal_data;
+ struct gpio_desc *reset_gpio;
+ };
+
++/* Temporary to avoid a build break with the HDA driver */
++static inline int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base)
++{
++ return 0;
++}
++
++static inline bool cs35l56_is_otp_register(unsigned int reg)
++{
++ return (reg >> 16) == 3;
++}
++
+ extern struct regmap_config cs35l56_regmap_i2c;
+ extern struct regmap_config cs35l56_regmap_spi;
+ extern struct regmap_config cs35l56_regmap_sdw;
+@@ -284,8 +294,6 @@ extern const char * const cs35l56_tx_input_texts[CS35L56_NUM_INPUT_SRC];
+ extern const unsigned int cs35l56_tx_input_values[CS35L56_NUM_INPUT_SRC];
+
+ int cs35l56_set_patch(struct cs35l56_base *cs35l56_base);
+-int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base);
+-int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base);
+ int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command);
+ int cs35l56_firmware_shutdown(struct cs35l56_base *cs35l56_base);
+ int cs35l56_wait_for_firmware_boot(struct cs35l56_base *cs35l56_base);
+diff --git a/io_uring/net.c b/io_uring/net.c
+index cf742bdd2a93e..09bb82bc209a1 100644
+--- a/io_uring/net.c
++++ b/io_uring/net.c
+@@ -591,17 +591,18 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
+ .iovs = &kmsg->fast_iov,
+ .max_len = INT_MAX,
+ .nr_iovs = 1,
+- .mode = KBUF_MODE_EXPAND,
+ };
+
+ if (kmsg->free_iov) {
+ arg.nr_iovs = kmsg->free_iov_nr;
+ arg.iovs = kmsg->free_iov;
+- arg.mode |= KBUF_MODE_FREE;
++ arg.mode = KBUF_MODE_FREE;
+ }
+
+ if (!(sr->flags & IORING_RECVSEND_BUNDLE))
+ arg.nr_iovs = 1;
++ else
++ arg.mode |= KBUF_MODE_EXPAND;
+
+ ret = io_buffers_select(req, &arg, issue_flags);
+ if (unlikely(ret < 0))
+@@ -613,6 +614,7 @@ int io_send(struct io_kiocb *req, unsigned int issue_flags)
+ if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
+ kmsg->free_iov_nr = ret;
+ kmsg->free_iov = arg.iovs;
++ req->flags |= REQ_F_NEED_CLEANUP;
+ }
+ }
+
+@@ -1084,6 +1086,7 @@ static int io_recv_buf_select(struct io_kiocb *req, struct io_async_msghdr *kmsg
+ if (arg.iovs != &kmsg->fast_iov && arg.iovs != kmsg->free_iov) {
+ kmsg->free_iov_nr = ret;
+ kmsg->free_iov = arg.iovs;
++ req->flags |= REQ_F_NEED_CLEANUP;
+ }
+ } else {
+ void __user *buf;
+diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
+index 6b422c275f78c..a8845cc299fec 100644
+--- a/kernel/bpf/verifier.c
++++ b/kernel/bpf/verifier.c
+@@ -7716,6 +7716,13 @@ static int process_dynptr_func(struct bpf_verifier_env *env, int regno, int insn
+ struct bpf_reg_state *regs = cur_regs(env), *reg = ®s[regno];
+ int err;
+
++ if (reg->type != PTR_TO_STACK && reg->type != CONST_PTR_TO_DYNPTR) {
++ verbose(env,
++ "arg#%d expected pointer to stack or const struct bpf_dynptr\n",
++ regno);
++ return -EINVAL;
++ }
++
+ /* MEM_UNINIT and MEM_RDONLY are exclusive, when applied to an
+ * ARG_PTR_TO_DYNPTR (or ARG_PTR_TO_DYNPTR | DYNPTR_TYPE_*):
+ */
+@@ -9465,6 +9472,10 @@ static int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog,
+ return -EINVAL;
+ }
+ } else if (arg->arg_type == (ARG_PTR_TO_DYNPTR | MEM_RDONLY)) {
++ ret = check_func_arg_reg_off(env, reg, regno, ARG_PTR_TO_DYNPTR);
++ if (ret)
++ return ret;
++
+ ret = process_dynptr_func(env, regno, -1, arg->arg_type, 0);
+ if (ret)
+ return ret;
+@@ -11958,12 +11969,6 @@ static int check_kfunc_args(struct bpf_verifier_env *env, struct bpf_kfunc_call_
+ enum bpf_arg_type dynptr_arg_type = ARG_PTR_TO_DYNPTR;
+ int clone_ref_obj_id = 0;
+
+- if (reg->type != PTR_TO_STACK &&
+- reg->type != CONST_PTR_TO_DYNPTR) {
+- verbose(env, "arg#%d expected pointer to stack or dynptr_ptr\n", i);
+- return -EINVAL;
+- }
+-
+ if (reg->type == CONST_PTR_TO_DYNPTR)
+ dynptr_arg_type |= MEM_RDONLY;
+
+diff --git a/kernel/irq/irqdesc.c b/kernel/irq/irqdesc.c
+index 07e99c936ba5d..1dee88ba0ae44 100644
+--- a/kernel/irq/irqdesc.c
++++ b/kernel/irq/irqdesc.c
+@@ -530,6 +530,7 @@ static int alloc_descs(unsigned int start, unsigned int cnt, int node,
+ flags = IRQD_AFFINITY_MANAGED |
+ IRQD_MANAGED_SHUTDOWN;
+ }
++ flags |= IRQD_AFFINITY_SET;
+ mask = &affinity->mask;
+ node = cpu_to_node(cpumask_first(mask));
+ affinity++;
+diff --git a/kernel/jump_label.c b/kernel/jump_label.c
+index 1f05a19918f47..c6ac0d0377d72 100644
+--- a/kernel/jump_label.c
++++ b/kernel/jump_label.c
+@@ -231,7 +231,7 @@ void static_key_disable_cpuslocked(struct static_key *key)
+ }
+
+ jump_label_lock();
+- if (atomic_cmpxchg(&key->enabled, 1, 0))
++ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
+ jump_label_update(key);
+ jump_label_unlock();
+ }
+@@ -284,7 +284,7 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
+ return;
+
+ guard(mutex)(&jump_label_mutex);
+- if (atomic_cmpxchg(&key->enabled, 1, 0))
++ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
+ jump_label_update(key);
+ else
+ WARN_ON_ONCE(!static_key_slow_try_dec(key));
+diff --git a/kernel/kcov.c b/kernel/kcov.c
+index f0a69d402066e..274b6b7c718de 100644
+--- a/kernel/kcov.c
++++ b/kernel/kcov.c
+@@ -161,6 +161,15 @@ static void kcov_remote_area_put(struct kcov_remote_area *area,
+ kmsan_unpoison_memory(&area->list, sizeof(area->list));
+ }
+
++/*
++ * Unlike in_serving_softirq(), this function returns false when called during
++ * a hardirq or an NMI that happened in the softirq context.
++ */
++static inline bool in_softirq_really(void)
++{
++ return in_serving_softirq() && !in_hardirq() && !in_nmi();
++}
++
+ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_struct *t)
+ {
+ unsigned int mode;
+@@ -170,7 +179,7 @@ static notrace bool check_kcov_mode(enum kcov_mode needed_mode, struct task_stru
+ * so we ignore code executed in interrupts, unless we are in a remote
+ * coverage collection section in a softirq.
+ */
+- if (!in_task() && !(in_serving_softirq() && t->kcov_softirq))
++ if (!in_task() && !(in_softirq_really() && t->kcov_softirq))
+ return false;
+ mode = READ_ONCE(t->kcov_mode);
+ /*
+@@ -849,7 +858,7 @@ void kcov_remote_start(u64 handle)
+
+ if (WARN_ON(!kcov_check_handle(handle, true, true, true)))
+ return;
+- if (!in_task() && !in_serving_softirq())
++ if (!in_task() && !in_softirq_really())
+ return;
+
+ local_lock_irqsave(&kcov_percpu_data.lock, flags);
+@@ -991,7 +1000,7 @@ void kcov_remote_stop(void)
+ int sequence;
+ unsigned long flags;
+
+- if (!in_task() && !in_serving_softirq())
++ if (!in_task() && !in_softirq_really())
+ return;
+
+ local_lock_irqsave(&kcov_percpu_data.lock, flags);
+diff --git a/kernel/kprobes.c b/kernel/kprobes.c
+index 6a76a81000735..85251c254d8a6 100644
+--- a/kernel/kprobes.c
++++ b/kernel/kprobes.c
+@@ -1557,8 +1557,8 @@ static bool is_cfi_preamble_symbol(unsigned long addr)
+ if (lookup_symbol_name(addr, symbuf))
+ return false;
+
+- return str_has_prefix("__cfi_", symbuf) ||
+- str_has_prefix("__pfx_", symbuf);
++ return str_has_prefix(symbuf, "__cfi_") ||
++ str_has_prefix(symbuf, "__pfx_");
+ }
+
+ static int check_kprobe_address_safe(struct kprobe *p,
+diff --git a/kernel/locking/qspinlock_paravirt.h b/kernel/locking/qspinlock_paravirt.h
+index f5a36e67b5935..ac2e225027410 100644
+--- a/kernel/locking/qspinlock_paravirt.h
++++ b/kernel/locking/qspinlock_paravirt.h
+@@ -357,7 +357,7 @@ static void pv_wait_node(struct mcs_spinlock *node, struct mcs_spinlock *prev)
+ static void pv_kick_node(struct qspinlock *lock, struct mcs_spinlock *node)
+ {
+ struct pv_node *pn = (struct pv_node *)node;
+- enum vcpu_state old = vcpu_halted;
++ u8 old = vcpu_halted;
+ /*
+ * If the vCPU is indeed halted, advance its state to match that of
+ * pv_wait_node(). If OTOH this fails, the vCPU was running and will
+diff --git a/kernel/module/main.c b/kernel/module/main.c
+index d18a94b973e10..3f9da537024a1 100644
+--- a/kernel/module/main.c
++++ b/kernel/module/main.c
+@@ -3101,7 +3101,7 @@ static bool idempotent(struct idempotent *u, const void *cookie)
+ struct idempotent *existing;
+ bool first;
+
+- u->ret = 0;
++ u->ret = -EINTR;
+ u->cookie = cookie;
+ init_completion(&u->complete);
+
+@@ -3137,7 +3137,7 @@ static int idempotent_complete(struct idempotent *u, int ret)
+ hlist_for_each_entry_safe(pos, next, head, entry) {
+ if (pos->cookie != cookie)
+ continue;
+- hlist_del(&pos->entry);
++ hlist_del_init(&pos->entry);
+ pos->ret = ret;
+ complete(&pos->complete);
+ }
+@@ -3145,6 +3145,28 @@ static int idempotent_complete(struct idempotent *u, int ret)
+ return ret;
+ }
+
++/*
++ * Wait for the idempotent worker.
++ *
++ * If we get interrupted, we need to remove ourselves from the
++ * the idempotent list, and the completion may still come in.
++ *
++ * The 'idem_lock' protects against the race, and 'idem.ret' was
++ * initialized to -EINTR and is thus always the right return
++ * value even if the idempotent work then completes between
++ * the wait_for_completion and the cleanup.
++ */
++static int idempotent_wait_for_completion(struct idempotent *u)
++{
++ if (wait_for_completion_interruptible(&u->complete)) {
++ spin_lock(&idem_lock);
++ if (!hlist_unhashed(&u->entry))
++ hlist_del(&u->entry);
++ spin_unlock(&idem_lock);
++ }
++ return u->ret;
++}
++
+ static int init_module_from_file(struct file *f, const char __user * uargs, int flags)
+ {
+ struct load_info info = { };
+@@ -3180,15 +3202,16 @@ static int idempotent_init_module(struct file *f, const char __user * uargs, int
+ if (!f || !(f->f_mode & FMODE_READ))
+ return -EBADF;
+
+- /* See if somebody else is doing the operation? */
+- if (idempotent(&idem, file_inode(f))) {
+- wait_for_completion(&idem.complete);
+- return idem.ret;
++ /* Are we the winners of the race and get to do this? */
++ if (!idempotent(&idem, file_inode(f))) {
++ int ret = init_module_from_file(f, uargs, flags);
++ return idempotent_complete(&idem, ret);
+ }
+
+- /* Otherwise, we'll do it and complete others */
+- return idempotent_complete(&idem,
+- init_module_from_file(f, uargs, flags));
++ /*
++ * Somebody else won the race and is loading the module.
++ */
++ return idempotent_wait_for_completion(&idem);
+ }
+
+ SYSCALL_DEFINE3(finit_module, int, fd, const char __user *, uargs, int, flags)
+diff --git a/kernel/padata.c b/kernel/padata.c
+index 53f4bc9127127..0fa6c28954603 100644
+--- a/kernel/padata.c
++++ b/kernel/padata.c
+@@ -517,6 +517,13 @@ void __init padata_do_multithreaded(struct padata_mt_job *job)
+ ps.chunk_size = max(ps.chunk_size, job->min_chunk);
+ ps.chunk_size = roundup(ps.chunk_size, job->align);
+
++ /*
++ * chunk_size can be 0 if the caller sets min_chunk to 0. So force it
++ * to at least 1 to prevent divide-by-0 panic in padata_mt_helper().`
++ */
++ if (!ps.chunk_size)
++ ps.chunk_size = 1U;
++
+ list_for_each_entry(pw, &works, pw_list)
+ if (job->numa_aware) {
+ int old_node = atomic_read(&last_used_nid);
+diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
+index 25f3cf679b358..bdf0087d64423 100644
+--- a/kernel/pid_namespace.c
++++ b/kernel/pid_namespace.c
+@@ -249,24 +249,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
+ set_current_state(TASK_INTERRUPTIBLE);
+ if (pid_ns->pid_allocated == init_pids)
+ break;
+- /*
+- * Release tasks_rcu_exit_srcu to avoid following deadlock:
+- *
+- * 1) TASK A unshare(CLONE_NEWPID)
+- * 2) TASK A fork() twice -> TASK B (child reaper for new ns)
+- * and TASK C
+- * 3) TASK B exits, kills TASK C, waits for TASK A to reap it
+- * 4) TASK A calls synchronize_rcu_tasks()
+- * -> synchronize_srcu(tasks_rcu_exit_srcu)
+- * 5) *DEADLOCK*
+- *
+- * It is considered safe to release tasks_rcu_exit_srcu here
+- * because we assume the current task can not be concurrently
+- * reaped at this point.
+- */
+- exit_tasks_rcu_stop();
+ schedule();
+- exit_tasks_rcu_start();
+ }
+ __set_current_state(TASK_RUNNING);
+
+diff --git a/kernel/profile.c b/kernel/profile.c
+index 2b775cc5c28f9..f2bb82c69f720 100644
+--- a/kernel/profile.c
++++ b/kernel/profile.c
+@@ -57,20 +57,11 @@ static DEFINE_MUTEX(profile_flip_mutex);
+ int profile_setup(char *str)
+ {
+ static const char schedstr[] = "schedule";
+- static const char sleepstr[] = "sleep";
+ static const char kvmstr[] = "kvm";
+ const char *select = NULL;
+ int par;
+
+- if (!strncmp(str, sleepstr, strlen(sleepstr))) {
+-#ifdef CONFIG_SCHEDSTATS
+- force_schedstat_enabled();
+- prof_on = SLEEP_PROFILING;
+- select = sleepstr;
+-#else
+- pr_warn("kernel sleep profiling requires CONFIG_SCHEDSTATS\n");
+-#endif /* CONFIG_SCHEDSTATS */
+- } else if (!strncmp(str, schedstr, strlen(schedstr))) {
++ if (!strncmp(str, schedstr, strlen(schedstr))) {
+ prof_on = SCHED_PROFILING;
+ select = schedstr;
+ } else if (!strncmp(str, kvmstr, strlen(kvmstr))) {
+diff --git a/kernel/rcu/rcutorture.c b/kernel/rcu/rcutorture.c
+index 807fbf6123a77..251cead744603 100644
+--- a/kernel/rcu/rcutorture.c
++++ b/kernel/rcu/rcutorture.c
+@@ -2626,7 +2626,7 @@ static void rcu_torture_fwd_cb_cr(struct rcu_head *rhp)
+ spin_lock_irqsave(&rfp->rcu_fwd_lock, flags);
+ rfcpp = rfp->rcu_fwd_cb_tail;
+ rfp->rcu_fwd_cb_tail = &rfcp->rfc_next;
+- WRITE_ONCE(*rfcpp, rfcp);
++ smp_store_release(rfcpp, rfcp);
+ WRITE_ONCE(rfp->n_launders_cb, rfp->n_launders_cb + 1);
+ i = ((jiffies - rfp->rcu_fwd_startat) / (HZ / FWD_CBS_HIST_DIV));
+ if (i >= ARRAY_SIZE(rfp->n_launders_hist))
+diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
+index 098e82bcc427f..ba3440a45b6dd 100644
+--- a/kernel/rcu/tasks.h
++++ b/kernel/rcu/tasks.h
+@@ -858,7 +858,7 @@ static void rcu_tasks_wait_gp(struct rcu_tasks *rtp)
+ // not know to synchronize with this RCU Tasks grace period) have
+ // completed exiting. The synchronize_rcu() in rcu_tasks_postgp()
+ // will take care of any tasks stuck in the non-preemptible region
+-// of do_exit() following its call to exit_tasks_rcu_stop().
++// of do_exit() following its call to exit_tasks_rcu_finish().
+ // check_all_holdout_tasks(), repeatedly until holdout list is empty:
+ // Scans the holdout list, attempting to identify a quiescent state
+ // for each task on the list. If there is a quiescent state, the
+@@ -1220,7 +1220,7 @@ void exit_tasks_rcu_start(void)
+ * Remove the task from the "yet another list" because do_exit() is now
+ * non-preemptible, allowing synchronize_rcu() to wait beyond this point.
+ */
+-void exit_tasks_rcu_stop(void)
++void exit_tasks_rcu_finish(void)
+ {
+ unsigned long flags;
+ struct rcu_tasks_percpu *rtpcp;
+@@ -1231,22 +1231,12 @@ void exit_tasks_rcu_stop(void)
+ raw_spin_lock_irqsave_rcu_node(rtpcp, flags);
+ list_del_init(&t->rcu_tasks_exit_list);
+ raw_spin_unlock_irqrestore_rcu_node(rtpcp, flags);
+-}
+
+-/*
+- * Contribute to protect against tasklist scan blind spot while the
+- * task is exiting and may be removed from the tasklist. See
+- * corresponding synchronize_srcu() for further details.
+- */
+-void exit_tasks_rcu_finish(void)
+-{
+- exit_tasks_rcu_stop();
+- exit_tasks_rcu_finish_trace(current);
++ exit_tasks_rcu_finish_trace(t);
+ }
+
+ #else /* #ifdef CONFIG_TASKS_RCU */
+ void exit_tasks_rcu_start(void) { }
+-void exit_tasks_rcu_stop(void) { }
+ void exit_tasks_rcu_finish(void) { exit_tasks_rcu_finish_trace(current); }
+ #endif /* #else #ifdef CONFIG_TASKS_RCU */
+
+diff --git a/kernel/rcu/tree.c b/kernel/rcu/tree.c
+index 28c7031711a3f..63fb007beeaf5 100644
+--- a/kernel/rcu/tree.c
++++ b/kernel/rcu/tree.c
+@@ -5110,11 +5110,15 @@ void rcutree_migrate_callbacks(int cpu)
+ struct rcu_data *rdp = per_cpu_ptr(&rcu_data, cpu);
+ bool needwake;
+
+- if (rcu_rdp_is_offloaded(rdp) ||
+- rcu_segcblist_empty(&rdp->cblist))
+- return; /* No callbacks to migrate. */
++ if (rcu_rdp_is_offloaded(rdp))
++ return;
+
+ raw_spin_lock_irqsave(&rcu_state.barrier_lock, flags);
++ if (rcu_segcblist_empty(&rdp->cblist)) {
++ raw_spin_unlock_irqrestore(&rcu_state.barrier_lock, flags);
++ return; /* No callbacks to migrate. */
++ }
++
+ WARN_ON_ONCE(rcu_rdp_cpu_online(rdp));
+ rcu_barrier_entrain(rdp);
+ my_rdp = this_cpu_ptr(&rcu_data);
+diff --git a/kernel/sched/core.c b/kernel/sched/core.c
+index ebf21373f6634..3e84a3b7b7bb9 100644
+--- a/kernel/sched/core.c
++++ b/kernel/sched/core.c
+@@ -9604,6 +9604,30 @@ void set_rq_offline(struct rq *rq)
+ }
+ }
+
++static inline void sched_set_rq_online(struct rq *rq, int cpu)
++{
++ struct rq_flags rf;
++
++ rq_lock_irqsave(rq, &rf);
++ if (rq->rd) {
++ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
++ set_rq_online(rq);
++ }
++ rq_unlock_irqrestore(rq, &rf);
++}
++
++static inline void sched_set_rq_offline(struct rq *rq, int cpu)
++{
++ struct rq_flags rf;
++
++ rq_lock_irqsave(rq, &rf);
++ if (rq->rd) {
++ BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
++ set_rq_offline(rq);
++ }
++ rq_unlock_irqrestore(rq, &rf);
++}
++
+ /*
+ * used to mark begin/end of suspend/resume:
+ */
+@@ -9654,10 +9678,25 @@ static int cpuset_cpu_inactive(unsigned int cpu)
+ return 0;
+ }
+
++static inline void sched_smt_present_inc(int cpu)
++{
++#ifdef CONFIG_SCHED_SMT
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
++ static_branch_inc_cpuslocked(&sched_smt_present);
++#endif
++}
++
++static inline void sched_smt_present_dec(int cpu)
++{
++#ifdef CONFIG_SCHED_SMT
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
++ static_branch_dec_cpuslocked(&sched_smt_present);
++#endif
++}
++
+ int sched_cpu_activate(unsigned int cpu)
+ {
+ struct rq *rq = cpu_rq(cpu);
+- struct rq_flags rf;
+
+ /*
+ * Clear the balance_push callback and prepare to schedule
+@@ -9665,13 +9704,10 @@ int sched_cpu_activate(unsigned int cpu)
+ */
+ balance_push_set(cpu, false);
+
+-#ifdef CONFIG_SCHED_SMT
+ /*
+ * When going up, increment the number of cores with SMT present.
+ */
+- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+- static_branch_inc_cpuslocked(&sched_smt_present);
+-#endif
++ sched_smt_present_inc(cpu);
+ set_cpu_active(cpu, true);
+
+ if (sched_smp_initialized) {
+@@ -9689,12 +9725,7 @@ int sched_cpu_activate(unsigned int cpu)
+ * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
+ * domains.
+ */
+- rq_lock_irqsave(rq, &rf);
+- if (rq->rd) {
+- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+- set_rq_online(rq);
+- }
+- rq_unlock_irqrestore(rq, &rf);
++ sched_set_rq_online(rq, cpu);
+
+ return 0;
+ }
+@@ -9702,7 +9733,6 @@ int sched_cpu_activate(unsigned int cpu)
+ int sched_cpu_deactivate(unsigned int cpu)
+ {
+ struct rq *rq = cpu_rq(cpu);
+- struct rq_flags rf;
+ int ret;
+
+ /*
+@@ -9733,20 +9763,14 @@ int sched_cpu_deactivate(unsigned int cpu)
+ */
+ synchronize_rcu();
+
+- rq_lock_irqsave(rq, &rf);
+- if (rq->rd) {
+- BUG_ON(!cpumask_test_cpu(cpu, rq->rd->span));
+- set_rq_offline(rq);
+- }
+- rq_unlock_irqrestore(rq, &rf);
++ sched_set_rq_offline(rq, cpu);
+
+-#ifdef CONFIG_SCHED_SMT
+ /*
+ * When going down, decrement the number of cores with SMT present.
+ */
+- if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
+- static_branch_dec_cpuslocked(&sched_smt_present);
++ sched_smt_present_dec(cpu);
+
++#ifdef CONFIG_SCHED_SMT
+ sched_core_cpu_deactivate(cpu);
+ #endif
+
+@@ -9756,6 +9780,8 @@ int sched_cpu_deactivate(unsigned int cpu)
+ sched_update_numa(cpu, false);
+ ret = cpuset_cpu_inactive(cpu);
+ if (ret) {
++ sched_smt_present_inc(cpu);
++ sched_set_rq_online(rq, cpu);
+ balance_push_set(cpu, false);
+ set_cpu_active(cpu, true);
+ sched_update_numa(cpu, true);
+diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
+index aa48b2ec879df..4feef0d4e4494 100644
+--- a/kernel/sched/cputime.c
++++ b/kernel/sched/cputime.c
+@@ -582,6 +582,12 @@ void cputime_adjust(struct task_cputime *curr, struct prev_cputime *prev,
+ }
+
+ stime = mul_u64_u64_div_u64(stime, rtime, stime + utime);
++ /*
++ * Because mul_u64_u64_div_u64() can approximate on some
++ * achitectures; enforce the constraint that: a*b/(b+c) <= a.
++ */
++ if (unlikely(stime > rtime))
++ stime = rtime;
+
+ update:
+ /*
+diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
+index 78e48f5426ee1..eb0cdcd4d9212 100644
+--- a/kernel/sched/stats.c
++++ b/kernel/sched/stats.c
+@@ -92,16 +92,6 @@ void __update_stats_enqueue_sleeper(struct rq *rq, struct task_struct *p,
+
+ trace_sched_stat_blocked(p, delta);
+
+- /*
+- * Blocking time is in units of nanosecs, so shift by
+- * 20 to get a milliseconds-range estimation of the
+- * amount of time that the task spent sleeping:
+- */
+- if (unlikely(prof_on == SLEEP_PROFILING)) {
+- profile_hits(SLEEP_PROFILING,
+- (void *)get_wchan(p),
+- delta >> 20);
+- }
+ account_scheduler_latency(p, delta >> 10, 0);
+ }
+ }
+diff --git a/kernel/time/clocksource.c b/kernel/time/clocksource.c
+index d25ba49e313cc..d0538a75f4c63 100644
+--- a/kernel/time/clocksource.c
++++ b/kernel/time/clocksource.c
+@@ -246,7 +246,7 @@ static enum wd_read_status cs_watchdog_read(struct clocksource *cs, u64 *csnow,
+
+ wd_delay = cycles_to_nsec_safe(watchdog, *wdnow, wd_end);
+ if (wd_delay <= WATCHDOG_MAX_SKEW) {
+- if (nretries > 1 || nretries >= max_retries) {
++ if (nretries > 1 && nretries >= max_retries) {
+ pr_warn("timekeeping watchdog on CPU%d: %s retried %d times before success\n",
+ smp_processor_id(), watchdog->name, nretries);
+ }
+diff --git a/kernel/time/ntp.c b/kernel/time/ntp.c
+index 406dccb79c2b6..8d2dd214ec682 100644
+--- a/kernel/time/ntp.c
++++ b/kernel/time/ntp.c
+@@ -727,17 +727,16 @@ static inline void process_adjtimex_modes(const struct __kernel_timex *txc,
+ }
+
+ if (txc->modes & ADJ_MAXERROR)
+- time_maxerror = txc->maxerror;
++ time_maxerror = clamp(txc->maxerror, 0, NTP_PHASE_LIMIT);
+
+ if (txc->modes & ADJ_ESTERROR)
+- time_esterror = txc->esterror;
++ time_esterror = clamp(txc->esterror, 0, NTP_PHASE_LIMIT);
+
+ if (txc->modes & ADJ_TIMECONST) {
+- time_constant = txc->constant;
++ time_constant = clamp(txc->constant, 0, MAXTC);
+ if (!(time_status & STA_NANO))
+ time_constant += 4;
+- time_constant = min(time_constant, (long)MAXTC);
+- time_constant = max(time_constant, 0l);
++ time_constant = clamp(time_constant, 0, MAXTC);
+ }
+
+ if (txc->modes & ADJ_TAI &&
+diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
+index b4843099a8da7..ed58eebb4e8f4 100644
+--- a/kernel/time/tick-broadcast.c
++++ b/kernel/time/tick-broadcast.c
+@@ -1141,7 +1141,6 @@ void tick_broadcast_switch_to_oneshot(void)
+ #ifdef CONFIG_HOTPLUG_CPU
+ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+ {
+- struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+ struct clock_event_device *bc;
+ unsigned long flags;
+
+@@ -1167,6 +1166,8 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+ * device to avoid the starvation.
+ */
+ if (tick_check_broadcast_expired()) {
++ struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
++
+ cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask);
+ tick_program_event(td->evtdev->next_event, 1);
+ }
+diff --git a/kernel/time/timekeeping.c b/kernel/time/timekeeping.c
+index 4e18db1819f84..0381366c541e0 100644
+--- a/kernel/time/timekeeping.c
++++ b/kernel/time/timekeeping.c
+@@ -2479,7 +2479,7 @@ int do_adjtimex(struct __kernel_timex *txc)
+ clock_set |= timekeeping_advance(TK_ADV_FREQ);
+
+ if (clock_set)
+- clock_was_set(CLOCK_REALTIME);
++ clock_was_set(CLOCK_SET_WALL);
+
+ ntp_notify_cmos_timer();
+
+diff --git a/kernel/trace/trace.h b/kernel/trace/trace.h
+index 749a182dab480..8edab43580d5a 100644
+--- a/kernel/trace/trace.h
++++ b/kernel/trace/trace.h
+@@ -1573,6 +1573,29 @@ static inline void *event_file_data(struct file *filp)
+ extern struct mutex event_mutex;
+ extern struct list_head ftrace_events;
+
++/*
++ * When the trace_event_file is the filp->i_private pointer,
++ * it must be taken under the event_mutex lock, and then checked
++ * if the EVENT_FILE_FL_FREED flag is set. If it is, then the
++ * data pointed to by the trace_event_file can not be trusted.
++ *
++ * Use the event_file_file() to access the trace_event_file from
++ * the filp the first time under the event_mutex and check for
++ * NULL. If it is needed to be retrieved again and the event_mutex
++ * is still held, then the event_file_data() can be used and it
++ * is guaranteed to be valid.
++ */
++static inline struct trace_event_file *event_file_file(struct file *filp)
++{
++ struct trace_event_file *file;
++
++ lockdep_assert_held(&event_mutex);
++ file = READ_ONCE(file_inode(filp)->i_private);
++ if (!file || file->flags & EVENT_FILE_FL_FREED)
++ return NULL;
++ return file;
++}
++
+ extern const struct file_operations event_trigger_fops;
+ extern const struct file_operations event_hist_fops;
+ extern const struct file_operations event_hist_debug_fops;
+diff --git a/kernel/trace/trace_events.c b/kernel/trace/trace_events.c
+index 6ef29eba90ceb..f08fbaf8cad67 100644
+--- a/kernel/trace/trace_events.c
++++ b/kernel/trace/trace_events.c
+@@ -1386,12 +1386,12 @@ event_enable_read(struct file *filp, char __user *ubuf, size_t cnt,
+ char buf[4] = "0";
+
+ mutex_lock(&event_mutex);
+- file = event_file_data(filp);
++ file = event_file_file(filp);
+ if (likely(file))
+ flags = file->flags;
+ mutex_unlock(&event_mutex);
+
+- if (!file || flags & EVENT_FILE_FL_FREED)
++ if (!file)
+ return -ENODEV;
+
+ if (flags & EVENT_FILE_FL_ENABLED &&
+@@ -1424,8 +1424,8 @@ event_enable_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ case 1:
+ ret = -ENODEV;
+ mutex_lock(&event_mutex);
+- file = event_file_data(filp);
+- if (likely(file && !(file->flags & EVENT_FILE_FL_FREED))) {
++ file = event_file_file(filp);
++ if (likely(file)) {
+ ret = tracing_update_buffers(file->tr);
+ if (ret < 0) {
+ mutex_unlock(&event_mutex);
+@@ -1540,7 +1540,8 @@ enum {
+
+ static void *f_next(struct seq_file *m, void *v, loff_t *pos)
+ {
+- struct trace_event_call *call = event_file_data(m->private);
++ struct trace_event_file *file = event_file_data(m->private);
++ struct trace_event_call *call = file->event_call;
+ struct list_head *common_head = &ftrace_common_fields;
+ struct list_head *head = trace_get_fields(call);
+ struct list_head *node = v;
+@@ -1572,7 +1573,8 @@ static void *f_next(struct seq_file *m, void *v, loff_t *pos)
+
+ static int f_show(struct seq_file *m, void *v)
+ {
+- struct trace_event_call *call = event_file_data(m->private);
++ struct trace_event_file *file = event_file_data(m->private);
++ struct trace_event_call *call = file->event_call;
+ struct ftrace_event_field *field;
+ const char *array_descriptor;
+
+@@ -1627,12 +1629,14 @@ static int f_show(struct seq_file *m, void *v)
+
+ static void *f_start(struct seq_file *m, loff_t *pos)
+ {
++ struct trace_event_file *file;
+ void *p = (void *)FORMAT_HEADER;
+ loff_t l = 0;
+
+ /* ->stop() is called even if ->start() fails */
+ mutex_lock(&event_mutex);
+- if (!event_file_data(m->private))
++ file = event_file_file(m->private);
++ if (!file)
+ return ERR_PTR(-ENODEV);
+
+ while (l < *pos && p)
+@@ -1706,8 +1710,8 @@ event_filter_read(struct file *filp, char __user *ubuf, size_t cnt,
+ trace_seq_init(s);
+
+ mutex_lock(&event_mutex);
+- file = event_file_data(filp);
+- if (file && !(file->flags & EVENT_FILE_FL_FREED))
++ file = event_file_file(filp);
++ if (file)
+ print_event_filter(file, s);
+ mutex_unlock(&event_mutex);
+
+@@ -1736,9 +1740,13 @@ event_filter_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ return PTR_ERR(buf);
+
+ mutex_lock(&event_mutex);
+- file = event_file_data(filp);
+- if (file)
+- err = apply_event_filter(file, buf);
++ file = event_file_file(filp);
++ if (file) {
++ if (file->flags & EVENT_FILE_FL_FREED)
++ err = -ENODEV;
++ else
++ err = apply_event_filter(file, buf);
++ }
+ mutex_unlock(&event_mutex);
+
+ kfree(buf);
+@@ -2485,7 +2493,6 @@ static int event_callback(const char *name, umode_t *mode, void **data,
+ if (strcmp(name, "format") == 0) {
+ *mode = TRACE_MODE_READ;
+ *fops = &ftrace_event_format_fops;
+- *data = call;
+ return 1;
+ }
+
+diff --git a/kernel/trace/trace_events_hist.c b/kernel/trace/trace_events_hist.c
+index 6ece1308d36a0..5f9119eb7c67f 100644
+--- a/kernel/trace/trace_events_hist.c
++++ b/kernel/trace/trace_events_hist.c
+@@ -5601,7 +5601,7 @@ static int hist_show(struct seq_file *m, void *v)
+
+ mutex_lock(&event_mutex);
+
+- event_file = event_file_data(m->private);
++ event_file = event_file_file(m->private);
+ if (unlikely(!event_file)) {
+ ret = -ENODEV;
+ goto out_unlock;
+@@ -5880,7 +5880,7 @@ static int hist_debug_show(struct seq_file *m, void *v)
+
+ mutex_lock(&event_mutex);
+
+- event_file = event_file_data(m->private);
++ event_file = event_file_file(m->private);
+ if (unlikely(!event_file)) {
+ ret = -ENODEV;
+ goto out_unlock;
+diff --git a/kernel/trace/trace_events_inject.c b/kernel/trace/trace_events_inject.c
+index 8650562bdaa98..a8f076809db4d 100644
+--- a/kernel/trace/trace_events_inject.c
++++ b/kernel/trace/trace_events_inject.c
+@@ -299,7 +299,7 @@ event_inject_write(struct file *filp, const char __user *ubuf, size_t cnt,
+ strim(buf);
+
+ mutex_lock(&event_mutex);
+- file = event_file_data(filp);
++ file = event_file_file(filp);
+ if (file) {
+ call = file->event_call;
+ size = parse_entry(buf, call, &entry);
+diff --git a/kernel/trace/trace_events_trigger.c b/kernel/trace/trace_events_trigger.c
+index 4bec043c8690d..a5e3d6acf1e1e 100644
+--- a/kernel/trace/trace_events_trigger.c
++++ b/kernel/trace/trace_events_trigger.c
+@@ -159,7 +159,7 @@ static void *trigger_start(struct seq_file *m, loff_t *pos)
+
+ /* ->stop() is called even if ->start() fails */
+ mutex_lock(&event_mutex);
+- event_file = event_file_data(m->private);
++ event_file = event_file_file(m->private);
+ if (unlikely(!event_file))
+ return ERR_PTR(-ENODEV);
+
+@@ -213,7 +213,7 @@ static int event_trigger_regex_open(struct inode *inode, struct file *file)
+
+ mutex_lock(&event_mutex);
+
+- if (unlikely(!event_file_data(file))) {
++ if (unlikely(!event_file_file(file))) {
+ mutex_unlock(&event_mutex);
+ return -ENODEV;
+ }
+@@ -293,7 +293,7 @@ static ssize_t event_trigger_regex_write(struct file *file,
+ strim(buf);
+
+ mutex_lock(&event_mutex);
+- event_file = event_file_data(file);
++ event_file = event_file_file(file);
+ if (unlikely(!event_file)) {
+ mutex_unlock(&event_mutex);
+ kfree(buf);
+diff --git a/kernel/trace/tracing_map.c b/kernel/trace/tracing_map.c
+index a4dcf0f243521..3a56e7c8aa4f6 100644
+--- a/kernel/trace/tracing_map.c
++++ b/kernel/trace/tracing_map.c
+@@ -454,7 +454,7 @@ static struct tracing_map_elt *get_free_elt(struct tracing_map *map)
+ struct tracing_map_elt *elt = NULL;
+ int idx;
+
+- idx = atomic_inc_return(&map->next_elt);
++ idx = atomic_fetch_add_unless(&map->next_elt, 1, map->max_elts);
+ if (idx < map->max_elts) {
+ elt = *(TRACING_MAP_ELT(map->elts, idx));
+ if (map->ops && map->ops->elt_init)
+@@ -699,7 +699,7 @@ void tracing_map_clear(struct tracing_map *map)
+ {
+ unsigned int i;
+
+- atomic_set(&map->next_elt, -1);
++ atomic_set(&map->next_elt, 0);
+ atomic64_set(&map->hits, 0);
+ atomic64_set(&map->drops, 0);
+
+@@ -783,7 +783,7 @@ struct tracing_map *tracing_map_create(unsigned int map_bits,
+
+ map->map_bits = map_bits;
+ map->max_elts = (1 << map_bits);
+- atomic_set(&map->next_elt, -1);
++ atomic_set(&map->next_elt, 0);
+
+ map->map_size = (1 << (map_bits + 1));
+ map->ops = ops;
+diff --git a/lib/debugobjects.c b/lib/debugobjects.c
+index fb12a9bacd2fa..7cea91e193a8f 100644
+--- a/lib/debugobjects.c
++++ b/lib/debugobjects.c
+@@ -78,16 +78,17 @@ static bool obj_freeing;
+ /* The number of objs on the global free list */
+ static int obj_nr_tofree;
+
+-static int debug_objects_maxchain __read_mostly;
+-static int __maybe_unused debug_objects_maxchecked __read_mostly;
+-static int debug_objects_fixups __read_mostly;
+-static int debug_objects_warnings __read_mostly;
+-static int debug_objects_enabled __read_mostly
+- = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
+-static int debug_objects_pool_size __read_mostly
+- = ODEBUG_POOL_SIZE;
+-static int debug_objects_pool_min_level __read_mostly
+- = ODEBUG_POOL_MIN_LEVEL;
++static int __data_racy debug_objects_maxchain __read_mostly;
++static int __data_racy __maybe_unused debug_objects_maxchecked __read_mostly;
++static int __data_racy debug_objects_fixups __read_mostly;
++static int __data_racy debug_objects_warnings __read_mostly;
++static int __data_racy debug_objects_enabled __read_mostly
++ = CONFIG_DEBUG_OBJECTS_ENABLE_DEFAULT;
++static int __data_racy debug_objects_pool_size __read_mostly
++ = ODEBUG_POOL_SIZE;
++static int __data_racy debug_objects_pool_min_level __read_mostly
++ = ODEBUG_POOL_MIN_LEVEL;
++
+ static const struct debug_obj_descr *descr_test __read_mostly;
+ static struct kmem_cache *obj_cache __ro_after_init;
+
+diff --git a/mm/list_lru.c b/mm/list_lru.c
+index 3fd64736bc458..6ac393ea7439f 100644
+--- a/mm/list_lru.c
++++ b/mm/list_lru.c
+@@ -85,6 +85,7 @@ list_lru_from_memcg_idx(struct list_lru *lru, int nid, int idx)
+ }
+ #endif /* CONFIG_MEMCG_KMEM */
+
++/* The caller must ensure the memcg lifetime. */
+ bool list_lru_add(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg)
+ {
+@@ -109,14 +110,22 @@ EXPORT_SYMBOL_GPL(list_lru_add);
+
+ bool list_lru_add_obj(struct list_lru *lru, struct list_head *item)
+ {
++ bool ret;
+ int nid = page_to_nid(virt_to_page(item));
+- struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+- mem_cgroup_from_slab_obj(item) : NULL;
+
+- return list_lru_add(lru, item, nid, memcg);
++ if (list_lru_memcg_aware(lru)) {
++ rcu_read_lock();
++ ret = list_lru_add(lru, item, nid, mem_cgroup_from_slab_obj(item));
++ rcu_read_unlock();
++ } else {
++ ret = list_lru_add(lru, item, nid, NULL);
++ }
++
++ return ret;
+ }
+ EXPORT_SYMBOL_GPL(list_lru_add_obj);
+
++/* The caller must ensure the memcg lifetime. */
+ bool list_lru_del(struct list_lru *lru, struct list_head *item, int nid,
+ struct mem_cgroup *memcg)
+ {
+@@ -139,11 +148,18 @@ EXPORT_SYMBOL_GPL(list_lru_del);
+
+ bool list_lru_del_obj(struct list_lru *lru, struct list_head *item)
+ {
++ bool ret;
+ int nid = page_to_nid(virt_to_page(item));
+- struct mem_cgroup *memcg = list_lru_memcg_aware(lru) ?
+- mem_cgroup_from_slab_obj(item) : NULL;
+
+- return list_lru_del(lru, item, nid, memcg);
++ if (list_lru_memcg_aware(lru)) {
++ rcu_read_lock();
++ ret = list_lru_del(lru, item, nid, mem_cgroup_from_slab_obj(item));
++ rcu_read_unlock();
++ } else {
++ ret = list_lru_del(lru, item, nid, NULL);
++ }
++
++ return ret;
+ }
+ EXPORT_SYMBOL_GPL(list_lru_del_obj);
+
+diff --git a/mm/memcontrol.c b/mm/memcontrol.c
+index 8f2f1bb18c9cb..88c7a0861017c 100644
+--- a/mm/memcontrol.c
++++ b/mm/memcontrol.c
+@@ -5568,11 +5568,28 @@ static struct cftype mem_cgroup_legacy_files[] = {
+
+ #define MEM_CGROUP_ID_MAX ((1UL << MEM_CGROUP_ID_SHIFT) - 1)
+ static DEFINE_IDR(mem_cgroup_idr);
++static DEFINE_SPINLOCK(memcg_idr_lock);
++
++static int mem_cgroup_alloc_id(void)
++{
++ int ret;
++
++ idr_preload(GFP_KERNEL);
++ spin_lock(&memcg_idr_lock);
++ ret = idr_alloc(&mem_cgroup_idr, NULL, 1, MEM_CGROUP_ID_MAX + 1,
++ GFP_NOWAIT);
++ spin_unlock(&memcg_idr_lock);
++ idr_preload_end();
++ return ret;
++}
+
+ static void mem_cgroup_id_remove(struct mem_cgroup *memcg)
+ {
+ if (memcg->id.id > 0) {
++ spin_lock(&memcg_idr_lock);
+ idr_remove(&mem_cgroup_idr, memcg->id.id);
++ spin_unlock(&memcg_idr_lock);
++
+ memcg->id.id = 0;
+ }
+ }
+@@ -5706,8 +5723,7 @@ static struct mem_cgroup *mem_cgroup_alloc(struct mem_cgroup *parent)
+ if (!memcg)
+ return ERR_PTR(error);
+
+- memcg->id.id = idr_alloc(&mem_cgroup_idr, NULL,
+- 1, MEM_CGROUP_ID_MAX + 1, GFP_KERNEL);
++ memcg->id.id = mem_cgroup_alloc_id();
+ if (memcg->id.id < 0) {
+ error = memcg->id.id;
+ goto fail;
+@@ -5854,7 +5870,9 @@ static int mem_cgroup_css_online(struct cgroup_subsys_state *css)
+ * publish it here at the end of onlining. This matches the
+ * regular ID destruction during offlining.
+ */
++ spin_lock(&memcg_idr_lock);
+ idr_replace(&mem_cgroup_idr, memcg, memcg->id.id);
++ spin_unlock(&memcg_idr_lock);
+
+ return 0;
+ offline_kmem:
+diff --git a/mm/slub.c b/mm/slub.c
+index 4927edec6a8c9..849e8972e2ffc 100644
+--- a/mm/slub.c
++++ b/mm/slub.c
+@@ -4655,6 +4655,9 @@ static void __kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p)
+ if (!df.slab)
+ continue;
+
++ if (kfence_free(df.freelist))
++ continue;
++
+ do_slab_free(df.s, df.slab, df.freelist, df.tail, df.cnt,
+ _RET_IP_);
+ } while (likely(size));
+diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
+index 2f26147fdf3c9..4e90bd722e7b5 100644
+--- a/net/bluetooth/hci_sync.c
++++ b/net/bluetooth/hci_sync.c
+@@ -2972,6 +2972,20 @@ static int hci_passive_scan_sync(struct hci_dev *hdev)
+ } else if (hci_is_adv_monitoring(hdev)) {
+ window = hdev->le_scan_window_adv_monitor;
+ interval = hdev->le_scan_int_adv_monitor;
++
++ /* Disable duplicates filter when scanning for advertisement
++ * monitor for the following reasons.
++ *
++ * For HW pattern filtering (ex. MSFT), Realtek and Qualcomm
++ * controllers ignore RSSI_Sampling_Period when the duplicates
++ * filter is enabled.
++ *
++ * For SW pattern filtering, when we're not doing interleaved
++ * scanning, it is necessary to disable duplicates filter,
++ * otherwise hosts can only receive one advertisement and it's
++ * impossible to know if a peer is still in range.
++ */
++ filter_dups = LE_SCAN_FILTER_DUP_DISABLE;
+ } else {
+ window = hdev->le_scan_window;
+ interval = hdev->le_scan_interval;
+diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c
+index c3c26bbb5ddae..9988ba382b686 100644
+--- a/net/bluetooth/l2cap_core.c
++++ b/net/bluetooth/l2cap_core.c
+@@ -6774,6 +6774,7 @@ static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm,
+ bt_cb(skb)->l2cap.psm = psm;
+
+ if (!chan->ops->recv(chan, skb)) {
++ l2cap_chan_unlock(chan);
+ l2cap_chan_put(chan);
+ return;
+ }
+diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c
+index 9a1cb5079a7a0..b2ae0d2434d2e 100644
+--- a/net/bridge/br_multicast.c
++++ b/net/bridge/br_multicast.c
+@@ -2045,16 +2045,14 @@ void br_multicast_del_port(struct net_bridge_port *port)
+ {
+ struct net_bridge *br = port->br;
+ struct net_bridge_port_group *pg;
+- HLIST_HEAD(deleted_head);
+ struct hlist_node *n;
+
+ /* Take care of the remaining groups, only perm ones should be left */
+ spin_lock_bh(&br->multicast_lock);
+ hlist_for_each_entry_safe(pg, n, &port->mglist, mglist)
+ br_multicast_find_del_pg(br, pg);
+- hlist_move_list(&br->mcast_gc_list, &deleted_head);
+ spin_unlock_bh(&br->multicast_lock);
+- br_multicast_gc(&deleted_head);
++ flush_work(&br->mcast_gc_work);
+ br_multicast_port_ctx_deinit(&port->multicast_ctx);
+ free_percpu(port->mcast_stats);
+ }
+diff --git a/net/core/link_watch.c b/net/core/link_watch.c
+index 8ec35194bfcb8..ab150641142aa 100644
+--- a/net/core/link_watch.c
++++ b/net/core/link_watch.c
+@@ -148,9 +148,9 @@ static void linkwatch_schedule_work(int urgent)
+ * override the existing timer.
+ */
+ if (test_bit(LW_URGENT, &linkwatch_flags))
+- mod_delayed_work(system_wq, &linkwatch_work, 0);
++ mod_delayed_work(system_unbound_wq, &linkwatch_work, 0);
+ else
+- schedule_delayed_work(&linkwatch_work, delay);
++ queue_delayed_work(system_unbound_wq, &linkwatch_work, delay);
+ }
+
+
+diff --git a/net/ipv4/tcp_ao.c b/net/ipv4/tcp_ao.c
+index 09c0fa6756b7d..9171e1066808f 100644
+--- a/net/ipv4/tcp_ao.c
++++ b/net/ipv4/tcp_ao.c
+@@ -266,32 +266,49 @@ static void tcp_ao_key_free_rcu(struct rcu_head *head)
+ kfree_sensitive(key);
+ }
+
+-void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
++static void tcp_ao_info_free_rcu(struct rcu_head *head)
+ {
+- struct tcp_ao_info *ao;
++ struct tcp_ao_info *ao = container_of(head, struct tcp_ao_info, rcu);
+ struct tcp_ao_key *key;
+ struct hlist_node *n;
+
++ hlist_for_each_entry_safe(key, n, &ao->head, node) {
++ hlist_del(&key->node);
++ tcp_sigpool_release(key->tcp_sigpool_id);
++ kfree_sensitive(key);
++ }
++ kfree(ao);
++ static_branch_slow_dec_deferred(&tcp_ao_needed);
++}
++
++static void tcp_ao_sk_omem_free(struct sock *sk, struct tcp_ao_info *ao)
++{
++ size_t total_ao_sk_mem = 0;
++ struct tcp_ao_key *key;
++
++ hlist_for_each_entry(key, &ao->head, node)
++ total_ao_sk_mem += tcp_ao_sizeof_key(key);
++ atomic_sub(total_ao_sk_mem, &sk->sk_omem_alloc);
++}
++
++void tcp_ao_destroy_sock(struct sock *sk, bool twsk)
++{
++ struct tcp_ao_info *ao;
++
+ if (twsk) {
+ ao = rcu_dereference_protected(tcp_twsk(sk)->ao_info, 1);
+- tcp_twsk(sk)->ao_info = NULL;
++ rcu_assign_pointer(tcp_twsk(sk)->ao_info, NULL);
+ } else {
+ ao = rcu_dereference_protected(tcp_sk(sk)->ao_info, 1);
+- tcp_sk(sk)->ao_info = NULL;
++ rcu_assign_pointer(tcp_sk(sk)->ao_info, NULL);
+ }
+
+ if (!ao || !refcount_dec_and_test(&ao->refcnt))
+ return;
+
+- hlist_for_each_entry_safe(key, n, &ao->head, node) {
+- hlist_del_rcu(&key->node);
+- if (!twsk)
+- atomic_sub(tcp_ao_sizeof_key(key), &sk->sk_omem_alloc);
+- call_rcu(&key->rcu, tcp_ao_key_free_rcu);
+- }
+-
+- kfree_rcu(ao, rcu);
+- static_branch_slow_dec_deferred(&tcp_ao_needed);
++ if (!twsk)
++ tcp_ao_sk_omem_free(sk, ao);
++ call_rcu(&ao->rcu, tcp_ao_info_free_rcu);
+ }
+
+ void tcp_ao_time_wait(struct tcp_timewait_sock *tcptw, struct tcp_sock *tp)
+diff --git a/net/ipv4/tcp_offload.c b/net/ipv4/tcp_offload.c
+index 4b791e74529e1..e4ad3311e1489 100644
+--- a/net/ipv4/tcp_offload.c
++++ b/net/ipv4/tcp_offload.c
+@@ -140,6 +140,9 @@ struct sk_buff *tcp_gso_segment(struct sk_buff *skb,
+ if (thlen < sizeof(*th))
+ goto out;
+
++ if (unlikely(skb_checksum_start(skb) != skb_transport_header(skb)))
++ goto out;
++
+ if (!pskb_may_pull(skb, thlen))
+ goto out;
+
+diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c
+index 59448a2dbf2c7..ee9af921556a7 100644
+--- a/net/ipv4/udp_offload.c
++++ b/net/ipv4/udp_offload.c
+@@ -278,6 +278,10 @@ struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
+ if (gso_skb->len <= sizeof(*uh) + mss)
+ return ERR_PTR(-EINVAL);
+
++ if (unlikely(skb_checksum_start(gso_skb) !=
++ skb_transport_header(gso_skb)))
++ return ERR_PTR(-EINVAL);
++
+ if (skb_gso_ok(gso_skb, features | NETIF_F_GSO_ROBUST)) {
+ /* Packet is from an untrusted source, reset gso_segs. */
+ skb_shinfo(gso_skb)->gso_segs = DIV_ROUND_UP(gso_skb->len - sizeof(*uh),
+diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c
+index 88a34db265d86..7ea4adf81d859 100644
+--- a/net/l2tp/l2tp_core.c
++++ b/net/l2tp/l2tp_core.c
+@@ -88,6 +88,11 @@
+ /* Default trace flags */
+ #define L2TP_DEFAULT_DEBUG_FLAGS 0
+
++#define L2TP_DEPTH_NESTING 2
++#if L2TP_DEPTH_NESTING == SINGLE_DEPTH_NESTING
++#error "L2TP requires its own lockdep subclass"
++#endif
++
+ /* Private data stored for received packets in the skb.
+ */
+ struct l2tp_skb_cb {
+@@ -1085,7 +1090,13 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
+ IPCB(skb)->flags &= ~(IPSKB_XFRM_TUNNEL_SIZE | IPSKB_XFRM_TRANSFORMED | IPSKB_REROUTED);
+ nf_reset_ct(skb);
+
+- bh_lock_sock_nested(sk);
++ /* L2TP uses its own lockdep subclass to avoid lockdep splats caused by
++ * nested socket calls on the same lockdep socket class. This can
++ * happen when data from a user socket is routed over l2tp, which uses
++ * another userspace socket.
++ */
++ spin_lock_nested(&sk->sk_lock.slock, L2TP_DEPTH_NESTING);
++
+ if (sock_owned_by_user(sk)) {
+ kfree_skb(skb);
+ ret = NET_XMIT_DROP;
+@@ -1137,7 +1148,7 @@ static int l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, uns
+ ret = l2tp_xmit_queue(tunnel, skb, &inet->cork.fl);
+
+ out_unlock:
+- bh_unlock_sock(sk);
++ spin_unlock(&sk->sk_lock.slock);
+
+ return ret;
+ }
+diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c
+index 21d55dc539f6c..677bbbac9f169 100644
+--- a/net/mac80211/agg-tx.c
++++ b/net/mac80211/agg-tx.c
+@@ -616,7 +616,9 @@ int ieee80211_start_tx_ba_session(struct ieee80211_sta *pubsta, u16 tid,
+ return -EINVAL;
+
+ if (!pubsta->deflink.ht_cap.ht_supported &&
+- sta->sdata->vif.bss_conf.chanreq.oper.chan->band != NL80211_BAND_6GHZ)
++ !pubsta->deflink.vht_cap.vht_supported &&
++ !pubsta->deflink.he_cap.has_he &&
++ !pubsta->deflink.eht_cap.has_eht)
+ return -EINVAL;
+
+ if (WARN_ON_ONCE(!local->ops->ampdu_action))
+diff --git a/net/mptcp/options.c b/net/mptcp/options.c
+index 8a68382a4fe91..ac2f1a54cc43a 100644
+--- a/net/mptcp/options.c
++++ b/net/mptcp/options.c
+@@ -958,7 +958,8 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk,
+
+ if (subflow->remote_key_valid &&
+ (((mp_opt->suboptions & OPTION_MPTCP_DSS) && mp_opt->use_ack) ||
+- ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) && !mp_opt->echo))) {
++ ((mp_opt->suboptions & OPTION_MPTCP_ADD_ADDR) &&
++ (!mp_opt->echo || subflow->mp_join)))) {
+ /* subflows are fully established as soon as we get any
+ * additional ack, including ADD_ADDR.
+ */
+diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
+index 37954a0b087d2..4cae2aa7be5cb 100644
+--- a/net/mptcp/pm_netlink.c
++++ b/net/mptcp/pm_netlink.c
+@@ -348,7 +348,7 @@ bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk,
+ add_entry = mptcp_lookup_anno_list_by_saddr(msk, addr);
+
+ if (add_entry) {
+- if (mptcp_pm_is_kernel(msk))
++ if (WARN_ON_ONCE(mptcp_pm_is_kernel(msk)))
+ return false;
+
+ sk_reset_timer(sk, &add_entry->add_timer,
+@@ -512,8 +512,8 @@ __lookup_addr(struct pm_nl_pernet *pernet, const struct mptcp_addr_info *info)
+
+ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+ {
++ struct mptcp_pm_addr_entry *local, *signal_and_subflow = NULL;
+ struct sock *sk = (struct sock *)msk;
+- struct mptcp_pm_addr_entry *local;
+ unsigned int add_addr_signal_max;
+ unsigned int local_addr_max;
+ struct pm_nl_pernet *pernet;
+@@ -555,8 +555,6 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+
+ /* check first for announce */
+ if (msk->pm.add_addr_signaled < add_addr_signal_max) {
+- local = select_signal_address(pernet, msk);
+-
+ /* due to racing events on both ends we can reach here while
+ * previous add address is still running: if we invoke now
+ * mptcp_pm_announce_addr(), that will fail and the
+@@ -567,16 +565,26 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+ if (msk->pm.addr_signal & BIT(MPTCP_ADD_ADDR_SIGNAL))
+ return;
+
+- if (local) {
+- if (mptcp_pm_alloc_anno_list(msk, &local->addr)) {
+- __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
+- msk->pm.add_addr_signaled++;
+- mptcp_pm_announce_addr(msk, &local->addr, false);
+- mptcp_pm_nl_addr_send_ack(msk);
+- }
+- }
++ local = select_signal_address(pernet, msk);
++ if (!local)
++ goto subflow;
++
++ /* If the alloc fails, we are on memory pressure, not worth
++ * continuing, and trying to create subflows.
++ */
++ if (!mptcp_pm_alloc_anno_list(msk, &local->addr))
++ return;
++
++ __clear_bit(local->addr.id, msk->pm.id_avail_bitmap);
++ msk->pm.add_addr_signaled++;
++ mptcp_pm_announce_addr(msk, &local->addr, false);
++ mptcp_pm_nl_addr_send_ack(msk);
++
++ if (local->flags & MPTCP_PM_ADDR_FLAG_SUBFLOW)
++ signal_and_subflow = local;
+ }
+
++subflow:
+ /* check if should create a new subflow */
+ while (msk->pm.local_addr_used < local_addr_max &&
+ msk->pm.subflows < subflows_max) {
+@@ -584,9 +592,14 @@ static void mptcp_pm_create_subflow_or_signal_addr(struct mptcp_sock *msk)
+ bool fullmesh;
+ int i, nr;
+
+- local = select_local_address(pernet, msk);
+- if (!local)
+- break;
++ if (signal_and_subflow) {
++ local = signal_and_subflow;
++ signal_and_subflow = NULL;
++ } else {
++ local = select_local_address(pernet, msk);
++ if (!local)
++ break;
++ }
+
+ fullmesh = !!(local->flags & MPTCP_PM_ADDR_FLAG_FULLMESH);
+
+@@ -1328,8 +1341,8 @@ int mptcp_pm_nl_add_addr_doit(struct sk_buff *skb, struct genl_info *info)
+ if (ret < 0)
+ return ret;
+
+- if (addr.addr.port && !(addr.flags & MPTCP_PM_ADDR_FLAG_SIGNAL)) {
+- GENL_SET_ERR_MSG(info, "flags must have signal when using port");
++ if (addr.addr.port && !address_use_port(&addr)) {
++ GENL_SET_ERR_MSG(info, "flags must have signal and not subflow when using port");
+ return -EINVAL;
+ }
+
+diff --git a/net/sctp/input.c b/net/sctp/input.c
+index 17fcaa9b0df94..a8a254a5008e5 100644
+--- a/net/sctp/input.c
++++ b/net/sctp/input.c
+@@ -735,15 +735,19 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
+ struct sock *sk = ep->base.sk;
+ struct net *net = sock_net(sk);
+ struct sctp_hashbucket *head;
++ int err = 0;
+
+ ep->hashent = sctp_ep_hashfn(net, ep->base.bind_addr.port);
+ head = &sctp_ep_hashtable[ep->hashent];
+
++ write_lock(&head->lock);
+ if (sk->sk_reuseport) {
+ bool any = sctp_is_ep_boundall(sk);
+ struct sctp_endpoint *ep2;
+ struct list_head *list;
+- int cnt = 0, err = 1;
++ int cnt = 0;
++
++ err = 1;
+
+ list_for_each(list, &ep->base.bind_addr.address_list)
+ cnt++;
+@@ -761,24 +765,24 @@ static int __sctp_hash_endpoint(struct sctp_endpoint *ep)
+ if (!err) {
+ err = reuseport_add_sock(sk, sk2, any);
+ if (err)
+- return err;
++ goto out;
+ break;
+ } else if (err < 0) {
+- return err;
++ goto out;
+ }
+ }
+
+ if (err) {
+ err = reuseport_alloc(sk, any);
+ if (err)
+- return err;
++ goto out;
+ }
+ }
+
+- write_lock(&head->lock);
+ hlist_add_head(&ep->node, &head->chain);
++out:
+ write_unlock(&head->lock);
+- return 0;
++ return err;
+ }
+
+ /* Add an endpoint to the hash. Local BH-safe. */
+@@ -803,10 +807,9 @@ static void __sctp_unhash_endpoint(struct sctp_endpoint *ep)
+
+ head = &sctp_ep_hashtable[ep->hashent];
+
++ write_lock(&head->lock);
+ if (rcu_access_pointer(sk->sk_reuseport_cb))
+ reuseport_detach_sock(sk);
+-
+- write_lock(&head->lock);
+ hlist_del_init(&ep->node);
+ write_unlock(&head->lock);
+ }
+diff --git a/net/smc/smc_stats.h b/net/smc/smc_stats.h
+index 9d32058db2b5d..e19177ce40923 100644
+--- a/net/smc/smc_stats.h
++++ b/net/smc/smc_stats.h
+@@ -19,7 +19,7 @@
+
+ #include "smc_clc.h"
+
+-#define SMC_MAX_FBACK_RSN_CNT 30
++#define SMC_MAX_FBACK_RSN_CNT 36
+
+ enum {
+ SMC_BUF_8K,
+diff --git a/net/sunrpc/sched.c b/net/sunrpc/sched.c
+index 6debf4fd42d4e..cef623ea15060 100644
+--- a/net/sunrpc/sched.c
++++ b/net/sunrpc/sched.c
+@@ -369,8 +369,10 @@ static void rpc_make_runnable(struct workqueue_struct *wq,
+ if (RPC_IS_ASYNC(task)) {
+ INIT_WORK(&task->u.tk_work, rpc_async_schedule);
+ queue_work(wq, &task->u.tk_work);
+- } else
++ } else {
++ smp_mb__after_atomic();
+ wake_up_bit(&task->tk_runstate, RPC_TASK_QUEUED);
++ }
+ }
+
+ /*
+diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
+index 11cb5badafb6d..be5266007b489 100644
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -1473,6 +1473,7 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ struct unix_sock *u = unix_sk(sk), *newu, *otheru;
+ struct net *net = sock_net(sk);
+ struct sk_buff *skb = NULL;
++ unsigned char state;
+ long timeo;
+ int err;
+
+@@ -1523,7 +1524,6 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ goto out;
+ }
+
+- /* Latch state of peer */
+ unix_state_lock(other);
+
+ /* Apparently VFS overslept socket death. Retry. */
+@@ -1553,37 +1553,21 @@ static int unix_stream_connect(struct socket *sock, struct sockaddr *uaddr,
+ goto restart;
+ }
+
+- /* Latch our state.
+-
+- It is tricky place. We need to grab our state lock and cannot
+- drop lock on peer. It is dangerous because deadlock is
+- possible. Connect to self case and simultaneous
+- attempt to connect are eliminated by checking socket
+- state. other is TCP_LISTEN, if sk is TCP_LISTEN we
+- check this before attempt to grab lock.
+-
+- Well, and we have to recheck the state after socket locked.
++ /* self connect and simultaneous connect are eliminated
++ * by rejecting TCP_LISTEN socket to avoid deadlock.
+ */
+- switch (READ_ONCE(sk->sk_state)) {
+- case TCP_CLOSE:
+- /* This is ok... continue with connect */
+- break;
+- case TCP_ESTABLISHED:
+- /* Socket is already connected */
+- err = -EISCONN;
+- goto out_unlock;
+- default:
+- err = -EINVAL;
++ state = READ_ONCE(sk->sk_state);
++ if (unlikely(state != TCP_CLOSE)) {
++ err = state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
+ goto out_unlock;
+ }
+
+ unix_state_lock_nested(sk, U_LOCK_SECOND);
+
+- if (sk->sk_state != TCP_CLOSE) {
++ if (unlikely(sk->sk_state != TCP_CLOSE)) {
++ err = sk->sk_state == TCP_ESTABLISHED ? -EISCONN : -EINVAL;
+ unix_state_unlock(sk);
+- unix_state_unlock(other);
+- sock_put(other);
+- goto restart;
++ goto out_unlock;
+ }
+
+ err = security_unix_stream_connect(sk, other, newsk);
+diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
+index 0fd075238fc74..c2829d673bc76 100644
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -3422,6 +3422,33 @@ static int __nl80211_set_channel(struct cfg80211_registered_device *rdev,
+ if (chandef.chan != cur_chan)
+ return -EBUSY;
+
++ /* only allow this for regular channel widths */
++ switch (wdev->links[link_id].ap.chandef.width) {
++ case NL80211_CHAN_WIDTH_20_NOHT:
++ case NL80211_CHAN_WIDTH_20:
++ case NL80211_CHAN_WIDTH_40:
++ case NL80211_CHAN_WIDTH_80:
++ case NL80211_CHAN_WIDTH_80P80:
++ case NL80211_CHAN_WIDTH_160:
++ case NL80211_CHAN_WIDTH_320:
++ break;
++ default:
++ return -EINVAL;
++ }
++
++ switch (chandef.width) {
++ case NL80211_CHAN_WIDTH_20_NOHT:
++ case NL80211_CHAN_WIDTH_20:
++ case NL80211_CHAN_WIDTH_40:
++ case NL80211_CHAN_WIDTH_80:
++ case NL80211_CHAN_WIDTH_80P80:
++ case NL80211_CHAN_WIDTH_160:
++ case NL80211_CHAN_WIDTH_320:
++ break;
++ default:
++ return -EINVAL;
++ }
++
+ result = rdev_set_ap_chanwidth(rdev, dev, link_id,
+ &chandef);
+ if (result)
+@@ -4458,10 +4485,7 @@ static void get_key_callback(void *c, struct key_params *params)
+ struct nlattr *key;
+ struct get_key_cookie *cookie = c;
+
+- if ((params->key &&
+- nla_put(cookie->msg, NL80211_ATTR_KEY_DATA,
+- params->key_len, params->key)) ||
+- (params->seq &&
++ if ((params->seq &&
+ nla_put(cookie->msg, NL80211_ATTR_KEY_SEQ,
+ params->seq_len, params->seq)) ||
+ (params->cipher &&
+@@ -4473,10 +4497,7 @@ static void get_key_callback(void *c, struct key_params *params)
+ if (!key)
+ goto nla_put_failure;
+
+- if ((params->key &&
+- nla_put(cookie->msg, NL80211_KEY_DATA,
+- params->key_len, params->key)) ||
+- (params->seq &&
++ if ((params->seq &&
+ nla_put(cookie->msg, NL80211_KEY_SEQ,
+ params->seq_len, params->seq)) ||
+ (params->cipher &&
+diff --git a/sound/pci/hda/patch_hdmi.c b/sound/pci/hda/patch_hdmi.c
+index 707d203ba6527..78042ac2b71f2 100644
+--- a/sound/pci/hda/patch_hdmi.c
++++ b/sound/pci/hda/patch_hdmi.c
+@@ -1989,6 +1989,8 @@ static int hdmi_add_cvt(struct hda_codec *codec, hda_nid_t cvt_nid)
+ }
+
+ static const struct snd_pci_quirk force_connect_list[] = {
++ SND_PCI_QUIRK(0x103c, 0x83e2, "HP EliteDesk 800 G4", 1),
++ SND_PCI_QUIRK(0x103c, 0x83ef, "HP MP9 G4 Retail System AMS", 1),
+ SND_PCI_QUIRK(0x103c, 0x870f, "HP", 1),
+ SND_PCI_QUIRK(0x103c, 0x871a, "HP", 1),
+ SND_PCI_QUIRK(0x103c, 0x8711, "HP", 1),
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index a6c1e2199e703..3840565ef8b02 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -10671,6 +10671,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x8086, 0x3038, "Intel NUC 13", ALC295_FIXUP_CHROME_BOOK),
+ SND_PCI_QUIRK(0xf111, 0x0001, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0xf111, 0x0006, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
++ SND_PCI_QUIRK(0xf111, 0x0009, "Framework Laptop", ALC295_FIXUP_FRAMEWORK_LAPTOP_MIC_NO_PRESENCE),
+
+ #if 0
+ /* Below is a quirk table taken from the old code.
+diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
+index 36dddf230c2c4..d597e59863ee3 100644
+--- a/sound/soc/amd/yc/acp6x-mach.c
++++ b/sound/soc/amd/yc/acp6x-mach.c
+@@ -409,6 +409,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
+ DMI_MATCH(DMI_BOARD_NAME, "8A43"),
+ }
+ },
++ {
++ .driver_data = &acp6x_card,
++ .matches = {
++ DMI_MATCH(DMI_BOARD_VENDOR, "HP"),
++ DMI_MATCH(DMI_BOARD_NAME, "8A44"),
++ }
++ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+diff --git a/sound/soc/codecs/cs-amp-lib.c b/sound/soc/codecs/cs-amp-lib.c
+index 287ac01a38735..605964af8afad 100644
+--- a/sound/soc/codecs/cs-amp-lib.c
++++ b/sound/soc/codecs/cs-amp-lib.c
+@@ -108,7 +108,7 @@ static efi_status_t cs_amp_get_efi_variable(efi_char16_t *name,
+
+ KUNIT_STATIC_STUB_REDIRECT(cs_amp_get_efi_variable, name, guid, size, buf);
+
+- if (IS_ENABLED(CONFIG_EFI))
++ if (efi_rt_services_supported(EFI_RT_SUPPORTED_GET_VARIABLE))
+ return efi.get_variable(name, guid, &attr, size, buf);
+
+ return EFI_NOT_FOUND;
+diff --git a/sound/soc/codecs/cs35l56-sdw.c b/sound/soc/codecs/cs35l56-sdw.c
+index 70ff55c1517fe..29a5476af95ae 100644
+--- a/sound/soc/codecs/cs35l56-sdw.c
++++ b/sound/soc/codecs/cs35l56-sdw.c
+@@ -23,6 +23,79 @@
+ /* Register addresses are offset when sent over SoundWire */
+ #define CS35L56_SDW_ADDR_OFFSET 0x8000
+
++/* Cirrus bus bridge registers */
++#define CS35L56_SDW_MEM_ACCESS_STATUS 0xd0
++#define CS35L56_SDW_MEM_READ_DATA 0xd8
++
++#define CS35L56_SDW_LAST_LATE BIT(3)
++#define CS35L56_SDW_CMD_IN_PROGRESS BIT(2)
++#define CS35L56_SDW_RDATA_RDY BIT(0)
++
++#define CS35L56_LATE_READ_POLL_US 10
++#define CS35L56_LATE_READ_TIMEOUT_US 1000
++
++static int cs35l56_sdw_poll_mem_status(struct sdw_slave *peripheral,
++ unsigned int mask,
++ unsigned int match)
++{
++ int ret, val;
++
++ ret = read_poll_timeout(sdw_read_no_pm, val,
++ (val < 0) || ((val & mask) == match),
++ CS35L56_LATE_READ_POLL_US, CS35L56_LATE_READ_TIMEOUT_US,
++ false, peripheral, CS35L56_SDW_MEM_ACCESS_STATUS);
++ if (ret < 0)
++ return ret;
++
++ if (val < 0)
++ return val;
++
++ return 0;
++}
++
++static int cs35l56_sdw_slow_read(struct sdw_slave *peripheral, unsigned int reg,
++ u8 *buf, size_t val_size)
++{
++ int ret, i;
++
++ reg += CS35L56_SDW_ADDR_OFFSET;
++
++ for (i = 0; i < val_size; i += sizeof(u32)) {
++ /* Poll for bus bridge idle */
++ ret = cs35l56_sdw_poll_mem_status(peripheral,
++ CS35L56_SDW_CMD_IN_PROGRESS,
++ 0);
++ if (ret < 0) {
++ dev_err(&peripheral->dev, "!CMD_IN_PROGRESS fail: %d\n", ret);
++ return ret;
++ }
++
++ /* Reading LSByte triggers read of register to holding buffer */
++ sdw_read_no_pm(peripheral, reg + i);
++
++ /* Wait for data available */
++ ret = cs35l56_sdw_poll_mem_status(peripheral,
++ CS35L56_SDW_RDATA_RDY,
++ CS35L56_SDW_RDATA_RDY);
++ if (ret < 0) {
++ dev_err(&peripheral->dev, "RDATA_RDY fail: %d\n", ret);
++ return ret;
++ }
++
++ /* Read data from buffer */
++ ret = sdw_nread_no_pm(peripheral, CS35L56_SDW_MEM_READ_DATA,
++ sizeof(u32), &buf[i]);
++ if (ret) {
++ dev_err(&peripheral->dev, "Late read @%#x failed: %d\n", reg + i, ret);
++ return ret;
++ }
++
++ swab32s((u32 *)&buf[i]);
++ }
++
++ return 0;
++}
++
+ static int cs35l56_sdw_read_one(struct sdw_slave *peripheral, unsigned int reg, void *buf)
+ {
+ int ret;
+@@ -48,6 +121,10 @@ static int cs35l56_sdw_read(void *context, const void *reg_buf,
+ int ret;
+
+ reg = le32_to_cpu(*(const __le32 *)reg_buf);
++
++ if (cs35l56_is_otp_register(reg))
++ return cs35l56_sdw_slow_read(peripheral, reg, buf8, val_size);
++
+ reg += CS35L56_SDW_ADDR_OFFSET;
+
+ if (val_size == 4)
+diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
+index f609cade805d7..6d821a793045e 100644
+--- a/sound/soc/codecs/cs35l56-shared.c
++++ b/sound/soc/codecs/cs35l56-shared.c
+@@ -20,6 +20,18 @@ static const struct reg_sequence cs35l56_patch[] = {
+ * Firmware can change these to non-defaults to satisfy SDCA.
+ * Ensure that they are at known defaults.
+ */
++ { CS35L56_ASP1_ENABLES1, 0x00000000 },
++ { CS35L56_ASP1_CONTROL1, 0x00000028 },
++ { CS35L56_ASP1_CONTROL2, 0x18180200 },
++ { CS35L56_ASP1_CONTROL3, 0x00000002 },
++ { CS35L56_ASP1_FRAME_CONTROL1, 0x03020100 },
++ { CS35L56_ASP1_FRAME_CONTROL5, 0x00020100 },
++ { CS35L56_ASP1_DATA_CONTROL1, 0x00000018 },
++ { CS35L56_ASP1_DATA_CONTROL5, 0x00000018 },
++ { CS35L56_ASP1TX1_INPUT, 0x00000000 },
++ { CS35L56_ASP1TX2_INPUT, 0x00000000 },
++ { CS35L56_ASP1TX3_INPUT, 0x00000000 },
++ { CS35L56_ASP1TX4_INPUT, 0x00000000 },
+ { CS35L56_SWIRE_DP3_CH1_INPUT, 0x00000018 },
+ { CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 },
+ { CS35L56_SWIRE_DP3_CH3_INPUT, 0x00000029 },
+@@ -41,12 +53,18 @@ EXPORT_SYMBOL_NS_GPL(cs35l56_set_patch, SND_SOC_CS35L56_SHARED);
+ static const struct reg_default cs35l56_reg_defaults[] = {
+ /* no defaults for OTP_MEM - first read populates cache */
+
+- /*
+- * No defaults for ASP1 control or ASP1TX mixer. See
+- * cs35l56_populate_asp1_register_defaults() and
+- * cs35l56_sync_asp1_mixer_widgets_with_firmware().
+- */
+-
++ { CS35L56_ASP1_ENABLES1, 0x00000000 },
++ { CS35L56_ASP1_CONTROL1, 0x00000028 },
++ { CS35L56_ASP1_CONTROL2, 0x18180200 },
++ { CS35L56_ASP1_CONTROL3, 0x00000002 },
++ { CS35L56_ASP1_FRAME_CONTROL1, 0x03020100 },
++ { CS35L56_ASP1_FRAME_CONTROL5, 0x00020100 },
++ { CS35L56_ASP1_DATA_CONTROL1, 0x00000018 },
++ { CS35L56_ASP1_DATA_CONTROL5, 0x00000018 },
++ { CS35L56_ASP1TX1_INPUT, 0x00000000 },
++ { CS35L56_ASP1TX2_INPUT, 0x00000000 },
++ { CS35L56_ASP1TX3_INPUT, 0x00000000 },
++ { CS35L56_ASP1TX4_INPUT, 0x00000000 },
+ { CS35L56_SWIRE_DP3_CH1_INPUT, 0x00000018 },
+ { CS35L56_SWIRE_DP3_CH2_INPUT, 0x00000019 },
+ { CS35L56_SWIRE_DP3_CH3_INPUT, 0x00000029 },
+@@ -206,77 +224,6 @@ static bool cs35l56_volatile_reg(struct device *dev, unsigned int reg)
+ }
+ }
+
+-static const struct reg_sequence cs35l56_asp1_defaults[] = {
+- REG_SEQ0(CS35L56_ASP1_ENABLES1, 0x00000000),
+- REG_SEQ0(CS35L56_ASP1_CONTROL1, 0x00000028),
+- REG_SEQ0(CS35L56_ASP1_CONTROL2, 0x18180200),
+- REG_SEQ0(CS35L56_ASP1_CONTROL3, 0x00000002),
+- REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL1, 0x03020100),
+- REG_SEQ0(CS35L56_ASP1_FRAME_CONTROL5, 0x00020100),
+- REG_SEQ0(CS35L56_ASP1_DATA_CONTROL1, 0x00000018),
+- REG_SEQ0(CS35L56_ASP1_DATA_CONTROL5, 0x00000018),
+- REG_SEQ0(CS35L56_ASP1TX1_INPUT, 0x00000000),
+- REG_SEQ0(CS35L56_ASP1TX2_INPUT, 0x00000000),
+- REG_SEQ0(CS35L56_ASP1TX3_INPUT, 0x00000000),
+- REG_SEQ0(CS35L56_ASP1TX4_INPUT, 0x00000000),
+-};
+-
+-/*
+- * The firmware can have control of the ASP so we don't provide regmap
+- * with defaults for these registers, to prevent a regcache_sync() from
+- * overwriting the firmware settings. But if the machine driver hooks up
+- * the ASP it means the driver is taking control of the ASP, so then the
+- * registers are populated with the defaults.
+- */
+-int cs35l56_init_asp1_regs_for_driver_control(struct cs35l56_base *cs35l56_base)
+-{
+- if (!cs35l56_base->fw_owns_asp1)
+- return 0;
+-
+- cs35l56_base->fw_owns_asp1 = false;
+-
+- return regmap_multi_reg_write(cs35l56_base->regmap, cs35l56_asp1_defaults,
+- ARRAY_SIZE(cs35l56_asp1_defaults));
+-}
+-EXPORT_SYMBOL_NS_GPL(cs35l56_init_asp1_regs_for_driver_control, SND_SOC_CS35L56_SHARED);
+-
+-/*
+- * The firmware boot sequence can overwrite the ASP1 config registers so that
+- * they don't match regmap's view of their values. Rewrite the values from the
+- * regmap cache into the hardware registers.
+- */
+-int cs35l56_force_sync_asp1_registers_from_cache(struct cs35l56_base *cs35l56_base)
+-{
+- struct reg_sequence asp1_regs[ARRAY_SIZE(cs35l56_asp1_defaults)];
+- int i, ret;
+-
+- if (cs35l56_base->fw_owns_asp1)
+- return 0;
+-
+- memcpy(asp1_regs, cs35l56_asp1_defaults, sizeof(asp1_regs));
+-
+- /* Read current values from regmap cache into the write sequence */
+- for (i = 0; i < ARRAY_SIZE(asp1_regs); ++i) {
+- ret = regmap_read(cs35l56_base->regmap, asp1_regs[i].reg, &asp1_regs[i].def);
+- if (ret)
+- goto err;
+- }
+-
+- /* Write the values cache-bypassed so that they will be written to silicon */
+- ret = regmap_multi_reg_write_bypassed(cs35l56_base->regmap, asp1_regs,
+- ARRAY_SIZE(asp1_regs));
+- if (ret)
+- goto err;
+-
+- return 0;
+-
+-err:
+- dev_err(cs35l56_base->dev, "Failed to sync ASP1 registers: %d\n", ret);
+-
+- return ret;
+-}
+-EXPORT_SYMBOL_NS_GPL(cs35l56_force_sync_asp1_registers_from_cache, SND_SOC_CS35L56_SHARED);
+-
+ int cs35l56_mbox_send(struct cs35l56_base *cs35l56_base, unsigned int command)
+ {
+ unsigned int val;
+diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
+index 7f2f2f8c13fae..84c34f5b1a516 100644
+--- a/sound/soc/codecs/cs35l56.c
++++ b/sound/soc/codecs/cs35l56.c
+@@ -63,131 +63,6 @@ static int cs35l56_dspwait_put_volsw(struct snd_kcontrol *kcontrol,
+ return snd_soc_put_volsw(kcontrol, ucontrol);
+ }
+
+-static const unsigned short cs35l56_asp1_mixer_regs[] = {
+- CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX2_INPUT,
+- CS35L56_ASP1TX3_INPUT, CS35L56_ASP1TX4_INPUT,
+-};
+-
+-static const char * const cs35l56_asp1_mux_control_names[] = {
+- "ASP1 TX1 Source", "ASP1 TX2 Source", "ASP1 TX3 Source", "ASP1 TX4 Source"
+-};
+-
+-static int cs35l56_sync_asp1_mixer_widgets_with_firmware(struct cs35l56_private *cs35l56)
+-{
+- struct snd_soc_dapm_context *dapm = snd_soc_component_get_dapm(cs35l56->component);
+- const char *prefix = cs35l56->component->name_prefix;
+- char full_name[SNDRV_CTL_ELEM_ID_NAME_MAXLEN];
+- const char *name;
+- struct snd_kcontrol *kcontrol;
+- struct soc_enum *e;
+- unsigned int val[4];
+- int i, item, ret;
+-
+- if (cs35l56->asp1_mixer_widgets_initialized)
+- return 0;
+-
+- /*
+- * Resume so we can read the registers from silicon if the regmap
+- * cache has not yet been populated.
+- */
+- ret = pm_runtime_resume_and_get(cs35l56->base.dev);
+- if (ret < 0)
+- return ret;
+-
+- /* Wait for firmware download and reboot */
+- cs35l56_wait_dsp_ready(cs35l56);
+-
+- ret = regmap_bulk_read(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT,
+- val, ARRAY_SIZE(val));
+-
+- pm_runtime_mark_last_busy(cs35l56->base.dev);
+- pm_runtime_put_autosuspend(cs35l56->base.dev);
+-
+- if (ret) {
+- dev_err(cs35l56->base.dev, "Failed to read ASP1 mixer regs: %d\n", ret);
+- return ret;
+- }
+-
+- for (i = 0; i < ARRAY_SIZE(cs35l56_asp1_mux_control_names); ++i) {
+- name = cs35l56_asp1_mux_control_names[i];
+-
+- if (prefix) {
+- snprintf(full_name, sizeof(full_name), "%s %s", prefix, name);
+- name = full_name;
+- }
+-
+- kcontrol = snd_soc_card_get_kcontrol_locked(dapm->card, name);
+- if (!kcontrol) {
+- dev_warn(cs35l56->base.dev, "Could not find control %s\n", name);
+- continue;
+- }
+-
+- e = (struct soc_enum *)kcontrol->private_value;
+- item = snd_soc_enum_val_to_item(e, val[i] & CS35L56_ASP_TXn_SRC_MASK);
+- snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+- }
+-
+- cs35l56->asp1_mixer_widgets_initialized = true;
+-
+- return 0;
+-}
+-
+-static int cs35l56_dspwait_asp1tx_get(struct snd_kcontrol *kcontrol,
+- struct snd_ctl_elem_value *ucontrol)
+-{
+- struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+- struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+- struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+- int index = e->shift_l;
+- unsigned int addr, val;
+- int ret;
+-
+- ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+- if (ret)
+- return ret;
+-
+- addr = cs35l56_asp1_mixer_regs[index];
+- ret = regmap_read(cs35l56->base.regmap, addr, &val);
+- if (ret)
+- return ret;
+-
+- val &= CS35L56_ASP_TXn_SRC_MASK;
+- ucontrol->value.enumerated.item[0] = snd_soc_enum_val_to_item(e, val);
+-
+- return 0;
+-}
+-
+-static int cs35l56_dspwait_asp1tx_put(struct snd_kcontrol *kcontrol,
+- struct snd_ctl_elem_value *ucontrol)
+-{
+- struct snd_soc_component *component = snd_soc_dapm_kcontrol_component(kcontrol);
+- struct snd_soc_dapm_context *dapm = snd_soc_dapm_kcontrol_dapm(kcontrol);
+- struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+- struct soc_enum *e = (struct soc_enum *)kcontrol->private_value;
+- int item = ucontrol->value.enumerated.item[0];
+- int index = e->shift_l;
+- unsigned int addr, val;
+- bool changed;
+- int ret;
+-
+- ret = cs35l56_sync_asp1_mixer_widgets_with_firmware(cs35l56);
+- if (ret)
+- return ret;
+-
+- addr = cs35l56_asp1_mixer_regs[index];
+- val = snd_soc_enum_item_to_val(e, item);
+-
+- ret = regmap_update_bits_check(cs35l56->base.regmap, addr,
+- CS35L56_ASP_TXn_SRC_MASK, val, &changed);
+- if (ret)
+- return ret;
+-
+- if (changed)
+- snd_soc_dapm_mux_update_power(dapm, kcontrol, item, e, NULL);
+-
+- return changed;
+-}
+-
+ static DECLARE_TLV_DB_SCALE(vol_tlv, -10000, 25, 0);
+
+ static const struct snd_kcontrol_new cs35l56_controls[] = {
+@@ -210,44 +85,40 @@ static const struct snd_kcontrol_new cs35l56_controls[] = {
+ };
+
+ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx1_enum,
+- SND_SOC_NOPM,
+- 0, 0,
++ CS35L56_ASP1TX1_INPUT,
++ 0, CS35L56_ASP_TXn_SRC_MASK,
+ cs35l56_tx_input_texts,
+ cs35l56_tx_input_values);
+
+ static const struct snd_kcontrol_new asp1_tx1_mux =
+- SOC_DAPM_ENUM_EXT("ASP1TX1 SRC", cs35l56_asp1tx1_enum,
+- cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
++ SOC_DAPM_ENUM("ASP1TX1 SRC", cs35l56_asp1tx1_enum);
+
+ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx2_enum,
+- SND_SOC_NOPM,
+- 1, 0,
++ CS35L56_ASP1TX2_INPUT,
++ 0, CS35L56_ASP_TXn_SRC_MASK,
+ cs35l56_tx_input_texts,
+ cs35l56_tx_input_values);
+
+ static const struct snd_kcontrol_new asp1_tx2_mux =
+- SOC_DAPM_ENUM_EXT("ASP1TX2 SRC", cs35l56_asp1tx2_enum,
+- cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
++ SOC_DAPM_ENUM("ASP1TX2 SRC", cs35l56_asp1tx2_enum);
+
+ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx3_enum,
+- SND_SOC_NOPM,
+- 2, 0,
++ CS35L56_ASP1TX3_INPUT,
++ 0, CS35L56_ASP_TXn_SRC_MASK,
+ cs35l56_tx_input_texts,
+ cs35l56_tx_input_values);
+
+ static const struct snd_kcontrol_new asp1_tx3_mux =
+- SOC_DAPM_ENUM_EXT("ASP1TX3 SRC", cs35l56_asp1tx3_enum,
+- cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
++ SOC_DAPM_ENUM("ASP1TX3 SRC", cs35l56_asp1tx3_enum);
+
+ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_asp1tx4_enum,
+- SND_SOC_NOPM,
+- 3, 0,
++ CS35L56_ASP1TX4_INPUT,
++ 0, CS35L56_ASP_TXn_SRC_MASK,
+ cs35l56_tx_input_texts,
+ cs35l56_tx_input_values);
+
+ static const struct snd_kcontrol_new asp1_tx4_mux =
+- SOC_DAPM_ENUM_EXT("ASP1TX4 SRC", cs35l56_asp1tx4_enum,
+- cs35l56_dspwait_asp1tx_get, cs35l56_dspwait_asp1tx_put);
++ SOC_DAPM_ENUM("ASP1TX4 SRC", cs35l56_asp1tx4_enum);
+
+ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx1_enum,
+ CS35L56_SWIRE_DP3_CH1_INPUT,
+@@ -285,21 +156,6 @@ static SOC_VALUE_ENUM_SINGLE_DECL(cs35l56_sdw1tx4_enum,
+ static const struct snd_kcontrol_new sdw1_tx4_mux =
+ SOC_DAPM_ENUM("SDW1TX4 SRC", cs35l56_sdw1tx4_enum);
+
+-static int cs35l56_asp1_cfg_event(struct snd_soc_dapm_widget *w,
+- struct snd_kcontrol *kcontrol, int event)
+-{
+- struct snd_soc_component *component = snd_soc_dapm_to_component(w->dapm);
+- struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(component);
+-
+- switch (event) {
+- case SND_SOC_DAPM_PRE_PMU:
+- /* Override register values set by firmware boot */
+- return cs35l56_force_sync_asp1_registers_from_cache(&cs35l56->base);
+- default:
+- return 0;
+- }
+-}
+-
+ static int cs35l56_play_event(struct snd_soc_dapm_widget *w,
+ struct snd_kcontrol *kcontrol, int event)
+ {
+@@ -336,9 +192,6 @@ static const struct snd_soc_dapm_widget cs35l56_dapm_widgets[] = {
+ SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_B", 0, 0),
+ SND_SOC_DAPM_REGULATOR_SUPPLY("VDD_AMP", 0, 0),
+
+- SND_SOC_DAPM_SUPPLY("ASP1 CFG", SND_SOC_NOPM, 0, 0, cs35l56_asp1_cfg_event,
+- SND_SOC_DAPM_PRE_PMU),
+-
+ SND_SOC_DAPM_SUPPLY("PLAY", SND_SOC_NOPM, 0, 0, cs35l56_play_event,
+ SND_SOC_DAPM_PRE_PMU | SND_SOC_DAPM_POST_PMU | SND_SOC_DAPM_POST_PMD),
+
+@@ -406,9 +259,6 @@ static const struct snd_soc_dapm_route cs35l56_audio_map[] = {
+ { "AMP", NULL, "VDD_B" },
+ { "AMP", NULL, "VDD_AMP" },
+
+- { "ASP1 Playback", NULL, "ASP1 CFG" },
+- { "ASP1 Capture", NULL, "ASP1 CFG" },
+-
+ { "ASP1 Playback", NULL, "PLAY" },
+ { "SDW1 Playback", NULL, "PLAY" },
+
+@@ -459,14 +309,9 @@ static int cs35l56_asp_dai_set_fmt(struct snd_soc_dai *codec_dai, unsigned int f
+ {
+ struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(codec_dai->component);
+ unsigned int val;
+- int ret;
+
+ dev_dbg(cs35l56->base.dev, "%s: %#x\n", __func__, fmt);
+
+- ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+- if (ret)
+- return ret;
+-
+ switch (fmt & SND_SOC_DAIFMT_CLOCK_PROVIDER_MASK) {
+ case SND_SOC_DAIFMT_CBC_CFC:
+ break;
+@@ -540,11 +385,6 @@ static int cs35l56_asp_dai_set_tdm_slot(struct snd_soc_dai *dai, unsigned int tx
+ unsigned int rx_mask, int slots, int slot_width)
+ {
+ struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component);
+- int ret;
+-
+- ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+- if (ret)
+- return ret;
+
+ if ((slots == 0) || (slot_width == 0)) {
+ dev_dbg(cs35l56->base.dev, "tdm config cleared\n");
+@@ -593,11 +433,6 @@ static int cs35l56_asp_dai_hw_params(struct snd_pcm_substream *substream,
+ struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component);
+ unsigned int rate = params_rate(params);
+ u8 asp_width, asp_wl;
+- int ret;
+-
+- ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+- if (ret)
+- return ret;
+
+ asp_wl = params_width(params);
+ if (cs35l56->asp_slot_width)
+@@ -654,11 +489,7 @@ static int cs35l56_asp_dai_set_sysclk(struct snd_soc_dai *dai,
+ int clk_id, unsigned int freq, int dir)
+ {
+ struct cs35l56_private *cs35l56 = snd_soc_component_get_drvdata(dai->component);
+- int freq_id, ret;
+-
+- ret = cs35l56_init_asp1_regs_for_driver_control(&cs35l56->base);
+- if (ret)
+- return ret;
++ int freq_id;
+
+ if (freq == 0) {
+ cs35l56->sysclk_set = false;
+@@ -1039,13 +870,6 @@ static int cs35l56_component_probe(struct snd_soc_component *component)
+ debugfs_create_bool("can_hibernate", 0444, debugfs_root, &cs35l56->base.can_hibernate);
+ debugfs_create_bool("fw_patched", 0444, debugfs_root, &cs35l56->base.fw_patched);
+
+- /*
+- * The widgets for the ASP1TX mixer can't be initialized
+- * until the firmware has been downloaded and rebooted.
+- */
+- regcache_drop_region(cs35l56->base.regmap, CS35L56_ASP1TX1_INPUT, CS35L56_ASP1TX4_INPUT);
+- cs35l56->asp1_mixer_widgets_initialized = false;
+-
+ queue_work(cs35l56->dsp_wq, &cs35l56->dsp_work);
+
+ return 0;
+@@ -1436,9 +1260,6 @@ int cs35l56_common_probe(struct cs35l56_private *cs35l56)
+ cs35l56->base.cal_index = -1;
+ cs35l56->speaker_id = -ENOENT;
+
+- /* Assume that the firmware owns ASP1 until we know different */
+- cs35l56->base.fw_owns_asp1 = true;
+-
+ dev_set_drvdata(cs35l56->base.dev, cs35l56);
+
+ cs35l56_fill_supply_names(cs35l56->supplies);
+diff --git a/sound/soc/codecs/cs35l56.h b/sound/soc/codecs/cs35l56.h
+index b000e7365e406..200f695efca3d 100644
+--- a/sound/soc/codecs/cs35l56.h
++++ b/sound/soc/codecs/cs35l56.h
+@@ -51,7 +51,6 @@ struct cs35l56_private {
+ u8 asp_slot_count;
+ bool tdm_mode;
+ bool sysclk_set;
+- bool asp1_mixer_widgets_initialized;
+ u8 old_sdw_clock_scale;
+ };
+
+diff --git a/sound/soc/codecs/wcd938x-sdw.c b/sound/soc/codecs/wcd938x-sdw.c
+index a1f04010da95f..132c1d24f8f6e 100644
+--- a/sound/soc/codecs/wcd938x-sdw.c
++++ b/sound/soc/codecs/wcd938x-sdw.c
+@@ -1252,12 +1252,12 @@ static int wcd9380_probe(struct sdw_slave *pdev,
+ pdev->prop.lane_control_support = true;
+ pdev->prop.simple_clk_stop_capable = true;
+ if (wcd->is_tx) {
+- pdev->prop.source_ports = GENMASK(WCD938X_MAX_SWR_PORTS, 0);
++ pdev->prop.source_ports = GENMASK(WCD938X_MAX_SWR_PORTS - 1, 0);
+ pdev->prop.src_dpn_prop = wcd938x_dpn_prop;
+ wcd->ch_info = &wcd938x_sdw_tx_ch_info[0];
+ pdev->prop.wake_capable = true;
+ } else {
+- pdev->prop.sink_ports = GENMASK(WCD938X_MAX_SWR_PORTS, 0);
++ pdev->prop.sink_ports = GENMASK(WCD938X_MAX_SWR_PORTS - 1, 0);
+ pdev->prop.sink_dpn_prop = wcd938x_dpn_prop;
+ wcd->ch_info = &wcd938x_sdw_rx_ch_info[0];
+ }
+diff --git a/sound/soc/codecs/wcd939x-sdw.c b/sound/soc/codecs/wcd939x-sdw.c
+index 8acb5651c5bca..392f4dcab3e09 100644
+--- a/sound/soc/codecs/wcd939x-sdw.c
++++ b/sound/soc/codecs/wcd939x-sdw.c
+@@ -1453,12 +1453,12 @@ static int wcd9390_probe(struct sdw_slave *pdev, const struct sdw_device_id *id)
+ pdev->prop.lane_control_support = true;
+ pdev->prop.simple_clk_stop_capable = true;
+ if (wcd->is_tx) {
+- pdev->prop.source_ports = GENMASK(WCD939X_MAX_TX_SWR_PORTS, 0);
++ pdev->prop.source_ports = GENMASK(WCD939X_MAX_TX_SWR_PORTS - 1, 0);
+ pdev->prop.src_dpn_prop = wcd939x_tx_dpn_prop;
+ wcd->ch_info = &wcd939x_sdw_tx_ch_info[0];
+ pdev->prop.wake_capable = true;
+ } else {
+- pdev->prop.sink_ports = GENMASK(WCD939X_MAX_RX_SWR_PORTS, 0);
++ pdev->prop.sink_ports = GENMASK(WCD939X_MAX_RX_SWR_PORTS - 1, 0);
+ pdev->prop.sink_dpn_prop = wcd939x_rx_dpn_prop;
+ wcd->ch_info = &wcd939x_sdw_rx_ch_info[0];
+ }
+diff --git a/sound/soc/codecs/wsa881x.c b/sound/soc/codecs/wsa881x.c
+index 1253695bebd86..53b828f681020 100644
+--- a/sound/soc/codecs/wsa881x.c
++++ b/sound/soc/codecs/wsa881x.c
+@@ -1152,7 +1152,7 @@ static int wsa881x_probe(struct sdw_slave *pdev,
+ wsa881x->sconfig.frame_rate = 48000;
+ wsa881x->sconfig.direction = SDW_DATA_DIR_RX;
+ wsa881x->sconfig.type = SDW_STREAM_PDM;
+- pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS, 0);
++ pdev->prop.sink_ports = GENMASK(WSA881X_MAX_SWR_PORTS - 1, 0);
+ pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop;
+ pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+ pdev->prop.clk_stop_mode1 = true;
+diff --git a/sound/soc/codecs/wsa883x.c b/sound/soc/codecs/wsa883x.c
+index a2e86ef7d18f5..2169d93989841 100644
+--- a/sound/soc/codecs/wsa883x.c
++++ b/sound/soc/codecs/wsa883x.c
+@@ -1399,7 +1399,15 @@ static int wsa883x_probe(struct sdw_slave *pdev,
+ wsa883x->sconfig.direction = SDW_DATA_DIR_RX;
+ wsa883x->sconfig.type = SDW_STREAM_PDM;
+
+- pdev->prop.sink_ports = GENMASK(WSA883X_MAX_SWR_PORTS, 0);
++ /**
++ * Port map index starts with 0, however the data port for this codec
++ * are from index 1
++ */
++ if (of_property_read_u32_array(dev->of_node, "qcom,port-mapping", &pdev->m_port_map[1],
++ WSA883X_MAX_SWR_PORTS))
++ dev_dbg(dev, "Static Port mapping not specified\n");
++
++ pdev->prop.sink_ports = GENMASK(WSA883X_MAX_SWR_PORTS - 1, 0);
+ pdev->prop.simple_clk_stop_capable = true;
+ pdev->prop.sink_dpn_prop = wsa_sink_dpn_prop;
+ pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+diff --git a/sound/soc/codecs/wsa884x.c b/sound/soc/codecs/wsa884x.c
+index a9767ef0e39d1..de4caf61eef9e 100644
+--- a/sound/soc/codecs/wsa884x.c
++++ b/sound/soc/codecs/wsa884x.c
+@@ -1887,7 +1887,15 @@ static int wsa884x_probe(struct sdw_slave *pdev,
+ wsa884x->sconfig.direction = SDW_DATA_DIR_RX;
+ wsa884x->sconfig.type = SDW_STREAM_PDM;
+
+- pdev->prop.sink_ports = GENMASK(WSA884X_MAX_SWR_PORTS, 0);
++ /**
++ * Port map index starts with 0, however the data port for this codec
++ * are from index 1
++ */
++ if (of_property_read_u32_array(dev->of_node, "qcom,port-mapping", &pdev->m_port_map[1],
++ WSA884X_MAX_SWR_PORTS))
++ dev_dbg(dev, "Static Port mapping not specified\n");
++
++ pdev->prop.sink_ports = GENMASK(WSA884X_MAX_SWR_PORTS - 1, 0);
+ pdev->prop.simple_clk_stop_capable = true;
+ pdev->prop.sink_dpn_prop = wsa884x_sink_dpn_prop;
+ pdev->prop.scp_int1_mask = SDW_SCP_INT1_BUS_CLASH | SDW_SCP_INT1_PARITY;
+diff --git a/sound/soc/meson/axg-fifo.c b/sound/soc/meson/axg-fifo.c
+index 59abe0b3c59fb..486c56a84552d 100644
+--- a/sound/soc/meson/axg-fifo.c
++++ b/sound/soc/meson/axg-fifo.c
+@@ -207,25 +207,18 @@ static irqreturn_t axg_fifo_pcm_irq_block(int irq, void *dev_id)
+ status = FIELD_GET(STATUS1_INT_STS, status);
+ axg_fifo_ack_irq(fifo, status);
+
+- /* Use the thread to call period elapsed on nonatomic links */
+- if (status & FIFO_INT_COUNT_REPEAT)
+- return IRQ_WAKE_THREAD;
++ if (status & ~FIFO_INT_COUNT_REPEAT)
++ dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n",
++ status);
+
+- dev_dbg(axg_fifo_dev(ss), "unexpected irq - STS 0x%02x\n",
+- status);
++ if (status & FIFO_INT_COUNT_REPEAT) {
++ snd_pcm_period_elapsed(ss);
++ return IRQ_HANDLED;
++ }
+
+ return IRQ_NONE;
+ }
+
+-static irqreturn_t axg_fifo_pcm_irq_block_thread(int irq, void *dev_id)
+-{
+- struct snd_pcm_substream *ss = dev_id;
+-
+- snd_pcm_period_elapsed(ss);
+-
+- return IRQ_HANDLED;
+-}
+-
+ int axg_fifo_pcm_open(struct snd_soc_component *component,
+ struct snd_pcm_substream *ss)
+ {
+@@ -251,8 +244,9 @@ int axg_fifo_pcm_open(struct snd_soc_component *component,
+ if (ret)
+ return ret;
+
+- ret = request_threaded_irq(fifo->irq, axg_fifo_pcm_irq_block,
+- axg_fifo_pcm_irq_block_thread,
++ /* Use the threaded irq handler only with non-atomic links */
++ ret = request_threaded_irq(fifo->irq, NULL,
++ axg_fifo_pcm_irq_block,
+ IRQF_ONESHOT, dev_name(dev), ss);
+ if (ret)
+ return ret;
+diff --git a/sound/soc/sof/mediatek/mt8195/mt8195.c b/sound/soc/sof/mediatek/mt8195/mt8195.c
+index 31dc98d1b1d8b..8d3fc167cd810 100644
+--- a/sound/soc/sof/mediatek/mt8195/mt8195.c
++++ b/sound/soc/sof/mediatek/mt8195/mt8195.c
+@@ -573,7 +573,7 @@ static const struct snd_sof_dsp_ops sof_mt8195_ops = {
+ static struct snd_sof_of_mach sof_mt8195_machs[] = {
+ {
+ .compatible = "google,tomato",
+- .sof_tplg_filename = "sof-mt8195-mt6359-rt1019-rt5682-dts.tplg"
++ .sof_tplg_filename = "sof-mt8195-mt6359-rt1019-rt5682.tplg"
+ }, {
+ .compatible = "mediatek,mt8195",
+ .sof_tplg_filename = "sof-mt8195.tplg"
+diff --git a/sound/soc/sti/sti_uniperif.c b/sound/soc/sti/sti_uniperif.c
+index ba824f14a39cf..a7956e5a4ee5d 100644
+--- a/sound/soc/sti/sti_uniperif.c
++++ b/sound/soc/sti/sti_uniperif.c
+@@ -352,7 +352,7 @@ static int sti_uniperiph_resume(struct snd_soc_component *component)
+ return ret;
+ }
+
+-static int sti_uniperiph_dai_probe(struct snd_soc_dai *dai)
++int sti_uniperiph_dai_probe(struct snd_soc_dai *dai)
+ {
+ struct sti_uniperiph_data *priv = snd_soc_dai_get_drvdata(dai);
+ struct sti_uniperiph_dai *dai_data = &priv->dai_data;
+diff --git a/sound/soc/sti/uniperif.h b/sound/soc/sti/uniperif.h
+index 2a5de328501c1..74e51f0ff85c8 100644
+--- a/sound/soc/sti/uniperif.h
++++ b/sound/soc/sti/uniperif.h
+@@ -1380,6 +1380,7 @@ int uni_reader_init(struct platform_device *pdev,
+ struct uniperif *reader);
+
+ /* common */
++int sti_uniperiph_dai_probe(struct snd_soc_dai *dai);
+ int sti_uniperiph_dai_set_fmt(struct snd_soc_dai *dai,
+ unsigned int fmt);
+
+diff --git a/sound/soc/sti/uniperif_player.c b/sound/soc/sti/uniperif_player.c
+index dd9013c476649..6d1ce030963c6 100644
+--- a/sound/soc/sti/uniperif_player.c
++++ b/sound/soc/sti/uniperif_player.c
+@@ -1038,6 +1038,7 @@ static const struct snd_soc_dai_ops uni_player_dai_ops = {
+ .startup = uni_player_startup,
+ .shutdown = uni_player_shutdown,
+ .prepare = uni_player_prepare,
++ .probe = sti_uniperiph_dai_probe,
+ .trigger = uni_player_trigger,
+ .hw_params = sti_uniperiph_dai_hw_params,
+ .set_fmt = sti_uniperiph_dai_set_fmt,
+diff --git a/sound/soc/sti/uniperif_reader.c b/sound/soc/sti/uniperif_reader.c
+index 065c5f0d1f5f0..05ea2b794eb92 100644
+--- a/sound/soc/sti/uniperif_reader.c
++++ b/sound/soc/sti/uniperif_reader.c
+@@ -401,6 +401,7 @@ static const struct snd_soc_dai_ops uni_reader_dai_ops = {
+ .startup = uni_reader_startup,
+ .shutdown = uni_reader_shutdown,
+ .prepare = uni_reader_prepare,
++ .probe = sti_uniperiph_dai_probe,
+ .trigger = uni_reader_trigger,
+ .hw_params = sti_uniperiph_dai_hw_params,
+ .set_fmt = sti_uniperiph_dai_set_fmt,
+diff --git a/sound/usb/line6/driver.c b/sound/usb/line6/driver.c
+index f4437015d43a7..9df49a880b750 100644
+--- a/sound/usb/line6/driver.c
++++ b/sound/usb/line6/driver.c
+@@ -286,12 +286,14 @@ static void line6_data_received(struct urb *urb)
+ {
+ struct usb_line6 *line6 = (struct usb_line6 *)urb->context;
+ struct midi_buffer *mb = &line6->line6midi->midibuf_in;
++ unsigned long flags;
+ int done;
+
+ if (urb->status == -ESHUTDOWN)
+ return;
+
+ if (line6->properties->capabilities & LINE6_CAP_CONTROL_MIDI) {
++ spin_lock_irqsave(&line6->line6midi->lock, flags);
+ done =
+ line6_midibuf_write(mb, urb->transfer_buffer, urb->actual_length);
+
+@@ -300,12 +302,15 @@ static void line6_data_received(struct urb *urb)
+ dev_dbg(line6->ifcdev, "%d %d buffer overflow - message skipped\n",
+ done, urb->actual_length);
+ }
++ spin_unlock_irqrestore(&line6->line6midi->lock, flags);
+
+ for (;;) {
++ spin_lock_irqsave(&line6->line6midi->lock, flags);
+ done =
+ line6_midibuf_read(mb, line6->buffer_message,
+ LINE6_MIDI_MESSAGE_MAXLEN,
+ LINE6_MIDIBUF_READ_RX);
++ spin_unlock_irqrestore(&line6->line6midi->lock, flags);
+
+ if (done <= 0)
+ break;
+diff --git a/sound/usb/quirks-table.h b/sound/usb/quirks-table.h
+index 73abc38a54006..f13a8d63a019a 100644
+--- a/sound/usb/quirks-table.h
++++ b/sound/usb/quirks-table.h
+@@ -2594,6 +2594,10 @@ YAMAHA_DEVICE(0x7010, "UB99"),
+ }
+ },
+
++/* Stanton ScratchAmp */
++{ USB_DEVICE(0x103d, 0x0100) },
++{ USB_DEVICE(0x103d, 0x0101) },
++
+ /* Novation EMS devices */
+ {
+ USB_DEVICE_VENDOR_SPEC(0x1235, 0x0001),
+diff --git a/tools/testing/selftests/bpf/prog_tests/send_signal.c b/tools/testing/selftests/bpf/prog_tests/send_signal.c
+index 920aee41bd58c..6cc69900b3106 100644
+--- a/tools/testing/selftests/bpf/prog_tests/send_signal.c
++++ b/tools/testing/selftests/bpf/prog_tests/send_signal.c
+@@ -156,7 +156,8 @@ static void test_send_signal_tracepoint(bool signal_thread)
+ static void test_send_signal_perf(bool signal_thread)
+ {
+ struct perf_event_attr attr = {
+- .sample_period = 1,
++ .freq = 1,
++ .sample_freq = 1000,
+ .type = PERF_TYPE_SOFTWARE,
+ .config = PERF_COUNT_SW_CPU_CLOCK,
+ };
+diff --git a/tools/testing/selftests/devices/ksft.py b/tools/testing/selftests/devices/ksft.py
+index cd89fb2bc10e7..bf215790a89d7 100644
+--- a/tools/testing/selftests/devices/ksft.py
++++ b/tools/testing/selftests/devices/ksft.py
+@@ -70,7 +70,7 @@ def test_result(condition, description=""):
+
+
+ def finished():
+- if ksft_cnt["pass"] == ksft_num_tests:
++ if ksft_cnt["pass"] + ksft_cnt["skip"] == ksft_num_tests:
+ exit_code = KSFT_PASS
+ else:
+ exit_code = KSFT_FAIL
+diff --git a/tools/testing/selftests/mm/Makefile b/tools/testing/selftests/mm/Makefile
+index 3b49bc3d0a3b2..478cd26f62fdd 100644
+--- a/tools/testing/selftests/mm/Makefile
++++ b/tools/testing/selftests/mm/Makefile
+@@ -106,7 +106,7 @@ endif
+
+ endif
+
+-ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64))
++ifneq (,$(filter $(ARCH),arm64 ia64 mips64 parisc64 powerpc riscv64 s390x sparc64 x86_64 s390))
+ TEST_GEN_FILES += va_high_addr_switch
+ TEST_GEN_FILES += virtual_address_range
+ TEST_GEN_FILES += write_to_hugetlbfs
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+index 7043984b7e74a..a3293043c85dd 100755
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+@@ -1415,18 +1415,28 @@ chk_add_nr()
+ local add_nr=$1
+ local echo_nr=$2
+ local port_nr=${3:-0}
+- local syn_nr=${4:-$port_nr}
+- local syn_ack_nr=${5:-$port_nr}
+- local ack_nr=${6:-$port_nr}
+- local mis_syn_nr=${7:-0}
+- local mis_ack_nr=${8:-0}
++ local ns_invert=${4:-""}
++ local syn_nr=$port_nr
++ local syn_ack_nr=$port_nr
++ local ack_nr=$port_nr
++ local mis_syn_nr=0
++ local mis_ack_nr=0
++ local ns_tx=$ns1
++ local ns_rx=$ns2
++ local extra_msg=""
+ local count
+ local timeout
+
+- timeout=$(ip netns exec $ns1 sysctl -n net.mptcp.add_addr_timeout)
++ if [[ $ns_invert = "invert" ]]; then
++ ns_tx=$ns2
++ ns_rx=$ns1
++ extra_msg="invert"
++ fi
++
++ timeout=$(ip netns exec ${ns_tx} sysctl -n net.mptcp.add_addr_timeout)
+
+ print_check "add"
+- count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtAddAddr")
++ count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtAddAddr")
+ if [ -z "$count" ]; then
+ print_skip
+ # if the test configured a short timeout tolerate greater then expected
+@@ -1438,7 +1448,7 @@ chk_add_nr()
+ fi
+
+ print_check "echo"
+- count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtEchoAdd")
++ count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtEchoAdd")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$echo_nr" ]; then
+@@ -1449,7 +1459,7 @@ chk_add_nr()
+
+ if [ $port_nr -gt 0 ]; then
+ print_check "pt"
+- count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtPortAdd")
++ count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtPortAdd")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$port_nr" ]; then
+@@ -1459,7 +1469,7 @@ chk_add_nr()
+ fi
+
+ print_check "syn"
+- count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortSynRx")
++ count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortSynRx")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$syn_nr" ]; then
+@@ -1470,7 +1480,7 @@ chk_add_nr()
+ fi
+
+ print_check "synack"
+- count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinPortSynAckRx")
++ count=$(mptcp_lib_get_counter ${ns_rx} "MPTcpExtMPJoinPortSynAckRx")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$syn_ack_nr" ]; then
+@@ -1481,7 +1491,7 @@ chk_add_nr()
+ fi
+
+ print_check "ack"
+- count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinPortAckRx")
++ count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMPJoinPortAckRx")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$ack_nr" ]; then
+@@ -1492,7 +1502,7 @@ chk_add_nr()
+ fi
+
+ print_check "syn"
+- count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortSynRx")
++ count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortSynRx")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$mis_syn_nr" ]; then
+@@ -1503,7 +1513,7 @@ chk_add_nr()
+ fi
+
+ print_check "ack"
+- count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMismatchPortAckRx")
++ count=$(mptcp_lib_get_counter ${ns_tx} "MPTcpExtMismatchPortAckRx")
+ if [ -z "$count" ]; then
+ print_skip
+ elif [ "$count" != "$mis_ack_nr" ]; then
+@@ -1513,6 +1523,8 @@ chk_add_nr()
+ print_ok
+ fi
+ fi
++
++ print_info "$extra_msg"
+ }
+
+ chk_add_tx_nr()
+@@ -1977,6 +1989,21 @@ signal_address_tests()
+ chk_add_nr 1 1
+ fi
+
++ # uncommon: subflow and signal flags on the same endpoint
++ # or because the user wrongly picked both, but still expects the client
++ # to create additional subflows
++ if reset "subflow and signal together"; then
++ pm_nl_set_limits $ns1 0 2
++ pm_nl_set_limits $ns2 0 2
++ pm_nl_add_endpoint $ns2 10.0.3.2 flags signal,subflow
++ run_tests $ns1 $ns2 10.0.1.1
++ chk_join_nr 1 1 1
++ chk_add_nr 1 1 0 invert # only initiated by ns2
++ chk_add_nr 0 0 0 # none initiated by ns1
++ chk_rst_nr 0 0 invert # no RST sent by the client
++ chk_rst_nr 0 0 # no RST sent by the server
++ fi
++
+ # accept and use add_addr with additional subflows
+ if reset "multiple subflows and signal"; then
+ pm_nl_set_limits $ns1 0 3
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-11 13:27 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-11 13:27 UTC (permalink / raw
To: gentoo-commits
commit: e04d2b24f04bf9588f97a3d1cb94143daf632b49
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sun Aug 11 13:27:27 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sun Aug 11 13:27:27 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=e04d2b24
Linux patch 6.10.4
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1003_linux-6.10.4.patch | 7592 +++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 7596 insertions(+)
diff --git a/0000_README b/0000_README
index 180f4b70..8befc23c 100644
--- a/0000_README
+++ b/0000_README
@@ -55,6 +55,10 @@ Patch: 1002_linux-6.10.3.patch
From: https://www.kernel.org
Desc: Linux 6.10.3
+Patch: 1003_linux-6.10.4.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.4
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1003_linux-6.10.4.patch b/1003_linux-6.10.4.patch
new file mode 100644
index 00000000..a0fa4b2f
--- /dev/null
+++ b/1003_linux-6.10.4.patch
@@ -0,0 +1,7592 @@
+diff --git a/Documentation/admin-guide/mm/transhuge.rst b/Documentation/admin-guide/mm/transhuge.rst
+index d414d3f5592a8..1f901de208bca 100644
+--- a/Documentation/admin-guide/mm/transhuge.rst
++++ b/Documentation/admin-guide/mm/transhuge.rst
+@@ -202,12 +202,11 @@ PMD-mappable transparent hugepage::
+
+ cat /sys/kernel/mm/transparent_hugepage/hpage_pmd_size
+
+-khugepaged will be automatically started when one or more hugepage
+-sizes are enabled (either by directly setting "always" or "madvise",
+-or by setting "inherit" while the top-level enabled is set to "always"
+-or "madvise"), and it'll be automatically shutdown when the last
+-hugepage size is disabled (either by directly setting "never", or by
+-setting "inherit" while the top-level enabled is set to "never").
++khugepaged will be automatically started when PMD-sized THP is enabled
++(either of the per-size anon control or the top-level control are set
++to "always" or "madvise"), and it'll be automatically shutdown when
++PMD-sized THP is disabled (when both the per-size anon control and the
++top-level control are "never")
+
+ Khugepaged controls
+ -------------------
+diff --git a/Documentation/netlink/specs/ethtool.yaml b/Documentation/netlink/specs/ethtool.yaml
+index 4510e8d1adcb8..238145c31835e 100644
+--- a/Documentation/netlink/specs/ethtool.yaml
++++ b/Documentation/netlink/specs/ethtool.yaml
+@@ -1634,6 +1634,7 @@ operations:
+ request:
+ attributes:
+ - header
++ - context
+ reply:
+ attributes:
+ - header
+@@ -1642,7 +1643,6 @@ operations:
+ - indir
+ - hkey
+ - input_xfrm
+- dump: *rss-get-op
+ -
+ name: plca-get-cfg
+ doc: Get PLCA params.
+diff --git a/Documentation/networking/ethtool-netlink.rst b/Documentation/networking/ethtool-netlink.rst
+index 160bfb0ae8bae..0d8c487be3993 100644
+--- a/Documentation/networking/ethtool-netlink.rst
++++ b/Documentation/networking/ethtool-netlink.rst
+@@ -1800,6 +1800,7 @@ Kernel response contents:
+
+ ===================================== ====== ==========================
+ ``ETHTOOL_A_RSS_HEADER`` nested reply header
++ ``ETHTOOL_A_RSS_CONTEXT`` u32 context number
+ ``ETHTOOL_A_RSS_HFUNC`` u32 RSS hash func
+ ``ETHTOOL_A_RSS_INDIR`` binary Indir table bytes
+ ``ETHTOOL_A_RSS_HKEY`` binary Hash key bytes
+diff --git a/Makefile b/Makefile
+index c0af6d8aeb05f..aec5cc0babf8c 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 3
++SUBLEVEL = 4
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm/kernel/perf_callchain.c b/arch/arm/kernel/perf_callchain.c
+index 7147edbe56c67..1d230ac9d0eb5 100644
+--- a/arch/arm/kernel/perf_callchain.c
++++ b/arch/arm/kernel/perf_callchain.c
+@@ -85,8 +85,7 @@ static bool
+ callchain_trace(void *data, unsigned long pc)
+ {
+ struct perf_callchain_entry_ctx *entry = data;
+- perf_callchain_store(entry, pc);
+- return true;
++ return perf_callchain_store(entry, pc) == 0;
+ }
+
+ void
+diff --git a/arch/arm/mm/proc.c b/arch/arm/mm/proc.c
+index bdbbf65d1b366..2027845efefb6 100644
+--- a/arch/arm/mm/proc.c
++++ b/arch/arm/mm/proc.c
+@@ -17,7 +17,7 @@ void cpu_arm7tdmi_proc_init(void);
+ __ADDRESSABLE(cpu_arm7tdmi_proc_init);
+ void cpu_arm7tdmi_proc_fin(void);
+ __ADDRESSABLE(cpu_arm7tdmi_proc_fin);
+-void cpu_arm7tdmi_reset(void);
++void cpu_arm7tdmi_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm7tdmi_reset);
+ int cpu_arm7tdmi_do_idle(void);
+ __ADDRESSABLE(cpu_arm7tdmi_do_idle);
+@@ -32,7 +32,7 @@ void cpu_arm720_proc_init(void);
+ __ADDRESSABLE(cpu_arm720_proc_init);
+ void cpu_arm720_proc_fin(void);
+ __ADDRESSABLE(cpu_arm720_proc_fin);
+-void cpu_arm720_reset(void);
++void cpu_arm720_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm720_reset);
+ int cpu_arm720_do_idle(void);
+ __ADDRESSABLE(cpu_arm720_do_idle);
+@@ -49,7 +49,7 @@ void cpu_arm740_proc_init(void);
+ __ADDRESSABLE(cpu_arm740_proc_init);
+ void cpu_arm740_proc_fin(void);
+ __ADDRESSABLE(cpu_arm740_proc_fin);
+-void cpu_arm740_reset(void);
++void cpu_arm740_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm740_reset);
+ int cpu_arm740_do_idle(void);
+ __ADDRESSABLE(cpu_arm740_do_idle);
+@@ -64,7 +64,7 @@ void cpu_arm9tdmi_proc_init(void);
+ __ADDRESSABLE(cpu_arm9tdmi_proc_init);
+ void cpu_arm9tdmi_proc_fin(void);
+ __ADDRESSABLE(cpu_arm9tdmi_proc_fin);
+-void cpu_arm9tdmi_reset(void);
++void cpu_arm9tdmi_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm9tdmi_reset);
+ int cpu_arm9tdmi_do_idle(void);
+ __ADDRESSABLE(cpu_arm9tdmi_do_idle);
+@@ -79,7 +79,7 @@ void cpu_arm920_proc_init(void);
+ __ADDRESSABLE(cpu_arm920_proc_init);
+ void cpu_arm920_proc_fin(void);
+ __ADDRESSABLE(cpu_arm920_proc_fin);
+-void cpu_arm920_reset(void);
++void cpu_arm920_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm920_reset);
+ int cpu_arm920_do_idle(void);
+ __ADDRESSABLE(cpu_arm920_do_idle);
+@@ -102,7 +102,7 @@ void cpu_arm922_proc_init(void);
+ __ADDRESSABLE(cpu_arm922_proc_init);
+ void cpu_arm922_proc_fin(void);
+ __ADDRESSABLE(cpu_arm922_proc_fin);
+-void cpu_arm922_reset(void);
++void cpu_arm922_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm922_reset);
+ int cpu_arm922_do_idle(void);
+ __ADDRESSABLE(cpu_arm922_do_idle);
+@@ -119,7 +119,7 @@ void cpu_arm925_proc_init(void);
+ __ADDRESSABLE(cpu_arm925_proc_init);
+ void cpu_arm925_proc_fin(void);
+ __ADDRESSABLE(cpu_arm925_proc_fin);
+-void cpu_arm925_reset(void);
++void cpu_arm925_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm925_reset);
+ int cpu_arm925_do_idle(void);
+ __ADDRESSABLE(cpu_arm925_do_idle);
+@@ -159,7 +159,7 @@ void cpu_arm940_proc_init(void);
+ __ADDRESSABLE(cpu_arm940_proc_init);
+ void cpu_arm940_proc_fin(void);
+ __ADDRESSABLE(cpu_arm940_proc_fin);
+-void cpu_arm940_reset(void);
++void cpu_arm940_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm940_reset);
+ int cpu_arm940_do_idle(void);
+ __ADDRESSABLE(cpu_arm940_do_idle);
+@@ -174,7 +174,7 @@ void cpu_arm946_proc_init(void);
+ __ADDRESSABLE(cpu_arm946_proc_init);
+ void cpu_arm946_proc_fin(void);
+ __ADDRESSABLE(cpu_arm946_proc_fin);
+-void cpu_arm946_reset(void);
++void cpu_arm946_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_arm946_reset);
+ int cpu_arm946_do_idle(void);
+ __ADDRESSABLE(cpu_arm946_do_idle);
+@@ -429,7 +429,7 @@ void cpu_v7_proc_init(void);
+ __ADDRESSABLE(cpu_v7_proc_init);
+ void cpu_v7_proc_fin(void);
+ __ADDRESSABLE(cpu_v7_proc_fin);
+-void cpu_v7_reset(void);
++void cpu_v7_reset(unsigned long addr, bool hvc);
+ __ADDRESSABLE(cpu_v7_reset);
+ int cpu_v7_do_idle(void);
+ __ADDRESSABLE(cpu_v7_do_idle);
+diff --git a/arch/arm64/include/asm/jump_label.h b/arch/arm64/include/asm/jump_label.h
+index 4e753908b8018..a0a5bbae7229e 100644
+--- a/arch/arm64/include/asm/jump_label.h
++++ b/arch/arm64/include/asm/jump_label.h
+@@ -13,6 +13,7 @@
+ #include <linux/types.h>
+ #include <asm/insn.h>
+
++#define HAVE_JUMP_LABEL_BATCH
+ #define JUMP_LABEL_NOP_SIZE AARCH64_INSN_SIZE
+
+ #define JUMP_TABLE_ENTRY(key, label) \
+diff --git a/arch/arm64/kernel/jump_label.c b/arch/arm64/kernel/jump_label.c
+index faf88ec9c48e8..f63ea915d6ad2 100644
+--- a/arch/arm64/kernel/jump_label.c
++++ b/arch/arm64/kernel/jump_label.c
+@@ -7,11 +7,12 @@
+ */
+ #include <linux/kernel.h>
+ #include <linux/jump_label.h>
++#include <linux/smp.h>
+ #include <asm/insn.h>
+ #include <asm/patching.h>
+
+-void arch_jump_label_transform(struct jump_entry *entry,
+- enum jump_label_type type)
++bool arch_jump_label_transform_queue(struct jump_entry *entry,
++ enum jump_label_type type)
+ {
+ void *addr = (void *)jump_entry_code(entry);
+ u32 insn;
+@@ -25,4 +26,10 @@ void arch_jump_label_transform(struct jump_entry *entry,
+ }
+
+ aarch64_insn_patch_text_nosync(addr, insn);
++ return true;
++}
++
++void arch_jump_label_transform_apply(void)
++{
++ kick_all_cpus_sync();
+ }
+diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+index c0be84a6e81fd..cc7747c5f21f3 100644
+--- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
++++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+@@ -99,8 +99,8 @@ liointc1: interrupt-controller@1fe11440 {
+ rtc0: rtc@1fe07800 {
+ compatible = "loongson,ls2k1000-rtc";
+ reg = <0 0x1fe07800 0 0x78>;
+- interrupt-parent = <&liointc0>;
+- interrupts = <60 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-parent = <&liointc1>;
++ interrupts = <8 IRQ_TYPE_LEVEL_HIGH>;
+ };
+
+ uart0: serial@1fe00000 {
+@@ -108,7 +108,7 @@ uart0: serial@1fe00000 {
+ reg = <0 0x1fe00000 0 0x8>;
+ clock-frequency = <125000000>;
+ interrupt-parent = <&liointc0>;
+- interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+ no-loopback-test;
+ };
+
+@@ -117,7 +117,6 @@ pci@1a000000 {
+ device_type = "pci";
+ #address-cells = <3>;
+ #size-cells = <2>;
+- #interrupt-cells = <2>;
+
+ reg = <0 0x1a000000 0 0x02000000>,
+ <0xfe 0x00000000 0 0x20000000>;
+@@ -132,8 +131,8 @@ gmac@3,0 {
+ "pciclass0c03";
+
+ reg = <0x1800 0x0 0x0 0x0 0x0>;
+- interrupts = <12 IRQ_TYPE_LEVEL_LOW>,
+- <13 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <12 IRQ_TYPE_LEVEL_HIGH>,
++ <13 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
+ interrupt-parent = <&liointc0>;
+ phy-mode = "rgmii-id";
+@@ -156,8 +155,8 @@ gmac@3,1 {
+ "loongson, pci-gmac";
+
+ reg = <0x1900 0x0 0x0 0x0 0x0>;
+- interrupts = <14 IRQ_TYPE_LEVEL_LOW>,
+- <15 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <14 IRQ_TYPE_LEVEL_HIGH>,
++ <15 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-names = "macirq", "eth_lpi";
+ interrupt-parent = <&liointc0>;
+ phy-mode = "rgmii-id";
+@@ -179,7 +178,7 @@ ehci@4,1 {
+ "pciclass0c03";
+
+ reg = <0x2100 0x0 0x0 0x0 0x0>;
+- interrupts = <18 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <18 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ };
+
+@@ -190,7 +189,7 @@ ohci@4,2 {
+ "pciclass0c03";
+
+ reg = <0x2200 0x0 0x0 0x0 0x0>;
+- interrupts = <19 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ };
+
+@@ -201,97 +200,121 @@ sata@8,0 {
+ "pciclass0106";
+
+ reg = <0x4000 0x0 0x0 0x0 0x0>;
+- interrupts = <19 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <19 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc0>;
+ };
+
+- pci_bridge@9,0 {
++ pcie@9,0 {
+ compatible = "pci0014,7a19.0",
+ "pci0014,7a19",
+ "pciclass060400",
+ "pciclass0604";
+
+ reg = <0x4800 0x0 0x0 0x0 0x0>;
++ #address-cells = <3>;
++ #size-cells = <2>;
++ device_type = "pci";
+ #interrupt-cells = <1>;
+- interrupts = <0 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <0 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ interrupt-map-mask = <0 0 0 0>;
+- interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-map = <0 0 0 0 &liointc1 0 IRQ_TYPE_LEVEL_HIGH>;
++ ranges;
+ external-facing;
+ };
+
+- pci_bridge@a,0 {
++ pcie@a,0 {
+ compatible = "pci0014,7a09.0",
+ "pci0014,7a09",
+ "pciclass060400",
+ "pciclass0604";
+
+ reg = <0x5000 0x0 0x0 0x0 0x0>;
++ #address-cells = <3>;
++ #size-cells = <2>;
++ device_type = "pci";
+ #interrupt-cells = <1>;
+- interrupts = <1 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <1 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ interrupt-map-mask = <0 0 0 0>;
+- interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-map = <0 0 0 0 &liointc1 1 IRQ_TYPE_LEVEL_HIGH>;
++ ranges;
+ external-facing;
+ };
+
+- pci_bridge@b,0 {
++ pcie@b,0 {
+ compatible = "pci0014,7a09.0",
+ "pci0014,7a09",
+ "pciclass060400",
+ "pciclass0604";
+
+ reg = <0x5800 0x0 0x0 0x0 0x0>;
++ #address-cells = <3>;
++ #size-cells = <2>;
++ device_type = "pci";
+ #interrupt-cells = <1>;
+- interrupts = <2 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <2 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ interrupt-map-mask = <0 0 0 0>;
+- interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-map = <0 0 0 0 &liointc1 2 IRQ_TYPE_LEVEL_HIGH>;
++ ranges;
+ external-facing;
+ };
+
+- pci_bridge@c,0 {
++ pcie@c,0 {
+ compatible = "pci0014,7a09.0",
+ "pci0014,7a09",
+ "pciclass060400",
+ "pciclass0604";
+
+ reg = <0x6000 0x0 0x0 0x0 0x0>;
++ #address-cells = <3>;
++ #size-cells = <2>;
++ device_type = "pci";
+ #interrupt-cells = <1>;
+- interrupts = <3 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <3 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ interrupt-map-mask = <0 0 0 0>;
+- interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-map = <0 0 0 0 &liointc1 3 IRQ_TYPE_LEVEL_HIGH>;
++ ranges;
+ external-facing;
+ };
+
+- pci_bridge@d,0 {
++ pcie@d,0 {
+ compatible = "pci0014,7a19.0",
+ "pci0014,7a19",
+ "pciclass060400",
+ "pciclass0604";
+
+ reg = <0x6800 0x0 0x0 0x0 0x0>;
++ #address-cells = <3>;
++ #size-cells = <2>;
++ device_type = "pci";
+ #interrupt-cells = <1>;
+- interrupts = <4 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <4 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ interrupt-map-mask = <0 0 0 0>;
+- interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-map = <0 0 0 0 &liointc1 4 IRQ_TYPE_LEVEL_HIGH>;
++ ranges;
+ external-facing;
+ };
+
+- pci_bridge@e,0 {
++ pcie@e,0 {
+ compatible = "pci0014,7a09.0",
+ "pci0014,7a09",
+ "pciclass060400",
+ "pciclass0604";
+
+ reg = <0x7000 0x0 0x0 0x0 0x0>;
++ #address-cells = <3>;
++ #size-cells = <2>;
++ device_type = "pci";
+ #interrupt-cells = <1>;
+- interrupts = <5 IRQ_TYPE_LEVEL_LOW>;
++ interrupts = <5 IRQ_TYPE_LEVEL_HIGH>;
+ interrupt-parent = <&liointc1>;
+ interrupt-map-mask = <0 0 0 0>;
+- interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-map = <0 0 0 0 &liointc1 5 IRQ_TYPE_LEVEL_HIGH>;
++ ranges;
+ external-facing;
+ };
+
+diff --git a/arch/riscv/kernel/sbi-ipi.c b/arch/riscv/kernel/sbi-ipi.c
+index 1026e22955ccc..0cc5559c08d8f 100644
+--- a/arch/riscv/kernel/sbi-ipi.c
++++ b/arch/riscv/kernel/sbi-ipi.c
+@@ -71,7 +71,7 @@ void __init sbi_ipi_init(void)
+ * the masking/unmasking of virtual IPIs is done
+ * via generic IPI-Mux
+ */
+- cpuhp_setup_state(CPUHP_AP_ONLINE_DYN,
++ cpuhp_setup_state(CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING,
+ "irqchip/sbi-ipi:starting",
+ sbi_ipi_starting_cpu, NULL);
+
+diff --git a/arch/riscv/mm/fault.c b/arch/riscv/mm/fault.c
+index 5224f37338022..a9f2b4af8f3f1 100644
+--- a/arch/riscv/mm/fault.c
++++ b/arch/riscv/mm/fault.c
+@@ -61,26 +61,27 @@ static inline void no_context(struct pt_regs *regs, unsigned long addr)
+
+ static inline void mm_fault_error(struct pt_regs *regs, unsigned long addr, vm_fault_t fault)
+ {
++ if (!user_mode(regs)) {
++ no_context(regs, addr);
++ return;
++ }
++
+ if (fault & VM_FAULT_OOM) {
+ /*
+ * We ran out of memory, call the OOM killer, and return the userspace
+ * (which will retry the fault, or kill us if we got oom-killed).
+ */
+- if (!user_mode(regs)) {
+- no_context(regs, addr);
+- return;
+- }
+ pagefault_out_of_memory();
+ return;
+ } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) {
+ /* Kernel mode? Handle exceptions or die */
+- if (!user_mode(regs)) {
+- no_context(regs, addr);
+- return;
+- }
+ do_trap(regs, SIGBUS, BUS_ADRERR, addr);
+ return;
++ } else if (fault & VM_FAULT_SIGSEGV) {
++ do_trap(regs, SIGSEGV, SEGV_MAPERR, addr);
++ return;
+ }
++
+ BUG();
+ }
+
+diff --git a/arch/riscv/mm/init.c b/arch/riscv/mm/init.c
+index e3405e4b99af5..7e25606f858aa 100644
+--- a/arch/riscv/mm/init.c
++++ b/arch/riscv/mm/init.c
+@@ -233,8 +233,6 @@ static void __init setup_bootmem(void)
+ */
+ memblock_reserve(vmlinux_start, vmlinux_end - vmlinux_start);
+
+- phys_ram_end = memblock_end_of_DRAM();
+-
+ /*
+ * Make sure we align the start of the memory on a PMD boundary so that
+ * at worst, we map the linear mapping with PMD mappings.
+@@ -249,6 +247,16 @@ static void __init setup_bootmem(void)
+ if (IS_ENABLED(CONFIG_64BIT) && IS_ENABLED(CONFIG_MMU))
+ kernel_map.va_pa_offset = PAGE_OFFSET - phys_ram_base;
+
++ /*
++ * The size of the linear page mapping may restrict the amount of
++ * usable RAM.
++ */
++ if (IS_ENABLED(CONFIG_64BIT)) {
++ max_mapped_addr = __pa(PAGE_OFFSET) + KERN_VIRT_SIZE;
++ memblock_cap_memory_range(phys_ram_base,
++ max_mapped_addr - phys_ram_base);
++ }
++
+ /*
+ * Reserve physical address space that would be mapped to virtual
+ * addresses greater than (void *)(-PAGE_SIZE) because:
+@@ -265,6 +273,7 @@ static void __init setup_bootmem(void)
+ memblock_reserve(max_mapped_addr, (phys_addr_t)-max_mapped_addr);
+ }
+
++ phys_ram_end = memblock_end_of_DRAM();
+ min_low_pfn = PFN_UP(phys_ram_base);
+ max_low_pfn = max_pfn = PFN_DOWN(phys_ram_end);
+ high_memory = (void *)(__va(PFN_PHYS(max_low_pfn)));
+@@ -1289,8 +1298,6 @@ static void __init create_linear_mapping_page_table(void)
+ if (start <= __pa(PAGE_OFFSET) &&
+ __pa(PAGE_OFFSET) < end)
+ start = __pa(PAGE_OFFSET);
+- if (end >= __pa(PAGE_OFFSET) + memory_limit)
+- end = __pa(PAGE_OFFSET) + memory_limit;
+
+ create_linear_mapping_range(start, end, 0);
+ }
+diff --git a/arch/riscv/purgatory/entry.S b/arch/riscv/purgatory/entry.S
+index 5bcf3af903daa..0e6ca6d5ae4b4 100644
+--- a/arch/riscv/purgatory/entry.S
++++ b/arch/riscv/purgatory/entry.S
+@@ -7,6 +7,7 @@
+ * Author: Li Zhengyu (lizhengyu3@huawei.com)
+ *
+ */
++#include <asm/asm.h>
+ #include <linux/linkage.h>
+
+ .text
+@@ -34,6 +35,7 @@ SYM_CODE_END(purgatory_start)
+
+ .data
+
++.align LGREG
+ SYM_DATA(riscv_kernel_entry, .quad 0)
+
+ .end
+diff --git a/arch/s390/kernel/fpu.c b/arch/s390/kernel/fpu.c
+index fa90bbdc5ef94..6f2e87920288a 100644
+--- a/arch/s390/kernel/fpu.c
++++ b/arch/s390/kernel/fpu.c
+@@ -113,7 +113,7 @@ void load_fpu_state(struct fpu *state, int flags)
+ int mask;
+
+ if (flags & KERNEL_FPC)
+- fpu_lfpc(&state->fpc);
++ fpu_lfpc_safe(&state->fpc);
+ if (!cpu_has_vx()) {
+ if (flags & KERNEL_VXR_V0V7)
+ load_fp_regs_vx(state->vxrs);
+diff --git a/arch/s390/mm/dump_pagetables.c b/arch/s390/mm/dump_pagetables.c
+index ffd07ed7b4af8..9d0805d6dc1b2 100644
+--- a/arch/s390/mm/dump_pagetables.c
++++ b/arch/s390/mm/dump_pagetables.c
+@@ -20,8 +20,8 @@ struct addr_marker {
+ };
+
+ enum address_markers_idx {
+- IDENTITY_BEFORE_NR = 0,
+- IDENTITY_BEFORE_END_NR,
++ LOWCORE_START_NR = 0,
++ LOWCORE_END_NR,
+ AMODE31_START_NR,
+ AMODE31_END_NR,
+ KERNEL_START_NR,
+@@ -30,8 +30,8 @@ enum address_markers_idx {
+ KFENCE_START_NR,
+ KFENCE_END_NR,
+ #endif
+- IDENTITY_AFTER_NR,
+- IDENTITY_AFTER_END_NR,
++ IDENTITY_START_NR,
++ IDENTITY_END_NR,
+ VMEMMAP_NR,
+ VMEMMAP_END_NR,
+ VMALLOC_NR,
+@@ -49,8 +49,10 @@ enum address_markers_idx {
+ };
+
+ static struct addr_marker address_markers[] = {
+- [IDENTITY_BEFORE_NR] = {0, "Identity Mapping Start"},
+- [IDENTITY_BEFORE_END_NR] = {(unsigned long)_stext, "Identity Mapping End"},
++ [LOWCORE_START_NR] = {0, "Lowcore Start"},
++ [LOWCORE_END_NR] = {0, "Lowcore End"},
++ [IDENTITY_START_NR] = {0, "Identity Mapping Start"},
++ [IDENTITY_END_NR] = {0, "Identity Mapping End"},
+ [AMODE31_START_NR] = {0, "Amode31 Area Start"},
+ [AMODE31_END_NR] = {0, "Amode31 Area End"},
+ [KERNEL_START_NR] = {(unsigned long)_stext, "Kernel Image Start"},
+@@ -59,8 +61,6 @@ static struct addr_marker address_markers[] = {
+ [KFENCE_START_NR] = {0, "KFence Pool Start"},
+ [KFENCE_END_NR] = {0, "KFence Pool End"},
+ #endif
+- [IDENTITY_AFTER_NR] = {(unsigned long)_end, "Identity Mapping Start"},
+- [IDENTITY_AFTER_END_NR] = {0, "Identity Mapping End"},
+ [VMEMMAP_NR] = {0, "vmemmap Area Start"},
+ [VMEMMAP_END_NR] = {0, "vmemmap Area End"},
+ [VMALLOC_NR] = {0, "vmalloc Area Start"},
+@@ -290,7 +290,10 @@ static int pt_dump_init(void)
+ */
+ max_addr = (S390_lowcore.kernel_asce.val & _REGION_ENTRY_TYPE_MASK) >> 2;
+ max_addr = 1UL << (max_addr * 11 + 31);
+- address_markers[IDENTITY_AFTER_END_NR].start_address = ident_map_size;
++ address_markers[LOWCORE_START_NR].start_address = 0;
++ address_markers[LOWCORE_END_NR].start_address = sizeof(struct lowcore);
++ address_markers[IDENTITY_START_NR].start_address = __identity_base;
++ address_markers[IDENTITY_END_NR].start_address = __identity_base + ident_map_size;
+ address_markers[AMODE31_START_NR].start_address = (unsigned long)__samode31;
+ address_markers[AMODE31_END_NR].start_address = (unsigned long)__eamode31;
+ address_markers[MODULES_NR].start_address = MODULES_VADDR;
+diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
+index 38c1b1f1deaad..101a21fe9c213 100644
+--- a/arch/x86/events/intel/core.c
++++ b/arch/x86/events/intel/core.c
+@@ -4698,8 +4698,8 @@ static void intel_pmu_check_extra_regs(struct extra_reg *extra_regs);
+ static inline bool intel_pmu_broken_perf_cap(void)
+ {
+ /* The Perf Metric (Bit 15) is always cleared */
+- if ((boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE) ||
+- (boot_cpu_data.x86_model == INTEL_FAM6_METEORLAKE_L))
++ if (boot_cpu_data.x86_vfm == INTEL_METEORLAKE ||
++ boot_cpu_data.x86_vfm == INTEL_METEORLAKE_L)
+ return true;
+
+ return false;
+@@ -6238,19 +6238,19 @@ __init int intel_pmu_init(void)
+ /*
+ * Install the hw-cache-events table:
+ */
+- switch (boot_cpu_data.x86_model) {
+- case INTEL_FAM6_CORE_YONAH:
++ switch (boot_cpu_data.x86_vfm) {
++ case INTEL_CORE_YONAH:
+ pr_cont("Core events, ");
+ name = "core";
+ break;
+
+- case INTEL_FAM6_CORE2_MEROM:
++ case INTEL_CORE2_MEROM:
+ x86_add_quirk(intel_clovertown_quirk);
+ fallthrough;
+
+- case INTEL_FAM6_CORE2_MEROM_L:
+- case INTEL_FAM6_CORE2_PENRYN:
+- case INTEL_FAM6_CORE2_DUNNINGTON:
++ case INTEL_CORE2_MEROM_L:
++ case INTEL_CORE2_PENRYN:
++ case INTEL_CORE2_DUNNINGTON:
+ memcpy(hw_cache_event_ids, core2_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+@@ -6262,9 +6262,9 @@ __init int intel_pmu_init(void)
+ name = "core2";
+ break;
+
+- case INTEL_FAM6_NEHALEM:
+- case INTEL_FAM6_NEHALEM_EP:
+- case INTEL_FAM6_NEHALEM_EX:
++ case INTEL_NEHALEM:
++ case INTEL_NEHALEM_EP:
++ case INTEL_NEHALEM_EX:
+ memcpy(hw_cache_event_ids, nehalem_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+@@ -6296,11 +6296,11 @@ __init int intel_pmu_init(void)
+ name = "nehalem";
+ break;
+
+- case INTEL_FAM6_ATOM_BONNELL:
+- case INTEL_FAM6_ATOM_BONNELL_MID:
+- case INTEL_FAM6_ATOM_SALTWELL:
+- case INTEL_FAM6_ATOM_SALTWELL_MID:
+- case INTEL_FAM6_ATOM_SALTWELL_TABLET:
++ case INTEL_ATOM_BONNELL:
++ case INTEL_ATOM_BONNELL_MID:
++ case INTEL_ATOM_SALTWELL:
++ case INTEL_ATOM_SALTWELL_MID:
++ case INTEL_ATOM_SALTWELL_TABLET:
+ memcpy(hw_cache_event_ids, atom_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+
+@@ -6313,11 +6313,11 @@ __init int intel_pmu_init(void)
+ name = "bonnell";
+ break;
+
+- case INTEL_FAM6_ATOM_SILVERMONT:
+- case INTEL_FAM6_ATOM_SILVERMONT_D:
+- case INTEL_FAM6_ATOM_SILVERMONT_MID:
+- case INTEL_FAM6_ATOM_AIRMONT:
+- case INTEL_FAM6_ATOM_AIRMONT_MID:
++ case INTEL_ATOM_SILVERMONT:
++ case INTEL_ATOM_SILVERMONT_D:
++ case INTEL_ATOM_SILVERMONT_MID:
++ case INTEL_ATOM_AIRMONT:
++ case INTEL_ATOM_AIRMONT_MID:
+ memcpy(hw_cache_event_ids, slm_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, slm_hw_cache_extra_regs,
+@@ -6335,8 +6335,8 @@ __init int intel_pmu_init(void)
+ name = "silvermont";
+ break;
+
+- case INTEL_FAM6_ATOM_GOLDMONT:
+- case INTEL_FAM6_ATOM_GOLDMONT_D:
++ case INTEL_ATOM_GOLDMONT:
++ case INTEL_ATOM_GOLDMONT_D:
+ memcpy(hw_cache_event_ids, glm_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, glm_hw_cache_extra_regs,
+@@ -6362,7 +6362,7 @@ __init int intel_pmu_init(void)
+ name = "goldmont";
+ break;
+
+- case INTEL_FAM6_ATOM_GOLDMONT_PLUS:
++ case INTEL_ATOM_GOLDMONT_PLUS:
+ memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, glp_hw_cache_extra_regs,
+@@ -6391,9 +6391,9 @@ __init int intel_pmu_init(void)
+ name = "goldmont_plus";
+ break;
+
+- case INTEL_FAM6_ATOM_TREMONT_D:
+- case INTEL_FAM6_ATOM_TREMONT:
+- case INTEL_FAM6_ATOM_TREMONT_L:
++ case INTEL_ATOM_TREMONT_D:
++ case INTEL_ATOM_TREMONT:
++ case INTEL_ATOM_TREMONT_L:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, glp_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+@@ -6420,7 +6420,7 @@ __init int intel_pmu_init(void)
+ name = "Tremont";
+ break;
+
+- case INTEL_FAM6_ATOM_GRACEMONT:
++ case INTEL_ATOM_GRACEMONT:
+ intel_pmu_init_grt(NULL);
+ intel_pmu_pebs_data_source_grt();
+ x86_pmu.pebs_latency_data = adl_latency_data_small;
+@@ -6432,8 +6432,8 @@ __init int intel_pmu_init(void)
+ name = "gracemont";
+ break;
+
+- case INTEL_FAM6_ATOM_CRESTMONT:
+- case INTEL_FAM6_ATOM_CRESTMONT_X:
++ case INTEL_ATOM_CRESTMONT:
++ case INTEL_ATOM_CRESTMONT_X:
+ intel_pmu_init_grt(NULL);
+ x86_pmu.extra_regs = intel_cmt_extra_regs;
+ intel_pmu_pebs_data_source_cmt();
+@@ -6446,9 +6446,9 @@ __init int intel_pmu_init(void)
+ name = "crestmont";
+ break;
+
+- case INTEL_FAM6_WESTMERE:
+- case INTEL_FAM6_WESTMERE_EP:
+- case INTEL_FAM6_WESTMERE_EX:
++ case INTEL_WESTMERE:
++ case INTEL_WESTMERE_EP:
++ case INTEL_WESTMERE_EX:
+ memcpy(hw_cache_event_ids, westmere_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, nehalem_hw_cache_extra_regs,
+@@ -6477,8 +6477,8 @@ __init int intel_pmu_init(void)
+ name = "westmere";
+ break;
+
+- case INTEL_FAM6_SANDYBRIDGE:
+- case INTEL_FAM6_SANDYBRIDGE_X:
++ case INTEL_SANDYBRIDGE:
++ case INTEL_SANDYBRIDGE_X:
+ x86_add_quirk(intel_sandybridge_quirk);
+ x86_add_quirk(intel_ht_bug);
+ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+@@ -6491,7 +6491,7 @@ __init int intel_pmu_init(void)
+ x86_pmu.event_constraints = intel_snb_event_constraints;
+ x86_pmu.pebs_constraints = intel_snb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_snb;
+- if (boot_cpu_data.x86_model == INTEL_FAM6_SANDYBRIDGE_X)
++ if (boot_cpu_data.x86_vfm == INTEL_SANDYBRIDGE_X)
+ x86_pmu.extra_regs = intel_snbep_extra_regs;
+ else
+ x86_pmu.extra_regs = intel_snb_extra_regs;
+@@ -6517,8 +6517,8 @@ __init int intel_pmu_init(void)
+ name = "sandybridge";
+ break;
+
+- case INTEL_FAM6_IVYBRIDGE:
+- case INTEL_FAM6_IVYBRIDGE_X:
++ case INTEL_IVYBRIDGE:
++ case INTEL_IVYBRIDGE_X:
+ x86_add_quirk(intel_ht_bug);
+ memcpy(hw_cache_event_ids, snb_hw_cache_event_ids,
+ sizeof(hw_cache_event_ids));
+@@ -6534,7 +6534,7 @@ __init int intel_pmu_init(void)
+ x86_pmu.pebs_constraints = intel_ivb_pebs_event_constraints;
+ x86_pmu.pebs_aliases = intel_pebs_aliases_ivb;
+ x86_pmu.pebs_prec_dist = true;
+- if (boot_cpu_data.x86_model == INTEL_FAM6_IVYBRIDGE_X)
++ if (boot_cpu_data.x86_vfm == INTEL_IVYBRIDGE_X)
+ x86_pmu.extra_regs = intel_snbep_extra_regs;
+ else
+ x86_pmu.extra_regs = intel_snb_extra_regs;
+@@ -6556,10 +6556,10 @@ __init int intel_pmu_init(void)
+ break;
+
+
+- case INTEL_FAM6_HASWELL:
+- case INTEL_FAM6_HASWELL_X:
+- case INTEL_FAM6_HASWELL_L:
+- case INTEL_FAM6_HASWELL_G:
++ case INTEL_HASWELL:
++ case INTEL_HASWELL_X:
++ case INTEL_HASWELL_L:
++ case INTEL_HASWELL_G:
+ x86_add_quirk(intel_ht_bug);
+ x86_add_quirk(intel_pebs_isolation_quirk);
+ x86_pmu.late_ack = true;
+@@ -6589,10 +6589,10 @@ __init int intel_pmu_init(void)
+ name = "haswell";
+ break;
+
+- case INTEL_FAM6_BROADWELL:
+- case INTEL_FAM6_BROADWELL_D:
+- case INTEL_FAM6_BROADWELL_G:
+- case INTEL_FAM6_BROADWELL_X:
++ case INTEL_BROADWELL:
++ case INTEL_BROADWELL_D:
++ case INTEL_BROADWELL_G:
++ case INTEL_BROADWELL_X:
+ x86_add_quirk(intel_pebs_isolation_quirk);
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, hsw_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+@@ -6631,8 +6631,8 @@ __init int intel_pmu_init(void)
+ name = "broadwell";
+ break;
+
+- case INTEL_FAM6_XEON_PHI_KNL:
+- case INTEL_FAM6_XEON_PHI_KNM:
++ case INTEL_XEON_PHI_KNL:
++ case INTEL_XEON_PHI_KNM:
+ memcpy(hw_cache_event_ids,
+ slm_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs,
+@@ -6651,15 +6651,15 @@ __init int intel_pmu_init(void)
+ name = "knights-landing";
+ break;
+
+- case INTEL_FAM6_SKYLAKE_X:
++ case INTEL_SKYLAKE_X:
+ pmem = true;
+ fallthrough;
+- case INTEL_FAM6_SKYLAKE_L:
+- case INTEL_FAM6_SKYLAKE:
+- case INTEL_FAM6_KABYLAKE_L:
+- case INTEL_FAM6_KABYLAKE:
+- case INTEL_FAM6_COMETLAKE_L:
+- case INTEL_FAM6_COMETLAKE:
++ case INTEL_SKYLAKE_L:
++ case INTEL_SKYLAKE:
++ case INTEL_KABYLAKE_L:
++ case INTEL_KABYLAKE:
++ case INTEL_COMETLAKE_L:
++ case INTEL_COMETLAKE:
+ x86_add_quirk(intel_pebs_isolation_quirk);
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+@@ -6708,16 +6708,16 @@ __init int intel_pmu_init(void)
+ name = "skylake";
+ break;
+
+- case INTEL_FAM6_ICELAKE_X:
+- case INTEL_FAM6_ICELAKE_D:
++ case INTEL_ICELAKE_X:
++ case INTEL_ICELAKE_D:
+ x86_pmu.pebs_ept = 1;
+ pmem = true;
+ fallthrough;
+- case INTEL_FAM6_ICELAKE_L:
+- case INTEL_FAM6_ICELAKE:
+- case INTEL_FAM6_TIGERLAKE_L:
+- case INTEL_FAM6_TIGERLAKE:
+- case INTEL_FAM6_ROCKETLAKE:
++ case INTEL_ICELAKE_L:
++ case INTEL_ICELAKE:
++ case INTEL_TIGERLAKE_L:
++ case INTEL_TIGERLAKE:
++ case INTEL_ROCKETLAKE:
+ x86_pmu.late_ack = true;
+ memcpy(hw_cache_event_ids, skl_hw_cache_event_ids, sizeof(hw_cache_event_ids));
+ memcpy(hw_cache_extra_regs, skl_hw_cache_extra_regs, sizeof(hw_cache_extra_regs));
+@@ -6752,16 +6752,22 @@ __init int intel_pmu_init(void)
+ name = "icelake";
+ break;
+
+- case INTEL_FAM6_SAPPHIRERAPIDS_X:
+- case INTEL_FAM6_EMERALDRAPIDS_X:
++ case INTEL_SAPPHIRERAPIDS_X:
++ case INTEL_EMERALDRAPIDS_X:
+ x86_pmu.flags |= PMU_FL_MEM_LOADS_AUX;
+ x86_pmu.extra_regs = intel_glc_extra_regs;
+- fallthrough;
+- case INTEL_FAM6_GRANITERAPIDS_X:
+- case INTEL_FAM6_GRANITERAPIDS_D:
++ pr_cont("Sapphire Rapids events, ");
++ name = "sapphire_rapids";
++ goto glc_common;
++
++ case INTEL_GRANITERAPIDS_X:
++ case INTEL_GRANITERAPIDS_D:
++ x86_pmu.extra_regs = intel_rwc_extra_regs;
++ pr_cont("Granite Rapids events, ");
++ name = "granite_rapids";
++
++ glc_common:
+ intel_pmu_init_glc(NULL);
+- if (!x86_pmu.extra_regs)
+- x86_pmu.extra_regs = intel_rwc_extra_regs;
+ x86_pmu.pebs_ept = 1;
+ x86_pmu.hw_config = hsw_hw_config;
+ x86_pmu.get_event_constraints = glc_get_event_constraints;
+@@ -6772,15 +6778,13 @@ __init int intel_pmu_init(void)
+ td_attr = glc_td_events_attrs;
+ tsx_attr = glc_tsx_events_attrs;
+ intel_pmu_pebs_data_source_skl(true);
+- pr_cont("Sapphire Rapids events, ");
+- name = "sapphire_rapids";
+ break;
+
+- case INTEL_FAM6_ALDERLAKE:
+- case INTEL_FAM6_ALDERLAKE_L:
+- case INTEL_FAM6_RAPTORLAKE:
+- case INTEL_FAM6_RAPTORLAKE_P:
+- case INTEL_FAM6_RAPTORLAKE_S:
++ case INTEL_ALDERLAKE:
++ case INTEL_ALDERLAKE_L:
++ case INTEL_RAPTORLAKE:
++ case INTEL_RAPTORLAKE_P:
++ case INTEL_RAPTORLAKE_S:
+ /*
+ * Alder Lake has 2 types of CPU, core and atom.
+ *
+@@ -6838,8 +6842,8 @@ __init int intel_pmu_init(void)
+ name = "alderlake_hybrid";
+ break;
+
+- case INTEL_FAM6_METEORLAKE:
+- case INTEL_FAM6_METEORLAKE_L:
++ case INTEL_METEORLAKE:
++ case INTEL_METEORLAKE_L:
+ intel_pmu_init_hybrid(hybrid_big_small);
+
+ x86_pmu.pebs_latency_data = mtl_latency_data_small;
+diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
+index 7ecc67deecb09..93900c37349c1 100644
+--- a/drivers/bluetooth/btintel.c
++++ b/drivers/bluetooth/btintel.c
+@@ -3012,6 +3012,9 @@ static int btintel_setup_combined(struct hci_dev *hdev)
+ btintel_set_dsm_reset_method(hdev, &ver_tlv);
+
+ err = btintel_bootloader_setup_tlv(hdev, &ver_tlv);
++ if (err)
++ goto exit_error;
++
+ btintel_register_devcoredump_support(hdev);
+ btintel_print_fseq_info(hdev);
+ break;
+diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
+index 359b68adafc1b..79628ff837e6f 100644
+--- a/drivers/gpu/drm/Kconfig
++++ b/drivers/gpu/drm/Kconfig
+@@ -253,6 +253,7 @@ config DRM_EXEC
+ config DRM_GPUVM
+ tristate
+ depends on DRM
++ select DRM_EXEC
+ help
+ GPU-VM representation providing helpers to manage a GPUs virtual
+ address space
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+index ec888fc6ead8d..13eb2bc69e342 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_cs.c
+@@ -1763,7 +1763,7 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
+ struct ttm_operation_ctx ctx = { false, false };
+ struct amdgpu_vm *vm = &fpriv->vm;
+ struct amdgpu_bo_va_mapping *mapping;
+- int r;
++ int i, r;
+
+ addr /= AMDGPU_GPU_PAGE_SIZE;
+
+@@ -1778,13 +1778,13 @@ int amdgpu_cs_find_mapping(struct amdgpu_cs_parser *parser,
+ if (dma_resv_locking_ctx((*bo)->tbo.base.resv) != &parser->exec.ticket)
+ return -EINVAL;
+
+- if (!((*bo)->flags & AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS)) {
+- (*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
+- amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
+- r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
+- if (r)
+- return r;
+- }
++ (*bo)->flags |= AMDGPU_GEM_CREATE_VRAM_CONTIGUOUS;
++ amdgpu_bo_placement_from_domain(*bo, (*bo)->allowed_domains);
++ for (i = 0; i < (*bo)->placement.num_placement; i++)
++ (*bo)->placements[i].flags |= TTM_PL_FLAG_CONTIGUOUS;
++ r = ttm_bo_validate(&(*bo)->tbo, &(*bo)->placement, &ctx);
++ if (r)
++ return r;
+
+ return amdgpu_ttm_alloc_gart(&(*bo)->tbo);
+ }
+diff --git a/drivers/gpu/drm/ast/ast_dp.c b/drivers/gpu/drm/ast/ast_dp.c
+index 1e9259416980e..e6c7f0d64e995 100644
+--- a/drivers/gpu/drm/ast/ast_dp.c
++++ b/drivers/gpu/drm/ast/ast_dp.c
+@@ -158,7 +158,14 @@ void ast_dp_launch(struct drm_device *dev)
+ ASTDP_HOST_EDID_READ_DONE);
+ }
+
++bool ast_dp_power_is_on(struct ast_device *ast)
++{
++ u8 vgacre3;
++
++ vgacre3 = ast_get_index_reg(ast, AST_IO_VGACRI, 0xe3);
+
++ return !(vgacre3 & AST_DP_PHY_SLEEP);
++}
+
+ void ast_dp_power_on_off(struct drm_device *dev, bool on)
+ {
+diff --git a/drivers/gpu/drm/ast/ast_drv.c b/drivers/gpu/drm/ast/ast_drv.c
+index f8c49ba68e789..af2368f6f00f4 100644
+--- a/drivers/gpu/drm/ast/ast_drv.c
++++ b/drivers/gpu/drm/ast/ast_drv.c
+@@ -391,6 +391,11 @@ static int ast_drm_freeze(struct drm_device *dev)
+
+ static int ast_drm_thaw(struct drm_device *dev)
+ {
++ struct ast_device *ast = to_ast_device(dev);
++
++ ast_enable_vga(ast->ioregs);
++ ast_open_key(ast->ioregs);
++ ast_enable_mmio(dev->dev, ast->ioregs);
+ ast_post_gpu(dev);
+
+ return drm_mode_config_helper_resume(dev);
+diff --git a/drivers/gpu/drm/ast/ast_drv.h b/drivers/gpu/drm/ast/ast_drv.h
+index ba3d86973995f..47bab5596c16e 100644
+--- a/drivers/gpu/drm/ast/ast_drv.h
++++ b/drivers/gpu/drm/ast/ast_drv.h
+@@ -472,6 +472,7 @@ void ast_init_3rdtx(struct drm_device *dev);
+ bool ast_astdp_is_connected(struct ast_device *ast);
+ int ast_astdp_read_edid(struct drm_device *dev, u8 *ediddata);
+ void ast_dp_launch(struct drm_device *dev);
++bool ast_dp_power_is_on(struct ast_device *ast);
+ void ast_dp_power_on_off(struct drm_device *dev, bool no);
+ void ast_dp_set_on_off(struct drm_device *dev, bool no);
+ void ast_dp_set_mode(struct drm_crtc *crtc, struct ast_vbios_mode_info *vbios_mode);
+diff --git a/drivers/gpu/drm/ast/ast_mode.c b/drivers/gpu/drm/ast/ast_mode.c
+index 6695af70768f9..88f830a7d285a 100644
+--- a/drivers/gpu/drm/ast/ast_mode.c
++++ b/drivers/gpu/drm/ast/ast_mode.c
+@@ -28,6 +28,7 @@
+ * Authors: Dave Airlie <airlied@redhat.com>
+ */
+
++#include <linux/delay.h>
+ #include <linux/export.h>
+ #include <linux/pci.h>
+
+@@ -1641,11 +1642,35 @@ static int ast_astdp_connector_helper_detect_ctx(struct drm_connector *connector
+ struct drm_modeset_acquire_ctx *ctx,
+ bool force)
+ {
++ struct drm_device *dev = connector->dev;
+ struct ast_device *ast = to_ast_device(connector->dev);
++ enum drm_connector_status status = connector_status_disconnected;
++ struct drm_connector_state *connector_state = connector->state;
++ bool is_active = false;
++
++ mutex_lock(&ast->modeset_lock);
++
++ if (connector_state && connector_state->crtc) {
++ struct drm_crtc_state *crtc_state = connector_state->crtc->state;
++
++ if (crtc_state && crtc_state->active)
++ is_active = true;
++ }
++
++ if (!is_active && !ast_dp_power_is_on(ast)) {
++ ast_dp_power_on_off(dev, true);
++ msleep(50);
++ }
+
+ if (ast_astdp_is_connected(ast))
+- return connector_status_connected;
+- return connector_status_disconnected;
++ status = connector_status_connected;
++
++ if (!is_active && status == connector_status_disconnected)
++ ast_dp_power_on_off(dev, false);
++
++ mutex_unlock(&ast->modeset_lock);
++
++ return status;
+ }
+
+ static const struct drm_connector_helper_funcs ast_astdp_connector_helper_funcs = {
+diff --git a/drivers/gpu/drm/drm_atomic_uapi.c b/drivers/gpu/drm/drm_atomic_uapi.c
+index fc16fddee5c59..02b1235c6d619 100644
+--- a/drivers/gpu/drm/drm_atomic_uapi.c
++++ b/drivers/gpu/drm/drm_atomic_uapi.c
+@@ -1066,7 +1066,10 @@ int drm_atomic_set_property(struct drm_atomic_state *state,
+ break;
+ }
+
+- if (async_flip && prop != config->prop_fb_id) {
++ if (async_flip &&
++ prop != config->prop_fb_id &&
++ prop != config->prop_in_fence_fd &&
++ prop != config->prop_fb_damage_clips) {
+ ret = drm_atomic_plane_get_property(plane, plane_state,
+ prop, &old_val);
+ ret = drm_atomic_check_prop_changes(ret, old_val, prop_value, prop);
+diff --git a/drivers/gpu/drm/drm_client.c b/drivers/gpu/drm/drm_client.c
+index 2803ac111bbd8..bfedcbf516dbe 100644
+--- a/drivers/gpu/drm/drm_client.c
++++ b/drivers/gpu/drm/drm_client.c
+@@ -355,7 +355,7 @@ int drm_client_buffer_vmap_local(struct drm_client_buffer *buffer,
+
+ err_drm_gem_vmap_unlocked:
+ drm_gem_unlock(gem);
+- return 0;
++ return ret;
+ }
+ EXPORT_SYMBOL(drm_client_buffer_vmap_local);
+
+diff --git a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+index 90998b037349d..292d163036b12 100644
+--- a/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
++++ b/drivers/gpu/drm/i915/display/intel_dpll_mgr.c
+@@ -1658,7 +1658,7 @@ static void skl_wrpll_params_populate(struct skl_wrpll_params *params,
+ }
+
+ static int
+-skl_ddi_calculate_wrpll(int clock /* in Hz */,
++skl_ddi_calculate_wrpll(int clock,
+ int ref_clock,
+ struct skl_wrpll_params *wrpll_params)
+ {
+@@ -1683,7 +1683,7 @@ skl_ddi_calculate_wrpll(int clock /* in Hz */,
+ };
+ unsigned int dco, d, i;
+ unsigned int p0, p1, p2;
+- u64 afe_clock = clock * 5; /* AFE Clock is 5x Pixel clock */
++ u64 afe_clock = (u64)clock * 1000 * 5; /* AFE Clock is 5x Pixel clock, in Hz */
+
+ for (d = 0; d < ARRAY_SIZE(dividers); d++) {
+ for (dco = 0; dco < ARRAY_SIZE(dco_central_freq); dco++) {
+@@ -1808,7 +1808,7 @@ static int skl_ddi_hdmi_pll_dividers(struct intel_crtc_state *crtc_state)
+ struct skl_wrpll_params wrpll_params = {};
+ int ret;
+
+- ret = skl_ddi_calculate_wrpll(crtc_state->port_clock * 1000,
++ ret = skl_ddi_calculate_wrpll(crtc_state->port_clock,
+ i915->display.dpll.ref_clks.nssc, &wrpll_params);
+ if (ret)
+ return ret;
+diff --git a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h
+index a568a457e5326..f590d7f48ba74 100644
+--- a/drivers/gpu/drm/i915/display/intel_hdcp_regs.h
++++ b/drivers/gpu/drm/i915/display/intel_hdcp_regs.h
+@@ -251,7 +251,7 @@
+ #define HDCP2_STREAM_STATUS(dev_priv, trans, port) \
+ (TRANS_HDCP(dev_priv) ? \
+ TRANS_HDCP2_STREAM_STATUS(trans) : \
+- PIPE_HDCP2_STREAM_STATUS(pipe))
++ PIPE_HDCP2_STREAM_STATUS(port))
+
+ #define _PORTA_HDCP2_AUTH_STREAM 0x66F00
+ #define _PORTB_HDCP2_AUTH_STREAM 0x66F04
+diff --git a/drivers/gpu/drm/i915/i915_perf.c b/drivers/gpu/drm/i915/i915_perf.c
+index 0b1cd4c7a525f..025a79fe5920e 100644
+--- a/drivers/gpu/drm/i915/i915_perf.c
++++ b/drivers/gpu/drm/i915/i915_perf.c
+@@ -2748,26 +2748,6 @@ oa_configure_all_contexts(struct i915_perf_stream *stream,
+ return 0;
+ }
+
+-static int
+-gen12_configure_all_contexts(struct i915_perf_stream *stream,
+- const struct i915_oa_config *oa_config,
+- struct i915_active *active)
+-{
+- struct flex regs[] = {
+- {
+- GEN8_R_PWR_CLK_STATE(RENDER_RING_BASE),
+- CTX_R_PWR_CLK_STATE,
+- },
+- };
+-
+- if (stream->engine->class != RENDER_CLASS)
+- return 0;
+-
+- return oa_configure_all_contexts(stream,
+- regs, ARRAY_SIZE(regs),
+- active);
+-}
+-
+ static int
+ lrc_configure_all_contexts(struct i915_perf_stream *stream,
+ const struct i915_oa_config *oa_config,
+@@ -2874,7 +2854,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
+ {
+ struct drm_i915_private *i915 = stream->perf->i915;
+ struct intel_uncore *uncore = stream->uncore;
+- struct i915_oa_config *oa_config = stream->oa_config;
+ bool periodic = stream->periodic;
+ u32 period_exponent = stream->period_exponent;
+ u32 sqcnt1;
+@@ -2918,15 +2897,6 @@ gen12_enable_metric_set(struct i915_perf_stream *stream,
+
+ intel_uncore_rmw(uncore, GEN12_SQCNT1, 0, sqcnt1);
+
+- /*
+- * Update all contexts prior writing the mux configurations as we need
+- * to make sure all slices/subslices are ON before writing to NOA
+- * registers.
+- */
+- ret = gen12_configure_all_contexts(stream, oa_config, active);
+- if (ret)
+- return ret;
+-
+ /*
+ * For Gen12, performance counters are context
+ * saved/restored. Only enable it for the context that
+@@ -2980,9 +2950,6 @@ static void gen12_disable_metric_set(struct i915_perf_stream *stream)
+ _MASKED_BIT_DISABLE(GEN12_DISABLE_DOP_GATING));
+ }
+
+- /* Reset all contexts' slices/subslices configurations. */
+- gen12_configure_all_contexts(stream, NULL, NULL);
+-
+ /* disable the context save/restore or OAR counters */
+ if (stream->ctx)
+ gen12_configure_oar_context(stream, NULL);
+diff --git a/drivers/gpu/drm/nouveau/nouveau_prime.c b/drivers/gpu/drm/nouveau/nouveau_prime.c
+index b58ab595faf82..cd95446d68511 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_prime.c
++++ b/drivers/gpu/drm/nouveau/nouveau_prime.c
+@@ -64,7 +64,8 @@ struct drm_gem_object *nouveau_gem_prime_import_sg_table(struct drm_device *dev,
+ * to the caller, instead of a normal nouveau_bo ttm reference. */
+ ret = drm_gem_object_init(dev, &nvbo->bo.base, size);
+ if (ret) {
+- nouveau_bo_ref(NULL, &nvbo);
++ drm_gem_object_release(&nvbo->bo.base);
++ kfree(nvbo);
+ obj = ERR_PTR(-ENOMEM);
+ goto unlock;
+ }
+diff --git a/drivers/gpu/drm/nouveau/nouveau_uvmm.c b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+index ee02cd833c5e4..84a36fe7c37dd 100644
+--- a/drivers/gpu/drm/nouveau/nouveau_uvmm.c
++++ b/drivers/gpu/drm/nouveau/nouveau_uvmm.c
+@@ -1803,6 +1803,7 @@ nouveau_uvmm_bo_validate(struct drm_gpuvm_bo *vm_bo, struct drm_exec *exec)
+ {
+ struct nouveau_bo *nvbo = nouveau_gem_object(vm_bo->obj);
+
++ nouveau_bo_placement_set(nvbo, nvbo->valid_domains, 0);
+ return nouveau_bo_validate(nvbo, true, false);
+ }
+
+diff --git a/drivers/gpu/drm/v3d/v3d_drv.h b/drivers/gpu/drm/v3d/v3d_drv.h
+index a2c516fe6d796..1d535abedc57b 100644
+--- a/drivers/gpu/drm/v3d/v3d_drv.h
++++ b/drivers/gpu/drm/v3d/v3d_drv.h
+@@ -556,6 +556,10 @@ void v3d_mmu_insert_ptes(struct v3d_bo *bo);
+ void v3d_mmu_remove_ptes(struct v3d_bo *bo);
+
+ /* v3d_sched.c */
++void v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info,
++ unsigned int count);
++void v3d_performance_query_info_free(struct v3d_performance_query_info *query_info,
++ unsigned int count);
+ void v3d_job_update_stats(struct v3d_job *job, enum v3d_queue queue);
+ int v3d_sched_init(struct v3d_dev *v3d);
+ void v3d_sched_fini(struct v3d_dev *v3d);
+diff --git a/drivers/gpu/drm/v3d/v3d_sched.c b/drivers/gpu/drm/v3d/v3d_sched.c
+index 7cd8c335cd9b7..30d5366d62883 100644
+--- a/drivers/gpu/drm/v3d/v3d_sched.c
++++ b/drivers/gpu/drm/v3d/v3d_sched.c
+@@ -73,24 +73,44 @@ v3d_sched_job_free(struct drm_sched_job *sched_job)
+ v3d_job_cleanup(job);
+ }
+
++void
++v3d_timestamp_query_info_free(struct v3d_timestamp_query_info *query_info,
++ unsigned int count)
++{
++ if (query_info->queries) {
++ unsigned int i;
++
++ for (i = 0; i < count; i++)
++ drm_syncobj_put(query_info->queries[i].syncobj);
++
++ kvfree(query_info->queries);
++ }
++}
++
++void
++v3d_performance_query_info_free(struct v3d_performance_query_info *query_info,
++ unsigned int count)
++{
++ if (query_info->queries) {
++ unsigned int i;
++
++ for (i = 0; i < count; i++)
++ drm_syncobj_put(query_info->queries[i].syncobj);
++
++ kvfree(query_info->queries);
++ }
++}
++
+ static void
+ v3d_cpu_job_free(struct drm_sched_job *sched_job)
+ {
+ struct v3d_cpu_job *job = to_cpu_job(sched_job);
+- struct v3d_timestamp_query_info *timestamp_query = &job->timestamp_query;
+- struct v3d_performance_query_info *performance_query = &job->performance_query;
+
+- if (timestamp_query->queries) {
+- for (int i = 0; i < timestamp_query->count; i++)
+- drm_syncobj_put(timestamp_query->queries[i].syncobj);
+- kvfree(timestamp_query->queries);
+- }
++ v3d_timestamp_query_info_free(&job->timestamp_query,
++ job->timestamp_query.count);
+
+- if (performance_query->queries) {
+- for (int i = 0; i < performance_query->count; i++)
+- drm_syncobj_put(performance_query->queries[i].syncobj);
+- kvfree(performance_query->queries);
+- }
++ v3d_performance_query_info_free(&job->performance_query,
++ job->performance_query.count);
+
+ v3d_job_cleanup(&job->base);
+ }
+diff --git a/drivers/gpu/drm/v3d/v3d_submit.c b/drivers/gpu/drm/v3d/v3d_submit.c
+index 88f63d526b223..4cdfabbf4964f 100644
+--- a/drivers/gpu/drm/v3d/v3d_submit.c
++++ b/drivers/gpu/drm/v3d/v3d_submit.c
+@@ -452,6 +452,8 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv,
+ {
+ u32 __user *offsets, *syncs;
+ struct drm_v3d_timestamp_query timestamp;
++ unsigned int i;
++ int err;
+
+ if (!job) {
+ DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
+@@ -480,26 +482,34 @@ v3d_get_cpu_timestamp_query_params(struct drm_file *file_priv,
+ offsets = u64_to_user_ptr(timestamp.offsets);
+ syncs = u64_to_user_ptr(timestamp.syncs);
+
+- for (int i = 0; i < timestamp.count; i++) {
++ for (i = 0; i < timestamp.count; i++) {
+ u32 offset, sync;
+
+ if (copy_from_user(&offset, offsets++, sizeof(offset))) {
+- kvfree(job->timestamp_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ job->timestamp_query.queries[i].offset = offset;
+
+ if (copy_from_user(&sync, syncs++, sizeof(sync))) {
+- kvfree(job->timestamp_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
++ if (!job->timestamp_query.queries[i].syncobj) {
++ err = -ENOENT;
++ goto error;
++ }
+ }
+ job->timestamp_query.count = timestamp.count;
+
+ return 0;
++
++error:
++ v3d_timestamp_query_info_free(&job->timestamp_query, i);
++ return err;
+ }
+
+ static int
+@@ -509,6 +519,8 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv,
+ {
+ u32 __user *syncs;
+ struct drm_v3d_reset_timestamp_query reset;
++ unsigned int i;
++ int err;
+
+ if (!job) {
+ DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
+@@ -533,21 +545,29 @@ v3d_get_cpu_reset_timestamp_params(struct drm_file *file_priv,
+
+ syncs = u64_to_user_ptr(reset.syncs);
+
+- for (int i = 0; i < reset.count; i++) {
++ for (i = 0; i < reset.count; i++) {
+ u32 sync;
+
+ job->timestamp_query.queries[i].offset = reset.offset + 8 * i;
+
+ if (copy_from_user(&sync, syncs++, sizeof(sync))) {
+- kvfree(job->timestamp_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
++ if (!job->timestamp_query.queries[i].syncobj) {
++ err = -ENOENT;
++ goto error;
++ }
+ }
+ job->timestamp_query.count = reset.count;
+
+ return 0;
++
++error:
++ v3d_timestamp_query_info_free(&job->timestamp_query, i);
++ return err;
+ }
+
+ /* Get data for the copy timestamp query results job submission. */
+@@ -558,7 +578,8 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv,
+ {
+ u32 __user *offsets, *syncs;
+ struct drm_v3d_copy_timestamp_query copy;
+- int i;
++ unsigned int i;
++ int err;
+
+ if (!job) {
+ DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
+@@ -591,18 +612,22 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv,
+ u32 offset, sync;
+
+ if (copy_from_user(&offset, offsets++, sizeof(offset))) {
+- kvfree(job->timestamp_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ job->timestamp_query.queries[i].offset = offset;
+
+ if (copy_from_user(&sync, syncs++, sizeof(sync))) {
+- kvfree(job->timestamp_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ job->timestamp_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
++ if (!job->timestamp_query.queries[i].syncobj) {
++ err = -ENOENT;
++ goto error;
++ }
+ }
+ job->timestamp_query.count = copy.count;
+
+@@ -613,6 +638,10 @@ v3d_get_cpu_copy_query_results_params(struct drm_file *file_priv,
+ job->copy.stride = copy.stride;
+
+ return 0;
++
++error:
++ v3d_timestamp_query_info_free(&job->timestamp_query, i);
++ return err;
+ }
+
+ static int
+@@ -623,6 +652,8 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv,
+ u32 __user *syncs;
+ u64 __user *kperfmon_ids;
+ struct drm_v3d_reset_performance_query reset;
++ unsigned int i, j;
++ int err;
+
+ if (!job) {
+ DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
+@@ -637,6 +668,9 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv,
+ if (copy_from_user(&reset, ext, sizeof(reset)))
+ return -EFAULT;
+
++ if (reset.nperfmons > V3D_MAX_PERFMONS)
++ return -EINVAL;
++
+ job->job_type = V3D_CPU_JOB_TYPE_RESET_PERFORMANCE_QUERY;
+
+ job->performance_query.queries = kvmalloc_array(reset.count,
+@@ -648,39 +682,47 @@ v3d_get_cpu_reset_performance_params(struct drm_file *file_priv,
+ syncs = u64_to_user_ptr(reset.syncs);
+ kperfmon_ids = u64_to_user_ptr(reset.kperfmon_ids);
+
+- for (int i = 0; i < reset.count; i++) {
++ for (i = 0; i < reset.count; i++) {
+ u32 sync;
+ u64 ids;
+ u32 __user *ids_pointer;
+ u32 id;
+
+ if (copy_from_user(&sync, syncs++, sizeof(sync))) {
+- kvfree(job->performance_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+- job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+-
+ if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) {
+- kvfree(job->performance_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ ids_pointer = u64_to_user_ptr(ids);
+
+- for (int j = 0; j < reset.nperfmons; j++) {
++ for (j = 0; j < reset.nperfmons; j++) {
+ if (copy_from_user(&id, ids_pointer++, sizeof(id))) {
+- kvfree(job->performance_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ job->performance_query.queries[i].kperfmon_ids[j] = id;
+ }
++
++ job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
++ if (!job->performance_query.queries[i].syncobj) {
++ err = -ENOENT;
++ goto error;
++ }
+ }
+ job->performance_query.count = reset.count;
+ job->performance_query.nperfmons = reset.nperfmons;
+
+ return 0;
++
++error:
++ v3d_performance_query_info_free(&job->performance_query, i);
++ return err;
+ }
+
+ static int
+@@ -691,6 +733,8 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
+ u32 __user *syncs;
+ u64 __user *kperfmon_ids;
+ struct drm_v3d_copy_performance_query copy;
++ unsigned int i, j;
++ int err;
+
+ if (!job) {
+ DRM_DEBUG("CPU job extension was attached to a GPU job.\n");
+@@ -708,6 +752,9 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
+ if (copy.pad)
+ return -EINVAL;
+
++ if (copy.nperfmons > V3D_MAX_PERFMONS)
++ return -EINVAL;
++
+ job->job_type = V3D_CPU_JOB_TYPE_COPY_PERFORMANCE_QUERY;
+
+ job->performance_query.queries = kvmalloc_array(copy.count,
+@@ -719,34 +766,38 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
+ syncs = u64_to_user_ptr(copy.syncs);
+ kperfmon_ids = u64_to_user_ptr(copy.kperfmon_ids);
+
+- for (int i = 0; i < copy.count; i++) {
++ for (i = 0; i < copy.count; i++) {
+ u32 sync;
+ u64 ids;
+ u32 __user *ids_pointer;
+ u32 id;
+
+ if (copy_from_user(&sync, syncs++, sizeof(sync))) {
+- kvfree(job->performance_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+- job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
+-
+ if (copy_from_user(&ids, kperfmon_ids++, sizeof(ids))) {
+- kvfree(job->performance_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ ids_pointer = u64_to_user_ptr(ids);
+
+- for (int j = 0; j < copy.nperfmons; j++) {
++ for (j = 0; j < copy.nperfmons; j++) {
+ if (copy_from_user(&id, ids_pointer++, sizeof(id))) {
+- kvfree(job->performance_query.queries);
+- return -EFAULT;
++ err = -EFAULT;
++ goto error;
+ }
+
+ job->performance_query.queries[i].kperfmon_ids[j] = id;
+ }
++
++ job->performance_query.queries[i].syncobj = drm_syncobj_find(file_priv, sync);
++ if (!job->performance_query.queries[i].syncobj) {
++ err = -ENOENT;
++ goto error;
++ }
+ }
+ job->performance_query.count = copy.count;
+ job->performance_query.nperfmons = copy.nperfmons;
+@@ -759,6 +810,10 @@ v3d_get_cpu_copy_performance_query_params(struct drm_file *file_priv,
+ job->copy.stride = copy.stride;
+
+ return 0;
++
++error:
++ v3d_performance_query_info_free(&job->performance_query, i);
++ return err;
+ }
+
+ /* Whenever userspace sets ioctl extensions, v3d_get_extensions parses data
+diff --git a/drivers/gpu/drm/virtio/virtgpu_submit.c b/drivers/gpu/drm/virtio/virtgpu_submit.c
+index 1c7c7f61a2228..7d34cf83f5f2b 100644
+--- a/drivers/gpu/drm/virtio/virtgpu_submit.c
++++ b/drivers/gpu/drm/virtio/virtgpu_submit.c
+@@ -48,7 +48,7 @@ struct virtio_gpu_submit {
+ static int virtio_gpu_do_fence_wait(struct virtio_gpu_submit *submit,
+ struct dma_fence *in_fence)
+ {
+- u32 context = submit->fence_ctx + submit->ring_idx;
++ u64 context = submit->fence_ctx + submit->ring_idx;
+
+ if (dma_fence_match_context(in_fence, context))
+ return 0;
+diff --git a/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
+index b0d87c5f58d8e..1ac3cb151b117 100644
+--- a/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
++++ b/drivers/gpu/drm/vmwgfx/vmw_surface_cache.h
+@@ -1,6 +1,8 @@
++/* SPDX-License-Identifier: GPL-2.0 OR MIT */
+ /**********************************************************
+- * Copyright 2021 VMware, Inc.
+- * SPDX-License-Identifier: GPL-2.0 OR MIT
++ *
++ * Copyright (c) 2021-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person
+ * obtaining a copy of this software and associated documentation
+@@ -31,6 +33,10 @@
+
+ #include <drm/vmwgfx_drm.h>
+
++#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) ((svga3d_flags) >> 32)
++#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \
++ ((svga3d_flags) & ((uint64_t)U32_MAX))
++
+ static inline u32 clamped_umul32(u32 a, u32 b)
+ {
+ uint64_t tmp = (uint64_t) a*b;
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+index 00144632c600e..f42ebc4a7c225 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.c
+@@ -1,8 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /**************************************************************************
+ *
+- * Copyright © 2011-2023 VMware, Inc., Palo Alto, CA., USA
+- * All Rights Reserved.
++ * Copyright (c) 2011-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -28,15 +28,39 @@
+
+ #include "vmwgfx_bo.h"
+ #include "vmwgfx_drv.h"
+-
++#include "vmwgfx_resource_priv.h"
+
+ #include <drm/ttm/ttm_placement.h>
+
+ static void vmw_bo_release(struct vmw_bo *vbo)
+ {
++ struct vmw_resource *res;
++
+ WARN_ON(vbo->tbo.base.funcs &&
+ kref_read(&vbo->tbo.base.refcount) != 0);
+ vmw_bo_unmap(vbo);
++
++ xa_destroy(&vbo->detached_resources);
++ WARN_ON(vbo->is_dumb && !vbo->dumb_surface);
++ if (vbo->is_dumb && vbo->dumb_surface) {
++ res = &vbo->dumb_surface->res;
++ WARN_ON(vbo != res->guest_memory_bo);
++ WARN_ON(!res->guest_memory_bo);
++ if (res->guest_memory_bo) {
++ /* Reserve and switch the backing mob. */
++ mutex_lock(&res->dev_priv->cmdbuf_mutex);
++ (void)vmw_resource_reserve(res, false, true);
++ vmw_resource_mob_detach(res);
++ if (res->coherent)
++ vmw_bo_dirty_release(res->guest_memory_bo);
++ res->guest_memory_bo = NULL;
++ res->guest_memory_offset = 0;
++ vmw_resource_unreserve(res, false, false, false, NULL,
++ 0);
++ mutex_unlock(&res->dev_priv->cmdbuf_mutex);
++ }
++ vmw_surface_unreference(&vbo->dumb_surface);
++ }
+ drm_gem_object_release(&vbo->tbo.base);
+ }
+
+@@ -325,6 +349,11 @@ void vmw_bo_pin_reserved(struct vmw_bo *vbo, bool pin)
+ *
+ */
+ void *vmw_bo_map_and_cache(struct vmw_bo *vbo)
++{
++ return vmw_bo_map_and_cache_size(vbo, vbo->tbo.base.size);
++}
++
++void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size)
+ {
+ struct ttm_buffer_object *bo = &vbo->tbo;
+ bool not_used;
+@@ -335,9 +364,10 @@ void *vmw_bo_map_and_cache(struct vmw_bo *vbo)
+ if (virtual)
+ return virtual;
+
+- ret = ttm_bo_kmap(bo, 0, PFN_UP(bo->base.size), &vbo->map);
++ ret = ttm_bo_kmap(bo, 0, PFN_UP(size), &vbo->map);
+ if (ret)
+- DRM_ERROR("Buffer object map failed: %d.\n", ret);
++ DRM_ERROR("Buffer object map failed: %d (size: bo = %zu, map = %zu).\n",
++ ret, bo->base.size, size);
+
+ return ttm_kmap_obj_virtual(&vbo->map, ¬_used);
+ }
+@@ -390,6 +420,7 @@ static int vmw_bo_init(struct vmw_private *dev_priv,
+ BUILD_BUG_ON(TTM_MAX_BO_PRIORITY <= 3);
+ vmw_bo->tbo.priority = 3;
+ vmw_bo->res_tree = RB_ROOT;
++ xa_init(&vmw_bo->detached_resources);
+
+ params->size = ALIGN(params->size, PAGE_SIZE);
+ drm_gem_private_object_init(vdev, &vmw_bo->tbo.base, params->size);
+@@ -654,52 +685,6 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+ dma_fence_put(&fence->base);
+ }
+
+-
+-/**
+- * vmw_dumb_create - Create a dumb kms buffer
+- *
+- * @file_priv: Pointer to a struct drm_file identifying the caller.
+- * @dev: Pointer to the drm device.
+- * @args: Pointer to a struct drm_mode_create_dumb structure
+- * Return: Zero on success, negative error code on failure.
+- *
+- * This is a driver callback for the core drm create_dumb functionality.
+- * Note that this is very similar to the vmw_bo_alloc ioctl, except
+- * that the arguments have a different format.
+- */
+-int vmw_dumb_create(struct drm_file *file_priv,
+- struct drm_device *dev,
+- struct drm_mode_create_dumb *args)
+-{
+- struct vmw_private *dev_priv = vmw_priv(dev);
+- struct vmw_bo *vbo;
+- int cpp = DIV_ROUND_UP(args->bpp, 8);
+- int ret;
+-
+- switch (cpp) {
+- case 1: /* DRM_FORMAT_C8 */
+- case 2: /* DRM_FORMAT_RGB565 */
+- case 4: /* DRM_FORMAT_XRGB8888 */
+- break;
+- default:
+- /*
+- * Dumb buffers don't allow anything else.
+- * This is tested via IGT's dumb_buffers
+- */
+- return -EINVAL;
+- }
+-
+- args->pitch = args->width * cpp;
+- args->size = ALIGN(args->pitch * args->height, PAGE_SIZE);
+-
+- ret = vmw_gem_object_create_with_handle(dev_priv, file_priv,
+- args->size, &args->handle,
+- &vbo);
+- /* drop reference from allocate - handle holds it now */
+- drm_gem_object_put(&vbo->tbo.base);
+- return ret;
+-}
+-
+ /**
+ * vmw_bo_swap_notify - swapout notify callback.
+ *
+@@ -853,3 +838,43 @@ void vmw_bo_placement_set_default_accelerated(struct vmw_bo *bo)
+
+ vmw_bo_placement_set(bo, domain, domain);
+ }
++
++void vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res)
++{
++ xa_store(&vbo->detached_resources, (unsigned long)res, res, GFP_KERNEL);
++}
++
++void vmw_bo_del_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res)
++{
++ xa_erase(&vbo->detached_resources, (unsigned long)res);
++}
++
++struct vmw_surface *vmw_bo_surface(struct vmw_bo *vbo)
++{
++ unsigned long index;
++ struct vmw_resource *res = NULL;
++ struct vmw_surface *surf = NULL;
++ struct rb_node *rb_itr = vbo->res_tree.rb_node;
++
++ if (vbo->is_dumb && vbo->dumb_surface) {
++ res = &vbo->dumb_surface->res;
++ goto out;
++ }
++
++ xa_for_each(&vbo->detached_resources, index, res) {
++ if (res->func->res_type == vmw_res_surface)
++ goto out;
++ }
++
++ for (rb_itr = rb_first(&vbo->res_tree); rb_itr;
++ rb_itr = rb_next(rb_itr)) {
++ res = rb_entry(rb_itr, struct vmw_resource, mob_node);
++ if (res->func->res_type == vmw_res_surface)
++ goto out;
++ }
++
++out:
++ if (res)
++ surf = vmw_res_to_srf(res);
++ return surf;
++}
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+index f349642e6190d..62b4342d5f7c5 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_bo.h
+@@ -1,7 +1,8 @@
+ /* SPDX-License-Identifier: GPL-2.0 OR MIT */
+ /**************************************************************************
+ *
+- * Copyright 2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2023-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -35,11 +36,13 @@
+
+ #include <linux/rbtree_types.h>
+ #include <linux/types.h>
++#include <linux/xarray.h>
+
+ struct vmw_bo_dirty;
+ struct vmw_fence_obj;
+ struct vmw_private;
+ struct vmw_resource;
++struct vmw_surface;
+
+ enum vmw_bo_domain {
+ VMW_BO_DOMAIN_SYS = BIT(0),
+@@ -85,11 +88,15 @@ struct vmw_bo {
+
+ struct rb_root res_tree;
+ u32 res_prios[TTM_MAX_BO_PRIORITY];
++ struct xarray detached_resources;
+
+ atomic_t cpu_writers;
+ /* Not ref-counted. Protected by binding_mutex */
+ struct vmw_resource *dx_query_ctx;
+ struct vmw_bo_dirty *dirty;
++
++ bool is_dumb;
++ struct vmw_surface *dumb_surface;
+ };
+
+ void vmw_bo_placement_set(struct vmw_bo *bo, u32 domain, u32 busy_domain);
+@@ -124,15 +131,21 @@ void vmw_bo_fence_single(struct ttm_buffer_object *bo,
+ struct vmw_fence_obj *fence);
+
+ void *vmw_bo_map_and_cache(struct vmw_bo *vbo);
++void *vmw_bo_map_and_cache_size(struct vmw_bo *vbo, size_t size);
+ void vmw_bo_unmap(struct vmw_bo *vbo);
+
+ void vmw_bo_move_notify(struct ttm_buffer_object *bo,
+ struct ttm_resource *mem);
+ void vmw_bo_swap_notify(struct ttm_buffer_object *bo);
+
++void vmw_bo_add_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res);
++void vmw_bo_del_detached_resource(struct vmw_bo *vbo, struct vmw_resource *res);
++struct vmw_surface *vmw_bo_surface(struct vmw_bo *vbo);
++
+ int vmw_user_bo_lookup(struct drm_file *filp,
+ u32 handle,
+ struct vmw_bo **out);
++
+ /**
+ * vmw_bo_adjust_prio - Adjust the buffer object eviction priority
+ * according to attached resources
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+index a1ce41e1c4684..32f50e5958097 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_drv.h
+@@ -1,7 +1,8 @@
+ /* SPDX-License-Identifier: GPL-2.0 OR MIT */
+ /**************************************************************************
+ *
+- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -762,6 +763,26 @@ extern int vmw_gmr_bind(struct vmw_private *dev_priv,
+ int gmr_id);
+ extern void vmw_gmr_unbind(struct vmw_private *dev_priv, int gmr_id);
+
++/**
++ * User handles
++ */
++struct vmw_user_object {
++ struct vmw_surface *surface;
++ struct vmw_bo *buffer;
++};
++
++int vmw_user_object_lookup(struct vmw_private *dev_priv, struct drm_file *filp,
++ u32 handle, struct vmw_user_object *uo);
++struct vmw_user_object *vmw_user_object_ref(struct vmw_user_object *uo);
++void vmw_user_object_unref(struct vmw_user_object *uo);
++bool vmw_user_object_is_null(struct vmw_user_object *uo);
++struct vmw_surface *vmw_user_object_surface(struct vmw_user_object *uo);
++struct vmw_bo *vmw_user_object_buffer(struct vmw_user_object *uo);
++void *vmw_user_object_map(struct vmw_user_object *uo);
++void *vmw_user_object_map_size(struct vmw_user_object *uo, size_t size);
++void vmw_user_object_unmap(struct vmw_user_object *uo);
++bool vmw_user_object_is_mapped(struct vmw_user_object *uo);
++
+ /**
+ * Resource utilities - vmwgfx_resource.c
+ */
+@@ -776,11 +797,6 @@ extern int vmw_resource_validate(struct vmw_resource *res, bool intr,
+ extern int vmw_resource_reserve(struct vmw_resource *res, bool interruptible,
+ bool no_backup);
+ extern bool vmw_resource_needs_backup(const struct vmw_resource *res);
+-extern int vmw_user_lookup_handle(struct vmw_private *dev_priv,
+- struct drm_file *filp,
+- uint32_t handle,
+- struct vmw_surface **out_surf,
+- struct vmw_bo **out_buf);
+ extern int vmw_user_resource_lookup_handle(
+ struct vmw_private *dev_priv,
+ struct ttm_object_file *tfile,
+@@ -1057,9 +1073,6 @@ int vmw_kms_suspend(struct drm_device *dev);
+ int vmw_kms_resume(struct drm_device *dev);
+ void vmw_kms_lost_device(struct drm_device *dev);
+
+-int vmw_dumb_create(struct drm_file *file_priv,
+- struct drm_device *dev,
+- struct drm_mode_create_dumb *args);
+ extern int vmw_resource_pin(struct vmw_resource *res, bool interruptible);
+ extern void vmw_resource_unpin(struct vmw_resource *res);
+ extern enum vmw_res_type vmw_res_type(const struct vmw_resource *res);
+@@ -1176,6 +1189,15 @@ extern int vmw_gb_surface_reference_ext_ioctl(struct drm_device *dev,
+ int vmw_gb_surface_define(struct vmw_private *dev_priv,
+ const struct vmw_surface_metadata *req,
+ struct vmw_surface **srf_out);
++struct vmw_surface *vmw_lookup_surface_for_buffer(struct vmw_private *vmw,
++ struct vmw_bo *bo,
++ u32 handle);
++u32 vmw_lookup_surface_handle_for_buffer(struct vmw_private *vmw,
++ struct vmw_bo *bo,
++ u32 handle);
++int vmw_dumb_create(struct drm_file *file_priv,
++ struct drm_device *dev,
++ struct drm_mode_create_dumb *args);
+
+ /*
+ * Shader management - vmwgfx_shader.c
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+index 5efc6a766f64e..588d50ababf60 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_fence.c
+@@ -32,7 +32,6 @@
+ #define VMW_FENCE_WRAP (1 << 31)
+
+ struct vmw_fence_manager {
+- int num_fence_objects;
+ struct vmw_private *dev_priv;
+ spinlock_t lock;
+ struct list_head fence_list;
+@@ -124,13 +123,13 @@ static void vmw_fence_obj_destroy(struct dma_fence *f)
+ {
+ struct vmw_fence_obj *fence =
+ container_of(f, struct vmw_fence_obj, base);
+-
+ struct vmw_fence_manager *fman = fman_from_fence(fence);
+
+- spin_lock(&fman->lock);
+- list_del_init(&fence->head);
+- --fman->num_fence_objects;
+- spin_unlock(&fman->lock);
++ if (!list_empty(&fence->head)) {
++ spin_lock(&fman->lock);
++ list_del_init(&fence->head);
++ spin_unlock(&fman->lock);
++ }
+ fence->destroy(fence);
+ }
+
+@@ -257,7 +256,6 @@ static const struct dma_fence_ops vmw_fence_ops = {
+ .release = vmw_fence_obj_destroy,
+ };
+
+-
+ /*
+ * Execute signal actions on fences recently signaled.
+ * This is done from a workqueue so we don't have to execute
+@@ -355,7 +353,6 @@ static int vmw_fence_obj_init(struct vmw_fence_manager *fman,
+ goto out_unlock;
+ }
+ list_add_tail(&fence->head, &fman->fence_list);
+- ++fman->num_fence_objects;
+
+ out_unlock:
+ spin_unlock(&fman->lock);
+@@ -403,7 +400,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman,
+ u32 passed_seqno)
+ {
+ u32 goal_seqno;
+- struct vmw_fence_obj *fence;
++ struct vmw_fence_obj *fence, *next_fence;
+
+ if (likely(!fman->seqno_valid))
+ return false;
+@@ -413,7 +410,7 @@ static bool vmw_fence_goal_new_locked(struct vmw_fence_manager *fman,
+ return false;
+
+ fman->seqno_valid = false;
+- list_for_each_entry(fence, &fman->fence_list, head) {
++ list_for_each_entry_safe(fence, next_fence, &fman->fence_list, head) {
+ if (!list_empty(&fence->seq_passed_actions)) {
+ fman->seqno_valid = true;
+ vmw_fence_goal_write(fman->dev_priv,
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+index 00c4ff6841301..288ed0bb75cb9 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.c
+@@ -1,7 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /**************************************************************************
+ *
+- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -193,13 +194,16 @@ static u32 vmw_du_cursor_mob_size(u32 w, u32 h)
+ */
+ static u32 *vmw_du_cursor_plane_acquire_image(struct vmw_plane_state *vps)
+ {
+- if (vps->surf) {
+- if (vps->surf_mapped)
+- return vmw_bo_map_and_cache(vps->surf->res.guest_memory_bo);
+- return vps->surf->snooper.image;
+- } else if (vps->bo)
+- return vmw_bo_map_and_cache(vps->bo);
+- return NULL;
++ struct vmw_surface *surf;
++
++ if (vmw_user_object_is_null(&vps->uo))
++ return NULL;
++
++ surf = vmw_user_object_surface(&vps->uo);
++ if (surf && !vmw_user_object_is_mapped(&vps->uo))
++ return surf->snooper.image;
++
++ return vmw_user_object_map(&vps->uo);
+ }
+
+ static bool vmw_du_cursor_plane_has_changed(struct vmw_plane_state *old_vps,
+@@ -536,22 +540,16 @@ void vmw_du_primary_plane_destroy(struct drm_plane *plane)
+ * vmw_du_plane_unpin_surf - unpins resource associated with a framebuffer surface
+ *
+ * @vps: plane state associated with the display surface
+- * @unreference: true if we also want to unreference the display.
+ */
+-void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps,
+- bool unreference)
++void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps)
+ {
+- if (vps->surf) {
++ struct vmw_surface *surf = vmw_user_object_surface(&vps->uo);
++
++ if (surf) {
+ if (vps->pinned) {
+- vmw_resource_unpin(&vps->surf->res);
++ vmw_resource_unpin(&surf->res);
+ vps->pinned--;
+ }
+-
+- if (unreference) {
+- if (vps->pinned)
+- DRM_ERROR("Surface still pinned\n");
+- vmw_surface_unreference(&vps->surf);
+- }
+ }
+ }
+
+@@ -572,7 +570,7 @@ vmw_du_plane_cleanup_fb(struct drm_plane *plane,
+ {
+ struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
+
+- vmw_du_plane_unpin_surf(vps, false);
++ vmw_du_plane_unpin_surf(vps);
+ }
+
+
+@@ -661,25 +659,14 @@ vmw_du_cursor_plane_cleanup_fb(struct drm_plane *plane,
+ struct vmw_cursor_plane *vcp = vmw_plane_to_vcp(plane);
+ struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
+
+- if (vps->surf_mapped) {
+- vmw_bo_unmap(vps->surf->res.guest_memory_bo);
+- vps->surf_mapped = false;
+- }
++ if (!vmw_user_object_is_null(&vps->uo))
++ vmw_user_object_unmap(&vps->uo);
+
+ vmw_du_cursor_plane_unmap_cm(vps);
+ vmw_du_put_cursor_mob(vcp, vps);
+
+- vmw_du_plane_unpin_surf(vps, false);
+-
+- if (vps->surf) {
+- vmw_surface_unreference(&vps->surf);
+- vps->surf = NULL;
+- }
+-
+- if (vps->bo) {
+- vmw_bo_unreference(&vps->bo);
+- vps->bo = NULL;
+- }
++ vmw_du_plane_unpin_surf(vps);
++ vmw_user_object_unref(&vps->uo);
+ }
+
+
+@@ -698,64 +685,48 @@ vmw_du_cursor_plane_prepare_fb(struct drm_plane *plane,
+ struct drm_framebuffer *fb = new_state->fb;
+ struct vmw_cursor_plane *vcp = vmw_plane_to_vcp(plane);
+ struct vmw_plane_state *vps = vmw_plane_state_to_vps(new_state);
++ struct vmw_bo *bo = NULL;
+ int ret = 0;
+
+- if (vps->surf) {
+- if (vps->surf_mapped) {
+- vmw_bo_unmap(vps->surf->res.guest_memory_bo);
+- vps->surf_mapped = false;
+- }
+- vmw_surface_unreference(&vps->surf);
+- vps->surf = NULL;
+- }
+-
+- if (vps->bo) {
+- vmw_bo_unreference(&vps->bo);
+- vps->bo = NULL;
++ if (!vmw_user_object_is_null(&vps->uo)) {
++ vmw_user_object_unmap(&vps->uo);
++ vmw_user_object_unref(&vps->uo);
+ }
+
+ if (fb) {
+ if (vmw_framebuffer_to_vfb(fb)->bo) {
+- vps->bo = vmw_framebuffer_to_vfbd(fb)->buffer;
+- vmw_bo_reference(vps->bo);
++ vps->uo.buffer = vmw_framebuffer_to_vfbd(fb)->buffer;
++ vps->uo.surface = NULL;
+ } else {
+- vps->surf = vmw_framebuffer_to_vfbs(fb)->surface;
+- vmw_surface_reference(vps->surf);
++ memcpy(&vps->uo, &vmw_framebuffer_to_vfbs(fb)->uo, sizeof(vps->uo));
+ }
++ vmw_user_object_ref(&vps->uo);
+ }
+
+- if (!vps->surf && vps->bo) {
+- const u32 size = new_state->crtc_w * new_state->crtc_h * sizeof(u32);
++ bo = vmw_user_object_buffer(&vps->uo);
++ if (bo) {
++ struct ttm_operation_ctx ctx = {false, false};
+
+- /*
+- * Not using vmw_bo_map_and_cache() helper here as we need to
+- * reserve the ttm_buffer_object first which
+- * vmw_bo_map_and_cache() omits.
+- */
+- ret = ttm_bo_reserve(&vps->bo->tbo, true, false, NULL);
+-
+- if (unlikely(ret != 0))
++ ret = ttm_bo_reserve(&bo->tbo, true, false, NULL);
++ if (ret != 0)
+ return -ENOMEM;
+
+- ret = ttm_bo_kmap(&vps->bo->tbo, 0, PFN_UP(size), &vps->bo->map);
+-
+- ttm_bo_unreserve(&vps->bo->tbo);
+-
+- if (unlikely(ret != 0))
++ ret = ttm_bo_validate(&bo->tbo, &bo->placement, &ctx);
++ if (ret != 0)
+ return -ENOMEM;
+- } else if (vps->surf && !vps->bo && vps->surf->res.guest_memory_bo) {
+
+- WARN_ON(vps->surf->snooper.image);
+- ret = ttm_bo_reserve(&vps->surf->res.guest_memory_bo->tbo, true, false,
+- NULL);
+- if (unlikely(ret != 0))
+- return -ENOMEM;
+- vmw_bo_map_and_cache(vps->surf->res.guest_memory_bo);
+- ttm_bo_unreserve(&vps->surf->res.guest_memory_bo->tbo);
+- vps->surf_mapped = true;
++ vmw_bo_pin_reserved(bo, true);
++ if (vmw_framebuffer_to_vfb(fb)->bo) {
++ const u32 size = new_state->crtc_w * new_state->crtc_h * sizeof(u32);
++
++ (void)vmw_bo_map_and_cache_size(bo, size);
++ } else {
++ vmw_bo_map_and_cache(bo);
++ }
++ ttm_bo_unreserve(&bo->tbo);
+ }
+
+- if (vps->surf || vps->bo) {
++ if (!vmw_user_object_is_null(&vps->uo)) {
+ vmw_du_get_cursor_mob(vcp, vps);
+ vmw_du_cursor_plane_map_cm(vps);
+ }
+@@ -777,14 +748,17 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
+ struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+ struct vmw_plane_state *vps = vmw_plane_state_to_vps(new_state);
+ struct vmw_plane_state *old_vps = vmw_plane_state_to_vps(old_state);
++ struct vmw_bo *old_bo = NULL;
++ struct vmw_bo *new_bo = NULL;
+ s32 hotspot_x, hotspot_y;
++ int ret;
+
+ hotspot_x = du->hotspot_x + new_state->hotspot_x;
+ hotspot_y = du->hotspot_y + new_state->hotspot_y;
+
+- du->cursor_surface = vps->surf;
++ du->cursor_surface = vmw_user_object_surface(&vps->uo);
+
+- if (!vps->surf && !vps->bo) {
++ if (vmw_user_object_is_null(&vps->uo)) {
+ vmw_cursor_update_position(dev_priv, false, 0, 0);
+ return;
+ }
+@@ -792,10 +766,26 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
+ vps->cursor.hotspot_x = hotspot_x;
+ vps->cursor.hotspot_y = hotspot_y;
+
+- if (vps->surf) {
++ if (du->cursor_surface)
+ du->cursor_age = du->cursor_surface->snooper.age;
++
++ if (!vmw_user_object_is_null(&old_vps->uo)) {
++ old_bo = vmw_user_object_buffer(&old_vps->uo);
++ ret = ttm_bo_reserve(&old_bo->tbo, false, false, NULL);
++ if (ret != 0)
++ return;
+ }
+
++ if (!vmw_user_object_is_null(&vps->uo)) {
++ new_bo = vmw_user_object_buffer(&vps->uo);
++ if (old_bo != new_bo) {
++ ret = ttm_bo_reserve(&new_bo->tbo, false, false, NULL);
++ if (ret != 0)
++ return;
++ } else {
++ new_bo = NULL;
++ }
++ }
+ if (!vmw_du_cursor_plane_has_changed(old_vps, vps)) {
+ /*
+ * If it hasn't changed, avoid making the device do extra
+@@ -813,6 +803,11 @@ vmw_du_cursor_plane_atomic_update(struct drm_plane *plane,
+ hotspot_x, hotspot_y);
+ }
+
++ if (old_bo)
++ ttm_bo_unreserve(&old_bo->tbo);
++ if (new_bo)
++ ttm_bo_unreserve(&new_bo->tbo);
++
+ du->cursor_x = new_state->crtc_x + du->set_gui_x;
+ du->cursor_y = new_state->crtc_y + du->set_gui_y;
+
+@@ -913,7 +908,7 @@ int vmw_du_cursor_plane_atomic_check(struct drm_plane *plane,
+ }
+
+ if (!vmw_framebuffer_to_vfb(fb)->bo) {
+- surface = vmw_framebuffer_to_vfbs(fb)->surface;
++ surface = vmw_user_object_surface(&vmw_framebuffer_to_vfbs(fb)->uo);
+
+ WARN_ON(!surface);
+
+@@ -1074,12 +1069,7 @@ vmw_du_plane_duplicate_state(struct drm_plane *plane)
+ memset(&vps->cursor, 0, sizeof(vps->cursor));
+
+ /* Each ref counted resource needs to be acquired again */
+- if (vps->surf)
+- (void) vmw_surface_reference(vps->surf);
+-
+- if (vps->bo)
+- (void) vmw_bo_reference(vps->bo);
+-
++ vmw_user_object_ref(&vps->uo);
+ state = &vps->base;
+
+ __drm_atomic_helper_plane_duplicate_state(plane, state);
+@@ -1128,11 +1118,7 @@ vmw_du_plane_destroy_state(struct drm_plane *plane,
+ struct vmw_plane_state *vps = vmw_plane_state_to_vps(state);
+
+ /* Should have been freed by cleanup_fb */
+- if (vps->surf)
+- vmw_surface_unreference(&vps->surf);
+-
+- if (vps->bo)
+- vmw_bo_unreference(&vps->bo);
++ vmw_user_object_unref(&vps->uo);
+
+ drm_atomic_helper_plane_destroy_state(plane, state);
+ }
+@@ -1227,7 +1213,7 @@ static void vmw_framebuffer_surface_destroy(struct drm_framebuffer *framebuffer)
+ vmw_framebuffer_to_vfbs(framebuffer);
+
+ drm_framebuffer_cleanup(framebuffer);
+- vmw_surface_unreference(&vfbs->surface);
++ vmw_user_object_unref(&vfbs->uo);
+
+ kfree(vfbs);
+ }
+@@ -1272,29 +1258,41 @@ int vmw_kms_readback(struct vmw_private *dev_priv,
+ return -ENOSYS;
+ }
+
++static int vmw_framebuffer_surface_create_handle(struct drm_framebuffer *fb,
++ struct drm_file *file_priv,
++ unsigned int *handle)
++{
++ struct vmw_framebuffer_surface *vfbs = vmw_framebuffer_to_vfbs(fb);
++ struct vmw_bo *bo = vmw_user_object_buffer(&vfbs->uo);
++
++ return drm_gem_handle_create(file_priv, &bo->tbo.base, handle);
++}
+
+ static const struct drm_framebuffer_funcs vmw_framebuffer_surface_funcs = {
++ .create_handle = vmw_framebuffer_surface_create_handle,
+ .destroy = vmw_framebuffer_surface_destroy,
+ .dirty = drm_atomic_helper_dirtyfb,
+ };
+
+ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
+- struct vmw_surface *surface,
++ struct vmw_user_object *uo,
+ struct vmw_framebuffer **out,
+ const struct drm_mode_fb_cmd2
+- *mode_cmd,
+- bool is_bo_proxy)
++ *mode_cmd)
+
+ {
+ struct drm_device *dev = &dev_priv->drm;
+ struct vmw_framebuffer_surface *vfbs;
+ enum SVGA3dSurfaceFormat format;
++ struct vmw_surface *surface;
+ int ret;
+
+ /* 3D is only supported on HWv8 and newer hosts */
+ if (dev_priv->active_display_unit == vmw_du_legacy)
+ return -ENOSYS;
+
++ surface = vmw_user_object_surface(uo);
++
+ /*
+ * Sanity checks.
+ */
+@@ -1357,8 +1355,8 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
+ }
+
+ drm_helper_mode_fill_fb_struct(dev, &vfbs->base.base, mode_cmd);
+- vfbs->surface = vmw_surface_reference(surface);
+- vfbs->is_bo_proxy = is_bo_proxy;
++ memcpy(&vfbs->uo, uo, sizeof(vfbs->uo));
++ vmw_user_object_ref(&vfbs->uo);
+
+ *out = &vfbs->base;
+
+@@ -1370,7 +1368,7 @@ static int vmw_kms_new_framebuffer_surface(struct vmw_private *dev_priv,
+ return 0;
+
+ out_err2:
+- vmw_surface_unreference(&surface);
++ vmw_user_object_unref(&vfbs->uo);
+ kfree(vfbs);
+ out_err1:
+ return ret;
+@@ -1386,7 +1384,6 @@ static int vmw_framebuffer_bo_create_handle(struct drm_framebuffer *fb,
+ {
+ struct vmw_framebuffer_bo *vfbd =
+ vmw_framebuffer_to_vfbd(fb);
+-
+ return drm_gem_handle_create(file_priv, &vfbd->buffer->tbo.base, handle);
+ }
+
+@@ -1407,86 +1404,6 @@ static const struct drm_framebuffer_funcs vmw_framebuffer_bo_funcs = {
+ .dirty = drm_atomic_helper_dirtyfb,
+ };
+
+-/**
+- * vmw_create_bo_proxy - create a proxy surface for the buffer object
+- *
+- * @dev: DRM device
+- * @mode_cmd: parameters for the new surface
+- * @bo_mob: MOB backing the buffer object
+- * @srf_out: newly created surface
+- *
+- * When the content FB is a buffer object, we create a surface as a proxy to the
+- * same buffer. This way we can do a surface copy rather than a surface DMA.
+- * This is a more efficient approach
+- *
+- * RETURNS:
+- * 0 on success, error code otherwise
+- */
+-static int vmw_create_bo_proxy(struct drm_device *dev,
+- const struct drm_mode_fb_cmd2 *mode_cmd,
+- struct vmw_bo *bo_mob,
+- struct vmw_surface **srf_out)
+-{
+- struct vmw_surface_metadata metadata = {0};
+- uint32_t format;
+- struct vmw_resource *res;
+- unsigned int bytes_pp;
+- int ret;
+-
+- switch (mode_cmd->pixel_format) {
+- case DRM_FORMAT_ARGB8888:
+- case DRM_FORMAT_XRGB8888:
+- format = SVGA3D_X8R8G8B8;
+- bytes_pp = 4;
+- break;
+-
+- case DRM_FORMAT_RGB565:
+- case DRM_FORMAT_XRGB1555:
+- format = SVGA3D_R5G6B5;
+- bytes_pp = 2;
+- break;
+-
+- case 8:
+- format = SVGA3D_P8;
+- bytes_pp = 1;
+- break;
+-
+- default:
+- DRM_ERROR("Invalid framebuffer format %p4cc\n",
+- &mode_cmd->pixel_format);
+- return -EINVAL;
+- }
+-
+- metadata.format = format;
+- metadata.mip_levels[0] = 1;
+- metadata.num_sizes = 1;
+- metadata.base_size.width = mode_cmd->pitches[0] / bytes_pp;
+- metadata.base_size.height = mode_cmd->height;
+- metadata.base_size.depth = 1;
+- metadata.scanout = true;
+-
+- ret = vmw_gb_surface_define(vmw_priv(dev), &metadata, srf_out);
+- if (ret) {
+- DRM_ERROR("Failed to allocate proxy content buffer\n");
+- return ret;
+- }
+-
+- res = &(*srf_out)->res;
+-
+- /* Reserve and switch the backing mob. */
+- mutex_lock(&res->dev_priv->cmdbuf_mutex);
+- (void) vmw_resource_reserve(res, false, true);
+- vmw_user_bo_unref(&res->guest_memory_bo);
+- res->guest_memory_bo = vmw_user_bo_ref(bo_mob);
+- res->guest_memory_offset = 0;
+- vmw_resource_unreserve(res, false, false, false, NULL, 0);
+- mutex_unlock(&res->dev_priv->cmdbuf_mutex);
+-
+- return 0;
+-}
+-
+-
+-
+ static int vmw_kms_new_framebuffer_bo(struct vmw_private *dev_priv,
+ struct vmw_bo *bo,
+ struct vmw_framebuffer **out,
+@@ -1565,55 +1482,24 @@ vmw_kms_srf_ok(struct vmw_private *dev_priv, uint32_t width, uint32_t height)
+ * vmw_kms_new_framebuffer - Create a new framebuffer.
+ *
+ * @dev_priv: Pointer to device private struct.
+- * @bo: Pointer to buffer object to wrap the kms framebuffer around.
+- * Either @bo or @surface must be NULL.
+- * @surface: Pointer to a surface to wrap the kms framebuffer around.
+- * Either @bo or @surface must be NULL.
+- * @only_2d: No presents will occur to this buffer object based framebuffer.
+- * This helps the code to do some important optimizations.
++ * @uo: Pointer to user object to wrap the kms framebuffer around.
++ * Either the buffer or surface inside the user object must be NULL.
+ * @mode_cmd: Frame-buffer metadata.
+ */
+ struct vmw_framebuffer *
+ vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
+- struct vmw_bo *bo,
+- struct vmw_surface *surface,
+- bool only_2d,
++ struct vmw_user_object *uo,
+ const struct drm_mode_fb_cmd2 *mode_cmd)
+ {
+ struct vmw_framebuffer *vfb = NULL;
+- bool is_bo_proxy = false;
+ int ret;
+
+- /*
+- * We cannot use the SurfaceDMA command in an non-accelerated VM,
+- * therefore, wrap the buffer object in a surface so we can use the
+- * SurfaceCopy command.
+- */
+- if (vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height) &&
+- bo && only_2d &&
+- mode_cmd->width > 64 && /* Don't create a proxy for cursor */
+- dev_priv->active_display_unit == vmw_du_screen_target) {
+- ret = vmw_create_bo_proxy(&dev_priv->drm, mode_cmd,
+- bo, &surface);
+- if (ret)
+- return ERR_PTR(ret);
+-
+- is_bo_proxy = true;
+- }
+-
+ /* Create the new framebuffer depending one what we have */
+- if (surface) {
+- ret = vmw_kms_new_framebuffer_surface(dev_priv, surface, &vfb,
+- mode_cmd,
+- is_bo_proxy);
+- /*
+- * vmw_create_bo_proxy() adds a reference that is no longer
+- * needed
+- */
+- if (is_bo_proxy)
+- vmw_surface_unreference(&surface);
+- } else if (bo) {
+- ret = vmw_kms_new_framebuffer_bo(dev_priv, bo, &vfb,
++ if (vmw_user_object_surface(uo)) {
++ ret = vmw_kms_new_framebuffer_surface(dev_priv, uo, &vfb,
++ mode_cmd);
++ } else if (uo->buffer) {
++ ret = vmw_kms_new_framebuffer_bo(dev_priv, uo->buffer, &vfb,
+ mode_cmd);
+ } else {
+ BUG();
+@@ -1635,14 +1521,12 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
+ {
+ struct vmw_private *dev_priv = vmw_priv(dev);
+ struct vmw_framebuffer *vfb = NULL;
+- struct vmw_surface *surface = NULL;
+- struct vmw_bo *bo = NULL;
++ struct vmw_user_object uo = {0};
+ int ret;
+
+ /* returns either a bo or surface */
+- ret = vmw_user_lookup_handle(dev_priv, file_priv,
+- mode_cmd->handles[0],
+- &surface, &bo);
++ ret = vmw_user_object_lookup(dev_priv, file_priv, mode_cmd->handles[0],
++ &uo);
+ if (ret) {
+ DRM_ERROR("Invalid buffer object handle %u (0x%x).\n",
+ mode_cmd->handles[0], mode_cmd->handles[0]);
+@@ -1650,7 +1534,7 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
+ }
+
+
+- if (!bo &&
++ if (vmw_user_object_surface(&uo) &&
+ !vmw_kms_srf_ok(dev_priv, mode_cmd->width, mode_cmd->height)) {
+ DRM_ERROR("Surface size cannot exceed %dx%d\n",
+ dev_priv->texture_max_width,
+@@ -1659,20 +1543,15 @@ static struct drm_framebuffer *vmw_kms_fb_create(struct drm_device *dev,
+ }
+
+
+- vfb = vmw_kms_new_framebuffer(dev_priv, bo, surface,
+- !(dev_priv->capabilities & SVGA_CAP_3D),
+- mode_cmd);
++ vfb = vmw_kms_new_framebuffer(dev_priv, &uo, mode_cmd);
+ if (IS_ERR(vfb)) {
+ ret = PTR_ERR(vfb);
+ goto err_out;
+ }
+
+ err_out:
+- /* vmw_user_lookup_handle takes one ref so does new_fb */
+- if (bo)
+- vmw_user_bo_unref(&bo);
+- if (surface)
+- vmw_surface_unreference(&surface);
++ /* vmw_user_object_lookup takes one ref so does new_fb */
++ vmw_user_object_unref(&uo);
+
+ if (ret) {
+ DRM_ERROR("failed to create vmw_framebuffer: %i\n", ret);
+@@ -2584,72 +2463,6 @@ void vmw_kms_helper_validation_finish(struct vmw_private *dev_priv,
+ vmw_fence_obj_unreference(&fence);
+ }
+
+-/**
+- * vmw_kms_update_proxy - Helper function to update a proxy surface from
+- * its backing MOB.
+- *
+- * @res: Pointer to the surface resource
+- * @clips: Clip rects in framebuffer (surface) space.
+- * @num_clips: Number of clips in @clips.
+- * @increment: Integer with which to increment the clip counter when looping.
+- * Used to skip a predetermined number of clip rects.
+- *
+- * This function makes sure the proxy surface is updated from its backing MOB
+- * using the region given by @clips. The surface resource @res and its backing
+- * MOB needs to be reserved and validated on call.
+- */
+-int vmw_kms_update_proxy(struct vmw_resource *res,
+- const struct drm_clip_rect *clips,
+- unsigned num_clips,
+- int increment)
+-{
+- struct vmw_private *dev_priv = res->dev_priv;
+- struct drm_vmw_size *size = &vmw_res_to_srf(res)->metadata.base_size;
+- struct {
+- SVGA3dCmdHeader header;
+- SVGA3dCmdUpdateGBImage body;
+- } *cmd;
+- SVGA3dBox *box;
+- size_t copy_size = 0;
+- int i;
+-
+- if (!clips)
+- return 0;
+-
+- cmd = VMW_CMD_RESERVE(dev_priv, sizeof(*cmd) * num_clips);
+- if (!cmd)
+- return -ENOMEM;
+-
+- for (i = 0; i < num_clips; ++i, clips += increment, ++cmd) {
+- box = &cmd->body.box;
+-
+- cmd->header.id = SVGA_3D_CMD_UPDATE_GB_IMAGE;
+- cmd->header.size = sizeof(cmd->body);
+- cmd->body.image.sid = res->id;
+- cmd->body.image.face = 0;
+- cmd->body.image.mipmap = 0;
+-
+- if (clips->x1 > size->width || clips->x2 > size->width ||
+- clips->y1 > size->height || clips->y2 > size->height) {
+- DRM_ERROR("Invalid clips outsize of framebuffer.\n");
+- return -EINVAL;
+- }
+-
+- box->x = clips->x1;
+- box->y = clips->y1;
+- box->z = 0;
+- box->w = clips->x2 - clips->x1;
+- box->h = clips->y2 - clips->y1;
+- box->d = 1;
+-
+- copy_size += sizeof(*cmd);
+- }
+-
+- vmw_cmd_commit(dev_priv, copy_size);
+-
+- return 0;
+-}
+-
+ /**
+ * vmw_kms_create_implicit_placement_property - Set up the implicit placement
+ * property.
+@@ -2784,8 +2597,9 @@ int vmw_du_helper_plane_update(struct vmw_du_update_plane *update)
+ } else {
+ struct vmw_framebuffer_surface *vfbs =
+ container_of(update->vfb, typeof(*vfbs), base);
++ struct vmw_surface *surf = vmw_user_object_surface(&vfbs->uo);
+
+- ret = vmw_validation_add_resource(&val_ctx, &vfbs->surface->res,
++ ret = vmw_validation_add_resource(&val_ctx, &surf->res,
+ 0, VMW_RES_DIRTY_NONE, NULL,
+ NULL);
+ }
+@@ -2941,3 +2755,93 @@ int vmw_connector_get_modes(struct drm_connector *connector)
+
+ return num_modes;
+ }
++
++struct vmw_user_object *vmw_user_object_ref(struct vmw_user_object *uo)
++{
++ if (uo->buffer)
++ vmw_user_bo_ref(uo->buffer);
++ else if (uo->surface)
++ vmw_surface_reference(uo->surface);
++ return uo;
++}
++
++void vmw_user_object_unref(struct vmw_user_object *uo)
++{
++ if (uo->buffer)
++ vmw_user_bo_unref(&uo->buffer);
++ else if (uo->surface)
++ vmw_surface_unreference(&uo->surface);
++}
++
++struct vmw_bo *
++vmw_user_object_buffer(struct vmw_user_object *uo)
++{
++ if (uo->buffer)
++ return uo->buffer;
++ else if (uo->surface)
++ return uo->surface->res.guest_memory_bo;
++ return NULL;
++}
++
++struct vmw_surface *
++vmw_user_object_surface(struct vmw_user_object *uo)
++{
++ if (uo->buffer)
++ return uo->buffer->dumb_surface;
++ return uo->surface;
++}
++
++void *vmw_user_object_map(struct vmw_user_object *uo)
++{
++ struct vmw_bo *bo = vmw_user_object_buffer(uo);
++
++ WARN_ON(!bo);
++ return vmw_bo_map_and_cache(bo);
++}
++
++void *vmw_user_object_map_size(struct vmw_user_object *uo, size_t size)
++{
++ struct vmw_bo *bo = vmw_user_object_buffer(uo);
++
++ WARN_ON(!bo);
++ return vmw_bo_map_and_cache_size(bo, size);
++}
++
++void vmw_user_object_unmap(struct vmw_user_object *uo)
++{
++ struct vmw_bo *bo = vmw_user_object_buffer(uo);
++ int ret;
++
++ WARN_ON(!bo);
++
++ /* Fence the mob creation so we are guarateed to have the mob */
++ ret = ttm_bo_reserve(&bo->tbo, false, false, NULL);
++ if (ret != 0)
++ return;
++
++ vmw_bo_unmap(bo);
++ vmw_bo_pin_reserved(bo, false);
++
++ ttm_bo_unreserve(&bo->tbo);
++}
++
++bool vmw_user_object_is_mapped(struct vmw_user_object *uo)
++{
++ struct vmw_bo *bo;
++
++ if (!uo || vmw_user_object_is_null(uo))
++ return false;
++
++ bo = vmw_user_object_buffer(uo);
++
++ if (WARN_ON(!bo))
++ return false;
++
++ WARN_ON(bo->map.bo && !bo->map.virtual);
++ return bo->map.virtual;
++}
++
++bool vmw_user_object_is_null(struct vmw_user_object *uo)
++{
++ return !uo->buffer && !uo->surface;
++}
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+index bf24f2f0dcfc9..6141fadf81efe 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_kms.h
+@@ -1,7 +1,8 @@
+ /* SPDX-License-Identifier: GPL-2.0 OR MIT */
+ /**************************************************************************
+ *
+- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -221,11 +222,9 @@ struct vmw_framebuffer {
+
+ struct vmw_framebuffer_surface {
+ struct vmw_framebuffer base;
+- struct vmw_surface *surface;
+- bool is_bo_proxy; /* true if this is proxy surface for DMA buf */
++ struct vmw_user_object uo;
+ };
+
+-
+ struct vmw_framebuffer_bo {
+ struct vmw_framebuffer base;
+ struct vmw_bo *buffer;
+@@ -277,8 +276,7 @@ struct vmw_cursor_plane_state {
+ */
+ struct vmw_plane_state {
+ struct drm_plane_state base;
+- struct vmw_surface *surf;
+- struct vmw_bo *bo;
++ struct vmw_user_object uo;
+
+ int content_fb_type;
+ unsigned long bo_size;
+@@ -457,9 +455,7 @@ int vmw_kms_readback(struct vmw_private *dev_priv,
+ uint32_t num_clips);
+ struct vmw_framebuffer *
+ vmw_kms_new_framebuffer(struct vmw_private *dev_priv,
+- struct vmw_bo *bo,
+- struct vmw_surface *surface,
+- bool only_2d,
++ struct vmw_user_object *uo,
+ const struct drm_mode_fb_cmd2 *mode_cmd);
+ void vmw_guess_mode_timing(struct drm_display_mode *mode);
+ void vmw_kms_update_implicit_fb(struct vmw_private *dev_priv);
+@@ -486,8 +482,7 @@ void vmw_du_plane_reset(struct drm_plane *plane);
+ struct drm_plane_state *vmw_du_plane_duplicate_state(struct drm_plane *plane);
+ void vmw_du_plane_destroy_state(struct drm_plane *plane,
+ struct drm_plane_state *state);
+-void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps,
+- bool unreference);
++void vmw_du_plane_unpin_surf(struct vmw_plane_state *vps);
+
+ int vmw_du_crtc_atomic_check(struct drm_crtc *crtc,
+ struct drm_atomic_state *state);
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+index 5befc2719a498..39949e0a493f3 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_ldu.c
+@@ -1,7 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /**************************************************************************
+ *
+- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -147,8 +148,9 @@ static int vmw_ldu_fb_pin(struct vmw_framebuffer *vfb)
+ struct vmw_bo *buf;
+ int ret;
+
+- buf = vfb->bo ? vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+- vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.guest_memory_bo;
++ buf = vfb->bo ?
++ vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
++ vmw_user_object_buffer(&vmw_framebuffer_to_vfbs(&vfb->base)->uo);
+
+ if (!buf)
+ return 0;
+@@ -169,8 +171,10 @@ static int vmw_ldu_fb_unpin(struct vmw_framebuffer *vfb)
+ struct vmw_private *dev_priv = vmw_priv(vfb->base.dev);
+ struct vmw_bo *buf;
+
+- buf = vfb->bo ? vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
+- vmw_framebuffer_to_vfbs(&vfb->base)->surface->res.guest_memory_bo;
++ buf = vfb->bo ?
++ vmw_framebuffer_to_vfbd(&vfb->base)->buffer :
++ vmw_user_object_buffer(&vmw_framebuffer_to_vfbs(&vfb->base)->uo);
++
+
+ if (WARN_ON(!buf))
+ return 0;
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+index c45b4724e4141..e20f64b67b266 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_overlay.c
+@@ -92,7 +92,7 @@ static int vmw_overlay_send_put(struct vmw_private *dev_priv,
+ {
+ struct vmw_escape_video_flush *flush;
+ size_t fifo_size;
+- bool have_so = (dev_priv->active_display_unit == vmw_du_screen_object);
++ bool have_so = (dev_priv->active_display_unit != vmw_du_legacy);
+ int i, num_items;
+ SVGAGuestPtr ptr;
+
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+index c99cad4449915..598b90ac7590b 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_prime.c
+@@ -1,7 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /**************************************************************************
+ *
+- * Copyright 2013 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2013-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -31,6 +32,7 @@
+ */
+
+ #include "vmwgfx_drv.h"
++#include "vmwgfx_bo.h"
+ #include "ttm_object.h"
+ #include <linux/dma-buf.h>
+
+@@ -88,13 +90,35 @@ int vmw_prime_handle_to_fd(struct drm_device *dev,
+ uint32_t handle, uint32_t flags,
+ int *prime_fd)
+ {
++ struct vmw_private *vmw = vmw_priv(dev);
+ struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
++ struct vmw_bo *vbo;
+ int ret;
++ int surf_handle;
+
+- if (handle > VMWGFX_NUM_MOB)
++ if (handle > VMWGFX_NUM_MOB) {
+ ret = ttm_prime_handle_to_fd(tfile, handle, flags, prime_fd);
+- else
+- ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle, flags, prime_fd);
++ } else {
++ ret = vmw_user_bo_lookup(file_priv, handle, &vbo);
++ if (ret)
++ return ret;
++ if (vbo && vbo->is_dumb) {
++ ret = drm_gem_prime_handle_to_fd(dev, file_priv, handle,
++ flags, prime_fd);
++ } else {
++ surf_handle = vmw_lookup_surface_handle_for_buffer(vmw,
++ vbo,
++ handle);
++ if (surf_handle > 0)
++ ret = ttm_prime_handle_to_fd(tfile, surf_handle,
++ flags, prime_fd);
++ else
++ ret = drm_gem_prime_handle_to_fd(dev, file_priv,
++ handle, flags,
++ prime_fd);
++ }
++ vmw_user_bo_unref(&vbo);
++ }
+
+ return ret;
+ }
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+index 848dba09981b0..a73af8a355fbf 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_resource.c
+@@ -1,7 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /**************************************************************************
+ *
+- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -58,6 +59,7 @@ void vmw_resource_mob_attach(struct vmw_resource *res)
+
+ rb_link_node(&res->mob_node, parent, new);
+ rb_insert_color(&res->mob_node, &gbo->res_tree);
++ vmw_bo_del_detached_resource(gbo, res);
+
+ vmw_bo_prio_add(gbo, res->used_prio);
+ }
+@@ -287,28 +289,35 @@ int vmw_user_resource_lookup_handle(struct vmw_private *dev_priv,
+ *
+ * The pointer this pointed at by out_surf and out_buf needs to be null.
+ */
+-int vmw_user_lookup_handle(struct vmw_private *dev_priv,
++int vmw_user_object_lookup(struct vmw_private *dev_priv,
+ struct drm_file *filp,
+- uint32_t handle,
+- struct vmw_surface **out_surf,
+- struct vmw_bo **out_buf)
++ u32 handle,
++ struct vmw_user_object *uo)
+ {
+ struct ttm_object_file *tfile = vmw_fpriv(filp)->tfile;
+ struct vmw_resource *res;
+ int ret;
+
+- BUG_ON(*out_surf || *out_buf);
++ WARN_ON(uo->surface || uo->buffer);
+
+ ret = vmw_user_resource_lookup_handle(dev_priv, tfile, handle,
+ user_surface_converter,
+ &res);
+ if (!ret) {
+- *out_surf = vmw_res_to_srf(res);
++ uo->surface = vmw_res_to_srf(res);
+ return 0;
+ }
+
+- *out_surf = NULL;
+- ret = vmw_user_bo_lookup(filp, handle, out_buf);
++ uo->surface = NULL;
++ ret = vmw_user_bo_lookup(filp, handle, &uo->buffer);
++ if (!ret && !uo->buffer->is_dumb) {
++ uo->surface = vmw_lookup_surface_for_buffer(dev_priv,
++ uo->buffer,
++ handle);
++ if (uo->surface)
++ vmw_user_bo_unref(&uo->buffer);
++ }
++
+ return ret;
+ }
+
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+index df0039a8ef29a..0f4bfd98480af 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_scrn.c
+@@ -1,7 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /**************************************************************************
+ *
+- * Copyright 2011-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2011-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -240,7 +241,7 @@ static void vmw_sou_crtc_mode_set_nofb(struct drm_crtc *crtc)
+ struct vmw_connector_state *vmw_conn_state;
+ int x, y;
+
+- sou->buffer = vps->bo;
++ sou->buffer = vmw_user_object_buffer(&vps->uo);
+
+ conn_state = sou->base.connector.state;
+ vmw_conn_state = vmw_connector_state_to_vcs(conn_state);
+@@ -376,10 +377,11 @@ vmw_sou_primary_plane_cleanup_fb(struct drm_plane *plane,
+ struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
+ struct drm_crtc *crtc = plane->state->crtc ?
+ plane->state->crtc : old_state->crtc;
++ struct vmw_bo *bo = vmw_user_object_buffer(&vps->uo);
+
+- if (vps->bo)
+- vmw_bo_unpin(vmw_priv(crtc->dev), vps->bo, false);
+- vmw_bo_unreference(&vps->bo);
++ if (bo)
++ vmw_bo_unpin(vmw_priv(crtc->dev), bo, false);
++ vmw_user_object_unref(&vps->uo);
+ vps->bo_size = 0;
+
+ vmw_du_plane_cleanup_fb(plane, old_state);
+@@ -411,9 +413,10 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
+ .bo_type = ttm_bo_type_device,
+ .pin = true
+ };
++ struct vmw_bo *bo = NULL;
+
+ if (!new_fb) {
+- vmw_bo_unreference(&vps->bo);
++ vmw_user_object_unref(&vps->uo);
+ vps->bo_size = 0;
+
+ return 0;
+@@ -422,17 +425,17 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
+ bo_params.size = new_state->crtc_w * new_state->crtc_h * 4;
+ dev_priv = vmw_priv(crtc->dev);
+
+- if (vps->bo) {
++ bo = vmw_user_object_buffer(&vps->uo);
++ if (bo) {
+ if (vps->bo_size == bo_params.size) {
+ /*
+ * Note that this might temporarily up the pin-count
+ * to 2, until cleanup_fb() is called.
+ */
+- return vmw_bo_pin_in_vram(dev_priv, vps->bo,
+- true);
++ return vmw_bo_pin_in_vram(dev_priv, bo, true);
+ }
+
+- vmw_bo_unreference(&vps->bo);
++ vmw_user_object_unref(&vps->uo);
+ vps->bo_size = 0;
+ }
+
+@@ -442,7 +445,7 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
+ * resume the overlays, this is preferred to failing to alloc.
+ */
+ vmw_overlay_pause_all(dev_priv);
+- ret = vmw_bo_create(dev_priv, &bo_params, &vps->bo);
++ ret = vmw_gem_object_create(dev_priv, &bo_params, &vps->uo.buffer);
+ vmw_overlay_resume_all(dev_priv);
+ if (ret)
+ return ret;
+@@ -453,7 +456,7 @@ vmw_sou_primary_plane_prepare_fb(struct drm_plane *plane,
+ * TTM already thinks the buffer is pinned, but make sure the
+ * pin_count is upped.
+ */
+- return vmw_bo_pin_in_vram(dev_priv, vps->bo, true);
++ return vmw_bo_pin_in_vram(dev_priv, vps->uo.buffer, true);
+ }
+
+ static uint32_t vmw_sou_bo_fifo_size(struct vmw_du_update_plane *update,
+@@ -580,6 +583,7 @@ static uint32_t vmw_sou_surface_pre_clip(struct vmw_du_update_plane *update,
+ {
+ struct vmw_kms_sou_dirty_cmd *blit = cmd;
+ struct vmw_framebuffer_surface *vfbs;
++ struct vmw_surface *surf = NULL;
+
+ vfbs = container_of(update->vfb, typeof(*vfbs), base);
+
+@@ -587,7 +591,8 @@ static uint32_t vmw_sou_surface_pre_clip(struct vmw_du_update_plane *update,
+ blit->header.size = sizeof(blit->body) + sizeof(SVGASignedRect) *
+ num_hits;
+
+- blit->body.srcImage.sid = vfbs->surface->res.id;
++ surf = vmw_user_object_surface(&vfbs->uo);
++ blit->body.srcImage.sid = surf->res.id;
+ blit->body.destScreenId = update->du->unit;
+
+ /* Update the source and destination bounding box later in post_clip */
+@@ -1104,7 +1109,7 @@ int vmw_kms_sou_do_surface_dirty(struct vmw_private *dev_priv,
+ int ret;
+
+ if (!srf)
+- srf = &vfbs->surface->res;
++ srf = &vmw_user_object_surface(&vfbs->uo)->res;
+
+ ret = vmw_validation_add_resource(&val_ctx, srf, 0, VMW_RES_DIRTY_NONE,
+ NULL, NULL);
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+index a04e0736318da..5453f7cf0e2d7 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_stdu.c
+@@ -1,7 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /******************************************************************************
+ *
+- * COPYRIGHT (C) 2014-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2014-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -29,6 +30,7 @@
+ #include "vmwgfx_kms.h"
+ #include "vmwgfx_vkms.h"
+ #include "vmw_surface_cache.h"
++#include <linux/fsnotify.h>
+
+ #include <drm/drm_atomic.h>
+ #include <drm/drm_atomic_helper.h>
+@@ -735,7 +737,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
+ int ret;
+
+ if (!srf)
+- srf = &vfbs->surface->res;
++ srf = &vmw_user_object_surface(&vfbs->uo)->res;
+
+ ret = vmw_validation_add_resource(&val_ctx, srf, 0, VMW_RES_DIRTY_NONE,
+ NULL, NULL);
+@@ -746,12 +748,6 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
+ if (ret)
+ goto out_unref;
+
+- if (vfbs->is_bo_proxy) {
+- ret = vmw_kms_update_proxy(srf, clips, num_clips, inc);
+- if (ret)
+- goto out_finish;
+- }
+-
+ sdirty.base.fifo_commit = vmw_kms_stdu_surface_fifo_commit;
+ sdirty.base.clip = vmw_kms_stdu_surface_clip;
+ sdirty.base.fifo_reserve_size = sizeof(struct vmw_stdu_surface_copy) +
+@@ -765,7 +761,7 @@ int vmw_kms_stdu_surface_dirty(struct vmw_private *dev_priv,
+ ret = vmw_kms_helper_dirty(dev_priv, framebuffer, clips, vclips,
+ dest_x, dest_y, num_clips, inc,
+ &sdirty.base);
+-out_finish:
++
+ vmw_kms_helper_validation_finish(dev_priv, NULL, &val_ctx, out_fence,
+ NULL);
+
+@@ -877,6 +873,32 @@ vmw_stdu_connector_mode_valid(struct drm_connector *connector,
+ return MODE_OK;
+ }
+
++/*
++ * Trigger a modeset if the X,Y position of the Screen Target changes.
++ * This is needed when multi-mon is cycled. The original Screen Target will have
++ * the same mode but its relative X,Y position in the topology will change.
++ */
++static int vmw_stdu_connector_atomic_check(struct drm_connector *conn,
++ struct drm_atomic_state *state)
++{
++ struct drm_connector_state *conn_state;
++ struct vmw_screen_target_display_unit *du;
++ struct drm_crtc_state *new_crtc_state;
++
++ conn_state = drm_atomic_get_connector_state(state, conn);
++ du = vmw_connector_to_stdu(conn);
++
++ if (!conn_state->crtc)
++ return 0;
++
++ new_crtc_state = drm_atomic_get_new_crtc_state(state, conn_state->crtc);
++ if (du->base.gui_x != du->base.set_gui_x ||
++ du->base.gui_y != du->base.set_gui_y)
++ new_crtc_state->mode_changed = true;
++
++ return 0;
++}
++
+ static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
+ .dpms = vmw_du_connector_dpms,
+ .detect = vmw_du_connector_detect,
+@@ -891,7 +913,8 @@ static const struct drm_connector_funcs vmw_stdu_connector_funcs = {
+ static const struct
+ drm_connector_helper_funcs vmw_stdu_connector_helper_funcs = {
+ .get_modes = vmw_connector_get_modes,
+- .mode_valid = vmw_stdu_connector_mode_valid
++ .mode_valid = vmw_stdu_connector_mode_valid,
++ .atomic_check = vmw_stdu_connector_atomic_check,
+ };
+
+
+@@ -918,9 +941,8 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane,
+ {
+ struct vmw_plane_state *vps = vmw_plane_state_to_vps(old_state);
+
+- if (vps->surf)
++ if (vmw_user_object_surface(&vps->uo))
+ WARN_ON(!vps->pinned);
+-
+ vmw_du_plane_cleanup_fb(plane, old_state);
+
+ vps->content_fb_type = SAME_AS_DISPLAY;
+@@ -928,7 +950,6 @@ vmw_stdu_primary_plane_cleanup_fb(struct drm_plane *plane,
+ }
+
+
+-
+ /**
+ * vmw_stdu_primary_plane_prepare_fb - Readies the display surface
+ *
+@@ -952,13 +973,15 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
+ enum stdu_content_type new_content_type;
+ struct vmw_framebuffer_surface *new_vfbs;
+ uint32_t hdisplay = new_state->crtc_w, vdisplay = new_state->crtc_h;
++ struct drm_plane_state *old_state = plane->state;
++ struct drm_rect rect;
+ int ret;
+
+ /* No FB to prepare */
+ if (!new_fb) {
+- if (vps->surf) {
++ if (vmw_user_object_surface(&vps->uo)) {
+ WARN_ON(vps->pinned != 0);
+- vmw_surface_unreference(&vps->surf);
++ vmw_user_object_unref(&vps->uo);
+ }
+
+ return 0;
+@@ -968,8 +991,8 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
+ new_vfbs = (vfb->bo) ? NULL : vmw_framebuffer_to_vfbs(new_fb);
+
+ if (new_vfbs &&
+- new_vfbs->surface->metadata.base_size.width == hdisplay &&
+- new_vfbs->surface->metadata.base_size.height == vdisplay)
++ vmw_user_object_surface(&new_vfbs->uo)->metadata.base_size.width == hdisplay &&
++ vmw_user_object_surface(&new_vfbs->uo)->metadata.base_size.height == vdisplay)
+ new_content_type = SAME_AS_DISPLAY;
+ else if (vfb->bo)
+ new_content_type = SEPARATE_BO;
+@@ -1007,29 +1030,29 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
+ metadata.num_sizes = 1;
+ metadata.scanout = true;
+ } else {
+- metadata = new_vfbs->surface->metadata;
++ metadata = vmw_user_object_surface(&new_vfbs->uo)->metadata;
+ }
+
+ metadata.base_size.width = hdisplay;
+ metadata.base_size.height = vdisplay;
+ metadata.base_size.depth = 1;
+
+- if (vps->surf) {
++ if (vmw_user_object_surface(&vps->uo)) {
+ struct drm_vmw_size cur_base_size =
+- vps->surf->metadata.base_size;
++ vmw_user_object_surface(&vps->uo)->metadata.base_size;
+
+ if (cur_base_size.width != metadata.base_size.width ||
+ cur_base_size.height != metadata.base_size.height ||
+- vps->surf->metadata.format != metadata.format) {
++ vmw_user_object_surface(&vps->uo)->metadata.format != metadata.format) {
+ WARN_ON(vps->pinned != 0);
+- vmw_surface_unreference(&vps->surf);
++ vmw_user_object_unref(&vps->uo);
+ }
+
+ }
+
+- if (!vps->surf) {
++ if (!vmw_user_object_surface(&vps->uo)) {
+ ret = vmw_gb_surface_define(dev_priv, &metadata,
+- &vps->surf);
++ &vps->uo.surface);
+ if (ret != 0) {
+ DRM_ERROR("Couldn't allocate STDU surface.\n");
+ return ret;
+@@ -1042,18 +1065,19 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
+ * The only time we add a reference in prepare_fb is if the
+ * state object doesn't have a reference to begin with
+ */
+- if (vps->surf) {
++ if (vmw_user_object_surface(&vps->uo)) {
+ WARN_ON(vps->pinned != 0);
+- vmw_surface_unreference(&vps->surf);
++ vmw_user_object_unref(&vps->uo);
+ }
+
+- vps->surf = vmw_surface_reference(new_vfbs->surface);
++ memcpy(&vps->uo, &new_vfbs->uo, sizeof(vps->uo));
++ vmw_user_object_ref(&vps->uo);
+ }
+
+- if (vps->surf) {
++ if (vmw_user_object_surface(&vps->uo)) {
+
+ /* Pin new surface before flipping */
+- ret = vmw_resource_pin(&vps->surf->res, false);
++ ret = vmw_resource_pin(&vmw_user_object_surface(&vps->uo)->res, false);
+ if (ret)
+ goto out_srf_unref;
+
+@@ -1062,6 +1086,34 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
+
+ vps->content_fb_type = new_content_type;
+
++ /*
++ * The drm fb code will do blit's via the vmap interface, which doesn't
++ * trigger vmw_bo page dirty tracking due to being kernel side (and thus
++ * doesn't require mmap'ing) so we have to update the surface's dirty
++ * regions by hand but we want to be careful to not overwrite the
++ * resource if it has been written to by the gpu (res_dirty).
++ */
++ if (vps->uo.buffer && vps->uo.buffer->is_dumb) {
++ struct vmw_surface *surf = vmw_user_object_surface(&vps->uo);
++ struct vmw_resource *res = &surf->res;
++
++ if (!res->res_dirty && drm_atomic_helper_damage_merged(old_state,
++ new_state,
++ &rect)) {
++ /*
++ * At some point it might be useful to actually translate
++ * (rect.x1, rect.y1) => start, and (rect.x2, rect.y2) => end,
++ * but currently the fb code will just report the entire fb
++ * dirty so in practice it doesn't matter.
++ */
++ pgoff_t start = res->guest_memory_offset >> PAGE_SHIFT;
++ pgoff_t end = __KERNEL_DIV_ROUND_UP(res->guest_memory_offset +
++ res->guest_memory_size,
++ PAGE_SIZE);
++ vmw_resource_dirty_update(res, start, end);
++ }
++ }
++
+ /*
+ * This should only happen if the buffer object is too large to create a
+ * proxy surface for.
+@@ -1072,7 +1124,7 @@ vmw_stdu_primary_plane_prepare_fb(struct drm_plane *plane,
+ return 0;
+
+ out_srf_unref:
+- vmw_surface_unreference(&vps->surf);
++ vmw_user_object_unref(&vps->uo);
+ return ret;
+ }
+
+@@ -1214,14 +1266,8 @@ static uint32_t
+ vmw_stdu_surface_fifo_size_same_display(struct vmw_du_update_plane *update,
+ uint32_t num_hits)
+ {
+- struct vmw_framebuffer_surface *vfbs;
+ uint32_t size = 0;
+
+- vfbs = container_of(update->vfb, typeof(*vfbs), base);
+-
+- if (vfbs->is_bo_proxy)
+- size += sizeof(struct vmw_stdu_update_gb_image) * num_hits;
+-
+ size += sizeof(struct vmw_stdu_update);
+
+ return size;
+@@ -1230,61 +1276,14 @@ vmw_stdu_surface_fifo_size_same_display(struct vmw_du_update_plane *update,
+ static uint32_t vmw_stdu_surface_fifo_size(struct vmw_du_update_plane *update,
+ uint32_t num_hits)
+ {
+- struct vmw_framebuffer_surface *vfbs;
+ uint32_t size = 0;
+
+- vfbs = container_of(update->vfb, typeof(*vfbs), base);
+-
+- if (vfbs->is_bo_proxy)
+- size += sizeof(struct vmw_stdu_update_gb_image) * num_hits;
+-
+ size += sizeof(struct vmw_stdu_surface_copy) + sizeof(SVGA3dCopyBox) *
+ num_hits + sizeof(struct vmw_stdu_update);
+
+ return size;
+ }
+
+-static uint32_t
+-vmw_stdu_surface_update_proxy(struct vmw_du_update_plane *update, void *cmd)
+-{
+- struct vmw_framebuffer_surface *vfbs;
+- struct drm_plane_state *state = update->plane->state;
+- struct drm_plane_state *old_state = update->old_state;
+- struct vmw_stdu_update_gb_image *cmd_update = cmd;
+- struct drm_atomic_helper_damage_iter iter;
+- struct drm_rect clip;
+- uint32_t copy_size = 0;
+-
+- vfbs = container_of(update->vfb, typeof(*vfbs), base);
+-
+- /*
+- * proxy surface is special where a buffer object type fb is wrapped
+- * in a surface and need an update gb image command to sync with device.
+- */
+- drm_atomic_helper_damage_iter_init(&iter, old_state, state);
+- drm_atomic_for_each_plane_damage(&iter, &clip) {
+- SVGA3dBox *box = &cmd_update->body.box;
+-
+- cmd_update->header.id = SVGA_3D_CMD_UPDATE_GB_IMAGE;
+- cmd_update->header.size = sizeof(cmd_update->body);
+- cmd_update->body.image.sid = vfbs->surface->res.id;
+- cmd_update->body.image.face = 0;
+- cmd_update->body.image.mipmap = 0;
+-
+- box->x = clip.x1;
+- box->y = clip.y1;
+- box->z = 0;
+- box->w = drm_rect_width(&clip);
+- box->h = drm_rect_height(&clip);
+- box->d = 1;
+-
+- copy_size += sizeof(*cmd_update);
+- cmd_update++;
+- }
+-
+- return copy_size;
+-}
+-
+ static uint32_t
+ vmw_stdu_surface_populate_copy(struct vmw_du_update_plane *update, void *cmd,
+ uint32_t num_hits)
+@@ -1299,7 +1298,7 @@ vmw_stdu_surface_populate_copy(struct vmw_du_update_plane *update, void *cmd,
+ cmd_copy->header.id = SVGA_3D_CMD_SURFACE_COPY;
+ cmd_copy->header.size = sizeof(cmd_copy->body) + sizeof(SVGA3dCopyBox) *
+ num_hits;
+- cmd_copy->body.src.sid = vfbs->surface->res.id;
++ cmd_copy->body.src.sid = vmw_user_object_surface(&vfbs->uo)->res.id;
+ cmd_copy->body.dest.sid = stdu->display_srf->res.id;
+
+ return sizeof(*cmd_copy);
+@@ -1370,10 +1369,7 @@ static int vmw_stdu_plane_update_surface(struct vmw_private *dev_priv,
+ srf_update.mutex = &dev_priv->cmdbuf_mutex;
+ srf_update.intr = true;
+
+- if (vfbs->is_bo_proxy)
+- srf_update.post_prepare = vmw_stdu_surface_update_proxy;
+-
+- if (vfbs->surface->res.id != stdu->display_srf->res.id) {
++ if (vmw_user_object_surface(&vfbs->uo)->res.id != stdu->display_srf->res.id) {
+ srf_update.calc_fifo_size = vmw_stdu_surface_fifo_size;
+ srf_update.pre_clip = vmw_stdu_surface_populate_copy;
+ srf_update.clip = vmw_stdu_surface_populate_clip;
+@@ -1417,7 +1413,7 @@ vmw_stdu_primary_plane_atomic_update(struct drm_plane *plane,
+ stdu = vmw_crtc_to_stdu(crtc);
+ dev_priv = vmw_priv(crtc->dev);
+
+- stdu->display_srf = vps->surf;
++ stdu->display_srf = vmw_user_object_surface(&vps->uo);
+ stdu->content_fb_type = vps->content_fb_type;
+ stdu->cpp = vps->cpp;
+
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+index e7a744dfcecfd..8ae6a761c9003 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_surface.c
+@@ -1,7 +1,8 @@
+ // SPDX-License-Identifier: GPL-2.0 OR MIT
+ /**************************************************************************
+ *
+- * Copyright 2009-2023 VMware, Inc., Palo Alto, CA., USA
++ * Copyright (c) 2009-2024 Broadcom. All Rights Reserved. The term
++ * “Broadcom” refers to Broadcom Inc. and/or its subsidiaries.
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a
+ * copy of this software and associated documentation files (the
+@@ -36,9 +37,6 @@
+ #include <drm/ttm/ttm_placement.h>
+
+ #define SVGA3D_FLAGS_64(upper32, lower32) (((uint64_t)upper32 << 32) | lower32)
+-#define SVGA3D_FLAGS_UPPER_32(svga3d_flags) (svga3d_flags >> 32)
+-#define SVGA3D_FLAGS_LOWER_32(svga3d_flags) \
+- (svga3d_flags & ((uint64_t)U32_MAX))
+
+ /**
+ * struct vmw_user_surface - User-space visible surface resource
+@@ -686,6 +684,14 @@ static void vmw_user_surface_base_release(struct ttm_base_object **p_base)
+ struct vmw_resource *res = &user_srf->srf.res;
+
+ *p_base = NULL;
++
++ /*
++ * Dumb buffers own the resource and they'll unref the
++ * resource themselves
++ */
++ if (res && res->guest_memory_bo && res->guest_memory_bo->is_dumb)
++ return;
++
+ vmw_resource_unreference(&res);
+ }
+
+@@ -812,7 +818,8 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
+ }
+ }
+ res->guest_memory_size = cur_bo_offset;
+- if (metadata->scanout &&
++ if (!file_priv->atomic &&
++ metadata->scanout &&
+ metadata->num_sizes == 1 &&
+ metadata->sizes[0].width == VMW_CURSOR_SNOOP_WIDTH &&
+ metadata->sizes[0].height == VMW_CURSOR_SNOOP_HEIGHT &&
+@@ -864,6 +871,7 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
+ vmw_resource_unreference(&res);
+ goto out_unlock;
+ }
++ vmw_bo_add_detached_resource(res->guest_memory_bo, res);
+ }
+
+ tmp = vmw_resource_reference(&srf->res);
+@@ -892,6 +900,113 @@ int vmw_surface_define_ioctl(struct drm_device *dev, void *data,
+ return ret;
+ }
+
++static struct vmw_user_surface *
++vmw_lookup_user_surface_for_buffer(struct vmw_private *vmw, struct vmw_bo *bo,
++ u32 handle)
++{
++ struct vmw_user_surface *user_srf = NULL;
++ struct vmw_surface *surf;
++ struct ttm_base_object *base;
++
++ surf = vmw_bo_surface(bo);
++ if (surf) {
++ rcu_read_lock();
++ user_srf = container_of(surf, struct vmw_user_surface, srf);
++ base = &user_srf->prime.base;
++ if (base && !kref_get_unless_zero(&base->refcount)) {
++ drm_dbg_driver(&vmw->drm,
++ "%s: referencing a stale surface handle %d\n",
++ __func__, handle);
++ base = NULL;
++ user_srf = NULL;
++ }
++ rcu_read_unlock();
++ }
++
++ return user_srf;
++}
++
++struct vmw_surface *vmw_lookup_surface_for_buffer(struct vmw_private *vmw,
++ struct vmw_bo *bo,
++ u32 handle)
++{
++ struct vmw_user_surface *user_srf =
++ vmw_lookup_user_surface_for_buffer(vmw, bo, handle);
++ struct vmw_surface *surf = NULL;
++ struct ttm_base_object *base;
++
++ if (user_srf) {
++ surf = vmw_surface_reference(&user_srf->srf);
++ base = &user_srf->prime.base;
++ ttm_base_object_unref(&base);
++ }
++ return surf;
++}
++
++u32 vmw_lookup_surface_handle_for_buffer(struct vmw_private *vmw,
++ struct vmw_bo *bo,
++ u32 handle)
++{
++ struct vmw_user_surface *user_srf =
++ vmw_lookup_user_surface_for_buffer(vmw, bo, handle);
++ int surf_handle = 0;
++ struct ttm_base_object *base;
++
++ if (user_srf) {
++ base = &user_srf->prime.base;
++ surf_handle = (u32)base->handle;
++ ttm_base_object_unref(&base);
++ }
++ return surf_handle;
++}
++
++static int vmw_buffer_prime_to_surface_base(struct vmw_private *dev_priv,
++ struct drm_file *file_priv,
++ u32 fd, u32 *handle,
++ struct ttm_base_object **base_p)
++{
++ struct ttm_base_object *base;
++ struct vmw_bo *bo;
++ struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
++ struct vmw_user_surface *user_srf;
++ int ret;
++
++ ret = drm_gem_prime_fd_to_handle(&dev_priv->drm, file_priv, fd, handle);
++ if (ret) {
++ drm_warn(&dev_priv->drm,
++ "Wasn't able to find user buffer for fd = %u.\n", fd);
++ return ret;
++ }
++
++ ret = vmw_user_bo_lookup(file_priv, *handle, &bo);
++ if (ret) {
++ drm_warn(&dev_priv->drm,
++ "Wasn't able to lookup user buffer for handle = %u.\n", *handle);
++ return ret;
++ }
++
++ user_srf = vmw_lookup_user_surface_for_buffer(dev_priv, bo, *handle);
++ if (WARN_ON(!user_srf)) {
++ drm_warn(&dev_priv->drm,
++ "User surface fd %d (handle %d) is null.\n", fd, *handle);
++ ret = -EINVAL;
++ goto out;
++ }
++
++ base = &user_srf->prime.base;
++ ret = ttm_ref_object_add(tfile, base, NULL, false);
++ if (ret) {
++ drm_warn(&dev_priv->drm,
++ "Couldn't add an object ref for the buffer (%d).\n", *handle);
++ goto out;
++ }
++
++ *base_p = base;
++out:
++ vmw_user_bo_unref(&bo);
++
++ return ret;
++}
+
+ static int
+ vmw_surface_handle_reference(struct vmw_private *dev_priv,
+@@ -901,15 +1016,19 @@ vmw_surface_handle_reference(struct vmw_private *dev_priv,
+ struct ttm_base_object **base_p)
+ {
+ struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
+- struct vmw_user_surface *user_srf;
++ struct vmw_user_surface *user_srf = NULL;
+ uint32_t handle;
+ struct ttm_base_object *base;
+ int ret;
+
+ if (handle_type == DRM_VMW_HANDLE_PRIME) {
+ ret = ttm_prime_fd_to_handle(tfile, u_handle, &handle);
+- if (unlikely(ret != 0))
+- return ret;
++ if (ret)
++ return vmw_buffer_prime_to_surface_base(dev_priv,
++ file_priv,
++ u_handle,
++ &handle,
++ base_p);
+ } else {
+ handle = u_handle;
+ }
+@@ -1503,7 +1622,12 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
+ ret = vmw_user_bo_lookup(file_priv, req->base.buffer_handle,
+ &res->guest_memory_bo);
+ if (ret == 0) {
+- if (res->guest_memory_bo->tbo.base.size < res->guest_memory_size) {
++ if (res->guest_memory_bo->is_dumb) {
++ VMW_DEBUG_USER("Can't backup surface with a dumb buffer.\n");
++ vmw_user_bo_unref(&res->guest_memory_bo);
++ ret = -EINVAL;
++ goto out_unlock;
++ } else if (res->guest_memory_bo->tbo.base.size < res->guest_memory_size) {
+ VMW_DEBUG_USER("Surface backup buffer too small.\n");
+ vmw_user_bo_unref(&res->guest_memory_bo);
+ ret = -EINVAL;
+@@ -1560,6 +1684,7 @@ vmw_gb_surface_define_internal(struct drm_device *dev,
+ rep->handle = user_srf->prime.base.handle;
+ rep->backup_size = res->guest_memory_size;
+ if (res->guest_memory_bo) {
++ vmw_bo_add_detached_resource(res->guest_memory_bo, res);
+ rep->buffer_map_handle =
+ drm_vma_node_offset_addr(&res->guest_memory_bo->tbo.base.vma_node);
+ rep->buffer_size = res->guest_memory_bo->tbo.base.size;
+@@ -2100,3 +2225,140 @@ int vmw_gb_surface_define(struct vmw_private *dev_priv,
+ out_unlock:
+ return ret;
+ }
++
++static SVGA3dSurfaceFormat vmw_format_bpp_to_svga(struct vmw_private *vmw,
++ int bpp)
++{
++ switch (bpp) {
++ case 8: /* DRM_FORMAT_C8 */
++ return SVGA3D_P8;
++ case 16: /* DRM_FORMAT_RGB565 */
++ return SVGA3D_R5G6B5;
++ case 32: /* DRM_FORMAT_XRGB8888 */
++ if (has_sm4_context(vmw))
++ return SVGA3D_B8G8R8X8_UNORM;
++ return SVGA3D_X8R8G8B8;
++ default:
++ drm_warn(&vmw->drm, "Unsupported format bpp: %d\n", bpp);
++ return SVGA3D_X8R8G8B8;
++ }
++}
++
++/**
++ * vmw_dumb_create - Create a dumb kms buffer
++ *
++ * @file_priv: Pointer to a struct drm_file identifying the caller.
++ * @dev: Pointer to the drm device.
++ * @args: Pointer to a struct drm_mode_create_dumb structure
++ * Return: Zero on success, negative error code on failure.
++ *
++ * This is a driver callback for the core drm create_dumb functionality.
++ * Note that this is very similar to the vmw_bo_alloc ioctl, except
++ * that the arguments have a different format.
++ */
++int vmw_dumb_create(struct drm_file *file_priv,
++ struct drm_device *dev,
++ struct drm_mode_create_dumb *args)
++{
++ struct vmw_private *dev_priv = vmw_priv(dev);
++ struct ttm_object_file *tfile = vmw_fpriv(file_priv)->tfile;
++ struct vmw_bo *vbo = NULL;
++ struct vmw_resource *res = NULL;
++ union drm_vmw_gb_surface_create_ext_arg arg = { 0 };
++ struct drm_vmw_gb_surface_create_ext_req *req = &arg.req;
++ int ret;
++ struct drm_vmw_size drm_size = {
++ .width = args->width,
++ .height = args->height,
++ .depth = 1,
++ };
++ SVGA3dSurfaceFormat format = vmw_format_bpp_to_svga(dev_priv, args->bpp);
++ const struct SVGA3dSurfaceDesc *desc = vmw_surface_get_desc(format);
++ SVGA3dSurfaceAllFlags flags = SVGA3D_SURFACE_HINT_TEXTURE |
++ SVGA3D_SURFACE_HINT_RENDERTARGET |
++ SVGA3D_SURFACE_SCREENTARGET |
++ SVGA3D_SURFACE_BIND_SHADER_RESOURCE |
++ SVGA3D_SURFACE_BIND_RENDER_TARGET;
++
++ /*
++ * Without mob support we're just going to use raw memory buffer
++ * because we wouldn't be able to support full surface coherency
++ * without mobs
++ */
++ if (!dev_priv->has_mob) {
++ int cpp = DIV_ROUND_UP(args->bpp, 8);
++
++ switch (cpp) {
++ case 1: /* DRM_FORMAT_C8 */
++ case 2: /* DRM_FORMAT_RGB565 */
++ case 4: /* DRM_FORMAT_XRGB8888 */
++ break;
++ default:
++ /*
++ * Dumb buffers don't allow anything else.
++ * This is tested via IGT's dumb_buffers
++ */
++ return -EINVAL;
++ }
++
++ args->pitch = args->width * cpp;
++ args->size = ALIGN(args->pitch * args->height, PAGE_SIZE);
++
++ ret = vmw_gem_object_create_with_handle(dev_priv, file_priv,
++ args->size, &args->handle,
++ &vbo);
++ /* drop reference from allocate - handle holds it now */
++ drm_gem_object_put(&vbo->tbo.base);
++ return ret;
++ }
++
++ req->version = drm_vmw_gb_surface_v1;
++ req->multisample_pattern = SVGA3D_MS_PATTERN_NONE;
++ req->quality_level = SVGA3D_MS_QUALITY_NONE;
++ req->buffer_byte_stride = 0;
++ req->must_be_zero = 0;
++ req->base.svga3d_flags = SVGA3D_FLAGS_LOWER_32(flags);
++ req->svga3d_flags_upper_32_bits = SVGA3D_FLAGS_UPPER_32(flags);
++ req->base.format = (uint32_t)format;
++ req->base.drm_surface_flags = drm_vmw_surface_flag_scanout;
++ req->base.drm_surface_flags |= drm_vmw_surface_flag_shareable;
++ req->base.drm_surface_flags |= drm_vmw_surface_flag_create_buffer;
++ req->base.drm_surface_flags |= drm_vmw_surface_flag_coherent;
++ req->base.base_size.width = args->width;
++ req->base.base_size.height = args->height;
++ req->base.base_size.depth = 1;
++ req->base.array_size = 0;
++ req->base.mip_levels = 1;
++ req->base.multisample_count = 0;
++ req->base.buffer_handle = SVGA3D_INVALID_ID;
++ req->base.autogen_filter = SVGA3D_TEX_FILTER_NONE;
++ ret = vmw_gb_surface_define_ext_ioctl(dev, &arg, file_priv);
++ if (ret) {
++ drm_warn(dev, "Unable to create a dumb buffer\n");
++ return ret;
++ }
++
++ args->handle = arg.rep.buffer_handle;
++ args->size = arg.rep.buffer_size;
++ args->pitch = vmw_surface_calculate_pitch(desc, &drm_size);
++
++ ret = vmw_user_resource_lookup_handle(dev_priv, tfile, arg.rep.handle,
++ user_surface_converter,
++ &res);
++ if (ret) {
++ drm_err(dev, "Created resource handle doesn't exist!\n");
++ goto err;
++ }
++
++ vbo = res->guest_memory_bo;
++ vbo->is_dumb = true;
++ vbo->dumb_surface = vmw_res_to_srf(res);
++
++err:
++ if (res)
++ vmw_resource_unreference(&res);
++ if (ret)
++ ttm_ref_object_base_unref(tfile, arg.rep.handle);
++
++ return ret;
++}
+diff --git a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
+index 7e93a45948f79..ac002048d8e5e 100644
+--- a/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
++++ b/drivers/gpu/drm/vmwgfx/vmwgfx_vkms.c
+@@ -76,7 +76,7 @@ vmw_surface_sync(struct vmw_private *vmw,
+ return ret;
+ }
+
+-static int
++static void
+ compute_crc(struct drm_crtc *crtc,
+ struct vmw_surface *surf,
+ u32 *crc)
+@@ -102,8 +102,6 @@ compute_crc(struct drm_crtc *crtc,
+ }
+
+ vmw_bo_unmap(bo);
+-
+- return 0;
+ }
+
+ static void
+@@ -117,7 +115,6 @@ crc_generate_worker(struct work_struct *work)
+ u64 frame_start, frame_end;
+ u32 crc32 = 0;
+ struct vmw_surface *surf = 0;
+- int ret;
+
+ spin_lock_irq(&du->vkms.crc_state_lock);
+ crc_pending = du->vkms.crc_pending;
+@@ -131,22 +128,24 @@ crc_generate_worker(struct work_struct *work)
+ return;
+
+ spin_lock_irq(&du->vkms.crc_state_lock);
+- surf = du->vkms.surface;
++ surf = vmw_surface_reference(du->vkms.surface);
+ spin_unlock_irq(&du->vkms.crc_state_lock);
+
+- if (vmw_surface_sync(vmw, surf)) {
+- drm_warn(crtc->dev, "CRC worker wasn't able to sync the crc surface!\n");
+- return;
+- }
++ if (surf) {
++ if (vmw_surface_sync(vmw, surf)) {
++ drm_warn(
++ crtc->dev,
++ "CRC worker wasn't able to sync the crc surface!\n");
++ return;
++ }
+
+- ret = compute_crc(crtc, surf, &crc32);
+- if (ret)
+- return;
++ compute_crc(crtc, surf, &crc32);
++ vmw_surface_unreference(&surf);
++ }
+
+ spin_lock_irq(&du->vkms.crc_state_lock);
+ frame_start = du->vkms.frame_start;
+ frame_end = du->vkms.frame_end;
+- crc_pending = du->vkms.crc_pending;
+ du->vkms.frame_start = 0;
+ du->vkms.frame_end = 0;
+ du->vkms.crc_pending = false;
+@@ -165,7 +164,7 @@ vmw_vkms_vblank_simulate(struct hrtimer *timer)
+ struct vmw_display_unit *du = container_of(timer, struct vmw_display_unit, vkms.timer);
+ struct drm_crtc *crtc = &du->crtc;
+ struct vmw_private *vmw = vmw_priv(crtc->dev);
+- struct vmw_surface *surf = NULL;
++ bool has_surface = false;
+ u64 ret_overrun;
+ bool locked, ret;
+
+@@ -180,10 +179,10 @@ vmw_vkms_vblank_simulate(struct hrtimer *timer)
+ WARN_ON(!ret);
+ if (!locked)
+ return HRTIMER_RESTART;
+- surf = du->vkms.surface;
++ has_surface = du->vkms.surface != NULL;
+ vmw_vkms_unlock(crtc);
+
+- if (du->vkms.crc_enabled && surf) {
++ if (du->vkms.crc_enabled && has_surface) {
+ u64 frame = drm_crtc_accurate_vblank_count(crtc);
+
+ spin_lock(&du->vkms.crc_state_lock);
+@@ -337,6 +336,8 @@ vmw_vkms_crtc_cleanup(struct drm_crtc *crtc)
+ {
+ struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+
++ if (du->vkms.surface)
++ vmw_surface_unreference(&du->vkms.surface);
+ WARN_ON(work_pending(&du->vkms.crc_generator_work));
+ hrtimer_cancel(&du->vkms.timer);
+ }
+@@ -498,9 +499,12 @@ vmw_vkms_set_crc_surface(struct drm_crtc *crtc,
+ struct vmw_display_unit *du = vmw_crtc_to_du(crtc);
+ struct vmw_private *vmw = vmw_priv(crtc->dev);
+
+- if (vmw->vkms_enabled) {
++ if (vmw->vkms_enabled && du->vkms.surface != surf) {
+ WARN_ON(atomic_read(&du->vkms.atomic_lock) != VMW_VKMS_LOCK_MODESET);
+- du->vkms.surface = surf;
++ if (du->vkms.surface)
++ vmw_surface_unreference(&du->vkms.surface);
++ if (surf)
++ du->vkms.surface = vmw_surface_reference(surf);
+ }
+ }
+
+diff --git a/drivers/hid/amd-sfh-hid/amd_sfh_client.c b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
+index bdb578e0899f5..4b59687ff5d82 100644
+--- a/drivers/hid/amd-sfh-hid/amd_sfh_client.c
++++ b/drivers/hid/amd-sfh-hid/amd_sfh_client.c
+@@ -288,12 +288,22 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
+ mp2_ops->start(privdata, info);
+ cl_data->sensor_sts[i] = amd_sfh_wait_for_response
+ (privdata, cl_data->sensor_idx[i], SENSOR_ENABLED);
++
++ if (cl_data->sensor_sts[i] == SENSOR_ENABLED)
++ cl_data->is_any_sensor_enabled = true;
++ }
++
++ if (!cl_data->is_any_sensor_enabled ||
++ (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) {
++ dev_warn(dev, "Failed to discover, sensors not enabled is %d\n",
++ cl_data->is_any_sensor_enabled);
++ rc = -EOPNOTSUPP;
++ goto cleanup;
+ }
+
+ for (i = 0; i < cl_data->num_hid_devices; i++) {
+ cl_data->cur_hid_dev = i;
+ if (cl_data->sensor_sts[i] == SENSOR_ENABLED) {
+- cl_data->is_any_sensor_enabled = true;
+ rc = amdtp_hid_probe(i, cl_data);
+ if (rc)
+ goto cleanup;
+@@ -305,12 +315,6 @@ int amd_sfh_hid_client_init(struct amd_mp2_dev *privdata)
+ cl_data->sensor_sts[i]);
+ }
+
+- if (!cl_data->is_any_sensor_enabled ||
+- (mp2_ops->discovery_status && mp2_ops->discovery_status(privdata) == 0)) {
+- dev_warn(dev, "Failed to discover, sensors not enabled is %d\n", cl_data->is_any_sensor_enabled);
+- rc = -EOPNOTSUPP;
+- goto cleanup;
+- }
+ schedule_delayed_work(&cl_data->work_buffer, msecs_to_jiffies(AMD_SFH_IDLE_LOOP));
+ return 0;
+
+diff --git a/drivers/hid/wacom_wac.c b/drivers/hid/wacom_wac.c
+index a44367aef6216..20de97ce0f5ee 100644
+--- a/drivers/hid/wacom_wac.c
++++ b/drivers/hid/wacom_wac.c
+@@ -714,13 +714,12 @@ static int wacom_intuos_get_tool_type(int tool_id)
+ case 0x8e2: /* IntuosHT2 pen */
+ case 0x022:
+ case 0x200: /* Pro Pen 3 */
+- case 0x04200: /* Pro Pen 3 */
+ case 0x10842: /* MobileStudio Pro Pro Pen slim */
+ case 0x14802: /* Intuos4/5 13HD/24HD Classic Pen */
+ case 0x16802: /* Cintiq 13HD Pro Pen */
+ case 0x18802: /* DTH2242 Pen */
+ case 0x10802: /* Intuos4/5 13HD/24HD General Pen */
+- case 0x80842: /* Intuos Pro and Cintiq Pro 3D Pen */
++ case 0x8842: /* Intuos Pro and Cintiq Pro 3D Pen */
+ tool_type = BTN_TOOL_PEN;
+ break;
+
+diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+index 43952689bfb0c..23627c973e40f 100644
+--- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c
++++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c
+@@ -7491,8 +7491,8 @@ static int bnxt_get_avail_msix(struct bnxt *bp, int num);
+ static int __bnxt_reserve_rings(struct bnxt *bp)
+ {
+ struct bnxt_hw_rings hwr = {0};
++ int rx_rings, old_rx_rings, rc;
+ int cp = bp->cp_nr_rings;
+- int rx_rings, rc;
+ int ulp_msix = 0;
+ bool sh = false;
+ int tx_cp;
+@@ -7526,6 +7526,7 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
+ hwr.grp = bp->rx_nr_rings;
+ hwr.rss_ctx = bnxt_get_total_rss_ctxs(bp, &hwr);
+ hwr.stat = bnxt_get_func_stat_ctxs(bp);
++ old_rx_rings = bp->hw_resc.resv_rx_rings;
+
+ rc = bnxt_hwrm_reserve_rings(bp, &hwr);
+ if (rc)
+@@ -7580,7 +7581,8 @@ static int __bnxt_reserve_rings(struct bnxt *bp)
+ if (!bnxt_rings_ok(bp, &hwr))
+ return -ENOMEM;
+
+- if (!netif_is_rxfh_configured(bp->dev))
++ if (old_rx_rings != bp->hw_resc.resv_rx_rings &&
++ !netif_is_rxfh_configured(bp->dev))
+ bnxt_set_dflt_rss_indir_tbl(bp, NULL);
+
+ if (!bnxt_ulp_registered(bp->edev) && BNXT_NEW_RM(bp)) {
+diff --git a/drivers/net/ethernet/intel/ice/ice.h b/drivers/net/ethernet/intel/ice/ice.h
+index 99a75a59078ef..caaa10157909e 100644
+--- a/drivers/net/ethernet/intel/ice/ice.h
++++ b/drivers/net/ethernet/intel/ice/ice.h
+@@ -765,18 +765,17 @@ static inline struct xsk_buff_pool *ice_get_xp_from_qid(struct ice_vsi *vsi,
+ }
+
+ /**
+- * ice_xsk_pool - get XSK buffer pool bound to a ring
++ * ice_rx_xsk_pool - assign XSK buff pool to Rx ring
+ * @ring: Rx ring to use
+ *
+- * Returns a pointer to xsk_buff_pool structure if there is a buffer pool
+- * present, NULL otherwise.
++ * Sets XSK buff pool pointer on Rx ring.
+ */
+-static inline struct xsk_buff_pool *ice_xsk_pool(struct ice_rx_ring *ring)
++static inline void ice_rx_xsk_pool(struct ice_rx_ring *ring)
+ {
+ struct ice_vsi *vsi = ring->vsi;
+ u16 qid = ring->q_index;
+
+- return ice_get_xp_from_qid(vsi, qid);
++ WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
+ }
+
+ /**
+@@ -801,7 +800,7 @@ static inline void ice_tx_xsk_pool(struct ice_vsi *vsi, u16 qid)
+ if (!ring)
+ return;
+
+- ring->xsk_pool = ice_get_xp_from_qid(vsi, qid);
++ WRITE_ONCE(ring->xsk_pool, ice_get_xp_from_qid(vsi, qid));
+ }
+
+ /**
+diff --git a/drivers/net/ethernet/intel/ice/ice_base.c b/drivers/net/ethernet/intel/ice/ice_base.c
+index 5d396c1a77314..1facf179a96fd 100644
+--- a/drivers/net/ethernet/intel/ice/ice_base.c
++++ b/drivers/net/ethernet/intel/ice/ice_base.c
+@@ -536,7 +536,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
+ return err;
+ }
+
+- ring->xsk_pool = ice_xsk_pool(ring);
++ ice_rx_xsk_pool(ring);
+ if (ring->xsk_pool) {
+ xdp_rxq_info_unreg(&ring->xdp_rxq);
+
+@@ -597,7 +597,7 @@ static int ice_vsi_cfg_rxq(struct ice_rx_ring *ring)
+ return 0;
+ }
+
+- ok = ice_alloc_rx_bufs_zc(ring, num_bufs);
++ ok = ice_alloc_rx_bufs_zc(ring, ring->xsk_pool, num_bufs);
+ if (!ok) {
+ u16 pf_q = ring->vsi->rxq_map[ring->q_index];
+
+diff --git a/drivers/net/ethernet/intel/ice/ice_main.c b/drivers/net/ethernet/intel/ice/ice_main.c
+index 55a42aad92a51..9b075dd48889e 100644
+--- a/drivers/net/ethernet/intel/ice/ice_main.c
++++ b/drivers/net/ethernet/intel/ice/ice_main.c
+@@ -2949,7 +2949,7 @@ static void ice_vsi_rx_napi_schedule(struct ice_vsi *vsi)
+ ice_for_each_rxq(vsi, i) {
+ struct ice_rx_ring *rx_ring = vsi->rx_rings[i];
+
+- if (rx_ring->xsk_pool)
++ if (READ_ONCE(rx_ring->xsk_pool))
+ napi_schedule(&rx_ring->q_vector->napi);
+ }
+ }
+diff --git a/drivers/net/ethernet/intel/ice/ice_txrx.c b/drivers/net/ethernet/intel/ice/ice_txrx.c
+index 8bb743f78fcb4..8d25b69812698 100644
+--- a/drivers/net/ethernet/intel/ice/ice_txrx.c
++++ b/drivers/net/ethernet/intel/ice/ice_txrx.c
+@@ -456,7 +456,7 @@ void ice_free_rx_ring(struct ice_rx_ring *rx_ring)
+ if (rx_ring->vsi->type == ICE_VSI_PF)
+ if (xdp_rxq_info_is_reg(&rx_ring->xdp_rxq))
+ xdp_rxq_info_unreg(&rx_ring->xdp_rxq);
+- rx_ring->xdp_prog = NULL;
++ WRITE_ONCE(rx_ring->xdp_prog, NULL);
+ if (rx_ring->xsk_pool) {
+ kfree(rx_ring->xdp_buf);
+ rx_ring->xdp_buf = NULL;
+@@ -1521,10 +1521,11 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
+ * budget and be more aggressive about cleaning up the Tx descriptors.
+ */
+ ice_for_each_tx_ring(tx_ring, q_vector->tx) {
++ struct xsk_buff_pool *xsk_pool = READ_ONCE(tx_ring->xsk_pool);
+ bool wd;
+
+- if (tx_ring->xsk_pool)
+- wd = ice_xmit_zc(tx_ring);
++ if (xsk_pool)
++ wd = ice_xmit_zc(tx_ring, xsk_pool);
+ else if (ice_ring_is_xdp(tx_ring))
+ wd = true;
+ else
+@@ -1550,6 +1551,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
+ budget_per_ring = budget;
+
+ ice_for_each_rx_ring(rx_ring, q_vector->rx) {
++ struct xsk_buff_pool *xsk_pool = READ_ONCE(rx_ring->xsk_pool);
+ int cleaned;
+
+ /* A dedicated path for zero-copy allows making a single
+@@ -1557,7 +1559,7 @@ int ice_napi_poll(struct napi_struct *napi, int budget)
+ * ice_clean_rx_irq function and makes the codebase cleaner.
+ */
+ cleaned = rx_ring->xsk_pool ?
+- ice_clean_rx_irq_zc(rx_ring, budget_per_ring) :
++ ice_clean_rx_irq_zc(rx_ring, xsk_pool, budget_per_ring) :
+ ice_clean_rx_irq(rx_ring, budget_per_ring);
+ work_done += cleaned;
+ /* if we clean as many as budgeted, we must not be done */
+diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.c b/drivers/net/ethernet/intel/ice/ice_xsk.c
+index a65955eb23c0b..240a7bec242be 100644
+--- a/drivers/net/ethernet/intel/ice/ice_xsk.c
++++ b/drivers/net/ethernet/intel/ice/ice_xsk.c
+@@ -52,10 +52,8 @@ static void ice_qp_reset_stats(struct ice_vsi *vsi, u16 q_idx)
+ static void ice_qp_clean_rings(struct ice_vsi *vsi, u16 q_idx)
+ {
+ ice_clean_tx_ring(vsi->tx_rings[q_idx]);
+- if (ice_is_xdp_ena_vsi(vsi)) {
+- synchronize_rcu();
++ if (ice_is_xdp_ena_vsi(vsi))
+ ice_clean_tx_ring(vsi->xdp_rings[q_idx]);
+- }
+ ice_clean_rx_ring(vsi->rx_rings[q_idx]);
+ }
+
+@@ -112,25 +110,29 @@ ice_qvec_dis_irq(struct ice_vsi *vsi, struct ice_rx_ring *rx_ring,
+ * ice_qvec_cfg_msix - Enable IRQ for given queue vector
+ * @vsi: the VSI that contains queue vector
+ * @q_vector: queue vector
++ * @qid: queue index
+ */
+ static void
+-ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector)
++ice_qvec_cfg_msix(struct ice_vsi *vsi, struct ice_q_vector *q_vector, u16 qid)
+ {
+ u16 reg_idx = q_vector->reg_idx;
+ struct ice_pf *pf = vsi->back;
+ struct ice_hw *hw = &pf->hw;
+- struct ice_tx_ring *tx_ring;
+- struct ice_rx_ring *rx_ring;
++ int q, _qid = qid;
+
+ ice_cfg_itr(hw, q_vector);
+
+- ice_for_each_tx_ring(tx_ring, q_vector->tx)
+- ice_cfg_txq_interrupt(vsi, tx_ring->reg_idx, reg_idx,
+- q_vector->tx.itr_idx);
++ for (q = 0; q < q_vector->num_ring_tx; q++) {
++ ice_cfg_txq_interrupt(vsi, _qid, reg_idx, q_vector->tx.itr_idx);
++ _qid++;
++ }
++
++ _qid = qid;
+
+- ice_for_each_rx_ring(rx_ring, q_vector->rx)
+- ice_cfg_rxq_interrupt(vsi, rx_ring->reg_idx, reg_idx,
+- q_vector->rx.itr_idx);
++ for (q = 0; q < q_vector->num_ring_rx; q++) {
++ ice_cfg_rxq_interrupt(vsi, _qid, reg_idx, q_vector->rx.itr_idx);
++ _qid++;
++ }
+
+ ice_flush(hw);
+ }
+@@ -164,6 +166,7 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+ struct ice_tx_ring *tx_ring;
+ struct ice_rx_ring *rx_ring;
+ int timeout = 50;
++ int fail = 0;
+ int err;
+
+ if (q_idx >= vsi->num_rxq || q_idx >= vsi->num_txq)
+@@ -180,15 +183,17 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+ usleep_range(1000, 2000);
+ }
+
++ synchronize_net();
++ netif_carrier_off(vsi->netdev);
++ netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
++
+ ice_qvec_dis_irq(vsi, rx_ring, q_vector);
+ ice_qvec_toggle_napi(vsi, q_vector, false);
+
+- netif_tx_stop_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
+-
+ ice_fill_txq_meta(vsi, tx_ring, &txq_meta);
+ err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, tx_ring, &txq_meta);
+- if (err)
+- return err;
++ if (!fail)
++ fail = err;
+ if (ice_is_xdp_ena_vsi(vsi)) {
+ struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
+
+@@ -196,17 +201,15 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+ ice_fill_txq_meta(vsi, xdp_ring, &txq_meta);
+ err = ice_vsi_stop_tx_ring(vsi, ICE_NO_RESET, 0, xdp_ring,
+ &txq_meta);
+- if (err)
+- return err;
++ if (!fail)
++ fail = err;
+ }
+- err = ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, true);
+- if (err)
+- return err;
+
++ ice_vsi_ctrl_one_rx_ring(vsi, false, q_idx, false);
+ ice_qp_clean_rings(vsi, q_idx);
+ ice_qp_reset_stats(vsi, q_idx);
+
+- return 0;
++ return fail;
+ }
+
+ /**
+@@ -219,40 +222,48 @@ static int ice_qp_dis(struct ice_vsi *vsi, u16 q_idx)
+ static int ice_qp_ena(struct ice_vsi *vsi, u16 q_idx)
+ {
+ struct ice_q_vector *q_vector;
++ int fail = 0;
++ bool link_up;
+ int err;
+
+ err = ice_vsi_cfg_single_txq(vsi, vsi->tx_rings, q_idx);
+- if (err)
+- return err;
++ if (!fail)
++ fail = err;
+
+ if (ice_is_xdp_ena_vsi(vsi)) {
+ struct ice_tx_ring *xdp_ring = vsi->xdp_rings[q_idx];
+
+ err = ice_vsi_cfg_single_txq(vsi, vsi->xdp_rings, q_idx);
+- if (err)
+- return err;
++ if (!fail)
++ fail = err;
+ ice_set_ring_xdp(xdp_ring);
+ ice_tx_xsk_pool(vsi, q_idx);
+ }
+
+ err = ice_vsi_cfg_single_rxq(vsi, q_idx);
+- if (err)
+- return err;
++ if (!fail)
++ fail = err;
+
+ q_vector = vsi->rx_rings[q_idx]->q_vector;
+- ice_qvec_cfg_msix(vsi, q_vector);
++ ice_qvec_cfg_msix(vsi, q_vector, q_idx);
+
+ err = ice_vsi_ctrl_one_rx_ring(vsi, true, q_idx, true);
+- if (err)
+- return err;
++ if (!fail)
++ fail = err;
+
+ ice_qvec_toggle_napi(vsi, q_vector, true);
+ ice_qvec_ena_irq(vsi, q_vector);
+
+- netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
++ /* make sure NAPI sees updated ice_{t,x}_ring::xsk_pool */
++ synchronize_net();
++ ice_get_link_status(vsi->port_info, &link_up);
++ if (link_up) {
++ netif_tx_start_queue(netdev_get_tx_queue(vsi->netdev, q_idx));
++ netif_carrier_on(vsi->netdev);
++ }
+ clear_bit(ICE_CFG_BUSY, vsi->state);
+
+- return 0;
++ return fail;
+ }
+
+ /**
+@@ -459,6 +470,7 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
+ /**
+ * __ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
+ * @rx_ring: Rx ring
++ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
+ * @count: The number of buffers to allocate
+ *
+ * Place the @count of descriptors onto Rx ring. Handle the ring wrap
+@@ -467,7 +479,8 @@ static u16 ice_fill_rx_descs(struct xsk_buff_pool *pool, struct xdp_buff **xdp,
+ *
+ * Returns true if all allocations were successful, false if any fail.
+ */
+-static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
++static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
++ struct xsk_buff_pool *xsk_pool, u16 count)
+ {
+ u32 nb_buffs_extra = 0, nb_buffs = 0;
+ union ice_32b_rx_flex_desc *rx_desc;
+@@ -479,8 +492,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+ xdp = ice_xdp_buf(rx_ring, ntu);
+
+ if (ntu + count >= rx_ring->count) {
+- nb_buffs_extra = ice_fill_rx_descs(rx_ring->xsk_pool, xdp,
+- rx_desc,
++ nb_buffs_extra = ice_fill_rx_descs(xsk_pool, xdp, rx_desc,
+ rx_ring->count - ntu);
+ if (nb_buffs_extra != rx_ring->count - ntu) {
+ ntu += nb_buffs_extra;
+@@ -493,7 +505,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+ ice_release_rx_desc(rx_ring, 0);
+ }
+
+- nb_buffs = ice_fill_rx_descs(rx_ring->xsk_pool, xdp, rx_desc, count);
++ nb_buffs = ice_fill_rx_descs(xsk_pool, xdp, rx_desc, count);
+
+ ntu += nb_buffs;
+ if (ntu == rx_ring->count)
+@@ -509,6 +521,7 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+ /**
+ * ice_alloc_rx_bufs_zc - allocate a number of Rx buffers
+ * @rx_ring: Rx ring
++ * @xsk_pool: XSK buffer pool to pick buffers to be filled by HW
+ * @count: The number of buffers to allocate
+ *
+ * Wrapper for internal allocation routine; figure out how many tail
+@@ -516,7 +529,8 @@ static bool __ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+ *
+ * Returns true if all calls to internal alloc routine succeeded
+ */
+-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
++bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
++ struct xsk_buff_pool *xsk_pool, u16 count)
+ {
+ u16 rx_thresh = ICE_RING_QUARTER(rx_ring);
+ u16 leftover, i, tail_bumps;
+@@ -525,9 +539,9 @@ bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count)
+ leftover = count - (tail_bumps * rx_thresh);
+
+ for (i = 0; i < tail_bumps; i++)
+- if (!__ice_alloc_rx_bufs_zc(rx_ring, rx_thresh))
++ if (!__ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, rx_thresh))
+ return false;
+- return __ice_alloc_rx_bufs_zc(rx_ring, leftover);
++ return __ice_alloc_rx_bufs_zc(rx_ring, xsk_pool, leftover);
+ }
+
+ /**
+@@ -596,8 +610,10 @@ ice_construct_skb_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp)
+ /**
+ * ice_clean_xdp_irq_zc - produce AF_XDP descriptors to CQ
+ * @xdp_ring: XDP Tx ring
++ * @xsk_pool: AF_XDP buffer pool pointer
+ */
+-static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
++static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring,
++ struct xsk_buff_pool *xsk_pool)
+ {
+ u16 ntc = xdp_ring->next_to_clean;
+ struct ice_tx_desc *tx_desc;
+@@ -648,7 +664,7 @@ static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+ if (xdp_ring->next_to_clean >= cnt)
+ xdp_ring->next_to_clean -= cnt;
+ if (xsk_frames)
+- xsk_tx_completed(xdp_ring->xsk_pool, xsk_frames);
++ xsk_tx_completed(xsk_pool, xsk_frames);
+
+ return completed_frames;
+ }
+@@ -657,6 +673,7 @@ static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+ * ice_xmit_xdp_tx_zc - AF_XDP ZC handler for XDP_TX
+ * @xdp: XDP buffer to xmit
+ * @xdp_ring: XDP ring to produce descriptor onto
++ * @xsk_pool: AF_XDP buffer pool pointer
+ *
+ * note that this function works directly on xdp_buff, no need to convert
+ * it to xdp_frame. xdp_buff pointer is stored to ice_tx_buf so that cleaning
+@@ -666,7 +683,8 @@ static u32 ice_clean_xdp_irq_zc(struct ice_tx_ring *xdp_ring)
+ * was not enough space on XDP ring
+ */
+ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
+- struct ice_tx_ring *xdp_ring)
++ struct ice_tx_ring *xdp_ring,
++ struct xsk_buff_pool *xsk_pool)
+ {
+ struct skb_shared_info *sinfo = NULL;
+ u32 size = xdp->data_end - xdp->data;
+@@ -680,7 +698,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
+
+ free_space = ICE_DESC_UNUSED(xdp_ring);
+ if (free_space < ICE_RING_QUARTER(xdp_ring))
+- free_space += ice_clean_xdp_irq_zc(xdp_ring);
++ free_space += ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
+
+ if (unlikely(!free_space))
+ goto busy;
+@@ -700,7 +718,7 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
+ dma_addr_t dma;
+
+ dma = xsk_buff_xdp_get_dma(xdp);
+- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, size);
++ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, size);
+
+ tx_buf->xdp = xdp;
+ tx_buf->type = ICE_TX_BUF_XSK_TX;
+@@ -742,12 +760,14 @@ static int ice_xmit_xdp_tx_zc(struct xdp_buff *xdp,
+ * @xdp: xdp_buff used as input to the XDP program
+ * @xdp_prog: XDP program to run
+ * @xdp_ring: ring to be used for XDP_TX action
++ * @xsk_pool: AF_XDP buffer pool pointer
+ *
+ * Returns any of ICE_XDP_{PASS, CONSUMED, TX, REDIR}
+ */
+ static int
+ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+- struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring)
++ struct bpf_prog *xdp_prog, struct ice_tx_ring *xdp_ring,
++ struct xsk_buff_pool *xsk_pool)
+ {
+ int err, result = ICE_XDP_PASS;
+ u32 act;
+@@ -758,7 +778,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+ err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog);
+ if (!err)
+ return ICE_XDP_REDIR;
+- if (xsk_uses_need_wakeup(rx_ring->xsk_pool) && err == -ENOBUFS)
++ if (xsk_uses_need_wakeup(xsk_pool) && err == -ENOBUFS)
+ result = ICE_XDP_EXIT;
+ else
+ result = ICE_XDP_CONSUMED;
+@@ -769,7 +789,7 @@ ice_run_xdp_zc(struct ice_rx_ring *rx_ring, struct xdp_buff *xdp,
+ case XDP_PASS:
+ break;
+ case XDP_TX:
+- result = ice_xmit_xdp_tx_zc(xdp, xdp_ring);
++ result = ice_xmit_xdp_tx_zc(xdp, xdp_ring, xsk_pool);
+ if (result == ICE_XDP_CONSUMED)
+ goto out_failure;
+ break;
+@@ -821,14 +841,16 @@ ice_add_xsk_frag(struct ice_rx_ring *rx_ring, struct xdp_buff *first,
+ /**
+ * ice_clean_rx_irq_zc - consumes packets from the hardware ring
+ * @rx_ring: AF_XDP Rx ring
++ * @xsk_pool: AF_XDP buffer pool pointer
+ * @budget: NAPI budget
+ *
+ * Returns number of processed packets on success, remaining budget on failure.
+ */
+-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
++int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
++ struct xsk_buff_pool *xsk_pool,
++ int budget)
+ {
+ unsigned int total_rx_bytes = 0, total_rx_packets = 0;
+- struct xsk_buff_pool *xsk_pool = rx_ring->xsk_pool;
+ u32 ntc = rx_ring->next_to_clean;
+ u32 ntu = rx_ring->next_to_use;
+ struct xdp_buff *first = NULL;
+@@ -891,7 +913,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
+ if (ice_is_non_eop(rx_ring, rx_desc))
+ continue;
+
+- xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring);
++ xdp_res = ice_run_xdp_zc(rx_ring, first, xdp_prog, xdp_ring,
++ xsk_pool);
+ if (likely(xdp_res & (ICE_XDP_TX | ICE_XDP_REDIR))) {
+ xdp_xmit |= xdp_res;
+ } else if (xdp_res == ICE_XDP_EXIT) {
+@@ -940,7 +963,8 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
+ rx_ring->next_to_clean = ntc;
+ entries_to_alloc = ICE_RX_DESC_UNUSED(rx_ring);
+ if (entries_to_alloc > ICE_RING_QUARTER(rx_ring))
+- failure |= !ice_alloc_rx_bufs_zc(rx_ring, entries_to_alloc);
++ failure |= !ice_alloc_rx_bufs_zc(rx_ring, xsk_pool,
++ entries_to_alloc);
+
+ ice_finalize_xdp_rx(xdp_ring, xdp_xmit, 0);
+ ice_update_rx_ring_stats(rx_ring, total_rx_packets, total_rx_bytes);
+@@ -963,17 +987,19 @@ int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget)
+ /**
+ * ice_xmit_pkt - produce a single HW Tx descriptor out of AF_XDP descriptor
+ * @xdp_ring: XDP ring to produce the HW Tx descriptor on
++ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
+ * @desc: AF_XDP descriptor to pull the DMA address and length from
+ * @total_bytes: bytes accumulator that will be used for stats update
+ */
+-static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
++static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring,
++ struct xsk_buff_pool *xsk_pool, struct xdp_desc *desc,
+ unsigned int *total_bytes)
+ {
+ struct ice_tx_desc *tx_desc;
+ dma_addr_t dma;
+
+- dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, desc->addr);
+- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, desc->len);
++ dma = xsk_buff_raw_get_dma(xsk_pool, desc->addr);
++ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, desc->len);
+
+ tx_desc = ICE_TX_DESC(xdp_ring, xdp_ring->next_to_use++);
+ tx_desc->buf_addr = cpu_to_le64(dma);
+@@ -986,10 +1012,13 @@ static void ice_xmit_pkt(struct ice_tx_ring *xdp_ring, struct xdp_desc *desc,
+ /**
+ * ice_xmit_pkt_batch - produce a batch of HW Tx descriptors out of AF_XDP descriptors
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
++ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
+ * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
+ * @total_bytes: bytes accumulator that will be used for stats update
+ */
+-static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
++static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring,
++ struct xsk_buff_pool *xsk_pool,
++ struct xdp_desc *descs,
+ unsigned int *total_bytes)
+ {
+ u16 ntu = xdp_ring->next_to_use;
+@@ -999,8 +1028,8 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
+ loop_unrolled_for(i = 0; i < PKTS_PER_BATCH; i++) {
+ dma_addr_t dma;
+
+- dma = xsk_buff_raw_get_dma(xdp_ring->xsk_pool, descs[i].addr);
+- xsk_buff_raw_dma_sync_for_device(xdp_ring->xsk_pool, dma, descs[i].len);
++ dma = xsk_buff_raw_get_dma(xsk_pool, descs[i].addr);
++ xsk_buff_raw_dma_sync_for_device(xsk_pool, dma, descs[i].len);
+
+ tx_desc = ICE_TX_DESC(xdp_ring, ntu++);
+ tx_desc->buf_addr = cpu_to_le64(dma);
+@@ -1016,60 +1045,69 @@ static void ice_xmit_pkt_batch(struct ice_tx_ring *xdp_ring, struct xdp_desc *de
+ /**
+ * ice_fill_tx_hw_ring - produce the number of Tx descriptors onto ring
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
++ * @xsk_pool: XSK buffer pool to pick buffers to be consumed by HW
+ * @descs: AF_XDP descriptors to pull the DMA addresses and lengths from
+ * @nb_pkts: count of packets to be send
+ * @total_bytes: bytes accumulator that will be used for stats update
+ */
+-static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring, struct xdp_desc *descs,
+- u32 nb_pkts, unsigned int *total_bytes)
++static void ice_fill_tx_hw_ring(struct ice_tx_ring *xdp_ring,
++ struct xsk_buff_pool *xsk_pool,
++ struct xdp_desc *descs, u32 nb_pkts,
++ unsigned int *total_bytes)
+ {
+ u32 batched, leftover, i;
+
+ batched = ALIGN_DOWN(nb_pkts, PKTS_PER_BATCH);
+ leftover = nb_pkts & (PKTS_PER_BATCH - 1);
+ for (i = 0; i < batched; i += PKTS_PER_BATCH)
+- ice_xmit_pkt_batch(xdp_ring, &descs[i], total_bytes);
++ ice_xmit_pkt_batch(xdp_ring, xsk_pool, &descs[i], total_bytes);
+ for (; i < batched + leftover; i++)
+- ice_xmit_pkt(xdp_ring, &descs[i], total_bytes);
++ ice_xmit_pkt(xdp_ring, xsk_pool, &descs[i], total_bytes);
+ }
+
+ /**
+ * ice_xmit_zc - take entries from XSK Tx ring and place them onto HW Tx ring
+ * @xdp_ring: XDP ring to produce the HW Tx descriptors on
++ * @xsk_pool: AF_XDP buffer pool pointer
+ *
+ * Returns true if there is no more work that needs to be done, false otherwise
+ */
+-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring)
++bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool)
+ {
+- struct xdp_desc *descs = xdp_ring->xsk_pool->tx_descs;
++ struct xdp_desc *descs = xsk_pool->tx_descs;
+ u32 nb_pkts, nb_processed = 0;
+ unsigned int total_bytes = 0;
+ int budget;
+
+- ice_clean_xdp_irq_zc(xdp_ring);
++ ice_clean_xdp_irq_zc(xdp_ring, xsk_pool);
++
++ if (!netif_carrier_ok(xdp_ring->vsi->netdev) ||
++ !netif_running(xdp_ring->vsi->netdev))
++ return true;
+
+ budget = ICE_DESC_UNUSED(xdp_ring);
+ budget = min_t(u16, budget, ICE_RING_QUARTER(xdp_ring));
+
+- nb_pkts = xsk_tx_peek_release_desc_batch(xdp_ring->xsk_pool, budget);
++ nb_pkts = xsk_tx_peek_release_desc_batch(xsk_pool, budget);
+ if (!nb_pkts)
+ return true;
+
+ if (xdp_ring->next_to_use + nb_pkts >= xdp_ring->count) {
+ nb_processed = xdp_ring->count - xdp_ring->next_to_use;
+- ice_fill_tx_hw_ring(xdp_ring, descs, nb_processed, &total_bytes);
++ ice_fill_tx_hw_ring(xdp_ring, xsk_pool, descs, nb_processed,
++ &total_bytes);
+ xdp_ring->next_to_use = 0;
+ }
+
+- ice_fill_tx_hw_ring(xdp_ring, &descs[nb_processed], nb_pkts - nb_processed,
+- &total_bytes);
++ ice_fill_tx_hw_ring(xdp_ring, xsk_pool, &descs[nb_processed],
++ nb_pkts - nb_processed, &total_bytes);
+
+ ice_set_rs_bit(xdp_ring);
+ ice_xdp_ring_update_tail(xdp_ring);
+ ice_update_tx_ring_stats(xdp_ring, nb_pkts, total_bytes);
+
+- if (xsk_uses_need_wakeup(xdp_ring->xsk_pool))
+- xsk_set_tx_need_wakeup(xdp_ring->xsk_pool);
++ if (xsk_uses_need_wakeup(xsk_pool))
++ xsk_set_tx_need_wakeup(xsk_pool);
+
+ return nb_pkts < budget;
+ }
+@@ -1091,7 +1129,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
+ struct ice_vsi *vsi = np->vsi;
+ struct ice_tx_ring *ring;
+
+- if (test_bit(ICE_VSI_DOWN, vsi->state))
++ if (test_bit(ICE_VSI_DOWN, vsi->state) || !netif_carrier_ok(netdev))
+ return -ENETDOWN;
+
+ if (!ice_is_xdp_ena_vsi(vsi))
+@@ -1102,7 +1140,7 @@ ice_xsk_wakeup(struct net_device *netdev, u32 queue_id,
+
+ ring = vsi->rx_rings[queue_id]->xdp_ring;
+
+- if (!ring->xsk_pool)
++ if (!READ_ONCE(ring->xsk_pool))
+ return -EINVAL;
+
+ /* The idea here is that if NAPI is running, mark a miss, so
+diff --git a/drivers/net/ethernet/intel/ice/ice_xsk.h b/drivers/net/ethernet/intel/ice/ice_xsk.h
+index 6fa181f080ef1..45adeb513253a 100644
+--- a/drivers/net/ethernet/intel/ice/ice_xsk.h
++++ b/drivers/net/ethernet/intel/ice/ice_xsk.h
+@@ -20,16 +20,20 @@ struct ice_vsi;
+ #ifdef CONFIG_XDP_SOCKETS
+ int ice_xsk_pool_setup(struct ice_vsi *vsi, struct xsk_buff_pool *pool,
+ u16 qid);
+-int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring, int budget);
++int ice_clean_rx_irq_zc(struct ice_rx_ring *rx_ring,
++ struct xsk_buff_pool *xsk_pool,
++ int budget);
+ int ice_xsk_wakeup(struct net_device *netdev, u32 queue_id, u32 flags);
+-bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring, u16 count);
++bool ice_alloc_rx_bufs_zc(struct ice_rx_ring *rx_ring,
++ struct xsk_buff_pool *xsk_pool, u16 count);
+ bool ice_xsk_any_rx_ring_ena(struct ice_vsi *vsi);
+ void ice_xsk_clean_rx_ring(struct ice_rx_ring *rx_ring);
+ void ice_xsk_clean_xdp_ring(struct ice_tx_ring *xdp_ring);
+-bool ice_xmit_zc(struct ice_tx_ring *xdp_ring);
++bool ice_xmit_zc(struct ice_tx_ring *xdp_ring, struct xsk_buff_pool *xsk_pool);
+ int ice_realloc_zc_buf(struct ice_vsi *vsi, bool zc);
+ #else
+-static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring)
++static inline bool ice_xmit_zc(struct ice_tx_ring __always_unused *xdp_ring,
++ struct xsk_buff_pool __always_unused *xsk_pool)
+ {
+ return false;
+ }
+@@ -44,6 +48,7 @@ ice_xsk_pool_setup(struct ice_vsi __always_unused *vsi,
+
+ static inline int
+ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
++ struct xsk_buff_pool __always_unused *xsk_pool,
+ int __always_unused budget)
+ {
+ return 0;
+@@ -51,6 +56,7 @@ ice_clean_rx_irq_zc(struct ice_rx_ring __always_unused *rx_ring,
+
+ static inline bool
+ ice_alloc_rx_bufs_zc(struct ice_rx_ring __always_unused *rx_ring,
++ struct xsk_buff_pool __always_unused *xsk_pool,
+ u16 __always_unused count)
+ {
+ return false;
+diff --git a/drivers/net/ethernet/intel/igc/igc_main.c b/drivers/net/ethernet/intel/igc/igc_main.c
+index 87b655b839c1c..33069880c86c0 100644
+--- a/drivers/net/ethernet/intel/igc/igc_main.c
++++ b/drivers/net/ethernet/intel/igc/igc_main.c
+@@ -6310,21 +6310,6 @@ static int igc_save_qbv_schedule(struct igc_adapter *adapter,
+ size_t n;
+ int i;
+
+- switch (qopt->cmd) {
+- case TAPRIO_CMD_REPLACE:
+- break;
+- case TAPRIO_CMD_DESTROY:
+- return igc_tsn_clear_schedule(adapter);
+- case TAPRIO_CMD_STATS:
+- igc_taprio_stats(adapter->netdev, &qopt->stats);
+- return 0;
+- case TAPRIO_CMD_QUEUE_STATS:
+- igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
+- return 0;
+- default:
+- return -EOPNOTSUPP;
+- }
+-
+ if (qopt->base_time < 0)
+ return -ERANGE;
+
+@@ -6433,7 +6418,23 @@ static int igc_tsn_enable_qbv_scheduling(struct igc_adapter *adapter,
+ if (hw->mac.type != igc_i225)
+ return -EOPNOTSUPP;
+
+- err = igc_save_qbv_schedule(adapter, qopt);
++ switch (qopt->cmd) {
++ case TAPRIO_CMD_REPLACE:
++ err = igc_save_qbv_schedule(adapter, qopt);
++ break;
++ case TAPRIO_CMD_DESTROY:
++ err = igc_tsn_clear_schedule(adapter);
++ break;
++ case TAPRIO_CMD_STATS:
++ igc_taprio_stats(adapter->netdev, &qopt->stats);
++ return 0;
++ case TAPRIO_CMD_QUEUE_STATS:
++ igc_taprio_queue_stats(adapter->netdev, &qopt->queue_stats);
++ return 0;
++ default:
++ return -EOPNOTSUPP;
++ }
++
+ if (err)
+ return err;
+
+diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+index 9adf4301c9b1d..a40b631188866 100644
+--- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
++++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c
+@@ -953,13 +953,13 @@ static void mvpp2_bm_pool_update_fc(struct mvpp2_port *port,
+ static void mvpp2_bm_pool_update_priv_fc(struct mvpp2 *priv, bool en)
+ {
+ struct mvpp2_port *port;
+- int i;
++ int i, j;
+
+ for (i = 0; i < priv->port_count; i++) {
+ port = priv->port_list[i];
+ if (port->priv->percpu_pools) {
+- for (i = 0; i < port->nrxqs; i++)
+- mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[i],
++ for (j = 0; j < port->nrxqs; j++)
++ mvpp2_bm_pool_update_fc(port, &port->priv->bm_pools[j],
+ port->tx_fc & en);
+ } else {
+ mvpp2_bm_pool_update_fc(port, port->pool_long, port->tx_fc & en);
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+index fadfa8b50bebe..8c4e3ecef5901 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en/tc_ct.c
+@@ -920,6 +920,7 @@ mlx5_tc_ct_entry_replace_rule(struct mlx5_tc_ct_priv *ct_priv,
+ mlx5_tc_ct_entry_destroy_mod_hdr(ct_priv, zone_rule->attr, mh);
+ mlx5_put_label_mapping(ct_priv, attr->ct_attr.ct_labels_id);
+ err_mod_hdr:
++ *attr = *old_attr;
+ kfree(old_attr);
+ err_attr:
+ kvfree(spec);
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+index 6e00afe4671b7..797db853de363 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec_offload.c
+@@ -51,9 +51,10 @@ u32 mlx5_ipsec_device_caps(struct mlx5_core_dev *mdev)
+ MLX5_CAP_FLOWTABLE_NIC_RX(mdev, decap))
+ caps |= MLX5_IPSEC_CAP_PACKET_OFFLOAD;
+
+- if ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
+- MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
+- MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level))
++ if (IS_ENABLED(CONFIG_MLX5_CLS_ACT) &&
++ ((MLX5_CAP_FLOWTABLE_NIC_TX(mdev, ignore_flow_level) &&
++ MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ignore_flow_level)) ||
++ MLX5_CAP_ESW_FLOWTABLE_FDB(mdev, ignore_flow_level)))
+ caps |= MLX5_IPSEC_CAP_PRIO;
+
+ if (MLX5_CAP_FLOWTABLE_NIC_TX(mdev,
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+index 3320f12ba2dbd..58eb96a688533 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c
+@@ -1409,7 +1409,12 @@ static int mlx5e_ethtool_set_link_ksettings(struct mlx5e_priv *priv,
+ if (!an_changes && link_modes == eproto.admin)
+ goto out;
+
+- mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
++ err = mlx5_port_set_eth_ptys(mdev, an_disable, link_modes, ext);
++ if (err) {
++ netdev_err(priv->netdev, "%s: failed to set ptys reg: %d\n", __func__, err);
++ goto out;
++ }
++
+ mlx5_toggle_port_link(mdev);
+
+ out:
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+index 979c49ae6b5cc..b43ca0b762c30 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/fw_reset.c
+@@ -207,6 +207,7 @@ int mlx5_fw_reset_set_live_patch(struct mlx5_core_dev *dev)
+ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unloaded)
+ {
+ struct mlx5_fw_reset *fw_reset = dev->priv.fw_reset;
++ struct devlink *devlink = priv_to_devlink(dev);
+
+ /* if this is the driver that initiated the fw reset, devlink completed the reload */
+ if (test_bit(MLX5_FW_RESET_FLAGS_PENDING_COMP, &fw_reset->reset_flags)) {
+@@ -218,9 +219,11 @@ static void mlx5_fw_reset_complete_reload(struct mlx5_core_dev *dev, bool unload
+ mlx5_core_err(dev, "reset reload flow aborted, PCI reads still not working\n");
+ else
+ mlx5_load_one(dev, true);
+- devlink_remote_reload_actions_performed(priv_to_devlink(dev), 0,
++ devl_lock(devlink);
++ devlink_remote_reload_actions_performed(devlink, 0,
+ BIT(DEVLINK_RELOAD_ACTION_DRIVER_REINIT) |
+ BIT(DEVLINK_RELOAD_ACTION_FW_ACTIVATE));
++ devl_unlock(devlink);
+ }
+ }
+
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+index 612e666ec2635..e2230c8f18152 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/irq_affinity.c
+@@ -48,6 +48,7 @@ static struct mlx5_irq *
+ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_desc)
+ {
+ struct irq_affinity_desc auto_desc = {};
++ struct mlx5_irq *irq;
+ u32 irq_index;
+ int err;
+
+@@ -64,9 +65,12 @@ irq_pool_request_irq(struct mlx5_irq_pool *pool, struct irq_affinity_desc *af_de
+ else
+ cpu_get(pool, cpumask_first(&af_desc->mask));
+ }
+- return mlx5_irq_alloc(pool, irq_index,
+- cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
+- NULL);
++ irq = mlx5_irq_alloc(pool, irq_index,
++ cpumask_empty(&auto_desc.mask) ? af_desc : &auto_desc,
++ NULL);
++ if (IS_ERR(irq))
++ xa_erase(&pool->irqs, irq_index);
++ return irq;
+ }
+
+ /* Looking for the IRQ with the smallest refcount that fits req_mask.
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+index d0871c46b8c54..cf8045b926892 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/lag/lag.c
+@@ -1538,7 +1538,7 @@ u8 mlx5_lag_get_slave_port(struct mlx5_core_dev *dev,
+ goto unlock;
+
+ for (i = 0; i < ldev->ports; i++) {
+- if (ldev->pf[MLX5_LAG_P1].netdev == slave) {
++ if (ldev->pf[i].netdev == slave) {
+ port = i;
+ break;
+ }
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c
+index 459a836a5d9c1..3e55a6c6a7c9b 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/main.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c
+@@ -2140,7 +2140,6 @@ static int mlx5_try_fast_unload(struct mlx5_core_dev *dev)
+ /* Panic tear down fw command will stop the PCI bus communication
+ * with the HCA, so the health poll is no longer needed.
+ */
+- mlx5_drain_health_wq(dev);
+ mlx5_stop_health_poll(dev, false);
+
+ ret = mlx5_cmd_fast_teardown_hca(dev);
+@@ -2175,6 +2174,7 @@ static void shutdown(struct pci_dev *pdev)
+
+ mlx5_core_info(dev, "Shutdown was called\n");
+ set_bit(MLX5_BREAK_FW_WAIT, &dev->intf_state);
++ mlx5_drain_health_wq(dev);
+ err = mlx5_try_fast_unload(dev);
+ if (err)
+ mlx5_unload_one(dev, false);
+diff --git a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+index b2986175d9afe..b706f1486504a 100644
+--- a/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
++++ b/drivers/net/ethernet/mellanox/mlx5/core/sf/dev/driver.c
+@@ -112,6 +112,7 @@ static void mlx5_sf_dev_shutdown(struct auxiliary_device *adev)
+ struct mlx5_core_dev *mdev = sf_dev->mdev;
+
+ set_bit(MLX5_BREAK_FW_WAIT, &mdev->intf_state);
++ mlx5_drain_health_wq(mdev);
+ mlx5_unload_one(mdev, false);
+ }
+
+diff --git a/drivers/net/ethernet/realtek/r8169_main.c b/drivers/net/ethernet/realtek/r8169_main.c
+index 7b9e04884575e..b6e89fc5a4ae7 100644
+--- a/drivers/net/ethernet/realtek/r8169_main.c
++++ b/drivers/net/ethernet/realtek/r8169_main.c
+@@ -4347,7 +4347,8 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
+ if (unlikely(!rtl_tx_slots_avail(tp))) {
+ if (net_ratelimit())
+ netdev_err(dev, "BUG! Tx Ring full when queue awake!\n");
+- goto err_stop_0;
++ netif_stop_queue(dev);
++ return NETDEV_TX_BUSY;
+ }
+
+ opts[1] = rtl8169_tx_vlan_tag(skb);
+@@ -4403,11 +4404,6 @@ static netdev_tx_t rtl8169_start_xmit(struct sk_buff *skb,
+ dev_kfree_skb_any(skb);
+ dev->stats.tx_dropped++;
+ return NETDEV_TX_OK;
+-
+-err_stop_0:
+- netif_stop_queue(dev);
+- dev->stats.tx_dropped++;
+- return NETDEV_TX_BUSY;
+ }
+
+ static unsigned int rtl_last_frag_len(struct sk_buff *skb)
+diff --git a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+index c29809cd92015..fa510f4e26008 100644
+--- a/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
++++ b/drivers/net/ethernet/xilinx/xilinx_axienet_main.c
+@@ -2219,9 +2219,9 @@ static void axienet_dma_err_handler(struct work_struct *work)
+ ~(XAE_OPTION_TXEN | XAE_OPTION_RXEN));
+ axienet_set_mac_address(ndev, NULL);
+ axienet_set_multicast_list(ndev);
+- axienet_setoptions(ndev, lp->options);
+ napi_enable(&lp->napi_rx);
+ napi_enable(&lp->napi_tx);
++ axienet_setoptions(ndev, lp->options);
+ }
+
+ /**
+diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c
+index ebafedde0ab74..0803b6e83cf74 100644
+--- a/drivers/net/phy/micrel.c
++++ b/drivers/net/phy/micrel.c
+@@ -1389,6 +1389,8 @@ static int ksz9131_config_init(struct phy_device *phydev)
+ const struct device *dev_walker;
+ int ret;
+
++ phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
++
+ dev_walker = &phydev->mdio.dev;
+ do {
+ of_node = dev_walker->of_node;
+@@ -1438,28 +1440,30 @@ static int ksz9131_config_init(struct phy_device *phydev)
+ #define MII_KSZ9131_AUTO_MDIX 0x1C
+ #define MII_KSZ9131_AUTO_MDI_SET BIT(7)
+ #define MII_KSZ9131_AUTO_MDIX_SWAP_OFF BIT(6)
++#define MII_KSZ9131_DIG_AXAN_STS 0x14
++#define MII_KSZ9131_DIG_AXAN_STS_LINK_DET BIT(14)
++#define MII_KSZ9131_DIG_AXAN_STS_A_SELECT BIT(12)
+
+ static int ksz9131_mdix_update(struct phy_device *phydev)
+ {
+ int ret;
+
+- ret = phy_read(phydev, MII_KSZ9131_AUTO_MDIX);
+- if (ret < 0)
+- return ret;
+-
+- if (ret & MII_KSZ9131_AUTO_MDIX_SWAP_OFF) {
+- if (ret & MII_KSZ9131_AUTO_MDI_SET)
+- phydev->mdix_ctrl = ETH_TP_MDI;
+- else
+- phydev->mdix_ctrl = ETH_TP_MDI_X;
++ if (phydev->mdix_ctrl != ETH_TP_MDI_AUTO) {
++ phydev->mdix = phydev->mdix_ctrl;
+ } else {
+- phydev->mdix_ctrl = ETH_TP_MDI_AUTO;
+- }
++ ret = phy_read(phydev, MII_KSZ9131_DIG_AXAN_STS);
++ if (ret < 0)
++ return ret;
+
+- if (ret & MII_KSZ9131_AUTO_MDI_SET)
+- phydev->mdix = ETH_TP_MDI;
+- else
+- phydev->mdix = ETH_TP_MDI_X;
++ if (ret & MII_KSZ9131_DIG_AXAN_STS_LINK_DET) {
++ if (ret & MII_KSZ9131_DIG_AXAN_STS_A_SELECT)
++ phydev->mdix = ETH_TP_MDI;
++ else
++ phydev->mdix = ETH_TP_MDI_X;
++ } else {
++ phydev->mdix = ETH_TP_MDI_INVALID;
++ }
++ }
+
+ return 0;
+ }
+diff --git a/drivers/net/phy/realtek.c b/drivers/net/phy/realtek.c
+index 7ab41f95dae5f..ffa07c3f04c26 100644
+--- a/drivers/net/phy/realtek.c
++++ b/drivers/net/phy/realtek.c
+@@ -1351,6 +1351,13 @@ static struct phy_driver realtek_drvs[] = {
+ .handle_interrupt = genphy_handle_interrupt_no_ack,
+ .suspend = genphy_suspend,
+ .resume = genphy_resume,
++ }, {
++ PHY_ID_MATCH_EXACT(0x001cc960),
++ .name = "RTL8366S Gigabit Ethernet",
++ .suspend = genphy_suspend,
++ .resume = genphy_resume,
++ .read_mmd = genphy_read_mmd_unsupported,
++ .write_mmd = genphy_write_mmd_unsupported,
+ },
+ };
+
+diff --git a/drivers/net/usb/sr9700.c b/drivers/net/usb/sr9700.c
+index 0a662e42ed965..cb7d2f798fb43 100644
+--- a/drivers/net/usb/sr9700.c
++++ b/drivers/net/usb/sr9700.c
+@@ -179,6 +179,7 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
+ struct usbnet *dev = netdev_priv(netdev);
+ __le16 res;
+ int rc = 0;
++ int err;
+
+ if (phy_id) {
+ netdev_dbg(netdev, "Only internal phy supported\n");
+@@ -189,11 +190,17 @@ static int sr_mdio_read(struct net_device *netdev, int phy_id, int loc)
+ if (loc == MII_BMSR) {
+ u8 value;
+
+- sr_read_reg(dev, SR_NSR, &value);
++ err = sr_read_reg(dev, SR_NSR, &value);
++ if (err < 0)
++ return err;
++
+ if (value & NSR_LINKST)
+ rc = 1;
+ }
+- sr_share_read_word(dev, 1, loc, &res);
++ err = sr_share_read_word(dev, 1, loc, &res);
++ if (err < 0)
++ return err;
++
+ if (rc == 1)
+ res = le16_to_cpu(res) | BMSR_LSTATUS;
+ else
+diff --git a/drivers/net/wan/fsl_qmc_hdlc.c b/drivers/net/wan/fsl_qmc_hdlc.c
+index c5e7ca793c433..8fcfbde31a1c6 100644
+--- a/drivers/net/wan/fsl_qmc_hdlc.c
++++ b/drivers/net/wan/fsl_qmc_hdlc.c
+@@ -18,6 +18,7 @@
+ #include <linux/hdlc.h>
+ #include <linux/mod_devicetable.h>
+ #include <linux/module.h>
++#include <linux/mutex.h>
+ #include <linux/platform_device.h>
+ #include <linux/slab.h>
+ #include <linux/spinlock.h>
+@@ -37,7 +38,7 @@ struct qmc_hdlc {
+ struct qmc_chan *qmc_chan;
+ struct net_device *netdev;
+ struct framer *framer;
+- spinlock_t carrier_lock; /* Protect carrier detection */
++ struct mutex carrier_lock; /* Protect carrier detection */
+ struct notifier_block nb;
+ bool is_crc32;
+ spinlock_t tx_lock; /* Protect tx descriptors */
+@@ -60,7 +61,7 @@ static int qmc_hdlc_framer_set_carrier(struct qmc_hdlc *qmc_hdlc)
+ if (!qmc_hdlc->framer)
+ return 0;
+
+- guard(spinlock_irqsave)(&qmc_hdlc->carrier_lock);
++ guard(mutex)(&qmc_hdlc->carrier_lock);
+
+ ret = framer_get_status(qmc_hdlc->framer, &framer_status);
+ if (ret) {
+@@ -249,6 +250,7 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl
+ struct qmc_hdlc_desc *desc = context;
+ struct net_device *netdev;
+ struct qmc_hdlc *qmc_hdlc;
++ size_t crc_size;
+ int ret;
+
+ netdev = desc->netdev;
+@@ -267,15 +269,26 @@ static void qmc_hcld_recv_complete(void *context, size_t length, unsigned int fl
+ if (flags & QMC_RX_FLAG_HDLC_CRC) /* CRC error */
+ netdev->stats.rx_crc_errors++;
+ kfree_skb(desc->skb);
+- } else {
+- netdev->stats.rx_packets++;
+- netdev->stats.rx_bytes += length;
++ goto re_queue;
++ }
+
+- skb_put(desc->skb, length);
+- desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
+- netif_rx(desc->skb);
++ /* Discard the CRC */
++ crc_size = qmc_hdlc->is_crc32 ? 4 : 2;
++ if (length < crc_size) {
++ netdev->stats.rx_length_errors++;
++ kfree_skb(desc->skb);
++ goto re_queue;
+ }
++ length -= crc_size;
++
++ netdev->stats.rx_packets++;
++ netdev->stats.rx_bytes += length;
++
++ skb_put(desc->skb, length);
++ desc->skb->protocol = hdlc_type_trans(desc->skb, netdev);
++ netif_rx(desc->skb);
+
++re_queue:
+ /* Re-queue a transfer using the same descriptor */
+ ret = qmc_hdlc_recv_queue(qmc_hdlc, desc, desc->dma_size);
+ if (ret) {
+@@ -706,7 +719,7 @@ static int qmc_hdlc_probe(struct platform_device *pdev)
+
+ qmc_hdlc->dev = dev;
+ spin_lock_init(&qmc_hdlc->tx_lock);
+- spin_lock_init(&qmc_hdlc->carrier_lock);
++ mutex_init(&qmc_hdlc->carrier_lock);
+
+ qmc_hdlc->qmc_chan = devm_qmc_chan_get_bychild(dev, dev->of_node);
+ if (IS_ERR(qmc_hdlc->qmc_chan))
+diff --git a/drivers/net/wireless/ath/ath12k/pci.c b/drivers/net/wireless/ath/ath12k/pci.c
+index 16af046c33d9e..55fde0d33183c 100644
+--- a/drivers/net/wireless/ath/ath12k/pci.c
++++ b/drivers/net/wireless/ath/ath12k/pci.c
+@@ -472,7 +472,8 @@ static void __ath12k_pci_ext_irq_disable(struct ath12k_base *ab)
+ {
+ int i;
+
+- clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags);
++ if (!test_and_clear_bit(ATH12K_FLAG_EXT_IRQ_ENABLED, &ab->dev_flags))
++ return;
+
+ for (i = 0; i < ATH12K_EXT_IRQ_GRP_NUM_MAX; i++) {
+ struct ath12k_ext_irq_grp *irq_grp = &ab->ext_irq_grp[i];
+diff --git a/drivers/pci/hotplug/pciehp_hpc.c b/drivers/pci/hotplug/pciehp_hpc.c
+index b1d0a1b3917d4..9d3c249207c47 100644
+--- a/drivers/pci/hotplug/pciehp_hpc.c
++++ b/drivers/pci/hotplug/pciehp_hpc.c
+@@ -485,7 +485,9 @@ int pciehp_set_raw_indicator_status(struct hotplug_slot *hotplug_slot,
+ struct pci_dev *pdev = ctrl_dev(ctrl);
+
+ pci_config_pm_runtime_get(pdev);
+- pcie_write_cmd_nowait(ctrl, FIELD_PREP(PCI_EXP_SLTCTL_AIC, status),
++
++ /* Attention and Power Indicator Control bits are supported */
++ pcie_write_cmd_nowait(ctrl, FIELD_PREP(PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC, status),
+ PCI_EXP_SLTCTL_AIC | PCI_EXP_SLTCTL_PIC);
+ pci_config_pm_runtime_put(pdev);
+ return 0;
+diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c
+index 72c2d3074cded..98af97750a6e3 100644
+--- a/drivers/perf/fsl_imx9_ddr_perf.c
++++ b/drivers/perf/fsl_imx9_ddr_perf.c
+@@ -476,12 +476,12 @@ static int ddr_perf_event_add(struct perf_event *event, int flags)
+ hwc->idx = counter;
+ hwc->state |= PERF_HES_STOPPED;
+
+- if (flags & PERF_EF_START)
+- ddr_perf_event_start(event, flags);
+-
+ /* read trans, write trans, read beat */
+ ddr_perf_monitor_config(pmu, cfg, cfg1, cfg2);
+
++ if (flags & PERF_EF_START)
++ ddr_perf_event_start(event, flags);
++
+ return 0;
+ }
+
+diff --git a/drivers/perf/riscv_pmu_sbi.c b/drivers/perf/riscv_pmu_sbi.c
+index 4e842dcedfbaa..11c7c85047ed4 100644
+--- a/drivers/perf/riscv_pmu_sbi.c
++++ b/drivers/perf/riscv_pmu_sbi.c
+@@ -412,7 +412,7 @@ static int pmu_sbi_ctr_get_idx(struct perf_event *event)
+ * but not in the user access mode as we want to use the other counters
+ * that support sampling/filtering.
+ */
+- if (hwc->flags & PERF_EVENT_FLAG_LEGACY) {
++ if ((hwc->flags & PERF_EVENT_FLAG_LEGACY) && (event->attr.type == PERF_TYPE_HARDWARE)) {
+ if (event->attr.config == PERF_COUNT_HW_CPU_CYCLES) {
+ cflags |= SBI_PMU_CFG_FLAG_SKIP_MATCH;
+ cmask = 1;
+diff --git a/drivers/platform/chrome/cros_ec_proto.c b/drivers/platform/chrome/cros_ec_proto.c
+index 945b1b15a04ca..f8242b8dda908 100644
+--- a/drivers/platform/chrome/cros_ec_proto.c
++++ b/drivers/platform/chrome/cros_ec_proto.c
+@@ -805,9 +805,11 @@ int cros_ec_get_next_event(struct cros_ec_device *ec_dev,
+ if (ret == -ENOPROTOOPT) {
+ dev_dbg(ec_dev->dev,
+ "GET_NEXT_EVENT returned invalid version error.\n");
++ mutex_lock(&ec_dev->lock);
+ ret = cros_ec_get_host_command_version_mask(ec_dev,
+ EC_CMD_GET_NEXT_EVENT,
+ &ver_mask);
++ mutex_unlock(&ec_dev->lock);
+ if (ret < 0 || ver_mask == 0)
+ /*
+ * Do not change the MKBP supported version if we can't
+diff --git a/fs/btrfs/block-group.c b/fs/btrfs/block-group.c
+index 60066822b5329..350cd1201cdbe 100644
+--- a/fs/btrfs/block-group.c
++++ b/fs/btrfs/block-group.c
+@@ -1216,8 +1216,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
+ block_group->space_info->total_bytes -= block_group->length;
+ block_group->space_info->bytes_readonly -=
+ (block_group->length - block_group->zone_unusable);
+- block_group->space_info->bytes_zone_unusable -=
+- block_group->zone_unusable;
++ btrfs_space_info_update_bytes_zone_unusable(fs_info, block_group->space_info,
++ -block_group->zone_unusable);
+ block_group->space_info->disk_total -= block_group->length * factor;
+
+ spin_unlock(&block_group->space_info->lock);
+@@ -1389,7 +1389,8 @@ static int inc_block_group_ro(struct btrfs_block_group *cache, int force)
+ if (btrfs_is_zoned(cache->fs_info)) {
+ /* Migrate zone_unusable bytes to readonly */
+ sinfo->bytes_readonly += cache->zone_unusable;
+- sinfo->bytes_zone_unusable -= cache->zone_unusable;
++ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
++ -cache->zone_unusable);
+ cache->zone_unusable = 0;
+ }
+ cache->ro++;
+@@ -3034,9 +3035,11 @@ void btrfs_dec_block_group_ro(struct btrfs_block_group *cache)
+ if (btrfs_is_zoned(cache->fs_info)) {
+ /* Migrate zone_unusable bytes back */
+ cache->zone_unusable =
+- (cache->alloc_offset - cache->used) +
++ (cache->alloc_offset - cache->used - cache->pinned -
++ cache->reserved) +
+ (cache->length - cache->zone_capacity);
+- sinfo->bytes_zone_unusable += cache->zone_unusable;
++ btrfs_space_info_update_bytes_zone_unusable(cache->fs_info, sinfo,
++ cache->zone_unusable);
+ sinfo->bytes_readonly -= cache->zone_unusable;
+ }
+ num_bytes = cache->length - cache->reserved -
+diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
+index 3774c191e36dc..b75e14f399a01 100644
+--- a/fs/btrfs/extent-tree.c
++++ b/fs/btrfs/extent-tree.c
+@@ -2806,7 +2806,8 @@ static int unpin_extent_range(struct btrfs_fs_info *fs_info,
+ readonly = true;
+ } else if (btrfs_is_zoned(fs_info)) {
+ /* Need reset before reusing in a zoned block group */
+- space_info->bytes_zone_unusable += len;
++ btrfs_space_info_update_bytes_zone_unusable(fs_info, space_info,
++ len);
+ readonly = true;
+ }
+ spin_unlock(&cache->lock);
+diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
+index dabc3d0793cf4..d674f2106593a 100644
+--- a/fs/btrfs/free-space-cache.c
++++ b/fs/btrfs/free-space-cache.c
+@@ -2723,8 +2723,10 @@ static int __btrfs_add_free_space_zoned(struct btrfs_block_group *block_group,
+ * If the block group is read-only, we should account freed space into
+ * bytes_readonly.
+ */
+- if (!block_group->ro)
++ if (!block_group->ro) {
+ block_group->zone_unusable += to_unusable;
++ WARN_ON(block_group->zone_unusable > block_group->length);
++ }
+ spin_unlock(&ctl->tree_lock);
+ if (!used) {
+ spin_lock(&block_group->lock);
+diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
+index 3a2b902b2d1f9..39d22693e47b6 100644
+--- a/fs/btrfs/inode.c
++++ b/fs/btrfs/inode.c
+@@ -737,8 +737,9 @@ static noinline int __cow_file_range_inline(struct btrfs_inode *inode, u64 offse
+ return ret;
+ }
+
+-static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
+- u64 end,
++static noinline int cow_file_range_inline(struct btrfs_inode *inode,
++ struct page *locked_page,
++ u64 offset, u64 end,
+ size_t compressed_size,
+ int compress_type,
+ struct folio *compressed_folio,
+@@ -762,7 +763,10 @@ static noinline int cow_file_range_inline(struct btrfs_inode *inode, u64 offset,
+ return ret;
+ }
+
+- extent_clear_unlock_delalloc(inode, offset, end, NULL, &cached,
++ if (ret == 0)
++ locked_page = NULL;
++
++ extent_clear_unlock_delalloc(inode, offset, end, locked_page, &cached,
+ clear_flags,
+ PAGE_UNLOCK | PAGE_START_WRITEBACK |
+ PAGE_END_WRITEBACK);
+@@ -1037,10 +1041,10 @@ static void compress_file_range(struct btrfs_work *work)
+ * extent for the subpage case.
+ */
+ if (total_in < actual_end)
+- ret = cow_file_range_inline(inode, start, end, 0,
++ ret = cow_file_range_inline(inode, NULL, start, end, 0,
+ BTRFS_COMPRESS_NONE, NULL, false);
+ else
+- ret = cow_file_range_inline(inode, start, end, total_compressed,
++ ret = cow_file_range_inline(inode, NULL, start, end, total_compressed,
+ compress_type, folios[0], false);
+ if (ret <= 0) {
+ if (ret < 0)
+@@ -1359,7 +1363,7 @@ static noinline int cow_file_range(struct btrfs_inode *inode,
+
+ if (!no_inline) {
+ /* lets try to make an inline extent */
+- ret = cow_file_range_inline(inode, start, end, 0,
++ ret = cow_file_range_inline(inode, locked_page, start, end, 0,
+ BTRFS_COMPRESS_NONE, NULL, false);
+ if (ret <= 0) {
+ /*
+diff --git a/fs/btrfs/space-info.c b/fs/btrfs/space-info.c
+index ae8c56442549c..8f194eefd3f38 100644
+--- a/fs/btrfs/space-info.c
++++ b/fs/btrfs/space-info.c
+@@ -311,7 +311,7 @@ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
+ found->bytes_used += block_group->used;
+ found->disk_used += block_group->used * factor;
+ found->bytes_readonly += block_group->bytes_super;
+- found->bytes_zone_unusable += block_group->zone_unusable;
++ btrfs_space_info_update_bytes_zone_unusable(info, found, block_group->zone_unusable);
+ if (block_group->length > 0)
+ found->full = 0;
+ btrfs_try_granting_tickets(info, found);
+@@ -573,8 +573,7 @@ void btrfs_dump_space_info(struct btrfs_fs_info *fs_info,
+
+ spin_lock(&cache->lock);
+ avail = cache->length - cache->used - cache->pinned -
+- cache->reserved - cache->delalloc_bytes -
+- cache->bytes_super - cache->zone_unusable;
++ cache->reserved - cache->bytes_super - cache->zone_unusable;
+ btrfs_info(fs_info,
+ "block group %llu has %llu bytes, %llu used %llu pinned %llu reserved %llu delalloc %llu super %llu zone_unusable (%llu bytes available) %s",
+ cache->start, cache->length, cache->used, cache->pinned,
+diff --git a/fs/btrfs/space-info.h b/fs/btrfs/space-info.h
+index a733458fd13b3..3e304300fc624 100644
+--- a/fs/btrfs/space-info.h
++++ b/fs/btrfs/space-info.h
+@@ -207,6 +207,7 @@ btrfs_space_info_update_##name(struct btrfs_fs_info *fs_info, \
+
+ DECLARE_SPACE_INFO_UPDATE(bytes_may_use, "space_info");
+ DECLARE_SPACE_INFO_UPDATE(bytes_pinned, "pinned");
++DECLARE_SPACE_INFO_UPDATE(bytes_zone_unusable, "zone_unusable");
+
+ int btrfs_init_space_info(struct btrfs_fs_info *fs_info);
+ void btrfs_add_bg_to_space_info(struct btrfs_fs_info *info,
+diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
+index c4941ba245ac3..68df96800ea99 100644
+--- a/fs/ceph/caps.c
++++ b/fs/ceph/caps.c
+@@ -2016,6 +2016,8 @@ bool __ceph_should_report_size(struct ceph_inode_info *ci)
+ * CHECK_CAPS_AUTHONLY - we should only check the auth cap
+ * CHECK_CAPS_FLUSH - we should flush any dirty caps immediately, without
+ * further delay.
++ * CHECK_CAPS_FLUSH_FORCE - we should flush any caps immediately, without
++ * further delay.
+ */
+ void ceph_check_caps(struct ceph_inode_info *ci, int flags)
+ {
+@@ -2097,7 +2099,7 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags)
+ }
+
+ doutc(cl, "%p %llx.%llx file_want %s used %s dirty %s "
+- "flushing %s issued %s revoking %s retain %s %s%s%s\n",
++ "flushing %s issued %s revoking %s retain %s %s%s%s%s\n",
+ inode, ceph_vinop(inode), ceph_cap_string(file_wanted),
+ ceph_cap_string(used), ceph_cap_string(ci->i_dirty_caps),
+ ceph_cap_string(ci->i_flushing_caps),
+@@ -2105,7 +2107,8 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags)
+ ceph_cap_string(retain),
+ (flags & CHECK_CAPS_AUTHONLY) ? " AUTHONLY" : "",
+ (flags & CHECK_CAPS_FLUSH) ? " FLUSH" : "",
+- (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "");
++ (flags & CHECK_CAPS_NOINVAL) ? " NOINVAL" : "",
++ (flags & CHECK_CAPS_FLUSH_FORCE) ? " FLUSH_FORCE" : "");
+
+ /*
+ * If we no longer need to hold onto old our caps, and we may
+@@ -2180,6 +2183,11 @@ void ceph_check_caps(struct ceph_inode_info *ci, int flags)
+ queue_writeback = true;
+ }
+
++ if (flags & CHECK_CAPS_FLUSH_FORCE) {
++ doutc(cl, "force to flush caps\n");
++ goto ack;
++ }
++
+ if (cap == ci->i_auth_cap &&
+ (cap->issued & CEPH_CAP_FILE_WR)) {
+ /* request larger max_size from MDS? */
+@@ -3504,6 +3512,8 @@ static void handle_cap_grant(struct inode *inode,
+ bool queue_invalidate = false;
+ bool deleted_inode = false;
+ bool fill_inline = false;
++ bool revoke_wait = false;
++ int flags = 0;
+
+ /*
+ * If there is at least one crypto block then we'll trust
+@@ -3699,16 +3709,18 @@ static void handle_cap_grant(struct inode *inode,
+ ceph_cap_string(cap->issued), ceph_cap_string(newcaps),
+ ceph_cap_string(revoking));
+ if (S_ISREG(inode->i_mode) &&
+- (revoking & used & CEPH_CAP_FILE_BUFFER))
++ (revoking & used & CEPH_CAP_FILE_BUFFER)) {
+ writeback = true; /* initiate writeback; will delay ack */
+- else if (queue_invalidate &&
++ revoke_wait = true;
++ } else if (queue_invalidate &&
+ revoking == CEPH_CAP_FILE_CACHE &&
+- (newcaps & CEPH_CAP_FILE_LAZYIO) == 0)
+- ; /* do nothing yet, invalidation will be queued */
+- else if (cap == ci->i_auth_cap)
++ (newcaps & CEPH_CAP_FILE_LAZYIO) == 0) {
++ revoke_wait = true; /* do nothing yet, invalidation will be queued */
++ } else if (cap == ci->i_auth_cap) {
+ check_caps = 1; /* check auth cap only */
+- else
++ } else {
+ check_caps = 2; /* check all caps */
++ }
+ /* If there is new caps, try to wake up the waiters */
+ if (~cap->issued & newcaps)
+ wake = true;
+@@ -3735,8 +3747,9 @@ static void handle_cap_grant(struct inode *inode,
+ BUG_ON(cap->issued & ~cap->implemented);
+
+ /* don't let check_caps skip sending a response to MDS for revoke msgs */
+- if (le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) {
++ if (!revoke_wait && le32_to_cpu(grant->op) == CEPH_CAP_OP_REVOKE) {
+ cap->mds_wanted = 0;
++ flags |= CHECK_CAPS_FLUSH_FORCE;
+ if (cap == ci->i_auth_cap)
+ check_caps = 1; /* check auth cap only */
+ else
+@@ -3792,9 +3805,9 @@ static void handle_cap_grant(struct inode *inode,
+
+ mutex_unlock(&session->s_mutex);
+ if (check_caps == 1)
+- ceph_check_caps(ci, CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL);
++ ceph_check_caps(ci, flags | CHECK_CAPS_AUTHONLY | CHECK_CAPS_NOINVAL);
+ else if (check_caps == 2)
+- ceph_check_caps(ci, CHECK_CAPS_NOINVAL);
++ ceph_check_caps(ci, flags | CHECK_CAPS_NOINVAL);
+ }
+
+ /*
+diff --git a/fs/ceph/super.h b/fs/ceph/super.h
+index b63b4cd9b5b68..6e817bf1337c6 100644
+--- a/fs/ceph/super.h
++++ b/fs/ceph/super.h
+@@ -200,9 +200,10 @@ struct ceph_cap {
+ struct list_head caps_item;
+ };
+
+-#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */
+-#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */
+-#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */
++#define CHECK_CAPS_AUTHONLY 1 /* only check auth cap */
++#define CHECK_CAPS_FLUSH 2 /* flush any dirty caps */
++#define CHECK_CAPS_NOINVAL 4 /* don't invalidate pagecache */
++#define CHECK_CAPS_FLUSH_FORCE 8 /* force flush any caps */
+
+ struct ceph_cap_flush {
+ u64 tid;
+diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
+index 4bae9ccf5fe01..4b0d64a76e88e 100644
+--- a/fs/ext4/inode.c
++++ b/fs/ext4/inode.c
+@@ -453,6 +453,35 @@ static void ext4_map_blocks_es_recheck(handle_t *handle,
+ }
+ #endif /* ES_AGGRESSIVE_TEST */
+
++static int ext4_map_query_blocks(handle_t *handle, struct inode *inode,
++ struct ext4_map_blocks *map)
++{
++ unsigned int status;
++ int retval;
++
++ if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
++ retval = ext4_ext_map_blocks(handle, inode, map, 0);
++ else
++ retval = ext4_ind_map_blocks(handle, inode, map, 0);
++
++ if (retval <= 0)
++ return retval;
++
++ if (unlikely(retval != map->m_len)) {
++ ext4_warning(inode->i_sb,
++ "ES len assertion failed for inode "
++ "%lu: retval %d != map->m_len %d",
++ inode->i_ino, retval, map->m_len);
++ WARN_ON(1);
++ }
++
++ status = map->m_flags & EXT4_MAP_UNWRITTEN ?
++ EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
++ ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
++ map->m_pblk, status);
++ return retval;
++}
++
+ /*
+ * The ext4_map_blocks() function tries to look up the requested blocks,
+ * and returns if the blocks are already mapped.
+@@ -1708,6 +1737,7 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+ if (ext4_es_is_hole(&es))
+ goto add_delayed;
+
++found:
+ /*
+ * Delayed extent could be allocated by fallocate.
+ * So we need to check it.
+@@ -1744,36 +1774,34 @@ static int ext4_da_map_blocks(struct inode *inode, sector_t iblock,
+ down_read(&EXT4_I(inode)->i_data_sem);
+ if (ext4_has_inline_data(inode))
+ retval = 0;
+- else if (ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))
+- retval = ext4_ext_map_blocks(NULL, inode, map, 0);
+ else
+- retval = ext4_ind_map_blocks(NULL, inode, map, 0);
+- if (retval < 0) {
+- up_read(&EXT4_I(inode)->i_data_sem);
++ retval = ext4_map_query_blocks(NULL, inode, map);
++ up_read(&EXT4_I(inode)->i_data_sem);
++ if (retval)
+ return retval;
+- }
+- if (retval > 0) {
+- unsigned int status;
+
+- if (unlikely(retval != map->m_len)) {
+- ext4_warning(inode->i_sb,
+- "ES len assertion failed for inode "
+- "%lu: retval %d != map->m_len %d",
+- inode->i_ino, retval, map->m_len);
+- WARN_ON(1);
++add_delayed:
++ down_write(&EXT4_I(inode)->i_data_sem);
++ /*
++ * Page fault path (ext4_page_mkwrite does not take i_rwsem)
++ * and fallocate path (no folio lock) can race. Make sure we
++ * lookup the extent status tree here again while i_data_sem
++ * is held in write mode, before inserting a new da entry in
++ * the extent status tree.
++ */
++ if (ext4_es_lookup_extent(inode, iblock, NULL, &es)) {
++ if (!ext4_es_is_hole(&es)) {
++ up_write(&EXT4_I(inode)->i_data_sem);
++ goto found;
++ }
++ } else if (!ext4_has_inline_data(inode)) {
++ retval = ext4_map_query_blocks(NULL, inode, map);
++ if (retval) {
++ up_write(&EXT4_I(inode)->i_data_sem);
++ return retval;
+ }
+-
+- status = map->m_flags & EXT4_MAP_UNWRITTEN ?
+- EXTENT_STATUS_UNWRITTEN : EXTENT_STATUS_WRITTEN;
+- ext4_es_insert_extent(inode, map->m_lblk, map->m_len,
+- map->m_pblk, status);
+- up_read(&EXT4_I(inode)->i_data_sem);
+- return retval;
+ }
+- up_read(&EXT4_I(inode)->i_data_sem);
+
+-add_delayed:
+- down_write(&EXT4_I(inode)->i_data_sem);
+ retval = ext4_insert_delayed_block(inode, map->m_lblk);
+ up_write(&EXT4_I(inode)->i_data_sem);
+ if (retval)
+diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
+index 259e235becc59..601825785226d 100644
+--- a/fs/f2fs/segment.c
++++ b/fs/f2fs/segment.c
+@@ -3483,7 +3483,9 @@ static int __get_segment_type_6(struct f2fs_io_info *fio)
+ if (page_private_gcing(fio->page)) {
+ if (fio->sbi->am.atgc_enabled &&
+ (fio->io_type == FS_DATA_IO) &&
+- (fio->sbi->gc_mode != GC_URGENT_HIGH))
++ (fio->sbi->gc_mode != GC_URGENT_HIGH) &&
++ __is_valid_data_blkaddr(fio->old_blkaddr) &&
++ !is_inode_flag_set(inode, FI_OPU_WRITE))
+ return CURSEG_ALL_DATA_ATGC;
+ else
+ return CURSEG_COLD_DATA;
+diff --git a/fs/file.c b/fs/file.c
+index a3b72aa64f116..a11e59b5d6026 100644
+--- a/fs/file.c
++++ b/fs/file.c
+@@ -1248,6 +1248,7 @@ __releases(&files->file_lock)
+ * tables and this condition does not arise without those.
+ */
+ fdt = files_fdtable(files);
++ fd = array_index_nospec(fd, fdt->max_fds);
+ tofree = fdt->fd[fd];
+ if (!tofree && fd_is_open(fd, fdt))
+ goto Ebusy;
+diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
+index 7a5785f405b62..0a8fd4a3d04c9 100644
+--- a/include/linux/cpuhotplug.h
++++ b/include/linux/cpuhotplug.h
+@@ -147,6 +147,7 @@ enum cpuhp_state {
+ CPUHP_AP_IRQ_LOONGARCH_STARTING,
+ CPUHP_AP_IRQ_SIFIVE_PLIC_STARTING,
+ CPUHP_AP_IRQ_RISCV_IMSIC_STARTING,
++ CPUHP_AP_IRQ_RISCV_SBI_IPI_STARTING,
+ CPUHP_AP_ARM_MVEBU_COHERENCY,
+ CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
+ CPUHP_AP_PERF_X86_STARTING,
+diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
+index c73ad77fa33d3..d73c7d89d27b9 100644
+--- a/include/linux/huge_mm.h
++++ b/include/linux/huge_mm.h
+@@ -132,18 +132,6 @@ static inline bool hugepage_global_always(void)
+ (1<<TRANSPARENT_HUGEPAGE_FLAG);
+ }
+
+-static inline bool hugepage_flags_enabled(void)
+-{
+- /*
+- * We cover both the anon and the file-backed case here; we must return
+- * true if globally enabled, even when all anon sizes are set to never.
+- * So we don't need to look at huge_anon_orders_inherit.
+- */
+- return hugepage_global_enabled() ||
+- huge_anon_orders_always ||
+- huge_anon_orders_madvise;
+-}
+-
+ static inline int highest_order(unsigned long orders)
+ {
+ return fls_long(orders) - 1;
+diff --git a/include/linux/migrate.h b/include/linux/migrate.h
+index 2ce13e8a309bd..9438cc7c2aeb5 100644
+--- a/include/linux/migrate.h
++++ b/include/linux/migrate.h
+@@ -142,9 +142,16 @@ const struct movable_operations *page_movable_ops(struct page *page)
+ }
+
+ #ifdef CONFIG_NUMA_BALANCING
++int migrate_misplaced_folio_prepare(struct folio *folio,
++ struct vm_area_struct *vma, int node);
+ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
+ int node);
+ #else
++static inline int migrate_misplaced_folio_prepare(struct folio *folio,
++ struct vm_area_struct *vma, int node)
++{
++ return -EAGAIN; /* can't migrate now */
++}
+ static inline int migrate_misplaced_folio(struct folio *folio,
+ struct vm_area_struct *vma, int node)
+ {
+diff --git a/include/trace/events/btrfs.h b/include/trace/events/btrfs.h
+index c978fa2893a53..9b38d015c53c1 100644
+--- a/include/trace/events/btrfs.h
++++ b/include/trace/events/btrfs.h
+@@ -2394,6 +2394,14 @@ DEFINE_EVENT(btrfs__space_info_update, update_bytes_pinned,
+ TP_ARGS(fs_info, sinfo, old, diff)
+ );
+
++DEFINE_EVENT(btrfs__space_info_update, update_bytes_zone_unusable,
++
++ TP_PROTO(const struct btrfs_fs_info *fs_info,
++ const struct btrfs_space_info *sinfo, u64 old, s64 diff),
++
++ TP_ARGS(fs_info, sinfo, old, diff)
++);
++
+ DECLARE_EVENT_CLASS(btrfs_raid56_bio,
+
+ TP_PROTO(const struct btrfs_raid_bio *rbio,
+diff --git a/include/trace/events/mptcp.h b/include/trace/events/mptcp.h
+index 09e72215b9f9b..085b749cdd97e 100644
+--- a/include/trace/events/mptcp.h
++++ b/include/trace/events/mptcp.h
+@@ -34,7 +34,7 @@ TRACE_EVENT(mptcp_subflow_get_send,
+ struct sock *ssk;
+
+ __entry->active = mptcp_subflow_active(subflow);
+- __entry->backup = subflow->backup;
++ __entry->backup = subflow->backup || subflow->request_bkup;
+
+ if (subflow->tcp_sock && sk_fullsock(subflow->tcp_sock))
+ __entry->free = sk_stream_memory_free(subflow->tcp_sock);
+diff --git a/init/Kconfig b/init/Kconfig
+index febdea2afc3be..d8a971b804d32 100644
+--- a/init/Kconfig
++++ b/init/Kconfig
+@@ -1906,6 +1906,7 @@ config RUST
+ depends on !MODVERSIONS
+ depends on !GCC_PLUGINS
+ depends on !RANDSTRUCT
++ depends on !SHADOW_CALL_STACK
+ depends on !DEBUG_INFO_BTF || PAHOLE_HAS_LANG_EXCLUDE
+ help
+ Enables Rust support in the kernel.
+diff --git a/io_uring/poll.c b/io_uring/poll.c
+index 0a8e02944689f..1f63b60e85e7c 100644
+--- a/io_uring/poll.c
++++ b/io_uring/poll.c
+@@ -347,6 +347,7 @@ static int io_poll_check_events(struct io_kiocb *req, struct io_tw_state *ts)
+ v &= IO_POLL_REF_MASK;
+ } while (atomic_sub_return(v, &req->poll_refs) & IO_POLL_REF_MASK);
+
++ io_napi_add(req);
+ return IOU_POLL_NO_ACTION;
+ }
+
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 374a0d54b08df..5f32a196a612e 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -517,6 +517,13 @@ static ssize_t thpsize_enabled_store(struct kobject *kobj,
+ } else
+ ret = -EINVAL;
+
++ if (ret > 0) {
++ int err;
++
++ err = start_stop_khugepaged();
++ if (err)
++ ret = err;
++ }
+ return ret;
+ }
+
+@@ -1659,7 +1666,7 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
+ unsigned long haddr = vmf->address & HPAGE_PMD_MASK;
+ int nid = NUMA_NO_NODE;
+ int target_nid, last_cpupid = (-1 & LAST_CPUPID_MASK);
+- bool migrated = false, writable = false;
++ bool writable = false;
+ int flags = 0;
+
+ vmf->ptl = pmd_lock(vma->vm_mm, vmf->pmd);
+@@ -1695,16 +1702,17 @@ vm_fault_t do_huge_pmd_numa_page(struct vm_fault *vmf)
+ if (node_is_toptier(nid))
+ last_cpupid = folio_last_cpupid(folio);
+ target_nid = numa_migrate_prep(folio, vmf, haddr, nid, &flags);
+- if (target_nid == NUMA_NO_NODE) {
+- folio_put(folio);
++ if (target_nid == NUMA_NO_NODE)
++ goto out_map;
++ if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
++ flags |= TNF_MIGRATE_FAIL;
+ goto out_map;
+ }
+-
++ /* The folio is isolated and isolation code holds a folio reference. */
+ spin_unlock(vmf->ptl);
+ writable = false;
+
+- migrated = migrate_misplaced_folio(folio, vma, target_nid);
+- if (migrated) {
++ if (!migrate_misplaced_folio(folio, vma, target_nid)) {
+ flags |= TNF_MIGRATED;
+ nid = target_nid;
+ } else {
+diff --git a/mm/khugepaged.c b/mm/khugepaged.c
+index 774a97e6e2da3..92ecd59fffd41 100644
+--- a/mm/khugepaged.c
++++ b/mm/khugepaged.c
+@@ -416,6 +416,26 @@ static inline int hpage_collapse_test_exit_or_disable(struct mm_struct *mm)
+ test_bit(MMF_DISABLE_THP, &mm->flags);
+ }
+
++static bool hugepage_pmd_enabled(void)
++{
++ /*
++ * We cover both the anon and the file-backed case here; file-backed
++ * hugepages, when configured in, are determined by the global control.
++ * Anon pmd-sized hugepages are determined by the pmd-size control.
++ */
++ if (IS_ENABLED(CONFIG_READ_ONLY_THP_FOR_FS) &&
++ hugepage_global_enabled())
++ return true;
++ if (test_bit(PMD_ORDER, &huge_anon_orders_always))
++ return true;
++ if (test_bit(PMD_ORDER, &huge_anon_orders_madvise))
++ return true;
++ if (test_bit(PMD_ORDER, &huge_anon_orders_inherit) &&
++ hugepage_global_enabled())
++ return true;
++ return false;
++}
++
+ void __khugepaged_enter(struct mm_struct *mm)
+ {
+ struct khugepaged_mm_slot *mm_slot;
+@@ -452,7 +472,7 @@ void khugepaged_enter_vma(struct vm_area_struct *vma,
+ unsigned long vm_flags)
+ {
+ if (!test_bit(MMF_VM_HUGEPAGE, &vma->vm_mm->flags) &&
+- hugepage_flags_enabled()) {
++ hugepage_pmd_enabled()) {
+ if (thp_vma_allowable_order(vma, vm_flags, TVA_ENFORCE_SYSFS,
+ PMD_ORDER))
+ __khugepaged_enter(vma->vm_mm);
+@@ -2465,8 +2485,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int *result,
+
+ static int khugepaged_has_work(void)
+ {
+- return !list_empty(&khugepaged_scan.mm_head) &&
+- hugepage_flags_enabled();
++ return !list_empty(&khugepaged_scan.mm_head) && hugepage_pmd_enabled();
+ }
+
+ static int khugepaged_wait_event(void)
+@@ -2539,7 +2558,7 @@ static void khugepaged_wait_work(void)
+ return;
+ }
+
+- if (hugepage_flags_enabled())
++ if (hugepage_pmd_enabled())
+ wait_event_freezable(khugepaged_wait, khugepaged_wait_event());
+ }
+
+@@ -2570,7 +2589,7 @@ static void set_recommended_min_free_kbytes(void)
+ int nr_zones = 0;
+ unsigned long recommended_min;
+
+- if (!hugepage_flags_enabled()) {
++ if (!hugepage_pmd_enabled()) {
+ calculate_min_free_kbytes();
+ goto update_wmarks;
+ }
+@@ -2620,7 +2639,7 @@ int start_stop_khugepaged(void)
+ int err = 0;
+
+ mutex_lock(&khugepaged_mutex);
+- if (hugepage_flags_enabled()) {
++ if (hugepage_pmd_enabled()) {
+ if (!khugepaged_thread)
+ khugepaged_thread = kthread_run(khugepaged, NULL,
+ "khugepaged");
+@@ -2646,7 +2665,7 @@ int start_stop_khugepaged(void)
+ void khugepaged_min_free_kbytes_update(void)
+ {
+ mutex_lock(&khugepaged_mutex);
+- if (hugepage_flags_enabled() && khugepaged_thread)
++ if (hugepage_pmd_enabled() && khugepaged_thread)
+ set_recommended_min_free_kbytes();
+ mutex_unlock(&khugepaged_mutex);
+ }
+diff --git a/mm/memory.c b/mm/memory.c
+index f81760c93801f..755ffe082e217 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -5067,8 +5067,6 @@ int numa_migrate_prep(struct folio *folio, struct vm_fault *vmf,
+ {
+ struct vm_area_struct *vma = vmf->vma;
+
+- folio_get(folio);
+-
+ /* Record the current PID acceesing VMA */
+ vma_set_access_pid_bit(vma);
+
+@@ -5205,16 +5203,19 @@ static vm_fault_t do_numa_page(struct vm_fault *vmf)
+ else
+ last_cpupid = folio_last_cpupid(folio);
+ target_nid = numa_migrate_prep(folio, vmf, vmf->address, nid, &flags);
+- if (target_nid == NUMA_NO_NODE) {
+- folio_put(folio);
++ if (target_nid == NUMA_NO_NODE)
++ goto out_map;
++ if (migrate_misplaced_folio_prepare(folio, vma, target_nid)) {
++ flags |= TNF_MIGRATE_FAIL;
+ goto out_map;
+ }
++ /* The folio is isolated and isolation code holds a folio reference. */
+ pte_unmap_unlock(vmf->pte, vmf->ptl);
+ writable = false;
+ ignore_writable = true;
+
+ /* Migrate to the requested node */
+- if (migrate_misplaced_folio(folio, vma, target_nid)) {
++ if (!migrate_misplaced_folio(folio, vma, target_nid)) {
+ nid = target_nid;
+ flags |= TNF_MIGRATED;
+ } else {
+diff --git a/mm/migrate.c b/mm/migrate.c
+index a8c6f466e33ac..9dabeb90f772d 100644
+--- a/mm/migrate.c
++++ b/mm/migrate.c
+@@ -2557,16 +2557,44 @@ static struct folio *alloc_misplaced_dst_folio(struct folio *src,
+ return __folio_alloc_node(gfp, order, nid);
+ }
+
+-static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio)
++/*
++ * Prepare for calling migrate_misplaced_folio() by isolating the folio if
++ * permitted. Must be called with the PTL still held.
++ */
++int migrate_misplaced_folio_prepare(struct folio *folio,
++ struct vm_area_struct *vma, int node)
+ {
+ int nr_pages = folio_nr_pages(folio);
++ pg_data_t *pgdat = NODE_DATA(node);
++
++ if (folio_is_file_lru(folio)) {
++ /*
++ * Do not migrate file folios that are mapped in multiple
++ * processes with execute permissions as they are probably
++ * shared libraries.
++ *
++ * See folio_likely_mapped_shared() on possible imprecision
++ * when we cannot easily detect if a folio is shared.
++ */
++ if ((vma->vm_flags & VM_EXEC) &&
++ folio_likely_mapped_shared(folio))
++ return -EACCES;
++
++ /*
++ * Do not migrate dirty folios as not all filesystems can move
++ * dirty folios in MIGRATE_ASYNC mode which is a waste of
++ * cycles.
++ */
++ if (folio_test_dirty(folio))
++ return -EAGAIN;
++ }
+
+ /* Avoid migrating to a node that is nearly full */
+ if (!migrate_balanced_pgdat(pgdat, nr_pages)) {
+ int z;
+
+ if (!(sysctl_numa_balancing_mode & NUMA_BALANCING_MEMORY_TIERING))
+- return 0;
++ return -EAGAIN;
+ for (z = pgdat->nr_zones - 1; z >= 0; z--) {
+ if (managed_zone(pgdat->node_zones + z))
+ break;
+@@ -2577,78 +2605,42 @@ static int numamigrate_isolate_folio(pg_data_t *pgdat, struct folio *folio)
+ * further.
+ */
+ if (z < 0)
+- return 0;
++ return -EAGAIN;
+
+ wakeup_kswapd(pgdat->node_zones + z, 0,
+ folio_order(folio), ZONE_MOVABLE);
+- return 0;
++ return -EAGAIN;
+ }
+
+ if (!folio_isolate_lru(folio))
+- return 0;
++ return -EAGAIN;
+
+ node_stat_mod_folio(folio, NR_ISOLATED_ANON + folio_is_file_lru(folio),
+ nr_pages);
+-
+- /*
+- * Isolating the folio has taken another reference, so the
+- * caller's reference can be safely dropped without the folio
+- * disappearing underneath us during migration.
+- */
+- folio_put(folio);
+- return 1;
++ return 0;
+ }
+
+ /*
+ * Attempt to migrate a misplaced folio to the specified destination
+- * node. Caller is expected to have an elevated reference count on
+- * the folio that will be dropped by this function before returning.
++ * node. Caller is expected to have isolated the folio by calling
++ * migrate_misplaced_folio_prepare(), which will result in an
++ * elevated reference count on the folio. This function will un-isolate the
++ * folio, dereferencing the folio before returning.
+ */
+ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
+ int node)
+ {
+ pg_data_t *pgdat = NODE_DATA(node);
+- int isolated;
+ int nr_remaining;
+ unsigned int nr_succeeded;
+ LIST_HEAD(migratepages);
+- int nr_pages = folio_nr_pages(folio);
+-
+- /*
+- * Don't migrate file folios that are mapped in multiple processes
+- * with execute permissions as they are probably shared libraries.
+- *
+- * See folio_likely_mapped_shared() on possible imprecision when we
+- * cannot easily detect if a folio is shared.
+- */
+- if (folio_likely_mapped_shared(folio) && folio_is_file_lru(folio) &&
+- (vma->vm_flags & VM_EXEC))
+- goto out;
+-
+- /*
+- * Also do not migrate dirty folios as not all filesystems can move
+- * dirty folios in MIGRATE_ASYNC mode which is a waste of cycles.
+- */
+- if (folio_is_file_lru(folio) && folio_test_dirty(folio))
+- goto out;
+-
+- isolated = numamigrate_isolate_folio(pgdat, folio);
+- if (!isolated)
+- goto out;
+
+ list_add(&folio->lru, &migratepages);
+ nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_folio,
+ NULL, node, MIGRATE_ASYNC,
+ MR_NUMA_MISPLACED, &nr_succeeded);
+- if (nr_remaining) {
+- if (!list_empty(&migratepages)) {
+- list_del(&folio->lru);
+- node_stat_mod_folio(folio, NR_ISOLATED_ANON +
+- folio_is_file_lru(folio), -nr_pages);
+- folio_putback_lru(folio);
+- }
+- isolated = 0;
+- }
++ if (nr_remaining && !list_empty(&migratepages))
++ putback_movable_pages(&migratepages);
+ if (nr_succeeded) {
+ count_vm_numa_events(NUMA_PAGE_MIGRATE, nr_succeeded);
+ if (!node_is_toptier(folio_nid(folio)) && node_is_toptier(node))
+@@ -2656,11 +2648,7 @@ int migrate_misplaced_folio(struct folio *folio, struct vm_area_struct *vma,
+ nr_succeeded);
+ }
+ BUG_ON(!list_empty(&migratepages));
+- return isolated;
+-
+-out:
+- folio_put(folio);
+- return 0;
++ return nr_remaining ? -EAGAIN : 0;
+ }
+ #endif /* CONFIG_NUMA_BALANCING */
+ #endif /* CONFIG_NUMA */
+diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
+index 7ae118a6d947b..6ecb110bf46bc 100644
+--- a/net/bluetooth/hci_core.c
++++ b/net/bluetooth/hci_core.c
+@@ -120,13 +120,6 @@ void hci_discovery_set_state(struct hci_dev *hdev, int state)
+ case DISCOVERY_STARTING:
+ break;
+ case DISCOVERY_FINDING:
+- /* If discovery was not started then it was initiated by the
+- * MGMT interface so no MGMT event shall be generated either
+- */
+- if (old_state != DISCOVERY_STARTING) {
+- hdev->discovery.state = old_state;
+- return;
+- }
+ mgmt_discovering(hdev, 1);
+ break;
+ case DISCOVERY_RESOLVING:
+diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
+index 4611a67d7dcc3..a78f6d706cd43 100644
+--- a/net/bluetooth/hci_event.c
++++ b/net/bluetooth/hci_event.c
+@@ -1722,9 +1722,10 @@ static void le_set_scan_enable_complete(struct hci_dev *hdev, u8 enable)
+ switch (enable) {
+ case LE_SCAN_ENABLE:
+ hci_dev_set_flag(hdev, HCI_LE_SCAN);
+- if (hdev->le_scan_type == LE_SCAN_ACTIVE)
++ if (hdev->le_scan_type == LE_SCAN_ACTIVE) {
+ clear_pending_adv_report(hdev);
+- hci_discovery_set_state(hdev, DISCOVERY_FINDING);
++ hci_discovery_set_state(hdev, DISCOVERY_FINDING);
++ }
+ break;
+
+ case LE_SCAN_DISABLE:
+diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
+index bb704088559fb..2f26147fdf3c9 100644
+--- a/net/bluetooth/hci_sync.c
++++ b/net/bluetooth/hci_sync.c
+@@ -2929,6 +2929,27 @@ static int hci_passive_scan_sync(struct hci_dev *hdev)
+ */
+ filter_policy = hci_update_accept_list_sync(hdev);
+
++ /* If suspended and filter_policy set to 0x00 (no acceptlist) then
++ * passive scanning cannot be started since that would require the host
++ * to be woken up to process the reports.
++ */
++ if (hdev->suspended && !filter_policy) {
++ /* Check if accept list is empty then there is no need to scan
++ * while suspended.
++ */
++ if (list_empty(&hdev->le_accept_list))
++ return 0;
++
++ /* If there are devices is the accept_list that means some
++ * devices could not be programmed which in non-suspended case
++ * means filter_policy needs to be set to 0x00 so the host needs
++ * to filter, but since this is treating suspended case we
++ * can ignore device needing host to filter to allow devices in
++ * the acceptlist to be able to wakeup the system.
++ */
++ filter_policy = 0x01;
++ }
++
+ /* When the controller is using random resolvable addresses and
+ * with that having LE privacy enabled, then controllers with
+ * Extended Scanner Filter Policies support can now enable support
+diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c
+index 4668d67180407..5e589f0a62bc5 100644
+--- a/net/core/rtnetlink.c
++++ b/net/core/rtnetlink.c
+@@ -3288,7 +3288,7 @@ static int rtnl_dellink(struct sk_buff *skb, struct nlmsghdr *nlh,
+ if (ifm->ifi_index > 0)
+ dev = __dev_get_by_index(tgt_net, ifm->ifi_index);
+ else if (tb[IFLA_IFNAME] || tb[IFLA_ALT_IFNAME])
+- dev = rtnl_dev_get(net, tb);
++ dev = rtnl_dev_get(tgt_net, tb);
+ else if (tb[IFLA_GROUP])
+ err = rtnl_group_dellink(tgt_net, nla_get_u32(tb[IFLA_GROUP]));
+ else
+diff --git a/net/ethtool/ioctl.c b/net/ethtool/ioctl.c
+index 223dcd25d88a2..fcc3dbef8b503 100644
+--- a/net/ethtool/ioctl.c
++++ b/net/ethtool/ioctl.c
+@@ -1277,11 +1277,11 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
+ u32 rss_cfg_offset = offsetof(struct ethtool_rxfh, rss_config[0]);
+ const struct ethtool_ops *ops = dev->ethtool_ops;
+ u32 dev_indir_size = 0, dev_key_size = 0, i;
++ u32 user_indir_len = 0, indir_bytes = 0;
+ struct ethtool_rxfh_param rxfh_dev = {};
+ struct netlink_ext_ack *extack = NULL;
+ struct ethtool_rxnfc rx_rings;
+ struct ethtool_rxfh rxfh;
+- u32 indir_bytes = 0;
+ u8 *rss_config;
+ int ret;
+
+@@ -1342,6 +1342,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
+ */
+ if (rxfh.indir_size &&
+ rxfh.indir_size != ETH_RXFH_INDIR_NO_CHANGE) {
++ user_indir_len = indir_bytes;
+ rxfh_dev.indir = (u32 *)rss_config;
+ rxfh_dev.indir_size = dev_indir_size;
+ ret = ethtool_copy_validate_indir(rxfh_dev.indir,
+@@ -1368,7 +1369,7 @@ static noinline_for_stack int ethtool_set_rxfh(struct net_device *dev,
+ rxfh_dev.key_size = dev_key_size;
+ rxfh_dev.key = rss_config + indir_bytes;
+ if (copy_from_user(rxfh_dev.key,
+- useraddr + rss_cfg_offset + indir_bytes,
++ useraddr + rss_cfg_offset + user_indir_len,
+ rxfh.key_size)) {
+ ret = -EFAULT;
+ goto out;
+diff --git a/net/ethtool/rss.c b/net/ethtool/rss.c
+index 71679137eff21..5c4c4505ab9a4 100644
+--- a/net/ethtool/rss.c
++++ b/net/ethtool/rss.c
+@@ -111,7 +111,8 @@ rss_reply_size(const struct ethnl_req_info *req_base,
+ const struct rss_reply_data *data = RSS_REPDATA(reply_base);
+ int len;
+
+- len = nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */
++ len = nla_total_size(sizeof(u32)) + /* _RSS_CONTEXT */
++ nla_total_size(sizeof(u32)) + /* _RSS_HFUNC */
+ nla_total_size(sizeof(u32)) + /* _RSS_INPUT_XFRM */
+ nla_total_size(sizeof(u32) * data->indir_size) + /* _RSS_INDIR */
+ nla_total_size(data->hkey_size); /* _RSS_HKEY */
+@@ -124,6 +125,11 @@ rss_fill_reply(struct sk_buff *skb, const struct ethnl_req_info *req_base,
+ const struct ethnl_reply_data *reply_base)
+ {
+ const struct rss_reply_data *data = RSS_REPDATA(reply_base);
++ struct rss_req_info *request = RSS_REQINFO(req_base);
++
++ if (request->rss_context &&
++ nla_put_u32(skb, ETHTOOL_A_RSS_CONTEXT, request->rss_context))
++ return -EMSGSIZE;
+
+ if ((data->hfunc &&
+ nla_put_u32(skb, ETHTOOL_A_RSS_HFUNC, data->hfunc)) ||
+diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c
+index 4d42d0756fd70..a5db7c67d61be 100644
+--- a/net/ipv4/netfilter/iptable_nat.c
++++ b/net/ipv4/netfilter/iptable_nat.c
+@@ -145,25 +145,27 @@ static struct pernet_operations iptable_nat_net_ops = {
+
+ static int __init iptable_nat_init(void)
+ {
+- int ret = xt_register_template(&nf_nat_ipv4_table,
+- iptable_nat_table_init);
++ int ret;
+
++ /* net->gen->ptr[iptable_nat_net_id] must be allocated
++ * before calling iptable_nat_table_init().
++ */
++ ret = register_pernet_subsys(&iptable_nat_net_ops);
+ if (ret < 0)
+ return ret;
+
+- ret = register_pernet_subsys(&iptable_nat_net_ops);
+- if (ret < 0) {
+- xt_unregister_template(&nf_nat_ipv4_table);
+- return ret;
+- }
++ ret = xt_register_template(&nf_nat_ipv4_table,
++ iptable_nat_table_init);
++ if (ret < 0)
++ unregister_pernet_subsys(&iptable_nat_net_ops);
+
+ return ret;
+ }
+
+ static void __exit iptable_nat_exit(void)
+ {
+- unregister_pernet_subsys(&iptable_nat_net_ops);
+ xt_unregister_template(&nf_nat_ipv4_table);
++ unregister_pernet_subsys(&iptable_nat_net_ops);
+ }
+
+ module_init(iptable_nat_init);
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+index 570e87ad9a56e..ecd521108559f 100644
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -754,8 +754,7 @@ void tcp_rcv_space_adjust(struct sock *sk)
+ * <prev RTT . ><current RTT .. ><next RTT .... >
+ */
+
+- if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) &&
+- !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
++ if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf)) {
+ u64 rcvwin, grow;
+ int rcvbuf;
+
+@@ -771,12 +770,22 @@ void tcp_rcv_space_adjust(struct sock *sk)
+
+ rcvbuf = min_t(u64, tcp_space_from_win(sk, rcvwin),
+ READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]));
+- if (rcvbuf > sk->sk_rcvbuf) {
+- WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
++ if (!(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) {
++ if (rcvbuf > sk->sk_rcvbuf) {
++ WRITE_ONCE(sk->sk_rcvbuf, rcvbuf);
+
+- /* Make the window clamp follow along. */
+- WRITE_ONCE(tp->window_clamp,
+- tcp_win_from_space(sk, rcvbuf));
++ /* Make the window clamp follow along. */
++ WRITE_ONCE(tp->window_clamp,
++ tcp_win_from_space(sk, rcvbuf));
++ }
++ } else {
++ /* Make the window clamp follow along while being bounded
++ * by SO_RCVBUF.
++ */
++ int clamp = tcp_win_from_space(sk, min(rcvbuf, sk->sk_rcvbuf));
++
++ if (clamp > tp->window_clamp)
++ WRITE_ONCE(tp->window_clamp, clamp);
+ }
+ }
+ tp->rcvq_space.space = copied;
+diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c
+index d914b23256ce6..0282d15725095 100644
+--- a/net/ipv6/ndisc.c
++++ b/net/ipv6/ndisc.c
+@@ -227,6 +227,7 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+ return NULL;
+ memset(ndopts, 0, sizeof(*ndopts));
+ while (opt_len) {
++ bool unknown = false;
+ int l;
+ if (opt_len < sizeof(struct nd_opt_hdr))
+ return NULL;
+@@ -262,22 +263,23 @@ struct ndisc_options *ndisc_parse_options(const struct net_device *dev,
+ break;
+ #endif
+ default:
+- if (ndisc_is_useropt(dev, nd_opt)) {
+- ndopts->nd_useropts_end = nd_opt;
+- if (!ndopts->nd_useropts)
+- ndopts->nd_useropts = nd_opt;
+- } else {
+- /*
+- * Unknown options must be silently ignored,
+- * to accommodate future extension to the
+- * protocol.
+- */
+- ND_PRINTK(2, notice,
+- "%s: ignored unsupported option; type=%d, len=%d\n",
+- __func__,
+- nd_opt->nd_opt_type,
+- nd_opt->nd_opt_len);
+- }
++ unknown = true;
++ }
++ if (ndisc_is_useropt(dev, nd_opt)) {
++ ndopts->nd_useropts_end = nd_opt;
++ if (!ndopts->nd_useropts)
++ ndopts->nd_useropts = nd_opt;
++ } else if (unknown) {
++ /*
++ * Unknown options must be silently ignored,
++ * to accommodate future extension to the
++ * protocol.
++ */
++ ND_PRINTK(2, notice,
++ "%s: ignored unsupported option; type=%d, len=%d\n",
++ __func__,
++ nd_opt->nd_opt_type,
++ nd_opt->nd_opt_len);
+ }
+ next_opt:
+ opt_len -= l;
+diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c
+index 52cf104e34788..e119d4f090cc8 100644
+--- a/net/ipv6/netfilter/ip6table_nat.c
++++ b/net/ipv6/netfilter/ip6table_nat.c
+@@ -147,23 +147,27 @@ static struct pernet_operations ip6table_nat_net_ops = {
+
+ static int __init ip6table_nat_init(void)
+ {
+- int ret = xt_register_template(&nf_nat_ipv6_table,
+- ip6table_nat_table_init);
++ int ret;
+
++ /* net->gen->ptr[ip6table_nat_net_id] must be allocated
++ * before calling ip6t_nat_register_lookups().
++ */
++ ret = register_pernet_subsys(&ip6table_nat_net_ops);
+ if (ret < 0)
+ return ret;
+
+- ret = register_pernet_subsys(&ip6table_nat_net_ops);
++ ret = xt_register_template(&nf_nat_ipv6_table,
++ ip6table_nat_table_init);
+ if (ret)
+- xt_unregister_template(&nf_nat_ipv6_table);
++ unregister_pernet_subsys(&ip6table_nat_net_ops);
+
+ return ret;
+ }
+
+ static void __exit ip6table_nat_exit(void)
+ {
+- unregister_pernet_subsys(&ip6table_nat_net_ops);
+ xt_unregister_template(&nf_nat_ipv6_table);
++ unregister_pernet_subsys(&ip6table_nat_net_ops);
+ }
+
+ module_init(ip6table_nat_init);
+diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c
+index c3b0b610b0aa3..c00323fa9eb66 100644
+--- a/net/iucv/af_iucv.c
++++ b/net/iucv/af_iucv.c
+@@ -335,8 +335,8 @@ static void iucv_sever_path(struct sock *sk, int with_user_data)
+ struct iucv_sock *iucv = iucv_sk(sk);
+ struct iucv_path *path = iucv->path;
+
+- if (iucv->path) {
+- iucv->path = NULL;
++ /* Whoever resets the path pointer, must sever and free it. */
++ if (xchg(&iucv->path, NULL)) {
+ if (with_user_data) {
+ low_nmcpy(user_data, iucv->src_name);
+ high_nmcpy(user_data, iucv->dst_name);
+diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c
+index 83ad6c9709fe6..87a7b569cc774 100644
+--- a/net/mac80211/cfg.c
++++ b/net/mac80211/cfg.c
+@@ -114,7 +114,7 @@ static int ieee80211_set_mon_options(struct ieee80211_sub_if_data *sdata,
+
+ /* apply all changes now - no failures allowed */
+
+- if (monitor_sdata)
++ if (monitor_sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
+ ieee80211_set_mu_mimo_follow(monitor_sdata, params);
+
+ if (params->flags) {
+@@ -3038,6 +3038,9 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
+ sdata = IEEE80211_WDEV_TO_SUB_IF(wdev);
+
+ if (sdata->vif.type == NL80211_IFTYPE_MONITOR) {
++ if (!ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF))
++ return -EOPNOTSUPP;
++
+ sdata = wiphy_dereference(local->hw.wiphy,
+ local->monitor_sdata);
+ if (!sdata)
+@@ -3100,7 +3103,7 @@ static int ieee80211_set_tx_power(struct wiphy *wiphy,
+ if (has_monitor) {
+ sdata = wiphy_dereference(local->hw.wiphy,
+ local->monitor_sdata);
+- if (sdata) {
++ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
+ sdata->deflink.user_power_level = local->user_power_level;
+ if (txp_type != sdata->vif.bss_conf.txpower_type)
+ update_txp_type = true;
+diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
+index 72a9ba8bc5fd9..edba4a31844fb 100644
+--- a/net/mac80211/tx.c
++++ b/net/mac80211/tx.c
+@@ -1768,7 +1768,7 @@ static bool __ieee80211_tx(struct ieee80211_local *local,
+ break;
+ }
+ sdata = rcu_dereference(local->monitor_sdata);
+- if (sdata) {
++ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
+ vif = &sdata->vif;
+ info->hw_queue =
+ vif->hw_queue[skb_get_queue_mapping(skb)];
+@@ -3957,7 +3957,8 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
+ break;
+ }
+ tx.sdata = rcu_dereference(local->monitor_sdata);
+- if (tx.sdata) {
++ if (tx.sdata &&
++ ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF)) {
+ vif = &tx.sdata->vif;
+ info->hw_queue =
+ vif->hw_queue[skb_get_queue_mapping(skb)];
+diff --git a/net/mac80211/util.c b/net/mac80211/util.c
+index 771c05640aa3a..c11dbe82ae1b3 100644
+--- a/net/mac80211/util.c
++++ b/net/mac80211/util.c
+@@ -776,7 +776,7 @@ static void __iterate_interfaces(struct ieee80211_local *local,
+ sdata = rcu_dereference_check(local->monitor_sdata,
+ lockdep_is_held(&local->iflist_mtx) ||
+ lockdep_is_held(&local->hw.wiphy->mtx));
+- if (sdata &&
++ if (sdata && ieee80211_hw_check(&local->hw, WANT_MONITOR_VIF) &&
+ (iter_flags & IEEE80211_IFACE_ITER_RESUME_ALL || !active_only ||
+ sdata->flags & IEEE80211_SDATA_IN_DRIVER))
+ iterator(data, sdata->vif.addr, &sdata->vif);
+diff --git a/net/mptcp/mib.c b/net/mptcp/mib.c
+index c30405e768337..7884217f33eb2 100644
+--- a/net/mptcp/mib.c
++++ b/net/mptcp/mib.c
+@@ -19,7 +19,9 @@ static const struct snmp_mib mptcp_snmp_list[] = {
+ SNMP_MIB_ITEM("MPTCPRetrans", MPTCP_MIB_RETRANSSEGS),
+ SNMP_MIB_ITEM("MPJoinNoTokenFound", MPTCP_MIB_JOINNOTOKEN),
+ SNMP_MIB_ITEM("MPJoinSynRx", MPTCP_MIB_JOINSYNRX),
++ SNMP_MIB_ITEM("MPJoinSynBackupRx", MPTCP_MIB_JOINSYNBACKUPRX),
+ SNMP_MIB_ITEM("MPJoinSynAckRx", MPTCP_MIB_JOINSYNACKRX),
++ SNMP_MIB_ITEM("MPJoinSynAckBackupRx", MPTCP_MIB_JOINSYNACKBACKUPRX),
+ SNMP_MIB_ITEM("MPJoinSynAckHMacFailure", MPTCP_MIB_JOINSYNACKMAC),
+ SNMP_MIB_ITEM("MPJoinAckRx", MPTCP_MIB_JOINACKRX),
+ SNMP_MIB_ITEM("MPJoinAckHMacFailure", MPTCP_MIB_JOINACKMAC),
+diff --git a/net/mptcp/mib.h b/net/mptcp/mib.h
+index 2704afd0dfe45..66aa67f49d032 100644
+--- a/net/mptcp/mib.h
++++ b/net/mptcp/mib.h
+@@ -14,7 +14,9 @@ enum linux_mptcp_mib_field {
+ MPTCP_MIB_RETRANSSEGS, /* Segments retransmitted at the MPTCP-level */
+ MPTCP_MIB_JOINNOTOKEN, /* Received MP_JOIN but the token was not found */
+ MPTCP_MIB_JOINSYNRX, /* Received a SYN + MP_JOIN */
++ MPTCP_MIB_JOINSYNBACKUPRX, /* Received a SYN + MP_JOIN + backup flag */
+ MPTCP_MIB_JOINSYNACKRX, /* Received a SYN/ACK + MP_JOIN */
++ MPTCP_MIB_JOINSYNACKBACKUPRX, /* Received a SYN/ACK + MP_JOIN + backup flag */
+ MPTCP_MIB_JOINSYNACKMAC, /* HMAC was wrong on SYN/ACK + MP_JOIN */
+ MPTCP_MIB_JOINACKRX, /* Received an ACK + MP_JOIN */
+ MPTCP_MIB_JOINACKMAC, /* HMAC was wrong on ACK + MP_JOIN */
+diff --git a/net/mptcp/options.c b/net/mptcp/options.c
+index 8e8dcfbc29938..8a68382a4fe91 100644
+--- a/net/mptcp/options.c
++++ b/net/mptcp/options.c
+@@ -909,7 +909,7 @@ bool mptcp_synack_options(const struct request_sock *req, unsigned int *size,
+ return true;
+ } else if (subflow_req->mp_join) {
+ opts->suboptions = OPTION_MPTCP_MPJ_SYNACK;
+- opts->backup = subflow_req->backup;
++ opts->backup = subflow_req->request_bkup;
+ opts->join_id = subflow_req->local_id;
+ opts->thmac = subflow_req->thmac;
+ opts->nonce = subflow_req->local_nonce;
+diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c
+index 55406720c6071..23bb89c94e90d 100644
+--- a/net/mptcp/pm.c
++++ b/net/mptcp/pm.c
+@@ -426,6 +426,18 @@ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc)
+ return mptcp_pm_nl_get_local_id(msk, &skc_local);
+ }
+
++bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc)
++{
++ struct mptcp_addr_info skc_local;
++
++ mptcp_local_address((struct sock_common *)skc, &skc_local);
++
++ if (mptcp_pm_is_userspace(msk))
++ return mptcp_userspace_pm_is_backup(msk, &skc_local);
++
++ return mptcp_pm_nl_is_backup(msk, &skc_local);
++}
++
+ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id,
+ u8 *flags, int *ifindex)
+ {
+diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c
+index ea9e5817b9e9d..37954a0b087d2 100644
+--- a/net/mptcp/pm_netlink.c
++++ b/net/mptcp/pm_netlink.c
+@@ -471,7 +471,6 @@ static void __mptcp_pm_send_ack(struct mptcp_sock *msk, struct mptcp_subflow_con
+ slow = lock_sock_fast(ssk);
+ if (prio) {
+ subflow->send_mp_prio = 1;
+- subflow->backup = backup;
+ subflow->request_bkup = backup;
+ }
+
+@@ -1102,6 +1101,24 @@ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc
+ return ret;
+ }
+
++bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc)
++{
++ struct pm_nl_pernet *pernet = pm_nl_get_pernet_from_msk(msk);
++ struct mptcp_pm_addr_entry *entry;
++ bool backup = false;
++
++ rcu_read_lock();
++ list_for_each_entry_rcu(entry, &pernet->local_addr_list, list) {
++ if (mptcp_addresses_equal(&entry->addr, skc, entry->addr.port)) {
++ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
++ break;
++ }
++ }
++ rcu_read_unlock();
++
++ return backup;
++}
++
+ #define MPTCP_PM_CMD_GRP_OFFSET 0
+ #define MPTCP_PM_EV_GRP_OFFSET 1
+
+@@ -1401,6 +1418,7 @@ static bool mptcp_pm_remove_anno_addr(struct mptcp_sock *msk,
+ ret = remove_anno_list_by_saddr(msk, addr);
+ if (ret || force) {
+ spin_lock_bh(&msk->pm.lock);
++ msk->pm.add_addr_signaled -= ret;
+ mptcp_pm_remove_addr(msk, &list);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+@@ -1534,16 +1552,25 @@ void mptcp_pm_remove_addrs(struct mptcp_sock *msk, struct list_head *rm_list)
+ {
+ struct mptcp_rm_list alist = { .nr = 0 };
+ struct mptcp_pm_addr_entry *entry;
++ int anno_nr = 0;
+
+ list_for_each_entry(entry, rm_list, list) {
+- if ((remove_anno_list_by_saddr(msk, &entry->addr) ||
+- lookup_subflow_by_saddr(&msk->conn_list, &entry->addr)) &&
+- alist.nr < MPTCP_RM_IDS_MAX)
+- alist.ids[alist.nr++] = entry->addr.id;
++ if (alist.nr >= MPTCP_RM_IDS_MAX)
++ break;
++
++ /* only delete if either announced or matching a subflow */
++ if (remove_anno_list_by_saddr(msk, &entry->addr))
++ anno_nr++;
++ else if (!lookup_subflow_by_saddr(&msk->conn_list,
++ &entry->addr))
++ continue;
++
++ alist.ids[alist.nr++] = entry->addr.id;
+ }
+
+ if (alist.nr) {
+ spin_lock_bh(&msk->pm.lock);
++ msk->pm.add_addr_signaled -= anno_nr;
+ mptcp_pm_remove_addr(msk, &alist);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+@@ -1556,17 +1583,18 @@ static void mptcp_pm_remove_addrs_and_subflows(struct mptcp_sock *msk,
+ struct mptcp_pm_addr_entry *entry;
+
+ list_for_each_entry(entry, rm_list, list) {
+- if (lookup_subflow_by_saddr(&msk->conn_list, &entry->addr) &&
+- slist.nr < MPTCP_RM_IDS_MAX)
++ if (slist.nr < MPTCP_RM_IDS_MAX &&
++ lookup_subflow_by_saddr(&msk->conn_list, &entry->addr))
+ slist.ids[slist.nr++] = entry->addr.id;
+
+- if (remove_anno_list_by_saddr(msk, &entry->addr) &&
+- alist.nr < MPTCP_RM_IDS_MAX)
++ if (alist.nr < MPTCP_RM_IDS_MAX &&
++ remove_anno_list_by_saddr(msk, &entry->addr))
+ alist.ids[alist.nr++] = entry->addr.id;
+ }
+
+ if (alist.nr) {
+ spin_lock_bh(&msk->pm.lock);
++ msk->pm.add_addr_signaled -= alist.nr;
+ mptcp_pm_remove_addr(msk, &alist);
+ spin_unlock_bh(&msk->pm.lock);
+ }
+diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c
+index f0a4590506c69..8eaa9fbe3e343 100644
+--- a/net/mptcp/pm_userspace.c
++++ b/net/mptcp/pm_userspace.c
+@@ -165,6 +165,24 @@ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk,
+ return mptcp_userspace_pm_append_new_local_addr(msk, &new_entry, true);
+ }
+
++bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk,
++ struct mptcp_addr_info *skc)
++{
++ struct mptcp_pm_addr_entry *entry;
++ bool backup = false;
++
++ spin_lock_bh(&msk->pm.lock);
++ list_for_each_entry(entry, &msk->pm.userspace_pm_local_addr_list, list) {
++ if (mptcp_addresses_equal(&entry->addr, skc, false)) {
++ backup = !!(entry->flags & MPTCP_PM_ADDR_FLAG_BACKUP);
++ break;
++ }
++ }
++ spin_unlock_bh(&msk->pm.lock);
++
++ return backup;
++}
++
+ int mptcp_pm_nl_announce_doit(struct sk_buff *skb, struct genl_info *info)
+ {
+ struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN];
+diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c
+index bb7dca8aa2d9c..ff8292d0cf4e6 100644
+--- a/net/mptcp/protocol.c
++++ b/net/mptcp/protocol.c
+@@ -350,8 +350,10 @@ static bool __mptcp_move_skb(struct mptcp_sock *msk, struct sock *ssk,
+ skb_orphan(skb);
+
+ /* try to fetch required memory from subflow */
+- if (!mptcp_rmem_schedule(sk, ssk, skb->truesize))
++ if (!mptcp_rmem_schedule(sk, ssk, skb->truesize)) {
++ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
+ goto drop;
++ }
+
+ has_rxtstamp = TCP_SKB_CB(skb)->has_rxtstamp;
+
+@@ -844,10 +846,8 @@ void mptcp_data_ready(struct sock *sk, struct sock *ssk)
+ sk_rbuf = ssk_rbuf;
+
+ /* over limit? can't append more skbs to msk, Also, no need to wake-up*/
+- if (__mptcp_rmem(sk) > sk_rbuf) {
+- MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RCVPRUNED);
++ if (__mptcp_rmem(sk) > sk_rbuf)
+ return;
+- }
+
+ /* Wake-up the reader only for in-sequence data */
+ mptcp_data_lock(sk);
+@@ -1422,13 +1422,15 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+ }
+
+ mptcp_for_each_subflow(msk, subflow) {
++ bool backup = subflow->backup || subflow->request_bkup;
++
+ trace_mptcp_subflow_get_send(subflow);
+ ssk = mptcp_subflow_tcp_sock(subflow);
+ if (!mptcp_subflow_active(subflow))
+ continue;
+
+ tout = max(tout, mptcp_timeout_from_subflow(subflow));
+- nr_active += !subflow->backup;
++ nr_active += !backup;
+ pace = subflow->avg_pacing_rate;
+ if (unlikely(!pace)) {
+ /* init pacing rate from socket */
+@@ -1439,9 +1441,9 @@ struct sock *mptcp_subflow_get_send(struct mptcp_sock *msk)
+ }
+
+ linger_time = div_u64((u64)READ_ONCE(ssk->sk_wmem_queued) << 32, pace);
+- if (linger_time < send_info[subflow->backup].linger_time) {
+- send_info[subflow->backup].ssk = ssk;
+- send_info[subflow->backup].linger_time = linger_time;
++ if (linger_time < send_info[backup].linger_time) {
++ send_info[backup].ssk = ssk;
++ send_info[backup].linger_time = linger_time;
+ }
+ }
+ __mptcp_set_timeout(sk, tout);
+diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h
+index 7aa47e2dd52b1..8357046732f71 100644
+--- a/net/mptcp/protocol.h
++++ b/net/mptcp/protocol.h
+@@ -443,6 +443,7 @@ struct mptcp_subflow_request_sock {
+ u16 mp_capable : 1,
+ mp_join : 1,
+ backup : 1,
++ request_bkup : 1,
+ csum_reqd : 1,
+ allow_join_id0 : 1;
+ u8 local_id;
+@@ -1103,6 +1104,9 @@ bool mptcp_pm_rm_addr_signal(struct mptcp_sock *msk, unsigned int remaining,
+ int mptcp_pm_get_local_id(struct mptcp_sock *msk, struct sock_common *skc);
+ int mptcp_pm_nl_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+ int mptcp_userspace_pm_get_local_id(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
++bool mptcp_pm_is_backup(struct mptcp_sock *msk, struct sock_common *skc);
++bool mptcp_pm_nl_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
++bool mptcp_userspace_pm_is_backup(struct mptcp_sock *msk, struct mptcp_addr_info *skc);
+ int mptcp_pm_dump_addr(struct sk_buff *msg, struct netlink_callback *cb);
+ int mptcp_pm_nl_dump_addr(struct sk_buff *msg,
+ struct netlink_callback *cb);
+diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c
+index 612c38570a642..c330946384ba0 100644
+--- a/net/mptcp/subflow.c
++++ b/net/mptcp/subflow.c
+@@ -100,6 +100,7 @@ static struct mptcp_sock *subflow_token_join_request(struct request_sock *req)
+ return NULL;
+ }
+ subflow_req->local_id = local_id;
++ subflow_req->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)req);
+
+ return msk;
+ }
+@@ -168,6 +169,9 @@ static int subflow_check_req(struct request_sock *req,
+ return 0;
+ } else if (opt_mp_join) {
+ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNRX);
++
++ if (mp_opt.backup)
++ SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_JOINSYNBACKUPRX);
+ }
+
+ if (opt_mp_capable && listener->request_mptcp) {
+@@ -577,6 +581,9 @@ static void subflow_finish_connect(struct sock *sk, const struct sk_buff *skb)
+ subflow->mp_join = 1;
+ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKRX);
+
++ if (subflow->backup)
++ MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_JOINSYNACKBACKUPRX);
++
+ if (subflow_use_different_dport(msk, sk)) {
+ pr_debug("synack inet_dport=%d %d",
+ ntohs(inet_sk(sk)->inet_dport),
+@@ -614,6 +621,8 @@ static int subflow_chk_local_id(struct sock *sk)
+ return err;
+
+ subflow_set_local_id(subflow, err);
++ subflow->request_bkup = mptcp_pm_is_backup(msk, (struct sock_common *)sk);
++
+ return 0;
+ }
+
+@@ -1221,14 +1230,22 @@ static void mptcp_subflow_discard_data(struct sock *ssk, struct sk_buff *skb,
+ {
+ struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk);
+ bool fin = TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN;
+- u32 incr;
++ struct tcp_sock *tp = tcp_sk(ssk);
++ u32 offset, incr, avail_len;
+
+- incr = limit >= skb->len ? skb->len + fin : limit;
++ offset = tp->copied_seq - TCP_SKB_CB(skb)->seq;
++ if (WARN_ON_ONCE(offset > skb->len))
++ goto out;
+
+- pr_debug("discarding=%d len=%d seq=%d", incr, skb->len,
+- subflow->map_subflow_seq);
++ avail_len = skb->len - offset;
++ incr = limit >= avail_len ? avail_len + fin : limit;
++
++ pr_debug("discarding=%d len=%d offset=%d seq=%d", incr, skb->len,
++ offset, subflow->map_subflow_seq);
+ MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DUPDATA);
+ tcp_sk(ssk)->copied_seq += incr;
++
++out:
+ if (!before(tcp_sk(ssk)->copied_seq, TCP_SKB_CB(skb)->end_seq))
+ sk_eat_skb(ssk, skb);
+ if (mptcp_subflow_get_map_offset(subflow) >= subflow->map_data_len)
+@@ -2005,6 +2022,7 @@ static void subflow_ulp_clone(const struct request_sock *req,
+ new_ctx->fully_established = 1;
+ new_ctx->remote_key_valid = 1;
+ new_ctx->backup = subflow_req->backup;
++ new_ctx->request_bkup = subflow_req->request_bkup;
+ WRITE_ONCE(new_ctx->remote_id, subflow_req->remote_id);
+ new_ctx->token = subflow_req->token;
+ new_ctx->thmac = subflow_req->thmac;
+diff --git a/net/sched/act_ct.c b/net/sched/act_ct.c
+index 6fa3cca87d346..9d451d77d54e2 100644
+--- a/net/sched/act_ct.c
++++ b/net/sched/act_ct.c
+@@ -44,6 +44,8 @@ static DEFINE_MUTEX(zones_mutex);
+ struct zones_ht_key {
+ struct net *net;
+ u16 zone;
++ /* Note : pad[] must be the last field. */
++ u8 pad[];
+ };
+
+ struct tcf_ct_flow_table {
+@@ -60,7 +62,7 @@ struct tcf_ct_flow_table {
+ static const struct rhashtable_params zones_params = {
+ .head_offset = offsetof(struct tcf_ct_flow_table, node),
+ .key_offset = offsetof(struct tcf_ct_flow_table, key),
+- .key_len = sizeof_field(struct tcf_ct_flow_table, key),
++ .key_len = offsetof(struct zones_ht_key, pad),
+ .automatic_shrinking = true,
+ };
+
+diff --git a/net/wireless/scan.c b/net/wireless/scan.c
+index 0222ede0feb60..292b530a6dd31 100644
+--- a/net/wireless/scan.c
++++ b/net/wireless/scan.c
+@@ -3136,8 +3136,7 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
+ struct ieee80211_mgmt *mgmt, size_t len,
+ gfp_t gfp)
+ {
+- size_t min_hdr_len = offsetof(struct ieee80211_mgmt,
+- u.probe_resp.variable);
++ size_t min_hdr_len;
+ struct ieee80211_ext *ext = NULL;
+ enum cfg80211_bss_frame_type ftype;
+ u16 beacon_interval;
+@@ -3160,10 +3159,16 @@ cfg80211_inform_bss_frame_data(struct wiphy *wiphy,
+
+ if (ieee80211_is_s1g_beacon(mgmt->frame_control)) {
+ ext = (void *) mgmt;
+- min_hdr_len = offsetof(struct ieee80211_ext, u.s1g_beacon);
+ if (ieee80211_is_s1g_short_beacon(mgmt->frame_control))
+ min_hdr_len = offsetof(struct ieee80211_ext,
+ u.s1g_short_beacon.variable);
++ else
++ min_hdr_len = offsetof(struct ieee80211_ext,
++ u.s1g_beacon.variable);
++ } else {
++ /* same for beacons */
++ min_hdr_len = offsetof(struct ieee80211_mgmt,
++ u.probe_resp.variable);
+ }
+
+ if (WARN_ON(len < min_hdr_len))
+diff --git a/net/wireless/sme.c b/net/wireless/sme.c
+index a8ad55f11133b..1cfe673bc52f3 100644
+--- a/net/wireless/sme.c
++++ b/net/wireless/sme.c
+@@ -1045,6 +1045,7 @@ void cfg80211_connect_done(struct net_device *dev,
+ cfg80211_hold_bss(
+ bss_from_pub(params->links[link].bss));
+ ev->cr.links[link].bss = params->links[link].bss;
++ ev->cr.links[link].status = params->links[link].status;
+
+ if (params->links[link].addr) {
+ ev->cr.links[link].addr = next;
+diff --git a/sound/core/seq/seq_ump_convert.c b/sound/core/seq/seq_ump_convert.c
+index e90b27a135e6f..d9dacfbe4a9ae 100644
+--- a/sound/core/seq/seq_ump_convert.c
++++ b/sound/core/seq/seq_ump_convert.c
+@@ -1192,44 +1192,53 @@ static int cvt_sysex_to_ump(struct snd_seq_client *dest,
+ {
+ struct snd_seq_ump_event ev_cvt;
+ unsigned char status;
+- u8 buf[6], *xbuf;
++ u8 buf[8], *xbuf;
+ int offset = 0;
+ int len, err;
++ bool finished = false;
+
+ if (!snd_seq_ev_is_variable(event))
+ return 0;
+
+ setup_ump_event(&ev_cvt, event);
+- for (;;) {
++ while (!finished) {
+ len = snd_seq_expand_var_event_at(event, sizeof(buf), buf, offset);
+ if (len <= 0)
+ break;
+- if (WARN_ON(len > 6))
++ if (WARN_ON(len > sizeof(buf)))
+ break;
+- offset += len;
++
+ xbuf = buf;
++ status = UMP_SYSEX_STATUS_CONTINUE;
++ /* truncate the sysex start-marker */
+ if (*xbuf == UMP_MIDI1_MSG_SYSEX_START) {
+ status = UMP_SYSEX_STATUS_START;
+- xbuf++;
+ len--;
+- if (len > 0 && xbuf[len - 1] == UMP_MIDI1_MSG_SYSEX_END) {
++ offset++;
++ xbuf++;
++ }
++
++ /* if the last of this packet or the 1st byte of the next packet
++ * is the end-marker, finish the transfer with this packet
++ */
++ if (len > 0 && len < 8 &&
++ xbuf[len - 1] == UMP_MIDI1_MSG_SYSEX_END) {
++ if (status == UMP_SYSEX_STATUS_START)
+ status = UMP_SYSEX_STATUS_SINGLE;
+- len--;
+- }
+- } else {
+- if (xbuf[len - 1] == UMP_MIDI1_MSG_SYSEX_END) {
++ else
+ status = UMP_SYSEX_STATUS_END;
+- len--;
+- } else {
+- status = UMP_SYSEX_STATUS_CONTINUE;
+- }
++ len--;
++ finished = true;
+ }
++
++ len = min(len, 6);
+ fill_sysex7_ump(dest_port, ev_cvt.ump, status, xbuf, len);
+ err = __snd_seq_deliver_single_event(dest, dest_port,
+ (struct snd_seq_event *)&ev_cvt,
+ atomic, hop);
+ if (err < 0)
+ return err;
++ offset += len;
+ }
+ return 0;
+ }
+diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
+index 1a163bbcabd79..c827d7d8d8003 100644
+--- a/sound/firewire/amdtp-stream.c
++++ b/sound/firewire/amdtp-stream.c
+@@ -77,6 +77,8 @@
+ // overrun. Actual device can skip more, then this module stops the packet streaming.
+ #define IR_JUMBO_PAYLOAD_MAX_SKIP_CYCLES 5
+
++static void pcm_period_work(struct work_struct *work);
++
+ /**
+ * amdtp_stream_init - initialize an AMDTP stream structure
+ * @s: the AMDTP stream to initialize
+@@ -105,6 +107,7 @@ int amdtp_stream_init(struct amdtp_stream *s, struct fw_unit *unit,
+ s->flags = flags;
+ s->context = ERR_PTR(-1);
+ mutex_init(&s->mutex);
++ INIT_WORK(&s->period_work, pcm_period_work);
+ s->packet_index = 0;
+
+ init_waitqueue_head(&s->ready_wait);
+@@ -347,6 +350,7 @@ EXPORT_SYMBOL(amdtp_stream_get_max_payload);
+ */
+ void amdtp_stream_pcm_prepare(struct amdtp_stream *s)
+ {
++ cancel_work_sync(&s->period_work);
+ s->pcm_buffer_pointer = 0;
+ s->pcm_period_pointer = 0;
+ }
+@@ -611,19 +615,21 @@ static void update_pcm_pointers(struct amdtp_stream *s,
+ // The program in user process should periodically check the status of intermediate
+ // buffer associated to PCM substream to process PCM frames in the buffer, instead
+ // of receiving notification of period elapsed by poll wait.
+- if (!pcm->runtime->no_period_wakeup) {
+- if (in_softirq()) {
+- // In software IRQ context for 1394 OHCI.
+- snd_pcm_period_elapsed(pcm);
+- } else {
+- // In process context of ALSA PCM application under acquired lock of
+- // PCM substream.
+- snd_pcm_period_elapsed_under_stream_lock(pcm);
+- }
+- }
++ if (!pcm->runtime->no_period_wakeup)
++ queue_work(system_highpri_wq, &s->period_work);
+ }
+ }
+
++static void pcm_period_work(struct work_struct *work)
++{
++ struct amdtp_stream *s = container_of(work, struct amdtp_stream,
++ period_work);
++ struct snd_pcm_substream *pcm = READ_ONCE(s->pcm);
++
++ if (pcm)
++ snd_pcm_period_elapsed(pcm);
++}
++
+ static int queue_packet(struct amdtp_stream *s, struct fw_iso_packet *params,
+ bool sched_irq)
+ {
+@@ -1849,11 +1855,14 @@ unsigned long amdtp_domain_stream_pcm_pointer(struct amdtp_domain *d,
+ {
+ struct amdtp_stream *irq_target = d->irq_target;
+
+- // Process isochronous packets queued till recent isochronous cycle to handle PCM frames.
+ if (irq_target && amdtp_stream_running(irq_target)) {
+- // In software IRQ context, the call causes dead-lock to disable the tasklet
+- // synchronously.
+- if (!in_softirq())
++ // use wq to prevent AB/BA deadlock competition for
++ // substream lock:
++ // fw_iso_context_flush_completions() acquires
++ // lock by ohci_flush_iso_completions(),
++ // amdtp-stream process_rx_packets() attempts to
++ // acquire same lock by snd_pcm_elapsed()
++ if (current_work() != &s->period_work)
+ fw_iso_context_flush_completions(irq_target->context);
+ }
+
+@@ -1909,6 +1918,7 @@ static void amdtp_stream_stop(struct amdtp_stream *s)
+ return;
+ }
+
++ cancel_work_sync(&s->period_work);
+ fw_iso_context_stop(s->context);
+ fw_iso_context_destroy(s->context);
+ s->context = ERR_PTR(-1);
+diff --git a/sound/firewire/amdtp-stream.h b/sound/firewire/amdtp-stream.h
+index a1ed2e80f91a7..775db3fc4959f 100644
+--- a/sound/firewire/amdtp-stream.h
++++ b/sound/firewire/amdtp-stream.h
+@@ -191,6 +191,7 @@ struct amdtp_stream {
+
+ /* For a PCM substream processing. */
+ struct snd_pcm_substream *pcm;
++ struct work_struct period_work;
+ snd_pcm_uframes_t pcm_buffer_pointer;
+ unsigned int pcm_period_pointer;
+ unsigned int pcm_frame_multiplier;
+diff --git a/sound/pci/hda/hda_controller.h b/sound/pci/hda/hda_controller.h
+index c2d0109866e62..68c883f202ca5 100644
+--- a/sound/pci/hda/hda_controller.h
++++ b/sound/pci/hda/hda_controller.h
+@@ -28,7 +28,7 @@
+ #else
+ #define AZX_DCAPS_I915_COMPONENT 0 /* NOP */
+ #endif
+-/* 14 unused */
++#define AZX_DCAPS_AMD_ALLOC_FIX (1 << 14) /* AMD allocation workaround */
+ #define AZX_DCAPS_CTX_WORKAROUND (1 << 15) /* X-Fi workaround */
+ #define AZX_DCAPS_POSFIX_LPIB (1 << 16) /* Use LPIB as default */
+ #define AZX_DCAPS_AMD_WORKAROUND (1 << 17) /* AMD-specific workaround */
+diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
+index 3500108f6ba37..87203b819dd47 100644
+--- a/sound/pci/hda/hda_intel.c
++++ b/sound/pci/hda/hda_intel.c
+@@ -40,6 +40,7 @@
+
+ #ifdef CONFIG_X86
+ /* for snoop control */
++#include <linux/dma-map-ops.h>
+ #include <asm/set_memory.h>
+ #include <asm/cpufeature.h>
+ #endif
+@@ -306,7 +307,7 @@ enum {
+
+ /* quirks for ATI HDMI with snoop off */
+ #define AZX_DCAPS_PRESET_ATI_HDMI_NS \
+- (AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_SNOOP_OFF)
++ (AZX_DCAPS_PRESET_ATI_HDMI | AZX_DCAPS_AMD_ALLOC_FIX)
+
+ /* quirks for AMD SB */
+ #define AZX_DCAPS_PRESET_AMD_SB \
+@@ -1702,6 +1703,13 @@ static void azx_check_snoop_available(struct azx *chip)
+ if (chip->driver_caps & AZX_DCAPS_SNOOP_OFF)
+ snoop = false;
+
++#ifdef CONFIG_X86
++ /* check the presence of DMA ops (i.e. IOMMU), disable snoop conditionally */
++ if ((chip->driver_caps & AZX_DCAPS_AMD_ALLOC_FIX) &&
++ !get_dma_ops(chip->card->dev))
++ snoop = false;
++#endif
++
+ chip->snoop = snoop;
+ if (!snoop) {
+ dev_info(chip->card->dev, "Force to non-snoop mode\n");
+diff --git a/sound/pci/hda/patch_conexant.c b/sound/pci/hda/patch_conexant.c
+index 17389a3801bd1..4472923ba694b 100644
+--- a/sound/pci/hda/patch_conexant.c
++++ b/sound/pci/hda/patch_conexant.c
+@@ -21,12 +21,6 @@
+ #include "hda_jack.h"
+ #include "hda_generic.h"
+
+-enum {
+- CX_HEADSET_NOPRESENT = 0,
+- CX_HEADSET_PARTPRESENT,
+- CX_HEADSET_ALLPRESENT,
+-};
+-
+ struct conexant_spec {
+ struct hda_gen_spec gen;
+
+@@ -48,7 +42,6 @@ struct conexant_spec {
+ unsigned int gpio_led;
+ unsigned int gpio_mute_led_mask;
+ unsigned int gpio_mic_led_mask;
+- unsigned int headset_present_flag;
+ bool is_cx8070_sn6140;
+ };
+
+@@ -250,48 +243,19 @@ static void cx_process_headset_plugin(struct hda_codec *codec)
+ }
+ }
+
+-static void cx_update_headset_mic_vref(struct hda_codec *codec, unsigned int res)
++static void cx_update_headset_mic_vref(struct hda_codec *codec, struct hda_jack_callback *event)
+ {
+- unsigned int phone_present, mic_persent, phone_tag, mic_tag;
+- struct conexant_spec *spec = codec->spec;
++ unsigned int mic_present;
+
+ /* In cx8070 and sn6140, the node 16 can only be config to headphone or disabled,
+ * the node 19 can only be config to microphone or disabled.
+ * Check hp&mic tag to process headset pulgin&plugout.
+ */
+- phone_tag = snd_hda_codec_read(codec, 0x16, 0, AC_VERB_GET_UNSOLICITED_RESPONSE, 0x0);
+- mic_tag = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_UNSOLICITED_RESPONSE, 0x0);
+- if ((phone_tag & (res >> AC_UNSOL_RES_TAG_SHIFT)) ||
+- (mic_tag & (res >> AC_UNSOL_RES_TAG_SHIFT))) {
+- phone_present = snd_hda_codec_read(codec, 0x16, 0, AC_VERB_GET_PIN_SENSE, 0x0);
+- if (!(phone_present & AC_PINSENSE_PRESENCE)) {/* headphone plugout */
+- spec->headset_present_flag = CX_HEADSET_NOPRESENT;
+- snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x20);
+- return;
+- }
+- if (spec->headset_present_flag == CX_HEADSET_NOPRESENT) {
+- spec->headset_present_flag = CX_HEADSET_PARTPRESENT;
+- } else if (spec->headset_present_flag == CX_HEADSET_PARTPRESENT) {
+- mic_persent = snd_hda_codec_read(codec, 0x19, 0,
+- AC_VERB_GET_PIN_SENSE, 0x0);
+- /* headset is present */
+- if ((phone_present & AC_PINSENSE_PRESENCE) &&
+- (mic_persent & AC_PINSENSE_PRESENCE)) {
+- cx_process_headset_plugin(codec);
+- spec->headset_present_flag = CX_HEADSET_ALLPRESENT;
+- }
+- }
+- }
+-}
+-
+-static void cx_jack_unsol_event(struct hda_codec *codec, unsigned int res)
+-{
+- struct conexant_spec *spec = codec->spec;
+-
+- if (spec->is_cx8070_sn6140)
+- cx_update_headset_mic_vref(codec, res);
+-
+- snd_hda_jack_unsol_event(codec, res);
++ mic_present = snd_hda_codec_read(codec, 0x19, 0, AC_VERB_GET_PIN_SENSE, 0x0);
++ if (!(mic_present & AC_PINSENSE_PRESENCE)) /* mic plugout */
++ snd_hda_codec_write(codec, 0x19, 0, AC_VERB_SET_PIN_WIDGET_CONTROL, 0x20);
++ else
++ cx_process_headset_plugin(codec);
+ }
+
+ static int cx_auto_suspend(struct hda_codec *codec)
+@@ -305,7 +269,7 @@ static const struct hda_codec_ops cx_auto_patch_ops = {
+ .build_pcms = snd_hda_gen_build_pcms,
+ .init = cx_auto_init,
+ .free = cx_auto_free,
+- .unsol_event = cx_jack_unsol_event,
++ .unsol_event = snd_hda_jack_unsol_event,
+ .suspend = cx_auto_suspend,
+ .check_power_status = snd_hda_gen_check_power_status,
+ };
+@@ -1163,7 +1127,7 @@ static int patch_conexant_auto(struct hda_codec *codec)
+ case 0x14f11f86:
+ case 0x14f11f87:
+ spec->is_cx8070_sn6140 = true;
+- spec->headset_present_flag = CX_HEADSET_NOPRESENT;
++ snd_hda_jack_detect_enable_callback(codec, 0x19, cx_update_headset_mic_vref);
+ break;
+ }
+
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index d749769438ea5..a6c1e2199e703 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -9866,6 +9866,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1025, 0x079b, "Acer Aspire V5-573G", ALC282_FIXUP_ASPIRE_V5_PINS),
+ SND_PCI_QUIRK(0x1025, 0x080d, "Acer Aspire V5-122P", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
+ SND_PCI_QUIRK(0x1025, 0x0840, "Acer Aspire E1", ALC269VB_FIXUP_ASPIRE_E1_COEF),
++ SND_PCI_QUIRK(0x1025, 0x100c, "Acer Aspire E5-574G", ALC255_FIXUP_ACER_LIMIT_INT_MIC_BOOST),
+ SND_PCI_QUIRK(0x1025, 0x101c, "Acer Veriton N2510G", ALC269_FIXUP_LIFEBOOK),
+ SND_PCI_QUIRK(0x1025, 0x102b, "Acer Aspire C24-860", ALC286_FIXUP_ACER_AIO_MIC_NO_PRESENCE),
+ SND_PCI_QUIRK(0x1025, 0x1065, "Acer Aspire C20-820", ALC269VC_FIXUP_ACER_HEADSET_MIC),
+diff --git a/sound/usb/stream.c b/sound/usb/stream.c
+index d5409f3879455..e14c725acebf2 100644
+--- a/sound/usb/stream.c
++++ b/sound/usb/stream.c
+@@ -244,8 +244,8 @@ static struct snd_pcm_chmap_elem *convert_chmap(int channels, unsigned int bits,
+ SNDRV_CHMAP_FR, /* right front */
+ SNDRV_CHMAP_FC, /* center front */
+ SNDRV_CHMAP_LFE, /* LFE */
+- SNDRV_CHMAP_SL, /* left surround */
+- SNDRV_CHMAP_SR, /* right surround */
++ SNDRV_CHMAP_RL, /* left surround */
++ SNDRV_CHMAP_RR, /* right surround */
+ SNDRV_CHMAP_FLC, /* left of center */
+ SNDRV_CHMAP_FRC, /* right of center */
+ SNDRV_CHMAP_RC, /* surround */
+diff --git a/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json b/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json
+index 9b4a032186a7b..7149caec4f80e 100644
+--- a/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json
++++ b/tools/perf/pmu-events/arch/riscv/andes/ax45/firmware.json
+@@ -36,7 +36,7 @@
+ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+ },
+ {
+- "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
++ "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT"
+ },
+ {
+ "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+diff --git a/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json b/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json
+index a9939823b14b5..0c9b9a2d2958a 100644
+--- a/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json
++++ b/tools/perf/pmu-events/arch/riscv/riscv-sbi-firmware.json
+@@ -74,7 +74,7 @@
+ {
+ "PublicDescription": "Sent SFENCE.VMA with ASID request to other HART event",
+ "ConfigCode": "0x800000000000000c",
+- "EventName": "FW_SFENCE_VMA_RECEIVED",
++ "EventName": "FW_SFENCE_VMA_ASID_SENT",
+ "BriefDescription": "Sent SFENCE.VMA with ASID request to other HART event"
+ },
+ {
+diff --git a/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json b/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json
+index 9b4a032186a7b..7149caec4f80e 100644
+--- a/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json
++++ b/tools/perf/pmu-events/arch/riscv/sifive/u74/firmware.json
+@@ -36,7 +36,7 @@
+ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+ },
+ {
+- "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
++ "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT"
+ },
+ {
+ "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+diff --git a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json
+index 9b4a032186a7b..7149caec4f80e 100644
+--- a/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json
++++ b/tools/perf/pmu-events/arch/riscv/starfive/dubhe-80/firmware.json
+@@ -36,7 +36,7 @@
+ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+ },
+ {
+- "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
++ "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT"
+ },
+ {
+ "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+diff --git a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
+index 9b4a032186a7b..7149caec4f80e 100644
+--- a/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
++++ b/tools/perf/pmu-events/arch/riscv/thead/c900-legacy/firmware.json
+@@ -36,7 +36,7 @@
+ "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
+ },
+ {
+- "ArchStdEvent": "FW_SFENCE_VMA_RECEIVED"
++ "ArchStdEvent": "FW_SFENCE_VMA_ASID_SENT"
+ },
+ {
+ "ArchStdEvent": "FW_SFENCE_VMA_ASID_RECEIVED"
+diff --git a/tools/perf/util/callchain.c b/tools/perf/util/callchain.c
+index 1730b852a9474..6d075648d2ccf 100644
+--- a/tools/perf/util/callchain.c
++++ b/tools/perf/util/callchain.c
+@@ -1141,7 +1141,7 @@ int hist_entry__append_callchain(struct hist_entry *he, struct perf_sample *samp
+ int fill_callchain_info(struct addr_location *al, struct callchain_cursor_node *node,
+ bool hide_unresolved)
+ {
+- struct machine *machine = maps__machine(node->ms.maps);
++ struct machine *machine = node->ms.maps ? maps__machine(node->ms.maps) : NULL;
+
+ maps__put(al->maps);
+ al->maps = maps__get(node->ms.maps);
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_connect.c b/tools/testing/selftests/net/mptcp/mptcp_connect.c
+index d2043ec3bf6d6..4209b95690394 100644
+--- a/tools/testing/selftests/net/mptcp/mptcp_connect.c
++++ b/tools/testing/selftests/net/mptcp/mptcp_connect.c
+@@ -1115,11 +1115,11 @@ int main_loop_s(int listensock)
+ return 1;
+ }
+
+- if (--cfg_repeat > 0) {
+- if (cfg_input)
+- close(fd);
++ if (cfg_input)
++ close(fd);
++
++ if (--cfg_repeat > 0)
+ goto again;
+- }
+
+ return 0;
+ }
+diff --git a/tools/testing/selftests/net/mptcp/mptcp_join.sh b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+index 108aeeb84ef10..7043984b7e74a 100755
+--- a/tools/testing/selftests/net/mptcp/mptcp_join.sh
++++ b/tools/testing/selftests/net/mptcp/mptcp_join.sh
+@@ -661,7 +661,7 @@ pm_nl_check_endpoint()
+ done
+
+ if [ -z "${id}" ]; then
+- test_fail "bad test - missing endpoint id"
++ fail_test "bad test - missing endpoint id"
+ return
+ fi
+
+@@ -1634,6 +1634,8 @@ chk_prio_nr()
+ {
+ local mp_prio_nr_tx=$1
+ local mp_prio_nr_rx=$2
++ local mpj_syn=$3
++ local mpj_syn_ack=$4
+ local count
+
+ print_check "ptx"
+@@ -1655,6 +1657,26 @@ chk_prio_nr()
+ else
+ print_ok
+ fi
++
++ print_check "syn backup"
++ count=$(mptcp_lib_get_counter ${ns1} "MPTcpExtMPJoinSynBackupRx")
++ if [ -z "$count" ]; then
++ print_skip
++ elif [ "$count" != "$mpj_syn" ]; then
++ fail_test "got $count JOIN[s] syn with Backup expected $mpj_syn"
++ else
++ print_ok
++ fi
++
++ print_check "synack backup"
++ count=$(mptcp_lib_get_counter ${ns2} "MPTcpExtMPJoinSynAckBackupRx")
++ if [ -z "$count" ]; then
++ print_skip
++ elif [ "$count" != "$mpj_syn_ack" ]; then
++ fail_test "got $count JOIN[s] synack with Backup expected $mpj_syn_ack"
++ else
++ print_ok
++ fi
+ }
+
+ chk_subflow_nr()
+@@ -2612,11 +2634,24 @@ backup_tests()
+ sflags=nobackup speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 1
+- chk_prio_nr 0 1
++ chk_prio_nr 0 1 1 0
+ fi
+
+ # single address, backup
+ if reset "single address, backup" &&
++ continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
++ pm_nl_set_limits $ns1 0 1
++ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup
++ pm_nl_set_limits $ns2 1 1
++ sflags=nobackup speed=slow \
++ run_tests $ns1 $ns2 10.0.1.1
++ chk_join_nr 1 1 1
++ chk_add_nr 1 1
++ chk_prio_nr 1 0 0 1
++ fi
++
++ # single address, switch to backup
++ if reset "single address, switch to backup" &&
+ continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+ pm_nl_set_limits $ns1 0 1
+ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
+@@ -2625,20 +2660,20 @@ backup_tests()
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 1
+ chk_add_nr 1 1
+- chk_prio_nr 1 1
++ chk_prio_nr 1 1 0 0
+ fi
+
+ # single address with port, backup
+ if reset "single address with port, backup" &&
+ continue_if mptcp_lib_kallsyms_has "subflow_rebuild_header$"; then
+ pm_nl_set_limits $ns1 0 1
+- pm_nl_add_endpoint $ns1 10.0.2.1 flags signal port 10100
++ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal,backup port 10100
+ pm_nl_set_limits $ns2 1 1
+- sflags=backup speed=slow \
++ sflags=nobackup speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 1
+ chk_add_nr 1 1
+- chk_prio_nr 1 1
++ chk_prio_nr 1 0 0 1
+ fi
+
+ if reset "mpc backup" &&
+@@ -2647,17 +2682,26 @@ backup_tests()
+ speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 0 0 0
+- chk_prio_nr 0 1
++ chk_prio_nr 0 1 0 0
+ fi
+
+ if reset "mpc backup both sides" &&
+ continue_if mptcp_lib_kallsyms_doesnt_have "T mptcp_subflow_send_ack$"; then
+- pm_nl_add_endpoint $ns1 10.0.1.1 flags subflow,backup
++ pm_nl_set_limits $ns1 0 2
++ pm_nl_set_limits $ns2 1 2
++ pm_nl_add_endpoint $ns1 10.0.1.1 flags signal,backup
+ pm_nl_add_endpoint $ns2 10.0.1.2 flags subflow,backup
++
++ # 10.0.2.2 (non-backup) -> 10.0.1.1 (backup)
++ pm_nl_add_endpoint $ns2 10.0.2.2 flags subflow
++ # 10.0.1.2 (backup) -> 10.0.2.1 (non-backup)
++ pm_nl_add_endpoint $ns1 10.0.2.1 flags signal
++ ip -net "$ns2" route add 10.0.2.1 via 10.0.1.1 dev ns2eth1 # force this path
++
+ speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+- chk_join_nr 0 0 0
+- chk_prio_nr 1 1
++ chk_join_nr 2 2 2
++ chk_prio_nr 1 1 1 1
+ fi
+
+ if reset "mpc switch to backup" &&
+@@ -2666,7 +2710,7 @@ backup_tests()
+ sflags=backup speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 0 0 0
+- chk_prio_nr 0 1
++ chk_prio_nr 0 1 0 0
+ fi
+
+ if reset "mpc switch to backup both sides" &&
+@@ -2676,7 +2720,7 @@ backup_tests()
+ sflags=backup speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 0 0 0
+- chk_prio_nr 1 1
++ chk_prio_nr 1 1 0 0
+ fi
+ }
+
+@@ -3053,7 +3097,7 @@ fullmesh_tests()
+ addr_nr_ns2=1 sflags=backup,fullmesh speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 2 2 2
+- chk_prio_nr 0 1
++ chk_prio_nr 0 1 1 0
+ chk_rm_nr 0 1
+ fi
+
+@@ -3066,7 +3110,7 @@ fullmesh_tests()
+ sflags=nobackup,nofullmesh speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 2 2 2
+- chk_prio_nr 0 1
++ chk_prio_nr 0 1 1 0
+ chk_rm_nr 0 1
+ fi
+ }
+@@ -3318,7 +3362,7 @@ userspace_tests()
+ sflags=backup speed=slow \
+ run_tests $ns1 $ns2 10.0.1.1
+ chk_join_nr 1 1 0
+- chk_prio_nr 0 0
++ chk_prio_nr 0 0 0 0
+ fi
+
+ # userspace pm type prevents rm_addr
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-09 18:13 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-09 18:13 UTC (permalink / raw
To: gentoo-commits
commit: b5d74b80983311dd62baedc8e4e94656ed58b8eb
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Fri Aug 9 18:13:16 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Fri Aug 9 18:13:16 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=b5d74b80
libbpf: workaround -Wmaybe-uninitialized false positive
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 ++
...workaround-Wmaybe-uninitialized-false-pos.patch | 67 ++++++++++++++++++++++
2 files changed, 71 insertions(+)
diff --git a/0000_README b/0000_README
index 6ab23d2a..180f4b70 100644
--- a/0000_README
+++ b/0000_README
@@ -87,6 +87,10 @@ Patch: 2950_jump-label-fix.patch
From: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/
Desc: jump_label: Fix a regression
+Patch: 2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch
+From: https://lore.kernel.org/bpf/3ebbe7a4e93a5ddc3a26e2e11d329801d7c8de6b.1723217044.git.sam@gentoo.org/
+Desc: libbpf: workaround -Wmaybe-uninitialized false positive
+
Patch: 3000_Support-printing-firmware-info.patch
From: https://bugs.gentoo.org/732852
Desc: Print firmware info (Reqs CONFIG_GENTOO_PRINT_FIRMWARE_INFO). Thanks to Georgy Yakovlev
diff --git a/2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch b/2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch
new file mode 100644
index 00000000..86de18d7
--- /dev/null
+++ b/2990_libbpf-workaround-Wmaybe-uninitialized-false-pos.patch
@@ -0,0 +1,67 @@
+From git@z Thu Jan 1 00:00:00 1970
+Subject: [PATCH] libbpf: workaround -Wmaybe-uninitialized false positive
+From: Sam James <sam@gentoo.org>
+Date: Fri, 09 Aug 2024 16:24:04 +0100
+Message-Id: <3ebbe7a4e93a5ddc3a26e2e11d329801d7c8de6b.1723217044.git.sam@gentoo.org>
+MIME-Version: 1.0
+Content-Type: text/plain; charset="utf-8"
+Content-Transfer-Encoding: 8bit
+
+In `elf_close`, we get this with GCC 15 -O3 (at least):
+```
+In function ‘elf_close’,
+ inlined from ‘elf_close’ at elf.c:53:6,
+ inlined from ‘elf_find_func_offset_from_file’ at elf.c:384:2:
+elf.c:57:9: warning: ‘elf_fd.elf’ may be used uninitialized [-Wmaybe-uninitialized]
+ 57 | elf_end(elf_fd->elf);
+ | ^~~~~~~~~~~~~~~~~~~~
+elf.c: In function ‘elf_find_func_offset_from_file’:
+elf.c:377:23: note: ‘elf_fd.elf’ was declared here
+ 377 | struct elf_fd elf_fd;
+ | ^~~~~~
+In function ‘elf_close’,
+ inlined from ‘elf_close’ at elf.c:53:6,
+ inlined from ‘elf_find_func_offset_from_file’ at elf.c:384:2:
+elf.c:58:9: warning: ‘elf_fd.fd’ may be used uninitialized [-Wmaybe-uninitialized]
+ 58 | close(elf_fd->fd);
+ | ^~~~~~~~~~~~~~~~~
+elf.c: In function ‘elf_find_func_offset_from_file’:
+elf.c:377:23: note: ‘elf_fd.fd’ was declared here
+ 377 | struct elf_fd elf_fd;
+ | ^~~~~~
+```
+
+In reality, our use is fine, it's just that GCC doesn't model errno
+here (see linked GCC bug). Suppress -Wmaybe-uninitialized accordingly.
+
+Link: https://gcc.gnu.org/PR114952
+Signed-off-by: Sam James <sam@gentoo.org>
+---
+ tools/lib/bpf/elf.c | 4 ++++
+ 1 file changed, 4 insertions(+)
+
+diff --git a/tools/lib/bpf/elf.c b/tools/lib/bpf/elf.c
+index c92e02394159e..ee226bb8e1af0 100644
+--- a/tools/lib/bpf/elf.c
++++ b/tools/lib/bpf/elf.c
+@@ -369,6 +369,9 @@ long elf_find_func_offset(Elf *elf, const char *binary_path, const char *name)
+ return ret;
+ }
+
++#pragma GCC diagnostic push
++/* https://gcc.gnu.org/PR114952 */
++#pragma GCC diagnostic ignored "-Wmaybe-uninitialized"
+ /* Find offset of function name in ELF object specified by path. "name" matches
+ * symbol name or name@@LIB for library functions.
+ */
+@@ -384,6 +387,7 @@ long elf_find_func_offset_from_file(const char *binary_path, const char *name)
+ elf_close(&elf_fd);
+ return ret;
+ }
++#pragma GCC diagnostic pop
+
+ struct symbol {
+ const char *name;
+--
+2.45.2
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-03 15:55 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-03 15:55 UTC (permalink / raw
To: gentoo-commits
commit: e4136859a1f44f287a38a3244451ce8de37e2cb2
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Aug 3 15:55:24 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Aug 3 15:55:24 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=e4136859
Temporarily remove BMQ due to imcompatibility
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 8 -
5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch | 11474 -------------------------
5021_BMQ-and-PDS-gentoo-defaults.patch | 12 -
3 files changed, 11494 deletions(-)
diff --git a/0000_README b/0000_README
index 3c01ecbe..6ab23d2a 100644
--- a/0000_README
+++ b/0000_README
@@ -98,11 +98,3 @@ Desc: Add Gentoo Linux support config settings and defaults.
Patch: 5010_enable-cpu-optimizations-universal.patch
From: https://github.com/graysky2/kernel_compiler_patch
Desc: Kernel >= 5.15 patch enables gcc = v11.1+ optimizations for additional CPUs.
-
-Patch: 5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch
-From: https://github.com/Frogging-Family/linux-tkg
-Desc: BMQ(BitMap Queue) Scheduler. A new CPU scheduler developed from PDS(incld). Inspired by the scheduler in zircon.
-
-Patch: 5021_BMQ-and-PDS-gentoo-defaults.patch
-From: https://gitweb.gentoo.org/proj/linux-patches.git/
-Desc: Set defaults for BMQ. default to n
diff --git a/5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch b/5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch
deleted file mode 100644
index 5f577d24..00000000
--- a/5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch
+++ /dev/null
@@ -1,11474 +0,0 @@
-diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
---- a/Documentation/admin-guide/sysctl/kernel.rst 2024-07-15 00:43:32.000000000 +0200
-+++ b/Documentation/admin-guide/sysctl/kernel.rst 2024-07-16 11:57:40.064869171 +0200
-@@ -1673,3 +1673,12 @@ is 10 seconds.
-
- The softlockup threshold is (``2 * watchdog_thresh``). Setting this
- tunable to zero will disable lockup detection altogether.
-+
-+yield_type:
-+===========
-+
-+BMQ/PDS CPU scheduler only. This determines what type of yield calls
-+to sched_yield() will be performed.
-+
-+ 0 - No yield.
-+ 1 - Requeue task. (default)
-diff --git a/Documentation/scheduler/sched-BMQ.txt b/Documentation/scheduler/sched-BMQ.txt
---- a/Documentation/scheduler/sched-BMQ.txt 1970-01-01 01:00:00.000000000 +0100
-+++ b/Documentation/scheduler/sched-BMQ.txt 2024-07-16 11:57:40.268882498 +0200
-@@ -0,0 +1,110 @@
-+ BitMap queue CPU Scheduler
-+ --------------------------
-+
-+CONTENT
-+========
-+
-+ Background
-+ Design
-+ Overview
-+ Task policy
-+ Priority management
-+ BitMap Queue
-+ CPU Assignment and Migration
-+
-+
-+Background
-+==========
-+
-+BitMap Queue CPU scheduler, referred to as BMQ from here on, is an evolution
-+of previous Priority and Deadline based Skiplist multiple queue scheduler(PDS),
-+and inspired by Zircon scheduler. The goal of it is to keep the scheduler code
-+simple, while efficiency and scalable for interactive tasks, such as desktop,
-+movie playback and gaming etc.
-+
-+Design
-+======
-+
-+Overview
-+--------
-+
-+BMQ use per CPU run queue design, each CPU(logical) has it's own run queue,
-+each CPU is responsible for scheduling the tasks that are putting into it's
-+run queue.
-+
-+The run queue is a set of priority queues. Note that these queues are fifo
-+queue for non-rt tasks or priority queue for rt tasks in data structure. See
-+BitMap Queue below for details. BMQ is optimized for non-rt tasks in the fact
-+that most applications are non-rt tasks. No matter the queue is fifo or
-+priority, In each queue is an ordered list of runnable tasks awaiting execution
-+and the data structures are the same. When it is time for a new task to run,
-+the scheduler simply looks the lowest numbered queueue that contains a task,
-+and runs the first task from the head of that queue. And per CPU idle task is
-+also in the run queue, so the scheduler can always find a task to run on from
-+its run queue.
-+
-+Each task will assigned the same timeslice(default 4ms) when it is picked to
-+start running. Task will be reinserted at the end of the appropriate priority
-+queue when it uses its whole timeslice. When the scheduler selects a new task
-+from the priority queue it sets the CPU's preemption timer for the remainder of
-+the previous timeslice. When that timer fires the scheduler will stop execution
-+on that task, select another task and start over again.
-+
-+If a task blocks waiting for a shared resource then it's taken out of its
-+priority queue and is placed in a wait queue for the shared resource. When it
-+is unblocked it will be reinserted in the appropriate priority queue of an
-+eligible CPU.
-+
-+Task policy
-+-----------
-+
-+BMQ supports DEADLINE, FIFO, RR, NORMAL, BATCH and IDLE task policy like the
-+mainline CFS scheduler. But BMQ is heavy optimized for non-rt task, that's
-+NORMAL/BATCH/IDLE policy tasks. Below is the implementation detail of each
-+policy.
-+
-+DEADLINE
-+ It is squashed as priority 0 FIFO task.
-+
-+FIFO/RR
-+ All RT tasks share one single priority queue in BMQ run queue designed. The
-+complexity of insert operation is O(n). BMQ is not designed for system runs
-+with major rt policy tasks.
-+
-+NORMAL/BATCH/IDLE
-+ BATCH and IDLE tasks are treated as the same policy. They compete CPU with
-+NORMAL policy tasks, but they just don't boost. To control the priority of
-+NORMAL/BATCH/IDLE tasks, simply use nice level.
-+
-+ISO
-+ ISO policy is not supported in BMQ. Please use nice level -20 NORMAL policy
-+task instead.
-+
-+Priority management
-+-------------------
-+
-+RT tasks have priority from 0-99. For non-rt tasks, there are three different
-+factors used to determine the effective priority of a task. The effective
-+priority being what is used to determine which queue it will be in.
-+
-+The first factor is simply the task’s static priority. Which is assigned from
-+task's nice level, within [-20, 19] in userland's point of view and [0, 39]
-+internally.
-+
-+The second factor is the priority boost. This is a value bounded between
-+[-MAX_PRIORITY_ADJ, MAX_PRIORITY_ADJ] used to offset the base priority, it is
-+modified by the following cases:
-+
-+*When a thread has used up its entire timeslice, always deboost its boost by
-+increasing by one.
-+*When a thread gives up cpu control(voluntary or non-voluntary) to reschedule,
-+and its switch-in time(time after last switch and run) below the thredhold
-+based on its priority boost, will boost its boost by decreasing by one buti is
-+capped at 0 (won’t go negative).
-+
-+The intent in this system is to ensure that interactive threads are serviced
-+quickly. These are usually the threads that interact directly with the user
-+and cause user-perceivable latency. These threads usually do little work and
-+spend most of their time blocked awaiting another user event. So they get the
-+priority boost from unblocking while background threads that do most of the
-+processing receive the priority penalty for using their entire timeslice.
-diff --git a/fs/proc/base.c b/fs/proc/base.c
---- a/fs/proc/base.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/fs/proc/base.c 2024-07-16 11:57:44.113126230 +0200
-@@ -481,7 +481,7 @@ static int proc_pid_schedstat(struct seq
- seq_puts(m, "0 0 0\n");
- else
- seq_printf(m, "%llu %llu %lu\n",
-- (unsigned long long)task->se.sum_exec_runtime,
-+ (unsigned long long)tsk_seruntime(task),
- (unsigned long long)task->sched_info.run_delay,
- task->sched_info.pcount);
-
-diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h
---- a/include/asm-generic/resource.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/include/asm-generic/resource.h 2024-07-16 11:57:44.173129878 +0200
-@@ -23,7 +23,7 @@
- [RLIMIT_LOCKS] = { RLIM_INFINITY, RLIM_INFINITY }, \
- [RLIMIT_SIGPENDING] = { 0, 0 }, \
- [RLIMIT_MSGQUEUE] = { MQ_BYTES_MAX, MQ_BYTES_MAX }, \
-- [RLIMIT_NICE] = { 0, 0 }, \
-+ [RLIMIT_NICE] = { 30, 30 }, \
- [RLIMIT_RTPRIO] = { 0, 0 }, \
- [RLIMIT_RTTIME] = { RLIM_INFINITY, RLIM_INFINITY }, \
- }
-diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
---- a/include/linux/sched/deadline.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/include/linux/sched/deadline.h 2024-07-16 11:57:44.289136930 +0200
-@@ -2,6 +2,25 @@
- #ifndef _LINUX_SCHED_DEADLINE_H
- #define _LINUX_SCHED_DEADLINE_H
-
-+#ifdef CONFIG_SCHED_ALT
-+
-+static inline int dl_task(struct task_struct *p)
-+{
-+ return 0;
-+}
-+
-+#ifdef CONFIG_SCHED_BMQ
-+#define __tsk_deadline(p) (0UL)
-+#endif
-+
-+#ifdef CONFIG_SCHED_PDS
-+#define __tsk_deadline(p) ((((u64) ((p)->prio))<<56) | (p)->deadline)
-+#endif
-+
-+#else
-+
-+#define __tsk_deadline(p) ((p)->dl.deadline)
-+
- /*
- * SCHED_DEADLINE tasks has negative priorities, reflecting
- * the fact that any of them has higher prio than RT and
-@@ -23,6 +42,7 @@ static inline int dl_task(struct task_st
- {
- return dl_prio(p->prio);
- }
-+#endif /* CONFIG_SCHED_ALT */
-
- static inline bool dl_time_before(u64 a, u64 b)
- {
-diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
---- a/include/linux/sched/prio.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/include/linux/sched/prio.h 2024-07-16 11:57:44.289136930 +0200
-@@ -18,6 +18,28 @@
- #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH)
- #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2)
-
-+#ifdef CONFIG_SCHED_ALT
-+
-+/* Undefine MAX_PRIO and DEFAULT_PRIO */
-+#undef MAX_PRIO
-+#undef DEFAULT_PRIO
-+
-+/* +/- priority levels from the base priority */
-+#ifdef CONFIG_SCHED_BMQ
-+#define MAX_PRIORITY_ADJ (12)
-+#endif
-+
-+#ifdef CONFIG_SCHED_PDS
-+#define MAX_PRIORITY_ADJ (0)
-+#endif
-+
-+#define MIN_NORMAL_PRIO (128)
-+#define NORMAL_PRIO_NUM (64)
-+#define MAX_PRIO (MIN_NORMAL_PRIO + NORMAL_PRIO_NUM)
-+#define DEFAULT_PRIO (MAX_PRIO - MAX_PRIORITY_ADJ - NICE_WIDTH / 2)
-+
-+#endif /* CONFIG_SCHED_ALT */
-+
- /*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
-diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
---- a/include/linux/sched/rt.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/include/linux/sched/rt.h 2024-07-16 11:57:44.289136930 +0200
-@@ -24,8 +24,10 @@ static inline bool task_is_realtime(stru
-
- if (policy == SCHED_FIFO || policy == SCHED_RR)
- return true;
-+#ifndef CONFIG_SCHED_ALT
- if (policy == SCHED_DEADLINE)
- return true;
-+#endif
- return false;
- }
-
-diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
---- a/include/linux/sched/topology.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/include/linux/sched/topology.h 2024-07-16 11:57:44.289136930 +0200
-@@ -244,7 +244,8 @@ static inline bool cpus_share_resources(
-
- #endif /* !CONFIG_SMP */
-
--#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) && \
-+ !defined(CONFIG_SCHED_ALT)
- extern void rebuild_sched_domains_energy(void);
- #else
- static inline void rebuild_sched_domains_energy(void)
-diff --git a/include/linux/sched.h b/include/linux/sched.h
---- a/include/linux/sched.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/include/linux/sched.h 2024-07-16 11:57:44.285136688 +0200
-@@ -774,9 +774,16 @@ struct task_struct {
- struct alloc_tag *alloc_tag;
- #endif
-
--#ifdef CONFIG_SMP
-+#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_ALT)
- int on_cpu;
-+#endif
-+
-+#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_ALT)
- struct __call_single_node wake_entry;
-+#endif
-+
-+#ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- unsigned int wakee_flips;
- unsigned long wakee_flip_decay_ts;
- struct task_struct *last_wakee;
-@@ -790,6 +797,7 @@ struct task_struct {
- */
- int recent_used_cpu;
- int wake_cpu;
-+#endif /* !CONFIG_SCHED_ALT */
- #endif
- int on_rq;
-
-@@ -798,6 +806,19 @@ struct task_struct {
- int normal_prio;
- unsigned int rt_priority;
-
-+#ifdef CONFIG_SCHED_ALT
-+ u64 last_ran;
-+ s64 time_slice;
-+ struct list_head sq_node;
-+#ifdef CONFIG_SCHED_BMQ
-+ int boost_prio;
-+#endif /* CONFIG_SCHED_BMQ */
-+#ifdef CONFIG_SCHED_PDS
-+ u64 deadline;
-+#endif /* CONFIG_SCHED_PDS */
-+ /* sched_clock time spent running */
-+ u64 sched_time;
-+#else /* !CONFIG_SCHED_ALT */
- struct sched_entity se;
- struct sched_rt_entity rt;
- struct sched_dl_entity dl;
-@@ -809,6 +830,7 @@ struct task_struct {
- unsigned long core_cookie;
- unsigned int core_occupation;
- #endif
-+#endif /* !CONFIG_SCHED_ALT */
-
- #ifdef CONFIG_CGROUP_SCHED
- struct task_group *sched_task_group;
-@@ -1571,6 +1593,15 @@ struct task_struct {
- */
- };
-
-+#ifdef CONFIG_SCHED_ALT
-+#define tsk_seruntime(t) ((t)->sched_time)
-+/* replace the uncertian rt_timeout with 0UL */
-+#define tsk_rttimeout(t) (0UL)
-+#else /* CFS */
-+#define tsk_seruntime(t) ((t)->se.sum_exec_runtime)
-+#define tsk_rttimeout(t) ((t)->rt.timeout)
-+#endif /* !CONFIG_SCHED_ALT */
-+
- #define TASK_REPORT_IDLE (TASK_REPORT + 1)
- #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
-
-diff --git a/init/init_task.c b/init/init_task.c
---- a/init/init_task.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/init/init_task.c 2024-07-16 11:57:44.401143740 +0200
-@@ -70,9 +70,15 @@ struct task_struct init_task __aligned(L
- .stack = init_stack,
- .usage = REFCOUNT_INIT(2),
- .flags = PF_KTHREAD,
-+#ifdef CONFIG_SCHED_ALT
-+ .prio = DEFAULT_PRIO,
-+ .static_prio = DEFAULT_PRIO,
-+ .normal_prio = DEFAULT_PRIO,
-+#else
- .prio = MAX_PRIO - 20,
- .static_prio = MAX_PRIO - 20,
- .normal_prio = MAX_PRIO - 20,
-+#endif
- .policy = SCHED_NORMAL,
- .cpus_ptr = &init_task.cpus_mask,
- .user_cpus_ptr = NULL,
-@@ -85,6 +91,16 @@ struct task_struct init_task __aligned(L
- .restart_block = {
- .fn = do_no_restart_syscall,
- },
-+#ifdef CONFIG_SCHED_ALT
-+ .sq_node = LIST_HEAD_INIT(init_task.sq_node),
-+#ifdef CONFIG_SCHED_BMQ
-+ .boost_prio = 0,
-+#endif
-+#ifdef CONFIG_SCHED_PDS
-+ .deadline = 0,
-+#endif
-+ .time_slice = HZ,
-+#else
- .se = {
- .group_node = LIST_HEAD_INIT(init_task.se.group_node),
- },
-@@ -92,6 +108,7 @@ struct task_struct init_task __aligned(L
- .run_list = LIST_HEAD_INIT(init_task.rt.run_list),
- .time_slice = RR_TIMESLICE,
- },
-+#endif
- .tasks = LIST_HEAD_INIT(init_task.tasks),
- #ifdef CONFIG_SMP
- .pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
-diff --git a/init/Kconfig b/init/Kconfig
---- a/init/Kconfig 2024-07-15 00:43:32.000000000 +0200
-+++ b/init/Kconfig 2024-07-16 11:57:44.401143740 +0200
-@@ -638,6 +638,7 @@ config TASK_IO_ACCOUNTING
-
- config PSI
- bool "Pressure stall information tracking"
-+ depends on !SCHED_ALT
- select KERNFS
- help
- Collect metrics that indicate how overcommitted the CPU, memory,
-@@ -803,6 +804,7 @@ menu "Scheduler features"
- config UCLAMP_TASK
- bool "Enable utilization clamping for RT/FAIR tasks"
- depends on CPU_FREQ_GOV_SCHEDUTIL
-+ depends on !SCHED_ALT
- help
- This feature enables the scheduler to track the clamped utilization
- of each CPU based on RUNNABLE tasks scheduled on that CPU.
-@@ -849,6 +851,35 @@ config UCLAMP_BUCKETS_COUNT
-
- If in doubt, use the default value.
-
-+menuconfig SCHED_ALT
-+ bool "Alternative CPU Schedulers"
-+ default y
-+ help
-+ This feature enable alternative CPU scheduler"
-+
-+if SCHED_ALT
-+
-+choice
-+ prompt "Alternative CPU Scheduler"
-+ default SCHED_BMQ
-+
-+config SCHED_BMQ
-+ bool "BMQ CPU scheduler"
-+ help
-+ The BitMap Queue CPU scheduler for excellent interactivity and
-+ responsiveness on the desktop and solid scalability on normal
-+ hardware and commodity servers.
-+
-+config SCHED_PDS
-+ bool "PDS CPU scheduler"
-+ help
-+ The Priority and Deadline based Skip list multiple queue CPU
-+ Scheduler.
-+
-+endchoice
-+
-+endif
-+
- endmenu
-
- #
-@@ -914,6 +945,7 @@ config NUMA_BALANCING
- depends on ARCH_SUPPORTS_NUMA_BALANCING
- depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
- depends on SMP && NUMA && MIGRATION && !PREEMPT_RT
-+ depends on !SCHED_ALT
- help
- This option adds support for automatic NUMA aware memory/task placement.
- The mechanism is quite primitive and is based on migrating memory when
-@@ -1015,6 +1047,7 @@ config FAIR_GROUP_SCHED
- depends on CGROUP_SCHED
- default CGROUP_SCHED
-
-+if !SCHED_ALT
- config CFS_BANDWIDTH
- bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
- depends on FAIR_GROUP_SCHED
-@@ -1037,6 +1070,7 @@ config RT_GROUP_SCHED
- realtime bandwidth for them.
- See Documentation/scheduler/sched-rt-group.rst for more information.
-
-+endif #!SCHED_ALT
- endif #CGROUP_SCHED
-
- config SCHED_MM_CID
-@@ -1285,6 +1319,7 @@ config CHECKPOINT_RESTORE
-
- config SCHED_AUTOGROUP
- bool "Automatic process group scheduling"
-+ depends on !SCHED_ALT
- select CGROUPS
- select CGROUP_SCHED
- select FAIR_GROUP_SCHED
-diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
---- a/kernel/cgroup/cpuset.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/cgroup/cpuset.c 2024-07-16 11:57:44.421144957 +0200
-@@ -846,7 +846,7 @@ out:
- return ret;
- }
-
--#ifdef CONFIG_SMP
-+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_ALT)
- /*
- * Helper routine for generate_sched_domains().
- * Do cpusets a, b have overlapping effective cpus_allowed masks?
-@@ -1245,7 +1245,7 @@ static void rebuild_sched_domains_locked
- /* Have scheduler rebuild the domains */
- partition_and_rebuild_sched_domains(ndoms, doms, attr);
- }
--#else /* !CONFIG_SMP */
-+#else /* !CONFIG_SMP || CONFIG_SCHED_ALT */
- static void rebuild_sched_domains_locked(void)
- {
- }
-@@ -3301,12 +3301,15 @@ static int cpuset_can_attach(struct cgro
- goto out_unlock;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- if (dl_task(task)) {
- cs->nr_migrate_dl_tasks++;
- cs->sum_migrate_dl_bw += task->dl.dl_bw;
- }
-+#endif
- }
-
-+#ifndef CONFIG_SCHED_ALT
- if (!cs->nr_migrate_dl_tasks)
- goto out_success;
-
-@@ -3327,6 +3330,7 @@ static int cpuset_can_attach(struct cgro
- }
-
- out_success:
-+#endif
- /*
- * Mark attach is in progress. This makes validate_change() fail
- * changes which zero cpus/mems_allowed.
-@@ -3350,12 +3354,14 @@ static void cpuset_cancel_attach(struct
- if (!cs->attach_in_progress)
- wake_up(&cpuset_attach_wq);
-
-+#ifndef CONFIG_SCHED_ALT
- if (cs->nr_migrate_dl_tasks) {
- int cpu = cpumask_any(cs->effective_cpus);
-
- dl_bw_free(cpu, cs->sum_migrate_dl_bw);
- reset_migrate_dl_data(cs);
- }
-+#endif
-
- mutex_unlock(&cpuset_mutex);
- }
-diff --git a/kernel/delayacct.c b/kernel/delayacct.c
---- a/kernel/delayacct.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/delayacct.c 2024-07-16 11:57:44.421144957 +0200
-@@ -149,7 +149,7 @@ int delayacct_add_tsk(struct taskstats *
- */
- t1 = tsk->sched_info.pcount;
- t2 = tsk->sched_info.run_delay;
-- t3 = tsk->se.sum_exec_runtime;
-+ t3 = tsk_seruntime(tsk);
-
- d->cpu_count += t1;
-
-diff --git a/kernel/exit.c b/kernel/exit.c
---- a/kernel/exit.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/exit.c 2024-07-16 11:57:44.425145200 +0200
-@@ -175,7 +175,7 @@ static void __exit_signal(struct task_st
- sig->curr_target = next_thread(tsk);
- }
-
-- add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
-+ add_device_randomness((const void*) &tsk_seruntime(tsk),
- sizeof(unsigned long long));
-
- /*
-@@ -196,7 +196,7 @@ static void __exit_signal(struct task_st
- sig->inblock += task_io_get_inblock(tsk);
- sig->oublock += task_io_get_oublock(tsk);
- task_io_accounting_add(&sig->ioac, &tsk->ioac);
-- sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
-+ sig->sum_sched_runtime += tsk_seruntime(tsk);
- sig->nr_threads--;
- __unhash_process(tsk, group_dead);
- write_sequnlock(&sig->stats_lock);
-diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
---- a/kernel/Kconfig.preempt 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/Kconfig.preempt 2024-07-16 11:57:44.409144227 +0200
-@@ -117,7 +117,7 @@ config PREEMPT_DYNAMIC
-
- config SCHED_CORE
- bool "Core Scheduling for SMT"
-- depends on SCHED_SMT
-+ depends on SCHED_SMT && !SCHED_ALT
- help
- This option permits Core Scheduling, a means of coordinated task
- selection across SMT siblings. When enabled -- see
-diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
---- a/kernel/locking/rtmutex.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/locking/rtmutex.c 2024-07-16 11:57:44.433145686 +0200
-@@ -363,7 +363,7 @@ waiter_update_prio(struct rt_mutex_waite
- lockdep_assert(RB_EMPTY_NODE(&waiter->tree.entry));
-
- waiter->tree.prio = __waiter_prio(task);
-- waiter->tree.deadline = task->dl.deadline;
-+ waiter->tree.deadline = __tsk_deadline(task);
- }
-
- /*
-@@ -384,16 +384,20 @@ waiter_clone_prio(struct rt_mutex_waiter
- * Only use with rt_waiter_node_{less,equal}()
- */
- #define task_to_waiter_node(p) \
-- &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
-+ &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = __tsk_deadline(p) }
- #define task_to_waiter(p) \
- &(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
-
- static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
- struct rt_waiter_node *right)
- {
-+#ifdef CONFIG_SCHED_PDS
-+ return (left->deadline < right->deadline);
-+#else
- if (left->prio < right->prio)
- return 1;
-
-+#ifndef CONFIG_SCHED_BMQ
- /*
- * If both waiters have dl_prio(), we check the deadlines of the
- * associated tasks.
-@@ -402,16 +406,22 @@ static __always_inline int rt_waiter_nod
- */
- if (dl_prio(left->prio))
- return dl_time_before(left->deadline, right->deadline);
-+#endif
-
- return 0;
-+#endif
- }
-
- static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
- struct rt_waiter_node *right)
- {
-+#ifdef CONFIG_SCHED_PDS
-+ return (left->deadline == right->deadline);
-+#else
- if (left->prio != right->prio)
- return 0;
-
-+#ifndef CONFIG_SCHED_BMQ
- /*
- * If both waiters have dl_prio(), we check the deadlines of the
- * associated tasks.
-@@ -420,8 +430,10 @@ static __always_inline int rt_waiter_nod
- */
- if (dl_prio(left->prio))
- return left->deadline == right->deadline;
-+#endif
-
- return 1;
-+#endif
- }
-
- static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
-diff --git a/kernel/sched/alt_core.c b/kernel/sched/alt_core.c
---- a/kernel/sched/alt_core.c 1970-01-01 01:00:00.000000000 +0100
-+++ b/kernel/sched/alt_core.c 2024-07-16 11:57:44.445146416 +0200
-@@ -0,0 +1,8963 @@
-+/*
-+ * kernel/sched/alt_core.c
-+ *
-+ * Core alternative kernel scheduler code and related syscalls
-+ *
-+ * Copyright (C) 1991-2002 Linus Torvalds
-+ *
-+ * 2009-08-13 Brainfuck deadline scheduling policy by Con Kolivas deletes
-+ * a whole lot of those previous things.
-+ * 2017-09-06 Priority and Deadline based Skip list multiple queue kernel
-+ * scheduler by Alfred Chen.
-+ * 2019-02-20 BMQ(BitMap Queue) kernel scheduler by Alfred Chen.
-+ */
-+#include <linux/sched/clock.h>
-+#include <linux/sched/cputime.h>
-+#include <linux/sched/debug.h>
-+#include <linux/sched/hotplug.h>
-+#include <linux/sched/init.h>
-+#include <linux/sched/isolation.h>
-+#include <linux/sched/loadavg.h>
-+#include <linux/sched/mm.h>
-+#include <linux/sched/nohz.h>
-+#include <linux/sched/stat.h>
-+#include <linux/sched/wake_q.h>
-+
-+#include <linux/blkdev.h>
-+#include <linux/context_tracking.h>
-+#include <linux/cpuset.h>
-+#include <linux/delayacct.h>
-+#include <linux/init_task.h>
-+#include <linux/kcov.h>
-+#include <linux/kprobes.h>
-+#include <linux/nmi.h>
-+#include <linux/rseq.h>
-+#include <linux/scs.h>
-+
-+#include <uapi/linux/sched/types.h>
-+
-+#include <asm/irq_regs.h>
-+#include <asm/switch_to.h>
-+
-+#define CREATE_TRACE_POINTS
-+#include <trace/events/sched.h>
-+#include <trace/events/ipi.h>
-+#undef CREATE_TRACE_POINTS
-+
-+#include "sched.h"
-+#include "smp.h"
-+
-+#include "pelt.h"
-+
-+#include "../../io_uring/io-wq.h"
-+#include "../smpboot.h"
-+
-+EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu);
-+EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask);
-+
-+/*
-+ * Export tracepoints that act as a bare tracehook (ie: have no trace event
-+ * associated with them) to allow external modules to probe them.
-+ */
-+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+#define sched_feat(x) (1)
-+/*
-+ * Print a warning if need_resched is set for the given duration (if
-+ * LATENCY_WARN is enabled).
-+ *
-+ * If sysctl_resched_latency_warn_once is set, only one warning will be shown
-+ * per boot.
-+ */
-+__read_mostly int sysctl_resched_latency_warn_ms = 100;
-+__read_mostly int sysctl_resched_latency_warn_once = 1;
-+#else
-+#define sched_feat(x) (0)
-+#endif /* CONFIG_SCHED_DEBUG */
-+
-+#define ALT_SCHED_VERSION "v6.10-r0"
-+
-+/*
-+ * Compile time debug macro
-+ * #define ALT_SCHED_DEBUG
-+ */
-+
-+/* rt_prio(prio) defined in include/linux/sched/rt.h */
-+#define rt_task(p) rt_prio((p)->prio)
-+#define rt_policy(policy) ((policy) == SCHED_FIFO || (policy) == SCHED_RR)
-+#define task_has_rt_policy(p) (rt_policy((p)->policy))
-+
-+#define STOP_PRIO (MAX_RT_PRIO - 1)
-+
-+/*
-+ * Time slice
-+ * (default: 4 msec, units: nanoseconds)
-+ */
-+unsigned int sysctl_sched_base_slice __read_mostly = (4 << 20);
-+
-+#ifdef CONFIG_SCHED_BMQ
-+#include "bmq.h"
-+#endif
-+#ifdef CONFIG_SCHED_PDS
-+#include "pds.h"
-+#endif
-+
-+struct affinity_context {
-+ const struct cpumask *new_mask;
-+ struct cpumask *user_mask;
-+ unsigned int flags;
-+};
-+
-+/* Reschedule if less than this many μs left */
-+#define RESCHED_NS (100 << 10)
-+
-+/**
-+ * sched_yield_type - Type of sched_yield() will be performed.
-+ * 0: No yield.
-+ * 1: Requeue task. (default)
-+ */
-+int sched_yield_type __read_mostly = 1;
-+
-+#ifdef CONFIG_SMP
-+static cpumask_t sched_rq_pending_mask ____cacheline_aligned_in_smp;
-+
-+DEFINE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
-+DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_llc_mask);
-+DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_topo_end_mask);
-+
-+#ifdef CONFIG_SCHED_SMT
-+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-+EXPORT_SYMBOL_GPL(sched_smt_present);
-+#endif
-+
-+/*
-+ * Keep a unique ID per domain (we use the first CPUs number in the cpumask of
-+ * the domain), this allows us to quickly tell if two cpus are in the same cache
-+ * domain, see cpus_share_cache().
-+ */
-+DEFINE_PER_CPU(int, sd_llc_id);
-+#endif /* CONFIG_SMP */
-+
-+static DEFINE_MUTEX(sched_hotcpu_mutex);
-+
-+DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-+
-+#ifndef prepare_arch_switch
-+# define prepare_arch_switch(next) do { } while (0)
-+#endif
-+#ifndef finish_arch_post_lock_switch
-+# define finish_arch_post_lock_switch() do { } while (0)
-+#endif
-+
-+static cpumask_t sched_preempt_mask[SCHED_QUEUE_BITS + 1] ____cacheline_aligned_in_smp;
-+
-+static cpumask_t *const sched_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS - 1];
-+#ifdef CONFIG_SCHED_SMT
-+static cpumask_t *const sched_sg_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS];
-+#endif
-+
-+/* task function */
-+static inline const struct cpumask *task_user_cpus(struct task_struct *p)
-+{
-+ if (!p->user_cpus_ptr)
-+ return cpu_possible_mask; /* &init_task.cpus_mask */
-+ return p->user_cpus_ptr;
-+}
-+
-+/* sched_queue related functions */
-+static inline void sched_queue_init(struct sched_queue *q)
-+{
-+ int i;
-+
-+ bitmap_zero(q->bitmap, SCHED_QUEUE_BITS);
-+ for(i = 0; i < SCHED_LEVELS; i++)
-+ INIT_LIST_HEAD(&q->heads[i]);
-+}
-+
-+/*
-+ * Init idle task and put into queue structure of rq
-+ * IMPORTANT: may be called multiple times for a single cpu
-+ */
-+static inline void sched_queue_init_idle(struct sched_queue *q,
-+ struct task_struct *idle)
-+{
-+ INIT_LIST_HEAD(&q->heads[IDLE_TASK_SCHED_PRIO]);
-+ list_add_tail(&idle->sq_node, &q->heads[IDLE_TASK_SCHED_PRIO]);
-+ idle->on_rq = TASK_ON_RQ_QUEUED;
-+}
-+
-+#define CLEAR_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
-+ if (low < pr && pr <= high) \
-+ cpumask_clear_cpu(cpu, sched_preempt_mask + pr);
-+
-+#define SET_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
-+ if (low < pr && pr <= high) \
-+ cpumask_set_cpu(cpu, sched_preempt_mask + pr);
-+
-+static atomic_t sched_prio_record = ATOMIC_INIT(0);
-+
-+/* water mark related functions */
-+static inline void update_sched_preempt_mask(struct rq *rq)
-+{
-+ int prio = find_first_bit(rq->queue.bitmap, SCHED_QUEUE_BITS);
-+ int last_prio = rq->prio;
-+ int cpu, pr;
-+
-+ if (prio == last_prio)
-+ return;
-+
-+ rq->prio = prio;
-+#ifdef CONFIG_SCHED_PDS
-+ rq->prio_idx = sched_prio2idx(rq->prio, rq);
-+#endif
-+ cpu = cpu_of(rq);
-+ pr = atomic_read(&sched_prio_record);
-+
-+ if (prio < last_prio) {
-+ if (IDLE_TASK_SCHED_PRIO == last_prio) {
-+#ifdef CONFIG_SCHED_SMT
-+ if (static_branch_likely(&sched_smt_present))
-+ cpumask_andnot(sched_sg_idle_mask,
-+ sched_sg_idle_mask, cpu_smt_mask(cpu));
-+#endif
-+ cpumask_clear_cpu(cpu, sched_idle_mask);
-+ last_prio -= 2;
-+ }
-+ CLEAR_CACHED_PREEMPT_MASK(pr, prio, last_prio, cpu);
-+
-+ return;
-+ }
-+ /* last_prio < prio */
-+ if (IDLE_TASK_SCHED_PRIO == prio) {
-+#ifdef CONFIG_SCHED_SMT
-+ if (static_branch_likely(&sched_smt_present) &&
-+ cpumask_intersects(cpu_smt_mask(cpu), sched_idle_mask))
-+ cpumask_or(sched_sg_idle_mask, sched_sg_idle_mask, cpu_smt_mask(cpu));
-+#endif
-+ cpumask_set_cpu(cpu, sched_idle_mask);
-+ prio -= 2;
-+ }
-+ SET_CACHED_PREEMPT_MASK(pr, last_prio, prio, cpu);
-+}
-+
-+/*
-+ * This routine assume that the idle task always in queue
-+ */
-+static inline struct task_struct *sched_rq_first_task(struct rq *rq)
-+{
-+ const struct list_head *head = &rq->queue.heads[sched_rq_prio_idx(rq)];
-+
-+ return list_first_entry(head, struct task_struct, sq_node);
-+}
-+
-+static inline struct task_struct * sched_rq_next_task(struct task_struct *p, struct rq *rq)
-+{
-+ struct list_head *next = p->sq_node.next;
-+
-+ if (&rq->queue.heads[0] <= next && next < &rq->queue.heads[SCHED_LEVELS]) {
-+ struct list_head *head;
-+ unsigned long idx = next - &rq->queue.heads[0];
-+
-+ idx = find_next_bit(rq->queue.bitmap, SCHED_QUEUE_BITS,
-+ sched_idx2prio(idx, rq) + 1);
-+ head = &rq->queue.heads[sched_prio2idx(idx, rq)];
-+
-+ return list_first_entry(head, struct task_struct, sq_node);
-+ }
-+
-+ return list_next_entry(p, sq_node);
-+}
-+
-+/*
-+ * Serialization rules:
-+ *
-+ * Lock order:
-+ *
-+ * p->pi_lock
-+ * rq->lock
-+ * hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
-+ *
-+ * rq1->lock
-+ * rq2->lock where: rq1 < rq2
-+ *
-+ * Regular state:
-+ *
-+ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
-+ * local CPU's rq->lock, it optionally removes the task from the runqueue and
-+ * always looks at the local rq data structures to find the most eligible task
-+ * to run next.
-+ *
-+ * Task enqueue is also under rq->lock, possibly taken from another CPU.
-+ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
-+ * the local CPU to avoid bouncing the runqueue state around [ see
-+ * ttwu_queue_wakelist() ]
-+ *
-+ * Task wakeup, specifically wakeups that involve migration, are horribly
-+ * complicated to avoid having to take two rq->locks.
-+ *
-+ * Special state:
-+ *
-+ * System-calls and anything external will use task_rq_lock() which acquires
-+ * both p->pi_lock and rq->lock. As a consequence the state they change is
-+ * stable while holding either lock:
-+ *
-+ * - sched_setaffinity()/
-+ * set_cpus_allowed_ptr(): p->cpus_ptr, p->nr_cpus_allowed
-+ * - set_user_nice(): p->se.load, p->*prio
-+ * - __sched_setscheduler(): p->sched_class, p->policy, p->*prio,
-+ * p->se.load, p->rt_priority,
-+ * p->dl.dl_{runtime, deadline, period, flags, bw, density}
-+ * - sched_setnuma(): p->numa_preferred_nid
-+ * - sched_move_task(): p->sched_task_group
-+ * - uclamp_update_active() p->uclamp*
-+ *
-+ * p->state <- TASK_*:
-+ *
-+ * is changed locklessly using set_current_state(), __set_current_state() or
-+ * set_special_state(), see their respective comments, or by
-+ * try_to_wake_up(). This latter uses p->pi_lock to serialize against
-+ * concurrent self.
-+ *
-+ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
-+ *
-+ * is set by activate_task() and cleared by deactivate_task(), under
-+ * rq->lock. Non-zero indicates the task is runnable, the special
-+ * ON_RQ_MIGRATING state is used for migration without holding both
-+ * rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
-+ *
-+ * p->on_cpu <- { 0, 1 }:
-+ *
-+ * is set by prepare_task() and cleared by finish_task() such that it will be
-+ * set before p is scheduled-in and cleared after p is scheduled-out, both
-+ * under rq->lock. Non-zero indicates the task is running on its CPU.
-+ *
-+ * [ The astute reader will observe that it is possible for two tasks on one
-+ * CPU to have ->on_cpu = 1 at the same time. ]
-+ *
-+ * task_cpu(p): is changed by set_task_cpu(), the rules are:
-+ *
-+ * - Don't call set_task_cpu() on a blocked task:
-+ *
-+ * We don't care what CPU we're not running on, this simplifies hotplug,
-+ * the CPU assignment of blocked tasks isn't required to be valid.
-+ *
-+ * - for try_to_wake_up(), called under p->pi_lock:
-+ *
-+ * This allows try_to_wake_up() to only take one rq->lock, see its comment.
-+ *
-+ * - for migration called under rq->lock:
-+ * [ see task_on_rq_migrating() in task_rq_lock() ]
-+ *
-+ * o move_queued_task()
-+ * o detach_task()
-+ *
-+ * - for migration called under double_rq_lock():
-+ *
-+ * o __migrate_swap_task()
-+ * o push_rt_task() / pull_rt_task()
-+ * o push_dl_task() / pull_dl_task()
-+ * o dl_task_offline_migration()
-+ *
-+ */
-+
-+/*
-+ * Context: p->pi_lock
-+ */
-+static inline struct rq *__task_access_lock(struct task_struct *p, raw_spinlock_t **plock)
-+{
-+ struct rq *rq;
-+ for (;;) {
-+ rq = task_rq(p);
-+ if (p->on_cpu || task_on_rq_queued(p)) {
-+ raw_spin_lock(&rq->lock);
-+ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
-+ *plock = &rq->lock;
-+ return rq;
-+ }
-+ raw_spin_unlock(&rq->lock);
-+ } else if (task_on_rq_migrating(p)) {
-+ do {
-+ cpu_relax();
-+ } while (unlikely(task_on_rq_migrating(p)));
-+ } else {
-+ *plock = NULL;
-+ return rq;
-+ }
-+ }
-+}
-+
-+static inline void __task_access_unlock(struct task_struct *p, raw_spinlock_t *lock)
-+{
-+ if (NULL != lock)
-+ raw_spin_unlock(lock);
-+}
-+
-+static inline struct rq *
-+task_access_lock_irqsave(struct task_struct *p, raw_spinlock_t **plock, unsigned long *flags)
-+{
-+ struct rq *rq;
-+ for (;;) {
-+ rq = task_rq(p);
-+ if (p->on_cpu || task_on_rq_queued(p)) {
-+ raw_spin_lock_irqsave(&rq->lock, *flags);
-+ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
-+ *plock = &rq->lock;
-+ return rq;
-+ }
-+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
-+ } else if (task_on_rq_migrating(p)) {
-+ do {
-+ cpu_relax();
-+ } while (unlikely(task_on_rq_migrating(p)));
-+ } else {
-+ raw_spin_lock_irqsave(&p->pi_lock, *flags);
-+ if (likely(!p->on_cpu && !p->on_rq && rq == task_rq(p))) {
-+ *plock = &p->pi_lock;
-+ return rq;
-+ }
-+ raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-+ }
-+ }
-+}
-+
-+static inline void
-+task_access_unlock_irqrestore(struct task_struct *p, raw_spinlock_t *lock, unsigned long *flags)
-+{
-+ raw_spin_unlock_irqrestore(lock, *flags);
-+}
-+
-+/*
-+ * __task_rq_lock - lock the rq @p resides on.
-+ */
-+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ struct rq *rq;
-+
-+ lockdep_assert_held(&p->pi_lock);
-+
-+ for (;;) {
-+ rq = task_rq(p);
-+ raw_spin_lock(&rq->lock);
-+ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-+ return rq;
-+ raw_spin_unlock(&rq->lock);
-+
-+ while (unlikely(task_on_rq_migrating(p)))
-+ cpu_relax();
-+ }
-+}
-+
-+/*
-+ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
-+ */
-+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(p->pi_lock)
-+ __acquires(rq->lock)
-+{
-+ struct rq *rq;
-+
-+ for (;;) {
-+ raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
-+ rq = task_rq(p);
-+ raw_spin_lock(&rq->lock);
-+ /*
-+ * move_queued_task() task_rq_lock()
-+ *
-+ * ACQUIRE (rq->lock)
-+ * [S] ->on_rq = MIGRATING [L] rq = task_rq()
-+ * WMB (__set_task_cpu()) ACQUIRE (rq->lock);
-+ * [S] ->cpu = new_cpu [L] task_rq()
-+ * [L] ->on_rq
-+ * RELEASE (rq->lock)
-+ *
-+ * If we observe the old CPU in task_rq_lock(), the acquire of
-+ * the old rq->lock will fully serialize against the stores.
-+ *
-+ * If we observe the new CPU in task_rq_lock(), the address
-+ * dependency headed by '[L] rq = task_rq()' and the acquire
-+ * will pair with the WMB to ensure we then also see migrating.
-+ */
-+ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-+ return rq;
-+ }
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
-+
-+ while (unlikely(task_on_rq_migrating(p)))
-+ cpu_relax();
-+ }
-+}
-+
-+static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ raw_spin_lock_irqsave(&rq->lock, rf->flags);
-+}
-+
-+static inline void rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
-+}
-+
-+DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
-+ rq_lock_irqsave(_T->lock, &_T->rf),
-+ rq_unlock_irqrestore(_T->lock, &_T->rf),
-+ struct rq_flags rf)
-+
-+void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
-+{
-+ raw_spinlock_t *lock;
-+
-+ /* Matches synchronize_rcu() in __sched_core_enable() */
-+ preempt_disable();
-+
-+ for (;;) {
-+ lock = __rq_lockp(rq);
-+ raw_spin_lock_nested(lock, subclass);
-+ if (likely(lock == __rq_lockp(rq))) {
-+ /* preempt_count *MUST* be > 1 */
-+ preempt_enable_no_resched();
-+ return;
-+ }
-+ raw_spin_unlock(lock);
-+ }
-+}
-+
-+void raw_spin_rq_unlock(struct rq *rq)
-+{
-+ raw_spin_unlock(rq_lockp(rq));
-+}
-+
-+/*
-+ * RQ-clock updating methods:
-+ */
-+
-+static void update_rq_clock_task(struct rq *rq, s64 delta)
-+{
-+/*
-+ * In theory, the compile should just see 0 here, and optimize out the call
-+ * to sched_rt_avg_update. But I don't trust it...
-+ */
-+ s64 __maybe_unused steal = 0, irq_delta = 0;
-+
-+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-+ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
-+
-+ /*
-+ * Since irq_time is only updated on {soft,}irq_exit, we might run into
-+ * this case when a previous update_rq_clock() happened inside a
-+ * {soft,}irq region.
-+ *
-+ * When this happens, we stop ->clock_task and only update the
-+ * prev_irq_time stamp to account for the part that fit, so that a next
-+ * update will consume the rest. This ensures ->clock_task is
-+ * monotonic.
-+ *
-+ * It does however cause some slight miss-attribution of {soft,}irq
-+ * time, a more accurate solution would be to update the irq_time using
-+ * the current rq->clock timestamp, except that would require using
-+ * atomic ops.
-+ */
-+ if (irq_delta > delta)
-+ irq_delta = delta;
-+
-+ rq->prev_irq_time += irq_delta;
-+ delta -= irq_delta;
-+ delayacct_irq(rq->curr, irq_delta);
-+#endif
-+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-+ if (static_key_false((¶virt_steal_rq_enabled))) {
-+ steal = paravirt_steal_clock(cpu_of(rq));
-+ steal -= rq->prev_steal_time_rq;
-+
-+ if (unlikely(steal > delta))
-+ steal = delta;
-+
-+ rq->prev_steal_time_rq += steal;
-+ delta -= steal;
-+ }
-+#endif
-+
-+ rq->clock_task += delta;
-+
-+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
-+ if ((irq_delta + steal))
-+ update_irq_load_avg(rq, irq_delta + steal);
-+#endif
-+}
-+
-+static inline void update_rq_clock(struct rq *rq)
-+{
-+ s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
-+
-+ if (unlikely(delta <= 0))
-+ return;
-+ rq->clock += delta;
-+ sched_update_rq_clock(rq);
-+ update_rq_clock_task(rq, delta);
-+}
-+
-+/*
-+ * RQ Load update routine
-+ */
-+#define RQ_LOAD_HISTORY_BITS (sizeof(s32) * 8ULL)
-+#define RQ_UTIL_SHIFT (8)
-+#define RQ_LOAD_HISTORY_TO_UTIL(l) (((l) >> (RQ_LOAD_HISTORY_BITS - 1 - RQ_UTIL_SHIFT)) & 0xff)
-+
-+#define LOAD_BLOCK(t) ((t) >> 17)
-+#define LOAD_HALF_BLOCK(t) ((t) >> 16)
-+#define BLOCK_MASK(t) ((t) & ((0x01 << 18) - 1))
-+#define LOAD_BLOCK_BIT(b) (1UL << (RQ_LOAD_HISTORY_BITS - 1 - (b)))
-+#define CURRENT_LOAD_BIT LOAD_BLOCK_BIT(0)
-+
-+static inline void rq_load_update(struct rq *rq)
-+{
-+ u64 time = rq->clock;
-+ u64 delta = min(LOAD_BLOCK(time) - LOAD_BLOCK(rq->load_stamp), RQ_LOAD_HISTORY_BITS - 1);
-+ u64 prev = !!(rq->load_history & CURRENT_LOAD_BIT);
-+ u64 curr = !!rq->nr_running;
-+
-+ if (delta) {
-+ rq->load_history = rq->load_history >> delta;
-+
-+ if (delta < RQ_UTIL_SHIFT) {
-+ rq->load_block += (~BLOCK_MASK(rq->load_stamp)) * prev;
-+ if (!!LOAD_HALF_BLOCK(rq->load_block) ^ curr)
-+ rq->load_history ^= LOAD_BLOCK_BIT(delta);
-+ }
-+
-+ rq->load_block = BLOCK_MASK(time) * prev;
-+ } else {
-+ rq->load_block += (time - rq->load_stamp) * prev;
-+ }
-+ if (prev ^ curr)
-+ rq->load_history ^= CURRENT_LOAD_BIT;
-+ rq->load_stamp = time;
-+}
-+
-+unsigned long rq_load_util(struct rq *rq, unsigned long max)
-+{
-+ return RQ_LOAD_HISTORY_TO_UTIL(rq->load_history) * (max >> RQ_UTIL_SHIFT);
-+}
-+
-+#ifdef CONFIG_SMP
-+unsigned long sched_cpu_util(int cpu)
-+{
-+ return rq_load_util(cpu_rq(cpu), arch_scale_cpu_capacity(cpu));
-+}
-+#endif /* CONFIG_SMP */
-+
-+#ifdef CONFIG_CPU_FREQ
-+/**
-+ * cpufreq_update_util - Take a note about CPU utilization changes.
-+ * @rq: Runqueue to carry out the update for.
-+ * @flags: Update reason flags.
-+ *
-+ * This function is called by the scheduler on the CPU whose utilization is
-+ * being updated.
-+ *
-+ * It can only be called from RCU-sched read-side critical sections.
-+ *
-+ * The way cpufreq is currently arranged requires it to evaluate the CPU
-+ * performance state (frequency/voltage) on a regular basis to prevent it from
-+ * being stuck in a completely inadequate performance level for too long.
-+ * That is not guaranteed to happen if the updates are only triggered from CFS
-+ * and DL, though, because they may not be coming in if only RT tasks are
-+ * active all the time (or there are RT tasks only).
-+ *
-+ * As a workaround for that issue, this function is called periodically by the
-+ * RT sched class to trigger extra cpufreq updates to prevent it from stalling,
-+ * but that really is a band-aid. Going forward it should be replaced with
-+ * solutions targeted more specifically at RT tasks.
-+ */
-+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
-+{
-+ struct update_util_data *data;
-+
-+#ifdef CONFIG_SMP
-+ rq_load_update(rq);
-+#endif
-+ data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, cpu_of(rq)));
-+ if (data)
-+ data->func(data, rq_clock(rq), flags);
-+}
-+#else
-+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
-+{
-+#ifdef CONFIG_SMP
-+ rq_load_update(rq);
-+#endif
-+}
-+#endif /* CONFIG_CPU_FREQ */
-+
-+#ifdef CONFIG_NO_HZ_FULL
-+/*
-+ * Tick may be needed by tasks in the runqueue depending on their policy and
-+ * requirements. If tick is needed, lets send the target an IPI to kick it out
-+ * of nohz mode if necessary.
-+ */
-+static inline void sched_update_tick_dependency(struct rq *rq)
-+{
-+ int cpu = cpu_of(rq);
-+
-+ if (!tick_nohz_full_cpu(cpu))
-+ return;
-+
-+ if (rq->nr_running < 2)
-+ tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
-+ else
-+ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
-+}
-+#else /* !CONFIG_NO_HZ_FULL */
-+static inline void sched_update_tick_dependency(struct rq *rq) { }
-+#endif
-+
-+bool sched_task_on_rq(struct task_struct *p)
-+{
-+ return task_on_rq_queued(p);
-+}
-+
-+unsigned long get_wchan(struct task_struct *p)
-+{
-+ unsigned long ip = 0;
-+ unsigned int state;
-+
-+ if (!p || p == current)
-+ return 0;
-+
-+ /* Only get wchan if task is blocked and we can keep it that way. */
-+ raw_spin_lock_irq(&p->pi_lock);
-+ state = READ_ONCE(p->__state);
-+ smp_rmb(); /* see try_to_wake_up() */
-+ if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq)
-+ ip = __get_wchan(p);
-+ raw_spin_unlock_irq(&p->pi_lock);
-+
-+ return ip;
-+}
-+
-+/*
-+ * Add/Remove/Requeue task to/from the runqueue routines
-+ * Context: rq->lock
-+ */
-+#define __SCHED_DEQUEUE_TASK(p, rq, flags, func) \
-+ sched_info_dequeue(rq, p); \
-+ \
-+ __list_del_entry(&p->sq_node); \
-+ if (p->sq_node.prev == p->sq_node.next) { \
-+ clear_bit(sched_idx2prio(p->sq_node.next - &rq->queue.heads[0], rq), \
-+ rq->queue.bitmap); \
-+ func; \
-+ }
-+
-+#define __SCHED_ENQUEUE_TASK(p, rq, flags, func) \
-+ sched_info_enqueue(rq, p); \
-+ { \
-+ int idx, prio; \
-+ TASK_SCHED_PRIO_IDX(p, rq, idx, prio); \
-+ list_add_tail(&p->sq_node, &rq->queue.heads[idx]); \
-+ if (list_is_first(&p->sq_node, &rq->queue.heads[idx])) { \
-+ set_bit(prio, rq->queue.bitmap); \
-+ func; \
-+ } \
-+ }
-+
-+static inline void dequeue_task(struct task_struct *p, struct rq *rq, int flags)
-+{
-+#ifdef ALT_SCHED_DEBUG
-+ lockdep_assert_held(&rq->lock);
-+
-+ /*printk(KERN_INFO "sched: dequeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
-+ WARN_ONCE(task_rq(p) != rq, "sched: dequeue task reside on cpu%d from cpu%d\n",
-+ task_cpu(p), cpu_of(rq));
-+#endif
-+
-+ __SCHED_DEQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
-+ --rq->nr_running;
-+#ifdef CONFIG_SMP
-+ if (1 == rq->nr_running)
-+ cpumask_clear_cpu(cpu_of(rq), &sched_rq_pending_mask);
-+#endif
-+
-+ sched_update_tick_dependency(rq);
-+}
-+
-+static inline void enqueue_task(struct task_struct *p, struct rq *rq, int flags)
-+{
-+#ifdef ALT_SCHED_DEBUG
-+ lockdep_assert_held(&rq->lock);
-+
-+ /*printk(KERN_INFO "sched: enqueue(%d) %px %d\n", cpu_of(rq), p, p->prio);*/
-+ WARN_ONCE(task_rq(p) != rq, "sched: enqueue task reside on cpu%d to cpu%d\n",
-+ task_cpu(p), cpu_of(rq));
-+#endif
-+
-+ __SCHED_ENQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
-+ ++rq->nr_running;
-+#ifdef CONFIG_SMP
-+ if (2 == rq->nr_running)
-+ cpumask_set_cpu(cpu_of(rq), &sched_rq_pending_mask);
-+#endif
-+
-+ sched_update_tick_dependency(rq);
-+}
-+
-+static inline void requeue_task(struct task_struct *p, struct rq *rq)
-+{
-+ struct list_head *node = &p->sq_node;
-+ int deq_idx, idx, prio;
-+
-+ TASK_SCHED_PRIO_IDX(p, rq, idx, prio);
-+#ifdef ALT_SCHED_DEBUG
-+ lockdep_assert_held(&rq->lock);
-+ /*printk(KERN_INFO "sched: requeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
-+ WARN_ONCE(task_rq(p) != rq, "sched: cpu[%d] requeue task reside on cpu%d\n",
-+ cpu_of(rq), task_cpu(p));
-+#endif
-+ if (list_is_last(node, &rq->queue.heads[idx]))
-+ return;
-+
-+ __list_del_entry(node);
-+ if (node->prev == node->next && (deq_idx = node->next - &rq->queue.heads[0]) != idx)
-+ clear_bit(sched_idx2prio(deq_idx, rq), rq->queue.bitmap);
-+
-+ list_add_tail(node, &rq->queue.heads[idx]);
-+ if (list_is_first(node, &rq->queue.heads[idx]))
-+ set_bit(prio, rq->queue.bitmap);
-+ update_sched_preempt_mask(rq);
-+}
-+
-+/*
-+ * cmpxchg based fetch_or, macro so it works for different integer types
-+ */
-+#define fetch_or(ptr, mask) \
-+ ({ \
-+ typeof(ptr) _ptr = (ptr); \
-+ typeof(mask) _mask = (mask); \
-+ typeof(*_ptr) _val = *_ptr; \
-+ \
-+ do { \
-+ } while (!try_cmpxchg(_ptr, &_val, _val | _mask)); \
-+ _val; \
-+})
-+
-+#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
-+/*
-+ * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
-+ * this avoids any races wrt polling state changes and thereby avoids
-+ * spurious IPIs.
-+ */
-+static inline bool set_nr_and_not_polling(struct task_struct *p)
-+{
-+ struct thread_info *ti = task_thread_info(p);
-+ return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
-+}
-+
-+/*
-+ * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
-+ *
-+ * If this returns true, then the idle task promises to call
-+ * sched_ttwu_pending() and reschedule soon.
-+ */
-+static bool set_nr_if_polling(struct task_struct *p)
-+{
-+ struct thread_info *ti = task_thread_info(p);
-+ typeof(ti->flags) val = READ_ONCE(ti->flags);
-+
-+ do {
-+ if (!(val & _TIF_POLLING_NRFLAG))
-+ return false;
-+ if (val & _TIF_NEED_RESCHED)
-+ return true;
-+ } while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
-+
-+ return true;
-+}
-+
-+#else
-+static inline bool set_nr_and_not_polling(struct task_struct *p)
-+{
-+ set_tsk_need_resched(p);
-+ return true;
-+}
-+
-+#ifdef CONFIG_SMP
-+static inline bool set_nr_if_polling(struct task_struct *p)
-+{
-+ return false;
-+}
-+#endif
-+#endif
-+
-+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
-+{
-+ struct wake_q_node *node = &task->wake_q;
-+
-+ /*
-+ * Atomically grab the task, if ->wake_q is !nil already it means
-+ * it's already queued (either by us or someone else) and will get the
-+ * wakeup due to that.
-+ *
-+ * In order to ensure that a pending wakeup will observe our pending
-+ * state, even in the failed case, an explicit smp_mb() must be used.
-+ */
-+ smp_mb__before_atomic();
-+ if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
-+ return false;
-+
-+ /*
-+ * The head is context local, there can be no concurrency.
-+ */
-+ *head->lastp = node;
-+ head->lastp = &node->next;
-+ return true;
-+}
-+
-+/**
-+ * wake_q_add() - queue a wakeup for 'later' waking.
-+ * @head: the wake_q_head to add @task to
-+ * @task: the task to queue for 'later' wakeup
-+ *
-+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
-+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
-+ * instantly.
-+ *
-+ * This function must be used as-if it were wake_up_process(); IOW the task
-+ * must be ready to be woken at this location.
-+ */
-+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
-+{
-+ if (__wake_q_add(head, task))
-+ get_task_struct(task);
-+}
-+
-+/**
-+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
-+ * @head: the wake_q_head to add @task to
-+ * @task: the task to queue for 'later' wakeup
-+ *
-+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
-+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
-+ * instantly.
-+ *
-+ * This function must be used as-if it were wake_up_process(); IOW the task
-+ * must be ready to be woken at this location.
-+ *
-+ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
-+ * that already hold reference to @task can call the 'safe' version and trust
-+ * wake_q to do the right thing depending whether or not the @task is already
-+ * queued for wakeup.
-+ */
-+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
-+{
-+ if (!__wake_q_add(head, task))
-+ put_task_struct(task);
-+}
-+
-+void wake_up_q(struct wake_q_head *head)
-+{
-+ struct wake_q_node *node = head->first;
-+
-+ while (node != WAKE_Q_TAIL) {
-+ struct task_struct *task;
-+
-+ task = container_of(node, struct task_struct, wake_q);
-+ /* task can safely be re-inserted now: */
-+ node = node->next;
-+ task->wake_q.next = NULL;
-+
-+ /*
-+ * wake_up_process() executes a full barrier, which pairs with
-+ * the queueing in wake_q_add() so as not to miss wakeups.
-+ */
-+ wake_up_process(task);
-+ put_task_struct(task);
-+ }
-+}
-+
-+/*
-+ * resched_curr - mark rq's current task 'to be rescheduled now'.
-+ *
-+ * On UP this means the setting of the need_resched flag, on SMP it
-+ * might also involve a cross-CPU call to trigger the scheduler on
-+ * the target CPU.
-+ */
-+static inline void resched_curr(struct rq *rq)
-+{
-+ struct task_struct *curr = rq->curr;
-+ int cpu;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ if (test_tsk_need_resched(curr))
-+ return;
-+
-+ cpu = cpu_of(rq);
-+ if (cpu == smp_processor_id()) {
-+ set_tsk_need_resched(curr);
-+ set_preempt_need_resched();
-+ return;
-+ }
-+
-+ if (set_nr_and_not_polling(curr))
-+ smp_send_reschedule(cpu);
-+ else
-+ trace_sched_wake_idle_without_ipi(cpu);
-+}
-+
-+void resched_cpu(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ if (cpu_online(cpu) || cpu == smp_processor_id())
-+ resched_curr(cpu_rq(cpu));
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+}
-+
-+#ifdef CONFIG_SMP
-+#ifdef CONFIG_NO_HZ_COMMON
-+/*
-+ * This routine will record that the CPU is going idle with tick stopped.
-+ * This info will be used in performing idle load balancing in the future.
-+ */
-+void nohz_balance_enter_idle(int cpu) {}
-+
-+/*
-+ * In the semi idle case, use the nearest busy CPU for migrating timers
-+ * from an idle CPU. This is good for power-savings.
-+ *
-+ * We don't do similar optimization for completely idle system, as
-+ * selecting an idle CPU will add more delays to the timers than intended
-+ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
-+ */
-+int get_nohz_timer_target(void)
-+{
-+ int i, cpu = smp_processor_id(), default_cpu = -1;
-+ struct cpumask *mask;
-+ const struct cpumask *hk_mask;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
-+ if (!idle_cpu(cpu))
-+ return cpu;
-+ default_cpu = cpu;
-+ }
-+
-+ hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
-+
-+ for (mask = per_cpu(sched_cpu_topo_masks, cpu);
-+ mask < per_cpu(sched_cpu_topo_end_mask, cpu); mask++)
-+ for_each_cpu_and(i, mask, hk_mask)
-+ if (!idle_cpu(i))
-+ return i;
-+
-+ if (default_cpu == -1)
-+ default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
-+ cpu = default_cpu;
-+
-+ return cpu;
-+}
-+
-+/*
-+ * When add_timer_on() enqueues a timer into the timer wheel of an
-+ * idle CPU then this timer might expire before the next timer event
-+ * which is scheduled to wake up that CPU. In case of a completely
-+ * idle system the next event might even be infinite time into the
-+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
-+ * leaves the inner idle loop so the newly added timer is taken into
-+ * account when the CPU goes back to idle and evaluates the timer
-+ * wheel for the next timer event.
-+ */
-+static inline void wake_up_idle_cpu(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ if (cpu == smp_processor_id())
-+ return;
-+
-+ /*
-+ * Set TIF_NEED_RESCHED and send an IPI if in the non-polling
-+ * part of the idle loop. This forces an exit from the idle loop
-+ * and a round trip to schedule(). Now this could be optimized
-+ * because a simple new idle loop iteration is enough to
-+ * re-evaluate the next tick. Provided some re-ordering of tick
-+ * nohz functions that would need to follow TIF_NR_POLLING
-+ * clearing:
-+ *
-+ * - On most archs, a simple fetch_or on ti::flags with a
-+ * "0" value would be enough to know if an IPI needs to be sent.
-+ *
-+ * - x86 needs to perform a last need_resched() check between
-+ * monitor and mwait which doesn't take timers into account.
-+ * There a dedicated TIF_TIMER flag would be required to
-+ * fetch_or here and be checked along with TIF_NEED_RESCHED
-+ * before mwait().
-+ *
-+ * However, remote timer enqueue is not such a frequent event
-+ * and testing of the above solutions didn't appear to report
-+ * much benefits.
-+ */
-+ if (set_nr_and_not_polling(rq->idle))
-+ smp_send_reschedule(cpu);
-+ else
-+ trace_sched_wake_idle_without_ipi(cpu);
-+}
-+
-+static inline bool wake_up_full_nohz_cpu(int cpu)
-+{
-+ /*
-+ * We just need the target to call irq_exit() and re-evaluate
-+ * the next tick. The nohz full kick at least implies that.
-+ * If needed we can still optimize that later with an
-+ * empty IRQ.
-+ */
-+ if (cpu_is_offline(cpu))
-+ return true; /* Don't try to wake offline CPUs. */
-+ if (tick_nohz_full_cpu(cpu)) {
-+ if (cpu != smp_processor_id() ||
-+ tick_nohz_tick_stopped())
-+ tick_nohz_full_kick_cpu(cpu);
-+ return true;
-+ }
-+
-+ return false;
-+}
-+
-+void wake_up_nohz_cpu(int cpu)
-+{
-+ if (!wake_up_full_nohz_cpu(cpu))
-+ wake_up_idle_cpu(cpu);
-+}
-+
-+static void nohz_csd_func(void *info)
-+{
-+ struct rq *rq = info;
-+ int cpu = cpu_of(rq);
-+ unsigned int flags;
-+
-+ /*
-+ * Release the rq::nohz_csd.
-+ */
-+ flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
-+ WARN_ON(!(flags & NOHZ_KICK_MASK));
-+
-+ rq->idle_balance = idle_cpu(cpu);
-+ if (rq->idle_balance && !need_resched()) {
-+ rq->nohz_idle_balance = flags;
-+ raise_softirq_irqoff(SCHED_SOFTIRQ);
-+ }
-+}
-+
-+#endif /* CONFIG_NO_HZ_COMMON */
-+#endif /* CONFIG_SMP */
-+
-+static inline void wakeup_preempt(struct rq *rq)
-+{
-+ if (sched_rq_first_task(rq) != rq->curr)
-+ resched_curr(rq);
-+}
-+
-+static __always_inline
-+int __task_state_match(struct task_struct *p, unsigned int state)
-+{
-+ if (READ_ONCE(p->__state) & state)
-+ return 1;
-+
-+ if (READ_ONCE(p->saved_state) & state)
-+ return -1;
-+
-+ return 0;
-+}
-+
-+static __always_inline
-+int task_state_match(struct task_struct *p, unsigned int state)
-+{
-+ /*
-+ * Serialize against current_save_and_set_rtlock_wait_state(),
-+ * current_restore_rtlock_saved_state(), and __refrigerator().
-+ */
-+ guard(raw_spinlock_irq)(&p->pi_lock);
-+
-+ return __task_state_match(p, state);
-+}
-+
-+/*
-+ * wait_task_inactive - wait for a thread to unschedule.
-+ *
-+ * Wait for the thread to block in any of the states set in @match_state.
-+ * If it changes, i.e. @p might have woken up, then return zero. When we
-+ * succeed in waiting for @p to be off its CPU, we return a positive number
-+ * (its total switch count). If a second call a short while later returns the
-+ * same number, the caller can be sure that @p has remained unscheduled the
-+ * whole time.
-+ *
-+ * The caller must ensure that the task *will* unschedule sometime soon,
-+ * else this function might spin for a *long* time. This function can't
-+ * be called with interrupts off, or it may introduce deadlock with
-+ * smp_call_function() if an IPI is sent by the same process we are
-+ * waiting to become inactive.
-+ */
-+unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
-+{
-+ unsigned long flags;
-+ int running, queued, match;
-+ unsigned long ncsw;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ for (;;) {
-+ rq = task_rq(p);
-+
-+ /*
-+ * If the task is actively running on another CPU
-+ * still, just relax and busy-wait without holding
-+ * any locks.
-+ *
-+ * NOTE! Since we don't hold any locks, it's not
-+ * even sure that "rq" stays as the right runqueue!
-+ * But we don't care, since this will return false
-+ * if the runqueue has changed and p is actually now
-+ * running somewhere else!
-+ */
-+ while (task_on_cpu(p)) {
-+ if (!task_state_match(p, match_state))
-+ return 0;
-+ cpu_relax();
-+ }
-+
-+ /*
-+ * Ok, time to look more closely! We need the rq
-+ * lock now, to be *sure*. If we're wrong, we'll
-+ * just go back and repeat.
-+ */
-+ task_access_lock_irqsave(p, &lock, &flags);
-+ trace_sched_wait_task(p);
-+ running = task_on_cpu(p);
-+ queued = p->on_rq;
-+ ncsw = 0;
-+ if ((match = __task_state_match(p, match_state))) {
-+ /*
-+ * When matching on p->saved_state, consider this task
-+ * still queued so it will wait.
-+ */
-+ if (match < 0)
-+ queued = 1;
-+ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
-+ }
-+ task_access_unlock_irqrestore(p, lock, &flags);
-+
-+ /*
-+ * If it changed from the expected state, bail out now.
-+ */
-+ if (unlikely(!ncsw))
-+ break;
-+
-+ /*
-+ * Was it really running after all now that we
-+ * checked with the proper locks actually held?
-+ *
-+ * Oops. Go back and try again..
-+ */
-+ if (unlikely(running)) {
-+ cpu_relax();
-+ continue;
-+ }
-+
-+ /*
-+ * It's not enough that it's not actively running,
-+ * it must be off the runqueue _entirely_, and not
-+ * preempted!
-+ *
-+ * So if it was still runnable (but just not actively
-+ * running right now), it's preempted, and we should
-+ * yield - it could be a while.
-+ */
-+ if (unlikely(queued)) {
-+ ktime_t to = NSEC_PER_SEC / HZ;
-+
-+ set_current_state(TASK_UNINTERRUPTIBLE);
-+ schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
-+ continue;
-+ }
-+
-+ /*
-+ * Ahh, all good. It wasn't running, and it wasn't
-+ * runnable, which means that it will never become
-+ * running in the future either. We're all done!
-+ */
-+ break;
-+ }
-+
-+ return ncsw;
-+}
-+
-+#ifdef CONFIG_SCHED_HRTICK
-+/*
-+ * Use HR-timers to deliver accurate preemption points.
-+ */
-+
-+static void hrtick_clear(struct rq *rq)
-+{
-+ if (hrtimer_active(&rq->hrtick_timer))
-+ hrtimer_cancel(&rq->hrtick_timer);
-+}
-+
-+/*
-+ * High-resolution timer tick.
-+ * Runs from hardirq context with interrupts disabled.
-+ */
-+static enum hrtimer_restart hrtick(struct hrtimer *timer)
-+{
-+ struct rq *rq = container_of(timer, struct rq, hrtick_timer);
-+
-+ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-+
-+ raw_spin_lock(&rq->lock);
-+ resched_curr(rq);
-+ raw_spin_unlock(&rq->lock);
-+
-+ return HRTIMER_NORESTART;
-+}
-+
-+/*
-+ * Use hrtick when:
-+ * - enabled by features
-+ * - hrtimer is actually high res
-+ */
-+static inline int hrtick_enabled(struct rq *rq)
-+{
-+ /**
-+ * Alt schedule FW doesn't support sched_feat yet
-+ if (!sched_feat(HRTICK))
-+ return 0;
-+ */
-+ if (!cpu_active(cpu_of(rq)))
-+ return 0;
-+ return hrtimer_is_hres_active(&rq->hrtick_timer);
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+static void __hrtick_restart(struct rq *rq)
-+{
-+ struct hrtimer *timer = &rq->hrtick_timer;
-+ ktime_t time = rq->hrtick_time;
-+
-+ hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
-+}
-+
-+/*
-+ * called from hardirq (IPI) context
-+ */
-+static void __hrtick_start(void *arg)
-+{
-+ struct rq *rq = arg;
-+
-+ raw_spin_lock(&rq->lock);
-+ __hrtick_restart(rq);
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+/*
-+ * Called to set the hrtick timer state.
-+ *
-+ * called with rq->lock held and irqs disabled
-+ */
-+static inline void hrtick_start(struct rq *rq, u64 delay)
-+{
-+ struct hrtimer *timer = &rq->hrtick_timer;
-+ s64 delta;
-+
-+ /*
-+ * Don't schedule slices shorter than 10000ns, that just
-+ * doesn't make sense and can cause timer DoS.
-+ */
-+ delta = max_t(s64, delay, 10000LL);
-+
-+ rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
-+
-+ if (rq == this_rq())
-+ __hrtick_restart(rq);
-+ else
-+ smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
-+}
-+
-+#else
-+/*
-+ * Called to set the hrtick timer state.
-+ *
-+ * called with rq->lock held and irqs disabled
-+ */
-+static inline void hrtick_start(struct rq *rq, u64 delay)
-+{
-+ /*
-+ * Don't schedule slices shorter than 10000ns, that just
-+ * doesn't make sense. Rely on vruntime for fairness.
-+ */
-+ delay = max_t(u64, delay, 10000LL);
-+ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
-+ HRTIMER_MODE_REL_PINNED_HARD);
-+}
-+#endif /* CONFIG_SMP */
-+
-+static void hrtick_rq_init(struct rq *rq)
-+{
-+#ifdef CONFIG_SMP
-+ INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
-+#endif
-+
-+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-+ rq->hrtick_timer.function = hrtick;
-+}
-+#else /* CONFIG_SCHED_HRTICK */
-+static inline int hrtick_enabled(struct rq *rq)
-+{
-+ return 0;
-+}
-+
-+static inline void hrtick_clear(struct rq *rq)
-+{
-+}
-+
-+static inline void hrtick_rq_init(struct rq *rq)
-+{
-+}
-+#endif /* CONFIG_SCHED_HRTICK */
-+
-+static inline int __normal_prio(int policy, int rt_prio, int static_prio)
-+{
-+ return rt_policy(policy) ? (MAX_RT_PRIO - 1 - rt_prio) : static_prio;
-+}
-+
-+/*
-+ * Calculate the expected normal priority: i.e. priority
-+ * without taking RT-inheritance into account. Might be
-+ * boosted by interactivity modifiers. Changes upon fork,
-+ * setprio syscalls, and whenever the interactivity
-+ * estimator recalculates.
-+ */
-+static inline int normal_prio(struct task_struct *p)
-+{
-+ return __normal_prio(p->policy, p->rt_priority, p->static_prio);
-+}
-+
-+/*
-+ * Calculate the current priority, i.e. the priority
-+ * taken into account by the scheduler. This value might
-+ * be boosted by RT tasks as it will be RT if the task got
-+ * RT-boosted. If not then it returns p->normal_prio.
-+ */
-+static int effective_prio(struct task_struct *p)
-+{
-+ p->normal_prio = normal_prio(p);
-+ /*
-+ * If we are RT tasks or we were boosted to RT priority,
-+ * keep the priority unchanged. Otherwise, update priority
-+ * to the normal priority:
-+ */
-+ if (!rt_prio(p->prio))
-+ return p->normal_prio;
-+ return p->prio;
-+}
-+
-+/*
-+ * activate_task - move a task to the runqueue.
-+ *
-+ * Context: rq->lock
-+ */
-+static void activate_task(struct task_struct *p, struct rq *rq)
-+{
-+ enqueue_task(p, rq, ENQUEUE_WAKEUP);
-+
-+ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
-+ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
-+
-+ /*
-+ * If in_iowait is set, the code below may not trigger any cpufreq
-+ * utilization updates, so do it here explicitly with the IOWAIT flag
-+ * passed.
-+ */
-+ cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT * p->in_iowait);
-+}
-+
-+/*
-+ * deactivate_task - remove a task from the runqueue.
-+ *
-+ * Context: rq->lock
-+ */
-+static inline void deactivate_task(struct task_struct *p, struct rq *rq)
-+{
-+ WRITE_ONCE(p->on_rq, 0);
-+ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
-+
-+ dequeue_task(p, rq, DEQUEUE_SLEEP);
-+
-+ cpufreq_update_util(rq, 0);
-+}
-+
-+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
-+{
-+#ifdef CONFIG_SMP
-+ /*
-+ * After ->cpu is set up to a new value, task_access_lock(p, ...) can be
-+ * successfully executed on another CPU. We must ensure that updates of
-+ * per-task data have been completed by this moment.
-+ */
-+ smp_wmb();
-+
-+ WRITE_ONCE(task_thread_info(p)->cpu, cpu);
-+#endif
-+}
-+
-+static inline bool is_migration_disabled(struct task_struct *p)
-+{
-+#ifdef CONFIG_SMP
-+ return p->migration_disabled;
-+#else
-+ return false;
-+#endif
-+}
-+
-+#define SCA_CHECK 0x01
-+#define SCA_USER 0x08
-+
-+#ifdef CONFIG_SMP
-+
-+void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
-+{
-+#ifdef CONFIG_SCHED_DEBUG
-+ unsigned int state = READ_ONCE(p->__state);
-+
-+ /*
-+ * We should never call set_task_cpu() on a blocked task,
-+ * ttwu() will sort out the placement.
-+ */
-+ WARN_ON_ONCE(state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq);
-+
-+#ifdef CONFIG_LOCKDEP
-+ /*
-+ * The caller should hold either p->pi_lock or rq->lock, when changing
-+ * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
-+ *
-+ * sched_move_task() holds both and thus holding either pins the cgroup,
-+ * see task_group().
-+ */
-+ WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
-+ lockdep_is_held(&task_rq(p)->lock)));
-+#endif
-+ /*
-+ * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
-+ */
-+ WARN_ON_ONCE(!cpu_online(new_cpu));
-+
-+ WARN_ON_ONCE(is_migration_disabled(p));
-+#endif
-+ trace_sched_migrate_task(p, new_cpu);
-+
-+ if (task_cpu(p) != new_cpu)
-+ {
-+ rseq_migrate(p);
-+ perf_event_task_migrate(p);
-+ }
-+
-+ __set_task_cpu(p, new_cpu);
-+}
-+
-+#define MDF_FORCE_ENABLED 0x80
-+
-+static void
-+__do_set_cpus_ptr(struct task_struct *p, const struct cpumask *new_mask)
-+{
-+ /*
-+ * This here violates the locking rules for affinity, since we're only
-+ * supposed to change these variables while holding both rq->lock and
-+ * p->pi_lock.
-+ *
-+ * HOWEVER, it magically works, because ttwu() is the only code that
-+ * accesses these variables under p->pi_lock and only does so after
-+ * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
-+ * before finish_task().
-+ *
-+ * XXX do further audits, this smells like something putrid.
-+ */
-+ SCHED_WARN_ON(!p->on_cpu);
-+ p->cpus_ptr = new_mask;
-+}
-+
-+void migrate_disable(void)
-+{
-+ struct task_struct *p = current;
-+ int cpu;
-+
-+ if (p->migration_disabled) {
-+ p->migration_disabled++;
-+ return;
-+ }
-+
-+ guard(preempt)();
-+ cpu = smp_processor_id();
-+ if (cpumask_test_cpu(cpu, &p->cpus_mask)) {
-+ cpu_rq(cpu)->nr_pinned++;
-+ p->migration_disabled = 1;
-+ p->migration_flags &= ~MDF_FORCE_ENABLED;
-+
-+ /*
-+ * Violates locking rules! see comment in __do_set_cpus_ptr().
-+ */
-+ if (p->cpus_ptr == &p->cpus_mask)
-+ __do_set_cpus_ptr(p, cpumask_of(cpu));
-+ }
-+}
-+EXPORT_SYMBOL_GPL(migrate_disable);
-+
-+void migrate_enable(void)
-+{
-+ struct task_struct *p = current;
-+
-+ if (0 == p->migration_disabled)
-+ return;
-+
-+ if (p->migration_disabled > 1) {
-+ p->migration_disabled--;
-+ return;
-+ }
-+
-+ if (WARN_ON_ONCE(!p->migration_disabled))
-+ return;
-+
-+ /*
-+ * Ensure stop_task runs either before or after this, and that
-+ * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
-+ */
-+ guard(preempt)();
-+ /*
-+ * Assumption: current should be running on allowed cpu
-+ */
-+ WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &p->cpus_mask));
-+ if (p->cpus_ptr != &p->cpus_mask)
-+ __do_set_cpus_ptr(p, &p->cpus_mask);
-+ /*
-+ * Mustn't clear migration_disabled() until cpus_ptr points back at the
-+ * regular cpus_mask, otherwise things that race (eg.
-+ * select_fallback_rq) get confused.
-+ */
-+ barrier();
-+ p->migration_disabled = 0;
-+ this_rq()->nr_pinned--;
-+}
-+EXPORT_SYMBOL_GPL(migrate_enable);
-+
-+static inline bool rq_has_pinned_tasks(struct rq *rq)
-+{
-+ return rq->nr_pinned;
-+}
-+
-+/*
-+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
-+ * __set_cpus_allowed_ptr() and select_fallback_rq().
-+ */
-+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
-+{
-+ /* When not in the task's cpumask, no point in looking further. */
-+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
-+ return false;
-+
-+ /* migrate_disabled() must be allowed to finish. */
-+ if (is_migration_disabled(p))
-+ return cpu_online(cpu);
-+
-+ /* Non kernel threads are not allowed during either online or offline. */
-+ if (!(p->flags & PF_KTHREAD))
-+ return cpu_active(cpu) && task_cpu_possible(cpu, p);
-+
-+ /* KTHREAD_IS_PER_CPU is always allowed. */
-+ if (kthread_is_per_cpu(p))
-+ return cpu_online(cpu);
-+
-+ /* Regular kernel threads don't get to stay during offline. */
-+ if (cpu_dying(cpu))
-+ return false;
-+
-+ /* But are allowed during online. */
-+ return cpu_online(cpu);
-+}
-+
-+/*
-+ * This is how migration works:
-+ *
-+ * 1) we invoke migration_cpu_stop() on the target CPU using
-+ * stop_one_cpu().
-+ * 2) stopper starts to run (implicitly forcing the migrated thread
-+ * off the CPU)
-+ * 3) it checks whether the migrated task is still in the wrong runqueue.
-+ * 4) if it's in the wrong runqueue then the migration thread removes
-+ * it and puts it into the right queue.
-+ * 5) stopper completes and stop_one_cpu() returns and the migration
-+ * is done.
-+ */
-+
-+/*
-+ * move_queued_task - move a queued task to new rq.
-+ *
-+ * Returns (locked) new rq. Old rq's lock is released.
-+ */
-+static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
-+{
-+ int src_cpu;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ src_cpu = cpu_of(rq);
-+ WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
-+ dequeue_task(p, rq, 0);
-+ set_task_cpu(p, new_cpu);
-+ raw_spin_unlock(&rq->lock);
-+
-+ rq = cpu_rq(new_cpu);
-+
-+ raw_spin_lock(&rq->lock);
-+ WARN_ON_ONCE(task_cpu(p) != new_cpu);
-+
-+ sched_mm_cid_migrate_to(rq, p, src_cpu);
-+
-+ sched_task_sanity_check(p, rq);
-+ enqueue_task(p, rq, 0);
-+ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
-+ wakeup_preempt(rq);
-+
-+ return rq;
-+}
-+
-+struct migration_arg {
-+ struct task_struct *task;
-+ int dest_cpu;
-+};
-+
-+/*
-+ * Move (not current) task off this CPU, onto the destination CPU. We're doing
-+ * this because either it can't run here any more (set_cpus_allowed()
-+ * away from this CPU, or CPU going down), or because we're
-+ * attempting to rebalance this task on exec (sched_exec).
-+ *
-+ * So we race with normal scheduler movements, but that's OK, as long
-+ * as the task is no longer on this CPU.
-+ */
-+static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
-+{
-+ /* Affinity changed (again). */
-+ if (!is_cpu_allowed(p, dest_cpu))
-+ return rq;
-+
-+ return move_queued_task(rq, p, dest_cpu);
-+}
-+
-+/*
-+ * migration_cpu_stop - this will be executed by a highprio stopper thread
-+ * and performs thread migration by bumping thread off CPU then
-+ * 'pushing' onto another runqueue.
-+ */
-+static int migration_cpu_stop(void *data)
-+{
-+ struct migration_arg *arg = data;
-+ struct task_struct *p = arg->task;
-+ struct rq *rq = this_rq();
-+ unsigned long flags;
-+
-+ /*
-+ * The original target CPU might have gone down and we might
-+ * be on another CPU but it doesn't matter.
-+ */
-+ local_irq_save(flags);
-+ /*
-+ * We need to explicitly wake pending tasks before running
-+ * __migrate_task() such that we will not miss enforcing cpus_ptr
-+ * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
-+ */
-+ flush_smp_call_function_queue();
-+
-+ raw_spin_lock(&p->pi_lock);
-+ raw_spin_lock(&rq->lock);
-+ /*
-+ * If task_rq(p) != rq, it cannot be migrated here, because we're
-+ * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
-+ * we're holding p->pi_lock.
-+ */
-+ if (task_rq(p) == rq && task_on_rq_queued(p)) {
-+ update_rq_clock(rq);
-+ rq = __migrate_task(rq, p, arg->dest_cpu);
-+ }
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+
-+ return 0;
-+}
-+
-+static inline void
-+set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx)
-+{
-+ cpumask_copy(&p->cpus_mask, ctx->new_mask);
-+ p->nr_cpus_allowed = cpumask_weight(ctx->new_mask);
-+
-+ /*
-+ * Swap in a new user_cpus_ptr if SCA_USER flag set
-+ */
-+ if (ctx->flags & SCA_USER)
-+ swap(p->user_cpus_ptr, ctx->user_mask);
-+}
-+
-+static void
-+__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
-+{
-+ lockdep_assert_held(&p->pi_lock);
-+ set_cpus_allowed_common(p, ctx);
-+}
-+
-+/*
-+ * Used for kthread_bind() and select_fallback_rq(), in both cases the user
-+ * affinity (if any) should be destroyed too.
-+ */
-+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = new_mask,
-+ .user_mask = NULL,
-+ .flags = SCA_USER, /* clear the user requested mask */
-+ };
-+ union cpumask_rcuhead {
-+ cpumask_t cpumask;
-+ struct rcu_head rcu;
-+ };
-+
-+ __do_set_cpus_allowed(p, &ac);
-+
-+ /*
-+ * Because this is called with p->pi_lock held, it is not possible
-+ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
-+ * kfree_rcu().
-+ */
-+ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
-+}
-+
-+static cpumask_t *alloc_user_cpus_ptr(int node)
-+{
-+ /*
-+ * See do_set_cpus_allowed() above for the rcu_head usage.
-+ */
-+ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
-+
-+ return kmalloc_node(size, GFP_KERNEL, node);
-+}
-+
-+int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
-+ int node)
-+{
-+ cpumask_t *user_mask;
-+ unsigned long flags;
-+
-+ /*
-+ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
-+ * may differ by now due to racing.
-+ */
-+ dst->user_cpus_ptr = NULL;
-+
-+ /*
-+ * This check is racy and losing the race is a valid situation.
-+ * It is not worth the extra overhead of taking the pi_lock on
-+ * every fork/clone.
-+ */
-+ if (data_race(!src->user_cpus_ptr))
-+ return 0;
-+
-+ user_mask = alloc_user_cpus_ptr(node);
-+ if (!user_mask)
-+ return -ENOMEM;
-+
-+ /*
-+ * Use pi_lock to protect content of user_cpus_ptr
-+ *
-+ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
-+ * do_set_cpus_allowed().
-+ */
-+ raw_spin_lock_irqsave(&src->pi_lock, flags);
-+ if (src->user_cpus_ptr) {
-+ swap(dst->user_cpus_ptr, user_mask);
-+ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
-+ }
-+ raw_spin_unlock_irqrestore(&src->pi_lock, flags);
-+
-+ if (unlikely(user_mask))
-+ kfree(user_mask);
-+
-+ return 0;
-+}
-+
-+static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
-+{
-+ struct cpumask *user_mask = NULL;
-+
-+ swap(p->user_cpus_ptr, user_mask);
-+
-+ return user_mask;
-+}
-+
-+void release_user_cpus_ptr(struct task_struct *p)
-+{
-+ kfree(clear_user_cpus_ptr(p));
-+}
-+
-+#endif
-+
-+/**
-+ * task_curr - is this task currently executing on a CPU?
-+ * @p: the task in question.
-+ *
-+ * Return: 1 if the task is currently executing. 0 otherwise.
-+ */
-+inline int task_curr(const struct task_struct *p)
-+{
-+ return cpu_curr(task_cpu(p)) == p;
-+}
-+
-+#ifdef CONFIG_SMP
-+/***
-+ * kick_process - kick a running thread to enter/exit the kernel
-+ * @p: the to-be-kicked thread
-+ *
-+ * Cause a process which is running on another CPU to enter
-+ * kernel-mode, without any delay. (to get signals handled.)
-+ *
-+ * NOTE: this function doesn't have to take the runqueue lock,
-+ * because all it wants to ensure is that the remote task enters
-+ * the kernel. If the IPI races and the task has been migrated
-+ * to another CPU then no harm is done and the purpose has been
-+ * achieved as well.
-+ */
-+void kick_process(struct task_struct *p)
-+{
-+ guard(preempt)();
-+ int cpu = task_cpu(p);
-+
-+ if ((cpu != smp_processor_id()) && task_curr(p))
-+ smp_send_reschedule(cpu);
-+}
-+EXPORT_SYMBOL_GPL(kick_process);
-+
-+/*
-+ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
-+ *
-+ * A few notes on cpu_active vs cpu_online:
-+ *
-+ * - cpu_active must be a subset of cpu_online
-+ *
-+ * - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
-+ * see __set_cpus_allowed_ptr(). At this point the newly online
-+ * CPU isn't yet part of the sched domains, and balancing will not
-+ * see it.
-+ *
-+ * - on cpu-down we clear cpu_active() to mask the sched domains and
-+ * avoid the load balancer to place new tasks on the to be removed
-+ * CPU. Existing tasks will remain running there and will be taken
-+ * off.
-+ *
-+ * This means that fallback selection must not select !active CPUs.
-+ * And can assume that any active CPU must be online. Conversely
-+ * select_task_rq() below may allow selection of !active CPUs in order
-+ * to satisfy the above rules.
-+ */
-+static int select_fallback_rq(int cpu, struct task_struct *p)
-+{
-+ int nid = cpu_to_node(cpu);
-+ const struct cpumask *nodemask = NULL;
-+ enum { cpuset, possible, fail } state = cpuset;
-+ int dest_cpu;
-+
-+ /*
-+ * If the node that the CPU is on has been offlined, cpu_to_node()
-+ * will return -1. There is no CPU on the node, and we should
-+ * select the CPU on the other node.
-+ */
-+ if (nid != -1) {
-+ nodemask = cpumask_of_node(nid);
-+
-+ /* Look for allowed, online CPU in same node. */
-+ for_each_cpu(dest_cpu, nodemask) {
-+ if (is_cpu_allowed(p, dest_cpu))
-+ return dest_cpu;
-+ }
-+ }
-+
-+ for (;;) {
-+ /* Any allowed, online CPU? */
-+ for_each_cpu(dest_cpu, p->cpus_ptr) {
-+ if (!is_cpu_allowed(p, dest_cpu))
-+ continue;
-+ goto out;
-+ }
-+
-+ /* No more Mr. Nice Guy. */
-+ switch (state) {
-+ case cpuset:
-+ if (cpuset_cpus_allowed_fallback(p)) {
-+ state = possible;
-+ break;
-+ }
-+ fallthrough;
-+ case possible:
-+ /*
-+ * XXX When called from select_task_rq() we only
-+ * hold p->pi_lock and again violate locking order.
-+ *
-+ * More yuck to audit.
-+ */
-+ do_set_cpus_allowed(p, task_cpu_possible_mask(p));
-+ state = fail;
-+ break;
-+
-+ case fail:
-+ BUG();
-+ break;
-+ }
-+ }
-+
-+out:
-+ if (state != cpuset) {
-+ /*
-+ * Don't tell them about moving exiting tasks or
-+ * kernel threads (both mm NULL), since they never
-+ * leave kernel.
-+ */
-+ if (p->mm && printk_ratelimit()) {
-+ printk_deferred("process %d (%s) no longer affine to cpu%d\n",
-+ task_pid_nr(p), p->comm, cpu);
-+ }
-+ }
-+
-+ return dest_cpu;
-+}
-+
-+static inline void
-+sched_preempt_mask_flush(cpumask_t *mask, int prio, int ref)
-+{
-+ int cpu;
-+
-+ cpumask_copy(mask, sched_preempt_mask + ref);
-+ if (prio < ref) {
-+ for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) {
-+ if (prio < cpu_rq(cpu)->prio)
-+ cpumask_set_cpu(cpu, mask);
-+ }
-+ } else {
-+ for_each_cpu_andnot(cpu, mask, sched_idle_mask) {
-+ if (prio >= cpu_rq(cpu)->prio)
-+ cpumask_clear_cpu(cpu, mask);
-+ }
-+ }
-+}
-+
-+static inline int
-+preempt_mask_check(cpumask_t *preempt_mask, cpumask_t *allow_mask, int prio)
-+{
-+ cpumask_t *mask = sched_preempt_mask + prio;
-+ int pr = atomic_read(&sched_prio_record);
-+
-+ if (pr != prio && SCHED_QUEUE_BITS - 1 != prio) {
-+ sched_preempt_mask_flush(mask, prio, pr);
-+ atomic_set(&sched_prio_record, prio);
-+ }
-+
-+ return cpumask_and(preempt_mask, allow_mask, mask);
-+}
-+
-+static inline int select_task_rq(struct task_struct *p)
-+{
-+ cpumask_t allow_mask, mask;
-+
-+ if (unlikely(!cpumask_and(&allow_mask, p->cpus_ptr, cpu_active_mask)))
-+ return select_fallback_rq(task_cpu(p), p);
-+
-+ if (
-+#ifdef CONFIG_SCHED_SMT
-+ cpumask_and(&mask, &allow_mask, sched_sg_idle_mask) ||
-+#endif
-+ cpumask_and(&mask, &allow_mask, sched_idle_mask) ||
-+ preempt_mask_check(&mask, &allow_mask, task_sched_prio(p)))
-+ return best_mask_cpu(task_cpu(p), &mask);
-+
-+ return best_mask_cpu(task_cpu(p), &allow_mask);
-+}
-+
-+void sched_set_stop_task(int cpu, struct task_struct *stop)
-+{
-+ static struct lock_class_key stop_pi_lock;
-+ struct sched_param stop_param = { .sched_priority = STOP_PRIO };
-+ struct sched_param start_param = { .sched_priority = 0 };
-+ struct task_struct *old_stop = cpu_rq(cpu)->stop;
-+
-+ if (stop) {
-+ /*
-+ * Make it appear like a SCHED_FIFO task, its something
-+ * userspace knows about and won't get confused about.
-+ *
-+ * Also, it will make PI more or less work without too
-+ * much confusion -- but then, stop work should not
-+ * rely on PI working anyway.
-+ */
-+ sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param);
-+
-+ /*
-+ * The PI code calls rt_mutex_setprio() with ->pi_lock held to
-+ * adjust the effective priority of a task. As a result,
-+ * rt_mutex_setprio() can trigger (RT) balancing operations,
-+ * which can then trigger wakeups of the stop thread to push
-+ * around the current task.
-+ *
-+ * The stop task itself will never be part of the PI-chain, it
-+ * never blocks, therefore that ->pi_lock recursion is safe.
-+ * Tell lockdep about this by placing the stop->pi_lock in its
-+ * own class.
-+ */
-+ lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
-+ }
-+
-+ cpu_rq(cpu)->stop = stop;
-+
-+ if (old_stop) {
-+ /*
-+ * Reset it back to a normal scheduling policy so that
-+ * it can die in pieces.
-+ */
-+ sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param);
-+ }
-+}
-+
-+static int affine_move_task(struct rq *rq, struct task_struct *p, int dest_cpu,
-+ raw_spinlock_t *lock, unsigned long irq_flags)
-+ __releases(rq->lock)
-+ __releases(p->pi_lock)
-+{
-+ /* Can the task run on the task's current CPU? If so, we're done */
-+ if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
-+ if (p->migration_disabled) {
-+ if (likely(p->cpus_ptr != &p->cpus_mask))
-+ __do_set_cpus_ptr(p, &p->cpus_mask);
-+ p->migration_disabled = 0;
-+ p->migration_flags |= MDF_FORCE_ENABLED;
-+ /* When p is migrate_disabled, rq->lock should be held */
-+ rq->nr_pinned--;
-+ }
-+
-+ if (task_on_cpu(p) || READ_ONCE(p->__state) == TASK_WAKING) {
-+ struct migration_arg arg = { p, dest_cpu };
-+
-+ /* Need help from migration thread: drop lock and wait. */
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-+ return 0;
-+ }
-+ if (task_on_rq_queued(p)) {
-+ /*
-+ * OK, since we're going to drop the lock immediately
-+ * afterwards anyway.
-+ */
-+ update_rq_clock(rq);
-+ rq = move_queued_task(rq, p, dest_cpu);
-+ lock = &rq->lock;
-+ }
-+ }
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+ return 0;
-+}
-+
-+static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
-+ struct affinity_context *ctx,
-+ struct rq *rq,
-+ raw_spinlock_t *lock,
-+ unsigned long irq_flags)
-+{
-+ const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
-+ const struct cpumask *cpu_valid_mask = cpu_active_mask;
-+ bool kthread = p->flags & PF_KTHREAD;
-+ int dest_cpu;
-+ int ret = 0;
-+
-+ if (kthread || is_migration_disabled(p)) {
-+ /*
-+ * Kernel threads are allowed on online && !active CPUs,
-+ * however, during cpu-hot-unplug, even these might get pushed
-+ * away if not KTHREAD_IS_PER_CPU.
-+ *
-+ * Specifically, migration_disabled() tasks must not fail the
-+ * cpumask_any_and_distribute() pick below, esp. so on
-+ * SCA_MIGRATE_ENABLE, otherwise we'll not call
-+ * set_cpus_allowed_common() and actually reset p->cpus_ptr.
-+ */
-+ cpu_valid_mask = cpu_online_mask;
-+ }
-+
-+ if (!kthread && !cpumask_subset(ctx->new_mask, cpu_allowed_mask)) {
-+ ret = -EINVAL;
-+ goto out;
-+ }
-+
-+ /*
-+ * Must re-check here, to close a race against __kthread_bind(),
-+ * sched_setaffinity() is not guaranteed to observe the flag.
-+ */
-+ if ((ctx->flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
-+ ret = -EINVAL;
-+ goto out;
-+ }
-+
-+ if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
-+ goto out;
-+
-+ dest_cpu = cpumask_any_and(cpu_valid_mask, ctx->new_mask);
-+ if (dest_cpu >= nr_cpu_ids) {
-+ ret = -EINVAL;
-+ goto out;
-+ }
-+
-+ __do_set_cpus_allowed(p, ctx);
-+
-+ return affine_move_task(rq, p, dest_cpu, lock, irq_flags);
-+
-+out:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+
-+ return ret;
-+}
-+
-+/*
-+ * Change a given task's CPU affinity. Migrate the thread to a
-+ * is removed from the allowed bitmask.
-+ *
-+ * NOTE: the caller must have a valid reference to the task, the
-+ * task must not exit() & deallocate itself prematurely. The
-+ * call is not atomic; no spinlocks may be held.
-+ */
-+static int __set_cpus_allowed_ptr(struct task_struct *p,
-+ struct affinity_context *ctx)
-+{
-+ unsigned long irq_flags;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
-+ rq = __task_access_lock(p, &lock);
-+ /*
-+ * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
-+ * flags are set.
-+ */
-+ if (p->user_cpus_ptr &&
-+ !(ctx->flags & SCA_USER) &&
-+ cpumask_and(rq->scratch_mask, ctx->new_mask, p->user_cpus_ptr))
-+ ctx->new_mask = rq->scratch_mask;
-+
-+
-+ return __set_cpus_allowed_ptr_locked(p, ctx, rq, lock, irq_flags);
-+}
-+
-+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = new_mask,
-+ .flags = 0,
-+ };
-+
-+ return __set_cpus_allowed_ptr(p, &ac);
-+}
-+EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
-+
-+/*
-+ * Change a given task's CPU affinity to the intersection of its current
-+ * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
-+ * If user_cpus_ptr is defined, use it as the basis for restricting CPU
-+ * affinity or use cpu_online_mask instead.
-+ *
-+ * If the resulting mask is empty, leave the affinity unchanged and return
-+ * -EINVAL.
-+ */
-+static int restrict_cpus_allowed_ptr(struct task_struct *p,
-+ struct cpumask *new_mask,
-+ const struct cpumask *subset_mask)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = new_mask,
-+ .flags = 0,
-+ };
-+ unsigned long irq_flags;
-+ raw_spinlock_t *lock;
-+ struct rq *rq;
-+ int err;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
-+ rq = __task_access_lock(p, &lock);
-+
-+ if (!cpumask_and(new_mask, task_user_cpus(p), subset_mask)) {
-+ err = -EINVAL;
-+ goto err_unlock;
-+ }
-+
-+ return __set_cpus_allowed_ptr_locked(p, &ac, rq, lock, irq_flags);
-+
-+err_unlock:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+ return err;
-+}
-+
-+/*
-+ * Restrict the CPU affinity of task @p so that it is a subset of
-+ * task_cpu_possible_mask() and point @p->user_cpus_ptr to a copy of the
-+ * old affinity mask. If the resulting mask is empty, we warn and walk
-+ * up the cpuset hierarchy until we find a suitable mask.
-+ */
-+void force_compatible_cpus_allowed_ptr(struct task_struct *p)
-+{
-+ cpumask_var_t new_mask;
-+ const struct cpumask *override_mask = task_cpu_possible_mask(p);
-+
-+ alloc_cpumask_var(&new_mask, GFP_KERNEL);
-+
-+ /*
-+ * __migrate_task() can fail silently in the face of concurrent
-+ * offlining of the chosen destination CPU, so take the hotplug
-+ * lock to ensure that the migration succeeds.
-+ */
-+ cpus_read_lock();
-+ if (!cpumask_available(new_mask))
-+ goto out_set_mask;
-+
-+ if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
-+ goto out_free_mask;
-+
-+ /*
-+ * We failed to find a valid subset of the affinity mask for the
-+ * task, so override it based on its cpuset hierarchy.
-+ */
-+ cpuset_cpus_allowed(p, new_mask);
-+ override_mask = new_mask;
-+
-+out_set_mask:
-+ if (printk_ratelimit()) {
-+ printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
-+ task_pid_nr(p), p->comm,
-+ cpumask_pr_args(override_mask));
-+ }
-+
-+ WARN_ON(set_cpus_allowed_ptr(p, override_mask));
-+out_free_mask:
-+ cpus_read_unlock();
-+ free_cpumask_var(new_mask);
-+}
-+
-+static int
-+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
-+
-+/*
-+ * Restore the affinity of a task @p which was previously restricted by a
-+ * call to force_compatible_cpus_allowed_ptr().
-+ *
-+ * It is the caller's responsibility to serialise this with any calls to
-+ * force_compatible_cpus_allowed_ptr(@p).
-+ */
-+void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = task_user_cpus(p),
-+ .flags = 0,
-+ };
-+ int ret;
-+
-+ /*
-+ * Try to restore the old affinity mask with __sched_setaffinity().
-+ * Cpuset masking will be done there too.
-+ */
-+ ret = __sched_setaffinity(p, &ac);
-+ WARN_ON_ONCE(ret);
-+}
-+
-+#else /* CONFIG_SMP */
-+
-+static inline int select_task_rq(struct task_struct *p)
-+{
-+ return 0;
-+}
-+
-+static inline int
-+__set_cpus_allowed_ptr(struct task_struct *p,
-+ struct affinity_context *ctx)
-+{
-+ return set_cpus_allowed_ptr(p, ctx->new_mask);
-+}
-+
-+static inline bool rq_has_pinned_tasks(struct rq *rq)
-+{
-+ return false;
-+}
-+
-+static inline cpumask_t *alloc_user_cpus_ptr(int node)
-+{
-+ return NULL;
-+}
-+
-+#endif /* !CONFIG_SMP */
-+
-+static void
-+ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ struct rq *rq;
-+
-+ if (!schedstat_enabled())
-+ return;
-+
-+ rq = this_rq();
-+
-+#ifdef CONFIG_SMP
-+ if (cpu == rq->cpu) {
-+ __schedstat_inc(rq->ttwu_local);
-+ __schedstat_inc(p->stats.nr_wakeups_local);
-+ } else {
-+ /** Alt schedule FW ToDo:
-+ * How to do ttwu_wake_remote
-+ */
-+ }
-+#endif /* CONFIG_SMP */
-+
-+ __schedstat_inc(rq->ttwu_count);
-+ __schedstat_inc(p->stats.nr_wakeups);
-+}
-+
-+/*
-+ * Mark the task runnable.
-+ */
-+static inline void ttwu_do_wakeup(struct task_struct *p)
-+{
-+ WRITE_ONCE(p->__state, TASK_RUNNING);
-+ trace_sched_wakeup(p);
-+}
-+
-+static inline void
-+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
-+{
-+ if (p->sched_contributes_to_load)
-+ rq->nr_uninterruptible--;
-+
-+ if (
-+#ifdef CONFIG_SMP
-+ !(wake_flags & WF_MIGRATED) &&
-+#endif
-+ p->in_iowait) {
-+ delayacct_blkio_end(p);
-+ atomic_dec(&task_rq(p)->nr_iowait);
-+ }
-+
-+ activate_task(p, rq);
-+ wakeup_preempt(rq);
-+
-+ ttwu_do_wakeup(p);
-+}
-+
-+/*
-+ * Consider @p being inside a wait loop:
-+ *
-+ * for (;;) {
-+ * set_current_state(TASK_UNINTERRUPTIBLE);
-+ *
-+ * if (CONDITION)
-+ * break;
-+ *
-+ * schedule();
-+ * }
-+ * __set_current_state(TASK_RUNNING);
-+ *
-+ * between set_current_state() and schedule(). In this case @p is still
-+ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
-+ * an atomic manner.
-+ *
-+ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
-+ * then schedule() must still happen and p->state can be changed to
-+ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
-+ * need to do a full wakeup with enqueue.
-+ *
-+ * Returns: %true when the wakeup is done,
-+ * %false otherwise.
-+ */
-+static int ttwu_runnable(struct task_struct *p, int wake_flags)
-+{
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+ int ret = 0;
-+
-+ rq = __task_access_lock(p, &lock);
-+ if (task_on_rq_queued(p)) {
-+ if (!task_on_cpu(p)) {
-+ /*
-+ * When on_rq && !on_cpu the task is preempted, see if
-+ * it should preempt the task that is current now.
-+ */
-+ update_rq_clock(rq);
-+ wakeup_preempt(rq);
-+ }
-+ ttwu_do_wakeup(p);
-+ ret = 1;
-+ }
-+ __task_access_unlock(p, lock);
-+
-+ return ret;
-+}
-+
-+#ifdef CONFIG_SMP
-+void sched_ttwu_pending(void *arg)
-+{
-+ struct llist_node *llist = arg;
-+ struct rq *rq = this_rq();
-+ struct task_struct *p, *t;
-+ struct rq_flags rf;
-+
-+ if (!llist)
-+ return;
-+
-+ rq_lock_irqsave(rq, &rf);
-+ update_rq_clock(rq);
-+
-+ llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
-+ if (WARN_ON_ONCE(p->on_cpu))
-+ smp_cond_load_acquire(&p->on_cpu, !VAL);
-+
-+ if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
-+ set_task_cpu(p, cpu_of(rq));
-+
-+ ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0);
-+ }
-+
-+ /*
-+ * Must be after enqueueing at least once task such that
-+ * idle_cpu() does not observe a false-negative -- if it does,
-+ * it is possible for select_idle_siblings() to stack a number
-+ * of tasks on this CPU during that window.
-+ *
-+ * It is ok to clear ttwu_pending when another task pending.
-+ * We will receive IPI after local irq enabled and then enqueue it.
-+ * Since now nr_running > 0, idle_cpu() will always get correct result.
-+ */
-+ WRITE_ONCE(rq->ttwu_pending, 0);
-+ rq_unlock_irqrestore(rq, &rf);
-+}
-+
-+/*
-+ * Prepare the scene for sending an IPI for a remote smp_call
-+ *
-+ * Returns true if the caller can proceed with sending the IPI.
-+ * Returns false otherwise.
-+ */
-+bool call_function_single_prep_ipi(int cpu)
-+{
-+ if (set_nr_if_polling(cpu_rq(cpu)->idle)) {
-+ trace_sched_wake_idle_without_ipi(cpu);
-+ return false;
-+ }
-+
-+ return true;
-+}
-+
-+/*
-+ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
-+ * necessary. The wakee CPU on receipt of the IPI will queue the task
-+ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
-+ * of the wakeup instead of the waker.
-+ */
-+static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
-+
-+ WRITE_ONCE(rq->ttwu_pending, 1);
-+ __smp_call_single_queue(cpu, &p->wake_entry.llist);
-+}
-+
-+static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
-+{
-+ /*
-+ * Do not complicate things with the async wake_list while the CPU is
-+ * in hotplug state.
-+ */
-+ if (!cpu_active(cpu))
-+ return false;
-+
-+ /* Ensure the task will still be allowed to run on the CPU. */
-+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
-+ return false;
-+
-+ /*
-+ * If the CPU does not share cache, then queue the task on the
-+ * remote rqs wakelist to avoid accessing remote data.
-+ */
-+ if (!cpus_share_cache(smp_processor_id(), cpu))
-+ return true;
-+
-+ if (cpu == smp_processor_id())
-+ return false;
-+
-+ /*
-+ * If the wakee cpu is idle, or the task is descheduling and the
-+ * only running task on the CPU, then use the wakelist to offload
-+ * the task activation to the idle (or soon-to-be-idle) CPU as
-+ * the current CPU is likely busy. nr_running is checked to
-+ * avoid unnecessary task stacking.
-+ *
-+ * Note that we can only get here with (wakee) p->on_rq=0,
-+ * p->on_cpu can be whatever, we've done the dequeue, so
-+ * the wakee has been accounted out of ->nr_running.
-+ */
-+ if (!cpu_rq(cpu)->nr_running)
-+ return true;
-+
-+ return false;
-+}
-+
-+static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ if (__is_defined(ALT_SCHED_TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
-+ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
-+ __ttwu_queue_wakelist(p, cpu, wake_flags);
-+ return true;
-+ }
-+
-+ return false;
-+}
-+
-+void wake_up_if_idle(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ guard(rcu)();
-+ if (is_idle_task(rcu_dereference(rq->curr))) {
-+ guard(raw_spinlock_irqsave)(&rq->lock);
-+ if (is_idle_task(rq->curr))
-+ resched_curr(rq);
-+ }
-+}
-+
-+extern struct static_key_false sched_asym_cpucapacity;
-+
-+static __always_inline bool sched_asym_cpucap_active(void)
-+{
-+ return static_branch_unlikely(&sched_asym_cpucapacity);
-+}
-+
-+bool cpus_equal_capacity(int this_cpu, int that_cpu)
-+{
-+ if (!sched_asym_cpucap_active())
-+ return true;
-+
-+ if (this_cpu == that_cpu)
-+ return true;
-+
-+ return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu);
-+}
-+
-+bool cpus_share_cache(int this_cpu, int that_cpu)
-+{
-+ if (this_cpu == that_cpu)
-+ return true;
-+
-+ return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
-+}
-+#else /* !CONFIG_SMP */
-+
-+static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ return false;
-+}
-+
-+#endif /* CONFIG_SMP */
-+
-+static inline void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ if (ttwu_queue_wakelist(p, cpu, wake_flags))
-+ return;
-+
-+ raw_spin_lock(&rq->lock);
-+ update_rq_clock(rq);
-+ ttwu_do_activate(rq, p, wake_flags);
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+/*
-+ * Invoked from try_to_wake_up() to check whether the task can be woken up.
-+ *
-+ * The caller holds p::pi_lock if p != current or has preemption
-+ * disabled when p == current.
-+ *
-+ * The rules of saved_state:
-+ *
-+ * The related locking code always holds p::pi_lock when updating
-+ * p::saved_state, which means the code is fully serialized in both cases.
-+ *
-+ * For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
-+ * No other bits set. This allows to distinguish all wakeup scenarios.
-+ *
-+ * For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
-+ * allows us to prevent early wakeup of tasks before they can be run on
-+ * asymmetric ISA architectures (eg ARMv9).
-+ */
-+static __always_inline
-+bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
-+{
-+ int match;
-+
-+ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
-+ WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
-+ state != TASK_RTLOCK_WAIT);
-+ }
-+
-+ *success = !!(match = __task_state_match(p, state));
-+
-+ /*
-+ * Saved state preserves the task state across blocking on
-+ * an RT lock or TASK_FREEZABLE tasks. If the state matches,
-+ * set p::saved_state to TASK_RUNNING, but do not wake the task
-+ * because it waits for a lock wakeup or __thaw_task(). Also
-+ * indicate success because from the regular waker's point of
-+ * view this has succeeded.
-+ *
-+ * After acquiring the lock the task will restore p::__state
-+ * from p::saved_state which ensures that the regular
-+ * wakeup is not lost. The restore will also set
-+ * p::saved_state to TASK_RUNNING so any further tests will
-+ * not result in false positives vs. @success
-+ */
-+ if (match < 0)
-+ p->saved_state = TASK_RUNNING;
-+
-+ return match > 0;
-+}
-+
-+/*
-+ * Notes on Program-Order guarantees on SMP systems.
-+ *
-+ * MIGRATION
-+ *
-+ * The basic program-order guarantee on SMP systems is that when a task [t]
-+ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
-+ * execution on its new CPU [c1].
-+ *
-+ * For migration (of runnable tasks) this is provided by the following means:
-+ *
-+ * A) UNLOCK of the rq(c0)->lock scheduling out task t
-+ * B) migration for t is required to synchronize *both* rq(c0)->lock and
-+ * rq(c1)->lock (if not at the same time, then in that order).
-+ * C) LOCK of the rq(c1)->lock scheduling in task
-+ *
-+ * Transitivity guarantees that B happens after A and C after B.
-+ * Note: we only require RCpc transitivity.
-+ * Note: the CPU doing B need not be c0 or c1
-+ *
-+ * Example:
-+ *
-+ * CPU0 CPU1 CPU2
-+ *
-+ * LOCK rq(0)->lock
-+ * sched-out X
-+ * sched-in Y
-+ * UNLOCK rq(0)->lock
-+ *
-+ * LOCK rq(0)->lock // orders against CPU0
-+ * dequeue X
-+ * UNLOCK rq(0)->lock
-+ *
-+ * LOCK rq(1)->lock
-+ * enqueue X
-+ * UNLOCK rq(1)->lock
-+ *
-+ * LOCK rq(1)->lock // orders against CPU2
-+ * sched-out Z
-+ * sched-in X
-+ * UNLOCK rq(1)->lock
-+ *
-+ *
-+ * BLOCKING -- aka. SLEEP + WAKEUP
-+ *
-+ * For blocking we (obviously) need to provide the same guarantee as for
-+ * migration. However the means are completely different as there is no lock
-+ * chain to provide order. Instead we do:
-+ *
-+ * 1) smp_store_release(X->on_cpu, 0) -- finish_task()
-+ * 2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
-+ *
-+ * Example:
-+ *
-+ * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule)
-+ *
-+ * LOCK rq(0)->lock LOCK X->pi_lock
-+ * dequeue X
-+ * sched-out X
-+ * smp_store_release(X->on_cpu, 0);
-+ *
-+ * smp_cond_load_acquire(&X->on_cpu, !VAL);
-+ * X->state = WAKING
-+ * set_task_cpu(X,2)
-+ *
-+ * LOCK rq(2)->lock
-+ * enqueue X
-+ * X->state = RUNNING
-+ * UNLOCK rq(2)->lock
-+ *
-+ * LOCK rq(2)->lock // orders against CPU1
-+ * sched-out Z
-+ * sched-in X
-+ * UNLOCK rq(2)->lock
-+ *
-+ * UNLOCK X->pi_lock
-+ * UNLOCK rq(0)->lock
-+ *
-+ *
-+ * However; for wakeups there is a second guarantee we must provide, namely we
-+ * must observe the state that lead to our wakeup. That is, not only must our
-+ * task observe its own prior state, it must also observe the stores prior to
-+ * its wakeup.
-+ *
-+ * This means that any means of doing remote wakeups must order the CPU doing
-+ * the wakeup against the CPU the task is going to end up running on. This,
-+ * however, is already required for the regular Program-Order guarantee above,
-+ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
-+ *
-+ */
-+
-+/**
-+ * try_to_wake_up - wake up a thread
-+ * @p: the thread to be awakened
-+ * @state: the mask of task states that can be woken
-+ * @wake_flags: wake modifier flags (WF_*)
-+ *
-+ * Conceptually does:
-+ *
-+ * If (@state & @p->state) @p->state = TASK_RUNNING.
-+ *
-+ * If the task was not queued/runnable, also place it back on a runqueue.
-+ *
-+ * This function is atomic against schedule() which would dequeue the task.
-+ *
-+ * It issues a full memory barrier before accessing @p->state, see the comment
-+ * with set_current_state().
-+ *
-+ * Uses p->pi_lock to serialize against concurrent wake-ups.
-+ *
-+ * Relies on p->pi_lock stabilizing:
-+ * - p->sched_class
-+ * - p->cpus_ptr
-+ * - p->sched_task_group
-+ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
-+ *
-+ * Tries really hard to only take one task_rq(p)->lock for performance.
-+ * Takes rq->lock in:
-+ * - ttwu_runnable() -- old rq, unavoidable, see comment there;
-+ * - ttwu_queue() -- new rq, for enqueue of the task;
-+ * - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
-+ *
-+ * As a consequence we race really badly with just about everything. See the
-+ * many memory barriers and their comments for details.
-+ *
-+ * Return: %true if @p->state changes (an actual wakeup was done),
-+ * %false otherwise.
-+ */
-+int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
-+{
-+ guard(preempt)();
-+ int cpu, success = 0;
-+
-+ if (p == current) {
-+ /*
-+ * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
-+ * == smp_processor_id()'. Together this means we can special
-+ * case the whole 'p->on_rq && ttwu_runnable()' case below
-+ * without taking any locks.
-+ *
-+ * In particular:
-+ * - we rely on Program-Order guarantees for all the ordering,
-+ * - we're serialized against set_special_state() by virtue of
-+ * it disabling IRQs (this allows not taking ->pi_lock).
-+ */
-+ if (!ttwu_state_match(p, state, &success))
-+ goto out;
-+
-+ trace_sched_waking(p);
-+ ttwu_do_wakeup(p);
-+ goto out;
-+ }
-+
-+ /*
-+ * If we are going to wake up a thread waiting for CONDITION we
-+ * need to ensure that CONDITION=1 done by the caller can not be
-+ * reordered with p->state check below. This pairs with smp_store_mb()
-+ * in set_current_state() that the waiting thread does.
-+ */
-+ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
-+ smp_mb__after_spinlock();
-+ if (!ttwu_state_match(p, state, &success))
-+ break;
-+
-+ trace_sched_waking(p);
-+
-+ /*
-+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
-+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
-+ * in smp_cond_load_acquire() below.
-+ *
-+ * sched_ttwu_pending() try_to_wake_up()
-+ * STORE p->on_rq = 1 LOAD p->state
-+ * UNLOCK rq->lock
-+ *
-+ * __schedule() (switch to task 'p')
-+ * LOCK rq->lock smp_rmb();
-+ * smp_mb__after_spinlock();
-+ * UNLOCK rq->lock
-+ *
-+ * [task p]
-+ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
-+ *
-+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
-+ * __schedule(). See the comment for smp_mb__after_spinlock().
-+ *
-+ * A similar smp_rmb() lives in __task_needs_rq_lock().
-+ */
-+ smp_rmb();
-+ if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
-+ break;
-+
-+#ifdef CONFIG_SMP
-+ /*
-+ * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
-+ * possible to, falsely, observe p->on_cpu == 0.
-+ *
-+ * One must be running (->on_cpu == 1) in order to remove oneself
-+ * from the runqueue.
-+ *
-+ * __schedule() (switch to task 'p') try_to_wake_up()
-+ * STORE p->on_cpu = 1 LOAD p->on_rq
-+ * UNLOCK rq->lock
-+ *
-+ * __schedule() (put 'p' to sleep)
-+ * LOCK rq->lock smp_rmb();
-+ * smp_mb__after_spinlock();
-+ * STORE p->on_rq = 0 LOAD p->on_cpu
-+ *
-+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
-+ * __schedule(). See the comment for smp_mb__after_spinlock().
-+ *
-+ * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
-+ * schedule()'s deactivate_task() has 'happened' and p will no longer
-+ * care about it's own p->state. See the comment in __schedule().
-+ */
-+ smp_acquire__after_ctrl_dep();
-+
-+ /*
-+ * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
-+ * == 0), which means we need to do an enqueue, change p->state to
-+ * TASK_WAKING such that we can unlock p->pi_lock before doing the
-+ * enqueue, such as ttwu_queue_wakelist().
-+ */
-+ WRITE_ONCE(p->__state, TASK_WAKING);
-+
-+ /*
-+ * If the owning (remote) CPU is still in the middle of schedule() with
-+ * this task as prev, considering queueing p on the remote CPUs wake_list
-+ * which potentially sends an IPI instead of spinning on p->on_cpu to
-+ * let the waker make forward progress. This is safe because IRQs are
-+ * disabled and the IPI will deliver after on_cpu is cleared.
-+ *
-+ * Ensure we load task_cpu(p) after p->on_cpu:
-+ *
-+ * set_task_cpu(p, cpu);
-+ * STORE p->cpu = @cpu
-+ * __schedule() (switch to task 'p')
-+ * LOCK rq->lock
-+ * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
-+ * STORE p->on_cpu = 1 LOAD p->cpu
-+ *
-+ * to ensure we observe the correct CPU on which the task is currently
-+ * scheduling.
-+ */
-+ if (smp_load_acquire(&p->on_cpu) &&
-+ ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
-+ break;
-+
-+ /*
-+ * If the owning (remote) CPU is still in the middle of schedule() with
-+ * this task as prev, wait until it's done referencing the task.
-+ *
-+ * Pairs with the smp_store_release() in finish_task().
-+ *
-+ * This ensures that tasks getting woken will be fully ordered against
-+ * their previous state and preserve Program Order.
-+ */
-+ smp_cond_load_acquire(&p->on_cpu, !VAL);
-+
-+ sched_task_ttwu(p);
-+
-+ if ((wake_flags & WF_CURRENT_CPU) &&
-+ cpumask_test_cpu(smp_processor_id(), p->cpus_ptr))
-+ cpu = smp_processor_id();
-+ else
-+ cpu = select_task_rq(p);
-+
-+ if (cpu != task_cpu(p)) {
-+ if (p->in_iowait) {
-+ delayacct_blkio_end(p);
-+ atomic_dec(&task_rq(p)->nr_iowait);
-+ }
-+
-+ wake_flags |= WF_MIGRATED;
-+ set_task_cpu(p, cpu);
-+ }
-+#else
-+ sched_task_ttwu(p);
-+
-+ cpu = task_cpu(p);
-+#endif /* CONFIG_SMP */
-+
-+ ttwu_queue(p, cpu, wake_flags);
-+ }
-+out:
-+ if (success)
-+ ttwu_stat(p, task_cpu(p), wake_flags);
-+
-+ return success;
-+}
-+
-+static bool __task_needs_rq_lock(struct task_struct *p)
-+{
-+ unsigned int state = READ_ONCE(p->__state);
-+
-+ /*
-+ * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
-+ * the task is blocked. Make sure to check @state since ttwu() can drop
-+ * locks at the end, see ttwu_queue_wakelist().
-+ */
-+ if (state == TASK_RUNNING || state == TASK_WAKING)
-+ return true;
-+
-+ /*
-+ * Ensure we load p->on_rq after p->__state, otherwise it would be
-+ * possible to, falsely, observe p->on_rq == 0.
-+ *
-+ * See try_to_wake_up() for a longer comment.
-+ */
-+ smp_rmb();
-+ if (p->on_rq)
-+ return true;
-+
-+#ifdef CONFIG_SMP
-+ /*
-+ * Ensure the task has finished __schedule() and will not be referenced
-+ * anymore. Again, see try_to_wake_up() for a longer comment.
-+ */
-+ smp_rmb();
-+ smp_cond_load_acquire(&p->on_cpu, !VAL);
-+#endif
-+
-+ return false;
-+}
-+
-+/**
-+ * task_call_func - Invoke a function on task in fixed state
-+ * @p: Process for which the function is to be invoked, can be @current.
-+ * @func: Function to invoke.
-+ * @arg: Argument to function.
-+ *
-+ * Fix the task in it's current state by avoiding wakeups and or rq operations
-+ * and call @func(@arg) on it. This function can use ->on_rq and task_curr()
-+ * to work out what the state is, if required. Given that @func can be invoked
-+ * with a runqueue lock held, it had better be quite lightweight.
-+ *
-+ * Returns:
-+ * Whatever @func returns
-+ */
-+int task_call_func(struct task_struct *p, task_call_f func, void *arg)
-+{
-+ struct rq *rq = NULL;
-+ struct rq_flags rf;
-+ int ret;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
-+
-+ if (__task_needs_rq_lock(p))
-+ rq = __task_rq_lock(p, &rf);
-+
-+ /*
-+ * At this point the task is pinned; either:
-+ * - blocked and we're holding off wakeups (pi->lock)
-+ * - woken, and we're holding off enqueue (rq->lock)
-+ * - queued, and we're holding off schedule (rq->lock)
-+ * - running, and we're holding off de-schedule (rq->lock)
-+ *
-+ * The called function (@func) can use: task_curr(), p->on_rq and
-+ * p->__state to differentiate between these states.
-+ */
-+ ret = func(p, arg);
-+
-+ if (rq)
-+ __task_rq_unlock(rq, &rf);
-+
-+ raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
-+ return ret;
-+}
-+
-+/**
-+ * cpu_curr_snapshot - Return a snapshot of the currently running task
-+ * @cpu: The CPU on which to snapshot the task.
-+ *
-+ * Returns the task_struct pointer of the task "currently" running on
-+ * the specified CPU. If the same task is running on that CPU throughout,
-+ * the return value will be a pointer to that task's task_struct structure.
-+ * If the CPU did any context switches even vaguely concurrently with the
-+ * execution of this function, the return value will be a pointer to the
-+ * task_struct structure of a randomly chosen task that was running on
-+ * that CPU somewhere around the time that this function was executing.
-+ *
-+ * If the specified CPU was offline, the return value is whatever it
-+ * is, perhaps a pointer to the task_struct structure of that CPU's idle
-+ * task, but there is no guarantee. Callers wishing a useful return
-+ * value must take some action to ensure that the specified CPU remains
-+ * online throughout.
-+ *
-+ * This function executes full memory barriers before and after fetching
-+ * the pointer, which permits the caller to confine this function's fetch
-+ * with respect to the caller's accesses to other shared variables.
-+ */
-+struct task_struct *cpu_curr_snapshot(int cpu)
-+{
-+ struct task_struct *t;
-+
-+ smp_mb(); /* Pairing determined by caller's synchronization design. */
-+ t = rcu_dereference(cpu_curr(cpu));
-+ smp_mb(); /* Pairing determined by caller's synchronization design. */
-+ return t;
-+}
-+
-+/**
-+ * wake_up_process - Wake up a specific process
-+ * @p: The process to be woken up.
-+ *
-+ * Attempt to wake up the nominated process and move it to the set of runnable
-+ * processes.
-+ *
-+ * Return: 1 if the process was woken up, 0 if it was already running.
-+ *
-+ * This function executes a full memory barrier before accessing the task state.
-+ */
-+int wake_up_process(struct task_struct *p)
-+{
-+ return try_to_wake_up(p, TASK_NORMAL, 0);
-+}
-+EXPORT_SYMBOL(wake_up_process);
-+
-+int wake_up_state(struct task_struct *p, unsigned int state)
-+{
-+ return try_to_wake_up(p, state, 0);
-+}
-+
-+/*
-+ * Perform scheduler related setup for a newly forked process p.
-+ * p is forked by current.
-+ *
-+ * __sched_fork() is basic setup used by init_idle() too:
-+ */
-+static inline void __sched_fork(unsigned long clone_flags, struct task_struct *p)
-+{
-+ p->on_rq = 0;
-+ p->on_cpu = 0;
-+ p->utime = 0;
-+ p->stime = 0;
-+ p->sched_time = 0;
-+
-+#ifdef CONFIG_SCHEDSTATS
-+ /* Even if schedstat is disabled, there should not be garbage */
-+ memset(&p->stats, 0, sizeof(p->stats));
-+#endif
-+
-+#ifdef CONFIG_PREEMPT_NOTIFIERS
-+ INIT_HLIST_HEAD(&p->preempt_notifiers);
-+#endif
-+
-+#ifdef CONFIG_COMPACTION
-+ p->capture_control = NULL;
-+#endif
-+#ifdef CONFIG_SMP
-+ p->wake_entry.u_flags = CSD_TYPE_TTWU;
-+#endif
-+ init_sched_mm_cid(p);
-+}
-+
-+/*
-+ * fork()/clone()-time setup:
-+ */
-+int sched_fork(unsigned long clone_flags, struct task_struct *p)
-+{
-+ __sched_fork(clone_flags, p);
-+ /*
-+ * We mark the process as NEW here. This guarantees that
-+ * nobody will actually run it, and a signal or other external
-+ * event cannot wake it up and insert it on the runqueue either.
-+ */
-+ p->__state = TASK_NEW;
-+
-+ /*
-+ * Make sure we do not leak PI boosting priority to the child.
-+ */
-+ p->prio = current->normal_prio;
-+
-+ /*
-+ * Revert to default priority/policy on fork if requested.
-+ */
-+ if (unlikely(p->sched_reset_on_fork)) {
-+ if (task_has_rt_policy(p)) {
-+ p->policy = SCHED_NORMAL;
-+ p->static_prio = NICE_TO_PRIO(0);
-+ p->rt_priority = 0;
-+ } else if (PRIO_TO_NICE(p->static_prio) < 0)
-+ p->static_prio = NICE_TO_PRIO(0);
-+
-+ p->prio = p->normal_prio = p->static_prio;
-+
-+ /*
-+ * We don't need the reset flag anymore after the fork. It has
-+ * fulfilled its duty:
-+ */
-+ p->sched_reset_on_fork = 0;
-+ }
-+
-+#ifdef CONFIG_SCHED_INFO
-+ if (unlikely(sched_info_on()))
-+ memset(&p->sched_info, 0, sizeof(p->sched_info));
-+#endif
-+ init_task_preempt_count(p);
-+
-+ return 0;
-+}
-+
-+void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+
-+ /*
-+ * Because we're not yet on the pid-hash, p->pi_lock isn't strictly
-+ * required yet, but lockdep gets upset if rules are violated.
-+ */
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+ /*
-+ * Share the timeslice between parent and child, thus the
-+ * total amount of pending timeslices in the system doesn't change,
-+ * resulting in more scheduling fairness.
-+ */
-+ rq = this_rq();
-+ raw_spin_lock(&rq->lock);
-+
-+ rq->curr->time_slice /= 2;
-+ p->time_slice = rq->curr->time_slice;
-+#ifdef CONFIG_SCHED_HRTICK
-+ hrtick_start(rq, rq->curr->time_slice);
-+#endif
-+
-+ if (p->time_slice < RESCHED_NS) {
-+ p->time_slice = sysctl_sched_base_slice;
-+ resched_curr(rq);
-+ }
-+ sched_task_fork(p, rq);
-+ raw_spin_unlock(&rq->lock);
-+
-+ rseq_migrate(p);
-+ /*
-+ * We're setting the CPU for the first time, we don't migrate,
-+ * so use __set_task_cpu().
-+ */
-+ __set_task_cpu(p, smp_processor_id());
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+}
-+
-+void sched_post_fork(struct task_struct *p)
-+{
-+}
-+
-+#ifdef CONFIG_SCHEDSTATS
-+
-+DEFINE_STATIC_KEY_FALSE(sched_schedstats);
-+
-+static void set_schedstats(bool enabled)
-+{
-+ if (enabled)
-+ static_branch_enable(&sched_schedstats);
-+ else
-+ static_branch_disable(&sched_schedstats);
-+}
-+
-+void force_schedstat_enabled(void)
-+{
-+ if (!schedstat_enabled()) {
-+ pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
-+ static_branch_enable(&sched_schedstats);
-+ }
-+}
-+
-+static int __init setup_schedstats(char *str)
-+{
-+ int ret = 0;
-+ if (!str)
-+ goto out;
-+
-+ if (!strcmp(str, "enable")) {
-+ set_schedstats(true);
-+ ret = 1;
-+ } else if (!strcmp(str, "disable")) {
-+ set_schedstats(false);
-+ ret = 1;
-+ }
-+out:
-+ if (!ret)
-+ pr_warn("Unable to parse schedstats=\n");
-+
-+ return ret;
-+}
-+__setup("schedstats=", setup_schedstats);
-+
-+#ifdef CONFIG_PROC_SYSCTL
-+static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
-+ size_t *lenp, loff_t *ppos)
-+{
-+ struct ctl_table t;
-+ int err;
-+ int state = static_branch_likely(&sched_schedstats);
-+
-+ if (write && !capable(CAP_SYS_ADMIN))
-+ return -EPERM;
-+
-+ t = *table;
-+ t.data = &state;
-+ err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
-+ if (err < 0)
-+ return err;
-+ if (write)
-+ set_schedstats(state);
-+ return err;
-+}
-+
-+static struct ctl_table sched_core_sysctls[] = {
-+ {
-+ .procname = "sched_schedstats",
-+ .data = NULL,
-+ .maxlen = sizeof(unsigned int),
-+ .mode = 0644,
-+ .proc_handler = sysctl_schedstats,
-+ .extra1 = SYSCTL_ZERO,
-+ .extra2 = SYSCTL_ONE,
-+ },
-+};
-+static int __init sched_core_sysctl_init(void)
-+{
-+ register_sysctl_init("kernel", sched_core_sysctls);
-+ return 0;
-+}
-+late_initcall(sched_core_sysctl_init);
-+#endif /* CONFIG_PROC_SYSCTL */
-+#endif /* CONFIG_SCHEDSTATS */
-+
-+/*
-+ * wake_up_new_task - wake up a newly created task for the first time.
-+ *
-+ * This function will do some initial scheduler statistics housekeeping
-+ * that must be done for every newly created context, then puts the task
-+ * on the runqueue and wakes it.
-+ */
-+void wake_up_new_task(struct task_struct *p)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+ WRITE_ONCE(p->__state, TASK_RUNNING);
-+ rq = cpu_rq(select_task_rq(p));
-+#ifdef CONFIG_SMP
-+ rseq_migrate(p);
-+ /*
-+ * Fork balancing, do it here and not earlier because:
-+ * - cpus_ptr can change in the fork path
-+ * - any previously selected CPU might disappear through hotplug
-+ *
-+ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
-+ * as we're not fully set-up yet.
-+ */
-+ __set_task_cpu(p, cpu_of(rq));
-+#endif
-+
-+ raw_spin_lock(&rq->lock);
-+ update_rq_clock(rq);
-+
-+ activate_task(p, rq);
-+ trace_sched_wakeup_new(p);
-+ wakeup_preempt(rq);
-+
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+}
-+
-+#ifdef CONFIG_PREEMPT_NOTIFIERS
-+
-+static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
-+
-+void preempt_notifier_inc(void)
-+{
-+ static_branch_inc(&preempt_notifier_key);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_inc);
-+
-+void preempt_notifier_dec(void)
-+{
-+ static_branch_dec(&preempt_notifier_key);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_dec);
-+
-+/**
-+ * preempt_notifier_register - tell me when current is being preempted & rescheduled
-+ * @notifier: notifier struct to register
-+ */
-+void preempt_notifier_register(struct preempt_notifier *notifier)
-+{
-+ if (!static_branch_unlikely(&preempt_notifier_key))
-+ WARN(1, "registering preempt_notifier while notifiers disabled\n");
-+
-+ hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_register);
-+
-+/**
-+ * preempt_notifier_unregister - no longer interested in preemption notifications
-+ * @notifier: notifier struct to unregister
-+ *
-+ * This is *not* safe to call from within a preemption notifier.
-+ */
-+void preempt_notifier_unregister(struct preempt_notifier *notifier)
-+{
-+ hlist_del(¬ifier->link);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
-+
-+static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
-+{
-+ struct preempt_notifier *notifier;
-+
-+ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
-+ notifier->ops->sched_in(notifier, raw_smp_processor_id());
-+}
-+
-+static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
-+{
-+ if (static_branch_unlikely(&preempt_notifier_key))
-+ __fire_sched_in_preempt_notifiers(curr);
-+}
-+
-+static void
-+__fire_sched_out_preempt_notifiers(struct task_struct *curr,
-+ struct task_struct *next)
-+{
-+ struct preempt_notifier *notifier;
-+
-+ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
-+ notifier->ops->sched_out(notifier, next);
-+}
-+
-+static __always_inline void
-+fire_sched_out_preempt_notifiers(struct task_struct *curr,
-+ struct task_struct *next)
-+{
-+ if (static_branch_unlikely(&preempt_notifier_key))
-+ __fire_sched_out_preempt_notifiers(curr, next);
-+}
-+
-+#else /* !CONFIG_PREEMPT_NOTIFIERS */
-+
-+static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
-+{
-+}
-+
-+static inline void
-+fire_sched_out_preempt_notifiers(struct task_struct *curr,
-+ struct task_struct *next)
-+{
-+}
-+
-+#endif /* CONFIG_PREEMPT_NOTIFIERS */
-+
-+static inline void prepare_task(struct task_struct *next)
-+{
-+ /*
-+ * Claim the task as running, we do this before switching to it
-+ * such that any running task will have this set.
-+ *
-+ * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
-+ * its ordering comment.
-+ */
-+ WRITE_ONCE(next->on_cpu, 1);
-+}
-+
-+static inline void finish_task(struct task_struct *prev)
-+{
-+#ifdef CONFIG_SMP
-+ /*
-+ * This must be the very last reference to @prev from this CPU. After
-+ * p->on_cpu is cleared, the task can be moved to a different CPU. We
-+ * must ensure this doesn't happen until the switch is completely
-+ * finished.
-+ *
-+ * In particular, the load of prev->state in finish_task_switch() must
-+ * happen before this.
-+ *
-+ * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
-+ */
-+ smp_store_release(&prev->on_cpu, 0);
-+#else
-+ prev->on_cpu = 0;
-+#endif
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
-+{
-+ void (*func)(struct rq *rq);
-+ struct balance_callback *next;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ while (head) {
-+ func = (void (*)(struct rq *))head->func;
-+ next = head->next;
-+ head->next = NULL;
-+ head = next;
-+
-+ func(rq);
-+ }
-+}
-+
-+static void balance_push(struct rq *rq);
-+
-+/*
-+ * balance_push_callback is a right abuse of the callback interface and plays
-+ * by significantly different rules.
-+ *
-+ * Where the normal balance_callback's purpose is to be ran in the same context
-+ * that queued it (only later, when it's safe to drop rq->lock again),
-+ * balance_push_callback is specifically targeted at __schedule().
-+ *
-+ * This abuse is tolerated because it places all the unlikely/odd cases behind
-+ * a single test, namely: rq->balance_callback == NULL.
-+ */
-+struct balance_callback balance_push_callback = {
-+ .next = NULL,
-+ .func = balance_push,
-+};
-+
-+static inline struct balance_callback *
-+__splice_balance_callbacks(struct rq *rq, bool split)
-+{
-+ struct balance_callback *head = rq->balance_callback;
-+
-+ if (likely(!head))
-+ return NULL;
-+
-+ lockdep_assert_rq_held(rq);
-+ /*
-+ * Must not take balance_push_callback off the list when
-+ * splice_balance_callbacks() and balance_callbacks() are not
-+ * in the same rq->lock section.
-+ *
-+ * In that case it would be possible for __schedule() to interleave
-+ * and observe the list empty.
-+ */
-+ if (split && head == &balance_push_callback)
-+ head = NULL;
-+ else
-+ rq->balance_callback = NULL;
-+
-+ return head;
-+}
-+
-+static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
-+{
-+ return __splice_balance_callbacks(rq, true);
-+}
-+
-+static void __balance_callbacks(struct rq *rq)
-+{
-+ do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
-+}
-+
-+static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
-+{
-+ unsigned long flags;
-+
-+ if (unlikely(head)) {
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ do_balance_callbacks(rq, head);
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+ }
-+}
-+
-+#else
-+
-+static inline void __balance_callbacks(struct rq *rq)
-+{
-+}
-+
-+static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
-+{
-+ return NULL;
-+}
-+
-+static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
-+{
-+}
-+
-+#endif
-+
-+static inline void
-+prepare_lock_switch(struct rq *rq, struct task_struct *next)
-+{
-+ /*
-+ * Since the runqueue lock will be released by the next
-+ * task (which is an invalid locking op but in the case
-+ * of the scheduler it's an obvious special-case), so we
-+ * do an early lockdep release here:
-+ */
-+ spin_release(&rq->lock.dep_map, _THIS_IP_);
-+#ifdef CONFIG_DEBUG_SPINLOCK
-+ /* this is a valid case when another task releases the spinlock */
-+ rq->lock.owner = next;
-+#endif
-+}
-+
-+static inline void finish_lock_switch(struct rq *rq)
-+{
-+ /*
-+ * If we are tracking spinlock dependencies then we have to
-+ * fix up the runqueue lock - which gets 'carried over' from
-+ * prev into current:
-+ */
-+ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
-+ __balance_callbacks(rq);
-+ raw_spin_unlock_irq(&rq->lock);
-+}
-+
-+/*
-+ * NOP if the arch has not defined these:
-+ */
-+
-+#ifndef prepare_arch_switch
-+# define prepare_arch_switch(next) do { } while (0)
-+#endif
-+
-+#ifndef finish_arch_post_lock_switch
-+# define finish_arch_post_lock_switch() do { } while (0)
-+#endif
-+
-+static inline void kmap_local_sched_out(void)
-+{
-+#ifdef CONFIG_KMAP_LOCAL
-+ if (unlikely(current->kmap_ctrl.idx))
-+ __kmap_local_sched_out();
-+#endif
-+}
-+
-+static inline void kmap_local_sched_in(void)
-+{
-+#ifdef CONFIG_KMAP_LOCAL
-+ if (unlikely(current->kmap_ctrl.idx))
-+ __kmap_local_sched_in();
-+#endif
-+}
-+
-+/**
-+ * prepare_task_switch - prepare to switch tasks
-+ * @rq: the runqueue preparing to switch
-+ * @next: the task we are going to switch to.
-+ *
-+ * This is called with the rq lock held and interrupts off. It must
-+ * be paired with a subsequent finish_task_switch after the context
-+ * switch.
-+ *
-+ * prepare_task_switch sets up locking and calls architecture specific
-+ * hooks.
-+ */
-+static inline void
-+prepare_task_switch(struct rq *rq, struct task_struct *prev,
-+ struct task_struct *next)
-+{
-+ kcov_prepare_switch(prev);
-+ sched_info_switch(rq, prev, next);
-+ perf_event_task_sched_out(prev, next);
-+ rseq_preempt(prev);
-+ fire_sched_out_preempt_notifiers(prev, next);
-+ kmap_local_sched_out();
-+ prepare_task(next);
-+ prepare_arch_switch(next);
-+}
-+
-+/**
-+ * finish_task_switch - clean up after a task-switch
-+ * @rq: runqueue associated with task-switch
-+ * @prev: the thread we just switched away from.
-+ *
-+ * finish_task_switch must be called after the context switch, paired
-+ * with a prepare_task_switch call before the context switch.
-+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
-+ * and do any other architecture-specific cleanup actions.
-+ *
-+ * Note that we may have delayed dropping an mm in context_switch(). If
-+ * so, we finish that here outside of the runqueue lock. (Doing it
-+ * with the lock held can cause deadlocks; see schedule() for
-+ * details.)
-+ *
-+ * The context switch have flipped the stack from under us and restored the
-+ * local variables which were saved when this task called schedule() in the
-+ * past. prev == current is still correct but we need to recalculate this_rq
-+ * because prev may have moved to another CPU.
-+ */
-+static struct rq *finish_task_switch(struct task_struct *prev)
-+ __releases(rq->lock)
-+{
-+ struct rq *rq = this_rq();
-+ struct mm_struct *mm = rq->prev_mm;
-+ unsigned int prev_state;
-+
-+ /*
-+ * The previous task will have left us with a preempt_count of 2
-+ * because it left us after:
-+ *
-+ * schedule()
-+ * preempt_disable(); // 1
-+ * __schedule()
-+ * raw_spin_lock_irq(&rq->lock) // 2
-+ *
-+ * Also, see FORK_PREEMPT_COUNT.
-+ */
-+ if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
-+ "corrupted preempt_count: %s/%d/0x%x\n",
-+ current->comm, current->pid, preempt_count()))
-+ preempt_count_set(FORK_PREEMPT_COUNT);
-+
-+ rq->prev_mm = NULL;
-+
-+ /*
-+ * A task struct has one reference for the use as "current".
-+ * If a task dies, then it sets TASK_DEAD in tsk->state and calls
-+ * schedule one last time. The schedule call will never return, and
-+ * the scheduled task must drop that reference.
-+ *
-+ * We must observe prev->state before clearing prev->on_cpu (in
-+ * finish_task), otherwise a concurrent wakeup can get prev
-+ * running on another CPU and we could rave with its RUNNING -> DEAD
-+ * transition, resulting in a double drop.
-+ */
-+ prev_state = READ_ONCE(prev->__state);
-+ vtime_task_switch(prev);
-+ perf_event_task_sched_in(prev, current);
-+ finish_task(prev);
-+ tick_nohz_task_switch();
-+ finish_lock_switch(rq);
-+ finish_arch_post_lock_switch();
-+ kcov_finish_switch(current);
-+ /*
-+ * kmap_local_sched_out() is invoked with rq::lock held and
-+ * interrupts disabled. There is no requirement for that, but the
-+ * sched out code does not have an interrupt enabled section.
-+ * Restoring the maps on sched in does not require interrupts being
-+ * disabled either.
-+ */
-+ kmap_local_sched_in();
-+
-+ fire_sched_in_preempt_notifiers(current);
-+ /*
-+ * When switching through a kernel thread, the loop in
-+ * membarrier_{private,global}_expedited() may have observed that
-+ * kernel thread and not issued an IPI. It is therefore possible to
-+ * schedule between user->kernel->user threads without passing though
-+ * switch_mm(). Membarrier requires a barrier after storing to
-+ * rq->curr, before returning to userspace, so provide them here:
-+ *
-+ * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
-+ * provided by mmdrop(),
-+ * - a sync_core for SYNC_CORE.
-+ */
-+ if (mm) {
-+ membarrier_mm_sync_core_before_usermode(mm);
-+ mmdrop_sched(mm);
-+ }
-+ if (unlikely(prev_state == TASK_DEAD)) {
-+ /* Task is done with its stack. */
-+ put_task_stack(prev);
-+
-+ put_task_struct_rcu_user(prev);
-+ }
-+
-+ return rq;
-+}
-+
-+/**
-+ * schedule_tail - first thing a freshly forked thread must call.
-+ * @prev: the thread we just switched away from.
-+ */
-+asmlinkage __visible void schedule_tail(struct task_struct *prev)
-+ __releases(rq->lock)
-+{
-+ /*
-+ * New tasks start with FORK_PREEMPT_COUNT, see there and
-+ * finish_task_switch() for details.
-+ *
-+ * finish_task_switch() will drop rq->lock() and lower preempt_count
-+ * and the preempt_enable() will end up enabling preemption (on
-+ * PREEMPT_COUNT kernels).
-+ */
-+
-+ finish_task_switch(prev);
-+ preempt_enable();
-+
-+ if (current->set_child_tid)
-+ put_user(task_pid_vnr(current), current->set_child_tid);
-+
-+ calculate_sigpending();
-+}
-+
-+/*
-+ * context_switch - switch to the new MM and the new thread's register state.
-+ */
-+static __always_inline struct rq *
-+context_switch(struct rq *rq, struct task_struct *prev,
-+ struct task_struct *next)
-+{
-+ prepare_task_switch(rq, prev, next);
-+
-+ /*
-+ * For paravirt, this is coupled with an exit in switch_to to
-+ * combine the page table reload and the switch backend into
-+ * one hypercall.
-+ */
-+ arch_start_context_switch(prev);
-+
-+ /*
-+ * kernel -> kernel lazy + transfer active
-+ * user -> kernel lazy + mmgrab() active
-+ *
-+ * kernel -> user switch + mmdrop() active
-+ * user -> user switch
-+ *
-+ * switch_mm_cid() needs to be updated if the barriers provided
-+ * by context_switch() are modified.
-+ */
-+ if (!next->mm) { // to kernel
-+ enter_lazy_tlb(prev->active_mm, next);
-+
-+ next->active_mm = prev->active_mm;
-+ if (prev->mm) // from user
-+ mmgrab(prev->active_mm);
-+ else
-+ prev->active_mm = NULL;
-+ } else { // to user
-+ membarrier_switch_mm(rq, prev->active_mm, next->mm);
-+ /*
-+ * sys_membarrier() requires an smp_mb() between setting
-+ * rq->curr / membarrier_switch_mm() and returning to userspace.
-+ *
-+ * The below provides this either through switch_mm(), or in
-+ * case 'prev->active_mm == next->mm' through
-+ * finish_task_switch()'s mmdrop().
-+ */
-+ switch_mm_irqs_off(prev->active_mm, next->mm, next);
-+ lru_gen_use_mm(next->mm);
-+
-+ if (!prev->mm) { // from kernel
-+ /* will mmdrop() in finish_task_switch(). */
-+ rq->prev_mm = prev->active_mm;
-+ prev->active_mm = NULL;
-+ }
-+ }
-+
-+ /* switch_mm_cid() requires the memory barriers above. */
-+ switch_mm_cid(rq, prev, next);
-+
-+ prepare_lock_switch(rq, next);
-+
-+ /* Here we just switch the register state and the stack. */
-+ switch_to(prev, next, prev);
-+ barrier();
-+
-+ return finish_task_switch(prev);
-+}
-+
-+/*
-+ * nr_running, nr_uninterruptible and nr_context_switches:
-+ *
-+ * externally visible scheduler statistics: current number of runnable
-+ * threads, total number of context switches performed since bootup.
-+ */
-+unsigned int nr_running(void)
-+{
-+ unsigned int i, sum = 0;
-+
-+ for_each_online_cpu(i)
-+ sum += cpu_rq(i)->nr_running;
-+
-+ return sum;
-+}
-+
-+/*
-+ * Check if only the current task is running on the CPU.
-+ *
-+ * Caution: this function does not check that the caller has disabled
-+ * preemption, thus the result might have a time-of-check-to-time-of-use
-+ * race. The caller is responsible to use it correctly, for example:
-+ *
-+ * - from a non-preemptible section (of course)
-+ *
-+ * - from a thread that is bound to a single CPU
-+ *
-+ * - in a loop with very short iterations (e.g. a polling loop)
-+ */
-+bool single_task_running(void)
-+{
-+ return raw_rq()->nr_running == 1;
-+}
-+EXPORT_SYMBOL(single_task_running);
-+
-+unsigned long long nr_context_switches_cpu(int cpu)
-+{
-+ return cpu_rq(cpu)->nr_switches;
-+}
-+
-+unsigned long long nr_context_switches(void)
-+{
-+ int i;
-+ unsigned long long sum = 0;
-+
-+ for_each_possible_cpu(i)
-+ sum += cpu_rq(i)->nr_switches;
-+
-+ return sum;
-+}
-+
-+/*
-+ * Consumers of these two interfaces, like for example the cpuidle menu
-+ * governor, are using nonsensical data. Preferring shallow idle state selection
-+ * for a CPU that has IO-wait which might not even end up running the task when
-+ * it does become runnable.
-+ */
-+
-+unsigned int nr_iowait_cpu(int cpu)
-+{
-+ return atomic_read(&cpu_rq(cpu)->nr_iowait);
-+}
-+
-+/*
-+ * IO-wait accounting, and how it's mostly bollocks (on SMP).
-+ *
-+ * The idea behind IO-wait account is to account the idle time that we could
-+ * have spend running if it were not for IO. That is, if we were to improve the
-+ * storage performance, we'd have a proportional reduction in IO-wait time.
-+ *
-+ * This all works nicely on UP, where, when a task blocks on IO, we account
-+ * idle time as IO-wait, because if the storage were faster, it could've been
-+ * running and we'd not be idle.
-+ *
-+ * This has been extended to SMP, by doing the same for each CPU. This however
-+ * is broken.
-+ *
-+ * Imagine for instance the case where two tasks block on one CPU, only the one
-+ * CPU will have IO-wait accounted, while the other has regular idle. Even
-+ * though, if the storage were faster, both could've ran at the same time,
-+ * utilising both CPUs.
-+ *
-+ * This means, that when looking globally, the current IO-wait accounting on
-+ * SMP is a lower bound, by reason of under accounting.
-+ *
-+ * Worse, since the numbers are provided per CPU, they are sometimes
-+ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
-+ * associated with any one particular CPU, it can wake to another CPU than it
-+ * blocked on. This means the per CPU IO-wait number is meaningless.
-+ *
-+ * Task CPU affinities can make all that even more 'interesting'.
-+ */
-+
-+unsigned int nr_iowait(void)
-+{
-+ unsigned int i, sum = 0;
-+
-+ for_each_possible_cpu(i)
-+ sum += nr_iowait_cpu(i);
-+
-+ return sum;
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+/*
-+ * sched_exec - execve() is a valuable balancing opportunity, because at
-+ * this point the task has the smallest effective memory and cache
-+ * footprint.
-+ */
-+void sched_exec(void)
-+{
-+}
-+
-+#endif
-+
-+DEFINE_PER_CPU(struct kernel_stat, kstat);
-+DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
-+
-+EXPORT_PER_CPU_SYMBOL(kstat);
-+EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
-+
-+static inline void update_curr(struct rq *rq, struct task_struct *p)
-+{
-+ s64 ns = rq->clock_task - p->last_ran;
-+
-+ p->sched_time += ns;
-+ cgroup_account_cputime(p, ns);
-+ account_group_exec_runtime(p, ns);
-+
-+ p->time_slice -= ns;
-+ p->last_ran = rq->clock_task;
-+}
-+
-+/*
-+ * Return accounted runtime for the task.
-+ * Return separately the current's pending runtime that have not been
-+ * accounted yet.
-+ */
-+unsigned long long task_sched_runtime(struct task_struct *p)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+ u64 ns;
-+
-+#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
-+ /*
-+ * 64-bit doesn't need locks to atomically read a 64-bit value.
-+ * So we have a optimization chance when the task's delta_exec is 0.
-+ * Reading ->on_cpu is racy, but this is ok.
-+ *
-+ * If we race with it leaving CPU, we'll take a lock. So we're correct.
-+ * If we race with it entering CPU, unaccounted time is 0. This is
-+ * indistinguishable from the read occurring a few cycles earlier.
-+ * If we see ->on_cpu without ->on_rq, the task is leaving, and has
-+ * been accounted, so we're correct here as well.
-+ */
-+ if (!p->on_cpu || !task_on_rq_queued(p))
-+ return tsk_seruntime(p);
-+#endif
-+
-+ rq = task_access_lock_irqsave(p, &lock, &flags);
-+ /*
-+ * Must be ->curr _and_ ->on_rq. If dequeued, we would
-+ * project cycles that may never be accounted to this
-+ * thread, breaking clock_gettime().
-+ */
-+ if (p == rq->curr && task_on_rq_queued(p)) {
-+ update_rq_clock(rq);
-+ update_curr(rq, p);
-+ }
-+ ns = tsk_seruntime(p);
-+ task_access_unlock_irqrestore(p, lock, &flags);
-+
-+ return ns;
-+}
-+
-+/* This manages tasks that have run out of timeslice during a scheduler_tick */
-+static inline void scheduler_task_tick(struct rq *rq)
-+{
-+ struct task_struct *p = rq->curr;
-+
-+ if (is_idle_task(p))
-+ return;
-+
-+ update_curr(rq, p);
-+ cpufreq_update_util(rq, 0);
-+
-+ /*
-+ * Tasks have less than RESCHED_NS of time slice left they will be
-+ * rescheduled.
-+ */
-+ if (p->time_slice >= RESCHED_NS)
-+ return;
-+ set_tsk_need_resched(p);
-+ set_preempt_need_resched();
-+}
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+static u64 cpu_resched_latency(struct rq *rq)
-+{
-+ int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
-+ u64 resched_latency, now = rq_clock(rq);
-+ static bool warned_once;
-+
-+ if (sysctl_resched_latency_warn_once && warned_once)
-+ return 0;
-+
-+ if (!need_resched() || !latency_warn_ms)
-+ return 0;
-+
-+ if (system_state == SYSTEM_BOOTING)
-+ return 0;
-+
-+ if (!rq->last_seen_need_resched_ns) {
-+ rq->last_seen_need_resched_ns = now;
-+ rq->ticks_without_resched = 0;
-+ return 0;
-+ }
-+
-+ rq->ticks_without_resched++;
-+ resched_latency = now - rq->last_seen_need_resched_ns;
-+ if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC)
-+ return 0;
-+
-+ warned_once = true;
-+
-+ return resched_latency;
-+}
-+
-+static int __init setup_resched_latency_warn_ms(char *str)
-+{
-+ long val;
-+
-+ if ((kstrtol(str, 0, &val))) {
-+ pr_warn("Unable to set resched_latency_warn_ms\n");
-+ return 1;
-+ }
-+
-+ sysctl_resched_latency_warn_ms = val;
-+ return 1;
-+}
-+__setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
-+#else
-+static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
-+#endif /* CONFIG_SCHED_DEBUG */
-+
-+/*
-+ * This function gets called by the timer code, with HZ frequency.
-+ * We call it with interrupts disabled.
-+ */
-+void sched_tick(void)
-+{
-+ int cpu __maybe_unused = smp_processor_id();
-+ struct rq *rq = cpu_rq(cpu);
-+ struct task_struct *curr = rq->curr;
-+ u64 resched_latency;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
-+ arch_scale_freq_tick();
-+
-+ sched_clock_tick();
-+
-+ raw_spin_lock(&rq->lock);
-+ update_rq_clock(rq);
-+
-+ scheduler_task_tick(rq);
-+ if (sched_feat(LATENCY_WARN))
-+ resched_latency = cpu_resched_latency(rq);
-+ calc_global_load_tick(rq);
-+
-+ task_tick_mm_cid(rq, rq->curr);
-+
-+ raw_spin_unlock(&rq->lock);
-+
-+ if (sched_feat(LATENCY_WARN) && resched_latency)
-+ resched_latency_warn(cpu, resched_latency);
-+
-+ perf_event_task_tick();
-+
-+ if (curr->flags & PF_WQ_WORKER)
-+ wq_worker_tick(curr);
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+static int active_balance_cpu_stop(void *data)
-+{
-+ struct balance_arg *arg = data;
-+ struct task_struct *p = arg->task;
-+ struct rq *rq = this_rq();
-+ unsigned long flags;
-+ cpumask_t tmp;
-+
-+ local_irq_save(flags);
-+
-+ raw_spin_lock(&p->pi_lock);
-+ raw_spin_lock(&rq->lock);
-+
-+ arg->active = 0;
-+
-+ if (task_on_rq_queued(p) && task_rq(p) == rq &&
-+ cpumask_and(&tmp, p->cpus_ptr, arg->cpumask) &&
-+ !is_migration_disabled(p)) {
-+ int dcpu = __best_mask_cpu(&tmp, per_cpu(sched_cpu_llc_mask, cpu_of(rq)));
-+ rq = move_queued_task(rq, p, dcpu);
-+ }
-+
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+
-+ return 0;
-+}
-+
-+/* trigger_active_balance - for @cpu/@rq */
-+static inline int
-+trigger_active_balance(struct rq *src_rq, struct rq *rq, struct balance_arg *arg)
-+{
-+ unsigned long flags;
-+ struct task_struct *p;
-+ int res;
-+
-+ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
-+ return 0;
-+
-+ res = (1 == rq->nr_running) && \
-+ !is_migration_disabled((p = sched_rq_first_task(rq))) && \
-+ cpumask_intersects(p->cpus_ptr, arg->cpumask) && \
-+ !arg->active;
-+ if (res) {
-+ arg->task = p;
-+
-+ arg->active = 1;
-+ }
-+
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+ if (res) {
-+ preempt_disable();
-+ raw_spin_unlock(&src_rq->lock);
-+
-+ stop_one_cpu_nowait(cpu_of(rq), active_balance_cpu_stop,
-+ arg, &rq->active_balance_work);
-+
-+ preempt_enable();
-+ raw_spin_lock(&src_rq->lock);
-+ }
-+
-+ return res;
-+}
-+
-+#ifdef CONFIG_SCHED_SMT
-+/*
-+ * sg_balance - slibing group balance check for run queue @rq
-+ */
-+static inline void sg_balance(struct rq *rq)
-+{
-+ cpumask_t chk;
-+
-+ if (cpumask_andnot(&chk, cpu_active_mask, sched_idle_mask) &&
-+ cpumask_andnot(&chk, &chk, &sched_rq_pending_mask)) {
-+ int i, cpu = cpu_of(rq);
-+
-+ for_each_cpu_wrap(i, &chk, cpu) {
-+ if (cpumask_subset(cpu_smt_mask(i), &chk)) {
-+ struct rq *target_rq = cpu_rq(i);
-+ if (trigger_active_balance(rq, target_rq, &target_rq->sg_balance_arg))
-+ return;
-+ }
-+ }
-+ }
-+}
-+
-+static DEFINE_PER_CPU(struct balance_callback, sg_balance_head) = {
-+ .func = sg_balance,
-+};
-+#endif /* CONFIG_SCHED_SMT */
-+
-+#endif /* CONFIG_SMP */
-+
-+#ifdef CONFIG_NO_HZ_FULL
-+
-+struct tick_work {
-+ int cpu;
-+ atomic_t state;
-+ struct delayed_work work;
-+};
-+/* Values for ->state, see diagram below. */
-+#define TICK_SCHED_REMOTE_OFFLINE 0
-+#define TICK_SCHED_REMOTE_OFFLINING 1
-+#define TICK_SCHED_REMOTE_RUNNING 2
-+
-+/*
-+ * State diagram for ->state:
-+ *
-+ *
-+ * TICK_SCHED_REMOTE_OFFLINE
-+ * | ^
-+ * | |
-+ * | | sched_tick_remote()
-+ * | |
-+ * | |
-+ * +--TICK_SCHED_REMOTE_OFFLINING
-+ * | ^
-+ * | |
-+ * sched_tick_start() | | sched_tick_stop()
-+ * | |
-+ * V |
-+ * TICK_SCHED_REMOTE_RUNNING
-+ *
-+ *
-+ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
-+ * and sched_tick_start() are happy to leave the state in RUNNING.
-+ */
-+
-+static struct tick_work __percpu *tick_work_cpu;
-+
-+static void sched_tick_remote(struct work_struct *work)
-+{
-+ struct delayed_work *dwork = to_delayed_work(work);
-+ struct tick_work *twork = container_of(dwork, struct tick_work, work);
-+ int cpu = twork->cpu;
-+ struct rq *rq = cpu_rq(cpu);
-+ int os;
-+
-+ /*
-+ * Handle the tick only if it appears the remote CPU is running in full
-+ * dynticks mode. The check is racy by nature, but missing a tick or
-+ * having one too much is no big deal because the scheduler tick updates
-+ * statistics and checks timeslices in a time-independent way, regardless
-+ * of when exactly it is running.
-+ */
-+ if (tick_nohz_tick_stopped_cpu(cpu)) {
-+ guard(raw_spinlock_irqsave)(&rq->lock);
-+ struct task_struct *curr = rq->curr;
-+
-+ if (cpu_online(cpu)) {
-+ update_rq_clock(rq);
-+
-+ if (!is_idle_task(curr)) {
-+ /*
-+ * Make sure the next tick runs within a
-+ * reasonable amount of time.
-+ */
-+ u64 delta = rq_clock_task(rq) - curr->last_ran;
-+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
-+ }
-+ scheduler_task_tick(rq);
-+
-+ calc_load_nohz_remote(rq);
-+ }
-+ }
-+
-+ /*
-+ * Run the remote tick once per second (1Hz). This arbitrary
-+ * frequency is large enough to avoid overload but short enough
-+ * to keep scheduler internal stats reasonably up to date. But
-+ * first update state to reflect hotplug activity if required.
-+ */
-+ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
-+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
-+ if (os == TICK_SCHED_REMOTE_RUNNING)
-+ queue_delayed_work(system_unbound_wq, dwork, HZ);
-+}
-+
-+static void sched_tick_start(int cpu)
-+{
-+ int os;
-+ struct tick_work *twork;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
-+ return;
-+
-+ WARN_ON_ONCE(!tick_work_cpu);
-+
-+ twork = per_cpu_ptr(tick_work_cpu, cpu);
-+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
-+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
-+ if (os == TICK_SCHED_REMOTE_OFFLINE) {
-+ twork->cpu = cpu;
-+ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
-+ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
-+ }
-+}
-+
-+#ifdef CONFIG_HOTPLUG_CPU
-+static void sched_tick_stop(int cpu)
-+{
-+ struct tick_work *twork;
-+ int os;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
-+ return;
-+
-+ WARN_ON_ONCE(!tick_work_cpu);
-+
-+ twork = per_cpu_ptr(tick_work_cpu, cpu);
-+ /* There cannot be competing actions, but don't rely on stop-machine. */
-+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
-+ WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
-+ /* Don't cancel, as this would mess up the state machine. */
-+}
-+#endif /* CONFIG_HOTPLUG_CPU */
-+
-+int __init sched_tick_offload_init(void)
-+{
-+ tick_work_cpu = alloc_percpu(struct tick_work);
-+ BUG_ON(!tick_work_cpu);
-+ return 0;
-+}
-+
-+#else /* !CONFIG_NO_HZ_FULL */
-+static inline void sched_tick_start(int cpu) { }
-+static inline void sched_tick_stop(int cpu) { }
-+#endif
-+
-+#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
-+ defined(CONFIG_PREEMPT_TRACER))
-+/*
-+ * If the value passed in is equal to the current preempt count
-+ * then we just disabled preemption. Start timing the latency.
-+ */
-+static inline void preempt_latency_start(int val)
-+{
-+ if (preempt_count() == val) {
-+ unsigned long ip = get_lock_parent_ip();
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ current->preempt_disable_ip = ip;
-+#endif
-+ trace_preempt_off(CALLER_ADDR0, ip);
-+ }
-+}
-+
-+void preempt_count_add(int val)
-+{
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ /*
-+ * Underflow?
-+ */
-+ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
-+ return;
-+#endif
-+ __preempt_count_add(val);
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ /*
-+ * Spinlock count overflowing soon?
-+ */
-+ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
-+ PREEMPT_MASK - 10);
-+#endif
-+ preempt_latency_start(val);
-+}
-+EXPORT_SYMBOL(preempt_count_add);
-+NOKPROBE_SYMBOL(preempt_count_add);
-+
-+/*
-+ * If the value passed in equals to the current preempt count
-+ * then we just enabled preemption. Stop timing the latency.
-+ */
-+static inline void preempt_latency_stop(int val)
-+{
-+ if (preempt_count() == val)
-+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
-+}
-+
-+void preempt_count_sub(int val)
-+{
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ /*
-+ * Underflow?
-+ */
-+ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
-+ return;
-+ /*
-+ * Is the spinlock portion underflowing?
-+ */
-+ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
-+ !(preempt_count() & PREEMPT_MASK)))
-+ return;
-+#endif
-+
-+ preempt_latency_stop(val);
-+ __preempt_count_sub(val);
-+}
-+EXPORT_SYMBOL(preempt_count_sub);
-+NOKPROBE_SYMBOL(preempt_count_sub);
-+
-+#else
-+static inline void preempt_latency_start(int val) { }
-+static inline void preempt_latency_stop(int val) { }
-+#endif
-+
-+static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
-+{
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ return p->preempt_disable_ip;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+/*
-+ * Print scheduling while atomic bug:
-+ */
-+static noinline void __schedule_bug(struct task_struct *prev)
-+{
-+ /* Save this before calling printk(), since that will clobber it */
-+ unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
-+
-+ if (oops_in_progress)
-+ return;
-+
-+ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
-+ prev->comm, prev->pid, preempt_count());
-+
-+ debug_show_held_locks(prev);
-+ print_modules();
-+ if (irqs_disabled())
-+ print_irqtrace_events(prev);
-+ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
-+ pr_err("Preemption disabled at:");
-+ print_ip_sym(KERN_ERR, preempt_disable_ip);
-+ }
-+ check_panic_on_warn("scheduling while atomic");
-+
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+
-+/*
-+ * Various schedule()-time debugging checks and statistics:
-+ */
-+static inline void schedule_debug(struct task_struct *prev, bool preempt)
-+{
-+#ifdef CONFIG_SCHED_STACK_END_CHECK
-+ if (task_stack_end_corrupted(prev))
-+ panic("corrupted stack end detected inside scheduler\n");
-+
-+ if (task_scs_end_corrupted(prev))
-+ panic("corrupted shadow stack detected inside scheduler\n");
-+#endif
-+
-+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-+ if (!preempt && READ_ONCE(prev->__state) && prev->non_block_count) {
-+ printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
-+ prev->comm, prev->pid, prev->non_block_count);
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+ }
-+#endif
-+
-+ if (unlikely(in_atomic_preempt_off())) {
-+ __schedule_bug(prev);
-+ preempt_count_set(PREEMPT_DISABLED);
-+ }
-+ rcu_sleep_check();
-+ SCHED_WARN_ON(ct_state() == CONTEXT_USER);
-+
-+ profile_hit(SCHED_PROFILING, __builtin_return_address(0));
-+
-+ schedstat_inc(this_rq()->sched_count);
-+}
-+
-+#ifdef ALT_SCHED_DEBUG
-+void alt_sched_debug(void)
-+{
-+ printk(KERN_INFO "sched: pending: 0x%04lx, idle: 0x%04lx, sg_idle: 0x%04lx\n",
-+ sched_rq_pending_mask.bits[0],
-+ sched_idle_mask->bits[0],
-+ sched_sg_idle_mask.bits[0]);
-+}
-+#else
-+inline void alt_sched_debug(void) {}
-+#endif
-+
-+#ifdef CONFIG_SMP
-+
-+#ifdef CONFIG_PREEMPT_RT
-+#define SCHED_NR_MIGRATE_BREAK 8
-+#else
-+#define SCHED_NR_MIGRATE_BREAK 32
-+#endif
-+
-+const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
-+
-+/*
-+ * Migrate pending tasks in @rq to @dest_cpu
-+ */
-+static inline int
-+migrate_pending_tasks(struct rq *rq, struct rq *dest_rq, const int dest_cpu)
-+{
-+ struct task_struct *p, *skip = rq->curr;
-+ int nr_migrated = 0;
-+ int nr_tries = min(rq->nr_running / 2, sysctl_sched_nr_migrate);
-+
-+ /* WA to check rq->curr is still on rq */
-+ if (!task_on_rq_queued(skip))
-+ return 0;
-+
-+ while (skip != rq->idle && nr_tries &&
-+ (p = sched_rq_next_task(skip, rq)) != rq->idle) {
-+ skip = sched_rq_next_task(p, rq);
-+ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) {
-+ __SCHED_DEQUEUE_TASK(p, rq, 0, );
-+ set_task_cpu(p, dest_cpu);
-+ sched_task_sanity_check(p, dest_rq);
-+ sched_mm_cid_migrate_to(dest_rq, p, cpu_of(rq));
-+ __SCHED_ENQUEUE_TASK(p, dest_rq, 0, );
-+ nr_migrated++;
-+ }
-+ nr_tries--;
-+ }
-+
-+ return nr_migrated;
-+}
-+
-+static inline int take_other_rq_tasks(struct rq *rq, int cpu)
-+{
-+ cpumask_t *topo_mask, *end_mask, chk;
-+
-+ if (unlikely(!rq->online))
-+ return 0;
-+
-+ if (cpumask_empty(&sched_rq_pending_mask))
-+ return 0;
-+
-+ topo_mask = per_cpu(sched_cpu_topo_masks, cpu);
-+ end_mask = per_cpu(sched_cpu_topo_end_mask, cpu);
-+ do {
-+ int i;
-+
-+ if (!cpumask_and(&chk, &sched_rq_pending_mask, topo_mask))
-+ continue;
-+
-+ for_each_cpu_wrap(i, &chk, cpu) {
-+ int nr_migrated;
-+ struct rq *src_rq;
-+
-+ src_rq = cpu_rq(i);
-+ if (!do_raw_spin_trylock(&src_rq->lock))
-+ continue;
-+ spin_acquire(&src_rq->lock.dep_map,
-+ SINGLE_DEPTH_NESTING, 1, _RET_IP_);
-+
-+ if ((nr_migrated = migrate_pending_tasks(src_rq, rq, cpu))) {
-+ src_rq->nr_running -= nr_migrated;
-+ if (src_rq->nr_running < 2)
-+ cpumask_clear_cpu(i, &sched_rq_pending_mask);
-+
-+ spin_release(&src_rq->lock.dep_map, _RET_IP_);
-+ do_raw_spin_unlock(&src_rq->lock);
-+
-+ rq->nr_running += nr_migrated;
-+ if (rq->nr_running > 1)
-+ cpumask_set_cpu(cpu, &sched_rq_pending_mask);
-+
-+ update_sched_preempt_mask(rq);
-+ cpufreq_update_util(rq, 0);
-+
-+ return 1;
-+ }
-+
-+ spin_release(&src_rq->lock.dep_map, _RET_IP_);
-+ do_raw_spin_unlock(&src_rq->lock);
-+ }
-+ } while (++topo_mask < end_mask);
-+
-+ return 0;
-+}
-+#endif
-+
-+static inline void time_slice_expired(struct task_struct *p, struct rq *rq)
-+{
-+ p->time_slice = sysctl_sched_base_slice;
-+
-+ sched_task_renew(p, rq);
-+
-+ if (SCHED_FIFO != p->policy && task_on_rq_queued(p))
-+ requeue_task(p, rq);
-+}
-+
-+/*
-+ * Timeslices below RESCHED_NS are considered as good as expired as there's no
-+ * point rescheduling when there's so little time left.
-+ */
-+static inline void check_curr(struct task_struct *p, struct rq *rq)
-+{
-+ if (unlikely(rq->idle == p))
-+ return;
-+
-+ update_curr(rq, p);
-+
-+ if (p->time_slice < RESCHED_NS)
-+ time_slice_expired(p, rq);
-+}
-+
-+static inline struct task_struct *
-+choose_next_task(struct rq *rq, int cpu)
-+{
-+ struct task_struct *next = sched_rq_first_task(rq);
-+
-+ if (next == rq->idle) {
-+#ifdef CONFIG_SMP
-+ if (!take_other_rq_tasks(rq, cpu)) {
-+#endif
-+
-+#ifdef CONFIG_SCHED_SMT
-+ if (static_key_count(&sched_smt_present.key) > 1 &&
-+ cpumask_test_cpu(cpu, sched_sg_idle_mask) &&
-+ rq->online)
-+ __queue_balance_callback(rq, &per_cpu(sg_balance_head, cpu));
-+#endif
-+ schedstat_inc(rq->sched_goidle);
-+ /*printk(KERN_INFO "sched: choose_next_task(%d) idle %px\n", cpu, next);*/
-+ return next;
-+#ifdef CONFIG_SMP
-+ }
-+ next = sched_rq_first_task(rq);
-+#endif
-+ }
-+#ifdef CONFIG_HIGH_RES_TIMERS
-+ hrtick_start(rq, next->time_slice);
-+#endif
-+ /*printk(KERN_INFO "sched: choose_next_task(%d) next %px\n", cpu, next);*/
-+ return next;
-+}
-+
-+/*
-+ * Constants for the sched_mode argument of __schedule().
-+ *
-+ * The mode argument allows RT enabled kernels to differentiate a
-+ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
-+ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
-+ * optimize the AND operation out and just check for zero.
-+ */
-+#define SM_NONE 0x0
-+#define SM_PREEMPT 0x1
-+#define SM_RTLOCK_WAIT 0x2
-+
-+#ifndef CONFIG_PREEMPT_RT
-+# define SM_MASK_PREEMPT (~0U)
-+#else
-+# define SM_MASK_PREEMPT SM_PREEMPT
-+#endif
-+
-+/*
-+ * schedule() is the main scheduler function.
-+ *
-+ * The main means of driving the scheduler and thus entering this function are:
-+ *
-+ * 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
-+ *
-+ * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
-+ * paths. For example, see arch/x86/entry_64.S.
-+ *
-+ * To drive preemption between tasks, the scheduler sets the flag in timer
-+ * interrupt handler sched_tick().
-+ *
-+ * 3. Wakeups don't really cause entry into schedule(). They add a
-+ * task to the run-queue and that's it.
-+ *
-+ * Now, if the new task added to the run-queue preempts the current
-+ * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
-+ * called on the nearest possible occasion:
-+ *
-+ * - If the kernel is preemptible (CONFIG_PREEMPTION=y):
-+ *
-+ * - in syscall or exception context, at the next outmost
-+ * preempt_enable(). (this might be as soon as the wake_up()'s
-+ * spin_unlock()!)
-+ *
-+ * - in IRQ context, return from interrupt-handler to
-+ * preemptible context
-+ *
-+ * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
-+ * then at the next:
-+ *
-+ * - cond_resched() call
-+ * - explicit schedule() call
-+ * - return from syscall or exception to user-space
-+ * - return from interrupt-handler to user-space
-+ *
-+ * WARNING: must be called with preemption disabled!
-+ */
-+static void __sched notrace __schedule(unsigned int sched_mode)
-+{
-+ struct task_struct *prev, *next;
-+ unsigned long *switch_count;
-+ unsigned long prev_state;
-+ struct rq *rq;
-+ int cpu;
-+
-+ cpu = smp_processor_id();
-+ rq = cpu_rq(cpu);
-+ prev = rq->curr;
-+
-+ schedule_debug(prev, !!sched_mode);
-+
-+ /* by passing sched_feat(HRTICK) checking which Alt schedule FW doesn't support */
-+ hrtick_clear(rq);
-+
-+ local_irq_disable();
-+ rcu_note_context_switch(!!sched_mode);
-+
-+ /*
-+ * Make sure that signal_pending_state()->signal_pending() below
-+ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-+ * done by the caller to avoid the race with signal_wake_up():
-+ *
-+ * __set_current_state(@state) signal_wake_up()
-+ * schedule() set_tsk_thread_flag(p, TIF_SIGPENDING)
-+ * wake_up_state(p, state)
-+ * LOCK rq->lock LOCK p->pi_state
-+ * smp_mb__after_spinlock() smp_mb__after_spinlock()
-+ * if (signal_pending_state()) if (p->state & @state)
-+ *
-+ * Also, the membarrier system call requires a full memory barrier
-+ * after coming from user-space, before storing to rq->curr; this
-+ * barrier matches a full barrier in the proximity of the membarrier
-+ * system call exit.
-+ */
-+ raw_spin_lock(&rq->lock);
-+ smp_mb__after_spinlock();
-+
-+ update_rq_clock(rq);
-+
-+ switch_count = &prev->nivcsw;
-+ /*
-+ * We must load prev->state once (task_struct::state is volatile), such
-+ * that we form a control dependency vs deactivate_task() below.
-+ */
-+ prev_state = READ_ONCE(prev->__state);
-+ if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
-+ if (signal_pending_state(prev_state, prev)) {
-+ WRITE_ONCE(prev->__state, TASK_RUNNING);
-+ } else {
-+ prev->sched_contributes_to_load =
-+ (prev_state & TASK_UNINTERRUPTIBLE) &&
-+ !(prev_state & TASK_NOLOAD) &&
-+ !(prev_state & TASK_FROZEN);
-+
-+ if (prev->sched_contributes_to_load)
-+ rq->nr_uninterruptible++;
-+
-+ /*
-+ * __schedule() ttwu()
-+ * prev_state = prev->state; if (p->on_rq && ...)
-+ * if (prev_state) goto out;
-+ * p->on_rq = 0; smp_acquire__after_ctrl_dep();
-+ * p->state = TASK_WAKING
-+ *
-+ * Where __schedule() and ttwu() have matching control dependencies.
-+ *
-+ * After this, schedule() must not care about p->state any more.
-+ */
-+ sched_task_deactivate(prev, rq);
-+ deactivate_task(prev, rq);
-+
-+ if (prev->in_iowait) {
-+ atomic_inc(&rq->nr_iowait);
-+ delayacct_blkio_start();
-+ }
-+ }
-+ switch_count = &prev->nvcsw;
-+ }
-+
-+ check_curr(prev, rq);
-+
-+ next = choose_next_task(rq, cpu);
-+ clear_tsk_need_resched(prev);
-+ clear_preempt_need_resched();
-+#ifdef CONFIG_SCHED_DEBUG
-+ rq->last_seen_need_resched_ns = 0;
-+#endif
-+
-+ if (likely(prev != next)) {
-+ next->last_ran = rq->clock_task;
-+
-+ /*printk(KERN_INFO "sched: %px -> %px\n", prev, next);*/
-+ rq->nr_switches++;
-+ /*
-+ * RCU users of rcu_dereference(rq->curr) may not see
-+ * changes to task_struct made by pick_next_task().
-+ */
-+ RCU_INIT_POINTER(rq->curr, next);
-+ /*
-+ * The membarrier system call requires each architecture
-+ * to have a full memory barrier after updating
-+ * rq->curr, before returning to user-space.
-+ *
-+ * Here are the schemes providing that barrier on the
-+ * various architectures:
-+ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC,
-+ * RISC-V. switch_mm() relies on membarrier_arch_switch_mm()
-+ * on PowerPC and on RISC-V.
-+ * - finish_lock_switch() for weakly-ordered
-+ * architectures where spin_unlock is a full barrier,
-+ * - switch_to() for arm64 (weakly-ordered, spin_unlock
-+ * is a RELEASE barrier),
-+ *
-+ * The barrier matches a full barrier in the proximity of
-+ * the membarrier system call entry.
-+ *
-+ * On RISC-V, this barrier pairing is also needed for the
-+ * SYNC_CORE command when switching between processes, cf.
-+ * the inline comments in membarrier_arch_switch_mm().
-+ */
-+ ++*switch_count;
-+
-+ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
-+
-+ /* Also unlocks the rq: */
-+ rq = context_switch(rq, prev, next);
-+
-+ cpu = cpu_of(rq);
-+ } else {
-+ __balance_callbacks(rq);
-+ raw_spin_unlock_irq(&rq->lock);
-+ }
-+}
-+
-+void __noreturn do_task_dead(void)
-+{
-+ /* Causes final put_task_struct in finish_task_switch(): */
-+ set_special_state(TASK_DEAD);
-+
-+ /* Tell freezer to ignore us: */
-+ current->flags |= PF_NOFREEZE;
-+
-+ __schedule(SM_NONE);
-+ BUG();
-+
-+ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
-+ for (;;)
-+ cpu_relax();
-+}
-+
-+static inline void sched_submit_work(struct task_struct *tsk)
-+{
-+ static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
-+ unsigned int task_flags;
-+
-+ /*
-+ * Establish LD_WAIT_CONFIG context to ensure none of the code called
-+ * will use a blocking primitive -- which would lead to recursion.
-+ */
-+ lock_map_acquire_try(&sched_map);
-+
-+ task_flags = tsk->flags;
-+ /*
-+ * If a worker goes to sleep, notify and ask workqueue whether it
-+ * wants to wake up a task to maintain concurrency.
-+ */
-+ if (task_flags & PF_WQ_WORKER)
-+ wq_worker_sleeping(tsk);
-+ else if (task_flags & PF_IO_WORKER)
-+ io_wq_worker_sleeping(tsk);
-+
-+ /*
-+ * spinlock and rwlock must not flush block requests. This will
-+ * deadlock if the callback attempts to acquire a lock which is
-+ * already acquired.
-+ */
-+ SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
-+
-+ /*
-+ * If we are going to sleep and we have plugged IO queued,
-+ * make sure to submit it to avoid deadlocks.
-+ */
-+ blk_flush_plug(tsk->plug, true);
-+
-+ lock_map_release(&sched_map);
-+}
-+
-+static void sched_update_worker(struct task_struct *tsk)
-+{
-+ if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
-+ if (tsk->flags & PF_BLOCK_TS)
-+ blk_plug_invalidate_ts(tsk);
-+ if (tsk->flags & PF_WQ_WORKER)
-+ wq_worker_running(tsk);
-+ else if (tsk->flags & PF_IO_WORKER)
-+ io_wq_worker_running(tsk);
-+ }
-+}
-+
-+static __always_inline void __schedule_loop(unsigned int sched_mode)
-+{
-+ do {
-+ preempt_disable();
-+ __schedule(sched_mode);
-+ sched_preempt_enable_no_resched();
-+ } while (need_resched());
-+}
-+
-+asmlinkage __visible void __sched schedule(void)
-+{
-+ struct task_struct *tsk = current;
-+
-+#ifdef CONFIG_RT_MUTEXES
-+ lockdep_assert(!tsk->sched_rt_mutex);
-+#endif
-+
-+ if (!task_is_running(tsk))
-+ sched_submit_work(tsk);
-+ __schedule_loop(SM_NONE);
-+ sched_update_worker(tsk);
-+}
-+EXPORT_SYMBOL(schedule);
-+
-+/*
-+ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
-+ * state (have scheduled out non-voluntarily) by making sure that all
-+ * tasks have either left the run queue or have gone into user space.
-+ * As idle tasks do not do either, they must not ever be preempted
-+ * (schedule out non-voluntarily).
-+ *
-+ * schedule_idle() is similar to schedule_preempt_disable() except that it
-+ * never enables preemption because it does not call sched_submit_work().
-+ */
-+void __sched schedule_idle(void)
-+{
-+ /*
-+ * As this skips calling sched_submit_work(), which the idle task does
-+ * regardless because that function is a nop when the task is in a
-+ * TASK_RUNNING state, make sure this isn't used someplace that the
-+ * current task can be in any other state. Note, idle is always in the
-+ * TASK_RUNNING state.
-+ */
-+ WARN_ON_ONCE(current->__state);
-+ do {
-+ __schedule(SM_NONE);
-+ } while (need_resched());
-+}
-+
-+#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK)
-+asmlinkage __visible void __sched schedule_user(void)
-+{
-+ /*
-+ * If we come here after a random call to set_need_resched(),
-+ * or we have been woken up remotely but the IPI has not yet arrived,
-+ * we haven't yet exited the RCU idle mode. Do it here manually until
-+ * we find a better solution.
-+ *
-+ * NB: There are buggy callers of this function. Ideally we
-+ * should warn if prev_state != CONTEXT_USER, but that will trigger
-+ * too frequently to make sense yet.
-+ */
-+ enum ctx_state prev_state = exception_enter();
-+ schedule();
-+ exception_exit(prev_state);
-+}
-+#endif
-+
-+/**
-+ * schedule_preempt_disabled - called with preemption disabled
-+ *
-+ * Returns with preemption disabled. Note: preempt_count must be 1
-+ */
-+void __sched schedule_preempt_disabled(void)
-+{
-+ sched_preempt_enable_no_resched();
-+ schedule();
-+ preempt_disable();
-+}
-+
-+#ifdef CONFIG_PREEMPT_RT
-+void __sched notrace schedule_rtlock(void)
-+{
-+ __schedule_loop(SM_RTLOCK_WAIT);
-+}
-+NOKPROBE_SYMBOL(schedule_rtlock);
-+#endif
-+
-+static void __sched notrace preempt_schedule_common(void)
-+{
-+ do {
-+ /*
-+ * Because the function tracer can trace preempt_count_sub()
-+ * and it also uses preempt_enable/disable_notrace(), if
-+ * NEED_RESCHED is set, the preempt_enable_notrace() called
-+ * by the function tracer will call this function again and
-+ * cause infinite recursion.
-+ *
-+ * Preemption must be disabled here before the function
-+ * tracer can trace. Break up preempt_disable() into two
-+ * calls. One to disable preemption without fear of being
-+ * traced. The other to still record the preemption latency,
-+ * which can also be traced by the function tracer.
-+ */
-+ preempt_disable_notrace();
-+ preempt_latency_start(1);
-+ __schedule(SM_PREEMPT);
-+ preempt_latency_stop(1);
-+ preempt_enable_no_resched_notrace();
-+
-+ /*
-+ * Check again in case we missed a preemption opportunity
-+ * between schedule and now.
-+ */
-+ } while (need_resched());
-+}
-+
-+#ifdef CONFIG_PREEMPTION
-+/*
-+ * This is the entry point to schedule() from in-kernel preemption
-+ * off of preempt_enable.
-+ */
-+asmlinkage __visible void __sched notrace preempt_schedule(void)
-+{
-+ /*
-+ * If there is a non-zero preempt_count or interrupts are disabled,
-+ * we do not want to preempt the current task. Just return..
-+ */
-+ if (likely(!preemptible()))
-+ return;
-+
-+ preempt_schedule_common();
-+}
-+NOKPROBE_SYMBOL(preempt_schedule);
-+EXPORT_SYMBOL(preempt_schedule);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#ifndef preempt_schedule_dynamic_enabled
-+#define preempt_schedule_dynamic_enabled preempt_schedule
-+#define preempt_schedule_dynamic_disabled NULL
-+#endif
-+DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
-+EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
-+void __sched notrace dynamic_preempt_schedule(void)
-+{
-+ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
-+ return;
-+ preempt_schedule();
-+}
-+NOKPROBE_SYMBOL(dynamic_preempt_schedule);
-+EXPORT_SYMBOL(dynamic_preempt_schedule);
-+#endif
-+#endif
-+
-+/**
-+ * preempt_schedule_notrace - preempt_schedule called by tracing
-+ *
-+ * The tracing infrastructure uses preempt_enable_notrace to prevent
-+ * recursion and tracing preempt enabling caused by the tracing
-+ * infrastructure itself. But as tracing can happen in areas coming
-+ * from userspace or just about to enter userspace, a preempt enable
-+ * can occur before user_exit() is called. This will cause the scheduler
-+ * to be called when the system is still in usermode.
-+ *
-+ * To prevent this, the preempt_enable_notrace will use this function
-+ * instead of preempt_schedule() to exit user context if needed before
-+ * calling the scheduler.
-+ */
-+asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
-+{
-+ enum ctx_state prev_ctx;
-+
-+ if (likely(!preemptible()))
-+ return;
-+
-+ do {
-+ /*
-+ * Because the function tracer can trace preempt_count_sub()
-+ * and it also uses preempt_enable/disable_notrace(), if
-+ * NEED_RESCHED is set, the preempt_enable_notrace() called
-+ * by the function tracer will call this function again and
-+ * cause infinite recursion.
-+ *
-+ * Preemption must be disabled here before the function
-+ * tracer can trace. Break up preempt_disable() into two
-+ * calls. One to disable preemption without fear of being
-+ * traced. The other to still record the preemption latency,
-+ * which can also be traced by the function tracer.
-+ */
-+ preempt_disable_notrace();
-+ preempt_latency_start(1);
-+ /*
-+ * Needs preempt disabled in case user_exit() is traced
-+ * and the tracer calls preempt_enable_notrace() causing
-+ * an infinite recursion.
-+ */
-+ prev_ctx = exception_enter();
-+ __schedule(SM_PREEMPT);
-+ exception_exit(prev_ctx);
-+
-+ preempt_latency_stop(1);
-+ preempt_enable_no_resched_notrace();
-+ } while (need_resched());
-+}
-+EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#ifndef preempt_schedule_notrace_dynamic_enabled
-+#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace
-+#define preempt_schedule_notrace_dynamic_disabled NULL
-+#endif
-+DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
-+EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
-+void __sched notrace dynamic_preempt_schedule_notrace(void)
-+{
-+ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
-+ return;
-+ preempt_schedule_notrace();
-+}
-+NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
-+EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
-+#endif
-+#endif
-+
-+#endif /* CONFIG_PREEMPTION */
-+
-+/*
-+ * This is the entry point to schedule() from kernel preemption
-+ * off of irq context.
-+ * Note, that this is called and return with irqs disabled. This will
-+ * protect us against recursive calling from irq.
-+ */
-+asmlinkage __visible void __sched preempt_schedule_irq(void)
-+{
-+ enum ctx_state prev_state;
-+
-+ /* Catch callers which need to be fixed */
-+ BUG_ON(preempt_count() || !irqs_disabled());
-+
-+ prev_state = exception_enter();
-+
-+ do {
-+ preempt_disable();
-+ local_irq_enable();
-+ __schedule(SM_PREEMPT);
-+ local_irq_disable();
-+ sched_preempt_enable_no_resched();
-+ } while (need_resched());
-+
-+ exception_exit(prev_state);
-+}
-+
-+int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
-+ void *key)
-+{
-+ WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
-+ return try_to_wake_up(curr->private, mode, wake_flags);
-+}
-+EXPORT_SYMBOL(default_wake_function);
-+
-+static inline void check_task_changed(struct task_struct *p, struct rq *rq)
-+{
-+ /* Trigger resched if task sched_prio has been modified. */
-+ if (task_on_rq_queued(p)) {
-+ update_rq_clock(rq);
-+ requeue_task(p, rq);
-+ wakeup_preempt(rq);
-+ }
-+}
-+
-+static void __setscheduler_prio(struct task_struct *p, int prio)
-+{
-+ p->prio = prio;
-+}
-+
-+#ifdef CONFIG_RT_MUTEXES
-+
-+/*
-+ * Would be more useful with typeof()/auto_type but they don't mix with
-+ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
-+ * name such that if someone were to implement this function we get to compare
-+ * notes.
-+ */
-+#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
-+
-+void rt_mutex_pre_schedule(void)
-+{
-+ lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
-+ sched_submit_work(current);
-+}
-+
-+void rt_mutex_schedule(void)
-+{
-+ lockdep_assert(current->sched_rt_mutex);
-+ __schedule_loop(SM_NONE);
-+}
-+
-+void rt_mutex_post_schedule(void)
-+{
-+ sched_update_worker(current);
-+ lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
-+}
-+
-+static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
-+{
-+ if (pi_task)
-+ prio = min(prio, pi_task->prio);
-+
-+ return prio;
-+}
-+
-+static inline int rt_effective_prio(struct task_struct *p, int prio)
-+{
-+ struct task_struct *pi_task = rt_mutex_get_top_task(p);
-+
-+ return __rt_effective_prio(pi_task, prio);
-+}
-+
-+/*
-+ * rt_mutex_setprio - set the current priority of a task
-+ * @p: task to boost
-+ * @pi_task: donor task
-+ *
-+ * This function changes the 'effective' priority of a task. It does
-+ * not touch ->normal_prio like __setscheduler().
-+ *
-+ * Used by the rt_mutex code to implement priority inheritance
-+ * logic. Call site only calls if the priority of the task changed.
-+ */
-+void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
-+{
-+ int prio;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ /* XXX used to be waiter->prio, not waiter->task->prio */
-+ prio = __rt_effective_prio(pi_task, p->normal_prio);
-+
-+ /*
-+ * If nothing changed; bail early.
-+ */
-+ if (p->pi_top_task == pi_task && prio == p->prio)
-+ return;
-+
-+ rq = __task_access_lock(p, &lock);
-+ /*
-+ * Set under pi_lock && rq->lock, such that the value can be used under
-+ * either lock.
-+ *
-+ * Note that there is loads of tricky to make this pointer cache work
-+ * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
-+ * ensure a task is de-boosted (pi_task is set to NULL) before the
-+ * task is allowed to run again (and can exit). This ensures the pointer
-+ * points to a blocked task -- which guarantees the task is present.
-+ */
-+ p->pi_top_task = pi_task;
-+
-+ /*
-+ * For FIFO/RR we only need to set prio, if that matches we're done.
-+ */
-+ if (prio == p->prio)
-+ goto out_unlock;
-+
-+ /*
-+ * Idle task boosting is a nono in general. There is one
-+ * exception, when PREEMPT_RT and NOHZ is active:
-+ *
-+ * The idle task calls get_next_timer_interrupt() and holds
-+ * the timer wheel base->lock on the CPU and another CPU wants
-+ * to access the timer (probably to cancel it). We can safely
-+ * ignore the boosting request, as the idle CPU runs this code
-+ * with interrupts disabled and will complete the lock
-+ * protected section without being interrupted. So there is no
-+ * real need to boost.
-+ */
-+ if (unlikely(p == rq->idle)) {
-+ WARN_ON(p != rq->curr);
-+ WARN_ON(p->pi_blocked_on);
-+ goto out_unlock;
-+ }
-+
-+ trace_sched_pi_setprio(p, pi_task);
-+
-+ __setscheduler_prio(p, prio);
-+
-+ check_task_changed(p, rq);
-+out_unlock:
-+ /* Avoid rq from going away on us: */
-+ preempt_disable();
-+
-+ if (task_on_rq_queued(p))
-+ __balance_callbacks(rq);
-+ __task_access_unlock(p, lock);
-+
-+ preempt_enable();
-+}
-+#else
-+static inline int rt_effective_prio(struct task_struct *p, int prio)
-+{
-+ return prio;
-+}
-+#endif
-+
-+void set_user_nice(struct task_struct *p, long nice)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
-+ return;
-+ /*
-+ * We have to be careful, if called from sys_setpriority(),
-+ * the task might be in the middle of scheduling on another CPU.
-+ */
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+ rq = __task_access_lock(p, &lock);
-+
-+ p->static_prio = NICE_TO_PRIO(nice);
-+ /*
-+ * The RT priorities are set via sched_setscheduler(), but we still
-+ * allow the 'normal' nice value to be set - but as expected
-+ * it won't have any effect on scheduling until the task is
-+ * not SCHED_NORMAL/SCHED_BATCH:
-+ */
-+ if (task_has_rt_policy(p))
-+ goto out_unlock;
-+
-+ p->prio = effective_prio(p);
-+
-+ check_task_changed(p, rq);
-+out_unlock:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+}
-+EXPORT_SYMBOL(set_user_nice);
-+
-+/*
-+ * is_nice_reduction - check if nice value is an actual reduction
-+ *
-+ * Similar to can_nice() but does not perform a capability check.
-+ *
-+ * @p: task
-+ * @nice: nice value
-+ */
-+static bool is_nice_reduction(const struct task_struct *p, const int nice)
-+{
-+ /* Convert nice value [19,-20] to rlimit style value [1,40]: */
-+ int nice_rlim = nice_to_rlimit(nice);
-+
-+ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));
-+}
-+
-+/*
-+ * can_nice - check if a task can reduce its nice value
-+ * @p: task
-+ * @nice: nice value
-+ */
-+int can_nice(const struct task_struct *p, const int nice)
-+{
-+ return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);
-+}
-+
-+#ifdef __ARCH_WANT_SYS_NICE
-+
-+/*
-+ * sys_nice - change the priority of the current process.
-+ * @increment: priority increment
-+ *
-+ * sys_setpriority is a more generic, but much slower function that
-+ * does similar things.
-+ */
-+SYSCALL_DEFINE1(nice, int, increment)
-+{
-+ long nice, retval;
-+
-+ /*
-+ * Setpriority might change our priority at the same moment.
-+ * We don't have to worry. Conceptually one call occurs first
-+ * and we have a single winner.
-+ */
-+
-+ increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
-+ nice = task_nice(current) + increment;
-+
-+ nice = clamp_val(nice, MIN_NICE, MAX_NICE);
-+ if (increment < 0 && !can_nice(current, nice))
-+ return -EPERM;
-+
-+ retval = security_task_setnice(current, nice);
-+ if (retval)
-+ return retval;
-+
-+ set_user_nice(current, nice);
-+ return 0;
-+}
-+
-+#endif
-+
-+/**
-+ * task_prio - return the priority value of a given task.
-+ * @p: the task in question.
-+ *
-+ * Return: The priority value as seen by users in /proc.
-+ *
-+ * sched policy return value kernel prio user prio/nice
-+ *
-+ * (BMQ)normal, batch, idle[0 ... 53] [100 ... 139] 0/[-20 ... 19]/[-7 ... 7]
-+ * (PDS)normal, batch, idle[0 ... 39] 100 0/[-20 ... 19]
-+ * fifo, rr [-1 ... -100] [99 ... 0] [0 ... 99]
-+ */
-+int task_prio(const struct task_struct *p)
-+{
-+ return (p->prio < MAX_RT_PRIO) ? p->prio - MAX_RT_PRIO :
-+ task_sched_prio_normal(p, task_rq(p));
-+}
-+
-+/**
-+ * idle_cpu - is a given CPU idle currently?
-+ * @cpu: the processor in question.
-+ *
-+ * Return: 1 if the CPU is currently idle. 0 otherwise.
-+ */
-+int idle_cpu(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ if (rq->curr != rq->idle)
-+ return 0;
-+
-+ if (rq->nr_running)
-+ return 0;
-+
-+#ifdef CONFIG_SMP
-+ if (rq->ttwu_pending)
-+ return 0;
-+#endif
-+
-+ return 1;
-+}
-+
-+/**
-+ * idle_task - return the idle task for a given CPU.
-+ * @cpu: the processor in question.
-+ *
-+ * Return: The idle task for the cpu @cpu.
-+ */
-+struct task_struct *idle_task(int cpu)
-+{
-+ return cpu_rq(cpu)->idle;
-+}
-+
-+/**
-+ * find_process_by_pid - find a process with a matching PID value.
-+ * @pid: the pid in question.
-+ *
-+ * The task of @pid, if found. %NULL otherwise.
-+ */
-+static inline struct task_struct *find_process_by_pid(pid_t pid)
-+{
-+ return pid ? find_task_by_vpid(pid) : current;
-+}
-+
-+static struct task_struct *find_get_task(pid_t pid)
-+{
-+ struct task_struct *p;
-+ guard(rcu)();
-+
-+ p = find_process_by_pid(pid);
-+ if (likely(p))
-+ get_task_struct(p);
-+
-+ return p;
-+}
-+
-+DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
-+ find_get_task(pid), pid_t pid)
-+
-+/*
-+ * sched_setparam() passes in -1 for its policy, to let the functions
-+ * it calls know not to change it.
-+ */
-+#define SETPARAM_POLICY -1
-+
-+static void __setscheduler_params(struct task_struct *p,
-+ const struct sched_attr *attr)
-+{
-+ int policy = attr->sched_policy;
-+
-+ if (policy == SETPARAM_POLICY)
-+ policy = p->policy;
-+
-+ p->policy = policy;
-+
-+ /*
-+ * allow normal nice value to be set, but will not have any
-+ * effect on scheduling until the task not SCHED_NORMAL/
-+ * SCHED_BATCH
-+ */
-+ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
-+
-+ /*
-+ * __sched_setscheduler() ensures attr->sched_priority == 0 when
-+ * !rt_policy. Always setting this ensures that things like
-+ * getparam()/getattr() don't report silly values for !rt tasks.
-+ */
-+ p->rt_priority = attr->sched_priority;
-+ p->normal_prio = normal_prio(p);
-+}
-+
-+/*
-+ * check the target process has a UID that matches the current process's
-+ */
-+static bool check_same_owner(struct task_struct *p)
-+{
-+ const struct cred *cred = current_cred(), *pcred;
-+ guard(rcu)();
-+
-+ pcred = __task_cred(p);
-+ return (uid_eq(cred->euid, pcred->euid) ||
-+ uid_eq(cred->euid, pcred->uid));
-+}
-+
-+/*
-+ * Allow unprivileged RT tasks to decrease priority.
-+ * Only issue a capable test if needed and only once to avoid an audit
-+ * event on permitted non-privileged operations:
-+ */
-+static int user_check_sched_setscheduler(struct task_struct *p,
-+ const struct sched_attr *attr,
-+ int policy, int reset_on_fork)
-+{
-+ if (rt_policy(policy)) {
-+ unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
-+
-+ /* Can't set/change the rt policy: */
-+ if (policy != p->policy && !rlim_rtprio)
-+ goto req_priv;
-+
-+ /* Can't increase priority: */
-+ if (attr->sched_priority > p->rt_priority &&
-+ attr->sched_priority > rlim_rtprio)
-+ goto req_priv;
-+ }
-+
-+ /* Can't change other user's priorities: */
-+ if (!check_same_owner(p))
-+ goto req_priv;
-+
-+ /* Normal users shall not reset the sched_reset_on_fork flag: */
-+ if (p->sched_reset_on_fork && !reset_on_fork)
-+ goto req_priv;
-+
-+ return 0;
-+
-+req_priv:
-+ if (!capable(CAP_SYS_NICE))
-+ return -EPERM;
-+
-+ return 0;
-+}
-+
-+static int __sched_setscheduler(struct task_struct *p,
-+ const struct sched_attr *attr,
-+ bool user, bool pi)
-+{
-+ const struct sched_attr dl_squash_attr = {
-+ .size = sizeof(struct sched_attr),
-+ .sched_policy = SCHED_FIFO,
-+ .sched_nice = 0,
-+ .sched_priority = 99,
-+ };
-+ int oldpolicy = -1, policy = attr->sched_policy;
-+ int retval, newprio;
-+ struct balance_callback *head;
-+ unsigned long flags;
-+ struct rq *rq;
-+ int reset_on_fork;
-+ raw_spinlock_t *lock;
-+
-+ /* The pi code expects interrupts enabled */
-+ BUG_ON(pi && in_interrupt());
-+
-+ /*
-+ * Alt schedule FW supports SCHED_DEADLINE by squash it as prio 0 SCHED_FIFO
-+ */
-+ if (unlikely(SCHED_DEADLINE == policy)) {
-+ attr = &dl_squash_attr;
-+ policy = attr->sched_policy;
-+ }
-+recheck:
-+ /* Double check policy once rq lock held */
-+ if (policy < 0) {
-+ reset_on_fork = p->sched_reset_on_fork;
-+ policy = oldpolicy = p->policy;
-+ } else {
-+ reset_on_fork = !!(attr->sched_flags & SCHED_RESET_ON_FORK);
-+
-+ if (policy > SCHED_IDLE)
-+ return -EINVAL;
-+ }
-+
-+ if (attr->sched_flags & ~(SCHED_FLAG_ALL))
-+ return -EINVAL;
-+
-+ /*
-+ * Valid priorities for SCHED_FIFO and SCHED_RR are
-+ * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL and
-+ * SCHED_BATCH and SCHED_IDLE is 0.
-+ */
-+ if (attr->sched_priority < 0 ||
-+ (p->mm && attr->sched_priority > MAX_RT_PRIO - 1) ||
-+ (!p->mm && attr->sched_priority > MAX_RT_PRIO - 1))
-+ return -EINVAL;
-+ if ((SCHED_RR == policy || SCHED_FIFO == policy) !=
-+ (attr->sched_priority != 0))
-+ return -EINVAL;
-+
-+ if (user) {
-+ retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork);
-+ if (retval)
-+ return retval;
-+
-+ retval = security_task_setscheduler(p);
-+ if (retval)
-+ return retval;
-+ }
-+
-+ /*
-+ * Make sure no PI-waiters arrive (or leave) while we are
-+ * changing the priority of the task:
-+ */
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+
-+ /*
-+ * To be able to change p->policy safely, task_access_lock()
-+ * must be called.
-+ * IF use task_access_lock() here:
-+ * For the task p which is not running, reading rq->stop is
-+ * racy but acceptable as ->stop doesn't change much.
-+ * An enhancemnet can be made to read rq->stop saftly.
-+ */
-+ rq = __task_access_lock(p, &lock);
-+
-+ /*
-+ * Changing the policy of the stop threads its a very bad idea
-+ */
-+ if (p == rq->stop) {
-+ retval = -EINVAL;
-+ goto unlock;
-+ }
-+
-+ /*
-+ * If not changing anything there's no need to proceed further:
-+ */
-+ if (unlikely(policy == p->policy)) {
-+ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
-+ goto change;
-+ if (!rt_policy(policy) &&
-+ NICE_TO_PRIO(attr->sched_nice) != p->static_prio)
-+ goto change;
-+
-+ p->sched_reset_on_fork = reset_on_fork;
-+ retval = 0;
-+ goto unlock;
-+ }
-+change:
-+
-+ /* Re-check policy now with rq lock held */
-+ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
-+ policy = oldpolicy = -1;
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+ goto recheck;
-+ }
-+
-+ p->sched_reset_on_fork = reset_on_fork;
-+
-+ newprio = __normal_prio(policy, attr->sched_priority, NICE_TO_PRIO(attr->sched_nice));
-+ if (pi) {
-+ /*
-+ * Take priority boosted tasks into account. If the new
-+ * effective priority is unchanged, we just store the new
-+ * normal parameters and do not touch the scheduler class and
-+ * the runqueue. This will be done when the task deboost
-+ * itself.
-+ */
-+ newprio = rt_effective_prio(p, newprio);
-+ }
-+
-+ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
-+ __setscheduler_params(p, attr);
-+ __setscheduler_prio(p, newprio);
-+ }
-+
-+ check_task_changed(p, rq);
-+
-+ /* Avoid rq from going away on us: */
-+ preempt_disable();
-+ head = splice_balance_callbacks(rq);
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+
-+ if (pi)
-+ rt_mutex_adjust_pi(p);
-+
-+ /* Run balance callbacks after we've adjusted the PI chain: */
-+ balance_callbacks(rq, head);
-+ preempt_enable();
-+
-+ return 0;
-+
-+unlock:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+ return retval;
-+}
-+
-+static int _sched_setscheduler(struct task_struct *p, int policy,
-+ const struct sched_param *param, bool check)
-+{
-+ struct sched_attr attr = {
-+ .sched_policy = policy,
-+ .sched_priority = param->sched_priority,
-+ .sched_nice = PRIO_TO_NICE(p->static_prio),
-+ };
-+
-+ /* Fixup the legacy SCHED_RESET_ON_FORK hack. */
-+ if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
-+ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-+ policy &= ~SCHED_RESET_ON_FORK;
-+ attr.sched_policy = policy;
-+ }
-+
-+ return __sched_setscheduler(p, &attr, check, true);
-+}
-+
-+/**
-+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
-+ * @p: the task in question.
-+ * @policy: new policy.
-+ * @param: structure containing the new RT priority.
-+ *
-+ * Use sched_set_fifo(), read its comment.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ *
-+ * NOTE that the task may be already dead.
-+ */
-+int sched_setscheduler(struct task_struct *p, int policy,
-+ const struct sched_param *param)
-+{
-+ return _sched_setscheduler(p, policy, param, true);
-+}
-+
-+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
-+{
-+ return __sched_setscheduler(p, attr, true, true);
-+}
-+
-+int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
-+{
-+ return __sched_setscheduler(p, attr, false, true);
-+}
-+EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
-+
-+/**
-+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
-+ * @p: the task in question.
-+ * @policy: new policy.
-+ * @param: structure containing the new RT priority.
-+ *
-+ * Just like sched_setscheduler, only don't bother checking if the
-+ * current context has permission. For example, this is needed in
-+ * stop_machine(): we create temporary high priority worker threads,
-+ * but our caller might not have that capability.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ */
-+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
-+ const struct sched_param *param)
-+{
-+ return _sched_setscheduler(p, policy, param, false);
-+}
-+
-+/*
-+ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
-+ * incapable of resource management, which is the one thing an OS really should
-+ * be doing.
-+ *
-+ * This is of course the reason it is limited to privileged users only.
-+ *
-+ * Worse still; it is fundamentally impossible to compose static priority
-+ * workloads. You cannot take two correctly working static prio workloads
-+ * and smash them together and still expect them to work.
-+ *
-+ * For this reason 'all' FIFO tasks the kernel creates are basically at:
-+ *
-+ * MAX_RT_PRIO / 2
-+ *
-+ * The administrator _MUST_ configure the system, the kernel simply doesn't
-+ * know enough information to make a sensible choice.
-+ */
-+void sched_set_fifo(struct task_struct *p)
-+{
-+ struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
-+ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
-+}
-+EXPORT_SYMBOL_GPL(sched_set_fifo);
-+
-+/*
-+ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
-+ */
-+void sched_set_fifo_low(struct task_struct *p)
-+{
-+ struct sched_param sp = { .sched_priority = 1 };
-+ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
-+}
-+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
-+
-+void sched_set_normal(struct task_struct *p, int nice)
-+{
-+ struct sched_attr attr = {
-+ .sched_policy = SCHED_NORMAL,
-+ .sched_nice = nice,
-+ };
-+ WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
-+}
-+EXPORT_SYMBOL_GPL(sched_set_normal);
-+
-+static int
-+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
-+{
-+ struct sched_param lparam;
-+
-+ if (!param || pid < 0)
-+ return -EINVAL;
-+ if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
-+ return -EFAULT;
-+
-+ CLASS(find_get_task, p)(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ return sched_setscheduler(p, policy, &lparam);
-+}
-+
-+/*
-+ * Mimics kernel/events/core.c perf_copy_attr().
-+ */
-+static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
-+{
-+ u32 size;
-+ int ret;
-+
-+ /* Zero the full structure, so that a short copy will be nice: */
-+ memset(attr, 0, sizeof(*attr));
-+
-+ ret = get_user(size, &uattr->size);
-+ if (ret)
-+ return ret;
-+
-+ /* ABI compatibility quirk: */
-+ if (!size)
-+ size = SCHED_ATTR_SIZE_VER0;
-+
-+ if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
-+ goto err_size;
-+
-+ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
-+ if (ret) {
-+ if (ret == -E2BIG)
-+ goto err_size;
-+ return ret;
-+ }
-+
-+ /*
-+ * XXX: Do we want to be lenient like existing syscalls; or do we want
-+ * to be strict and return an error on out-of-bounds values?
-+ */
-+ attr->sched_nice = clamp(attr->sched_nice, -20, 19);
-+
-+ /* sched/core.c uses zero here but we already know ret is zero */
-+ return 0;
-+
-+err_size:
-+ put_user(sizeof(*attr), &uattr->size);
-+ return -E2BIG;
-+}
-+
-+/**
-+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
-+ * @pid: the pid in question.
-+ * @policy: new policy.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ * @param: structure containing the new RT priority.
-+ */
-+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
-+{
-+ if (policy < 0)
-+ return -EINVAL;
-+
-+ return do_sched_setscheduler(pid, policy, param);
-+}
-+
-+/**
-+ * sys_sched_setparam - set/change the RT priority of a thread
-+ * @pid: the pid in question.
-+ * @param: structure containing the new RT priority.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ */
-+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
-+{
-+ return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
-+}
-+
-+static void get_params(struct task_struct *p, struct sched_attr *attr)
-+{
-+ if (task_has_rt_policy(p))
-+ attr->sched_priority = p->rt_priority;
-+ else
-+ attr->sched_nice = task_nice(p);
-+}
-+
-+/**
-+ * sys_sched_setattr - same as above, but with extended sched_attr
-+ * @pid: the pid in question.
-+ * @uattr: structure containing the extended parameters.
-+ */
-+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
-+ unsigned int, flags)
-+{
-+ struct sched_attr attr;
-+ int retval;
-+
-+ if (!uattr || pid < 0 || flags)
-+ return -EINVAL;
-+
-+ retval = sched_copy_attr(uattr, &attr);
-+ if (retval)
-+ return retval;
-+
-+ if ((int)attr.sched_policy < 0)
-+ return -EINVAL;
-+
-+ CLASS(find_get_task, p)(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
-+ get_params(p, &attr);
-+
-+ return sched_setattr(p, &attr);
-+}
-+
-+/**
-+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
-+ * @pid: the pid in question.
-+ *
-+ * Return: On success, the policy of the thread. Otherwise, a negative error
-+ * code.
-+ */
-+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
-+{
-+ struct task_struct *p;
-+ int retval = -EINVAL;
-+
-+ if (pid < 0)
-+ return -ESRCH;
-+
-+ guard(rcu)();
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ retval = security_task_getscheduler(p);
-+ if (!retval)
-+ retval = p->policy;
-+
-+ return retval;
-+}
-+
-+/**
-+ * sys_sched_getscheduler - get the RT priority of a thread
-+ * @pid: the pid in question.
-+ * @param: structure containing the RT priority.
-+ *
-+ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
-+ * code.
-+ */
-+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
-+{
-+ struct sched_param lp = { .sched_priority = 0 };
-+ struct task_struct *p;
-+
-+ if (!param || pid < 0)
-+ return -EINVAL;
-+
-+ scoped_guard (rcu) {
-+ int retval;
-+
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -EINVAL;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ if (task_has_rt_policy(p))
-+ lp.sched_priority = p->rt_priority;
-+ }
-+
-+ /*
-+ * This one might sleep, we cannot do it with a spinlock held ...
-+ */
-+ return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
-+}
-+
-+/*
-+ * Copy the kernel size attribute structure (which might be larger
-+ * than what user-space knows about) to user-space.
-+ *
-+ * Note that all cases are valid: user-space buffer can be larger or
-+ * smaller than the kernel-space buffer. The usual case is that both
-+ * have the same size.
-+ */
-+static int
-+sched_attr_copy_to_user(struct sched_attr __user *uattr,
-+ struct sched_attr *kattr,
-+ unsigned int usize)
-+{
-+ unsigned int ksize = sizeof(*kattr);
-+
-+ if (!access_ok(uattr, usize))
-+ return -EFAULT;
-+
-+ /*
-+ * sched_getattr() ABI forwards and backwards compatibility:
-+ *
-+ * If usize == ksize then we just copy everything to user-space and all is good.
-+ *
-+ * If usize < ksize then we only copy as much as user-space has space for,
-+ * this keeps ABI compatibility as well. We skip the rest.
-+ *
-+ * If usize > ksize then user-space is using a newer version of the ABI,
-+ * which part the kernel doesn't know about. Just ignore it - tooling can
-+ * detect the kernel's knowledge of attributes from the attr->size value
-+ * which is set to ksize in this case.
-+ */
-+ kattr->size = min(usize, ksize);
-+
-+ if (copy_to_user(uattr, kattr, kattr->size))
-+ return -EFAULT;
-+
-+ return 0;
-+}
-+
-+/**
-+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
-+ * @pid: the pid in question.
-+ * @uattr: structure containing the extended parameters.
-+ * @usize: sizeof(attr) for fwd/bwd comp.
-+ * @flags: for future extension.
-+ */
-+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-+ unsigned int, usize, unsigned int, flags)
-+{
-+ struct sched_attr kattr = { };
-+ struct task_struct *p;
-+ int retval;
-+
-+ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
-+ usize < SCHED_ATTR_SIZE_VER0 || flags)
-+ return -EINVAL;
-+
-+ scoped_guard (rcu) {
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ kattr.sched_policy = p->policy;
-+ if (p->sched_reset_on_fork)
-+ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-+ get_params(p, &kattr);
-+ kattr.sched_flags &= SCHED_FLAG_ALL;
-+
-+#ifdef CONFIG_UCLAMP_TASK
-+ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
-+ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
-+#endif
-+ }
-+
-+ return sched_attr_copy_to_user(uattr, &kattr, usize);
-+}
-+
-+#ifdef CONFIG_SMP
-+int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
-+{
-+ return 0;
-+}
-+#endif
-+
-+static int
-+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
-+{
-+ int retval;
-+ cpumask_var_t cpus_allowed, new_mask;
-+
-+ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
-+ return -ENOMEM;
-+
-+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
-+ retval = -ENOMEM;
-+ goto out_free_cpus_allowed;
-+ }
-+
-+ cpuset_cpus_allowed(p, cpus_allowed);
-+ cpumask_and(new_mask, ctx->new_mask, cpus_allowed);
-+
-+ ctx->new_mask = new_mask;
-+ ctx->flags |= SCA_CHECK;
-+
-+ retval = __set_cpus_allowed_ptr(p, ctx);
-+ if (retval)
-+ goto out_free_new_mask;
-+
-+ cpuset_cpus_allowed(p, cpus_allowed);
-+ if (!cpumask_subset(new_mask, cpus_allowed)) {
-+ /*
-+ * We must have raced with a concurrent cpuset
-+ * update. Just reset the cpus_allowed to the
-+ * cpuset's cpus_allowed
-+ */
-+ cpumask_copy(new_mask, cpus_allowed);
-+
-+ /*
-+ * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr()
-+ * will restore the previous user_cpus_ptr value.
-+ *
-+ * In the unlikely event a previous user_cpus_ptr exists,
-+ * we need to further restrict the mask to what is allowed
-+ * by that old user_cpus_ptr.
-+ */
-+ if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) {
-+ bool empty = !cpumask_and(new_mask, new_mask,
-+ ctx->user_mask);
-+
-+ if (WARN_ON_ONCE(empty))
-+ cpumask_copy(new_mask, cpus_allowed);
-+ }
-+ __set_cpus_allowed_ptr(p, ctx);
-+ retval = -EINVAL;
-+ }
-+
-+out_free_new_mask:
-+ free_cpumask_var(new_mask);
-+out_free_cpus_allowed:
-+ free_cpumask_var(cpus_allowed);
-+ return retval;
-+}
-+
-+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
-+{
-+ struct affinity_context ac;
-+ struct cpumask *user_mask;
-+ int retval;
-+
-+ CLASS(find_get_task, p)(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ if (p->flags & PF_NO_SETAFFINITY)
-+ return -EINVAL;
-+
-+ if (!check_same_owner(p)) {
-+ guard(rcu)();
-+ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
-+ return -EPERM;
-+ }
-+
-+ retval = security_task_setscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ /*
-+ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
-+ * alloc_user_cpus_ptr() returns NULL.
-+ */
-+ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
-+ if (user_mask) {
-+ cpumask_copy(user_mask, in_mask);
-+ } else if (IS_ENABLED(CONFIG_SMP)) {
-+ return -ENOMEM;
-+ }
-+
-+ ac = (struct affinity_context){
-+ .new_mask = in_mask,
-+ .user_mask = user_mask,
-+ .flags = SCA_USER,
-+ };
-+
-+ retval = __sched_setaffinity(p, &ac);
-+ kfree(ac.user_mask);
-+
-+ return retval;
-+}
-+
-+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
-+ struct cpumask *new_mask)
-+{
-+ if (len < cpumask_size())
-+ cpumask_clear(new_mask);
-+ else if (len > cpumask_size())
-+ len = cpumask_size();
-+
-+ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
-+}
-+
-+/**
-+ * sys_sched_setaffinity - set the CPU affinity of a process
-+ * @pid: pid of the process
-+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
-+ * @user_mask_ptr: user-space pointer to the new CPU mask
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ */
-+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
-+ unsigned long __user *, user_mask_ptr)
-+{
-+ cpumask_var_t new_mask;
-+ int retval;
-+
-+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
-+ return -ENOMEM;
-+
-+ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
-+ if (retval == 0)
-+ retval = sched_setaffinity(pid, new_mask);
-+ free_cpumask_var(new_mask);
-+ return retval;
-+}
-+
-+long sched_getaffinity(pid_t pid, cpumask_t *mask)
-+{
-+ struct task_struct *p;
-+ int retval;
-+
-+ guard(rcu)();
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ guard(raw_spinlock_irqsave)(&p->pi_lock);
-+ cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
-+
-+ return retval;
-+}
-+
-+/**
-+ * sys_sched_getaffinity - get the CPU affinity of a process
-+ * @pid: pid of the process
-+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
-+ * @user_mask_ptr: user-space pointer to hold the current CPU mask
-+ *
-+ * Return: size of CPU mask copied to user_mask_ptr on success. An
-+ * error code otherwise.
-+ */
-+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
-+ unsigned long __user *, user_mask_ptr)
-+{
-+ int ret;
-+ cpumask_var_t mask;
-+
-+ if ((len * BITS_PER_BYTE) < nr_cpu_ids)
-+ return -EINVAL;
-+ if (len & (sizeof(unsigned long)-1))
-+ return -EINVAL;
-+
-+ if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
-+ return -ENOMEM;
-+
-+ ret = sched_getaffinity(pid, mask);
-+ if (ret == 0) {
-+ unsigned int retlen = min(len, cpumask_size());
-+
-+ if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen))
-+ ret = -EFAULT;
-+ else
-+ ret = retlen;
-+ }
-+ free_cpumask_var(mask);
-+
-+ return ret;
-+}
-+
-+static void do_sched_yield(void)
-+{
-+ struct rq *rq;
-+ struct rq_flags rf;
-+ struct task_struct *p;
-+
-+ if (!sched_yield_type)
-+ return;
-+
-+ rq = this_rq_lock_irq(&rf);
-+
-+ schedstat_inc(rq->yld_count);
-+
-+ p = current;
-+ if (rt_task(p)) {
-+ if (task_on_rq_queued(p))
-+ requeue_task(p, rq);
-+ } else if (rq->nr_running > 1) {
-+ do_sched_yield_type_1(p, rq);
-+ if (task_on_rq_queued(p))
-+ requeue_task(p, rq);
-+ }
-+
-+ preempt_disable();
-+ raw_spin_unlock_irq(&rq->lock);
-+ sched_preempt_enable_no_resched();
-+
-+ schedule();
-+}
-+
-+/**
-+ * sys_sched_yield - yield the current processor to other threads.
-+ *
-+ * This function yields the current CPU to other tasks. If there are no
-+ * other threads running on this CPU then this function will return.
-+ *
-+ * Return: 0.
-+ */
-+SYSCALL_DEFINE0(sched_yield)
-+{
-+ do_sched_yield();
-+ return 0;
-+}
-+
-+#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
-+int __sched __cond_resched(void)
-+{
-+ if (should_resched(0)) {
-+ preempt_schedule_common();
-+ return 1;
-+ }
-+ /*
-+ * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
-+ * whether the current CPU is in an RCU read-side critical section,
-+ * so the tick can report quiescent states even for CPUs looping
-+ * in kernel context. In contrast, in non-preemptible kernels,
-+ * RCU readers leave no in-memory hints, which means that CPU-bound
-+ * processes executing in kernel context might never report an
-+ * RCU quiescent state. Therefore, the following code causes
-+ * cond_resched() to report a quiescent state, but only when RCU
-+ * is in urgent need of one.
-+ */
-+#ifndef CONFIG_PREEMPT_RCU
-+ rcu_all_qs();
-+#endif
-+ return 0;
-+}
-+EXPORT_SYMBOL(__cond_resched);
-+#endif
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#define cond_resched_dynamic_enabled __cond_resched
-+#define cond_resched_dynamic_disabled ((void *)&__static_call_return0)
-+DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
-+EXPORT_STATIC_CALL_TRAMP(cond_resched);
-+
-+#define might_resched_dynamic_enabled __cond_resched
-+#define might_resched_dynamic_disabled ((void *)&__static_call_return0)
-+DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
-+EXPORT_STATIC_CALL_TRAMP(might_resched);
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
-+int __sched dynamic_cond_resched(void)
-+{
-+ klp_sched_try_switch();
-+ if (!static_branch_unlikely(&sk_dynamic_cond_resched))
-+ return 0;
-+ return __cond_resched();
-+}
-+EXPORT_SYMBOL(dynamic_cond_resched);
-+
-+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
-+int __sched dynamic_might_resched(void)
-+{
-+ if (!static_branch_unlikely(&sk_dynamic_might_resched))
-+ return 0;
-+ return __cond_resched();
-+}
-+EXPORT_SYMBOL(dynamic_might_resched);
-+#endif
-+#endif
-+
-+/*
-+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
-+ * call schedule, and on return reacquire the lock.
-+ *
-+ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
-+ * operations here to prevent schedule() from being called twice (once via
-+ * spin_unlock(), once by hand).
-+ */
-+int __cond_resched_lock(spinlock_t *lock)
-+{
-+ int resched = should_resched(PREEMPT_LOCK_OFFSET);
-+ int ret = 0;
-+
-+ lockdep_assert_held(lock);
-+
-+ if (spin_needbreak(lock) || resched) {
-+ spin_unlock(lock);
-+ if (!_cond_resched())
-+ cpu_relax();
-+ ret = 1;
-+ spin_lock(lock);
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL(__cond_resched_lock);
-+
-+int __cond_resched_rwlock_read(rwlock_t *lock)
-+{
-+ int resched = should_resched(PREEMPT_LOCK_OFFSET);
-+ int ret = 0;
-+
-+ lockdep_assert_held_read(lock);
-+
-+ if (rwlock_needbreak(lock) || resched) {
-+ read_unlock(lock);
-+ if (!_cond_resched())
-+ cpu_relax();
-+ ret = 1;
-+ read_lock(lock);
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL(__cond_resched_rwlock_read);
-+
-+int __cond_resched_rwlock_write(rwlock_t *lock)
-+{
-+ int resched = should_resched(PREEMPT_LOCK_OFFSET);
-+ int ret = 0;
-+
-+ lockdep_assert_held_write(lock);
-+
-+ if (rwlock_needbreak(lock) || resched) {
-+ write_unlock(lock);
-+ if (!_cond_resched())
-+ cpu_relax();
-+ ret = 1;
-+ write_lock(lock);
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL(__cond_resched_rwlock_write);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+
-+#ifdef CONFIG_GENERIC_ENTRY
-+#include <linux/entry-common.h>
-+#endif
-+
-+/*
-+ * SC:cond_resched
-+ * SC:might_resched
-+ * SC:preempt_schedule
-+ * SC:preempt_schedule_notrace
-+ * SC:irqentry_exit_cond_resched
-+ *
-+ *
-+ * NONE:
-+ * cond_resched <- __cond_resched
-+ * might_resched <- RET0
-+ * preempt_schedule <- NOP
-+ * preempt_schedule_notrace <- NOP
-+ * irqentry_exit_cond_resched <- NOP
-+ *
-+ * VOLUNTARY:
-+ * cond_resched <- __cond_resched
-+ * might_resched <- __cond_resched
-+ * preempt_schedule <- NOP
-+ * preempt_schedule_notrace <- NOP
-+ * irqentry_exit_cond_resched <- NOP
-+ *
-+ * FULL:
-+ * cond_resched <- RET0
-+ * might_resched <- RET0
-+ * preempt_schedule <- preempt_schedule
-+ * preempt_schedule_notrace <- preempt_schedule_notrace
-+ * irqentry_exit_cond_resched <- irqentry_exit_cond_resched
-+ */
-+
-+enum {
-+ preempt_dynamic_undefined = -1,
-+ preempt_dynamic_none,
-+ preempt_dynamic_voluntary,
-+ preempt_dynamic_full,
-+};
-+
-+int preempt_dynamic_mode = preempt_dynamic_undefined;
-+
-+int sched_dynamic_mode(const char *str)
-+{
-+ if (!strcmp(str, "none"))
-+ return preempt_dynamic_none;
-+
-+ if (!strcmp(str, "voluntary"))
-+ return preempt_dynamic_voluntary;
-+
-+ if (!strcmp(str, "full"))
-+ return preempt_dynamic_full;
-+
-+ return -EINVAL;
-+}
-+
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled)
-+#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled)
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key)
-+#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key)
-+#else
-+#error "Unsupported PREEMPT_DYNAMIC mechanism"
-+#endif
-+
-+static DEFINE_MUTEX(sched_dynamic_mutex);
-+static bool klp_override;
-+
-+static void __sched_dynamic_update(int mode)
-+{
-+ /*
-+ * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
-+ * the ZERO state, which is invalid.
-+ */
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_enable(might_resched);
-+ preempt_dynamic_enable(preempt_schedule);
-+ preempt_dynamic_enable(preempt_schedule_notrace);
-+ preempt_dynamic_enable(irqentry_exit_cond_resched);
-+
-+ switch (mode) {
-+ case preempt_dynamic_none:
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_disable(might_resched);
-+ preempt_dynamic_disable(preempt_schedule);
-+ preempt_dynamic_disable(preempt_schedule_notrace);
-+ preempt_dynamic_disable(irqentry_exit_cond_resched);
-+ if (mode != preempt_dynamic_mode)
-+ pr_info("Dynamic Preempt: none\n");
-+ break;
-+
-+ case preempt_dynamic_voluntary:
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_enable(might_resched);
-+ preempt_dynamic_disable(preempt_schedule);
-+ preempt_dynamic_disable(preempt_schedule_notrace);
-+ preempt_dynamic_disable(irqentry_exit_cond_resched);
-+ if (mode != preempt_dynamic_mode)
-+ pr_info("Dynamic Preempt: voluntary\n");
-+ break;
-+
-+ case preempt_dynamic_full:
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_disable(might_resched);
-+ preempt_dynamic_enable(preempt_schedule);
-+ preempt_dynamic_enable(preempt_schedule_notrace);
-+ preempt_dynamic_enable(irqentry_exit_cond_resched);
-+ if (mode != preempt_dynamic_mode)
-+ pr_info("Dynamic Preempt: full\n");
-+ break;
-+ }
-+
-+ preempt_dynamic_mode = mode;
-+}
-+
-+void sched_dynamic_update(int mode)
-+{
-+ mutex_lock(&sched_dynamic_mutex);
-+ __sched_dynamic_update(mode);
-+ mutex_unlock(&sched_dynamic_mutex);
-+}
-+
-+#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
-+
-+static int klp_cond_resched(void)
-+{
-+ __klp_sched_try_switch();
-+ return __cond_resched();
-+}
-+
-+void sched_dynamic_klp_enable(void)
-+{
-+ mutex_lock(&sched_dynamic_mutex);
-+
-+ klp_override = true;
-+ static_call_update(cond_resched, klp_cond_resched);
-+
-+ mutex_unlock(&sched_dynamic_mutex);
-+}
-+
-+void sched_dynamic_klp_disable(void)
-+{
-+ mutex_lock(&sched_dynamic_mutex);
-+
-+ klp_override = false;
-+ __sched_dynamic_update(preempt_dynamic_mode);
-+
-+ mutex_unlock(&sched_dynamic_mutex);
-+}
-+
-+#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-+
-+
-+static int __init setup_preempt_mode(char *str)
-+{
-+ int mode = sched_dynamic_mode(str);
-+ if (mode < 0) {
-+ pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
-+ return 0;
-+ }
-+
-+ sched_dynamic_update(mode);
-+ return 1;
-+}
-+__setup("preempt=", setup_preempt_mode);
-+
-+static void __init preempt_dynamic_init(void)
-+{
-+ if (preempt_dynamic_mode == preempt_dynamic_undefined) {
-+ if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
-+ sched_dynamic_update(preempt_dynamic_none);
-+ } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
-+ sched_dynamic_update(preempt_dynamic_voluntary);
-+ } else {
-+ /* Default static call setting, nothing to do */
-+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
-+ preempt_dynamic_mode = preempt_dynamic_full;
-+ pr_info("Dynamic Preempt: full\n");
-+ }
-+ }
-+}
-+
-+#define PREEMPT_MODEL_ACCESSOR(mode) \
-+ bool preempt_model_##mode(void) \
-+ { \
-+ WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
-+ return preempt_dynamic_mode == preempt_dynamic_##mode; \
-+ } \
-+ EXPORT_SYMBOL_GPL(preempt_model_##mode)
-+
-+PREEMPT_MODEL_ACCESSOR(none);
-+PREEMPT_MODEL_ACCESSOR(voluntary);
-+PREEMPT_MODEL_ACCESSOR(full);
-+
-+#else /* !CONFIG_PREEMPT_DYNAMIC */
-+
-+static inline void preempt_dynamic_init(void) { }
-+
-+#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
-+
-+/**
-+ * yield - yield the current processor to other threads.
-+ *
-+ * Do not ever use this function, there's a 99% chance you're doing it wrong.
-+ *
-+ * The scheduler is at all times free to pick the calling task as the most
-+ * eligible task to run, if removing the yield() call from your code breaks
-+ * it, it's already broken.
-+ *
-+ * Typical broken usage is:
-+ *
-+ * while (!event)
-+ * yield();
-+ *
-+ * where one assumes that yield() will let 'the other' process run that will
-+ * make event true. If the current task is a SCHED_FIFO task that will never
-+ * happen. Never use yield() as a progress guarantee!!
-+ *
-+ * If you want to use yield() to wait for something, use wait_event().
-+ * If you want to use yield() to be 'nice' for others, use cond_resched().
-+ * If you still want to use yield(), do not!
-+ */
-+void __sched yield(void)
-+{
-+ set_current_state(TASK_RUNNING);
-+ do_sched_yield();
-+}
-+EXPORT_SYMBOL(yield);
-+
-+/**
-+ * yield_to - yield the current processor to another thread in
-+ * your thread group, or accelerate that thread toward the
-+ * processor it's on.
-+ * @p: target task
-+ * @preempt: whether task preemption is allowed or not
-+ *
-+ * It's the caller's job to ensure that the target task struct
-+ * can't go away on us before we can do any checks.
-+ *
-+ * In Alt schedule FW, yield_to is not supported.
-+ *
-+ * Return:
-+ * true (>0) if we indeed boosted the target task.
-+ * false (0) if we failed to boost the target.
-+ * -ESRCH if there's no task to yield to.
-+ */
-+int __sched yield_to(struct task_struct *p, bool preempt)
-+{
-+ return 0;
-+}
-+EXPORT_SYMBOL_GPL(yield_to);
-+
-+int io_schedule_prepare(void)
-+{
-+ int old_iowait = current->in_iowait;
-+
-+ current->in_iowait = 1;
-+ blk_flush_plug(current->plug, true);
-+ return old_iowait;
-+}
-+
-+void io_schedule_finish(int token)
-+{
-+ current->in_iowait = token;
-+}
-+
-+/*
-+ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
-+ * that process accounting knows that this is a task in IO wait state.
-+ *
-+ * But don't do that if it is a deliberate, throttling IO wait (this task
-+ * has set its backing_dev_info: the queue against which it should throttle)
-+ */
-+
-+long __sched io_schedule_timeout(long timeout)
-+{
-+ int token;
-+ long ret;
-+
-+ token = io_schedule_prepare();
-+ ret = schedule_timeout(timeout);
-+ io_schedule_finish(token);
-+
-+ return ret;
-+}
-+EXPORT_SYMBOL(io_schedule_timeout);
-+
-+void __sched io_schedule(void)
-+{
-+ int token;
-+
-+ token = io_schedule_prepare();
-+ schedule();
-+ io_schedule_finish(token);
-+}
-+EXPORT_SYMBOL(io_schedule);
-+
-+/**
-+ * sys_sched_get_priority_max - return maximum RT priority.
-+ * @policy: scheduling class.
-+ *
-+ * Return: On success, this syscall returns the maximum
-+ * rt_priority that can be used by a given scheduling class.
-+ * On failure, a negative error code is returned.
-+ */
-+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
-+{
-+ int ret = -EINVAL;
-+
-+ switch (policy) {
-+ case SCHED_FIFO:
-+ case SCHED_RR:
-+ ret = MAX_RT_PRIO - 1;
-+ break;
-+ case SCHED_NORMAL:
-+ case SCHED_BATCH:
-+ case SCHED_IDLE:
-+ ret = 0;
-+ break;
-+ }
-+ return ret;
-+}
-+
-+/**
-+ * sys_sched_get_priority_min - return minimum RT priority.
-+ * @policy: scheduling class.
-+ *
-+ * Return: On success, this syscall returns the minimum
-+ * rt_priority that can be used by a given scheduling class.
-+ * On failure, a negative error code is returned.
-+ */
-+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
-+{
-+ int ret = -EINVAL;
-+
-+ switch (policy) {
-+ case SCHED_FIFO:
-+ case SCHED_RR:
-+ ret = 1;
-+ break;
-+ case SCHED_NORMAL:
-+ case SCHED_BATCH:
-+ case SCHED_IDLE:
-+ ret = 0;
-+ break;
-+ }
-+ return ret;
-+}
-+
-+static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
-+{
-+ struct task_struct *p;
-+ int retval;
-+
-+ alt_sched_debug();
-+
-+ if (pid < 0)
-+ return -EINVAL;
-+
-+ guard(rcu)();
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -EINVAL;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ *t = ns_to_timespec64(sysctl_sched_base_slice);
-+ return 0;
-+}
-+
-+/**
-+ * sys_sched_rr_get_interval - return the default timeslice of a process.
-+ * @pid: pid of the process.
-+ * @interval: userspace pointer to the timeslice value.
-+ *
-+ *
-+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
-+ * an error code.
-+ */
-+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
-+ struct __kernel_timespec __user *, interval)
-+{
-+ struct timespec64 t;
-+ int retval = sched_rr_get_interval(pid, &t);
-+
-+ if (retval == 0)
-+ retval = put_timespec64(&t, interval);
-+
-+ return retval;
-+}
-+
-+#ifdef CONFIG_COMPAT_32BIT_TIME
-+SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
-+ struct old_timespec32 __user *, interval)
-+{
-+ struct timespec64 t;
-+ int retval = sched_rr_get_interval(pid, &t);
-+
-+ if (retval == 0)
-+ retval = put_old_timespec32(&t, interval);
-+ return retval;
-+}
-+#endif
-+
-+void sched_show_task(struct task_struct *p)
-+{
-+ unsigned long free = 0;
-+ int ppid;
-+
-+ if (!try_get_task_stack(p))
-+ return;
-+
-+ pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
-+
-+ if (task_is_running(p))
-+ pr_cont(" running task ");
-+#ifdef CONFIG_DEBUG_STACK_USAGE
-+ free = stack_not_used(p);
-+#endif
-+ ppid = 0;
-+ rcu_read_lock();
-+ if (pid_alive(p))
-+ ppid = task_pid_nr(rcu_dereference(p->real_parent));
-+ rcu_read_unlock();
-+ pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
-+ free, task_pid_nr(p), task_tgid_nr(p),
-+ ppid, read_task_thread_flags(p));
-+
-+ print_worker_info(KERN_INFO, p);
-+ print_stop_info(KERN_INFO, p);
-+ show_stack(p, NULL, KERN_INFO);
-+ put_task_stack(p);
-+}
-+EXPORT_SYMBOL_GPL(sched_show_task);
-+
-+static inline bool
-+state_filter_match(unsigned long state_filter, struct task_struct *p)
-+{
-+ unsigned int state = READ_ONCE(p->__state);
-+
-+ /* no filter, everything matches */
-+ if (!state_filter)
-+ return true;
-+
-+ /* filter, but doesn't match */
-+ if (!(state & state_filter))
-+ return false;
-+
-+ /*
-+ * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
-+ * TASK_KILLABLE).
-+ */
-+ if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD))
-+ return false;
-+
-+ return true;
-+}
-+
-+
-+void show_state_filter(unsigned int state_filter)
-+{
-+ struct task_struct *g, *p;
-+
-+ rcu_read_lock();
-+ for_each_process_thread(g, p) {
-+ /*
-+ * reset the NMI-timeout, listing all files on a slow
-+ * console might take a lot of time:
-+ * Also, reset softlockup watchdogs on all CPUs, because
-+ * another CPU might be blocked waiting for us to process
-+ * an IPI.
-+ */
-+ touch_nmi_watchdog();
-+ touch_all_softlockup_watchdogs();
-+ if (state_filter_match(state_filter, p))
-+ sched_show_task(p);
-+ }
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+ /* TODO: Alt schedule FW should support this
-+ if (!state_filter)
-+ sysrq_sched_debug_show();
-+ */
-+#endif
-+ rcu_read_unlock();
-+ /*
-+ * Only show locks if all tasks are dumped:
-+ */
-+ if (!state_filter)
-+ debug_show_all_locks();
-+}
-+
-+void dump_cpu_task(int cpu)
-+{
-+ if (cpu == smp_processor_id() && in_hardirq()) {
-+ struct pt_regs *regs;
-+
-+ regs = get_irq_regs();
-+ if (regs) {
-+ show_regs(regs);
-+ return;
-+ }
-+ }
-+
-+ if (trigger_single_cpu_backtrace(cpu))
-+ return;
-+
-+ pr_info("Task dump for CPU %d:\n", cpu);
-+ sched_show_task(cpu_curr(cpu));
-+}
-+
-+/**
-+ * init_idle - set up an idle thread for a given CPU
-+ * @idle: task in question
-+ * @cpu: CPU the idle task belongs to
-+ *
-+ * NOTE: this function does not set the idle thread's NEED_RESCHED
-+ * flag, to make booting more robust.
-+ */
-+void __init init_idle(struct task_struct *idle, int cpu)
-+{
-+#ifdef CONFIG_SMP
-+ struct affinity_context ac = (struct affinity_context) {
-+ .new_mask = cpumask_of(cpu),
-+ .flags = 0,
-+ };
-+#endif
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ __sched_fork(0, idle);
-+
-+ raw_spin_lock_irqsave(&idle->pi_lock, flags);
-+ raw_spin_lock(&rq->lock);
-+
-+ idle->last_ran = rq->clock_task;
-+ idle->__state = TASK_RUNNING;
-+ /*
-+ * PF_KTHREAD should already be set at this point; regardless, make it
-+ * look like a proper per-CPU kthread.
-+ */
-+ idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
-+ kthread_set_per_cpu(idle, cpu);
-+
-+ sched_queue_init_idle(&rq->queue, idle);
-+
-+#ifdef CONFIG_SMP
-+ /*
-+ * It's possible that init_idle() gets called multiple times on a task,
-+ * in that case do_set_cpus_allowed() will not do the right thing.
-+ *
-+ * And since this is boot we can forgo the serialisation.
-+ */
-+ set_cpus_allowed_common(idle, &ac);
-+#endif
-+
-+ /* Silence PROVE_RCU */
-+ rcu_read_lock();
-+ __set_task_cpu(idle, cpu);
-+ rcu_read_unlock();
-+
-+ rq->idle = idle;
-+ rcu_assign_pointer(rq->curr, idle);
-+ idle->on_cpu = 1;
-+
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
-+
-+ /* Set the preempt count _outside_ the spinlocks! */
-+ init_idle_preempt_count(idle, cpu);
-+
-+ ftrace_graph_init_idle_task(idle, cpu);
-+ vtime_init_idle(idle, cpu);
-+#ifdef CONFIG_SMP
-+ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
-+#endif
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur,
-+ const struct cpumask __maybe_unused *trial)
-+{
-+ return 1;
-+}
-+
-+int task_can_attach(struct task_struct *p)
-+{
-+ int ret = 0;
-+
-+ /*
-+ * Kthreads which disallow setaffinity shouldn't be moved
-+ * to a new cpuset; we don't want to change their CPU
-+ * affinity and isolating such threads by their set of
-+ * allowed nodes is unnecessary. Thus, cpusets are not
-+ * applicable for such threads. This prevents checking for
-+ * success of set_cpus_allowed_ptr() on all attached tasks
-+ * before cpus_mask may be changed.
-+ */
-+ if (p->flags & PF_NO_SETAFFINITY)
-+ ret = -EINVAL;
-+
-+ return ret;
-+}
-+
-+bool sched_smp_initialized __read_mostly;
-+
-+#ifdef CONFIG_HOTPLUG_CPU
-+/*
-+ * Ensures that the idle task is using init_mm right before its CPU goes
-+ * offline.
-+ */
-+void idle_task_exit(void)
-+{
-+ struct mm_struct *mm = current->active_mm;
-+
-+ BUG_ON(current != this_rq()->idle);
-+
-+ if (mm != &init_mm) {
-+ switch_mm(mm, &init_mm, current);
-+ finish_arch_post_lock_switch();
-+ }
-+
-+ /* finish_cpu(), as ran on the BP, will clean up the active_mm state */
-+}
-+
-+static int __balance_push_cpu_stop(void *arg)
-+{
-+ struct task_struct *p = arg;
-+ struct rq *rq = this_rq();
-+ struct rq_flags rf;
-+ int cpu;
-+
-+ raw_spin_lock_irq(&p->pi_lock);
-+ rq_lock(rq, &rf);
-+
-+ update_rq_clock(rq);
-+
-+ if (task_rq(p) == rq && task_on_rq_queued(p)) {
-+ cpu = select_fallback_rq(rq->cpu, p);
-+ rq = __migrate_task(rq, p, cpu);
-+ }
-+
-+ rq_unlock(rq, &rf);
-+ raw_spin_unlock_irq(&p->pi_lock);
-+
-+ put_task_struct(p);
-+
-+ return 0;
-+}
-+
-+static DEFINE_PER_CPU(struct cpu_stop_work, push_work);
-+
-+/*
-+ * This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only
-+ * effective when the hotplug motion is down.
-+ */
-+static void balance_push(struct rq *rq)
-+{
-+ struct task_struct *push_task = rq->curr;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ /*
-+ * Ensure the thing is persistent until balance_push_set(.on = false);
-+ */
-+ rq->balance_callback = &balance_push_callback;
-+
-+ /*
-+ * Only active while going offline and when invoked on the outgoing
-+ * CPU.
-+ */
-+ if (!cpu_dying(rq->cpu) || rq != this_rq())
-+ return;
-+
-+ /*
-+ * Both the cpu-hotplug and stop task are in this case and are
-+ * required to complete the hotplug process.
-+ */
-+ if (kthread_is_per_cpu(push_task) ||
-+ is_migration_disabled(push_task)) {
-+
-+ /*
-+ * If this is the idle task on the outgoing CPU try to wake
-+ * up the hotplug control thread which might wait for the
-+ * last task to vanish. The rcuwait_active() check is
-+ * accurate here because the waiter is pinned on this CPU
-+ * and can't obviously be running in parallel.
-+ *
-+ * On RT kernels this also has to check whether there are
-+ * pinned and scheduled out tasks on the runqueue. They
-+ * need to leave the migrate disabled section first.
-+ */
-+ if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
-+ rcuwait_active(&rq->hotplug_wait)) {
-+ raw_spin_unlock(&rq->lock);
-+ rcuwait_wake_up(&rq->hotplug_wait);
-+ raw_spin_lock(&rq->lock);
-+ }
-+ return;
-+ }
-+
-+ get_task_struct(push_task);
-+ /*
-+ * Temporarily drop rq->lock such that we can wake-up the stop task.
-+ * Both preemption and IRQs are still disabled.
-+ */
-+ preempt_disable();
-+ raw_spin_unlock(&rq->lock);
-+ stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
-+ this_cpu_ptr(&push_work));
-+ preempt_enable();
-+ /*
-+ * At this point need_resched() is true and we'll take the loop in
-+ * schedule(). The next pick is obviously going to be the stop task
-+ * which kthread_is_per_cpu() and will push this task away.
-+ */
-+ raw_spin_lock(&rq->lock);
-+}
-+
-+static void balance_push_set(int cpu, bool on)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ struct rq_flags rf;
-+
-+ rq_lock_irqsave(rq, &rf);
-+ if (on) {
-+ WARN_ON_ONCE(rq->balance_callback);
-+ rq->balance_callback = &balance_push_callback;
-+ } else if (rq->balance_callback == &balance_push_callback) {
-+ rq->balance_callback = NULL;
-+ }
-+ rq_unlock_irqrestore(rq, &rf);
-+}
-+
-+/*
-+ * Invoked from a CPUs hotplug control thread after the CPU has been marked
-+ * inactive. All tasks which are not per CPU kernel threads are either
-+ * pushed off this CPU now via balance_push() or placed on a different CPU
-+ * during wakeup. Wait until the CPU is quiescent.
-+ */
-+static void balance_hotplug_wait(void)
-+{
-+ struct rq *rq = this_rq();
-+
-+ rcuwait_wait_event(&rq->hotplug_wait,
-+ rq->nr_running == 1 && !rq_has_pinned_tasks(rq),
-+ TASK_UNINTERRUPTIBLE);
-+}
-+
-+#else
-+
-+static void balance_push(struct rq *rq)
-+{
-+}
-+
-+static void balance_push_set(int cpu, bool on)
-+{
-+}
-+
-+static inline void balance_hotplug_wait(void)
-+{
-+}
-+#endif /* CONFIG_HOTPLUG_CPU */
-+
-+static void set_rq_offline(struct rq *rq)
-+{
-+ if (rq->online) {
-+ update_rq_clock(rq);
-+ rq->online = false;
-+ }
-+}
-+
-+static void set_rq_online(struct rq *rq)
-+{
-+ if (!rq->online)
-+ rq->online = true;
-+}
-+
-+/*
-+ * used to mark begin/end of suspend/resume:
-+ */
-+static int num_cpus_frozen;
-+
-+/*
-+ * Update cpusets according to cpu_active mask. If cpusets are
-+ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
-+ * around partition_sched_domains().
-+ *
-+ * If we come here as part of a suspend/resume, don't touch cpusets because we
-+ * want to restore it back to its original state upon resume anyway.
-+ */
-+static void cpuset_cpu_active(void)
-+{
-+ if (cpuhp_tasks_frozen) {
-+ /*
-+ * num_cpus_frozen tracks how many CPUs are involved in suspend
-+ * resume sequence. As long as this is not the last online
-+ * operation in the resume sequence, just build a single sched
-+ * domain, ignoring cpusets.
-+ */
-+ partition_sched_domains(1, NULL, NULL);
-+ if (--num_cpus_frozen)
-+ return;
-+ /*
-+ * This is the last CPU online operation. So fall through and
-+ * restore the original sched domains by considering the
-+ * cpuset configurations.
-+ */
-+ cpuset_force_rebuild();
-+ }
-+
-+ cpuset_update_active_cpus();
-+}
-+
-+static int cpuset_cpu_inactive(unsigned int cpu)
-+{
-+ if (!cpuhp_tasks_frozen) {
-+ cpuset_update_active_cpus();
-+ } else {
-+ num_cpus_frozen++;
-+ partition_sched_domains(1, NULL, NULL);
-+ }
-+ return 0;
-+}
-+
-+int sched_cpu_activate(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ /*
-+ * Clear the balance_push callback and prepare to schedule
-+ * regular tasks.
-+ */
-+ balance_push_set(cpu, false);
-+
-+#ifdef CONFIG_SCHED_SMT
-+ /*
-+ * When going up, increment the number of cores with SMT present.
-+ */
-+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-+ static_branch_inc_cpuslocked(&sched_smt_present);
-+#endif
-+ set_cpu_active(cpu, true);
-+
-+ if (sched_smp_initialized)
-+ cpuset_cpu_active();
-+
-+ /*
-+ * Put the rq online, if not already. This happens:
-+ *
-+ * 1) In the early boot process, because we build the real domains
-+ * after all cpus have been brought up.
-+ *
-+ * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
-+ * domains.
-+ */
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ set_rq_online(rq);
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+ return 0;
-+}
-+
-+int sched_cpu_deactivate(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+ int ret;
-+
-+ set_cpu_active(cpu, false);
-+
-+ /*
-+ * From this point forward, this CPU will refuse to run any task that
-+ * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively
-+ * push those tasks away until this gets cleared, see
-+ * sched_cpu_dying().
-+ */
-+ balance_push_set(cpu, true);
-+
-+ /*
-+ * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
-+ * users of this state to go away such that all new such users will
-+ * observe it.
-+ *
-+ * Specifically, we rely on ttwu to no longer target this CPU, see
-+ * ttwu_queue_cond() and is_cpu_allowed().
-+ *
-+ * Do sync before park smpboot threads to take care the rcu boost case.
-+ */
-+ synchronize_rcu();
-+
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ set_rq_offline(rq);
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+#ifdef CONFIG_SCHED_SMT
-+ /*
-+ * When going down, decrement the number of cores with SMT present.
-+ */
-+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) {
-+ static_branch_dec_cpuslocked(&sched_smt_present);
-+ if (!static_branch_likely(&sched_smt_present))
-+ cpumask_clear(sched_sg_idle_mask);
-+ }
-+#endif
-+
-+ if (!sched_smp_initialized)
-+ return 0;
-+
-+ ret = cpuset_cpu_inactive(cpu);
-+ if (ret) {
-+ balance_push_set(cpu, false);
-+ set_cpu_active(cpu, true);
-+ return ret;
-+ }
-+
-+ return 0;
-+}
-+
-+static void sched_rq_cpu_starting(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ rq->calc_load_update = calc_load_update;
-+}
-+
-+int sched_cpu_starting(unsigned int cpu)
-+{
-+ sched_rq_cpu_starting(cpu);
-+ sched_tick_start(cpu);
-+ return 0;
-+}
-+
-+#ifdef CONFIG_HOTPLUG_CPU
-+
-+/*
-+ * Invoked immediately before the stopper thread is invoked to bring the
-+ * CPU down completely. At this point all per CPU kthreads except the
-+ * hotplug thread (current) and the stopper thread (inactive) have been
-+ * either parked or have been unbound from the outgoing CPU. Ensure that
-+ * any of those which might be on the way out are gone.
-+ *
-+ * If after this point a bound task is being woken on this CPU then the
-+ * responsible hotplug callback has failed to do it's job.
-+ * sched_cpu_dying() will catch it with the appropriate fireworks.
-+ */
-+int sched_cpu_wait_empty(unsigned int cpu)
-+{
-+ balance_hotplug_wait();
-+ return 0;
-+}
-+
-+/*
-+ * Since this CPU is going 'away' for a while, fold any nr_active delta we
-+ * might have. Called from the CPU stopper task after ensuring that the
-+ * stopper is the last running task on the CPU, so nr_active count is
-+ * stable. We need to take the teardown thread which is calling this into
-+ * account, so we hand in adjust = 1 to the load calculation.
-+ *
-+ * Also see the comment "Global load-average calculations".
-+ */
-+static void calc_load_migrate(struct rq *rq)
-+{
-+ long delta = calc_load_fold_active(rq, 1);
-+
-+ if (delta)
-+ atomic_long_add(delta, &calc_load_tasks);
-+}
-+
-+static void dump_rq_tasks(struct rq *rq, const char *loglvl)
-+{
-+ struct task_struct *g, *p;
-+ int cpu = cpu_of(rq);
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
-+ for_each_process_thread(g, p) {
-+ if (task_cpu(p) != cpu)
-+ continue;
-+
-+ if (!task_on_rq_queued(p))
-+ continue;
-+
-+ printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm);
-+ }
-+}
-+
-+int sched_cpu_dying(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ /* Handle pending wakeups and then migrate everything off */
-+ sched_tick_stop(cpu);
-+
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
-+ WARN(true, "Dying CPU not properly vacated!");
-+ dump_rq_tasks(rq, KERN_WARNING);
-+ }
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+ calc_load_migrate(rq);
-+ hrtick_clear(rq);
-+ return 0;
-+}
-+#endif
-+
-+#ifdef CONFIG_SMP
-+static void sched_init_topology_cpumask_early(void)
-+{
-+ int cpu;
-+ cpumask_t *tmp;
-+
-+ for_each_possible_cpu(cpu) {
-+ /* init topo masks */
-+ tmp = per_cpu(sched_cpu_topo_masks, cpu);
-+
-+ cpumask_copy(tmp, cpu_possible_mask);
-+ per_cpu(sched_cpu_llc_mask, cpu) = tmp;
-+ per_cpu(sched_cpu_topo_end_mask, cpu) = ++tmp;
-+ }
-+}
-+
-+#define TOPOLOGY_CPUMASK(name, mask, last)\
-+ if (cpumask_and(topo, topo, mask)) { \
-+ cpumask_copy(topo, mask); \
-+ printk(KERN_INFO "sched: cpu#%02d topo: 0x%08lx - "#name, \
-+ cpu, (topo++)->bits[0]); \
-+ } \
-+ if (!last) \
-+ bitmap_complement(cpumask_bits(topo), cpumask_bits(mask), \
-+ nr_cpumask_bits);
-+
-+static void sched_init_topology_cpumask(void)
-+{
-+ int cpu;
-+ cpumask_t *topo;
-+
-+ for_each_online_cpu(cpu) {
-+ /* take chance to reset time slice for idle tasks */
-+ cpu_rq(cpu)->idle->time_slice = sysctl_sched_base_slice;
-+
-+ topo = per_cpu(sched_cpu_topo_masks, cpu);
-+
-+ bitmap_complement(cpumask_bits(topo), cpumask_bits(cpumask_of(cpu)),
-+ nr_cpumask_bits);
-+#ifdef CONFIG_SCHED_SMT
-+ TOPOLOGY_CPUMASK(smt, topology_sibling_cpumask(cpu), false);
-+#endif
-+ TOPOLOGY_CPUMASK(cluster, topology_cluster_cpumask(cpu), false);
-+
-+ per_cpu(sd_llc_id, cpu) = cpumask_first(cpu_coregroup_mask(cpu));
-+ per_cpu(sched_cpu_llc_mask, cpu) = topo;
-+ TOPOLOGY_CPUMASK(coregroup, cpu_coregroup_mask(cpu), false);
-+
-+ TOPOLOGY_CPUMASK(core, topology_core_cpumask(cpu), false);
-+
-+ TOPOLOGY_CPUMASK(others, cpu_online_mask, true);
-+
-+ per_cpu(sched_cpu_topo_end_mask, cpu) = topo;
-+ printk(KERN_INFO "sched: cpu#%02d llc_id = %d, llc_mask idx = %d\n",
-+ cpu, per_cpu(sd_llc_id, cpu),
-+ (int) (per_cpu(sched_cpu_llc_mask, cpu) -
-+ per_cpu(sched_cpu_topo_masks, cpu)));
-+ }
-+}
-+#endif
-+
-+void __init sched_init_smp(void)
-+{
-+ /* Move init over to a non-isolated CPU */
-+ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
-+ BUG();
-+ current->flags &= ~PF_NO_SETAFFINITY;
-+
-+ sched_init_topology_cpumask();
-+
-+ sched_smp_initialized = true;
-+}
-+
-+static int __init migration_init(void)
-+{
-+ sched_cpu_starting(smp_processor_id());
-+ return 0;
-+}
-+early_initcall(migration_init);
-+
-+#else
-+void __init sched_init_smp(void)
-+{
-+ cpu_rq(0)->idle->time_slice = sysctl_sched_base_slice;
-+}
-+#endif /* CONFIG_SMP */
-+
-+int in_sched_functions(unsigned long addr)
-+{
-+ return in_lock_functions(addr) ||
-+ (addr >= (unsigned long)__sched_text_start
-+ && addr < (unsigned long)__sched_text_end);
-+}
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+/*
-+ * Default task group.
-+ * Every task in system belongs to this group at bootup.
-+ */
-+struct task_group root_task_group;
-+LIST_HEAD(task_groups);
-+
-+/* Cacheline aligned slab cache for task_group */
-+static struct kmem_cache *task_group_cache __ro_after_init;
-+#endif /* CONFIG_CGROUP_SCHED */
-+
-+void __init sched_init(void)
-+{
-+ int i;
-+ struct rq *rq;
-+#ifdef CONFIG_SCHED_SMT
-+ struct balance_arg balance_arg = {.cpumask = sched_sg_idle_mask, .active = 0};
-+#endif
-+
-+ printk(KERN_INFO "sched/alt: "ALT_SCHED_NAME" CPU Scheduler "ALT_SCHED_VERSION\
-+ " by Alfred Chen.\n");
-+
-+ wait_bit_init();
-+
-+#ifdef CONFIG_SMP
-+ for (i = 0; i < SCHED_QUEUE_BITS; i++)
-+ cpumask_copy(sched_preempt_mask + i, cpu_present_mask);
-+#endif
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+ task_group_cache = KMEM_CACHE(task_group, 0);
-+
-+ list_add(&root_task_group.list, &task_groups);
-+ INIT_LIST_HEAD(&root_task_group.children);
-+ INIT_LIST_HEAD(&root_task_group.siblings);
-+#endif /* CONFIG_CGROUP_SCHED */
-+ for_each_possible_cpu(i) {
-+ rq = cpu_rq(i);
-+
-+ sched_queue_init(&rq->queue);
-+ rq->prio = IDLE_TASK_SCHED_PRIO;
-+#ifdef CONFIG_SCHED_PDS
-+ rq->prio_idx = rq->prio;
-+#endif
-+
-+ raw_spin_lock_init(&rq->lock);
-+ rq->nr_running = rq->nr_uninterruptible = 0;
-+ rq->calc_load_active = 0;
-+ rq->calc_load_update = jiffies + LOAD_FREQ;
-+#ifdef CONFIG_SMP
-+ rq->online = false;
-+ rq->cpu = i;
-+
-+#ifdef CONFIG_SCHED_SMT
-+ rq->sg_balance_arg = balance_arg;
-+#endif
-+
-+#ifdef CONFIG_NO_HZ_COMMON
-+ INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
-+#endif
-+ rq->balance_callback = &balance_push_callback;
-+#ifdef CONFIG_HOTPLUG_CPU
-+ rcuwait_init(&rq->hotplug_wait);
-+#endif
-+#endif /* CONFIG_SMP */
-+ rq->nr_switches = 0;
-+
-+ hrtick_rq_init(rq);
-+ atomic_set(&rq->nr_iowait, 0);
-+
-+ zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
-+ }
-+#ifdef CONFIG_SMP
-+ /* Set rq->online for cpu 0 */
-+ cpu_rq(0)->online = true;
-+#endif
-+ /*
-+ * The boot idle thread does lazy MMU switching as well:
-+ */
-+ mmgrab(&init_mm);
-+ enter_lazy_tlb(&init_mm, current);
-+
-+ /*
-+ * The idle task doesn't need the kthread struct to function, but it
-+ * is dressed up as a per-CPU kthread and thus needs to play the part
-+ * if we want to avoid special-casing it in code that deals with per-CPU
-+ * kthreads.
-+ */
-+ WARN_ON(!set_kthread_struct(current));
-+
-+ /*
-+ * Make us the idle thread. Technically, schedule() should not be
-+ * called from this thread, however somewhere below it might be,
-+ * but because we are the idle thread, we just pick up running again
-+ * when this runqueue becomes "idle".
-+ */
-+ init_idle(current, smp_processor_id());
-+
-+ calc_load_update = jiffies + LOAD_FREQ;
-+
-+#ifdef CONFIG_SMP
-+ idle_thread_set_boot_cpu();
-+ balance_push_set(smp_processor_id(), false);
-+
-+ sched_init_topology_cpumask_early();
-+#endif /* SMP */
-+
-+ preempt_dynamic_init();
-+}
-+
-+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-+
-+void __might_sleep(const char *file, int line)
-+{
-+ unsigned int state = get_current_state();
-+ /*
-+ * Blocking primitives will set (and therefore destroy) current->state,
-+ * since we will exit with TASK_RUNNING make sure we enter with it,
-+ * otherwise we will destroy state.
-+ */
-+ WARN_ONCE(state != TASK_RUNNING && current->task_state_change,
-+ "do not call blocking ops when !TASK_RUNNING; "
-+ "state=%x set at [<%p>] %pS\n", state,
-+ (void *)current->task_state_change,
-+ (void *)current->task_state_change);
-+
-+ __might_resched(file, line, 0);
-+}
-+EXPORT_SYMBOL(__might_sleep);
-+
-+static void print_preempt_disable_ip(int preempt_offset, unsigned long ip)
-+{
-+ if (!IS_ENABLED(CONFIG_DEBUG_PREEMPT))
-+ return;
-+
-+ if (preempt_count() == preempt_offset)
-+ return;
-+
-+ pr_err("Preemption disabled at:");
-+ print_ip_sym(KERN_ERR, ip);
-+}
-+
-+static inline bool resched_offsets_ok(unsigned int offsets)
-+{
-+ unsigned int nested = preempt_count();
-+
-+ nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT;
-+
-+ return nested == offsets;
-+}
-+
-+void __might_resched(const char *file, int line, unsigned int offsets)
-+{
-+ /* Ratelimiting timestamp: */
-+ static unsigned long prev_jiffy;
-+
-+ unsigned long preempt_disable_ip;
-+
-+ /* WARN_ON_ONCE() by default, no rate limit required: */
-+ rcu_sleep_check();
-+
-+ if ((resched_offsets_ok(offsets) && !irqs_disabled() &&
-+ !is_idle_task(current) && !current->non_block_count) ||
-+ system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
-+ oops_in_progress)
-+ return;
-+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-+ return;
-+ prev_jiffy = jiffies;
-+
-+ /* Save this before calling printk(), since that will clobber it: */
-+ preempt_disable_ip = get_preempt_disable_ip(current);
-+
-+ pr_err("BUG: sleeping function called from invalid context at %s:%d\n",
-+ file, line);
-+ pr_err("in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
-+ in_atomic(), irqs_disabled(), current->non_block_count,
-+ current->pid, current->comm);
-+ pr_err("preempt_count: %x, expected: %x\n", preempt_count(),
-+ offsets & MIGHT_RESCHED_PREEMPT_MASK);
-+
-+ if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
-+ pr_err("RCU nest depth: %d, expected: %u\n",
-+ rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT);
-+ }
-+
-+ if (task_stack_end_corrupted(current))
-+ pr_emerg("Thread overran stack, or stack corrupted\n");
-+
-+ debug_show_held_locks(current);
-+ if (irqs_disabled())
-+ print_irqtrace_events(current);
-+
-+ print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK,
-+ preempt_disable_ip);
-+
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+EXPORT_SYMBOL(__might_resched);
-+
-+void __cant_sleep(const char *file, int line, int preempt_offset)
-+{
-+ static unsigned long prev_jiffy;
-+
-+ if (irqs_disabled())
-+ return;
-+
-+ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
-+ return;
-+
-+ if (preempt_count() > preempt_offset)
-+ return;
-+
-+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-+ return;
-+ prev_jiffy = jiffies;
-+
-+ printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
-+ printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
-+ in_atomic(), irqs_disabled(),
-+ current->pid, current->comm);
-+
-+ debug_show_held_locks(current);
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+EXPORT_SYMBOL_GPL(__cant_sleep);
-+
-+#ifdef CONFIG_SMP
-+void __cant_migrate(const char *file, int line)
-+{
-+ static unsigned long prev_jiffy;
-+
-+ if (irqs_disabled())
-+ return;
-+
-+ if (is_migration_disabled(current))
-+ return;
-+
-+ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
-+ return;
-+
-+ if (preempt_count() > 0)
-+ return;
-+
-+ if (current->migration_flags & MDF_FORCE_ENABLED)
-+ return;
-+
-+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-+ return;
-+ prev_jiffy = jiffies;
-+
-+ pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
-+ pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
-+ in_atomic(), irqs_disabled(), is_migration_disabled(current),
-+ current->pid, current->comm);
-+
-+ debug_show_held_locks(current);
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+EXPORT_SYMBOL_GPL(__cant_migrate);
-+#endif
-+#endif
-+
-+#ifdef CONFIG_MAGIC_SYSRQ
-+void normalize_rt_tasks(void)
-+{
-+ struct task_struct *g, *p;
-+ struct sched_attr attr = {
-+ .sched_policy = SCHED_NORMAL,
-+ };
-+
-+ read_lock(&tasklist_lock);
-+ for_each_process_thread(g, p) {
-+ /*
-+ * Only normalize user tasks:
-+ */
-+ if (p->flags & PF_KTHREAD)
-+ continue;
-+
-+ schedstat_set(p->stats.wait_start, 0);
-+ schedstat_set(p->stats.sleep_start, 0);
-+ schedstat_set(p->stats.block_start, 0);
-+
-+ if (!rt_task(p)) {
-+ /*
-+ * Renice negative nice level userspace
-+ * tasks back to 0:
-+ */
-+ if (task_nice(p) < 0)
-+ set_user_nice(p, 0);
-+ continue;
-+ }
-+
-+ __sched_setscheduler(p, &attr, false, false);
-+ }
-+ read_unlock(&tasklist_lock);
-+}
-+#endif /* CONFIG_MAGIC_SYSRQ */
-+
-+#if defined(CONFIG_KGDB_KDB)
-+/*
-+ * These functions are only useful for kdb.
-+ *
-+ * They can only be called when the whole system has been
-+ * stopped - every CPU needs to be quiescent, and no scheduling
-+ * activity can take place. Using them for anything else would
-+ * be a serious bug, and as a result, they aren't even visible
-+ * under any other configuration.
-+ */
-+
-+/**
-+ * curr_task - return the current task for a given CPU.
-+ * @cpu: the processor in question.
-+ *
-+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
-+ *
-+ * Return: The current task for @cpu.
-+ */
-+struct task_struct *curr_task(int cpu)
-+{
-+ return cpu_curr(cpu);
-+}
-+
-+#endif /* defined(CONFIG_KGDB_KDB) */
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+static void sched_free_group(struct task_group *tg)
-+{
-+ kmem_cache_free(task_group_cache, tg);
-+}
-+
-+static void sched_free_group_rcu(struct rcu_head *rhp)
-+{
-+ sched_free_group(container_of(rhp, struct task_group, rcu));
-+}
-+
-+static void sched_unregister_group(struct task_group *tg)
-+{
-+ /*
-+ * We have to wait for yet another RCU grace period to expire, as
-+ * print_cfs_stats() might run concurrently.
-+ */
-+ call_rcu(&tg->rcu, sched_free_group_rcu);
-+}
-+
-+/* allocate runqueue etc for a new task group */
-+struct task_group *sched_create_group(struct task_group *parent)
-+{
-+ struct task_group *tg;
-+
-+ tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
-+ if (!tg)
-+ return ERR_PTR(-ENOMEM);
-+
-+ return tg;
-+}
-+
-+void sched_online_group(struct task_group *tg, struct task_group *parent)
-+{
-+}
-+
-+/* rcu callback to free various structures associated with a task group */
-+static void sched_unregister_group_rcu(struct rcu_head *rhp)
-+{
-+ /* Now it should be safe to free those cfs_rqs: */
-+ sched_unregister_group(container_of(rhp, struct task_group, rcu));
-+}
-+
-+void sched_destroy_group(struct task_group *tg)
-+{
-+ /* Wait for possible concurrent references to cfs_rqs complete: */
-+ call_rcu(&tg->rcu, sched_unregister_group_rcu);
-+}
-+
-+void sched_release_group(struct task_group *tg)
-+{
-+}
-+
-+static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
-+{
-+ return css ? container_of(css, struct task_group, css) : NULL;
-+}
-+
-+static struct cgroup_subsys_state *
-+cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
-+{
-+ struct task_group *parent = css_tg(parent_css);
-+ struct task_group *tg;
-+
-+ if (!parent) {
-+ /* This is early initialization for the top cgroup */
-+ return &root_task_group.css;
-+ }
-+
-+ tg = sched_create_group(parent);
-+ if (IS_ERR(tg))
-+ return ERR_PTR(-ENOMEM);
-+ return &tg->css;
-+}
-+
-+/* Expose task group only after completing cgroup initialization */
-+static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
-+{
-+ struct task_group *tg = css_tg(css);
-+ struct task_group *parent = css_tg(css->parent);
-+
-+ if (parent)
-+ sched_online_group(tg, parent);
-+ return 0;
-+}
-+
-+static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
-+{
-+ struct task_group *tg = css_tg(css);
-+
-+ sched_release_group(tg);
-+}
-+
-+static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
-+{
-+ struct task_group *tg = css_tg(css);
-+
-+ /*
-+ * Relies on the RCU grace period between css_released() and this.
-+ */
-+ sched_unregister_group(tg);
-+}
-+
-+#ifdef CONFIG_RT_GROUP_SCHED
-+static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
-+{
-+ return 0;
-+}
-+#endif
-+
-+static void cpu_cgroup_attach(struct cgroup_taskset *tset)
-+{
-+}
-+
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+static DEFINE_MUTEX(shares_mutex);
-+
-+static int sched_group_set_shares(struct task_group *tg, unsigned long shares)
-+{
-+ /*
-+ * We can't change the weight of the root cgroup.
-+ */
-+ if (&root_task_group == tg)
-+ return -EINVAL;
-+
-+ shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
-+
-+ mutex_lock(&shares_mutex);
-+ if (tg->shares == shares)
-+ goto done;
-+
-+ tg->shares = shares;
-+done:
-+ mutex_unlock(&shares_mutex);
-+ return 0;
-+}
-+
-+static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 shareval)
-+{
-+ if (shareval > scale_load_down(ULONG_MAX))
-+ shareval = MAX_SHARES;
-+ return sched_group_set_shares(css_tg(css), scale_load(shareval));
-+}
-+
-+static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ struct task_group *tg = css_tg(css);
-+
-+ return (u64) scale_load_down(tg->shares);
-+}
-+#endif
-+
-+static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, s64 cfs_quota_us)
-+{
-+ return 0;
-+}
-+
-+static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 cfs_period_us)
-+{
-+ return 0;
-+}
-+
-+static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 cfs_burst_us)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
-+ struct cftype *cft, s64 val)
-+{
-+ return 0;
-+}
-+
-+static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 rt_period_us)
-+{
-+ return 0;
-+}
-+
-+static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
-+ char *buf, size_t nbytes,
-+ loff_t off)
-+{
-+ return nbytes;
-+}
-+
-+static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
-+ char *buf, size_t nbytes,
-+ loff_t off)
-+{
-+ return nbytes;
-+}
-+
-+static struct cftype cpu_legacy_files[] = {
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+ {
-+ .name = "shares",
-+ .read_u64 = cpu_shares_read_u64,
-+ .write_u64 = cpu_shares_write_u64,
-+ },
-+#endif
-+ {
-+ .name = "cfs_quota_us",
-+ .read_s64 = cpu_cfs_quota_read_s64,
-+ .write_s64 = cpu_cfs_quota_write_s64,
-+ },
-+ {
-+ .name = "cfs_period_us",
-+ .read_u64 = cpu_cfs_period_read_u64,
-+ .write_u64 = cpu_cfs_period_write_u64,
-+ },
-+ {
-+ .name = "cfs_burst_us",
-+ .read_u64 = cpu_cfs_burst_read_u64,
-+ .write_u64 = cpu_cfs_burst_write_u64,
-+ },
-+ {
-+ .name = "stat",
-+ .seq_show = cpu_cfs_stat_show,
-+ },
-+ {
-+ .name = "stat.local",
-+ .seq_show = cpu_cfs_local_stat_show,
-+ },
-+ {
-+ .name = "rt_runtime_us",
-+ .read_s64 = cpu_rt_runtime_read,
-+ .write_s64 = cpu_rt_runtime_write,
-+ },
-+ {
-+ .name = "rt_period_us",
-+ .read_u64 = cpu_rt_period_read_uint,
-+ .write_u64 = cpu_rt_period_write_uint,
-+ },
-+ {
-+ .name = "uclamp.min",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_min_show,
-+ .write = cpu_uclamp_min_write,
-+ },
-+ {
-+ .name = "uclamp.max",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_max_show,
-+ .write = cpu_uclamp_max_write,
-+ },
-+ { } /* Terminate */
-+};
-+
-+static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft, u64 weight)
-+{
-+ return 0;
-+}
-+
-+static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft, s64 nice)
-+{
-+ return 0;
-+}
-+
-+static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft, s64 idle)
-+{
-+ return 0;
-+}
-+
-+static int cpu_max_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static ssize_t cpu_max_write(struct kernfs_open_file *of,
-+ char *buf, size_t nbytes, loff_t off)
-+{
-+ return nbytes;
-+}
-+
-+static struct cftype cpu_files[] = {
-+ {
-+ .name = "weight",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_u64 = cpu_weight_read_u64,
-+ .write_u64 = cpu_weight_write_u64,
-+ },
-+ {
-+ .name = "weight.nice",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_s64 = cpu_weight_nice_read_s64,
-+ .write_s64 = cpu_weight_nice_write_s64,
-+ },
-+ {
-+ .name = "idle",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_s64 = cpu_idle_read_s64,
-+ .write_s64 = cpu_idle_write_s64,
-+ },
-+ {
-+ .name = "max",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_max_show,
-+ .write = cpu_max_write,
-+ },
-+ {
-+ .name = "max.burst",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_u64 = cpu_cfs_burst_read_u64,
-+ .write_u64 = cpu_cfs_burst_write_u64,
-+ },
-+ {
-+ .name = "uclamp.min",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_min_show,
-+ .write = cpu_uclamp_min_write,
-+ },
-+ {
-+ .name = "uclamp.max",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_max_show,
-+ .write = cpu_uclamp_max_write,
-+ },
-+ { } /* terminate */
-+};
-+
-+static int cpu_extra_stat_show(struct seq_file *sf,
-+ struct cgroup_subsys_state *css)
-+{
-+ return 0;
-+}
-+
-+static int cpu_local_stat_show(struct seq_file *sf,
-+ struct cgroup_subsys_state *css)
-+{
-+ return 0;
-+}
-+
-+struct cgroup_subsys cpu_cgrp_subsys = {
-+ .css_alloc = cpu_cgroup_css_alloc,
-+ .css_online = cpu_cgroup_css_online,
-+ .css_released = cpu_cgroup_css_released,
-+ .css_free = cpu_cgroup_css_free,
-+ .css_extra_stat_show = cpu_extra_stat_show,
-+ .css_local_stat_show = cpu_local_stat_show,
-+#ifdef CONFIG_RT_GROUP_SCHED
-+ .can_attach = cpu_cgroup_can_attach,
-+#endif
-+ .attach = cpu_cgroup_attach,
-+ .legacy_cftypes = cpu_legacy_files,
-+ .dfl_cftypes = cpu_files,
-+ .early_init = true,
-+ .threaded = true,
-+};
-+#endif /* CONFIG_CGROUP_SCHED */
-+
-+#undef CREATE_TRACE_POINTS
-+
-+#ifdef CONFIG_SCHED_MM_CID
-+
-+#
-+/*
-+ * @cid_lock: Guarantee forward-progress of cid allocation.
-+ *
-+ * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock
-+ * is only used when contention is detected by the lock-free allocation so
-+ * forward progress can be guaranteed.
-+ */
-+DEFINE_RAW_SPINLOCK(cid_lock);
-+
-+/*
-+ * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock.
-+ *
-+ * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is
-+ * detected, it is set to 1 to ensure that all newly coming allocations are
-+ * serialized by @cid_lock until the allocation which detected contention
-+ * completes and sets @use_cid_lock back to 0. This guarantees forward progress
-+ * of a cid allocation.
-+ */
-+int use_cid_lock;
-+
-+/*
-+ * mm_cid remote-clear implements a lock-free algorithm to clear per-mm/cpu cid
-+ * concurrently with respect to the execution of the source runqueue context
-+ * switch.
-+ *
-+ * There is one basic properties we want to guarantee here:
-+ *
-+ * (1) Remote-clear should _never_ mark a per-cpu cid UNSET when it is actively
-+ * used by a task. That would lead to concurrent allocation of the cid and
-+ * userspace corruption.
-+ *
-+ * Provide this guarantee by introducing a Dekker memory ordering to guarantee
-+ * that a pair of loads observe at least one of a pair of stores, which can be
-+ * shown as:
-+ *
-+ * X = Y = 0
-+ *
-+ * w[X]=1 w[Y]=1
-+ * MB MB
-+ * r[Y]=y r[X]=x
-+ *
-+ * Which guarantees that x==0 && y==0 is impossible. But rather than using
-+ * values 0 and 1, this algorithm cares about specific state transitions of the
-+ * runqueue current task (as updated by the scheduler context switch), and the
-+ * per-mm/cpu cid value.
-+ *
-+ * Let's introduce task (Y) which has task->mm == mm and task (N) which has
-+ * task->mm != mm for the rest of the discussion. There are two scheduler state
-+ * transitions on context switch we care about:
-+ *
-+ * (TSA) Store to rq->curr with transition from (N) to (Y)
-+ *
-+ * (TSB) Store to rq->curr with transition from (Y) to (N)
-+ *
-+ * On the remote-clear side, there is one transition we care about:
-+ *
-+ * (TMA) cmpxchg to *pcpu_cid to set the LAZY flag
-+ *
-+ * There is also a transition to UNSET state which can be performed from all
-+ * sides (scheduler, remote-clear). It is always performed with a cmpxchg which
-+ * guarantees that only a single thread will succeed:
-+ *
-+ * (TMB) cmpxchg to *pcpu_cid to mark UNSET
-+ *
-+ * Just to be clear, what we do _not_ want to happen is a transition to UNSET
-+ * when a thread is actively using the cid (property (1)).
-+ *
-+ * Let's looks at the relevant combinations of TSA/TSB, and TMA transitions.
-+ *
-+ * Scenario A) (TSA)+(TMA) (from next task perspective)
-+ *
-+ * CPU0 CPU1
-+ *
-+ * Context switch CS-1 Remote-clear
-+ * - store to rq->curr: (N)->(Y) (TSA) - cmpxchg to *pcpu_id to LAZY (TMA)
-+ * (implied barrier after cmpxchg)
-+ * - switch_mm_cid()
-+ * - memory barrier (see switch_mm_cid()
-+ * comment explaining how this barrier
-+ * is combined with other scheduler
-+ * barriers)
-+ * - mm_cid_get (next)
-+ * - READ_ONCE(*pcpu_cid) - rcu_dereference(src_rq->curr)
-+ *
-+ * This Dekker ensures that either task (Y) is observed by the
-+ * rcu_dereference() or the LAZY flag is observed by READ_ONCE(), or both are
-+ * observed.
-+ *
-+ * If task (Y) store is observed by rcu_dereference(), it means that there is
-+ * still an active task on the cpu. Remote-clear will therefore not transition
-+ * to UNSET, which fulfills property (1).
-+ *
-+ * If task (Y) is not observed, but the lazy flag is observed by READ_ONCE(),
-+ * it will move its state to UNSET, which clears the percpu cid perhaps
-+ * uselessly (which is not an issue for correctness). Because task (Y) is not
-+ * observed, CPU1 can move ahead to set the state to UNSET. Because moving
-+ * state to UNSET is done with a cmpxchg expecting that the old state has the
-+ * LAZY flag set, only one thread will successfully UNSET.
-+ *
-+ * If both states (LAZY flag and task (Y)) are observed, the thread on CPU0
-+ * will observe the LAZY flag and transition to UNSET (perhaps uselessly), and
-+ * CPU1 will observe task (Y) and do nothing more, which is fine.
-+ *
-+ * What we are effectively preventing with this Dekker is a scenario where
-+ * neither LAZY flag nor store (Y) are observed, which would fail property (1)
-+ * because this would UNSET a cid which is actively used.
-+ */
-+
-+void sched_mm_cid_migrate_from(struct task_struct *t)
-+{
-+ t->migrate_from_cpu = task_cpu(t);
-+}
-+
-+static
-+int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
-+ struct task_struct *t,
-+ struct mm_cid *src_pcpu_cid)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct task_struct *src_task;
-+ int src_cid, last_mm_cid;
-+
-+ if (!mm)
-+ return -1;
-+
-+ last_mm_cid = t->last_mm_cid;
-+ /*
-+ * If the migrated task has no last cid, or if the current
-+ * task on src rq uses the cid, it means the source cid does not need
-+ * to be moved to the destination cpu.
-+ */
-+ if (last_mm_cid == -1)
-+ return -1;
-+ src_cid = READ_ONCE(src_pcpu_cid->cid);
-+ if (!mm_cid_is_valid(src_cid) || last_mm_cid != src_cid)
-+ return -1;
-+
-+ /*
-+ * If we observe an active task using the mm on this rq, it means we
-+ * are not the last task to be migrated from this cpu for this mm, so
-+ * there is no need to move src_cid to the destination cpu.
-+ */
-+ rcu_read_lock();
-+ src_task = rcu_dereference(src_rq->curr);
-+ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-+ rcu_read_unlock();
-+ t->last_mm_cid = -1;
-+ return -1;
-+ }
-+ rcu_read_unlock();
-+
-+ return src_cid;
-+}
-+
-+static
-+int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
-+ struct task_struct *t,
-+ struct mm_cid *src_pcpu_cid,
-+ int src_cid)
-+{
-+ struct task_struct *src_task;
-+ struct mm_struct *mm = t->mm;
-+ int lazy_cid;
-+
-+ if (src_cid == -1)
-+ return -1;
-+
-+ /*
-+ * Attempt to clear the source cpu cid to move it to the destination
-+ * cpu.
-+ */
-+ lazy_cid = mm_cid_set_lazy_put(src_cid);
-+ if (!try_cmpxchg(&src_pcpu_cid->cid, &src_cid, lazy_cid))
-+ return -1;
-+
-+ /*
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm matches the scheduler barrier in context_switch()
-+ * between store to rq->curr and load of prev and next task's
-+ * per-mm/cpu cid.
-+ *
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm_cid_active matches the barrier in
-+ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
-+ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
-+ * load of per-mm/cpu cid.
-+ */
-+
-+ /*
-+ * If we observe an active task using the mm on this rq after setting
-+ * the lazy-put flag, this task will be responsible for transitioning
-+ * from lazy-put flag set to MM_CID_UNSET.
-+ */
-+ scoped_guard (rcu) {
-+ src_task = rcu_dereference(src_rq->curr);
-+ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-+ rcu_read_unlock();
-+ /*
-+ * We observed an active task for this mm, there is therefore
-+ * no point in moving this cid to the destination cpu.
-+ */
-+ t->last_mm_cid = -1;
-+ return -1;
-+ }
-+ }
-+
-+ /*
-+ * The src_cid is unused, so it can be unset.
-+ */
-+ if (!try_cmpxchg(&src_pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
-+ return -1;
-+ return src_cid;
-+}
-+
-+/*
-+ * Migration to dst cpu. Called with dst_rq lock held.
-+ * Interrupts are disabled, which keeps the window of cid ownership without the
-+ * source rq lock held small.
-+ */
-+void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu)
-+{
-+ struct mm_cid *src_pcpu_cid, *dst_pcpu_cid;
-+ struct mm_struct *mm = t->mm;
-+ int src_cid, dst_cid;
-+ struct rq *src_rq;
-+
-+ lockdep_assert_rq_held(dst_rq);
-+
-+ if (!mm)
-+ return;
-+ if (src_cpu == -1) {
-+ t->last_mm_cid = -1;
-+ return;
-+ }
-+ /*
-+ * Move the src cid if the dst cid is unset. This keeps id
-+ * allocation closest to 0 in cases where few threads migrate around
-+ * many cpus.
-+ *
-+ * If destination cid is already set, we may have to just clear
-+ * the src cid to ensure compactness in frequent migrations
-+ * scenarios.
-+ *
-+ * It is not useful to clear the src cid when the number of threads is
-+ * greater or equal to the number of allowed cpus, because user-space
-+ * can expect that the number of allowed cids can reach the number of
-+ * allowed cpus.
-+ */
-+ dst_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(dst_rq));
-+ dst_cid = READ_ONCE(dst_pcpu_cid->cid);
-+ if (!mm_cid_is_unset(dst_cid) &&
-+ atomic_read(&mm->mm_users) >= t->nr_cpus_allowed)
-+ return;
-+ src_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, src_cpu);
-+ src_rq = cpu_rq(src_cpu);
-+ src_cid = __sched_mm_cid_migrate_from_fetch_cid(src_rq, t, src_pcpu_cid);
-+ if (src_cid == -1)
-+ return;
-+ src_cid = __sched_mm_cid_migrate_from_try_steal_cid(src_rq, t, src_pcpu_cid,
-+ src_cid);
-+ if (src_cid == -1)
-+ return;
-+ if (!mm_cid_is_unset(dst_cid)) {
-+ __mm_cid_put(mm, src_cid);
-+ return;
-+ }
-+ /* Move src_cid to dst cpu. */
-+ mm_cid_snapshot_time(dst_rq, mm);
-+ WRITE_ONCE(dst_pcpu_cid->cid, src_cid);
-+}
-+
-+static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_cid,
-+ int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ struct task_struct *t;
-+ int cid, lazy_cid;
-+
-+ cid = READ_ONCE(pcpu_cid->cid);
-+ if (!mm_cid_is_valid(cid))
-+ return;
-+
-+ /*
-+ * Clear the cpu cid if it is set to keep cid allocation compact. If
-+ * there happens to be other tasks left on the source cpu using this
-+ * mm, the next task using this mm will reallocate its cid on context
-+ * switch.
-+ */
-+ lazy_cid = mm_cid_set_lazy_put(cid);
-+ if (!try_cmpxchg(&pcpu_cid->cid, &cid, lazy_cid))
-+ return;
-+
-+ /*
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm matches the scheduler barrier in context_switch()
-+ * between store to rq->curr and load of prev and next task's
-+ * per-mm/cpu cid.
-+ *
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm_cid_active matches the barrier in
-+ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
-+ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
-+ * load of per-mm/cpu cid.
-+ */
-+
-+ /*
-+ * If we observe an active task using the mm on this rq after setting
-+ * the lazy-put flag, that task will be responsible for transitioning
-+ * from lazy-put flag set to MM_CID_UNSET.
-+ */
-+ scoped_guard (rcu) {
-+ t = rcu_dereference(rq->curr);
-+ if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
-+ return;
-+ }
-+
-+ /*
-+ * The cid is unused, so it can be unset.
-+ * Disable interrupts to keep the window of cid ownership without rq
-+ * lock small.
-+ */
-+ scoped_guard (irqsave) {
-+ if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
-+ __mm_cid_put(mm, cid);
-+ }
-+}
-+
-+static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ struct mm_cid *pcpu_cid;
-+ struct task_struct *curr;
-+ u64 rq_clock;
-+
-+ /*
-+ * rq->clock load is racy on 32-bit but one spurious clear once in a
-+ * while is irrelevant.
-+ */
-+ rq_clock = READ_ONCE(rq->clock);
-+ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
-+
-+ /*
-+ * In order to take care of infrequently scheduled tasks, bump the time
-+ * snapshot associated with this cid if an active task using the mm is
-+ * observed on this rq.
-+ */
-+ scoped_guard (rcu) {
-+ curr = rcu_dereference(rq->curr);
-+ if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
-+ WRITE_ONCE(pcpu_cid->time, rq_clock);
-+ return;
-+ }
-+ }
-+
-+ if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
-+ return;
-+ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
-+}
-+
-+static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu,
-+ int weight)
-+{
-+ struct mm_cid *pcpu_cid;
-+ int cid;
-+
-+ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
-+ cid = READ_ONCE(pcpu_cid->cid);
-+ if (!mm_cid_is_valid(cid) || cid < weight)
-+ return;
-+ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
-+}
-+
-+static void task_mm_cid_work(struct callback_head *work)
-+{
-+ unsigned long now = jiffies, old_scan, next_scan;
-+ struct task_struct *t = current;
-+ struct cpumask *cidmask;
-+ struct mm_struct *mm;
-+ int weight, cpu;
-+
-+ SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work));
-+
-+ work->next = work; /* Prevent double-add */
-+ if (t->flags & PF_EXITING)
-+ return;
-+ mm = t->mm;
-+ if (!mm)
-+ return;
-+ old_scan = READ_ONCE(mm->mm_cid_next_scan);
-+ next_scan = now + msecs_to_jiffies(MM_CID_SCAN_DELAY);
-+ if (!old_scan) {
-+ unsigned long res;
-+
-+ res = cmpxchg(&mm->mm_cid_next_scan, old_scan, next_scan);
-+ if (res != old_scan)
-+ old_scan = res;
-+ else
-+ old_scan = next_scan;
-+ }
-+ if (time_before(now, old_scan))
-+ return;
-+ if (!try_cmpxchg(&mm->mm_cid_next_scan, &old_scan, next_scan))
-+ return;
-+ cidmask = mm_cidmask(mm);
-+ /* Clear cids that were not recently used. */
-+ for_each_possible_cpu(cpu)
-+ sched_mm_cid_remote_clear_old(mm, cpu);
-+ weight = cpumask_weight(cidmask);
-+ /*
-+ * Clear cids that are greater or equal to the cidmask weight to
-+ * recompact it.
-+ */
-+ for_each_possible_cpu(cpu)
-+ sched_mm_cid_remote_clear_weight(mm, cpu, weight);
-+}
-+
-+void init_sched_mm_cid(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ int mm_users = 0;
-+
-+ if (mm) {
-+ mm_users = atomic_read(&mm->mm_users);
-+ if (mm_users == 1)
-+ mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY);
-+ }
-+ t->cid_work.next = &t->cid_work; /* Protect against double add */
-+ init_task_work(&t->cid_work, task_mm_cid_work);
-+}
-+
-+void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
-+{
-+ struct callback_head *work = &curr->cid_work;
-+ unsigned long now = jiffies;
-+
-+ if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) ||
-+ work->next != work)
-+ return;
-+ if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan)))
-+ return;
-+ task_work_add(curr, work, TWA_RESUME);
-+}
-+
-+void sched_mm_cid_exit_signals(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct rq *rq;
-+
-+ if (!mm)
-+ return;
-+
-+ preempt_disable();
-+ rq = this_rq();
-+ guard(rq_lock_irqsave)(rq);
-+ preempt_enable_no_resched(); /* holding spinlock */
-+ WRITE_ONCE(t->mm_cid_active, 0);
-+ /*
-+ * Store t->mm_cid_active before loading per-mm/cpu cid.
-+ * Matches barrier in sched_mm_cid_remote_clear_old().
-+ */
-+ smp_mb();
-+ mm_cid_put(mm);
-+ t->last_mm_cid = t->mm_cid = -1;
-+}
-+
-+void sched_mm_cid_before_execve(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct rq *rq;
-+
-+ if (!mm)
-+ return;
-+
-+ preempt_disable();
-+ rq = this_rq();
-+ guard(rq_lock_irqsave)(rq);
-+ preempt_enable_no_resched(); /* holding spinlock */
-+ WRITE_ONCE(t->mm_cid_active, 0);
-+ /*
-+ * Store t->mm_cid_active before loading per-mm/cpu cid.
-+ * Matches barrier in sched_mm_cid_remote_clear_old().
-+ */
-+ smp_mb();
-+ mm_cid_put(mm);
-+ t->last_mm_cid = t->mm_cid = -1;
-+}
-+
-+void sched_mm_cid_after_execve(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct rq *rq;
-+
-+ if (!mm)
-+ return;
-+
-+ preempt_disable();
-+ rq = this_rq();
-+ scoped_guard (rq_lock_irqsave, rq) {
-+ preempt_enable_no_resched(); /* holding spinlock */
-+ WRITE_ONCE(t->mm_cid_active, 1);
-+ /*
-+ * Store t->mm_cid_active before loading per-mm/cpu cid.
-+ * Matches barrier in sched_mm_cid_remote_clear_old().
-+ */
-+ smp_mb();
-+ t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
-+ }
-+ rseq_set_notify_resume(t);
-+}
-+
-+void sched_mm_cid_fork(struct task_struct *t)
-+{
-+ WARN_ON_ONCE(!t->mm || t->mm_cid != -1);
-+ t->mm_cid_active = 1;
-+}
-+#endif
-diff --git a/kernel/sched/alt_debug.c b/kernel/sched/alt_debug.c
---- a/kernel/sched/alt_debug.c 1970-01-01 01:00:00.000000000 +0100
-+++ b/kernel/sched/alt_debug.c 2024-07-16 11:57:44.445146416 +0200
-@@ -0,0 +1,32 @@
-+/*
-+ * kernel/sched/alt_debug.c
-+ *
-+ * Print the alt scheduler debugging details
-+ *
-+ * Author: Alfred Chen
-+ * Date : 2020
-+ */
-+#include "sched.h"
-+#include "linux/sched/debug.h"
-+
-+/*
-+ * This allows printing both to /proc/sched_debug and
-+ * to the console
-+ */
-+#define SEQ_printf(m, x...) \
-+ do { \
-+ if (m) \
-+ seq_printf(m, x); \
-+ else \
-+ pr_cont(x); \
-+ } while (0)
-+
-+void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
-+ struct seq_file *m)
-+{
-+ SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns),
-+ get_nr_threads(p));
-+}
-+
-+void proc_sched_set_task(struct task_struct *p)
-+{}
-diff --git a/kernel/sched/alt_sched.h b/kernel/sched/alt_sched.h
---- a/kernel/sched/alt_sched.h 1970-01-01 01:00:00.000000000 +0100
-+++ b/kernel/sched/alt_sched.h 2024-07-16 11:57:44.445146416 +0200
-@@ -0,0 +1,976 @@
-+#ifndef ALT_SCHED_H
-+#define ALT_SCHED_H
-+
-+#include <linux/context_tracking.h>
-+#include <linux/profile.h>
-+#include <linux/stop_machine.h>
-+#include <linux/syscalls.h>
-+#include <linux/tick.h>
-+
-+#include <trace/events/power.h>
-+#include <trace/events/sched.h>
-+
-+#include "../workqueue_internal.h"
-+
-+#include "cpupri.h"
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+/* task group related information */
-+struct task_group {
-+ struct cgroup_subsys_state css;
-+
-+ struct rcu_head rcu;
-+ struct list_head list;
-+
-+ struct task_group *parent;
-+ struct list_head siblings;
-+ struct list_head children;
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+ unsigned long shares;
-+#endif
-+};
-+
-+extern struct task_group *sched_create_group(struct task_group *parent);
-+extern void sched_online_group(struct task_group *tg,
-+ struct task_group *parent);
-+extern void sched_destroy_group(struct task_group *tg);
-+extern void sched_release_group(struct task_group *tg);
-+#endif /* CONFIG_CGROUP_SCHED */
-+
-+#define MIN_SCHED_NORMAL_PRIO (32)
-+/*
-+ * levels: RT(0-24), reserved(25-31), NORMAL(32-63), cpu idle task(64)
-+ *
-+ * -- BMQ --
-+ * NORMAL: (lower boost range 12, NICE_WIDTH 40, higher boost range 12) / 2
-+ * -- PDS --
-+ * NORMAL: SCHED_EDGE_DELTA + ((NICE_WIDTH 40) / 2)
-+ */
-+#define SCHED_LEVELS (64 + 1)
-+
-+#define IDLE_TASK_SCHED_PRIO (SCHED_LEVELS - 1)
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
-+extern void resched_latency_warn(int cpu, u64 latency);
-+#else
-+# define SCHED_WARN_ON(x) ({ (void)(x), 0; })
-+static inline void resched_latency_warn(int cpu, u64 latency) {}
-+#endif
-+
-+/*
-+ * Increase resolution of nice-level calculations for 64-bit architectures.
-+ * The extra resolution improves shares distribution and load balancing of
-+ * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
-+ * hierarchies, especially on larger systems. This is not a user-visible change
-+ * and does not change the user-interface for setting shares/weights.
-+ *
-+ * We increase resolution only if we have enough bits to allow this increased
-+ * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
-+ * are pretty high and the returns do not justify the increased costs.
-+ *
-+ * Really only required when CONFIG_FAIR_GROUP_SCHED=y is also set, but to
-+ * increase coverage and consistency always enable it on 64-bit platforms.
-+ */
-+#ifdef CONFIG_64BIT
-+# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
-+# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
-+# define scale_load_down(w) \
-+({ \
-+ unsigned long __w = (w); \
-+ if (__w) \
-+ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
-+ __w; \
-+})
-+#else
-+# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
-+# define scale_load(w) (w)
-+# define scale_load_down(w) (w)
-+#endif
-+
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
-+
-+/*
-+ * A weight of 0 or 1 can cause arithmetics problems.
-+ * A weight of a cfs_rq is the sum of weights of which entities
-+ * are queued on this cfs_rq, so a weight of a entity should not be
-+ * too large, so as the shares value of a task group.
-+ * (The default weight is 1024 - so there's no practical
-+ * limitation from this.)
-+ */
-+#define MIN_SHARES (1UL << 1)
-+#define MAX_SHARES (1UL << 18)
-+#endif
-+
-+/*
-+ * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
-+ */
-+#ifdef CONFIG_SCHED_DEBUG
-+# define const_debug __read_mostly
-+#else
-+# define const_debug const
-+#endif
-+
-+/* task_struct::on_rq states: */
-+#define TASK_ON_RQ_QUEUED 1
-+#define TASK_ON_RQ_MIGRATING 2
-+
-+static inline int task_on_rq_queued(struct task_struct *p)
-+{
-+ return p->on_rq == TASK_ON_RQ_QUEUED;
-+}
-+
-+static inline int task_on_rq_migrating(struct task_struct *p)
-+{
-+ return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
-+}
-+
-+/* Wake flags. The first three directly map to some SD flag value */
-+#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
-+#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
-+#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
-+
-+#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
-+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
-+#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
-+
-+#ifdef CONFIG_SMP
-+static_assert(WF_EXEC == SD_BALANCE_EXEC);
-+static_assert(WF_FORK == SD_BALANCE_FORK);
-+static_assert(WF_TTWU == SD_BALANCE_WAKE);
-+#endif
-+
-+#define SCHED_QUEUE_BITS (SCHED_LEVELS - 1)
-+
-+struct sched_queue {
-+ DECLARE_BITMAP(bitmap, SCHED_QUEUE_BITS);
-+ struct list_head heads[SCHED_LEVELS];
-+};
-+
-+struct rq;
-+struct cpuidle_state;
-+
-+struct balance_callback {
-+ struct balance_callback *next;
-+ void (*func)(struct rq *rq);
-+};
-+
-+struct balance_arg {
-+ struct task_struct *task;
-+ int active;
-+ cpumask_t *cpumask;
-+};
-+
-+/*
-+ * This is the main, per-CPU runqueue data structure.
-+ * This data should only be modified by the local cpu.
-+ */
-+struct rq {
-+ /* runqueue lock: */
-+ raw_spinlock_t lock;
-+
-+ struct task_struct __rcu *curr;
-+ struct task_struct *idle;
-+ struct task_struct *stop;
-+ struct mm_struct *prev_mm;
-+
-+ struct sched_queue queue ____cacheline_aligned;
-+
-+ int prio;
-+#ifdef CONFIG_SCHED_PDS
-+ int prio_idx;
-+ u64 time_edge;
-+#endif
-+
-+ /* switch count */
-+ u64 nr_switches;
-+
-+ atomic_t nr_iowait;
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+ u64 last_seen_need_resched_ns;
-+ int ticks_without_resched;
-+#endif
-+
-+#ifdef CONFIG_MEMBARRIER
-+ int membarrier_state;
-+#endif
-+
-+#ifdef CONFIG_SMP
-+ int cpu; /* cpu of this runqueue */
-+ bool online;
-+
-+ unsigned int ttwu_pending;
-+ unsigned char nohz_idle_balance;
-+ unsigned char idle_balance;
-+
-+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
-+ struct sched_avg avg_irq;
-+#endif
-+
-+#ifdef CONFIG_SCHED_SMT
-+ struct balance_arg sg_balance_arg ____cacheline_aligned;
-+#endif
-+ struct cpu_stop_work active_balance_work;
-+
-+ struct balance_callback *balance_callback;
-+#ifdef CONFIG_HOTPLUG_CPU
-+ struct rcuwait hotplug_wait;
-+#endif
-+ unsigned int nr_pinned;
-+
-+#endif /* CONFIG_SMP */
-+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-+ u64 prev_irq_time;
-+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-+#ifdef CONFIG_PARAVIRT
-+ u64 prev_steal_time;
-+#endif /* CONFIG_PARAVIRT */
-+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-+ u64 prev_steal_time_rq;
-+#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */
-+
-+ /* For genenal cpu load util */
-+ s32 load_history;
-+ u64 load_block;
-+ u64 load_stamp;
-+
-+ /* calc_load related fields */
-+ unsigned long calc_load_update;
-+ long calc_load_active;
-+
-+ /* Ensure that all clocks are in the same cache line */
-+ u64 clock ____cacheline_aligned;
-+ u64 clock_task;
-+
-+ unsigned int nr_running;
-+ unsigned long nr_uninterruptible;
-+
-+#ifdef CONFIG_SCHED_HRTICK
-+#ifdef CONFIG_SMP
-+ call_single_data_t hrtick_csd;
-+#endif
-+ struct hrtimer hrtick_timer;
-+ ktime_t hrtick_time;
-+#endif
-+
-+#ifdef CONFIG_SCHEDSTATS
-+
-+ /* latency stats */
-+ struct sched_info rq_sched_info;
-+ unsigned long long rq_cpu_time;
-+ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
-+
-+ /* sys_sched_yield() stats */
-+ unsigned int yld_count;
-+
-+ /* schedule() stats */
-+ unsigned int sched_switch;
-+ unsigned int sched_count;
-+ unsigned int sched_goidle;
-+
-+ /* try_to_wake_up() stats */
-+ unsigned int ttwu_count;
-+ unsigned int ttwu_local;
-+#endif /* CONFIG_SCHEDSTATS */
-+
-+#ifdef CONFIG_CPU_IDLE
-+ /* Must be inspected within a rcu lock section */
-+ struct cpuidle_state *idle_state;
-+#endif
-+
-+#ifdef CONFIG_NO_HZ_COMMON
-+#ifdef CONFIG_SMP
-+ call_single_data_t nohz_csd;
-+#endif
-+ atomic_t nohz_flags;
-+#endif /* CONFIG_NO_HZ_COMMON */
-+
-+ /* Scratch cpumask to be temporarily used under rq_lock */
-+ cpumask_var_t scratch_mask;
-+};
-+
-+extern unsigned int sysctl_sched_base_slice;
-+
-+extern unsigned long rq_load_util(struct rq *rq, unsigned long max);
-+
-+extern unsigned long calc_load_update;
-+extern atomic_long_t calc_load_tasks;
-+
-+extern void calc_global_load_tick(struct rq *this_rq);
-+extern long calc_load_fold_active(struct rq *this_rq, long adjust);
-+
-+DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-+#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
-+#define this_rq() this_cpu_ptr(&runqueues)
-+#define task_rq(p) cpu_rq(task_cpu(p))
-+#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
-+#define raw_rq() raw_cpu_ptr(&runqueues)
-+
-+#ifdef CONFIG_SMP
-+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
-+void register_sched_domain_sysctl(void);
-+void unregister_sched_domain_sysctl(void);
-+#else
-+static inline void register_sched_domain_sysctl(void)
-+{
-+}
-+static inline void unregister_sched_domain_sysctl(void)
-+{
-+}
-+#endif
-+
-+extern bool sched_smp_initialized;
-+
-+enum {
-+#ifdef CONFIG_SCHED_SMT
-+ SMT_LEVEL_SPACE_HOLDER,
-+#endif
-+ COREGROUP_LEVEL_SPACE_HOLDER,
-+ CORE_LEVEL_SPACE_HOLDER,
-+ OTHER_LEVEL_SPACE_HOLDER,
-+ NR_CPU_AFFINITY_LEVELS
-+};
-+
-+DECLARE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
-+
-+static inline int
-+__best_mask_cpu(const cpumask_t *cpumask, const cpumask_t *mask)
-+{
-+ int cpu;
-+
-+ while ((cpu = cpumask_any_and(cpumask, mask)) >= nr_cpu_ids)
-+ mask++;
-+
-+ return cpu;
-+}
-+
-+static inline int best_mask_cpu(int cpu, const cpumask_t *mask)
-+{
-+ return __best_mask_cpu(mask, per_cpu(sched_cpu_topo_masks, cpu));
-+}
-+
-+#endif
-+
-+#ifndef arch_scale_freq_tick
-+static __always_inline
-+void arch_scale_freq_tick(void)
-+{
-+}
-+#endif
-+
-+#ifndef arch_scale_freq_capacity
-+static __always_inline
-+unsigned long arch_scale_freq_capacity(int cpu)
-+{
-+ return SCHED_CAPACITY_SCALE;
-+}
-+#endif
-+
-+static inline u64 __rq_clock_broken(struct rq *rq)
-+{
-+ return READ_ONCE(rq->clock);
-+}
-+
-+static inline u64 rq_clock(struct rq *rq)
-+{
-+ /*
-+ * Relax lockdep_assert_held() checking as in VRQ, call to
-+ * sched_info_xxxx() may not held rq->lock
-+ * lockdep_assert_held(&rq->lock);
-+ */
-+ return rq->clock;
-+}
-+
-+static inline u64 rq_clock_task(struct rq *rq)
-+{
-+ /*
-+ * Relax lockdep_assert_held() checking as in VRQ, call to
-+ * sched_info_xxxx() may not held rq->lock
-+ * lockdep_assert_held(&rq->lock);
-+ */
-+ return rq->clock_task;
-+}
-+
-+/*
-+ * {de,en}queue flags:
-+ *
-+ * DEQUEUE_SLEEP - task is no longer runnable
-+ * ENQUEUE_WAKEUP - task just became runnable
-+ *
-+ */
-+
-+#define DEQUEUE_SLEEP 0x01
-+
-+#define ENQUEUE_WAKEUP 0x01
-+
-+
-+/*
-+ * Below are scheduler API which using in other kernel code
-+ * It use the dummy rq_flags
-+ * ToDo : BMQ need to support these APIs for compatibility with mainline
-+ * scheduler code.
-+ */
-+struct rq_flags {
-+ unsigned long flags;
-+};
-+
-+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(rq->lock);
-+
-+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(p->pi_lock)
-+ __acquires(rq->lock);
-+
-+static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+static inline void
-+task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
-+ __releases(rq->lock)
-+ __releases(p->pi_lock)
-+{
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
-+}
-+
-+static inline void
-+rq_lock(struct rq *rq, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ raw_spin_lock(&rq->lock);
-+}
-+
-+static inline void
-+rq_unlock(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+static inline void
-+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ raw_spin_lock_irq(&rq->lock);
-+}
-+
-+static inline void
-+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock_irq(&rq->lock);
-+}
-+
-+static inline struct rq *
-+this_rq_lock_irq(struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ struct rq *rq;
-+
-+ local_irq_disable();
-+ rq = this_rq();
-+ raw_spin_lock(&rq->lock);
-+
-+ return rq;
-+}
-+
-+static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
-+{
-+ return &rq->lock;
-+}
-+
-+static inline raw_spinlock_t *rq_lockp(struct rq *rq)
-+{
-+ return __rq_lockp(rq);
-+}
-+
-+static inline void lockdep_assert_rq_held(struct rq *rq)
-+{
-+ lockdep_assert_held(__rq_lockp(rq));
-+}
-+
-+extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
-+extern void raw_spin_rq_unlock(struct rq *rq);
-+
-+static inline void raw_spin_rq_lock(struct rq *rq)
-+{
-+ raw_spin_rq_lock_nested(rq, 0);
-+}
-+
-+static inline void raw_spin_rq_lock_irq(struct rq *rq)
-+{
-+ local_irq_disable();
-+ raw_spin_rq_lock(rq);
-+}
-+
-+static inline void raw_spin_rq_unlock_irq(struct rq *rq)
-+{
-+ raw_spin_rq_unlock(rq);
-+ local_irq_enable();
-+}
-+
-+static inline int task_current(struct rq *rq, struct task_struct *p)
-+{
-+ return rq->curr == p;
-+}
-+
-+static inline bool task_on_cpu(struct task_struct *p)
-+{
-+ return p->on_cpu;
-+}
-+
-+extern int task_running_nice(struct task_struct *p);
-+
-+extern struct static_key_false sched_schedstats;
-+
-+#ifdef CONFIG_CPU_IDLE
-+static inline void idle_set_state(struct rq *rq,
-+ struct cpuidle_state *idle_state)
-+{
-+ rq->idle_state = idle_state;
-+}
-+
-+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
-+{
-+ WARN_ON(!rcu_read_lock_held());
-+ return rq->idle_state;
-+}
-+#else
-+static inline void idle_set_state(struct rq *rq,
-+ struct cpuidle_state *idle_state)
-+{
-+}
-+
-+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
-+{
-+ return NULL;
-+}
-+#endif
-+
-+static inline int cpu_of(const struct rq *rq)
-+{
-+#ifdef CONFIG_SMP
-+ return rq->cpu;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+extern void resched_cpu(int cpu);
-+
-+#include "stats.h"
-+
-+#ifdef CONFIG_NO_HZ_COMMON
-+#define NOHZ_BALANCE_KICK_BIT 0
-+#define NOHZ_STATS_KICK_BIT 1
-+
-+#define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT)
-+#define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT)
-+
-+#define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
-+
-+#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
-+
-+/* TODO: needed?
-+extern void nohz_balance_exit_idle(struct rq *rq);
-+#else
-+static inline void nohz_balance_exit_idle(struct rq *rq) { }
-+*/
-+#endif
-+
-+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-+struct irqtime {
-+ u64 total;
-+ u64 tick_delta;
-+ u64 irq_start_time;
-+ struct u64_stats_sync sync;
-+};
-+
-+DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
-+
-+/*
-+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
-+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
-+ * and never move forward.
-+ */
-+static inline u64 irq_time_read(int cpu)
-+{
-+ struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
-+ unsigned int seq;
-+ u64 total;
-+
-+ do {
-+ seq = __u64_stats_fetch_begin(&irqtime->sync);
-+ total = irqtime->total;
-+ } while (__u64_stats_fetch_retry(&irqtime->sync, seq));
-+
-+ return total;
-+}
-+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-+
-+#ifdef CONFIG_CPU_FREQ
-+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
-+#endif /* CONFIG_CPU_FREQ */
-+
-+#ifdef CONFIG_NO_HZ_FULL
-+extern int __init sched_tick_offload_init(void);
-+#else
-+static inline int sched_tick_offload_init(void) { return 0; }
-+#endif
-+
-+#ifdef arch_scale_freq_capacity
-+#ifndef arch_scale_freq_invariant
-+#define arch_scale_freq_invariant() (true)
-+#endif
-+#else /* arch_scale_freq_capacity */
-+#define arch_scale_freq_invariant() (false)
-+#endif
-+
-+#ifdef CONFIG_SMP
-+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
-+ unsigned long min,
-+ unsigned long max);
-+#endif /* CONFIG_SMP */
-+
-+extern void schedule_idle(void);
-+
-+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
-+
-+/*
-+ * !! For sched_setattr_nocheck() (kernel) only !!
-+ *
-+ * This is actually gross. :(
-+ *
-+ * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE
-+ * tasks, but still be able to sleep. We need this on platforms that cannot
-+ * atomically change clock frequency. Remove once fast switching will be
-+ * available on such platforms.
-+ *
-+ * SUGOV stands for SchedUtil GOVernor.
-+ */
-+#define SCHED_FLAG_SUGOV 0x10000000
-+
-+#ifdef CONFIG_MEMBARRIER
-+/*
-+ * The scheduler provides memory barriers required by membarrier between:
-+ * - prior user-space memory accesses and store to rq->membarrier_state,
-+ * - store to rq->membarrier_state and following user-space memory accesses.
-+ * In the same way it provides those guarantees around store to rq->curr.
-+ */
-+static inline void membarrier_switch_mm(struct rq *rq,
-+ struct mm_struct *prev_mm,
-+ struct mm_struct *next_mm)
-+{
-+ int membarrier_state;
-+
-+ if (prev_mm == next_mm)
-+ return;
-+
-+ membarrier_state = atomic_read(&next_mm->membarrier_state);
-+ if (READ_ONCE(rq->membarrier_state) == membarrier_state)
-+ return;
-+
-+ WRITE_ONCE(rq->membarrier_state, membarrier_state);
-+}
-+#else
-+static inline void membarrier_switch_mm(struct rq *rq,
-+ struct mm_struct *prev_mm,
-+ struct mm_struct *next_mm)
-+{
-+}
-+#endif
-+
-+#ifdef CONFIG_NUMA
-+extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
-+#else
-+static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
-+{
-+ return nr_cpu_ids;
-+}
-+#endif
-+
-+extern void swake_up_all_locked(struct swait_queue_head *q);
-+extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
-+
-+extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+extern int preempt_dynamic_mode;
-+extern int sched_dynamic_mode(const char *str);
-+extern void sched_dynamic_update(int mode);
-+#endif
-+
-+static inline void nohz_run_idle_balance(int cpu) { }
-+
-+static inline
-+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-+ struct task_struct *p)
-+{
-+ return util;
-+}
-+
-+static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
-+
-+#ifdef CONFIG_SCHED_MM_CID
-+
-+#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */
-+#define MM_CID_SCAN_DELAY 100 /* 100ms */
-+
-+extern raw_spinlock_t cid_lock;
-+extern int use_cid_lock;
-+
-+extern void sched_mm_cid_migrate_from(struct task_struct *t);
-+extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu);
-+extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr);
-+extern void init_sched_mm_cid(struct task_struct *t);
-+
-+static inline void __mm_cid_put(struct mm_struct *mm, int cid)
-+{
-+ if (cid < 0)
-+ return;
-+ cpumask_clear_cpu(cid, mm_cidmask(mm));
-+}
-+
-+/*
-+ * The per-mm/cpu cid can have the MM_CID_LAZY_PUT flag set or transition to
-+ * the MM_CID_UNSET state without holding the rq lock, but the rq lock needs to
-+ * be held to transition to other states.
-+ *
-+ * State transitions synchronized with cmpxchg or try_cmpxchg need to be
-+ * consistent across cpus, which prevents use of this_cpu_cmpxchg.
-+ */
-+static inline void mm_cid_put_lazy(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-+ int cid;
-+
-+ lockdep_assert_irqs_disabled();
-+ cid = __this_cpu_read(pcpu_cid->cid);
-+ if (!mm_cid_is_lazy_put(cid) ||
-+ !try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
-+ return;
-+ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
-+}
-+
-+static inline int mm_cid_pcpu_unset(struct mm_struct *mm)
-+{
-+ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-+ int cid, res;
-+
-+ lockdep_assert_irqs_disabled();
-+ cid = __this_cpu_read(pcpu_cid->cid);
-+ for (;;) {
-+ if (mm_cid_is_unset(cid))
-+ return MM_CID_UNSET;
-+ /*
-+ * Attempt transition from valid or lazy-put to unset.
-+ */
-+ res = cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, cid, MM_CID_UNSET);
-+ if (res == cid)
-+ break;
-+ cid = res;
-+ }
-+ return cid;
-+}
-+
-+static inline void mm_cid_put(struct mm_struct *mm)
-+{
-+ int cid;
-+
-+ lockdep_assert_irqs_disabled();
-+ cid = mm_cid_pcpu_unset(mm);
-+ if (cid == MM_CID_UNSET)
-+ return;
-+ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
-+}
-+
-+static inline int __mm_cid_try_get(struct mm_struct *mm)
-+{
-+ struct cpumask *cpumask;
-+ int cid;
-+
-+ cpumask = mm_cidmask(mm);
-+ /*
-+ * Retry finding first zero bit if the mask is temporarily
-+ * filled. This only happens during concurrent remote-clear
-+ * which owns a cid without holding a rq lock.
-+ */
-+ for (;;) {
-+ cid = cpumask_first_zero(cpumask);
-+ if (cid < nr_cpu_ids)
-+ break;
-+ cpu_relax();
-+ }
-+ if (cpumask_test_and_set_cpu(cid, cpumask))
-+ return -1;
-+ return cid;
-+}
-+
-+/*
-+ * Save a snapshot of the current runqueue time of this cpu
-+ * with the per-cpu cid value, allowing to estimate how recently it was used.
-+ */
-+static inline void mm_cid_snapshot_time(struct rq *rq, struct mm_struct *mm)
-+{
-+ struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(rq));
-+
-+ lockdep_assert_rq_held(rq);
-+ WRITE_ONCE(pcpu_cid->time, rq->clock);
-+}
-+
-+static inline int __mm_cid_get(struct rq *rq, struct mm_struct *mm)
-+{
-+ int cid;
-+
-+ /*
-+ * All allocations (even those using the cid_lock) are lock-free. If
-+ * use_cid_lock is set, hold the cid_lock to perform cid allocation to
-+ * guarantee forward progress.
-+ */
-+ if (!READ_ONCE(use_cid_lock)) {
-+ cid = __mm_cid_try_get(mm);
-+ if (cid >= 0)
-+ goto end;
-+ raw_spin_lock(&cid_lock);
-+ } else {
-+ raw_spin_lock(&cid_lock);
-+ cid = __mm_cid_try_get(mm);
-+ if (cid >= 0)
-+ goto unlock;
-+ }
-+
-+ /*
-+ * cid concurrently allocated. Retry while forcing following
-+ * allocations to use the cid_lock to ensure forward progress.
-+ */
-+ WRITE_ONCE(use_cid_lock, 1);
-+ /*
-+ * Set use_cid_lock before allocation. Only care about program order
-+ * because this is only required for forward progress.
-+ */
-+ barrier();
-+ /*
-+ * Retry until it succeeds. It is guaranteed to eventually succeed once
-+ * all newcoming allocations observe the use_cid_lock flag set.
-+ */
-+ do {
-+ cid = __mm_cid_try_get(mm);
-+ cpu_relax();
-+ } while (cid < 0);
-+ /*
-+ * Allocate before clearing use_cid_lock. Only care about
-+ * program order because this is for forward progress.
-+ */
-+ barrier();
-+ WRITE_ONCE(use_cid_lock, 0);
-+unlock:
-+ raw_spin_unlock(&cid_lock);
-+end:
-+ mm_cid_snapshot_time(rq, mm);
-+ return cid;
-+}
-+
-+static inline int mm_cid_get(struct rq *rq, struct mm_struct *mm)
-+{
-+ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-+ struct cpumask *cpumask;
-+ int cid;
-+
-+ lockdep_assert_rq_held(rq);
-+ cpumask = mm_cidmask(mm);
-+ cid = __this_cpu_read(pcpu_cid->cid);
-+ if (mm_cid_is_valid(cid)) {
-+ mm_cid_snapshot_time(rq, mm);
-+ return cid;
-+ }
-+ if (mm_cid_is_lazy_put(cid)) {
-+ if (try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
-+ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
-+ }
-+ cid = __mm_cid_get(rq, mm);
-+ __this_cpu_write(pcpu_cid->cid, cid);
-+ return cid;
-+}
-+
-+static inline void switch_mm_cid(struct rq *rq,
-+ struct task_struct *prev,
-+ struct task_struct *next)
-+{
-+ /*
-+ * Provide a memory barrier between rq->curr store and load of
-+ * {prev,next}->mm->pcpu_cid[cpu] on rq->curr->mm transition.
-+ *
-+ * Should be adapted if context_switch() is modified.
-+ */
-+ if (!next->mm) { // to kernel
-+ /*
-+ * user -> kernel transition does not guarantee a barrier, but
-+ * we can use the fact that it performs an atomic operation in
-+ * mmgrab().
-+ */
-+ if (prev->mm) // from user
-+ smp_mb__after_mmgrab();
-+ /*
-+ * kernel -> kernel transition does not change rq->curr->mm
-+ * state. It stays NULL.
-+ */
-+ } else { // to user
-+ /*
-+ * kernel -> user transition does not provide a barrier
-+ * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
-+ * Provide it here.
-+ */
-+ if (!prev->mm) // from kernel
-+ smp_mb();
-+ /*
-+ * user -> user transition guarantees a memory barrier through
-+ * switch_mm() when current->mm changes. If current->mm is
-+ * unchanged, no barrier is needed.
-+ */
-+ }
-+ if (prev->mm_cid_active) {
-+ mm_cid_snapshot_time(rq, prev->mm);
-+ mm_cid_put_lazy(prev);
-+ prev->mm_cid = -1;
-+ }
-+ if (next->mm_cid_active)
-+ next->last_mm_cid = next->mm_cid = mm_cid_get(rq, next->mm);
-+}
-+
-+#else
-+static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { }
-+static inline void sched_mm_cid_migrate_from(struct task_struct *t) { }
-+static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu) { }
-+static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
-+static inline void init_sched_mm_cid(struct task_struct *t) { }
-+#endif
-+
-+#ifdef CONFIG_SMP
-+extern struct balance_callback balance_push_callback;
-+
-+static inline void
-+__queue_balance_callback(struct rq *rq,
-+ struct balance_callback *head)
-+{
-+ lockdep_assert_rq_held(rq);
-+
-+ /*
-+ * Don't (re)queue an already queued item; nor queue anything when
-+ * balance_push() is active, see the comment with
-+ * balance_push_callback.
-+ */
-+ if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
-+ return;
-+
-+ head->next = rq->balance_callback;
-+ rq->balance_callback = head;
-+}
-+#endif /* CONFIG_SMP */
-+
-+#endif /* ALT_SCHED_H */
-diff --git a/kernel/sched/bmq.h b/kernel/sched/bmq.h
---- a/kernel/sched/bmq.h 1970-01-01 01:00:00.000000000 +0100
-+++ b/kernel/sched/bmq.h 2024-07-16 11:57:44.445146416 +0200
-@@ -0,0 +1,98 @@
-+#define ALT_SCHED_NAME "BMQ"
-+
-+/*
-+ * BMQ only routines
-+ */
-+static inline void boost_task(struct task_struct *p, int n)
-+{
-+ int limit;
-+
-+ switch (p->policy) {
-+ case SCHED_NORMAL:
-+ limit = -MAX_PRIORITY_ADJ;
-+ break;
-+ case SCHED_BATCH:
-+ limit = 0;
-+ break;
-+ default:
-+ return;
-+ }
-+
-+ p->boost_prio = max(limit, p->boost_prio - n);
-+}
-+
-+static inline void deboost_task(struct task_struct *p)
-+{
-+ if (p->boost_prio < MAX_PRIORITY_ADJ)
-+ p->boost_prio++;
-+}
-+
-+/*
-+ * Common interfaces
-+ */
-+static inline void sched_timeslice_imp(const int timeslice_ms) {}
-+
-+/* This API is used in task_prio(), return value readed by human users */
-+static inline int
-+task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
-+{
-+ return p->prio + p->boost_prio - MIN_NORMAL_PRIO;
-+}
-+
-+static inline int task_sched_prio(const struct task_struct *p)
-+{
-+ return (p->prio < MIN_NORMAL_PRIO)? (p->prio >> 2) :
-+ MIN_SCHED_NORMAL_PRIO + (p->prio + p->boost_prio - MIN_NORMAL_PRIO) / 2;
-+}
-+
-+#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
-+ prio = task_sched_prio(p); \
-+ idx = prio;
-+
-+static inline int sched_prio2idx(int prio, struct rq *rq)
-+{
-+ return prio;
-+}
-+
-+static inline int sched_idx2prio(int idx, struct rq *rq)
-+{
-+ return idx;
-+}
-+
-+static inline int sched_rq_prio_idx(struct rq *rq)
-+{
-+ return rq->prio;
-+}
-+
-+inline int task_running_nice(struct task_struct *p)
-+{
-+ return (p->prio + p->boost_prio > DEFAULT_PRIO);
-+}
-+
-+static inline void sched_update_rq_clock(struct rq *rq) {}
-+
-+static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
-+{
-+ deboost_task(p);
-+}
-+
-+static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq) {}
-+static void sched_task_fork(struct task_struct *p, struct rq *rq) {}
-+
-+static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
-+{
-+ p->boost_prio = MAX_PRIORITY_ADJ;
-+}
-+
-+static inline void sched_task_ttwu(struct task_struct *p)
-+{
-+ s64 delta = this_rq()->clock_task > p->last_ran;
-+
-+ if (likely(delta > 0))
-+ boost_task(p, delta >> 22);
-+}
-+
-+static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq)
-+{
-+ boost_task(p, 1);
-+}
-diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
---- a/kernel/sched/build_policy.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/build_policy.c 2024-07-16 11:57:44.445146416 +0200
-@@ -42,13 +42,19 @@
-
- #include "idle.c"
-
-+#ifndef CONFIG_SCHED_ALT
- #include "rt.c"
-+#endif
-
- #ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- # include "cpudeadline.c"
-+#endif
- # include "pelt.c"
- #endif
-
- #include "cputime.c"
--#include "deadline.c"
-
-+#ifndef CONFIG_SCHED_ALT
-+#include "deadline.c"
-+#endif
-diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
---- a/kernel/sched/build_utility.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/build_utility.c 2024-07-16 11:57:44.445146416 +0200
-@@ -84,7 +84,9 @@
-
- #ifdef CONFIG_SMP
- # include "cpupri.c"
-+#ifndef CONFIG_SCHED_ALT
- # include "stop_task.c"
-+#endif
- # include "topology.c"
- #endif
-
-diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
---- a/kernel/sched/cpufreq_schedutil.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/cpufreq_schedutil.c 2024-07-16 11:57:44.445146416 +0200
-@@ -197,12 +197,17 @@ unsigned long sugov_effective_cpu_perf(i
-
- static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
- {
-+#ifndef CONFIG_SCHED_ALT
- unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
-
- util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
- util = max(util, boost);
- sg_cpu->bw_min = min;
- sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
-+#else /* CONFIG_SCHED_ALT */
-+ sg_cpu->bw_min = 0;
-+ sg_cpu->util = rq_load_util(cpu_rq(sg_cpu->cpu), arch_scale_cpu_capacity(sg_cpu->cpu));
-+#endif /* CONFIG_SCHED_ALT */
- }
-
- /**
-@@ -343,8 +348,10 @@ static inline bool sugov_cpu_is_busy(str
- */
- static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
- {
-+#ifndef CONFIG_SCHED_ALT
- if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
- sg_cpu->sg_policy->limits_changed = true;
-+#endif
- }
-
- static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
-@@ -676,6 +683,7 @@ static int sugov_kthread_create(struct s
- }
-
- ret = sched_setattr_nocheck(thread, &attr);
-+
- if (ret) {
- kthread_stop(thread);
- pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
-diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
---- a/kernel/sched/cputime.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/cputime.c 2024-07-16 11:57:44.445146416 +0200
-@@ -126,7 +126,7 @@ void account_user_time(struct task_struc
- p->utime += cputime;
- account_group_user_time(p, cputime);
-
-- index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
-+ index = task_running_nice(p) ? CPUTIME_NICE : CPUTIME_USER;
-
- /* Add user time to cpustat. */
- task_group_account_field(p, index, cputime);
-@@ -150,7 +150,7 @@ void account_guest_time(struct task_stru
- p->gtime += cputime;
-
- /* Add guest time to cpustat. */
-- if (task_nice(p) > 0) {
-+ if (task_running_nice(p)) {
- task_group_account_field(p, CPUTIME_NICE, cputime);
- cpustat[CPUTIME_GUEST_NICE] += cputime;
- } else {
-@@ -288,7 +288,7 @@ static inline u64 account_other_time(u64
- #ifdef CONFIG_64BIT
- static inline u64 read_sum_exec_runtime(struct task_struct *t)
- {
-- return t->se.sum_exec_runtime;
-+ return tsk_seruntime(t);
- }
- #else
- static u64 read_sum_exec_runtime(struct task_struct *t)
-@@ -298,7 +298,7 @@ static u64 read_sum_exec_runtime(struct
- struct rq *rq;
-
- rq = task_rq_lock(t, &rf);
-- ns = t->se.sum_exec_runtime;
-+ ns = tsk_seruntime(t);
- task_rq_unlock(rq, t, &rf);
-
- return ns;
-@@ -617,7 +617,7 @@ out:
- void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
- {
- struct task_cputime cputime = {
-- .sum_exec_runtime = p->se.sum_exec_runtime,
-+ .sum_exec_runtime = tsk_seruntime(p),
- };
-
- if (task_cputime(p, &cputime.utime, &cputime.stime))
-diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
---- a/kernel/sched/debug.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/debug.c 2024-07-16 11:57:44.445146416 +0200
-@@ -7,6 +7,7 @@
- * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
- */
-
-+#ifndef CONFIG_SCHED_ALT
- /*
- * This allows printing both to /sys/kernel/debug/sched/debug and
- * to the console
-@@ -215,6 +216,7 @@ static const struct file_operations sche
- };
-
- #endif /* SMP */
-+#endif /* !CONFIG_SCHED_ALT */
-
- #ifdef CONFIG_PREEMPT_DYNAMIC
-
-@@ -278,6 +280,7 @@ static const struct file_operations sche
-
- #endif /* CONFIG_PREEMPT_DYNAMIC */
-
-+#ifndef CONFIG_SCHED_ALT
- __read_mostly bool sched_debug_verbose;
-
- #ifdef CONFIG_SMP
-@@ -332,6 +335,7 @@ static const struct file_operations sche
- .llseek = seq_lseek,
- .release = seq_release,
- };
-+#endif /* !CONFIG_SCHED_ALT */
-
- static struct dentry *debugfs_sched;
-
-@@ -341,14 +345,17 @@ static __init int sched_init_debug(void)
-
- debugfs_sched = debugfs_create_dir("sched", NULL);
-
-+#ifndef CONFIG_SCHED_ALT
- debugfs_create_file("features", 0644, debugfs_sched, NULL, &sched_feat_fops);
- debugfs_create_file_unsafe("verbose", 0644, debugfs_sched, &sched_debug_verbose, &sched_verbose_fops);
-+#endif /* !CONFIG_SCHED_ALT */
- #ifdef CONFIG_PREEMPT_DYNAMIC
- debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
- #endif
-
- debugfs_create_u32("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
-
-+#ifndef CONFIG_SCHED_ALT
- debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
- debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
-
-@@ -373,11 +380,13 @@ static __init int sched_init_debug(void)
- #endif
-
- debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
-+#endif /* !CONFIG_SCHED_ALT */
-
- return 0;
- }
- late_initcall(sched_init_debug);
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_SMP
-
- static cpumask_var_t sd_sysctl_cpus;
-@@ -1111,6 +1120,7 @@ void proc_sched_set_task(struct task_str
- memset(&p->stats, 0, sizeof(p->stats));
- #endif
- }
-+#endif /* !CONFIG_SCHED_ALT */
-
- void resched_latency_warn(int cpu, u64 latency)
- {
-diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
---- a/kernel/sched/idle.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/idle.c 2024-07-16 11:57:44.449146659 +0200
-@@ -430,6 +430,7 @@ void cpu_startup_entry(enum cpuhp_state
- do_idle();
- }
-
-+#ifndef CONFIG_SCHED_ALT
- /*
- * idle-task scheduling class.
- */
-@@ -551,3 +552,4 @@ DEFINE_SCHED_CLASS(idle) = {
- .switched_to = switched_to_idle,
- .update_curr = update_curr_idle,
- };
-+#endif
-diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
---- a/kernel/sched/Makefile 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/Makefile 2024-07-16 11:57:44.441146173 +0200
-@@ -28,7 +28,12 @@ endif
- # These compilation units have roughly the same size and complexity - so their
- # build parallelizes well and finishes roughly at once:
- #
-+ifdef CONFIG_SCHED_ALT
-+obj-y += alt_core.o
-+obj-$(CONFIG_SCHED_DEBUG) += alt_debug.o
-+else
- obj-y += core.o
- obj-y += fair.o
-+endif
- obj-y += build_policy.o
- obj-y += build_utility.o
-diff --git a/kernel/sched/pds.h b/kernel/sched/pds.h
---- a/kernel/sched/pds.h 1970-01-01 01:00:00.000000000 +0100
-+++ b/kernel/sched/pds.h 2024-07-16 11:57:44.449146659 +0200
-@@ -0,0 +1,134 @@
-+#define ALT_SCHED_NAME "PDS"
-+
-+static const u64 RT_MASK = ((1ULL << MIN_SCHED_NORMAL_PRIO) - 1);
-+
-+#define SCHED_NORMAL_PRIO_NUM (32)
-+#define SCHED_EDGE_DELTA (SCHED_NORMAL_PRIO_NUM - NICE_WIDTH / 2)
-+
-+/* PDS assume SCHED_NORMAL_PRIO_NUM is power of 2 */
-+#define SCHED_NORMAL_PRIO_MOD(x) ((x) & (SCHED_NORMAL_PRIO_NUM - 1))
-+
-+/* default time slice 4ms -> shift 22, 2 time slice slots -> shift 23 */
-+static __read_mostly int sched_timeslice_shift = 23;
-+
-+/*
-+ * Common interfaces
-+ */
-+static inline int
-+task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
-+{
-+ u64 sched_dl = max(p->deadline, rq->time_edge);
-+
-+#ifdef ALT_SCHED_DEBUG
-+ if (WARN_ONCE(sched_dl - rq->time_edge > NORMAL_PRIO_NUM - 1,
-+ "pds: task_sched_prio_normal() delta %lld\n", sched_dl - rq->time_edge))
-+ return SCHED_NORMAL_PRIO_NUM - 1;
-+#endif
-+
-+ return sched_dl - rq->time_edge;
-+}
-+
-+static inline int task_sched_prio(const struct task_struct *p)
-+{
-+ return (p->prio < MIN_NORMAL_PRIO) ? (p->prio >> 2) :
-+ MIN_SCHED_NORMAL_PRIO + task_sched_prio_normal(p, task_rq(p));
-+}
-+
-+#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
-+ if (p->prio < MIN_NORMAL_PRIO) { \
-+ prio = p->prio >> 2; \
-+ idx = prio; \
-+ } else { \
-+ u64 sched_dl = max(p->deadline, rq->time_edge); \
-+ prio = MIN_SCHED_NORMAL_PRIO + sched_dl - rq->time_edge; \
-+ idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_dl); \
-+ }
-+
-+static inline int sched_prio2idx(int sched_prio, struct rq *rq)
-+{
-+ return (IDLE_TASK_SCHED_PRIO == sched_prio || sched_prio < MIN_SCHED_NORMAL_PRIO) ?
-+ sched_prio :
-+ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_prio + rq->time_edge);
-+}
-+
-+static inline int sched_idx2prio(int sched_idx, struct rq *rq)
-+{
-+ return (sched_idx < MIN_SCHED_NORMAL_PRIO) ?
-+ sched_idx :
-+ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_idx - rq->time_edge);
-+}
-+
-+static inline int sched_rq_prio_idx(struct rq *rq)
-+{
-+ return rq->prio_idx;
-+}
-+
-+int task_running_nice(struct task_struct *p)
-+{
-+ return (p->prio > DEFAULT_PRIO);
-+}
-+
-+static inline void sched_update_rq_clock(struct rq *rq)
-+{
-+ struct list_head head;
-+ u64 old = rq->time_edge;
-+ u64 now = rq->clock >> sched_timeslice_shift;
-+ u64 prio, delta;
-+ DECLARE_BITMAP(normal, SCHED_QUEUE_BITS);
-+
-+ if (now == old)
-+ return;
-+
-+ rq->time_edge = now;
-+ delta = min_t(u64, SCHED_NORMAL_PRIO_NUM, now - old);
-+ INIT_LIST_HEAD(&head);
-+
-+ prio = MIN_SCHED_NORMAL_PRIO;
-+ for_each_set_bit_from(prio, rq->queue.bitmap, MIN_SCHED_NORMAL_PRIO + delta)
-+ list_splice_tail_init(rq->queue.heads + MIN_SCHED_NORMAL_PRIO +
-+ SCHED_NORMAL_PRIO_MOD(prio + old), &head);
-+
-+ bitmap_shift_right(normal, rq->queue.bitmap, delta, SCHED_QUEUE_BITS);
-+ if (!list_empty(&head)) {
-+ u64 idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(now);
-+
-+ __list_splice(&head, rq->queue.heads + idx, rq->queue.heads[idx].next);
-+ set_bit(MIN_SCHED_NORMAL_PRIO, normal);
-+ }
-+ bitmap_replace(rq->queue.bitmap, normal, rq->queue.bitmap,
-+ (const unsigned long *)&RT_MASK, SCHED_QUEUE_BITS);
-+
-+ if (rq->prio < MIN_SCHED_NORMAL_PRIO || IDLE_TASK_SCHED_PRIO == rq->prio)
-+ return;
-+
-+ rq->prio = max_t(u64, MIN_SCHED_NORMAL_PRIO, rq->prio - delta);
-+ rq->prio_idx = sched_prio2idx(rq->prio, rq);
-+}
-+
-+static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
-+{
-+ if (p->prio >= MIN_NORMAL_PRIO)
-+ p->deadline = rq->time_edge + SCHED_EDGE_DELTA +
-+ (p->static_prio - (MAX_PRIO - NICE_WIDTH)) / 2;
-+}
-+
-+static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq)
-+{
-+ u64 max_dl = rq->time_edge + SCHED_EDGE_DELTA + NICE_WIDTH / 2 - 1;
-+ if (unlikely(p->deadline > max_dl))
-+ p->deadline = max_dl;
-+}
-+
-+static void sched_task_fork(struct task_struct *p, struct rq *rq)
-+{
-+ sched_task_renew(p, rq);
-+}
-+
-+static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
-+{
-+ p->time_slice = sysctl_sched_base_slice;
-+ sched_task_renew(p, rq);
-+}
-+
-+static inline void sched_task_ttwu(struct task_struct *p) {}
-+static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq) {}
-diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
---- a/kernel/sched/pelt.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/pelt.c 2024-07-16 11:57:44.449146659 +0200
-@@ -266,6 +266,7 @@ ___update_load_avg(struct sched_avg *sa,
- WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
- }
-
-+#ifndef CONFIG_SCHED_ALT
- /*
- * sched_entity:
- *
-@@ -383,8 +384,9 @@ int update_dl_rq_load_avg(u64 now, struc
-
- return 0;
- }
-+#endif
-
--#ifdef CONFIG_SCHED_HW_PRESSURE
-+#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
- /*
- * hardware:
- *
-diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
---- a/kernel/sched/pelt.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/pelt.h 2024-07-16 11:57:44.449146659 +0200
-@@ -1,13 +1,15 @@
- #ifdef CONFIG_SMP
- #include "sched-pelt.h"
-
-+#ifndef CONFIG_SCHED_ALT
- int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
- int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
- int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
- int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
- int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
-+#endif
-
--#ifdef CONFIG_SCHED_HW_PRESSURE
-+#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
- int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity);
-
- static inline u64 hw_load_avg(struct rq *rq)
-@@ -44,6 +46,7 @@ static inline u32 get_pelt_divider(struc
- return PELT_MIN_DIVIDER + avg->period_contrib;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- static inline void cfs_se_util_change(struct sched_avg *avg)
- {
- unsigned int enqueued;
-@@ -180,9 +183,11 @@ static inline u64 cfs_rq_clock_pelt(stru
- return rq_clock_pelt(rq_of(cfs_rq));
- }
- #endif
-+#endif /* CONFIG_SCHED_ALT */
-
- #else
-
-+#ifndef CONFIG_SCHED_ALT
- static inline int
- update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
- {
-@@ -200,6 +205,7 @@ update_dl_rq_load_avg(u64 now, struct rq
- {
- return 0;
- }
-+#endif
-
- static inline int
- update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
-diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
---- a/kernel/sched/sched.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/sched.h 2024-07-16 11:57:44.449146659 +0200
-@@ -5,6 +5,10 @@
- #ifndef _KERNEL_SCHED_SCHED_H
- #define _KERNEL_SCHED_SCHED_H
-
-+#ifdef CONFIG_SCHED_ALT
-+#include "alt_sched.h"
-+#else
-+
- #include <linux/sched/affinity.h>
- #include <linux/sched/autogroup.h>
- #include <linux/sched/cpufreq.h>
-@@ -3481,4 +3485,9 @@ static inline void init_sched_mm_cid(str
- extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
- extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
-
-+static inline int task_running_nice(struct task_struct *p)
-+{
-+ return (task_nice(p) > 0);
-+}
-+#endif /* !CONFIG_SCHED_ALT */
- #endif /* _KERNEL_SCHED_SCHED_H */
-diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
---- a/kernel/sched/stats.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/stats.c 2024-07-16 11:57:44.449146659 +0200
-@@ -125,9 +125,11 @@ static int show_schedstat(struct seq_fil
- } else {
- struct rq *rq;
- #ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- struct sched_domain *sd;
- int dcount = 0;
- #endif
-+#endif
- cpu = (unsigned long)(v - 2);
- rq = cpu_rq(cpu);
-
-@@ -143,6 +145,7 @@ static int show_schedstat(struct seq_fil
- seq_printf(seq, "\n");
-
- #ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- /* domain-specific stats */
- rcu_read_lock();
- for_each_domain(cpu, sd) {
-@@ -171,6 +174,7 @@ static int show_schedstat(struct seq_fil
- }
- rcu_read_unlock();
- #endif
-+#endif
- }
- return 0;
- }
-diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
---- a/kernel/sched/stats.h 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/stats.h 2024-07-16 11:57:44.449146659 +0200
-@@ -89,6 +89,7 @@ static inline void rq_sched_info_depart
-
- #endif /* CONFIG_SCHEDSTATS */
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_FAIR_GROUP_SCHED
- struct sched_entity_stats {
- struct sched_entity se;
-@@ -105,6 +106,7 @@ __schedstats_from_se(struct sched_entity
- #endif
- return &task_of(se)->stats;
- }
-+#endif /* CONFIG_SCHED_ALT */
-
- #ifdef CONFIG_PSI
- void psi_task_change(struct task_struct *task, int clear, int set);
-diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
---- a/kernel/sched/topology.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sched/topology.c 2024-07-16 11:57:44.449146659 +0200
-@@ -3,6 +3,7 @@
- * Scheduler topology setup/handling methods
- */
-
-+#ifndef CONFIG_SCHED_ALT
- #include <linux/bsearch.h>
-
- DEFINE_MUTEX(sched_domains_mutex);
-@@ -1451,8 +1452,10 @@ static void asym_cpu_capacity_scan(void)
- */
-
- static int default_relax_domain_level = -1;
-+#endif /* CONFIG_SCHED_ALT */
- int sched_domain_level_max;
-
-+#ifndef CONFIG_SCHED_ALT
- static int __init setup_relax_domain_level(char *str)
- {
- if (kstrtoint(str, 0, &default_relax_domain_level))
-@@ -1687,6 +1690,7 @@ sd_init(struct sched_domain_topology_lev
-
- return sd;
- }
-+#endif /* CONFIG_SCHED_ALT */
-
- /*
- * Topology list, bottom-up.
-@@ -1723,6 +1727,7 @@ void __init set_sched_topology(struct sc
- sched_domain_topology_saved = NULL;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_NUMA
-
- static const struct cpumask *sd_numa_mask(int cpu)
-@@ -2789,3 +2794,28 @@ void partition_sched_domains(int ndoms_n
- partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
- mutex_unlock(&sched_domains_mutex);
- }
-+#else /* CONFIG_SCHED_ALT */
-+DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
-+
-+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-+ struct sched_domain_attr *dattr_new)
-+{}
-+
-+#ifdef CONFIG_NUMA
-+int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
-+{
-+ return best_mask_cpu(cpu, cpus);
-+}
-+
-+int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
-+{
-+ return cpumask_nth(cpu, cpus);
-+}
-+
-+const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops)
-+{
-+ return ERR_PTR(-EOPNOTSUPP);
-+}
-+EXPORT_SYMBOL_GPL(sched_numa_hop_mask);
-+#endif /* CONFIG_NUMA */
-+#endif
-diff --git a/kernel/sysctl.c b/kernel/sysctl.c
---- a/kernel/sysctl.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/sysctl.c 2024-07-16 11:57:44.449146659 +0200
-@@ -92,6 +92,10 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals);
-
- /* Constants used for minimum and maximum */
-
-+#ifdef CONFIG_SCHED_ALT
-+extern int sched_yield_type;
-+#endif
-+
- #ifdef CONFIG_PERF_EVENTS
- static const int six_hundred_forty_kb = 640 * 1024;
- #endif
-@@ -1912,6 +1916,17 @@ static struct ctl_table kern_table[] = {
- .proc_handler = proc_dointvec,
- },
- #endif
-+#ifdef CONFIG_SCHED_ALT
-+ {
-+ .procname = "yield_type",
-+ .data = &sched_yield_type,
-+ .maxlen = sizeof (int),
-+ .mode = 0644,
-+ .proc_handler = &proc_dointvec_minmax,
-+ .extra1 = SYSCTL_ZERO,
-+ .extra2 = SYSCTL_TWO,
-+ },
-+#endif
- #if defined(CONFIG_S390) && defined(CONFIG_SMP)
- {
- .procname = "spin_retry",
-diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
---- a/kernel/time/hrtimer.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/time/hrtimer.c 2024-07-16 11:57:44.453146902 +0200
-@@ -2074,8 +2074,10 @@ long hrtimer_nanosleep(ktime_t rqtp, con
- int ret = 0;
- u64 slack;
-
-+#ifndef CONFIG_SCHED_ALT
- slack = current->timer_slack_ns;
-- if (rt_task(current))
-+ if (dl_task(current) || rt_task(current))
-+#endif
- slack = 0;
-
- hrtimer_init_sleeper_on_stack(&t, clockid, mode);
-diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
---- a/kernel/time/posix-cpu-timers.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/time/posix-cpu-timers.c 2024-07-16 11:57:44.453146902 +0200
-@@ -223,7 +223,7 @@ static void task_sample_cputime(struct t
- u64 stime, utime;
-
- task_cputime(p, &utime, &stime);
-- store_samples(samples, stime, utime, p->se.sum_exec_runtime);
-+ store_samples(samples, stime, utime, tsk_seruntime(p));
- }
-
- static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
-@@ -867,6 +867,7 @@ static void collect_posix_cputimers(stru
- }
- }
-
-+#ifndef CONFIG_SCHED_ALT
- static inline void check_dl_overrun(struct task_struct *tsk)
- {
- if (tsk->dl.dl_overrun) {
-@@ -874,6 +875,7 @@ static inline void check_dl_overrun(stru
- send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
- }
- }
-+#endif
-
- static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
- {
-@@ -901,8 +903,10 @@ static void check_thread_timers(struct t
- u64 samples[CPUCLOCK_MAX];
- unsigned long soft;
-
-+#ifndef CONFIG_SCHED_ALT
- if (dl_task(tsk))
- check_dl_overrun(tsk);
-+#endif
-
- if (expiry_cache_is_inactive(pct))
- return;
-@@ -916,7 +920,7 @@ static void check_thread_timers(struct t
- soft = task_rlimit(tsk, RLIMIT_RTTIME);
- if (soft != RLIM_INFINITY) {
- /* Task RT timeout is accounted in jiffies. RTTIME is usec */
-- unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ);
-+ unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ);
- unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
-
- /* At the hard limit, send SIGKILL. No further action. */
-@@ -1152,8 +1156,10 @@ static inline bool fastpath_timer_check(
- return true;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- if (dl_task(tsk) && tsk->dl.dl_overrun)
- return true;
-+#endif
-
- return false;
- }
-diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
---- a/kernel/trace/trace_selftest.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/trace/trace_selftest.c 2024-07-16 11:57:44.461147389 +0200
-@@ -1155,10 +1155,15 @@ static int trace_wakeup_test_thread(void
- {
- /* Make this a -deadline thread */
- static const struct sched_attr attr = {
-+#ifdef CONFIG_SCHED_ALT
-+ /* No deadline on BMQ/PDS, use RR */
-+ .sched_policy = SCHED_RR,
-+#else
- .sched_policy = SCHED_DEADLINE,
- .sched_runtime = 100000ULL,
- .sched_deadline = 10000000ULL,
- .sched_period = 10000000ULL
-+#endif
- };
- struct wakeup_test_data *x = data;
-
-diff --git a/kernel/workqueue.c b/kernel/workqueue.c
---- a/kernel/workqueue.c 2024-07-15 00:43:32.000000000 +0200
-+++ b/kernel/workqueue.c 2024-07-16 11:57:44.465147632 +0200
-@@ -1248,6 +1248,7 @@ static bool kick_pool(struct worker_pool
-
- p = worker->task;
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_SMP
- /*
- * Idle @worker is about to execute @work and waking up provides an
-@@ -1277,6 +1278,8 @@ static bool kick_pool(struct worker_pool
- }
- }
- #endif
-+#endif /* !CONFIG_SCHED_ALT */
-+
- wake_up_process(p);
- return true;
- }
-@@ -1405,7 +1408,11 @@ void wq_worker_running(struct task_struc
- * CPU intensive auto-detection cares about how long a work item hogged
- * CPU without sleeping. Reset the starting timestamp on wakeup.
- */
-+#ifdef CONFIG_SCHED_ALT
-+ worker->current_at = worker->task->sched_time;
-+#else
- worker->current_at = worker->task->se.sum_exec_runtime;
-+#endif
-
- WRITE_ONCE(worker->sleeping, 0);
- }
-@@ -1490,7 +1497,11 @@ void wq_worker_tick(struct task_struct *
- * We probably want to make this prettier in the future.
- */
- if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) ||
-+#ifdef CONFIG_SCHED_ALT
-+ worker->task->sched_time - worker->current_at <
-+#else
- worker->task->se.sum_exec_runtime - worker->current_at <
-+#endif
- wq_cpu_intensive_thresh_us * NSEC_PER_USEC)
- return;
-
-@@ -3176,7 +3187,11 @@ __acquires(&pool->lock)
- worker->current_func = work->func;
- worker->current_pwq = pwq;
- if (worker->task)
-+#ifdef CONFIG_SCHED_ALT
-+ worker->current_at = worker->task->sched_time;
-+#else
- worker->current_at = worker->task->se.sum_exec_runtime;
-+#endif
- work_data = *work_data_bits(work);
- worker->current_color = get_work_color(work_data);
-
diff --git a/5021_BMQ-and-PDS-gentoo-defaults.patch b/5021_BMQ-and-PDS-gentoo-defaults.patch
deleted file mode 100644
index 409dda6b..00000000
--- a/5021_BMQ-and-PDS-gentoo-defaults.patch
+++ /dev/null
@@ -1,12 +0,0 @@
---- a/init/Kconfig 2023-02-13 08:16:09.534315265 -0500
-+++ b/init/Kconfig 2023-02-13 08:17:24.130237204 -0500
-@@ -867,8 +867,9 @@ config UCLAMP_BUCKETS_COUNT
- If in doubt, use the default value.
-
- menuconfig SCHED_ALT
-+ depends on X86_64
- bool "Alternative CPU Schedulers"
-- default y
-+ default n
- help
- This feature enable alternative CPU scheduler"
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-08-03 15:16 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-08-03 15:16 UTC (permalink / raw
To: gentoo-commits
commit: 3d6d5815699a3eec9e13019fcac398bd3992bb7d
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Aug 3 15:15:05 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Aug 3 15:15:05 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=3d6d5815
Linux 6.10.3, and additional patches
Rename 6.10.1 patch
Add jump label fix patch thanks to Holger Hoffstätte
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 8 +
1001_linux-6.10.1.patch => 1000_linux-6.10.1.patch | 0
1002_linux-6.10.3.patch | 31017 +++++++++++++++++++
2950_jump-label-fix.patch | 57 +
4 files changed, 31082 insertions(+)
diff --git a/0000_README b/0000_README
index f2aa0e92..3c01ecbe 100644
--- a/0000_README
+++ b/0000_README
@@ -51,6 +51,10 @@ Patch: 1001_linux-6.10.2.patch
From: https://www.kernel.org
Desc: Linux 6.10.2
+Patch: 1002_linux-6.10.3.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.3
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
@@ -79,6 +83,10 @@ Patch: 2920_sign-file-patch-for-libressl.patch
From: https://bugs.gentoo.org/717166
Desc: sign-file: full functionality with modern LibreSSL
+Patch: 2950_jump-label-fix.patch
+From: https://git.kernel.org/pub/scm/linux/kernel/git/tip/tip.git/
+Desc: jump_label: Fix a regression
+
Patch: 3000_Support-printing-firmware-info.patch
From: https://bugs.gentoo.org/732852
Desc: Print firmware info (Reqs CONFIG_GENTOO_PRINT_FIRMWARE_INFO). Thanks to Georgy Yakovlev
diff --git a/1001_linux-6.10.1.patch b/1000_linux-6.10.1.patch
similarity index 100%
rename from 1001_linux-6.10.1.patch
rename to 1000_linux-6.10.1.patch
diff --git a/1002_linux-6.10.3.patch b/1002_linux-6.10.3.patch
new file mode 100644
index 00000000..77023431
--- /dev/null
+++ b/1002_linux-6.10.3.patch
@@ -0,0 +1,31017 @@
+diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
+index 27ec49af1bf27..2569e7f19b476 100644
+--- a/Documentation/admin-guide/kernel-parameters.txt
++++ b/Documentation/admin-guide/kernel-parameters.txt
+@@ -4749,7 +4749,9 @@
+ none - Limited to cond_resched() calls
+ voluntary - Limited to cond_resched() and might_sleep() calls
+ full - Any section that isn't explicitly preempt disabled
+- can be preempted anytime.
++ can be preempted anytime. Tasks will also yield
++ contended spinlocks (if the critical section isn't
++ explicitly preempt disabled beyond the lock itself).
+
+ print-fatal-signals=
+ [KNL] debug: print fatal signals
+diff --git a/Documentation/arch/powerpc/kvm-nested.rst b/Documentation/arch/powerpc/kvm-nested.rst
+index 630602a8aa008..5defd13cc6c17 100644
+--- a/Documentation/arch/powerpc/kvm-nested.rst
++++ b/Documentation/arch/powerpc/kvm-nested.rst
+@@ -546,7 +546,9 @@ table information.
+ +--------+-------+----+--------+----------------------------------+
+ | 0x1052 | 0x08 | RW | T | CTRL |
+ +--------+-------+----+--------+----------------------------------+
+-| 0x1053-| | | | Reserved |
++| 0x1053 | 0x08 | RW | T | DPDES |
+++--------+-------+----+--------+----------------------------------+
++| 0x1054-| | | | Reserved |
+ | 0x1FFF | | | | |
+ +--------+-------+----+--------+----------------------------------+
+ | 0x2000 | 0x04 | RW | T | CR |
+diff --git a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
+index 325585bc881ba..212e56eb1bec2 100644
+--- a/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
++++ b/Documentation/devicetree/bindings/phy/qcom,sc8280xp-qmp-usb3-uni-phy.yaml
+@@ -20,7 +20,7 @@ properties:
+ - qcom,ipq8074-qmp-usb3-phy
+ - qcom,ipq9574-qmp-usb3-phy
+ - qcom,msm8996-qmp-usb3-phy
+- - com,qdu1000-qmp-usb3-uni-phy
++ - qcom,qdu1000-qmp-usb3-uni-phy
+ - qcom,sa8775p-qmp-usb3-uni-phy
+ - qcom,sc8280xp-qmp-usb3-uni-phy
+ - qcom,sdm845-qmp-usb3-uni-phy
+diff --git a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
+index 68398e7e86556..606b80965a44a 100644
+--- a/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
++++ b/Documentation/devicetree/bindings/thermal/thermal-zones.yaml
+@@ -49,7 +49,10 @@ properties:
+ to take when the temperature crosses those thresholds.
+
+ patternProperties:
+- "^[a-zA-Z][a-zA-Z0-9\\-]{1,12}-thermal$":
++ # Node name is limited in size due to Linux kernel requirements - 19
++ # characters in total (see THERMAL_NAME_LENGTH, including terminating NUL
++ # byte):
++ "^[a-zA-Z][a-zA-Z0-9\\-]{1,10}-thermal$":
+ type: object
+ description:
+ Each thermal zone node contains information about how frequently it
+diff --git a/Documentation/networking/xsk-tx-metadata.rst b/Documentation/networking/xsk-tx-metadata.rst
+index bd033fe95cca5..e76b0cfc32f7d 100644
+--- a/Documentation/networking/xsk-tx-metadata.rst
++++ b/Documentation/networking/xsk-tx-metadata.rst
+@@ -11,12 +11,16 @@ metadata on the receive side.
+ General Design
+ ==============
+
+-The headroom for the metadata is reserved via ``tx_metadata_len`` in
+-``struct xdp_umem_reg``. The metadata length is therefore the same for
+-every socket that shares the same umem. The metadata layout is a fixed UAPI,
+-refer to ``union xsk_tx_metadata`` in ``include/uapi/linux/if_xdp.h``.
+-Thus, generally, the ``tx_metadata_len`` field above should contain
+-``sizeof(union xsk_tx_metadata)``.
++The headroom for the metadata is reserved via ``tx_metadata_len`` and
++``XDP_UMEM_TX_METADATA_LEN`` flag in ``struct xdp_umem_reg``. The metadata
++length is therefore the same for every socket that shares the same umem.
++The metadata layout is a fixed UAPI, refer to ``union xsk_tx_metadata`` in
++``include/uapi/linux/if_xdp.h``. Thus, generally, the ``tx_metadata_len``
++field above should contain ``sizeof(union xsk_tx_metadata)``.
++
++Note that in the original implementation the ``XDP_UMEM_TX_METADATA_LEN``
++flag was not required. Applications might attempt to create a umem
++with a flag first and if it fails, do another attempt without a flag.
+
+ The headroom and the metadata itself should be located right before
+ ``xdp_desc->addr`` in the umem frame. Within a frame, the metadata
+diff --git a/Documentation/virt/kvm/api.rst b/Documentation/virt/kvm/api.rst
+index a71d91978d9ef..eec8df1dde06a 100644
+--- a/Documentation/virt/kvm/api.rst
++++ b/Documentation/virt/kvm/api.rst
+@@ -1403,6 +1403,12 @@ Instead, an abort (data abort if the cause of the page-table update
+ was a load or a store, instruction abort if it was an instruction
+ fetch) is injected in the guest.
+
++S390:
++^^^^^
++
++Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set.
++Returns -EINVAL if called on a protected VM.
++
+ 4.36 KVM_SET_TSS_ADDR
+ ---------------------
+
+@@ -6273,6 +6279,12 @@ state. At VM creation time, all memory is shared, i.e. the PRIVATE attribute
+ is '0' for all gfns. Userspace can control whether memory is shared/private by
+ toggling KVM_MEMORY_ATTRIBUTE_PRIVATE via KVM_SET_MEMORY_ATTRIBUTES as needed.
+
++S390:
++^^^^^
++
++Returns -EINVAL if the VM has the KVM_VM_S390_UCONTROL flag set.
++Returns -EINVAL if called on a protected VM.
++
+ 4.141 KVM_SET_MEMORY_ATTRIBUTES
+ -------------------------------
+
+diff --git a/Makefile b/Makefile
+index 07e1aec72c171..c0af6d8aeb05f 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 2
++SUBLEVEL = 3
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm/boot/dts/allwinner/Makefile b/arch/arm/boot/dts/allwinner/Makefile
+index 4247f19b1adc2..cd0d044882cf8 100644
+--- a/arch/arm/boot/dts/allwinner/Makefile
++++ b/arch/arm/boot/dts/allwinner/Makefile
+@@ -261,68 +261,6 @@ dtb-$(CONFIG_MACH_SUN8I) += \
+ sun8i-v3s-licheepi-zero.dtb \
+ sun8i-v3s-licheepi-zero-dock.dtb \
+ sun8i-v40-bananapi-m2-berry.dtb
+-dtb-$(CONFIG_MACH_SUN8I) += \
+- sun8i-a23-evb.dtb \
+- sun8i-a23-gt90h-v4.dtb \
+- sun8i-a23-inet86dz.dtb \
+- sun8i-a23-ippo-q8h-v5.dtb \
+- sun8i-a23-ippo-q8h-v1.2.dtb \
+- sun8i-a23-polaroid-mid2407pxe03.dtb \
+- sun8i-a23-polaroid-mid2809pxe04.dtb \
+- sun8i-a23-q8-tablet.dtb \
+- sun8i-a33-et-q8-v1.6.dtb \
+- sun8i-a33-ga10h-v1.1.dtb \
+- sun8i-a33-inet-d978-rev2.dtb \
+- sun8i-a33-ippo-q8h-v1.2.dtb \
+- sun8i-a33-olinuxino.dtb \
+- sun8i-a33-q8-tablet.dtb \
+- sun8i-a33-sinlinx-sina33.dtb \
+- sun8i-a83t-allwinner-h8homlet-v2.dtb \
+- sun8i-a83t-bananapi-m3.dtb \
+- sun8i-a83t-cubietruck-plus.dtb \
+- sun8i-a83t-tbs-a711.dtb \
+- sun8i-h2-plus-bananapi-m2-zero.dtb \
+- sun8i-h2-plus-libretech-all-h3-cc.dtb \
+- sun8i-h2-plus-orangepi-r1.dtb \
+- sun8i-h2-plus-orangepi-zero.dtb \
+- sun8i-h3-bananapi-m2-plus.dtb \
+- sun8i-h3-bananapi-m2-plus-v1.2.dtb \
+- sun8i-h3-beelink-x2.dtb \
+- sun8i-h3-libretech-all-h3-cc.dtb \
+- sun8i-h3-mapleboard-mp130.dtb \
+- sun8i-h3-nanopi-duo2.dtb \
+- sun8i-h3-nanopi-m1.dtb\
+- \
+- sun8i-h3-nanopi-m1-plus.dtb \
+- sun8i-h3-nanopi-neo.dtb \
+- sun8i-h3-nanopi-neo-air.dtb \
+- sun8i-h3-nanopi-r1.dtb \
+- sun8i-h3-orangepi-2.dtb \
+- sun8i-h3-orangepi-lite.dtb \
+- sun8i-h3-orangepi-one.dtb \
+- sun8i-h3-orangepi-pc.dtb \
+- sun8i-h3-orangepi-pc-plus.dtb \
+- sun8i-h3-orangepi-plus.dtb \
+- sun8i-h3-orangepi-plus2e.dtb \
+- sun8i-h3-orangepi-zero-plus2.dtb \
+- sun8i-h3-rervision-dvk.dtb \
+- sun8i-h3-zeropi.dtb \
+- sun8i-h3-emlid-neutis-n5h3-devboard.dtb \
+- sun8i-r16-bananapi-m2m.dtb \
+- sun8i-r16-nintendo-nes-classic.dtb \
+- sun8i-r16-nintendo-super-nes-classic.dtb \
+- sun8i-r16-parrot.dtb \
+- sun8i-r40-bananapi-m2-ultra.dtb \
+- sun8i-r40-oka40i-c.dtb \
+- sun8i-s3-elimo-initium.dtb \
+- sun8i-s3-lichee-zero-plus.dtb \
+- sun8i-s3-pinecube.dtb \
+- sun8i-t113s-mangopi-mq-r-t113.dtb \
+- sun8i-t3-cqa3t-bv3.dtb \
+- sun8i-v3-sl631-imx179.dtb \
+- sun8i-v3s-licheepi-zero.dtb \
+- sun8i-v3s-licheepi-zero-dock.dtb \
+- sun8i-v40-bananapi-m2-berry.dtb
+ dtb-$(CONFIG_MACH_SUN9I) += \
+ sun9i-a80-optimus.dtb \
+ sun9i-a80-cubieboard4.dtb
+diff --git a/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi b/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi
+index 4d6a0c3e8455f..ff062f4fd726e 100644
+--- a/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi
++++ b/arch/arm/boot/dts/nxp/imx/imx6q-kontron-samx6i.dtsi
+@@ -5,31 +5,8 @@
+
+ #include "imx6q.dtsi"
+ #include "imx6qdl-kontron-samx6i.dtsi"
+-#include <dt-bindings/gpio/gpio.h>
+
+ / {
+ model = "Kontron SMARC sAMX6i Quad/Dual";
+ compatible = "kontron,imx6q-samx6i", "fsl,imx6q";
+ };
+-
+-/* Quad/Dual SoMs have 3 chip-select signals */
+-&ecspi4 {
+- cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>,
+- <&gpio3 29 GPIO_ACTIVE_LOW>,
+- <&gpio3 25 GPIO_ACTIVE_LOW>;
+-};
+-
+-&pinctrl_ecspi4 {
+- fsl,pins = <
+- MX6QDL_PAD_EIM_D21__ECSPI4_SCLK 0x100b1
+- MX6QDL_PAD_EIM_D28__ECSPI4_MOSI 0x100b1
+- MX6QDL_PAD_EIM_D22__ECSPI4_MISO 0x100b1
+-
+- /* SPI4_IMX_CS2# - connected to internal flash */
+- MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0
+- /* SPI4_IMX_CS0# - connected to SMARC SPI0_CS0# */
+- MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0
+- /* SPI4_CS3# - connected to SMARC SPI0_CS1# */
+- MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0
+- >;
+-};
+diff --git a/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi b/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi
+index 85aeebc9485dd..668d33d1ff0c1 100644
+--- a/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi
++++ b/arch/arm/boot/dts/nxp/imx/imx6qdl-kontron-samx6i.dtsi
+@@ -244,7 +244,8 @@ &ecspi4 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_ecspi4>;
+ cs-gpios = <&gpio3 24 GPIO_ACTIVE_LOW>,
+- <&gpio3 29 GPIO_ACTIVE_LOW>;
++ <&gpio3 29 GPIO_ACTIVE_LOW>,
++ <&gpio3 25 GPIO_ACTIVE_LOW>;
+ status = "okay";
+
+ /* default boot source: workaround #1 for errata ERR006282 */
+@@ -259,7 +260,7 @@ smarc_flash: flash@0 {
+ &fec {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_enet>;
+- phy-mode = "rgmii";
++ phy-connection-type = "rgmii-id";
+ phy-handle = <ðphy>;
+
+ mdio {
+@@ -269,7 +270,7 @@ mdio {
+ ethphy: ethernet-phy@1 {
+ compatible = "ethernet-phy-ieee802.3-c22";
+ reg = <1>;
+- reset-gpios = <&gpio1 25 GPIO_ACTIVE_LOW>;
++ reset-gpios = <&gpio2 1 GPIO_ACTIVE_LOW>;
+ reset-assert-us = <1000>;
+ };
+ };
+@@ -464,6 +465,8 @@ MX6QDL_PAD_EIM_D22__ECSPI4_MISO 0x100b1
+ MX6QDL_PAD_EIM_D24__GPIO3_IO24 0x1b0b0
+ /* SPI_IMX_CS0# - connected to SMARC SPI0_CS0# */
+ MX6QDL_PAD_EIM_D29__GPIO3_IO29 0x1b0b0
++ /* SPI4_CS3# - connected to SMARC SPI0_CS1# */
++ MX6QDL_PAD_EIM_D25__GPIO3_IO25 0x1b0b0
+ >;
+ };
+
+@@ -516,7 +519,7 @@ MX6QDL_PAD_RGMII_RX_CTL__RGMII_RX_CTL 0x1b0b0
+ MX6QDL_PAD_ENET_MDIO__ENET_MDIO 0x1b0b0
+ MX6QDL_PAD_ENET_MDC__ENET_MDC 0x1b0b0
+ MX6QDL_PAD_ENET_REF_CLK__ENET_TX_CLK 0x1b0b0
+- MX6QDL_PAD_ENET_CRS_DV__GPIO1_IO25 0x1b0b0 /* RST_GBE0_PHY# */
++ MX6QDL_PAD_NANDF_D1__GPIO2_IO01 0x1b0b0 /* RST_GBE0_PHY# */
+ >;
+ };
+
+@@ -729,7 +732,7 @@ &pcie {
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_pcie>;
+ wake-up-gpio = <&gpio6 18 GPIO_ACTIVE_HIGH>;
+- reset-gpio = <&gpio3 13 GPIO_ACTIVE_HIGH>;
++ reset-gpio = <&gpio3 13 GPIO_ACTIVE_LOW>;
+ };
+
+ /* LCD_BKLT_PWM */
+@@ -817,5 +820,6 @@ &wdog1 {
+ /* CPLD is feeded by watchdog (hardwired) */
+ pinctrl-names = "default";
+ pinctrl-0 = <&pinctrl_wdog1>;
++ fsl,ext-reset-output;
+ status = "okay";
+ };
+diff --git a/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-common.dtsi b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-common.dtsi
+index 525d8c608b06f..8839b23fc6936 100644
+--- a/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-common.dtsi
++++ b/arch/arm/boot/dts/qcom/qcom-msm8226-microsoft-common.dtsi
+@@ -287,6 +287,10 @@ &sdhc_2 {
+ status = "okay";
+ };
+
++&smbb {
++ status = "okay";
++};
++
+ &usb {
+ extcon = <&smbb>;
+ dr_mode = "peripheral";
+diff --git a/arch/arm/boot/dts/st/stm32mp151.dtsi b/arch/arm/boot/dts/st/stm32mp151.dtsi
+index 90c5c72c87ab7..4f878ec102c1f 100644
+--- a/arch/arm/boot/dts/st/stm32mp151.dtsi
++++ b/arch/arm/boot/dts/st/stm32mp151.dtsi
+@@ -50,6 +50,7 @@ timer {
+ <GIC_PPI 11 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>,
+ <GIC_PPI 10 (GIC_CPU_MASK_SIMPLE(1) | IRQ_TYPE_LEVEL_LOW)>;
+ interrupt-parent = <&intc>;
++ arm,no-tick-in-suspend;
+ };
+
+ clocks {
+diff --git a/arch/arm/mach-pxa/spitz.c b/arch/arm/mach-pxa/spitz.c
+index 3c5f5a3cb480c..10ab16dcd8276 100644
+--- a/arch/arm/mach-pxa/spitz.c
++++ b/arch/arm/mach-pxa/spitz.c
+@@ -520,10 +520,8 @@ static struct gpiod_lookup_table spitz_ads7846_gpio_table = {
+ static struct gpiod_lookup_table spitz_lcdcon_gpio_table = {
+ .dev_id = "spi2.1",
+ .table = {
+- GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_CONT,
+- "BL_CONT", GPIO_ACTIVE_LOW),
+- GPIO_LOOKUP("gpio-pxa", SPITZ_GPIO_BACKLIGHT_ON,
+- "BL_ON", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("sharp-scoop.1", 6, "BL_CONT", GPIO_ACTIVE_LOW),
++ GPIO_LOOKUP("sharp-scoop.1", 7, "BL_ON", GPIO_ACTIVE_HIGH),
+ { },
+ },
+ };
+@@ -531,10 +529,8 @@ static struct gpiod_lookup_table spitz_lcdcon_gpio_table = {
+ static struct gpiod_lookup_table akita_lcdcon_gpio_table = {
+ .dev_id = "spi2.1",
+ .table = {
+- GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_CONT,
+- "BL_CONT", GPIO_ACTIVE_LOW),
+- GPIO_LOOKUP("gpio-pxa", AKITA_GPIO_BACKLIGHT_ON,
+- "BL_ON", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("i2c-max7310", 3, "BL_ON", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("i2c-max7310", 4, "BL_CONT", GPIO_ACTIVE_LOW),
+ { },
+ },
+ };
+@@ -964,12 +960,9 @@ static inline void spitz_i2c_init(void) {}
+ static struct gpiod_lookup_table spitz_audio_gpio_table = {
+ .dev_id = "spitz-audio",
+ .table = {
+- GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE,
+- "mute-l", GPIO_ACTIVE_HIGH),
+- GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE,
+- "mute-r", GPIO_ACTIVE_HIGH),
+- GPIO_LOOKUP("sharp-scoop.1", SPITZ_GPIO_MIC_BIAS - SPITZ_SCP2_GPIO_BASE,
+- "mic", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("sharp-scoop.1", 8, "mic", GPIO_ACTIVE_HIGH),
+ { },
+ },
+ };
+@@ -977,12 +970,9 @@ static struct gpiod_lookup_table spitz_audio_gpio_table = {
+ static struct gpiod_lookup_table akita_audio_gpio_table = {
+ .dev_id = "spitz-audio",
+ .table = {
+- GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_L - SPITZ_SCP_GPIO_BASE,
+- "mute-l", GPIO_ACTIVE_HIGH),
+- GPIO_LOOKUP("sharp-scoop.0", SPITZ_GPIO_MUTE_R - SPITZ_SCP_GPIO_BASE,
+- "mute-r", GPIO_ACTIVE_HIGH),
+- GPIO_LOOKUP("i2c-max7310", AKITA_GPIO_MIC_BIAS - AKITA_IOEXP_GPIO_BASE,
+- "mic", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("sharp-scoop.0", 3, "mute-l", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("sharp-scoop.0", 4, "mute-r", GPIO_ACTIVE_HIGH),
++ GPIO_LOOKUP("i2c-max7310", 2, "mic", GPIO_ACTIVE_HIGH),
+ { },
+ },
+ };
+diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
+index 67c425341a951..ab01b51de5590 100644
+--- a/arch/arm/mm/fault.c
++++ b/arch/arm/mm/fault.c
+@@ -25,6 +25,8 @@
+
+ #include "fault.h"
+
++#ifdef CONFIG_MMU
++
+ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
+ {
+ unsigned long addr = (unsigned long)unsafe_src;
+@@ -32,8 +34,6 @@ bool copy_from_kernel_nofault_allowed(const void *unsafe_src, size_t size)
+ return addr >= TASK_SIZE && ULONG_MAX - addr >= size;
+ }
+
+-#ifdef CONFIG_MMU
+-
+ /*
+ * This is useful to dump out the page tables associated with
+ * 'addr' in mm 'mm'.
+diff --git a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+index b058ed78faf00..dbadbdb8f9310 100644
+--- a/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
++++ b/arch/arm64/boot/dts/amlogic/meson-g12-common.dtsi
+@@ -215,6 +215,11 @@ hdmi_tx: hdmi-tx@0 {
+ #sound-dai-cells = <0>;
+ status = "disabled";
+
++ assigned-clocks = <&clkc CLKID_HDMI_SEL>,
++ <&clkc CLKID_HDMI>;
++ assigned-clock-parents = <&xtal>, <0>;
++ assigned-clock-rates = <0>, <24000000>;
++
+ /* VPU VENC Input */
+ hdmi_tx_venc_port: port@0 {
+ reg = <0>;
+diff --git a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi
+index e732df3f3114d..664912d1beaab 100644
+--- a/arch/arm64/boot/dts/amlogic/meson-g12.dtsi
++++ b/arch/arm64/boot/dts/amlogic/meson-g12.dtsi
+@@ -363,6 +363,10 @@ ðmac {
+ power-domains = <&pwrc PWRC_G12A_ETH_ID>;
+ };
+
++&hdmi_tx {
++ power-domains = <&pwrc PWRC_G12A_VPU_ID>;
++};
++
+ &vpu {
+ power-domains = <&pwrc PWRC_G12A_VPU_ID>;
+ };
+diff --git a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+index 12ef6e81c8bd6..ed00e67e6923a 100644
+--- a/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
++++ b/arch/arm64/boot/dts/amlogic/meson-gxbb.dtsi
+@@ -311,10 +311,16 @@ &hdmi_tx {
+ <&reset RESET_HDMI_SYSTEM_RESET>,
+ <&reset RESET_HDMI_TX>;
+ reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy";
+- clocks = <&clkc CLKID_HDMI_PCLK>,
+- <&clkc CLKID_CLK81>,
++ clocks = <&clkc CLKID_HDMI>,
++ <&clkc CLKID_HDMI_PCLK>,
+ <&clkc CLKID_GCLK_VENCI_INT0>;
+ clock-names = "isfr", "iahb", "venci";
++ power-domains = <&pwrc PWRC_GXBB_VPU_ID>;
++
++ assigned-clocks = <&clkc CLKID_HDMI_SEL>,
++ <&clkc CLKID_HDMI>;
++ assigned-clock-parents = <&xtal>, <0>;
++ assigned-clock-rates = <0>, <24000000>;
+ };
+
+ &sysctrl {
+diff --git a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+index 17bcfa4702e17..f58d1790de1cb 100644
+--- a/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
++++ b/arch/arm64/boot/dts/amlogic/meson-gxl.dtsi
+@@ -323,10 +323,16 @@ &hdmi_tx {
+ <&reset RESET_HDMI_SYSTEM_RESET>,
+ <&reset RESET_HDMI_TX>;
+ reset-names = "hdmitx_apb", "hdmitx", "hdmitx_phy";
+- clocks = <&clkc CLKID_HDMI_PCLK>,
+- <&clkc CLKID_CLK81>,
++ clocks = <&clkc CLKID_HDMI>,
++ <&clkc CLKID_HDMI_PCLK>,
+ <&clkc CLKID_GCLK_VENCI_INT0>;
+ clock-names = "isfr", "iahb", "venci";
++ power-domains = <&pwrc PWRC_GXBB_VPU_ID>;
++
++ assigned-clocks = <&clkc CLKID_HDMI_SEL>,
++ <&clkc CLKID_HDMI>;
++ assigned-clock-parents = <&xtal>, <0>;
++ assigned-clock-rates = <0>, <24000000>;
+ };
+
+ &sysctrl {
+diff --git a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi
+index 643f94d9d08e1..13e742ba00bea 100644
+--- a/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi
++++ b/arch/arm64/boot/dts/amlogic/meson-sm1.dtsi
+@@ -339,7 +339,7 @@ tdmin_lb: audio-controller@3c0 {
+ };
+
+ spdifin: audio-controller@400 {
+- compatible = "amlogic,g12a-spdifin",
++ compatible = "amlogic,sm1-spdifin",
+ "amlogic,axg-spdifin";
+ reg = <0x0 0x400 0x0 0x30>;
+ #sound-dai-cells = <0>;
+@@ -353,7 +353,7 @@ spdifin: audio-controller@400 {
+ };
+
+ spdifout_a: audio-controller@480 {
+- compatible = "amlogic,g12a-spdifout",
++ compatible = "amlogic,sm1-spdifout",
+ "amlogic,axg-spdifout";
+ reg = <0x0 0x480 0x0 0x50>;
+ #sound-dai-cells = <0>;
+@@ -518,6 +518,10 @@ &gpio_intc {
+ "amlogic,meson-gpio-intc";
+ };
+
++&hdmi_tx {
++ power-domains = <&pwrc PWRC_SM1_VPU_ID>;
++};
++
+ &pcie {
+ power-domains = <&pwrc PWRC_SM1_PCIE_ID>;
+ };
+diff --git a/arch/arm64/boot/dts/freescale/imx8mp.dtsi b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+index b92abb5a5c536..ee0c864f27e89 100644
+--- a/arch/arm64/boot/dts/freescale/imx8mp.dtsi
++++ b/arch/arm64/boot/dts/freescale/imx8mp.dtsi
+@@ -789,6 +789,23 @@ pgc_usb2_phy: power-domain@3 {
+ reg = <IMX8MP_POWER_DOMAIN_USB2_PHY>;
+ };
+
++ pgc_mlmix: power-domain@4 {
++ #power-domain-cells = <0>;
++ reg = <IMX8MP_POWER_DOMAIN_MLMIX>;
++ clocks = <&clk IMX8MP_CLK_ML_AXI>,
++ <&clk IMX8MP_CLK_ML_AHB>,
++ <&clk IMX8MP_CLK_NPU_ROOT>;
++ assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
++ <&clk IMX8MP_CLK_ML_AXI>,
++ <&clk IMX8MP_CLK_ML_AHB>;
++ assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
++ <&clk IMX8MP_SYS_PLL1_800M>,
++ <&clk IMX8MP_SYS_PLL1_800M>;
++ assigned-clock-rates = <800000000>,
++ <800000000>,
++ <300000000>;
++ };
++
+ pgc_audio: power-domain@5 {
+ #power-domain-cells = <0>;
+ reg = <IMX8MP_POWER_DOMAIN_AUDIOMIX>;
+@@ -821,6 +838,12 @@ pgc_gpumix: power-domain@7 {
+ assigned-clock-rates = <800000000>, <400000000>;
+ };
+
++ pgc_vpumix: power-domain@8 {
++ #power-domain-cells = <0>;
++ reg = <IMX8MP_POWER_DOMAIN_VPUMIX>;
++ clocks = <&clk IMX8MP_CLK_VPU_ROOT>;
++ };
++
+ pgc_gpu3d: power-domain@9 {
+ #power-domain-cells = <0>;
+ reg = <IMX8MP_POWER_DOMAIN_GPU3D>;
+@@ -836,6 +859,28 @@ pgc_mediamix: power-domain@10 {
+ <&clk IMX8MP_CLK_MEDIA_APB_ROOT>;
+ };
+
++ pgc_vpu_g1: power-domain@11 {
++ #power-domain-cells = <0>;
++ power-domains = <&pgc_vpumix>;
++ reg = <IMX8MP_POWER_DOMAIN_VPU_G1>;
++ clocks = <&clk IMX8MP_CLK_VPU_G1_ROOT>;
++ };
++
++ pgc_vpu_g2: power-domain@12 {
++ #power-domain-cells = <0>;
++ power-domains = <&pgc_vpumix>;
++ reg = <IMX8MP_POWER_DOMAIN_VPU_G2>;
++ clocks = <&clk IMX8MP_CLK_VPU_G2_ROOT>;
++
++ };
++
++ pgc_vpu_vc8000e: power-domain@13 {
++ #power-domain-cells = <0>;
++ power-domains = <&pgc_vpumix>;
++ reg = <IMX8MP_POWER_DOMAIN_VPU_VC8000E>;
++ clocks = <&clk IMX8MP_CLK_VPU_VC8KE_ROOT>;
++ };
++
+ pgc_hdmimix: power-domain@14 {
+ #power-domain-cells = <0>;
+ reg = <IMX8MP_POWER_DOMAIN_HDMIMIX>;
+@@ -873,50 +918,6 @@ pgc_ispdwp: power-domain@18 {
+ reg = <IMX8MP_POWER_DOMAIN_MEDIAMIX_ISPDWP>;
+ clocks = <&clk IMX8MP_CLK_MEDIA_ISP_ROOT>;
+ };
+-
+- pgc_vpumix: power-domain@19 {
+- #power-domain-cells = <0>;
+- reg = <IMX8MP_POWER_DOMAIN_VPUMIX>;
+- clocks = <&clk IMX8MP_CLK_VPU_ROOT>;
+- };
+-
+- pgc_vpu_g1: power-domain@20 {
+- #power-domain-cells = <0>;
+- power-domains = <&pgc_vpumix>;
+- reg = <IMX8MP_POWER_DOMAIN_VPU_G1>;
+- clocks = <&clk IMX8MP_CLK_VPU_G1_ROOT>;
+- };
+-
+- pgc_vpu_g2: power-domain@21 {
+- #power-domain-cells = <0>;
+- power-domains = <&pgc_vpumix>;
+- reg = <IMX8MP_POWER_DOMAIN_VPU_G2>;
+- clocks = <&clk IMX8MP_CLK_VPU_G2_ROOT>;
+- };
+-
+- pgc_vpu_vc8000e: power-domain@22 {
+- #power-domain-cells = <0>;
+- power-domains = <&pgc_vpumix>;
+- reg = <IMX8MP_POWER_DOMAIN_VPU_VC8000E>;
+- clocks = <&clk IMX8MP_CLK_VPU_VC8KE_ROOT>;
+- };
+-
+- pgc_mlmix: power-domain@24 {
+- #power-domain-cells = <0>;
+- reg = <IMX8MP_POWER_DOMAIN_MLMIX>;
+- clocks = <&clk IMX8MP_CLK_ML_AXI>,
+- <&clk IMX8MP_CLK_ML_AHB>,
+- <&clk IMX8MP_CLK_NPU_ROOT>;
+- assigned-clocks = <&clk IMX8MP_CLK_ML_CORE>,
+- <&clk IMX8MP_CLK_ML_AXI>,
+- <&clk IMX8MP_CLK_ML_AHB>;
+- assigned-clock-parents = <&clk IMX8MP_SYS_PLL1_800M>,
+- <&clk IMX8MP_SYS_PLL1_800M>,
+- <&clk IMX8MP_SYS_PLL1_800M>;
+- assigned-clock-rates = <800000000>,
+- <800000000>,
+- <300000000>;
+- };
+ };
+ };
+ };
+diff --git a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
+index 224bb289660c0..2791de5b28f6a 100644
+--- a/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
++++ b/arch/arm64/boot/dts/mediatek/mt7622-bananapi-bpi-r64.dts
+@@ -329,8 +329,8 @@ asm_sel {
+ /* eMMC is shared pin with parallel NAND */
+ emmc_pins_default: emmc-pins-default {
+ mux {
+- function = "emmc", "emmc_rst";
+- groups = "emmc";
++ function = "emmc";
++ groups = "emmc", "emmc_rst";
+ };
+
+ /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7",
+diff --git a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
+index 41629769bdc85..8c3e2e2578bce 100644
+--- a/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
++++ b/arch/arm64/boot/dts/mediatek/mt7622-rfb1.dts
+@@ -268,8 +268,8 @@ &pio {
+ /* eMMC is shared pin with parallel NAND */
+ emmc_pins_default: emmc-pins-default {
+ mux {
+- function = "emmc", "emmc_rst";
+- groups = "emmc";
++ function = "emmc";
++ groups = "emmc", "emmc_rst";
+ };
+
+ /* "NDL0","NDL1","NDL2","NDL3","NDL4","NDL5","NDL6","NDL7",
+diff --git a/arch/arm64/boot/dts/mediatek/mt7981b.dtsi b/arch/arm64/boot/dts/mediatek/mt7981b.dtsi
+index 4feff3d1c5f4e..178e1e96c3a49 100644
+--- a/arch/arm64/boot/dts/mediatek/mt7981b.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt7981b.dtsi
+@@ -78,10 +78,10 @@ pwm@10048000 {
+ compatible = "mediatek,mt7981-pwm";
+ reg = <0 0x10048000 0 0x1000>;
+ clocks = <&infracfg CLK_INFRA_PWM_STA>,
+- <&infracfg CLK_INFRA_PWM_HCK>,
+- <&infracfg CLK_INFRA_PWM1_CK>,
+- <&infracfg CLK_INFRA_PWM2_CK>,
+- <&infracfg CLK_INFRA_PWM3_CK>;
++ <&infracfg CLK_INFRA_PWM_HCK>,
++ <&infracfg CLK_INFRA_PWM1_CK>,
++ <&infracfg CLK_INFRA_PWM2_CK>,
++ <&infracfg CLK_INFRA_PWM3_CK>;
+ clock-names = "top", "main", "pwm1", "pwm2", "pwm3";
+ #pwm-cells = <2>;
+ };
+diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi
+index 8b57706ac8140..586eee79c73cf 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-audio-da7219.dtsi
+@@ -27,7 +27,7 @@ da7219_aad {
+ dlg,btn-cfg = <50>;
+ dlg,mic-det-thr = <500>;
+ dlg,jack-ins-deb = <20>;
+- dlg,jack-det-rate = "32ms_64ms";
++ dlg,jack-det-rate = "32_64";
+ dlg,jack-rem-deb = <1>;
+
+ dlg,a-d-btn-thr = <0xa>;
+diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
+index 6a7ae616512d6..0d5a11c93c681 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
++++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi-pico6.dts
+@@ -17,7 +17,7 @@ bt_wakeup: bt-wakeup {
+ pinctrl-names = "default";
+ pinctrl-0 = <&bt_pins_wakeup>;
+
+- wobt {
++ event-wobt {
+ label = "Wake on BT";
+ gpios = <&pio 42 GPIO_ACTIVE_HIGH>;
+ linux,code = <KEY_WAKEUP>;
+@@ -47,10 +47,8 @@ trackpad@2c {
+ };
+ };
+
+-&wifi_wakeup {
+- wowlan {
+- gpios = <&pio 113 GPIO_ACTIVE_LOW>;
+- };
++&wifi_wakeup_event {
++ gpios = <&pio 113 GPIO_ACTIVE_LOW>;
+ };
+
+ &wifi_pwrseq {
+diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
+index 7592e3b860377..fa4ab4d2899f9 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui-jacuzzi.dtsi
+@@ -155,21 +155,24 @@ anx_bridge: anx7625@58 {
+ vdd18-supply = <&pp1800_mipibrdg>;
+ vdd33-supply = <&vddio_mipibrdg>;
+
+- #address-cells = <1>;
+- #size-cells = <0>;
+- port@0 {
+- reg = <0>;
++ ports {
++ #address-cells = <1>;
++ #size-cells = <0>;
+
+- anx7625_in: endpoint {
+- remote-endpoint = <&dsi_out>;
++ port@0 {
++ reg = <0>;
++
++ anx7625_in: endpoint {
++ remote-endpoint = <&dsi_out>;
++ };
+ };
+- };
+
+- port@1 {
+- reg = <1>;
++ port@1 {
++ reg = <1>;
+
+- anx7625_out: endpoint {
+- remote-endpoint = <&panel_in>;
++ anx7625_out: endpoint {
++ remote-endpoint = <&panel_in>;
++ };
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+index 100191c6453ba..2fbd226bf142c 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8183-kukui.dtsi
+@@ -152,7 +152,7 @@ wifi_wakeup: wifi-wakeup {
+ pinctrl-names = "default";
+ pinctrl-0 = <&wifi_pins_wakeup>;
+
+- button-wowlan {
++ wifi_wakeup_event: event-wowlan {
+ label = "Wake on WiFi";
+ gpios = <&pio 113 GPIO_ACTIVE_HIGH>;
+ linux,code = <KEY_WAKEUP>;
+@@ -803,7 +803,6 @@ pins-tx {
+ };
+ pins-rts {
+ pinmux = <PINMUX_GPIO47__FUNC_URTS1>;
+- output-enable;
+ };
+ pins-cts {
+ pinmux = <PINMUX_GPIO46__FUNC_UCTS1>;
+@@ -822,7 +821,6 @@ pins-tx {
+ };
+ pins-rts {
+ pinmux = <PINMUX_GPIO47__FUNC_URTS1>;
+- output-enable;
+ };
+ pins-cts {
+ pinmux = <PINMUX_GPIO46__FUNC_UCTS1>;
+diff --git a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
+index 7a704246678f0..08d71ddf36683 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8192-asurada.dtsi
+@@ -147,6 +147,7 @@ pp3300_mipibrdg: regulator-3v3-mipibrdg {
+ regulator-boot-on;
+ gpio = <&pio 127 GPIO_ACTIVE_HIGH>;
+ vin-supply = <&pp3300_g>;
++ off-on-delay-us = <500000>;
+ };
+
+ /* separately switched 3.3V power rail */
+diff --git a/arch/arm64/boot/dts/mediatek/mt8192.dtsi b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
+index 84cbdf6e9eb0c..47dea10dd3b8b 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8192.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8192.dtsi
+@@ -2234,7 +2234,7 @@ vpu1_crit: trip-crit {
+ };
+ };
+
+- gpu0-thermal {
++ gpu-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <250>;
+ thermal-sensors = <&lvts_ap MT8192_AP_GPU0>;
+diff --git a/arch/arm64/boot/dts/mediatek/mt8195.dtsi b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+index 5d8b68f86ce44..2ee45752583c0 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8195.dtsi
++++ b/arch/arm64/boot/dts/mediatek/mt8195.dtsi
+@@ -3880,7 +3880,7 @@ vpu1_crit: trip-crit {
+ };
+ };
+
+- gpu0-thermal {
++ gpu-thermal {
+ polling-delay = <1000>;
+ polling-delay-passive = <250>;
+ thermal-sensors = <&lvts_ap MT8195_AP_GPU0>;
+diff --git a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
+index e5d9b671a4057..97634cc04e659 100644
+--- a/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
++++ b/arch/arm64/boot/dts/mediatek/mt8395-radxa-nio-12l.dts
+@@ -528,7 +528,7 @@ i2c6_pins: i2c6-pins {
+ pins {
+ pinmux = <PINMUX_GPIO25__FUNC_SDA6>,
+ <PINMUX_GPIO26__FUNC_SCL6>;
+- bias-pull-up = <MTK_PULL_SET_RSEL_111>;
++ bias-disable;
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi
+index 5ab583be9e0a0..0386636a29f05 100644
+--- a/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi
++++ b/arch/arm64/boot/dts/qcom/msm8996-xiaomi-common.dtsi
+@@ -405,7 +405,6 @@ &usb3_dwc3 {
+
+ &hsusb_phy1 {
+ status = "okay";
+- extcon = <&typec>;
+
+ vdda-pll-supply = <&vreg_l12a_1p8>;
+ vdda-phy-dpdm-supply = <&vreg_l24a_3p075>;
+diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
+index 6e7a4bb08b35c..0717605ac5a0e 100644
+--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
++++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
+@@ -2102,7 +2102,7 @@ ufshc: ufshc@624000 {
+ <&gcc GCC_UFS_RX_SYMBOL_0_CLK>;
+ freq-table-hz =
+ <100000000 200000000>,
+- <0 0>,
++ <100000000 200000000>,
+ <0 0>,
+ <0 0>,
+ <0 0>,
+diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
+index 2dbef4b526ab7..a88bff737d173 100644
+--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
++++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
+@@ -1590,7 +1590,6 @@ adreno_smmu: iommu@5040000 {
+ * SoC VDDMX RPM Power Domain in the Adreno driver.
+ */
+ power-domains = <&gpucc GPU_GX_GDSC>;
+- status = "disabled";
+ };
+
+ gpucc: clock-controller@5065000 {
+diff --git a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
+index f3432701945f7..8cd2fe80dbb2c 100644
+--- a/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
++++ b/arch/arm64/boot/dts/qcom/qcm6490-fairphone-fp5.dts
+@@ -864,7 +864,6 @@ sw_ctrl_default: sw-ctrl-default-state {
+ };
+
+ &uart5 {
+- compatible = "qcom,geni-debug-uart";
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
+index 47ca2d0003414..107302680f562 100644
+--- a/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
++++ b/arch/arm64/boot/dts/qcom/qcm6490-idp.dts
+@@ -658,7 +658,6 @@ &tlmm {
+ };
+
+ &uart5 {
+- compatible = "qcom,geni-debug-uart";
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
+index a085ff5b5fb21..7256b51eb08f9 100644
+--- a/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
++++ b/arch/arm64/boot/dts/qcom/qcs6490-rb3gen2.dts
+@@ -632,7 +632,6 @@ &tlmm {
+ };
+
+ &uart5 {
+- compatible = "qcom,geni-debug-uart";
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/qdu1000.dtsi b/arch/arm64/boot/dts/qcom/qdu1000.dtsi
+index f90f03fa6a24f..1da40f4b4f8ac 100644
+--- a/arch/arm64/boot/dts/qcom/qdu1000.dtsi
++++ b/arch/arm64/boot/dts/qcom/qdu1000.dtsi
+@@ -1478,6 +1478,21 @@ system-cache-controller@19200000 {
+ "llcc7_base",
+ "llcc_broadcast_base";
+ interrupts = <GIC_SPI 266 IRQ_TYPE_LEVEL_HIGH>;
++
++ nvmem-cells = <&multi_chan_ddr>;
++ nvmem-cell-names = "multi-chan-ddr";
++ };
++
++ sec_qfprom: efuse@221c8000 {
++ compatible = "qcom,qdu1000-sec-qfprom", "qcom,sec-qfprom";
++ reg = <0 0x221c8000 0 0x1000>;
++ #address-cells = <1>;
++ #size-cells = <1>;
++
++ multi_chan_ddr: multi-chan-ddr@12b {
++ reg = <0x12b 0x1>;
++ bits = <0 2>;
++ };
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
+index cb8a62714a302..1888d99d398b1 100644
+--- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
++++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
+@@ -305,7 +305,7 @@ pmi632_ss_in: endpoint {
+
+ &pmi632_vbus {
+ regulator-min-microamp = <500000>;
+- regulator-max-microamp = <3000000>;
++ regulator-max-microamp = <1000000>;
+ status = "okay";
+ };
+
+@@ -414,6 +414,8 @@ vreg_l9a_1p8: l9 {
+ regulator-min-microvolt = <1800000>;
+ regulator-max-microvolt = <1800000>;
+ regulator-allow-set-load;
++ regulator-always-on;
++ regulator-boot-on;
+ };
+
+ vreg_l10a_1p8: l10 {
+diff --git a/arch/arm64/boot/dts/qcom/sa8775p.dtsi b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
+index 1b3dc0ece54de..490e0369f5299 100644
+--- a/arch/arm64/boot/dts/qcom/sa8775p.dtsi
++++ b/arch/arm64/boot/dts/qcom/sa8775p.dtsi
+@@ -2504,6 +2504,7 @@ ethernet1: ethernet@23000000 {
+ phy-names = "serdes";
+
+ iommus = <&apps_smmu 0x140 0xf>;
++ dma-coherent;
+
+ snps,tso;
+ snps,pbl = <32>;
+@@ -2538,6 +2539,7 @@ ethernet0: ethernet@23040000 {
+ phy-names = "serdes";
+
+ iommus = <&apps_smmu 0x120 0xf>;
++ dma-coherent;
+
+ snps,tso;
+ snps,pbl = <32>;
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-kb.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-kb.dts
+index 919bfaea6189c..340cb119d0a0d 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-kb.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-kb.dts
+@@ -12,6 +12,6 @@ / {
+ compatible = "google,lazor-rev1-sku2", "google,lazor-rev2-sku2", "qcom,sc7180";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-lte.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-lte.dts
+index eb20157f6af98..d45e60e3eb9eb 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-lte.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r1-lte.dts
+@@ -17,6 +17,6 @@ &ap_sar_sensor_i2c {
+ status = "okay";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-kb.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-kb.dts
+index 45d34718a1bce..e906ce877b8cd 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-kb.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-kb.dts
+@@ -18,6 +18,6 @@ / {
+ compatible = "google,lazor-sku2", "qcom,sc7180";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-lte.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-lte.dts
+index 79028d0dd1b0c..4b9ee15b09f6b 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-lte.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r10-lte.dts
+@@ -22,6 +22,6 @@ &ap_sar_sensor_i2c {
+ status = "okay";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-kb.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-kb.dts
+index 3459b81c56283..a960553f39946 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-kb.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-kb.dts
+@@ -21,6 +21,6 @@ / {
+ "qcom,sc7180";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-lte.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-lte.dts
+index ff8f47da109d8..82bd9ed7e21a9 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-lte.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r3-lte.dts
+@@ -25,6 +25,6 @@ &ap_sar_sensor_i2c {
+ status = "okay";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-kb.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-kb.dts
+index faf527972977a..6278c1715d3fd 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-kb.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-kb.dts
+@@ -18,6 +18,6 @@ / {
+ compatible = "google,lazor-rev9-sku2", "qcom,sc7180";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-lte.dts b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-lte.dts
+index d737fd0637fbc..0ec1697ae2c97 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-lte.dts
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor-lazor-r9-lte.dts
+@@ -22,6 +22,6 @@ &ap_sar_sensor_i2c {
+ status = "okay";
+ };
+
+-&keyboard_backlight {
++&pwmleds {
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
+index 8513be2971201..098a8b4c793e6 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc7180-trogdor.dtsi
+@@ -359,10 +359,11 @@ max98360a: audio-codec-0 {
+ #sound-dai-cells = <0>;
+ };
+
+- pwmleds {
++ pwmleds: pwmleds {
+ compatible = "pwm-leds";
++ status = "disabled";
++
+ keyboard_backlight: led-0 {
+- status = "disabled";
+ label = "cros_ec::kbd_backlight";
+ function = LED_FUNCTION_KBD_BACKLIGHT;
+ pwms = <&cros_ec_pwm 0>;
+diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
+index e9deffe3aaf6c..9ab0c98cac054 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
+@@ -1582,8 +1582,7 @@ &mc_virt SLAVE_EBI1 QCOM_ICC_TAG_ALWAYS>,
+ };
+
+ ufs_mem_phy: phy@1d87000 {
+- compatible = "qcom,sc7180-qmp-ufs-phy",
+- "qcom,sm7150-qmp-ufs-phy";
++ compatible = "qcom,sc7180-qmp-ufs-phy";
+ reg = <0 0x01d87000 0 0x1000>;
+ clocks = <&rpmhcc RPMH_CXO_CLK>,
+ <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+diff --git a/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi b/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi
+index a0059527d9e48..7370aa0dbf0e3 100644
+--- a/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc7280-idp.dtsi
+@@ -495,7 +495,6 @@ wcd_tx: codec@0,3 {
+ };
+
+ &uart5 {
+- compatible = "qcom,geni-debug-uart";
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi b/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi
+index f9b96bd2477ea..7d1d5bbbbbd95 100644
+--- a/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc7280-qcard.dtsi
+@@ -427,7 +427,6 @@ wcd_tx: codec@0,3 {
+ };
+
+ uart_dbg: &uart5 {
+- compatible = "qcom,geni-debug-uart";
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
+index 2f7780f629ac5..c4a05d7b7ce65 100644
+--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
+@@ -1440,12 +1440,12 @@ spi5: spi@994000 {
+ };
+
+ uart5: serial@994000 {
+- compatible = "qcom,geni-uart";
++ compatible = "qcom,geni-debug-uart";
+ reg = <0 0x00994000 0 0x4000>;
+ clocks = <&gcc GCC_QUPV3_WRAP0_S5_CLK>;
+ clock-names = "se";
+ pinctrl-names = "default";
+- pinctrl-0 = <&qup_uart5_cts>, <&qup_uart5_rts>, <&qup_uart5_tx>, <&qup_uart5_rx>;
++ pinctrl-0 = <&qup_uart5_tx>, <&qup_uart5_rx>;
+ interrupts = <GIC_SPI 606 IRQ_TYPE_LEVEL_HIGH>;
+ power-domains = <&rpmhpd SC7280_CX>;
+ operating-points-v2 = <&qup_opp_table>;
+@@ -5408,16 +5408,6 @@ qup_uart4_rx: qup-uart4-rx-state {
+ function = "qup04";
+ };
+
+- qup_uart5_cts: qup-uart5-cts-state {
+- pins = "gpio20";
+- function = "qup05";
+- };
+-
+- qup_uart5_rts: qup-uart5-rts-state {
+- pins = "gpio21";
+- function = "qup05";
+- };
+-
+ qup_uart5_tx: qup-uart5-tx-state {
+ pins = "gpio22";
+ function = "qup05";
+diff --git a/arch/arm64/boot/dts/qcom/sc8180x.dtsi b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
+index 581a70c34fd29..da69577b6f09b 100644
+--- a/arch/arm64/boot/dts/qcom/sc8180x.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc8180x.dtsi
+@@ -1890,7 +1890,7 @@ pcie3: pcie@1c08000 {
+ power-domains = <&gcc PCIE_3_GDSC>;
+
+ interconnects = <&aggre2_noc MASTER_PCIE_3 0 &mc_virt SLAVE_EBI_CH0 0>,
+- <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_0 0>;
++ <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_3 0>;
+ interconnect-names = "pcie-mem", "cpu-pcie";
+
+ phys = <&pcie3_phy>;
+@@ -2012,7 +2012,7 @@ pcie1: pcie@1c10000 {
+ power-domains = <&gcc PCIE_1_GDSC>;
+
+ interconnects = <&aggre2_noc MASTER_PCIE_1 0 &mc_virt SLAVE_EBI_CH0 0>,
+- <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_0 0>;
++ <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_1 0>;
+ interconnect-names = "pcie-mem", "cpu-pcie";
+
+ phys = <&pcie1_phy>;
+@@ -2134,7 +2134,7 @@ pcie2: pcie@1c18000 {
+ power-domains = <&gcc PCIE_2_GDSC>;
+
+ interconnects = <&aggre2_noc MASTER_PCIE_2 0 &mc_virt SLAVE_EBI_CH0 0>,
+- <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_0 0>;
++ <&gem_noc MASTER_AMPSS_M0 0 &config_noc SLAVE_PCIE_2 0>;
+ interconnect-names = "pcie-mem", "cpu-pcie";
+
+ phys = <&pcie2_phy>;
+@@ -2245,6 +2245,8 @@ ufs_mem_phy: phy-wrapper@1d87000 {
+ resets = <&ufs_mem_hc 0>;
+ reset-names = "ufsphy";
+
++ power-domains = <&gcc UFS_PHY_GDSC>;
++
+ #phy-cells = <0>;
+
+ status = "disabled";
+diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
+index 4bf99b6b6e5fb..6b759e67f4d3d 100644
+--- a/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
++++ b/arch/arm64/boot/dts/qcom/sc8280xp-lenovo-thinkpad-x13s.dts
+@@ -299,7 +299,7 @@ linux,cma {
+ thermal-zones {
+ skin-temp-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <0>;
++
+ thermal-sensors = <&pmk8280_adc_tm 5>;
+
+ trips {
+diff --git a/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi
+index 945de77911de1..1e3babf2e40d8 100644
+--- a/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc8280xp-pmics.dtsi
+@@ -14,7 +14,7 @@ / {
+ thermal-zones {
+ pm8280_1_thermal: pm8280-1-thermal {
+ polling-delay-passive = <100>;
+- polling-delay = <0>;
++
+ thermal-sensors = <&pm8280_1_temp_alarm>;
+
+ trips {
+@@ -34,7 +34,7 @@ trip1 {
+
+ pm8280_2_thermal: pm8280-2-thermal {
+ polling-delay-passive = <100>;
+- polling-delay = <0>;
++
+ thermal-sensors = <&pm8280_2_temp_alarm>;
+
+ trips {
+diff --git a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
+index 59f0a850671a3..b0b0ab7794466 100644
+--- a/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc8280xp.dtsi
+@@ -5833,7 +5833,6 @@ sound: sound {
+ thermal-zones {
+ cpu0-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 1>;
+
+@@ -5848,7 +5847,6 @@ cpu-crit {
+
+ cpu1-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 2>;
+
+@@ -5863,7 +5861,6 @@ cpu-crit {
+
+ cpu2-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 3>;
+
+@@ -5878,7 +5875,6 @@ cpu-crit {
+
+ cpu3-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 4>;
+
+@@ -5893,7 +5889,6 @@ cpu-crit {
+
+ cpu4-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 5>;
+
+@@ -5908,7 +5903,6 @@ cpu-crit {
+
+ cpu5-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 6>;
+
+@@ -5923,7 +5917,6 @@ cpu-crit {
+
+ cpu6-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 7>;
+
+@@ -5938,7 +5931,6 @@ cpu-crit {
+
+ cpu7-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 8>;
+
+@@ -5953,7 +5945,6 @@ cpu-crit {
+
+ cluster0-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens0 9>;
+
+@@ -5967,13 +5958,25 @@ cpu-crit {
+ };
+
+ gpu-thermal {
+- polling-delay-passive = <0>;
+- polling-delay = <0>;
++ polling-delay-passive = <250>;
+
+ thermal-sensors = <&tsens2 2>;
+
++ cooling-maps {
++ map0 {
++ trip = <&gpu_alert0>;
++ cooling-device = <&gpu THERMAL_NO_LIMIT THERMAL_NO_LIMIT>;
++ };
++ };
++
+ trips {
+- gpu-crit {
++ gpu_alert0: trip-point0 {
++ temperature = <85000>;
++ hysteresis = <1000>;
++ type = "passive";
++ };
++
++ trip-point1 {
+ temperature = <110000>;
+ hysteresis = <1000>;
+ type = "critical";
+@@ -5983,7 +5986,6 @@ gpu-crit {
+
+ mem-thermal {
+ polling-delay-passive = <250>;
+- polling-delay = <1000>;
+
+ thermal-sensors = <&tsens1 15>;
+
+diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
+index d817a7751086e..4ad82b0eb1139 100644
+--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
++++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
+@@ -2666,6 +2666,8 @@ ufs_mem_phy: phy@1d87000 {
+ "ref_aux",
+ "qref";
+
++ power-domains = <&gcc UFS_PHY_GDSC>;
++
+ resets = <&ufs_mem_hc 0>;
+ reset-names = "ufsphy";
+
+diff --git a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
+index 47dc42f6e936c..8e30f8cc0916c 100644
+--- a/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
++++ b/arch/arm64/boot/dts/qcom/sdm850-lenovo-yoga-c630.dts
+@@ -494,6 +494,7 @@ ecsh: hid@5c {
+ &ipa {
+ qcom,gsi-loader = "self";
+ memory-region = <&ipa_fw_mem>;
++ firmware-name = "qcom/sdm850/LENOVO/81JL/ipa_fws.elf";
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi
+index b4ce5a322107e..8fa3bacfb2391 100644
+--- a/arch/arm64/boot/dts/qcom/sm6115.dtsi
++++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi
+@@ -1231,6 +1231,8 @@ ufs_mem_phy: phy@4807000 {
+ "ref_aux",
+ "qref";
+
++ power-domains = <&gcc GCC_UFS_PHY_GDSC>;
++
+ resets = <&ufs_mem_hc 0>;
+ reset-names = "ufsphy";
+
+diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi
+index 6c7eac0110ba1..60383f0d09f32 100644
+--- a/arch/arm64/boot/dts/qcom/sm6350.dtsi
++++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi
+@@ -1197,6 +1197,8 @@ ufs_mem_phy: phy@1d87000 {
+ "ref_aux",
+ "qref";
+
++ power-domains = <&gcc UFS_PHY_GDSC>;
++
+ resets = <&ufs_mem_hc 0>;
+ reset-names = "ufsphy";
+
+@@ -1321,6 +1323,7 @@ fastrpc {
+ compatible = "qcom,fastrpc";
+ qcom,glink-channels = "fastrpcglink-apps-dsp";
+ label = "adsp";
++ qcom,non-secure-domain;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+@@ -1580,6 +1583,7 @@ fastrpc {
+ compatible = "qcom,fastrpc";
+ qcom,glink-channels = "fastrpcglink-apps-dsp";
+ label = "cdsp";
++ qcom,non-secure-domain;
+ #address-cells = <1>;
+ #size-cells = <0>;
+
+diff --git a/arch/arm64/boot/dts/qcom/sm8250.dtsi b/arch/arm64/boot/dts/qcom/sm8250.dtsi
+index 8ccade628f1f4..b2af44bc3b78c 100644
+--- a/arch/arm64/boot/dts/qcom/sm8250.dtsi
++++ b/arch/arm64/boot/dts/qcom/sm8250.dtsi
+@@ -2580,6 +2580,8 @@ ufs_mem_phy: phy@1d87000 {
+ resets = <&ufs_mem_hc 0>;
+ reset-names = "ufsphy";
+
++ power-domains = <&gcc UFS_PHY_GDSC>;
++
+ #phy-cells = <0>;
+
+ status = "disabled";
+diff --git a/arch/arm64/boot/dts/qcom/sm8350.dtsi b/arch/arm64/boot/dts/qcom/sm8350.dtsi
+index f7c4700f00c36..da936548c2ac3 100644
+--- a/arch/arm64/boot/dts/qcom/sm8350.dtsi
++++ b/arch/arm64/boot/dts/qcom/sm8350.dtsi
+@@ -1779,6 +1779,8 @@ ufs_mem_phy: phy@1d87000 {
+ "ref_aux",
+ "qref";
+
++ power-domains = <&gcc UFS_PHY_GDSC>;
++
+ resets = <&ufs_mem_hc 0>;
+ reset-names = "ufsphy";
+
+diff --git a/arch/arm64/boot/dts/qcom/sm8450.dtsi b/arch/arm64/boot/dts/qcom/sm8450.dtsi
+index 616461fcbab99..59428d2ee1ad8 100644
+--- a/arch/arm64/boot/dts/qcom/sm8450.dtsi
++++ b/arch/arm64/boot/dts/qcom/sm8450.dtsi
+@@ -4429,6 +4429,8 @@ ufs_mem_phy: phy@1d87000 {
+ <&gcc GCC_UFS_PHY_PHY_AUX_CLK>,
+ <&gcc GCC_UFS_0_CLKREF_EN>;
+
++ power-domains = <&gcc UFS_PHY_GDSC>;
++
+ resets = <&ufs_mem_hc 0>;
+ reset-names = "ufsphy";
+
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+index 7618ae1f8b1c9..b063dd28149e7 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+@@ -840,7 +840,7 @@ &uart21 {
+ };
+
+ &usb_1_ss0_hsphy {
+- vdd-supply = <&vreg_l2e_0p8>;
++ vdd-supply = <&vreg_l3j_0p8>;
+ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_0_eusb2_repeater>;
+@@ -865,7 +865,7 @@ &usb_1_ss0_dwc3 {
+ };
+
+ &usb_1_ss1_hsphy {
+- vdd-supply = <&vreg_l2e_0p8>;
++ vdd-supply = <&vreg_l3j_0p8>;
+ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_1_eusb2_repeater>;
+@@ -890,7 +890,7 @@ &usb_1_ss1_dwc3 {
+ };
+
+ &usb_1_ss2_hsphy {
+- vdd-supply = <&vreg_l2e_0p8>;
++ vdd-supply = <&vreg_l3j_0p8>;
+ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_2_eusb2_repeater>;
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+index 5567636c8b27f..df3577fcd93c9 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+@@ -536,7 +536,7 @@ &uart21 {
+ };
+
+ &usb_1_ss0_hsphy {
+- vdd-supply = <&vreg_l2e_0p8>;
++ vdd-supply = <&vreg_l3j_0p8>;
+ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_0_eusb2_repeater>;
+@@ -561,7 +561,7 @@ &usb_1_ss0_dwc3 {
+ };
+
+ &usb_1_ss1_hsphy {
+- vdd-supply = <&vreg_l2e_0p8>;
++ vdd-supply = <&vreg_l3j_0p8>;
+ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_1_eusb2_repeater>;
+@@ -586,7 +586,7 @@ &usb_1_ss1_dwc3 {
+ };
+
+ &usb_1_ss2_hsphy {
+- vdd-supply = <&vreg_l2e_0p8>;
++ vdd-supply = <&vreg_l3j_0p8>;
+ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_2_eusb2_repeater>;
+diff --git a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
+index cfa70b441e329..d76347001cc13 100644
+--- a/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
++++ b/arch/arm64/boot/dts/renesas/r8a779a0.dtsi
+@@ -2919,6 +2919,9 @@ timer {
+ interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+- <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
++ <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
++ <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-names = "sec-phys", "phys", "virt", "hyp-phys",
++ "hyp-virt";
+ };
+ };
+diff --git a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
+index 72cf30341fc4d..9629adb47d99f 100644
+--- a/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
++++ b/arch/arm64/boot/dts/renesas/r8a779f0.dtsi
+@@ -1324,7 +1324,10 @@ timer {
+ interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+- <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
++ <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
++ <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-names = "sec-phys", "phys", "virt", "hyp-phys",
++ "hyp-virt";
+ };
+
+ ufs30_clk: ufs30-clk {
+diff --git a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
+index 9bc542bc61690..873588a84e15f 100644
+--- a/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
++++ b/arch/arm64/boot/dts/renesas/r8a779g0.dtsi
+@@ -2359,6 +2359,9 @@ timer {
+ interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+- <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
++ <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
++ <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-names = "sec-phys", "phys", "virt", "hyp-phys",
++ "hyp-virt";
+ };
+ };
+diff --git a/arch/arm64/boot/dts/renesas/r8a779h0.dtsi b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
+index 6d791024cabe1..792afe1a45747 100644
+--- a/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
++++ b/arch/arm64/boot/dts/renesas/r8a779h0.dtsi
+@@ -16,7 +16,6 @@ / {
+
+ cluster0_opp: opp-table-0 {
+ compatible = "operating-points-v2";
+- opp-shared;
+
+ opp-500000000 {
+ opp-hz = /bits/ 64 <500000000>;
+diff --git a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
+index 165bfcfef3bcc..18ef297db9336 100644
+--- a/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a07g043u.dtsi
+@@ -50,7 +50,10 @@ timer {
+ interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+- <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
++ <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
++ <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-names = "sec-phys", "phys", "virt", "hyp-phys",
++ "hyp-virt";
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
+index 88634ae432872..1a9891ba6c02c 100644
+--- a/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a07g044.dtsi
+@@ -1334,6 +1334,9 @@ timer {
+ interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+- <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
++ <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
++ <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-names = "sec-phys", "phys", "virt", "hyp-phys",
++ "hyp-virt";
+ };
+ };
+diff --git a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
+index e89bfe4085f5d..a2318478a66ba 100644
+--- a/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a07g054.dtsi
+@@ -1342,6 +1342,9 @@ timer {
+ interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+- <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
++ <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
++ <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-names = "sec-phys", "phys", "virt", "hyp-phys",
++ "hyp-virt";
+ };
+ };
+diff --git a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
+index f5f3f4f4c8d67..a2adc4e27ce97 100644
+--- a/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
++++ b/arch/arm64/boot/dts/renesas/r9a08g045.dtsi
+@@ -294,6 +294,9 @@ timer {
+ interrupts-extended = <&gic GIC_PPI 13 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 14 IRQ_TYPE_LEVEL_LOW>,
+ <&gic GIC_PPI 11 IRQ_TYPE_LEVEL_LOW>,
+- <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>;
++ <&gic GIC_PPI 10 IRQ_TYPE_LEVEL_LOW>,
++ <&gic GIC_PPI 12 IRQ_TYPE_LEVEL_LOW>;
++ interrupt-names = "sec-phys", "phys", "virt", "hyp-phys",
++ "hyp-virt";
+ };
+ };
+diff --git a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts
+index 079101cddd65f..f1d4118ffb7d6 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3308-rock-pi-s.dts
+@@ -17,6 +17,7 @@ aliases {
+ ethernet0 = &gmac;
+ mmc0 = &emmc;
+ mmc1 = &sdmmc;
++ mmc2 = &sdio;
+ };
+
+ chosen {
+@@ -144,11 +145,25 @@ &emmc {
+
+ &gmac {
+ clock_in_out = "output";
++ phy-handle = <&rtl8201f>;
+ phy-supply = <&vcc_io>;
+- snps,reset-gpio = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>;
+- snps,reset-active-low;
+- snps,reset-delays-us = <0 50000 50000>;
+ status = "okay";
++
++ mdio {
++ compatible = "snps,dwmac-mdio";
++ #address-cells = <1>;
++ #size-cells = <0>;
++
++ rtl8201f: ethernet-phy@1 {
++ compatible = "ethernet-phy-ieee802.3-c22";
++ reg = <1>;
++ pinctrl-names = "default";
++ pinctrl-0 = <&mac_rst>;
++ reset-assert-us = <20000>;
++ reset-deassert-us = <50000>;
++ reset-gpios = <&gpio0 RK_PA7 GPIO_ACTIVE_LOW>;
++ };
++ };
+ };
+
+ &gpio0 {
+@@ -221,6 +236,26 @@ &pinctrl {
+ pinctrl-names = "default";
+ pinctrl-0 = <&rtc_32k>;
+
++ bluetooth {
++ bt_reg_on: bt-reg-on {
++ rockchip,pins = <4 RK_PB3 RK_FUNC_GPIO &pcfg_pull_none>;
++ };
++
++ bt_wake_host: bt-wake-host {
++ rockchip,pins = <4 RK_PB4 RK_FUNC_GPIO &pcfg_pull_down>;
++ };
++
++ host_wake_bt: host-wake-bt {
++ rockchip,pins = <4 RK_PB2 RK_FUNC_GPIO &pcfg_pull_none>;
++ };
++ };
++
++ gmac {
++ mac_rst: mac-rst {
++ rockchip,pins = <0 RK_PA7 RK_FUNC_GPIO &pcfg_pull_none>;
++ };
++ };
++
+ leds {
+ green_led: green-led {
+ rockchip,pins = <0 RK_PA6 RK_FUNC_GPIO &pcfg_pull_none>;
+@@ -264,15 +299,31 @@ &sdio {
+ cap-sd-highspeed;
+ cap-sdio-irq;
+ keep-power-in-suspend;
+- max-frequency = <1000000>;
++ max-frequency = <100000000>;
+ mmc-pwrseq = <&sdio_pwrseq>;
++ no-mmc;
++ no-sd;
+ non-removable;
+- sd-uhs-sdr104;
++ sd-uhs-sdr50;
++ vmmc-supply = <&vcc_io>;
++ vqmmc-supply = <&vcc_1v8>;
+ status = "okay";
++
++ rtl8723ds: wifi@1 {
++ reg = <1>;
++ interrupt-parent = <&gpio0>;
++ interrupts = <RK_PA0 IRQ_TYPE_LEVEL_HIGH>;
++ interrupt-names = "host-wake";
++ pinctrl-names = "default";
++ pinctrl-0 = <&wifi_host_wake>;
++ };
+ };
+
+ &sdmmc {
++ cap-mmc-highspeed;
+ cap-sd-highspeed;
++ disable-wp;
++ vmmc-supply = <&vcc_io>;
+ status = "okay";
+ };
+
+@@ -291,16 +342,22 @@ u2phy_otg: otg-port {
+ };
+
+ &uart0 {
++ pinctrl-names = "default";
++ pinctrl-0 = <&uart0_xfer>;
+ status = "okay";
+ };
+
+ &uart4 {
++ uart-has-rtscts;
+ status = "okay";
+
+ bluetooth {
+- compatible = "realtek,rtl8723bs-bt";
+- device-wake-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>;
++ compatible = "realtek,rtl8723ds-bt";
++ device-wake-gpios = <&gpio4 RK_PB2 GPIO_ACTIVE_HIGH>;
++ enable-gpios = <&gpio4 RK_PB3 GPIO_ACTIVE_HIGH>;
+ host-wake-gpios = <&gpio4 RK_PB4 GPIO_ACTIVE_HIGH>;
++ pinctrl-names = "default";
++ pinctrl-0 = <&bt_reg_on &bt_wake_host &host_wake_bt>;
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/rockchip/rk3328.dtsi b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+index 07dcc949b8997..b01efd6d042c8 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3328.dtsi
++++ b/arch/arm64/boot/dts/rockchip/rk3328.dtsi
+@@ -850,8 +850,8 @@ cru: clock-controller@ff440000 {
+ <0>, <24000000>,
+ <24000000>, <24000000>,
+ <15000000>, <15000000>,
+- <100000000>, <100000000>,
+- <100000000>, <100000000>,
++ <300000000>, <100000000>,
++ <400000000>, <100000000>,
+ <50000000>, <100000000>,
+ <100000000>, <100000000>,
+ <50000000>, <50000000>,
+diff --git a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts
+index 63eea27293fe9..67e7801bd4896 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3566-roc-pc.dts
+@@ -269,7 +269,7 @@ rk809: pmic@20 {
+ vcc9-supply = <&vcc3v3_sys>;
+
+ codec {
+- mic-in-differential;
++ rockchip,mic-in-differential;
+ };
+
+ regulators {
+diff --git a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts
+index 19f8fc369b130..8c3ab07d38079 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3568-evb1-v10.dts
+@@ -475,7 +475,7 @@ regulator-state-mem {
+ };
+
+ codec {
+- mic-in-differential;
++ rockchip,mic-in-differential;
+ };
+ };
+ };
+diff --git a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts
+index 58ab7e9971dbc..b5e67990dd0f8 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dts
+@@ -11,6 +11,10 @@ aliases {
+ };
+ };
+
++&pmu_io_domains {
++ vccio3-supply = <&vccio_sd>;
++};
++
+ &sdmmc0 {
+ bus-width = <4>;
+ cap-mmc-highspeed;
+diff --git a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi
+index 89e84e3a92629..25c49bdbadbcb 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi
++++ b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r66s.dtsi
+@@ -39,9 +39,9 @@ status_led: led-status {
+ };
+ };
+
+- dc_12v: dc-12v-regulator {
++ vcc12v_dcin: vcc12v-dcin-regulator {
+ compatible = "regulator-fixed";
+- regulator-name = "dc_12v";
++ regulator-name = "vcc12v_dcin";
+ regulator-always-on;
+ regulator-boot-on;
+ regulator-min-microvolt = <12000000>;
+@@ -65,7 +65,7 @@ vcc3v3_sys: vcc3v3-sys-regulator {
+ regulator-boot-on;
+ regulator-min-microvolt = <3300000>;
+ regulator-max-microvolt = <3300000>;
+- vin-supply = <&dc_12v>;
++ vin-supply = <&vcc12v_dcin>;
+ };
+
+ vcc5v0_sys: vcc5v0-sys-regulator {
+@@ -75,16 +75,7 @@ vcc5v0_sys: vcc5v0-sys-regulator {
+ regulator-boot-on;
+ regulator-min-microvolt = <5000000>;
+ regulator-max-microvolt = <5000000>;
+- vin-supply = <&dc_12v>;
+- };
+-
+- vcc5v0_usb_host: vcc5v0-usb-host-regulator {
+- compatible = "regulator-fixed";
+- regulator-name = "vcc5v0_usb_host";
+- regulator-always-on;
+- regulator-boot-on;
+- regulator-min-microvolt = <5000000>;
+- regulator-max-microvolt = <5000000>;
++ vin-supply = <&vcc12v_dcin>;
+ };
+
+ vcc5v0_usb_otg: vcc5v0-usb-otg-regulator {
+@@ -94,8 +85,9 @@ vcc5v0_usb_otg: vcc5v0-usb-otg-regulator {
+ pinctrl-names = "default";
+ pinctrl-0 = <&vcc5v0_usb_otg_en>;
+ regulator-name = "vcc5v0_usb_otg";
+- regulator-always-on;
+- regulator-boot-on;
++ regulator-min-microvolt = <5000000>;
++ regulator-max-microvolt = <5000000>;
++ vin-supply = <&vcc5v0_sys>;
+ };
+ };
+
+@@ -123,6 +115,10 @@ &cpu3 {
+ cpu-supply = <&vdd_cpu>;
+ };
+
++&display_subsystem {
++ status = "disabled";
++};
++
+ &gpu {
+ mali-supply = <&vdd_gpu>;
+ status = "okay";
+@@ -405,8 +401,8 @@ vcc5v0_usb_otg_en: vcc5v0-usb-otg-en {
+ &pmu_io_domains {
+ pmuio1-supply = <&vcc3v3_pmu>;
+ pmuio2-supply = <&vcc3v3_pmu>;
+- vccio1-supply = <&vccio_acodec>;
+- vccio3-supply = <&vccio_sd>;
++ vccio1-supply = <&vcc_3v3>;
++ vccio2-supply = <&vcc_1v8>;
+ vccio4-supply = <&vcc_1v8>;
+ vccio5-supply = <&vcc_3v3>;
+ vccio6-supply = <&vcc_1v8>;
+@@ -429,28 +425,12 @@ &uart2 {
+ status = "okay";
+ };
+
+-&usb_host0_ehci {
+- status = "okay";
+-};
+-
+-&usb_host0_ohci {
+- status = "okay";
+-};
+-
+ &usb_host0_xhci {
+ dr_mode = "host";
+ extcon = <&usb2phy0>;
+ status = "okay";
+ };
+
+-&usb_host1_ehci {
+- status = "okay";
+-};
+-
+-&usb_host1_ohci {
+- status = "okay";
+-};
+-
+ &usb_host1_xhci {
+ status = "okay";
+ };
+@@ -460,7 +440,7 @@ &usb2phy0 {
+ };
+
+ &usb2phy0_host {
+- phy-supply = <&vcc5v0_usb_host>;
++ phy-supply = <&vcc5v0_sys>;
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts
+index e1fe5e442689a..ce2a5e1ccefc3 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3568-fastrhino-r68s.dts
+@@ -39,7 +39,7 @@ &gmac0_tx_bus2
+ &gmac0_rx_bus2
+ &gmac0_rgmii_clk
+ &gmac0_rgmii_bus>;
+- snps,reset-gpio = <&gpio0 RK_PB0 GPIO_ACTIVE_LOW>;
++ snps,reset-gpio = <&gpio1 RK_PB0 GPIO_ACTIVE_LOW>;
+ snps,reset-active-low;
+ /* Reset time is 15ms, 50ms for rtl8211f */
+ snps,reset-delays-us = <0 15000 50000>;
+@@ -61,7 +61,7 @@ &gmac1m1_tx_bus2
+ &gmac1m1_rx_bus2
+ &gmac1m1_rgmii_clk
+ &gmac1m1_rgmii_bus>;
+- snps,reset-gpio = <&gpio0 RK_PB1 GPIO_ACTIVE_LOW>;
++ snps,reset-gpio = <&gpio1 RK_PB1 GPIO_ACTIVE_LOW>;
+ snps,reset-active-low;
+ /* Reset time is 15ms, 50ms for rtl8211f */
+ snps,reset-delays-us = <0 15000 50000>;
+@@ -71,18 +71,18 @@ &gmac1m1_rgmii_clk
+ };
+
+ &mdio0 {
+- rgmii_phy0: ethernet-phy@0 {
++ rgmii_phy0: ethernet-phy@1 {
+ compatible = "ethernet-phy-ieee802.3-c22";
+- reg = <0>;
++ reg = <0x1>;
+ pinctrl-0 = <ð_phy0_reset_pin>;
+ pinctrl-names = "default";
+ };
+ };
+
+ &mdio1 {
+- rgmii_phy1: ethernet-phy@0 {
++ rgmii_phy1: ethernet-phy@1 {
+ compatible = "ethernet-phy-ieee802.3-c22";
+- reg = <0>;
++ reg = <0x1>;
+ pinctrl-0 = <ð_phy1_reset_pin>;
+ pinctrl-names = "default";
+ };
+@@ -102,6 +102,10 @@ eth_phy1_reset_pin: eth-phy1-reset-pin {
+ };
+ };
+
++&pmu_io_domains {
++ vccio3-supply = <&vcc_3v3>;
++};
++
+ &sdhci {
+ bus-width = <8>;
+ max-frequency = <200000000>;
+diff --git a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
+index ebdedea15ad16..59f1403b4fa56 100644
+--- a/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
++++ b/arch/arm64/boot/dts/rockchip/rk3568-rock-3a.dts
+@@ -531,10 +531,6 @@ regulator-state-mem {
+ };
+ };
+ };
+-
+- codec {
+- mic-in-differential;
+- };
+ };
+ };
+
+diff --git a/arch/arm64/boot/dts/rockchip/rk356x.dtsi b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
+index d8543b5557ee7..3e2a8bfcafeaa 100644
+--- a/arch/arm64/boot/dts/rockchip/rk356x.dtsi
++++ b/arch/arm64/boot/dts/rockchip/rk356x.dtsi
+@@ -790,6 +790,7 @@ vop_mmu: iommu@fe043e00 {
+ clocks = <&cru ACLK_VOP>, <&cru HCLK_VOP>;
+ clock-names = "aclk", "iface";
+ #iommu-cells = <0>;
++ power-domains = <&power RK3568_PD_VO>;
+ status = "disabled";
+ };
+
+diff --git a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
+index 448a59dc53a77..0f2722c4bcc32 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-am62-main.dtsi
+@@ -141,8 +141,8 @@ main_pktdma: dma-controller@485c0000 {
+ compatible = "ti,am64-dmss-pktdma";
+ reg = <0x00 0x485c0000 0x00 0x100>,
+ <0x00 0x4a800000 0x00 0x20000>,
+- <0x00 0x4aa00000 0x00 0x40000>,
+- <0x00 0x4b800000 0x00 0x400000>,
++ <0x00 0x4aa00000 0x00 0x20000>,
++ <0x00 0x4b800000 0x00 0x200000>,
+ <0x00 0x485e0000 0x00 0x10000>,
+ <0x00 0x484a0000 0x00 0x2000>,
+ <0x00 0x484c0000 0x00 0x2000>,
+diff --git a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
+index 2038c5e046390..359f53f3e019b 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-am62-verdin.dtsi
+@@ -1364,8 +1364,6 @@ &mcasp0 {
+ 0 0 0 0
+ >;
+ tdm-slots = <2>;
+- rx-num-evt = <32>;
+- tx-num-evt = <32>;
+ #sound-dai-cells = <0>;
+ status = "disabled";
+ };
+@@ -1382,8 +1380,6 @@ &mcasp1 {
+ 0 0 0 0
+ >;
+ tdm-slots = <2>;
+- rx-num-evt = <32>;
+- tx-num-evt = <32>;
+ #sound-dai-cells = <0>;
+ status = "disabled";
+ };
+diff --git a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
+index 18e3070a86839..70de288d728e4 100644
+--- a/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
++++ b/arch/arm64/boot/dts/ti/k3-am625-beagleplay.dts
+@@ -924,6 +924,4 @@ &mcasp1 {
+ 0 0 0 0
+ 0 0 0 0
+ >;
+- tx-num-evt = <32>;
+- rx-num-evt = <32>;
+ };
+diff --git a/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts b/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
+index 50d2573c840ee..6c24e4d39ee80 100644
+--- a/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
++++ b/arch/arm64/boot/dts/ti/k3-am625-phyboard-lyra-rdk.dts
+@@ -441,8 +441,6 @@ &mcasp2 {
+ 0 0 0 0
+ 0 0 0 0
+ >;
+- tx-num-evt = <32>;
+- rx-num-evt = <32>;
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
+index bf9c2d9c6439a..ce4a2f1056300 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-am62a-main.dtsi
+@@ -120,8 +120,8 @@ main_pktdma: dma-controller@485c0000 {
+ compatible = "ti,am64-dmss-pktdma";
+ reg = <0x00 0x485c0000 0x00 0x100>,
+ <0x00 0x4a800000 0x00 0x20000>,
+- <0x00 0x4aa00000 0x00 0x40000>,
+- <0x00 0x4b800000 0x00 0x400000>,
++ <0x00 0x4aa00000 0x00 0x20000>,
++ <0x00 0x4b800000 0x00 0x200000>,
+ <0x00 0x485e0000 0x00 0x10000>,
+ <0x00 0x484a0000 0x00 0x2000>,
+ <0x00 0x484c0000 0x00 0x2000>,
+diff --git a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
+index fa43cd0b631e6..e026f65738b39 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
++++ b/arch/arm64/boot/dts/ti/k3-am62a7-sk.dts
+@@ -701,8 +701,6 @@ &mcasp1 {
+ 0 0 0 0
+ 0 0 0 0
+ >;
+- tx-num-evt = <32>;
+- rx-num-evt = <32>;
+ };
+
+ &dss {
+diff --git a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
+index 900d1f9530a2a..2b9bc77a05404 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-am62p-main.dtsi
+@@ -123,8 +123,8 @@ main_pktdma: dma-controller@485c0000 {
+ compatible = "ti,am64-dmss-pktdma";
+ reg = <0x00 0x485c0000 0x00 0x100>,
+ <0x00 0x4a800000 0x00 0x20000>,
+- <0x00 0x4aa00000 0x00 0x40000>,
+- <0x00 0x4b800000 0x00 0x400000>,
++ <0x00 0x4aa00000 0x00 0x20000>,
++ <0x00 0x4b800000 0x00 0x200000>,
+ <0x00 0x485e0000 0x00 0x10000>,
+ <0x00 0x484a0000 0x00 0x2000>,
+ <0x00 0x484c0000 0x00 0x2000>,
+diff --git a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
+index 6e72346591113..fb980d46e3041 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
++++ b/arch/arm64/boot/dts/ti/k3-am62p5-sk.dts
+@@ -207,7 +207,7 @@ main_mcasp1_pins_default: main-mcasp1-default-pins {
+ pinctrl-single,pins = <
+ AM62PX_IOPAD(0x0090, PIN_INPUT, 2) /* (U24) GPMC0_BE0n_CLE.MCASP1_ACLKX */
+ AM62PX_IOPAD(0x0098, PIN_INPUT, 2) /* (AA24) GPMC0_WAIT0.MCASP1_AFSX */
+- AM62PX_IOPAD(0x008c, PIN_INPUT, 2) /* (T25) GPMC0_WEn.MCASP1_AXR0 */
++ AM62PX_IOPAD(0x008c, PIN_OUTPUT, 2) /* (T25) GPMC0_WEn.MCASP1_AXR0 */
+ AM62PX_IOPAD(0x0084, PIN_INPUT, 2) /* (R25) GPMC0_ADVn_ALE.MCASP1_AXR2 */
+ >;
+ };
+@@ -549,8 +549,6 @@ &mcasp1 {
+ 0 0 0 0
+ 0 0 0 0
+ >;
+- tx-num-evt = <32>;
+- rx-num-evt = <32>;
+ };
+
+ &fss {
+diff --git a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
+index 3c45782ab2b78..63b4e88e3a94a 100644
+--- a/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-am62x-sk-common.dtsi
+@@ -504,8 +504,6 @@ &mcasp1 {
+ 0 0 0 0
+ 0 0 0 0
+ >;
+- tx-num-evt = <32>;
+- rx-num-evt = <32>;
+ };
+
+ &dss {
+diff --git a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t.dts b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t.dts
+index 234d76e4e9445..5b5e9eeec5ac4 100644
+--- a/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t.dts
++++ b/arch/arm64/boot/dts/ti/k3-am642-hummingboard-t.dts
+@@ -282,7 +282,6 @@ &main_uart3 {
+ pinctrl-names = "default";
+ pinctrl-0 = <&main_uart3_default_pins>;
+ uart-has-rtscts;
+- rs485-rts-active-low;
+ linux,rs485-enabled-at-boot-time;
+ status = "okay";
+ };
+diff --git a/arch/arm64/boot/dts/ti/k3-j722s.dtsi b/arch/arm64/boot/dts/ti/k3-j722s.dtsi
+index c75744edb1433..9132b0232b0ba 100644
+--- a/arch/arm64/boot/dts/ti/k3-j722s.dtsi
++++ b/arch/arm64/boot/dts/ti/k3-j722s.dtsi
+@@ -83,6 +83,14 @@ &inta_main_dmss {
+ ti,interrupt-ranges = <7 71 21>;
+ };
+
++&main_gpio0 {
++ ti,ngpio = <87>;
++};
++
++&main_gpio1 {
++ ti,ngpio = <73>;
++};
++
+ &oc_sram {
+ reg = <0x00 0x70000000 0x00 0x40000>;
+ ranges = <0x00 0x00 0x70000000 0x40000>;
+diff --git a/arch/arm64/include/asm/pgtable.h b/arch/arm64/include/asm/pgtable.h
+index f8efbc128446d..7a4f5604be3f7 100644
+--- a/arch/arm64/include/asm/pgtable.h
++++ b/arch/arm64/include/asm/pgtable.h
+@@ -1065,6 +1065,28 @@ static inline bool pgtable_l5_enabled(void) { return false; }
+
+ #define p4d_offset_kimg(dir,addr) ((p4d_t *)dir)
+
++static inline
++p4d_t *p4d_offset_lockless_folded(pgd_t *pgdp, pgd_t pgd, unsigned long addr)
++{
++ /*
++ * With runtime folding of the pud, pud_offset_lockless() passes
++ * the 'pgd_t *' we return here to p4d_to_folded_pud(), which
++ * will offset the pointer assuming that it points into
++ * a page-table page. However, the fast GUP path passes us a
++ * pgd_t allocated on the stack and so we must use the original
++ * pointer in 'pgdp' to construct the p4d pointer instead of
++ * using the generic p4d_offset_lockless() implementation.
++ *
++ * Note: reusing the original pointer means that we may
++ * dereference the same (live) page-table entry multiple times.
++ * This is safe because it is still only loaded once in the
++ * context of each level and the CPU guarantees same-address
++ * read-after-read ordering.
++ */
++ return p4d_offset(pgdp, addr);
++}
++#define p4d_offset_lockless p4d_offset_lockless_folded
++
+ #endif /* CONFIG_PGTABLE_LEVELS > 4 */
+
+ #define pgd_ERROR(e) \
+diff --git a/arch/arm64/kernel/smp.c b/arch/arm64/kernel/smp.c
+index 31c8b3094dd7b..5de85dccc09cd 100644
+--- a/arch/arm64/kernel/smp.c
++++ b/arch/arm64/kernel/smp.c
+@@ -767,13 +767,15 @@ void __init smp_prepare_cpus(unsigned int max_cpus)
+ }
+ }
+
+-static const char *ipi_types[NR_IPI] __tracepoint_string = {
++static const char *ipi_types[MAX_IPI] __tracepoint_string = {
+ [IPI_RESCHEDULE] = "Rescheduling interrupts",
+ [IPI_CALL_FUNC] = "Function call interrupts",
+ [IPI_CPU_STOP] = "CPU stop interrupts",
+ [IPI_CPU_CRASH_STOP] = "CPU stop (for crash dump) interrupts",
+ [IPI_TIMER] = "Timer broadcast interrupts",
+ [IPI_IRQ_WORK] = "IRQ work interrupts",
++ [IPI_CPU_BACKTRACE] = "CPU backtrace interrupts",
++ [IPI_KGDB_ROUNDUP] = "KGDB roundup interrupts",
+ };
+
+ static void smp_cross_call(const struct cpumask *target, unsigned int ipinr);
+@@ -784,7 +786,7 @@ int arch_show_interrupts(struct seq_file *p, int prec)
+ {
+ unsigned int cpu, i;
+
+- for (i = 0; i < NR_IPI; i++) {
++ for (i = 0; i < MAX_IPI; i++) {
+ seq_printf(p, "%*s%u:%s", prec - 1, "IPI", i,
+ prec >= 4 ? " " : "");
+ for_each_online_cpu(cpu)
+diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c
+index 720336d288568..1bf483ec971d9 100644
+--- a/arch/arm64/net/bpf_jit_comp.c
++++ b/arch/arm64/net/bpf_jit_comp.c
+@@ -2141,7 +2141,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
+ emit(A64_STR64I(A64_R(20), A64_SP, regs_off + 8), ctx);
+
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+- emit_addr_mov_i64(A64_R(0), (const u64)im, ctx);
++ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+ emit_call((const u64)__bpf_tramp_enter, ctx);
+ }
+
+@@ -2185,7 +2185,7 @@ static int prepare_trampoline(struct jit_ctx *ctx, struct bpf_tramp_image *im,
+
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ im->ip_epilogue = ctx->ro_image + ctx->idx;
+- emit_addr_mov_i64(A64_R(0), (const u64)im, ctx);
++ emit_a64_mov_i64(A64_R(0), (const u64)im, ctx);
+ emit_call((const u64)__bpf_tramp_exit, ctx);
+ }
+
+diff --git a/arch/loongarch/kernel/hw_breakpoint.c b/arch/loongarch/kernel/hw_breakpoint.c
+index 621ad7634df71..a6e4b605bfa8d 100644
+--- a/arch/loongarch/kernel/hw_breakpoint.c
++++ b/arch/loongarch/kernel/hw_breakpoint.c
+@@ -221,7 +221,7 @@ static int hw_breakpoint_control(struct perf_event *bp,
+ }
+ enable = csr_read64(LOONGARCH_CSR_CRMD);
+ csr_write64(CSR_CRMD_WE | enable, LOONGARCH_CSR_CRMD);
+- if (bp->hw.target)
++ if (bp->hw.target && test_tsk_thread_flag(bp->hw.target, TIF_LOAD_WATCH))
+ regs->csr_prmd |= CSR_PRMD_PWE;
+ break;
+ case HW_BREAKPOINT_UNINSTALL:
+diff --git a/arch/loongarch/kernel/ptrace.c b/arch/loongarch/kernel/ptrace.c
+index 200109de1971a..19dc6eff45ccc 100644
+--- a/arch/loongarch/kernel/ptrace.c
++++ b/arch/loongarch/kernel/ptrace.c
+@@ -589,6 +589,7 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
+ struct perf_event *bp;
+ struct perf_event_attr attr;
+ struct arch_hw_breakpoint_ctrl ctrl;
++ struct thread_info *ti = task_thread_info(tsk);
+
+ bp = ptrace_hbp_get_initialised_bp(note_type, tsk, idx);
+ if (IS_ERR(bp))
+@@ -613,8 +614,10 @@ static int ptrace_hbp_set_ctrl(unsigned int note_type,
+ if (err)
+ return err;
+ attr.disabled = 0;
++ set_ti_thread_flag(ti, TIF_LOAD_WATCH);
+ } else {
+ attr.disabled = 1;
++ clear_ti_thread_flag(ti, TIF_LOAD_WATCH);
+ }
+
+ return modify_user_hw_breakpoint(bp, &attr);
+diff --git a/arch/m68k/amiga/config.c b/arch/m68k/amiga/config.c
+index d4b170c861bf0..0147130dc34e3 100644
+--- a/arch/m68k/amiga/config.c
++++ b/arch/m68k/amiga/config.c
+@@ -180,6 +180,15 @@ int __init amiga_parse_bootinfo(const struct bi_record *record)
+ dev->slotsize = be16_to_cpu(cd->cd_SlotSize);
+ dev->boardaddr = be32_to_cpu(cd->cd_BoardAddr);
+ dev->boardsize = be32_to_cpu(cd->cd_BoardSize);
++
++ /* CS-LAB Warp 1260 workaround */
++ if (be16_to_cpu(dev->rom.er_Manufacturer) == ZORRO_MANUF(ZORRO_PROD_CSLAB_WARP_1260) &&
++ dev->rom.er_Product == ZORRO_PROD(ZORRO_PROD_CSLAB_WARP_1260)) {
++
++ /* turn off all interrupts */
++ pr_info("Warp 1260 card detected: applying interrupt storm workaround\n");
++ *(uint32_t *)(dev->boardaddr + 0x1000) = 0xfff;
++ }
+ } else
+ pr_warn("amiga_parse_bootinfo: too many AutoConfig devices\n");
+ #endif /* CONFIG_ZORRO */
+diff --git a/arch/m68k/atari/ataints.c b/arch/m68k/atari/ataints.c
+index 23256434191c3..0465444ceb216 100644
+--- a/arch/m68k/atari/ataints.c
++++ b/arch/m68k/atari/ataints.c
+@@ -301,11 +301,7 @@ void __init atari_init_IRQ(void)
+
+ if (ATARIHW_PRESENT(SCU)) {
+ /* init the SCU if present */
+- tt_scu.sys_mask = 0x10; /* enable VBL (for the cursor) and
+- * disable HSYNC interrupts (who
+- * needs them?) MFP and SCC are
+- * enabled in VME mask
+- */
++ tt_scu.sys_mask = 0x0; /* disable all interrupts */
+ tt_scu.vme_mask = 0x60; /* enable MFP and SCC ints */
+ } else {
+ /* If no SCU and no Hades, the HSYNC interrupt needs to be
+diff --git a/arch/m68k/include/asm/cmpxchg.h b/arch/m68k/include/asm/cmpxchg.h
+index d7f3de9c5d6f7..4ba14f3535fcb 100644
+--- a/arch/m68k/include/asm/cmpxchg.h
++++ b/arch/m68k/include/asm/cmpxchg.h
+@@ -32,7 +32,7 @@ static inline unsigned long __arch_xchg(unsigned long x, volatile void * ptr, in
+ x = tmp;
+ break;
+ default:
+- tmp = __invalid_xchg_size(x, ptr, size);
++ x = __invalid_xchg_size(x, ptr, size);
+ break;
+ }
+
+diff --git a/arch/mips/Makefile b/arch/mips/Makefile
+index 80aecba248922..5785a3d5ccfbb 100644
+--- a/arch/mips/Makefile
++++ b/arch/mips/Makefile
+@@ -170,7 +170,7 @@ cflags-$(CONFIG_CPU_NEVADA) += $(call cc-option,-march=rm5200,-march=mips4) \
+ -Wa,--trap
+ cflags-$(CONFIG_CPU_RM7000) += $(call cc-option,-march=rm7000,-march=mips4) \
+ -Wa,--trap
+-cflags-$(CONFIG_CPU_SB1) += $(call cc-option,-march=sb1,-march=mips64r1) \
++cflags-$(CONFIG_CPU_SB1) += $(call cc-option,-march=sb1,-march=mips64) \
+ -Wa,--trap
+ cflags-$(CONFIG_CPU_SB1) += $(call cc-option,-mno-mdmx)
+ cflags-$(CONFIG_CPU_SB1) += $(call cc-option,-mno-mips3d)
+diff --git a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+index ee3e2153dd13f..c0be84a6e81fd 100644
+--- a/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
++++ b/arch/mips/boot/dts/loongson/loongson64-2k1000.dtsi
+@@ -23,14 +23,6 @@ cpu0: cpu@0 {
+ };
+ };
+
+- memory@200000 {
+- compatible = "memory";
+- device_type = "memory";
+- reg = <0x00000000 0x00200000 0x00000000 0x0ee00000>, /* 238 MB at 2 MB */
+- <0x00000000 0x20000000 0x00000000 0x1f000000>, /* 496 MB at 512 MB */
+- <0x00000001 0x10000000 0x00000001 0xb0000000>; /* 6912 MB at 4352MB */
+- };
+-
+ cpu_clk: cpu_clk {
+ #clock-cells = <0>;
+ compatible = "fixed-clock";
+@@ -52,6 +44,13 @@ package0: bus@10000000 {
+ 0 0x40000000 0 0x40000000 0 0x40000000
+ 0xfe 0x00000000 0xfe 0x00000000 0 0x40000000>;
+
++ isa@18000000 {
++ compatible = "isa";
++ #size-cells = <1>;
++ #address-cells = <2>;
++ ranges = <1 0x0 0x0 0x18000000 0x4000>;
++ };
++
+ pm: reset-controller@1fe07000 {
+ compatible = "loongson,ls2k-pm";
+ reg = <0 0x1fe07000 0 0x422>;
+@@ -137,7 +136,8 @@ gmac@3,0 {
+ <13 IRQ_TYPE_LEVEL_LOW>;
+ interrupt-names = "macirq", "eth_lpi";
+ interrupt-parent = <&liointc0>;
+- phy-mode = "rgmii";
++ phy-mode = "rgmii-id";
++ phy-handle = <&phy1>;
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+@@ -160,7 +160,8 @@ gmac@3,1 {
+ <15 IRQ_TYPE_LEVEL_LOW>;
+ interrupt-names = "macirq", "eth_lpi";
+ interrupt-parent = <&liointc0>;
+- phy-mode = "rgmii";
++ phy-mode = "rgmii-id";
++ phy-handle = <&phy1>;
+ mdio {
+ #address-cells = <1>;
+ #size-cells = <0>;
+diff --git a/arch/mips/include/asm/mach-loongson64/boot_param.h b/arch/mips/include/asm/mach-loongson64/boot_param.h
+index e007edd6b60a7..9218b3ae33832 100644
+--- a/arch/mips/include/asm/mach-loongson64/boot_param.h
++++ b/arch/mips/include/asm/mach-loongson64/boot_param.h
+@@ -42,12 +42,14 @@ enum loongson_cpu_type {
+ Legacy_1B = 0x5,
+ Legacy_2G = 0x6,
+ Legacy_2H = 0x7,
++ Legacy_2K = 0x8,
+ Loongson_1A = 0x100,
+ Loongson_1B = 0x101,
+ Loongson_2E = 0x200,
+ Loongson_2F = 0x201,
+ Loongson_2G = 0x202,
+ Loongson_2H = 0x203,
++ Loongson_2K = 0x204,
+ Loongson_3A = 0x300,
+ Loongson_3B = 0x301
+ };
+diff --git a/arch/mips/include/asm/mips-cm.h b/arch/mips/include/asm/mips-cm.h
+index c2930a75b7e44..1e782275850a3 100644
+--- a/arch/mips/include/asm/mips-cm.h
++++ b/arch/mips/include/asm/mips-cm.h
+@@ -240,6 +240,10 @@ GCR_ACCESSOR_RO(32, 0x0d0, gic_status)
+ GCR_ACCESSOR_RO(32, 0x0f0, cpc_status)
+ #define CM_GCR_CPC_STATUS_EX BIT(0)
+
++/* GCR_ACCESS - Controls core/IOCU access to GCRs */
++GCR_ACCESSOR_RW(32, 0x120, access_cm3)
++#define CM_GCR_ACCESS_ACCESSEN GENMASK(7, 0)
++
+ /* GCR_L2_CONFIG - Indicates L2 cache configuration when Config5.L2C=1 */
+ GCR_ACCESSOR_RW(32, 0x130, l2_config)
+ #define CM_GCR_L2_CONFIG_BYPASS BIT(20)
+diff --git a/arch/mips/kernel/smp-cps.c b/arch/mips/kernel/smp-cps.c
+index 9cc087dd1c194..395622c373258 100644
+--- a/arch/mips/kernel/smp-cps.c
++++ b/arch/mips/kernel/smp-cps.c
+@@ -317,7 +317,10 @@ static void boot_core(unsigned int core, unsigned int vpe_id)
+ write_gcr_co_reset_ext_base(CM_GCR_Cx_RESET_EXT_BASE_UEB);
+
+ /* Ensure the core can access the GCRs */
+- set_gcr_access(1 << core);
++ if (mips_cm_revision() < CM_REV_CM3)
++ set_gcr_access(1 << core);
++ else
++ set_gcr_access_cm3(1 << core);
+
+ if (mips_cpc_present()) {
+ /* Reset the core */
+diff --git a/arch/mips/loongson64/env.c b/arch/mips/loongson64/env.c
+index ef3750a6ffacf..09ff052698614 100644
+--- a/arch/mips/loongson64/env.c
++++ b/arch/mips/loongson64/env.c
+@@ -88,6 +88,12 @@ void __init prom_lefi_init_env(void)
+ cpu_clock_freq = ecpu->cpu_clock_freq;
+ loongson_sysconf.cputype = ecpu->cputype;
+ switch (ecpu->cputype) {
++ case Legacy_2K:
++ case Loongson_2K:
++ smp_group[0] = 0x900000001fe11000;
++ loongson_sysconf.cores_per_node = 2;
++ loongson_sysconf.cores_per_package = 2;
++ break;
+ case Legacy_3A:
+ case Loongson_3A:
+ loongson_sysconf.cores_per_node = 4;
+@@ -221,6 +227,8 @@ void __init prom_lefi_init_env(void)
+ default:
+ break;
+ }
++ } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64R) {
++ loongson_fdt_blob = __dtb_loongson64_2core_2k1000_begin;
+ } else if ((read_c0_prid() & PRID_IMP_MASK) == PRID_IMP_LOONGSON_64G) {
+ if (loongson_sysconf.bridgetype == LS7A)
+ loongson_fdt_blob = __dtb_loongson64g_4core_ls7a_begin;
+diff --git a/arch/mips/loongson64/reset.c b/arch/mips/loongson64/reset.c
+index e01c8d4a805a9..3e20ade0503ad 100644
+--- a/arch/mips/loongson64/reset.c
++++ b/arch/mips/loongson64/reset.c
+@@ -11,6 +11,7 @@
+ #include <linux/init.h>
+ #include <linux/kexec.h>
+ #include <linux/pm.h>
++#include <linux/reboot.h>
+ #include <linux/slab.h>
+
+ #include <asm/bootinfo.h>
+@@ -21,36 +22,21 @@
+ #include <loongson.h>
+ #include <boot_param.h>
+
+-static void loongson_restart(char *command)
++static int firmware_restart(struct sys_off_data *unusedd)
+ {
+
+ void (*fw_restart)(void) = (void *)loongson_sysconf.restart_addr;
+
+ fw_restart();
+- while (1) {
+- if (cpu_wait)
+- cpu_wait();
+- }
++ return NOTIFY_DONE;
+ }
+
+-static void loongson_poweroff(void)
++static int firmware_poweroff(struct sys_off_data *unused)
+ {
+ void (*fw_poweroff)(void) = (void *)loongson_sysconf.poweroff_addr;
+
+ fw_poweroff();
+- while (1) {
+- if (cpu_wait)
+- cpu_wait();
+- }
+-}
+-
+-static void loongson_halt(void)
+-{
+- pr_notice("\n\n** You can safely turn off the power now **\n\n");
+- while (1) {
+- if (cpu_wait)
+- cpu_wait();
+- }
++ return NOTIFY_DONE;
+ }
+
+ #ifdef CONFIG_KEXEC_CORE
+@@ -154,9 +140,17 @@ static void loongson_crash_shutdown(struct pt_regs *regs)
+
+ static int __init mips_reboot_setup(void)
+ {
+- _machine_restart = loongson_restart;
+- _machine_halt = loongson_halt;
+- pm_power_off = loongson_poweroff;
++ if (loongson_sysconf.restart_addr) {
++ register_sys_off_handler(SYS_OFF_MODE_RESTART,
++ SYS_OFF_PRIO_FIRMWARE,
++ firmware_restart, NULL);
++ }
++
++ if (loongson_sysconf.poweroff_addr) {
++ register_sys_off_handler(SYS_OFF_MODE_POWER_OFF,
++ SYS_OFF_PRIO_FIRMWARE,
++ firmware_poweroff, NULL);
++ }
+
+ #ifdef CONFIG_KEXEC_CORE
+ kexec_argv = kmalloc(KEXEC_ARGV_SIZE, GFP_KERNEL);
+diff --git a/arch/mips/loongson64/smp.c b/arch/mips/loongson64/smp.c
+index 5a990cdef91a6..66d049cdcf145 100644
+--- a/arch/mips/loongson64/smp.c
++++ b/arch/mips/loongson64/smp.c
+@@ -466,12 +466,25 @@ static void loongson3_smp_finish(void)
+ static void __init loongson3_smp_setup(void)
+ {
+ int i = 0, num = 0; /* i: physical id, num: logical id */
++ int max_cpus = 0;
+
+ init_cpu_possible(cpu_none_mask);
+
++ for (i = 0; i < ARRAY_SIZE(smp_group); i++) {
++ if (!smp_group[i])
++ break;
++ max_cpus += loongson_sysconf.cores_per_node;
++ }
++
++ if (max_cpus < loongson_sysconf.nr_cpus) {
++ pr_err("SMP Groups are less than the number of CPUs\n");
++ loongson_sysconf.nr_cpus = max_cpus ? max_cpus : 1;
++ }
++
+ /* For unified kernel, NR_CPUS is the maximum possible value,
+ * loongson_sysconf.nr_cpus is the really present value
+ */
++ i = 0;
+ while (i < loongson_sysconf.nr_cpus) {
+ if (loongson_sysconf.reserved_cpus_mask & (1<<i)) {
+ /* Reserved physical CPU cores */
+@@ -492,14 +505,14 @@ static void __init loongson3_smp_setup(void)
+ __cpu_logical_map[num] = -1;
+ num++;
+ }
+-
+ csr_ipi_probe();
+ ipi_set0_regs_init();
+ ipi_clear0_regs_init();
+ ipi_status0_regs_init();
+ ipi_en0_regs_init();
+ ipi_mailbox_buf_init();
+- ipi_write_enable(0);
++ if (smp_group[0])
++ ipi_write_enable(0);
+
+ cpu_set_core(&cpu_data[0],
+ cpu_logical_map(0) % loongson_sysconf.cores_per_package);
+@@ -818,6 +831,9 @@ static int loongson3_disable_clock(unsigned int cpu)
+ uint64_t core_id = cpu_core(&cpu_data[cpu]);
+ uint64_t package_id = cpu_data[cpu].package;
+
++ if (!loongson_chipcfg[package_id] || !loongson_freqctrl[package_id])
++ return 0;
++
+ if ((read_c0_prid() & PRID_REV_MASK) == PRID_REV_LOONGSON3A_R1) {
+ LOONGSON_CHIPCFG(package_id) &= ~(1 << (12 + core_id));
+ } else {
+@@ -832,6 +848,9 @@ static int loongson3_enable_clock(unsigned int cpu)
+ uint64_t core_id = cpu_core(&cpu_data[cpu]);
+ uint64_t package_id = cpu_data[cpu].package;
+
++ if (!loongson_chipcfg[package_id] || !loongson_freqctrl[package_id])
++ return 0;
++
+ if ((read_c0_prid() & PRID_REV_MASK) == PRID_REV_LOONGSON3A_R1) {
+ LOONGSON_CHIPCFG(package_id) |= 1 << (12 + core_id);
+ } else {
+diff --git a/arch/mips/pci/pcie-octeon.c b/arch/mips/pci/pcie-octeon.c
+old mode 100755
+new mode 100644
+diff --git a/arch/mips/sgi-ip30/ip30-console.c b/arch/mips/sgi-ip30/ip30-console.c
+index 7c6dcf6e73f70..a5f10097b9859 100644
+--- a/arch/mips/sgi-ip30/ip30-console.c
++++ b/arch/mips/sgi-ip30/ip30-console.c
+@@ -1,6 +1,7 @@
+ // SPDX-License-Identifier: GPL-2.0
+
+ #include <linux/io.h>
++#include <linux/processor.h>
+
+ #include <asm/sn/ioc3.h>
+ #include <asm/setup.h>
+diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
+index dc9b902de8ea9..9656e956ed135 100644
+--- a/arch/parisc/Kconfig
++++ b/arch/parisc/Kconfig
+@@ -86,6 +86,7 @@ config PARISC
+ select HAVE_SOFTIRQ_ON_OWN_STACK if IRQSTACKS
+ select TRACE_IRQFLAGS_SUPPORT
+ select HAVE_FUNCTION_DESCRIPTORS if 64BIT
++ select PCI_MSI_ARCH_FALLBACKS if PCI_MSI
+
+ help
+ The PA-RISC microprocessor is designed by Hewlett-Packard and used
+diff --git a/arch/powerpc/configs/85xx-hw.config b/arch/powerpc/configs/85xx-hw.config
+index 524db76f47b73..8aff832173977 100644
+--- a/arch/powerpc/configs/85xx-hw.config
++++ b/arch/powerpc/configs/85xx-hw.config
+@@ -24,6 +24,7 @@ CONFIG_FS_ENET=y
+ CONFIG_FSL_CORENET_CF=y
+ CONFIG_FSL_DMA=y
+ CONFIG_FSL_HV_MANAGER=y
++CONFIG_FSL_IFC=y
+ CONFIG_FSL_PQ_MDIO=y
+ CONFIG_FSL_RIO=y
+ CONFIG_FSL_XGMAC_MDIO=y
+@@ -58,6 +59,7 @@ CONFIG_INPUT_FF_MEMLESS=m
+ CONFIG_MARVELL_PHY=y
+ CONFIG_MDIO_BUS_MUX_GPIO=y
+ CONFIG_MDIO_BUS_MUX_MMIOREG=y
++CONFIG_MEMORY=y
+ CONFIG_MMC_SDHCI_OF_ESDHC=y
+ CONFIG_MMC_SDHCI_PLTFM=y
+ CONFIG_MMC_SDHCI=y
+diff --git a/arch/powerpc/include/asm/guest-state-buffer.h b/arch/powerpc/include/asm/guest-state-buffer.h
+index 808149f315763..d107abe1468fe 100644
+--- a/arch/powerpc/include/asm/guest-state-buffer.h
++++ b/arch/powerpc/include/asm/guest-state-buffer.h
+@@ -81,6 +81,7 @@
+ #define KVMPPC_GSID_HASHKEYR 0x1050
+ #define KVMPPC_GSID_HASHPKEYR 0x1051
+ #define KVMPPC_GSID_CTRL 0x1052
++#define KVMPPC_GSID_DPDES 0x1053
+
+ #define KVMPPC_GSID_CR 0x2000
+ #define KVMPPC_GSID_PIDR 0x2001
+@@ -110,7 +111,7 @@
+ #define KVMPPC_GSE_META_COUNT (KVMPPC_GSE_META_END - KVMPPC_GSE_META_START + 1)
+
+ #define KVMPPC_GSE_DW_REGS_START KVMPPC_GSID_GPR(0)
+-#define KVMPPC_GSE_DW_REGS_END KVMPPC_GSID_CTRL
++#define KVMPPC_GSE_DW_REGS_END KVMPPC_GSID_DPDES
+ #define KVMPPC_GSE_DW_REGS_COUNT \
+ (KVMPPC_GSE_DW_REGS_END - KVMPPC_GSE_DW_REGS_START + 1)
+
+diff --git a/arch/powerpc/include/asm/kvm_book3s.h b/arch/powerpc/include/asm/kvm_book3s.h
+index 3e1e2a698c9e7..10618622d7efc 100644
+--- a/arch/powerpc/include/asm/kvm_book3s.h
++++ b/arch/powerpc/include/asm/kvm_book3s.h
+@@ -594,6 +594,7 @@ static inline u##size kvmppc_get_##reg(struct kvm_vcpu *vcpu) \
+
+
+ KVMPPC_BOOK3S_VCORE_ACCESSOR(vtb, 64, KVMPPC_GSID_VTB)
++KVMPPC_BOOK3S_VCORE_ACCESSOR(dpdes, 64, KVMPPC_GSID_DPDES)
+ KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(arch_compat, 32, KVMPPC_GSID_LOGICAL_PVR)
+ KVMPPC_BOOK3S_VCORE_ACCESSOR_GET(lpcr, 64, KVMPPC_GSID_LPCR)
+ KVMPPC_BOOK3S_VCORE_ACCESSOR_SET(tb_offset, 64, KVMPPC_GSID_TB_OFFSET)
+diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
+index 60819751e55e6..0be07ed407c70 100644
+--- a/arch/powerpc/kernel/prom.c
++++ b/arch/powerpc/kernel/prom.c
+@@ -331,6 +331,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
+ void *data)
+ {
+ const char *type = of_get_flat_dt_prop(node, "device_type", NULL);
++ const __be32 *cpu_version = NULL;
+ const __be32 *prop;
+ const __be32 *intserv;
+ int i, nthreads;
+@@ -420,7 +421,7 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
+ prop = of_get_flat_dt_prop(node, "cpu-version", NULL);
+ if (prop && (be32_to_cpup(prop) & 0xff000000) == 0x0f000000) {
+ identify_cpu(0, be32_to_cpup(prop));
+- seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(prop));
++ cpu_version = prop;
+ }
+
+ check_cpu_feature_properties(node);
+@@ -431,6 +432,12 @@ static int __init early_init_dt_scan_cpus(unsigned long node,
+ }
+
+ identical_pvr_fixup(node);
++
++ // We can now add the CPU name & PVR to the hardware description
++ seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR));
++ if (cpu_version)
++ seq_buf_printf(&ppc_hw_desc, "0x%04x ", be32_to_cpup(cpu_version));
++
+ init_mmu_slb_size(node);
+
+ #ifdef CONFIG_PPC64
+@@ -881,9 +888,6 @@ void __init early_init_devtree(void *params)
+
+ dt_cpu_ftrs_scan();
+
+- // We can now add the CPU name & PVR to the hardware description
+- seq_buf_printf(&ppc_hw_desc, "%s 0x%04lx ", cur_cpu_spec->cpu_name, mfspr(SPRN_PVR));
+-
+ /* Retrieve CPU related informations from the flat tree
+ * (altivec support, boot CPU ID, ...)
+ */
+diff --git a/arch/powerpc/kexec/core_64.c b/arch/powerpc/kexec/core_64.c
+index 72b12bc10f90b..222aa326dacee 100644
+--- a/arch/powerpc/kexec/core_64.c
++++ b/arch/powerpc/kexec/core_64.c
+@@ -467,9 +467,15 @@ static int add_node_props(void *fdt, int node_offset, const struct device_node *
+ * @fdt: Flattened device tree of the kernel.
+ *
+ * Returns 0 on success, negative errno on error.
++ *
++ * Note: expecting no subnodes under /cpus/<node> with device_type == "cpu".
++ * If this changes, update this function to include them.
+ */
+ int update_cpus_node(void *fdt)
+ {
++ int prev_node_offset;
++ const char *device_type;
++ const struct fdt_property *prop;
+ struct device_node *cpus_node, *dn;
+ int cpus_offset, cpus_subnode_offset, ret = 0;
+
+@@ -480,30 +486,44 @@ int update_cpus_node(void *fdt)
+ return cpus_offset;
+ }
+
+- if (cpus_offset > 0) {
+- ret = fdt_del_node(fdt, cpus_offset);
++ prev_node_offset = cpus_offset;
++ /* Delete sub-nodes of /cpus node with device_type == "cpu" */
++ for (cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset); cpus_subnode_offset >= 0;) {
++ /* Ignore nodes that do not have a device_type property or device_type != "cpu" */
++ prop = fdt_get_property(fdt, cpus_subnode_offset, "device_type", NULL);
++ if (!prop || strcmp(prop->data, "cpu")) {
++ prev_node_offset = cpus_subnode_offset;
++ goto next_node;
++ }
++
++ ret = fdt_del_node(fdt, cpus_subnode_offset);
+ if (ret < 0) {
+- pr_err("Error deleting /cpus node: %s\n", fdt_strerror(ret));
+- return -EINVAL;
++ pr_err("Failed to delete a cpus sub-node: %s\n", fdt_strerror(ret));
++ return ret;
+ }
++next_node:
++ if (prev_node_offset == cpus_offset)
++ cpus_subnode_offset = fdt_first_subnode(fdt, cpus_offset);
++ else
++ cpus_subnode_offset = fdt_next_subnode(fdt, prev_node_offset);
+ }
+
+- /* Add cpus node to fdt */
+- cpus_offset = fdt_add_subnode(fdt, fdt_path_offset(fdt, "/"), "cpus");
+- if (cpus_offset < 0) {
+- pr_err("Error creating /cpus node: %s\n", fdt_strerror(cpus_offset));
++ cpus_node = of_find_node_by_path("/cpus");
++ /* Fail here to avoid kexec/kdump kernel boot hung */
++ if (!cpus_node) {
++ pr_err("No /cpus node found\n");
+ return -EINVAL;
+ }
+
+- /* Add cpus node properties */
+- cpus_node = of_find_node_by_path("/cpus");
+- ret = add_node_props(fdt, cpus_offset, cpus_node);
+- of_node_put(cpus_node);
+- if (ret < 0)
+- return ret;
++ /* Add all /cpus sub-nodes of device_type == "cpu" to FDT */
++ for_each_child_of_node(cpus_node, dn) {
++ /* Ignore device nodes that do not have a device_type property
++ * or device_type != "cpu".
++ */
++ device_type = of_get_property(dn, "device_type", NULL);
++ if (!device_type || strcmp(device_type, "cpu"))
++ continue;
+
+- /* Loop through all subnodes of cpus and add them to fdt */
+- for_each_node_by_type(dn, "cpu") {
+ cpus_subnode_offset = fdt_add_subnode(fdt, cpus_offset, dn->full_name);
+ if (cpus_subnode_offset < 0) {
+ pr_err("Unable to add %s subnode: %s\n", dn->full_name,
+@@ -517,6 +537,7 @@ int update_cpus_node(void *fdt)
+ goto out;
+ }
+ out:
++ of_node_put(cpus_node);
+ of_node_put(dn);
+ return ret;
+ }
+diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
+index daaf7faf21a5e..d8352e4d9cdc7 100644
+--- a/arch/powerpc/kvm/book3s_hv.c
++++ b/arch/powerpc/kvm/book3s_hv.c
+@@ -2305,7 +2305,7 @@ static int kvmppc_get_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+ *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu));
+ break;
+ case KVM_REG_PPC_SDAR:
+- *val = get_reg_val(id, kvmppc_get_siar_hv(vcpu));
++ *val = get_reg_val(id, kvmppc_get_sdar_hv(vcpu));
+ break;
+ case KVM_REG_PPC_SIER:
+ *val = get_reg_val(id, kvmppc_get_sier_hv(vcpu, 0));
+@@ -2540,7 +2540,7 @@ static int kvmppc_set_one_reg_hv(struct kvm_vcpu *vcpu, u64 id,
+ vcpu->arch.mmcrs = set_reg_val(id, *val);
+ break;
+ case KVM_REG_PPC_MMCR3:
+- *val = get_reg_val(id, vcpu->arch.mmcr[3]);
++ kvmppc_set_mmcr_hv(vcpu, 3, set_reg_val(id, *val));
+ break;
+ case KVM_REG_PPC_PMC1 ... KVM_REG_PPC_PMC8:
+ i = id - KVM_REG_PPC_PMC1;
+@@ -4116,6 +4116,11 @@ static int kvmhv_vcpu_entry_nestedv2(struct kvm_vcpu *vcpu, u64 time_limit,
+ int trap;
+ long rc;
+
++ if (vcpu->arch.doorbell_request) {
++ vcpu->arch.doorbell_request = 0;
++ kvmppc_set_dpdes(vcpu, 1);
++ }
++
+ io = &vcpu->arch.nestedv2_io;
+
+ msr = mfmsr();
+diff --git a/arch/powerpc/kvm/book3s_hv_nestedv2.c b/arch/powerpc/kvm/book3s_hv_nestedv2.c
+index 1091f7a83b255..342f583147709 100644
+--- a/arch/powerpc/kvm/book3s_hv_nestedv2.c
++++ b/arch/powerpc/kvm/book3s_hv_nestedv2.c
+@@ -311,6 +311,10 @@ static int gs_msg_ops_vcpu_fill_info(struct kvmppc_gs_buff *gsb,
+ rc = kvmppc_gse_put_u64(gsb, iden,
+ vcpu->arch.vcore->vtb);
+ break;
++ case KVMPPC_GSID_DPDES:
++ rc = kvmppc_gse_put_u64(gsb, iden,
++ vcpu->arch.vcore->dpdes);
++ break;
+ case KVMPPC_GSID_LPCR:
+ rc = kvmppc_gse_put_u64(gsb, iden,
+ vcpu->arch.vcore->lpcr);
+@@ -543,6 +547,9 @@ static int gs_msg_ops_vcpu_refresh_info(struct kvmppc_gs_msg *gsm,
+ case KVMPPC_GSID_VTB:
+ vcpu->arch.vcore->vtb = kvmppc_gse_get_u64(gse);
+ break;
++ case KVMPPC_GSID_DPDES:
++ vcpu->arch.vcore->dpdes = kvmppc_gse_get_u64(gse);
++ break;
+ case KVMPPC_GSID_LPCR:
+ vcpu->arch.vcore->lpcr = kvmppc_gse_get_u64(gse);
+ break;
+diff --git a/arch/powerpc/kvm/powerpc.c b/arch/powerpc/kvm/powerpc.c
+index d32abe7fe6ab7..d11767208bfc1 100644
+--- a/arch/powerpc/kvm/powerpc.c
++++ b/arch/powerpc/kvm/powerpc.c
+@@ -1984,8 +1984,10 @@ static int kvm_vcpu_ioctl_enable_cap(struct kvm_vcpu *vcpu,
+ break;
+
+ r = -ENXIO;
+- if (!xive_enabled())
++ if (!xive_enabled()) {
++ fdput(f);
+ break;
++ }
+
+ r = -EPERM;
+ dev = kvm_device_from_filp(f.file);
+diff --git a/arch/powerpc/kvm/test-guest-state-buffer.c b/arch/powerpc/kvm/test-guest-state-buffer.c
+index 4720b8dc88379..2571ccc618c96 100644
+--- a/arch/powerpc/kvm/test-guest-state-buffer.c
++++ b/arch/powerpc/kvm/test-guest-state-buffer.c
+@@ -151,7 +151,7 @@ static void test_gs_bitmap(struct kunit *test)
+ i++;
+ }
+
+- for (u16 iden = KVMPPC_GSID_GPR(0); iden <= KVMPPC_GSID_CTRL; iden++) {
++ for (u16 iden = KVMPPC_GSID_GPR(0); iden <= KVMPPC_GSE_DW_REGS_END; iden++) {
+ kvmppc_gsbm_set(&gsbm, iden);
+ kvmppc_gsbm_set(&gsbm1, iden);
+ KUNIT_EXPECT_TRUE(test, kvmppc_gsbm_test(&gsbm, iden));
+diff --git a/arch/powerpc/mm/nohash/8xx.c b/arch/powerpc/mm/nohash/8xx.c
+index 43d4842bb1c7a..d93433e26dedb 100644
+--- a/arch/powerpc/mm/nohash/8xx.c
++++ b/arch/powerpc/mm/nohash/8xx.c
+@@ -94,7 +94,8 @@ static int __ref __early_map_kernel_hugepage(unsigned long va, phys_addr_t pa,
+ return -EINVAL;
+
+ set_huge_pte_at(&init_mm, va, ptep,
+- pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)), psize);
++ pte_mkhuge(pfn_pte(pa >> PAGE_SHIFT, prot)),
++ 1UL << mmu_psize_to_shift(psize));
+
+ return 0;
+ }
+diff --git a/arch/powerpc/xmon/ppc-dis.c b/arch/powerpc/xmon/ppc-dis.c
+index 75fa98221d485..af105e1bc3fca 100644
+--- a/arch/powerpc/xmon/ppc-dis.c
++++ b/arch/powerpc/xmon/ppc-dis.c
+@@ -122,32 +122,21 @@ int print_insn_powerpc (unsigned long insn, unsigned long memaddr)
+ bool insn_is_short;
+ ppc_cpu_t dialect;
+
+- dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON
+- | PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_ALTIVEC;
++ dialect = PPC_OPCODE_PPC | PPC_OPCODE_COMMON;
+
+- if (cpu_has_feature(CPU_FTRS_POWER5))
+- dialect |= PPC_OPCODE_POWER5;
++ if (IS_ENABLED(CONFIG_PPC64))
++ dialect |= PPC_OPCODE_64 | PPC_OPCODE_POWER4 | PPC_OPCODE_CELL |
++ PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7 | PPC_OPCODE_POWER8 |
++ PPC_OPCODE_POWER9;
+
+- if (cpu_has_feature(CPU_FTRS_CELL))
+- dialect |= (PPC_OPCODE_CELL | PPC_OPCODE_ALTIVEC);
++ if (cpu_has_feature(CPU_FTR_TM))
++ dialect |= PPC_OPCODE_HTM;
+
+- if (cpu_has_feature(CPU_FTRS_POWER6))
+- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_ALTIVEC);
++ if (cpu_has_feature(CPU_FTR_ALTIVEC))
++ dialect |= PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2;
+
+- if (cpu_has_feature(CPU_FTRS_POWER7))
+- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
+- | PPC_OPCODE_ALTIVEC | PPC_OPCODE_VSX);
+-
+- if (cpu_has_feature(CPU_FTRS_POWER8))
+- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
+- | PPC_OPCODE_POWER8 | PPC_OPCODE_HTM
+- | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2 | PPC_OPCODE_VSX);
+-
+- if (cpu_has_feature(CPU_FTRS_POWER9))
+- dialect |= (PPC_OPCODE_POWER5 | PPC_OPCODE_POWER6 | PPC_OPCODE_POWER7
+- | PPC_OPCODE_POWER8 | PPC_OPCODE_POWER9 | PPC_OPCODE_HTM
+- | PPC_OPCODE_ALTIVEC | PPC_OPCODE_ALTIVEC2
+- | PPC_OPCODE_VSX | PPC_OPCODE_VSX3);
++ if (cpu_has_feature(CPU_FTR_VSX))
++ dialect |= PPC_OPCODE_VSX | PPC_OPCODE_VSX3;
+
+ /* Get the major opcode of the insn. */
+ opcode = NULL;
+diff --git a/arch/riscv/kernel/head.S b/arch/riscv/kernel/head.S
+index 4236a69c35cb3..a00f7523cb91f 100644
+--- a/arch/riscv/kernel/head.S
++++ b/arch/riscv/kernel/head.S
+@@ -165,9 +165,20 @@ secondary_start_sbi:
+ #endif
+ call .Lsetup_trap_vector
+ scs_load_current
+- tail smp_callin
++ call smp_callin
+ #endif /* CONFIG_SMP */
+
++.align 2
++.Lsecondary_park:
++ /*
++ * Park this hart if we:
++ * - have too many harts on CONFIG_RISCV_BOOT_SPINWAIT
++ * - receive an early trap, before setup_trap_vector finished
++ * - fail in smp_callin(), as a successful one wouldn't return
++ */
++ wfi
++ j .Lsecondary_park
++
+ .align 2
+ .Lsetup_trap_vector:
+ /* Set trap vector to exception handler */
+@@ -181,12 +192,6 @@ secondary_start_sbi:
+ csrw CSR_SCRATCH, zero
+ ret
+
+-.align 2
+-.Lsecondary_park:
+- /* We lack SMP support or have too many harts, so park this hart */
+- wfi
+- j .Lsecondary_park
+-
+ SYM_CODE_END(_start)
+
+ SYM_CODE_START(_start_kernel)
+diff --git a/arch/riscv/kernel/smpboot.c b/arch/riscv/kernel/smpboot.c
+index 1319b29ce3b59..19baf0d574d35 100644
+--- a/arch/riscv/kernel/smpboot.c
++++ b/arch/riscv/kernel/smpboot.c
+@@ -214,6 +214,15 @@ asmlinkage __visible void smp_callin(void)
+ struct mm_struct *mm = &init_mm;
+ unsigned int curr_cpuid = smp_processor_id();
+
++ if (has_vector()) {
++ /*
++ * Return as early as possible so the hart with a mismatching
++ * vlen won't boot.
++ */
++ if (riscv_v_setup_vsize())
++ return;
++ }
++
+ /* All kernel threads share the same mm context. */
+ mmgrab(mm);
+ current->active_mm = mm;
+@@ -226,11 +235,6 @@ asmlinkage __visible void smp_callin(void)
+ numa_add_cpu(curr_cpuid);
+ set_cpu_online(curr_cpuid, true);
+
+- if (has_vector()) {
+- if (riscv_v_setup_vsize())
+- elf_hwcap &= ~COMPAT_HWCAP_ISA_V;
+- }
+-
+ riscv_user_isa_enable();
+
+ /*
+diff --git a/arch/riscv/net/bpf_jit_comp64.c b/arch/riscv/net/bpf_jit_comp64.c
+index 79a001d5533ea..212b015e09b75 100644
+--- a/arch/riscv/net/bpf_jit_comp64.c
++++ b/arch/riscv/net/bpf_jit_comp64.c
+@@ -16,6 +16,8 @@
+ #include "bpf_jit.h"
+
+ #define RV_FENTRY_NINSNS 2
++/* imm that allows emit_imm to emit max count insns */
++#define RV_MAX_COUNT_IMM 0x7FFF7FF7FF7FF7FF
+
+ #define RV_REG_TCC RV_REG_A6
+ #define RV_REG_TCC_SAVED RV_REG_S6 /* Store A6 in S6 if program do calls */
+@@ -915,7 +917,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
+ orig_call += RV_FENTRY_NINSNS * 4;
+
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+- emit_imm(RV_REG_A0, (const s64)im, ctx);
++ emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx);
+ ret = emit_call((const u64)__bpf_tramp_enter, true, ctx);
+ if (ret)
+ return ret;
+@@ -976,7 +978,7 @@ static int __arch_prepare_bpf_trampoline(struct bpf_tramp_image *im,
+
+ if (flags & BPF_TRAMP_F_CALL_ORIG) {
+ im->ip_epilogue = ctx->insns + ctx->ninsns;
+- emit_imm(RV_REG_A0, (const s64)im, ctx);
++ emit_imm(RV_REG_A0, ctx->insns ? (const s64)im : RV_MAX_COUNT_IMM, ctx);
+ ret = emit_call((const u64)__bpf_tramp_exit, true, ctx);
+ if (ret)
+ goto out;
+@@ -1045,6 +1047,7 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
+ {
+ int ret;
+ struct rv_jit_context ctx;
++ u32 size = image_end - image;
+
+ ctx.ninsns = 0;
+ /*
+@@ -1058,11 +1061,16 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image,
+ ctx.ro_insns = image;
+ ret = __arch_prepare_bpf_trampoline(im, m, tlinks, func_addr, flags, &ctx);
+ if (ret < 0)
+- return ret;
++ goto out;
+
+- bpf_flush_icache(ctx.insns, ctx.insns + ctx.ninsns);
++ if (WARN_ON(size < ninsns_rvoff(ctx.ninsns))) {
++ ret = -E2BIG;
++ goto out;
++ }
+
+- return ninsns_rvoff(ret);
++ bpf_flush_icache(image, image_end);
++out:
++ return ret < 0 ? ret : size;
+ }
+
+ int bpf_jit_emit_insn(const struct bpf_insn *insn, struct rv_jit_context *ctx,
+diff --git a/arch/s390/kernel/perf_cpum_cf.c b/arch/s390/kernel/perf_cpum_cf.c
+index 1434642e9cba0..6968be98af117 100644
+--- a/arch/s390/kernel/perf_cpum_cf.c
++++ b/arch/s390/kernel/perf_cpum_cf.c
+@@ -556,25 +556,31 @@ static int cfdiag_diffctr(struct cpu_cf_events *cpuhw, unsigned long auth)
+ struct cf_trailer_entry *trailer_start, *trailer_stop;
+ struct cf_ctrset_entry *ctrstart, *ctrstop;
+ size_t offset = 0;
++ int i;
+
+- auth &= (1 << CPUMF_LCCTL_ENABLE_SHIFT) - 1;
+- do {
++ for (i = CPUMF_CTR_SET_BASIC; i < CPUMF_CTR_SET_MAX; ++i) {
+ ctrstart = (struct cf_ctrset_entry *)(cpuhw->start + offset);
+ ctrstop = (struct cf_ctrset_entry *)(cpuhw->stop + offset);
+
++ /* Counter set not authorized */
++ if (!(auth & cpumf_ctr_ctl[i]))
++ continue;
++ /* Counter set size zero was not saved */
++ if (!cpum_cf_read_setsize(i))
++ continue;
++
+ if (memcmp(ctrstop, ctrstart, sizeof(*ctrstop))) {
+ pr_err_once("cpum_cf_diag counter set compare error "
+ "in set %i\n", ctrstart->set);
+ return 0;
+ }
+- auth &= ~cpumf_ctr_ctl[ctrstart->set];
+ if (ctrstart->def == CF_DIAG_CTRSET_DEF) {
+ cfdiag_diffctrset((u64 *)(ctrstart + 1),
+ (u64 *)(ctrstop + 1), ctrstart->ctr);
+ offset += ctrstart->ctr * sizeof(u64) +
+ sizeof(*ctrstart);
+ }
+- } while (ctrstart->def && auth);
++ }
+
+ /* Save time_stamp from start of event in stop's trailer */
+ trailer_start = (struct cf_trailer_entry *)(cpuhw->start + offset);
+diff --git a/arch/s390/kernel/setup.c b/arch/s390/kernel/setup.c
+index 90c2c786bb355..610e6f794511a 100644
+--- a/arch/s390/kernel/setup.c
++++ b/arch/s390/kernel/setup.c
+@@ -149,7 +149,7 @@ unsigned long __bootdata_preserved(max_mappable);
+ struct physmem_info __bootdata(physmem_info);
+
+ struct vm_layout __bootdata_preserved(vm_layout);
+-EXPORT_SYMBOL_GPL(vm_layout);
++EXPORT_SYMBOL(vm_layout);
+ int __bootdata_preserved(__kaslr_enabled);
+ unsigned int __bootdata_preserved(zlib_dfltcc_support);
+ EXPORT_SYMBOL(zlib_dfltcc_support);
+diff --git a/arch/s390/kernel/uv.c b/arch/s390/kernel/uv.c
+index 265fea37e0308..016993e9eb72f 100644
+--- a/arch/s390/kernel/uv.c
++++ b/arch/s390/kernel/uv.c
+@@ -318,6 +318,13 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
+ rc = make_folio_secure(folio, uvcb);
+ folio_unlock(folio);
+ }
++
++ /*
++ * Once we drop the PTL, the folio may get unmapped and
++ * freed immediately. We need a temporary reference.
++ */
++ if (rc == -EAGAIN)
++ folio_get(folio);
+ }
+ unlock:
+ pte_unmap_unlock(ptep, ptelock);
+@@ -330,6 +337,7 @@ int gmap_make_secure(struct gmap *gmap, unsigned long gaddr, void *uvcb)
+ * completion, this is just a useless check, but it is safe.
+ */
+ folio_wait_writeback(folio);
++ folio_put(folio);
+ } else if (rc == -EBUSY) {
+ /*
+ * If we have tried a local drain and the folio refcount
+diff --git a/arch/s390/kvm/kvm-s390.c b/arch/s390/kvm/kvm-s390.c
+index 54b5b2565df8d..4a74effe68704 100644
+--- a/arch/s390/kvm/kvm-s390.c
++++ b/arch/s390/kvm/kvm-s390.c
+@@ -5749,6 +5749,9 @@ int kvm_arch_prepare_memory_region(struct kvm *kvm,
+ {
+ gpa_t size;
+
++ if (kvm_is_ucontrol(kvm))
++ return -EINVAL;
++
+ /* When we are protected, we should not change the memory slots */
+ if (kvm_s390_pv_get_handle(kvm))
+ return -EINVAL;
+diff --git a/arch/s390/pci/pci_irq.c b/arch/s390/pci/pci_irq.c
+index 0ef83b6ac0db7..84482a9213322 100644
+--- a/arch/s390/pci/pci_irq.c
++++ b/arch/s390/pci/pci_irq.c
+@@ -268,33 +268,20 @@ static void zpci_floating_irq_handler(struct airq_struct *airq,
+ }
+ }
+
+-int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
++static int __alloc_airq(struct zpci_dev *zdev, int msi_vecs,
++ unsigned long *bit)
+ {
+- struct zpci_dev *zdev = to_zpci(pdev);
+- unsigned int hwirq, msi_vecs, cpu;
+- unsigned long bit;
+- struct msi_desc *msi;
+- struct msi_msg msg;
+- int cpu_addr;
+- int rc, irq;
+-
+- zdev->aisb = -1UL;
+- zdev->msi_first_bit = -1U;
+- if (type == PCI_CAP_ID_MSI && nvec > 1)
+- return 1;
+- msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
+-
+ if (irq_delivery == DIRECTED) {
+ /* Allocate cpu vector bits */
+- bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
+- if (bit == -1UL)
++ *bit = airq_iv_alloc(zpci_ibv[0], msi_vecs);
++ if (*bit == -1UL)
+ return -EIO;
+ } else {
+ /* Allocate adapter summary indicator bit */
+- bit = airq_iv_alloc_bit(zpci_sbv);
+- if (bit == -1UL)
++ *bit = airq_iv_alloc_bit(zpci_sbv);
++ if (*bit == -1UL)
+ return -EIO;
+- zdev->aisb = bit;
++ zdev->aisb = *bit;
+
+ /* Create adapter interrupt vector */
+ zdev->aibv = airq_iv_create(msi_vecs, AIRQ_IV_DATA | AIRQ_IV_BITLOCK, NULL);
+@@ -302,27 +289,66 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+ return -ENOMEM;
+
+ /* Wire up shortcut pointer */
+- zpci_ibv[bit] = zdev->aibv;
++ zpci_ibv[*bit] = zdev->aibv;
+ /* Each function has its own interrupt vector */
+- bit = 0;
++ *bit = 0;
+ }
++ return 0;
++}
+
+- /* Request MSI interrupts */
++int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
++{
++ unsigned int hwirq, msi_vecs, irqs_per_msi, i, cpu;
++ struct zpci_dev *zdev = to_zpci(pdev);
++ struct msi_desc *msi;
++ struct msi_msg msg;
++ unsigned long bit;
++ int cpu_addr;
++ int rc, irq;
++
++ zdev->aisb = -1UL;
++ zdev->msi_first_bit = -1U;
++
++ msi_vecs = min_t(unsigned int, nvec, zdev->max_msi);
++ if (msi_vecs < nvec) {
++ pr_info("%s requested %d irqs, allocate system limit of %d",
++ pci_name(pdev), nvec, zdev->max_msi);
++ }
++
++ rc = __alloc_airq(zdev, msi_vecs, &bit);
++ if (rc < 0)
++ return rc;
++
++ /*
++ * Request MSI interrupts:
++ * When using MSI, nvec_used interrupt sources and their irq
++ * descriptors are controlled through one msi descriptor.
++ * Thus the outer loop over msi descriptors shall run only once,
++ * while two inner loops iterate over the interrupt vectors.
++ * When using MSI-X, each interrupt vector/irq descriptor
++ * is bound to exactly one msi descriptor (nvec_used is one).
++ * So the inner loops are executed once, while the outer iterates
++ * over the MSI-X descriptors.
++ */
+ hwirq = bit;
+ msi_for_each_desc(msi, &pdev->dev, MSI_DESC_NOTASSOCIATED) {
+- rc = -EIO;
+ if (hwirq - bit >= msi_vecs)
+ break;
+- irq = __irq_alloc_descs(-1, 0, 1, 0, THIS_MODULE,
+- (irq_delivery == DIRECTED) ?
+- msi->affinity : NULL);
++ irqs_per_msi = min_t(unsigned int, msi_vecs, msi->nvec_used);
++ irq = __irq_alloc_descs(-1, 0, irqs_per_msi, 0, THIS_MODULE,
++ (irq_delivery == DIRECTED) ?
++ msi->affinity : NULL);
+ if (irq < 0)
+ return -ENOMEM;
+- rc = irq_set_msi_desc(irq, msi);
+- if (rc)
+- return rc;
+- irq_set_chip_and_handler(irq, &zpci_irq_chip,
+- handle_percpu_irq);
++
++ for (i = 0; i < irqs_per_msi; i++) {
++ rc = irq_set_msi_desc_off(irq, i, msi);
++ if (rc)
++ return rc;
++ irq_set_chip_and_handler(irq + i, &zpci_irq_chip,
++ handle_percpu_irq);
++ }
++
+ msg.data = hwirq - bit;
+ if (irq_delivery == DIRECTED) {
+ if (msi->affinity)
+@@ -335,31 +361,35 @@ int arch_setup_msi_irqs(struct pci_dev *pdev, int nvec, int type)
+ msg.address_lo |= (cpu_addr << 8);
+
+ for_each_possible_cpu(cpu) {
+- airq_iv_set_data(zpci_ibv[cpu], hwirq, irq);
++ for (i = 0; i < irqs_per_msi; i++)
++ airq_iv_set_data(zpci_ibv[cpu],
++ hwirq + i, irq + i);
+ }
+ } else {
+ msg.address_lo = zdev->msi_addr & 0xffffffff;
+- airq_iv_set_data(zdev->aibv, hwirq, irq);
++ for (i = 0; i < irqs_per_msi; i++)
++ airq_iv_set_data(zdev->aibv, hwirq + i, irq + i);
+ }
+ msg.address_hi = zdev->msi_addr >> 32;
+ pci_write_msi_msg(irq, &msg);
+- hwirq++;
++ hwirq += irqs_per_msi;
+ }
+
+ zdev->msi_first_bit = bit;
+- zdev->msi_nr_irqs = msi_vecs;
++ zdev->msi_nr_irqs = hwirq - bit;
+
+ rc = zpci_set_irq(zdev);
+ if (rc)
+ return rc;
+
+- return (msi_vecs == nvec) ? 0 : msi_vecs;
++ return (zdev->msi_nr_irqs == nvec) ? 0 : zdev->msi_nr_irqs;
+ }
+
+ void arch_teardown_msi_irqs(struct pci_dev *pdev)
+ {
+ struct zpci_dev *zdev = to_zpci(pdev);
+ struct msi_desc *msi;
++ unsigned int i;
+ int rc;
+
+ /* Disable interrupts */
+@@ -369,8 +399,10 @@ void arch_teardown_msi_irqs(struct pci_dev *pdev)
+
+ /* Release MSI interrupts */
+ msi_for_each_desc(msi, &pdev->dev, MSI_DESC_ASSOCIATED) {
+- irq_set_msi_desc(msi->irq, NULL);
+- irq_free_desc(msi->irq);
++ for (i = 0; i < msi->nvec_used; i++) {
++ irq_set_msi_desc(msi->irq + i, NULL);
++ irq_free_desc(msi->irq + i);
++ }
+ msi->msg.address_lo = 0;
+ msi->msg.address_hi = 0;
+ msi->msg.data = 0;
+diff --git a/arch/sparc/include/asm/oplib_64.h b/arch/sparc/include/asm/oplib_64.h
+index a67abebd43592..1b86d02a84556 100644
+--- a/arch/sparc/include/asm/oplib_64.h
++++ b/arch/sparc/include/asm/oplib_64.h
+@@ -247,6 +247,7 @@ void prom_sun4v_guest_soft_state(void);
+ int prom_ihandle2path(int handle, char *buffer, int bufsize);
+
+ /* Client interface level routines. */
++void prom_cif_init(void *cif_handler);
+ void p1275_cmd_direct(unsigned long *);
+
+ #endif /* !(__SPARC64_OPLIB_H) */
+diff --git a/arch/sparc/prom/init_64.c b/arch/sparc/prom/init_64.c
+index 103aa91043185..f7b8a1a865b8f 100644
+--- a/arch/sparc/prom/init_64.c
++++ b/arch/sparc/prom/init_64.c
+@@ -26,9 +26,6 @@ phandle prom_chosen_node;
+ * routines in the prom library.
+ * It gets passed the pointer to the PROM vector.
+ */
+-
+-extern void prom_cif_init(void *);
+-
+ void __init prom_init(void *cif_handler)
+ {
+ phandle node;
+diff --git a/arch/sparc/prom/p1275.c b/arch/sparc/prom/p1275.c
+index 889aa602f8d86..51c3f984bbf72 100644
+--- a/arch/sparc/prom/p1275.c
++++ b/arch/sparc/prom/p1275.c
+@@ -49,7 +49,7 @@ void p1275_cmd_direct(unsigned long *args)
+ local_irq_restore(flags);
+ }
+
+-void prom_cif_init(void *cif_handler, void *cif_stack)
++void prom_cif_init(void *cif_handler)
+ {
+ p1275buf.prom_cif_handler = (void (*)(long *))cif_handler;
+ }
+diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
+index ef805eaa9e013..093c87879d08b 100644
+--- a/arch/um/drivers/ubd_kern.c
++++ b/arch/um/drivers/ubd_kern.c
+@@ -447,43 +447,31 @@ static int bulk_req_safe_read(
+ return n;
+ }
+
+-/* Called without dev->lock held, and only in interrupt context. */
+-static void ubd_handler(void)
++static void ubd_end_request(struct io_thread_req *io_req)
+ {
+- int n;
+- int count;
+-
+- while(1){
+- n = bulk_req_safe_read(
+- thread_fd,
+- irq_req_buffer,
+- &irq_remainder,
+- &irq_remainder_size,
+- UBD_REQ_BUFFER_SIZE
+- );
+- if (n < 0) {
+- if(n == -EAGAIN)
+- break;
+- printk(KERN_ERR "spurious interrupt in ubd_handler, "
+- "err = %d\n", -n);
+- return;
+- }
+- for (count = 0; count < n/sizeof(struct io_thread_req *); count++) {
+- struct io_thread_req *io_req = (*irq_req_buffer)[count];
+-
+- if ((io_req->error == BLK_STS_NOTSUPP) && (req_op(io_req->req) == REQ_OP_DISCARD)) {
+- blk_queue_max_discard_sectors(io_req->req->q, 0);
+- blk_queue_max_write_zeroes_sectors(io_req->req->q, 0);
+- }
+- blk_mq_end_request(io_req->req, io_req->error);
+- kfree(io_req);
+- }
++ if (io_req->error == BLK_STS_NOTSUPP) {
++ if (req_op(io_req->req) == REQ_OP_DISCARD)
++ blk_queue_max_discard_sectors(io_req->req->q, 0);
++ else if (req_op(io_req->req) == REQ_OP_WRITE_ZEROES)
++ blk_queue_max_write_zeroes_sectors(io_req->req->q, 0);
+ }
++ blk_mq_end_request(io_req->req, io_req->error);
++ kfree(io_req);
+ }
+
+ static irqreturn_t ubd_intr(int irq, void *dev)
+ {
+- ubd_handler();
++ int len, i;
++
++ while ((len = bulk_req_safe_read(thread_fd, irq_req_buffer,
++ &irq_remainder, &irq_remainder_size,
++ UBD_REQ_BUFFER_SIZE)) >= 0) {
++ for (i = 0; i < len / sizeof(struct io_thread_req *); i++)
++ ubd_end_request((*irq_req_buffer)[i]);
++ }
++
++ if (len < 0 && len != -EAGAIN)
++ pr_err("spurious interrupt in %s, err = %d\n", __func__, len);
+ return IRQ_HANDLED;
+ }
+
+diff --git a/arch/um/kernel/time.c b/arch/um/kernel/time.c
+index a8bfe8be15260..5b5fd8f68d9c1 100644
+--- a/arch/um/kernel/time.c
++++ b/arch/um/kernel/time.c
+@@ -875,9 +875,9 @@ static int setup_time_travel_start(char *str)
+ return 1;
+ }
+
+-__setup("time-travel-start", setup_time_travel_start);
++__setup("time-travel-start=", setup_time_travel_start);
+ __uml_help(setup_time_travel_start,
+-"time-travel-start=<seconds>\n"
++"time-travel-start=<nanoseconds>\n"
+ "Configure the UML instance's wall clock to start at this value rather than\n"
+ "the host's wall clock at the time of UML boot.\n");
+ #endif
+diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
+index 787cfb9a03088..b11ed66c8bb0e 100644
+--- a/arch/um/os-Linux/signal.c
++++ b/arch/um/os-Linux/signal.c
+@@ -8,6 +8,7 @@
+
+ #include <stdlib.h>
+ #include <stdarg.h>
++#include <stdbool.h>
+ #include <errno.h>
+ #include <signal.h>
+ #include <string.h>
+@@ -65,9 +66,7 @@ static void sig_handler_common(int sig, struct siginfo *si, mcontext_t *mc)
+
+ int signals_enabled;
+ #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
+-static int signals_blocked;
+-#else
+-#define signals_blocked 0
++static int signals_blocked, signals_blocked_pending;
+ #endif
+ static unsigned int signals_pending;
+ static unsigned int signals_active = 0;
+@@ -76,14 +75,27 @@ static void sig_handler(int sig, struct siginfo *si, mcontext_t *mc)
+ {
+ int enabled = signals_enabled;
+
+- if ((signals_blocked || !enabled) && (sig == SIGIO)) {
++#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
++ if ((signals_blocked ||
++ __atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) &&
++ (sig == SIGIO)) {
++ /* increment so unblock will do another round */
++ __atomic_add_fetch(&signals_blocked_pending, 1,
++ __ATOMIC_SEQ_CST);
++ return;
++ }
++#endif
++
++ if (!enabled && (sig == SIGIO)) {
+ /*
+ * In TT_MODE_EXTERNAL, need to still call time-travel
+- * handlers unless signals are also blocked for the
+- * external time message processing. This will mark
+- * signals_pending by itself (only if necessary.)
++ * handlers. This will mark signals_pending by itself
++ * (only if necessary.)
++ * Note we won't get here if signals are hard-blocked
++ * (which is handled above), in that case the hard-
++ * unblock will handle things.
+ */
+- if (!signals_blocked && time_travel_mode == TT_MODE_EXTERNAL)
++ if (time_travel_mode == TT_MODE_EXTERNAL)
+ sigio_run_timetravel_handlers();
+ else
+ signals_pending |= SIGIO_MASK;
+@@ -380,33 +392,99 @@ int um_set_signals_trace(int enable)
+ #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
+ void mark_sigio_pending(void)
+ {
++ /*
++ * It would seem that this should be atomic so
++ * it isn't a read-modify-write with a signal
++ * that could happen in the middle, losing the
++ * value set by the signal.
++ *
++ * However, this function is only called when in
++ * time-travel=ext simulation mode, in which case
++ * the only signal ever pending is SIGIO, which
++ * is blocked while this can be called, and the
++ * timer signal (SIGALRM) cannot happen.
++ */
+ signals_pending |= SIGIO_MASK;
+ }
+
+ void block_signals_hard(void)
+ {
+- if (signals_blocked)
+- return;
+- signals_blocked = 1;
++ signals_blocked++;
+ barrier();
+ }
+
+ void unblock_signals_hard(void)
+ {
++ static bool unblocking;
++
+ if (!signals_blocked)
++ panic("unblocking signals while not blocked");
++
++ if (--signals_blocked)
+ return;
+- /* Must be set to 0 before we check the pending bits etc. */
+- signals_blocked = 0;
++ /*
++ * Must be set to 0 before we check pending so the
++ * SIGIO handler will run as normal unless we're still
++ * going to process signals_blocked_pending.
++ */
+ barrier();
+
+- if (signals_pending && signals_enabled) {
+- /* this is a bit inefficient, but that's not really important */
+- block_signals();
+- unblock_signals();
+- } else if (signals_pending & SIGIO_MASK) {
+- /* we need to run time-travel handlers even if not enabled */
+- sigio_run_timetravel_handlers();
++ /*
++ * Note that block_signals_hard()/unblock_signals_hard() can be called
++ * within the unblock_signals()/sigio_run_timetravel_handlers() below.
++ * This would still be prone to race conditions since it's actually a
++ * call _within_ e.g. vu_req_read_message(), where we observed this
++ * issue, which loops. Thus, if the inner call handles the recorded
++ * pending signals, we can get out of the inner call with the real
++ * signal hander no longer blocked, and still have a race. Thus don't
++ * handle unblocking in the inner call, if it happens, but only in
++ * the outermost call - 'unblocking' serves as an ownership for the
++ * signals_blocked_pending decrement.
++ */
++ if (unblocking)
++ return;
++ unblocking = true;
++
++ while (__atomic_load_n(&signals_blocked_pending, __ATOMIC_SEQ_CST)) {
++ if (signals_enabled) {
++ /* signals are enabled so we can touch this */
++ signals_pending |= SIGIO_MASK;
++ /*
++ * this is a bit inefficient, but that's
++ * not really important
++ */
++ block_signals();
++ unblock_signals();
++ } else {
++ /*
++ * we need to run time-travel handlers even
++ * if not enabled
++ */
++ sigio_run_timetravel_handlers();
++ }
++
++ /*
++ * The decrement of signals_blocked_pending must be atomic so
++ * that the signal handler will either happen before or after
++ * the decrement, not during a read-modify-write:
++ * - If it happens before, it can increment it and we'll
++ * decrement it and do another round in the loop.
++ * - If it happens after it'll see 0 for both signals_blocked
++ * and signals_blocked_pending and thus run the handler as
++ * usual (subject to signals_enabled, but that's unrelated.)
++ *
++ * Note that a call to unblock_signals_hard() within the calls
++ * to unblock_signals() or sigio_run_timetravel_handlers() above
++ * will do nothing due to the 'unblocking' state, so this cannot
++ * underflow as the only one decrementing will be the outermost
++ * one.
++ */
++ if (__atomic_sub_fetch(&signals_blocked_pending, 1,
++ __ATOMIC_SEQ_CST) < 0)
++ panic("signals_blocked_pending underflow");
+ }
++
++ unblocking = false;
+ }
+ #endif
+
+diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler
+index 59aedf32c4eaa..6d20a6ce0507d 100644
+--- a/arch/x86/Kconfig.assembler
++++ b/arch/x86/Kconfig.assembler
+@@ -36,6 +36,6 @@ config AS_VPCLMULQDQ
+ Supported by binutils >= 2.30 and LLVM integrated assembler
+
+ config AS_WRUSS
+- def_bool $(as-instr,wrussq %rax$(comma)(%rbx))
++ def_bool $(as-instr64,wrussq %rax$(comma)(%rbx))
+ help
+ Supported by binutils >= 2.31 and LLVM integrated assembler
+diff --git a/arch/x86/Makefile.um b/arch/x86/Makefile.um
+index 2106a2bd152bf..a46b1397ad01c 100644
+--- a/arch/x86/Makefile.um
++++ b/arch/x86/Makefile.um
+@@ -9,6 +9,7 @@ core-y += arch/x86/crypto/
+ #
+ ifeq ($(CONFIG_CC_IS_CLANG),y)
+ KBUILD_CFLAGS += -mno-sse -mno-mmx -mno-sse2 -mno-3dnow -mno-avx
++KBUILD_RUSTFLAGS += --target=$(objtree)/scripts/target.json
+ KBUILD_RUSTFLAGS += -Ctarget-feature=-sse,-sse2,-sse3,-ssse3,-sse4.1,-sse4.2,-avx,-avx2
+ endif
+
+diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c
+index c2235bae17ef6..8cc9950d7104a 100644
+--- a/arch/x86/entry/syscall_32.c
++++ b/arch/x86/entry/syscall_32.c
+@@ -14,9 +14,12 @@
+ #endif
+
+ #define __SYSCALL(nr, sym) extern long __ia32_##sym(const struct pt_regs *);
+-
++#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __ia32_##sym(const struct pt_regs *);
+ #include <asm/syscalls_32.h>
+-#undef __SYSCALL
++#undef __SYSCALL
++
++#undef __SYSCALL_NORETURN
++#define __SYSCALL_NORETURN __SYSCALL
+
+ /*
+ * The sys_call_table[] is no longer used for system calls, but
+@@ -28,11 +31,10 @@
+ const sys_call_ptr_t sys_call_table[] = {
+ #include <asm/syscalls_32.h>
+ };
+-#undef __SYSCALL
++#undef __SYSCALL
+ #endif
+
+ #define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs);
+-
+ long ia32_sys_call(const struct pt_regs *regs, unsigned int nr)
+ {
+ switch (nr) {
+diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c
+index 33b3f09e6f151..ba8354424860c 100644
+--- a/arch/x86/entry/syscall_64.c
++++ b/arch/x86/entry/syscall_64.c
+@@ -8,8 +8,12 @@
+ #include <asm/syscall.h>
+
+ #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
++#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
+ #include <asm/syscalls_64.h>
+-#undef __SYSCALL
++#undef __SYSCALL
++
++#undef __SYSCALL_NORETURN
++#define __SYSCALL_NORETURN __SYSCALL
+
+ /*
+ * The sys_call_table[] is no longer used for system calls, but
+@@ -20,10 +24,9 @@
+ const sys_call_ptr_t sys_call_table[] = {
+ #include <asm/syscalls_64.h>
+ };
+-#undef __SYSCALL
++#undef __SYSCALL
+
+ #define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+-
+ long x64_sys_call(const struct pt_regs *regs, unsigned int nr)
+ {
+ switch (nr) {
+diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c
+index 03de4a9321318..fb77908f44f37 100644
+--- a/arch/x86/entry/syscall_x32.c
++++ b/arch/x86/entry/syscall_x32.c
+@@ -8,11 +8,14 @@
+ #include <asm/syscall.h>
+
+ #define __SYSCALL(nr, sym) extern long __x64_##sym(const struct pt_regs *);
++#define __SYSCALL_NORETURN(nr, sym) extern long __noreturn __x64_##sym(const struct pt_regs *);
+ #include <asm/syscalls_x32.h>
+-#undef __SYSCALL
++#undef __SYSCALL
+
+-#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
++#undef __SYSCALL_NORETURN
++#define __SYSCALL_NORETURN __SYSCALL
+
++#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs);
+ long x32_sys_call(const struct pt_regs *regs, unsigned int nr)
+ {
+ switch (nr) {
+diff --git a/arch/x86/entry/syscalls/syscall_32.tbl b/arch/x86/entry/syscalls/syscall_32.tbl
+index d6ebcab1d8b28..4b71a2607bf58 100644
+--- a/arch/x86/entry/syscalls/syscall_32.tbl
++++ b/arch/x86/entry/syscalls/syscall_32.tbl
+@@ -2,7 +2,7 @@
+ # 32-bit system call numbers and entry vectors
+ #
+ # The format is:
+-# <number> <abi> <name> <entry point> <compat entry point>
++# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
+ #
+ # The __ia32_sys and __ia32_compat_sys stubs are created on-the-fly for
+ # sys_*() system calls and compat_sys_*() compat system calls if
+@@ -12,7 +12,7 @@
+ # The abi is always "i386" for this file.
+ #
+ 0 i386 restart_syscall sys_restart_syscall
+-1 i386 exit sys_exit
++1 i386 exit sys_exit - noreturn
+ 2 i386 fork sys_fork
+ 3 i386 read sys_read
+ 4 i386 write sys_write
+@@ -263,7 +263,7 @@
+ 249 i386 io_cancel sys_io_cancel
+ 250 i386 fadvise64 sys_ia32_fadvise64
+ # 251 is available for reuse (was briefly sys_set_zone_reclaim)
+-252 i386 exit_group sys_exit_group
++252 i386 exit_group sys_exit_group - noreturn
+ 253 i386 lookup_dcookie
+ 254 i386 epoll_create sys_epoll_create
+ 255 i386 epoll_ctl sys_epoll_ctl
+diff --git a/arch/x86/entry/syscalls/syscall_64.tbl b/arch/x86/entry/syscalls/syscall_64.tbl
+index a396f6e6ab5bf..a8068f937290a 100644
+--- a/arch/x86/entry/syscalls/syscall_64.tbl
++++ b/arch/x86/entry/syscalls/syscall_64.tbl
+@@ -2,7 +2,7 @@
+ # 64-bit system call numbers and entry vectors
+ #
+ # The format is:
+-# <number> <abi> <name> <entry point>
++# <number> <abi> <name> <entry point> [<compat entry point> [noreturn]]
+ #
+ # The __x64_sys_*() stubs are created on-the-fly for sys_*() system calls
+ #
+@@ -68,7 +68,7 @@
+ 57 common fork sys_fork
+ 58 common vfork sys_vfork
+ 59 64 execve sys_execve
+-60 common exit sys_exit
++60 common exit sys_exit - noreturn
+ 61 common wait4 sys_wait4
+ 62 common kill sys_kill
+ 63 common uname sys_newuname
+@@ -239,7 +239,7 @@
+ 228 common clock_gettime sys_clock_gettime
+ 229 common clock_getres sys_clock_getres
+ 230 common clock_nanosleep sys_clock_nanosleep
+-231 common exit_group sys_exit_group
++231 common exit_group sys_exit_group - noreturn
+ 232 common epoll_wait sys_epoll_wait
+ 233 common epoll_ctl sys_epoll_ctl
+ 234 common tgkill sys_tgkill
+diff --git a/arch/x86/events/amd/uncore.c b/arch/x86/events/amd/uncore.c
+index 4ccb8fa483e61..5a4bfe9aea237 100644
+--- a/arch/x86/events/amd/uncore.c
++++ b/arch/x86/events/amd/uncore.c
+@@ -639,7 +639,7 @@ void amd_uncore_df_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
+ info.split.aux_data = 0;
+ info.split.num_pmcs = NUM_COUNTERS_NB;
+ info.split.gid = 0;
+- info.split.cid = topology_die_id(cpu);
++ info.split.cid = topology_logical_package_id(cpu);
+
+ if (pmu_version >= 2) {
+ ebx.full = cpuid_ebx(EXT_PERFMON_DEBUG_FEATURES);
+@@ -654,17 +654,20 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+ {
+ struct attribute **df_attr = amd_uncore_df_format_attr;
+ struct amd_uncore_pmu *pmu;
++ int num_counters;
+
+ /* Run just once */
+ if (uncore->init_done)
+ return amd_uncore_ctx_init(uncore, cpu);
+
++ num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
++ if (!num_counters)
++ goto done;
++
+ /* No grouping, single instance for a system */
+ uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
+- if (!uncore->pmus) {
+- uncore->num_pmus = 0;
++ if (!uncore->pmus)
+ goto done;
+- }
+
+ /*
+ * For Family 17h and above, the Northbridge counters are repurposed
+@@ -674,7 +677,7 @@ int amd_uncore_df_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+ pmu = &uncore->pmus[0];
+ strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_df" : "amd_nb",
+ sizeof(pmu->name));
+- pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
++ pmu->num_counters = num_counters;
+ pmu->msr_base = MSR_F15H_NB_PERF_CTL;
+ pmu->rdpmc_base = RDPMC_BASE_NB;
+ pmu->group = amd_uncore_ctx_gid(uncore, cpu);
+@@ -785,17 +788,20 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+ {
+ struct attribute **l3_attr = amd_uncore_l3_format_attr;
+ struct amd_uncore_pmu *pmu;
++ int num_counters;
+
+ /* Run just once */
+ if (uncore->init_done)
+ return amd_uncore_ctx_init(uncore, cpu);
+
++ num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
++ if (!num_counters)
++ goto done;
++
+ /* No grouping, single instance for a system */
+ uncore->pmus = kzalloc(sizeof(*uncore->pmus), GFP_KERNEL);
+- if (!uncore->pmus) {
+- uncore->num_pmus = 0;
++ if (!uncore->pmus)
+ goto done;
+- }
+
+ /*
+ * For Family 17h and above, L3 cache counters are available instead
+@@ -805,7 +811,7 @@ int amd_uncore_l3_ctx_init(struct amd_uncore *uncore, unsigned int cpu)
+ pmu = &uncore->pmus[0];
+ strscpy(pmu->name, boot_cpu_data.x86 >= 0x17 ? "amd_l3" : "amd_l2",
+ sizeof(pmu->name));
+- pmu->num_counters = amd_uncore_ctx_num_pmcs(uncore, cpu);
++ pmu->num_counters = num_counters;
+ pmu->msr_base = MSR_F16H_L2I_PERF_CTL;
+ pmu->rdpmc_base = RDPMC_BASE_LLC;
+ pmu->group = amd_uncore_ctx_gid(uncore, cpu);
+@@ -893,8 +899,8 @@ void amd_uncore_umc_ctx_scan(struct amd_uncore *uncore, unsigned int cpu)
+ cpuid(EXT_PERFMON_DEBUG_FEATURES, &eax, &ebx.full, &ecx, &edx);
+ info.split.aux_data = ecx; /* stash active mask */
+ info.split.num_pmcs = ebx.split.num_umc_pmc;
+- info.split.gid = topology_die_id(cpu);
+- info.split.cid = topology_die_id(cpu);
++ info.split.gid = topology_logical_package_id(cpu);
++ info.split.cid = topology_logical_package_id(cpu);
+ *per_cpu_ptr(uncore->info, cpu) = info;
+ }
+
+diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
+index 5b0dd07b1ef19..acd367c453341 100644
+--- a/arch/x86/events/core.c
++++ b/arch/x86/events/core.c
+@@ -2547,6 +2547,7 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+ {
++ static DEFINE_MUTEX(rdpmc_mutex);
+ unsigned long val;
+ ssize_t ret;
+
+@@ -2560,6 +2561,8 @@ static ssize_t set_attr_rdpmc(struct device *cdev,
+ if (x86_pmu.attr_rdpmc_broken)
+ return -ENOTSUPP;
+
++ guard(mutex)(&rdpmc_mutex);
++
+ if (val != x86_pmu.attr_rdpmc) {
+ /*
+ * Changing into or out of never available or always available,
+diff --git a/arch/x86/events/intel/cstate.c b/arch/x86/events/intel/cstate.c
+index 9d6e8f13d13a7..dd18320558914 100644
+--- a/arch/x86/events/intel/cstate.c
++++ b/arch/x86/events/intel/cstate.c
+@@ -81,7 +81,7 @@
+ * MSR_PKG_C7_RESIDENCY: Package C7 Residency Counter.
+ * perf code: 0x03
+ * Available model: NHM,WSM,SNB,IVB,HSW,BDW,SKL,CNL,
+- * KBL,CML,ICL,TGL,RKL,ADL,RPL,MTL
++ * KBL,CML,ICL,TGL,RKL
+ * Scope: Package (physical package)
+ * MSR_PKG_C8_RESIDENCY: Package C8 Residency Counter.
+ * perf code: 0x04
+@@ -90,8 +90,7 @@
+ * Scope: Package (physical package)
+ * MSR_PKG_C9_RESIDENCY: Package C9 Residency Counter.
+ * perf code: 0x05
+- * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL,
+- * ADL,RPL,MTL
++ * Available model: HSW ULT,KBL,CNL,CML,ICL,TGL,RKL
+ * Scope: Package (physical package)
+ * MSR_PKG_C10_RESIDENCY: Package C10 Residency Counter.
+ * perf code: 0x06
+@@ -637,9 +636,7 @@ static const struct cstate_model adl_cstates __initconst = {
+ .pkg_events = BIT(PERF_CSTATE_PKG_C2_RES) |
+ BIT(PERF_CSTATE_PKG_C3_RES) |
+ BIT(PERF_CSTATE_PKG_C6_RES) |
+- BIT(PERF_CSTATE_PKG_C7_RES) |
+ BIT(PERF_CSTATE_PKG_C8_RES) |
+- BIT(PERF_CSTATE_PKG_C9_RES) |
+ BIT(PERF_CSTATE_PKG_C10_RES),
+ };
+
+diff --git a/arch/x86/events/intel/ds.c b/arch/x86/events/intel/ds.c
+index e010bfed84170..80a4f712217b7 100644
+--- a/arch/x86/events/intel/ds.c
++++ b/arch/x86/events/intel/ds.c
+@@ -1831,8 +1831,12 @@ static void setup_pebs_adaptive_sample_data(struct perf_event *event,
+ set_linear_ip(regs, basic->ip);
+ regs->flags = PERF_EFLAGS_EXACT;
+
+- if ((sample_type & PERF_SAMPLE_WEIGHT_STRUCT) && (x86_pmu.flags & PMU_FL_RETIRE_LATENCY))
+- data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
++ if (sample_type & PERF_SAMPLE_WEIGHT_STRUCT) {
++ if (x86_pmu.flags & PMU_FL_RETIRE_LATENCY)
++ data->weight.var3_w = format_size >> PEBS_RETIRE_LATENCY_OFFSET & PEBS_LATENCY_MASK;
++ else
++ data->weight.var3_w = 0;
++ }
+
+ /*
+ * The record for MEMINFO is in front of GP
+diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
+index 14db6d9d318b3..b4aa8daa47738 100644
+--- a/arch/x86/events/intel/pt.c
++++ b/arch/x86/events/intel/pt.c
+@@ -878,7 +878,7 @@ static void pt_update_head(struct pt *pt)
+ */
+ static void *pt_buffer_region(struct pt_buffer *buf)
+ {
+- return phys_to_virt(TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
++ return phys_to_virt((phys_addr_t)TOPA_ENTRY(buf->cur, buf->cur_idx)->base << TOPA_SHIFT);
+ }
+
+ /**
+@@ -990,7 +990,7 @@ pt_topa_entry_for_page(struct pt_buffer *buf, unsigned int pg)
+ * order allocations, there shouldn't be many of these.
+ */
+ list_for_each_entry(topa, &buf->tables, list) {
+- if (topa->offset + topa->size > pg << PAGE_SHIFT)
++ if (topa->offset + topa->size > (unsigned long)pg << PAGE_SHIFT)
+ goto found;
+ }
+
+diff --git a/arch/x86/events/intel/pt.h b/arch/x86/events/intel/pt.h
+index 96906a62aacda..f5e46c04c145d 100644
+--- a/arch/x86/events/intel/pt.h
++++ b/arch/x86/events/intel/pt.h
+@@ -33,8 +33,8 @@ struct topa_entry {
+ u64 rsvd2 : 1;
+ u64 size : 4;
+ u64 rsvd3 : 2;
+- u64 base : 36;
+- u64 rsvd4 : 16;
++ u64 base : 40;
++ u64 rsvd4 : 12;
+ };
+
+ /* TSC to Core Crystal Clock Ratio */
+diff --git a/arch/x86/events/intel/uncore_snbep.c b/arch/x86/events/intel/uncore_snbep.c
+index 74b8b21e8990b..1891c2c7823b1 100644
+--- a/arch/x86/events/intel/uncore_snbep.c
++++ b/arch/x86/events/intel/uncore_snbep.c
+@@ -462,6 +462,7 @@
+ #define SPR_UBOX_DID 0x3250
+
+ /* SPR CHA */
++#define SPR_CHA_EVENT_MASK_EXT 0xffffffff
+ #define SPR_CHA_PMON_CTL_TID_EN (1 << 16)
+ #define SPR_CHA_PMON_EVENT_MASK (SNBEP_PMON_RAW_EVENT_MASK | \
+ SPR_CHA_PMON_CTL_TID_EN)
+@@ -478,6 +479,7 @@ DEFINE_UNCORE_FORMAT_ATTR(umask_ext, umask, "config:8-15,32-43,45-55");
+ DEFINE_UNCORE_FORMAT_ATTR(umask_ext2, umask, "config:8-15,32-57");
+ DEFINE_UNCORE_FORMAT_ATTR(umask_ext3, umask, "config:8-15,32-39");
+ DEFINE_UNCORE_FORMAT_ATTR(umask_ext4, umask, "config:8-15,32-55");
++DEFINE_UNCORE_FORMAT_ATTR(umask_ext5, umask, "config:8-15,32-63");
+ DEFINE_UNCORE_FORMAT_ATTR(qor, qor, "config:16");
+ DEFINE_UNCORE_FORMAT_ATTR(edge, edge, "config:18");
+ DEFINE_UNCORE_FORMAT_ATTR(tid_en, tid_en, "config:19");
+@@ -5958,7 +5960,7 @@ static struct intel_uncore_ops spr_uncore_chabox_ops = {
+
+ static struct attribute *spr_uncore_cha_formats_attr[] = {
+ &format_attr_event.attr,
+- &format_attr_umask_ext4.attr,
++ &format_attr_umask_ext5.attr,
+ &format_attr_tid_en2.attr,
+ &format_attr_edge.attr,
+ &format_attr_inv.attr,
+@@ -5994,7 +5996,7 @@ ATTRIBUTE_GROUPS(uncore_alias);
+ static struct intel_uncore_type spr_uncore_chabox = {
+ .name = "cha",
+ .event_mask = SPR_CHA_PMON_EVENT_MASK,
+- .event_mask_ext = SPR_RAW_EVENT_MASK_EXT,
++ .event_mask_ext = SPR_CHA_EVENT_MASK_EXT,
+ .num_shared_regs = 1,
+ .constraints = skx_uncore_chabox_constraints,
+ .ops = &spr_uncore_chabox_ops,
+diff --git a/arch/x86/include/asm/kvm-x86-ops.h b/arch/x86/include/asm/kvm-x86-ops.h
+index 5187fcf4b610b..8d5a2b4f5f006 100644
+--- a/arch/x86/include/asm/kvm-x86-ops.h
++++ b/arch/x86/include/asm/kvm-x86-ops.h
+@@ -85,7 +85,6 @@ KVM_X86_OP_OPTIONAL(update_cr8_intercept)
+ KVM_X86_OP(refresh_apicv_exec_ctrl)
+ KVM_X86_OP_OPTIONAL(hwapic_irr_update)
+ KVM_X86_OP_OPTIONAL(hwapic_isr_update)
+-KVM_X86_OP_OPTIONAL_RET0(guest_apic_has_interrupt)
+ KVM_X86_OP_OPTIONAL(load_eoi_exitmap)
+ KVM_X86_OP_OPTIONAL(set_virtual_apic_mode)
+ KVM_X86_OP_OPTIONAL(set_apic_access_page_addr)
+diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h
+index f8ca74e7678f3..d0274b3be2c40 100644
+--- a/arch/x86/include/asm/kvm_host.h
++++ b/arch/x86/include/asm/kvm_host.h
+@@ -1714,7 +1714,6 @@ struct kvm_x86_ops {
+ void (*refresh_apicv_exec_ctrl)(struct kvm_vcpu *vcpu);
+ void (*hwapic_irr_update)(struct kvm_vcpu *vcpu, int max_irr);
+ void (*hwapic_isr_update)(int isr);
+- bool (*guest_apic_has_interrupt)(struct kvm_vcpu *vcpu);
+ void (*load_eoi_exitmap)(struct kvm_vcpu *vcpu, u64 *eoi_exit_bitmap);
+ void (*set_virtual_apic_mode)(struct kvm_vcpu *vcpu);
+ void (*set_apic_access_page_addr)(struct kvm_vcpu *vcpu);
+@@ -1819,7 +1818,7 @@ struct kvm_x86_nested_ops {
+ bool (*is_exception_vmexit)(struct kvm_vcpu *vcpu, u8 vector,
+ u32 error_code);
+ int (*check_events)(struct kvm_vcpu *vcpu);
+- bool (*has_events)(struct kvm_vcpu *vcpu);
++ bool (*has_events)(struct kvm_vcpu *vcpu, bool for_injection);
+ void (*triple_fault)(struct kvm_vcpu *vcpu);
+ int (*get_state)(struct kvm_vcpu *vcpu,
+ struct kvm_nested_state __user *user_kvm_nested_state,
+diff --git a/arch/x86/include/asm/shstk.h b/arch/x86/include/asm/shstk.h
+index 42fee8959df7b..896909f306e30 100644
+--- a/arch/x86/include/asm/shstk.h
++++ b/arch/x86/include/asm/shstk.h
+@@ -21,6 +21,7 @@ unsigned long shstk_alloc_thread_stack(struct task_struct *p, unsigned long clon
+ void shstk_free(struct task_struct *p);
+ int setup_signal_shadow_stack(struct ksignal *ksig);
+ int restore_signal_shadow_stack(void);
++int shstk_update_last_frame(unsigned long val);
+ #else
+ static inline long shstk_prctl(struct task_struct *task, int option,
+ unsigned long arg2) { return -EINVAL; }
+@@ -31,6 +32,7 @@ static inline unsigned long shstk_alloc_thread_stack(struct task_struct *p,
+ static inline void shstk_free(struct task_struct *p) {}
+ static inline int setup_signal_shadow_stack(struct ksignal *ksig) { return 0; }
+ static inline int restore_signal_shadow_stack(void) { return 0; }
++static inline int shstk_update_last_frame(unsigned long val) { return 0; }
+ #endif /* CONFIG_X86_USER_SHADOW_STACK */
+
+ #endif /* __ASSEMBLY__ */
+diff --git a/arch/x86/kernel/devicetree.c b/arch/x86/kernel/devicetree.c
+index 8e3c53b4d070e..64280879c68c0 100644
+--- a/arch/x86/kernel/devicetree.c
++++ b/arch/x86/kernel/devicetree.c
+@@ -83,7 +83,7 @@ static int x86_of_pci_irq_enable(struct pci_dev *dev)
+
+ ret = pci_read_config_byte(dev, PCI_INTERRUPT_PIN, &pin);
+ if (ret)
+- return ret;
++ return pcibios_err_to_errno(ret);
+ if (!pin)
+ return 0;
+
+diff --git a/arch/x86/kernel/shstk.c b/arch/x86/kernel/shstk.c
+index 6f1e9883f0742..9797d4cdb78a2 100644
+--- a/arch/x86/kernel/shstk.c
++++ b/arch/x86/kernel/shstk.c
+@@ -577,3 +577,14 @@ long shstk_prctl(struct task_struct *task, int option, unsigned long arg2)
+ return wrss_control(true);
+ return -EINVAL;
+ }
++
++int shstk_update_last_frame(unsigned long val)
++{
++ unsigned long ssp;
++
++ if (!features_enabled(ARCH_SHSTK_SHSTK))
++ return 0;
++
++ ssp = get_user_shstk_addr();
++ return write_user_shstk_64((u64 __user *)ssp, (u64)val);
++}
+diff --git a/arch/x86/kernel/uprobes.c b/arch/x86/kernel/uprobes.c
+index 6c07f6daaa227..6402fb3089d26 100644
+--- a/arch/x86/kernel/uprobes.c
++++ b/arch/x86/kernel/uprobes.c
+@@ -1076,8 +1076,13 @@ arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr, struct pt_regs
+ return orig_ret_vaddr;
+
+ nleft = copy_to_user((void __user *)regs->sp, &trampoline_vaddr, rasize);
+- if (likely(!nleft))
++ if (likely(!nleft)) {
++ if (shstk_update_last_frame(trampoline_vaddr)) {
++ force_sig(SIGSEGV);
++ return -1;
++ }
+ return orig_ret_vaddr;
++ }
+
+ if (nleft != rasize) {
+ pr_err("return address clobbered: pid=%d, %%sp=%#lx, %%ip=%#lx\n",
+diff --git a/arch/x86/kvm/vmx/main.c b/arch/x86/kvm/vmx/main.c
+index d4ed681785fd6..547fca3709feb 100644
+--- a/arch/x86/kvm/vmx/main.c
++++ b/arch/x86/kvm/vmx/main.c
+@@ -97,7 +97,6 @@ struct kvm_x86_ops vt_x86_ops __initdata = {
+ .required_apicv_inhibits = VMX_REQUIRED_APICV_INHIBITS,
+ .hwapic_irr_update = vmx_hwapic_irr_update,
+ .hwapic_isr_update = vmx_hwapic_isr_update,
+- .guest_apic_has_interrupt = vmx_guest_apic_has_interrupt,
+ .sync_pir_to_irr = vmx_sync_pir_to_irr,
+ .deliver_interrupt = vmx_deliver_interrupt,
+ .dy_apicv_has_pending_interrupt = pi_has_pending_interrupt,
+diff --git a/arch/x86/kvm/vmx/nested.c b/arch/x86/kvm/vmx/nested.c
+index 643935a0f70ab..7c57d6524f754 100644
+--- a/arch/x86/kvm/vmx/nested.c
++++ b/arch/x86/kvm/vmx/nested.c
+@@ -12,6 +12,7 @@
+ #include "mmu.h"
+ #include "nested.h"
+ #include "pmu.h"
++#include "posted_intr.h"
+ #include "sgx.h"
+ #include "trace.h"
+ #include "vmx.h"
+@@ -3899,8 +3900,8 @@ static int vmx_complete_nested_posted_interrupt(struct kvm_vcpu *vcpu)
+ if (!pi_test_and_clear_on(vmx->nested.pi_desc))
+ return 0;
+
+- max_irr = find_last_bit((unsigned long *)vmx->nested.pi_desc->pir, 256);
+- if (max_irr != 256) {
++ max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
++ if (max_irr > 0) {
+ vapic_page = vmx->nested.virtual_apic_map.hva;
+ if (!vapic_page)
+ goto mmio_needed;
+@@ -4031,10 +4032,46 @@ static bool nested_vmx_preemption_timer_pending(struct kvm_vcpu *vcpu)
+ to_vmx(vcpu)->nested.preemption_timer_expired;
+ }
+
+-static bool vmx_has_nested_events(struct kvm_vcpu *vcpu)
++static bool vmx_has_nested_events(struct kvm_vcpu *vcpu, bool for_injection)
+ {
+- return nested_vmx_preemption_timer_pending(vcpu) ||
+- to_vmx(vcpu)->nested.mtf_pending;
++ struct vcpu_vmx *vmx = to_vmx(vcpu);
++ void *vapic = vmx->nested.virtual_apic_map.hva;
++ int max_irr, vppr;
++
++ if (nested_vmx_preemption_timer_pending(vcpu) ||
++ vmx->nested.mtf_pending)
++ return true;
++
++ /*
++ * Virtual Interrupt Delivery doesn't require manual injection. Either
++ * the interrupt is already in GUEST_RVI and will be recognized by CPU
++ * at VM-Entry, or there is a KVM_REQ_EVENT pending and KVM will move
++ * the interrupt from the PIR to RVI prior to entering the guest.
++ */
++ if (for_injection)
++ return false;
++
++ if (!nested_cpu_has_vid(get_vmcs12(vcpu)) ||
++ __vmx_interrupt_blocked(vcpu))
++ return false;
++
++ if (!vapic)
++ return false;
++
++ vppr = *((u32 *)(vapic + APIC_PROCPRI));
++
++ max_irr = vmx_get_rvi();
++ if ((max_irr & 0xf0) > (vppr & 0xf0))
++ return true;
++
++ if (vmx->nested.pi_pending && vmx->nested.pi_desc &&
++ pi_test_on(vmx->nested.pi_desc)) {
++ max_irr = pi_find_highest_vector(vmx->nested.pi_desc);
++ if (max_irr > 0 && (max_irr & 0xf0) > (vppr & 0xf0))
++ return true;
++ }
++
++ return false;
+ }
+
+ /*
+diff --git a/arch/x86/kvm/vmx/posted_intr.h b/arch/x86/kvm/vmx/posted_intr.h
+index 6b2a0226257ea..1715d2ab07be5 100644
+--- a/arch/x86/kvm/vmx/posted_intr.h
++++ b/arch/x86/kvm/vmx/posted_intr.h
+@@ -1,6 +1,8 @@
+ /* SPDX-License-Identifier: GPL-2.0 */
+ #ifndef __KVM_X86_VMX_POSTED_INTR_H
+ #define __KVM_X86_VMX_POSTED_INTR_H
++
++#include <linux/find.h>
+ #include <asm/posted_intr.h>
+
+ void vmx_vcpu_pi_load(struct kvm_vcpu *vcpu, int cpu);
+@@ -12,4 +14,12 @@ int vmx_pi_update_irte(struct kvm *kvm, unsigned int host_irq,
+ uint32_t guest_irq, bool set);
+ void vmx_pi_start_assignment(struct kvm *kvm);
+
++static inline int pi_find_highest_vector(struct pi_desc *pi_desc)
++{
++ int vec;
++
++ vec = find_last_bit((unsigned long *)pi_desc->pir, 256);
++ return vec < 256 ? vec : -1;
++}
++
+ #endif /* __KVM_X86_VMX_POSTED_INTR_H */
+diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c
+index b3c83c06f8265..2792c50869773 100644
+--- a/arch/x86/kvm/vmx/vmx.c
++++ b/arch/x86/kvm/vmx/vmx.c
+@@ -4108,26 +4108,6 @@ void pt_update_intercept_for_msr(struct kvm_vcpu *vcpu)
+ }
+ }
+
+-bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+-{
+- struct vcpu_vmx *vmx = to_vmx(vcpu);
+- void *vapic_page;
+- u32 vppr;
+- int rvi;
+-
+- if (WARN_ON_ONCE(!is_guest_mode(vcpu)) ||
+- !nested_cpu_has_vid(get_vmcs12(vcpu)) ||
+- WARN_ON_ONCE(!vmx->nested.virtual_apic_map.gfn))
+- return false;
+-
+- rvi = vmx_get_rvi();
+-
+- vapic_page = vmx->nested.virtual_apic_map.hva;
+- vppr = *((u32 *)(vapic_page + APIC_PROCPRI));
+-
+- return ((rvi & 0xf0) > (vppr & 0xf0));
+-}
+-
+ void vmx_msr_filter_changed(struct kvm_vcpu *vcpu)
+ {
+ struct vcpu_vmx *vmx = to_vmx(vcpu);
+@@ -5052,14 +5032,19 @@ int vmx_nmi_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+ return !vmx_nmi_blocked(vcpu);
+ }
+
++bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu)
++{
++ return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) ||
++ (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
++ (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
++}
++
+ bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu)
+ {
+ if (is_guest_mode(vcpu) && nested_exit_on_intr(vcpu))
+ return false;
+
+- return !(vmx_get_rflags(vcpu) & X86_EFLAGS_IF) ||
+- (vmcs_read32(GUEST_INTERRUPTIBILITY_INFO) &
+- (GUEST_INTR_STATE_STI | GUEST_INTR_STATE_MOV_SS));
++ return __vmx_interrupt_blocked(vcpu);
+ }
+
+ int vmx_interrupt_allowed(struct kvm_vcpu *vcpu, bool for_injection)
+diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h
+index 7b64e271a9319..2e23a01fe3206 100644
+--- a/arch/x86/kvm/vmx/vmx.h
++++ b/arch/x86/kvm/vmx/vmx.h
+@@ -406,6 +406,7 @@ u64 construct_eptp(struct kvm_vcpu *vcpu, hpa_t root_hpa, int root_level);
+ bool vmx_guest_inject_ac(struct kvm_vcpu *vcpu);
+ void vmx_update_exception_bitmap(struct kvm_vcpu *vcpu);
+ bool vmx_nmi_blocked(struct kvm_vcpu *vcpu);
++bool __vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
+ bool vmx_interrupt_blocked(struct kvm_vcpu *vcpu);
+ bool vmx_get_nmi_mask(struct kvm_vcpu *vcpu);
+ void vmx_set_nmi_mask(struct kvm_vcpu *vcpu, bool masked);
+diff --git a/arch/x86/kvm/vmx/x86_ops.h b/arch/x86/kvm/vmx/x86_ops.h
+index 502704596c832..d404227c164d6 100644
+--- a/arch/x86/kvm/vmx/x86_ops.h
++++ b/arch/x86/kvm/vmx/x86_ops.h
+@@ -49,7 +49,6 @@ void vmx_apicv_pre_state_restore(struct kvm_vcpu *vcpu);
+ bool vmx_check_apicv_inhibit_reasons(enum kvm_apicv_inhibit reason);
+ void vmx_hwapic_irr_update(struct kvm_vcpu *vcpu, int max_irr);
+ void vmx_hwapic_isr_update(int max_isr);
+-bool vmx_guest_apic_has_interrupt(struct kvm_vcpu *vcpu);
+ int vmx_sync_pir_to_irr(struct kvm_vcpu *vcpu);
+ void vmx_deliver_interrupt(struct kvm_lapic *apic, int delivery_mode,
+ int trig_mode, int vector);
+diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
+index 0763a0f72a067..0b7adf3bc58a6 100644
+--- a/arch/x86/kvm/x86.c
++++ b/arch/x86/kvm/x86.c
+@@ -10516,7 +10516,7 @@ static int kvm_check_and_inject_events(struct kvm_vcpu *vcpu,
+
+ if (is_guest_mode(vcpu) &&
+ kvm_x86_ops.nested_ops->has_events &&
+- kvm_x86_ops.nested_ops->has_events(vcpu))
++ kvm_x86_ops.nested_ops->has_events(vcpu, true))
+ *req_immediate_exit = true;
+
+ /*
+@@ -13100,12 +13100,6 @@ void kvm_arch_commit_memory_region(struct kvm *kvm,
+ kvm_arch_free_memslot(kvm, old);
+ }
+
+-static inline bool kvm_guest_apic_has_interrupt(struct kvm_vcpu *vcpu)
+-{
+- return (is_guest_mode(vcpu) &&
+- static_call(kvm_x86_guest_apic_has_interrupt)(vcpu));
+-}
+-
+ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+ {
+ if (!list_empty_careful(&vcpu->async_pf.done))
+@@ -13136,9 +13130,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+ if (kvm_test_request(KVM_REQ_PMI, vcpu))
+ return true;
+
+- if (kvm_arch_interrupt_allowed(vcpu) &&
+- (kvm_cpu_has_interrupt(vcpu) ||
+- kvm_guest_apic_has_interrupt(vcpu)))
++ if (kvm_arch_interrupt_allowed(vcpu) && kvm_cpu_has_interrupt(vcpu))
+ return true;
+
+ if (kvm_hv_has_stimer_pending(vcpu))
+@@ -13146,7 +13138,7 @@ static inline bool kvm_vcpu_has_events(struct kvm_vcpu *vcpu)
+
+ if (is_guest_mode(vcpu) &&
+ kvm_x86_ops.nested_ops->has_events &&
+- kvm_x86_ops.nested_ops->has_events(vcpu))
++ kvm_x86_ops.nested_ops->has_events(vcpu, false))
+ return true;
+
+ if (kvm_xen_has_pending_events(vcpu))
+diff --git a/arch/x86/pci/intel_mid_pci.c b/arch/x86/pci/intel_mid_pci.c
+index 8edd622066044..722a33be08a18 100644
+--- a/arch/x86/pci/intel_mid_pci.c
++++ b/arch/x86/pci/intel_mid_pci.c
+@@ -233,9 +233,9 @@ static int intel_mid_pci_irq_enable(struct pci_dev *dev)
+ return 0;
+
+ ret = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
+- if (ret < 0) {
++ if (ret) {
+ dev_warn(&dev->dev, "Failed to read interrupt line: %d\n", ret);
+- return ret;
++ return pcibios_err_to_errno(ret);
+ }
+
+ id = x86_match_cpu(intel_mid_cpu_ids);
+diff --git a/arch/x86/pci/xen.c b/arch/x86/pci/xen.c
+index 652cd53e77f64..0f2fe524f60dc 100644
+--- a/arch/x86/pci/xen.c
++++ b/arch/x86/pci/xen.c
+@@ -38,10 +38,10 @@ static int xen_pcifront_enable_irq(struct pci_dev *dev)
+ u8 gsi;
+
+ rc = pci_read_config_byte(dev, PCI_INTERRUPT_LINE, &gsi);
+- if (rc < 0) {
++ if (rc) {
+ dev_warn(&dev->dev, "Xen PCI: failed to read interrupt line: %d\n",
+ rc);
+- return rc;
++ return pcibios_err_to_errno(rc);
+ }
+ /* In PV DomU the Xen PCI backend puts the PIRQ in the interrupt line.*/
+ pirq = gsi;
+diff --git a/arch/x86/platform/intel/iosf_mbi.c b/arch/x86/platform/intel/iosf_mbi.c
+index fdd49d70b4373..c81cea208c2c4 100644
+--- a/arch/x86/platform/intel/iosf_mbi.c
++++ b/arch/x86/platform/intel/iosf_mbi.c
+@@ -62,7 +62,7 @@ static int iosf_mbi_pci_read_mdr(u32 mcrx, u32 mcr, u32 *mdr)
+
+ fail_read:
+ dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
+- return result;
++ return pcibios_err_to_errno(result);
+ }
+
+ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr)
+@@ -91,7 +91,7 @@ static int iosf_mbi_pci_write_mdr(u32 mcrx, u32 mcr, u32 mdr)
+
+ fail_write:
+ dev_err(&mbi_pdev->dev, "PCI config access failed with %d\n", result);
+- return result;
++ return pcibios_err_to_errno(result);
+ }
+
+ int iosf_mbi_read(u8 port, u8 opcode, u32 offset, u32 *mdr)
+diff --git a/arch/x86/um/sys_call_table_32.c b/arch/x86/um/sys_call_table_32.c
+index 89df5d89d6640..51655133eee36 100644
+--- a/arch/x86/um/sys_call_table_32.c
++++ b/arch/x86/um/sys_call_table_32.c
+@@ -9,6 +9,10 @@
+ #include <linux/cache.h>
+ #include <asm/syscall.h>
+
++extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
++ unsigned long, unsigned long,
++ unsigned long, unsigned long);
++
+ /*
+ * Below you can see, in terms of #define's, the differences between the x86-64
+ * and the UML syscall table.
+@@ -22,15 +26,13 @@
+ #define sys_vm86 sys_ni_syscall
+
+ #define __SYSCALL_WITH_COMPAT(nr, native, compat) __SYSCALL(nr, native)
++#define __SYSCALL_NORETURN __SYSCALL
+
+ #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+ #include <asm/syscalls_32.h>
++#undef __SYSCALL
+
+-#undef __SYSCALL
+ #define __SYSCALL(nr, sym) sym,
+-
+-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+-
+ const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
+ #include <asm/syscalls_32.h>
+ };
+diff --git a/arch/x86/um/sys_call_table_64.c b/arch/x86/um/sys_call_table_64.c
+index b0b4cfd2308c8..943d414f21093 100644
+--- a/arch/x86/um/sys_call_table_64.c
++++ b/arch/x86/um/sys_call_table_64.c
+@@ -9,6 +9,10 @@
+ #include <linux/cache.h>
+ #include <asm/syscall.h>
+
++extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long,
++ unsigned long, unsigned long,
++ unsigned long, unsigned long);
++
+ /*
+ * Below you can see, in terms of #define's, the differences between the x86-64
+ * and the UML syscall table.
+@@ -18,14 +22,13 @@
+ #define sys_iopl sys_ni_syscall
+ #define sys_ioperm sys_ni_syscall
+
++#define __SYSCALL_NORETURN __SYSCALL
++
+ #define __SYSCALL(nr, sym) extern asmlinkage long sym(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+ #include <asm/syscalls_64.h>
++#undef __SYSCALL
+
+-#undef __SYSCALL
+ #define __SYSCALL(nr, sym) sym,
+-
+-extern asmlinkage long sys_ni_syscall(unsigned long, unsigned long, unsigned long, unsigned long, unsigned long, unsigned long);
+-
+ const sys_call_ptr_t sys_call_table[] ____cacheline_aligned = {
+ #include <asm/syscalls_64.h>
+ };
+diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c
+index 0ae10535c6999..0ce17766c0e52 100644
+--- a/arch/x86/virt/svm/sev.c
++++ b/arch/x86/virt/svm/sev.c
+@@ -120,7 +120,7 @@ static __init void snp_enable(void *arg)
+
+ bool snp_probe_rmptable_info(void)
+ {
+- u64 max_rmp_pfn, calc_rmp_sz, rmp_sz, rmp_base, rmp_end;
++ u64 rmp_sz, rmp_base, rmp_end;
+
+ rdmsrl(MSR_AMD64_RMP_BASE, rmp_base);
+ rdmsrl(MSR_AMD64_RMP_END, rmp_end);
+@@ -137,28 +137,11 @@ bool snp_probe_rmptable_info(void)
+
+ rmp_sz = rmp_end - rmp_base + 1;
+
+- /*
+- * Calculate the amount the memory that must be reserved by the BIOS to
+- * address the whole RAM, including the bookkeeping area. The RMP itself
+- * must also be covered.
+- */
+- max_rmp_pfn = max_pfn;
+- if (PHYS_PFN(rmp_end) > max_pfn)
+- max_rmp_pfn = PHYS_PFN(rmp_end);
+-
+- calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
+-
+- if (calc_rmp_sz > rmp_sz) {
+- pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
+- calc_rmp_sz, rmp_sz);
+- return false;
+- }
+-
+ probed_rmp_base = rmp_base;
+ probed_rmp_size = rmp_sz;
+
+ pr_info("RMP table physical range [0x%016llx - 0x%016llx]\n",
+- probed_rmp_base, probed_rmp_base + probed_rmp_size - 1);
++ rmp_base, rmp_end);
+
+ return true;
+ }
+@@ -206,9 +189,8 @@ void __init snp_fixup_e820_tables(void)
+ */
+ static int __init snp_rmptable_init(void)
+ {
++ u64 max_rmp_pfn, calc_rmp_sz, rmptable_size, rmp_end, val;
+ void *rmptable_start;
+- u64 rmptable_size;
+- u64 val;
+
+ if (!cc_platform_has(CC_ATTR_HOST_SEV_SNP))
+ return 0;
+@@ -219,10 +201,28 @@ static int __init snp_rmptable_init(void)
+ if (!probed_rmp_size)
+ goto nosnp;
+
++ rmp_end = probed_rmp_base + probed_rmp_size - 1;
++
++ /*
++ * Calculate the amount the memory that must be reserved by the BIOS to
++ * address the whole RAM, including the bookkeeping area. The RMP itself
++ * must also be covered.
++ */
++ max_rmp_pfn = max_pfn;
++ if (PFN_UP(rmp_end) > max_pfn)
++ max_rmp_pfn = PFN_UP(rmp_end);
++
++ calc_rmp_sz = (max_rmp_pfn << 4) + RMPTABLE_CPU_BOOKKEEPING_SZ;
++ if (calc_rmp_sz > probed_rmp_size) {
++ pr_err("Memory reserved for the RMP table does not cover full system RAM (expected 0x%llx got 0x%llx)\n",
++ calc_rmp_sz, probed_rmp_size);
++ goto nosnp;
++ }
++
+ rmptable_start = memremap(probed_rmp_base, probed_rmp_size, MEMREMAP_WB);
+ if (!rmptable_start) {
+ pr_err("Failed to map RMP table\n");
+- return 1;
++ goto nosnp;
+ }
+
+ /*
+diff --git a/arch/x86/xen/p2m.c b/arch/x86/xen/p2m.c
+index 99918beccd80c..6bcbdf3b7999f 100644
+--- a/arch/x86/xen/p2m.c
++++ b/arch/x86/xen/p2m.c
+@@ -730,7 +730,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
+ * immediate unmapping.
+ */
+ map_ops[i].status = GNTST_general_error;
+- unmap[0].host_addr = map_ops[i].host_addr,
++ unmap[0].host_addr = map_ops[i].host_addr;
+ unmap[0].handle = map_ops[i].handle;
+ map_ops[i].handle = INVALID_GRANT_HANDLE;
+ if (map_ops[i].flags & GNTMAP_device_map)
+@@ -740,7 +740,7 @@ int set_foreign_p2m_mapping(struct gnttab_map_grant_ref *map_ops,
+
+ if (kmap_ops) {
+ kmap_ops[i].status = GNTST_general_error;
+- unmap[1].host_addr = kmap_ops[i].host_addr,
++ unmap[1].host_addr = kmap_ops[i].host_addr;
+ unmap[1].handle = kmap_ops[i].handle;
+ kmap_ops[i].handle = INVALID_GRANT_HANDLE;
+ if (kmap_ops[i].flags & GNTMAP_device_map)
+diff --git a/block/bio-integrity.c b/block/bio-integrity.c
+index 8b528e12136f5..741581a752c47 100644
+--- a/block/bio-integrity.c
++++ b/block/bio-integrity.c
+@@ -454,6 +454,7 @@ bool bio_integrity_prep(struct bio *bio)
+ unsigned long start, end;
+ unsigned int len, nr_pages;
+ unsigned int bytes, offset, i;
++ gfp_t gfp = GFP_NOIO;
+
+ if (!bi)
+ return true;
+@@ -476,11 +477,19 @@ bool bio_integrity_prep(struct bio *bio)
+ if (!bi->profile->generate_fn ||
+ !(bi->flags & BLK_INTEGRITY_GENERATE))
+ return true;
++
++ /*
++ * Zero the memory allocated to not leak uninitialized kernel
++ * memory to disk. For PI this only affects the app tag, but
++ * for non-integrity metadata it affects the entire metadata
++ * buffer.
++ */
++ gfp |= __GFP_ZERO;
+ }
+
+ /* Allocate kernel buffer for protection data */
+ len = bio_integrity_bytes(bi, bio_sectors(bio));
+- buf = kmalloc(len, GFP_NOIO);
++ buf = kmalloc(len, gfp);
+ if (unlikely(buf == NULL)) {
+ printk(KERN_ERR "could not allocate integrity buffer\n");
+ goto err_end_io;
+diff --git a/block/blk-mq.c b/block/blk-mq.c
+index 3b4df8e5ac9e5..1c85a5c79ee63 100644
+--- a/block/blk-mq.c
++++ b/block/blk-mq.c
+@@ -448,6 +448,10 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
+ if (data->cmd_flags & REQ_NOWAIT)
+ data->flags |= BLK_MQ_REQ_NOWAIT;
+
++retry:
++ data->ctx = blk_mq_get_ctx(q);
++ data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
++
+ if (q->elevator) {
+ /*
+ * All requests use scheduler tags when an I/O scheduler is
+@@ -469,13 +473,9 @@ static struct request *__blk_mq_alloc_requests(struct blk_mq_alloc_data *data)
+ if (ops->limit_depth)
+ ops->limit_depth(data->cmd_flags, data);
+ }
+- }
+-
+-retry:
+- data->ctx = blk_mq_get_ctx(q);
+- data->hctx = blk_mq_map_queue(q, data->cmd_flags, data->ctx);
+- if (!(data->rq_flags & RQF_SCHED_TAGS))
++ } else {
+ blk_mq_tag_busy(data->hctx);
++ }
+
+ if (data->flags & BLK_MQ_REQ_RESERVED)
+ data->rq_flags |= RQF_RESV;
+@@ -2914,6 +2914,17 @@ static void blk_mq_use_cached_rq(struct request *rq, struct blk_plug *plug,
+ INIT_LIST_HEAD(&rq->queuelist);
+ }
+
++static bool bio_unaligned(const struct bio *bio, struct request_queue *q)
++{
++ unsigned int bs_mask = queue_logical_block_size(q) - 1;
++
++ /* .bi_sector of any zero sized bio need to be initialized */
++ if ((bio->bi_iter.bi_size & bs_mask) ||
++ ((bio->bi_iter.bi_sector << SECTOR_SHIFT) & bs_mask))
++ return true;
++ return false;
++}
++
+ /**
+ * blk_mq_submit_bio - Create and send a request to block device.
+ * @bio: Bio pointer.
+@@ -2966,6 +2977,15 @@ void blk_mq_submit_bio(struct bio *bio)
+ return;
+ }
+
++ /*
++ * Device reconfiguration may change logical block size, so alignment
++ * check has to be done with queue usage counter held
++ */
++ if (unlikely(bio_unaligned(bio, q))) {
++ bio_io_error(bio);
++ goto queue_exit;
++ }
++
+ if (unlikely(bio_may_exceed_limits(bio, &q->limits))) {
+ bio = __bio_split_to_limits(bio, &q->limits, &nr_segs);
+ if (!bio)
+diff --git a/block/genhd.c b/block/genhd.c
+index 8f1f3c6b4d672..c5fca3e893a06 100644
+--- a/block/genhd.c
++++ b/block/genhd.c
+@@ -663,12 +663,12 @@ void del_gendisk(struct gendisk *disk)
+ */
+ if (!test_bit(GD_DEAD, &disk->state))
+ blk_report_disk_dead(disk, false);
+- __blk_mark_disk_dead(disk);
+
+ /*
+ * Drop all partitions now that the disk is marked dead.
+ */
+ mutex_lock(&disk->open_mutex);
++ __blk_mark_disk_dead(disk);
+ xa_for_each_start(&disk->part_tbl, idx, part, 1)
+ drop_partition(part);
+ mutex_unlock(&disk->open_mutex);
+diff --git a/block/mq-deadline.c b/block/mq-deadline.c
+index 94eede4fb9ebe..acdc28756d9d7 100644
+--- a/block/mq-deadline.c
++++ b/block/mq-deadline.c
+@@ -487,6 +487,20 @@ static struct request *dd_dispatch_request(struct blk_mq_hw_ctx *hctx)
+ return rq;
+ }
+
++/*
++ * 'depth' is a number in the range 1..INT_MAX representing a number of
++ * requests. Scale it with a factor (1 << bt->sb.shift) / q->nr_requests since
++ * 1..(1 << bt->sb.shift) is the range expected by sbitmap_get_shallow().
++ * Values larger than q->nr_requests have the same effect as q->nr_requests.
++ */
++static int dd_to_word_depth(struct blk_mq_hw_ctx *hctx, unsigned int qdepth)
++{
++ struct sbitmap_queue *bt = &hctx->sched_tags->bitmap_tags;
++ const unsigned int nrr = hctx->queue->nr_requests;
++
++ return ((qdepth << bt->sb.shift) + nrr - 1) / nrr;
++}
++
+ /*
+ * Called by __blk_mq_alloc_request(). The shallow_depth value set by this
+ * function is used by __blk_mq_get_tag().
+@@ -503,7 +517,7 @@ static void dd_limit_depth(blk_opf_t opf, struct blk_mq_alloc_data *data)
+ * Throttle asynchronous requests and writes such that these requests
+ * do not block the allocation of synchronous requests.
+ */
+- data->shallow_depth = dd->async_depth;
++ data->shallow_depth = dd_to_word_depth(data->hctx, dd->async_depth);
+ }
+
+ /* Called by blk_mq_update_nr_requests(). */
+@@ -513,9 +527,9 @@ static void dd_depth_updated(struct blk_mq_hw_ctx *hctx)
+ struct deadline_data *dd = q->elevator->elevator_data;
+ struct blk_mq_tags *tags = hctx->sched_tags;
+
+- dd->async_depth = max(1UL, 3 * q->nr_requests / 4);
++ dd->async_depth = q->nr_requests;
+
+- sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, dd->async_depth);
++ sbitmap_queue_min_shallow_depth(&tags->bitmap_tags, 1);
+ }
+
+ /* Called by blk_mq_init_hctx() and blk_mq_init_sched(). */
+diff --git a/drivers/android/binder.c b/drivers/android/binder.c
+index b21a7b246a0dc..2d0a24a565084 100644
+--- a/drivers/android/binder.c
++++ b/drivers/android/binder.c
+@@ -570,9 +570,7 @@ static bool binder_has_work(struct binder_thread *thread, bool do_proc_work)
+ static bool binder_available_for_proc_work_ilocked(struct binder_thread *thread)
+ {
+ return !thread->transaction_stack &&
+- binder_worklist_empty_ilocked(&thread->todo) &&
+- (thread->looper & (BINDER_LOOPER_STATE_ENTERED |
+- BINDER_LOOPER_STATE_REGISTERED));
++ binder_worklist_empty_ilocked(&thread->todo);
+ }
+
+ static void binder_wakeup_poll_threads_ilocked(struct binder_proc *proc,
+diff --git a/drivers/ata/libata-scsi.c b/drivers/ata/libata-scsi.c
+index bb4d30d377ae5..076fbeadce015 100644
+--- a/drivers/ata/libata-scsi.c
++++ b/drivers/ata/libata-scsi.c
+@@ -230,6 +230,80 @@ void ata_scsi_set_sense_information(struct ata_device *dev,
+ SCSI_SENSE_BUFFERSIZE, information);
+ }
+
++/**
++ * ata_scsi_set_passthru_sense_fields - Set ATA fields in sense buffer
++ * @qc: ATA PASS-THROUGH command.
++ *
++ * Populates "ATA Status Return sense data descriptor" / "Fixed format
++ * sense data" with ATA taskfile fields.
++ *
++ * LOCKING:
++ * None.
++ */
++static void ata_scsi_set_passthru_sense_fields(struct ata_queued_cmd *qc)
++{
++ struct scsi_cmnd *cmd = qc->scsicmd;
++ struct ata_taskfile *tf = &qc->result_tf;
++ unsigned char *sb = cmd->sense_buffer;
++
++ if ((sb[0] & 0x7f) >= 0x72) {
++ unsigned char *desc;
++ u8 len;
++
++ /* descriptor format */
++ len = sb[7];
++ desc = (char *)scsi_sense_desc_find(sb, len + 8, 9);
++ if (!desc) {
++ if (SCSI_SENSE_BUFFERSIZE < len + 14)
++ return;
++ sb[7] = len + 14;
++ desc = sb + 8 + len;
++ }
++ desc[0] = 9;
++ desc[1] = 12;
++ /*
++ * Copy registers into sense buffer.
++ */
++ desc[2] = 0x00;
++ desc[3] = tf->error;
++ desc[5] = tf->nsect;
++ desc[7] = tf->lbal;
++ desc[9] = tf->lbam;
++ desc[11] = tf->lbah;
++ desc[12] = tf->device;
++ desc[13] = tf->status;
++
++ /*
++ * Fill in Extend bit, and the high order bytes
++ * if applicable.
++ */
++ if (tf->flags & ATA_TFLAG_LBA48) {
++ desc[2] |= 0x01;
++ desc[4] = tf->hob_nsect;
++ desc[6] = tf->hob_lbal;
++ desc[8] = tf->hob_lbam;
++ desc[10] = tf->hob_lbah;
++ }
++ } else {
++ /* Fixed sense format */
++ sb[0] |= 0x80;
++ sb[3] = tf->error;
++ sb[4] = tf->status;
++ sb[5] = tf->device;
++ sb[6] = tf->nsect;
++ if (tf->flags & ATA_TFLAG_LBA48) {
++ sb[8] |= 0x80;
++ if (tf->hob_nsect)
++ sb[8] |= 0x40;
++ if (tf->hob_lbal || tf->hob_lbam || tf->hob_lbah)
++ sb[8] |= 0x20;
++ }
++ sb[9] = tf->lbal;
++ sb[10] = tf->lbam;
++ sb[11] = tf->lbah;
++ }
++}
++
+ static void ata_scsi_set_invalid_field(struct ata_device *dev,
+ struct scsi_cmnd *cmd, u16 field, u8 bit)
+ {
+@@ -837,10 +911,8 @@ static void ata_to_sense_error(unsigned id, u8 drv_stat, u8 drv_err, u8 *sk,
+ * ata_gen_passthru_sense - Generate check condition sense block.
+ * @qc: Command that completed.
+ *
+- * This function is specific to the ATA descriptor format sense
+- * block specified for the ATA pass through commands. Regardless
+- * of whether the command errored or not, return a sense
+- * block. Copy all controller registers into the sense
++ * This function is specific to the ATA pass through commands.
++ * Regardless of whether the command errored or not, return a sense
+ * block. If there was no error, we get the request from an ATA
+ * passthrough command, so we use the following sense data:
+ * sk = RECOVERED ERROR
+@@ -855,7 +927,6 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc)
+ struct scsi_cmnd *cmd = qc->scsicmd;
+ struct ata_taskfile *tf = &qc->result_tf;
+ unsigned char *sb = cmd->sense_buffer;
+- unsigned char *desc = sb + 8;
+ u8 sense_key, asc, ascq;
+
+ memset(sb, 0, SCSI_SENSE_BUFFERSIZE);
+@@ -870,67 +941,8 @@ static void ata_gen_passthru_sense(struct ata_queued_cmd *qc)
+ &sense_key, &asc, &ascq);
+ ata_scsi_set_sense(qc->dev, cmd, sense_key, asc, ascq);
+ } else {
+- /*
+- * ATA PASS-THROUGH INFORMATION AVAILABLE
+- * Always in descriptor format sense.
+- */
+- scsi_build_sense(cmd, 1, RECOVERED_ERROR, 0, 0x1D);
+- }
+-
+- if ((cmd->sense_buffer[0] & 0x7f) >= 0x72) {
+- u8 len;
+-
+- /* descriptor format */
+- len = sb[7];
+- desc = (char *)scsi_sense_desc_find(sb, len + 8, 9);
+- if (!desc) {
+- if (SCSI_SENSE_BUFFERSIZE < len + 14)
+- return;
+- sb[7] = len + 14;
+- desc = sb + 8 + len;
+- }
+- desc[0] = 9;
+- desc[1] = 12;
+- /*
+- * Copy registers into sense buffer.
+- */
+- desc[2] = 0x00;
+- desc[3] = tf->error;
+- desc[5] = tf->nsect;
+- desc[7] = tf->lbal;
+- desc[9] = tf->lbam;
+- desc[11] = tf->lbah;
+- desc[12] = tf->device;
+- desc[13] = tf->status;
+-
+- /*
+- * Fill in Extend bit, and the high order bytes
+- * if applicable.
+- */
+- if (tf->flags & ATA_TFLAG_LBA48) {
+- desc[2] |= 0x01;
+- desc[4] = tf->hob_nsect;
+- desc[6] = tf->hob_lbal;
+- desc[8] = tf->hob_lbam;
+- desc[10] = tf->hob_lbah;
+- }
+- } else {
+- /* Fixed sense format */
+- desc[0] = tf->error;
+- desc[1] = tf->status;
+- desc[2] = tf->device;
+- desc[3] = tf->nsect;
+- desc[7] = 0;
+- if (tf->flags & ATA_TFLAG_LBA48) {
+- desc[8] |= 0x80;
+- if (tf->hob_nsect)
+- desc[8] |= 0x40;
+- if (tf->hob_lbal || tf->hob_lbam || tf->hob_lbah)
+- desc[8] |= 0x20;
+- }
+- desc[9] = tf->lbal;
+- desc[10] = tf->lbam;
+- desc[11] = tf->lbah;
++ /* ATA PASS-THROUGH INFORMATION AVAILABLE */
++ ata_scsi_set_sense(qc->dev, cmd, RECOVERED_ERROR, 0, 0x1D);
+ }
+ }
+
+@@ -1632,26 +1644,32 @@ static void ata_scsi_qc_complete(struct ata_queued_cmd *qc)
+ {
+ struct scsi_cmnd *cmd = qc->scsicmd;
+ u8 *cdb = cmd->cmnd;
+- int need_sense = (qc->err_mask != 0) &&
+- !(qc->flags & ATA_QCFLAG_SENSE_VALID);
++ bool have_sense = qc->flags & ATA_QCFLAG_SENSE_VALID;
++ bool is_ata_passthru = cdb[0] == ATA_16 || cdb[0] == ATA_12;
++ bool is_ck_cond_request = cdb[2] & 0x20;
++ bool is_error = qc->err_mask != 0;
+
+ /* For ATA pass thru (SAT) commands, generate a sense block if
+ * user mandated it or if there's an error. Note that if we
+- * generate because the user forced us to [CK_COND =1], a check
++ * generate because the user forced us to [CK_COND=1], a check
+ * condition is generated and the ATA register values are returned
+ * whether the command completed successfully or not. If there
+- * was no error, we use the following sense data:
++ * was no error, and CK_COND=1, we use the following sense data:
+ * sk = RECOVERED ERROR
+ * asc,ascq = ATA PASS-THROUGH INFORMATION AVAILABLE
+ */
+- if (((cdb[0] == ATA_16) || (cdb[0] == ATA_12)) &&
+- ((cdb[2] & 0x20) || need_sense))
+- ata_gen_passthru_sense(qc);
+- else if (need_sense)
++ if (is_ata_passthru && (is_ck_cond_request || is_error || have_sense)) {
++ if (!have_sense)
++ ata_gen_passthru_sense(qc);
++ ata_scsi_set_passthru_sense_fields(qc);
++ if (is_ck_cond_request)
++ set_status_byte(qc->scsicmd, SAM_STAT_CHECK_CONDITION);
++ } else if (is_error && !have_sense) {
+ ata_gen_ata_sense(qc);
+- else
++ } else {
+ /* Keep the SCSI ML and status byte, clear host byte. */
+ cmd->result &= 0x0000ffff;
++ }
+
+ ata_qc_done(qc);
+ }
+@@ -2590,14 +2608,8 @@ static void atapi_qc_complete(struct ata_queued_cmd *qc)
+ /* handle completion from EH */
+ if (unlikely(err_mask || qc->flags & ATA_QCFLAG_SENSE_VALID)) {
+
+- if (!(qc->flags & ATA_QCFLAG_SENSE_VALID)) {
+- /* FIXME: not quite right; we don't want the
+- * translation of taskfile registers into a
+- * sense descriptors, since that's only
+- * correct for ATA, not ATAPI
+- */
++ if (!(qc->flags & ATA_QCFLAG_SENSE_VALID))
+ ata_gen_passthru_sense(qc);
+- }
+
+ /* SCSI EH automatically locks door if sdev->locked is
+ * set. Sometimes door lock request continues to
+diff --git a/drivers/auxdisplay/ht16k33.c b/drivers/auxdisplay/ht16k33.c
+index ce987944662c8..8a7034b41d50e 100644
+--- a/drivers/auxdisplay/ht16k33.c
++++ b/drivers/auxdisplay/ht16k33.c
+@@ -483,6 +483,7 @@ static int ht16k33_led_probe(struct device *dev, struct led_classdev *led,
+ led->max_brightness = MAX_BRIGHTNESS;
+
+ err = devm_led_classdev_register_ext(dev, led, &init_data);
++ fwnode_handle_put(init_data.fwnode);
+ if (err)
+ dev_err(dev, "Failed to register LED\n");
+
+diff --git a/drivers/base/devres.c b/drivers/base/devres.c
+index 3df0025d12aa4..8d709dbd4e0c1 100644
+--- a/drivers/base/devres.c
++++ b/drivers/base/devres.c
+@@ -896,9 +896,12 @@ void *devm_krealloc(struct device *dev, void *ptr, size_t new_size, gfp_t gfp)
+ /*
+ * Otherwise: allocate new, larger chunk. We need to allocate before
+ * taking the lock as most probably the caller uses GFP_KERNEL.
++ * alloc_dr() will call check_dr_size() to reserve extra memory
++ * for struct devres automatically, so size @new_size user request
++ * is delivered to it directly as devm_kmalloc() does.
+ */
+ new_dr = alloc_dr(devm_kmalloc_release,
+- total_new_size, gfp, dev_to_node(dev));
++ new_size, gfp, dev_to_node(dev));
+ if (!new_dr)
+ return NULL;
+
+@@ -1222,7 +1225,11 @@ EXPORT_SYMBOL_GPL(__devm_alloc_percpu);
+ */
+ void devm_free_percpu(struct device *dev, void __percpu *pdata)
+ {
+- WARN_ON(devres_destroy(dev, devm_percpu_release, devm_percpu_match,
++ /*
++ * Use devres_release() to prevent memory leakage as
++ * devm_free_pages() does.
++ */
++ WARN_ON(devres_release(dev, devm_percpu_release, devm_percpu_match,
+ (__force void *)pdata));
+ }
+ EXPORT_SYMBOL_GPL(devm_free_percpu);
+diff --git a/drivers/block/null_blk/main.c b/drivers/block/null_blk/main.c
+index 75f189e42f885..f940580193526 100644
+--- a/drivers/block/null_blk/main.c
++++ b/drivers/block/null_blk/main.c
+@@ -227,7 +227,7 @@ MODULE_PARM_DESC(mbps, "Cache size in MiB for memory-backed device. Default: 0 (
+
+ static bool g_fua = true;
+ module_param_named(fua, g_fua, bool, 0444);
+-MODULE_PARM_DESC(zoned, "Enable/disable FUA support when cache_size is used. Default: true");
++MODULE_PARM_DESC(fua, "Enable/disable FUA support when cache_size is used. Default: true");
+
+ static unsigned int g_mbps;
+ module_param_named(mbps, g_mbps, uint, 0444);
+diff --git a/drivers/block/rbd.c b/drivers/block/rbd.c
+index 26ff5cd2bf0ab..da22ce38c0390 100644
+--- a/drivers/block/rbd.c
++++ b/drivers/block/rbd.c
+@@ -362,7 +362,7 @@ enum rbd_watch_state {
+ enum rbd_lock_state {
+ RBD_LOCK_STATE_UNLOCKED,
+ RBD_LOCK_STATE_LOCKED,
+- RBD_LOCK_STATE_RELEASING,
++ RBD_LOCK_STATE_QUIESCING,
+ };
+
+ /* WatchNotify::ClientId */
+@@ -422,7 +422,7 @@ struct rbd_device {
+ struct list_head running_list;
+ struct completion acquire_wait;
+ int acquire_err;
+- struct completion releasing_wait;
++ struct completion quiescing_wait;
+
+ spinlock_t object_map_lock;
+ u8 *object_map;
+@@ -525,7 +525,7 @@ static bool __rbd_is_lock_owner(struct rbd_device *rbd_dev)
+ lockdep_assert_held(&rbd_dev->lock_rwsem);
+
+ return rbd_dev->lock_state == RBD_LOCK_STATE_LOCKED ||
+- rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING;
++ rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING;
+ }
+
+ static bool rbd_is_lock_owner(struct rbd_device *rbd_dev)
+@@ -3457,13 +3457,14 @@ static void rbd_lock_del_request(struct rbd_img_request *img_req)
+ lockdep_assert_held(&rbd_dev->lock_rwsem);
+ spin_lock(&rbd_dev->lock_lists_lock);
+ if (!list_empty(&img_req->lock_item)) {
++ rbd_assert(!list_empty(&rbd_dev->running_list));
+ list_del_init(&img_req->lock_item);
+- need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_RELEASING &&
++ need_wakeup = (rbd_dev->lock_state == RBD_LOCK_STATE_QUIESCING &&
+ list_empty(&rbd_dev->running_list));
+ }
+ spin_unlock(&rbd_dev->lock_lists_lock);
+ if (need_wakeup)
+- complete(&rbd_dev->releasing_wait);
++ complete(&rbd_dev->quiescing_wait);
+ }
+
+ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
+@@ -3476,11 +3477,6 @@ static int rbd_img_exclusive_lock(struct rbd_img_request *img_req)
+ if (rbd_lock_add_request(img_req))
+ return 1;
+
+- if (rbd_dev->opts->exclusive) {
+- WARN_ON(1); /* lock got released? */
+- return -EROFS;
+- }
+-
+ /*
+ * Note the use of mod_delayed_work() in rbd_acquire_lock()
+ * and cancel_delayed_work() in wake_lock_waiters().
+@@ -4181,16 +4177,16 @@ static bool rbd_quiesce_lock(struct rbd_device *rbd_dev)
+ /*
+ * Ensure that all in-flight IO is flushed.
+ */
+- rbd_dev->lock_state = RBD_LOCK_STATE_RELEASING;
+- rbd_assert(!completion_done(&rbd_dev->releasing_wait));
++ rbd_dev->lock_state = RBD_LOCK_STATE_QUIESCING;
++ rbd_assert(!completion_done(&rbd_dev->quiescing_wait));
+ if (list_empty(&rbd_dev->running_list))
+ return true;
+
+ up_write(&rbd_dev->lock_rwsem);
+- wait_for_completion(&rbd_dev->releasing_wait);
++ wait_for_completion(&rbd_dev->quiescing_wait);
+
+ down_write(&rbd_dev->lock_rwsem);
+- if (rbd_dev->lock_state != RBD_LOCK_STATE_RELEASING)
++ if (rbd_dev->lock_state != RBD_LOCK_STATE_QUIESCING)
+ return false;
+
+ rbd_assert(list_empty(&rbd_dev->running_list));
+@@ -4601,6 +4597,10 @@ static void rbd_reacquire_lock(struct rbd_device *rbd_dev)
+ rbd_warn(rbd_dev, "failed to update lock cookie: %d",
+ ret);
+
++ if (rbd_dev->opts->exclusive)
++ rbd_warn(rbd_dev,
++ "temporarily releasing lock on exclusive mapping");
++
+ /*
+ * Lock cookie cannot be updated on older OSDs, so do
+ * a manual release and queue an acquire.
+@@ -5383,7 +5383,7 @@ static struct rbd_device *__rbd_dev_create(struct rbd_spec *spec)
+ INIT_LIST_HEAD(&rbd_dev->acquiring_list);
+ INIT_LIST_HEAD(&rbd_dev->running_list);
+ init_completion(&rbd_dev->acquire_wait);
+- init_completion(&rbd_dev->releasing_wait);
++ init_completion(&rbd_dev->quiescing_wait);
+
+ spin_lock_init(&rbd_dev->object_map_lock);
+
+@@ -6589,11 +6589,6 @@ static int rbd_add_acquire_lock(struct rbd_device *rbd_dev)
+ if (ret)
+ return ret;
+
+- /*
+- * The lock may have been released by now, unless automatic lock
+- * transitions are disabled.
+- */
+- rbd_assert(!rbd_dev->opts->exclusive || rbd_is_lock_owner(rbd_dev));
+ return 0;
+ }
+
+diff --git a/drivers/block/ublk_drv.c b/drivers/block/ublk_drv.c
+index 4e159948c912c..3b58839321333 100644
+--- a/drivers/block/ublk_drv.c
++++ b/drivers/block/ublk_drv.c
+@@ -48,6 +48,9 @@
+
+ #define UBLK_MINORS (1U << MINORBITS)
+
++/* private ioctl command mirror */
++#define UBLK_CMD_DEL_DEV_ASYNC _IOC_NR(UBLK_U_CMD_DEL_DEV_ASYNC)
++
+ /* All UBLK_F_* have to be included into UBLK_F_ALL */
+ #define UBLK_F_ALL (UBLK_F_SUPPORT_ZERO_COPY \
+ | UBLK_F_URING_CMD_COMP_IN_TASK \
+@@ -2904,7 +2907,7 @@ static int ublk_ctrl_uring_cmd(struct io_uring_cmd *cmd,
+ case UBLK_CMD_DEL_DEV:
+ ret = ublk_ctrl_del_dev(&ub, true);
+ break;
+- case UBLK_U_CMD_DEL_DEV_ASYNC:
++ case UBLK_CMD_DEL_DEV_ASYNC:
+ ret = ublk_ctrl_del_dev(&ub, false);
+ break;
+ case UBLK_CMD_GET_QUEUE_AFFINITY:
+diff --git a/drivers/block/xen-blkfront.c b/drivers/block/xen-blkfront.c
+index fd7c0ff2139ce..67aa63dabcff1 100644
+--- a/drivers/block/xen-blkfront.c
++++ b/drivers/block/xen-blkfront.c
+@@ -1063,8 +1063,7 @@ static char *encode_disk_name(char *ptr, unsigned int n)
+ }
+
+ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
+- struct blkfront_info *info, u16 sector_size,
+- unsigned int physical_sector_size)
++ struct blkfront_info *info)
+ {
+ struct queue_limits lim = {};
+ struct gendisk *gd;
+@@ -1159,8 +1158,6 @@ static int xlvbd_alloc_gendisk(blkif_sector_t capacity,
+
+ info->rq = gd->queue;
+ info->gd = gd;
+- info->sector_size = sector_size;
+- info->physical_sector_size = physical_sector_size;
+
+ xlvbd_flush(info);
+
+@@ -2315,8 +2312,6 @@ static void blkfront_gather_backend_features(struct blkfront_info *info)
+ static void blkfront_connect(struct blkfront_info *info)
+ {
+ unsigned long long sectors;
+- unsigned long sector_size;
+- unsigned int physical_sector_size;
+ int err, i;
+ struct blkfront_ring_info *rinfo;
+
+@@ -2355,7 +2350,7 @@ static void blkfront_connect(struct blkfront_info *info)
+ err = xenbus_gather(XBT_NIL, info->xbdev->otherend,
+ "sectors", "%llu", §ors,
+ "info", "%u", &info->vdisk_info,
+- "sector-size", "%lu", §or_size,
++ "sector-size", "%lu", &info->sector_size,
+ NULL);
+ if (err) {
+ xenbus_dev_fatal(info->xbdev, err,
+@@ -2369,9 +2364,9 @@ static void blkfront_connect(struct blkfront_info *info)
+ * provide this. Assume physical sector size to be the same as
+ * sector_size in that case.
+ */
+- physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend,
++ info->physical_sector_size = xenbus_read_unsigned(info->xbdev->otherend,
+ "physical-sector-size",
+- sector_size);
++ info->sector_size);
+ blkfront_gather_backend_features(info);
+ for_each_rinfo(info, rinfo, i) {
+ err = blkfront_setup_indirect(rinfo);
+@@ -2383,8 +2378,7 @@ static void blkfront_connect(struct blkfront_info *info)
+ }
+ }
+
+- err = xlvbd_alloc_gendisk(sectors, info, sector_size,
+- physical_sector_size);
++ err = xlvbd_alloc_gendisk(sectors, info);
+ if (err) {
+ xenbus_dev_fatal(info->xbdev, err, "xlvbd_add at %s",
+ info->xbdev->otherend);
+diff --git a/drivers/bluetooth/btintel.c b/drivers/bluetooth/btintel.c
+index 0c855c3ee1c1c..7ecc67deecb09 100644
+--- a/drivers/bluetooth/btintel.c
++++ b/drivers/bluetooth/btintel.c
+@@ -26,21 +26,11 @@
+ #define ECDSA_OFFSET 644
+ #define ECDSA_HEADER_LEN 320
+
+-#define BTINTEL_PPAG_NAME "PPAG"
+-
+ enum {
+ DSM_SET_WDISABLE2_DELAY = 1,
+ DSM_SET_RESET_METHOD = 3,
+ };
+
+-/* structure to store the PPAG data read from ACPI table */
+-struct btintel_ppag {
+- u32 domain;
+- u32 mode;
+- acpi_status status;
+- struct hci_dev *hdev;
+-};
+-
+ #define CMD_WRITE_BOOT_PARAMS 0xfc0e
+ struct cmd_write_boot_params {
+ __le32 boot_addr;
+@@ -1324,65 +1314,6 @@ static int btintel_read_debug_features(struct hci_dev *hdev,
+ return 0;
+ }
+
+-static acpi_status btintel_ppag_callback(acpi_handle handle, u32 lvl, void *data,
+- void **ret)
+-{
+- acpi_status status;
+- size_t len;
+- struct btintel_ppag *ppag = data;
+- union acpi_object *p, *elements;
+- struct acpi_buffer string = {ACPI_ALLOCATE_BUFFER, NULL};
+- struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
+- struct hci_dev *hdev = ppag->hdev;
+-
+- status = acpi_get_name(handle, ACPI_FULL_PATHNAME, &string);
+- if (ACPI_FAILURE(status)) {
+- bt_dev_warn(hdev, "PPAG-BT: ACPI Failure: %s", acpi_format_exception(status));
+- return status;
+- }
+-
+- len = strlen(string.pointer);
+- if (len < strlen(BTINTEL_PPAG_NAME)) {
+- kfree(string.pointer);
+- return AE_OK;
+- }
+-
+- if (strncmp((char *)string.pointer + len - 4, BTINTEL_PPAG_NAME, 4)) {
+- kfree(string.pointer);
+- return AE_OK;
+- }
+- kfree(string.pointer);
+-
+- status = acpi_evaluate_object(handle, NULL, NULL, &buffer);
+- if (ACPI_FAILURE(status)) {
+- ppag->status = status;
+- bt_dev_warn(hdev, "PPAG-BT: ACPI Failure: %s", acpi_format_exception(status));
+- return status;
+- }
+-
+- p = buffer.pointer;
+- ppag = (struct btintel_ppag *)data;
+-
+- if (p->type != ACPI_TYPE_PACKAGE || p->package.count != 2) {
+- kfree(buffer.pointer);
+- bt_dev_warn(hdev, "PPAG-BT: Invalid object type: %d or package count: %d",
+- p->type, p->package.count);
+- ppag->status = AE_ERROR;
+- return AE_ERROR;
+- }
+-
+- elements = p->package.elements;
+-
+- /* PPAG table is located at element[1] */
+- p = &elements[1];
+-
+- ppag->domain = (u32)p->package.elements[0].integer.value;
+- ppag->mode = (u32)p->package.elements[1].integer.value;
+- ppag->status = AE_OK;
+- kfree(buffer.pointer);
+- return AE_CTRL_TERMINATE;
+-}
+-
+ static int btintel_set_debug_features(struct hci_dev *hdev,
+ const struct intel_debug_features *features)
+ {
+@@ -2427,10 +2358,13 @@ static int btintel_configure_offload(struct hci_dev *hdev)
+
+ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver)
+ {
+- struct btintel_ppag ppag;
+ struct sk_buff *skb;
+ struct hci_ppag_enable_cmd ppag_cmd;
+ acpi_handle handle;
++ struct acpi_buffer buffer = {ACPI_ALLOCATE_BUFFER, NULL};
++ union acpi_object *p, *elements;
++ u32 domain, mode;
++ acpi_status status;
+
+ /* PPAG is not supported if CRF is HrP2, Jfp2, JfP1 */
+ switch (ver->cnvr_top & 0xFFF) {
+@@ -2448,22 +2382,34 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver
+ return;
+ }
+
+- memset(&ppag, 0, sizeof(ppag));
+-
+- ppag.hdev = hdev;
+- ppag.status = AE_NOT_FOUND;
+- acpi_walk_namespace(ACPI_TYPE_PACKAGE, handle, 1, NULL,
+- btintel_ppag_callback, &ppag, NULL);
+-
+- if (ACPI_FAILURE(ppag.status)) {
+- if (ppag.status == AE_NOT_FOUND) {
++ status = acpi_evaluate_object(handle, "PPAG", NULL, &buffer);
++ if (ACPI_FAILURE(status)) {
++ if (status == AE_NOT_FOUND) {
+ bt_dev_dbg(hdev, "PPAG-BT: ACPI entry not found");
+ return;
+ }
++ bt_dev_warn(hdev, "PPAG-BT: ACPI Failure: %s", acpi_format_exception(status));
++ return;
++ }
++
++ p = buffer.pointer;
++ if (p->type != ACPI_TYPE_PACKAGE || p->package.count != 2) {
++ bt_dev_warn(hdev, "PPAG-BT: Invalid object type: %d or package count: %d",
++ p->type, p->package.count);
++ kfree(buffer.pointer);
+ return;
+ }
+
+- if (ppag.domain != 0x12) {
++ elements = p->package.elements;
++
++ /* PPAG table is located at element[1] */
++ p = &elements[1];
++
++ domain = (u32)p->package.elements[0].integer.value;
++ mode = (u32)p->package.elements[1].integer.value;
++ kfree(buffer.pointer);
++
++ if (domain != 0x12) {
+ bt_dev_dbg(hdev, "PPAG-BT: Bluetooth domain is disabled in ACPI firmware");
+ return;
+ }
+@@ -2474,19 +2420,22 @@ static void btintel_set_ppag(struct hci_dev *hdev, struct intel_version_tlv *ver
+ * BIT 1 : 0 Disabled in China
+ * 1 Enabled in China
+ */
+- if ((ppag.mode & 0x01) != BIT(0) && (ppag.mode & 0x02) != BIT(1)) {
+- bt_dev_dbg(hdev, "PPAG-BT: EU, China mode are disabled in CB/BIOS");
++ mode &= 0x03;
++
++ if (!mode) {
++ bt_dev_dbg(hdev, "PPAG-BT: EU, China mode are disabled in BIOS");
+ return;
+ }
+
+- ppag_cmd.ppag_enable_flags = cpu_to_le32(ppag.mode);
++ ppag_cmd.ppag_enable_flags = cpu_to_le32(mode);
+
+- skb = __hci_cmd_sync(hdev, INTEL_OP_PPAG_CMD, sizeof(ppag_cmd), &ppag_cmd, HCI_CMD_TIMEOUT);
++ skb = __hci_cmd_sync(hdev, INTEL_OP_PPAG_CMD, sizeof(ppag_cmd),
++ &ppag_cmd, HCI_CMD_TIMEOUT);
+ if (IS_ERR(skb)) {
+ bt_dev_warn(hdev, "Failed to send PPAG Enable (%ld)", PTR_ERR(skb));
+ return;
+ }
+- bt_dev_info(hdev, "PPAG-BT: Enabled (Mode %d)", ppag.mode);
++ bt_dev_info(hdev, "PPAG-BT: Enabled (Mode %d)", mode);
+ kfree_skb(skb);
+ }
+
+diff --git a/drivers/bluetooth/btintel_pcie.c b/drivers/bluetooth/btintel_pcie.c
+index dd3c0626c72d8..b8120b98a2395 100644
+--- a/drivers/bluetooth/btintel_pcie.c
++++ b/drivers/bluetooth/btintel_pcie.c
+@@ -1327,6 +1327,12 @@ static void btintel_pcie_remove(struct pci_dev *pdev)
+ data = pci_get_drvdata(pdev);
+
+ btintel_pcie_reset_bt(data);
++ for (int i = 0; i < data->alloc_vecs; i++) {
++ struct msix_entry *msix_entry;
++
++ msix_entry = &data->msix_entries[i];
++ free_irq(msix_entry->vector, msix_entry);
++ }
+
+ pci_free_irq_vectors(pdev);
+
+diff --git a/drivers/bluetooth/btnxpuart.c b/drivers/bluetooth/btnxpuart.c
+index 9bfa9a6ad56c8..6a863328b8053 100644
+--- a/drivers/bluetooth/btnxpuart.c
++++ b/drivers/bluetooth/btnxpuart.c
+@@ -187,6 +187,11 @@ struct btnxpuart_dev {
+ #define NXP_NAK_V3 0x7b
+ #define NXP_CRC_ERROR_V3 0x7c
+
++/* Bootloader signature error codes */
++#define NXP_ACK_RX_TIMEOUT 0x0002 /* ACK not received from host */
++#define NXP_HDR_RX_TIMEOUT 0x0003 /* FW Header chunk not received */
++#define NXP_DATA_RX_TIMEOUT 0x0004 /* FW Data chunk not received */
++
+ #define HDR_LEN 16
+
+ #define NXP_RECV_CHIP_VER_V1 \
+@@ -277,6 +282,17 @@ struct nxp_bootloader_cmd {
+ __be32 crc;
+ } __packed;
+
++struct nxp_v3_rx_timeout_nak {
++ u8 nak;
++ __le32 offset;
++ u8 crc;
++} __packed;
++
++union nxp_v3_rx_timeout_nak_u {
++ struct nxp_v3_rx_timeout_nak pkt;
++ u8 buf[6];
++};
++
+ static u8 crc8_table[CRC8_TABLE_SIZE];
+
+ /* Default configurations */
+@@ -899,6 +915,32 @@ static int nxp_recv_chip_ver_v3(struct hci_dev *hdev, struct sk_buff *skb)
+ return 0;
+ }
+
++static void nxp_handle_fw_download_error(struct hci_dev *hdev, struct v3_data_req *req)
++{
++ struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
++ __u32 offset = __le32_to_cpu(req->offset);
++ __u16 err = __le16_to_cpu(req->error);
++ union nxp_v3_rx_timeout_nak_u nak_tx_buf;
++
++ switch (err) {
++ case NXP_ACK_RX_TIMEOUT:
++ case NXP_HDR_RX_TIMEOUT:
++ case NXP_DATA_RX_TIMEOUT:
++ nak_tx_buf.pkt.nak = NXP_NAK_V3;
++ nak_tx_buf.pkt.offset = __cpu_to_le32(offset);
++ nak_tx_buf.pkt.crc = crc8(crc8_table, nak_tx_buf.buf,
++ sizeof(nak_tx_buf) - 1, 0xff);
++ serdev_device_write_buf(nxpdev->serdev, nak_tx_buf.buf,
++ sizeof(nak_tx_buf));
++ break;
++ default:
++ bt_dev_dbg(hdev, "Unknown bootloader error code: %d", err);
++ break;
++
++ }
++
++}
++
+ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
+ {
+ struct btnxpuart_dev *nxpdev = hci_get_drvdata(hdev);
+@@ -913,7 +955,12 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
+ if (!req || !nxpdev->fw)
+ goto free_skb;
+
+- nxp_send_ack(NXP_ACK_V3, hdev);
++ if (!req->error) {
++ nxp_send_ack(NXP_ACK_V3, hdev);
++ } else {
++ nxp_handle_fw_download_error(hdev, req);
++ goto free_skb;
++ }
+
+ len = __le16_to_cpu(req->len);
+
+@@ -940,9 +987,6 @@ static int nxp_recv_fw_req_v3(struct hci_dev *hdev, struct sk_buff *skb)
+ wake_up_interruptible(&nxpdev->fw_dnld_done_wait_q);
+ goto free_skb;
+ }
+- if (req->error)
+- bt_dev_dbg(hdev, "FW Download received err 0x%02x from chip",
+- req->error);
+
+ offset = __le32_to_cpu(req->offset);
+ if (offset < nxpdev->fw_v3_offset_correction) {
+diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c
+index e384ef6ff050d..789c492df6fa2 100644
+--- a/drivers/bluetooth/btusb.c
++++ b/drivers/bluetooth/btusb.c
+@@ -555,6 +555,10 @@ static const struct usb_device_id quirks_table[] = {
+ BTUSB_WIDEBAND_SPEECH },
+ { USB_DEVICE(0x13d3, 0x3572), .driver_info = BTUSB_REALTEK |
+ BTUSB_WIDEBAND_SPEECH },
++ { USB_DEVICE(0x13d3, 0x3591), .driver_info = BTUSB_REALTEK |
++ BTUSB_WIDEBAND_SPEECH },
++ { USB_DEVICE(0x0489, 0xe125), .driver_info = BTUSB_REALTEK |
++ BTUSB_WIDEBAND_SPEECH },
+
+ /* Realtek 8852BT/8852BE-VT Bluetooth devices */
+ { USB_DEVICE(0x0bda, 0x8520), .driver_info = BTUSB_REALTEK |
+diff --git a/drivers/bluetooth/hci_bcm4377.c b/drivers/bluetooth/hci_bcm4377.c
+index d90858ea2fe59..a77a30fdc630e 100644
+--- a/drivers/bluetooth/hci_bcm4377.c
++++ b/drivers/bluetooth/hci_bcm4377.c
+@@ -32,7 +32,7 @@ enum bcm4377_chip {
+ #define BCM4378_DEVICE_ID 0x5f69
+ #define BCM4387_DEVICE_ID 0x5f71
+
+-#define BCM4377_TIMEOUT 1000
++#define BCM4377_TIMEOUT msecs_to_jiffies(1000)
+
+ /*
+ * These devices only support DMA transactions inside a 32bit window
+diff --git a/drivers/bus/mhi/ep/main.c b/drivers/bus/mhi/ep/main.c
+index f8f674adf1d40..4acfac73ca9ac 100644
+--- a/drivers/bus/mhi/ep/main.c
++++ b/drivers/bus/mhi/ep/main.c
+@@ -90,7 +90,7 @@ static int mhi_ep_send_completion_event(struct mhi_ep_cntrl *mhi_cntrl, struct m
+ struct mhi_ring_element *event;
+ int ret;
+
+- event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
++ event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL);
+ if (!event)
+ return -ENOMEM;
+
+@@ -109,7 +109,7 @@ int mhi_ep_send_state_change_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_stat
+ struct mhi_ring_element *event;
+ int ret;
+
+- event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
++ event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL);
+ if (!event)
+ return -ENOMEM;
+
+@@ -127,7 +127,7 @@ int mhi_ep_send_ee_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_ee_type exec_e
+ struct mhi_ring_element *event;
+ int ret;
+
+- event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
++ event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL);
+ if (!event)
+ return -ENOMEM;
+
+@@ -146,7 +146,7 @@ static int mhi_ep_send_cmd_comp_event(struct mhi_ep_cntrl *mhi_cntrl, enum mhi_e
+ struct mhi_ring_element *event;
+ int ret;
+
+- event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL | GFP_DMA);
++ event = kmem_cache_zalloc(mhi_cntrl->ev_ring_el_cache, GFP_KERNEL);
+ if (!event)
+ return -ENOMEM;
+
+@@ -438,7 +438,7 @@ static int mhi_ep_read_channel(struct mhi_ep_cntrl *mhi_cntrl,
+ read_offset = mhi_chan->tre_size - mhi_chan->tre_bytes_left;
+ write_offset = len - buf_left;
+
+- buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL | GFP_DMA);
++ buf_addr = kmem_cache_zalloc(mhi_cntrl->tre_buf_cache, GFP_KERNEL);
+ if (!buf_addr)
+ return -ENOMEM;
+
+@@ -1481,14 +1481,14 @@ int mhi_ep_register_controller(struct mhi_ep_cntrl *mhi_cntrl,
+
+ mhi_cntrl->ev_ring_el_cache = kmem_cache_create("mhi_ep_event_ring_el",
+ sizeof(struct mhi_ring_element), 0,
+- SLAB_CACHE_DMA, NULL);
++ 0, NULL);
+ if (!mhi_cntrl->ev_ring_el_cache) {
+ ret = -ENOMEM;
+ goto err_free_cmd;
+ }
+
+ mhi_cntrl->tre_buf_cache = kmem_cache_create("mhi_ep_tre_buf", MHI_EP_DEFAULT_MTU, 0,
+- SLAB_CACHE_DMA, NULL);
++ 0, NULL);
+ if (!mhi_cntrl->tre_buf_cache) {
+ ret = -ENOMEM;
+ goto err_destroy_ev_ring_el_cache;
+diff --git a/drivers/char/hw_random/amd-rng.c b/drivers/char/hw_random/amd-rng.c
+index 86162a13681e6..9a24d19236dc7 100644
+--- a/drivers/char/hw_random/amd-rng.c
++++ b/drivers/char/hw_random/amd-rng.c
+@@ -143,8 +143,10 @@ static int __init amd_rng_mod_init(void)
+
+ found:
+ err = pci_read_config_dword(pdev, 0x58, &pmbase);
+- if (err)
++ if (err) {
++ err = pcibios_err_to_errno(err);
+ goto put_dev;
++ }
+
+ pmbase &= 0x0000FF00;
+ if (pmbase == 0) {
+diff --git a/drivers/char/hw_random/core.c b/drivers/char/hw_random/core.c
+index 4084df65c9fa3..f6122a03ee37c 100644
+--- a/drivers/char/hw_random/core.c
++++ b/drivers/char/hw_random/core.c
+@@ -161,7 +161,6 @@ static int hwrng_init(struct hwrng *rng)
+ reinit_completion(&rng->cleanup_done);
+
+ skip_init:
+- rng->quality = min_t(u16, min_t(u16, default_quality, 1024), rng->quality ?: 1024);
+ current_quality = rng->quality; /* obsolete */
+
+ return 0;
+@@ -545,6 +544,9 @@ int hwrng_register(struct hwrng *rng)
+ complete(&rng->cleanup_done);
+ init_completion(&rng->dying);
+
++ /* Adjust quality field to always have a proper value */
++ rng->quality = min_t(u16, min_t(u16, default_quality, 1024), rng->quality ?: 1024);
++
+ if (!current_rng ||
+ (!cur_rng_set_by_user && rng->quality > current_rng->quality)) {
+ /*
+diff --git a/drivers/char/ipmi/ssif_bmc.c b/drivers/char/ipmi/ssif_bmc.c
+index 56346fb328727..ab4e87a99f087 100644
+--- a/drivers/char/ipmi/ssif_bmc.c
++++ b/drivers/char/ipmi/ssif_bmc.c
+@@ -177,13 +177,15 @@ static ssize_t ssif_bmc_write(struct file *file, const char __user *buf, size_t
+ unsigned long flags;
+ ssize_t ret;
+
+- if (count > sizeof(struct ipmi_ssif_msg))
++ if (count < sizeof(msg.len) ||
++ count > sizeof(struct ipmi_ssif_msg))
+ return -EINVAL;
+
+ if (copy_from_user(&msg, buf, count))
+ return -EFAULT;
+
+- if (!msg.len || count < sizeof_field(struct ipmi_ssif_msg, len) + msg.len)
++ if (!msg.len || msg.len > IPMI_SSIF_PAYLOAD_MAX ||
++ count < sizeof_field(struct ipmi_ssif_msg, len) + msg.len)
+ return -EINVAL;
+
+ spin_lock_irqsave(&ssif_bmc->lock, flags);
+diff --git a/drivers/char/tpm/eventlog/common.c b/drivers/char/tpm/eventlog/common.c
+index 639c3f395a5af..4c0bbba64ee50 100644
+--- a/drivers/char/tpm/eventlog/common.c
++++ b/drivers/char/tpm/eventlog/common.c
+@@ -47,6 +47,8 @@ static int tpm_bios_measurements_open(struct inode *inode,
+ if (!err) {
+ seq = file->private_data;
+ seq->private = chip;
++ } else {
++ put_device(&chip->dev);
+ }
+
+ return err;
+diff --git a/drivers/char/tpm/tpm_tis_spi_main.c b/drivers/char/tpm/tpm_tis_spi_main.c
+index c9eca24bbad47..61b42c83ced81 100644
+--- a/drivers/char/tpm/tpm_tis_spi_main.c
++++ b/drivers/char/tpm/tpm_tis_spi_main.c
+@@ -318,6 +318,7 @@ static void tpm_tis_spi_remove(struct spi_device *dev)
+ }
+
+ static const struct spi_device_id tpm_tis_spi_id[] = {
++ { "attpm20p", (unsigned long)tpm_tis_spi_probe },
+ { "st33htpm-spi", (unsigned long)tpm_tis_spi_probe },
+ { "slb9670", (unsigned long)tpm_tis_spi_probe },
+ { "tpm_tis_spi", (unsigned long)tpm_tis_spi_probe },
+diff --git a/drivers/clk/clk-en7523.c b/drivers/clk/clk-en7523.c
+index ccc3946926712..bdf5cbc12e236 100644
+--- a/drivers/clk/clk-en7523.c
++++ b/drivers/clk/clk-en7523.c
+@@ -57,6 +57,7 @@ struct en_clk_desc {
+ u8 div_shift;
+ u16 div_val0;
+ u8 div_step;
++ u8 div_offset;
+ };
+
+ struct en_clk_gate {
+@@ -90,6 +91,7 @@ static const struct en_clk_desc en7523_base_clks[] = {
+ .div_bits = 3,
+ .div_shift = 0,
+ .div_step = 1,
++ .div_offset = 1,
+ }, {
+ .id = EN7523_CLK_EMI,
+ .name = "emi",
+@@ -103,6 +105,7 @@ static const struct en_clk_desc en7523_base_clks[] = {
+ .div_bits = 3,
+ .div_shift = 0,
+ .div_step = 1,
++ .div_offset = 1,
+ }, {
+ .id = EN7523_CLK_BUS,
+ .name = "bus",
+@@ -116,6 +119,7 @@ static const struct en_clk_desc en7523_base_clks[] = {
+ .div_bits = 3,
+ .div_shift = 0,
+ .div_step = 1,
++ .div_offset = 1,
+ }, {
+ .id = EN7523_CLK_SLIC,
+ .name = "slic",
+@@ -156,13 +160,14 @@ static const struct en_clk_desc en7523_base_clks[] = {
+ .div_bits = 3,
+ .div_shift = 0,
+ .div_step = 1,
++ .div_offset = 1,
+ }, {
+ .id = EN7523_CLK_CRYPTO,
+ .name = "crypto",
+
+ .base_reg = REG_CRYPTO_CLKSRC,
+ .base_bits = 1,
+- .base_shift = 8,
++ .base_shift = 0,
+ .base_values = emi_base,
+ .n_base_values = ARRAY_SIZE(emi_base),
+ }
+@@ -202,7 +207,7 @@ static u32 en7523_get_div(void __iomem *base, int i)
+ if (!val && desc->div_val0)
+ return desc->div_val0;
+
+- return (val + 1) * desc->div_step;
++ return (val + desc->div_offset) * desc->div_step;
+ }
+
+ static int en7523_pci_is_enabled(struct clk_hw *hw)
+diff --git a/drivers/clk/davinci/da8xx-cfgchip.c b/drivers/clk/davinci/da8xx-cfgchip.c
+index ad2d0df43dc6f..ec60ecb517f1f 100644
+--- a/drivers/clk/davinci/da8xx-cfgchip.c
++++ b/drivers/clk/davinci/da8xx-cfgchip.c
+@@ -508,7 +508,7 @@ da8xx_cfgchip_register_usb0_clk48(struct device *dev,
+ const char * const parent_names[] = { "usb_refclkin", "pll0_auxclk" };
+ struct clk *fck_clk;
+ struct da8xx_usb0_clk48 *usb0;
+- struct clk_init_data init;
++ struct clk_init_data init = {};
+ int ret;
+
+ fck_clk = devm_clk_get(dev, "fck");
+@@ -583,7 +583,7 @@ da8xx_cfgchip_register_usb1_clk48(struct device *dev,
+ {
+ const char * const parent_names[] = { "usb0_clk48", "usb_refclkin" };
+ struct da8xx_usb1_clk48 *usb1;
+- struct clk_init_data init;
++ struct clk_init_data init = {};
+ int ret;
+
+ usb1 = devm_kzalloc(dev, sizeof(*usb1), GFP_KERNEL);
+diff --git a/drivers/clk/meson/s4-peripherals.c b/drivers/clk/meson/s4-peripherals.c
+index 5e17ca50ab091..73340c7e815e7 100644
+--- a/drivers/clk/meson/s4-peripherals.c
++++ b/drivers/clk/meson/s4-peripherals.c
+@@ -2978,7 +2978,7 @@ static struct clk_regmap s4_pwm_j_div = {
+ .name = "pwm_j_div",
+ .ops = &clk_regmap_divider_ops,
+ .parent_hws = (const struct clk_hw *[]) {
+- &s4_pwm_h_mux.hw
++ &s4_pwm_j_mux.hw
+ },
+ .num_parents = 1,
+ .flags = CLK_SET_RATE_PARENT,
+diff --git a/drivers/clk/meson/s4-pll.c b/drivers/clk/meson/s4-pll.c
+index d2650d96400cf..707c107a52918 100644
+--- a/drivers/clk/meson/s4-pll.c
++++ b/drivers/clk/meson/s4-pll.c
+@@ -38,6 +38,11 @@ static struct clk_regmap s4_fixed_pll_dco = {
+ .shift = 0,
+ .width = 8,
+ },
++ .frac = {
++ .reg_off = ANACTRL_FIXPLL_CTRL1,
++ .shift = 0,
++ .width = 17,
++ },
+ .n = {
+ .reg_off = ANACTRL_FIXPLL_CTRL0,
+ .shift = 10,
+diff --git a/drivers/clk/qcom/camcc-sc7280.c b/drivers/clk/qcom/camcc-sc7280.c
+index d89ddb2298e32..582fb3ba9c895 100644
+--- a/drivers/clk/qcom/camcc-sc7280.c
++++ b/drivers/clk/qcom/camcc-sc7280.c
+@@ -2260,6 +2260,7 @@ static struct gdsc cam_cc_bps_gdsc = {
+ .name = "cam_cc_bps_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .parent = &cam_cc_titan_top_gdsc.pd,
+ .flags = HW_CTRL | RETAIN_FF_ENABLE,
+ };
+
+@@ -2269,6 +2270,7 @@ static struct gdsc cam_cc_ife_0_gdsc = {
+ .name = "cam_cc_ife_0_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .parent = &cam_cc_titan_top_gdsc.pd,
+ .flags = RETAIN_FF_ENABLE,
+ };
+
+@@ -2278,6 +2280,7 @@ static struct gdsc cam_cc_ife_1_gdsc = {
+ .name = "cam_cc_ife_1_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .parent = &cam_cc_titan_top_gdsc.pd,
+ .flags = RETAIN_FF_ENABLE,
+ };
+
+@@ -2287,6 +2290,7 @@ static struct gdsc cam_cc_ife_2_gdsc = {
+ .name = "cam_cc_ife_2_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .parent = &cam_cc_titan_top_gdsc.pd,
+ .flags = RETAIN_FF_ENABLE,
+ };
+
+@@ -2296,6 +2300,7 @@ static struct gdsc cam_cc_ipe_0_gdsc = {
+ .name = "cam_cc_ipe_0_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .parent = &cam_cc_titan_top_gdsc.pd,
+ .flags = HW_CTRL | RETAIN_FF_ENABLE,
+ };
+
+diff --git a/drivers/clk/qcom/clk-rcg2.c b/drivers/clk/qcom/clk-rcg2.c
+index 9b3aaa7f20ac2..30b19bd39d087 100644
+--- a/drivers/clk/qcom/clk-rcg2.c
++++ b/drivers/clk/qcom/clk-rcg2.c
+@@ -1304,7 +1304,39 @@ clk_rcg2_shared_recalc_rate(struct clk_hw *hw, unsigned long parent_rate)
+ return clk_rcg2_recalc_rate(hw, parent_rate);
+ }
+
++static int clk_rcg2_shared_init(struct clk_hw *hw)
++{
++ /*
++ * This does a few things:
++ *
++ * 1. Sets rcg->parked_cfg to reflect the value at probe so that the
++ * proper parent is reported from clk_rcg2_shared_get_parent().
++ *
++ * 2. Clears the force enable bit of the RCG because we rely on child
++ * clks (branches) to turn the RCG on/off with a hardware feedback
++ * mechanism and only set the force enable bit in the RCG when we
++ * want to make sure the clk stays on for parent switches or
++ * parking.
++ *
++ * 3. Parks shared RCGs on the safe source at registration because we
++ * can't be certain that the parent clk will stay on during boot,
++ * especially if the parent is shared. If this RCG is enabled at
++ * boot, and the parent is turned off, the RCG will get stuck on. A
++ * GDSC can wedge if is turned on and the RCG is stuck on because
++ * the GDSC's controller will hang waiting for the clk status to
++ * toggle on when it never does.
++ *
++ * The safest option here is to "park" the RCG at init so that the clk
++ * can never get stuck on or off. This ensures the GDSC can't get
++ * wedged.
++ */
++ clk_rcg2_shared_disable(hw);
++
++ return 0;
++}
++
+ const struct clk_ops clk_rcg2_shared_ops = {
++ .init = clk_rcg2_shared_init,
+ .enable = clk_rcg2_shared_enable,
+ .disable = clk_rcg2_shared_disable,
+ .get_parent = clk_rcg2_shared_get_parent,
+diff --git a/drivers/clk/qcom/gcc-sa8775p.c b/drivers/clk/qcom/gcc-sa8775p.c
+index 5bcbfbf52cb9e..9bbc0836fae98 100644
+--- a/drivers/clk/qcom/gcc-sa8775p.c
++++ b/drivers/clk/qcom/gcc-sa8775p.c
+@@ -4305,74 +4305,114 @@ static struct clk_branch gcc_video_axi1_clk = {
+
+ static struct gdsc pcie_0_gdsc = {
+ .gdscr = 0xa9004,
++ .collapse_ctrl = 0x4b104,
++ .collapse_mask = BIT(0),
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "pcie_0_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = VOTABLE | RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc pcie_1_gdsc = {
+ .gdscr = 0x77004,
++ .collapse_ctrl = 0x4b104,
++ .collapse_mask = BIT(1),
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "pcie_1_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = VOTABLE | RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc ufs_card_gdsc = {
+ .gdscr = 0x81004,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "ufs_card_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc ufs_phy_gdsc = {
+ .gdscr = 0x83004,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "ufs_phy_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc usb20_prim_gdsc = {
+ .gdscr = 0x1c004,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "usb20_prim_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc usb30_prim_gdsc = {
+ .gdscr = 0x1b004,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "usb30_prim_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc usb30_sec_gdsc = {
+ .gdscr = 0x2f004,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "usb30_sec_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc emac0_gdsc = {
+ .gdscr = 0xb6004,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "emac0_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct gdsc emac1_gdsc = {
+ .gdscr = 0xb4004,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "emac1_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
++ .flags = RETAIN_FF_ENABLE | POLL_CFG_GDSCR,
+ };
+
+ static struct clk_regmap *gcc_sa8775p_clocks[] = {
+diff --git a/drivers/clk/qcom/gcc-sc7280.c b/drivers/clk/qcom/gcc-sc7280.c
+index f45a8318900c5..67ea9cf5303fa 100644
+--- a/drivers/clk/qcom/gcc-sc7280.c
++++ b/drivers/clk/qcom/gcc-sc7280.c
+@@ -3463,6 +3463,9 @@ static int gcc_sc7280_probe(struct platform_device *pdev)
+ qcom_branch_set_clk_en(regmap, 0x71004);/* GCC_GPU_CFG_AHB_CLK */
+ regmap_update_bits(regmap, 0x7100C, BIT(13), BIT(13));
+
++ /* FORCE_MEM_CORE_ON for ufs phy ice core clocks */
++ qcom_branch_set_force_mem_core(regmap, gcc_ufs_phy_ice_core_clk, true);
++
+ ret = qcom_cc_register_rcg_dfs(regmap, gcc_dfs_clocks,
+ ARRAY_SIZE(gcc_dfs_clocks));
+ if (ret)
+diff --git a/drivers/clk/qcom/gcc-x1e80100.c b/drivers/clk/qcom/gcc-x1e80100.c
+index 1404017be9180..a263f0c412f5a 100644
+--- a/drivers/clk/qcom/gcc-x1e80100.c
++++ b/drivers/clk/qcom/gcc-x1e80100.c
+@@ -2812,7 +2812,7 @@ static struct clk_branch gcc_pcie_0_mstr_axi_clk = {
+
+ static struct clk_branch gcc_pcie_0_pipe_clk = {
+ .halt_reg = 0xa0044,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52010,
+ .enable_mask = BIT(25),
+@@ -2901,7 +2901,7 @@ static struct clk_branch gcc_pcie_1_mstr_axi_clk = {
+
+ static struct clk_branch gcc_pcie_1_pipe_clk = {
+ .halt_reg = 0x2c044,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52020,
+ .enable_mask = BIT(30),
+@@ -2990,7 +2990,7 @@ static struct clk_branch gcc_pcie_2_mstr_axi_clk = {
+
+ static struct clk_branch gcc_pcie_2_pipe_clk = {
+ .halt_reg = 0x13044,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52020,
+ .enable_mask = BIT(23),
+@@ -3110,7 +3110,7 @@ static struct clk_branch gcc_pcie_3_phy_rchng_clk = {
+
+ static struct clk_branch gcc_pcie_3_pipe_clk = {
+ .halt_reg = 0x58050,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52020,
+ .enable_mask = BIT(3),
+@@ -3235,7 +3235,7 @@ static struct clk_branch gcc_pcie_4_phy_rchng_clk = {
+
+ static struct clk_branch gcc_pcie_4_pipe_clk = {
+ .halt_reg = 0x6b044,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52008,
+ .enable_mask = BIT(4),
+@@ -3360,7 +3360,7 @@ static struct clk_branch gcc_pcie_5_phy_rchng_clk = {
+
+ static struct clk_branch gcc_pcie_5_pipe_clk = {
+ .halt_reg = 0x2f044,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52018,
+ .enable_mask = BIT(17),
+@@ -3498,7 +3498,7 @@ static struct clk_branch gcc_pcie_6a_phy_rchng_clk = {
+
+ static struct clk_branch gcc_pcie_6a_pipe_clk = {
+ .halt_reg = 0x31050,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52018,
+ .enable_mask = BIT(26),
+@@ -3636,7 +3636,7 @@ static struct clk_branch gcc_pcie_6b_phy_rchng_clk = {
+
+ static struct clk_branch gcc_pcie_6b_pipe_clk = {
+ .halt_reg = 0x8d050,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52000,
+ .enable_mask = BIT(30),
+@@ -5109,7 +5109,7 @@ static struct clk_branch gcc_usb3_mp_phy_com_aux_clk = {
+
+ static struct clk_branch gcc_usb3_mp_phy_pipe_0_clk = {
+ .halt_reg = 0x17290,
+- .halt_check = BRANCH_HALT,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x17290,
+ .enable_mask = BIT(0),
+@@ -5122,7 +5122,7 @@ static struct clk_branch gcc_usb3_mp_phy_pipe_0_clk = {
+
+ static struct clk_branch gcc_usb3_mp_phy_pipe_1_clk = {
+ .halt_reg = 0x17298,
+- .halt_check = BRANCH_HALT,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x17298,
+ .enable_mask = BIT(0),
+@@ -5186,7 +5186,7 @@ static struct clk_regmap_mux gcc_usb3_prim_phy_pipe_clk_src = {
+
+ static struct clk_branch gcc_usb3_prim_phy_pipe_clk = {
+ .halt_reg = 0x39068,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .hwcg_reg = 0x39068,
+ .hwcg_bit = 1,
+ .clkr = {
+@@ -5257,7 +5257,7 @@ static struct clk_regmap_mux gcc_usb3_sec_phy_pipe_clk_src = {
+
+ static struct clk_branch gcc_usb3_sec_phy_pipe_clk = {
+ .halt_reg = 0xa1068,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .hwcg_reg = 0xa1068,
+ .hwcg_bit = 1,
+ .clkr = {
+@@ -5269,6 +5269,7 @@ static struct clk_branch gcc_usb3_sec_phy_pipe_clk = {
+ &gcc_usb3_sec_phy_pipe_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -5327,7 +5328,7 @@ static struct clk_regmap_mux gcc_usb3_tert_phy_pipe_clk_src = {
+
+ static struct clk_branch gcc_usb3_tert_phy_pipe_clk = {
+ .halt_reg = 0xa2068,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .hwcg_reg = 0xa2068,
+ .hwcg_bit = 1,
+ .clkr = {
+@@ -5339,6 +5340,7 @@ static struct clk_branch gcc_usb3_tert_phy_pipe_clk = {
+ &gcc_usb3_tert_phy_pipe_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -5405,7 +5407,7 @@ static struct clk_branch gcc_usb4_0_master_clk = {
+
+ static struct clk_branch gcc_usb4_0_phy_p2rr2p_pipe_clk = {
+ .halt_reg = 0x9f0d8,
+- .halt_check = BRANCH_HALT,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x9f0d8,
+ .enable_mask = BIT(0),
+@@ -5418,7 +5420,7 @@ static struct clk_branch gcc_usb4_0_phy_p2rr2p_pipe_clk = {
+
+ static struct clk_branch gcc_usb4_0_phy_pcie_pipe_clk = {
+ .halt_reg = 0x9f048,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52010,
+ .enable_mask = BIT(19),
+@@ -5457,7 +5459,7 @@ static struct clk_branch gcc_usb4_0_phy_rx1_clk = {
+
+ static struct clk_branch gcc_usb4_0_phy_usb_pipe_clk = {
+ .halt_reg = 0x9f0a4,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .hwcg_reg = 0x9f0a4,
+ .hwcg_bit = 1,
+ .clkr = {
+@@ -5582,7 +5584,7 @@ static struct clk_branch gcc_usb4_1_master_clk = {
+
+ static struct clk_branch gcc_usb4_1_phy_p2rr2p_pipe_clk = {
+ .halt_reg = 0x2b0d8,
+- .halt_check = BRANCH_HALT,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x2b0d8,
+ .enable_mask = BIT(0),
+@@ -5595,7 +5597,7 @@ static struct clk_branch gcc_usb4_1_phy_p2rr2p_pipe_clk = {
+
+ static struct clk_branch gcc_usb4_1_phy_pcie_pipe_clk = {
+ .halt_reg = 0x2b048,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52028,
+ .enable_mask = BIT(0),
+@@ -5634,7 +5636,7 @@ static struct clk_branch gcc_usb4_1_phy_rx1_clk = {
+
+ static struct clk_branch gcc_usb4_1_phy_usb_pipe_clk = {
+ .halt_reg = 0x2b0a4,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .hwcg_reg = 0x2b0a4,
+ .hwcg_bit = 1,
+ .clkr = {
+@@ -5759,7 +5761,7 @@ static struct clk_branch gcc_usb4_2_master_clk = {
+
+ static struct clk_branch gcc_usb4_2_phy_p2rr2p_pipe_clk = {
+ .halt_reg = 0x110d8,
+- .halt_check = BRANCH_HALT,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x110d8,
+ .enable_mask = BIT(0),
+@@ -5772,7 +5774,7 @@ static struct clk_branch gcc_usb4_2_phy_p2rr2p_pipe_clk = {
+
+ static struct clk_branch gcc_usb4_2_phy_pcie_pipe_clk = {
+ .halt_reg = 0x11048,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .clkr = {
+ .enable_reg = 0x52028,
+ .enable_mask = BIT(1),
+@@ -5811,7 +5813,7 @@ static struct clk_branch gcc_usb4_2_phy_rx1_clk = {
+
+ static struct clk_branch gcc_usb4_2_phy_usb_pipe_clk = {
+ .halt_reg = 0x110a4,
+- .halt_check = BRANCH_HALT_VOTED,
++ .halt_check = BRANCH_HALT_SKIP,
+ .hwcg_reg = 0x110a4,
+ .hwcg_bit = 1,
+ .clkr = {
+diff --git a/drivers/clk/qcom/gpucc-sa8775p.c b/drivers/clk/qcom/gpucc-sa8775p.c
+index 1167c42da39db..3deabf8333883 100644
+--- a/drivers/clk/qcom/gpucc-sa8775p.c
++++ b/drivers/clk/qcom/gpucc-sa8775p.c
+@@ -1,6 +1,6 @@
+ // SPDX-License-Identifier: GPL-2.0-only
+ /*
+- * Copyright (c) 2021-2022, Qualcomm Innovation Center, Inc. All rights reserved.
++ * Copyright (c) 2021-2022, 2024, Qualcomm Innovation Center, Inc. All rights reserved.
+ * Copyright (c) 2023, Linaro Limited
+ */
+
+@@ -161,7 +161,7 @@ static struct clk_rcg2 gpu_cc_ff_clk_src = {
+ .name = "gpu_cc_ff_clk_src",
+ .parent_data = gpu_cc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0),
+- .ops = &clk_rcg2_ops,
++ .ops = &clk_rcg2_shared_ops,
+ },
+ };
+
+@@ -181,7 +181,7 @@ static struct clk_rcg2 gpu_cc_gmu_clk_src = {
+ .parent_data = gpu_cc_parent_data_1,
+ .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_ops,
++ .ops = &clk_rcg2_shared_ops,
+ },
+ };
+
+@@ -200,7 +200,7 @@ static struct clk_rcg2 gpu_cc_hub_clk_src = {
+ .name = "gpu_cc_hub_clk_src",
+ .parent_data = gpu_cc_parent_data_2,
+ .num_parents = ARRAY_SIZE(gpu_cc_parent_data_2),
+- .ops = &clk_rcg2_ops,
++ .ops = &clk_rcg2_shared_ops,
+ },
+ };
+
+@@ -280,7 +280,7 @@ static struct clk_branch gpu_cc_ahb_clk = {
+ &gpu_cc_hub_ahb_div_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -294,8 +294,7 @@ static struct clk_branch gpu_cc_cb_clk = {
+ .enable_mask = BIT(0),
+ .hw.init = &(const struct clk_init_data){
+ .name = "gpu_cc_cb_clk",
+- .flags = CLK_IS_CRITICAL,
+- .ops = &clk_branch2_ops,
++ .ops = &clk_branch2_aon_ops,
+ },
+ },
+ };
+@@ -312,7 +311,7 @@ static struct clk_branch gpu_cc_crc_ahb_clk = {
+ &gpu_cc_hub_ahb_div_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -330,7 +329,7 @@ static struct clk_branch gpu_cc_cx_ff_clk = {
+ &gpu_cc_ff_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -348,7 +347,7 @@ static struct clk_branch gpu_cc_cx_gmu_clk = {
+ &gpu_cc_gmu_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_aon_ops,
+ },
+ },
+@@ -362,7 +361,6 @@ static struct clk_branch gpu_cc_cx_snoc_dvm_clk = {
+ .enable_mask = BIT(0),
+ .hw.init = &(const struct clk_init_data){
+ .name = "gpu_cc_cx_snoc_dvm_clk",
+- .flags = CLK_IS_CRITICAL,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -380,7 +378,7 @@ static struct clk_branch gpu_cc_cxo_aon_clk = {
+ &gpu_cc_xo_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -398,7 +396,7 @@ static struct clk_branch gpu_cc_cxo_clk = {
+ &gpu_cc_xo_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -416,7 +414,7 @@ static struct clk_branch gpu_cc_demet_clk = {
+ &gpu_cc_demet_div_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_aon_ops,
+ },
+ },
+@@ -430,7 +428,6 @@ static struct clk_branch gpu_cc_hlos1_vote_gpu_smmu_clk = {
+ .enable_mask = BIT(0),
+ .hw.init = &(const struct clk_init_data){
+ .name = "gpu_cc_hlos1_vote_gpu_smmu_clk",
+- .flags = CLK_IS_CRITICAL,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -448,7 +445,7 @@ static struct clk_branch gpu_cc_hub_aon_clk = {
+ &gpu_cc_hub_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_aon_ops,
+ },
+ },
+@@ -466,7 +463,7 @@ static struct clk_branch gpu_cc_hub_cx_int_clk = {
+ &gpu_cc_hub_cx_int_div_clk_src.clkr.hw,
+ },
+ .num_parents = 1,
+- .flags = CLK_SET_RATE_PARENT | CLK_IS_CRITICAL,
++ .flags = CLK_SET_RATE_PARENT,
+ .ops = &clk_branch2_aon_ops,
+ },
+ },
+@@ -480,7 +477,6 @@ static struct clk_branch gpu_cc_memnoc_gfx_clk = {
+ .enable_mask = BIT(0),
+ .hw.init = &(const struct clk_init_data){
+ .name = "gpu_cc_memnoc_gfx_clk",
+- .flags = CLK_IS_CRITICAL,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -494,7 +490,6 @@ static struct clk_branch gpu_cc_sleep_clk = {
+ .enable_mask = BIT(0),
+ .hw.init = &(const struct clk_init_data){
+ .name = "gpu_cc_sleep_clk",
+- .flags = CLK_IS_CRITICAL,
+ .ops = &clk_branch2_ops,
+ },
+ },
+@@ -528,16 +523,22 @@ static struct clk_regmap *gpu_cc_sa8775p_clocks[] = {
+
+ static struct gdsc cx_gdsc = {
+ .gdscr = 0x9108,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .gds_hw_ctrl = 0x953c,
+ .pd = {
+ .name = "cx_gdsc",
+ },
+ .pwrsts = PWRSTS_OFF_ON,
+- .flags = VOTABLE | RETAIN_FF_ENABLE | ALWAYS_ON,
++ .flags = VOTABLE | RETAIN_FF_ENABLE,
+ };
+
+ static struct gdsc gx_gdsc = {
+ .gdscr = 0x905c,
++ .en_rest_wait_val = 0x2,
++ .en_few_wait_val = 0x2,
++ .clk_dis_wait_val = 0xf,
+ .pd = {
+ .name = "gx_gdsc",
+ .power_on = gdsc_gx_do_nothing_enable,
+diff --git a/drivers/clk/qcom/gpucc-sm8350.c b/drivers/clk/qcom/gpucc-sm8350.c
+index 38505d1388b67..8d9dcff40dd0b 100644
+--- a/drivers/clk/qcom/gpucc-sm8350.c
++++ b/drivers/clk/qcom/gpucc-sm8350.c
+@@ -2,6 +2,7 @@
+ /*
+ * Copyright (c) 2019-2020, The Linux Foundation. All rights reserved.
+ * Copyright (c) 2022, Linaro Limited
++ * Copyright (c) 2024, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+ #include <linux/clk.h>
+@@ -147,7 +148,7 @@ static struct clk_rcg2 gpu_cc_gmu_clk_src = {
+ .parent_data = gpu_cc_parent_data_0,
+ .num_parents = ARRAY_SIZE(gpu_cc_parent_data_0),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_ops,
++ .ops = &clk_rcg2_shared_ops,
+ },
+ };
+
+@@ -169,7 +170,7 @@ static struct clk_rcg2 gpu_cc_hub_clk_src = {
+ .parent_data = gpu_cc_parent_data_1,
+ .num_parents = ARRAY_SIZE(gpu_cc_parent_data_1),
+ .flags = CLK_SET_RATE_PARENT,
+- .ops = &clk_rcg2_ops,
++ .ops = &clk_rcg2_shared_ops,
+ },
+ };
+
+diff --git a/drivers/clk/qcom/kpss-xcc.c b/drivers/clk/qcom/kpss-xcc.c
+index 23b0b11f00077..e7cfa8d22044e 100644
+--- a/drivers/clk/qcom/kpss-xcc.c
++++ b/drivers/clk/qcom/kpss-xcc.c
+@@ -58,9 +58,7 @@ static int kpss_xcc_driver_probe(struct platform_device *pdev)
+ if (IS_ERR(hw))
+ return PTR_ERR(hw);
+
+- of_clk_add_hw_provider(dev->of_node, of_clk_hw_simple_get, hw);
+-
+- return 0;
++ return of_clk_add_hw_provider(dev->of_node, of_clk_hw_simple_get, hw);
+ }
+
+ static struct platform_driver kpss_xcc_driver = {
+diff --git a/drivers/clk/samsung/clk-exynos4.c b/drivers/clk/samsung/clk-exynos4.c
+index a026ccca7315f..28945b6b0ee1c 100644
+--- a/drivers/clk/samsung/clk-exynos4.c
++++ b/drivers/clk/samsung/clk-exynos4.c
+@@ -1040,19 +1040,20 @@ static unsigned long __init exynos4_get_xom(void)
+ static void __init exynos4_clk_register_finpll(struct samsung_clk_provider *ctx)
+ {
+ struct samsung_fixed_rate_clock fclk;
+- struct clk *clk;
+- unsigned long finpll_f = 24000000;
++ unsigned long finpll_f;
++ unsigned int parent;
+ char *parent_name;
+ unsigned int xom = exynos4_get_xom();
+
+ parent_name = xom & 1 ? "xusbxti" : "xxti";
+- clk = clk_get(NULL, parent_name);
+- if (IS_ERR(clk)) {
++ parent = xom & 1 ? CLK_XUSBXTI : CLK_XXTI;
++
++ finpll_f = clk_hw_get_rate(ctx->clk_data.hws[parent]);
++ if (!finpll_f) {
+ pr_err("%s: failed to lookup parent clock %s, assuming "
+ "fin_pll clock frequency is 24MHz\n", __func__,
+ parent_name);
+- } else {
+- finpll_f = clk_get_rate(clk);
++ finpll_f = 24000000;
+ }
+
+ fclk.id = CLK_FIN_PLL;
+diff --git a/drivers/cpufreq/amd-pstate-ut.c b/drivers/cpufreq/amd-pstate-ut.c
+index fc275d41d51e9..66b73c308ce67 100644
+--- a/drivers/cpufreq/amd-pstate-ut.c
++++ b/drivers/cpufreq/amd-pstate-ut.c
+@@ -202,6 +202,7 @@ static void amd_pstate_ut_check_freq(u32 index)
+ int cpu = 0;
+ struct cpufreq_policy *policy = NULL;
+ struct amd_cpudata *cpudata = NULL;
++ u32 nominal_freq_khz;
+
+ for_each_possible_cpu(cpu) {
+ policy = cpufreq_cpu_get(cpu);
+@@ -209,13 +210,14 @@ static void amd_pstate_ut_check_freq(u32 index)
+ break;
+ cpudata = policy->driver_data;
+
+- if (!((cpudata->max_freq >= cpudata->nominal_freq) &&
+- (cpudata->nominal_freq > cpudata->lowest_nonlinear_freq) &&
++ nominal_freq_khz = cpudata->nominal_freq*1000;
++ if (!((cpudata->max_freq >= nominal_freq_khz) &&
++ (nominal_freq_khz > cpudata->lowest_nonlinear_freq) &&
+ (cpudata->lowest_nonlinear_freq > cpudata->min_freq) &&
+ (cpudata->min_freq > 0))) {
+ amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
+ pr_err("%s cpu%d max=%d >= nominal=%d > lowest_nonlinear=%d > min=%d > 0, the formula is incorrect!\n",
+- __func__, cpu, cpudata->max_freq, cpudata->nominal_freq,
++ __func__, cpu, cpudata->max_freq, nominal_freq_khz,
+ cpudata->lowest_nonlinear_freq, cpudata->min_freq);
+ goto skip_test;
+ }
+@@ -229,13 +231,13 @@ static void amd_pstate_ut_check_freq(u32 index)
+
+ if (cpudata->boost_supported) {
+ if ((policy->max == cpudata->max_freq) ||
+- (policy->max == cpudata->nominal_freq))
++ (policy->max == nominal_freq_khz))
+ amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_PASS;
+ else {
+ amd_pstate_ut_cases[index].result = AMD_PSTATE_UT_RESULT_FAIL;
+ pr_err("%s cpu%d policy_max=%d should be equal cpu_max=%d or cpu_nominal=%d !\n",
+ __func__, cpu, policy->max, cpudata->max_freq,
+- cpudata->nominal_freq);
++ nominal_freq_khz);
+ goto skip_test;
+ }
+ } else {
+diff --git a/drivers/cpufreq/amd-pstate.c b/drivers/cpufreq/amd-pstate.c
+index 9ad62dbe8bfbf..a092b13ffbc2f 100644
+--- a/drivers/cpufreq/amd-pstate.c
++++ b/drivers/cpufreq/amd-pstate.c
+@@ -247,6 +247,26 @@ static int amd_pstate_get_energy_pref_index(struct amd_cpudata *cpudata)
+ return index;
+ }
+
++static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
++ u32 des_perf, u32 max_perf, bool fast_switch)
++{
++ if (fast_switch)
++ wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
++ else
++ wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
++ READ_ONCE(cpudata->cppc_req_cached));
++}
++
++DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf);
++
++static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
++ u32 min_perf, u32 des_perf,
++ u32 max_perf, bool fast_switch)
++{
++ static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
++ max_perf, fast_switch);
++}
++
+ static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp)
+ {
+ int ret;
+@@ -263,6 +283,9 @@ static int amd_pstate_set_epp(struct amd_cpudata *cpudata, u32 epp)
+ if (!ret)
+ cpudata->epp_cached = epp;
+ } else {
++ amd_pstate_update_perf(cpudata, cpudata->min_limit_perf, 0U,
++ cpudata->max_limit_perf, false);
++
+ perf_ctrls.energy_perf = epp;
+ ret = cppc_set_epp_perf(cpudata->cpu, &perf_ctrls, 1);
+ if (ret) {
+@@ -452,16 +475,6 @@ static inline int amd_pstate_init_perf(struct amd_cpudata *cpudata)
+ return static_call(amd_pstate_init_perf)(cpudata);
+ }
+
+-static void pstate_update_perf(struct amd_cpudata *cpudata, u32 min_perf,
+- u32 des_perf, u32 max_perf, bool fast_switch)
+-{
+- if (fast_switch)
+- wrmsrl(MSR_AMD_CPPC_REQ, READ_ONCE(cpudata->cppc_req_cached));
+- else
+- wrmsrl_on_cpu(cpudata->cpu, MSR_AMD_CPPC_REQ,
+- READ_ONCE(cpudata->cppc_req_cached));
+-}
+-
+ static void cppc_update_perf(struct amd_cpudata *cpudata,
+ u32 min_perf, u32 des_perf,
+ u32 max_perf, bool fast_switch)
+@@ -475,16 +488,6 @@ static void cppc_update_perf(struct amd_cpudata *cpudata,
+ cppc_set_perf(cpudata->cpu, &perf_ctrls);
+ }
+
+-DEFINE_STATIC_CALL(amd_pstate_update_perf, pstate_update_perf);
+-
+-static inline void amd_pstate_update_perf(struct amd_cpudata *cpudata,
+- u32 min_perf, u32 des_perf,
+- u32 max_perf, bool fast_switch)
+-{
+- static_call(amd_pstate_update_perf)(cpudata, min_perf, des_perf,
+- max_perf, fast_switch);
+-}
+-
+ static inline bool amd_pstate_sample(struct amd_cpudata *cpudata)
+ {
+ u64 aperf, mperf, tsc;
+diff --git a/drivers/cpufreq/qcom-cpufreq-nvmem.c b/drivers/cpufreq/qcom-cpufreq-nvmem.c
+index ea05d9d674902..5004e1dbc7522 100644
+--- a/drivers/cpufreq/qcom-cpufreq-nvmem.c
++++ b/drivers/cpufreq/qcom-cpufreq-nvmem.c
+@@ -480,23 +480,30 @@ static int qcom_cpufreq_probe(struct platform_device *pdev)
+
+ drv = devm_kzalloc(&pdev->dev, struct_size(drv, cpus, num_possible_cpus()),
+ GFP_KERNEL);
+- if (!drv)
++ if (!drv) {
++ of_node_put(np);
+ return -ENOMEM;
++ }
+
+ match = pdev->dev.platform_data;
+ drv->data = match->data;
+- if (!drv->data)
++ if (!drv->data) {
++ of_node_put(np);
+ return -ENODEV;
++ }
+
+ if (drv->data->get_version) {
+ speedbin_nvmem = of_nvmem_cell_get(np, NULL);
+- if (IS_ERR(speedbin_nvmem))
++ if (IS_ERR(speedbin_nvmem)) {
++ of_node_put(np);
+ return dev_err_probe(cpu_dev, PTR_ERR(speedbin_nvmem),
+ "Could not get nvmem cell\n");
++ }
+
+ ret = drv->data->get_version(cpu_dev,
+ speedbin_nvmem, &pvs_name, drv);
+ if (ret) {
++ of_node_put(np);
+ nvmem_cell_put(speedbin_nvmem);
+ return ret;
+ }
+diff --git a/drivers/cpufreq/sun50i-cpufreq-nvmem.c b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+index 0b882765cd66f..ef83e4bf26391 100644
+--- a/drivers/cpufreq/sun50i-cpufreq-nvmem.c
++++ b/drivers/cpufreq/sun50i-cpufreq-nvmem.c
+@@ -131,7 +131,7 @@ static const struct of_device_id cpu_opp_match_list[] = {
+ static bool dt_has_supported_hw(void)
+ {
+ bool has_opp_supported_hw = false;
+- struct device_node *np, *opp;
++ struct device_node *np;
+ struct device *cpu_dev;
+
+ cpu_dev = get_cpu_device(0);
+@@ -142,7 +142,7 @@ static bool dt_has_supported_hw(void)
+ if (!np)
+ return false;
+
+- for_each_child_of_node(np, opp) {
++ for_each_child_of_node_scoped(np, opp) {
+ if (of_find_property(opp, "opp-supported-hw", NULL)) {
+ has_opp_supported_hw = true;
+ break;
+diff --git a/drivers/cpufreq/ti-cpufreq.c b/drivers/cpufreq/ti-cpufreq.c
+index 714ed53753fa5..5af85c4cbad0c 100644
+--- a/drivers/cpufreq/ti-cpufreq.c
++++ b/drivers/cpufreq/ti-cpufreq.c
+@@ -417,7 +417,7 @@ static int ti_cpufreq_probe(struct platform_device *pdev)
+
+ ret = dev_pm_opp_set_config(opp_data->cpu_dev, &config);
+ if (ret < 0) {
+- dev_err(opp_data->cpu_dev, "Failed to set OPP config\n");
++ dev_err_probe(opp_data->cpu_dev, ret, "Failed to set OPP config\n");
+ goto fail_put_node;
+ }
+
+diff --git a/drivers/crypto/atmel-sha204a.c b/drivers/crypto/atmel-sha204a.c
+index 24ffdf5050235..2034f60315183 100644
+--- a/drivers/crypto/atmel-sha204a.c
++++ b/drivers/crypto/atmel-sha204a.c
+@@ -106,7 +106,7 @@ static int atmel_sha204a_otp_read(struct i2c_client *client, u16 addr, u8 *otp)
+
+ if (cmd.data[0] == 0xff) {
+ dev_err(&client->dev, "failed, device not ready\n");
+- return -ret;
++ return -EINVAL;
+ }
+
+ memcpy(otp, cmd.data+1, 4);
+diff --git a/drivers/crypto/ccp/sev-dev.c b/drivers/crypto/ccp/sev-dev.c
+index 2102377f727b1..1912bee22dd4a 100644
+--- a/drivers/crypto/ccp/sev-dev.c
++++ b/drivers/crypto/ccp/sev-dev.c
+@@ -1642,10 +1642,16 @@ static int sev_update_firmware(struct device *dev)
+
+ static int __sev_snp_shutdown_locked(int *error, bool panic)
+ {
+- struct sev_device *sev = psp_master->sev_data;
++ struct psp_device *psp = psp_master;
++ struct sev_device *sev;
+ struct sev_data_snp_shutdown_ex data;
+ int ret;
+
++ if (!psp || !psp->sev_data)
++ return 0;
++
++ sev = psp->sev_data;
++
+ if (!sev->snp_initialized)
+ return 0;
+
+diff --git a/drivers/crypto/intel/qat/qat_common/adf_cfg.c b/drivers/crypto/intel/qat/qat_common/adf_cfg.c
+index 8836f015c39c4..2cf102ad4ca82 100644
+--- a/drivers/crypto/intel/qat/qat_common/adf_cfg.c
++++ b/drivers/crypto/intel/qat/qat_common/adf_cfg.c
+@@ -290,17 +290,19 @@ int adf_cfg_add_key_value_param(struct adf_accel_dev *accel_dev,
+ * 3. if the key exists with the same value, then return without doing
+ * anything (the newly created key_val is freed).
+ */
++ down_write(&cfg->lock);
+ if (!adf_cfg_key_val_get(accel_dev, section_name, key, temp_val)) {
+ if (strncmp(temp_val, key_val->val, sizeof(temp_val))) {
+ adf_cfg_keyval_remove(key, section);
+ } else {
+ kfree(key_val);
+- return 0;
++ goto out;
+ }
+ }
+
+- down_write(&cfg->lock);
+ adf_cfg_keyval_add(key_val, section);
++
++out:
+ up_write(&cfg->lock);
+ return 0;
+ }
+diff --git a/drivers/crypto/mxs-dcp.c b/drivers/crypto/mxs-dcp.c
+index 057d73c370b73..c82775dbb557a 100644
+--- a/drivers/crypto/mxs-dcp.c
++++ b/drivers/crypto/mxs-dcp.c
+@@ -225,7 +225,8 @@ static int mxs_dcp_start_dma(struct dcp_async_ctx *actx)
+ static int mxs_dcp_run_aes(struct dcp_async_ctx *actx,
+ struct skcipher_request *req, int init)
+ {
+- dma_addr_t key_phys, src_phys, dst_phys;
++ dma_addr_t key_phys = 0;
++ dma_addr_t src_phys, dst_phys;
+ struct dcp *sdcp = global_sdcp;
+ struct dcp_dma_desc *desc = &sdcp->coh->desc[actx->chan];
+ struct dcp_aes_req_ctx *rctx = skcipher_request_ctx(req);
+diff --git a/drivers/crypto/tegra/tegra-se-main.c b/drivers/crypto/tegra/tegra-se-main.c
+index 9955874b3dc37..f94c0331b148c 100644
+--- a/drivers/crypto/tegra/tegra-se-main.c
++++ b/drivers/crypto/tegra/tegra-se-main.c
+@@ -326,7 +326,6 @@ static void tegra_se_remove(struct platform_device *pdev)
+
+ crypto_engine_stop(se->engine);
+ crypto_engine_exit(se->engine);
+- iommu_fwspec_free(se->dev);
+ host1x_client_unregister(&se->client);
+ }
+
+diff --git a/drivers/dma/fsl-edma-common.c b/drivers/dma/fsl-edma-common.c
+index 3af4307873157..0af934b56a6cb 100644
+--- a/drivers/dma/fsl-edma-common.c
++++ b/drivers/dma/fsl-edma-common.c
+@@ -758,6 +758,8 @@ struct dma_async_tx_descriptor *fsl_edma_prep_memcpy(struct dma_chan *chan,
+ fsl_desc->iscyclic = false;
+
+ fsl_chan->is_sw = true;
++ if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_MEM_REMOTE)
++ fsl_chan->is_remote = true;
+
+ /* To match with copy_align and max_seg_size so 1 tcd is enough */
+ fsl_edma_fill_tcd(fsl_chan, fsl_desc->tcd[0].vtcd, dma_src, dma_dst,
+@@ -837,6 +839,7 @@ void fsl_edma_free_chan_resources(struct dma_chan *chan)
+ fsl_chan->tcd_pool = NULL;
+ fsl_chan->is_sw = false;
+ fsl_chan->srcid = 0;
++ fsl_chan->is_remote = false;
+ if (fsl_edma_drvflags(fsl_chan) & FSL_EDMA_DRV_HAS_CHCLK)
+ clk_disable_unprepare(fsl_chan->clk);
+ }
+diff --git a/drivers/dma/fsl-edma-common.h b/drivers/dma/fsl-edma-common.h
+index ac66222c16040..268db3876787c 100644
+--- a/drivers/dma/fsl-edma-common.h
++++ b/drivers/dma/fsl-edma-common.h
+@@ -194,6 +194,7 @@ struct fsl_edma_desc {
+ #define FSL_EDMA_DRV_HAS_PD BIT(5)
+ #define FSL_EDMA_DRV_HAS_CHCLK BIT(6)
+ #define FSL_EDMA_DRV_HAS_CHMUX BIT(7)
++#define FSL_EDMA_DRV_MEM_REMOTE BIT(8)
+ /* control and status register is in tcd address space, edma3 reg layout */
+ #define FSL_EDMA_DRV_SPLIT_REG BIT(9)
+ #define FSL_EDMA_DRV_BUS_8BYTE BIT(10)
+diff --git a/drivers/dma/fsl-edma-main.c b/drivers/dma/fsl-edma-main.c
+index 391e4f13dfeb0..43d84cfefbe20 100644
+--- a/drivers/dma/fsl-edma-main.c
++++ b/drivers/dma/fsl-edma-main.c
+@@ -342,7 +342,7 @@ static struct fsl_edma_drvdata imx7ulp_data = {
+ };
+
+ static struct fsl_edma_drvdata imx8qm_data = {
+- .flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3,
++ .flags = FSL_EDMA_DRV_HAS_PD | FSL_EDMA_DRV_EDMA3 | FSL_EDMA_DRV_MEM_REMOTE,
+ .chreg_space_sz = 0x10000,
+ .chreg_off = 0x10000,
+ .setup_irq = fsl_edma3_irq_init,
+diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c
+index 6400d06588a24..df507d96660b9 100644
+--- a/drivers/dma/ti/k3-udma.c
++++ b/drivers/dma/ti/k3-udma.c
+@@ -4472,7 +4472,9 @@ static int udma_get_mmrs(struct platform_device *pdev, struct udma_dev *ud)
+ ud->rchan_cnt = UDMA_CAP2_RCHAN_CNT(cap2);
+ break;
+ case DMA_TYPE_BCDMA:
+- ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2);
++ ud->bchan_cnt = BCDMA_CAP2_BCHAN_CNT(cap2) +
++ BCDMA_CAP3_HBCHAN_CNT(cap3) +
++ BCDMA_CAP3_UBCHAN_CNT(cap3);
+ ud->tchan_cnt = BCDMA_CAP2_TCHAN_CNT(cap2);
+ ud->rchan_cnt = BCDMA_CAP2_RCHAN_CNT(cap2);
+ ud->rflow_cnt = ud->rchan_cnt;
+diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
+index 9c09893695b7e..4edfb83ffbeef 100644
+--- a/drivers/edac/Makefile
++++ b/drivers/edac/Makefile
+@@ -54,11 +54,13 @@ obj-$(CONFIG_EDAC_MPC85XX) += mpc85xx_edac_mod.o
+ layerscape_edac_mod-y := fsl_ddr_edac.o layerscape_edac.o
+ obj-$(CONFIG_EDAC_LAYERSCAPE) += layerscape_edac_mod.o
+
+-skx_edac-y := skx_common.o skx_base.o
+-obj-$(CONFIG_EDAC_SKX) += skx_edac.o
++skx_edac_common-y := skx_common.o
+
+-i10nm_edac-y := skx_common.o i10nm_base.o
+-obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o
++skx_edac-y := skx_base.o
++obj-$(CONFIG_EDAC_SKX) += skx_edac.o skx_edac_common.o
++
++i10nm_edac-y := i10nm_base.o
++obj-$(CONFIG_EDAC_I10NM) += i10nm_edac.o skx_edac_common.o
+
+ obj-$(CONFIG_EDAC_CELL) += cell_edac.o
+ obj-$(CONFIG_EDAC_PPC4XX) += ppc4xx_edac.o
+diff --git a/drivers/edac/skx_common.c b/drivers/edac/skx_common.c
+index 27996b7924c82..8d18099fd528c 100644
+--- a/drivers/edac/skx_common.c
++++ b/drivers/edac/skx_common.c
+@@ -48,7 +48,7 @@ static u64 skx_tolm, skx_tohm;
+ static LIST_HEAD(dev_edac_list);
+ static bool skx_mem_cfg_2lm;
+
+-int __init skx_adxl_get(void)
++int skx_adxl_get(void)
+ {
+ const char * const *names;
+ int i, j;
+@@ -110,12 +110,14 @@ int __init skx_adxl_get(void)
+
+ return -ENODEV;
+ }
++EXPORT_SYMBOL_GPL(skx_adxl_get);
+
+-void __exit skx_adxl_put(void)
++void skx_adxl_put(void)
+ {
+ kfree(adxl_values);
+ kfree(adxl_msg);
+ }
++EXPORT_SYMBOL_GPL(skx_adxl_put);
+
+ static bool skx_adxl_decode(struct decoded_addr *res, bool error_in_1st_level_mem)
+ {
+@@ -187,12 +189,14 @@ void skx_set_mem_cfg(bool mem_cfg_2lm)
+ {
+ skx_mem_cfg_2lm = mem_cfg_2lm;
+ }
++EXPORT_SYMBOL_GPL(skx_set_mem_cfg);
+
+ void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log)
+ {
+ driver_decode = decode;
+ skx_show_retry_rd_err_log = show_retry_log;
+ }
++EXPORT_SYMBOL_GPL(skx_set_decode);
+
+ int skx_get_src_id(struct skx_dev *d, int off, u8 *id)
+ {
+@@ -206,6 +210,7 @@ int skx_get_src_id(struct skx_dev *d, int off, u8 *id)
+ *id = GET_BITFIELD(reg, 12, 14);
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(skx_get_src_id);
+
+ int skx_get_node_id(struct skx_dev *d, u8 *id)
+ {
+@@ -219,6 +224,7 @@ int skx_get_node_id(struct skx_dev *d, u8 *id)
+ *id = GET_BITFIELD(reg, 0, 2);
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(skx_get_node_id);
+
+ static int get_width(u32 mtr)
+ {
+@@ -284,6 +290,7 @@ int skx_get_all_bus_mappings(struct res_config *cfg, struct list_head **list)
+ *list = &dev_edac_list;
+ return ndev;
+ }
++EXPORT_SYMBOL_GPL(skx_get_all_bus_mappings);
+
+ int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm)
+ {
+@@ -323,6 +330,7 @@ int skx_get_hi_lo(unsigned int did, int off[], u64 *tolm, u64 *tohm)
+ pci_dev_put(pdev);
+ return -ENODEV;
+ }
++EXPORT_SYMBOL_GPL(skx_get_hi_lo);
+
+ static int skx_get_dimm_attr(u32 reg, int lobit, int hibit, int add,
+ int minval, int maxval, const char *name)
+@@ -394,6 +402,7 @@ int skx_get_dimm_info(u32 mtr, u32 mcmtr, u32 amap, struct dimm_info *dimm,
+
+ return 1;
+ }
++EXPORT_SYMBOL_GPL(skx_get_dimm_info);
+
+ int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc,
+ int chan, int dimmno, const char *mod_str)
+@@ -442,6 +451,7 @@ int skx_get_nvdimm_info(struct dimm_info *dimm, struct skx_imc *imc,
+
+ return (size == 0 || size == ~0ull) ? 0 : 1;
+ }
++EXPORT_SYMBOL_GPL(skx_get_nvdimm_info);
+
+ int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev,
+ const char *ctl_name, const char *mod_str,
+@@ -512,6 +522,7 @@ int skx_register_mci(struct skx_imc *imc, struct pci_dev *pdev,
+ imc->mci = NULL;
+ return rc;
+ }
++EXPORT_SYMBOL_GPL(skx_register_mci);
+
+ static void skx_unregister_mci(struct skx_imc *imc)
+ {
+@@ -688,6 +699,7 @@ int skx_mce_check_error(struct notifier_block *nb, unsigned long val,
+ mce->kflags |= MCE_HANDLED_EDAC;
+ return NOTIFY_DONE;
+ }
++EXPORT_SYMBOL_GPL(skx_mce_check_error);
+
+ void skx_remove(void)
+ {
+@@ -725,3 +737,8 @@ void skx_remove(void)
+ kfree(d);
+ }
+ }
++EXPORT_SYMBOL_GPL(skx_remove);
++
++MODULE_LICENSE("GPL v2");
++MODULE_AUTHOR("Tony Luck");
++MODULE_DESCRIPTION("MC Driver for Intel server processors");
+diff --git a/drivers/edac/skx_common.h b/drivers/edac/skx_common.h
+index b6d3607dffe27..11faf1db4fa48 100644
+--- a/drivers/edac/skx_common.h
++++ b/drivers/edac/skx_common.h
+@@ -231,8 +231,8 @@ typedef int (*get_dimm_config_f)(struct mem_ctl_info *mci,
+ typedef bool (*skx_decode_f)(struct decoded_addr *res);
+ typedef void (*skx_show_retry_log_f)(struct decoded_addr *res, char *msg, int len, bool scrub_err);
+
+-int __init skx_adxl_get(void);
+-void __exit skx_adxl_put(void);
++int skx_adxl_get(void);
++void skx_adxl_put(void);
+ void skx_set_decode(skx_decode_f decode, skx_show_retry_log_f show_retry_log);
+ void skx_set_mem_cfg(bool mem_cfg_2lm);
+
+diff --git a/drivers/firmware/efi/libstub/screen_info.c b/drivers/firmware/efi/libstub/screen_info.c
+index a51ec201ca3cb..5d3a1e32d1776 100644
+--- a/drivers/firmware/efi/libstub/screen_info.c
++++ b/drivers/firmware/efi/libstub/screen_info.c
+@@ -32,6 +32,8 @@ struct screen_info *__alloc_screen_info(void)
+ if (status != EFI_SUCCESS)
+ return NULL;
+
++ memset(si, 0, sizeof(*si));
++
+ status = efi_bs_call(install_configuration_table,
+ &screen_info_guid, si);
+ if (status == EFI_SUCCESS)
+diff --git a/drivers/firmware/efi/libstub/x86-stub.c b/drivers/firmware/efi/libstub/x86-stub.c
+index 1983fd3bf392e..99d39eda51342 100644
+--- a/drivers/firmware/efi/libstub/x86-stub.c
++++ b/drivers/firmware/efi/libstub/x86-stub.c
+@@ -469,11 +469,12 @@ void __noreturn efi_stub_entry(efi_handle_t handle,
+ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
+ efi_system_table_t *sys_table_arg)
+ {
+- static struct boot_params boot_params __page_aligned_bss;
+- struct setup_header *hdr = &boot_params.hdr;
+ efi_guid_t proto = LOADED_IMAGE_PROTOCOL_GUID;
++ struct boot_params *boot_params;
++ struct setup_header *hdr;
+ int options_size = 0;
+ efi_status_t status;
++ unsigned long alloc;
+ char *cmdline_ptr;
+
+ if (efi_is_native())
+@@ -491,6 +492,13 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
+ efi_exit(handle, status);
+ }
+
++ status = efi_allocate_pages(PARAM_SIZE, &alloc, ULONG_MAX);
++ if (status != EFI_SUCCESS)
++ efi_exit(handle, status);
++
++ boot_params = memset((void *)alloc, 0x0, PARAM_SIZE);
++ hdr = &boot_params->hdr;
++
+ /* Assign the setup_header fields that the kernel actually cares about */
+ hdr->root_flags = 1;
+ hdr->vid_mode = 0xffff;
+@@ -500,17 +508,16 @@ efi_status_t __efiapi efi_pe_entry(efi_handle_t handle,
+
+ /* Convert unicode cmdline to ascii */
+ cmdline_ptr = efi_convert_cmdline(image, &options_size);
+- if (!cmdline_ptr)
+- goto fail;
++ if (!cmdline_ptr) {
++ efi_free(PARAM_SIZE, alloc);
++ efi_exit(handle, EFI_OUT_OF_RESOURCES);
++ }
+
+ efi_set_u64_split((unsigned long)cmdline_ptr, &hdr->cmd_line_ptr,
+- &boot_params.ext_cmd_line_ptr);
++ &boot_params->ext_cmd_line_ptr);
+
+- efi_stub_entry(handle, sys_table_arg, &boot_params);
++ efi_stub_entry(handle, sys_table_arg, boot_params);
+ /* not reached */
+-
+-fail:
+- efi_exit(handle, status);
+ }
+
+ static void add_e820ext(struct boot_params *params,
+diff --git a/drivers/firmware/turris-mox-rwtm.c b/drivers/firmware/turris-mox-rwtm.c
+index 31d962cdd6eb2..3e7f186d239a2 100644
+--- a/drivers/firmware/turris-mox-rwtm.c
++++ b/drivers/firmware/turris-mox-rwtm.c
+@@ -2,7 +2,7 @@
+ /*
+ * Turris Mox rWTM firmware driver
+ *
+- * Copyright (C) 2019 Marek Behún <kabel@kernel.org>
++ * Copyright (C) 2019, 2024 Marek Behún <kabel@kernel.org>
+ */
+
+ #include <linux/armada-37xx-rwtm-mailbox.h>
+@@ -174,6 +174,9 @@ static void mox_rwtm_rx_callback(struct mbox_client *cl, void *data)
+ struct mox_rwtm *rwtm = dev_get_drvdata(cl->dev);
+ struct armada_37xx_rwtm_rx_msg *msg = data;
+
++ if (completion_done(&rwtm->cmd_done))
++ return;
++
+ rwtm->reply = *msg;
+ complete(&rwtm->cmd_done);
+ }
+@@ -199,9 +202,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm)
+ if (ret < 0)
+ return ret;
+
+- ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2);
+- if (ret < 0)
+- return ret;
++ if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2))
++ return -ETIMEDOUT;
+
+ ret = mox_get_status(MBOX_CMD_BOARD_INFO, reply->retval);
+ if (ret == -ENODATA) {
+@@ -235,9 +237,8 @@ static int mox_get_board_info(struct mox_rwtm *rwtm)
+ if (ret < 0)
+ return ret;
+
+- ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2);
+- if (ret < 0)
+- return ret;
++ if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2))
++ return -ETIMEDOUT;
+
+ ret = mox_get_status(MBOX_CMD_ECDSA_PUB_KEY, reply->retval);
+ if (ret == -ENODATA) {
+@@ -274,9 +275,8 @@ static int check_get_random_support(struct mox_rwtm *rwtm)
+ if (ret < 0)
+ return ret;
+
+- ret = wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2);
+- if (ret < 0)
+- return ret;
++ if (!wait_for_completion_timeout(&rwtm->cmd_done, HZ / 2))
++ return -ETIMEDOUT;
+
+ return mox_get_status(MBOX_CMD_GET_RANDOM, rwtm->reply.retval);
+ }
+@@ -499,6 +499,7 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev)
+ platform_set_drvdata(pdev, rwtm);
+
+ mutex_init(&rwtm->busy);
++ init_completion(&rwtm->cmd_done);
+
+ rwtm->mbox_client.dev = dev;
+ rwtm->mbox_client.rx_callback = mox_rwtm_rx_callback;
+@@ -512,8 +513,6 @@ static int turris_mox_rwtm_probe(struct platform_device *pdev)
+ goto remove_files;
+ }
+
+- init_completion(&rwtm->cmd_done);
+-
+ ret = mox_get_board_info(rwtm);
+ if (ret < 0)
+ dev_warn(dev, "Cannot read board information: %i\n", ret);
+diff --git a/drivers/gpu/drm/Kconfig b/drivers/gpu/drm/Kconfig
+index d0aa277fc3bff..359b68adafc1b 100644
+--- a/drivers/gpu/drm/Kconfig
++++ b/drivers/gpu/drm/Kconfig
+@@ -106,8 +106,7 @@ config DRM_KMS_HELPER
+
+ config DRM_PANIC
+ bool "Display a user-friendly message when a kernel panic occurs"
+- depends on DRM && !FRAMEBUFFER_CONSOLE
+- select DRM_KMS_HELPER
++ depends on DRM && !(FRAMEBUFFER_CONSOLE && VT_CONSOLE)
+ select FONT_SUPPORT
+ help
+ Enable a drm panic handler, which will display a user-friendly message
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+index 33f791d92ddf3..ee7df1d84e028 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_device.c
+@@ -6173,7 +6173,7 @@ int amdgpu_device_baco_exit(struct drm_device *dev)
+ adev->nbio.funcs->enable_doorbell_interrupt)
+ adev->nbio.funcs->enable_doorbell_interrupt(adev, true);
+
+- if (amdgpu_passthrough(adev) &&
++ if (amdgpu_passthrough(adev) && adev->nbio.funcs &&
+ adev->nbio.funcs->clear_doorbell_interrupt)
+ adev->nbio.funcs->clear_doorbell_interrupt(adev);
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+index 1d955652f3ba6..e92bdc9a39d35 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c
+@@ -329,8 +329,9 @@ int amdgpu_gfx_kiq_init_ring(struct amdgpu_device *adev, int xcc_id)
+
+ ring->eop_gpu_addr = kiq->eop_gpu_addr;
+ ring->no_scheduler = true;
+- snprintf(ring->name, sizeof(ring->name), "kiq_%d.%d.%d.%d",
+- xcc_id, ring->me, ring->pipe, ring->queue);
++ snprintf(ring->name, sizeof(ring->name), "kiq_%hhu.%hhu.%hhu.%hhu",
++ (unsigned char)xcc_id, (unsigned char)ring->me,
++ (unsigned char)ring->pipe, (unsigned char)ring->queue);
+ r = amdgpu_ring_init(adev, ring, 1024, irq, AMDGPU_CP_KIQ_IRQ_DRIVER0,
+ AMDGPU_RING_PRIO_DEFAULT, NULL);
+ if (r)
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+index 08b9dfb653355..86b096ad0319c 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gmc.c
+@@ -878,7 +878,6 @@ void amdgpu_gmc_noretry_set(struct amdgpu_device *adev)
+ struct amdgpu_gmc *gmc = &adev->gmc;
+ uint32_t gc_ver = amdgpu_ip_version(adev, GC_HWIP, 0);
+ bool noretry_default = (gc_ver == IP_VERSION(9, 0, 1) ||
+- gc_ver == IP_VERSION(9, 3, 0) ||
+ gc_ver == IP_VERSION(9, 4, 0) ||
+ gc_ver == IP_VERSION(9, 4, 1) ||
+ gc_ver == IP_VERSION(9, 4, 2) ||
+diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+index 4e2391c83d7c7..0f7106066480e 100644
+--- a/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
++++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_vm.c
+@@ -434,7 +434,7 @@ uint64_t amdgpu_vm_generation(struct amdgpu_device *adev, struct amdgpu_vm *vm)
+ if (!vm)
+ return result;
+
+- result += vm->generation;
++ result += lower_32_bits(vm->generation);
+ /* Add one if the page tables will be re-generated on next CS */
+ if (drm_sched_entity_error(&vm->delayed))
+ ++result;
+@@ -463,13 +463,14 @@ int amdgpu_vm_validate(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+ int (*validate)(void *p, struct amdgpu_bo *bo),
+ void *param)
+ {
++ uint64_t new_vm_generation = amdgpu_vm_generation(adev, vm);
+ struct amdgpu_vm_bo_base *bo_base;
+ struct amdgpu_bo *shadow;
+ struct amdgpu_bo *bo;
+ int r;
+
+- if (drm_sched_entity_error(&vm->delayed)) {
+- ++vm->generation;
++ if (vm->generation != new_vm_generation) {
++ vm->generation = new_vm_generation;
+ amdgpu_vm_bo_reset_state_machine(vm);
+ amdgpu_vm_fini_entities(vm);
+ r = amdgpu_vm_init_entities(adev, vm);
+@@ -2441,7 +2442,7 @@ int amdgpu_vm_init(struct amdgpu_device *adev, struct amdgpu_vm *vm,
+ vm->last_update = dma_fence_get_stub();
+ vm->last_unlocked = dma_fence_get_stub();
+ vm->last_tlb_flush = dma_fence_get_stub();
+- vm->generation = 0;
++ vm->generation = amdgpu_vm_generation(adev, NULL);
+
+ mutex_init(&vm->eviction_lock);
+ vm->evicting = false;
+diff --git a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+index c4ec1358f3aa6..f7f4924751020 100644
+--- a/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/gmc_v9_0.c
+@@ -1910,7 +1910,7 @@ gmc_v9_0_init_sw_mem_ranges(struct amdgpu_device *adev,
+ break;
+ }
+
+- size = adev->gmc.real_vram_size >> AMDGPU_GPU_PAGE_SHIFT;
++ size = (adev->gmc.real_vram_size + SZ_16M) >> AMDGPU_GPU_PAGE_SHIFT;
+ size /= adev->gmc.num_mem_partitions;
+
+ for (i = 0; i < adev->gmc.num_mem_partitions; ++i) {
+diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+index cc9e961f00787..af1e90159ce36 100644
+--- a/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
++++ b/drivers/gpu/drm/amd/amdgpu/sdma_v5_2.c
+@@ -176,6 +176,14 @@ static void sdma_v5_2_ring_set_wptr(struct amdgpu_ring *ring)
+ DRM_DEBUG("calling WDOORBELL64(0x%08x, 0x%016llx)\n",
+ ring->doorbell_index, ring->wptr << 2);
+ WDOORBELL64(ring->doorbell_index, ring->wptr << 2);
++ /* SDMA seems to miss doorbells sometimes when powergating kicks in.
++ * Updating the wptr directly will wake it. This is only safe because
++ * we disallow gfxoff in begin_use() and then allow it again in end_use().
++ */
++ WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR),
++ lower_32_bits(ring->wptr << 2));
++ WREG32(sdma_v5_2_get_reg_offset(adev, ring->me, mmSDMA0_GFX_RB_WPTR_HI),
++ upper_32_bits(ring->wptr << 2));
+ } else {
+ DRM_DEBUG("Not using doorbell -- "
+ "mmSDMA%i_GFX_RB_WPTR == 0x%08x "
+@@ -1647,6 +1655,10 @@ static void sdma_v5_2_ring_begin_use(struct amdgpu_ring *ring)
+ * but it shouldn't hurt for other parts since
+ * this GFXOFF will be disallowed anyway when SDMA is
+ * active, this just makes it explicit.
++ * sdma_v5_2_ring_set_wptr() takes advantage of this
++ * to update the wptr because sometimes SDMA seems to miss
++ * doorbells when entering PG. If you remove this, update
++ * sdma_v5_2_ring_set_wptr() as well!
+ */
+ amdgpu_gfx_off_ctrl(adev, false);
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
+index 04c797d54511b..0af648931df58 100644
+--- a/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
++++ b/drivers/gpu/drm/amd/amdgpu/smu_v13_0_10.c
+@@ -91,7 +91,7 @@ static int smu_v13_0_10_mode2_suspend_ip(struct amdgpu_device *adev)
+ adev->ip_blocks[i].status.hw = false;
+ }
+
+- return r;
++ return 0;
+ }
+
+ static int
+diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+index ac1b8ead03b3b..9a33d3d000655 100644
+--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0.c
+@@ -1053,6 +1053,9 @@ static int vcn_v4_0_start(struct amdgpu_device *adev)
+ amdgpu_dpm_enable_uvd(adev, true);
+
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
++ if (adev->vcn.harvest_config & (1 << i))
++ continue;
++
+ fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+
+ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+@@ -1506,6 +1509,9 @@ static int vcn_v4_0_stop(struct amdgpu_device *adev)
+ int i, r = 0;
+
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
++ if (adev->vcn.harvest_config & (1 << i))
++ continue;
++
+ fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+ fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+index 81fb99729f37d..30e80c6f11ed6 100644
+--- a/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
++++ b/drivers/gpu/drm/amd/amdgpu/vcn_v4_0_5.c
+@@ -964,6 +964,9 @@ static int vcn_v4_0_5_start(struct amdgpu_device *adev)
+ amdgpu_dpm_enable_uvd(adev, true);
+
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
++ if (adev->vcn.harvest_config & (1 << i))
++ continue;
++
+ fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+
+ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+@@ -1168,6 +1171,9 @@ static int vcn_v4_0_5_stop(struct amdgpu_device *adev)
+ int i, r = 0;
+
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
++ if (adev->vcn.harvest_config & (1 << i))
++ continue;
++
+ fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+ fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+
+diff --git a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+index 851975b5ce298..fbd3f7a582c12 100644
+--- a/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/vcn_v5_0_0.c
+@@ -722,6 +722,9 @@ static int vcn_v5_0_0_start(struct amdgpu_device *adev)
+ amdgpu_dpm_enable_uvd(adev, true);
+
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
++ if (adev->vcn.harvest_config & (1 << i))
++ continue;
++
+ fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+
+ if (adev->pg_flags & AMD_PG_SUPPORT_VCN_DPG) {
+@@ -899,6 +902,9 @@ static int vcn_v5_0_0_stop(struct amdgpu_device *adev)
+ int i, r = 0;
+
+ for (i = 0; i < adev->vcn.num_vcn_inst; ++i) {
++ if (adev->vcn.harvest_config & (1 << i))
++ continue;
++
+ fw_shared = adev->vcn.inst[i].fw_shared.cpu_addr;
+ fw_shared->sq.queue_mode |= FW_QUEUE_DPG_HOLD_OFF;
+
+diff --git a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+index 6bddc16808d7a..8ec136eba54a9 100644
+--- a/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
++++ b/drivers/gpu/drm/amd/amdkfd/kfd_mqd_manager_v9.c
+@@ -713,7 +713,7 @@ static void update_mqd_v9_4_3(struct mqd_manager *mm, void *mqd,
+ m = get_mqd(mqd + size * xcc);
+ update_mqd(mm, m, q, minfo);
+
+- update_cu_mask(mm, mqd, minfo, xcc);
++ update_cu_mask(mm, m, minfo, xcc);
+
+ if (q->format == KFD_QUEUE_FORMAT_AQL) {
+ switch (xcc) {
+diff --git a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+index 067f6555cfdff..ccbb15f1638c8 100644
+--- a/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
++++ b/drivers/gpu/drm/amd/display/dc/core/dc_surface.c
+@@ -143,7 +143,8 @@ const struct dc_plane_status *dc_plane_get_status(
+ if (pipe_ctx->plane_state != plane_state)
+ continue;
+
+- pipe_ctx->plane_state->status.is_flip_pending = false;
++ if (pipe_ctx->plane_state)
++ pipe_ctx->plane_state->status.is_flip_pending = false;
+
+ break;
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/dc.h b/drivers/gpu/drm/amd/display/dc/dc.h
+index 3c33c3bcbe2cb..4362fca1f15ad 100644
+--- a/drivers/gpu/drm/amd/display/dc/dc.h
++++ b/drivers/gpu/drm/amd/display/dc/dc.h
+@@ -1392,6 +1392,7 @@ struct dc {
+ } scratch;
+
+ struct dml2_configuration_options dml2_options;
++ struct dml2_configuration_options dml2_tmp;
+ enum dc_acpi_cm_power_state power_state;
+
+ };
+diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c
+index 282d70e2b18ab..3d29169dd6bbf 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c
++++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_mall_phantom.c
+@@ -750,6 +750,8 @@ static void enable_phantom_plane(struct dml2_context *ctx,
+ ctx->config.svp_pstate.callbacks.dc,
+ state,
+ curr_pipe->plane_state);
++ if (!phantom_plane)
++ return;
+ }
+
+ memcpy(&phantom_plane->address, &curr_pipe->plane_state->address, sizeof(phantom_plane->address));
+diff --git a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+index 8ecc972dbffde..edff6b447680c 100644
+--- a/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
++++ b/drivers/gpu/drm/amd/display/dc/dml2/dml2_translation_helper.c
+@@ -804,7 +804,7 @@ static void populate_dml_surface_cfg_from_plane_state(enum dml_project_id dml2_p
+ }
+ }
+
+-static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context)
++static void get_scaler_data_for_plane(const struct dc_plane_state *in, struct dc_state *context, struct scaler_data *out)
+ {
+ int i;
+ struct pipe_ctx *temp_pipe = &context->res_ctx.temp_pipe;
+@@ -825,7 +825,7 @@ static struct scaler_data get_scaler_data_for_plane(const struct dc_plane_state
+ }
+
+ ASSERT(i < MAX_PIPES);
+- return temp_pipe->plane_res.scl_data;
++ memcpy(out, &temp_pipe->plane_res.scl_data, sizeof(*out));
+ }
+
+ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_stream_state *in)
+@@ -884,27 +884,31 @@ static void populate_dummy_dml_plane_cfg(struct dml_plane_cfg_st *out, unsigned
+
+ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out, unsigned int location, const struct dc_plane_state *in, struct dc_state *context)
+ {
+- const struct scaler_data scaler_data = get_scaler_data_for_plane(in, context);
++ struct scaler_data *scaler_data = kzalloc(sizeof(*scaler_data), GFP_KERNEL);
++ if (!scaler_data)
++ return;
++
++ get_scaler_data_for_plane(in, context, scaler_data);
+
+ out->CursorBPP[location] = dml_cur_32bit;
+ out->CursorWidth[location] = 256;
+
+ out->GPUVMMinPageSizeKBytes[location] = 256;
+
+- out->ViewportWidth[location] = scaler_data.viewport.width;
+- out->ViewportHeight[location] = scaler_data.viewport.height;
+- out->ViewportWidthChroma[location] = scaler_data.viewport_c.width;
+- out->ViewportHeightChroma[location] = scaler_data.viewport_c.height;
+- out->ViewportXStart[location] = scaler_data.viewport.x;
+- out->ViewportYStart[location] = scaler_data.viewport.y;
+- out->ViewportXStartC[location] = scaler_data.viewport_c.x;
+- out->ViewportYStartC[location] = scaler_data.viewport_c.y;
++ out->ViewportWidth[location] = scaler_data->viewport.width;
++ out->ViewportHeight[location] = scaler_data->viewport.height;
++ out->ViewportWidthChroma[location] = scaler_data->viewport_c.width;
++ out->ViewportHeightChroma[location] = scaler_data->viewport_c.height;
++ out->ViewportXStart[location] = scaler_data->viewport.x;
++ out->ViewportYStart[location] = scaler_data->viewport.y;
++ out->ViewportXStartC[location] = scaler_data->viewport_c.x;
++ out->ViewportYStartC[location] = scaler_data->viewport_c.y;
+ out->ViewportStationary[location] = false;
+
+- out->ScalerEnabled[location] = scaler_data.ratios.horz.value != dc_fixpt_one.value ||
+- scaler_data.ratios.horz_c.value != dc_fixpt_one.value ||
+- scaler_data.ratios.vert.value != dc_fixpt_one.value ||
+- scaler_data.ratios.vert_c.value != dc_fixpt_one.value;
++ out->ScalerEnabled[location] = scaler_data->ratios.horz.value != dc_fixpt_one.value ||
++ scaler_data->ratios.horz_c.value != dc_fixpt_one.value ||
++ scaler_data->ratios.vert.value != dc_fixpt_one.value ||
++ scaler_data->ratios.vert_c.value != dc_fixpt_one.value;
+
+ /* Current driver code base uses LBBitPerPixel as 57. There is a discrepancy
+ * from the HW/DML teams about this value. Initialize LBBitPerPixel with the
+@@ -920,25 +924,25 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
+ out->VRatioChroma[location] = 1;
+ } else {
+ /* Follow the original dml_wrapper.c code direction to fix scaling issues */
+- out->HRatio[location] = (dml_float_t)scaler_data.ratios.horz.value / (1ULL << 32);
+- out->HRatioChroma[location] = (dml_float_t)scaler_data.ratios.horz_c.value / (1ULL << 32);
+- out->VRatio[location] = (dml_float_t)scaler_data.ratios.vert.value / (1ULL << 32);
+- out->VRatioChroma[location] = (dml_float_t)scaler_data.ratios.vert_c.value / (1ULL << 32);
++ out->HRatio[location] = (dml_float_t)scaler_data->ratios.horz.value / (1ULL << 32);
++ out->HRatioChroma[location] = (dml_float_t)scaler_data->ratios.horz_c.value / (1ULL << 32);
++ out->VRatio[location] = (dml_float_t)scaler_data->ratios.vert.value / (1ULL << 32);
++ out->VRatioChroma[location] = (dml_float_t)scaler_data->ratios.vert_c.value / (1ULL << 32);
+ }
+
+- if (!scaler_data.taps.h_taps) {
++ if (!scaler_data->taps.h_taps) {
+ out->HTaps[location] = 1;
+ out->HTapsChroma[location] = 1;
+ } else {
+- out->HTaps[location] = scaler_data.taps.h_taps;
+- out->HTapsChroma[location] = scaler_data.taps.h_taps_c;
++ out->HTaps[location] = scaler_data->taps.h_taps;
++ out->HTapsChroma[location] = scaler_data->taps.h_taps_c;
+ }
+- if (!scaler_data.taps.v_taps) {
++ if (!scaler_data->taps.v_taps) {
+ out->VTaps[location] = 1;
+ out->VTapsChroma[location] = 1;
+ } else {
+- out->VTaps[location] = scaler_data.taps.v_taps;
+- out->VTapsChroma[location] = scaler_data.taps.v_taps_c;
++ out->VTaps[location] = scaler_data->taps.v_taps;
++ out->VTapsChroma[location] = scaler_data->taps.v_taps_c;
+ }
+
+ out->SourceScan[location] = (enum dml_rotation_angle)in->rotation;
+@@ -949,6 +953,8 @@ static void populate_dml_plane_cfg_from_plane_state(struct dml_plane_cfg_st *out
+ out->DynamicMetadataTransmittedBytes[location] = 0;
+
+ out->NumberOfCursors[location] = 1;
++
++ kfree(scaler_data);
+ }
+
+ static unsigned int map_stream_to_dml_display_cfg(const struct dml2_context *dml2,
+diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
+index 5574bc628053c..f109a101d84f3 100644
+--- a/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
++++ b/drivers/gpu/drm/amd/display/dc/optc/dcn10/dcn10_optc.c
+@@ -945,19 +945,10 @@ void optc1_set_drr(
+ OTG_FORCE_LOCK_ON_EVENT, 0,
+ OTG_SET_V_TOTAL_MIN_MASK_EN, 0,
+ OTG_SET_V_TOTAL_MIN_MASK, 0);
+-
+- // Setup manual flow control for EOF via TRIG_A
+- optc->funcs->setup_manual_trigger(optc);
+-
+- } else {
+- REG_UPDATE_4(OTG_V_TOTAL_CONTROL,
+- OTG_SET_V_TOTAL_MIN_MASK, 0,
+- OTG_V_TOTAL_MIN_SEL, 0,
+- OTG_V_TOTAL_MAX_SEL, 0,
+- OTG_FORCE_LOCK_ON_EVENT, 0);
+-
+- optc->funcs->set_vtotal_min_max(optc, 0, 0);
+ }
++
++ // Setup manual flow control for EOF via TRIG_A
++ optc->funcs->setup_manual_trigger(optc);
+ }
+
+ void optc1_set_vtotal_min_max(struct timing_generator *optc, int vtotal_min, int vtotal_max)
+diff --git a/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c b/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
+index d6f095b4555dc..58bdbd859bf9b 100644
+--- a/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
++++ b/drivers/gpu/drm/amd/display/dc/optc/dcn20/dcn20_optc.c
+@@ -462,6 +462,16 @@ void optc2_setup_manual_trigger(struct timing_generator *optc)
+ {
+ struct optc *optc1 = DCN10TG_FROM_TG(optc);
+
++ /* Set the min/max selectors unconditionally so that
++ * DMCUB fw may change OTG timings when necessary
++ * TODO: Remove the w/a after fixing the issue in DMCUB firmware
++ */
++ REG_UPDATE_4(OTG_V_TOTAL_CONTROL,
++ OTG_V_TOTAL_MIN_SEL, 1,
++ OTG_V_TOTAL_MAX_SEL, 1,
++ OTG_FORCE_LOCK_ON_EVENT, 0,
++ OTG_SET_V_TOTAL_MIN_MASK, (1 << 1)); /* TRIGA */
++
+ REG_SET_8(OTG_TRIGA_CNTL, 0,
+ OTG_TRIGA_SOURCE_SELECT, 21,
+ OTG_TRIGA_SOURCE_PIPE_SELECT, optc->inst,
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+index abd76345d1e43..d84c8e0e5c2f0 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn32/dcn32_resource.c
+@@ -2006,19 +2006,21 @@ void dcn32_calculate_wm_and_dlg(struct dc *dc, struct dc_state *context,
+
+ static void dcn32_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
+ {
+- struct dml2_configuration_options dml2_opt = dc->dml2_options;
++ struct dml2_configuration_options *dml2_opt = &dc->dml2_tmp;
++
++ memcpy(dml2_opt, &dc->dml2_options, sizeof(dc->dml2_options));
+
+ DC_FP_START();
+
+ dcn32_update_bw_bounding_box_fpu(dc, bw_params);
+
+- dml2_opt.use_clock_dc_limits = false;
++ dml2_opt->use_clock_dc_limits = false;
+ if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2)
+- dml2_reinit(dc, &dml2_opt, &dc->current_state->bw_ctx.dml2);
++ dml2_reinit(dc, dml2_opt, &dc->current_state->bw_ctx.dml2);
+
+- dml2_opt.use_clock_dc_limits = true;
++ dml2_opt->use_clock_dc_limits = true;
+ if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2_dc_power_source)
+- dml2_reinit(dc, &dml2_opt, &dc->current_state->bw_ctx.dml2_dc_power_source);
++ dml2_reinit(dc, dml2_opt, &dc->current_state->bw_ctx.dml2_dc_power_source);
+
+ DC_FP_END();
+ }
+diff --git a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+index e4b360d89b3be..9a3cc0514a36e 100644
+--- a/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
++++ b/drivers/gpu/drm/amd/display/dc/resource/dcn321/dcn321_resource.c
+@@ -1581,19 +1581,21 @@ static struct dc_cap_funcs cap_funcs = {
+
+ static void dcn321_update_bw_bounding_box(struct dc *dc, struct clk_bw_params *bw_params)
+ {
+- struct dml2_configuration_options dml2_opt = dc->dml2_options;
++ struct dml2_configuration_options *dml2_opt = &dc->dml2_tmp;
++
++ memcpy(dml2_opt, &dc->dml2_options, sizeof(dc->dml2_options));
+
+ DC_FP_START();
+
+ dcn321_update_bw_bounding_box_fpu(dc, bw_params);
+
+- dml2_opt.use_clock_dc_limits = false;
++ dml2_opt->use_clock_dc_limits = false;
+ if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2)
+- dml2_reinit(dc, &dml2_opt, &dc->current_state->bw_ctx.dml2);
++ dml2_reinit(dc, dml2_opt, &dc->current_state->bw_ctx.dml2);
+
+- dml2_opt.use_clock_dc_limits = true;
++ dml2_opt->use_clock_dc_limits = true;
+ if (dc->debug.using_dml2 && dc->current_state && dc->current_state->bw_ctx.dml2_dc_power_source)
+- dml2_reinit(dc, &dml2_opt, &dc->current_state->bw_ctx.dml2_dc_power_source);
++ dml2_reinit(dc, dml2_opt, &dc->current_state->bw_ctx.dml2_dc_power_source);
+
+ DC_FP_END();
+ }
+diff --git a/drivers/gpu/drm/amd/display/include/grph_object_id.h b/drivers/gpu/drm/amd/display/include/grph_object_id.h
+index 08ee0350b31fb..54e33062b3c02 100644
+--- a/drivers/gpu/drm/amd/display/include/grph_object_id.h
++++ b/drivers/gpu/drm/amd/display/include/grph_object_id.h
+@@ -226,8 +226,8 @@ enum dp_alt_mode {
+
+ struct graphics_object_id {
+ uint32_t id:8;
+- enum object_enum_id enum_id;
+- enum object_type type;
++ enum object_enum_id enum_id :4;
++ enum object_type type :4;
+ uint32_t reserved:16; /* for padding. total size should be u32 */
+ };
+
+diff --git a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+index a8d34adc7d3f1..b63ad9cb24bfd 100644
+--- a/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
++++ b/drivers/gpu/drm/amd/pm/swsmu/smu13/smu_v13_0.c
+@@ -79,8 +79,8 @@ MODULE_FIRMWARE("amdgpu/smu_13_0_10.bin");
+ #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD_MASK 0x00000070L
+ #define PCIE_LC_LINK_WIDTH_CNTL__LC_LINK_WIDTH_RD__SHIFT 0x4
+ #define smnPCIE_LC_SPEED_CNTL 0x11140290
+-#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xC000
+-#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0xE
++#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE_MASK 0xE0
++#define PCIE_LC_SPEED_CNTL__LC_CURRENT_DATA_RATE__SHIFT 0x5
+
+ #define ENABLE_IMU_ARG_GFXOFF_ENABLE 1
+
+diff --git a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
+index 2c661f28410ed..b645c5998230b 100644
+--- a/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
++++ b/drivers/gpu/drm/arm/display/komeda/komeda_crtc.c
+@@ -5,6 +5,7 @@
+ *
+ */
+ #include <linux/clk.h>
++#include <linux/of.h>
+ #include <linux/pm_runtime.h>
+ #include <linux/spinlock.h>
+
+@@ -610,12 +611,34 @@ get_crtc_primary(struct komeda_kms_dev *kms, struct komeda_crtc *crtc)
+ return NULL;
+ }
+
++static int komeda_attach_bridge(struct device *dev,
++ struct komeda_pipeline *pipe,
++ struct drm_encoder *encoder)
++{
++ struct drm_bridge *bridge;
++ int err;
++
++ bridge = devm_drm_of_get_bridge(dev, pipe->of_node,
++ KOMEDA_OF_PORT_OUTPUT, 0);
++ if (IS_ERR(bridge))
++ return dev_err_probe(dev, PTR_ERR(bridge), "remote bridge not found for pipe: %s\n",
++ of_node_full_name(pipe->of_node));
++
++ err = drm_bridge_attach(encoder, bridge, NULL, 0);
++ if (err)
++ dev_err(dev, "bridge_attach() failed for pipe: %s\n",
++ of_node_full_name(pipe->of_node));
++
++ return err;
++}
++
+ static int komeda_crtc_add(struct komeda_kms_dev *kms,
+ struct komeda_crtc *kcrtc)
+ {
+ struct drm_crtc *crtc = &kcrtc->base;
+ struct drm_device *base = &kms->base;
+- struct drm_bridge *bridge;
++ struct komeda_pipeline *pipe = kcrtc->master;
++ struct drm_encoder *encoder = &kcrtc->encoder;
+ int err;
+
+ err = drm_crtc_init_with_planes(base, crtc,
+@@ -626,27 +649,25 @@ static int komeda_crtc_add(struct komeda_kms_dev *kms,
+
+ drm_crtc_helper_add(crtc, &komeda_crtc_helper_funcs);
+
+- crtc->port = kcrtc->master->of_output_port;
++ crtc->port = pipe->of_output_port;
+
+ /* Construct an encoder for each pipeline and attach it to the remote
+ * bridge
+ */
+ kcrtc->encoder.possible_crtcs = drm_crtc_mask(crtc);
+- err = drm_simple_encoder_init(base, &kcrtc->encoder,
+- DRM_MODE_ENCODER_TMDS);
++ err = drm_simple_encoder_init(base, encoder, DRM_MODE_ENCODER_TMDS);
+ if (err)
+ return err;
+
+- bridge = devm_drm_of_get_bridge(base->dev, kcrtc->master->of_node,
+- KOMEDA_OF_PORT_OUTPUT, 0);
+- if (IS_ERR(bridge))
+- return PTR_ERR(bridge);
+-
+- err = drm_bridge_attach(&kcrtc->encoder, bridge, NULL, 0);
++ if (pipe->of_output_links[0]) {
++ err = komeda_attach_bridge(base->dev, pipe, encoder);
++ if (err)
++ return err;
++ }
+
+ drm_crtc_enable_color_mgmt(crtc, 0, true, KOMEDA_COLOR_LUT_SIZE);
+
+- return err;
++ return 0;
+ }
+
+ int komeda_kms_add_crtcs(struct komeda_kms_dev *kms, struct komeda_dev *mdev)
+diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511.h b/drivers/gpu/drm/bridge/adv7511/adv7511.h
+index ea271f62b214d..ec0b7f3d889c4 100644
+--- a/drivers/gpu/drm/bridge/adv7511/adv7511.h
++++ b/drivers/gpu/drm/bridge/adv7511/adv7511.h
+@@ -401,7 +401,7 @@ struct adv7511 {
+
+ #ifdef CONFIG_DRM_I2C_ADV7511_CEC
+ int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511);
+-void adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1);
++int adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1);
+ #else
+ static inline int adv7511_cec_init(struct device *dev, struct adv7511 *adv7511)
+ {
+diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c b/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c
+index 44451a9658a32..2e9c88a2b5ed4 100644
+--- a/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c
++++ b/drivers/gpu/drm/bridge/adv7511/adv7511_cec.c
+@@ -119,7 +119,7 @@ static void adv7511_cec_rx(struct adv7511 *adv7511, int rx_buf)
+ cec_received_msg(adv7511->cec_adap, &msg);
+ }
+
+-void adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1)
++int adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1)
+ {
+ unsigned int offset = adv7511->info->reg_cec_offset;
+ const u32 irq_tx_mask = ADV7511_INT1_CEC_TX_READY |
+@@ -131,16 +131,19 @@ void adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1)
+ unsigned int rx_status;
+ int rx_order[3] = { -1, -1, -1 };
+ int i;
++ int irq_status = IRQ_NONE;
+
+- if (irq1 & irq_tx_mask)
++ if (irq1 & irq_tx_mask) {
+ adv_cec_tx_raw_status(adv7511, irq1);
++ irq_status = IRQ_HANDLED;
++ }
+
+ if (!(irq1 & irq_rx_mask))
+- return;
++ return irq_status;
+
+ if (regmap_read(adv7511->regmap_cec,
+ ADV7511_REG_CEC_RX_STATUS + offset, &rx_status))
+- return;
++ return irq_status;
+
+ /*
+ * ADV7511_REG_CEC_RX_STATUS[5:0] contains the reception order of RX
+@@ -172,6 +175,8 @@ void adv7511_cec_irq_process(struct adv7511 *adv7511, unsigned int irq1)
+
+ adv7511_cec_rx(adv7511, rx_buf);
+ }
++
++ return IRQ_HANDLED;
+ }
+
+ static int adv7511_cec_adap_enable(struct cec_adapter *adap, bool enable)
+diff --git a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+index 66ccb61e2a660..c8d2c4a157b24 100644
+--- a/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
++++ b/drivers/gpu/drm/bridge/adv7511/adv7511_drv.c
+@@ -469,6 +469,8 @@ static int adv7511_irq_process(struct adv7511 *adv7511, bool process_hpd)
+ {
+ unsigned int irq0, irq1;
+ int ret;
++ int cec_status = IRQ_NONE;
++ int irq_status = IRQ_NONE;
+
+ ret = regmap_read(adv7511->regmap, ADV7511_REG_INT(0), &irq0);
+ if (ret < 0)
+@@ -478,29 +480,31 @@ static int adv7511_irq_process(struct adv7511 *adv7511, bool process_hpd)
+ if (ret < 0)
+ return ret;
+
+- /* If there is no IRQ to handle, exit indicating no IRQ data */
+- if (!(irq0 & (ADV7511_INT0_HPD | ADV7511_INT0_EDID_READY)) &&
+- !(irq1 & ADV7511_INT1_DDC_ERROR))
+- return -ENODATA;
+-
+ regmap_write(adv7511->regmap, ADV7511_REG_INT(0), irq0);
+ regmap_write(adv7511->regmap, ADV7511_REG_INT(1), irq1);
+
+- if (process_hpd && irq0 & ADV7511_INT0_HPD && adv7511->bridge.encoder)
++ if (process_hpd && irq0 & ADV7511_INT0_HPD && adv7511->bridge.encoder) {
+ schedule_work(&adv7511->hpd_work);
++ irq_status = IRQ_HANDLED;
++ }
+
+ if (irq0 & ADV7511_INT0_EDID_READY || irq1 & ADV7511_INT1_DDC_ERROR) {
+ adv7511->edid_read = true;
+
+ if (adv7511->i2c_main->irq)
+ wake_up_all(&adv7511->wq);
++ irq_status = IRQ_HANDLED;
+ }
+
+ #ifdef CONFIG_DRM_I2C_ADV7511_CEC
+- adv7511_cec_irq_process(adv7511, irq1);
++ cec_status = adv7511_cec_irq_process(adv7511, irq1);
+ #endif
+
+- return 0;
++ /* If there is no IRQ to handle, exit indicating no IRQ data */
++ if (irq_status == IRQ_HANDLED || cec_status == IRQ_HANDLED)
++ return IRQ_HANDLED;
++
++ return IRQ_NONE;
+ }
+
+ static irqreturn_t adv7511_irq_handler(int irq, void *devid)
+@@ -509,7 +513,7 @@ static irqreturn_t adv7511_irq_handler(int irq, void *devid)
+ int ret;
+
+ ret = adv7511_irq_process(adv7511, true);
+- return ret < 0 ? IRQ_NONE : IRQ_HANDLED;
++ return ret < 0 ? IRQ_NONE : ret;
+ }
+
+ /* -----------------------------------------------------------------------------
+diff --git a/drivers/gpu/drm/bridge/ite-it6505.c b/drivers/gpu/drm/bridge/ite-it6505.c
+index 3f68c82888c2c..cf59347d3d605 100644
+--- a/drivers/gpu/drm/bridge/ite-it6505.c
++++ b/drivers/gpu/drm/bridge/ite-it6505.c
+@@ -1307,9 +1307,15 @@ static void it6505_video_reset(struct it6505 *it6505)
+ it6505_link_reset_step_train(it6505);
+ it6505_set_bits(it6505, REG_DATA_MUTE_CTRL, EN_VID_MUTE, EN_VID_MUTE);
+ it6505_set_bits(it6505, REG_INFOFRAME_CTRL, EN_VID_CTRL_PKT, 0x00);
+- it6505_set_bits(it6505, REG_RESET_CTRL, VIDEO_RESET, VIDEO_RESET);
++
++ it6505_set_bits(it6505, REG_VID_BUS_CTRL1, TX_FIFO_RESET, TX_FIFO_RESET);
++ it6505_set_bits(it6505, REG_VID_BUS_CTRL1, TX_FIFO_RESET, 0x00);
++
+ it6505_set_bits(it6505, REG_501_FIFO_CTRL, RST_501_FIFO, RST_501_FIFO);
+ it6505_set_bits(it6505, REG_501_FIFO_CTRL, RST_501_FIFO, 0x00);
++
++ it6505_set_bits(it6505, REG_RESET_CTRL, VIDEO_RESET, VIDEO_RESET);
++ usleep_range(1000, 2000);
+ it6505_set_bits(it6505, REG_RESET_CTRL, VIDEO_RESET, 0x00);
+ }
+
+@@ -2245,12 +2251,11 @@ static void it6505_link_training_work(struct work_struct *work)
+ if (ret) {
+ it6505->auto_train_retry = AUTO_TRAIN_RETRY;
+ it6505_link_train_ok(it6505);
+- return;
+ } else {
+ it6505->auto_train_retry--;
++ it6505_dump(it6505);
+ }
+
+- it6505_dump(it6505);
+ }
+
+ static void it6505_plugged_status_to_codec(struct it6505 *it6505)
+@@ -2471,31 +2476,53 @@ static void it6505_irq_link_train_fail(struct it6505 *it6505)
+ schedule_work(&it6505->link_works);
+ }
+
+-static void it6505_irq_video_fifo_error(struct it6505 *it6505)
++static bool it6505_test_bit(unsigned int bit, const unsigned int *addr)
+ {
+- struct device *dev = it6505->dev;
+-
+- DRM_DEV_DEBUG_DRIVER(dev, "video fifo overflow interrupt");
+- it6505->auto_train_retry = AUTO_TRAIN_RETRY;
+- flush_work(&it6505->link_works);
+- it6505_stop_hdcp(it6505);
+- it6505_video_reset(it6505);
++ return 1 & (addr[bit / BITS_PER_BYTE] >> (bit % BITS_PER_BYTE));
+ }
+
+-static void it6505_irq_io_latch_fifo_overflow(struct it6505 *it6505)
++static void it6505_irq_video_handler(struct it6505 *it6505, const int *int_status)
+ {
+ struct device *dev = it6505->dev;
++ int reg_0d, reg_int03;
+
+- DRM_DEV_DEBUG_DRIVER(dev, "IO latch fifo overflow interrupt");
+- it6505->auto_train_retry = AUTO_TRAIN_RETRY;
+- flush_work(&it6505->link_works);
+- it6505_stop_hdcp(it6505);
+- it6505_video_reset(it6505);
+-}
++ /*
++ * When video SCDT change with video not stable,
++ * Or video FIFO error, need video reset
++ */
+
+-static bool it6505_test_bit(unsigned int bit, const unsigned int *addr)
+-{
+- return 1 & (addr[bit / BITS_PER_BYTE] >> (bit % BITS_PER_BYTE));
++ if ((!it6505_get_video_status(it6505) &&
++ (it6505_test_bit(INT_SCDT_CHANGE, (unsigned int *)int_status))) ||
++ (it6505_test_bit(BIT_INT_IO_FIFO_OVERFLOW,
++ (unsigned int *)int_status)) ||
++ (it6505_test_bit(BIT_INT_VID_FIFO_ERROR,
++ (unsigned int *)int_status))) {
++ it6505->auto_train_retry = AUTO_TRAIN_RETRY;
++ flush_work(&it6505->link_works);
++ it6505_stop_hdcp(it6505);
++ it6505_video_reset(it6505);
++
++ usleep_range(10000, 11000);
++
++ /*
++ * Clear FIFO error IRQ to prevent fifo error -> reset loop
++ * HW will trigger SCDT change IRQ again when video stable
++ */
++
++ reg_int03 = it6505_read(it6505, INT_STATUS_03);
++ reg_0d = it6505_read(it6505, REG_SYSTEM_STS);
++
++ reg_int03 &= (BIT(INT_VID_FIFO_ERROR) | BIT(INT_IO_LATCH_FIFO_OVERFLOW));
++ it6505_write(it6505, INT_STATUS_03, reg_int03);
++
++ DRM_DEV_DEBUG_DRIVER(dev, "reg08 = 0x%02x", reg_int03);
++ DRM_DEV_DEBUG_DRIVER(dev, "reg0D = 0x%02x", reg_0d);
++
++ return;
++ }
++
++ if (it6505_test_bit(INT_SCDT_CHANGE, (unsigned int *)int_status))
++ it6505_irq_scdt(it6505);
+ }
+
+ static irqreturn_t it6505_int_threaded_handler(int unused, void *data)
+@@ -2508,15 +2535,12 @@ static irqreturn_t it6505_int_threaded_handler(int unused, void *data)
+ } irq_vec[] = {
+ { BIT_INT_HPD, it6505_irq_hpd },
+ { BIT_INT_HPD_IRQ, it6505_irq_hpd_irq },
+- { BIT_INT_SCDT, it6505_irq_scdt },
+ { BIT_INT_HDCP_FAIL, it6505_irq_hdcp_fail },
+ { BIT_INT_HDCP_DONE, it6505_irq_hdcp_done },
+ { BIT_INT_AUX_CMD_FAIL, it6505_irq_aux_cmd_fail },
+ { BIT_INT_HDCP_KSV_CHECK, it6505_irq_hdcp_ksv_check },
+ { BIT_INT_AUDIO_FIFO_ERROR, it6505_irq_audio_fifo_error },
+ { BIT_INT_LINK_TRAIN_FAIL, it6505_irq_link_train_fail },
+- { BIT_INT_VID_FIFO_ERROR, it6505_irq_video_fifo_error },
+- { BIT_INT_IO_FIFO_OVERFLOW, it6505_irq_io_latch_fifo_overflow },
+ };
+ int int_status[3], i;
+
+@@ -2546,6 +2570,7 @@ static irqreturn_t it6505_int_threaded_handler(int unused, void *data)
+ if (it6505_test_bit(irq_vec[i].bit, (unsigned int *)int_status))
+ irq_vec[i].handler(it6505);
+ }
++ it6505_irq_video_handler(it6505, (unsigned int *)int_status);
+ }
+
+ pm_runtime_put_sync(dev);
+diff --git a/drivers/gpu/drm/bridge/samsung-dsim.c b/drivers/gpu/drm/bridge/samsung-dsim.c
+index 95fedc68b0ae5..8476650c477c2 100644
+--- a/drivers/gpu/drm/bridge/samsung-dsim.c
++++ b/drivers/gpu/drm/bridge/samsung-dsim.c
+@@ -574,8 +574,8 @@ static unsigned long samsung_dsim_pll_find_pms(struct samsung_dsim *dsi,
+ u16 _m, best_m;
+ u8 _s, best_s;
+
+- p_min = DIV_ROUND_UP(fin, (12 * MHZ));
+- p_max = fin / (6 * MHZ);
++ p_min = DIV_ROUND_UP(fin, (driver_data->pll_fin_max * MHZ));
++ p_max = fin / (driver_data->pll_fin_min * MHZ);
+
+ for (_p = p_min; _p <= p_max; ++_p) {
+ for (_s = 0; _s <= 5; ++_s) {
+diff --git a/drivers/gpu/drm/display/drm_dp_mst_topology.c b/drivers/gpu/drm/display/drm_dp_mst_topology.c
+index 7f8e1cfbe19d9..68831f4e502a2 100644
+--- a/drivers/gpu/drm/display/drm_dp_mst_topology.c
++++ b/drivers/gpu/drm/display/drm_dp_mst_topology.c
+@@ -2929,7 +2929,7 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
+
+ /* FIXME: Actually do some real error handling here */
+ ret = drm_dp_mst_wait_tx_reply(mstb, txmsg);
+- if (ret <= 0) {
++ if (ret < 0) {
+ drm_err(mgr->dev, "Sending link address failed with %d\n", ret);
+ goto out;
+ }
+@@ -2981,7 +2981,7 @@ static int drm_dp_send_link_address(struct drm_dp_mst_topology_mgr *mgr,
+ mutex_unlock(&mgr->lock);
+
+ out:
+- if (ret <= 0)
++ if (ret < 0)
+ mstb->link_address_sent = false;
+ kfree(txmsg);
+ return ret < 0 ? ret : changed;
+diff --git a/drivers/gpu/drm/drm_fbdev_dma.c b/drivers/gpu/drm/drm_fbdev_dma.c
+index 13cd754af311d..77695339e4d4c 100644
+--- a/drivers/gpu/drm/drm_fbdev_dma.c
++++ b/drivers/gpu/drm/drm_fbdev_dma.c
+@@ -90,7 +90,8 @@ static int drm_fbdev_dma_helper_fb_probe(struct drm_fb_helper *fb_helper,
+ sizes->surface_width, sizes->surface_height,
+ sizes->surface_bpp);
+
+- format = drm_mode_legacy_fb_format(sizes->surface_bpp, sizes->surface_depth);
++ format = drm_driver_legacy_fb_format(dev, sizes->surface_bpp,
++ sizes->surface_depth);
+ buffer = drm_client_framebuffer_create(client, sizes->surface_width,
+ sizes->surface_height, format);
+ if (IS_ERR(buffer))
+diff --git a/drivers/gpu/drm/drm_panic.c b/drivers/gpu/drm/drm_panic.c
+index 7ece67086cecb..831b214975a51 100644
+--- a/drivers/gpu/drm/drm_panic.c
++++ b/drivers/gpu/drm/drm_panic.c
+@@ -15,7 +15,6 @@
+ #include <linux/types.h>
+
+ #include <drm/drm_drv.h>
+-#include <drm/drm_format_helper.h>
+ #include <drm/drm_fourcc.h>
+ #include <drm/drm_framebuffer.h>
+ #include <drm/drm_modeset_helper_vtables.h>
+@@ -194,40 +193,42 @@ static u32 convert_from_xrgb8888(u32 color, u32 format)
+ /*
+ * Blit & Fill
+ */
++/* check if the pixel at coord x,y is 1 (foreground) or 0 (background) */
++static bool drm_panic_is_pixel_fg(const u8 *sbuf8, unsigned int spitch, int x, int y)
++{
++ return (sbuf8[(y * spitch) + x / 8] & (0x80 >> (x % 8))) != 0;
++}
++
+ static void drm_panic_blit16(struct iosys_map *dmap, unsigned int dpitch,
+ const u8 *sbuf8, unsigned int spitch,
+ unsigned int height, unsigned int width,
+- u16 fg16, u16 bg16)
++ u16 fg16)
+ {
+ unsigned int y, x;
+- u16 val16;
+
+- for (y = 0; y < height; y++) {
+- for (x = 0; x < width; x++) {
+- val16 = (sbuf8[(y * spitch) + x / 8] & (0x80 >> (x % 8))) ? fg16 : bg16;
+- iosys_map_wr(dmap, y * dpitch + x * sizeof(u16), u16, val16);
+- }
+- }
++ for (y = 0; y < height; y++)
++ for (x = 0; x < width; x++)
++ if (drm_panic_is_pixel_fg(sbuf8, spitch, x, y))
++ iosys_map_wr(dmap, y * dpitch + x * sizeof(u16), u16, fg16);
+ }
+
+ static void drm_panic_blit24(struct iosys_map *dmap, unsigned int dpitch,
+ const u8 *sbuf8, unsigned int spitch,
+ unsigned int height, unsigned int width,
+- u32 fg32, u32 bg32)
++ u32 fg32)
+ {
+ unsigned int y, x;
+- u32 val32;
+
+ for (y = 0; y < height; y++) {
+ for (x = 0; x < width; x++) {
+ u32 off = y * dpitch + x * 3;
+
+- val32 = (sbuf8[(y * spitch) + x / 8] & (0x80 >> (x % 8))) ? fg32 : bg32;
+-
+- /* write blue-green-red to output in little endianness */
+- iosys_map_wr(dmap, off, u8, (val32 & 0x000000FF) >> 0);
+- iosys_map_wr(dmap, off + 1, u8, (val32 & 0x0000FF00) >> 8);
+- iosys_map_wr(dmap, off + 2, u8, (val32 & 0x00FF0000) >> 16);
++ if (drm_panic_is_pixel_fg(sbuf8, spitch, x, y)) {
++ /* write blue-green-red to output in little endianness */
++ iosys_map_wr(dmap, off, u8, (fg32 & 0x000000FF) >> 0);
++ iosys_map_wr(dmap, off + 1, u8, (fg32 & 0x0000FF00) >> 8);
++ iosys_map_wr(dmap, off + 2, u8, (fg32 & 0x00FF0000) >> 16);
++ }
+ }
+ }
+ }
+@@ -235,17 +236,14 @@ static void drm_panic_blit24(struct iosys_map *dmap, unsigned int dpitch,
+ static void drm_panic_blit32(struct iosys_map *dmap, unsigned int dpitch,
+ const u8 *sbuf8, unsigned int spitch,
+ unsigned int height, unsigned int width,
+- u32 fg32, u32 bg32)
++ u32 fg32)
+ {
+ unsigned int y, x;
+- u32 val32;
+
+- for (y = 0; y < height; y++) {
+- for (x = 0; x < width; x++) {
+- val32 = (sbuf8[(y * spitch) + x / 8] & (0x80 >> (x % 8))) ? fg32 : bg32;
+- iosys_map_wr(dmap, y * dpitch + x * sizeof(u32), u32, val32);
+- }
+- }
++ for (y = 0; y < height; y++)
++ for (x = 0; x < width; x++)
++ if (drm_panic_is_pixel_fg(sbuf8, spitch, x, y))
++ iosys_map_wr(dmap, y * dpitch + x * sizeof(u32), u32, fg32);
+ }
+
+ /*
+@@ -257,7 +255,6 @@ static void drm_panic_blit32(struct iosys_map *dmap, unsigned int dpitch,
+ * @height: height of the image to copy, in pixels
+ * @width: width of the image to copy, in pixels
+ * @fg_color: foreground color, in destination format
+- * @bg_color: background color, in destination format
+ * @pixel_width: pixel width in bytes.
+ *
+ * This can be used to draw a font character, which is a monochrome image, to a
+@@ -266,21 +263,20 @@ static void drm_panic_blit32(struct iosys_map *dmap, unsigned int dpitch,
+ static void drm_panic_blit(struct iosys_map *dmap, unsigned int dpitch,
+ const u8 *sbuf8, unsigned int spitch,
+ unsigned int height, unsigned int width,
+- u32 fg_color, u32 bg_color,
+- unsigned int pixel_width)
++ u32 fg_color, unsigned int pixel_width)
+ {
+ switch (pixel_width) {
+ case 2:
+ drm_panic_blit16(dmap, dpitch, sbuf8, spitch,
+- height, width, fg_color, bg_color);
++ height, width, fg_color);
+ break;
+ case 3:
+ drm_panic_blit24(dmap, dpitch, sbuf8, spitch,
+- height, width, fg_color, bg_color);
++ height, width, fg_color);
+ break;
+ case 4:
+ drm_panic_blit32(dmap, dpitch, sbuf8, spitch,
+- height, width, fg_color, bg_color);
++ height, width, fg_color);
+ break;
+ default:
+ WARN_ONCE(1, "Can't blit with pixel width %d\n", pixel_width);
+@@ -381,8 +377,7 @@ static void draw_txt_rectangle(struct drm_scanout_buffer *sb,
+ unsigned int msg_lines,
+ bool centered,
+ struct drm_rect *clip,
+- u32 fg_color,
+- u32 bg_color)
++ u32 color)
+ {
+ int i, j;
+ const u8 *src;
+@@ -404,8 +399,7 @@ static void draw_txt_rectangle(struct drm_scanout_buffer *sb,
+ for (j = 0; j < line_len; j++) {
+ src = get_char_bitmap(font, msg[i].txt[j], font_pitch);
+ drm_panic_blit(&dst, sb->pitch[0], src, font_pitch,
+- font->height, font->width,
+- fg_color, bg_color, px_width);
++ font->height, font->width, color, px_width);
+ iosys_map_incr(&dst, font->width * px_width);
+ }
+ }
+@@ -444,10 +438,10 @@ static void draw_panic_static(struct drm_scanout_buffer *sb)
+ bg_color, sb->format->cpp[0]);
+
+ if ((r_msg.x1 >= drm_rect_width(&r_logo) || r_msg.y1 >= drm_rect_height(&r_logo)) &&
+- drm_rect_width(&r_logo) < sb->width && drm_rect_height(&r_logo) < sb->height) {
+- draw_txt_rectangle(sb, font, logo, logo_lines, false, &r_logo, fg_color, bg_color);
++ drm_rect_width(&r_logo) <= sb->width && drm_rect_height(&r_logo) <= sb->height) {
++ draw_txt_rectangle(sb, font, logo, logo_lines, false, &r_logo, fg_color);
+ }
+- draw_txt_rectangle(sb, font, panic_msg, msg_lines, true, &r_msg, fg_color, bg_color);
++ draw_txt_rectangle(sb, font, panic_msg, msg_lines, true, &r_msg, fg_color);
+ }
+
+ /*
+diff --git a/drivers/gpu/drm/etnaviv/etnaviv_gem.c b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+index 71a6d2b1c80f5..5c0c9d4e3be18 100644
+--- a/drivers/gpu/drm/etnaviv/etnaviv_gem.c
++++ b/drivers/gpu/drm/etnaviv/etnaviv_gem.c
+@@ -355,9 +355,11 @@ static void *etnaviv_gem_vmap_impl(struct etnaviv_gem_object *obj)
+
+ static inline enum dma_data_direction etnaviv_op_to_dma_dir(u32 op)
+ {
+- if (op & ETNA_PREP_READ)
++ op &= ETNA_PREP_READ | ETNA_PREP_WRITE;
++
++ if (op == ETNA_PREP_READ)
+ return DMA_FROM_DEVICE;
+- else if (op & ETNA_PREP_WRITE)
++ else if (op == ETNA_PREP_WRITE)
+ return DMA_TO_DEVICE;
+ else
+ return DMA_BIDIRECTIONAL;
+diff --git a/drivers/gpu/drm/etnaviv/etnaviv_sched.c b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+index c4b04b0dee16a..62dcfdc7894dd 100644
+--- a/drivers/gpu/drm/etnaviv/etnaviv_sched.c
++++ b/drivers/gpu/drm/etnaviv/etnaviv_sched.c
+@@ -38,9 +38,6 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
+ u32 dma_addr;
+ int change;
+
+- /* block scheduler */
+- drm_sched_stop(&gpu->sched, sched_job);
+-
+ /*
+ * If the GPU managed to complete this jobs fence, the timout is
+ * spurious. Bail out.
+@@ -63,6 +60,9 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
+ goto out_no_timeout;
+ }
+
++ /* block scheduler */
++ drm_sched_stop(&gpu->sched, sched_job);
++
+ if(sched_job)
+ drm_sched_increase_karma(sched_job);
+
+@@ -76,8 +76,7 @@ static enum drm_gpu_sched_stat etnaviv_sched_timedout_job(struct drm_sched_job
+ return DRM_GPU_SCHED_STAT_NOMINAL;
+
+ out_no_timeout:
+- /* restart scheduler after GPU is usable again */
+- drm_sched_start(&gpu->sched, true);
++ list_add(&sched_job->list, &sched_job->sched->pending_list);
+ return DRM_GPU_SCHED_STAT_NOMINAL;
+ }
+
+diff --git a/drivers/gpu/drm/gma500/cdv_intel_lvds.c b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
+index f08a6803dc184..3adc2c9ab72da 100644
+--- a/drivers/gpu/drm/gma500/cdv_intel_lvds.c
++++ b/drivers/gpu/drm/gma500/cdv_intel_lvds.c
+@@ -311,6 +311,9 @@ static int cdv_intel_lvds_get_modes(struct drm_connector *connector)
+ if (mode_dev->panel_fixed_mode != NULL) {
+ struct drm_display_mode *mode =
+ drm_mode_duplicate(dev, mode_dev->panel_fixed_mode);
++ if (!mode)
++ return 0;
++
+ drm_mode_probed_add(connector, mode);
+ return 1;
+ }
+diff --git a/drivers/gpu/drm/gma500/psb_intel_lvds.c b/drivers/gpu/drm/gma500/psb_intel_lvds.c
+index 8486de230ec91..8d1be94a443b2 100644
+--- a/drivers/gpu/drm/gma500/psb_intel_lvds.c
++++ b/drivers/gpu/drm/gma500/psb_intel_lvds.c
+@@ -504,6 +504,9 @@ static int psb_intel_lvds_get_modes(struct drm_connector *connector)
+ if (mode_dev->panel_fixed_mode != NULL) {
+ struct drm_display_mode *mode =
+ drm_mode_duplicate(dev, mode_dev->panel_fixed_mode);
++ if (!mode)
++ return 0;
++
+ drm_mode_probed_add(connector, mode);
+ return 1;
+ }
+diff --git a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c
+index ccaa4cb2809b0..bddcc9edeab42 100644
+--- a/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c
++++ b/drivers/gpu/drm/i915/display/intel_crtc_state_dump.c
+@@ -251,9 +251,10 @@ void intel_crtc_state_dump(const struct intel_crtc_state *pipe_config,
+ drm_printf(&p, "sdp split: %s\n",
+ str_enabled_disabled(pipe_config->sdp_split_enable));
+
+- drm_printf(&p, "psr: %s, psr2: %s, panel replay: %s, selective fetch: %s\n",
+- str_enabled_disabled(pipe_config->has_psr),
+- str_enabled_disabled(pipe_config->has_psr2),
++ drm_printf(&p, "psr: %s, selective update: %s, panel replay: %s, selective fetch: %s\n",
++ str_enabled_disabled(pipe_config->has_psr &&
++ !pipe_config->has_panel_replay),
++ str_enabled_disabled(pipe_config->has_sel_update),
+ str_enabled_disabled(pipe_config->has_panel_replay),
+ str_enabled_disabled(pipe_config->enable_psr2_sel_fetch));
+ }
+diff --git a/drivers/gpu/drm/i915/display/intel_display.c b/drivers/gpu/drm/i915/display/intel_display.c
+index 273323f30ae29..e53d3e900b3e4 100644
+--- a/drivers/gpu/drm/i915/display/intel_display.c
++++ b/drivers/gpu/drm/i915/display/intel_display.c
+@@ -5318,9 +5318,11 @@ intel_pipe_config_compare(const struct intel_crtc_state *current_config,
+ * Panel replay has to be enabled before link training. PSR doesn't have
+ * this requirement -> check these only if using panel replay
+ */
+- if (current_config->has_panel_replay || pipe_config->has_panel_replay) {
++ if (current_config->active_planes &&
++ (current_config->has_panel_replay ||
++ pipe_config->has_panel_replay)) {
+ PIPE_CONF_CHECK_BOOL(has_psr);
+- PIPE_CONF_CHECK_BOOL(has_psr2);
++ PIPE_CONF_CHECK_BOOL(has_sel_update);
+ PIPE_CONF_CHECK_BOOL(enable_psr2_sel_fetch);
+ PIPE_CONF_CHECK_BOOL(enable_psr2_su_region_et);
+ PIPE_CONF_CHECK_BOOL(has_panel_replay);
+diff --git a/drivers/gpu/drm/i915/display/intel_display_types.h b/drivers/gpu/drm/i915/display/intel_display_types.h
+index 62f7a30c37dcf..6747c10da298e 100644
+--- a/drivers/gpu/drm/i915/display/intel_display_types.h
++++ b/drivers/gpu/drm/i915/display/intel_display_types.h
+@@ -1189,7 +1189,7 @@ struct intel_crtc_state {
+
+ /* PSR is supported but might not be enabled due the lack of enabled planes */
+ bool has_psr;
+- bool has_psr2;
++ bool has_sel_update;
+ bool enable_psr2_sel_fetch;
+ bool enable_psr2_su_region_et;
+ bool req_psr2_sdp_prior_scanline;
+diff --git a/drivers/gpu/drm/i915/display/intel_dp.c b/drivers/gpu/drm/i915/display/intel_dp.c
+index 5b3b6ae1e3d71..9c9e060476c72 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp.c
++++ b/drivers/gpu/drm/i915/display/intel_dp.c
+@@ -2664,7 +2664,7 @@ static void intel_dp_compute_vsc_sdp(struct intel_dp *intel_dp,
+ if (intel_dp_needs_vsc_sdp(crtc_state, conn_state)) {
+ intel_dp_compute_vsc_colorimetry(crtc_state, conn_state,
+ vsc);
+- } else if (crtc_state->has_psr2) {
++ } else if (crtc_state->has_sel_update) {
+ /*
+ * [PSR2 without colorimetry]
+ * Prepare VSC Header for SU as per eDP 1.4 spec, Table 6-11
+@@ -5267,6 +5267,8 @@ int intel_dp_retrain_link(struct intel_encoder *encoder,
+ !intel_dp_mst_is_master_trans(crtc_state))
+ continue;
+
++ intel_dp->link_trained = false;
++
+ intel_dp_check_frl_training(intel_dp);
+ intel_dp_pcon_dsc_configure(intel_dp, crtc_state);
+ intel_dp_start_link_train(intel_dp, crtc_state);
+diff --git a/drivers/gpu/drm/i915/display/intel_dp_link_training.c b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+index 947575140059d..8cfc55f3d98ef 100644
+--- a/drivers/gpu/drm/i915/display/intel_dp_link_training.c
++++ b/drivers/gpu/drm/i915/display/intel_dp_link_training.c
+@@ -114,10 +114,24 @@ intel_dp_set_lttpr_transparent_mode(struct intel_dp *intel_dp, bool enable)
+ return drm_dp_dpcd_write(&intel_dp->aux, DP_PHY_REPEATER_MODE, &val, 1) == 1;
+ }
+
+-static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE])
++static bool intel_dp_lttpr_transparent_mode_enabled(struct intel_dp *intel_dp)
++{
++ return intel_dp->lttpr_common_caps[DP_PHY_REPEATER_MODE -
++ DP_LT_TUNABLE_PHY_REPEATER_FIELD_DATA_STRUCTURE_REV] ==
++ DP_PHY_REPEATER_MODE_TRANSPARENT;
++}
++
++/*
++ * Read the LTTPR common capabilities and switch the LTTPR PHYs to
++ * non-transparent mode if this is supported. Preserve the
++ * transparent/non-transparent mode on an active link.
++ *
++ * Return the number of detected LTTPRs in non-transparent mode or 0 if the
++ * LTTPRs are in transparent mode or the detection failed.
++ */
++static int intel_dp_init_lttpr_phys(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE])
+ {
+ int lttpr_count;
+- int i;
+
+ if (!intel_dp_read_lttpr_common_caps(intel_dp, dpcd))
+ return 0;
+@@ -131,6 +145,19 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI
+ if (lttpr_count == 0)
+ return 0;
+
++ /*
++ * Don't change the mode on an active link, to prevent a loss of link
++ * synchronization. See DP Standard v2.0 3.6.7. about the LTTPR
++ * resetting its internal state when the mode is changed from
++ * non-transparent to transparent.
++ */
++ if (intel_dp->link_trained) {
++ if (lttpr_count < 0 || intel_dp_lttpr_transparent_mode_enabled(intel_dp))
++ goto out_reset_lttpr_count;
++
++ return lttpr_count;
++ }
++
+ /*
+ * See DP Standard v2.0 3.6.6.1. about the explicit disabling of
+ * non-transparent mode and the disable->enable non-transparent mode
+@@ -151,11 +178,25 @@ static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEI
+ "Switching to LTTPR non-transparent LT mode failed, fall-back to transparent mode\n");
+
+ intel_dp_set_lttpr_transparent_mode(intel_dp, true);
+- intel_dp_reset_lttpr_count(intel_dp);
+
+- return 0;
++ goto out_reset_lttpr_count;
+ }
+
++ return lttpr_count;
++
++out_reset_lttpr_count:
++ intel_dp_reset_lttpr_count(intel_dp);
++
++ return 0;
++}
++
++static int intel_dp_init_lttpr(struct intel_dp *intel_dp, const u8 dpcd[DP_RECEIVER_CAP_SIZE])
++{
++ int lttpr_count;
++ int i;
++
++ lttpr_count = intel_dp_init_lttpr_phys(intel_dp, dpcd);
++
+ for (i = 0; i < lttpr_count; i++)
+ intel_dp_read_lttpr_phy_caps(intel_dp, dpcd, DP_PHY_LTTPR(i));
+
+@@ -1372,10 +1413,10 @@ void intel_dp_start_link_train(struct intel_dp *intel_dp,
+ {
+ struct drm_i915_private *i915 = dp_to_i915(intel_dp);
+ bool passed;
+-
+ /*
+- * TODO: Reiniting LTTPRs here won't be needed once proper connector
+- * HW state readout is added.
++ * Reinit the LTTPRs here to ensure that they are switched to
++ * non-transparent mode. During an earlier LTTPR detection this
++ * could've been prevented by an active link.
+ */
+ int lttpr_count = intel_dp_init_lttpr_and_dprx_caps(intel_dp);
+
+diff --git a/drivers/gpu/drm/i915/display/intel_fbc.c b/drivers/gpu/drm/i915/display/intel_fbc.c
+index 151dcd0c45b60..984f13d8c0c88 100644
+--- a/drivers/gpu/drm/i915/display/intel_fbc.c
++++ b/drivers/gpu/drm/i915/display/intel_fbc.c
+@@ -1251,7 +1251,7 @@ static int intel_fbc_check_plane(struct intel_atomic_state *state,
+ * Recommendation is to keep this combination disabled
+ * Bspec: 50422 HSD: 14010260002
+ */
+- if (IS_DISPLAY_VER(i915, 12, 14) && crtc_state->has_psr2) {
++ if (IS_DISPLAY_VER(i915, 12, 14) && crtc_state->has_sel_update) {
+ plane_state->no_fbc_reason = "PSR2 enabled";
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/i915/display/intel_psr.c b/drivers/gpu/drm/i915/display/intel_psr.c
+index f5b33335a9ae0..3c7da862222bf 100644
+--- a/drivers/gpu/drm/i915/display/intel_psr.c
++++ b/drivers/gpu/drm/i915/display/intel_psr.c
+@@ -651,7 +651,7 @@ void intel_psr_enable_sink(struct intel_dp *intel_dp,
+ struct drm_i915_private *dev_priv = dp_to_i915(intel_dp);
+ u8 dpcd_val = DP_PSR_ENABLE;
+
+- if (crtc_state->has_psr2) {
++ if (crtc_state->has_sel_update) {
+ /* Enable ALPM at sink for psr2 */
+ if (!crtc_state->has_panel_replay) {
+ drm_dp_dpcd_writeb(&intel_dp->aux,
+@@ -659,7 +659,7 @@ void intel_psr_enable_sink(struct intel_dp *intel_dp,
+ DP_ALPM_ENABLE |
+ DP_ALPM_LOCK_ERROR_IRQ_HPD_ENABLE);
+
+- if (psr2_su_region_et_valid(intel_dp))
++ if (crtc_state->enable_psr2_su_region_et)
+ dpcd_val |= DP_PSR_ENABLE_SU_REGION_ET;
+ }
+
+@@ -1639,7 +1639,7 @@ void intel_psr_compute_config(struct intel_dp *intel_dp,
+ if (!crtc_state->has_psr)
+ return;
+
+- crtc_state->has_psr2 = intel_psr2_config_valid(intel_dp, crtc_state);
++ crtc_state->has_sel_update = intel_psr2_config_valid(intel_dp, crtc_state);
+ }
+
+ void intel_psr_get_config(struct intel_encoder *encoder,
+@@ -1672,7 +1672,7 @@ void intel_psr_get_config(struct intel_encoder *encoder,
+ pipe_config->has_psr = true;
+ }
+
+- pipe_config->has_psr2 = intel_dp->psr.psr2_enabled;
++ pipe_config->has_sel_update = intel_dp->psr.psr2_enabled;
+ pipe_config->infoframes.enable |= intel_hdmi_infoframe_enable(DP_SDP_VSC);
+
+ if (!intel_dp->psr.psr2_enabled)
+@@ -1960,7 +1960,7 @@ static void intel_psr_enable_locked(struct intel_dp *intel_dp,
+
+ drm_WARN_ON(&dev_priv->drm, intel_dp->psr.enabled);
+
+- intel_dp->psr.psr2_enabled = crtc_state->has_psr2;
++ intel_dp->psr.psr2_enabled = crtc_state->has_sel_update;
+ intel_dp->psr.panel_replay_enabled = crtc_state->has_panel_replay;
+ intel_dp->psr.busy_frontbuffer_bits = 0;
+ intel_dp->psr.pipe = to_intel_crtc(crtc_state->uapi.crtc)->pipe;
+@@ -2484,7 +2484,7 @@ int intel_psr2_sel_fetch_update(struct intel_atomic_state *state,
+
+ crtc_state->psr2_su_area.x1 = 0;
+ crtc_state->psr2_su_area.y1 = -1;
+- crtc_state->psr2_su_area.x2 = INT_MAX;
++ crtc_state->psr2_su_area.x2 = drm_rect_width(&crtc_state->pipe_src);
+ crtc_state->psr2_su_area.y2 = -1;
+
+ /*
+@@ -2688,7 +2688,7 @@ void intel_psr_pre_plane_update(struct intel_atomic_state *state,
+ needs_to_disable |= intel_crtc_needs_modeset(new_crtc_state);
+ needs_to_disable |= !new_crtc_state->has_psr;
+ needs_to_disable |= !new_crtc_state->active_planes;
+- needs_to_disable |= new_crtc_state->has_psr2 != psr->psr2_enabled;
++ needs_to_disable |= new_crtc_state->has_sel_update != psr->psr2_enabled;
+ needs_to_disable |= DISPLAY_VER(i915) < 11 &&
+ new_crtc_state->wm_level_disabled;
+
+@@ -3694,16 +3694,9 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data)
+ "reserved",
+ "sink internal error",
+ };
+- static const char * const panel_replay_status[] = {
+- "Sink device frame is locked to the Source device",
+- "Sink device is coasting, using the VTotal target",
+- "Sink device is governing the frame rate (frame rate unlock is granted)",
+- "Sink device in the process of re-locking with the Source device",
+- };
+ const char *str;
+ int ret;
+ u8 status, error_status;
+- u32 idx;
+
+ if (!(CAN_PSR(intel_dp) || CAN_PANEL_REPLAY(intel_dp))) {
+ seq_puts(m, "PSR/Panel-Replay Unsupported\n");
+@@ -3717,16 +3710,11 @@ static int i915_psr_sink_status_show(struct seq_file *m, void *data)
+ if (ret)
+ return ret;
+
+- str = "unknown";
+- if (intel_dp->psr.panel_replay_enabled) {
+- idx = (status & DP_SINK_FRAME_LOCKED_MASK) >> DP_SINK_FRAME_LOCKED_SHIFT;
+- if (idx < ARRAY_SIZE(panel_replay_status))
+- str = panel_replay_status[idx];
+- } else if (intel_dp->psr.enabled) {
+- idx = status & DP_PSR_SINK_STATE_MASK;
+- if (idx < ARRAY_SIZE(sink_status))
+- str = sink_status[idx];
+- }
++ status &= DP_PSR_SINK_STATE_MASK;
++ if (status < ARRAY_SIZE(sink_status))
++ str = sink_status[status];
++ else
++ str = "unknown";
+
+ seq_printf(m, "Sink %s status: 0x%x [%s]\n", psr_mode_str(intel_dp), status, str);
+
+diff --git a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+index 21829439e6867..72090f52fb850 100644
+--- a/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
++++ b/drivers/gpu/drm/i915/gt/intel_execlists_submission.c
+@@ -3315,11 +3315,7 @@ static void remove_from_engine(struct i915_request *rq)
+
+ static bool can_preempt(struct intel_engine_cs *engine)
+ {
+- if (GRAPHICS_VER(engine->i915) > 8)
+- return true;
+-
+- /* GPGPU on bdw requires extra w/a; not implemented */
+- return engine->class != RENDER_CLASS;
++ return GRAPHICS_VER(engine->i915) > 8;
+ }
+
+ static void kick_execlists(const struct i915_request *rq, int prio)
+diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
+index 17b0364112922..be66d94be3613 100644
+--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
++++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.c
+@@ -514,29 +514,42 @@ static bool mtk_ddp_comp_find(struct device *dev,
+ return false;
+ }
+
+-static unsigned int mtk_ddp_comp_find_in_route(struct device *dev,
+- const struct mtk_drm_route *routes,
+- unsigned int num_routes,
+- struct mtk_ddp_comp *ddp_comp)
++static int mtk_ddp_comp_find_in_route(struct device *dev,
++ const struct mtk_drm_route *routes,
++ unsigned int num_routes,
++ struct mtk_ddp_comp *ddp_comp)
+ {
+- int ret;
+ unsigned int i;
+
+- if (!routes) {
+- ret = -EINVAL;
+- goto err;
+- }
++ if (!routes)
++ return -EINVAL;
+
+ for (i = 0; i < num_routes; i++)
+ if (dev == ddp_comp[routes[i].route_ddp].dev)
+ return BIT(routes[i].crtc_id);
+
+- ret = -ENODEV;
+-err:
++ return -ENODEV;
++}
+
+- DRM_INFO("Failed to find comp in ddp table, ret = %d\n", ret);
++static bool mtk_ddp_path_available(const unsigned int *path,
++ unsigned int path_len,
++ struct device_node **comp_node)
++{
++ unsigned int i;
+
+- return 0;
++ if (!path || !path_len)
++ return false;
++
++ for (i = 0U; i < path_len; i++) {
++ /* OVL_ADAPTOR doesn't have a device node */
++ if (path[i] == DDP_COMPONENT_DRM_OVL_ADAPTOR)
++ continue;
++
++ if (!comp_node[path[i]])
++ return false;
++ }
++
++ return true;
+ }
+
+ int mtk_ddp_comp_get_id(struct device_node *node,
+@@ -554,31 +567,53 @@ int mtk_ddp_comp_get_id(struct device_node *node,
+ return -EINVAL;
+ }
+
+-unsigned int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev)
++int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev)
+ {
+ struct mtk_drm_private *private = drm->dev_private;
+- unsigned int ret = 0;
+-
+- if (mtk_ddp_comp_find(dev,
+- private->data->main_path,
+- private->data->main_len,
+- private->ddp_comp))
+- ret = BIT(0);
+- else if (mtk_ddp_comp_find(dev,
+- private->data->ext_path,
+- private->data->ext_len,
+- private->ddp_comp))
+- ret = BIT(1);
+- else if (mtk_ddp_comp_find(dev,
+- private->data->third_path,
+- private->data->third_len,
+- private->ddp_comp))
+- ret = BIT(2);
+- else
+- ret = mtk_ddp_comp_find_in_route(dev,
+- private->data->conn_routes,
+- private->data->num_conn_routes,
+- private->ddp_comp);
++ const struct mtk_mmsys_driver_data *data;
++ struct mtk_drm_private *priv_n;
++ int i = 0, j;
++ int ret;
++
++ for (j = 0; j < private->data->mmsys_dev_num; j++) {
++ priv_n = private->all_drm_private[j];
++ data = priv_n->data;
++
++ if (mtk_ddp_path_available(data->main_path, data->main_len,
++ priv_n->comp_node)) {
++ if (mtk_ddp_comp_find(dev, data->main_path,
++ data->main_len,
++ priv_n->ddp_comp))
++ return BIT(i);
++ i++;
++ }
++
++ if (mtk_ddp_path_available(data->ext_path, data->ext_len,
++ priv_n->comp_node)) {
++ if (mtk_ddp_comp_find(dev, data->ext_path,
++ data->ext_len,
++ priv_n->ddp_comp))
++ return BIT(i);
++ i++;
++ }
++
++ if (mtk_ddp_path_available(data->third_path, data->third_len,
++ priv_n->comp_node)) {
++ if (mtk_ddp_comp_find(dev, data->third_path,
++ data->third_len,
++ priv_n->ddp_comp))
++ return BIT(i);
++ i++;
++ }
++ }
++
++ ret = mtk_ddp_comp_find_in_route(dev,
++ private->data->conn_routes,
++ private->data->num_conn_routes,
++ private->ddp_comp);
++
++ if (ret < 0)
++ DRM_INFO("Failed to find comp in ddp table, ret = %d\n", ret);
+
+ return ret;
+ }
+@@ -593,7 +628,7 @@ int mtk_ddp_comp_init(struct device_node *node, struct mtk_ddp_comp *comp,
+ int ret;
+ #endif
+
+- if (comp_id < 0 || comp_id >= DDP_COMPONENT_DRM_ID_MAX)
++ if (comp_id >= DDP_COMPONENT_DRM_ID_MAX)
+ return -EINVAL;
+
+ type = mtk_ddp_matches[comp_id].type;
+diff --git a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
+index 26236691ce4c2..ecf6dc283cd7c 100644
+--- a/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
++++ b/drivers/gpu/drm/mediatek/mtk_ddp_comp.h
+@@ -192,7 +192,11 @@ unsigned int mtk_ddp_comp_supported_rotations(struct mtk_ddp_comp *comp)
+ if (comp->funcs && comp->funcs->supported_rotations)
+ return comp->funcs->supported_rotations(comp->dev);
+
+- return 0;
++ /*
++ * In order to pass IGT tests, DRM_MODE_ROTATE_0 is required when
++ * rotation is not supported.
++ */
++ return DRM_MODE_ROTATE_0;
+ }
+
+ static inline unsigned int mtk_ddp_comp_layer_nr(struct mtk_ddp_comp *comp)
+@@ -326,7 +330,7 @@ static inline void mtk_ddp_comp_encoder_index_set(struct mtk_ddp_comp *comp)
+
+ int mtk_ddp_comp_get_id(struct device_node *node,
+ enum mtk_ddp_comp_type comp_type);
+-unsigned int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev);
++int mtk_find_possible_crtcs(struct drm_device *drm, struct device *dev);
+ int mtk_ddp_comp_init(struct device_node *comp_node, struct mtk_ddp_comp *comp,
+ unsigned int comp_id);
+ enum mtk_ddp_comp_type mtk_ddp_comp_get_type(unsigned int comp_id);
+diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+index b552a02d7eae7..26b598b9f71f2 100644
+--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
++++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl.c
+@@ -38,6 +38,7 @@
+ #define DISP_REG_OVL_PITCH_MSB(n) (0x0040 + 0x20 * (n))
+ #define OVL_PITCH_MSB_2ND_SUBBUF BIT(16)
+ #define DISP_REG_OVL_PITCH(n) (0x0044 + 0x20 * (n))
++#define OVL_CONST_BLEND BIT(28)
+ #define DISP_REG_OVL_RDMA_CTRL(n) (0x00c0 + 0x20 * (n))
+ #define DISP_REG_OVL_RDMA_GMC(n) (0x00c8 + 0x20 * (n))
+ #define DISP_REG_OVL_ADDR_MT2701 0x0040
+@@ -71,6 +72,8 @@
+ #define OVL_CON_VIRT_FLIP BIT(9)
+ #define OVL_CON_HORZ_FLIP BIT(10)
+
++#define OVL_COLOR_ALPHA GENMASK(31, 24)
++
+ static const u32 mt8173_formats[] = {
+ DRM_FORMAT_XRGB8888,
+ DRM_FORMAT_ARGB8888,
+@@ -273,7 +276,13 @@ void mtk_ovl_config(struct device *dev, unsigned int w,
+ if (w != 0 && h != 0)
+ mtk_ddp_write_relaxed(cmdq_pkt, h << 16 | w, &ovl->cmdq_reg, ovl->regs,
+ DISP_REG_OVL_ROI_SIZE);
+- mtk_ddp_write_relaxed(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_ROI_BGCLR);
++
++ /*
++ * The background color must be opaque black (ARGB),
++ * otherwise the alpha blending will have no effect
++ */
++ mtk_ddp_write_relaxed(cmdq_pkt, OVL_COLOR_ALPHA, &ovl->cmdq_reg,
++ ovl->regs, DISP_REG_OVL_ROI_BGCLR);
+
+ mtk_ddp_write(cmdq_pkt, 0x1, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_RST);
+ mtk_ddp_write(cmdq_pkt, 0x0, &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_RST);
+@@ -296,27 +305,20 @@ int mtk_ovl_layer_check(struct device *dev, unsigned int idx,
+ struct mtk_plane_state *mtk_state)
+ {
+ struct drm_plane_state *state = &mtk_state->base;
+- unsigned int rotation = 0;
+
+- rotation = drm_rotation_simplify(state->rotation,
+- DRM_MODE_ROTATE_0 |
+- DRM_MODE_REFLECT_X |
+- DRM_MODE_REFLECT_Y);
+- rotation &= ~DRM_MODE_ROTATE_0;
+-
+- /* We can only do reflection, not rotation */
+- if ((rotation & DRM_MODE_ROTATE_MASK) != 0)
++ /* check if any unsupported rotation is set */
++ if (state->rotation & ~mtk_ovl_supported_rotations(dev))
+ return -EINVAL;
+
+ /*
+ * TODO: Rotating/reflecting YUV buffers is not supported at this time.
+ * Only RGB[AX] variants are supported.
++ * Since DRM_MODE_ROTATE_0 means "no rotation", we should not
++ * reject layers with this property.
+ */
+- if (state->fb->format->is_yuv && rotation != 0)
++ if (state->fb->format->is_yuv && (state->rotation & ~DRM_MODE_ROTATE_0))
+ return -EINVAL;
+
+- state->rotation = rotation;
+-
+ return 0;
+ }
+
+@@ -407,6 +409,7 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
+ unsigned int fmt = pending->format;
+ unsigned int offset = (pending->y << 16) | pending->x;
+ unsigned int src_size = (pending->height << 16) | pending->width;
++ unsigned int ignore_pixel_alpha = 0;
+ unsigned int con;
+ bool is_afbc = pending->modifier != DRM_FORMAT_MOD_LINEAR;
+ union overlay_pitch {
+@@ -428,6 +431,14 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
+ if (state->base.fb && state->base.fb->format->has_alpha)
+ con |= OVL_CON_AEN | OVL_CON_ALPHA;
+
++ /* CONST_BLD must be enabled for XRGB formats although the alpha channel
++ * can be ignored, or OVL will still read the value from memory.
++ * For RGB888 related formats, whether CONST_BLD is enabled or not won't
++ * affect the result. Therefore we use !has_alpha as the condition.
++ */
++ if (state->base.fb && !state->base.fb->format->has_alpha)
++ ignore_pixel_alpha = OVL_CONST_BLEND;
++
+ if (pending->rotation & DRM_MODE_REFLECT_Y) {
+ con |= OVL_CON_VIRT_FLIP;
+ addr += (pending->height - 1) * pending->pitch;
+@@ -443,8 +454,8 @@ void mtk_ovl_layer_config(struct device *dev, unsigned int idx,
+
+ mtk_ddp_write_relaxed(cmdq_pkt, con, &ovl->cmdq_reg, ovl->regs,
+ DISP_REG_OVL_CON(idx));
+- mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb, &ovl->cmdq_reg, ovl->regs,
+- DISP_REG_OVL_PITCH(idx));
++ mtk_ddp_write_relaxed(cmdq_pkt, overlay_pitch.split_pitch.lsb | ignore_pixel_alpha,
++ &ovl->cmdq_reg, ovl->regs, DISP_REG_OVL_PITCH(idx));
+ mtk_ddp_write_relaxed(cmdq_pkt, src_size, &ovl->cmdq_reg, ovl->regs,
+ DISP_REG_OVL_SRC_SIZE(idx));
+ mtk_ddp_write_relaxed(cmdq_pkt, offset, &ovl->cmdq_reg, ovl->regs,
+diff --git a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
+index 02dd7dcdfedb2..2b62d64759181 100644
+--- a/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
++++ b/drivers/gpu/drm/mediatek/mtk_disp_ovl_adaptor.c
+@@ -158,7 +158,7 @@ void mtk_ovl_adaptor_layer_config(struct device *dev, unsigned int idx,
+ merge = ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_MERGE0 + idx];
+ ethdr = ovl_adaptor->ovl_adaptor_comp[OVL_ADAPTOR_ETHDR0];
+
+- if (!pending->enable) {
++ if (!pending->enable || !pending->width || !pending->height) {
+ mtk_merge_stop_cmdq(merge, cmdq_pkt);
+ mtk_mdp_rdma_stop(rdma_l, cmdq_pkt);
+ mtk_mdp_rdma_stop(rdma_r, cmdq_pkt);
+diff --git a/drivers/gpu/drm/mediatek/mtk_dp.c b/drivers/gpu/drm/mediatek/mtk_dp.c
+index 536366956447a..ada12927bbacf 100644
+--- a/drivers/gpu/drm/mediatek/mtk_dp.c
++++ b/drivers/gpu/drm/mediatek/mtk_dp.c
+@@ -2073,9 +2073,15 @@ static const struct drm_edid *mtk_dp_edid_read(struct drm_bridge *bridge,
+ */
+ const struct edid *edid = drm_edid_raw(drm_edid);
+ struct cea_sad *sads;
++ int ret;
+
+- audio_caps->sad_count = drm_edid_to_sad(edid, &sads);
+- kfree(sads);
++ ret = drm_edid_to_sad(edid, &sads);
++ /* Ignore any errors */
++ if (ret < 0)
++ ret = 0;
++ if (ret)
++ kfree(sads);
++ audio_caps->sad_count = ret;
+
+ /*
+ * FIXME: This should use connector->display_info.has_audio from
+diff --git a/drivers/gpu/drm/mediatek/mtk_dpi.c b/drivers/gpu/drm/mediatek/mtk_dpi.c
+index bfe8653005dbf..a08d206549543 100644
+--- a/drivers/gpu/drm/mediatek/mtk_dpi.c
++++ b/drivers/gpu/drm/mediatek/mtk_dpi.c
+@@ -805,7 +805,10 @@ static int mtk_dpi_bind(struct device *dev, struct device *master, void *data)
+ return ret;
+ }
+
+- dpi->encoder.possible_crtcs = mtk_find_possible_crtcs(drm_dev, dpi->dev);
++ ret = mtk_find_possible_crtcs(drm_dev, dpi->dev);
++ if (ret < 0)
++ goto err_cleanup;
++ dpi->encoder.possible_crtcs = ret;
+
+ ret = drm_bridge_attach(&dpi->encoder, &dpi->bridge, NULL,
+ DRM_BRIDGE_ATTACH_NO_CONNECTOR);
+diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.c b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+index de811e2265da7..56f409ad7f390 100644
+--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.c
++++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.c
+@@ -294,6 +294,9 @@ static const struct mtk_mmsys_driver_data mt8188_vdosys0_driver_data = {
+ .conn_routes = mt8188_mtk_ddp_main_routes,
+ .num_conn_routes = ARRAY_SIZE(mt8188_mtk_ddp_main_routes),
+ .mmsys_dev_num = 2,
++ .max_width = 8191,
++ .min_width = 1,
++ .min_height = 1,
+ };
+
+ static const struct mtk_mmsys_driver_data mt8192_mmsys_driver_data = {
+@@ -308,6 +311,9 @@ static const struct mtk_mmsys_driver_data mt8195_vdosys0_driver_data = {
+ .main_path = mt8195_mtk_ddp_main,
+ .main_len = ARRAY_SIZE(mt8195_mtk_ddp_main),
+ .mmsys_dev_num = 2,
++ .max_width = 8191,
++ .min_width = 1,
++ .min_height = 1,
+ };
+
+ static const struct mtk_mmsys_driver_data mt8195_vdosys1_driver_data = {
+@@ -315,6 +321,9 @@ static const struct mtk_mmsys_driver_data mt8195_vdosys1_driver_data = {
+ .ext_len = ARRAY_SIZE(mt8195_mtk_ddp_ext),
+ .mmsys_id = 1,
+ .mmsys_dev_num = 2,
++ .max_width = 8191,
++ .min_width = 2, /* 2-pixel align when ethdr is bypassed */
++ .min_height = 1,
+ };
+
+ static const struct of_device_id mtk_drm_of_ids[] = {
+@@ -493,6 +502,15 @@ static int mtk_drm_kms_init(struct drm_device *drm)
+ for (j = 0; j < private->data->mmsys_dev_num; j++) {
+ priv_n = private->all_drm_private[j];
+
++ if (priv_n->data->max_width)
++ drm->mode_config.max_width = priv_n->data->max_width;
++
++ if (priv_n->data->min_width)
++ drm->mode_config.min_width = priv_n->data->min_width;
++
++ if (priv_n->data->min_height)
++ drm->mode_config.min_height = priv_n->data->min_height;
++
+ if (i == CRTC_MAIN && priv_n->data->main_len) {
+ ret = mtk_crtc_create(drm, priv_n->data->main_path,
+ priv_n->data->main_len, j,
+@@ -520,6 +538,10 @@ static int mtk_drm_kms_init(struct drm_device *drm)
+ }
+ }
+
++ /* IGT will check if the cursor size is configured */
++ drm->mode_config.cursor_width = drm->mode_config.max_width;
++ drm->mode_config.cursor_height = drm->mode_config.max_height;
++
+ /* Use OVL device for all DMA memory allocations */
+ crtc = drm_crtc_from_index(drm, 0);
+ if (crtc)
+@@ -743,6 +765,8 @@ static const struct of_device_id mtk_ddp_comp_dt_ids[] = {
+ .data = (void *)MTK_DISP_OVL },
+ { .compatible = "mediatek,mt8192-disp-ovl",
+ .data = (void *)MTK_DISP_OVL },
++ { .compatible = "mediatek,mt8195-disp-ovl",
++ .data = (void *)MTK_DISP_OVL },
+ { .compatible = "mediatek,mt8183-disp-ovl-2l",
+ .data = (void *)MTK_DISP_OVL_2L },
+ { .compatible = "mediatek,mt8192-disp-ovl-2l",
+diff --git a/drivers/gpu/drm/mediatek/mtk_drm_drv.h b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+index 78d698ede1bf8..ce897984de51e 100644
+--- a/drivers/gpu/drm/mediatek/mtk_drm_drv.h
++++ b/drivers/gpu/drm/mediatek/mtk_drm_drv.h
+@@ -46,6 +46,10 @@ struct mtk_mmsys_driver_data {
+ bool shadow_register;
+ unsigned int mmsys_id;
+ unsigned int mmsys_dev_num;
++
++ u16 max_width;
++ u16 min_width;
++ u16 min_height;
+ };
+
+ struct mtk_drm_private {
+diff --git a/drivers/gpu/drm/mediatek/mtk_dsi.c b/drivers/gpu/drm/mediatek/mtk_dsi.c
+index c255559cc56ed..b6e3c011a12d8 100644
+--- a/drivers/gpu/drm/mediatek/mtk_dsi.c
++++ b/drivers/gpu/drm/mediatek/mtk_dsi.c
+@@ -837,7 +837,10 @@ static int mtk_dsi_encoder_init(struct drm_device *drm, struct mtk_dsi *dsi)
+ return ret;
+ }
+
+- dsi->encoder.possible_crtcs = mtk_find_possible_crtcs(drm, dsi->host.dev);
++ ret = mtk_find_possible_crtcs(drm, dsi->host.dev);
++ if (ret < 0)
++ goto err_cleanup_encoder;
++ dsi->encoder.possible_crtcs = ret;
+
+ ret = drm_bridge_attach(&dsi->encoder, &dsi->bridge, NULL,
+ DRM_BRIDGE_ATTACH_NO_CONNECTOR);
+diff --git a/drivers/gpu/drm/mediatek/mtk_ethdr.c b/drivers/gpu/drm/mediatek/mtk_ethdr.c
+index 156c6ff547e86..bf5826b7e7760 100644
+--- a/drivers/gpu/drm/mediatek/mtk_ethdr.c
++++ b/drivers/gpu/drm/mediatek/mtk_ethdr.c
+@@ -50,7 +50,6 @@
+
+ #define MIXER_INX_MODE_BYPASS 0
+ #define MIXER_INX_MODE_EVEN_EXTEND 1
+-#define DEFAULT_9BIT_ALPHA 0x100
+ #define MIXER_ALPHA_AEN BIT(8)
+ #define MIXER_ALPHA 0xff
+ #define ETHDR_CLK_NUM 13
+@@ -154,13 +153,19 @@ void mtk_ethdr_layer_config(struct device *dev, unsigned int idx,
+ unsigned int offset = (pending->x & 1) << 31 | pending->y << 16 | pending->x;
+ unsigned int align_width = ALIGN_DOWN(pending->width, 2);
+ unsigned int alpha_con = 0;
++ bool replace_src_a = false;
+
+ dev_dbg(dev, "%s+ idx:%d", __func__, idx);
+
+ if (idx >= 4)
+ return;
+
+- if (!pending->enable) {
++ if (!pending->enable || !pending->width || !pending->height) {
++ /*
++ * instead of disabling layer with MIX_SRC_CON directly
++ * set the size to 0 to avoid screen shift due to mixer
++ * mode switch (hardware behavior)
++ */
+ mtk_ddp_write(cmdq_pkt, 0, &mixer->cmdq_base, mixer->regs, MIX_L_SRC_SIZE(idx));
+ return;
+ }
+@@ -168,8 +173,16 @@ void mtk_ethdr_layer_config(struct device *dev, unsigned int idx,
+ if (state->base.fb && state->base.fb->format->has_alpha)
+ alpha_con = MIXER_ALPHA_AEN | MIXER_ALPHA;
+
+- mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1, alpha_con ? false : true,
+- DEFAULT_9BIT_ALPHA,
++ if (state->base.fb && !state->base.fb->format->has_alpha) {
++ /*
++ * Mixer doesn't support CONST_BLD mode,
++ * use a trick to make the output equivalent
++ */
++ replace_src_a = true;
++ }
++
++ mtk_mmsys_mixer_in_config(priv->mmsys_dev, idx + 1, replace_src_a,
++ MIXER_ALPHA,
+ pending->x & 1 ? MIXER_INX_MODE_EVEN_EXTEND :
+ MIXER_INX_MODE_BYPASS, align_width / 2 - 1, cmdq_pkt);
+
+diff --git a/drivers/gpu/drm/mediatek/mtk_plane.c b/drivers/gpu/drm/mediatek/mtk_plane.c
+index 4625deb21d406..1723d4333f371 100644
+--- a/drivers/gpu/drm/mediatek/mtk_plane.c
++++ b/drivers/gpu/drm/mediatek/mtk_plane.c
+@@ -227,6 +227,8 @@ static void mtk_plane_atomic_async_update(struct drm_plane *plane,
+ plane->state->src_y = new_state->src_y;
+ plane->state->src_h = new_state->src_h;
+ plane->state->src_w = new_state->src_w;
++ plane->state->dst.x1 = new_state->dst.x1;
++ plane->state->dst.y1 = new_state->dst.y1;
+
+ mtk_plane_update_new_state(new_state, new_plane_state);
+ swap(plane->state->fb, new_state->fb);
+@@ -336,7 +338,7 @@ int mtk_plane_init(struct drm_device *dev, struct drm_plane *plane,
+ return err;
+ }
+
+- if (supported_rotations & ~DRM_MODE_ROTATE_0) {
++ if (supported_rotations) {
+ err = drm_plane_create_rotation_property(plane,
+ DRM_MODE_ROTATE_0,
+ supported_rotations);
+diff --git a/drivers/gpu/drm/meson/meson_drv.c b/drivers/gpu/drm/meson/meson_drv.c
+index 17a5cca007e29..4bd0baa2a4f55 100644
+--- a/drivers/gpu/drm/meson/meson_drv.c
++++ b/drivers/gpu/drm/meson/meson_drv.c
+@@ -250,29 +250,20 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
+ if (ret)
+ goto free_drm;
+ ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_0);
+- if (ret) {
+- meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+- goto free_drm;
+- }
++ if (ret)
++ goto free_canvas_osd1;
+ ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_1);
+- if (ret) {
+- meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+- meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0);
+- goto free_drm;
+- }
++ if (ret)
++ goto free_canvas_vd1_0;
+ ret = meson_canvas_alloc(priv->canvas, &priv->canvas_id_vd1_2);
+- if (ret) {
+- meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+- meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0);
+- meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1);
+- goto free_drm;
+- }
++ if (ret)
++ goto free_canvas_vd1_1;
+
+ priv->vsync_irq = platform_get_irq(pdev, 0);
+
+ ret = drm_vblank_init(drm, 1);
+ if (ret)
+- goto free_drm;
++ goto free_canvas_vd1_2;
+
+ /* Assign limits per soc revision/package */
+ for (i = 0 ; i < ARRAY_SIZE(meson_drm_soc_attrs) ; ++i) {
+@@ -288,11 +279,11 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
+ */
+ ret = drm_aperture_remove_framebuffers(&meson_driver);
+ if (ret)
+- goto free_drm;
++ goto free_canvas_vd1_2;
+
+ ret = drmm_mode_config_init(drm);
+ if (ret)
+- goto free_drm;
++ goto free_canvas_vd1_2;
+ drm->mode_config.max_width = 3840;
+ drm->mode_config.max_height = 2160;
+ drm->mode_config.funcs = &meson_mode_config_funcs;
+@@ -307,7 +298,7 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
+ if (priv->afbcd.ops) {
+ ret = priv->afbcd.ops->init(priv);
+ if (ret)
+- goto free_drm;
++ goto free_canvas_vd1_2;
+ }
+
+ /* Encoder Initialization */
+@@ -371,6 +362,14 @@ static int meson_drv_bind_master(struct device *dev, bool has_components)
+ exit_afbcd:
+ if (priv->afbcd.ops)
+ priv->afbcd.ops->exit(priv);
++free_canvas_vd1_2:
++ meson_canvas_free(priv->canvas, priv->canvas_id_vd1_2);
++free_canvas_vd1_1:
++ meson_canvas_free(priv->canvas, priv->canvas_id_vd1_1);
++free_canvas_vd1_0:
++ meson_canvas_free(priv->canvas, priv->canvas_id_vd1_0);
++free_canvas_osd1:
++ meson_canvas_free(priv->canvas, priv->canvas_id_osd1);
+ free_drm:
+ drm_dev_put(drm);
+
+diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+index 973872ad0474e..5383aff848300 100644
+--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
++++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu.c
+@@ -1409,7 +1409,7 @@ static void a6xx_calc_ubwc_config(struct adreno_gpu *gpu)
+ if (adreno_is_a702(gpu)) {
+ gpu->ubwc_config.highest_bank_bit = 14;
+ gpu->ubwc_config.min_acc_len = 1;
+- gpu->ubwc_config.ubwc_mode = 2;
++ gpu->ubwc_config.ubwc_mode = 0;
+ }
+ }
+
+diff --git a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+index 0a7717a4fc2fd..789a11416f7a4 100644
+--- a/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
++++ b/drivers/gpu/drm/msm/adreno/a6xx_gpu_state.c
+@@ -8,19 +8,16 @@
+ #include "a6xx_gpu_state.h"
+ #include "a6xx_gmu.xml.h"
+
+-/* Ignore diagnostics about register tables that we aren't using yet. We don't
+- * want to modify these headers too much from their original source.
+- */
+-#pragma GCC diagnostic push
+-#pragma GCC diagnostic ignored "-Wunused-variable"
+-#pragma GCC diagnostic ignored "-Wunused-const-variable"
++static const unsigned int *gen7_0_0_external_core_regs[] __always_unused;
++static const unsigned int *gen7_2_0_external_core_regs[] __always_unused;
++static const unsigned int *gen7_9_0_external_core_regs[] __always_unused;
++static struct gen7_sptp_cluster_registers gen7_9_0_sptp_clusters[] __always_unused;
++static const u32 gen7_9_0_cx_debugbus_blocks[] __always_unused;
+
+ #include "adreno_gen7_0_0_snapshot.h"
+ #include "adreno_gen7_2_0_snapshot.h"
+ #include "adreno_gen7_9_0_snapshot.h"
+
+-#pragma GCC diagnostic pop
+-
+ struct a6xx_gpu_state_obj {
+ const void *handle;
+ u32 *data;
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+index 119f3ea50a7c6..697ad4a640516 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder.c
+@@ -428,7 +428,7 @@ int dpu_encoder_helper_wait_for_irq(struct dpu_encoder_phys *phys_enc,
+ return -EWOULDBLOCK;
+ }
+
+- if (irq_idx < 0) {
++ if (irq_idx == 0) {
+ DRM_DEBUG_KMS("skip irq wait id=%u, callback=%ps\n",
+ DRMID(phys_enc->parent), func);
+ return 0;
+@@ -1200,6 +1200,8 @@ static void dpu_encoder_virt_atomic_mode_set(struct drm_encoder *drm_enc,
+ phys->hw_ctl = to_dpu_hw_ctl(hw_ctl[i]);
+
+ phys->cached_mode = crtc_state->adjusted_mode;
++ if (phys->ops.atomic_mode_set)
++ phys->ops.atomic_mode_set(phys, crtc_state, conn_state);
+ }
+ }
+
+@@ -1741,8 +1743,7 @@ void dpu_encoder_trigger_kickoff_pending(struct drm_encoder *drm_enc)
+ phys = dpu_enc->phys_encs[i];
+
+ ctl = phys->hw_ctl;
+- if (ctl->ops.clear_pending_flush)
+- ctl->ops.clear_pending_flush(ctl);
++ ctl->ops.clear_pending_flush(ctl);
+
+ /* update only for command mode primary ctl */
+ if ((phys == dpu_enc->cur_master) &&
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
+index 002e89cc17058..30470cd15a484 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys.h
+@@ -69,6 +69,8 @@ struct dpu_encoder_phys;
+ * @is_master: Whether this phys_enc is the current master
+ * encoder. Can be switched at enable time. Based
+ * on split_role and current mode (CMD/VID).
++ * @atomic_mode_set: DRM Call. Set a DRM mode.
++ * This likely caches the mode, for use at enable.
+ * @enable: DRM Call. Enable a DRM mode.
+ * @disable: DRM Call. Disable mode.
+ * @control_vblank_irq Register/Deregister for VBLANK IRQ
+@@ -93,6 +95,9 @@ struct dpu_encoder_phys;
+ struct dpu_encoder_phys_ops {
+ void (*prepare_commit)(struct dpu_encoder_phys *encoder);
+ bool (*is_master)(struct dpu_encoder_phys *encoder);
++ void (*atomic_mode_set)(struct dpu_encoder_phys *encoder,
++ struct drm_crtc_state *crtc_state,
++ struct drm_connector_state *conn_state);
+ void (*enable)(struct dpu_encoder_phys *encoder);
+ void (*disable)(struct dpu_encoder_phys *encoder);
+ int (*control_vblank_irq)(struct dpu_encoder_phys *enc, bool enable);
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+index 489be1c0c7046..95cd39b496688 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_cmd.c
+@@ -142,6 +142,23 @@ static void dpu_encoder_phys_cmd_underrun_irq(void *arg)
+ dpu_encoder_underrun_callback(phys_enc->parent, phys_enc);
+ }
+
++static void dpu_encoder_phys_cmd_atomic_mode_set(
++ struct dpu_encoder_phys *phys_enc,
++ struct drm_crtc_state *crtc_state,
++ struct drm_connector_state *conn_state)
++{
++ phys_enc->irq[INTR_IDX_CTL_START] = phys_enc->hw_ctl->caps->intr_start;
++
++ phys_enc->irq[INTR_IDX_PINGPONG] = phys_enc->hw_pp->caps->intr_done;
++
++ if (phys_enc->has_intf_te)
++ phys_enc->irq[INTR_IDX_RDPTR] = phys_enc->hw_intf->cap->intr_tear_rd_ptr;
++ else
++ phys_enc->irq[INTR_IDX_RDPTR] = phys_enc->hw_pp->caps->intr_rdptr;
++
++ phys_enc->irq[INTR_IDX_UNDERRUN] = phys_enc->hw_intf->cap->intr_underrun;
++}
++
+ static int _dpu_encoder_phys_cmd_handle_ppdone_timeout(
+ struct dpu_encoder_phys *phys_enc)
+ {
+@@ -280,14 +297,6 @@ static void dpu_encoder_phys_cmd_irq_enable(struct dpu_encoder_phys *phys_enc)
+ phys_enc->hw_pp->idx - PINGPONG_0,
+ phys_enc->vblank_refcount);
+
+- phys_enc->irq[INTR_IDX_CTL_START] = phys_enc->hw_ctl->caps->intr_start;
+- phys_enc->irq[INTR_IDX_PINGPONG] = phys_enc->hw_pp->caps->intr_done;
+-
+- if (phys_enc->has_intf_te)
+- phys_enc->irq[INTR_IDX_RDPTR] = phys_enc->hw_intf->cap->intr_tear_rd_ptr;
+- else
+- phys_enc->irq[INTR_IDX_RDPTR] = phys_enc->hw_pp->caps->intr_rdptr;
+-
+ dpu_core_irq_register_callback(phys_enc->dpu_kms,
+ phys_enc->irq[INTR_IDX_PINGPONG],
+ dpu_encoder_phys_cmd_pp_tx_done_irq,
+@@ -318,10 +327,6 @@ static void dpu_encoder_phys_cmd_irq_disable(struct dpu_encoder_phys *phys_enc)
+ dpu_core_irq_unregister_callback(phys_enc->dpu_kms, phys_enc->irq[INTR_IDX_UNDERRUN]);
+ dpu_encoder_phys_cmd_control_vblank_irq(phys_enc, false);
+ dpu_core_irq_unregister_callback(phys_enc->dpu_kms, phys_enc->irq[INTR_IDX_PINGPONG]);
+-
+- phys_enc->irq[INTR_IDX_CTL_START] = 0;
+- phys_enc->irq[INTR_IDX_PINGPONG] = 0;
+- phys_enc->irq[INTR_IDX_RDPTR] = 0;
+ }
+
+ static void dpu_encoder_phys_cmd_tearcheck_config(
+@@ -698,6 +703,7 @@ static void dpu_encoder_phys_cmd_init_ops(
+ struct dpu_encoder_phys_ops *ops)
+ {
+ ops->is_master = dpu_encoder_phys_cmd_is_master;
++ ops->atomic_mode_set = dpu_encoder_phys_cmd_atomic_mode_set;
+ ops->enable = dpu_encoder_phys_cmd_enable;
+ ops->disable = dpu_encoder_phys_cmd_disable;
+ ops->control_vblank_irq = dpu_encoder_phys_cmd_control_vblank_irq;
+@@ -736,8 +742,6 @@ struct dpu_encoder_phys *dpu_encoder_phys_cmd_init(struct drm_device *dev,
+
+ dpu_encoder_phys_cmd_init_ops(&phys_enc->ops);
+ phys_enc->intf_mode = INTF_MODE_CMD;
+- phys_enc->irq[INTR_IDX_UNDERRUN] = phys_enc->hw_intf->cap->intr_underrun;
+-
+ cmd_enc->stream_sel = 0;
+
+ if (!phys_enc->hw_intf) {
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+index ef69c2f408c3e..636a97432d517 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_vid.c
+@@ -356,6 +356,16 @@ static bool dpu_encoder_phys_vid_needs_single_flush(
+ return phys_enc->split_role != ENC_ROLE_SOLO;
+ }
+
++static void dpu_encoder_phys_vid_atomic_mode_set(
++ struct dpu_encoder_phys *phys_enc,
++ struct drm_crtc_state *crtc_state,
++ struct drm_connector_state *conn_state)
++{
++ phys_enc->irq[INTR_IDX_VSYNC] = phys_enc->hw_intf->cap->intr_vsync;
++
++ phys_enc->irq[INTR_IDX_UNDERRUN] = phys_enc->hw_intf->cap->intr_underrun;
++}
++
+ static int dpu_encoder_phys_vid_control_vblank_irq(
+ struct dpu_encoder_phys *phys_enc,
+ bool enable)
+@@ -699,6 +709,7 @@ static int dpu_encoder_phys_vid_get_frame_count(
+ static void dpu_encoder_phys_vid_init_ops(struct dpu_encoder_phys_ops *ops)
+ {
+ ops->is_master = dpu_encoder_phys_vid_is_master;
++ ops->atomic_mode_set = dpu_encoder_phys_vid_atomic_mode_set;
+ ops->enable = dpu_encoder_phys_vid_enable;
+ ops->disable = dpu_encoder_phys_vid_disable;
+ ops->control_vblank_irq = dpu_encoder_phys_vid_control_vblank_irq;
+@@ -737,8 +748,6 @@ struct dpu_encoder_phys *dpu_encoder_phys_vid_init(struct drm_device *dev,
+
+ dpu_encoder_phys_vid_init_ops(&phys_enc->ops);
+ phys_enc->intf_mode = INTF_MODE_VIDEO;
+- phys_enc->irq[INTR_IDX_VSYNC] = phys_enc->hw_intf->cap->intr_vsync;
+- phys_enc->irq[INTR_IDX_UNDERRUN] = phys_enc->hw_intf->cap->intr_underrun;
+
+ DPU_DEBUG_VIDENC(phys_enc, "created intf idx:%d\n", p->hw_intf->idx);
+
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
+index d3ea91c1d7d2e..882c717859cec 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_encoder_phys_wb.c
+@@ -404,6 +404,15 @@ static void dpu_encoder_phys_wb_irq_disable(struct dpu_encoder_phys *phys)
+ dpu_core_irq_unregister_callback(phys->dpu_kms, phys->irq[INTR_IDX_WB_DONE]);
+ }
+
++static void dpu_encoder_phys_wb_atomic_mode_set(
++ struct dpu_encoder_phys *phys_enc,
++ struct drm_crtc_state *crtc_state,
++ struct drm_connector_state *conn_state)
++{
++
++ phys_enc->irq[INTR_IDX_WB_DONE] = phys_enc->hw_wb->caps->intr_wb_done;
++}
++
+ static void _dpu_encoder_phys_wb_handle_wbdone_timeout(
+ struct dpu_encoder_phys *phys_enc)
+ {
+@@ -529,8 +538,7 @@ static void dpu_encoder_phys_wb_disable(struct dpu_encoder_phys *phys_enc)
+ }
+
+ /* reset h/w before final flush */
+- if (phys_enc->hw_ctl->ops.clear_pending_flush)
+- phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl);
++ phys_enc->hw_ctl->ops.clear_pending_flush(phys_enc->hw_ctl);
+
+ /*
+ * New CTL reset sequence from 5.0 MDP onwards.
+@@ -640,6 +648,7 @@ static bool dpu_encoder_phys_wb_is_valid_for_commit(struct dpu_encoder_phys *phy
+ static void dpu_encoder_phys_wb_init_ops(struct dpu_encoder_phys_ops *ops)
+ {
+ ops->is_master = dpu_encoder_phys_wb_is_master;
++ ops->atomic_mode_set = dpu_encoder_phys_wb_atomic_mode_set;
+ ops->enable = dpu_encoder_phys_wb_enable;
+ ops->disable = dpu_encoder_phys_wb_disable;
+ ops->wait_for_commit_done = dpu_encoder_phys_wb_wait_for_commit_done;
+@@ -685,7 +694,6 @@ struct dpu_encoder_phys *dpu_encoder_phys_wb_init(struct drm_device *dev,
+
+ dpu_encoder_phys_wb_init_ops(&phys_enc->ops);
+ phys_enc->intf_mode = INTF_MODE_WB_LINE;
+- phys_enc->irq[INTR_IDX_WB_DONE] = phys_enc->hw_wb->caps->intr_wb_done;
+
+ atomic_set(&wb_enc->wbirq_refcount, 0);
+
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+index f2b6eac7601dd..9b72977feafa4 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_catalog.c
+@@ -220,12 +220,9 @@ static const u32 wb2_formats_rgb[] = {
+ DRM_FORMAT_RGBA4444,
+ DRM_FORMAT_RGBX4444,
+ DRM_FORMAT_XRGB4444,
+- DRM_FORMAT_BGR565,
+ DRM_FORMAT_BGR888,
+- DRM_FORMAT_ABGR8888,
+ DRM_FORMAT_BGRA8888,
+ DRM_FORMAT_BGRX8888,
+- DRM_FORMAT_XBGR8888,
+ DRM_FORMAT_ABGR1555,
+ DRM_FORMAT_BGRA5551,
+ DRM_FORMAT_XBGR1555,
+@@ -254,12 +251,9 @@ static const u32 wb2_formats_rgb_yuv[] = {
+ DRM_FORMAT_RGBA4444,
+ DRM_FORMAT_RGBX4444,
+ DRM_FORMAT_XRGB4444,
+- DRM_FORMAT_BGR565,
+ DRM_FORMAT_BGR888,
+- DRM_FORMAT_ABGR8888,
+ DRM_FORMAT_BGRA8888,
+ DRM_FORMAT_BGRX8888,
+- DRM_FORMAT_XBGR8888,
+ DRM_FORMAT_ABGR1555,
+ DRM_FORMAT_BGRA5551,
+ DRM_FORMAT_XBGR1555,
+diff --git a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
+index ef56280bea932..4401fdc0f3e4f 100644
+--- a/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
++++ b/drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.h
+@@ -83,7 +83,8 @@ struct dpu_hw_ctl_ops {
+
+ /**
+ * Clear the value of the cached pending_flush_mask
+- * No effect on hardware
++ * No effect on hardware.
++ * Required to be implemented.
+ * @ctx : ctl path ctx pointer
+ */
+ void (*clear_pending_flush)(struct dpu_hw_ctl *ctx);
+diff --git a/drivers/gpu/drm/msm/dp/dp_aux.c b/drivers/gpu/drm/msm/dp/dp_aux.c
+index da46a433bf747..00dfafbebe0e5 100644
+--- a/drivers/gpu/drm/msm/dp/dp_aux.c
++++ b/drivers/gpu/drm/msm/dp/dp_aux.c
+@@ -513,7 +513,10 @@ static int dp_wait_hpd_asserted(struct drm_dp_aux *dp_aux,
+
+ aux = container_of(dp_aux, struct dp_aux_private, dp_aux);
+
+- pm_runtime_get_sync(aux->dev);
++ ret = pm_runtime_resume_and_get(aux->dev);
++ if (ret)
++ return ret;
++
+ ret = dp_catalog_aux_wait_for_hpd_connect_state(aux->catalog, wait_us);
+ pm_runtime_put_sync(aux->dev);
+
+diff --git a/drivers/gpu/drm/msm/dsi/dsi_host.c b/drivers/gpu/drm/msm/dsi/dsi_host.c
+index a50f4dda59410..7252d36687e61 100644
+--- a/drivers/gpu/drm/msm/dsi/dsi_host.c
++++ b/drivers/gpu/drm/msm/dsi/dsi_host.c
+@@ -754,6 +754,8 @@ static void dsi_ctrl_enable(struct msm_dsi_host *msm_host,
+ data |= DSI_VID_CFG0_TRAFFIC_MODE(dsi_get_traffic_mode(flags));
+ data |= DSI_VID_CFG0_DST_FORMAT(dsi_get_vid_fmt(mipi_fmt));
+ data |= DSI_VID_CFG0_VIRT_CHANNEL(msm_host->channel);
++ if (msm_dsi_host_is_wide_bus_enabled(&msm_host->base))
++ data |= DSI_VID_CFG0_DATABUS_WIDEN;
+ dsi_write(msm_host, REG_DSI_VID_CFG0, data);
+
+ /* Do not swap RGB colors */
+@@ -778,7 +780,6 @@ static void dsi_ctrl_enable(struct msm_dsi_host *msm_host,
+ if (cfg_hnd->minor >= MSM_DSI_6G_VER_MINOR_V1_3)
+ data |= DSI_CMD_MODE_MDP_CTRL2_BURST_MODE;
+
+- /* TODO: Allow for video-mode support once tested/fixed */
+ if (msm_dsi_host_is_wide_bus_enabled(&msm_host->base))
+ data |= DSI_CMD_MODE_MDP_CTRL2_DATABUS_WIDEN;
+
+@@ -856,6 +857,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod
+ u32 slice_per_intf, total_bytes_per_intf;
+ u32 pkt_per_line;
+ u32 eol_byte_num;
++ u32 bytes_per_pkt;
+
+ /* first calculate dsc parameters and then program
+ * compress mode registers
+@@ -863,6 +865,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod
+ slice_per_intf = msm_dsc_get_slices_per_intf(dsc, hdisplay);
+
+ total_bytes_per_intf = dsc->slice_chunk_size * slice_per_intf;
++ bytes_per_pkt = dsc->slice_chunk_size; /* * slice_per_pkt; */
+
+ eol_byte_num = total_bytes_per_intf % 3;
+
+@@ -900,6 +903,7 @@ static void dsi_update_dsc_timing(struct msm_dsi_host *msm_host, bool is_cmd_mod
+ dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL, reg_ctrl);
+ dsi_write(msm_host, REG_DSI_COMMAND_COMPRESSION_MODE_CTRL2, reg_ctrl2);
+ } else {
++ reg |= DSI_VIDEO_COMPRESSION_MODE_CTRL_WC(bytes_per_pkt);
+ dsi_write(msm_host, REG_DSI_VIDEO_COMPRESSION_MODE_CTRL, reg);
+ }
+ }
+diff --git a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+index 0ffe8f8c01de8..83c604ba3ee1c 100644
+--- a/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
++++ b/drivers/gpu/drm/panel/panel-boe-tv101wum-nl6.c
+@@ -1507,7 +1507,11 @@ static int boe_panel_prepare(struct drm_panel *panel)
+ usleep_range(10000, 11000);
+
+ if (boe->desc->lp11_before_reset) {
+- mipi_dsi_dcs_nop(boe->dsi);
++ ret = mipi_dsi_dcs_nop(boe->dsi);
++ if (ret < 0) {
++ dev_err(&boe->dsi->dev, "Failed to send NOP: %d\n", ret);
++ goto poweroff;
++ }
+ usleep_range(1000, 2000);
+ }
+ gpiod_set_value(boe->enable_gpio, 1);
+@@ -1528,13 +1532,13 @@ static int boe_panel_prepare(struct drm_panel *panel)
+ return 0;
+
+ poweroff:
++ gpiod_set_value(boe->enable_gpio, 0);
+ regulator_disable(boe->avee);
+ poweroffavdd:
+ regulator_disable(boe->avdd);
+ poweroff1v8:
+ usleep_range(5000, 7000);
+ regulator_disable(boe->pp1800);
+- gpiod_set_value(boe->enable_gpio, 0);
+
+ return ret;
+ }
+diff --git a/drivers/gpu/drm/panel/panel-himax-hx8394.c b/drivers/gpu/drm/panel/panel-himax-hx8394.c
+index ff0dc08b98297..cb9f46e853de4 100644
+--- a/drivers/gpu/drm/panel/panel-himax-hx8394.c
++++ b/drivers/gpu/drm/panel/panel-himax-hx8394.c
+@@ -370,8 +370,7 @@ static int hx8394_enable(struct drm_panel *panel)
+
+ sleep_in:
+ /* This will probably fail, but let's try orderly power off anyway. */
+- ret = mipi_dsi_dcs_enter_sleep_mode(dsi);
+- if (!ret)
++ if (!mipi_dsi_dcs_enter_sleep_mode(dsi))
+ msleep(50);
+
+ return ret;
+diff --git a/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c b/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c
+index 267a5307041c9..35ea5494e0eb8 100644
+--- a/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c
++++ b/drivers/gpu/drm/panel/panel-ilitek-ili9882t.c
+@@ -560,7 +560,11 @@ static int ili9882t_prepare(struct drm_panel *panel)
+ usleep_range(10000, 11000);
+
+ // MIPI needs to keep the LP11 state before the lcm_reset pin is pulled high
+- mipi_dsi_dcs_nop(ili->dsi);
++ ret = mipi_dsi_dcs_nop(ili->dsi);
++ if (ret < 0) {
++ dev_err(&ili->dsi->dev, "Failed to send NOP: %d\n", ret);
++ goto poweroff;
++ }
+ usleep_range(1000, 2000);
+
+ gpiod_set_value(ili->enable_gpio, 1);
+@@ -579,13 +583,13 @@ static int ili9882t_prepare(struct drm_panel *panel)
+ return 0;
+
+ poweroff:
++ gpiod_set_value(ili->enable_gpio, 0);
+ regulator_disable(ili->avee);
+ poweroffavdd:
+ regulator_disable(ili->avdd);
+ poweroff1v8:
+ usleep_range(5000, 7000);
+ regulator_disable(ili->pp1800);
+- gpiod_set_value(ili->enable_gpio, 0);
+
+ return ret;
+ }
+diff --git a/drivers/gpu/drm/panel/panel-lg-sw43408.c b/drivers/gpu/drm/panel/panel-lg-sw43408.c
+index 2b3a73696dcec..67a98ac508f87 100644
+--- a/drivers/gpu/drm/panel/panel-lg-sw43408.c
++++ b/drivers/gpu/drm/panel/panel-lg-sw43408.c
+@@ -62,16 +62,25 @@ static int sw43408_program(struct drm_panel *panel)
+ {
+ struct sw43408_panel *ctx = to_panel_info(panel);
+ struct drm_dsc_picture_parameter_set pps;
++ int ret;
+
+ mipi_dsi_dcs_write_seq(ctx->link, MIPI_DCS_SET_GAMMA_CURVE, 0x02);
+
+- mipi_dsi_dcs_set_tear_on(ctx->link, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
++ ret = mipi_dsi_dcs_set_tear_on(ctx->link, MIPI_DSI_DCS_TEAR_MODE_VBLANK);
++ if (ret < 0) {
++ dev_err(panel->dev, "Failed to set tearing: %d\n", ret);
++ return ret;
++ }
+
+ mipi_dsi_dcs_write_seq(ctx->link, 0x53, 0x0c, 0x30);
+ mipi_dsi_dcs_write_seq(ctx->link, 0x55, 0x00, 0x70, 0xdf, 0x00, 0x70, 0xdf);
+ mipi_dsi_dcs_write_seq(ctx->link, 0xf7, 0x01, 0x49, 0x0c);
+
+- mipi_dsi_dcs_exit_sleep_mode(ctx->link);
++ ret = mipi_dsi_dcs_exit_sleep_mode(ctx->link);
++ if (ret < 0) {
++ dev_err(panel->dev, "Failed to exit sleep mode: %d\n", ret);
++ return ret;
++ }
+
+ msleep(135);
+
+@@ -97,14 +106,22 @@ static int sw43408_program(struct drm_panel *panel)
+ mipi_dsi_dcs_write_seq(ctx->link, 0x55, 0x04, 0x61, 0xdb, 0x04, 0x70, 0xdb);
+ mipi_dsi_dcs_write_seq(ctx->link, 0xb0, 0xca);
+
+- mipi_dsi_dcs_set_display_on(ctx->link);
++ ret = mipi_dsi_dcs_set_display_on(ctx->link);
++ if (ret < 0) {
++ dev_err(panel->dev, "Failed to set display on: %d\n", ret);
++ return ret;
++ }
+
+ msleep(50);
+
+ ctx->link->mode_flags &= ~MIPI_DSI_MODE_LPM;
+
+ drm_dsc_pps_payload_pack(&pps, ctx->link->dsc);
+- mipi_dsi_picture_parameter_set(ctx->link, &pps);
++ ret = mipi_dsi_picture_parameter_set(ctx->link, &pps);
++ if (ret < 0) {
++ dev_err(panel->dev, "Failed to set PPS: %d\n", ret);
++ return ret;
++ }
+
+ ctx->link->mode_flags |= MIPI_DSI_MODE_LPM;
+
+@@ -113,8 +130,12 @@ static int sw43408_program(struct drm_panel *panel)
+ * PPS 1 if pps_identifier is 0
+ * PPS 2 if pps_identifier is 1
+ */
+- mipi_dsi_compression_mode_ext(ctx->link, true,
+- MIPI_DSI_COMPRESSION_DSC, 1);
++ ret = mipi_dsi_compression_mode_ext(ctx->link, true,
++ MIPI_DSI_COMPRESSION_DSC, 1);
++ if (ret < 0) {
++ dev_err(panel->dev, "Failed to set compression mode: %d\n", ret);
++ return ret;
++ }
+
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/panfrost/panfrost_drv.c b/drivers/gpu/drm/panfrost/panfrost_drv.c
+index ef9f6c0716d5a..149737d7a07e3 100644
+--- a/drivers/gpu/drm/panfrost/panfrost_drv.c
++++ b/drivers/gpu/drm/panfrost/panfrost_drv.c
+@@ -828,3 +828,4 @@ module_platform_driver(panfrost_driver);
+ MODULE_AUTHOR("Panfrost Project Developers");
+ MODULE_DESCRIPTION("Panfrost DRM Driver");
+ MODULE_LICENSE("GPL v2");
++MODULE_SOFTDEP("pre: governor_simpleondemand");
+diff --git a/drivers/gpu/drm/panthor/panthor_sched.c b/drivers/gpu/drm/panthor/panthor_sched.c
+index 9a0ff48f7061d..463bcd3cf00f3 100644
+--- a/drivers/gpu/drm/panthor/panthor_sched.c
++++ b/drivers/gpu/drm/panthor/panthor_sched.c
+@@ -2939,6 +2939,7 @@ queue_run_job(struct drm_sched_job *sched_job)
+ pm_runtime_get(ptdev->base.dev);
+ sched->pm.has_ref = true;
+ }
++ panthor_devfreq_record_busy(sched->ptdev);
+ }
+
+ /* Update the last fence. */
+diff --git a/drivers/gpu/drm/qxl/qxl_display.c b/drivers/gpu/drm/qxl/qxl_display.c
+index c6d35c33d5d63..bc24af08dfcd5 100644
+--- a/drivers/gpu/drm/qxl/qxl_display.c
++++ b/drivers/gpu/drm/qxl/qxl_display.c
+@@ -236,6 +236,9 @@ static int qxl_add_mode(struct drm_connector *connector,
+ return 0;
+
+ mode = drm_cvt_mode(dev, width, height, 60, false, false, false);
++ if (!mode)
++ return 0;
++
+ if (preferred)
+ mode->type |= DRM_MODE_TYPE_PREFERRED;
+ mode->hdisplay = width;
+@@ -581,11 +584,11 @@ static struct qxl_bo *qxl_create_cursor(struct qxl_device *qdev,
+ if (ret)
+ goto err;
+
+- ret = qxl_bo_vmap(cursor_bo, &cursor_map);
++ ret = qxl_bo_pin_and_vmap(cursor_bo, &cursor_map);
+ if (ret)
+ goto err_unref;
+
+- ret = qxl_bo_vmap(user_bo, &user_map);
++ ret = qxl_bo_pin_and_vmap(user_bo, &user_map);
+ if (ret)
+ goto err_unmap;
+
+@@ -611,12 +614,12 @@ static struct qxl_bo *qxl_create_cursor(struct qxl_device *qdev,
+ user_map.vaddr, size);
+ }
+
+- qxl_bo_vunmap(user_bo);
+- qxl_bo_vunmap(cursor_bo);
++ qxl_bo_vunmap_and_unpin(user_bo);
++ qxl_bo_vunmap_and_unpin(cursor_bo);
+ return cursor_bo;
+
+ err_unmap:
+- qxl_bo_vunmap(cursor_bo);
++ qxl_bo_vunmap_and_unpin(cursor_bo);
+ err_unref:
+ qxl_bo_unpin(cursor_bo);
+ qxl_bo_unref(&cursor_bo);
+@@ -1202,7 +1205,7 @@ int qxl_create_monitors_object(struct qxl_device *qdev)
+ }
+ qdev->monitors_config_bo = gem_to_qxl_bo(gobj);
+
+- ret = qxl_bo_vmap(qdev->monitors_config_bo, &map);
++ ret = qxl_bo_pin_and_vmap(qdev->monitors_config_bo, &map);
+ if (ret)
+ return ret;
+
+@@ -1233,7 +1236,7 @@ int qxl_destroy_monitors_object(struct qxl_device *qdev)
+ qdev->monitors_config = NULL;
+ qdev->ram_header->monitors_config = 0;
+
+- ret = qxl_bo_vunmap(qdev->monitors_config_bo);
++ ret = qxl_bo_vunmap_and_unpin(qdev->monitors_config_bo);
+ if (ret)
+ return ret;
+
+diff --git a/drivers/gpu/drm/qxl/qxl_object.c b/drivers/gpu/drm/qxl/qxl_object.c
+index 5893e27a7ae50..66635c55cf857 100644
+--- a/drivers/gpu/drm/qxl/qxl_object.c
++++ b/drivers/gpu/drm/qxl/qxl_object.c
+@@ -182,7 +182,7 @@ int qxl_bo_vmap_locked(struct qxl_bo *bo, struct iosys_map *map)
+ return 0;
+ }
+
+-int qxl_bo_vmap(struct qxl_bo *bo, struct iosys_map *map)
++int qxl_bo_pin_and_vmap(struct qxl_bo *bo, struct iosys_map *map)
+ {
+ int r;
+
+@@ -190,7 +190,15 @@ int qxl_bo_vmap(struct qxl_bo *bo, struct iosys_map *map)
+ if (r)
+ return r;
+
++ r = qxl_bo_pin_locked(bo);
++ if (r) {
++ qxl_bo_unreserve(bo);
++ return r;
++ }
++
+ r = qxl_bo_vmap_locked(bo, map);
++ if (r)
++ qxl_bo_unpin_locked(bo);
+ qxl_bo_unreserve(bo);
+ return r;
+ }
+@@ -241,7 +249,7 @@ void qxl_bo_vunmap_locked(struct qxl_bo *bo)
+ ttm_bo_vunmap(&bo->tbo, &bo->map);
+ }
+
+-int qxl_bo_vunmap(struct qxl_bo *bo)
++int qxl_bo_vunmap_and_unpin(struct qxl_bo *bo)
+ {
+ int r;
+
+@@ -250,6 +258,7 @@ int qxl_bo_vunmap(struct qxl_bo *bo)
+ return r;
+
+ qxl_bo_vunmap_locked(bo);
++ qxl_bo_unpin_locked(bo);
+ qxl_bo_unreserve(bo);
+ return 0;
+ }
+diff --git a/drivers/gpu/drm/qxl/qxl_object.h b/drivers/gpu/drm/qxl/qxl_object.h
+index 1cf5bc7591016..875f63221074c 100644
+--- a/drivers/gpu/drm/qxl/qxl_object.h
++++ b/drivers/gpu/drm/qxl/qxl_object.h
+@@ -59,9 +59,9 @@ extern int qxl_bo_create(struct qxl_device *qdev,
+ u32 priority,
+ struct qxl_surface *surf,
+ struct qxl_bo **bo_ptr);
+-int qxl_bo_vmap(struct qxl_bo *bo, struct iosys_map *map);
++int qxl_bo_pin_and_vmap(struct qxl_bo *bo, struct iosys_map *map);
+ int qxl_bo_vmap_locked(struct qxl_bo *bo, struct iosys_map *map);
+-int qxl_bo_vunmap(struct qxl_bo *bo);
++int qxl_bo_vunmap_and_unpin(struct qxl_bo *bo);
+ void qxl_bo_vunmap_locked(struct qxl_bo *bo);
+ void *qxl_bo_kmap_atomic_page(struct qxl_device *qdev, struct qxl_bo *bo, int page_offset);
+ void qxl_bo_kunmap_atomic_page(struct qxl_device *qdev, struct qxl_bo *bo, void *map);
+diff --git a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+index 62ebbdb16253d..9873172e3fd33 100644
+--- a/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
++++ b/drivers/gpu/drm/rockchip/rockchip_drm_vop2.c
+@@ -2344,7 +2344,7 @@ static void vop2_setup_layer_mixer(struct vop2_video_port *vp)
+ port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX,
+ (vp2->nlayers + vp1->nlayers + vp0->nlayers - 1));
+ else
+- port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT1_MUX, 8);
++ port_sel |= FIELD_PREP(RK3568_OVL_PORT_SET__PORT2_MUX, 8);
+
+ layer_sel = vop2_readl(vop2, RK3568_OVL_LAYER_SEL);
+
+diff --git a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
+index 1f8a4f8adc929..801bb139075f3 100644
+--- a/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
++++ b/drivers/gpu/drm/ttm/tests/ttm_bo_test.c
+@@ -18,6 +18,12 @@
+
+ #define BO_SIZE SZ_8K
+
++#ifdef CONFIG_PREEMPT_RT
++#define ww_mutex_base_lock(b) rt_mutex_lock(b)
++#else
++#define ww_mutex_base_lock(b) mutex_lock(b)
++#endif
++
+ struct ttm_bo_test_case {
+ const char *description;
+ bool interruptible;
+@@ -56,7 +62,7 @@ static void ttm_bo_reserve_optimistic_no_ticket(struct kunit *test)
+ struct ttm_buffer_object *bo;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_bo_reserve(bo, params->interruptible, params->no_wait, NULL);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -71,7 +77,7 @@ static void ttm_bo_reserve_locked_no_sleep(struct kunit *test)
+ bool no_wait = true;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ /* Let's lock it beforehand */
+ dma_resv_lock(bo->base.resv, NULL);
+@@ -92,7 +98,7 @@ static void ttm_bo_reserve_no_wait_ticket(struct kunit *test)
+
+ ww_acquire_init(&ctx, &reservation_ww_class);
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_bo_reserve(bo, interruptible, no_wait, &ctx);
+ KUNIT_ASSERT_EQ(test, err, -EBUSY);
+@@ -110,7 +116,7 @@ static void ttm_bo_reserve_double_resv(struct kunit *test)
+
+ ww_acquire_init(&ctx, &reservation_ww_class);
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_bo_reserve(bo, interruptible, no_wait, &ctx);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -138,11 +144,11 @@ static void ttm_bo_reserve_deadlock(struct kunit *test)
+ bool no_wait = false;
+ int err;
+
+- bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
+- bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
++ bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ ww_acquire_init(&ctx1, &reservation_ww_class);
+- mutex_lock(&bo2->base.resv->lock.base);
++ ww_mutex_base_lock(&bo2->base.resv->lock.base);
+
+ /* The deadlock will be caught by WW mutex, don't warn about it */
+ lock_release(&bo2->base.resv->lock.base.dep_map, 1);
+@@ -208,7 +214,7 @@ static void ttm_bo_reserve_interrupted(struct kunit *test)
+ struct task_struct *task;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ task = kthread_create(threaded_ttm_bo_reserve, bo, "ttm-bo-reserve");
+
+@@ -249,7 +255,7 @@ static void ttm_bo_unreserve_basic(struct kunit *test)
+ KUNIT_ASSERT_EQ(test, err, 0);
+ priv->ttm_dev = ttm_dev;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+ bo->priority = bo_prio;
+
+ err = ttm_resource_alloc(bo, place, &res1);
+@@ -288,7 +294,7 @@ static void ttm_bo_unreserve_pinned(struct kunit *test)
+ KUNIT_ASSERT_EQ(test, err, 0);
+ priv->ttm_dev = ttm_dev;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+ place = ttm_place_kunit_init(test, mem_type, 0);
+
+ dma_resv_lock(bo->base.resv, NULL);
+@@ -321,6 +327,7 @@ static void ttm_bo_unreserve_bulk(struct kunit *test)
+ struct ttm_resource *res1, *res2;
+ struct ttm_device *ttm_dev;
+ struct ttm_place *place;
++ struct dma_resv *resv;
+ uint32_t mem_type = TTM_PL_SYSTEM;
+ unsigned int bo_priority = 0;
+ int err;
+@@ -332,12 +339,17 @@ static void ttm_bo_unreserve_bulk(struct kunit *test)
+ ttm_dev = kunit_kzalloc(test, sizeof(*ttm_dev), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
+
++ resv = kunit_kzalloc(test, sizeof(*resv), GFP_KERNEL);
++ KUNIT_ASSERT_NOT_NULL(test, ttm_dev);
++
+ err = ttm_device_kunit_init(priv, ttm_dev, false, false);
+ KUNIT_ASSERT_EQ(test, err, 0);
+ priv->ttm_dev = ttm_dev;
+
+- bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
+- bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ dma_resv_init(resv);
++
++ bo1 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, resv);
++ bo2 = ttm_bo_kunit_init(test, test->priv, BO_SIZE, resv);
+
+ dma_resv_lock(bo1->base.resv, NULL);
+ ttm_bo_set_bulk_move(bo1, &lru_bulk_move);
+@@ -363,6 +375,8 @@ static void ttm_bo_unreserve_bulk(struct kunit *test)
+
+ ttm_resource_free(bo1, &res1);
+ ttm_resource_free(bo2, &res2);
++
++ dma_resv_fini(resv);
+ }
+
+ static void ttm_bo_put_basic(struct kunit *test)
+@@ -384,7 +398,7 @@ static void ttm_bo_put_basic(struct kunit *test)
+ KUNIT_ASSERT_EQ(test, err, 0);
+ priv->ttm_dev = ttm_dev;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+ bo->type = ttm_bo_type_device;
+
+ err = ttm_resource_alloc(bo, place, &res);
+@@ -445,7 +459,7 @@ static void ttm_bo_put_shared_resv(struct kunit *test)
+
+ dma_fence_signal(fence);
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+ bo->type = ttm_bo_type_device;
+ bo->base.resv = external_resv;
+
+@@ -467,7 +481,7 @@ static void ttm_bo_pin_basic(struct kunit *test)
+ KUNIT_ASSERT_EQ(test, err, 0);
+ priv->ttm_dev = ttm_dev;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ for (int i = 0; i < no_pins; i++) {
+ dma_resv_lock(bo->base.resv, NULL);
+@@ -502,7 +516,7 @@ static void ttm_bo_pin_unpin_resource(struct kunit *test)
+ KUNIT_ASSERT_EQ(test, err, 0);
+ priv->ttm_dev = ttm_dev;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_resource_alloc(bo, place, &res);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -553,7 +567,7 @@ static void ttm_bo_multiple_pin_one_unpin(struct kunit *test)
+ KUNIT_ASSERT_EQ(test, err, 0);
+ priv->ttm_dev = ttm_dev;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_resource_alloc(bo, place, &res);
+ KUNIT_ASSERT_EQ(test, err, 0);
+diff --git a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
+index 7b7c1fa805fcb..5be317a0af56b 100644
+--- a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
++++ b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.c
+@@ -51,7 +51,8 @@ EXPORT_SYMBOL_GPL(ttm_device_kunit_init);
+
+ struct ttm_buffer_object *ttm_bo_kunit_init(struct kunit *test,
+ struct ttm_test_devices *devs,
+- size_t size)
++ size_t size,
++ struct dma_resv *obj)
+ {
+ struct drm_gem_object gem_obj = { };
+ struct ttm_buffer_object *bo;
+@@ -61,6 +62,10 @@ struct ttm_buffer_object *ttm_bo_kunit_init(struct kunit *test,
+ KUNIT_ASSERT_NOT_NULL(test, bo);
+
+ bo->base = gem_obj;
++
++ if (obj)
++ bo->base.resv = obj;
++
+ err = drm_gem_object_init(devs->drm, &bo->base, size);
+ KUNIT_ASSERT_EQ(test, err, 0);
+
+diff --git a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h
+index 2f51c833a5367..c83d31b23c9aa 100644
+--- a/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h
++++ b/drivers/gpu/drm/ttm/tests/ttm_kunit_helpers.h
+@@ -28,7 +28,8 @@ int ttm_device_kunit_init(struct ttm_test_devices *priv,
+ bool use_dma32);
+ struct ttm_buffer_object *ttm_bo_kunit_init(struct kunit *test,
+ struct ttm_test_devices *devs,
+- size_t size);
++ size_t size,
++ struct dma_resv *obj);
+ struct ttm_place *ttm_place_kunit_init(struct kunit *test,
+ uint32_t mem_type, uint32_t flags);
+
+diff --git a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
+index 0a3fede84da92..4643f91c6bd59 100644
+--- a/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
++++ b/drivers/gpu/drm/ttm/tests/ttm_pool_test.c
+@@ -57,7 +57,7 @@ static struct ttm_tt *ttm_tt_kunit_init(struct kunit *test,
+ struct ttm_tt *tt;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, priv->devs, size);
++ bo = ttm_bo_kunit_init(test, priv->devs, size, NULL);
+ KUNIT_ASSERT_NOT_NULL(test, bo);
+ priv->mock_bo = bo;
+
+@@ -209,7 +209,7 @@ static void ttm_pool_alloc_basic_dma_addr(struct kunit *test)
+ tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, tt);
+
+- bo = ttm_bo_kunit_init(test, devs, size);
++ bo = ttm_bo_kunit_init(test, devs, size, NULL);
+ KUNIT_ASSERT_NOT_NULL(test, bo);
+
+ err = ttm_sg_tt_init(tt, bo, 0, caching);
+diff --git a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
+index 029e1f094bb08..67584058dadbc 100644
+--- a/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
++++ b/drivers/gpu/drm/ttm/tests/ttm_resource_test.c
+@@ -54,7 +54,7 @@ static void ttm_init_test_mocks(struct kunit *test,
+ /* Make sure we have what we need for a good BO mock */
+ KUNIT_ASSERT_NOT_NULL(test, priv->devs->ttm_dev);
+
+- priv->bo = ttm_bo_kunit_init(test, priv->devs, size);
++ priv->bo = ttm_bo_kunit_init(test, priv->devs, size, NULL);
+ priv->place = ttm_place_kunit_init(test, mem_type, flags);
+ }
+
+diff --git a/drivers/gpu/drm/ttm/tests/ttm_tt_test.c b/drivers/gpu/drm/ttm/tests/ttm_tt_test.c
+index fd4502c18de67..67bf51723c92f 100644
+--- a/drivers/gpu/drm/ttm/tests/ttm_tt_test.c
++++ b/drivers/gpu/drm/ttm/tests/ttm_tt_test.c
+@@ -63,7 +63,7 @@ static void ttm_tt_init_basic(struct kunit *test)
+ tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, tt);
+
+- bo = ttm_bo_kunit_init(test, test->priv, params->size);
++ bo = ttm_bo_kunit_init(test, test->priv, params->size, NULL);
+
+ err = ttm_tt_init(tt, bo, page_flags, caching, extra_pages);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -89,7 +89,7 @@ static void ttm_tt_init_misaligned(struct kunit *test)
+ tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, tt);
+
+- bo = ttm_bo_kunit_init(test, test->priv, size);
++ bo = ttm_bo_kunit_init(test, test->priv, size, NULL);
+
+ /* Make the object size misaligned */
+ bo->base.size += 1;
+@@ -110,7 +110,7 @@ static void ttm_tt_fini_basic(struct kunit *test)
+ tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, tt);
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_tt_init(tt, bo, 0, caching, 0);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -130,7 +130,7 @@ static void ttm_tt_fini_sg(struct kunit *test)
+ tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, tt);
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_sg_tt_init(tt, bo, 0, caching);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -151,7 +151,7 @@ static void ttm_tt_fini_shmem(struct kunit *test)
+ tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, tt);
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_tt_init(tt, bo, 0, caching, 0);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -168,7 +168,7 @@ static void ttm_tt_create_basic(struct kunit *test)
+ struct ttm_buffer_object *bo;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+ bo->type = ttm_bo_type_device;
+
+ dma_resv_lock(bo->base.resv, NULL);
+@@ -187,7 +187,7 @@ static void ttm_tt_create_invalid_bo_type(struct kunit *test)
+ struct ttm_buffer_object *bo;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+ bo->type = ttm_bo_type_sg + 1;
+
+ dma_resv_lock(bo->base.resv, NULL);
+@@ -208,7 +208,7 @@ static void ttm_tt_create_ttm_exists(struct kunit *test)
+ tt = kunit_kzalloc(test, sizeof(*tt), GFP_KERNEL);
+ KUNIT_ASSERT_NOT_NULL(test, tt);
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ err = ttm_tt_init(tt, bo, 0, caching, 0);
+ KUNIT_ASSERT_EQ(test, err, 0);
+@@ -239,7 +239,7 @@ static void ttm_tt_create_failed(struct kunit *test)
+ struct ttm_buffer_object *bo;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ /* Update ttm_device_funcs so we don't alloc ttm_tt */
+ devs->ttm_dev->funcs = &ttm_dev_empty_funcs;
+@@ -257,7 +257,7 @@ static void ttm_tt_destroy_basic(struct kunit *test)
+ struct ttm_buffer_object *bo;
+ int err;
+
+- bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE);
++ bo = ttm_bo_kunit_init(test, test->priv, BO_SIZE, NULL);
+
+ dma_resv_lock(bo->base.resv, NULL);
+ err = ttm_tt_create(bo, false);
+diff --git a/drivers/gpu/drm/udl/udl_modeset.c b/drivers/gpu/drm/udl/udl_modeset.c
+index 7702359c90c22..751da3a294c44 100644
+--- a/drivers/gpu/drm/udl/udl_modeset.c
++++ b/drivers/gpu/drm/udl/udl_modeset.c
+@@ -527,8 +527,7 @@ struct drm_connector *udl_connector_init(struct drm_device *dev)
+
+ drm_connector_helper_add(connector, &udl_connector_helper_funcs);
+
+- connector->polled = DRM_CONNECTOR_POLL_HPD |
+- DRM_CONNECTOR_POLL_CONNECT |
++ connector->polled = DRM_CONNECTOR_POLL_CONNECT |
+ DRM_CONNECTOR_POLL_DISCONNECT;
+
+ return connector;
+diff --git a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c
+index d46f87a039f20..b3d3c065dd9d8 100644
+--- a/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c
++++ b/drivers/gpu/drm/xe/display/xe_hdcp_gsc.c
+@@ -159,12 +159,16 @@ void intel_hdcp_gsc_fini(struct xe_device *xe)
+ {
+ struct intel_hdcp_gsc_message *hdcp_message =
+ xe->display.hdcp.hdcp_message;
++ struct i915_hdcp_arbiter *arb = xe->display.hdcp.arbiter;
+
+- if (!hdcp_message)
+- return;
++ if (hdcp_message) {
++ xe_bo_unpin_map_no_vm(hdcp_message->hdcp_bo);
++ kfree(hdcp_message);
++ xe->display.hdcp.hdcp_message = NULL;
++ }
+
+- xe_bo_unpin_map_no_vm(hdcp_message->hdcp_bo);
+- kfree(hdcp_message);
++ kfree(arb);
++ xe->display.hdcp.arbiter = NULL;
+ }
+
+ static int xe_gsc_send_sync(struct xe_device *xe,
+diff --git a/drivers/gpu/drm/xe/xe_bo.c b/drivers/gpu/drm/xe/xe_bo.c
+index bc1f794e3e614..b6f3a43d637f7 100644
+--- a/drivers/gpu/drm/xe/xe_bo.c
++++ b/drivers/gpu/drm/xe/xe_bo.c
+@@ -317,7 +317,7 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
+ struct xe_device *xe = xe_bo_device(bo);
+ struct xe_ttm_tt *tt;
+ unsigned long extra_pages;
+- enum ttm_caching caching;
++ enum ttm_caching caching = ttm_cached;
+ int err;
+
+ tt = kzalloc(sizeof(*tt), GFP_KERNEL);
+@@ -331,26 +331,35 @@ static struct ttm_tt *xe_ttm_tt_create(struct ttm_buffer_object *ttm_bo,
+ extra_pages = DIV_ROUND_UP(xe_device_ccs_bytes(xe, bo->size),
+ PAGE_SIZE);
+
+- switch (bo->cpu_caching) {
+- case DRM_XE_GEM_CPU_CACHING_WC:
+- caching = ttm_write_combined;
+- break;
+- default:
+- caching = ttm_cached;
+- break;
+- }
+-
+- WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
+-
+ /*
+- * Display scanout is always non-coherent with the CPU cache.
+- *
+- * For Xe_LPG and beyond, PPGTT PTE lookups are also non-coherent and
+- * require a CPU:WC mapping.
++ * DGFX system memory is always WB / ttm_cached, since
++ * other caching modes are only supported on x86. DGFX
++ * GPU system memory accesses are always coherent with the
++ * CPU.
+ */
+- if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
+- (xe->info.graphics_verx100 >= 1270 && bo->flags & XE_BO_FLAG_PAGETABLE))
+- caching = ttm_write_combined;
++ if (!IS_DGFX(xe)) {
++ switch (bo->cpu_caching) {
++ case DRM_XE_GEM_CPU_CACHING_WC:
++ caching = ttm_write_combined;
++ break;
++ default:
++ caching = ttm_cached;
++ break;
++ }
++
++ WARN_ON((bo->flags & XE_BO_FLAG_USER) && !bo->cpu_caching);
++
++ /*
++ * Display scanout is always non-coherent with the CPU cache.
++ *
++ * For Xe_LPG and beyond, PPGTT PTE lookups are also
++ * non-coherent and require a CPU:WC mapping.
++ */
++ if ((!bo->cpu_caching && bo->flags & XE_BO_FLAG_SCANOUT) ||
++ (xe->info.graphics_verx100 >= 1270 &&
++ bo->flags & XE_BO_FLAG_PAGETABLE))
++ caching = ttm_write_combined;
++ }
+
+ err = ttm_tt_init(&tt->ttm, &bo->ttm, page_flags, caching, extra_pages);
+ if (err) {
+diff --git a/drivers/gpu/drm/xe/xe_bo_types.h b/drivers/gpu/drm/xe/xe_bo_types.h
+index 86422e113d396..10450f1fbbde7 100644
+--- a/drivers/gpu/drm/xe/xe_bo_types.h
++++ b/drivers/gpu/drm/xe/xe_bo_types.h
+@@ -66,7 +66,8 @@ struct xe_bo {
+
+ /**
+ * @cpu_caching: CPU caching mode. Currently only used for userspace
+- * objects.
++ * objects. Exceptions are system memory on DGFX, which is always
++ * WB.
+ */
+ u16 cpu_caching;
+
+diff --git a/drivers/gpu/drm/xe/xe_exec.c b/drivers/gpu/drm/xe/xe_exec.c
+index 97eeb973e897c..074344c739abc 100644
+--- a/drivers/gpu/drm/xe/xe_exec.c
++++ b/drivers/gpu/drm/xe/xe_exec.c
+@@ -118,7 +118,7 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+ u64 addresses[XE_HW_ENGINE_MAX_INSTANCE];
+ struct drm_gpuvm_exec vm_exec = {.extra.fn = xe_exec_fn};
+ struct drm_exec *exec = &vm_exec.exec;
+- u32 i, num_syncs = 0, num_ufence = 0;
++ u32 i, num_syncs, num_ufence = 0;
+ struct xe_sched_job *job;
+ struct xe_vm *vm;
+ bool write_locked, skip_retry = false;
+@@ -156,15 +156,15 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+
+ vm = q->vm;
+
+- for (i = 0; i < args->num_syncs; i++) {
+- err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs++],
+- &syncs_user[i], SYNC_PARSE_FLAG_EXEC |
++ for (num_syncs = 0; num_syncs < args->num_syncs; num_syncs++) {
++ err = xe_sync_entry_parse(xe, xef, &syncs[num_syncs],
++ &syncs_user[num_syncs], SYNC_PARSE_FLAG_EXEC |
+ (xe_vm_in_lr_mode(vm) ?
+ SYNC_PARSE_FLAG_LR_MODE : 0));
+ if (err)
+ goto err_syncs;
+
+- if (xe_sync_is_ufence(&syncs[i]))
++ if (xe_sync_is_ufence(&syncs[num_syncs]))
+ num_ufence++;
+ }
+
+@@ -325,8 +325,8 @@ int xe_exec_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
+ if (err == -EAGAIN && !skip_retry)
+ goto retry;
+ err_syncs:
+- for (i = 0; i < num_syncs; i++)
+- xe_sync_entry_cleanup(&syncs[i]);
++ while (num_syncs--)
++ xe_sync_entry_cleanup(&syncs[num_syncs]);
+ kfree(syncs);
+ err_exec_queue:
+ xe_exec_queue_put(q);
+diff --git a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+index 6c2cfc54442ce..4f40fe24c649c 100644
+--- a/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
++++ b/drivers/gpu/drm/xe/xe_gt_sriov_pf_config.c
+@@ -1527,6 +1527,7 @@ static u64 pf_estimate_fair_lmem(struct xe_gt *gt, unsigned int num_vfs)
+ u64 fair;
+
+ fair = div_u64(available, num_vfs);
++ fair = rounddown_pow_of_two(fair); /* XXX: ttm_vram_mgr & drm_buddy limitation */
+ fair = ALIGN_DOWN(fair, alignment);
+ #ifdef MAX_FAIR_LMEM
+ fair = min_t(u64, MAX_FAIR_LMEM, fair);
+diff --git a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
+index face8d6b2a6fb..f5781939de9c3 100644
+--- a/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
++++ b/drivers/gpu/drm/xlnx/zynqmp_dpsub.c
+@@ -269,6 +269,7 @@ static int zynqmp_dpsub_probe(struct platform_device *pdev)
+ return 0;
+
+ err_disp:
++ drm_bridge_remove(dpsub->bridge);
+ zynqmp_disp_remove(dpsub);
+ err_dp:
+ zynqmp_dp_remove(dpsub);
+diff --git a/drivers/gpu/drm/xlnx/zynqmp_kms.c b/drivers/gpu/drm/xlnx/zynqmp_kms.c
+index 43bf416b33d5c..f25583ce92e60 100644
+--- a/drivers/gpu/drm/xlnx/zynqmp_kms.c
++++ b/drivers/gpu/drm/xlnx/zynqmp_kms.c
+@@ -433,23 +433,28 @@ static int zynqmp_dpsub_kms_init(struct zynqmp_dpsub *dpsub)
+ DRM_BRIDGE_ATTACH_NO_CONNECTOR);
+ if (ret) {
+ dev_err(dpsub->dev, "failed to attach bridge to encoder\n");
+- return ret;
++ goto err_encoder;
+ }
+
+ /* Create the connector for the chain of bridges. */
+ connector = drm_bridge_connector_init(&dpsub->drm->dev, encoder);
+ if (IS_ERR(connector)) {
+ dev_err(dpsub->dev, "failed to created connector\n");
+- return PTR_ERR(connector);
++ ret = PTR_ERR(connector);
++ goto err_encoder;
+ }
+
+ ret = drm_connector_attach_encoder(connector, encoder);
+ if (ret < 0) {
+ dev_err(dpsub->dev, "failed to attach connector to encoder\n");
+- return ret;
++ goto err_encoder;
+ }
+
+ return 0;
++
++err_encoder:
++ drm_encoder_cleanup(encoder);
++ return ret;
+ }
+
+ static void zynqmp_dpsub_drm_release(struct drm_device *drm, void *res)
+@@ -529,5 +534,6 @@ void zynqmp_dpsub_drm_cleanup(struct zynqmp_dpsub *dpsub)
+
+ drm_dev_unregister(drm);
+ drm_atomic_helper_shutdown(drm);
++ drm_encoder_cleanup(&dpsub->drm->encoder);
+ drm_kms_helper_poll_fini(drm);
+ }
+diff --git a/drivers/hwmon/adt7475.c b/drivers/hwmon/adt7475.c
+index 4224ffb304832..ec3336804720e 100644
+--- a/drivers/hwmon/adt7475.c
++++ b/drivers/hwmon/adt7475.c
+@@ -1900,7 +1900,7 @@ static void adt7475_read_pwm(struct i2c_client *client, int index)
+ data->pwm[CONTROL][index] &= ~0xE0;
+ data->pwm[CONTROL][index] |= (7 << 5);
+
+- i2c_smbus_write_byte_data(client, PWM_CONFIG_REG(index),
++ i2c_smbus_write_byte_data(client, PWM_REG(index),
+ data->pwm[INPUT][index]);
+
+ i2c_smbus_write_byte_data(client, PWM_CONFIG_REG(index),
+diff --git a/drivers/hwmon/ltc2991.c b/drivers/hwmon/ltc2991.c
+index 06750bb93c236..f74ce9c25bf71 100644
+--- a/drivers/hwmon/ltc2991.c
++++ b/drivers/hwmon/ltc2991.c
+@@ -225,8 +225,8 @@ static umode_t ltc2991_is_visible(const void *data,
+ case hwmon_temp:
+ switch (attr) {
+ case hwmon_temp_input:
+- if (st->temp_en[channel] ||
+- channel == LTC2991_T_INT_CH_NR)
++ if (channel == LTC2991_T_INT_CH_NR ||
++ st->temp_en[channel])
+ return 0444;
+ break;
+ }
+diff --git a/drivers/hwmon/max6697.c b/drivers/hwmon/max6697.c
+index d161ba0e7813c..8aac8278193f0 100644
+--- a/drivers/hwmon/max6697.c
++++ b/drivers/hwmon/max6697.c
+@@ -311,6 +311,7 @@ static ssize_t temp_store(struct device *dev,
+ return ret;
+
+ mutex_lock(&data->update_lock);
++ temp = clamp_val(temp, -1000000, 1000000); /* prevent underflow */
+ temp = DIV_ROUND_CLOSEST(temp, 1000) + data->temp_offset;
+ temp = clamp_val(temp, 0, data->type == max6581 ? 255 : 127);
+ data->temp[nr][index] = temp;
+@@ -428,14 +429,14 @@ static SENSOR_DEVICE_ATTR_RO(temp6_max_alarm, alarm, 20);
+ static SENSOR_DEVICE_ATTR_RO(temp7_max_alarm, alarm, 21);
+ static SENSOR_DEVICE_ATTR_RO(temp8_max_alarm, alarm, 23);
+
+-static SENSOR_DEVICE_ATTR_RO(temp1_crit_alarm, alarm, 14);
++static SENSOR_DEVICE_ATTR_RO(temp1_crit_alarm, alarm, 15);
+ static SENSOR_DEVICE_ATTR_RO(temp2_crit_alarm, alarm, 8);
+ static SENSOR_DEVICE_ATTR_RO(temp3_crit_alarm, alarm, 9);
+ static SENSOR_DEVICE_ATTR_RO(temp4_crit_alarm, alarm, 10);
+ static SENSOR_DEVICE_ATTR_RO(temp5_crit_alarm, alarm, 11);
+ static SENSOR_DEVICE_ATTR_RO(temp6_crit_alarm, alarm, 12);
+ static SENSOR_DEVICE_ATTR_RO(temp7_crit_alarm, alarm, 13);
+-static SENSOR_DEVICE_ATTR_RO(temp8_crit_alarm, alarm, 15);
++static SENSOR_DEVICE_ATTR_RO(temp8_crit_alarm, alarm, 14);
+
+ static SENSOR_DEVICE_ATTR_RO(temp2_fault, alarm, 1);
+ static SENSOR_DEVICE_ATTR_RO(temp3_fault, alarm, 2);
+diff --git a/drivers/hwtracing/coresight/coresight-platform.c b/drivers/hwtracing/coresight/coresight-platform.c
+index 9d550f5697fa8..57a009552cc5c 100644
+--- a/drivers/hwtracing/coresight/coresight-platform.c
++++ b/drivers/hwtracing/coresight/coresight-platform.c
+@@ -297,8 +297,10 @@ static int of_get_coresight_platform_data(struct device *dev,
+ continue;
+
+ ret = of_coresight_parse_endpoint(dev, ep, pdata);
+- if (ret)
++ if (ret) {
++ of_node_put(ep);
+ return ret;
++ }
+ }
+
+ return 0;
+diff --git a/drivers/i3c/master/mipi-i3c-hci/core.c b/drivers/i3c/master/mipi-i3c-hci/core.c
+index d7e966a255833..4e7d6a43ee9b3 100644
+--- a/drivers/i3c/master/mipi-i3c-hci/core.c
++++ b/drivers/i3c/master/mipi-i3c-hci/core.c
+@@ -631,6 +631,7 @@ static irqreturn_t i3c_hci_irq_handler(int irq, void *dev_id)
+ static int i3c_hci_init(struct i3c_hci *hci)
+ {
+ u32 regval, offset;
++ bool size_in_dwords;
+ int ret;
+
+ /* Validate HCI hardware version */
+@@ -654,11 +655,16 @@ static int i3c_hci_init(struct i3c_hci *hci)
+ hci->caps = reg_read(HC_CAPABILITIES);
+ DBG("caps = %#x", hci->caps);
+
++ size_in_dwords = hci->version_major < 1 ||
++ (hci->version_major == 1 && hci->version_minor < 1);
++
+ regval = reg_read(DAT_SECTION);
+ offset = FIELD_GET(DAT_TABLE_OFFSET, regval);
+ hci->DAT_regs = offset ? hci->base_regs + offset : NULL;
+ hci->DAT_entries = FIELD_GET(DAT_TABLE_SIZE, regval);
+ hci->DAT_entry_size = FIELD_GET(DAT_ENTRY_SIZE, regval) ? 0 : 8;
++ if (size_in_dwords)
++ hci->DAT_entries = 4 * hci->DAT_entries / hci->DAT_entry_size;
+ dev_info(&hci->master.dev, "DAT: %u %u-bytes entries at offset %#x\n",
+ hci->DAT_entries, hci->DAT_entry_size, offset);
+
+@@ -667,6 +673,8 @@ static int i3c_hci_init(struct i3c_hci *hci)
+ hci->DCT_regs = offset ? hci->base_regs + offset : NULL;
+ hci->DCT_entries = FIELD_GET(DCT_TABLE_SIZE, regval);
+ hci->DCT_entry_size = FIELD_GET(DCT_ENTRY_SIZE, regval) ? 0 : 16;
++ if (size_in_dwords)
++ hci->DCT_entries = 4 * hci->DCT_entries / hci->DCT_entry_size;
+ dev_info(&hci->master.dev, "DCT: %u %u-bytes entries at offset %#x\n",
+ hci->DCT_entries, hci->DCT_entry_size, offset);
+
+diff --git a/drivers/iio/adc/ad9467.c b/drivers/iio/adc/ad9467.c
+index 8f5b9c3f6e3d6..1fd2211e29642 100644
+--- a/drivers/iio/adc/ad9467.c
++++ b/drivers/iio/adc/ad9467.c
+@@ -141,9 +141,10 @@ struct ad9467_state {
+ struct gpio_desc *pwrdown_gpio;
+ /* ensure consistent state obtained on multiple related accesses */
+ struct mutex lock;
++ u8 buf[3] __aligned(IIO_DMA_MINALIGN);
+ };
+
+-static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
++static int ad9467_spi_read(struct ad9467_state *st, unsigned int reg)
+ {
+ unsigned char tbuf[2], rbuf[1];
+ int ret;
+@@ -151,7 +152,7 @@ static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
+ tbuf[0] = 0x80 | (reg >> 8);
+ tbuf[1] = reg & 0xFF;
+
+- ret = spi_write_then_read(spi,
++ ret = spi_write_then_read(st->spi,
+ tbuf, ARRAY_SIZE(tbuf),
+ rbuf, ARRAY_SIZE(rbuf));
+
+@@ -161,35 +162,32 @@ static int ad9467_spi_read(struct spi_device *spi, unsigned int reg)
+ return rbuf[0];
+ }
+
+-static int ad9467_spi_write(struct spi_device *spi, unsigned int reg,
++static int ad9467_spi_write(struct ad9467_state *st, unsigned int reg,
+ unsigned int val)
+ {
+- unsigned char buf[3];
++ st->buf[0] = reg >> 8;
++ st->buf[1] = reg & 0xFF;
++ st->buf[2] = val;
+
+- buf[0] = reg >> 8;
+- buf[1] = reg & 0xFF;
+- buf[2] = val;
+-
+- return spi_write(spi, buf, ARRAY_SIZE(buf));
++ return spi_write(st->spi, st->buf, ARRAY_SIZE(st->buf));
+ }
+
+ static int ad9467_reg_access(struct iio_dev *indio_dev, unsigned int reg,
+ unsigned int writeval, unsigned int *readval)
+ {
+ struct ad9467_state *st = iio_priv(indio_dev);
+- struct spi_device *spi = st->spi;
+ int ret;
+
+ if (!readval) {
+ guard(mutex)(&st->lock);
+- ret = ad9467_spi_write(spi, reg, writeval);
++ ret = ad9467_spi_write(st, reg, writeval);
+ if (ret)
+ return ret;
+- return ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
++ return ad9467_spi_write(st, AN877_ADC_REG_TRANSFER,
+ AN877_ADC_TRANSFER_SYNC);
+ }
+
+- ret = ad9467_spi_read(spi, reg);
++ ret = ad9467_spi_read(st, reg);
+ if (ret < 0)
+ return ret;
+ *readval = ret;
+@@ -295,7 +293,7 @@ static int ad9467_get_scale(struct ad9467_state *st, int *val, int *val2)
+ unsigned int i, vref_val;
+ int ret;
+
+- ret = ad9467_spi_read(st->spi, AN877_ADC_REG_VREF);
++ ret = ad9467_spi_read(st, AN877_ADC_REG_VREF);
+ if (ret < 0)
+ return ret;
+
+@@ -330,31 +328,31 @@ static int ad9467_set_scale(struct ad9467_state *st, int val, int val2)
+ continue;
+
+ guard(mutex)(&st->lock);
+- ret = ad9467_spi_write(st->spi, AN877_ADC_REG_VREF,
++ ret = ad9467_spi_write(st, AN877_ADC_REG_VREF,
+ info->scale_table[i][1]);
+ if (ret < 0)
+ return ret;
+
+- return ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
++ return ad9467_spi_write(st, AN877_ADC_REG_TRANSFER,
+ AN877_ADC_TRANSFER_SYNC);
+ }
+
+ return -EINVAL;
+ }
+
+-static int ad9467_outputmode_set(struct spi_device *spi, unsigned int mode)
++static int ad9467_outputmode_set(struct ad9467_state *st, unsigned int mode)
+ {
+ int ret;
+
+- ret = ad9467_spi_write(spi, AN877_ADC_REG_OUTPUT_MODE, mode);
++ ret = ad9467_spi_write(st, AN877_ADC_REG_OUTPUT_MODE, mode);
+ if (ret < 0)
+ return ret;
+
+- return ad9467_spi_write(spi, AN877_ADC_REG_TRANSFER,
++ return ad9467_spi_write(st, AN877_ADC_REG_TRANSFER,
+ AN877_ADC_TRANSFER_SYNC);
+ }
+
+-static int ad9647_calibrate_prepare(const struct ad9467_state *st)
++static int ad9647_calibrate_prepare(struct ad9467_state *st)
+ {
+ struct iio_backend_data_fmt data = {
+ .enable = false,
+@@ -362,17 +360,17 @@ static int ad9647_calibrate_prepare(const struct ad9467_state *st)
+ unsigned int c;
+ int ret;
+
+- ret = ad9467_spi_write(st->spi, AN877_ADC_REG_TEST_IO,
++ ret = ad9467_spi_write(st, AN877_ADC_REG_TEST_IO,
+ AN877_ADC_TESTMODE_PN9_SEQ);
+ if (ret)
+ return ret;
+
+- ret = ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
++ ret = ad9467_spi_write(st, AN877_ADC_REG_TRANSFER,
+ AN877_ADC_TRANSFER_SYNC);
+ if (ret)
+ return ret;
+
+- ret = ad9467_outputmode_set(st->spi, st->info->default_output_mode);
++ ret = ad9467_outputmode_set(st, st->info->default_output_mode);
+ if (ret)
+ return ret;
+
+@@ -390,7 +388,7 @@ static int ad9647_calibrate_prepare(const struct ad9467_state *st)
+ return iio_backend_chan_enable(st->back, 0);
+ }
+
+-static int ad9647_calibrate_polarity_set(const struct ad9467_state *st,
++static int ad9647_calibrate_polarity_set(struct ad9467_state *st,
+ bool invert)
+ {
+ enum iio_backend_sample_trigger trigger;
+@@ -401,7 +399,7 @@ static int ad9647_calibrate_polarity_set(const struct ad9467_state *st,
+ if (invert)
+ phase |= AN877_ADC_INVERT_DCO_CLK;
+
+- return ad9467_spi_write(st->spi, AN877_ADC_REG_OUTPUT_PHASE,
++ return ad9467_spi_write(st, AN877_ADC_REG_OUTPUT_PHASE,
+ phase);
+ }
+
+@@ -437,19 +435,18 @@ static unsigned int ad9467_find_optimal_point(const unsigned long *calib_map,
+ return cnt;
+ }
+
+-static int ad9467_calibrate_apply(const struct ad9467_state *st,
+- unsigned int val)
++static int ad9467_calibrate_apply(struct ad9467_state *st, unsigned int val)
+ {
+ unsigned int lane;
+ int ret;
+
+ if (st->info->has_dco) {
+- ret = ad9467_spi_write(st->spi, AN877_ADC_REG_OUTPUT_DELAY,
++ ret = ad9467_spi_write(st, AN877_ADC_REG_OUTPUT_DELAY,
+ val);
+ if (ret)
+ return ret;
+
+- return ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
++ return ad9467_spi_write(st, AN877_ADC_REG_TRANSFER,
+ AN877_ADC_TRANSFER_SYNC);
+ }
+
+@@ -462,7 +459,7 @@ static int ad9467_calibrate_apply(const struct ad9467_state *st,
+ return 0;
+ }
+
+-static int ad9647_calibrate_stop(const struct ad9467_state *st)
++static int ad9647_calibrate_stop(struct ad9467_state *st)
+ {
+ struct iio_backend_data_fmt data = {
+ .sign_extend = true,
+@@ -487,16 +484,16 @@ static int ad9647_calibrate_stop(const struct ad9467_state *st)
+ }
+
+ mode = st->info->default_output_mode | AN877_ADC_OUTPUT_MODE_TWOS_COMPLEMENT;
+- ret = ad9467_outputmode_set(st->spi, mode);
++ ret = ad9467_outputmode_set(st, mode);
+ if (ret)
+ return ret;
+
+- ret = ad9467_spi_write(st->spi, AN877_ADC_REG_TEST_IO,
++ ret = ad9467_spi_write(st, AN877_ADC_REG_TEST_IO,
+ AN877_ADC_TESTMODE_OFF);
+ if (ret)
+ return ret;
+
+- return ad9467_spi_write(st->spi, AN877_ADC_REG_TRANSFER,
++ return ad9467_spi_write(st, AN877_ADC_REG_TRANSFER,
+ AN877_ADC_TRANSFER_SYNC);
+ }
+
+@@ -846,7 +843,7 @@ static int ad9467_probe(struct spi_device *spi)
+ if (ret)
+ return ret;
+
+- id = ad9467_spi_read(spi, AN877_ADC_REG_CHIP_ID);
++ id = ad9467_spi_read(st, AN877_ADC_REG_CHIP_ID);
+ if (id != st->info->id) {
+ dev_err(&spi->dev, "Mismatch CHIP_ID, got 0x%X, expected 0x%X\n",
+ id, st->info->id);
+diff --git a/drivers/iio/adc/adi-axi-adc.c b/drivers/iio/adc/adi-axi-adc.c
+index 0cf0d81358fd5..bf51d619ebbc9 100644
+--- a/drivers/iio/adc/adi-axi-adc.c
++++ b/drivers/iio/adc/adi-axi-adc.c
+@@ -85,6 +85,7 @@ static int axi_adc_enable(struct iio_backend *back)
+ struct adi_axi_adc_state *st = iio_backend_get_priv(back);
+ int ret;
+
++ guard(mutex)(&st->lock);
+ ret = regmap_set_bits(st->regmap, ADI_AXI_REG_RSTN,
+ ADI_AXI_REG_RSTN_MMCM_RSTN);
+ if (ret)
+@@ -99,6 +100,7 @@ static void axi_adc_disable(struct iio_backend *back)
+ {
+ struct adi_axi_adc_state *st = iio_backend_get_priv(back);
+
++ guard(mutex)(&st->lock);
+ regmap_write(st->regmap, ADI_AXI_REG_RSTN, 0);
+ }
+
+diff --git a/drivers/iio/frequency/adrf6780.c b/drivers/iio/frequency/adrf6780.c
+index b4defb82f37e3..3f46032c92752 100644
+--- a/drivers/iio/frequency/adrf6780.c
++++ b/drivers/iio/frequency/adrf6780.c
+@@ -9,7 +9,6 @@
+ #include <linux/bits.h>
+ #include <linux/clk.h>
+ #include <linux/clkdev.h>
+-#include <linux/clk-provider.h>
+ #include <linux/delay.h>
+ #include <linux/device.h>
+ #include <linux/iio/iio.h>
+diff --git a/drivers/iio/industrialio-gts-helper.c b/drivers/iio/industrialio-gts-helper.c
+index b51eb6cb766f3..59d7615c0f565 100644
+--- a/drivers/iio/industrialio-gts-helper.c
++++ b/drivers/iio/industrialio-gts-helper.c
+@@ -362,17 +362,20 @@ static int iio_gts_build_avail_time_table(struct iio_gts *gts)
+ for (i = gts->num_itime - 1; i >= 0; i--) {
+ int new = gts->itime_table[i].time_us;
+
+- if (times[idx] < new) {
++ if (idx == 0 || times[idx - 1] < new) {
+ times[idx++] = new;
+ continue;
+ }
+
+- for (j = 0; j <= idx; j++) {
++ for (j = 0; j < idx; j++) {
++ if (times[j] == new)
++ break;
+ if (times[j] > new) {
+ memmove(×[j + 1], ×[j],
+ (idx - j) * sizeof(int));
+ times[j] = new;
+ idx++;
++ break;
+ }
+ }
+ }
+diff --git a/drivers/infiniband/core/cache.c b/drivers/infiniband/core/cache.c
+index c02a96d3572a8..6791df64a5fe0 100644
+--- a/drivers/infiniband/core/cache.c
++++ b/drivers/infiniband/core/cache.c
+@@ -794,7 +794,6 @@ static struct ib_gid_table *alloc_gid_table(int sz)
+ static void release_gid_table(struct ib_device *device,
+ struct ib_gid_table *table)
+ {
+- bool leak = false;
+ int i;
+
+ if (!table)
+@@ -803,15 +802,12 @@ static void release_gid_table(struct ib_device *device,
+ for (i = 0; i < table->sz; i++) {
+ if (is_gid_entry_free(table->data_vec[i]))
+ continue;
+- if (kref_read(&table->data_vec[i]->kref) > 1) {
+- dev_err(&device->dev,
+- "GID entry ref leak for index %d ref=%u\n", i,
+- kref_read(&table->data_vec[i]->kref));
+- leak = true;
+- }
++
++ WARN_ONCE(true,
++ "GID entry ref leak for dev %s index %d ref=%u\n",
++ dev_name(&device->dev), i,
++ kref_read(&table->data_vec[i]->kref));
+ }
+- if (leak)
+- return;
+
+ mutex_destroy(&table->lock);
+ kfree(table->data_vec);
+diff --git a/drivers/infiniband/core/device.c b/drivers/infiniband/core/device.c
+index 55aa7aa32d4ab..46d1c2c32d719 100644
+--- a/drivers/infiniband/core/device.c
++++ b/drivers/infiniband/core/device.c
+@@ -2146,6 +2146,9 @@ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev,
+ unsigned long flags;
+ int ret;
+
++ if (!rdma_is_port_valid(ib_dev, port))
++ return -EINVAL;
++
+ /*
+ * Drivers wish to call this before ib_register_driver, so we have to
+ * setup the port data early.
+@@ -2154,9 +2157,6 @@ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev,
+ if (ret)
+ return ret;
+
+- if (!rdma_is_port_valid(ib_dev, port))
+- return -EINVAL;
+-
+ pdata = &ib_dev->port_data[port];
+ spin_lock_irqsave(&pdata->netdev_lock, flags);
+ old_ndev = rcu_dereference_protected(
+@@ -2166,16 +2166,12 @@ int ib_device_set_netdev(struct ib_device *ib_dev, struct net_device *ndev,
+ return 0;
+ }
+
+- if (old_ndev)
+- netdev_tracker_free(ndev, &pdata->netdev_tracker);
+- if (ndev)
+- netdev_hold(ndev, &pdata->netdev_tracker, GFP_ATOMIC);
+ rcu_assign_pointer(pdata->netdev, ndev);
++ netdev_put(old_ndev, &pdata->netdev_tracker);
++ netdev_hold(ndev, &pdata->netdev_tracker, GFP_ATOMIC);
+ spin_unlock_irqrestore(&pdata->netdev_lock, flags);
+
+ add_ndev_hash(pdata);
+- __dev_put(old_ndev);
+-
+ return 0;
+ }
+ EXPORT_SYMBOL(ib_device_set_netdev);
+diff --git a/drivers/infiniband/core/iwcm.c b/drivers/infiniband/core/iwcm.c
+index 0301fcad4b48b..bf3265e678651 100644
+--- a/drivers/infiniband/core/iwcm.c
++++ b/drivers/infiniband/core/iwcm.c
+@@ -368,8 +368,10 @@ EXPORT_SYMBOL(iw_cm_disconnect);
+ *
+ * Clean up all resources associated with the connection and release
+ * the initial reference taken by iw_create_cm_id.
++ *
++ * Returns true if and only if the last cm_id_priv reference has been dropped.
+ */
+-static void destroy_cm_id(struct iw_cm_id *cm_id)
++static bool destroy_cm_id(struct iw_cm_id *cm_id)
+ {
+ struct iwcm_id_private *cm_id_priv;
+ struct ib_qp *qp;
+@@ -439,7 +441,7 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
+ iwpm_remove_mapping(&cm_id->local_addr, RDMA_NL_IWCM);
+ }
+
+- (void)iwcm_deref_id(cm_id_priv);
++ return iwcm_deref_id(cm_id_priv);
+ }
+
+ /*
+@@ -450,7 +452,8 @@ static void destroy_cm_id(struct iw_cm_id *cm_id)
+ */
+ void iw_destroy_cm_id(struct iw_cm_id *cm_id)
+ {
+- destroy_cm_id(cm_id);
++ if (!destroy_cm_id(cm_id))
++ flush_workqueue(iwcm_wq);
+ }
+ EXPORT_SYMBOL(iw_destroy_cm_id);
+
+@@ -1034,7 +1037,7 @@ static void cm_work_handler(struct work_struct *_work)
+ if (!test_bit(IWCM_F_DROP_EVENTS, &cm_id_priv->flags)) {
+ ret = process_event(cm_id_priv, &levent);
+ if (ret)
+- destroy_cm_id(&cm_id_priv->id);
++ WARN_ON_ONCE(destroy_cm_id(&cm_id_priv->id));
+ } else
+ pr_debug("dropping event %d\n", levent.event);
+ if (iwcm_deref_id(cm_id_priv))
+diff --git a/drivers/infiniband/hw/bnxt_re/ib_verbs.c b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+index ce9c5bae83bf1..582e83a36ccbe 100644
+--- a/drivers/infiniband/hw/bnxt_re/ib_verbs.c
++++ b/drivers/infiniband/hw/bnxt_re/ib_verbs.c
+@@ -2479,7 +2479,7 @@ static int bnxt_re_build_send_wqe(struct bnxt_re_qp *qp,
+ break;
+ case IB_WR_SEND_WITH_IMM:
+ wqe->type = BNXT_QPLIB_SWQE_TYPE_SEND_WITH_IMM;
+- wqe->send.imm_data = wr->ex.imm_data;
++ wqe->send.imm_data = be32_to_cpu(wr->ex.imm_data);
+ break;
+ case IB_WR_SEND_WITH_INV:
+ wqe->type = BNXT_QPLIB_SWQE_TYPE_SEND_WITH_INV;
+@@ -2509,7 +2509,7 @@ static int bnxt_re_build_rdma_wqe(const struct ib_send_wr *wr,
+ break;
+ case IB_WR_RDMA_WRITE_WITH_IMM:
+ wqe->type = BNXT_QPLIB_SWQE_TYPE_RDMA_WRITE_WITH_IMM;
+- wqe->rdma.imm_data = wr->ex.imm_data;
++ wqe->rdma.imm_data = be32_to_cpu(wr->ex.imm_data);
+ break;
+ case IB_WR_RDMA_READ:
+ wqe->type = BNXT_QPLIB_SWQE_TYPE_RDMA_READ;
+@@ -3581,7 +3581,7 @@ static void bnxt_re_process_res_shadow_qp_wc(struct bnxt_re_qp *gsi_sqp,
+ wc->byte_len = orig_cqe->length;
+ wc->qp = &gsi_qp->ib_qp;
+
+- wc->ex.imm_data = orig_cqe->immdata;
++ wc->ex.imm_data = cpu_to_be32(le32_to_cpu(orig_cqe->immdata));
+ wc->src_qp = orig_cqe->src_qp;
+ memcpy(wc->smac, orig_cqe->smac, ETH_ALEN);
+ if (bnxt_re_is_vlan_pkt(orig_cqe, &vlan_id, &sl)) {
+@@ -3726,7 +3726,7 @@ int bnxt_re_poll_cq(struct ib_cq *ib_cq, int num_entries, struct ib_wc *wc)
+ (unsigned long)(cqe->qp_handle),
+ struct bnxt_re_qp, qplib_qp);
+ wc->qp = &qp->ib_qp;
+- wc->ex.imm_data = cqe->immdata;
++ wc->ex.imm_data = cpu_to_be32(le32_to_cpu(cqe->immdata));
+ wc->src_qp = cqe->src_qp;
+ memcpy(wc->smac, cqe->smac, ETH_ALEN);
+ wc->port_num = 1;
+diff --git a/drivers/infiniband/hw/bnxt_re/qplib_fp.h b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+index 7fd4506b3584f..244da20d1181f 100644
+--- a/drivers/infiniband/hw/bnxt_re/qplib_fp.h
++++ b/drivers/infiniband/hw/bnxt_re/qplib_fp.h
+@@ -164,7 +164,7 @@ struct bnxt_qplib_swqe {
+ /* Send, with imm, inval key */
+ struct {
+ union {
+- __be32 imm_data;
++ u32 imm_data;
+ u32 inv_key;
+ };
+ u32 q_key;
+@@ -182,7 +182,7 @@ struct bnxt_qplib_swqe {
+ /* RDMA write, with imm, read */
+ struct {
+ union {
+- __be32 imm_data;
++ u32 imm_data;
+ u32 inv_key;
+ };
+ u64 remote_va;
+@@ -389,7 +389,7 @@ struct bnxt_qplib_cqe {
+ u16 cfa_meta;
+ u64 wr_id;
+ union {
+- __be32 immdata;
++ __le32 immdata;
+ u32 invrkey;
+ };
+ u64 qp_handle;
+diff --git a/drivers/infiniband/hw/hns/hns_roce_device.h b/drivers/infiniband/hw/hns/hns_roce_device.h
+index ff0b3f68ee3a4..7d5931872f8a7 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_device.h
++++ b/drivers/infiniband/hw/hns/hns_roce_device.h
+@@ -83,6 +83,7 @@
+ #define MR_TYPE_DMA 0x03
+
+ #define HNS_ROCE_FRMR_MAX_PA 512
++#define HNS_ROCE_FRMR_ALIGN_SIZE 128
+
+ #define PKEY_ID 0xffff
+ #define NODE_DESC_SIZE 64
+@@ -91,6 +92,8 @@
+ /* Configure to HW for PAGE_SIZE larger than 4KB */
+ #define PG_SHIFT_OFFSET (PAGE_SHIFT - 12)
+
++#define ATOMIC_WR_LEN 8
++
+ #define HNS_ROCE_IDX_QUE_ENTRY_SZ 4
+ #define SRQ_DB_REG 0x230
+
+@@ -187,6 +190,9 @@ enum {
+ #define HNS_HW_PAGE_SHIFT 12
+ #define HNS_HW_PAGE_SIZE (1 << HNS_HW_PAGE_SHIFT)
+
++#define HNS_HW_MAX_PAGE_SHIFT 27
++#define HNS_HW_MAX_PAGE_SIZE (1 << HNS_HW_MAX_PAGE_SHIFT)
++
+ struct hns_roce_uar {
+ u64 pfn;
+ unsigned long index;
+@@ -715,6 +721,7 @@ struct hns_roce_eq {
+ int shift;
+ int event_type;
+ int sub_type;
++ struct work_struct work;
+ };
+
+ struct hns_roce_eq_table {
+diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+index 4287818a737f9..621b057fb9daa 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
++++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.c
+@@ -36,6 +36,7 @@
+ #include <linux/iopoll.h>
+ #include <linux/kernel.h>
+ #include <linux/types.h>
++#include <linux/workqueue.h>
+ #include <net/addrconf.h>
+ #include <rdma/ib_addr.h>
+ #include <rdma/ib_cache.h>
+@@ -591,11 +592,16 @@ static inline int set_rc_wqe(struct hns_roce_qp *qp,
+ (wr->send_flags & IB_SEND_SIGNALED) ? 1 : 0);
+
+ if (wr->opcode == IB_WR_ATOMIC_CMP_AND_SWP ||
+- wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD)
++ wr->opcode == IB_WR_ATOMIC_FETCH_AND_ADD) {
++ if (msg_len != ATOMIC_WR_LEN)
++ return -EINVAL;
+ set_atomic_seg(wr, rc_sq_wqe, valid_num_sge);
+- else if (wr->opcode != IB_WR_REG_MR)
++ } else if (wr->opcode != IB_WR_REG_MR) {
+ ret = set_rwqe_data_seg(&qp->ibqp, wr, rc_sq_wqe,
+ &curr_idx, valid_num_sge);
++ if (ret)
++ return ret;
++ }
+
+ /*
+ * The pipeline can sequentially post all valid WQEs into WQ buffer,
+@@ -1269,12 +1275,38 @@ static int hns_roce_cmd_err_convert_errno(u16 desc_ret)
+ return -EIO;
+ }
+
++static u32 hns_roce_cmdq_tx_timeout(u16 opcode, u32 tx_timeout)
++{
++ static const struct hns_roce_cmdq_tx_timeout_map cmdq_tx_timeout[] = {
++ {HNS_ROCE_OPC_POST_MB, HNS_ROCE_OPC_POST_MB_TIMEOUT},
++ };
++ int i;
++
++ for (i = 0; i < ARRAY_SIZE(cmdq_tx_timeout); i++)
++ if (cmdq_tx_timeout[i].opcode == opcode)
++ return cmdq_tx_timeout[i].tx_timeout;
++
++ return tx_timeout;
++}
++
++static void hns_roce_wait_csq_done(struct hns_roce_dev *hr_dev, u16 opcode)
++{
++ struct hns_roce_v2_priv *priv = hr_dev->priv;
++ u32 tx_timeout = hns_roce_cmdq_tx_timeout(opcode, priv->cmq.tx_timeout);
++ u32 timeout = 0;
++
++ do {
++ if (hns_roce_cmq_csq_done(hr_dev))
++ break;
++ udelay(1);
++ } while (++timeout < tx_timeout);
++}
++
+ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+ struct hns_roce_cmq_desc *desc, int num)
+ {
+ struct hns_roce_v2_priv *priv = hr_dev->priv;
+ struct hns_roce_v2_cmq_ring *csq = &priv->cmq.csq;
+- u32 timeout = 0;
+ u16 desc_ret;
+ u32 tail;
+ int ret;
+@@ -1295,12 +1327,7 @@ static int __hns_roce_cmq_send(struct hns_roce_dev *hr_dev,
+
+ atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CMDS_CNT]);
+
+- do {
+- if (hns_roce_cmq_csq_done(hr_dev))
+- break;
+- udelay(1);
+- } while (++timeout < priv->cmq.tx_timeout);
+-
++ hns_roce_wait_csq_done(hr_dev, le16_to_cpu(desc->opcode));
+ if (hns_roce_cmq_csq_done(hr_dev)) {
+ ret = 0;
+ for (i = 0; i < num; i++) {
+@@ -2457,14 +2484,16 @@ static int set_llm_cfg_to_hw(struct hns_roce_dev *hr_dev,
+ static struct hns_roce_link_table *
+ alloc_link_table_buf(struct hns_roce_dev *hr_dev)
+ {
++ u16 total_sl = hr_dev->caps.sl_num * hr_dev->func_num;
+ struct hns_roce_v2_priv *priv = hr_dev->priv;
+ struct hns_roce_link_table *link_tbl;
+ u32 pg_shift, size, min_size;
+
+ link_tbl = &priv->ext_llm;
+ pg_shift = hr_dev->caps.llm_buf_pg_sz + PAGE_SHIFT;
+- size = hr_dev->caps.num_qps * HNS_ROCE_V2_EXT_LLM_ENTRY_SZ;
+- min_size = HNS_ROCE_EXT_LLM_MIN_PAGES(hr_dev->caps.sl_num) << pg_shift;
++ size = hr_dev->caps.num_qps * hr_dev->func_num *
++ HNS_ROCE_V2_EXT_LLM_ENTRY_SZ;
++ min_size = HNS_ROCE_EXT_LLM_MIN_PAGES(total_sl) << pg_shift;
+
+ /* Alloc data table */
+ size = max(size, min_size);
+@@ -6135,33 +6164,11 @@ static struct hns_roce_ceqe *next_ceqe_sw_v2(struct hns_roce_eq *eq)
+ !!(eq->cons_index & eq->entries)) ? ceqe : NULL;
+ }
+
+-static irqreturn_t hns_roce_v2_ceq_int(struct hns_roce_dev *hr_dev,
+- struct hns_roce_eq *eq)
++static irqreturn_t hns_roce_v2_ceq_int(struct hns_roce_eq *eq)
+ {
+- struct hns_roce_ceqe *ceqe = next_ceqe_sw_v2(eq);
+- irqreturn_t ceqe_found = IRQ_NONE;
+- u32 cqn;
+-
+- while (ceqe) {
+- /* Make sure we read CEQ entry after we have checked the
+- * ownership bit
+- */
+- dma_rmb();
+-
+- cqn = hr_reg_read(ceqe, CEQE_CQN);
+-
+- hns_roce_cq_completion(hr_dev, cqn);
+-
+- ++eq->cons_index;
+- ceqe_found = IRQ_HANDLED;
+- atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CEQE_CNT]);
++ queue_work(system_bh_wq, &eq->work);
+
+- ceqe = next_ceqe_sw_v2(eq);
+- }
+-
+- update_eq_db(eq);
+-
+- return IRQ_RETVAL(ceqe_found);
++ return IRQ_HANDLED;
+ }
+
+ static irqreturn_t hns_roce_v2_msix_interrupt_eq(int irq, void *eq_ptr)
+@@ -6172,7 +6179,7 @@ static irqreturn_t hns_roce_v2_msix_interrupt_eq(int irq, void *eq_ptr)
+
+ if (eq->type_flag == HNS_ROCE_CEQ)
+ /* Completion event interrupt */
+- int_work = hns_roce_v2_ceq_int(hr_dev, eq);
++ int_work = hns_roce_v2_ceq_int(eq);
+ else
+ /* Asynchronous event interrupt */
+ int_work = hns_roce_v2_aeq_int(hr_dev, eq);
+@@ -6384,9 +6391,16 @@ static void hns_roce_v2_int_mask_enable(struct hns_roce_dev *hr_dev,
+ roce_write(hr_dev, ROCEE_VF_ABN_INT_CFG_REG, enable_flag);
+ }
+
+-static void hns_roce_v2_destroy_eqc(struct hns_roce_dev *hr_dev, u32 eqn)
++static void free_eq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
++{
++ hns_roce_mtr_destroy(hr_dev, &eq->mtr);
++}
++
++static void hns_roce_v2_destroy_eqc(struct hns_roce_dev *hr_dev,
++ struct hns_roce_eq *eq)
+ {
+ struct device *dev = hr_dev->dev;
++ int eqn = eq->eqn;
+ int ret;
+ u8 cmd;
+
+@@ -6397,12 +6411,9 @@ static void hns_roce_v2_destroy_eqc(struct hns_roce_dev *hr_dev, u32 eqn)
+
+ ret = hns_roce_destroy_hw_ctx(hr_dev, cmd, eqn & HNS_ROCE_V2_EQN_M);
+ if (ret)
+- dev_err(dev, "[mailbox cmd] destroy eqc(%u) failed.\n", eqn);
+-}
++ dev_err(dev, "[mailbox cmd] destroy eqc(%d) failed.\n", eqn);
+
+-static void free_eq_buf(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
+-{
+- hns_roce_mtr_destroy(hr_dev, &eq->mtr);
++ free_eq_buf(hr_dev, eq);
+ }
+
+ static void init_eq_config(struct hns_roce_dev *hr_dev, struct hns_roce_eq *eq)
+@@ -6540,6 +6551,34 @@ static int hns_roce_v2_create_eq(struct hns_roce_dev *hr_dev,
+ return ret;
+ }
+
++static void hns_roce_ceq_work(struct work_struct *work)
++{
++ struct hns_roce_eq *eq = from_work(eq, work, work);
++ struct hns_roce_ceqe *ceqe = next_ceqe_sw_v2(eq);
++ struct hns_roce_dev *hr_dev = eq->hr_dev;
++ int ceqe_num = 0;
++ u32 cqn;
++
++ while (ceqe && ceqe_num < hr_dev->caps.ceqe_depth) {
++ /* Make sure we read CEQ entry after we have checked the
++ * ownership bit
++ */
++ dma_rmb();
++
++ cqn = hr_reg_read(ceqe, CEQE_CQN);
++
++ hns_roce_cq_completion(hr_dev, cqn);
++
++ ++eq->cons_index;
++ ++ceqe_num;
++ atomic64_inc(&hr_dev->dfx_cnt[HNS_ROCE_DFX_CEQE_CNT]);
++
++ ceqe = next_ceqe_sw_v2(eq);
++ }
++
++ update_eq_db(eq);
++}
++
+ static int __hns_roce_request_irq(struct hns_roce_dev *hr_dev, int irq_num,
+ int comp_num, int aeq_num, int other_num)
+ {
+@@ -6571,21 +6610,24 @@ static int __hns_roce_request_irq(struct hns_roce_dev *hr_dev, int irq_num,
+ j - other_num - aeq_num);
+
+ for (j = 0; j < irq_num; j++) {
+- if (j < other_num)
++ if (j < other_num) {
+ ret = request_irq(hr_dev->irq[j],
+ hns_roce_v2_msix_interrupt_abn,
+ 0, hr_dev->irq_names[j], hr_dev);
+-
+- else if (j < (other_num + comp_num))
++ } else if (j < (other_num + comp_num)) {
++ INIT_WORK(&eq_table->eq[j - other_num].work,
++ hns_roce_ceq_work);
+ ret = request_irq(eq_table->eq[j - other_num].irq,
+ hns_roce_v2_msix_interrupt_eq,
+ 0, hr_dev->irq_names[j + aeq_num],
+ &eq_table->eq[j - other_num]);
+- else
++ } else {
+ ret = request_irq(eq_table->eq[j - other_num].irq,
+ hns_roce_v2_msix_interrupt_eq,
+ 0, hr_dev->irq_names[j - comp_num],
+ &eq_table->eq[j - other_num]);
++ }
++
+ if (ret) {
+ dev_err(hr_dev->dev, "request irq error!\n");
+ goto err_request_failed;
+@@ -6595,12 +6637,16 @@ static int __hns_roce_request_irq(struct hns_roce_dev *hr_dev, int irq_num,
+ return 0;
+
+ err_request_failed:
+- for (j -= 1; j >= 0; j--)
+- if (j < other_num)
++ for (j -= 1; j >= 0; j--) {
++ if (j < other_num) {
+ free_irq(hr_dev->irq[j], hr_dev);
+- else
+- free_irq(eq_table->eq[j - other_num].irq,
+- &eq_table->eq[j - other_num]);
++ continue;
++ }
++ free_irq(eq_table->eq[j - other_num].irq,
++ &eq_table->eq[j - other_num]);
++ if (j < other_num + comp_num)
++ cancel_work_sync(&eq_table->eq[j - other_num].work);
++ }
+
+ err_kzalloc_failed:
+ for (i -= 1; i >= 0; i--)
+@@ -6621,8 +6667,11 @@ static void __hns_roce_free_irq(struct hns_roce_dev *hr_dev)
+ for (i = 0; i < hr_dev->caps.num_other_vectors; i++)
+ free_irq(hr_dev->irq[i], hr_dev);
+
+- for (i = 0; i < eq_num; i++)
++ for (i = 0; i < eq_num; i++) {
+ free_irq(hr_dev->eq_table.eq[i].irq, &hr_dev->eq_table.eq[i]);
++ if (i < hr_dev->caps.num_comp_vectors)
++ cancel_work_sync(&hr_dev->eq_table.eq[i].work);
++ }
+
+ for (i = 0; i < irq_num; i++)
+ kfree(hr_dev->irq_names[i]);
+@@ -6711,7 +6760,7 @@ static int hns_roce_v2_init_eq_table(struct hns_roce_dev *hr_dev)
+
+ err_create_eq_fail:
+ for (i -= 1; i >= 0; i--)
+- free_eq_buf(hr_dev, &eq_table->eq[i]);
++ hns_roce_v2_destroy_eqc(hr_dev, &eq_table->eq[i]);
+ kfree(eq_table->eq);
+
+ return ret;
+@@ -6731,11 +6780,8 @@ static void hns_roce_v2_cleanup_eq_table(struct hns_roce_dev *hr_dev)
+ __hns_roce_free_irq(hr_dev);
+ destroy_workqueue(hr_dev->irq_workq);
+
+- for (i = 0; i < eq_num; i++) {
+- hns_roce_v2_destroy_eqc(hr_dev, i);
+-
+- free_eq_buf(hr_dev, &eq_table->eq[i]);
+- }
++ for (i = 0; i < eq_num; i++)
++ hns_roce_v2_destroy_eqc(hr_dev, &eq_table->eq[i]);
+
+ kfree(eq_table->eq);
+ }
+diff --git a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+index def1d15a03c7e..c65f68a14a260 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
++++ b/drivers/infiniband/hw/hns/hns_roce_hw_v2.h
+@@ -224,6 +224,12 @@ enum hns_roce_opcode_type {
+ HNS_SWITCH_PARAMETER_CFG = 0x1033,
+ };
+
++#define HNS_ROCE_OPC_POST_MB_TIMEOUT 35000
++struct hns_roce_cmdq_tx_timeout_map {
++ u16 opcode;
++ u32 tx_timeout;
++};
++
+ enum {
+ TYPE_CRQ,
+ TYPE_CSQ,
+diff --git a/drivers/infiniband/hw/hns/hns_roce_mr.c b/drivers/infiniband/hw/hns/hns_roce_mr.c
+index 1a61dceb33197..846da8c78b8b7 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_mr.c
++++ b/drivers/infiniband/hw/hns/hns_roce_mr.c
+@@ -443,6 +443,11 @@ int hns_roce_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
+ struct hns_roce_mtr *mtr = &mr->pbl_mtr;
+ int ret, sg_num = 0;
+
++ if (!IS_ALIGNED(*sg_offset, HNS_ROCE_FRMR_ALIGN_SIZE) ||
++ ibmr->page_size < HNS_HW_PAGE_SIZE ||
++ ibmr->page_size > HNS_HW_MAX_PAGE_SIZE)
++ return sg_num;
++
+ mr->npages = 0;
+ mr->page_list = kvcalloc(mr->pbl_mtr.hem_cfg.buf_pg_count,
+ sizeof(dma_addr_t), GFP_KERNEL);
+diff --git a/drivers/infiniband/hw/hns/hns_roce_qp.c b/drivers/infiniband/hw/hns/hns_roce_qp.c
+index db34665d1dfbf..1de384ce4d0e1 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_qp.c
++++ b/drivers/infiniband/hw/hns/hns_roce_qp.c
+@@ -532,13 +532,15 @@ static unsigned int get_sge_num_from_max_inl_data(bool is_ud_or_gsi,
+ {
+ unsigned int inline_sge;
+
+- inline_sge = roundup_pow_of_two(max_inline_data) / HNS_ROCE_SGE_SIZE;
++ if (!max_inline_data)
++ return 0;
+
+ /*
+ * if max_inline_data less than
+ * HNS_ROCE_SGE_IN_WQE * HNS_ROCE_SGE_SIZE,
+ * In addition to ud's mode, no need to extend sge.
+ */
++ inline_sge = roundup_pow_of_two(max_inline_data) / HNS_ROCE_SGE_SIZE;
+ if (!is_ud_or_gsi && inline_sge <= HNS_ROCE_SGE_IN_WQE)
+ inline_sge = 0;
+
+diff --git a/drivers/infiniband/hw/hns/hns_roce_srq.c b/drivers/infiniband/hw/hns/hns_roce_srq.c
+index f1997abc97cac..c9b8233f4b057 100644
+--- a/drivers/infiniband/hw/hns/hns_roce_srq.c
++++ b/drivers/infiniband/hw/hns/hns_roce_srq.c
+@@ -297,7 +297,7 @@ static int set_srq_basic_param(struct hns_roce_srq *srq,
+
+ max_sge = proc_srq_sge(hr_dev, srq, !!udata);
+ if (attr->max_wr > hr_dev->caps.max_srq_wrs ||
+- attr->max_sge > max_sge) {
++ attr->max_sge > max_sge || !attr->max_sge) {
+ ibdev_err(&hr_dev->ib_dev,
+ "invalid SRQ attr, depth = %u, sge = %u.\n",
+ attr->max_wr, attr->max_sge);
+diff --git a/drivers/infiniband/hw/mana/device.c b/drivers/infiniband/hw/mana/device.c
+index 7e09ceb3da537..7bb7e06392001 100644
+--- a/drivers/infiniband/hw/mana/device.c
++++ b/drivers/infiniband/hw/mana/device.c
+@@ -5,6 +5,7 @@
+
+ #include "mana_ib.h"
+ #include <net/mana/mana_auxiliary.h>
++#include <net/addrconf.h>
+
+ MODULE_DESCRIPTION("Microsoft Azure Network Adapter IB driver");
+ MODULE_LICENSE("GPL");
+@@ -55,7 +56,7 @@ static int mana_ib_probe(struct auxiliary_device *adev,
+ {
+ struct mana_adev *madev = container_of(adev, struct mana_adev, adev);
+ struct gdma_dev *mdev = madev->mdev;
+- struct net_device *upper_ndev;
++ struct net_device *ndev;
+ struct mana_context *mc;
+ struct mana_ib_dev *dev;
+ u8 mac_addr[ETH_ALEN];
+@@ -83,16 +84,17 @@ static int mana_ib_probe(struct auxiliary_device *adev,
+ dev->ib_dev.num_comp_vectors = mdev->gdma_context->max_num_queues;
+ dev->ib_dev.dev.parent = mdev->gdma_context->dev;
+
+- rcu_read_lock(); /* required to get upper dev */
+- upper_ndev = netdev_master_upper_dev_get_rcu(mc->ports[0]);
+- if (!upper_ndev) {
++ rcu_read_lock(); /* required to get primary netdev */
++ ndev = mana_get_primary_netdev_rcu(mc, 0);
++ if (!ndev) {
+ rcu_read_unlock();
+ ret = -ENODEV;
+- ibdev_err(&dev->ib_dev, "Failed to get master netdev");
++ ibdev_err(&dev->ib_dev, "Failed to get netdev for IB port 1");
+ goto free_ib_device;
+ }
+- ether_addr_copy(mac_addr, upper_ndev->dev_addr);
+- ret = ib_device_set_netdev(&dev->ib_dev, upper_ndev, 1);
++ ether_addr_copy(mac_addr, ndev->dev_addr);
++ addrconf_addr_eui48((u8 *)&dev->ib_dev.node_guid, ndev->dev_addr);
++ ret = ib_device_set_netdev(&dev->ib_dev, ndev, 1);
+ rcu_read_unlock();
+ if (ret) {
+ ibdev_err(&dev->ib_dev, "Failed to set ib netdev, ret %d", ret);
+diff --git a/drivers/infiniband/hw/mlx4/alias_GUID.c b/drivers/infiniband/hw/mlx4/alias_GUID.c
+index 111fa88a3be44..9a439569ffcf3 100644
+--- a/drivers/infiniband/hw/mlx4/alias_GUID.c
++++ b/drivers/infiniband/hw/mlx4/alias_GUID.c
+@@ -829,7 +829,7 @@ void mlx4_ib_destroy_alias_guid_service(struct mlx4_ib_dev *dev)
+
+ int mlx4_ib_init_alias_guid_service(struct mlx4_ib_dev *dev)
+ {
+- char alias_wq_name[15];
++ char alias_wq_name[22];
+ int ret = 0;
+ int i, j;
+ union ib_gid gid;
+diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
+index a37cfac5e23f9..dc9cf45d2d320 100644
+--- a/drivers/infiniband/hw/mlx4/mad.c
++++ b/drivers/infiniband/hw/mlx4/mad.c
+@@ -2158,7 +2158,7 @@ static int mlx4_ib_alloc_demux_ctx(struct mlx4_ib_dev *dev,
+ struct mlx4_ib_demux_ctx *ctx,
+ int port)
+ {
+- char name[12];
++ char name[21];
+ int ret = 0;
+ int i;
+
+diff --git a/drivers/infiniband/hw/mlx5/mlx5_ib.h b/drivers/infiniband/hw/mlx5/mlx5_ib.h
+index f255a12e26a02..f9abdca3493aa 100644
+--- a/drivers/infiniband/hw/mlx5/mlx5_ib.h
++++ b/drivers/infiniband/hw/mlx5/mlx5_ib.h
+@@ -115,6 +115,19 @@ unsigned long __mlx5_umem_find_best_quantized_pgoff(
+ __mlx5_bit_sz(typ, page_offset_fld), 0, scale, \
+ page_offset_quantized)
+
++static inline unsigned long
++mlx5_umem_dmabuf_find_best_pgsz(struct ib_umem_dmabuf *umem_dmabuf)
++{
++ /*
++ * mkeys used for dmabuf are fixed at PAGE_SIZE because we must be able
++ * to hold any sgl after a move operation. Ideally the mkc page size
++ * could be changed at runtime to be optimal, but right now the driver
++ * cannot do that.
++ */
++ return ib_umem_find_best_pgsz(&umem_dmabuf->umem, PAGE_SIZE,
++ umem_dmabuf->umem.iova);
++}
++
+ enum {
+ MLX5_IB_MMAP_OFFSET_START = 9,
+ MLX5_IB_MMAP_OFFSET_END = 255,
+diff --git a/drivers/infiniband/hw/mlx5/odp.c b/drivers/infiniband/hw/mlx5/odp.c
+index 4a04cbc5b78a4..a524181f34df9 100644
+--- a/drivers/infiniband/hw/mlx5/odp.c
++++ b/drivers/infiniband/hw/mlx5/odp.c
+@@ -705,10 +705,8 @@ static int pagefault_dmabuf_mr(struct mlx5_ib_mr *mr, size_t bcnt,
+ return err;
+ }
+
+- page_size = mlx5_umem_find_best_pgsz(&umem_dmabuf->umem, mkc,
+- log_page_size, 0,
+- umem_dmabuf->umem.iova);
+- if (unlikely(page_size < PAGE_SIZE)) {
++ page_size = mlx5_umem_dmabuf_find_best_pgsz(umem_dmabuf);
++ if (!page_size) {
+ ib_umem_dmabuf_unmap_pages(umem_dmabuf);
+ err = -EINVAL;
+ } else {
+diff --git a/drivers/infiniband/sw/rxe/rxe_req.c b/drivers/infiniband/sw/rxe/rxe_req.c
+index cd14c4c2dff9d..479c07e6e4ed3 100644
+--- a/drivers/infiniband/sw/rxe/rxe_req.c
++++ b/drivers/infiniband/sw/rxe/rxe_req.c
+@@ -424,7 +424,7 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
+ int paylen;
+ int solicited;
+ u32 qp_num;
+- int ack_req;
++ int ack_req = 0;
+
+ /* length from start of bth to end of icrc */
+ paylen = rxe_opcode[opcode].length + payload + pad + RXE_ICRC_SIZE;
+@@ -445,8 +445,9 @@ static struct sk_buff *init_req_packet(struct rxe_qp *qp,
+ qp_num = (pkt->mask & RXE_DETH_MASK) ? ibwr->wr.ud.remote_qpn :
+ qp->attr.dest_qp_num;
+
+- ack_req = ((pkt->mask & RXE_END_MASK) ||
+- (qp->req.noack_pkts++ > RXE_MAX_PKT_PER_ACK));
++ if (qp_type(qp) != IB_QPT_UD && qp_type(qp) != IB_QPT_UC)
++ ack_req = ((pkt->mask & RXE_END_MASK) ||
++ (qp->req.noack_pkts++ > RXE_MAX_PKT_PER_ACK));
+ if (ack_req)
+ qp->req.noack_pkts = 0;
+
+diff --git a/drivers/input/keyboard/qt1050.c b/drivers/input/keyboard/qt1050.c
+index b51dfcd760386..056e9bc260262 100644
+--- a/drivers/input/keyboard/qt1050.c
++++ b/drivers/input/keyboard/qt1050.c
+@@ -226,7 +226,12 @@ static bool qt1050_identify(struct qt1050_priv *ts)
+ int err;
+
+ /* Read Chip ID */
+- regmap_read(ts->regmap, QT1050_CHIP_ID, &val);
++ err = regmap_read(ts->regmap, QT1050_CHIP_ID, &val);
++ if (err) {
++ dev_err(&ts->client->dev, "Failed to read chip ID: %d\n", err);
++ return false;
++ }
++
+ if (val != QT1050_CHIP_ID_VER) {
+ dev_err(&ts->client->dev, "ID %d not supported\n", val);
+ return false;
+diff --git a/drivers/input/mouse/elan_i2c_core.c b/drivers/input/mouse/elan_i2c_core.c
+index c2aec5c360b3b..ce96513b34f64 100644
+--- a/drivers/input/mouse/elan_i2c_core.c
++++ b/drivers/input/mouse/elan_i2c_core.c
+@@ -1356,6 +1356,8 @@ static int elan_suspend(struct device *dev)
+ }
+
+ err:
++ if (ret)
++ enable_irq(client->irq);
+ mutex_unlock(&data->sysfs_mutex);
+ return ret;
+ }
+diff --git a/drivers/interconnect/qcom/qcm2290.c b/drivers/interconnect/qcom/qcm2290.c
+index ba4cc08684d63..ccbdc6202c07a 100644
+--- a/drivers/interconnect/qcom/qcm2290.c
++++ b/drivers/interconnect/qcom/qcm2290.c
+@@ -166,7 +166,7 @@ static struct qcom_icc_node mas_snoc_bimc = {
+ .qos.ap_owned = true,
+ .qos.qos_port = 6,
+ .qos.qos_mode = NOC_QOS_MODE_BYPASS,
+- .mas_rpm_id = 164,
++ .mas_rpm_id = 3,
+ .slv_rpm_id = -1,
+ .num_links = ARRAY_SIZE(mas_snoc_bimc_links),
+ .links = mas_snoc_bimc_links,
+diff --git a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+index ab415e107054c..f456bcf1890ba 100644
+--- a/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
++++ b/drivers/iommu/arm/arm-smmu-v3/arm-smmu-v3.c
+@@ -2302,7 +2302,7 @@ static int arm_smmu_domain_finalise_s1(struct arm_smmu_device *smmu,
+ struct arm_smmu_domain *smmu_domain)
+ {
+ int ret;
+- u32 asid;
++ u32 asid = 0;
+ struct arm_smmu_ctx_desc *cd = &smmu_domain->cd;
+
+ refcount_set(&cd->refs, 1);
+diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c
+index 552199cbd9e25..482c40aa029b4 100644
+--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c
++++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom-debug.c
+@@ -488,7 +488,7 @@ irqreturn_t qcom_smmu_context_fault(int irq, void *dev)
+ return ret;
+ }
+
+-static int qcom_tbu_probe(struct platform_device *pdev)
++int qcom_tbu_probe(struct platform_device *pdev)
+ {
+ struct of_phandle_args args = { .args_count = 2 };
+ struct device_node *np = pdev->dev.of_node;
+@@ -530,18 +530,3 @@ static int qcom_tbu_probe(struct platform_device *pdev)
+
+ return 0;
+ }
+-
+-static const struct of_device_id qcom_tbu_of_match[] = {
+- { .compatible = "qcom,sc7280-tbu" },
+- { .compatible = "qcom,sdm845-tbu" },
+- { }
+-};
+-
+-static struct platform_driver qcom_tbu_driver = {
+- .driver = {
+- .name = "qcom_tbu",
+- .of_match_table = qcom_tbu_of_match,
+- },
+- .probe = qcom_tbu_probe,
+-};
+-builtin_platform_driver(qcom_tbu_driver);
+diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+index 25f034677f568..13f3e2efb2ccb 100644
+--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
++++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.c
+@@ -8,6 +8,8 @@
+ #include <linux/delay.h>
+ #include <linux/of_device.h>
+ #include <linux/firmware/qcom/qcom_scm.h>
++#include <linux/platform_device.h>
++#include <linux/pm_runtime.h>
+
+ #include "arm-smmu.h"
+ #include "arm-smmu-qcom.h"
+@@ -561,10 +563,47 @@ static struct acpi_platform_list qcom_acpi_platlist[] = {
+ };
+ #endif
+
++static int qcom_smmu_tbu_probe(struct platform_device *pdev)
++{
++ struct device *dev = &pdev->dev;
++ int ret;
++
++ if (IS_ENABLED(CONFIG_ARM_SMMU_QCOM_DEBUG)) {
++ ret = qcom_tbu_probe(pdev);
++ if (ret)
++ return ret;
++ }
++
++ if (dev->pm_domain) {
++ pm_runtime_set_active(dev);
++ pm_runtime_enable(dev);
++ }
++
++ return 0;
++}
++
++static const struct of_device_id qcom_smmu_tbu_of_match[] = {
++ { .compatible = "qcom,sc7280-tbu" },
++ { .compatible = "qcom,sdm845-tbu" },
++ { }
++};
++
++static struct platform_driver qcom_smmu_tbu_driver = {
++ .driver = {
++ .name = "qcom_tbu",
++ .of_match_table = qcom_smmu_tbu_of_match,
++ },
++ .probe = qcom_smmu_tbu_probe,
++};
++
+ struct arm_smmu_device *qcom_smmu_impl_init(struct arm_smmu_device *smmu)
+ {
+ const struct device_node *np = smmu->dev->of_node;
+ const struct of_device_id *match;
++ static u8 tbu_registered;
++
++ if (!tbu_registered++)
++ platform_driver_register(&qcom_smmu_tbu_driver);
+
+ #ifdef CONFIG_ACPI
+ if (np == NULL) {
+diff --git a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
+index 9bb3ae7d62da6..3c134d1a62773 100644
+--- a/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
++++ b/drivers/iommu/arm/arm-smmu/arm-smmu-qcom.h
+@@ -34,8 +34,10 @@ irqreturn_t qcom_smmu_context_fault(int irq, void *dev);
+
+ #ifdef CONFIG_ARM_SMMU_QCOM_DEBUG
+ void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu);
++int qcom_tbu_probe(struct platform_device *pdev);
+ #else
+ static inline void qcom_smmu_tlb_sync_debug(struct arm_smmu_device *smmu) { }
++static inline int qcom_tbu_probe(struct platform_device *pdev) { return -EINVAL; }
+ #endif
+
+ #endif /* _ARM_SMMU_QCOM_H */
+diff --git a/drivers/iommu/intel/cache.c b/drivers/iommu/intel/cache.c
+index e8418cdd8331b..44e92638c0cd1 100644
+--- a/drivers/iommu/intel/cache.c
++++ b/drivers/iommu/intel/cache.c
+@@ -245,7 +245,8 @@ static unsigned long calculate_psi_aligned_address(unsigned long start,
+ * shared_bits are all equal in both pfn and end_pfn.
+ */
+ shared_bits = ~(pfn ^ end_pfn) & ~bitmask;
+- mask = shared_bits ? __ffs(shared_bits) : BITS_PER_LONG;
++ mask = shared_bits ? __ffs(shared_bits) : MAX_AGAW_PFN_WIDTH;
++ aligned_pages = 1UL << mask;
+ }
+
+ *_pages = aligned_pages;
+diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
+index fd11a080380c8..f55ec1fd7942a 100644
+--- a/drivers/iommu/intel/iommu.c
++++ b/drivers/iommu/intel/iommu.c
+@@ -2071,7 +2071,7 @@ static int __init si_domain_init(int hw)
+ for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) {
+ ret = iommu_domain_identity_map(si_domain,
+ mm_to_dma_pfn_start(start_pfn),
+- mm_to_dma_pfn_end(end_pfn));
++ mm_to_dma_pfn_end(end_pfn-1));
+ if (ret)
+ return ret;
+ }
+diff --git a/drivers/iommu/iommufd/iova_bitmap.c b/drivers/iommu/iommufd/iova_bitmap.c
+index db8c46bee1559..e33ddfc239b5b 100644
+--- a/drivers/iommu/iommufd/iova_bitmap.c
++++ b/drivers/iommu/iommufd/iova_bitmap.c
+@@ -384,8 +384,6 @@ static int iova_bitmap_advance(struct iova_bitmap *bitmap)
+ bitmap->mapped_base_index += count;
+
+ iova_bitmap_put(bitmap);
+- if (iova_bitmap_done(bitmap))
+- return 0;
+
+ /* Iterate, set and skip any bits requested for next iteration */
+ if (bitmap->set_ahead_length) {
+@@ -396,6 +394,9 @@ static int iova_bitmap_advance(struct iova_bitmap *bitmap)
+ return ret;
+ }
+
++ if (iova_bitmap_done(bitmap))
++ return 0;
++
+ /* When advancing the index we pin the next set of bitmap pages */
+ return iova_bitmap_get(bitmap);
+ }
+diff --git a/drivers/iommu/iommufd/selftest.c b/drivers/iommu/iommufd/selftest.c
+index 7a2199470f312..654ed33390957 100644
+--- a/drivers/iommu/iommufd/selftest.c
++++ b/drivers/iommu/iommufd/selftest.c
+@@ -1334,7 +1334,7 @@ static int iommufd_test_dirty(struct iommufd_ucmd *ucmd, unsigned int mockpt_id,
+ }
+
+ max = length / page_size;
+- bitmap_size = max / BITS_PER_BYTE;
++ bitmap_size = DIV_ROUND_UP(max, BITS_PER_BYTE);
+
+ tmp = kvzalloc(bitmap_size, GFP_KERNEL_ACCOUNT);
+ if (!tmp) {
+diff --git a/drivers/iommu/sprd-iommu.c b/drivers/iommu/sprd-iommu.c
+index ba53571a82390..a2f4ffe6d9491 100644
+--- a/drivers/iommu/sprd-iommu.c
++++ b/drivers/iommu/sprd-iommu.c
+@@ -232,8 +232,8 @@ static void sprd_iommu_cleanup(struct sprd_iommu_domain *dom)
+
+ pgt_size = sprd_iommu_pgt_size(&dom->domain);
+ dma_free_coherent(dom->sdev->dev, pgt_size, dom->pgt_va, dom->pgt_pa);
+- dom->sdev = NULL;
+ sprd_iommu_hw_en(dom->sdev, false);
++ dom->sdev = NULL;
+ }
+
+ static void sprd_iommu_domain_free(struct iommu_domain *domain)
+diff --git a/drivers/irqchip/irq-imx-irqsteer.c b/drivers/irqchip/irq-imx-irqsteer.c
+index 20cf7a9e9ece2..75a0e980ff352 100644
+--- a/drivers/irqchip/irq-imx-irqsteer.c
++++ b/drivers/irqchip/irq-imx-irqsteer.c
+@@ -36,6 +36,7 @@ struct irqsteer_data {
+ int channel;
+ struct irq_domain *domain;
+ u32 *saved_reg;
++ struct device *dev;
+ };
+
+ static int imx_irqsteer_get_reg_index(struct irqsteer_data *data,
+@@ -72,10 +73,26 @@ static void imx_irqsteer_irq_mask(struct irq_data *d)
+ raw_spin_unlock_irqrestore(&data->lock, flags);
+ }
+
++static void imx_irqsteer_irq_bus_lock(struct irq_data *d)
++{
++ struct irqsteer_data *data = d->chip_data;
++
++ pm_runtime_get_sync(data->dev);
++}
++
++static void imx_irqsteer_irq_bus_sync_unlock(struct irq_data *d)
++{
++ struct irqsteer_data *data = d->chip_data;
++
++ pm_runtime_put_autosuspend(data->dev);
++}
++
+ static const struct irq_chip imx_irqsteer_irq_chip = {
+- .name = "irqsteer",
+- .irq_mask = imx_irqsteer_irq_mask,
+- .irq_unmask = imx_irqsteer_irq_unmask,
++ .name = "irqsteer",
++ .irq_mask = imx_irqsteer_irq_mask,
++ .irq_unmask = imx_irqsteer_irq_unmask,
++ .irq_bus_lock = imx_irqsteer_irq_bus_lock,
++ .irq_bus_sync_unlock = imx_irqsteer_irq_bus_sync_unlock,
+ };
+
+ static int imx_irqsteer_irq_map(struct irq_domain *h, unsigned int irq,
+@@ -150,6 +167,7 @@ static int imx_irqsteer_probe(struct platform_device *pdev)
+ if (!data)
+ return -ENOMEM;
+
++ data->dev = &pdev->dev;
+ data->regs = devm_platform_ioremap_resource(pdev, 0);
+ if (IS_ERR(data->regs)) {
+ dev_err(&pdev->dev, "failed to initialize reg\n");
+diff --git a/drivers/isdn/hardware/mISDN/hfcmulti.c b/drivers/isdn/hardware/mISDN/hfcmulti.c
+index 2e5cb9dde3ec5..44383cec1f47a 100644
+--- a/drivers/isdn/hardware/mISDN/hfcmulti.c
++++ b/drivers/isdn/hardware/mISDN/hfcmulti.c
+@@ -1900,7 +1900,7 @@ hfcmulti_dtmf(struct hfc_multi *hc)
+ static void
+ hfcmulti_tx(struct hfc_multi *hc, int ch)
+ {
+- int i, ii, temp, len = 0;
++ int i, ii, temp, tmp_len, len = 0;
+ int Zspace, z1, z2; /* must be int for calculation */
+ int Fspace, f1, f2;
+ u_char *d;
+@@ -2121,14 +2121,15 @@ hfcmulti_tx(struct hfc_multi *hc, int ch)
+ HFC_wait_nodebug(hc);
+ }
+
++ tmp_len = (*sp)->len;
+ dev_kfree_skb(*sp);
+ /* check for next frame */
+ if (bch && get_next_bframe(bch)) {
+- len = (*sp)->len;
++ len = tmp_len;
+ goto next_frame;
+ }
+ if (dch && get_next_dframe(dch)) {
+- len = (*sp)->len;
++ len = tmp_len;
+ goto next_frame;
+ }
+
+diff --git a/drivers/leds/flash/leds-mt6360.c b/drivers/leds/flash/leds-mt6360.c
+index 1b75b4d368348..4c74f1cf01f00 100644
+--- a/drivers/leds/flash/leds-mt6360.c
++++ b/drivers/leds/flash/leds-mt6360.c
+@@ -643,14 +643,17 @@ static int mt6360_init_isnk_properties(struct mt6360_led *led,
+
+ ret = fwnode_property_read_u32(child, "reg", ®);
+ if (ret || reg > MT6360_LED_ISNK3 ||
+- priv->leds_active & BIT(reg))
++ priv->leds_active & BIT(reg)) {
++ fwnode_handle_put(child);
+ return -EINVAL;
++ }
+
+ ret = fwnode_property_read_u32(child, "color", &color);
+ if (ret) {
+ dev_err(priv->dev,
+ "led %d, no color specified\n",
+ led->led_no);
++ fwnode_handle_put(child);
+ return ret;
+ }
+
+diff --git a/drivers/leds/flash/leds-qcom-flash.c b/drivers/leds/flash/leds-qcom-flash.c
+index 7c99a30391716..bf70bf6fb0d59 100644
+--- a/drivers/leds/flash/leds-qcom-flash.c
++++ b/drivers/leds/flash/leds-qcom-flash.c
+@@ -505,6 +505,7 @@ qcom_flash_v4l2_init(struct device *dev, struct qcom_flash_led *led, struct fwno
+ struct qcom_flash_data *flash_data = led->flash_data;
+ struct v4l2_flash_config v4l2_cfg = { 0 };
+ struct led_flash_setting *intensity = &v4l2_cfg.intensity;
++ struct v4l2_flash *v4l2_flash;
+
+ if (!(led->flash.led_cdev.flags & LED_DEV_CAP_FLASH))
+ return 0;
+@@ -523,9 +524,12 @@ qcom_flash_v4l2_init(struct device *dev, struct qcom_flash_led *led, struct fwno
+ LED_FAULT_OVER_TEMPERATURE |
+ LED_FAULT_TIMEOUT;
+
+- flash_data->v4l2_flash[flash_data->leds_count] =
+- v4l2_flash_init(dev, fwnode, &led->flash, &qcom_v4l2_flash_ops, &v4l2_cfg);
+- return PTR_ERR_OR_ZERO(flash_data->v4l2_flash);
++ v4l2_flash = v4l2_flash_init(dev, fwnode, &led->flash, &qcom_v4l2_flash_ops, &v4l2_cfg);
++ if (IS_ERR(v4l2_flash))
++ return PTR_ERR(v4l2_flash);
++
++ flash_data->v4l2_flash[flash_data->leds_count] = v4l2_flash;
++ return 0;
+ }
+ # else
+ static int
+diff --git a/drivers/leds/led-class.c b/drivers/leds/led-class.c
+index ba1be15cfd8ea..c66d1bead0a4a 100644
+--- a/drivers/leds/led-class.c
++++ b/drivers/leds/led-class.c
+@@ -258,7 +258,6 @@ struct led_classdev *of_led_get(struct device_node *np, int index)
+
+ led_dev = class_find_device_by_of_node(&leds_class, led_node);
+ of_node_put(led_node);
+- put_device(led_dev);
+
+ return led_module_get(led_dev);
+ }
+diff --git a/drivers/leds/led-triggers.c b/drivers/leds/led-triggers.c
+index b1b323b19301d..6345c52afb564 100644
+--- a/drivers/leds/led-triggers.c
++++ b/drivers/leds/led-triggers.c
+@@ -179,9 +179,9 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
+
+ cancel_work_sync(&led_cdev->set_brightness_work);
+ led_stop_software_blink(led_cdev);
++ device_remove_groups(led_cdev->dev, led_cdev->trigger->groups);
+ if (led_cdev->trigger->deactivate)
+ led_cdev->trigger->deactivate(led_cdev);
+- device_remove_groups(led_cdev->dev, led_cdev->trigger->groups);
+ led_cdev->trigger = NULL;
+ led_cdev->trigger_data = NULL;
+ led_cdev->activated = false;
+@@ -194,6 +194,12 @@ int led_trigger_set(struct led_classdev *led_cdev, struct led_trigger *trig)
+ spin_unlock(&trig->leddev_list_lock);
+ led_cdev->trigger = trig;
+
++ /*
++ * If "set brightness to 0" is pending in workqueue,
++ * we don't want that to be reordered after ->activate()
++ */
++ flush_work(&led_cdev->set_brightness_work);
++
+ ret = 0;
+ if (trig->activate)
+ ret = trig->activate(led_cdev);
+diff --git a/drivers/leds/leds-ss4200.c b/drivers/leds/leds-ss4200.c
+index fcaa34706b6ca..2ef9fc7371bd1 100644
+--- a/drivers/leds/leds-ss4200.c
++++ b/drivers/leds/leds-ss4200.c
+@@ -356,8 +356,10 @@ static int ich7_lpc_probe(struct pci_dev *dev,
+
+ nas_gpio_pci_dev = dev;
+ status = pci_read_config_dword(dev, PMBASE, &g_pm_io_base);
+- if (status)
++ if (status) {
++ status = pcibios_err_to_errno(status);
+ goto out;
++ }
+ g_pm_io_base &= 0x00000ff80;
+
+ status = pci_read_config_dword(dev, GPIO_CTRL, &gc);
+@@ -369,8 +371,9 @@ static int ich7_lpc_probe(struct pci_dev *dev,
+ }
+
+ status = pci_read_config_dword(dev, GPIO_BASE, &nas_gpio_io_base);
+- if (0 > status) {
++ if (status) {
+ dev_info(&dev->dev, "Unable to read GPIOBASE.\n");
++ status = pcibios_err_to_errno(status);
+ goto out;
+ }
+ dev_dbg(&dev->dev, ": GPIOBASE = 0x%08x\n", nas_gpio_io_base);
+diff --git a/drivers/leds/rgb/leds-qcom-lpg.c b/drivers/leds/rgb/leds-qcom-lpg.c
+index 9467c796bd041..e74b2ceed1c26 100644
+--- a/drivers/leds/rgb/leds-qcom-lpg.c
++++ b/drivers/leds/rgb/leds-qcom-lpg.c
+@@ -2,7 +2,7 @@
+ /*
+ * Copyright (c) 2017-2022 Linaro Ltd
+ * Copyright (c) 2010-2012, The Linux Foundation. All rights reserved.
+- * Copyright (c) 2023, Qualcomm Innovation Center, Inc. All rights reserved.
++ * Copyright (c) 2023-2024, Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+ #include <linux/bits.h>
+ #include <linux/bitfield.h>
+@@ -254,6 +254,9 @@ static int lpg_clear_pbs_trigger(struct lpg *lpg, unsigned int lut_mask)
+ u8 val = 0;
+ int rc;
+
++ if (!lpg->lpg_chan_sdam)
++ return 0;
++
+ lpg->pbs_en_bitmap &= (~lut_mask);
+ if (!lpg->pbs_en_bitmap) {
+ rc = nvmem_device_write(lpg->lpg_chan_sdam, SDAM_REG_PBS_SEQ_EN, 1, &val);
+@@ -276,6 +279,9 @@ static int lpg_set_pbs_trigger(struct lpg *lpg, unsigned int lut_mask)
+ u8 val = PBS_SW_TRIG_BIT;
+ int rc;
+
++ if (!lpg->lpg_chan_sdam)
++ return 0;
++
+ if (!lpg->pbs_en_bitmap) {
+ rc = nvmem_device_write(lpg->lpg_chan_sdam, SDAM_REG_PBS_SEQ_EN, 1, &val);
+ if (rc < 0)
+diff --git a/drivers/leds/trigger/ledtrig-timer.c b/drivers/leds/trigger/ledtrig-timer.c
+index b4688d1d9d2b2..1d213c999d40a 100644
+--- a/drivers/leds/trigger/ledtrig-timer.c
++++ b/drivers/leds/trigger/ledtrig-timer.c
+@@ -110,11 +110,6 @@ static int timer_trig_activate(struct led_classdev *led_cdev)
+ led_cdev->flags &= ~LED_INIT_DEFAULT_TRIGGER;
+ }
+
+- /*
+- * If "set brightness to 0" is pending in workqueue, we don't
+- * want that to be reordered after blink_set()
+- */
+- flush_work(&led_cdev->set_brightness_work);
+ led_blink_set(led_cdev, &led_cdev->blink_delay_on,
+ &led_cdev->blink_delay_off);
+
+diff --git a/drivers/macintosh/therm_windtunnel.c b/drivers/macintosh/therm_windtunnel.c
+index 37cdc6931f6d0..2576a53f247ea 100644
+--- a/drivers/macintosh/therm_windtunnel.c
++++ b/drivers/macintosh/therm_windtunnel.c
+@@ -549,7 +549,7 @@ g4fan_exit( void )
+ platform_driver_unregister( &therm_of_driver );
+
+ if( x.of_dev )
+- of_device_unregister( x.of_dev );
++ of_platform_device_destroy(&x.of_dev->dev, NULL);
+ }
+
+ module_init(g4fan_init);
+diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
+index 933727f89431d..d17efb1dd0cb1 100644
+--- a/drivers/mailbox/imx-mailbox.c
++++ b/drivers/mailbox/imx-mailbox.c
+@@ -225,6 +225,8 @@ static int imx_mu_generic_tx(struct imx_mu_priv *priv,
+ void *data)
+ {
+ u32 *arg = data;
++ u32 val;
++ int ret;
+
+ switch (cp->type) {
+ case IMX_MU_TYPE_TX:
+@@ -236,7 +238,13 @@ static int imx_mu_generic_tx(struct imx_mu_priv *priv,
+ queue_work(system_bh_wq, &cp->txdb_work);
+ break;
+ case IMX_MU_TYPE_TXDB_V2:
+- imx_mu_xcr_rmw(priv, IMX_MU_GCR, IMX_MU_xCR_GIRn(priv->dcfg->type, cp->idx), 0);
++ imx_mu_write(priv, IMX_MU_xCR_GIRn(priv->dcfg->type, cp->idx),
++ priv->dcfg->xCR[IMX_MU_GCR]);
++ ret = readl_poll_timeout(priv->base + priv->dcfg->xCR[IMX_MU_GCR], val,
++ !(val & IMX_MU_xCR_GIRn(priv->dcfg->type, cp->idx)),
++ 0, 1000);
++ if (ret)
++ dev_warn_ratelimited(priv->dev, "channel type: %d failure\n", cp->type);
+ break;
+ default:
+ dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type);
+diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
+index 4aa394e91109c..63b5e3fe75281 100644
+--- a/drivers/mailbox/mtk-cmdq-mailbox.c
++++ b/drivers/mailbox/mtk-cmdq-mailbox.c
+@@ -662,12 +662,6 @@ static int cmdq_probe(struct platform_device *pdev)
+ cmdq->mbox.chans[i].con_priv = (void *)&cmdq->thread[i];
+ }
+
+- err = devm_mbox_controller_register(dev, &cmdq->mbox);
+- if (err < 0) {
+- dev_err(dev, "failed to register mailbox: %d\n", err);
+- return err;
+- }
+-
+ platform_set_drvdata(pdev, cmdq);
+
+ WARN_ON(clk_bulk_prepare(cmdq->pdata->gce_num, cmdq->clocks));
+@@ -695,6 +689,12 @@ static int cmdq_probe(struct platform_device *pdev)
+ pm_runtime_set_autosuspend_delay(dev, CMDQ_MBOX_AUTOSUSPEND_DELAY_MS);
+ pm_runtime_use_autosuspend(dev);
+
++ err = devm_mbox_controller_register(dev, &cmdq->mbox);
++ if (err < 0) {
++ dev_err(dev, "failed to register mailbox: %d\n", err);
++ return err;
++ }
++
+ return 0;
+ }
+
+diff --git a/drivers/mailbox/omap-mailbox.c b/drivers/mailbox/omap-mailbox.c
+index 46747559b438f..7a87424657a15 100644
+--- a/drivers/mailbox/omap-mailbox.c
++++ b/drivers/mailbox/omap-mailbox.c
+@@ -230,7 +230,8 @@ static int omap_mbox_startup(struct omap_mbox *mbox)
+ int ret = 0;
+
+ ret = request_threaded_irq(mbox->irq, NULL, mbox_interrupt,
+- IRQF_ONESHOT, mbox->name, mbox);
++ IRQF_SHARED | IRQF_ONESHOT, mbox->name,
++ mbox);
+ if (unlikely(ret)) {
+ pr_err("failed to register mailbox interrupt:%d\n", ret);
+ return ret;
+diff --git a/drivers/md/dm-raid.c b/drivers/md/dm-raid.c
+index abe88d1e67358..b149ac46a990e 100644
+--- a/drivers/md/dm-raid.c
++++ b/drivers/md/dm-raid.c
+@@ -4101,10 +4101,11 @@ static void raid_resume(struct dm_target *ti)
+ if (mddev->delta_disks < 0)
+ rs_set_capacity(rs);
+
++ mddev_lock_nointr(mddev);
+ WARN_ON_ONCE(!test_bit(MD_RECOVERY_FROZEN, &mddev->recovery));
+- WARN_ON_ONCE(test_bit(MD_RECOVERY_RUNNING, &mddev->recovery));
++ WARN_ON_ONCE(rcu_dereference_protected(mddev->sync_thread,
++ lockdep_is_held(&mddev->reconfig_mutex)));
+ clear_bit(RT_FLAG_RS_FROZEN, &rs->runtime_flags);
+- mddev_lock_nointr(mddev);
+ mddev->ro = 0;
+ mddev->in_sync = 0;
+ md_unfrozen_sync_thread(mddev);
+diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
+index b2d5246cff210..2fc847af254de 100644
+--- a/drivers/md/dm-table.c
++++ b/drivers/md/dm-table.c
+@@ -2028,10 +2028,7 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
+ dm_table_any_dev_attr(t, device_is_not_random, NULL))
+ blk_queue_flag_clear(QUEUE_FLAG_ADD_RANDOM, q);
+
+- /*
+- * For a zoned target, setup the zones related queue attributes
+- * and resources necessary for zone append emulation if necessary.
+- */
++ /* For a zoned table, setup the zone related queue attributes. */
+ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
+ r = dm_set_zones_restrictions(t, q, limits);
+ if (r)
+@@ -2042,6 +2039,16 @@ int dm_table_set_restrictions(struct dm_table *t, struct request_queue *q,
+ if (r)
+ return r;
+
++ /*
++ * Now that the limits are set, check the zones mapped by the table
++ * and setup the resources for zone append emulation if necessary.
++ */
++ if (IS_ENABLED(CONFIG_BLK_DEV_ZONED) && limits->zoned) {
++ r = dm_revalidate_zones(t, q);
++ if (r)
++ return r;
++ }
++
+ dm_update_crypto_profile(q, t);
+
+ /*
+diff --git a/drivers/md/dm-verity-target.c b/drivers/md/dm-verity-target.c
+index bb5da66da4c17..431a61e1a8b7b 100644
+--- a/drivers/md/dm-verity-target.c
++++ b/drivers/md/dm-verity-target.c
+@@ -1538,14 +1538,6 @@ static int verity_ctr(struct dm_target *ti, unsigned int argc, char **argv)
+ return r;
+ }
+
+-/*
+- * Check whether a DM target is a verity target.
+- */
+-bool dm_is_verity_target(struct dm_target *ti)
+-{
+- return ti->type->module == THIS_MODULE;
+-}
+-
+ /*
+ * Get the verity mode (error behavior) of a verity target.
+ *
+@@ -1599,6 +1591,14 @@ static struct target_type verity_target = {
+ };
+ module_dm(verity);
+
++/*
++ * Check whether a DM target is a verity target.
++ */
++bool dm_is_verity_target(struct dm_target *ti)
++{
++ return ti->type == &verity_target;
++}
++
+ MODULE_AUTHOR("Mikulas Patocka <mpatocka@redhat.com>");
+ MODULE_AUTHOR("Mandeep Baines <msb@chromium.org>");
+ MODULE_AUTHOR("Will Drewry <wad@chromium.org>");
+diff --git a/drivers/md/dm-zone.c b/drivers/md/dm-zone.c
+index 5d66d916730ef..75d0019a0649d 100644
+--- a/drivers/md/dm-zone.c
++++ b/drivers/md/dm-zone.c
+@@ -166,14 +166,22 @@ static int dm_check_zoned_cb(struct blk_zone *zone, unsigned int idx,
+ * blk_revalidate_disk_zones() function here as the mapped device is suspended
+ * (this is called from __bind() context).
+ */
+-static int dm_revalidate_zones(struct mapped_device *md, struct dm_table *t)
++int dm_revalidate_zones(struct dm_table *t, struct request_queue *q)
+ {
++ struct mapped_device *md = t->md;
+ struct gendisk *disk = md->disk;
+ int ret;
+
++ if (!get_capacity(disk))
++ return 0;
++
+ /* Revalidate only if something changed. */
+- if (!disk->nr_zones || disk->nr_zones != md->nr_zones)
++ if (!disk->nr_zones || disk->nr_zones != md->nr_zones) {
++ DMINFO("%s using %s zone append",
++ disk->disk_name,
++ queue_emulates_zone_append(q) ? "emulated" : "native");
+ md->nr_zones = 0;
++ }
+
+ if (md->nr_zones)
+ return 0;
+@@ -240,9 +248,6 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+ lim->max_zone_append_sectors = 0;
+ }
+
+- if (!get_capacity(md->disk))
+- return 0;
+-
+ /*
+ * Count conventional zones to check that the mapped device will indeed
+ * have sequential write required zones.
+@@ -269,16 +274,6 @@ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+ return 0;
+ }
+
+- if (!md->disk->nr_zones) {
+- DMINFO("%s using %s zone append",
+- md->disk->disk_name,
+- queue_emulates_zone_append(q) ? "emulated" : "native");
+- }
+-
+- ret = dm_revalidate_zones(md, t);
+- if (ret < 0)
+- return ret;
+-
+ if (!static_key_enabled(&zoned_enabled.key))
+ static_branch_enable(&zoned_enabled);
+ return 0;
+diff --git a/drivers/md/dm.h b/drivers/md/dm.h
+index 53ef8207fe2c1..c984ecb64b1e8 100644
+--- a/drivers/md/dm.h
++++ b/drivers/md/dm.h
+@@ -103,6 +103,7 @@ int dm_setup_md_queue(struct mapped_device *md, struct dm_table *t);
+ */
+ int dm_set_zones_restrictions(struct dm_table *t, struct request_queue *q,
+ struct queue_limits *lim);
++int dm_revalidate_zones(struct dm_table *t, struct request_queue *q);
+ void dm_zone_endio(struct dm_io *io, struct bio *clone);
+ #ifdef CONFIG_BLK_DEV_ZONED
+ int dm_blk_report_zones(struct gendisk *disk, sector_t sector,
+diff --git a/drivers/md/md-bitmap.c b/drivers/md/md-bitmap.c
+index 0a2d37eb38ef9..08232d8dc815e 100644
+--- a/drivers/md/md-bitmap.c
++++ b/drivers/md/md-bitmap.c
+@@ -227,6 +227,8 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
+ struct block_device *bdev;
+ struct mddev *mddev = bitmap->mddev;
+ struct bitmap_storage *store = &bitmap->storage;
++ unsigned int bitmap_limit = (bitmap->storage.file_pages - pg_index) <<
++ PAGE_SHIFT;
+ loff_t sboff, offset = mddev->bitmap_info.offset;
+ sector_t ps = pg_index * PAGE_SIZE / SECTOR_SIZE;
+ unsigned int size = PAGE_SIZE;
+@@ -269,11 +271,9 @@ static int __write_sb_page(struct md_rdev *rdev, struct bitmap *bitmap,
+ if (size == 0)
+ /* bitmap runs in to data */
+ return -EINVAL;
+- } else {
+- /* DATA METADATA BITMAP - no problems */
+ }
+
+- md_super_write(mddev, rdev, sboff + ps, (int) size, page);
++ md_super_write(mddev, rdev, sboff + ps, (int)min(size, bitmap_limit), page);
+ return 0;
+ }
+
+diff --git a/drivers/md/md-cluster.c b/drivers/md/md-cluster.c
+index 8e36a0feec098..b5a802ae17bb2 100644
+--- a/drivers/md/md-cluster.c
++++ b/drivers/md/md-cluster.c
+@@ -15,6 +15,7 @@
+
+ #define LVB_SIZE 64
+ #define NEW_DEV_TIMEOUT 5000
++#define WAIT_DLM_LOCK_TIMEOUT (30 * HZ)
+
+ struct dlm_lock_resource {
+ dlm_lockspace_t *ls;
+@@ -130,8 +131,13 @@ static int dlm_lock_sync(struct dlm_lock_resource *res, int mode)
+ 0, sync_ast, res, res->bast);
+ if (ret)
+ return ret;
+- wait_event(res->sync_locking, res->sync_locking_done);
++ ret = wait_event_timeout(res->sync_locking, res->sync_locking_done,
++ WAIT_DLM_LOCK_TIMEOUT);
+ res->sync_locking_done = false;
++ if (!ret) {
++ pr_err("locking DLM '%s' timeout!\n", res->name);
++ return -EBUSY;
++ }
+ if (res->lksb.sb_status == 0)
+ res->mode = mode;
+ return res->lksb.sb_status;
+@@ -743,7 +749,7 @@ static void unlock_comm(struct md_cluster_info *cinfo)
+ */
+ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
+ {
+- int error;
++ int error, unlock_error;
+ int slot = cinfo->slot_number - 1;
+
+ cmsg->slot = cpu_to_le32(slot);
+@@ -751,7 +757,7 @@ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
+ error = dlm_lock_sync(cinfo->message_lockres, DLM_LOCK_EX);
+ if (error) {
+ pr_err("md-cluster: failed to get EX on MESSAGE (%d)\n", error);
+- goto failed_message;
++ return error;
+ }
+
+ memcpy(cinfo->message_lockres->lksb.sb_lvbptr, (void *)cmsg,
+@@ -781,14 +787,10 @@ static int __sendmsg(struct md_cluster_info *cinfo, struct cluster_msg *cmsg)
+ }
+
+ failed_ack:
+- error = dlm_unlock_sync(cinfo->message_lockres);
+- if (unlikely(error != 0)) {
++ while ((unlock_error = dlm_unlock_sync(cinfo->message_lockres)))
+ pr_err("md-cluster: failed convert to NL on MESSAGE(%d)\n",
+- error);
+- /* in case the message can't be released due to some reason */
+- goto failed_ack;
+- }
+-failed_message:
++ unlock_error);
++
+ return error;
+ }
+
+diff --git a/drivers/md/md.c b/drivers/md/md.c
+index aff9118ff6975..9c5be016e5073 100644
+--- a/drivers/md/md.c
++++ b/drivers/md/md.c
+@@ -550,13 +550,9 @@ static void md_end_flush(struct bio *bio)
+
+ rdev_dec_pending(rdev, mddev);
+
+- if (atomic_dec_and_test(&mddev->flush_pending)) {
+- /* The pair is percpu_ref_get() from md_flush_request() */
+- percpu_ref_put(&mddev->active_io);
+-
++ if (atomic_dec_and_test(&mddev->flush_pending))
+ /* The pre-request flush has finished */
+ queue_work(md_wq, &mddev->flush_work);
+- }
+ }
+
+ static void md_submit_flush_data(struct work_struct *ws);
+@@ -587,12 +583,8 @@ static void submit_flushes(struct work_struct *ws)
+ rcu_read_lock();
+ }
+ rcu_read_unlock();
+- if (atomic_dec_and_test(&mddev->flush_pending)) {
+- /* The pair is percpu_ref_get() from md_flush_request() */
+- percpu_ref_put(&mddev->active_io);
+-
++ if (atomic_dec_and_test(&mddev->flush_pending))
+ queue_work(md_wq, &mddev->flush_work);
+- }
+ }
+
+ static void md_submit_flush_data(struct work_struct *ws)
+@@ -617,8 +609,20 @@ static void md_submit_flush_data(struct work_struct *ws)
+ bio_endio(bio);
+ } else {
+ bio->bi_opf &= ~REQ_PREFLUSH;
+- md_handle_request(mddev, bio);
++
++ /*
++ * make_requst() will never return error here, it only
++ * returns error in raid5_make_request() by dm-raid.
++ * Since dm always splits data and flush operation into
++ * two separate io, io size of flush submitted by dm
++ * always is 0, make_request() will not be called here.
++ */
++ if (WARN_ON_ONCE(!mddev->pers->make_request(mddev, bio)))
++ bio_io_error(bio);;
+ }
++
++ /* The pair is percpu_ref_get() from md_flush_request() */
++ percpu_ref_put(&mddev->active_io);
+ }
+
+ /*
+@@ -7742,12 +7746,6 @@ static int md_ioctl(struct block_device *bdev, blk_mode_t mode,
+ return get_bitmap_file(mddev, argp);
+ }
+
+- if (cmd == HOT_REMOVE_DISK)
+- /* need to ensure recovery thread has run */
+- wait_event_interruptible_timeout(mddev->sb_wait,
+- !test_bit(MD_RECOVERY_NEEDED,
+- &mddev->recovery),
+- msecs_to_jiffies(5000));
+ if (cmd == STOP_ARRAY || cmd == STOP_ARRAY_RO) {
+ /* Need to flush page cache, and ensure no-one else opens
+ * and writes
+diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
+index c5d4aeb68404c..81c01347cd24e 100644
+--- a/drivers/md/raid0.c
++++ b/drivers/md/raid0.c
+@@ -365,18 +365,13 @@ static sector_t raid0_size(struct mddev *mddev, sector_t sectors, int raid_disks
+ return array_sectors;
+ }
+
+-static void free_conf(struct mddev *mddev, struct r0conf *conf)
+-{
+- kfree(conf->strip_zone);
+- kfree(conf->devlist);
+- kfree(conf);
+-}
+-
+ static void raid0_free(struct mddev *mddev, void *priv)
+ {
+ struct r0conf *conf = priv;
+
+- free_conf(mddev, conf);
++ kfree(conf->strip_zone);
++ kfree(conf->devlist);
++ kfree(conf);
+ }
+
+ static int raid0_set_limits(struct mddev *mddev)
+@@ -415,7 +410,7 @@ static int raid0_run(struct mddev *mddev)
+ if (!mddev_is_dm(mddev)) {
+ ret = raid0_set_limits(mddev);
+ if (ret)
+- goto out_free_conf;
++ return ret;
+ }
+
+ /* calculate array device size */
+@@ -427,13 +422,7 @@ static int raid0_run(struct mddev *mddev)
+
+ dump_zones(mddev);
+
+- ret = md_integrity_register(mddev);
+- if (ret)
+- goto out_free_conf;
+- return 0;
+-out_free_conf:
+- free_conf(mddev, conf);
+- return ret;
++ return md_integrity_register(mddev);
+ }
+
+ /*
+diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
+index 7b8a71ca66dde..22bbd06ba6a29 100644
+--- a/drivers/md/raid1.c
++++ b/drivers/md/raid1.c
+@@ -680,6 +680,7 @@ static int choose_slow_rdev(struct r1conf *conf, struct r1bio *r1_bio,
+ len = r1_bio->sectors;
+ read_len = raid1_check_read_range(rdev, this_sector, &len);
+ if (read_len == r1_bio->sectors) {
++ *max_sectors = read_len;
+ update_read_sectors(conf, disk, this_sector, read_len);
+ return disk;
+ }
+@@ -3204,7 +3205,6 @@ static int raid1_set_limits(struct mddev *mddev)
+ return queue_limits_set(mddev->gendisk->queue, &lim);
+ }
+
+-static void raid1_free(struct mddev *mddev, void *priv);
+ static int raid1_run(struct mddev *mddev)
+ {
+ struct r1conf *conf;
+@@ -3238,7 +3238,7 @@ static int raid1_run(struct mddev *mddev)
+ if (!mddev_is_dm(mddev)) {
+ ret = raid1_set_limits(mddev);
+ if (ret)
+- goto abort;
++ return ret;
+ }
+
+ mddev->degraded = 0;
+@@ -3252,8 +3252,7 @@ static int raid1_run(struct mddev *mddev)
+ */
+ if (conf->raid_disks - mddev->degraded < 1) {
+ md_unregister_thread(mddev, &conf->thread);
+- ret = -EINVAL;
+- goto abort;
++ return -EINVAL;
+ }
+
+ if (conf->raid_disks - mddev->degraded == 1)
+@@ -3277,14 +3276,8 @@ static int raid1_run(struct mddev *mddev)
+ md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
+
+ ret = md_integrity_register(mddev);
+- if (ret) {
++ if (ret)
+ md_unregister_thread(mddev, &mddev->thread);
+- goto abort;
+- }
+- return 0;
+-
+-abort:
+- raid1_free(mddev, conf);
+ return ret;
+ }
+
+diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
+index 2bd1ce9b39226..1c6b58adec133 100644
+--- a/drivers/md/raid5.c
++++ b/drivers/md/raid5.c
+@@ -155,7 +155,7 @@ static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
+ return slot;
+ }
+
+-static void print_raid5_conf (struct r5conf *conf);
++static void print_raid5_conf(struct r5conf *conf);
+
+ static int stripe_operations_active(struct stripe_head *sh)
+ {
+@@ -5899,6 +5899,39 @@ static int add_all_stripe_bios(struct r5conf *conf,
+ return ret;
+ }
+
++enum reshape_loc {
++ LOC_NO_RESHAPE,
++ LOC_AHEAD_OF_RESHAPE,
++ LOC_INSIDE_RESHAPE,
++ LOC_BEHIND_RESHAPE,
++};
++
++static enum reshape_loc get_reshape_loc(struct mddev *mddev,
++ struct r5conf *conf, sector_t logical_sector)
++{
++ sector_t reshape_progress, reshape_safe;
++ /*
++ * Spinlock is needed as reshape_progress may be
++ * 64bit on a 32bit platform, and so it might be
++ * possible to see a half-updated value
++ * Of course reshape_progress could change after
++ * the lock is dropped, so once we get a reference
++ * to the stripe that we think it is, we will have
++ * to check again.
++ */
++ spin_lock_irq(&conf->device_lock);
++ reshape_progress = conf->reshape_progress;
++ reshape_safe = conf->reshape_safe;
++ spin_unlock_irq(&conf->device_lock);
++ if (reshape_progress == MaxSector)
++ return LOC_NO_RESHAPE;
++ if (ahead_of_reshape(mddev, logical_sector, reshape_progress))
++ return LOC_AHEAD_OF_RESHAPE;
++ if (ahead_of_reshape(mddev, logical_sector, reshape_safe))
++ return LOC_INSIDE_RESHAPE;
++ return LOC_BEHIND_RESHAPE;
++}
++
+ static enum stripe_result make_stripe_request(struct mddev *mddev,
+ struct r5conf *conf, struct stripe_request_ctx *ctx,
+ sector_t logical_sector, struct bio *bi)
+@@ -5913,28 +5946,14 @@ static enum stripe_result make_stripe_request(struct mddev *mddev,
+ seq = read_seqcount_begin(&conf->gen_lock);
+
+ if (unlikely(conf->reshape_progress != MaxSector)) {
+- /*
+- * Spinlock is needed as reshape_progress may be
+- * 64bit on a 32bit platform, and so it might be
+- * possible to see a half-updated value
+- * Of course reshape_progress could change after
+- * the lock is dropped, so once we get a reference
+- * to the stripe that we think it is, we will have
+- * to check again.
+- */
+- spin_lock_irq(&conf->device_lock);
+- if (ahead_of_reshape(mddev, logical_sector,
+- conf->reshape_progress)) {
+- previous = 1;
+- } else {
+- if (ahead_of_reshape(mddev, logical_sector,
+- conf->reshape_safe)) {
+- spin_unlock_irq(&conf->device_lock);
+- ret = STRIPE_SCHEDULE_AND_RETRY;
+- goto out;
+- }
++ enum reshape_loc loc = get_reshape_loc(mddev, conf,
++ logical_sector);
++ if (loc == LOC_INSIDE_RESHAPE) {
++ ret = STRIPE_SCHEDULE_AND_RETRY;
++ goto out;
+ }
+- spin_unlock_irq(&conf->device_lock);
++ if (loc == LOC_AHEAD_OF_RESHAPE)
++ previous = 1;
+ }
+
+ new_sector = raid5_compute_sector(conf, logical_sector, previous,
+@@ -6113,8 +6132,7 @@ static bool raid5_make_request(struct mddev *mddev, struct bio * bi)
+ /* Bail out if conflicts with reshape and REQ_NOWAIT is set */
+ if ((bi->bi_opf & REQ_NOWAIT) &&
+ (conf->reshape_progress != MaxSector) &&
+- !ahead_of_reshape(mddev, logical_sector, conf->reshape_progress) &&
+- ahead_of_reshape(mddev, logical_sector, conf->reshape_safe)) {
++ get_reshape_loc(mddev, conf, logical_sector) == LOC_INSIDE_RESHAPE) {
+ bio_wouldblock_error(bi);
+ if (rw == WRITE)
+ md_write_end(mddev);
+@@ -7562,11 +7580,11 @@ static struct r5conf *setup_conf(struct mddev *mddev)
+ if (test_bit(Replacement, &rdev->flags)) {
+ if (disk->replacement)
+ goto abort;
+- RCU_INIT_POINTER(disk->replacement, rdev);
++ disk->replacement = rdev;
+ } else {
+ if (disk->rdev)
+ goto abort;
+- RCU_INIT_POINTER(disk->rdev, rdev);
++ disk->rdev = rdev;
+ }
+
+ if (test_bit(In_sync, &rdev->flags)) {
+@@ -8048,7 +8066,7 @@ static void raid5_status(struct seq_file *seq, struct mddev *mddev)
+ seq_printf (seq, "]");
+ }
+
+-static void print_raid5_conf (struct r5conf *conf)
++static void print_raid5_conf(struct r5conf *conf)
+ {
+ struct md_rdev *rdev;
+ int i;
+@@ -8062,15 +8080,13 @@ static void print_raid5_conf (struct r5conf *conf)
+ conf->raid_disks,
+ conf->raid_disks - conf->mddev->degraded);
+
+- rcu_read_lock();
+ for (i = 0; i < conf->raid_disks; i++) {
+- rdev = rcu_dereference(conf->disks[i].rdev);
++ rdev = conf->disks[i].rdev;
+ if (rdev)
+ pr_debug(" disk %d, o:%d, dev:%pg\n",
+ i, !test_bit(Faulty, &rdev->flags),
+ rdev->bdev);
+ }
+- rcu_read_unlock();
+ }
+
+ static int raid5_spare_active(struct mddev *mddev)
+diff --git a/drivers/media/i2c/Kconfig b/drivers/media/i2c/Kconfig
+index c6d3ee472d814..742bc665602e9 100644
+--- a/drivers/media/i2c/Kconfig
++++ b/drivers/media/i2c/Kconfig
+@@ -679,6 +679,7 @@ config VIDEO_THP7312
+ tristate "THine THP7312 support"
+ depends on I2C
+ select FW_LOADER
++ select FW_UPLOAD
+ select MEDIA_CONTROLLER
+ select V4L2_CCI_I2C
+ select V4L2_FWNODE
+diff --git a/drivers/media/i2c/alvium-csi2.c b/drivers/media/i2c/alvium-csi2.c
+index e65702e3f73e8..272d892da56ee 100644
+--- a/drivers/media/i2c/alvium-csi2.c
++++ b/drivers/media/i2c/alvium-csi2.c
+@@ -1962,7 +1962,7 @@ static int alvium_g_volatile_ctrl(struct v4l2_ctrl *ctrl)
+ int val;
+
+ switch (ctrl->id) {
+- case V4L2_CID_GAIN:
++ case V4L2_CID_ANALOGUE_GAIN:
+ val = alvium_get_gain(alvium);
+ if (val < 0)
+ return val;
+@@ -1994,7 +1994,7 @@ static int alvium_s_ctrl(struct v4l2_ctrl *ctrl)
+ return 0;
+
+ switch (ctrl->id) {
+- case V4L2_CID_GAIN:
++ case V4L2_CID_ANALOGUE_GAIN:
+ ret = alvium_set_ctrl_gain(alvium, ctrl->val);
+ break;
+ case V4L2_CID_AUTOGAIN:
+@@ -2123,7 +2123,7 @@ static int alvium_ctrl_init(struct alvium_dev *alvium)
+
+ if (alvium->avail_ft.gain) {
+ ctrls->gain = v4l2_ctrl_new_std(hdl, ops,
+- V4L2_CID_GAIN,
++ V4L2_CID_ANALOGUE_GAIN,
+ alvium->min_gain,
+ alvium->max_gain,
+ alvium->inc_gain,
+diff --git a/drivers/media/i2c/hi846.c b/drivers/media/i2c/hi846.c
+index 9c565ec033d4e..52d9ca68a86c8 100644
+--- a/drivers/media/i2c/hi846.c
++++ b/drivers/media/i2c/hi846.c
+@@ -1851,7 +1851,7 @@ static int hi846_get_selection(struct v4l2_subdev *sd,
+ mutex_lock(&hi846->mutex);
+ switch (sel->which) {
+ case V4L2_SUBDEV_FORMAT_TRY:
+- v4l2_subdev_state_get_crop(sd_state, sel->pad);
++ sel->r = *v4l2_subdev_state_get_crop(sd_state, sel->pad);
+ break;
+ case V4L2_SUBDEV_FORMAT_ACTIVE:
+ sel->r = hi846->cur_mode->crop;
+diff --git a/drivers/media/i2c/imx219.c b/drivers/media/i2c/imx219.c
+index 51ebf5453fceb..e78a80b2bb2e4 100644
+--- a/drivers/media/i2c/imx219.c
++++ b/drivers/media/i2c/imx219.c
+@@ -162,8 +162,8 @@ static const struct cci_reg_sequence imx219_common_regs[] = {
+ { IMX219_REG_MODE_SELECT, 0x00 }, /* Mode Select */
+
+ /* To Access Addresses 3000-5fff, send the following commands */
+- { CCI_REG8(0x30eb), 0x0c },
+ { CCI_REG8(0x30eb), 0x05 },
++ { CCI_REG8(0x30eb), 0x0c },
+ { CCI_REG8(0x300a), 0xff },
+ { CCI_REG8(0x300b), 0xff },
+ { CCI_REG8(0x30eb), 0x05 },
+diff --git a/drivers/media/i2c/imx412.c b/drivers/media/i2c/imx412.c
+index 0efce329525e4..7d1f7af0a9dff 100644
+--- a/drivers/media/i2c/imx412.c
++++ b/drivers/media/i2c/imx412.c
+@@ -542,14 +542,13 @@ static int imx412_update_controls(struct imx412 *imx412,
+ */
+ static int imx412_update_exp_gain(struct imx412 *imx412, u32 exposure, u32 gain)
+ {
+- u32 lpfr, shutter;
++ u32 lpfr;
+ int ret;
+
+ lpfr = imx412->vblank + imx412->cur_mode->height;
+- shutter = lpfr - exposure;
+
+- dev_dbg(imx412->dev, "Set exp %u, analog gain %u, shutter %u, lpfr %u",
+- exposure, gain, shutter, lpfr);
++ dev_dbg(imx412->dev, "Set exp %u, analog gain %u, lpfr %u",
++ exposure, gain, lpfr);
+
+ ret = imx412_write_reg(imx412, IMX412_REG_HOLD, 1, 1);
+ if (ret)
+@@ -559,7 +558,7 @@ static int imx412_update_exp_gain(struct imx412 *imx412, u32 exposure, u32 gain)
+ if (ret)
+ goto error_release_group_hold;
+
+- ret = imx412_write_reg(imx412, IMX412_REG_EXPOSURE_CIT, 2, shutter);
++ ret = imx412_write_reg(imx412, IMX412_REG_EXPOSURE_CIT, 2, exposure);
+ if (ret)
+ goto error_release_group_hold;
+
+diff --git a/drivers/media/pci/intel/ivsc/mei_csi.c b/drivers/media/pci/intel/ivsc/mei_csi.c
+index f04a89584334b..16791a7f4f157 100644
+--- a/drivers/media/pci/intel/ivsc/mei_csi.c
++++ b/drivers/media/pci/intel/ivsc/mei_csi.c
+@@ -126,6 +126,8 @@ struct mei_csi {
+ struct v4l2_ctrl_handler ctrl_handler;
+ struct v4l2_ctrl *freq_ctrl;
+ struct v4l2_ctrl *privacy_ctrl;
++ /* lock for v4l2 controls */
++ struct mutex ctrl_lock;
+ unsigned int remote_pad;
+ /* start streaming or not */
+ int streaming;
+@@ -190,7 +192,11 @@ static int mei_csi_send(struct mei_csi *csi, u8 *buf, size_t len)
+
+ /* command response status */
+ ret = csi->cmd_response.status;
+- if (ret) {
++ if (ret == -1) {
++ /* notify privacy on instead of reporting error */
++ ret = 0;
++ v4l2_ctrl_s_ctrl(csi->privacy_ctrl, 1);
++ } else if (ret) {
+ ret = -EINVAL;
+ goto out;
+ }
+@@ -559,11 +565,13 @@ static int mei_csi_init_controls(struct mei_csi *csi)
+ u32 max;
+ int ret;
+
++ mutex_init(&csi->ctrl_lock);
++
+ ret = v4l2_ctrl_handler_init(&csi->ctrl_handler, 2);
+ if (ret)
+ return ret;
+
+- csi->ctrl_handler.lock = &csi->lock;
++ csi->ctrl_handler.lock = &csi->ctrl_lock;
+
+ max = ARRAY_SIZE(link_freq_menu_items) - 1;
+ csi->freq_ctrl = v4l2_ctrl_new_int_menu(&csi->ctrl_handler,
+@@ -755,6 +763,7 @@ static int mei_csi_probe(struct mei_cl_device *cldev,
+
+ err_ctrl_handler:
+ v4l2_ctrl_handler_free(&csi->ctrl_handler);
++ mutex_destroy(&csi->ctrl_lock);
+ v4l2_async_nf_unregister(&csi->notifier);
+ v4l2_async_nf_cleanup(&csi->notifier);
+
+@@ -774,6 +783,7 @@ static void mei_csi_remove(struct mei_cl_device *cldev)
+ v4l2_async_nf_unregister(&csi->notifier);
+ v4l2_async_nf_cleanup(&csi->notifier);
+ v4l2_ctrl_handler_free(&csi->ctrl_handler);
++ mutex_destroy(&csi->ctrl_lock);
+ v4l2_async_unregister_subdev(&csi->subdev);
+ v4l2_subdev_cleanup(&csi->subdev);
+ media_entity_cleanup(&csi->subdev.entity);
+diff --git a/drivers/media/pci/ivtv/ivtv-udma.c b/drivers/media/pci/ivtv/ivtv-udma.c
+index 99b9f55ca8292..f467a00492f4b 100644
+--- a/drivers/media/pci/ivtv/ivtv-udma.c
++++ b/drivers/media/pci/ivtv/ivtv-udma.c
+@@ -131,6 +131,8 @@ int ivtv_udma_setup(struct ivtv *itv, unsigned long ivtv_dest_addr,
+
+ /* Fill SG List with new values */
+ if (ivtv_udma_fill_sg_list(dma, &user_dma, 0) < 0) {
++ IVTV_DEBUG_WARN("%s: could not allocate bounce buffers for highmem userspace buffers\n",
++ __func__);
+ unpin_user_pages(dma->map, dma->page_count);
+ dma->page_count = 0;
+ return -ENOMEM;
+@@ -139,6 +141,12 @@ int ivtv_udma_setup(struct ivtv *itv, unsigned long ivtv_dest_addr,
+ /* Map SG List */
+ dma->SG_length = dma_map_sg(&itv->pdev->dev, dma->SGlist,
+ dma->page_count, DMA_TO_DEVICE);
++ if (!dma->SG_length) {
++ IVTV_DEBUG_WARN("%s: DMA map error, SG_length is 0\n", __func__);
++ unpin_user_pages(dma->map, dma->page_count);
++ dma->page_count = 0;
++ return -EINVAL;
++ }
+
+ /* Fill SG Array with new values */
+ ivtv_udma_fill_sg_array (dma, ivtv_dest_addr, 0, -1);
+diff --git a/drivers/media/pci/ivtv/ivtv-yuv.c b/drivers/media/pci/ivtv/ivtv-yuv.c
+index 582146f8d70d5..2d9274537725a 100644
+--- a/drivers/media/pci/ivtv/ivtv-yuv.c
++++ b/drivers/media/pci/ivtv/ivtv-yuv.c
+@@ -114,6 +114,12 @@ static int ivtv_yuv_prep_user_dma(struct ivtv *itv, struct ivtv_user_dma *dma,
+ }
+ dma->SG_length = dma_map_sg(&itv->pdev->dev, dma->SGlist,
+ dma->page_count, DMA_TO_DEVICE);
++ if (!dma->SG_length) {
++ IVTV_DEBUG_WARN("%s: DMA map error, SG_length is 0\n", __func__);
++ unpin_user_pages(dma->map, dma->page_count);
++ dma->page_count = 0;
++ return -EINVAL;
++ }
+
+ /* Fill SG Array with new values */
+ ivtv_udma_fill_sg_array(dma, y_buffer_offset, uv_buffer_offset, y_size);
+diff --git a/drivers/media/pci/ivtv/ivtvfb.c b/drivers/media/pci/ivtv/ivtvfb.c
+index 410477e3e6216..d1ab7fee0d057 100644
+--- a/drivers/media/pci/ivtv/ivtvfb.c
++++ b/drivers/media/pci/ivtv/ivtvfb.c
+@@ -281,10 +281,10 @@ static int ivtvfb_prep_dec_dma_to_device(struct ivtv *itv,
+ /* Map User DMA */
+ if (ivtv_udma_setup(itv, ivtv_dest_addr, userbuf, size_in_bytes) <= 0) {
+ mutex_unlock(&itv->udma.lock);
+- IVTVFB_WARN("ivtvfb_prep_dec_dma_to_device, Error with pin_user_pages: %d bytes, %d pages returned\n",
+- size_in_bytes, itv->udma.page_count);
++ IVTVFB_WARN("%s, Error in ivtv_udma_setup: %d bytes, %d pages returned\n",
++ __func__, size_in_bytes, itv->udma.page_count);
+
+- /* pin_user_pages must have failed completely */
++ /* pin_user_pages or DMA must have failed completely */
+ return -EIO;
+ }
+
+diff --git a/drivers/media/pci/saa7134/saa7134-dvb.c b/drivers/media/pci/saa7134/saa7134-dvb.c
+index 9c6cfef03331d..a66df6adfaad8 100644
+--- a/drivers/media/pci/saa7134/saa7134-dvb.c
++++ b/drivers/media/pci/saa7134/saa7134-dvb.c
+@@ -466,7 +466,9 @@ static int philips_europa_tuner_sleep(struct dvb_frontend *fe)
+ /* switch the board to analog mode */
+ if (fe->ops.i2c_gate_ctrl)
+ fe->ops.i2c_gate_ctrl(fe, 1);
+- i2c_transfer(&dev->i2c_adap, &analog_msg, 1);
++ if (i2c_transfer(&dev->i2c_adap, &analog_msg, 1) != 1)
++ return -EIO;
++
+ return 0;
+ }
+
+@@ -1018,7 +1020,9 @@ static int md8800_set_voltage2(struct dvb_frontend *fe,
+ else
+ wbuf[1] = rbuf & 0xef;
+ msg[0].len = 2;
+- i2c_transfer(&dev->i2c_adap, msg, 1);
++ if (i2c_transfer(&dev->i2c_adap, msg, 1) != 1)
++ return -EIO;
++
+ return 0;
+ }
+
+diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
+index 4bc89c8644fec..5f848691cea44 100644
+--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
++++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec/vdec_vp8_if.c
+@@ -449,7 +449,7 @@ static int vdec_vp8_decode(void *h_vdec, struct mtk_vcodec_mem *bs,
+ inst->frm_cnt, y_fb_dma, c_fb_dma, fb);
+
+ inst->cur_fb = fb;
+- dec->bs_dma = (uint64_t)bs->dma_addr;
++ dec->bs_dma = bs->dma_addr;
+ dec->bs_sz = bs->size;
+ dec->cur_y_fb_dma = y_fb_dma;
+ dec->cur_c_fb_dma = c_fb_dma;
+diff --git a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
+index da6be556727bb..145958206e38a 100644
+--- a/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
++++ b/drivers/media/platform/mediatek/vcodec/decoder/vdec_vpu_if.c
+@@ -233,6 +233,12 @@ int vpu_dec_init(struct vdec_vpu_inst *vpu)
+ mtk_vdec_debug(vpu->ctx, "vdec_inst=%p", vpu);
+
+ err = vcodec_vpu_send_msg(vpu, (void *)&msg, sizeof(msg));
++
++ if (IS_ERR_OR_NULL(vpu->vsi)) {
++ mtk_vdec_err(vpu->ctx, "invalid vdec vsi, status=%d", err);
++ return -EINVAL;
++ }
++
+ mtk_vdec_debug(vpu->ctx, "- ret=%d", err);
+ return err;
+ }
+diff --git a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
+index cc97790ed30f6..b1300f15e5020 100644
+--- a/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
++++ b/drivers/media/platform/nxp/imx-jpeg/mxc-jpeg.c
+@@ -1634,6 +1634,9 @@ static int mxc_jpeg_start_streaming(struct vb2_queue *q, unsigned int count)
+ dev_dbg(ctx->mxc_jpeg->dev, "Start streaming ctx=%p", ctx);
+ q_data->sequence = 0;
+
++ if (V4L2_TYPE_IS_CAPTURE(q->type))
++ ctx->need_initial_source_change_evt = false;
++
+ ret = pm_runtime_resume_and_get(ctx->mxc_jpeg->dev);
+ if (ret < 0) {
+ dev_err(ctx->mxc_jpeg->dev, "Failed to power up jpeg\n");
+diff --git a/drivers/media/platform/nxp/imx-pxp.c b/drivers/media/platform/nxp/imx-pxp.c
+index e62dc5c1a4aea..e4427e6487fba 100644
+--- a/drivers/media/platform/nxp/imx-pxp.c
++++ b/drivers/media/platform/nxp/imx-pxp.c
+@@ -1805,6 +1805,9 @@ static int pxp_probe(struct platform_device *pdev)
+ return PTR_ERR(mmio);
+ dev->regmap = devm_regmap_init_mmio(&pdev->dev, mmio,
+ &pxp_regmap_config);
++ if (IS_ERR(dev->regmap))
++ return dev_err_probe(&pdev->dev, PTR_ERR(dev->regmap),
++ "Failed to init regmap\n");
+
+ irq = platform_get_irq(pdev, 0);
+ if (irq < 0)
+diff --git a/drivers/media/platform/qcom/venus/vdec.c b/drivers/media/platform/qcom/venus/vdec.c
+index 29130a9441e70..d12089370d91e 100644
+--- a/drivers/media/platform/qcom/venus/vdec.c
++++ b/drivers/media/platform/qcom/venus/vdec.c
+@@ -1255,7 +1255,7 @@ static int vdec_stop_output(struct venus_inst *inst)
+ break;
+ case VENUS_DEC_STATE_INIT:
+ case VENUS_DEC_STATE_CAPTURE_SETUP:
+- ret = hfi_session_flush(inst, HFI_FLUSH_INPUT, true);
++ ret = hfi_session_flush(inst, HFI_FLUSH_ALL, true);
+ break;
+ default:
+ break;
+@@ -1747,6 +1747,7 @@ static int vdec_close(struct file *file)
+
+ vdec_pm_get(inst);
+
++ cancel_work_sync(&inst->delayed_process_work);
+ v4l2_m2m_ctx_release(inst->m2m_ctx);
+ v4l2_m2m_release(inst->m2m_dev);
+ vdec_ctrl_deinit(inst);
+diff --git a/drivers/media/platform/renesas/rcar-csi2.c b/drivers/media/platform/renesas/rcar-csi2.c
+index 582d5e35db0e5..2d464e43a5be8 100644
+--- a/drivers/media/platform/renesas/rcar-csi2.c
++++ b/drivers/media/platform/renesas/rcar-csi2.c
+@@ -1914,12 +1914,14 @@ static int rcsi2_probe(struct platform_device *pdev)
+
+ ret = v4l2_async_register_subdev(&priv->subdev);
+ if (ret < 0)
+- goto error_async;
++ goto error_pm_runtime;
+
+ dev_info(priv->dev, "%d lanes found\n", priv->lanes);
+
+ return 0;
+
++error_pm_runtime:
++ pm_runtime_disable(&pdev->dev);
+ error_async:
+ v4l2_async_nf_unregister(&priv->notifier);
+ v4l2_async_nf_cleanup(&priv->notifier);
+@@ -1936,6 +1938,7 @@ static void rcsi2_remove(struct platform_device *pdev)
+ v4l2_async_nf_unregister(&priv->notifier);
+ v4l2_async_nf_cleanup(&priv->notifier);
+ v4l2_async_unregister_subdev(&priv->subdev);
++ v4l2_subdev_cleanup(&priv->subdev);
+
+ pm_runtime_disable(&pdev->dev);
+
+diff --git a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c
+index e2c40abc6d3d1..21d5b2815e86a 100644
+--- a/drivers/media/platform/renesas/rcar-vin/rcar-dma.c
++++ b/drivers/media/platform/renesas/rcar-vin/rcar-dma.c
+@@ -742,12 +742,22 @@ static int rvin_setup(struct rvin_dev *vin)
+ */
+ switch (vin->mbus_code) {
+ case MEDIA_BUS_FMT_YUYV8_1X16:
+- /* BT.601/BT.1358 16bit YCbCr422 */
+- vnmc |= VNMC_INF_YUV16;
++ if (vin->is_csi)
++ /* YCbCr422 8-bit */
++ vnmc |= VNMC_INF_YUV8_BT601;
++ else
++ /* BT.601/BT.1358 16bit YCbCr422 */
++ vnmc |= VNMC_INF_YUV16;
+ input_is_yuv = true;
+ break;
+ case MEDIA_BUS_FMT_UYVY8_1X16:
+- vnmc |= VNMC_INF_YUV16 | VNMC_YCAL;
++ if (vin->is_csi)
++ /* YCbCr422 8-bit */
++ vnmc |= VNMC_INF_YUV8_BT601;
++ else
++ /* BT.601/BT.1358 16bit YCbCr422 */
++ vnmc |= VNMC_INF_YUV16;
++ vnmc |= VNMC_YCAL;
+ input_is_yuv = true;
+ break;
+ case MEDIA_BUS_FMT_UYVY8_2X8:
+diff --git a/drivers/media/platform/renesas/vsp1/vsp1_histo.c b/drivers/media/platform/renesas/vsp1/vsp1_histo.c
+index 71155282ca116..cd1c8778662e6 100644
+--- a/drivers/media/platform/renesas/vsp1/vsp1_histo.c
++++ b/drivers/media/platform/renesas/vsp1/vsp1_histo.c
+@@ -36,9 +36,8 @@ struct vsp1_histogram_buffer *
+ vsp1_histogram_buffer_get(struct vsp1_histogram *histo)
+ {
+ struct vsp1_histogram_buffer *buf = NULL;
+- unsigned long flags;
+
+- spin_lock_irqsave(&histo->irqlock, flags);
++ spin_lock(&histo->irqlock);
+
+ if (list_empty(&histo->irqqueue))
+ goto done;
+@@ -49,7 +48,7 @@ vsp1_histogram_buffer_get(struct vsp1_histogram *histo)
+ histo->readout = true;
+
+ done:
+- spin_unlock_irqrestore(&histo->irqlock, flags);
++ spin_unlock(&histo->irqlock);
+ return buf;
+ }
+
+@@ -58,7 +57,6 @@ void vsp1_histogram_buffer_complete(struct vsp1_histogram *histo,
+ size_t size)
+ {
+ struct vsp1_pipeline *pipe = histo->entity.pipe;
+- unsigned long flags;
+
+ /*
+ * The pipeline pointer is guaranteed to be valid as this function is
+@@ -70,10 +68,10 @@ void vsp1_histogram_buffer_complete(struct vsp1_histogram *histo,
+ vb2_set_plane_payload(&buf->buf.vb2_buf, 0, size);
+ vb2_buffer_done(&buf->buf.vb2_buf, VB2_BUF_STATE_DONE);
+
+- spin_lock_irqsave(&histo->irqlock, flags);
++ spin_lock(&histo->irqlock);
+ histo->readout = false;
+ wake_up(&histo->wait_queue);
+- spin_unlock_irqrestore(&histo->irqlock, flags);
++ spin_unlock(&histo->irqlock);
+ }
+
+ /* -----------------------------------------------------------------------------
+@@ -124,11 +122,10 @@ static void histo_buffer_queue(struct vb2_buffer *vb)
+ struct vb2_v4l2_buffer *vbuf = to_vb2_v4l2_buffer(vb);
+ struct vsp1_histogram *histo = vb2_get_drv_priv(vb->vb2_queue);
+ struct vsp1_histogram_buffer *buf = to_vsp1_histogram_buffer(vbuf);
+- unsigned long flags;
+
+- spin_lock_irqsave(&histo->irqlock, flags);
++ spin_lock_irq(&histo->irqlock);
+ list_add_tail(&buf->queue, &histo->irqqueue);
+- spin_unlock_irqrestore(&histo->irqlock, flags);
++ spin_unlock_irq(&histo->irqlock);
+ }
+
+ static int histo_start_streaming(struct vb2_queue *vq, unsigned int count)
+@@ -140,9 +137,8 @@ static void histo_stop_streaming(struct vb2_queue *vq)
+ {
+ struct vsp1_histogram *histo = vb2_get_drv_priv(vq);
+ struct vsp1_histogram_buffer *buffer;
+- unsigned long flags;
+
+- spin_lock_irqsave(&histo->irqlock, flags);
++ spin_lock_irq(&histo->irqlock);
+
+ /* Remove all buffers from the IRQ queue. */
+ list_for_each_entry(buffer, &histo->irqqueue, queue)
+@@ -152,7 +148,7 @@ static void histo_stop_streaming(struct vb2_queue *vq)
+ /* Wait for the buffer being read out (if any) to complete. */
+ wait_event_lock_irq(histo->wait_queue, !histo->readout, histo->irqlock);
+
+- spin_unlock_irqrestore(&histo->irqlock, flags);
++ spin_unlock_irq(&histo->irqlock);
+ }
+
+ static const struct vb2_ops histo_video_queue_qops = {
+diff --git a/drivers/media/platform/renesas/vsp1/vsp1_pipe.h b/drivers/media/platform/renesas/vsp1/vsp1_pipe.h
+index 674b5748d929e..85ecd53cda495 100644
+--- a/drivers/media/platform/renesas/vsp1/vsp1_pipe.h
++++ b/drivers/media/platform/renesas/vsp1/vsp1_pipe.h
+@@ -73,7 +73,7 @@ struct vsp1_partition_window {
+ * @wpf: The WPF partition window configuration
+ */
+ struct vsp1_partition {
+- struct vsp1_partition_window rpf;
++ struct vsp1_partition_window rpf[VSP1_MAX_RPF];
+ struct vsp1_partition_window uds_sink;
+ struct vsp1_partition_window uds_source;
+ struct vsp1_partition_window sru;
+diff --git a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
+index c47579efc65f6..6055554fb0714 100644
+--- a/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
++++ b/drivers/media/platform/renesas/vsp1/vsp1_rpf.c
+@@ -315,8 +315,8 @@ static void rpf_configure_partition(struct vsp1_entity *entity,
+ * 'width' need to be adjusted.
+ */
+ if (pipe->partitions > 1) {
+- crop.width = pipe->partition->rpf.width;
+- crop.left += pipe->partition->rpf.left;
++ crop.width = pipe->partition->rpf[rpf->entity.index].width;
++ crop.left += pipe->partition->rpf[rpf->entity.index].left;
+ }
+
+ if (pipe->interlaced) {
+@@ -371,7 +371,9 @@ static void rpf_partition(struct vsp1_entity *entity,
+ unsigned int partition_idx,
+ struct vsp1_partition_window *window)
+ {
+- partition->rpf = *window;
++ struct vsp1_rwpf *rpf = to_rwpf(&entity->subdev);
++
++ partition->rpf[rpf->entity.index] = *window;
+ }
+
+ static const struct vsp1_entity_operations rpf_entity_ops = {
+diff --git a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-debugfs.h b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-debugfs.h
+index 8e1bfd8605247..3fe177b59b16d 100644
+--- a/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-debugfs.h
++++ b/drivers/media/platform/st/sti/c8sectpfe/c8sectpfe-debugfs.h
+@@ -16,8 +16,8 @@
+ void c8sectpfe_debugfs_init(struct c8sectpfei *);
+ void c8sectpfe_debugfs_exit(struct c8sectpfei *);
+ #else
+-static inline void c8sectpfe_debugfs_init(struct c8sectpfei *) {};
+-static inline void c8sectpfe_debugfs_exit(struct c8sectpfei *) {};
++static inline void c8sectpfe_debugfs_init(struct c8sectpfei *fei) {};
++static inline void c8sectpfe_debugfs_exit(struct c8sectpfei *fei) {};
+ #endif
+
+ #endif /* __C8SECTPFE_DEBUG_H */
+diff --git a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c
+index 4acc3b90d03aa..7f771ea49b784 100644
+--- a/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c
++++ b/drivers/media/platform/st/stm32/stm32-dcmipp/dcmipp-core.c
+@@ -202,8 +202,8 @@ static int dcmipp_create_subdevs(struct dcmipp_device *dcmipp)
+ return 0;
+
+ err_init_entity:
+- while (i > 0)
+- dcmipp->pipe_cfg->ents[i - 1].release(dcmipp->entity[i - 1]);
++ while (i-- > 0)
++ dcmipp->pipe_cfg->ents[i].release(dcmipp->entity[i]);
+ return ret;
+ }
+
+diff --git a/drivers/media/rc/imon.c b/drivers/media/rc/imon.c
+index 0b55314a80827..8f1361bcce3a6 100644
+--- a/drivers/media/rc/imon.c
++++ b/drivers/media/rc/imon.c
+@@ -1148,10 +1148,7 @@ static int imon_ir_change_protocol(struct rc_dev *rc, u64 *rc_proto)
+
+ memcpy(ictx->usb_tx_buf, &ir_proto_packet, sizeof(ir_proto_packet));
+
+- if (!mutex_is_locked(&ictx->lock)) {
+- unlock = true;
+- mutex_lock(&ictx->lock);
+- }
++ unlock = mutex_trylock(&ictx->lock);
+
+ retval = send_packet(ictx);
+ if (retval)
+diff --git a/drivers/media/rc/lirc_dev.c b/drivers/media/rc/lirc_dev.c
+index 52aea41677183..717c441b4a865 100644
+--- a/drivers/media/rc/lirc_dev.c
++++ b/drivers/media/rc/lirc_dev.c
+@@ -828,8 +828,10 @@ struct rc_dev *rc_dev_get_from_fd(int fd, bool write)
+ return ERR_PTR(-EINVAL);
+ }
+
+- if (write && !(f.file->f_mode & FMODE_WRITE))
++ if (write && !(f.file->f_mode & FMODE_WRITE)) {
++ fdput(f);
+ return ERR_PTR(-EPERM);
++ }
+
+ fh = f.file->private_data;
+ dev = fh->rc;
+diff --git a/drivers/media/usb/dvb-usb/dvb-usb-init.c b/drivers/media/usb/dvb-usb/dvb-usb-init.c
+index fbf58012becdf..22d83ac18eb73 100644
+--- a/drivers/media/usb/dvb-usb/dvb-usb-init.c
++++ b/drivers/media/usb/dvb-usb/dvb-usb-init.c
+@@ -23,11 +23,40 @@ static int dvb_usb_force_pid_filter_usage;
+ module_param_named(force_pid_filter_usage, dvb_usb_force_pid_filter_usage, int, 0444);
+ MODULE_PARM_DESC(force_pid_filter_usage, "force all dvb-usb-devices to use a PID filter, if any (default: 0).");
+
++static int dvb_usb_check_bulk_endpoint(struct dvb_usb_device *d, u8 endpoint)
++{
++ if (endpoint) {
++ int ret;
++
++ ret = usb_pipe_type_check(d->udev, usb_sndbulkpipe(d->udev, endpoint));
++ if (ret)
++ return ret;
++ ret = usb_pipe_type_check(d->udev, usb_rcvbulkpipe(d->udev, endpoint));
++ if (ret)
++ return ret;
++ }
++ return 0;
++}
++
++static void dvb_usb_clear_halt(struct dvb_usb_device *d, u8 endpoint)
++{
++ if (endpoint) {
++ usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, endpoint));
++ usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, endpoint));
++ }
++}
++
+ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs)
+ {
+ struct dvb_usb_adapter *adap;
+ int ret, n, o;
+
++ ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint);
++ if (ret)
++ return ret;
++ ret = dvb_usb_check_bulk_endpoint(d, d->props.generic_bulk_ctrl_endpoint_response);
++ if (ret)
++ return ret;
+ for (n = 0; n < d->props.num_adapters; n++) {
+ adap = &d->adapter[n];
+ adap->dev = d;
+@@ -103,10 +132,8 @@ static int dvb_usb_adapter_init(struct dvb_usb_device *d, short *adapter_nrs)
+ * when reloading the driver w/o replugging the device
+ * sometimes a timeout occurs, this helps
+ */
+- if (d->props.generic_bulk_ctrl_endpoint != 0) {
+- usb_clear_halt(d->udev, usb_sndbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint));
+- usb_clear_halt(d->udev, usb_rcvbulkpipe(d->udev, d->props.generic_bulk_ctrl_endpoint));
+- }
++ dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint);
++ dvb_usb_clear_halt(d, d->props.generic_bulk_ctrl_endpoint_response);
+
+ return 0;
+
+diff --git a/drivers/media/usb/uvc/uvc_ctrl.c b/drivers/media/usb/uvc/uvc_ctrl.c
+index 4b685f883e4d7..a7d0ec22d95c0 100644
+--- a/drivers/media/usb/uvc/uvc_ctrl.c
++++ b/drivers/media/usb/uvc/uvc_ctrl.c
+@@ -2031,7 +2031,13 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev,
+ else
+ ret = uvc_query_ctrl(dev, UVC_GET_INFO, ctrl->entity->id,
+ dev->intfnum, info->selector, data, 1);
+- if (!ret)
++
++ if (!ret) {
++ info->flags &= ~(UVC_CTRL_FLAG_GET_CUR |
++ UVC_CTRL_FLAG_SET_CUR |
++ UVC_CTRL_FLAG_AUTO_UPDATE |
++ UVC_CTRL_FLAG_ASYNCHRONOUS);
++
+ info->flags |= (data[0] & UVC_CONTROL_CAP_GET ?
+ UVC_CTRL_FLAG_GET_CUR : 0)
+ | (data[0] & UVC_CONTROL_CAP_SET ?
+@@ -2040,6 +2046,7 @@ static int uvc_ctrl_get_flags(struct uvc_device *dev,
+ UVC_CTRL_FLAG_AUTO_UPDATE : 0)
+ | (data[0] & UVC_CONTROL_CAP_ASYNCHRONOUS ?
+ UVC_CTRL_FLAG_ASYNCHRONOUS : 0);
++ }
+
+ kfree(data);
+ return ret;
+diff --git a/drivers/media/usb/uvc/uvc_driver.c b/drivers/media/usb/uvc/uvc_driver.c
+index 8fe24c98087e6..d435b6a6c295d 100644
+--- a/drivers/media/usb/uvc/uvc_driver.c
++++ b/drivers/media/usb/uvc/uvc_driver.c
+@@ -2580,7 +2580,17 @@ static const struct usb_device_id uvc_ids[] = {
+ .bInterfaceClass = USB_CLASS_VIDEO,
+ .bInterfaceSubClass = 1,
+ .bInterfaceProtocol = 0,
+- .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_RESTORE_CTRLS_ON_INIT) },
++ .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_RESTORE_CTRLS_ON_INIT
++ | UVC_QUIRK_INVALID_DEVICE_SOF) },
++ /* Logitech HD Pro Webcam C922 */
++ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE
++ | USB_DEVICE_ID_MATCH_INT_INFO,
++ .idVendor = 0x046d,
++ .idProduct = 0x085c,
++ .bInterfaceClass = USB_CLASS_VIDEO,
++ .bInterfaceSubClass = 1,
++ .bInterfaceProtocol = 0,
++ .driver_info = UVC_INFO_QUIRK(UVC_QUIRK_INVALID_DEVICE_SOF) },
+ /* Logitech Rally Bar Huddle */
+ { .match_flags = USB_DEVICE_ID_MATCH_DEVICE
+ | USB_DEVICE_ID_MATCH_INT_INFO,
+diff --git a/drivers/media/usb/uvc/uvc_video.c b/drivers/media/usb/uvc/uvc_video.c
+index 7cbf4692bd875..51f4f653b983d 100644
+--- a/drivers/media/usb/uvc/uvc_video.c
++++ b/drivers/media/usb/uvc/uvc_video.c
+@@ -529,6 +529,17 @@ uvc_video_clock_decode(struct uvc_streaming *stream, struct uvc_buffer *buf,
+ stream->clock.last_sof = dev_sof;
+
+ host_sof = usb_get_current_frame_number(stream->dev->udev);
++
++ /*
++ * On some devices, like the Logitech C922, the device SOF does not run
++ * at a stable rate of 1kHz. For those devices use the host SOF instead.
++ * In the tests performed so far, this improves the timestamp precision.
++ * This is probably explained by a small packet handling jitter from the
++ * host, but the exact reason hasn't been fully determined.
++ */
++ if (stream->dev->quirks & UVC_QUIRK_INVALID_DEVICE_SOF)
++ dev_sof = host_sof;
++
+ time = uvc_video_get_time();
+
+ /*
+@@ -709,11 +720,11 @@ void uvc_video_clock_update(struct uvc_streaming *stream,
+ unsigned long flags;
+ u64 timestamp;
+ u32 delta_stc;
+- u32 y1, y2;
++ u32 y1;
+ u32 x1, x2;
+ u32 mean;
+ u32 sof;
+- u64 y;
++ u64 y, y2;
+
+ if (!uvc_hw_timestamps_param)
+ return;
+@@ -753,7 +764,7 @@ void uvc_video_clock_update(struct uvc_streaming *stream,
+ sof = y;
+
+ uvc_dbg(stream->dev, CLOCK,
+- "%s: PTS %u y %llu.%06llu SOF %u.%06llu (x1 %u x2 %u y1 %u y2 %u SOF offset %u)\n",
++ "%s: PTS %u y %llu.%06llu SOF %u.%06llu (x1 %u x2 %u y1 %u y2 %llu SOF offset %u)\n",
+ stream->dev->name, buf->pts,
+ y >> 16, div_u64((y & 0xffff) * 1000000, 65536),
+ sof >> 16, div_u64(((u64)sof & 0xffff) * 1000000LLU, 65536),
+@@ -768,7 +779,7 @@ void uvc_video_clock_update(struct uvc_streaming *stream,
+ goto done;
+
+ y1 = NSEC_PER_SEC;
+- y2 = (u32)ktime_to_ns(ktime_sub(last->host_time, first->host_time)) + y1;
++ y2 = ktime_to_ns(ktime_sub(last->host_time, first->host_time)) + y1;
+
+ /*
+ * Interpolated and host SOF timestamps can wrap around at slightly
+@@ -789,7 +800,7 @@ void uvc_video_clock_update(struct uvc_streaming *stream,
+ timestamp = ktime_to_ns(first->host_time) + y - y1;
+
+ uvc_dbg(stream->dev, CLOCK,
+- "%s: SOF %u.%06llu y %llu ts %llu buf ts %llu (x1 %u/%u/%u x2 %u/%u/%u y1 %u y2 %u)\n",
++ "%s: SOF %u.%06llu y %llu ts %llu buf ts %llu (x1 %u/%u/%u x2 %u/%u/%u y1 %u y2 %llu)\n",
+ stream->dev->name,
+ sof >> 16, div_u64(((u64)sof & 0xffff) * 1000000LLU, 65536),
+ y, timestamp, vbuf->vb2_buf.timestamp,
+diff --git a/drivers/media/usb/uvc/uvcvideo.h b/drivers/media/usb/uvc/uvcvideo.h
+index 3653b2c8a86cb..e5b12717016fa 100644
+--- a/drivers/media/usb/uvc/uvcvideo.h
++++ b/drivers/media/usb/uvc/uvcvideo.h
+@@ -75,6 +75,7 @@
+ #define UVC_QUIRK_WAKE_AUTOSUSPEND 0x00002000
+ #define UVC_QUIRK_NO_RESET_RESUME 0x00004000
+ #define UVC_QUIRK_DISABLE_AUTOSUSPEND 0x00008000
++#define UVC_QUIRK_INVALID_DEVICE_SOF 0x00010000
+
+ /* Format flags */
+ #define UVC_FMT_FLAG_COMPRESSED 0x00000001
+diff --git a/drivers/media/v4l2-core/v4l2-async.c b/drivers/media/v4l2-core/v4l2-async.c
+index 222f01665f7ce..c477723c07bf8 100644
+--- a/drivers/media/v4l2-core/v4l2-async.c
++++ b/drivers/media/v4l2-core/v4l2-async.c
+@@ -323,6 +323,9 @@ static int v4l2_async_create_ancillary_links(struct v4l2_async_notifier *n,
+ sd->entity.function != MEDIA_ENT_F_FLASH)
+ return 0;
+
++ if (!n->sd)
++ return 0;
++
+ link = media_create_ancillary_link(&n->sd->entity, &sd->entity);
+
+ return IS_ERR(link) ? PTR_ERR(link) : 0;
+diff --git a/drivers/memory/Kconfig b/drivers/memory/Kconfig
+index 8efdd1f971395..c82d8d8a16eaf 100644
+--- a/drivers/memory/Kconfig
++++ b/drivers/memory/Kconfig
+@@ -167,7 +167,7 @@ config FSL_CORENET_CF
+ represents a coherency violation.
+
+ config FSL_IFC
+- bool "Freescale IFC driver" if COMPILE_TEST
++ bool "Freescale IFC driver"
+ depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+ depends on HAS_IOMEM
+
+diff --git a/drivers/mfd/Makefile b/drivers/mfd/Makefile
+index c66f07edcd0e6..db1ba39de3b59 100644
+--- a/drivers/mfd/Makefile
++++ b/drivers/mfd/Makefile
+@@ -280,7 +280,5 @@ obj-$(CONFIG_MFD_INTEL_M10_BMC_PMCI) += intel-m10-bmc-pmci.o
+ obj-$(CONFIG_MFD_ATC260X) += atc260x-core.o
+ obj-$(CONFIG_MFD_ATC260X_I2C) += atc260x-i2c.o
+
+-rsmu-i2c-objs := rsmu_core.o rsmu_i2c.o
+-rsmu-spi-objs := rsmu_core.o rsmu_spi.o
+-obj-$(CONFIG_MFD_RSMU_I2C) += rsmu-i2c.o
+-obj-$(CONFIG_MFD_RSMU_SPI) += rsmu-spi.o
++obj-$(CONFIG_MFD_RSMU_I2C) += rsmu_i2c.o rsmu_core.o
++obj-$(CONFIG_MFD_RSMU_SPI) += rsmu_spi.o rsmu_core.o
+diff --git a/drivers/mfd/omap-usb-tll.c b/drivers/mfd/omap-usb-tll.c
+index b6303ddb013b0..f68dd02814638 100644
+--- a/drivers/mfd/omap-usb-tll.c
++++ b/drivers/mfd/omap-usb-tll.c
+@@ -230,8 +230,7 @@ static int usbtll_omap_probe(struct platform_device *pdev)
+ break;
+ }
+
+- tll = devm_kzalloc(dev, sizeof(*tll) + sizeof(tll->ch_clk[nch]),
+- GFP_KERNEL);
++ tll = devm_kzalloc(dev, struct_size(tll, ch_clk, nch), GFP_KERNEL);
+ if (!tll) {
+ pm_runtime_put_sync(dev);
+ pm_runtime_disable(dev);
+diff --git a/drivers/mfd/rsmu_core.c b/drivers/mfd/rsmu_core.c
+index 29437fd0bd5bf..fd04a6e5dfa31 100644
+--- a/drivers/mfd/rsmu_core.c
++++ b/drivers/mfd/rsmu_core.c
+@@ -78,11 +78,13 @@ int rsmu_core_init(struct rsmu_ddata *rsmu)
+
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(rsmu_core_init);
+
+ void rsmu_core_exit(struct rsmu_ddata *rsmu)
+ {
+ mutex_destroy(&rsmu->lock);
+ }
++EXPORT_SYMBOL_GPL(rsmu_core_exit);
+
+ MODULE_DESCRIPTION("Renesas SMU core driver");
+ MODULE_LICENSE("GPL");
+diff --git a/drivers/misc/eeprom/ee1004.c b/drivers/misc/eeprom/ee1004.c
+index 21feebc3044c3..71ca66d1df82c 100644
+--- a/drivers/misc/eeprom/ee1004.c
++++ b/drivers/misc/eeprom/ee1004.c
+@@ -185,6 +185,8 @@ BIN_ATTRIBUTE_GROUPS(ee1004);
+ static void ee1004_probe_temp_sensor(struct i2c_client *client)
+ {
+ struct i2c_board_info info = { .type = "jc42" };
++ unsigned short addr = 0x18 | (client->addr & 7);
++ unsigned short addr_list[] = { addr, I2C_CLIENT_END };
+ u8 byte14;
+ int ret;
+
+@@ -193,9 +195,7 @@ static void ee1004_probe_temp_sensor(struct i2c_client *client)
+ if (ret != 1 || !(byte14 & BIT(7)))
+ return;
+
+- info.addr = 0x18 | (client->addr & 7);
+-
+- i2c_new_client_device(client->adapter, &info);
++ i2c_new_scanned_device(client->adapter, &info, addr_list, NULL);
+ }
+
+ static void ee1004_cleanup(int idx, struct ee1004_bus_data *bd)
+diff --git a/drivers/mtd/nand/raw/Kconfig b/drivers/mtd/nand/raw/Kconfig
+index cbf8ae85e1ae0..6142573085169 100644
+--- a/drivers/mtd/nand/raw/Kconfig
++++ b/drivers/mtd/nand/raw/Kconfig
+@@ -234,8 +234,7 @@ config MTD_NAND_FSL_IFC
+ tristate "Freescale IFC NAND controller"
+ depends on FSL_SOC || ARCH_LAYERSCAPE || SOC_LS1021A || COMPILE_TEST
+ depends on HAS_IOMEM
+- select FSL_IFC
+- select MEMORY
++ depends on FSL_IFC
+ help
+ Various Freescale chips e.g P1010, include a NAND Flash machine
+ with built-in hardware ECC capabilities.
+diff --git a/drivers/mtd/spi-nor/winbond.c b/drivers/mtd/spi-nor/winbond.c
+index 142fb27b2ea9a..e065e4fd42a33 100644
+--- a/drivers/mtd/spi-nor/winbond.c
++++ b/drivers/mtd/spi-nor/winbond.c
+@@ -105,7 +105,9 @@ static const struct flash_info winbond_nor_parts[] = {
+ }, {
+ .id = SNOR_ID(0xef, 0x40, 0x18),
+ .name = "w25q128",
++ .size = SZ_16M,
+ .flags = SPI_NOR_HAS_LOCK | SPI_NOR_HAS_TB,
++ .no_sfdp_flags = SECT_4K | SPI_NOR_DUAL_READ | SPI_NOR_QUAD_READ,
+ }, {
+ .id = SNOR_ID(0xef, 0x40, 0x19),
+ .name = "w25q256",
+diff --git a/drivers/mtd/tests/Makefile b/drivers/mtd/tests/Makefile
+index 5de0378f90dbd..7dae831ee8b6b 100644
+--- a/drivers/mtd/tests/Makefile
++++ b/drivers/mtd/tests/Makefile
+@@ -1,19 +1,19 @@
+ # SPDX-License-Identifier: GPL-2.0
+-obj-$(CONFIG_MTD_TESTS) += mtd_oobtest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_pagetest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_readtest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_speedtest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_stresstest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_subpagetest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_torturetest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_nandecctest.o
+-obj-$(CONFIG_MTD_TESTS) += mtd_nandbiterrs.o
++obj-$(CONFIG_MTD_TESTS) += mtd_oobtest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_pagetest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_readtest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_speedtest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_stresstest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_subpagetest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_torturetest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_nandecctest.o mtd_test.o
++obj-$(CONFIG_MTD_TESTS) += mtd_nandbiterrs.o mtd_test.o
+
+-mtd_oobtest-objs := oobtest.o mtd_test.o
+-mtd_pagetest-objs := pagetest.o mtd_test.o
+-mtd_readtest-objs := readtest.o mtd_test.o
+-mtd_speedtest-objs := speedtest.o mtd_test.o
+-mtd_stresstest-objs := stresstest.o mtd_test.o
+-mtd_subpagetest-objs := subpagetest.o mtd_test.o
+-mtd_torturetest-objs := torturetest.o mtd_test.o
+-mtd_nandbiterrs-objs := nandbiterrs.o mtd_test.o
++mtd_oobtest-objs := oobtest.o
++mtd_pagetest-objs := pagetest.o
++mtd_readtest-objs := readtest.o
++mtd_speedtest-objs := speedtest.o
++mtd_stresstest-objs := stresstest.o
++mtd_subpagetest-objs := subpagetest.o
++mtd_torturetest-objs := torturetest.o
++mtd_nandbiterrs-objs := nandbiterrs.o
+diff --git a/drivers/mtd/tests/mtd_test.c b/drivers/mtd/tests/mtd_test.c
+index c84250beffdc9..f391e0300cdc9 100644
+--- a/drivers/mtd/tests/mtd_test.c
++++ b/drivers/mtd/tests/mtd_test.c
+@@ -25,6 +25,7 @@ int mtdtest_erase_eraseblock(struct mtd_info *mtd, unsigned int ebnum)
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(mtdtest_erase_eraseblock);
+
+ static int is_block_bad(struct mtd_info *mtd, unsigned int ebnum)
+ {
+@@ -57,6 +58,7 @@ int mtdtest_scan_for_bad_eraseblocks(struct mtd_info *mtd, unsigned char *bbt,
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(mtdtest_scan_for_bad_eraseblocks);
+
+ int mtdtest_erase_good_eraseblocks(struct mtd_info *mtd, unsigned char *bbt,
+ unsigned int eb, int ebcnt)
+@@ -75,6 +77,7 @@ int mtdtest_erase_good_eraseblocks(struct mtd_info *mtd, unsigned char *bbt,
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(mtdtest_erase_good_eraseblocks);
+
+ int mtdtest_read(struct mtd_info *mtd, loff_t addr, size_t size, void *buf)
+ {
+@@ -92,6 +95,7 @@ int mtdtest_read(struct mtd_info *mtd, loff_t addr, size_t size, void *buf)
+
+ return err;
+ }
++EXPORT_SYMBOL_GPL(mtdtest_read);
+
+ int mtdtest_write(struct mtd_info *mtd, loff_t addr, size_t size,
+ const void *buf)
+@@ -107,3 +111,8 @@ int mtdtest_write(struct mtd_info *mtd, loff_t addr, size_t size,
+
+ return err;
+ }
++EXPORT_SYMBOL_GPL(mtdtest_write);
++
++MODULE_LICENSE("GPL");
++MODULE_DESCRIPTION("MTD function test helpers");
++MODULE_AUTHOR("Akinobu Mita");
+diff --git a/drivers/mtd/ubi/eba.c b/drivers/mtd/ubi/eba.c
+index e5ac3cd0bbae6..c7ba7a15c9f78 100644
+--- a/drivers/mtd/ubi/eba.c
++++ b/drivers/mtd/ubi/eba.c
+@@ -1564,6 +1564,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap,
+ GFP_KERNEL);
+ if (!fm_eba[i]) {
+ ret = -ENOMEM;
++ kfree(scan_eba[i]);
+ goto out_free;
+ }
+
+@@ -1599,7 +1600,7 @@ int self_check_eba(struct ubi_device *ubi, struct ubi_attach_info *ai_fastmap,
+ }
+
+ out_free:
+- for (i = 0; i < num_volumes; i++) {
++ while (--i >= 0) {
+ if (!ubi->volumes[i])
+ continue;
+
+diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c
+index d19aabf5d4fba..2ed0da0684906 100644
+--- a/drivers/net/bonding/bond_main.c
++++ b/drivers/net/bonding/bond_main.c
+@@ -1121,13 +1121,10 @@ static struct slave *bond_find_best_slave(struct bonding *bond)
+ return bestslave;
+ }
+
++/* must be called in RCU critical section or with RTNL held */
+ static bool bond_should_notify_peers(struct bonding *bond)
+ {
+- struct slave *slave;
+-
+- rcu_read_lock();
+- slave = rcu_dereference(bond->curr_active_slave);
+- rcu_read_unlock();
++ struct slave *slave = rcu_dereference_rtnl(bond->curr_active_slave);
+
+ if (!slave || !bond->send_peer_notif ||
+ bond->send_peer_notif %
+diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c
+index 8f50abe739b71..0783fc121bbbf 100644
+--- a/drivers/net/dsa/b53/b53_common.c
++++ b/drivers/net/dsa/b53/b53_common.c
+@@ -2256,6 +2256,9 @@ static int b53_change_mtu(struct dsa_switch *ds, int port, int mtu)
+ if (is5325(dev) || is5365(dev))
+ return -EOPNOTSUPP;
+
++ if (!dsa_is_cpu_port(ds, port))
++ return 0;
++
+ enable_jumbo = (mtu >= JMS_MIN_SIZE);
+ allow_10_100 = (dev->chip_id == BCM583XX_DEVICE_ID);
+
+diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c
+index 0580b2fee21c3..baa1eeb9a1b04 100644
+--- a/drivers/net/dsa/microchip/ksz_common.c
++++ b/drivers/net/dsa/microchip/ksz_common.c
+@@ -3917,6 +3917,13 @@ static int ksz_hsr_join(struct dsa_switch *ds, int port, struct net_device *hsr,
+ return -EOPNOTSUPP;
+ }
+
++ /* KSZ9477 can only perform HSR offloading for up to two ports */
++ if (hweight8(dev->hsr_ports) >= 2) {
++ NL_SET_ERR_MSG_MOD(extack,
++ "Cannot offload more than two ports - using software HSR");
++ return -EOPNOTSUPP;
++ }
++
+ /* Self MAC address filtering, to avoid frames traversing
+ * the HSR ring more than once.
+ */
+diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c
+index 07c897b13de13..5b4e2ce5470d9 100644
+--- a/drivers/net/dsa/mv88e6xxx/chip.c
++++ b/drivers/net/dsa/mv88e6xxx/chip.c
+@@ -3626,7 +3626,8 @@ static int mv88e6xxx_change_mtu(struct dsa_switch *ds, int port, int new_mtu)
+ mv88e6xxx_reg_lock(chip);
+ if (chip->info->ops->port_set_jumbo_size)
+ ret = chip->info->ops->port_set_jumbo_size(chip, port, new_mtu);
+- else if (chip->info->ops->set_max_frame_size)
++ else if (chip->info->ops->set_max_frame_size &&
++ dsa_is_cpu_port(ds, port))
+ ret = chip->info->ops->set_max_frame_size(chip, new_mtu);
+ mv88e6xxx_reg_unlock(chip);
+
+diff --git a/drivers/net/ethernet/brocade/bna/bna_types.h b/drivers/net/ethernet/brocade/bna/bna_types.h
+index a5ebd7110e073..986f43d277119 100644
+--- a/drivers/net/ethernet/brocade/bna/bna_types.h
++++ b/drivers/net/ethernet/brocade/bna/bna_types.h
+@@ -416,7 +416,7 @@ struct bna_ib {
+ /* Tx object */
+
+ /* Tx datapath control structure */
+-#define BNA_Q_NAME_SIZE 16
++#define BNA_Q_NAME_SIZE (IFNAMSIZ + 6)
+ struct bna_tcb {
+ /* Fast path */
+ void **sw_qpt;
+diff --git a/drivers/net/ethernet/brocade/bna/bnad.c b/drivers/net/ethernet/brocade/bna/bnad.c
+index fe121d36112d5..ece6f3b483273 100644
+--- a/drivers/net/ethernet/brocade/bna/bnad.c
++++ b/drivers/net/ethernet/brocade/bna/bnad.c
+@@ -1534,8 +1534,9 @@ bnad_tx_msix_register(struct bnad *bnad, struct bnad_tx_info *tx_info,
+
+ for (i = 0; i < num_txqs; i++) {
+ vector_num = tx_info->tcb[i]->intr_vector;
+- sprintf(tx_info->tcb[i]->name, "%s TXQ %d", bnad->netdev->name,
+- tx_id + tx_info->tcb[i]->id);
++ snprintf(tx_info->tcb[i]->name, BNA_Q_NAME_SIZE, "%s TXQ %d",
++ bnad->netdev->name,
++ tx_id + tx_info->tcb[i]->id);
+ err = request_irq(bnad->msix_table[vector_num].vector,
+ (irq_handler_t)bnad_msix_tx, 0,
+ tx_info->tcb[i]->name,
+@@ -1585,9 +1586,9 @@ bnad_rx_msix_register(struct bnad *bnad, struct bnad_rx_info *rx_info,
+
+ for (i = 0; i < num_rxps; i++) {
+ vector_num = rx_info->rx_ctrl[i].ccb->intr_vector;
+- sprintf(rx_info->rx_ctrl[i].ccb->name, "%s CQ %d",
+- bnad->netdev->name,
+- rx_id + rx_info->rx_ctrl[i].ccb->id);
++ snprintf(rx_info->rx_ctrl[i].ccb->name, BNA_Q_NAME_SIZE,
++ "%s CQ %d", bnad->netdev->name,
++ rx_id + rx_info->rx_ctrl[i].ccb->id);
+ err = request_irq(bnad->msix_table[vector_num].vector,
+ (irq_handler_t)bnad_msix_rx, 0,
+ rx_info->rx_ctrl[i].ccb->name,
+diff --git a/drivers/net/ethernet/cortina/gemini.c b/drivers/net/ethernet/cortina/gemini.c
+index 5f0c9e1771dbf..7ebd61a3a49b0 100644
+--- a/drivers/net/ethernet/cortina/gemini.c
++++ b/drivers/net/ethernet/cortina/gemini.c
+@@ -79,7 +79,8 @@ MODULE_PARM_DESC(debug, "Debug level (0=none,...,16=all)");
+ #define GMAC0_IRQ4_8 (GMAC0_MIB_INT_BIT | GMAC0_RX_OVERRUN_INT_BIT)
+
+ #define GMAC_OFFLOAD_FEATURES (NETIF_F_SG | NETIF_F_IP_CSUM | \
+- NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM)
++ NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM | \
++ NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6)
+
+ /**
+ * struct gmac_queue_page - page buffer per-page info
+@@ -1148,13 +1149,25 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
+ skb_frag_t *skb_frag;
+ dma_addr_t mapping;
+ void *buffer;
++ u16 mss;
+ int ret;
+
+- /* TODO: implement proper TSO using MTU in word3 */
+ word1 = skb->len;
+ word3 = SOF_BIT;
+
+- if (skb->len >= ETH_FRAME_LEN) {
++ mss = skb_shinfo(skb)->gso_size;
++ if (mss) {
++ /* This means we are dealing with TCP and skb->len is the
++ * sum total of all the segments. The TSO will deal with
++ * chopping this up for us.
++ */
++ /* The accelerator needs the full frame size here */
++ mss += skb_tcp_all_headers(skb);
++ netdev_dbg(netdev, "segment offloading mss = %04x len=%04x\n",
++ mss, skb->len);
++ word1 |= TSS_MTU_ENABLE_BIT;
++ word3 |= mss;
++ } else if (skb->len >= ETH_FRAME_LEN) {
+ /* Hardware offloaded checksumming isn't working on frames
+ * bigger than 1514 bytes. A hypothesis about this is that the
+ * checksum buffer is only 1518 bytes, so when the frames get
+@@ -1169,7 +1182,9 @@ static int gmac_map_tx_bufs(struct net_device *netdev, struct sk_buff *skb,
+ return ret;
+ }
+ word1 |= TSS_BYPASS_BIT;
+- } else if (skb->ip_summed == CHECKSUM_PARTIAL) {
++ }
++
++ if (skb->ip_summed == CHECKSUM_PARTIAL) {
+ int tcp = 0;
+
+ /* We do not switch off the checksumming on non TCP/UDP
+diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c
+index 881ece735dcf1..fb19295529a21 100644
+--- a/drivers/net/ethernet/freescale/fec_main.c
++++ b/drivers/net/ethernet/freescale/fec_main.c
+@@ -1361,6 +1361,12 @@ fec_stop(struct net_device *ndev)
+ writel(FEC_ECR_ETHEREN, fep->hwp + FEC_ECNTRL);
+ writel(rmii_mode, fep->hwp + FEC_R_CNTRL);
+ }
++
++ if (fep->bufdesc_ex) {
++ val = readl(fep->hwp + FEC_ECNTRL);
++ val |= FEC_ECR_EN1588;
++ writel(val, fep->hwp + FEC_ECNTRL);
++ }
+ }
+
+ static void
+diff --git a/drivers/net/ethernet/google/gve/gve_tx.c b/drivers/net/ethernet/google/gve/gve_tx.c
+index 24a64ec1073e2..e7fb7d6d283df 100644
+--- a/drivers/net/ethernet/google/gve/gve_tx.c
++++ b/drivers/net/ethernet/google/gve/gve_tx.c
+@@ -158,15 +158,16 @@ static int gve_clean_xdp_done(struct gve_priv *priv, struct gve_tx_ring *tx,
+ u32 to_do)
+ {
+ struct gve_tx_buffer_state *info;
+- u32 clean_end = tx->done + to_do;
+ u64 pkts = 0, bytes = 0;
+ size_t space_freed = 0;
+ u32 xsk_complete = 0;
+ u32 idx;
++ int i;
+
+- for (; tx->done < clean_end; tx->done++) {
++ for (i = 0; i < to_do; i++) {
+ idx = tx->done & tx->mask;
+ info = &tx->info[idx];
++ tx->done++;
+
+ if (unlikely(!info->xdp.size))
+ continue;
+diff --git a/drivers/net/ethernet/google/gve/gve_tx_dqo.c b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+index 0b3cca3fc7921..f879426cb5523 100644
+--- a/drivers/net/ethernet/google/gve/gve_tx_dqo.c
++++ b/drivers/net/ethernet/google/gve/gve_tx_dqo.c
+@@ -866,22 +866,42 @@ static bool gve_can_send_tso(const struct sk_buff *skb)
+ const int header_len = skb_tcp_all_headers(skb);
+ const int gso_size = shinfo->gso_size;
+ int cur_seg_num_bufs;
++ int prev_frag_size;
+ int cur_seg_size;
+ int i;
+
+ cur_seg_size = skb_headlen(skb) - header_len;
++ prev_frag_size = skb_headlen(skb);
+ cur_seg_num_bufs = cur_seg_size > 0;
+
+ for (i = 0; i < shinfo->nr_frags; i++) {
+ if (cur_seg_size >= gso_size) {
+ cur_seg_size %= gso_size;
+ cur_seg_num_bufs = cur_seg_size > 0;
++
++ if (prev_frag_size > GVE_TX_MAX_BUF_SIZE_DQO) {
++ int prev_frag_remain = prev_frag_size %
++ GVE_TX_MAX_BUF_SIZE_DQO;
++
++ /* If the last descriptor of the previous frag
++ * is less than cur_seg_size, the segment will
++ * span two descriptors in the previous frag.
++ * Since max gso size (9728) is less than
++ * GVE_TX_MAX_BUF_SIZE_DQO, it is impossible
++ * for the segment to span more than two
++ * descriptors.
++ */
++ if (prev_frag_remain &&
++ cur_seg_size > prev_frag_remain)
++ cur_seg_num_bufs++;
++ }
+ }
+
+ if (unlikely(++cur_seg_num_bufs > max_bufs_per_seg))
+ return false;
+
+- cur_seg_size += skb_frag_size(&shinfo->frags[i]);
++ prev_frag_size = skb_frag_size(&shinfo->frags[i]);
++ cur_seg_size += prev_frag_size;
+ }
+
+ return true;
+diff --git a/drivers/net/ethernet/hisilicon/hns3/Makefile b/drivers/net/ethernet/hisilicon/hns3/Makefile
+index 8e9293e57bfd5..e8af26da1fc1e 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/Makefile
++++ b/drivers/net/ethernet/hisilicon/hns3/Makefile
+@@ -15,15 +15,14 @@ hns3-objs = hns3_enet.o hns3_ethtool.o hns3_debugfs.o
+
+ hns3-$(CONFIG_HNS3_DCB) += hns3_dcbnl.o
+
+-obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o
++obj-$(CONFIG_HNS3_HCLGEVF) += hclgevf.o hclge-common.o
+
+-hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o \
+- hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
++hclge-common-objs += hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
+
+-obj-$(CONFIG_HNS3_HCLGE) += hclge.o
++hclgevf-objs = hns3vf/hclgevf_main.o hns3vf/hclgevf_mbx.o hns3vf/hclgevf_devlink.o hns3vf/hclgevf_regs.o
++
++obj-$(CONFIG_HNS3_HCLGE) += hclge.o hclge-common.o
+ hclge-objs = hns3pf/hclge_main.o hns3pf/hclge_mdio.o hns3pf/hclge_tm.o hns3pf/hclge_regs.o \
+ hns3pf/hclge_mbx.o hns3pf/hclge_err.o hns3pf/hclge_debugfs.o hns3pf/hclge_ptp.o hns3pf/hclge_devlink.o \
+- hns3_common/hclge_comm_cmd.o hns3_common/hclge_comm_rss.o hns3_common/hclge_comm_tqp_stats.o
+-
+
+ hclge-$(CONFIG_HNS3_DCB) += hns3pf/hclge_dcb.o
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
+index ea40b594dbac7..4ad4e8ab2f1f3 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_cmd.c
+@@ -48,6 +48,7 @@ void hclge_comm_cmd_reuse_desc(struct hclge_desc *desc, bool is_read)
+ else
+ desc->flag &= cpu_to_le16(~HCLGE_COMM_CMD_FLAG_WR);
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_cmd_reuse_desc);
+
+ static void hclge_comm_set_default_capability(struct hnae3_ae_dev *ae_dev,
+ bool is_pf)
+@@ -72,6 +73,7 @@ void hclge_comm_cmd_setup_basic_desc(struct hclge_desc *desc,
+ if (is_read)
+ desc->flag |= cpu_to_le16(HCLGE_COMM_CMD_FLAG_WR);
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_cmd_setup_basic_desc);
+
+ int hclge_comm_firmware_compat_config(struct hnae3_ae_dev *ae_dev,
+ struct hclge_comm_hw *hw, bool en)
+@@ -517,6 +519,7 @@ int hclge_comm_cmd_send(struct hclge_comm_hw *hw, struct hclge_desc *desc,
+
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_cmd_send);
+
+ static void hclge_comm_cmd_uninit_regs(struct hclge_comm_hw *hw)
+ {
+@@ -553,6 +556,7 @@ void hclge_comm_cmd_uninit(struct hnae3_ae_dev *ae_dev,
+ hclge_comm_free_cmd_desc(&cmdq->csq);
+ hclge_comm_free_cmd_desc(&cmdq->crq);
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_cmd_uninit);
+
+ int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw)
+ {
+@@ -591,6 +595,7 @@ int hclge_comm_cmd_queue_init(struct pci_dev *pdev, struct hclge_comm_hw *hw)
+ hclge_comm_free_cmd_desc(&hw->cmq.csq);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_cmd_queue_init);
+
+ void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw,
+ const struct hclge_comm_cmq_ops *ops)
+@@ -602,6 +607,7 @@ void hclge_comm_cmd_init_ops(struct hclge_comm_hw *hw,
+ cmdq->ops.trace_cmd_get = ops->trace_cmd_get;
+ }
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_cmd_init_ops);
+
+ int hclge_comm_cmd_init(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw,
+ u32 *fw_version, bool is_pf,
+@@ -672,3 +678,8 @@ int hclge_comm_cmd_init(struct hnae3_ae_dev *ae_dev, struct hclge_comm_hw *hw,
+
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_cmd_init);
++
++MODULE_LICENSE("GPL");
++MODULE_DESCRIPTION("HNS3: Hisilicon Ethernet PF/VF Common Library");
++MODULE_AUTHOR("Huawei Tech. Co., Ltd.");
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
+index b4ae2160aff4f..4e2bb6556b1ce 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_rss.c
+@@ -62,6 +62,7 @@ int hclge_comm_rss_init_cfg(struct hnae3_handle *nic,
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_rss_init_cfg);
+
+ void hclge_comm_get_rss_tc_info(u16 rss_size, u8 hw_tc_map, u16 *tc_offset,
+ u16 *tc_valid, u16 *tc_size)
+@@ -78,6 +79,7 @@ void hclge_comm_get_rss_tc_info(u16 rss_size, u8 hw_tc_map, u16 *tc_offset,
+ tc_offset[i] = (hw_tc_map & BIT(i)) ? rss_size * i : 0;
+ }
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_get_rss_tc_info);
+
+ int hclge_comm_set_rss_tc_mode(struct hclge_comm_hw *hw, u16 *tc_offset,
+ u16 *tc_valid, u16 *tc_size)
+@@ -113,6 +115,7 @@ int hclge_comm_set_rss_tc_mode(struct hclge_comm_hw *hw, u16 *tc_offset,
+
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_set_rss_tc_mode);
+
+ int hclge_comm_set_rss_hash_key(struct hclge_comm_rss_cfg *rss_cfg,
+ struct hclge_comm_hw *hw, const u8 *key,
+@@ -143,6 +146,7 @@ int hclge_comm_set_rss_hash_key(struct hclge_comm_rss_cfg *rss_cfg,
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_set_rss_hash_key);
+
+ int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev,
+ struct hclge_comm_hw *hw,
+@@ -185,11 +189,13 @@ int hclge_comm_set_rss_tuple(struct hnae3_ae_dev *ae_dev,
+ rss_cfg->rss_tuple_sets.ipv6_fragment_en = req->ipv6_fragment_en;
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_set_rss_tuple);
+
+ u32 hclge_comm_get_rss_key_size(struct hnae3_handle *handle)
+ {
+ return HCLGE_COMM_RSS_KEY_SIZE;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_get_rss_key_size);
+
+ int hclge_comm_parse_rss_hfunc(struct hclge_comm_rss_cfg *rss_cfg,
+ const u8 hfunc, u8 *hash_algo)
+@@ -217,6 +223,7 @@ void hclge_comm_rss_indir_init_cfg(struct hnae3_ae_dev *ae_dev,
+ for (i = 0; i < ae_dev->dev_specs.rss_ind_tbl_size; i++)
+ rss_cfg->rss_indirection_tbl[i] = i % rss_cfg->rss_size;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_rss_indir_init_cfg);
+
+ int hclge_comm_get_rss_tuple(struct hclge_comm_rss_cfg *rss_cfg, int flow_type,
+ u8 *tuple_sets)
+@@ -250,6 +257,7 @@ int hclge_comm_get_rss_tuple(struct hclge_comm_rss_cfg *rss_cfg, int flow_type,
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_get_rss_tuple);
+
+ static void
+ hclge_comm_append_rss_msb_info(struct hclge_comm_rss_ind_tbl_cmd *req,
+@@ -304,6 +312,7 @@ int hclge_comm_set_rss_indir_table(struct hnae3_ae_dev *ae_dev,
+ }
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_set_rss_indir_table);
+
+ int hclge_comm_set_rss_input_tuple(struct hclge_comm_hw *hw,
+ struct hclge_comm_rss_cfg *rss_cfg)
+@@ -332,6 +341,7 @@ int hclge_comm_set_rss_input_tuple(struct hclge_comm_hw *hw,
+ "failed to configure rss input, ret = %d.\n", ret);
+ return ret;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_set_rss_input_tuple);
+
+ void hclge_comm_get_rss_hash_info(struct hclge_comm_rss_cfg *rss_cfg, u8 *key,
+ u8 *hfunc)
+@@ -355,6 +365,7 @@ void hclge_comm_get_rss_hash_info(struct hclge_comm_rss_cfg *rss_cfg, u8 *key,
+ if (key)
+ memcpy(key, rss_cfg->rss_hash_key, HCLGE_COMM_RSS_KEY_SIZE);
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_get_rss_hash_info);
+
+ void hclge_comm_get_rss_indir_tbl(struct hclge_comm_rss_cfg *rss_cfg,
+ u32 *indir, u16 rss_ind_tbl_size)
+@@ -367,6 +378,7 @@ void hclge_comm_get_rss_indir_tbl(struct hclge_comm_rss_cfg *rss_cfg,
+ for (i = 0; i < rss_ind_tbl_size; i++)
+ indir[i] = rss_cfg->rss_indirection_tbl[i];
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_get_rss_indir_tbl);
+
+ int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc,
+ const u8 *key)
+@@ -408,6 +420,7 @@ int hclge_comm_set_rss_algo_key(struct hclge_comm_hw *hw, const u8 hfunc,
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_set_rss_algo_key);
+
+ static u8 hclge_comm_get_rss_hash_bits(struct ethtool_rxnfc *nfc)
+ {
+@@ -502,3 +515,4 @@ u64 hclge_comm_convert_rss_tuple(u8 tuple_sets)
+
+ return tuple_data;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_convert_rss_tuple);
+diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
+index 618f66d9586b3..2b31188ff5558 100644
+--- a/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
++++ b/drivers/net/ethernet/hisilicon/hns3/hns3_common/hclge_comm_tqp_stats.c
+@@ -26,6 +26,7 @@ u64 *hclge_comm_tqps_get_stats(struct hnae3_handle *handle, u64 *data)
+
+ return buff;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_stats);
+
+ int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle)
+ {
+@@ -33,6 +34,7 @@ int hclge_comm_tqps_get_sset_count(struct hnae3_handle *handle)
+
+ return kinfo->num_tqps * HCLGE_COMM_QUEUE_PAIR_SIZE;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_sset_count);
+
+ u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
+ {
+@@ -56,6 +58,7 @@ u8 *hclge_comm_tqps_get_strings(struct hnae3_handle *handle, u8 *data)
+
+ return buff;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_tqps_get_strings);
+
+ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle,
+ struct hclge_comm_hw *hw)
+@@ -99,6 +102,7 @@ int hclge_comm_tqps_update_stats(struct hnae3_handle *handle,
+
+ return 0;
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_tqps_update_stats);
+
+ void hclge_comm_reset_tqp_stats(struct hnae3_handle *handle)
+ {
+@@ -113,3 +117,4 @@ void hclge_comm_reset_tqp_stats(struct hnae3_handle *handle)
+ memset(&tqp->tqp_stats, 0, sizeof(tqp->tqp_stats));
+ }
+ }
++EXPORT_SYMBOL_GPL(hclge_comm_reset_tqp_stats);
+diff --git a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+index e3cab8e98f525..5412eff8ef233 100644
+--- a/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
++++ b/drivers/net/ethernet/intel/ice/ice_ethtool_fdir.c
+@@ -534,7 +534,7 @@ ice_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp,
+ *
+ * Returns the number of available flow director filters to this VSI
+ */
+-static int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
++int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi)
+ {
+ u16 vsi_num = ice_get_hw_vsi_num(hw, vsi->idx);
+ u16 num_guar;
+diff --git a/drivers/net/ethernet/intel/ice/ice_fdir.h b/drivers/net/ethernet/intel/ice/ice_fdir.h
+index 021ecbac7848f..ab5b118daa2da 100644
+--- a/drivers/net/ethernet/intel/ice/ice_fdir.h
++++ b/drivers/net/ethernet/intel/ice/ice_fdir.h
+@@ -207,6 +207,8 @@ struct ice_fdir_base_pkt {
+ const u8 *tun_pkt;
+ };
+
++struct ice_vsi;
++
+ int ice_alloc_fd_res_cntr(struct ice_hw *hw, u16 *cntr_id);
+ int ice_free_fd_res_cntr(struct ice_hw *hw, u16 cntr_id);
+ int ice_alloc_fd_guar_item(struct ice_hw *hw, u16 *cntr_id, u16 num_fltr);
+@@ -218,6 +220,7 @@ int
+ ice_fdir_get_gen_prgm_pkt(struct ice_hw *hw, struct ice_fdir_fltr *input,
+ u8 *pkt, bool frag, bool tun);
+ int ice_get_fdir_cnt_all(struct ice_hw *hw);
++int ice_fdir_num_avail_fltr(struct ice_hw *hw, struct ice_vsi *vsi);
+ bool ice_fdir_is_dup_fltr(struct ice_hw *hw, struct ice_fdir_fltr *input);
+ bool ice_fdir_has_frag(enum ice_fltr_ptype flow);
+ struct ice_fdir_fltr *
+diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c
+index 1191031b2a43d..ffd6c42bda1ed 100644
+--- a/drivers/net/ethernet/intel/ice/ice_switch.c
++++ b/drivers/net/ethernet/intel/ice/ice_switch.c
+@@ -2413,10 +2413,10 @@ ice_get_recp_frm_fw(struct ice_hw *hw, struct ice_sw_recipe *recps, u8 rid,
+ /* Propagate some data to the recipe database */
+ recps[idx].is_root = !!is_root;
+ recps[idx].priority = root_bufs.content.act_ctrl_fwd_priority;
+- recps[idx].need_pass_l2 = root_bufs.content.act_ctrl &
+- ICE_AQ_RECIPE_ACT_NEED_PASS_L2;
+- recps[idx].allow_pass_l2 = root_bufs.content.act_ctrl &
+- ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2;
++ recps[idx].need_pass_l2 = !!(root_bufs.content.act_ctrl &
++ ICE_AQ_RECIPE_ACT_NEED_PASS_L2);
++ recps[idx].allow_pass_l2 = !!(root_bufs.content.act_ctrl &
++ ICE_AQ_RECIPE_ACT_ALLOW_PASS_L2);
+ bitmap_zero(recps[idx].res_idxs, ICE_MAX_FV_WORDS);
+ if (root_bufs.content.result_indx & ICE_AQ_RECIPE_RESULT_EN) {
+ recps[idx].chain_idx = root_bufs.content.result_indx &
+diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+index 8e4ff3af86c68..b4feb09276870 100644
+--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
++++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.c
+@@ -536,6 +536,8 @@ static void ice_vc_fdir_reset_cnt_all(struct ice_vf_fdir *fdir)
+ fdir->fdir_fltr_cnt[flow][0] = 0;
+ fdir->fdir_fltr_cnt[flow][1] = 0;
+ }
++
++ fdir->fdir_fltr_cnt_total = 0;
+ }
+
+ /**
+@@ -1560,6 +1562,7 @@ ice_vc_add_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
+ resp->status = status;
+ resp->flow_id = conf->flow_id;
+ vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]++;
++ vf->fdir.fdir_fltr_cnt_total++;
+
+ ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret,
+ (u8 *)resp, len);
+@@ -1624,6 +1627,7 @@ ice_vc_del_fdir_fltr_post(struct ice_vf *vf, struct ice_vf_fdir_ctx *ctx,
+ resp->status = status;
+ ice_vc_fdir_remove_entry(vf, conf, conf->flow_id);
+ vf->fdir.fdir_fltr_cnt[conf->input.flow_type][is_tun]--;
++ vf->fdir.fdir_fltr_cnt_total--;
+
+ ret = ice_vc_send_msg_to_vf(vf, ctx->v_opcode, v_ret,
+ (u8 *)resp, len);
+@@ -1790,6 +1794,7 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
+ struct virtchnl_fdir_add *stat = NULL;
+ struct virtchnl_fdir_fltr_conf *conf;
+ enum virtchnl_status_code v_ret;
++ struct ice_vsi *vf_vsi;
+ struct device *dev;
+ struct ice_pf *pf;
+ int is_tun = 0;
+@@ -1798,6 +1803,17 @@ int ice_vc_add_fdir_fltr(struct ice_vf *vf, u8 *msg)
+
+ pf = vf->pf;
+ dev = ice_pf_to_dev(pf);
++ vf_vsi = ice_get_vf_vsi(vf);
++
++#define ICE_VF_MAX_FDIR_FILTERS 128
++ if (!ice_fdir_num_avail_fltr(&pf->hw, vf_vsi) ||
++ vf->fdir.fdir_fltr_cnt_total >= ICE_VF_MAX_FDIR_FILTERS) {
++ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
++ dev_err(dev, "Max number of FDIR filters for VF %d is reached\n",
++ vf->vf_id);
++ goto err_exit;
++ }
++
+ ret = ice_vc_fdir_param_check(vf, fltr->vsi_id);
+ if (ret) {
+ v_ret = VIRTCHNL_STATUS_ERR_PARAM;
+diff --git a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
+index c5bcc8d7481ca..ac6dcab454b49 100644
+--- a/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
++++ b/drivers/net/ethernet/intel/ice/ice_virtchnl_fdir.h
+@@ -29,6 +29,7 @@ struct ice_vf_fdir_ctx {
+ struct ice_vf_fdir {
+ u16 fdir_fltr_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX];
+ int prof_entry_cnt[ICE_FLTR_PTYPE_MAX][ICE_FD_HW_SEG_MAX];
++ u16 fdir_fltr_cnt_total;
+ struct ice_fd_hw_prof **fdir_prof;
+
+ struct idr fdir_rule_idr;
+diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+index c84ce54a84a00..c11bb0f0b8c47 100644
+--- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c
++++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c
+@@ -4198,8 +4198,6 @@ static int mtk_free_dev(struct mtk_eth *eth)
+ metadata_dst_free(eth->dsa_meta[i]);
+ }
+
+- free_netdev(eth->dummy_dev);
+-
+ return 0;
+ }
+
+@@ -5048,6 +5046,7 @@ static void mtk_remove(struct platform_device *pdev)
+ netif_napi_del(ð->tx_napi);
+ netif_napi_del(ð->rx_napi);
+ mtk_cleanup(eth);
++ free_netdev(eth->dummy_dev);
+ mtk_mdio_cleanup(eth);
+ }
+
+diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+index 4b713832fdd55..f5c0a4214c4e5 100644
+--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_atcam.c
+@@ -391,7 +391,8 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
+ if (err)
+ return err;
+
+- lkey_id = aregion->ops->lkey_id_get(aregion, aentry->enc_key, erp_id);
++ lkey_id = aregion->ops->lkey_id_get(aregion, aentry->ht_key.enc_key,
++ erp_id);
+ if (IS_ERR(lkey_id))
+ return PTR_ERR(lkey_id);
+ aentry->lkey_id = lkey_id;
+@@ -399,7 +400,7 @@ mlxsw_sp_acl_atcam_region_entry_insert(struct mlxsw_sp *mlxsw_sp,
+ kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
+ mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_WRITE,
+ priority, region->tcam_region_info,
+- aentry->enc_key, erp_id,
++ aentry->ht_key.enc_key, erp_id,
+ aentry->delta_info.start,
+ aentry->delta_info.mask,
+ aentry->delta_info.value,
+@@ -428,7 +429,7 @@ mlxsw_sp_acl_atcam_region_entry_remove(struct mlxsw_sp *mlxsw_sp,
+
+ mlxsw_reg_ptce3_pack(ptce3_pl, false, MLXSW_REG_PTCE3_OP_WRITE_WRITE, 0,
+ region->tcam_region_info,
+- aentry->enc_key, erp_id,
++ aentry->ht_key.enc_key, erp_id,
+ aentry->delta_info.start,
+ aentry->delta_info.mask,
+ aentry->delta_info.value,
+@@ -457,7 +458,7 @@ mlxsw_sp_acl_atcam_region_entry_action_replace(struct mlxsw_sp *mlxsw_sp,
+ kvdl_index = mlxsw_afa_block_first_kvdl_index(rulei->act_block);
+ mlxsw_reg_ptce3_pack(ptce3_pl, true, MLXSW_REG_PTCE3_OP_WRITE_UPDATE,
+ priority, region->tcam_region_info,
+- aentry->enc_key, erp_id,
++ aentry->ht_key.enc_key, erp_id,
+ aentry->delta_info.start,
+ aentry->delta_info.mask,
+ aentry->delta_info.value,
+@@ -480,15 +481,13 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+ int err;
+
+ mlxsw_afk_encode(afk, region->key_info, &rulei->values,
+- aentry->ht_key.full_enc_key, mask);
++ aentry->ht_key.enc_key, mask);
+
+ erp_mask = mlxsw_sp_acl_erp_mask_get(aregion, mask, false);
+ if (IS_ERR(erp_mask))
+ return PTR_ERR(erp_mask);
+ aentry->erp_mask = erp_mask;
+ aentry->ht_key.erp_id = mlxsw_sp_acl_erp_mask_erp_id(erp_mask);
+- memcpy(aentry->enc_key, aentry->ht_key.full_enc_key,
+- sizeof(aentry->enc_key));
+
+ /* Compute all needed delta information and clear the delta bits
+ * from the encrypted key.
+@@ -497,9 +496,8 @@ __mlxsw_sp_acl_atcam_entry_add(struct mlxsw_sp *mlxsw_sp,
+ aentry->delta_info.start = mlxsw_sp_acl_erp_delta_start(delta);
+ aentry->delta_info.mask = mlxsw_sp_acl_erp_delta_mask(delta);
+ aentry->delta_info.value =
+- mlxsw_sp_acl_erp_delta_value(delta,
+- aentry->ht_key.full_enc_key);
+- mlxsw_sp_acl_erp_delta_clear(delta, aentry->enc_key);
++ mlxsw_sp_acl_erp_delta_value(delta, aentry->ht_key.enc_key);
++ mlxsw_sp_acl_erp_delta_clear(delta, aentry->ht_key.enc_key);
+
+ /* Add rule to the list of A-TCAM rules, assuming this
+ * rule is intended to A-TCAM. In case this rule does
+diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+index 95f63fcf4ba1f..a54eedb69a3f5 100644
+--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_bloom_filter.c
+@@ -249,7 +249,7 @@ __mlxsw_sp_acl_bf_key_encode(struct mlxsw_sp_acl_atcam_region *aregion,
+ memcpy(chunk + pad_bytes, &erp_region_id,
+ sizeof(erp_region_id));
+ memcpy(chunk + key_offset,
+- &aentry->enc_key[chunk_key_offsets[chunk_index]],
++ &aentry->ht_key.enc_key[chunk_key_offsets[chunk_index]],
+ chunk_key_len);
+ chunk += chunk_len;
+ }
+diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+index d231f4d2888be..9eee229303cce 100644
+--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_erp.c
+@@ -1217,18 +1217,6 @@ static bool mlxsw_sp_acl_erp_delta_check(void *priv, const void *parent_obj,
+ return err ? false : true;
+ }
+
+-static int mlxsw_sp_acl_erp_hints_obj_cmp(const void *obj1, const void *obj2)
+-{
+- const struct mlxsw_sp_acl_erp_key *key1 = obj1;
+- const struct mlxsw_sp_acl_erp_key *key2 = obj2;
+-
+- /* For hints purposes, two objects are considered equal
+- * in case the masks are the same. Does not matter what
+- * the "ctcam" value is.
+- */
+- return memcmp(key1->mask, key2->mask, sizeof(key1->mask));
+-}
+-
+ static void *mlxsw_sp_acl_erp_delta_create(void *priv, void *parent_obj,
+ void *obj)
+ {
+@@ -1308,7 +1296,6 @@ static void mlxsw_sp_acl_erp_root_destroy(void *priv, void *root_priv)
+ static const struct objagg_ops mlxsw_sp_acl_erp_objagg_ops = {
+ .obj_size = sizeof(struct mlxsw_sp_acl_erp_key),
+ .delta_check = mlxsw_sp_acl_erp_delta_check,
+- .hints_obj_cmp = mlxsw_sp_acl_erp_hints_obj_cmp,
+ .delta_create = mlxsw_sp_acl_erp_delta_create,
+ .delta_destroy = mlxsw_sp_acl_erp_delta_destroy,
+ .root_create = mlxsw_sp_acl_erp_root_create,
+diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+index 79a1d86065125..010204f73ea46 100644
+--- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
++++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_acl_tcam.h
+@@ -167,9 +167,9 @@ struct mlxsw_sp_acl_atcam_region {
+ };
+
+ struct mlxsw_sp_acl_atcam_entry_ht_key {
+- char full_enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded
+- * key.
+- */
++ char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key, minus
++ * delta bits.
++ */
+ u8 erp_id;
+ };
+
+@@ -181,9 +181,6 @@ struct mlxsw_sp_acl_atcam_entry {
+ struct rhash_head ht_node;
+ struct list_head list; /* Member in entries_list */
+ struct mlxsw_sp_acl_atcam_entry_ht_key ht_key;
+- char enc_key[MLXSW_REG_PTCEX_FLEX_KEY_BLOCKS_LEN]; /* Encoded key,
+- * minus delta bits.
+- */
+ struct {
+ u16 start;
+ u8 mask;
+diff --git a/drivers/net/ethernet/microsoft/mana/mana_en.c b/drivers/net/ethernet/microsoft/mana/mana_en.c
+index 608ad31a97022..ad7ae7ba2b8fc 100644
+--- a/drivers/net/ethernet/microsoft/mana/mana_en.c
++++ b/drivers/net/ethernet/microsoft/mana/mana_en.c
+@@ -2950,3 +2950,22 @@ void mana_remove(struct gdma_dev *gd, bool suspending)
+ gd->gdma_context = NULL;
+ kfree(ac);
+ }
++
++struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index)
++{
++ struct net_device *ndev;
++
++ RCU_LOCKDEP_WARN(!rcu_read_lock_held(),
++ "Taking primary netdev without holding the RCU read lock");
++ if (port_index >= ac->num_ports)
++ return NULL;
++
++ /* When mana is used in netvsc, the upper netdevice should be returned. */
++ if (ac->ports[port_index]->flags & IFF_SLAVE)
++ ndev = netdev_master_upper_dev_get_rcu(ac->ports[port_index]);
++ else
++ ndev = ac->ports[port_index];
++
++ return ndev;
++}
++EXPORT_SYMBOL_NS(mana_get_primary_netdev_rcu, NET_MANA);
+diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+index b25774d691957..8e2049ed60159 100644
+--- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
++++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c
+@@ -982,7 +982,7 @@ static void dwmac4_set_mac_loopback(void __iomem *ioaddr, bool enable)
+ }
+
+ static void dwmac4_update_vlan_hash(struct mac_device_info *hw, u32 hash,
+- __le16 perfect_match, bool is_double)
++ u16 perfect_match, bool is_double)
+ {
+ void __iomem *ioaddr = hw->pcsr;
+ u32 value;
+diff --git a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+index f8e7775bb6336..9a705a5a3a1ad 100644
+--- a/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
++++ b/drivers/net/ethernet/stmicro/stmmac/dwxgmac2_core.c
+@@ -615,7 +615,7 @@ static int dwxgmac2_rss_configure(struct mac_device_info *hw,
+ }
+
+ static void dwxgmac2_update_vlan_hash(struct mac_device_info *hw, u32 hash,
+- __le16 perfect_match, bool is_double)
++ u16 perfect_match, bool is_double)
+ {
+ void __iomem *ioaddr = hw->pcsr;
+
+diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h
+index 90384db228b5c..a318c84ddb8ac 100644
+--- a/drivers/net/ethernet/stmicro/stmmac/hwif.h
++++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h
+@@ -394,7 +394,7 @@ struct stmmac_ops {
+ struct stmmac_rss *cfg, u32 num_rxq);
+ /* VLAN */
+ void (*update_vlan_hash)(struct mac_device_info *hw, u32 hash,
+- __le16 perfect_match, bool is_double);
++ u16 perfect_match, bool is_double);
+ void (*enable_vlan)(struct mac_device_info *hw, u32 type);
+ void (*rx_hw_vlan)(struct mac_device_info *hw, struct dma_desc *rx_desc,
+ struct sk_buff *skb);
+diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+index c58782c41417a..33e2bd5a351ca 100644
+--- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
++++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c
+@@ -6640,7 +6640,7 @@ static u32 stmmac_vid_crc32_le(__le16 vid_le)
+ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
+ {
+ u32 crc, hash = 0;
+- __le16 pmatch = 0;
++ u16 pmatch = 0;
+ int count = 0;
+ u16 vid = 0;
+
+@@ -6655,7 +6655,7 @@ static int stmmac_vlan_update(struct stmmac_priv *priv, bool is_double)
+ if (count > 2) /* VID = 0 always passes filter */
+ return -EOPNOTSUPP;
+
+- pmatch = cpu_to_le16(vid);
++ pmatch = vid;
+ hash = 0;
+ }
+
+diff --git a/drivers/net/netconsole.c b/drivers/net/netconsole.c
+index d7070dd4fe736..aa66c923790ff 100644
+--- a/drivers/net/netconsole.c
++++ b/drivers/net/netconsole.c
+@@ -974,6 +974,7 @@ static int netconsole_netdev_event(struct notifier_block *this,
+ /* rtnl_lock already held
+ * we might sleep in __netpoll_cleanup()
+ */
++ nt->enabled = false;
+ spin_unlock_irqrestore(&target_list_lock, flags);
+
+ __netpoll_cleanup(&nt->np);
+@@ -981,7 +982,6 @@ static int netconsole_netdev_event(struct notifier_block *this,
+ spin_lock_irqsave(&target_list_lock, flags);
+ netdev_put(nt->np.dev, &nt->np.dev_tracker);
+ nt->np.dev = NULL;
+- nt->enabled = false;
+ stopped = true;
+ netconsole_target_put(nt);
+ goto restart;
+diff --git a/drivers/net/pse-pd/pse_core.c b/drivers/net/pse-pd/pse_core.c
+index 795ab264eaf27..513cd7f859337 100644
+--- a/drivers/net/pse-pd/pse_core.c
++++ b/drivers/net/pse-pd/pse_core.c
+@@ -719,13 +719,13 @@ int pse_ethtool_set_config(struct pse_control *psec,
+ {
+ int err = 0;
+
+- if (pse_has_c33(psec)) {
++ if (pse_has_c33(psec) && config->c33_admin_control) {
+ err = pse_ethtool_c33_set_config(psec, config);
+ if (err)
+ return err;
+ }
+
+- if (pse_has_podl(psec))
++ if (pse_has_podl(psec) && config->podl_admin_control)
+ err = pse_ethtool_podl_set_config(psec, config);
+
+ return err;
+diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c
+index ea10db9a09fa2..5161e7efda2cb 100644
+--- a/drivers/net/virtio_net.c
++++ b/drivers/net/virtio_net.c
+@@ -2313,7 +2313,7 @@ static int virtnet_receive(struct receive_queue *rq, int budget,
+ return packets;
+ }
+
+-static void virtnet_poll_cleantx(struct receive_queue *rq)
++static void virtnet_poll_cleantx(struct receive_queue *rq, int budget)
+ {
+ struct virtnet_info *vi = rq->vq->vdev->priv;
+ unsigned int index = vq2rxq(rq->vq);
+@@ -2331,7 +2331,7 @@ static void virtnet_poll_cleantx(struct receive_queue *rq)
+
+ do {
+ virtqueue_disable_cb(sq->vq);
+- free_old_xmit(sq, true);
++ free_old_xmit(sq, !!budget);
+ } while (unlikely(!virtqueue_enable_cb_delayed(sq->vq)));
+
+ if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
+@@ -2375,7 +2375,7 @@ static int virtnet_poll(struct napi_struct *napi, int budget)
+ unsigned int xdp_xmit = 0;
+ bool napi_complete;
+
+- virtnet_poll_cleantx(rq);
++ virtnet_poll_cleantx(rq, budget);
+
+ received = virtnet_receive(rq, budget, &xdp_xmit);
+ rq->packets_in_napi += received;
+@@ -2489,7 +2489,7 @@ static int virtnet_poll_tx(struct napi_struct *napi, int budget)
+ txq = netdev_get_tx_queue(vi->dev, index);
+ __netif_tx_lock(txq, raw_smp_processor_id());
+ virtqueue_disable_cb(sq->vq);
+- free_old_xmit(sq, true);
++ free_old_xmit(sq, !!budget);
+
+ if (sq->vq->num_free >= 2 + MAX_SKB_FRAGS) {
+ if (netif_tx_queue_stopped(txq)) {
+diff --git a/drivers/net/wireless/ath/ath11k/ce.h b/drivers/net/wireless/ath/ath11k/ce.h
+index 69946fc700777..bcde2fcf02cf7 100644
+--- a/drivers/net/wireless/ath/ath11k/ce.h
++++ b/drivers/net/wireless/ath/ath11k/ce.h
+@@ -1,7 +1,7 @@
+ /* SPDX-License-Identifier: BSD-3-Clause-Clear */
+ /*
+ * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
+- * Copyright (c) 2022 Qualcomm Innovation Center, Inc. All rights reserved.
++ * Copyright (c) 2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+ #ifndef ATH11K_CE_H
+@@ -146,7 +146,7 @@ struct ath11k_ce_ring {
+ /* Host address space */
+ void *base_addr_owner_space_unaligned;
+ /* CE address space */
+- u32 base_addr_ce_space_unaligned;
++ dma_addr_t base_addr_ce_space_unaligned;
+
+ /* Actual start of descriptors.
+ * Aligned to descriptor-size boundary.
+@@ -156,7 +156,7 @@ struct ath11k_ce_ring {
+ void *base_addr_owner_space;
+
+ /* CE address space */
+- u32 base_addr_ce_space;
++ dma_addr_t base_addr_ce_space;
+
+ /* HAL ring id */
+ u32 hal_ring_id;
+diff --git a/drivers/net/wireless/ath/ath11k/core.c b/drivers/net/wireless/ath/ath11k/core.c
+index b82e8fb285413..47554c3619633 100644
+--- a/drivers/net/wireless/ath/ath11k/core.c
++++ b/drivers/net/wireless/ath/ath11k/core.c
+@@ -1009,6 +1009,16 @@ int ath11k_core_resume(struct ath11k_base *ab)
+ return -ETIMEDOUT;
+ }
+
++ if (ab->hw_params.current_cc_support &&
++ ar->alpha2[0] != 0 && ar->alpha2[1] != 0) {
++ ret = ath11k_reg_set_cc(ar);
++ if (ret) {
++ ath11k_warn(ab, "failed to set country code during resume: %d\n",
++ ret);
++ return ret;
++ }
++ }
++
+ ret = ath11k_dp_rx_pktlog_start(ab);
+ if (ret)
+ ath11k_warn(ab, "failed to start rx pktlog during resume: %d\n",
+@@ -1978,23 +1988,20 @@ static void ath11k_update_11d(struct work_struct *work)
+ struct ath11k_base *ab = container_of(work, struct ath11k_base, update_11d_work);
+ struct ath11k *ar;
+ struct ath11k_pdev *pdev;
+- struct wmi_set_current_country_params set_current_param = {};
+ int ret, i;
+
+- spin_lock_bh(&ab->base_lock);
+- memcpy(&set_current_param.alpha2, &ab->new_alpha2, 2);
+- spin_unlock_bh(&ab->base_lock);
+-
+- ath11k_dbg(ab, ATH11K_DBG_WMI, "update 11d new cc %c%c\n",
+- set_current_param.alpha2[0],
+- set_current_param.alpha2[1]);
+-
+ for (i = 0; i < ab->num_radios; i++) {
+ pdev = &ab->pdevs[i];
+ ar = pdev->ar;
+
+- memcpy(&ar->alpha2, &set_current_param.alpha2, 2);
+- ret = ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
++ spin_lock_bh(&ab->base_lock);
++ memcpy(&ar->alpha2, &ab->new_alpha2, 2);
++ spin_unlock_bh(&ab->base_lock);
++
++ ath11k_dbg(ab, ATH11K_DBG_WMI, "update 11d new cc %c%c for pdev %d\n",
++ ar->alpha2[0], ar->alpha2[1], i);
++
++ ret = ath11k_reg_set_cc(ar);
+ if (ret)
+ ath11k_warn(ar->ab,
+ "pdev id %d failed set current country code: %d\n",
+diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.c b/drivers/net/wireless/ath/ath11k/dp_rx.c
+index afd481f5858f0..aabde24d87632 100644
+--- a/drivers/net/wireless/ath/ath11k/dp_rx.c
++++ b/drivers/net/wireless/ath/ath11k/dp_rx.c
+@@ -1877,8 +1877,7 @@ static void ath11k_dp_rx_h_csum_offload(struct ath11k *ar, struct sk_buff *msdu)
+ CHECKSUM_NONE : CHECKSUM_UNNECESSARY;
+ }
+
+-static int ath11k_dp_rx_crypto_mic_len(struct ath11k *ar,
+- enum hal_encrypt_type enctype)
++int ath11k_dp_rx_crypto_mic_len(struct ath11k *ar, enum hal_encrypt_type enctype)
+ {
+ switch (enctype) {
+ case HAL_ENCRYPT_TYPE_OPEN:
+diff --git a/drivers/net/wireless/ath/ath11k/dp_rx.h b/drivers/net/wireless/ath/ath11k/dp_rx.h
+index 623da3bf9dc81..c322e30caa968 100644
+--- a/drivers/net/wireless/ath/ath11k/dp_rx.h
++++ b/drivers/net/wireless/ath/ath11k/dp_rx.h
+@@ -1,6 +1,7 @@
+ /* SPDX-License-Identifier: BSD-3-Clause-Clear */
+ /*
+ * Copyright (c) 2018-2019 The Linux Foundation. All rights reserved.
++ * Copyright (c) 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+ #ifndef ATH11K_DP_RX_H
+ #define ATH11K_DP_RX_H
+@@ -95,4 +96,6 @@ int ath11k_peer_rx_frag_setup(struct ath11k *ar, const u8 *peer_mac, int vdev_id
+ int ath11k_dp_rx_pktlog_start(struct ath11k_base *ab);
+ int ath11k_dp_rx_pktlog_stop(struct ath11k_base *ab, bool stop_timer);
+
++int ath11k_dp_rx_crypto_mic_len(struct ath11k *ar, enum hal_encrypt_type enctype);
++
+ #endif /* ATH11K_DP_RX_H */
+diff --git a/drivers/net/wireless/ath/ath11k/mac.c b/drivers/net/wireless/ath/ath11k/mac.c
+index 9b96dbb21d833..eaa53bc39ab2c 100644
+--- a/drivers/net/wireless/ath/ath11k/mac.c
++++ b/drivers/net/wireless/ath/ath11k/mac.c
+@@ -4229,6 +4229,7 @@ static int ath11k_install_key(struct ath11k_vif *arvif,
+
+ switch (key->cipher) {
+ case WLAN_CIPHER_SUITE_CCMP:
++ case WLAN_CIPHER_SUITE_CCMP_256:
+ arg.key_cipher = WMI_CIPHER_AES_CCM;
+ /* TODO: Re-check if flag is valid */
+ key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT;
+@@ -4238,12 +4239,10 @@ static int ath11k_install_key(struct ath11k_vif *arvif,
+ arg.key_txmic_len = 8;
+ arg.key_rxmic_len = 8;
+ break;
+- case WLAN_CIPHER_SUITE_CCMP_256:
+- arg.key_cipher = WMI_CIPHER_AES_CCM;
+- break;
+ case WLAN_CIPHER_SUITE_GCMP:
+ case WLAN_CIPHER_SUITE_GCMP_256:
+ arg.key_cipher = WMI_CIPHER_AES_GCM;
++ key->flags |= IEEE80211_KEY_FLAG_GENERATE_IV_MGMT;
+ break;
+ default:
+ ath11k_warn(ar->ab, "cipher %d is not supported\n", key->cipher);
+@@ -5903,7 +5902,10 @@ static int ath11k_mac_mgmt_tx_wmi(struct ath11k *ar, struct ath11k_vif *arvif,
+ {
+ struct ath11k_base *ab = ar->ab;
+ struct ieee80211_hdr *hdr = (struct ieee80211_hdr *)skb->data;
++ struct ath11k_skb_cb *skb_cb = ATH11K_SKB_CB(skb);
+ struct ieee80211_tx_info *info;
++ enum hal_encrypt_type enctype;
++ unsigned int mic_len;
+ dma_addr_t paddr;
+ int buf_id;
+ int ret;
+@@ -5927,7 +5929,12 @@ static int ath11k_mac_mgmt_tx_wmi(struct ath11k *ar, struct ath11k_vif *arvif,
+ ieee80211_is_deauth(hdr->frame_control) ||
+ ieee80211_is_disassoc(hdr->frame_control)) &&
+ ieee80211_has_protected(hdr->frame_control)) {
+- skb_put(skb, IEEE80211_CCMP_MIC_LEN);
++ if (!(skb_cb->flags & ATH11K_SKB_CIPHER_SET))
++ ath11k_warn(ab, "WMI management tx frame without ATH11K_SKB_CIPHER_SET");
++
++ enctype = ath11k_dp_tx_get_encrypt_type(skb_cb->cipher);
++ mic_len = ath11k_dp_rx_crypto_mic_len(ar, enctype);
++ skb_put(skb, mic_len);
+ }
+ }
+
+@@ -8851,12 +8858,8 @@ ath11k_mac_op_reconfig_complete(struct ieee80211_hw *hw,
+ ieee80211_wake_queues(ar->hw);
+
+ if (ar->ab->hw_params.current_cc_support &&
+- ar->alpha2[0] != 0 && ar->alpha2[1] != 0) {
+- struct wmi_set_current_country_params set_current_param = {};
+-
+- memcpy(&set_current_param.alpha2, ar->alpha2, 2);
+- ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
+- }
++ ar->alpha2[0] != 0 && ar->alpha2[1] != 0)
++ ath11k_reg_set_cc(ar);
+
+ if (ab->is_reset) {
+ recovery_count = atomic_inc_return(&ab->recovery_count);
+@@ -10325,11 +10328,8 @@ static int __ath11k_mac_register(struct ath11k *ar)
+ }
+
+ if (ab->hw_params.current_cc_support && ab->new_alpha2[0]) {
+- struct wmi_set_current_country_params set_current_param = {};
+-
+- memcpy(&set_current_param.alpha2, ab->new_alpha2, 2);
+ memcpy(&ar->alpha2, ab->new_alpha2, 2);
+- ret = ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
++ ret = ath11k_reg_set_cc(ar);
+ if (ret)
+ ath11k_warn(ar->ab,
+ "failed set cc code for mac register: %d\n", ret);
+diff --git a/drivers/net/wireless/ath/ath11k/reg.c b/drivers/net/wireless/ath/ath11k/reg.c
+index 737fcd450d4bd..39232b8f52bae 100644
+--- a/drivers/net/wireless/ath/ath11k/reg.c
++++ b/drivers/net/wireless/ath/ath11k/reg.c
+@@ -49,7 +49,6 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
+ {
+ struct ieee80211_hw *hw = wiphy_to_ieee80211_hw(wiphy);
+ struct wmi_init_country_params init_country_param;
+- struct wmi_set_current_country_params set_current_param = {};
+ struct ath11k *ar = hw->priv;
+ int ret;
+
+@@ -83,9 +82,8 @@ ath11k_reg_notifier(struct wiphy *wiphy, struct regulatory_request *request)
+ * reg info
+ */
+ if (ar->ab->hw_params.current_cc_support) {
+- memcpy(&set_current_param.alpha2, request->alpha2, 2);
+- memcpy(&ar->alpha2, &set_current_param.alpha2, 2);
+- ret = ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
++ memcpy(&ar->alpha2, request->alpha2, 2);
++ ret = ath11k_reg_set_cc(ar);
+ if (ret)
+ ath11k_warn(ar->ab,
+ "failed set current country code: %d\n", ret);
+@@ -1017,3 +1015,11 @@ void ath11k_reg_free(struct ath11k_base *ab)
+ kfree(ab->new_regd[i]);
+ }
+ }
++
++int ath11k_reg_set_cc(struct ath11k *ar)
++{
++ struct wmi_set_current_country_params set_current_param = {};
++
++ memcpy(&set_current_param.alpha2, ar->alpha2, 2);
++ return ath11k_wmi_send_set_current_country_cmd(ar, &set_current_param);
++}
+diff --git a/drivers/net/wireless/ath/ath11k/reg.h b/drivers/net/wireless/ath/ath11k/reg.h
+index 64edb794260ab..263ea90619483 100644
+--- a/drivers/net/wireless/ath/ath11k/reg.h
++++ b/drivers/net/wireless/ath/ath11k/reg.h
+@@ -1,7 +1,7 @@
+ /* SPDX-License-Identifier: BSD-3-Clause-Clear */
+ /*
+ * Copyright (c) 2019 The Linux Foundation. All rights reserved.
+- * Copyright (c) 2022-2023 Qualcomm Innovation Center, Inc. All rights reserved.
++ * Copyright (c) 2022-2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+ #ifndef ATH11K_REG_H
+@@ -45,5 +45,5 @@ ath11k_reg_ap_pwr_convert(enum ieee80211_ap_reg_power power_type);
+ int ath11k_reg_handle_chan_list(struct ath11k_base *ab,
+ struct cur_regulatory_info *reg_info,
+ enum ieee80211_ap_reg_power power_type);
+-
++int ath11k_reg_set_cc(struct ath11k *ar);
+ #endif
+diff --git a/drivers/net/wireless/ath/ath12k/acpi.c b/drivers/net/wireless/ath/ath12k/acpi.c
+index 443ba12e01f37..0555d35aab477 100644
+--- a/drivers/net/wireless/ath/ath12k/acpi.c
++++ b/drivers/net/wireless/ath/ath12k/acpi.c
+@@ -391,4 +391,6 @@ void ath12k_acpi_stop(struct ath12k_base *ab)
+ acpi_remove_notify_handler(ACPI_HANDLE(ab->dev),
+ ACPI_DEVICE_NOTIFY,
+ ath12k_acpi_dsm_notify);
++
++ memset(&ab->acpi, 0, sizeof(ab->acpi));
+ }
+diff --git a/drivers/net/wireless/ath/ath12k/ce.h b/drivers/net/wireless/ath/ath12k/ce.h
+index 79af3b6159f1c..857bc5f9e946a 100644
+--- a/drivers/net/wireless/ath/ath12k/ce.h
++++ b/drivers/net/wireless/ath/ath12k/ce.h
+@@ -1,7 +1,7 @@
+ /* SPDX-License-Identifier: BSD-3-Clause-Clear */
+ /*
+ * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
+- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
++ * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+
+ #ifndef ATH12K_CE_H
+@@ -119,7 +119,7 @@ struct ath12k_ce_ring {
+ /* Host address space */
+ void *base_addr_owner_space_unaligned;
+ /* CE address space */
+- u32 base_addr_ce_space_unaligned;
++ dma_addr_t base_addr_ce_space_unaligned;
+
+ /* Actual start of descriptors.
+ * Aligned to descriptor-size boundary.
+@@ -129,7 +129,7 @@ struct ath12k_ce_ring {
+ void *base_addr_owner_space;
+
+ /* CE address space */
+- u32 base_addr_ce_space;
++ dma_addr_t base_addr_ce_space;
+
+ /* HAL ring id */
+ u32 hal_ring_id;
+diff --git a/drivers/net/wireless/ath/ath12k/core.c b/drivers/net/wireless/ath/ath12k/core.c
+index 6663f4e1792de..52969a1bb5a56 100644
+--- a/drivers/net/wireless/ath/ath12k/core.c
++++ b/drivers/net/wireless/ath/ath12k/core.c
+@@ -50,19 +50,16 @@ int ath12k_core_suspend(struct ath12k_base *ab)
+ if (!ab->hw_params->supports_suspend)
+ return -EOPNOTSUPP;
+
+- rcu_read_lock();
+ for (i = 0; i < ab->num_radios; i++) {
+- ar = ath12k_mac_get_ar_by_pdev_id(ab, i);
++ ar = ab->pdevs[i].ar;
+ if (!ar)
+ continue;
+ ret = ath12k_mac_wait_tx_complete(ar);
+ if (ret) {
+ ath12k_warn(ab, "failed to wait tx complete: %d\n", ret);
+- rcu_read_unlock();
+ return ret;
+ }
+ }
+- rcu_read_unlock();
+
+ /* PM framework skips suspend_late/resume_early callbacks
+ * if other devices report errors in their suspend callbacks.
+@@ -86,6 +83,8 @@ int ath12k_core_suspend_late(struct ath12k_base *ab)
+ if (!ab->hw_params->supports_suspend)
+ return -EOPNOTSUPP;
+
++ ath12k_acpi_stop(ab);
++
+ ath12k_hif_irq_disable(ab);
+ ath12k_hif_ce_irq_disable(ab);
+
+diff --git a/drivers/net/wireless/ath/ath12k/dp.c b/drivers/net/wireless/ath/ath12k/dp.c
+index 7843c76a82c17..90476f38e8d46 100644
+--- a/drivers/net/wireless/ath/ath12k/dp.c
++++ b/drivers/net/wireless/ath/ath12k/dp.c
+@@ -132,7 +132,9 @@ static int ath12k_dp_srng_find_ring_in_mask(int ring_num, const u8 *grp_mask)
+ static int ath12k_dp_srng_calculate_msi_group(struct ath12k_base *ab,
+ enum hal_ring_type type, int ring_num)
+ {
++ const struct ath12k_hal_tcl_to_wbm_rbm_map *map;
+ const u8 *grp_mask;
++ int i;
+
+ switch (type) {
+ case HAL_WBM2SW_RELEASE:
+@@ -140,6 +142,14 @@ static int ath12k_dp_srng_calculate_msi_group(struct ath12k_base *ab,
+ grp_mask = &ab->hw_params->ring_mask->rx_wbm_rel[0];
+ ring_num = 0;
+ } else {
++ map = ab->hw_params->hal_ops->tcl_to_wbm_rbm_map;
++ for (i = 0; i < ab->hw_params->max_tx_ring; i++) {
++ if (ring_num == map[i].wbm_ring_num) {
++ ring_num = i;
++ break;
++ }
++ }
++
+ grp_mask = &ab->hw_params->ring_mask->tx[0];
+ }
+ break;
+@@ -881,11 +891,9 @@ int ath12k_dp_service_srng(struct ath12k_base *ab,
+ enum dp_monitor_mode monitor_mode;
+ u8 ring_mask;
+
+- while (i < ab->hw_params->max_tx_ring) {
+- if (ab->hw_params->ring_mask->tx[grp_id] &
+- BIT(ab->hw_params->hal_ops->tcl_to_wbm_rbm_map[i].wbm_ring_num))
+- ath12k_dp_tx_completion_handler(ab, i);
+- i++;
++ if (ab->hw_params->ring_mask->tx[grp_id]) {
++ i = fls(ab->hw_params->ring_mask->tx[grp_id]) - 1;
++ ath12k_dp_tx_completion_handler(ab, i);
+ }
+
+ if (ab->hw_params->ring_mask->rx_err[grp_id]) {
+diff --git a/drivers/net/wireless/ath/ath12k/dp.h b/drivers/net/wireless/ath/ath12k/dp.h
+index 5cf0d21ef184b..4dfbff326030e 100644
+--- a/drivers/net/wireless/ath/ath12k/dp.h
++++ b/drivers/net/wireless/ath/ath12k/dp.h
+@@ -334,6 +334,7 @@ struct ath12k_dp {
+ struct dp_srng reo_except_ring;
+ struct dp_srng reo_cmd_ring;
+ struct dp_srng reo_status_ring;
++ enum ath12k_peer_metadata_version peer_metadata_ver;
+ struct dp_srng reo_dst_ring[DP_REO_DST_RING_MAX];
+ struct dp_tx_ring tx_ring[DP_TCL_NUM_RING_MAX];
+ struct hal_wbm_idle_scatter_list scatter_list[DP_IDLE_SCATTER_BUFS_MAX];
+diff --git a/drivers/net/wireless/ath/ath12k/dp_rx.c b/drivers/net/wireless/ath/ath12k/dp_rx.c
+index 75df622f25d85..121f27284be59 100644
+--- a/drivers/net/wireless/ath/ath12k/dp_rx.c
++++ b/drivers/net/wireless/ath/ath12k/dp_rx.c
+@@ -2383,8 +2383,10 @@ void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
+ channel_num = meta_data;
+ center_freq = meta_data >> 16;
+
+- if (center_freq >= 5935 && center_freq <= 7105) {
++ if (center_freq >= ATH12K_MIN_6G_FREQ &&
++ center_freq <= ATH12K_MAX_6G_FREQ) {
+ rx_status->band = NL80211_BAND_6GHZ;
++ rx_status->freq = center_freq;
+ } else if (channel_num >= 1 && channel_num <= 14) {
+ rx_status->band = NL80211_BAND_2GHZ;
+ } else if (channel_num >= 36 && channel_num <= 173) {
+@@ -2402,8 +2404,9 @@ void ath12k_dp_rx_h_ppdu(struct ath12k *ar, struct hal_rx_desc *rx_desc,
+ rx_desc, sizeof(*rx_desc));
+ }
+
+- rx_status->freq = ieee80211_channel_to_frequency(channel_num,
+- rx_status->band);
++ if (rx_status->band != NL80211_BAND_6GHZ)
++ rx_status->freq = ieee80211_channel_to_frequency(channel_num,
++ rx_status->band);
+
+ ath12k_dp_rx_h_rate(ar, rx_desc, rx_status);
+ }
+@@ -2604,6 +2607,29 @@ static void ath12k_dp_rx_process_received_packets(struct ath12k_base *ab,
+ rcu_read_unlock();
+ }
+
++static u16 ath12k_dp_rx_get_peer_id(struct ath12k_base *ab,
++ enum ath12k_peer_metadata_version ver,
++ __le32 peer_metadata)
++{
++ switch (ver) {
++ default:
++ ath12k_warn(ab, "Unknown peer metadata version: %d", ver);
++ fallthrough;
++ case ATH12K_PEER_METADATA_V0:
++ return le32_get_bits(peer_metadata,
++ RX_MPDU_DESC_META_DATA_V0_PEER_ID);
++ case ATH12K_PEER_METADATA_V1:
++ return le32_get_bits(peer_metadata,
++ RX_MPDU_DESC_META_DATA_V1_PEER_ID);
++ case ATH12K_PEER_METADATA_V1A:
++ return le32_get_bits(peer_metadata,
++ RX_MPDU_DESC_META_DATA_V1A_PEER_ID);
++ case ATH12K_PEER_METADATA_V1B:
++ return le32_get_bits(peer_metadata,
++ RX_MPDU_DESC_META_DATA_V1B_PEER_ID);
++ }
++}
++
+ int ath12k_dp_rx_process(struct ath12k_base *ab, int ring_id,
+ struct napi_struct *napi, int budget)
+ {
+@@ -2632,6 +2658,8 @@ int ath12k_dp_rx_process(struct ath12k_base *ab, int ring_id,
+ ath12k_hal_srng_access_begin(ab, srng);
+
+ while ((desc = ath12k_hal_srng_dst_get_next_entry(ab, srng))) {
++ struct rx_mpdu_desc *mpdu_info;
++ struct rx_msdu_desc *msdu_info;
+ enum hal_reo_dest_ring_push_reason push_reason;
+ u32 cookie;
+
+@@ -2678,16 +2706,19 @@ int ath12k_dp_rx_process(struct ath12k_base *ab, int ring_id,
+ continue;
+ }
+
+- rxcb->is_first_msdu = !!(le32_to_cpu(desc->rx_msdu_info.info0) &
++ msdu_info = &desc->rx_msdu_info;
++ mpdu_info = &desc->rx_mpdu_info;
++
++ rxcb->is_first_msdu = !!(le32_to_cpu(msdu_info->info0) &
+ RX_MSDU_DESC_INFO0_FIRST_MSDU_IN_MPDU);
+- rxcb->is_last_msdu = !!(le32_to_cpu(desc->rx_msdu_info.info0) &
++ rxcb->is_last_msdu = !!(le32_to_cpu(msdu_info->info0) &
+ RX_MSDU_DESC_INFO0_LAST_MSDU_IN_MPDU);
+- rxcb->is_continuation = !!(le32_to_cpu(desc->rx_msdu_info.info0) &
++ rxcb->is_continuation = !!(le32_to_cpu(msdu_info->info0) &
+ RX_MSDU_DESC_INFO0_MSDU_CONTINUATION);
+ rxcb->mac_id = mac_id;
+- rxcb->peer_id = le32_get_bits(desc->rx_mpdu_info.peer_meta_data,
+- RX_MPDU_DESC_META_DATA_PEER_ID);
+- rxcb->tid = le32_get_bits(desc->rx_mpdu_info.info0,
++ rxcb->peer_id = ath12k_dp_rx_get_peer_id(ab, dp->peer_metadata_ver,
++ mpdu_info->peer_meta_data);
++ rxcb->tid = le32_get_bits(mpdu_info->info0,
+ RX_MPDU_DESC_INFO0_TID);
+
+ __skb_queue_tail(&msdu_list, msdu);
+@@ -2991,7 +3022,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
+ struct hal_srng *srng;
+ dma_addr_t link_paddr, buf_paddr;
+ u32 desc_bank, msdu_info, msdu_ext_info, mpdu_info;
+- u32 cookie, hal_rx_desc_sz, dest_ring_info0;
++ u32 cookie, hal_rx_desc_sz, dest_ring_info0, queue_addr_hi;
+ int ret;
+ struct ath12k_rx_desc_info *desc_info;
+ u8 dst_ind;
+@@ -3027,7 +3058,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
+
+ buf_paddr = dma_map_single(ab->dev, defrag_skb->data,
+ defrag_skb->len + skb_tailroom(defrag_skb),
+- DMA_FROM_DEVICE);
++ DMA_TO_DEVICE);
+ if (dma_mapping_error(ab->dev, buf_paddr))
+ return -ENOMEM;
+
+@@ -3083,13 +3114,11 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
+ reo_ent_ring->rx_mpdu_info.peer_meta_data =
+ reo_dest_ring->rx_mpdu_info.peer_meta_data;
+
+- /* Firmware expects physical address to be filled in queue_addr_lo in
+- * the MLO scenario and in case of non MLO peer meta data needs to be
+- * filled.
+- * TODO: Need to handle for MLO scenario.
+- */
+- reo_ent_ring->queue_addr_lo = reo_dest_ring->rx_mpdu_info.peer_meta_data;
+- reo_ent_ring->info0 = le32_encode_bits(dst_ind,
++ reo_ent_ring->queue_addr_lo = cpu_to_le32(lower_32_bits(rx_tid->paddr));
++ queue_addr_hi = upper_32_bits(rx_tid->paddr);
++ reo_ent_ring->info0 = le32_encode_bits(queue_addr_hi,
++ HAL_REO_ENTR_RING_INFO0_QUEUE_ADDR_HI) |
++ le32_encode_bits(dst_ind,
+ HAL_REO_ENTR_RING_INFO0_DEST_IND);
+
+ reo_ent_ring->info1 = le32_encode_bits(rx_tid->cur_sn,
+@@ -3113,7 +3142,7 @@ static int ath12k_dp_rx_h_defrag_reo_reinject(struct ath12k *ar,
+ spin_unlock_bh(&dp->rx_desc_lock);
+ err_unmap_dma:
+ dma_unmap_single(ab->dev, buf_paddr, defrag_skb->len + skb_tailroom(defrag_skb),
+- DMA_FROM_DEVICE);
++ DMA_TO_DEVICE);
+ return ret;
+ }
+
+diff --git a/drivers/net/wireless/ath/ath12k/dp_tx.c b/drivers/net/wireless/ath/ath12k/dp_tx.c
+index 9b6d7d72f57c4..a7c7a868c14ce 100644
+--- a/drivers/net/wireless/ath/ath12k/dp_tx.c
++++ b/drivers/net/wireless/ath/ath12k/dp_tx.c
+@@ -352,15 +352,15 @@ static void ath12k_dp_tx_free_txbuf(struct ath12k_base *ab,
+ u8 pdev_id = ath12k_hw_mac_id_to_pdev_id(ab->hw_params, mac_id);
+
+ skb_cb = ATH12K_SKB_CB(msdu);
++ ar = ab->pdevs[pdev_id].ar;
+
+ dma_unmap_single(ab->dev, skb_cb->paddr, msdu->len, DMA_TO_DEVICE);
+ if (skb_cb->paddr_ext_desc)
+ dma_unmap_single(ab->dev, skb_cb->paddr_ext_desc,
+ sizeof(struct hal_tx_msdu_ext_desc), DMA_TO_DEVICE);
+
+- dev_kfree_skb_any(msdu);
++ ieee80211_free_txskb(ar->ah->hw, msdu);
+
+- ar = ab->pdevs[pdev_id].ar;
+ if (atomic_dec_and_test(&ar->dp.num_tx_pending))
+ wake_up(&ar->dp.tx_empty_waitq);
+ }
+@@ -448,6 +448,7 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
+ struct hal_tx_status *ts)
+ {
+ struct ath12k_base *ab = ar->ab;
++ struct ath12k_hw *ah = ar->ah;
+ struct ieee80211_tx_info *info;
+ struct ath12k_skb_cb *skb_cb;
+
+@@ -466,12 +467,12 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
+ rcu_read_lock();
+
+ if (!rcu_dereference(ab->pdevs_active[ar->pdev_idx])) {
+- dev_kfree_skb_any(msdu);
++ ieee80211_free_txskb(ah->hw, msdu);
+ goto exit;
+ }
+
+ if (!skb_cb->vif) {
+- dev_kfree_skb_any(msdu);
++ ieee80211_free_txskb(ah->hw, msdu);
+ goto exit;
+ }
+
+@@ -481,18 +482,36 @@ static void ath12k_dp_tx_complete_msdu(struct ath12k *ar,
+ /* skip tx rate update from ieee80211_status*/
+ info->status.rates[0].idx = -1;
+
+- if (ts->status == HAL_WBM_TQM_REL_REASON_FRAME_ACKED &&
+- !(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
+- info->flags |= IEEE80211_TX_STAT_ACK;
+- info->status.ack_signal = ATH12K_DEFAULT_NOISE_FLOOR +
+- ts->ack_rssi;
+- info->status.flags = IEEE80211_TX_STATUS_ACK_SIGNAL_VALID;
++ switch (ts->status) {
++ case HAL_WBM_TQM_REL_REASON_FRAME_ACKED:
++ if (!(info->flags & IEEE80211_TX_CTL_NO_ACK)) {
++ info->flags |= IEEE80211_TX_STAT_ACK;
++ info->status.ack_signal = ATH12K_DEFAULT_NOISE_FLOOR +
++ ts->ack_rssi;
++ info->status.flags = IEEE80211_TX_STATUS_ACK_SIGNAL_VALID;
++ }
++ break;
++ case HAL_WBM_TQM_REL_REASON_CMD_REMOVE_TX:
++ if (info->flags & IEEE80211_TX_CTL_NO_ACK) {
++ info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
++ break;
++ }
++ fallthrough;
++ case HAL_WBM_TQM_REL_REASON_CMD_REMOVE_MPDU:
++ case HAL_WBM_TQM_REL_REASON_DROP_THRESHOLD:
++ case HAL_WBM_TQM_REL_REASON_CMD_REMOVE_AGED_FRAMES:
++ /* The failure status is due to internal firmware tx failure
++ * hence drop the frame; do not update the status of frame to
++ * the upper layer
++ */
++ ieee80211_free_txskb(ah->hw, msdu);
++ goto exit;
++ default:
++ ath12k_dbg(ab, ATH12K_DBG_DP_TX, "tx frame is not acked status %d\n",
++ ts->status);
++ break;
+ }
+
+- if (ts->status == HAL_WBM_TQM_REL_REASON_CMD_REMOVE_TX &&
+- (info->flags & IEEE80211_TX_CTL_NO_ACK))
+- info->flags |= IEEE80211_TX_STAT_NOACK_TRANSMITTED;
+-
+ /* NOTE: Tx rate status reporting. Tx completion status does not have
+ * necessary information (for example nss) to build the tx rate.
+ * Might end up reporting it out-of-band from HTT stats.
+diff --git a/drivers/net/wireless/ath/ath12k/hal_desc.h b/drivers/net/wireless/ath/ath12k/hal_desc.h
+index 63340256d3f64..072e36365808e 100644
+--- a/drivers/net/wireless/ath/ath12k/hal_desc.h
++++ b/drivers/net/wireless/ath/ath12k/hal_desc.h
+@@ -1,7 +1,7 @@
+ /* SPDX-License-Identifier: BSD-3-Clause-Clear */
+ /*
+ * Copyright (c) 2018-2021 The Linux Foundation. All rights reserved.
+- * Copyright (c) 2021-2022 Qualcomm Innovation Center, Inc. All rights reserved.
++ * Copyright (c) 2021-2022, 2024 Qualcomm Innovation Center, Inc. All rights reserved.
+ */
+ #include "core.h"
+
+@@ -597,8 +597,30 @@ struct hal_tlv_64_hdr {
+ #define RX_MPDU_DESC_INFO0_MPDU_QOS_CTRL_VALID BIT(27)
+ #define RX_MPDU_DESC_INFO0_TID GENMASK(31, 28)
+
+-/* TODO revisit after meta data is concluded */
+-#define RX_MPDU_DESC_META_DATA_PEER_ID GENMASK(15, 0)
++/* Peer Metadata classification */
++
++/* Version 0 */
++#define RX_MPDU_DESC_META_DATA_V0_PEER_ID GENMASK(15, 0)
++#define RX_MPDU_DESC_META_DATA_V0_VDEV_ID GENMASK(23, 16)
++
++/* Version 1 */
++#define RX_MPDU_DESC_META_DATA_V1_PEER_ID GENMASK(13, 0)
++#define RX_MPDU_DESC_META_DATA_V1_LOGICAL_LINK_ID GENMASK(15, 14)
++#define RX_MPDU_DESC_META_DATA_V1_VDEV_ID GENMASK(23, 16)
++#define RX_MPDU_DESC_META_DATA_V1_LMAC_ID GENMASK(25, 24)
++#define RX_MPDU_DESC_META_DATA_V1_DEVICE_ID GENMASK(28, 26)
++
++/* Version 1A */
++#define RX_MPDU_DESC_META_DATA_V1A_PEER_ID GENMASK(13, 0)
++#define RX_MPDU_DESC_META_DATA_V1A_VDEV_ID GENMASK(21, 14)
++#define RX_MPDU_DESC_META_DATA_V1A_LOGICAL_LINK_ID GENMASK(25, 22)
++#define RX_MPDU_DESC_META_DATA_V1A_DEVICE_ID GENMASK(28, 26)
++
++/* Version 1B */
++#define RX_MPDU_DESC_META_DATA_V1B_PEER_ID GENMASK(13, 0)
++#define RX_MPDU_DESC_META_DATA_V1B_VDEV_ID GENMASK(21, 14)
++#define RX_MPDU_DESC_META_DATA_V1B_HW_LINK_ID GENMASK(25, 22)
++#define RX_MPDU_DESC_META_DATA_V1B_DEVICE_ID GENMASK(28, 26)
+
+ struct rx_mpdu_desc {
+ __le32 info0; /* %RX_MPDU_DESC_INFO */
+@@ -2048,6 +2070,19 @@ struct hal_wbm_release_ring {
+ * fw with fw_reason2.
+ * @HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON3: Remove command initiated by
+ * fw with fw_reason3.
++ * @HAL_WBM_TQM_REL_REASON_CMD_DISABLE_QUEUE: Remove command initiated by
++ * fw with disable queue.
++ * @HAL_WBM_TQM_REL_REASON_CMD_TILL_NONMATCHING: Remove command initiated by
++ * fw to remove all mpdu until 1st non-match.
++ * @HAL_WBM_TQM_REL_REASON_DROP_THRESHOLD: Dropped due to drop threshold
++ * criteria
++ * @HAL_WBM_TQM_REL_REASON_DROP_LINK_DESC_UNAVAIL: Dropped due to link desc
++ * not available
++ * @HAL_WBM_TQM_REL_REASON_DROP_OR_INVALID_MSDU: Dropped due drop bit set or
++ * null flow
++ * @HAL_WBM_TQM_REL_REASON_MULTICAST_DROP: Dropped due mcast drop set for VDEV
++ * @HAL_WBM_TQM_REL_REASON_VDEV_MISMATCH_DROP: Dropped due to being set with
++ * 'TCL_drop_reason'
+ */
+ enum hal_wbm_tqm_rel_reason {
+ HAL_WBM_TQM_REL_REASON_FRAME_ACKED,
+@@ -2058,6 +2093,13 @@ enum hal_wbm_tqm_rel_reason {
+ HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON1,
+ HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON2,
+ HAL_WBM_TQM_REL_REASON_CMD_REMOVE_RESEAON3,
++ HAL_WBM_TQM_REL_REASON_CMD_DISABLE_QUEUE,
++ HAL_WBM_TQM_REL_REASON_CMD_TILL_NONMATCHING,
++ HAL_WBM_TQM_REL_REASON_DROP_THRESHOLD,
++ HAL_WBM_TQM_REL_REASON_DROP_LINK_DESC_UNAVAIL,
++ HAL_WBM_TQM_REL_REASON_DROP_OR_INVALID_MSDU,
++ HAL_WBM_TQM_REL_REASON_MULTICAST_DROP,
++ HAL_WBM_TQM_REL_REASON_VDEV_MISMATCH_DROP,
+ };
+
+ struct hal_wbm_buffer_ring {
+diff --git a/drivers/net/wireless/ath/ath12k/hw.c b/drivers/net/wireless/ath/ath12k/hw.c
+index f4c8270158215..bff8cf97a18c6 100644
+--- a/drivers/net/wireless/ath/ath12k/hw.c
++++ b/drivers/net/wireless/ath/ath12k/hw.c
+@@ -544,9 +544,6 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
+ },
+ .rx_mon_dest = {
+ 0, 0, 0,
+- ATH12K_RX_MON_RING_MASK_0,
+- ATH12K_RX_MON_RING_MASK_1,
+- ATH12K_RX_MON_RING_MASK_2,
+ },
+ .rx = {
+ 0, 0, 0, 0,
+@@ -572,16 +569,15 @@ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_qcn9274 = {
+ ATH12K_HOST2RXDMA_RING_MASK_0,
+ },
+ .tx_mon_dest = {
+- ATH12K_TX_MON_RING_MASK_0,
+- ATH12K_TX_MON_RING_MASK_1,
++ 0, 0, 0,
+ },
+ };
+
+ static const struct ath12k_hw_ring_mask ath12k_hw_ring_mask_wcn7850 = {
+ .tx = {
+ ATH12K_TX_RING_MASK_0,
++ ATH12K_TX_RING_MASK_1,
+ ATH12K_TX_RING_MASK_2,
+- ATH12K_TX_RING_MASK_4,
+ },
+ .rx_mon_dest = {
+ },
+diff --git a/drivers/net/wireless/ath/ath12k/hw.h b/drivers/net/wireless/ath/ath12k/hw.h
+index 3f450ee93f34b..2a314cfc8cb84 100644
+--- a/drivers/net/wireless/ath/ath12k/hw.h
++++ b/drivers/net/wireless/ath/ath12k/hw.h
+@@ -78,8 +78,7 @@
+ #define TARGET_NUM_WDS_ENTRIES 32
+ #define TARGET_DMA_BURST_SIZE 1
+ #define TARGET_RX_BATCHMODE 1
+-#define TARGET_RX_PEER_METADATA_VER_V1A 2
+-#define TARGET_RX_PEER_METADATA_VER_V1B 3
++#define TARGET_EMA_MAX_PROFILE_PERIOD 8
+
+ #define ATH12K_HW_DEFAULT_QUEUE 0
+ #define ATH12K_HW_MAX_QUEUES 4
+diff --git a/drivers/net/wireless/ath/ath12k/mac.c b/drivers/net/wireless/ath/ath12k/mac.c
+index 805cb084484a4..ead37a4e002a2 100644
+--- a/drivers/net/wireless/ath/ath12k/mac.c
++++ b/drivers/net/wireless/ath/ath12k/mac.c
+@@ -7386,7 +7386,8 @@ ath12k_mac_op_unassign_vif_chanctx(struct ieee80211_hw *hw,
+ arvif->is_started = false;
+ }
+
+- if (arvif->vdev_type != WMI_VDEV_TYPE_STA) {
++ if (arvif->vdev_type != WMI_VDEV_TYPE_STA &&
++ arvif->vdev_type != WMI_VDEV_TYPE_MONITOR) {
+ ath12k_bss_disassoc(ar, arvif);
+ ret = ath12k_mac_vdev_stop(arvif);
+ if (ret)
+@@ -8488,19 +8489,23 @@ static int ath12k_mac_setup_iface_combinations(struct ath12k_hw *ah)
+
+ static const u8 ath12k_if_types_ext_capa[] = {
+ [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
++ [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
+ [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
+ };
+
+ static const u8 ath12k_if_types_ext_capa_sta[] = {
+ [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
++ [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
+ [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
+ [9] = WLAN_EXT_CAPA10_TWT_REQUESTER_SUPPORT,
+ };
+
+ static const u8 ath12k_if_types_ext_capa_ap[] = {
+ [0] = WLAN_EXT_CAPA1_EXT_CHANNEL_SWITCHING,
++ [2] = WLAN_EXT_CAPA3_MULTI_BSSID_SUPPORT,
+ [7] = WLAN_EXT_CAPA8_OPMODE_NOTIF,
+ [9] = WLAN_EXT_CAPA10_TWT_RESPONDER_SUPPORT,
++ [10] = WLAN_EXT_CAPA11_EMA_SUPPORT,
+ };
+
+ static const struct wiphy_iftype_ext_capab ath12k_iftypes_ext_capa[] = {
+@@ -8605,6 +8610,7 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
+ u32 ht_cap = U32_MAX, antennas_rx = 0, antennas_tx = 0;
+ bool is_6ghz = false, is_raw_mode = false, is_monitor_disable = false;
+ u8 *mac_addr = NULL;
++ u8 mbssid_max_interfaces = 0;
+
+ wiphy->max_ap_assoc_sta = 0;
+
+@@ -8648,6 +8654,8 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
+ mac_addr = ar->mac_addr;
+ else
+ mac_addr = ab->mac_addr;
++
++ mbssid_max_interfaces += TARGET_NUM_VDEVS;
+ }
+
+ wiphy->available_antennas_rx = antennas_rx;
+@@ -8739,6 +8747,9 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
+ wiphy->iftype_ext_capab = ath12k_iftypes_ext_capa;
+ wiphy->num_iftype_ext_capab = ARRAY_SIZE(ath12k_iftypes_ext_capa);
+
++ wiphy->mbssid_max_interfaces = mbssid_max_interfaces;
++ wiphy->ema_max_profile_periodicity = TARGET_EMA_MAX_PROFILE_PERIOD;
++
+ if (is_6ghz) {
+ wiphy_ext_feature_set(wiphy,
+ NL80211_EXT_FEATURE_FILS_DISCOVERY);
+@@ -8777,9 +8788,9 @@ static int ath12k_mac_hw_register(struct ath12k_hw *ah)
+ ath12k_err(ar->ab, "ath12k regd update failed: %d\n", ret);
+ goto err_unregister_hw;
+ }
+- }
+
+- ath12k_debugfs_register(ar);
++ ath12k_debugfs_register(ar);
++ }
+
+ return 0;
+
+diff --git a/drivers/net/wireless/ath/ath12k/wmi.c b/drivers/net/wireless/ath/ath12k/wmi.c
+index 7a52d2082b792..ef775af25093c 100644
+--- a/drivers/net/wireless/ath/ath12k/wmi.c
++++ b/drivers/net/wireless/ath/ath12k/wmi.c
+@@ -228,9 +228,12 @@ void ath12k_wmi_init_qcn9274(struct ath12k_base *ab,
+ config->peer_map_unmap_version = 0x32;
+ config->twt_ap_pdev_count = ab->num_radios;
+ config->twt_ap_sta_count = 1000;
++ config->ema_max_vap_cnt = ab->num_radios;
++ config->ema_max_profile_period = TARGET_EMA_MAX_PROFILE_PERIOD;
++ config->beacon_tx_offload_max_vdev += config->ema_max_vap_cnt;
+
+ if (test_bit(WMI_TLV_SERVICE_PEER_METADATA_V1A_V1B_SUPPORT, ab->wmi_ab.svc_map))
+- config->dp_peer_meta_data_ver = TARGET_RX_PEER_METADATA_VER_V1B;
++ config->peer_metadata_ver = ATH12K_PEER_METADATA_V1B;
+ }
+
+ void ath12k_wmi_init_wcn7850(struct ath12k_base *ab,
+@@ -3473,11 +3476,13 @@ ath12k_wmi_copy_resource_config(struct ath12k_wmi_resource_config_params *wmi_cf
+ wmi_cfg->sched_params = cpu_to_le32(tg_cfg->sched_params);
+ wmi_cfg->twt_ap_pdev_count = cpu_to_le32(tg_cfg->twt_ap_pdev_count);
+ wmi_cfg->twt_ap_sta_count = cpu_to_le32(tg_cfg->twt_ap_sta_count);
+- wmi_cfg->flags2 = le32_encode_bits(tg_cfg->dp_peer_meta_data_ver,
++ wmi_cfg->flags2 = le32_encode_bits(tg_cfg->peer_metadata_ver,
+ WMI_RSRC_CFG_FLAGS2_RX_PEER_METADATA_VERSION);
+-
+ wmi_cfg->host_service_flags = cpu_to_le32(tg_cfg->is_reg_cc_ext_event_supported <<
+ WMI_RSRC_CFG_HOST_SVC_FLAG_REG_CC_EXT_SUPPORT_BIT);
++ wmi_cfg->ema_max_vap_cnt = cpu_to_le32(tg_cfg->ema_max_vap_cnt);
++ wmi_cfg->ema_max_profile_period = cpu_to_le32(tg_cfg->ema_max_profile_period);
++ wmi_cfg->flags2 |= cpu_to_le32(WMI_RSRC_CFG_FLAGS2_CALC_NEXT_DTIM_COUNT_SET);
+ }
+
+ static int ath12k_init_cmd_send(struct ath12k_wmi_pdev *wmi,
+@@ -3701,6 +3706,8 @@ int ath12k_wmi_cmd_init(struct ath12k_base *ab)
+ arg.num_band_to_mac = ab->num_radios;
+ ath12k_fill_band_to_mac_param(ab, arg.band_to_mac);
+
++ ab->dp.peer_metadata_ver = arg.res_cfg.peer_metadata_ver;
++
+ return ath12k_init_cmd_send(&wmi_ab->wmi[0], &arg);
+ }
+
+@@ -6022,8 +6029,10 @@ static void ath12k_mgmt_rx_event(struct ath12k_base *ab, struct sk_buff *skb)
+ if (rx_ev.status & WMI_RX_STATUS_ERR_MIC)
+ status->flag |= RX_FLAG_MMIC_ERROR;
+
+- if (rx_ev.chan_freq >= ATH12K_MIN_6G_FREQ) {
++ if (rx_ev.chan_freq >= ATH12K_MIN_6G_FREQ &&
++ rx_ev.chan_freq <= ATH12K_MAX_6G_FREQ) {
+ status->band = NL80211_BAND_6GHZ;
++ status->freq = rx_ev.chan_freq;
+ } else if (rx_ev.channel >= 1 && rx_ev.channel <= 14) {
+ status->band = NL80211_BAND_2GHZ;
+ } else if (rx_ev.channel >= 36 && rx_ev.channel <= ATH12K_MAX_5G_CHAN) {
+@@ -6044,8 +6053,10 @@ static void ath12k_mgmt_rx_event(struct ath12k_base *ab, struct sk_buff *skb)
+
+ sband = &ar->mac.sbands[status->band];
+
+- status->freq = ieee80211_channel_to_frequency(rx_ev.channel,
+- status->band);
++ if (status->band != NL80211_BAND_6GHZ)
++ status->freq = ieee80211_channel_to_frequency(rx_ev.channel,
++ status->band);
++
+ status->signal = rx_ev.snr + ATH12K_DEFAULT_NOISE_FLOOR;
+ status->rate_idx = ath12k_mac_bitrate_to_idx(sband, rx_ev.rate / 100);
+
+diff --git a/drivers/net/wireless/ath/ath12k/wmi.h b/drivers/net/wireless/ath/ath12k/wmi.h
+index 496866673aead..742fe0b36cf20 100644
+--- a/drivers/net/wireless/ath/ath12k/wmi.h
++++ b/drivers/net/wireless/ath/ath12k/wmi.h
+@@ -2292,6 +2292,13 @@ struct ath12k_wmi_host_mem_chunk_arg {
+ u32 req_id;
+ };
+
++enum ath12k_peer_metadata_version {
++ ATH12K_PEER_METADATA_V0,
++ ATH12K_PEER_METADATA_V1,
++ ATH12K_PEER_METADATA_V1A,
++ ATH12K_PEER_METADATA_V1B
++};
++
+ struct ath12k_wmi_resource_config_arg {
+ u32 num_vdevs;
+ u32 num_peers;
+@@ -2354,8 +2361,10 @@ struct ath12k_wmi_resource_config_arg {
+ u32 sched_params;
+ u32 twt_ap_pdev_count;
+ u32 twt_ap_sta_count;
++ enum ath12k_peer_metadata_version peer_metadata_ver;
++ u32 ema_max_vap_cnt;
++ u32 ema_max_profile_period;
+ bool is_reg_cc_ext_event_supported;
+- u8 dp_peer_meta_data_ver;
+ };
+
+ struct ath12k_wmi_init_cmd_arg {
+@@ -2410,6 +2419,7 @@ struct wmi_init_cmd {
+ #define WMI_RSRC_CFG_HOST_SVC_FLAG_REG_CC_EXT_SUPPORT_BIT 4
+ #define WMI_RSRC_CFG_FLAGS2_RX_PEER_METADATA_VERSION GENMASK(5, 4)
+ #define WMI_RSRC_CFG_FLAG1_BSS_CHANNEL_INFO_64 BIT(5)
++#define WMI_RSRC_CFG_FLAGS2_CALC_NEXT_DTIM_COUNT_SET BIT(9)
+
+ struct ath12k_wmi_resource_config_params {
+ __le32 tlv_header;
+diff --git a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
+index aae2cf95fe958..e472591f321bd 100644
+--- a/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
++++ b/drivers/net/wireless/broadcom/brcm80211/brcmsmac/phy/phy_lcn.c
+@@ -2567,7 +2567,6 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi,
+
+ struct lcnphy_txgains cal_gains, temp_gains;
+ u16 hash;
+- u8 band_idx;
+ int j;
+ u16 ncorr_override[5];
+ u16 syst_coeffs[] = { 0x0000, 0x0000, 0x0000, 0x0000, 0x0000, 0x0000,
+@@ -2599,6 +2598,9 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi,
+ u16 *values_to_save;
+ struct brcms_phy_lcnphy *pi_lcn = pi->u.pi_lcnphy;
+
++ if (WARN_ON(CHSPEC_IS5G(pi->radio_chanspec)))
++ return;
++
+ values_to_save = kmalloc_array(20, sizeof(u16), GFP_ATOMIC);
+ if (NULL == values_to_save)
+ return;
+@@ -2662,20 +2664,18 @@ wlc_lcnphy_tx_iqlo_cal(struct brcms_phy *pi,
+ hash = (target_gains->gm_gain << 8) |
+ (target_gains->pga_gain << 4) | (target_gains->pad_gain);
+
+- band_idx = (CHSPEC_IS5G(pi->radio_chanspec) ? 1 : 0);
+-
+ cal_gains = *target_gains;
+ memset(ncorr_override, 0, sizeof(ncorr_override));
+- for (j = 0; j < iqcal_gainparams_numgains_lcnphy[band_idx]; j++) {
+- if (hash == tbl_iqcal_gainparams_lcnphy[band_idx][j][0]) {
++ for (j = 0; j < iqcal_gainparams_numgains_lcnphy[0]; j++) {
++ if (hash == tbl_iqcal_gainparams_lcnphy[0][j][0]) {
+ cal_gains.gm_gain =
+- tbl_iqcal_gainparams_lcnphy[band_idx][j][1];
++ tbl_iqcal_gainparams_lcnphy[0][j][1];
+ cal_gains.pga_gain =
+- tbl_iqcal_gainparams_lcnphy[band_idx][j][2];
++ tbl_iqcal_gainparams_lcnphy[0][j][2];
+ cal_gains.pad_gain =
+- tbl_iqcal_gainparams_lcnphy[band_idx][j][3];
++ tbl_iqcal_gainparams_lcnphy[0][j][3];
+ memcpy(ncorr_override,
+- &tbl_iqcal_gainparams_lcnphy[band_idx][j][3],
++ &tbl_iqcal_gainparams_lcnphy[0][j][3],
+ sizeof(ncorr_override));
+ break;
+ }
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/link.c b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+index 6ec9a8e21a34e..92ac6cc40faa7 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/link.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/link.c
+@@ -1082,6 +1082,15 @@ static void iwl_mvm_esr_unblocked(struct iwl_mvm *mvm,
+
+ IWL_DEBUG_INFO(mvm, "EMLSR is unblocked\n");
+
++ /* If we exited due to an EXIT reason, and the exit was in less than
++ * 30 seconds, then a MLO scan was scheduled already.
++ */
++ if (!need_new_sel &&
++ !(mvmvif->last_esr_exit.reason & IWL_MVM_BLOCK_ESR_REASONS)) {
++ IWL_DEBUG_INFO(mvm, "Wait for MLO scan\n");
++ return;
++ }
++
+ /*
+ * If EMLSR was blocked for more than 30 seconds, or the last link
+ * selection decided to not enter EMLSR, trigger a new scan.
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+index dac6155ae1bd0..259afecd1a98d 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/mac80211.c
+@@ -4861,6 +4861,7 @@ int iwl_mvm_roc_common(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+ const struct iwl_mvm_roc_ops *ops)
+ {
+ struct iwl_mvm *mvm = IWL_MAC80211_GET_MVM(hw);
++ struct ieee80211_vif *bss_vif = iwl_mvm_get_bss_vif(mvm);
+ u32 lmac_id;
+ int ret;
+
+@@ -4873,9 +4874,12 @@ int iwl_mvm_roc_common(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
+ */
+ flush_work(&mvm->roc_done_wk);
+
+- ret = iwl_mvm_esr_non_bss_link(mvm, vif, 0, true);
+- if (ret)
+- return ret;
++ if (!IS_ERR_OR_NULL(bss_vif)) {
++ ret = iwl_mvm_block_esr_sync(mvm, bss_vif,
++ IWL_MVM_ESR_BLOCKED_ROC);
++ if (ret)
++ return ret;
++ }
+
+ mutex_lock(&mvm->mutex);
+
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+index 0a1959bd40799..ded094b6b63df 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+@@ -360,7 +360,9 @@ struct iwl_mvm_vif_link_info {
+ * @IWL_MVM_ESR_BLOCKED_WOWLAN: WOWLAN is preventing the enablement of EMLSR
+ * @IWL_MVM_ESR_BLOCKED_TPT: block EMLSR when there is not enough traffic
+ * @IWL_MVM_ESR_BLOCKED_FW: FW didn't recommended/forced exit from EMLSR
+- * @IWL_MVM_ESR_BLOCKED_NON_BSS: An active non-bssid link's preventing EMLSR
++ * @IWL_MVM_ESR_BLOCKED_NON_BSS: An active non-BSS interface's link is
++ * preventing EMLSR
++ * @IWL_MVM_ESR_BLOCKED_ROC: remain-on-channel is preventing EMLSR
+ * @IWL_MVM_ESR_EXIT_MISSED_BEACON: exited EMLSR due to missed beacons
+ * @IWL_MVM_ESR_EXIT_LOW_RSSI: link is deactivated/not allowed for EMLSR
+ * due to low RSSI.
+@@ -377,6 +379,7 @@ enum iwl_mvm_esr_state {
+ IWL_MVM_ESR_BLOCKED_TPT = 0x4,
+ IWL_MVM_ESR_BLOCKED_FW = 0x8,
+ IWL_MVM_ESR_BLOCKED_NON_BSS = 0x10,
++ IWL_MVM_ESR_BLOCKED_ROC = 0x20,
+ IWL_MVM_ESR_EXIT_MISSED_BEACON = 0x10000,
+ IWL_MVM_ESR_EXIT_LOW_RSSI = 0x20000,
+ IWL_MVM_ESR_EXIT_COEX = 0x40000,
+@@ -1860,10 +1863,10 @@ static inline u8 iwl_mvm_get_valid_tx_ant(struct iwl_mvm *mvm)
+
+ static inline u8 iwl_mvm_get_valid_rx_ant(struct iwl_mvm *mvm)
+ {
+- u8 rx_ant = mvm->fw->valid_tx_ant;
++ u8 rx_ant = mvm->fw->valid_rx_ant;
+
+ if (mvm->nvm_data && mvm->nvm_data->valid_rx_ant)
+- rx_ant &= mvm->nvm_data->valid_tx_ant;
++ rx_ant &= mvm->nvm_data->valid_rx_ant;
+
+ if (mvm->set_rx_ant)
+ rx_ant &= mvm->set_rx_ant;
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+index 31bc80cdcb7d5..9d681377cbab3 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/time-event.c
+@@ -47,6 +47,7 @@ void iwl_mvm_te_clear_data(struct iwl_mvm *mvm,
+
+ static void iwl_mvm_cleanup_roc(struct iwl_mvm *mvm)
+ {
++ struct ieee80211_vif *bss_vif = iwl_mvm_get_bss_vif(mvm);
+ struct ieee80211_vif *vif = mvm->p2p_device_vif;
+
+ lockdep_assert_held(&mvm->mutex);
+@@ -119,9 +120,9 @@ static void iwl_mvm_cleanup_roc(struct iwl_mvm *mvm)
+ iwl_mvm_rm_aux_sta(mvm);
+ }
+
++ if (!IS_ERR_OR_NULL(bss_vif))
++ iwl_mvm_unblock_esr(mvm, bss_vif, IWL_MVM_ESR_BLOCKED_ROC);
+ mutex_unlock(&mvm->mutex);
+- if (vif)
+- iwl_mvm_esr_non_bss_link(mvm, vif, 0, false);
+ }
+
+ void iwl_mvm_roc_done_wk(struct work_struct *wk)
+diff --git a/drivers/net/wireless/marvell/mwifiex/cfg80211.c b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+index b909a7665e9cc..155eb0fab12a4 100644
+--- a/drivers/net/wireless/marvell/mwifiex/cfg80211.c
++++ b/drivers/net/wireless/marvell/mwifiex/cfg80211.c
+@@ -926,6 +926,8 @@ mwifiex_init_new_priv_params(struct mwifiex_private *priv,
+ return -EOPNOTSUPP;
+ }
+
++ priv->bss_num = mwifiex_get_unused_bss_num(adapter, priv->bss_type);
++
+ spin_lock_irqsave(&adapter->main_proc_lock, flags);
+ adapter->main_locked = false;
+ spin_unlock_irqrestore(&adapter->main_proc_lock, flags);
+diff --git a/drivers/net/wireless/realtek/rtl8xxxu/8188f.c b/drivers/net/wireless/realtek/rtl8xxxu/8188f.c
+index bd5a0603b4a23..3abf14d7044f3 100644
+--- a/drivers/net/wireless/realtek/rtl8xxxu/8188f.c
++++ b/drivers/net/wireless/realtek/rtl8xxxu/8188f.c
+@@ -697,9 +697,14 @@ static void rtl8188fu_init_statistics(struct rtl8xxxu_priv *priv)
+ rtl8xxxu_write32(priv, REG_OFDM0_FA_RSTC, val32);
+ }
+
++#define TX_POWER_INDEX_MAX 0x3F
++#define TX_POWER_INDEX_DEFAULT_CCK 0x22
++#define TX_POWER_INDEX_DEFAULT_HT40 0x27
++
+ static int rtl8188fu_parse_efuse(struct rtl8xxxu_priv *priv)
+ {
+ struct rtl8188fu_efuse *efuse = &priv->efuse_wifi.efuse8188fu;
++ int i;
+
+ if (efuse->rtl_id != cpu_to_le16(0x8129))
+ return -EINVAL;
+@@ -713,6 +718,16 @@ static int rtl8188fu_parse_efuse(struct rtl8xxxu_priv *priv)
+ efuse->tx_power_index_A.ht40_base,
+ sizeof(efuse->tx_power_index_A.ht40_base));
+
++ for (i = 0; i < ARRAY_SIZE(priv->cck_tx_power_index_A); i++) {
++ if (priv->cck_tx_power_index_A[i] > TX_POWER_INDEX_MAX)
++ priv->cck_tx_power_index_A[i] = TX_POWER_INDEX_DEFAULT_CCK;
++ }
++
++ for (i = 0; i < ARRAY_SIZE(priv->ht40_1s_tx_power_index_A); i++) {
++ if (priv->ht40_1s_tx_power_index_A[i] > TX_POWER_INDEX_MAX)
++ priv->ht40_1s_tx_power_index_A[i] = TX_POWER_INDEX_DEFAULT_HT40;
++ }
++
+ priv->ofdm_tx_power_diff[0].a = efuse->tx_power_index_A.ht20_ofdm_1s_diff.a;
+ priv->ht20_tx_power_diff[0].a = efuse->tx_power_index_A.ht20_ofdm_1s_diff.b;
+
+diff --git a/drivers/net/wireless/realtek/rtw88/mac.c b/drivers/net/wireless/realtek/rtw88/mac.c
+index 0dba8aae77160..564f5988ee82a 100644
+--- a/drivers/net/wireless/realtek/rtw88/mac.c
++++ b/drivers/net/wireless/realtek/rtw88/mac.c
+@@ -1201,6 +1201,15 @@ static int __priority_queue_cfg(struct rtw_dev *rtwdev,
+ rtw_write16(rtwdev, REG_FIFOPAGE_CTRL_2 + 2, fifo->rsvd_boundary);
+ rtw_write16(rtwdev, REG_BCNQ1_BDNY_V1, fifo->rsvd_boundary);
+ rtw_write32(rtwdev, REG_RXFF_BNDY, chip->rxff_size - C2H_PKT_BUF - 1);
++
++ if (rtwdev->hci.type == RTW_HCI_TYPE_USB) {
++ rtw_write8_mask(rtwdev, REG_AUTO_LLT_V1, BIT_MASK_BLK_DESC_NUM,
++ chip->usb_tx_agg_desc_num);
++
++ rtw_write8(rtwdev, REG_AUTO_LLT_V1 + 3, chip->usb_tx_agg_desc_num);
++ rtw_write8_set(rtwdev, REG_TXDMA_OFFSET_CHK + 1, BIT(1));
++ }
++
+ rtw_write8_set(rtwdev, REG_AUTO_LLT_V1, BIT_AUTO_INIT_LLT_V1);
+
+ if (!check_hw_ready(rtwdev, REG_AUTO_LLT_V1, BIT_AUTO_INIT_LLT_V1, 0))
+diff --git a/drivers/net/wireless/realtek/rtw88/main.h b/drivers/net/wireless/realtek/rtw88/main.h
+index 49894331f7b49..49a3fd4fb7dcd 100644
+--- a/drivers/net/wireless/realtek/rtw88/main.h
++++ b/drivers/net/wireless/realtek/rtw88/main.h
+@@ -1197,6 +1197,8 @@ struct rtw_chip_info {
+ u16 fw_fifo_addr[RTW_FW_FIFO_MAX];
+ const struct rtw_fwcd_segs *fwcd_segs;
+
++ u8 usb_tx_agg_desc_num;
++
+ u8 default_1ss_tx_path;
+
+ bool path_div_supported;
+diff --git a/drivers/net/wireless/realtek/rtw88/reg.h b/drivers/net/wireless/realtek/rtw88/reg.h
+index b122f226924be..02ef9a77316b4 100644
+--- a/drivers/net/wireless/realtek/rtw88/reg.h
++++ b/drivers/net/wireless/realtek/rtw88/reg.h
+@@ -270,6 +270,7 @@
+ #define BIT_MASK_BCN_HEAD_1_V1 0xfff
+ #define REG_AUTO_LLT_V1 0x0208
+ #define BIT_AUTO_INIT_LLT_V1 BIT(0)
++#define BIT_MASK_BLK_DESC_NUM GENMASK(7, 4)
+ #define REG_DWBCN0_CTRL 0x0208
+ #define BIT_BCN_VALID BIT(16)
+ #define REG_TXDMA_OFFSET_CHK 0x020C
+diff --git a/drivers/net/wireless/realtek/rtw88/rtw8703b.c b/drivers/net/wireless/realtek/rtw88/rtw8703b.c
+index 8919f9e11f037..222608de33cde 100644
+--- a/drivers/net/wireless/realtek/rtw88/rtw8703b.c
++++ b/drivers/net/wireless/realtek/rtw88/rtw8703b.c
+@@ -2013,6 +2013,7 @@ const struct rtw_chip_info rtw8703b_hw_spec = {
+ .tx_stbc = false,
+ .max_power_index = 0x3f,
+ .ampdu_density = IEEE80211_HT_MPDU_DENSITY_16,
++ .usb_tx_agg_desc_num = 1, /* Not sure if this chip has USB interface */
+
+ .path_div_supported = false,
+ .ht_supported = true,
+diff --git a/drivers/net/wireless/realtek/rtw88/rtw8723d.c b/drivers/net/wireless/realtek/rtw88/rtw8723d.c
+index f8df4c84d39f7..3fba4054d45f4 100644
+--- a/drivers/net/wireless/realtek/rtw88/rtw8723d.c
++++ b/drivers/net/wireless/realtek/rtw88/rtw8723d.c
+@@ -2171,6 +2171,7 @@ const struct rtw_chip_info rtw8723d_hw_spec = {
+ .band = RTW_BAND_2G,
+ .page_size = TX_PAGE_SIZE,
+ .dig_min = 0x20,
++ .usb_tx_agg_desc_num = 1,
+ .ht_supported = true,
+ .vht_supported = false,
+ .lps_deep_mode_supported = 0,
+diff --git a/drivers/net/wireless/realtek/rtw88/rtw8821c.c b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+index fe5d8e1883509..526e8de77b3e8 100644
+--- a/drivers/net/wireless/realtek/rtw88/rtw8821c.c
++++ b/drivers/net/wireless/realtek/rtw88/rtw8821c.c
+@@ -2008,6 +2008,7 @@ const struct rtw_chip_info rtw8821c_hw_spec = {
+ .band = RTW_BAND_2G | RTW_BAND_5G,
+ .page_size = TX_PAGE_SIZE,
+ .dig_min = 0x1c,
++ .usb_tx_agg_desc_num = 3,
+ .ht_supported = true,
+ .vht_supported = true,
+ .lps_deep_mode_supported = BIT(LPS_DEEP_MODE_LCLK),
+diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822b.c b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+index 3017a9760da8d..2456ff2428180 100644
+--- a/drivers/net/wireless/realtek/rtw88/rtw8822b.c
++++ b/drivers/net/wireless/realtek/rtw88/rtw8822b.c
+@@ -2548,6 +2548,7 @@ const struct rtw_chip_info rtw8822b_hw_spec = {
+ .band = RTW_BAND_2G | RTW_BAND_5G,
+ .page_size = TX_PAGE_SIZE,
+ .dig_min = 0x1c,
++ .usb_tx_agg_desc_num = 3,
+ .ht_supported = true,
+ .vht_supported = true,
+ .lps_deep_mode_supported = BIT(LPS_DEEP_MODE_LCLK),
+diff --git a/drivers/net/wireless/realtek/rtw88/rtw8822c.c b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+index cd965edc29cea..62376d1cca22f 100644
+--- a/drivers/net/wireless/realtek/rtw88/rtw8822c.c
++++ b/drivers/net/wireless/realtek/rtw88/rtw8822c.c
+@@ -5366,6 +5366,7 @@ const struct rtw_chip_info rtw8822c_hw_spec = {
+ .band = RTW_BAND_2G | RTW_BAND_5G,
+ .page_size = TX_PAGE_SIZE,
+ .dig_min = 0x20,
++ .usb_tx_agg_desc_num = 3,
+ .default_1ss_tx_path = BB_PATH_A,
+ .path_div_supported = true,
+ .ht_supported = true,
+diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c
+index a0188511099a1..0001a1ab6f38b 100644
+--- a/drivers/net/wireless/realtek/rtw88/usb.c
++++ b/drivers/net/wireless/realtek/rtw88/usb.c
+@@ -273,6 +273,8 @@ static void rtw_usb_write_port_tx_complete(struct urb *urb)
+ info = IEEE80211_SKB_CB(skb);
+ tx_data = rtw_usb_get_tx_data(skb);
+
++ skb_pull(skb, rtwdev->chip->tx_pkt_desc_sz);
++
+ /* enqueue to wait for tx report */
+ if (info->flags & IEEE80211_TX_CTL_REQ_TX_STATUS) {
+ rtw_tx_report_enqueue(rtwdev, skb, tx_data->sn);
+@@ -377,7 +379,9 @@ static bool rtw_usb_tx_agg_skb(struct rtw_usb *rtwusb, struct sk_buff_head *list
+
+ skb_iter = skb_peek(list);
+
+- if (skb_iter && skb_iter->len + skb_head->len <= RTW_USB_MAX_XMITBUF_SZ)
++ if (skb_iter &&
++ skb_iter->len + skb_head->len <= RTW_USB_MAX_XMITBUF_SZ &&
++ agg_num < rtwdev->chip->usb_tx_agg_desc_num)
+ __skb_unlink(skb_iter, list);
+ else
+ skb_iter = NULL;
+diff --git a/drivers/net/wireless/realtek/rtw89/debug.c b/drivers/net/wireless/realtek/rtw89/debug.c
+index affffc4092ba3..5b4077c9fd286 100644
+--- a/drivers/net/wireless/realtek/rtw89/debug.c
++++ b/drivers/net/wireless/realtek/rtw89/debug.c
+@@ -3531,7 +3531,7 @@ static void rtw89_sta_info_get_iter(void *data, struct ieee80211_sta *sta)
+ case RX_ENC_HE:
+ seq_printf(m, "HE %dSS MCS-%d GI:%s", status->nss, status->rate_idx,
+ status->he_gi <= NL80211_RATE_INFO_HE_GI_3_2 ?
+- he_gi_str[rate->he_gi] : "N/A");
++ he_gi_str[status->he_gi] : "N/A");
+ break;
+ case RX_ENC_EHT:
+ seq_printf(m, "EHT %dSS MCS-%d GI:%s", status->nss, status->rate_idx,
+diff --git a/drivers/net/wireless/realtek/rtw89/fw.c b/drivers/net/wireless/realtek/rtw89/fw.c
+index 044a5b90c7f4e..6cd6922882211 100644
+--- a/drivers/net/wireless/realtek/rtw89/fw.c
++++ b/drivers/net/wireless/realtek/rtw89/fw.c
+@@ -6245,7 +6245,14 @@ void rtw89_hw_scan_abort(struct rtw89_dev *rtwdev, struct ieee80211_vif *vif)
+
+ ret = rtw89_hw_scan_offload(rtwdev, vif, false);
+ if (ret)
+- rtw89_hw_scan_complete(rtwdev, vif, true);
++ rtw89_warn(rtwdev, "rtw89_hw_scan_offload failed ret %d\n", ret);
++
++ /* Indicate ieee80211_scan_completed() before returning, which is safe
++ * because scan abort command always waits for completion of
++ * RTW89_SCAN_END_SCAN_NOTIFY, so that ieee80211_stop() can flush scan
++ * work properly.
++ */
++ rtw89_hw_scan_complete(rtwdev, vif, true);
+ }
+
+ static bool rtw89_is_any_vif_connected_or_connecting(struct rtw89_dev *rtwdev)
+@@ -6715,10 +6722,8 @@ int rtw89_fw_h2c_wow_gtk_ofld(struct rtw89_dev *rtwdev,
+ skb_put(skb, len);
+ h2c = (struct rtw89_h2c_wow_gtk_ofld *)skb->data;
+
+- if (!enable) {
+- skb_put_zero(skb, sizeof(*gtk_info));
++ if (!enable)
+ goto hdr;
+- }
+
+ ret = rtw89_fw_h2c_add_general_pkt(rtwdev, rtwvif,
+ RTW89_PKT_OFLD_TYPE_EAPOL_KEY,
+diff --git a/drivers/net/wireless/realtek/rtw89/mac.c b/drivers/net/wireless/realtek/rtw89/mac.c
+index 3fe0046f6eaa2..185b9cd283ed4 100644
+--- a/drivers/net/wireless/realtek/rtw89/mac.c
++++ b/drivers/net/wireless/realtek/rtw89/mac.c
+@@ -4757,6 +4757,9 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb,
+ }
+ return;
+ case RTW89_SCAN_END_SCAN_NOTIFY:
++ if (rtwdev->scan_info.abort)
++ return;
++
+ if (rtwvif && rtwvif->scan_req &&
+ last_chan < rtwvif->scan_req->n_channels) {
+ ret = rtw89_hw_scan_offload(rtwdev, vif, true);
+@@ -4765,7 +4768,7 @@ rtw89_mac_c2h_scanofld_rsp(struct rtw89_dev *rtwdev, struct sk_buff *skb,
+ rtw89_warn(rtwdev, "HW scan failed: %d\n", ret);
+ }
+ } else {
+- rtw89_hw_scan_complete(rtwdev, vif, rtwdev->scan_info.abort);
++ rtw89_hw_scan_complete(rtwdev, vif, false);
+ }
+ break;
+ case RTW89_SCAN_ENTER_OP_NOTIFY:
+diff --git a/drivers/net/wireless/realtek/rtw89/pci.c b/drivers/net/wireless/realtek/rtw89/pci.c
+index 03bbcf9b6737c..b36aa9a6bb3fc 100644
+--- a/drivers/net/wireless/realtek/rtw89/pci.c
++++ b/drivers/net/wireless/realtek/rtw89/pci.c
+@@ -2330,21 +2330,20 @@ static void rtw89_pci_disable_eq(struct rtw89_dev *rtwdev)
+ u32 backup_aspm;
+ u32 phy_offset;
+ u16 oobs_val;
+- u16 val16;
+ int ret;
+
+ if (rtwdev->chip->chip_id != RTL8852C)
+ return;
+
+- backup_aspm = rtw89_read32(rtwdev, R_AX_PCIE_MIX_CFG_V1);
+- rtw89_write32_clr(rtwdev, R_AX_PCIE_MIX_CFG_V1, B_AX_ASPM_CTRL_MASK);
+-
+ g1_oobs = rtw89_read16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G1 +
+ RAC_ANA09 * RAC_MULT, BAC_OOBS_SEL);
+ g2_oobs = rtw89_read16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G2 +
+ RAC_ANA09 * RAC_MULT, BAC_OOBS_SEL);
+ if (g1_oobs && g2_oobs)
+- goto out;
++ return;
++
++ backup_aspm = rtw89_read32(rtwdev, R_AX_PCIE_MIX_CFG_V1);
++ rtw89_write32_clr(rtwdev, R_AX_PCIE_MIX_CFG_V1, B_AX_ASPM_CTRL_MASK);
+
+ ret = rtw89_pci_get_phy_offset_by_link_speed(rtwdev, &phy_offset);
+ if (ret)
+@@ -2354,15 +2353,16 @@ static void rtw89_pci_disable_eq(struct rtw89_dev *rtwdev)
+ rtw89_write16(rtwdev, phy_offset + RAC_ANA10 * RAC_MULT, ADDR_SEL_PINOUT_DIS_VAL);
+ rtw89_write16_set(rtwdev, phy_offset + RAC_ANA19 * RAC_MULT, B_PCIE_BIT_RD_SEL);
+
+- val16 = rtw89_read16_mask(rtwdev, phy_offset + RAC_ANA1F * RAC_MULT,
+- OOBS_LEVEL_MASK);
+- oobs_val = u16_encode_bits(val16, OOBS_SEN_MASK);
++ oobs_val = rtw89_read16_mask(rtwdev, phy_offset + RAC_ANA1F * RAC_MULT,
++ OOBS_LEVEL_MASK);
+
+- rtw89_write16(rtwdev, R_RAC_DIRECT_OFFSET_G1 + RAC_ANA03 * RAC_MULT, oobs_val);
++ rtw89_write16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G1 + RAC_ANA03 * RAC_MULT,
++ OOBS_SEN_MASK, oobs_val);
+ rtw89_write16_set(rtwdev, R_RAC_DIRECT_OFFSET_G1 + RAC_ANA09 * RAC_MULT,
+ BAC_OOBS_SEL);
+
+- rtw89_write16(rtwdev, R_RAC_DIRECT_OFFSET_G2 + RAC_ANA03 * RAC_MULT, oobs_val);
++ rtw89_write16_mask(rtwdev, R_RAC_DIRECT_OFFSET_G2 + RAC_ANA03 * RAC_MULT,
++ OOBS_SEN_MASK, oobs_val);
+ rtw89_write16_set(rtwdev, R_RAC_DIRECT_OFFSET_G2 + RAC_ANA09 * RAC_MULT,
+ BAC_OOBS_SEL);
+
+@@ -2783,7 +2783,6 @@ static int rtw89_pci_ops_mac_pre_init_ax(struct rtw89_dev *rtwdev)
+ const struct rtw89_pci_info *info = rtwdev->pci_info;
+ int ret;
+
+- rtw89_pci_disable_eq(rtwdev);
+ rtw89_pci_ber(rtwdev);
+ rtw89_pci_rxdma_prefth(rtwdev);
+ rtw89_pci_l1off_pwroff(rtwdev);
+@@ -4155,6 +4154,7 @@ static int __maybe_unused rtw89_pci_resume(struct device *dev)
+ B_AX_SEL_REQ_ENTR_L1);
+ }
+ rtw89_pci_l2_hci_ldo(rtwdev);
++ rtw89_pci_disable_eq(rtwdev);
+ rtw89_pci_filter_out(rtwdev);
+ rtw89_pci_link_cfg(rtwdev);
+ rtw89_pci_l1ss_cfg(rtwdev);
+@@ -4289,6 +4289,7 @@ int rtw89_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+ goto err_clear_resource;
+ }
+
++ rtw89_pci_disable_eq(rtwdev);
+ rtw89_pci_filter_out(rtwdev);
+ rtw89_pci_link_cfg(rtwdev);
+ rtw89_pci_l1ss_cfg(rtwdev);
+diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b.c b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+index d351096fa4b41..767de9a2de7e4 100644
+--- a/drivers/net/wireless/realtek/rtw89/rtw8852b.c
++++ b/drivers/net/wireless/realtek/rtw89/rtw8852b.c
+@@ -403,6 +403,8 @@ static int rtw8852b_pwr_on_func(struct rtw89_dev *rtwdev)
+ u32 val32;
+ u32 ret;
+
++ rtw8852b_pwr_sps_ana(rtwdev);
++
+ rtw89_write32_clr(rtwdev, R_AX_SYS_PW_CTRL, B_AX_AFSM_WLSUS_EN |
+ B_AX_AFSM_PCIE_SUS_EN);
+ rtw89_write32_set(rtwdev, R_AX_SYS_PW_CTRL, B_AX_DIS_WLBT_PDNSUSEN_SOPC);
+@@ -530,9 +532,7 @@ static int rtw8852b_pwr_off_func(struct rtw89_dev *rtwdev)
+ u32 val32;
+ u32 ret;
+
+- /* Only do once during probe stage after reading efuse */
+- if (!test_bit(RTW89_FLAG_PROBE_DONE, rtwdev->flags))
+- rtw8852b_pwr_sps_ana(rtwdev);
++ rtw8852b_pwr_sps_ana(rtwdev);
+
+ ret = rtw89_mac_write_xtal_si(rtwdev, XTAL_SI_ANAPAR_WL, XTAL_SI_RFC2RF,
+ XTAL_SI_RFC2RF);
+diff --git a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
+index 259df67836a0e..a2fa1d339bc21 100644
+--- a/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
++++ b/drivers/net/wireless/realtek/rtw89/rtw8852b_rfk.c
+@@ -20,7 +20,7 @@
+ #define RTW8852B_RF_REL_VERSION 34
+ #define RTW8852B_DPK_VER 0x0d
+ #define RTW8852B_DPK_RF_PATH 2
+-#define RTW8852B_DPK_KIP_REG_NUM 2
++#define RTW8852B_DPK_KIP_REG_NUM 3
+
+ #define _TSSI_DE_MASK GENMASK(21, 12)
+ #define ADDC_T_AVG 100
+diff --git a/drivers/net/wireless/virtual/virt_wifi.c b/drivers/net/wireless/virtual/virt_wifi.c
+index 6a84ec58d618b..4ee3740804667 100644
+--- a/drivers/net/wireless/virtual/virt_wifi.c
++++ b/drivers/net/wireless/virtual/virt_wifi.c
+@@ -136,6 +136,9 @@ static struct ieee80211_supported_band band_5ghz = {
+ /* Assigned at module init. Guaranteed locally-administered and unicast. */
+ static u8 fake_router_bssid[ETH_ALEN] __ro_after_init = {};
+
++#define VIRT_WIFI_SSID "VirtWifi"
++#define VIRT_WIFI_SSID_LEN 8
++
+ static void virt_wifi_inform_bss(struct wiphy *wiphy)
+ {
+ u64 tsf = div_u64(ktime_get_boottime_ns(), 1000);
+@@ -146,8 +149,8 @@ static void virt_wifi_inform_bss(struct wiphy *wiphy)
+ u8 ssid[8];
+ } __packed ssid = {
+ .tag = WLAN_EID_SSID,
+- .len = 8,
+- .ssid = "VirtWifi",
++ .len = VIRT_WIFI_SSID_LEN,
++ .ssid = VIRT_WIFI_SSID,
+ };
+
+ informed_bss = cfg80211_inform_bss(wiphy, &channel_5ghz,
+@@ -213,6 +216,8 @@ struct virt_wifi_netdev_priv {
+ struct net_device *upperdev;
+ u32 tx_packets;
+ u32 tx_failed;
++ u32 connect_requested_ssid_len;
++ u8 connect_requested_ssid[IEEE80211_MAX_SSID_LEN];
+ u8 connect_requested_bss[ETH_ALEN];
+ bool is_up;
+ bool is_connected;
+@@ -229,6 +234,12 @@ static int virt_wifi_connect(struct wiphy *wiphy, struct net_device *netdev,
+ if (priv->being_deleted || !priv->is_up)
+ return -EBUSY;
+
++ if (!sme->ssid)
++ return -EINVAL;
++
++ priv->connect_requested_ssid_len = sme->ssid_len;
++ memcpy(priv->connect_requested_ssid, sme->ssid, sme->ssid_len);
++
+ could_schedule = schedule_delayed_work(&priv->connect, HZ * 2);
+ if (!could_schedule)
+ return -EBUSY;
+@@ -252,12 +263,15 @@ static void virt_wifi_connect_complete(struct work_struct *work)
+ container_of(work, struct virt_wifi_netdev_priv, connect.work);
+ u8 *requested_bss = priv->connect_requested_bss;
+ bool right_addr = ether_addr_equal(requested_bss, fake_router_bssid);
++ bool right_ssid = priv->connect_requested_ssid_len == VIRT_WIFI_SSID_LEN &&
++ !memcmp(priv->connect_requested_ssid, VIRT_WIFI_SSID,
++ priv->connect_requested_ssid_len);
+ u16 status = WLAN_STATUS_SUCCESS;
+
+ if (is_zero_ether_addr(requested_bss))
+ requested_bss = NULL;
+
+- if (!priv->is_up || (requested_bss && !right_addr))
++ if (!priv->is_up || (requested_bss && !right_addr) || !right_ssid)
+ status = WLAN_STATUS_UNSPECIFIED_FAILURE;
+ else
+ priv->is_connected = true;
+diff --git a/drivers/nvme/host/pci.c b/drivers/nvme/host/pci.c
+index 102a9fb0c65ff..5a93f021ca4f1 100644
+--- a/drivers/nvme/host/pci.c
++++ b/drivers/nvme/host/pci.c
+@@ -863,7 +863,8 @@ static blk_status_t nvme_prep_rq(struct nvme_dev *dev, struct request *req)
+ nvme_start_request(req);
+ return BLK_STS_OK;
+ out_unmap_data:
+- nvme_unmap_data(dev, req);
++ if (blk_rq_nr_phys_segments(req))
++ nvme_unmap_data(dev, req);
+ out_free_cmd:
+ nvme_cleanup_cmd(req);
+ return ret;
+@@ -1274,7 +1275,7 @@ static void nvme_warn_reset(struct nvme_dev *dev, u32 csts)
+ dev_warn(dev->ctrl.device,
+ "Does your device have a faulty power saving mode enabled?\n");
+ dev_warn(dev->ctrl.device,
+- "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off\" and report a bug\n");
++ "Try \"nvme_core.default_ps_max_latency_us=0 pcie_aspm=off pcie_port_pm=off\" and report a bug\n");
+ }
+
+ static enum blk_eh_timer_return nvme_timeout(struct request *req)
+diff --git a/drivers/nvme/target/auth.c b/drivers/nvme/target/auth.c
+index 7d2633940f9b8..8bc3f431c77f6 100644
+--- a/drivers/nvme/target/auth.c
++++ b/drivers/nvme/target/auth.c
+@@ -314,7 +314,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
+ req->sq->dhchap_c1,
+ challenge, shash_len);
+ if (ret)
+- goto out_free_response;
++ goto out_free_challenge;
+ }
+
+ pr_debug("ctrl %d qid %d host response seq %u transaction %d\n",
+@@ -325,7 +325,7 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
+ GFP_KERNEL);
+ if (!shash) {
+ ret = -ENOMEM;
+- goto out_free_response;
++ goto out_free_challenge;
+ }
+ shash->tfm = shash_tfm;
+ ret = crypto_shash_init(shash);
+@@ -361,9 +361,10 @@ int nvmet_auth_host_hash(struct nvmet_req *req, u8 *response,
+ goto out;
+ ret = crypto_shash_final(shash, response);
+ out:
++ kfree(shash);
++out_free_challenge:
+ if (challenge != req->sq->dhchap_c1)
+ kfree(challenge);
+- kfree(shash);
+ out_free_response:
+ nvme_auth_free_key(transformed_key);
+ out_free_tfm:
+@@ -427,14 +428,14 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
+ req->sq->dhchap_c2,
+ challenge, shash_len);
+ if (ret)
+- goto out_free_response;
++ goto out_free_challenge;
+ }
+
+ shash = kzalloc(sizeof(*shash) + crypto_shash_descsize(shash_tfm),
+ GFP_KERNEL);
+ if (!shash) {
+ ret = -ENOMEM;
+- goto out_free_response;
++ goto out_free_challenge;
+ }
+ shash->tfm = shash_tfm;
+
+@@ -471,9 +472,10 @@ int nvmet_auth_ctrl_hash(struct nvmet_req *req, u8 *response,
+ goto out;
+ ret = crypto_shash_final(shash, response);
+ out:
++ kfree(shash);
++out_free_challenge:
+ if (challenge != req->sq->dhchap_c2)
+ kfree(challenge);
+- kfree(shash);
+ out_free_response:
+ nvme_auth_free_key(transformed_key);
+ out_free_tfm:
+diff --git a/drivers/nvmem/rockchip-otp.c b/drivers/nvmem/rockchip-otp.c
+index cb9aa5428350a..7107d68a2f8c7 100644
+--- a/drivers/nvmem/rockchip-otp.c
++++ b/drivers/nvmem/rockchip-otp.c
+@@ -255,6 +255,7 @@ static int rockchip_otp_read(void *context, unsigned int offset,
+ static struct nvmem_config otp_config = {
+ .name = "rockchip-otp",
+ .owner = THIS_MODULE,
++ .add_legacy_fixed_of_cells = true,
+ .read_only = true,
+ .stride = 1,
+ .word_size = 1,
+diff --git a/drivers/opp/core.c b/drivers/opp/core.c
+index cb4611fe1b5b2..4e4d293bf5b10 100644
+--- a/drivers/opp/core.c
++++ b/drivers/opp/core.c
+@@ -2443,8 +2443,10 @@ static int _opp_attach_genpd(struct opp_table *opp_table, struct device *dev,
+ * Cross check it again and fix if required.
+ */
+ gdev = dev_to_genpd_dev(virt_dev);
+- if (IS_ERR(gdev))
+- return PTR_ERR(gdev);
++ if (IS_ERR(gdev)) {
++ ret = PTR_ERR(gdev);
++ goto err;
++ }
+
+ genpd_table = _find_opp_table(gdev);
+ if (!IS_ERR(genpd_table)) {
+diff --git a/drivers/opp/ti-opp-supply.c b/drivers/opp/ti-opp-supply.c
+index e3b97cd1fbbf3..ec0056a4bb135 100644
+--- a/drivers/opp/ti-opp-supply.c
++++ b/drivers/opp/ti-opp-supply.c
+@@ -393,10 +393,12 @@ static int ti_opp_supply_probe(struct platform_device *pdev)
+ }
+
+ ret = dev_pm_opp_set_config_regulators(cpu_dev, ti_opp_config_regulators);
+- if (ret < 0)
++ if (ret < 0) {
+ _free_optimized_voltages(dev, &opp_data);
++ return ret;
++ }
+
+- return ret;
++ return 0;
+ }
+
+ static struct platform_driver ti_opp_supply_driver = {
+diff --git a/drivers/parport/procfs.c b/drivers/parport/procfs.c
+index bd388560ed592..c2e371c50dcfa 100644
+--- a/drivers/parport/procfs.c
++++ b/drivers/parport/procfs.c
+@@ -51,12 +51,12 @@ static int do_active_device(struct ctl_table *table, int write,
+
+ for (dev = port->devices; dev ; dev = dev->next) {
+ if(dev == port->cad) {
+- len += sprintf(buffer, "%s\n", dev->name);
++ len += snprintf(buffer, sizeof(buffer), "%s\n", dev->name);
+ }
+ }
+
+ if(!len) {
+- len += sprintf(buffer, "%s\n", "none");
++ len += snprintf(buffer, sizeof(buffer), "%s\n", "none");
+ }
+
+ if (len > *lenp)
+@@ -87,19 +87,19 @@ static int do_autoprobe(struct ctl_table *table, int write,
+ }
+
+ if ((str = info->class_name) != NULL)
+- len += sprintf (buffer + len, "CLASS:%s;\n", str);
++ len += snprintf (buffer + len, sizeof(buffer) - len, "CLASS:%s;\n", str);
+
+ if ((str = info->model) != NULL)
+- len += sprintf (buffer + len, "MODEL:%s;\n", str);
++ len += snprintf (buffer + len, sizeof(buffer) - len, "MODEL:%s;\n", str);
+
+ if ((str = info->mfr) != NULL)
+- len += sprintf (buffer + len, "MANUFACTURER:%s;\n", str);
++ len += snprintf (buffer + len, sizeof(buffer) - len, "MANUFACTURER:%s;\n", str);
+
+ if ((str = info->description) != NULL)
+- len += sprintf (buffer + len, "DESCRIPTION:%s;\n", str);
++ len += snprintf (buffer + len, sizeof(buffer) - len, "DESCRIPTION:%s;\n", str);
+
+ if ((str = info->cmdset) != NULL)
+- len += sprintf (buffer + len, "COMMAND SET:%s;\n", str);
++ len += snprintf (buffer + len, sizeof(buffer) - len, "COMMAND SET:%s;\n", str);
+
+ if (len > *lenp)
+ len = *lenp;
+@@ -117,7 +117,7 @@ static int do_hardware_base_addr(struct ctl_table *table, int write,
+ void *result, size_t *lenp, loff_t *ppos)
+ {
+ struct parport *port = (struct parport *)table->extra1;
+- char buffer[20];
++ char buffer[64];
+ int len = 0;
+
+ if (*ppos) {
+@@ -128,7 +128,7 @@ static int do_hardware_base_addr(struct ctl_table *table, int write,
+ if (write) /* permissions prevent this anyway */
+ return -EACCES;
+
+- len += sprintf (buffer, "%lu\t%lu\n", port->base, port->base_hi);
++ len += snprintf (buffer, sizeof(buffer), "%lu\t%lu\n", port->base, port->base_hi);
+
+ if (len > *lenp)
+ len = *lenp;
+@@ -155,7 +155,7 @@ static int do_hardware_irq(struct ctl_table *table, int write,
+ if (write) /* permissions prevent this anyway */
+ return -EACCES;
+
+- len += sprintf (buffer, "%d\n", port->irq);
++ len += snprintf (buffer, sizeof(buffer), "%d\n", port->irq);
+
+ if (len > *lenp)
+ len = *lenp;
+@@ -182,7 +182,7 @@ static int do_hardware_dma(struct ctl_table *table, int write,
+ if (write) /* permissions prevent this anyway */
+ return -EACCES;
+
+- len += sprintf (buffer, "%d\n", port->dma);
++ len += snprintf (buffer, sizeof(buffer), "%d\n", port->dma);
+
+ if (len > *lenp)
+ len = *lenp;
+@@ -213,7 +213,7 @@ static int do_hardware_modes(struct ctl_table *table, int write,
+ #define printmode(x) \
+ do { \
+ if (port->modes & PARPORT_MODE_##x) \
+- len += sprintf(buffer + len, "%s%s", f++ ? "," : "", #x); \
++ len += snprintf(buffer + len, sizeof(buffer) - len, "%s%s", f++ ? "," : "", #x); \
+ } while (0)
+ int f = 0;
+ printmode(PCSPP);
+diff --git a/drivers/pci/controller/dwc/pci-keystone.c b/drivers/pci/controller/dwc/pci-keystone.c
+index d3a7d14ee685a..cd0e0022f91d6 100644
+--- a/drivers/pci/controller/dwc/pci-keystone.c
++++ b/drivers/pci/controller/dwc/pci-keystone.c
+@@ -245,8 +245,68 @@ static struct irq_chip ks_pcie_msi_irq_chip = {
+ .irq_unmask = ks_pcie_msi_unmask,
+ };
+
++/**
++ * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask registers
++ * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone
++ * PCIe host controller driver information.
++ *
++ * Since modification of dbi_cs2 involves different clock domain, read the
++ * status back to ensure the transition is complete.
++ */
++static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie)
++{
++ u32 val;
++
++ val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
++ val |= DBI_CS2;
++ ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
++
++ do {
++ val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
++ } while (!(val & DBI_CS2));
++}
++
++/**
++ * ks_pcie_clear_dbi_mode() - Disable DBI mode
++ * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone
++ * PCIe host controller driver information.
++ *
++ * Since modification of dbi_cs2 involves different clock domain, read the
++ * status back to ensure the transition is complete.
++ */
++static void ks_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie)
++{
++ u32 val;
++
++ val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
++ val &= ~DBI_CS2;
++ ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
++
++ do {
++ val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
++ } while (val & DBI_CS2);
++}
++
+ static int ks_pcie_msi_host_init(struct dw_pcie_rp *pp)
+ {
++ struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
++ struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
++
++ /* Configure and set up BAR0 */
++ ks_pcie_set_dbi_mode(ks_pcie);
++
++ /* Enable BAR0 */
++ dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1);
++ dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1);
++
++ ks_pcie_clear_dbi_mode(ks_pcie);
++
++ /*
++ * For BAR0, just setting bus address for inbound writes (MSI) should
++ * be sufficient. Use physical address to avoid any conflicts.
++ */
++ dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start);
++
+ pp->msi_irq_chip = &ks_pcie_msi_irq_chip;
+ return dw_pcie_allocate_domains(pp);
+ }
+@@ -340,59 +400,22 @@ static const struct irq_domain_ops ks_pcie_intx_irq_domain_ops = {
+ .xlate = irq_domain_xlate_onetwocell,
+ };
+
+-/**
+- * ks_pcie_set_dbi_mode() - Set DBI mode to access overlaid BAR mask registers
+- * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone
+- * PCIe host controller driver information.
+- *
+- * Since modification of dbi_cs2 involves different clock domain, read the
+- * status back to ensure the transition is complete.
+- */
+-static void ks_pcie_set_dbi_mode(struct keystone_pcie *ks_pcie)
+-{
+- u32 val;
+-
+- val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+- val |= DBI_CS2;
+- ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+-
+- do {
+- val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+- } while (!(val & DBI_CS2));
+-}
+-
+-/**
+- * ks_pcie_clear_dbi_mode() - Disable DBI mode
+- * @ks_pcie: A pointer to the keystone_pcie structure which holds the KeyStone
+- * PCIe host controller driver information.
+- *
+- * Since modification of dbi_cs2 involves different clock domain, read the
+- * status back to ensure the transition is complete.
+- */
+-static void ks_pcie_clear_dbi_mode(struct keystone_pcie *ks_pcie)
+-{
+- u32 val;
+-
+- val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+- val &= ~DBI_CS2;
+- ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
+-
+- do {
+- val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+- } while (val & DBI_CS2);
+-}
+-
+-static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
++static int ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
+ {
+ u32 val;
+ u32 num_viewport = ks_pcie->num_viewport;
+ struct dw_pcie *pci = ks_pcie->pci;
+ struct dw_pcie_rp *pp = &pci->pp;
+- u64 start, end;
++ struct resource_entry *entry;
+ struct resource *mem;
++ u64 start, end;
+ int i;
+
+- mem = resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM)->res;
++ entry = resource_list_first_type(&pp->bridge->windows, IORESOURCE_MEM);
++ if (!entry)
++ return -ENODEV;
++
++ mem = entry->res;
+ start = mem->start;
+ end = mem->end;
+
+@@ -403,7 +426,7 @@ static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
+ ks_pcie_clear_dbi_mode(ks_pcie);
+
+ if (ks_pcie->is_am6)
+- return;
++ return 0;
+
+ val = ilog2(OB_WIN_SIZE);
+ ks_pcie_app_writel(ks_pcie, OB_SIZE, val);
+@@ -420,6 +443,8 @@ static void ks_pcie_setup_rc_app_regs(struct keystone_pcie *ks_pcie)
+ val = ks_pcie_app_readl(ks_pcie, CMD_STATUS);
+ val |= OB_XLAT_EN_VAL;
+ ks_pcie_app_writel(ks_pcie, CMD_STATUS, val);
++
++ return 0;
+ }
+
+ static void __iomem *ks_pcie_other_map_bus(struct pci_bus *bus,
+@@ -445,44 +470,10 @@ static struct pci_ops ks_child_pcie_ops = {
+ .write = pci_generic_config_write,
+ };
+
+-/**
+- * ks_pcie_v3_65_add_bus() - keystone add_bus post initialization
+- * @bus: A pointer to the PCI bus structure.
+- *
+- * This sets BAR0 to enable inbound access for MSI_IRQ register
+- */
+-static int ks_pcie_v3_65_add_bus(struct pci_bus *bus)
+-{
+- struct dw_pcie_rp *pp = bus->sysdata;
+- struct dw_pcie *pci = to_dw_pcie_from_pp(pp);
+- struct keystone_pcie *ks_pcie = to_keystone_pcie(pci);
+-
+- if (!pci_is_root_bus(bus))
+- return 0;
+-
+- /* Configure and set up BAR0 */
+- ks_pcie_set_dbi_mode(ks_pcie);
+-
+- /* Enable BAR0 */
+- dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, 1);
+- dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, SZ_4K - 1);
+-
+- ks_pcie_clear_dbi_mode(ks_pcie);
+-
+- /*
+- * For BAR0, just setting bus address for inbound writes (MSI) should
+- * be sufficient. Use physical address to avoid any conflicts.
+- */
+- dw_pcie_writel_dbi(pci, PCI_BASE_ADDRESS_0, ks_pcie->app.start);
+-
+- return 0;
+-}
+-
+ static struct pci_ops ks_pcie_ops = {
+ .map_bus = dw_pcie_own_conf_map_bus,
+ .read = pci_generic_config_read,
+ .write = pci_generic_config_write,
+- .add_bus = ks_pcie_v3_65_add_bus,
+ };
+
+ /**
+@@ -814,7 +805,10 @@ static int __init ks_pcie_host_init(struct dw_pcie_rp *pp)
+ return ret;
+
+ ks_pcie_stop_link(pci);
+- ks_pcie_setup_rc_app_regs(ks_pcie);
++ ret = ks_pcie_setup_rc_app_regs(ks_pcie);
++ if (ret)
++ return ret;
++
+ writew(PCI_IO_RANGE_TYPE_32 | (PCI_IO_RANGE_TYPE_32 << 8),
+ pci->dbi_base + PCI_IO_BASE);
+
+diff --git a/drivers/pci/controller/dwc/pcie-designware-ep.c b/drivers/pci/controller/dwc/pcie-designware-ep.c
+index 47391d7d3a734..769e848246870 100644
+--- a/drivers/pci/controller/dwc/pcie-designware-ep.c
++++ b/drivers/pci/controller/dwc/pcie-designware-ep.c
+@@ -161,7 +161,7 @@ static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type,
+ if (!ep->bar_to_atu[bar])
+ free_win = find_first_zero_bit(ep->ib_window_map, pci->num_ib_windows);
+ else
+- free_win = ep->bar_to_atu[bar];
++ free_win = ep->bar_to_atu[bar] - 1;
+
+ if (free_win >= pci->num_ib_windows) {
+ dev_err(pci->dev, "No free inbound window\n");
+@@ -175,7 +175,11 @@ static int dw_pcie_ep_inbound_atu(struct dw_pcie_ep *ep, u8 func_no, int type,
+ return ret;
+ }
+
+- ep->bar_to_atu[bar] = free_win;
++ /*
++ * Always increment free_win before assignment, since value 0 is used to identify
++ * unallocated mapping.
++ */
++ ep->bar_to_atu[bar] = free_win + 1;
+ set_bit(free_win, ep->ib_window_map);
+
+ return 0;
+@@ -212,7 +216,10 @@ static void dw_pcie_ep_clear_bar(struct pci_epc *epc, u8 func_no, u8 vfunc_no,
+ struct dw_pcie_ep *ep = epc_get_drvdata(epc);
+ struct dw_pcie *pci = to_dw_pcie_from_ep(ep);
+ enum pci_barno bar = epf_bar->barno;
+- u32 atu_index = ep->bar_to_atu[bar];
++ u32 atu_index = ep->bar_to_atu[bar] - 1;
++
++ if (!ep->bar_to_atu[bar])
++ return;
+
+ __dw_pcie_ep_reset_bar(pci, func_no, bar, epf_bar->flags);
+
+diff --git a/drivers/pci/controller/dwc/pcie-dw-rockchip.c b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+index d6842141d384d..a909e42b4273e 100644
+--- a/drivers/pci/controller/dwc/pcie-dw-rockchip.c
++++ b/drivers/pci/controller/dwc/pcie-dw-rockchip.c
+@@ -240,7 +240,7 @@ static int rockchip_pcie_resource_get(struct platform_device *pdev,
+ return PTR_ERR(rockchip->apb_base);
+
+ rockchip->rst_gpio = devm_gpiod_get_optional(&pdev->dev, "reset",
+- GPIOD_OUT_HIGH);
++ GPIOD_OUT_LOW);
+ if (IS_ERR(rockchip->rst_gpio))
+ return PTR_ERR(rockchip->rst_gpio);
+
+diff --git a/drivers/pci/controller/dwc/pcie-qcom-ep.c b/drivers/pci/controller/dwc/pcie-qcom-ep.c
+index 2fb8c15e7a911..50b1635e3cbb1 100644
+--- a/drivers/pci/controller/dwc/pcie-qcom-ep.c
++++ b/drivers/pci/controller/dwc/pcie-qcom-ep.c
+@@ -500,12 +500,6 @@ static int qcom_pcie_perst_deassert(struct dw_pcie *pci)
+ static void qcom_pcie_perst_assert(struct dw_pcie *pci)
+ {
+ struct qcom_pcie_ep *pcie_ep = to_pcie_ep(pci);
+- struct device *dev = pci->dev;
+-
+- if (pcie_ep->link_status == QCOM_PCIE_EP_LINK_DISABLED) {
+- dev_dbg(dev, "Link is already disabled\n");
+- return;
+- }
+
+ dw_pcie_ep_cleanup(&pci->ep);
+ qcom_pcie_disable_resources(pcie_ep);
+diff --git a/drivers/pci/controller/dwc/pcie-tegra194.c b/drivers/pci/controller/dwc/pcie-tegra194.c
+index 93f5433c5c550..4537313ef37a9 100644
+--- a/drivers/pci/controller/dwc/pcie-tegra194.c
++++ b/drivers/pci/controller/dwc/pcie-tegra194.c
+@@ -2015,6 +2015,7 @@ static const struct pci_epc_features tegra_pcie_epc_features = {
+ .bar[BAR_3] = { .type = BAR_RESERVED, },
+ .bar[BAR_4] = { .type = BAR_RESERVED, },
+ .bar[BAR_5] = { .type = BAR_RESERVED, },
++ .align = SZ_64K,
+ };
+
+ static const struct pci_epc_features*
+diff --git a/drivers/pci/controller/pci-hyperv.c b/drivers/pci/controller/pci-hyperv.c
+index 5992280e8110b..cdd5be16021dd 100644
+--- a/drivers/pci/controller/pci-hyperv.c
++++ b/drivers/pci/controller/pci-hyperv.c
+@@ -1130,8 +1130,8 @@ static void _hv_pcifront_read_config(struct hv_pci_dev *hpdev, int where,
+ PCI_CAPABILITY_LIST) {
+ /* ROM BARs are unimplemented */
+ *val = 0;
+- } else if (where >= PCI_INTERRUPT_LINE && where + size <=
+- PCI_INTERRUPT_PIN) {
++ } else if ((where >= PCI_INTERRUPT_LINE && where + size <= PCI_INTERRUPT_PIN) ||
++ (where >= PCI_INTERRUPT_PIN && where + size <= PCI_MIN_GNT)) {
+ /*
+ * Interrupt Line and Interrupt PIN are hard-wired to zero
+ * because this front-end only supports message-signaled
+diff --git a/drivers/pci/controller/pci-loongson.c b/drivers/pci/controller/pci-loongson.c
+index 8b34ccff073a9..bc630ab8a2831 100644
+--- a/drivers/pci/controller/pci-loongson.c
++++ b/drivers/pci/controller/pci-loongson.c
+@@ -163,6 +163,19 @@ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+ DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON,
+ DEV_LS7A_HDMI, loongson_pci_pin_quirk);
+
++static void loongson_pci_msi_quirk(struct pci_dev *dev)
++{
++ u16 val, class = dev->class >> 8;
++
++ if (class != PCI_CLASS_BRIDGE_HOST)
++ return;
++
++ pci_read_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, &val);
++ val |= PCI_MSI_FLAGS_ENABLE;
++ pci_write_config_word(dev, dev->msi_cap + PCI_MSI_FLAGS, val);
++}
++DECLARE_PCI_FIXUP_FINAL(PCI_VENDOR_ID_LOONGSON, DEV_LS7A_PCIE_PORT5, loongson_pci_msi_quirk);
++
+ static struct loongson_pci *pci_bus_to_loongson_pci(struct pci_bus *bus)
+ {
+ struct pci_config_window *cfg;
+diff --git a/drivers/pci/controller/pcie-rcar-host.c b/drivers/pci/controller/pcie-rcar-host.c
+index 996077ab7cfdb..c01efc6ea64f6 100644
+--- a/drivers/pci/controller/pcie-rcar-host.c
++++ b/drivers/pci/controller/pcie-rcar-host.c
+@@ -78,7 +78,11 @@ static int rcar_pcie_wakeup(struct device *pcie_dev, void __iomem *pcie_base)
+ writel(L1IATN, pcie_base + PMCTLR);
+ ret = readl_poll_timeout_atomic(pcie_base + PMSR, val,
+ val & L1FAEG, 10, 1000);
+- WARN(ret, "Timeout waiting for L1 link state, ret=%d\n", ret);
++ if (ret) {
++ dev_warn_ratelimited(pcie_dev,
++ "Timeout waiting for L1 link state, ret=%d\n",
++ ret);
++ }
+ writel(L1FAEG | PMEL1RX, pcie_base + PMSR);
+ }
+
+diff --git a/drivers/pci/controller/pcie-rockchip.c b/drivers/pci/controller/pcie-rockchip.c
+index 0ef2e622d36e1..c07d7129f1c7c 100644
+--- a/drivers/pci/controller/pcie-rockchip.c
++++ b/drivers/pci/controller/pcie-rockchip.c
+@@ -121,7 +121,7 @@ int rockchip_pcie_parse_dt(struct rockchip_pcie *rockchip)
+
+ if (rockchip->is_rc) {
+ rockchip->ep_gpio = devm_gpiod_get_optional(dev, "ep",
+- GPIOD_OUT_HIGH);
++ GPIOD_OUT_LOW);
+ if (IS_ERR(rockchip->ep_gpio))
+ return dev_err_probe(dev, PTR_ERR(rockchip->ep_gpio),
+ "failed to get ep GPIO\n");
+diff --git a/drivers/pci/endpoint/functions/pci-epf-test.c b/drivers/pci/endpoint/functions/pci-epf-test.c
+index 977fb79c15677..546d2a27955cf 100644
+--- a/drivers/pci/endpoint/functions/pci-epf-test.c
++++ b/drivers/pci/endpoint/functions/pci-epf-test.c
+@@ -735,20 +735,12 @@ static int pci_epf_test_core_init(struct pci_epf *epf)
+ {
+ struct pci_epf_test *epf_test = epf_get_drvdata(epf);
+ struct pci_epf_header *header = epf->header;
+- const struct pci_epc_features *epc_features;
++ const struct pci_epc_features *epc_features = epf_test->epc_features;
+ struct pci_epc *epc = epf->epc;
+ struct device *dev = &epf->dev;
+ bool linkup_notifier = false;
+- bool msix_capable = false;
+- bool msi_capable = true;
+ int ret;
+
+- epc_features = pci_epc_get_features(epc, epf->func_no, epf->vfunc_no);
+- if (epc_features) {
+- msix_capable = epc_features->msix_capable;
+- msi_capable = epc_features->msi_capable;
+- }
+-
+ if (epf->vfunc_no <= 1) {
+ ret = pci_epc_write_header(epc, epf->func_no, epf->vfunc_no, header);
+ if (ret) {
+@@ -761,7 +753,7 @@ static int pci_epf_test_core_init(struct pci_epf *epf)
+ if (ret)
+ return ret;
+
+- if (msi_capable) {
++ if (epc_features->msi_capable) {
+ ret = pci_epc_set_msi(epc, epf->func_no, epf->vfunc_no,
+ epf->msi_interrupts);
+ if (ret) {
+@@ -770,7 +762,7 @@ static int pci_epf_test_core_init(struct pci_epf *epf)
+ }
+ }
+
+- if (msix_capable) {
++ if (epc_features->msix_capable) {
+ ret = pci_epc_set_msix(epc, epf->func_no, epf->vfunc_no,
+ epf->msix_interrupts,
+ epf_test->test_reg_bar,
+diff --git a/drivers/pci/endpoint/functions/pci-epf-vntb.c b/drivers/pci/endpoint/functions/pci-epf-vntb.c
+index 8e779eecd62d4..874cb097b093a 100644
+--- a/drivers/pci/endpoint/functions/pci-epf-vntb.c
++++ b/drivers/pci/endpoint/functions/pci-epf-vntb.c
+@@ -799,8 +799,9 @@ static int epf_ntb_epc_init(struct epf_ntb *ntb)
+ */
+ static void epf_ntb_epc_cleanup(struct epf_ntb *ntb)
+ {
+- epf_ntb_db_bar_clear(ntb);
+ epf_ntb_mw_bar_clear(ntb, ntb->num_mws);
++ epf_ntb_db_bar_clear(ntb);
++ epf_ntb_config_sspad_bar_clear(ntb);
+ }
+
+ #define EPF_NTB_R(_name) \
+@@ -1018,8 +1019,10 @@ static int vpci_scan_bus(void *sysdata)
+ struct epf_ntb *ndev = sysdata;
+
+ vpci_bus = pci_scan_bus(ndev->vbus_number, &vpci_ops, sysdata);
+- if (vpci_bus)
+- pr_err("create pci bus\n");
++ if (!vpci_bus) {
++ pr_err("create pci bus failed\n");
++ return -EINVAL;
++ }
+
+ pci_bus_add_devices(vpci_bus);
+
+@@ -1335,13 +1338,19 @@ static int epf_ntb_bind(struct pci_epf *epf)
+ ret = pci_register_driver(&vntb_pci_driver);
+ if (ret) {
+ dev_err(dev, "failure register vntb pci driver\n");
+- goto err_bar_alloc;
++ goto err_epc_cleanup;
+ }
+
+- vpci_scan_bus(ntb);
++ ret = vpci_scan_bus(ntb);
++ if (ret)
++ goto err_unregister;
+
+ return 0;
+
++err_unregister:
++ pci_unregister_driver(&vntb_pci_driver);
++err_epc_cleanup:
++ epf_ntb_epc_cleanup(ntb);
+ err_bar_alloc:
+ epf_ntb_config_spad_bar_free(ntb);
+
+diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
+index 35fb1f17a589c..dff09e4892d39 100644
+--- a/drivers/pci/pci.c
++++ b/drivers/pci/pci.c
+@@ -4753,7 +4753,7 @@ static int pci_bus_max_d3cold_delay(const struct pci_bus *bus)
+ */
+ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type)
+ {
+- struct pci_dev *child;
++ struct pci_dev *child __free(pci_dev_put) = NULL;
+ int delay;
+
+ if (pci_dev_is_disconnected(dev))
+@@ -4782,8 +4782,8 @@ int pci_bridge_wait_for_secondary_bus(struct pci_dev *dev, char *reset_type)
+ return 0;
+ }
+
+- child = list_first_entry(&dev->subordinate->devices, struct pci_dev,
+- bus_list);
++ child = pci_dev_get(list_first_entry(&dev->subordinate->devices,
++ struct pci_dev, bus_list));
+ up_read(&pci_bus_sem);
+
+ /*
+diff --git a/drivers/pci/setup-bus.c b/drivers/pci/setup-bus.c
+index 909e6a7c3cc31..141d6b31959be 100644
+--- a/drivers/pci/setup-bus.c
++++ b/drivers/pci/setup-bus.c
+@@ -829,11 +829,9 @@ static resource_size_t calculate_memsize(resource_size_t size,
+ size = min_size;
+ if (old_size == 1)
+ old_size = 0;
+- if (size < old_size)
+- size = old_size;
+
+- size = ALIGN(max(size, add_size) + children_add_size, align);
+- return size;
++ size = max(size, add_size) + children_add_size;
++ return ALIGN(max(size, old_size), align);
+ }
+
+ resource_size_t __weak pcibios_window_alignment(struct pci_bus *bus,
+diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
+index 23fa6c5da82c4..8ed5c3358920a 100644
+--- a/drivers/perf/arm_pmuv3.c
++++ b/drivers/perf/arm_pmuv3.c
+@@ -338,6 +338,11 @@ static bool armv8pmu_event_want_user_access(struct perf_event *event)
+ return ATTR_CFG_GET_FLD(&event->attr, rdpmc);
+ }
+
++static u32 armv8pmu_event_get_threshold(struct perf_event_attr *attr)
++{
++ return ATTR_CFG_GET_FLD(attr, threshold);
++}
++
+ static u8 armv8pmu_event_threshold_control(struct perf_event_attr *attr)
+ {
+ u8 th_compare = ATTR_CFG_GET_FLD(attr, threshold_compare);
+@@ -941,7 +946,8 @@ static int armv8pmu_get_event_idx(struct pmu_hw_events *cpuc,
+ unsigned long evtype = hwc->config_base & ARMV8_PMU_EVTYPE_EVENT;
+
+ /* Always prefer to place a cycle counter into the cycle counter. */
+- if (evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) {
++ if ((evtype == ARMV8_PMUV3_PERFCTR_CPU_CYCLES) &&
++ !armv8pmu_event_get_threshold(&event->attr)) {
+ if (!test_and_set_bit(ARMV8_IDX_CYCLE_COUNTER, cpuc->used_mask))
+ return ARMV8_IDX_CYCLE_COUNTER;
+ else if (armv8pmu_event_is_64bit(event) &&
+@@ -1033,7 +1039,7 @@ static int armv8pmu_set_event_filter(struct hw_perf_event *event,
+ * If FEAT_PMUv3_TH isn't implemented, then THWIDTH (threshold_max) will
+ * be 0 and will also trigger this check, preventing it from being used.
+ */
+- th = ATTR_CFG_GET_FLD(attr, threshold);
++ th = armv8pmu_event_get_threshold(attr);
+ if (th > threshold_max(cpu_pmu)) {
+ pr_debug("PMU event threshold exceeds max value\n");
+ return -EINVAL;
+diff --git a/drivers/phy/cadence/phy-cadence-torrent.c b/drivers/phy/cadence/phy-cadence-torrent.c
+index 95924a09960cc..6113f0022e6ee 100644
+--- a/drivers/phy/cadence/phy-cadence-torrent.c
++++ b/drivers/phy/cadence/phy-cadence-torrent.c
+@@ -1156,6 +1156,9 @@ static int cdns_torrent_dp_set_power_state(struct cdns_torrent_phy *cdns_phy,
+ ret = regmap_read_poll_timeout(regmap, PHY_PMA_XCVR_POWER_STATE_ACK,
+ read_val, (read_val & mask) == value, 0,
+ POLL_TIMEOUT_US);
++ if (ret)
++ return ret;
++
+ cdns_torrent_dp_write(regmap, PHY_PMA_XCVR_POWER_STATE_REQ, 0x00000000);
+ ndelay(100);
+
+diff --git a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+index 6c796723c8f5a..8fcdcb193d241 100644
+--- a/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
++++ b/drivers/phy/qualcomm/phy-qcom-qmp-pcie.c
+@@ -3730,14 +3730,11 @@ static int phy_aux_clk_register(struct qmp_pcie *qmp, struct device_node *np)
+ {
+ struct clk_fixed_rate *fixed = &qmp->aux_clk_fixed;
+ struct clk_init_data init = { };
+- int ret;
++ char name[64];
+
+- ret = of_property_read_string_index(np, "clock-output-names", 1, &init.name);
+- if (ret) {
+- dev_err(qmp->dev, "%pOFn: No clock-output-names index 1\n", np);
+- return ret;
+- }
++ snprintf(name, sizeof(name), "%s::phy_aux_clk", dev_name(qmp->dev));
+
++ init.name = name;
+ init.ops = &clk_fixed_rate_ops;
+
+ fixed->fixed_rate = qmp->cfg->aux_clock_rate;
+diff --git a/drivers/phy/rockchip/Kconfig b/drivers/phy/rockchip/Kconfig
+index 08b0f43457606..490263375057b 100644
+--- a/drivers/phy/rockchip/Kconfig
++++ b/drivers/phy/rockchip/Kconfig
+@@ -86,7 +86,9 @@ config PHY_ROCKCHIP_PCIE
+ config PHY_ROCKCHIP_SAMSUNG_HDPTX
+ tristate "Rockchip Samsung HDMI/eDP Combo PHY driver"
+ depends on (ARCH_ROCKCHIP || COMPILE_TEST) && OF
++ depends on HAS_IOMEM
+ select GENERIC_PHY
++ select MFD_SYSCON
+ select RATIONAL
+ help
+ Enable this to support the Rockchip HDMI/eDP Combo PHY
+diff --git a/drivers/phy/xilinx/phy-zynqmp.c b/drivers/phy/xilinx/phy-zynqmp.c
+index dc8319bda43d7..f2bff7f25f05a 100644
+--- a/drivers/phy/xilinx/phy-zynqmp.c
++++ b/drivers/phy/xilinx/phy-zynqmp.c
+@@ -80,7 +80,8 @@
+
+ /* Reference clock selection parameters */
+ #define L0_Ln_REF_CLK_SEL(n) (0x2860 + (n) * 4)
+-#define L0_REF_CLK_SEL_MASK 0x8f
++#define L0_REF_CLK_LCL_SEL BIT(7)
++#define L0_REF_CLK_SEL_MASK 0x9f
+
+ /* Calibration digital logic parameters */
+ #define L3_TM_CALIB_DIG19 0xec4c
+@@ -349,11 +350,12 @@ static void xpsgtr_configure_pll(struct xpsgtr_phy *gtr_phy)
+ PLL_FREQ_MASK, ssc->pll_ref_clk);
+
+ /* Enable lane clock sharing, if required */
+- if (gtr_phy->refclk != gtr_phy->lane) {
+- /* Lane3 Ref Clock Selection Register */
++ if (gtr_phy->refclk == gtr_phy->lane)
++ xpsgtr_clr_set(gtr_phy->dev, L0_Ln_REF_CLK_SEL(gtr_phy->lane),
++ L0_REF_CLK_SEL_MASK, L0_REF_CLK_LCL_SEL);
++ else
+ xpsgtr_clr_set(gtr_phy->dev, L0_Ln_REF_CLK_SEL(gtr_phy->lane),
+ L0_REF_CLK_SEL_MASK, 1 << gtr_phy->refclk);
+- }
+
+ /* SSC step size [7:0] */
+ xpsgtr_clr_set_phy(gtr_phy, L0_PLL_SS_STEP_SIZE_0_LSB,
+@@ -573,7 +575,7 @@ static int xpsgtr_phy_init(struct phy *phy)
+ mutex_lock(>r_dev->gtr_mutex);
+
+ /* Configure and enable the clock when peripheral phy_init call */
+- if (clk_prepare_enable(gtr_dev->clk[gtr_phy->lane]))
++ if (clk_prepare_enable(gtr_dev->clk[gtr_phy->refclk]))
+ goto out;
+
+ /* Skip initialization if not required. */
+@@ -625,7 +627,7 @@ static int xpsgtr_phy_exit(struct phy *phy)
+ gtr_phy->skip_phy_init = false;
+
+ /* Ensure that disable clock only, which configure for lane */
+- clk_disable_unprepare(gtr_dev->clk[gtr_phy->lane]);
++ clk_disable_unprepare(gtr_dev->clk[gtr_phy->refclk]);
+
+ return 0;
+ }
+diff --git a/drivers/pinctrl/core.c b/drivers/pinctrl/core.c
+index f424a57f00136..4438f3b4b5ef9 100644
+--- a/drivers/pinctrl/core.c
++++ b/drivers/pinctrl/core.c
+@@ -2080,6 +2080,14 @@ pinctrl_init_controller(struct pinctrl_desc *pctldesc, struct device *dev,
+ return ERR_PTR(ret);
+ }
+
++static void pinctrl_uninit_controller(struct pinctrl_dev *pctldev, struct pinctrl_desc *pctldesc)
++{
++ pinctrl_free_pindescs(pctldev, pctldesc->pins,
++ pctldesc->npins);
++ mutex_destroy(&pctldev->mutex);
++ kfree(pctldev);
++}
++
+ static int pinctrl_claim_hogs(struct pinctrl_dev *pctldev)
+ {
+ pctldev->p = create_pinctrl(pctldev->dev, pctldev);
+@@ -2160,8 +2168,10 @@ struct pinctrl_dev *pinctrl_register(struct pinctrl_desc *pctldesc,
+ return pctldev;
+
+ error = pinctrl_enable(pctldev);
+- if (error)
++ if (error) {
++ pinctrl_uninit_controller(pctldev, pctldesc);
+ return ERR_PTR(error);
++ }
+
+ return pctldev;
+ }
+diff --git a/drivers/pinctrl/freescale/pinctrl-mxs.c b/drivers/pinctrl/freescale/pinctrl-mxs.c
+index e77311f26262a..4813a9e16cb3b 100644
+--- a/drivers/pinctrl/freescale/pinctrl-mxs.c
++++ b/drivers/pinctrl/freescale/pinctrl-mxs.c
+@@ -413,8 +413,8 @@ static int mxs_pinctrl_probe_dt(struct platform_device *pdev,
+ int ret;
+ u32 val;
+
+- child = of_get_next_child(np, NULL);
+- if (!child) {
++ val = of_get_child_count(np);
++ if (val == 0) {
+ dev_err(&pdev->dev, "no group is defined\n");
+ return -ENOENT;
+ }
+diff --git a/drivers/pinctrl/pinctrl-rockchip.c b/drivers/pinctrl/pinctrl-rockchip.c
+index 3f56991f5b892..6a74619786300 100644
+--- a/drivers/pinctrl/pinctrl-rockchip.c
++++ b/drivers/pinctrl/pinctrl-rockchip.c
+@@ -915,9 +915,8 @@ static struct rockchip_mux_route_data rk3308_mux_route_data[] = {
+ RK_MUXROUTE_SAME(0, RK_PC3, 1, 0x314, BIT(16 + 0) | BIT(0)), /* rtc_clk */
+ RK_MUXROUTE_SAME(1, RK_PC6, 2, 0x314, BIT(16 + 2) | BIT(16 + 3)), /* uart2_rxm0 */
+ RK_MUXROUTE_SAME(4, RK_PD2, 2, 0x314, BIT(16 + 2) | BIT(16 + 3) | BIT(2)), /* uart2_rxm1 */
+- RK_MUXROUTE_SAME(0, RK_PB7, 2, 0x608, BIT(16 + 8) | BIT(16 + 9)), /* i2c3_sdam0 */
+- RK_MUXROUTE_SAME(3, RK_PB4, 2, 0x608, BIT(16 + 8) | BIT(16 + 9) | BIT(8)), /* i2c3_sdam1 */
+- RK_MUXROUTE_SAME(2, RK_PA0, 3, 0x608, BIT(16 + 8) | BIT(16 + 9) | BIT(9)), /* i2c3_sdam2 */
++ RK_MUXROUTE_SAME(0, RK_PB7, 2, 0x314, BIT(16 + 4)), /* i2c3_sdam0 */
++ RK_MUXROUTE_SAME(3, RK_PB4, 2, 0x314, BIT(16 + 4) | BIT(4)), /* i2c3_sdam1 */
+ RK_MUXROUTE_SAME(1, RK_PA3, 2, 0x308, BIT(16 + 3)), /* i2s-8ch-1-sclktxm0 */
+ RK_MUXROUTE_SAME(1, RK_PA4, 2, 0x308, BIT(16 + 3)), /* i2s-8ch-1-sclkrxm0 */
+ RK_MUXROUTE_SAME(1, RK_PB5, 2, 0x308, BIT(16 + 3) | BIT(3)), /* i2s-8ch-1-sclktxm1 */
+@@ -926,18 +925,6 @@ static struct rockchip_mux_route_data rk3308_mux_route_data[] = {
+ RK_MUXROUTE_SAME(1, RK_PB6, 4, 0x308, BIT(16 + 12) | BIT(16 + 13) | BIT(12)), /* pdm-clkm1 */
+ RK_MUXROUTE_SAME(2, RK_PA6, 2, 0x308, BIT(16 + 12) | BIT(16 + 13) | BIT(13)), /* pdm-clkm2 */
+ RK_MUXROUTE_SAME(2, RK_PA4, 3, 0x600, BIT(16 + 2) | BIT(2)), /* pdm-clkm-m2 */
+- RK_MUXROUTE_SAME(3, RK_PB2, 3, 0x314, BIT(16 + 9)), /* spi1_miso */
+- RK_MUXROUTE_SAME(2, RK_PA4, 2, 0x314, BIT(16 + 9) | BIT(9)), /* spi1_miso_m1 */
+- RK_MUXROUTE_SAME(0, RK_PB3, 3, 0x314, BIT(16 + 10) | BIT(16 + 11)), /* owire_m0 */
+- RK_MUXROUTE_SAME(1, RK_PC6, 7, 0x314, BIT(16 + 10) | BIT(16 + 11) | BIT(10)), /* owire_m1 */
+- RK_MUXROUTE_SAME(2, RK_PA2, 5, 0x314, BIT(16 + 10) | BIT(16 + 11) | BIT(11)), /* owire_m2 */
+- RK_MUXROUTE_SAME(0, RK_PB3, 2, 0x314, BIT(16 + 12) | BIT(16 + 13)), /* can_rxd_m0 */
+- RK_MUXROUTE_SAME(1, RK_PC6, 5, 0x314, BIT(16 + 12) | BIT(16 + 13) | BIT(12)), /* can_rxd_m1 */
+- RK_MUXROUTE_SAME(2, RK_PA2, 4, 0x314, BIT(16 + 12) | BIT(16 + 13) | BIT(13)), /* can_rxd_m2 */
+- RK_MUXROUTE_SAME(1, RK_PC4, 3, 0x314, BIT(16 + 14)), /* mac_rxd0_m0 */
+- RK_MUXROUTE_SAME(4, RK_PA2, 2, 0x314, BIT(16 + 14) | BIT(14)), /* mac_rxd0_m1 */
+- RK_MUXROUTE_SAME(3, RK_PB4, 4, 0x314, BIT(16 + 15)), /* uart3_rx */
+- RK_MUXROUTE_SAME(0, RK_PC1, 3, 0x314, BIT(16 + 15) | BIT(15)), /* uart3_rx_m1 */
+ };
+
+ static struct rockchip_mux_route_data rk3328_mux_route_data[] = {
+diff --git a/drivers/pinctrl/pinctrl-single.c b/drivers/pinctrl/pinctrl-single.c
+index a798f31d69542..4c6bfabb6bd7d 100644
+--- a/drivers/pinctrl/pinctrl-single.c
++++ b/drivers/pinctrl/pinctrl-single.c
+@@ -1329,7 +1329,6 @@ static void pcs_irq_free(struct pcs_device *pcs)
+ static void pcs_free_resources(struct pcs_device *pcs)
+ {
+ pcs_irq_free(pcs);
+- pinctrl_unregister(pcs->pctl);
+
+ #if IS_BUILTIN(CONFIG_PINCTRL_SINGLE)
+ if (pcs->missing_nr_pinctrl_cells)
+@@ -1879,7 +1878,7 @@ static int pcs_probe(struct platform_device *pdev)
+ if (ret < 0)
+ goto free;
+
+- ret = pinctrl_register_and_init(&pcs->desc, pcs->dev, pcs, &pcs->pctl);
++ ret = devm_pinctrl_register_and_init(pcs->dev, &pcs->desc, pcs, &pcs->pctl);
+ if (ret) {
+ dev_err(pcs->dev, "could not register single pinctrl driver\n");
+ goto free;
+@@ -1912,8 +1911,10 @@ static int pcs_probe(struct platform_device *pdev)
+
+ dev_info(pcs->dev, "%i pins, size %u\n", pcs->desc.npins, pcs->size);
+
+- return pinctrl_enable(pcs->pctl);
++ if (pinctrl_enable(pcs->pctl))
++ goto free;
+
++ return 0;
+ free:
+ pcs_free_resources(pcs);
+
+diff --git a/drivers/pinctrl/renesas/pfc-r8a779g0.c b/drivers/pinctrl/renesas/pfc-r8a779g0.c
+index d2de526a3b588..bb843e333c880 100644
+--- a/drivers/pinctrl/renesas/pfc-r8a779g0.c
++++ b/drivers/pinctrl/renesas/pfc-r8a779g0.c
+@@ -68,20 +68,20 @@
+ #define GPSR0_9 F_(MSIOF5_SYNC, IP1SR0_7_4)
+ #define GPSR0_8 F_(MSIOF5_SS1, IP1SR0_3_0)
+ #define GPSR0_7 F_(MSIOF5_SS2, IP0SR0_31_28)
+-#define GPSR0_6 F_(IRQ0, IP0SR0_27_24)
+-#define GPSR0_5 F_(IRQ1, IP0SR0_23_20)
+-#define GPSR0_4 F_(IRQ2, IP0SR0_19_16)
+-#define GPSR0_3 F_(IRQ3, IP0SR0_15_12)
++#define GPSR0_6 F_(IRQ0_A, IP0SR0_27_24)
++#define GPSR0_5 F_(IRQ1_A, IP0SR0_23_20)
++#define GPSR0_4 F_(IRQ2_A, IP0SR0_19_16)
++#define GPSR0_3 F_(IRQ3_A, IP0SR0_15_12)
+ #define GPSR0_2 F_(GP0_02, IP0SR0_11_8)
+ #define GPSR0_1 F_(GP0_01, IP0SR0_7_4)
+ #define GPSR0_0 F_(GP0_00, IP0SR0_3_0)
+
+ /* GPSR1 */
+-#define GPSR1_28 F_(HTX3, IP3SR1_19_16)
+-#define GPSR1_27 F_(HCTS3_N, IP3SR1_15_12)
+-#define GPSR1_26 F_(HRTS3_N, IP3SR1_11_8)
+-#define GPSR1_25 F_(HSCK3, IP3SR1_7_4)
+-#define GPSR1_24 F_(HRX3, IP3SR1_3_0)
++#define GPSR1_28 F_(HTX3_A, IP3SR1_19_16)
++#define GPSR1_27 F_(HCTS3_N_A, IP3SR1_15_12)
++#define GPSR1_26 F_(HRTS3_N_A, IP3SR1_11_8)
++#define GPSR1_25 F_(HSCK3_A, IP3SR1_7_4)
++#define GPSR1_24 F_(HRX3_A, IP3SR1_3_0)
+ #define GPSR1_23 F_(GP1_23, IP2SR1_31_28)
+ #define GPSR1_22 F_(AUDIO_CLKIN, IP2SR1_27_24)
+ #define GPSR1_21 F_(AUDIO_CLKOUT, IP2SR1_23_20)
+@@ -119,14 +119,14 @@
+ #define GPSR2_11 F_(CANFD0_RX, IP1SR2_15_12)
+ #define GPSR2_10 F_(CANFD0_TX, IP1SR2_11_8)
+ #define GPSR2_9 F_(CAN_CLK, IP1SR2_7_4)
+-#define GPSR2_8 F_(TPU0TO0, IP1SR2_3_0)
+-#define GPSR2_7 F_(TPU0TO1, IP0SR2_31_28)
++#define GPSR2_8 F_(TPU0TO0_A, IP1SR2_3_0)
++#define GPSR2_7 F_(TPU0TO1_A, IP0SR2_31_28)
+ #define GPSR2_6 F_(FXR_TXDB, IP0SR2_27_24)
+-#define GPSR2_5 F_(FXR_TXENB_N, IP0SR2_23_20)
++#define GPSR2_5 F_(FXR_TXENB_N_A, IP0SR2_23_20)
+ #define GPSR2_4 F_(RXDB_EXTFXR, IP0SR2_19_16)
+ #define GPSR2_3 F_(CLK_EXTFXR, IP0SR2_15_12)
+ #define GPSR2_2 F_(RXDA_EXTFXR, IP0SR2_11_8)
+-#define GPSR2_1 F_(FXR_TXENA_N, IP0SR2_7_4)
++#define GPSR2_1 F_(FXR_TXENA_N_A, IP0SR2_7_4)
+ #define GPSR2_0 F_(FXR_TXDA, IP0SR2_3_0)
+
+ /* GPSR3 */
+@@ -275,13 +275,13 @@
+
+ /* SR0 */
+ /* IP0SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+-#define IP0SR0_3_0 F_(0, 0) FM(ERROROUTC_N_B) FM(TCLK2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR0_3_0 F_(0, 0) FM(ERROROUTC_N_B) FM(TCLK2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP0SR0_7_4 F_(0, 0) FM(MSIOF3_SS1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP0SR0_11_8 F_(0, 0) FM(MSIOF3_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR0_15_12 FM(IRQ3) FM(MSIOF3_SCK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR0_19_16 FM(IRQ2) FM(MSIOF3_TXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR0_23_20 FM(IRQ1) FM(MSIOF3_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR0_27_24 FM(IRQ0) FM(MSIOF3_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR0_15_12 FM(IRQ3_A) FM(MSIOF3_SCK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR0_19_16 FM(IRQ2_A) FM(MSIOF3_TXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR0_23_20 FM(IRQ1_A) FM(MSIOF3_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR0_27_24 FM(IRQ0_A) FM(MSIOF3_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP0SR0_31_28 FM(MSIOF5_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP1SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+@@ -290,72 +290,72 @@
+ #define IP1SR0_11_8 FM(MSIOF5_TXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR0_15_12 FM(MSIOF5_SCK) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR0_19_16 FM(MSIOF5_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR0_23_20 FM(MSIOF2_SS2) FM(TCLK1) FM(IRQ2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR0_27_24 FM(MSIOF2_SS1) FM(HTX1) FM(TX1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR0_31_28 FM(MSIOF2_SYNC) FM(HRX1) FM(RX1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR0_23_20 FM(MSIOF2_SS2) FM(TCLK1_A) FM(IRQ2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR0_27_24 FM(MSIOF2_SS1) FM(HTX1_A) FM(TX1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR0_31_28 FM(MSIOF2_SYNC) FM(HRX1_A) FM(RX1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP2SR0 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+-#define IP2SR0_3_0 FM(MSIOF2_TXD) FM(HCTS1_N) FM(CTS1_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP2SR0_7_4 FM(MSIOF2_SCK) FM(HRTS1_N) FM(RTS1_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP2SR0_11_8 FM(MSIOF2_RXD) FM(HSCK1) FM(SCK1) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR0_3_0 FM(MSIOF2_TXD) FM(HCTS1_N_A) FM(CTS1_N_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR0_7_4 FM(MSIOF2_SCK) FM(HRTS1_N_A) FM(RTS1_N_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR0_11_8 FM(MSIOF2_RXD) FM(HSCK1_A) FM(SCK1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* SR1 */
+ /* IP0SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+-#define IP0SR1_3_0 FM(MSIOF1_SS2) FM(HTX3_A) FM(TX3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR1_7_4 FM(MSIOF1_SS1) FM(HCTS3_N_A) FM(RX3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR1_11_8 FM(MSIOF1_SYNC) FM(HRTS3_N_A) FM(RTS3_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR1_15_12 FM(MSIOF1_SCK) FM(HSCK3_A) FM(CTS3_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR1_19_16 FM(MSIOF1_TXD) FM(HRX3_A) FM(SCK3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR1_3_0 FM(MSIOF1_SS2) FM(HTX3_B) FM(TX3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR1_7_4 FM(MSIOF1_SS1) FM(HCTS3_N_B) FM(RX3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR1_11_8 FM(MSIOF1_SYNC) FM(HRTS3_N_B) FM(RTS3_N_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR1_15_12 FM(MSIOF1_SCK) FM(HSCK3_B) FM(CTS3_N_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR1_19_16 FM(MSIOF1_TXD) FM(HRX3_B) FM(SCK3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP0SR1_23_20 FM(MSIOF1_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR1_27_24 FM(MSIOF0_SS2) FM(HTX1_X) FM(TX1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR1_31_28 FM(MSIOF0_SS1) FM(HRX1_X) FM(RX1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR1_27_24 FM(MSIOF0_SS2) FM(HTX1_B) FM(TX1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR1_31_28 FM(MSIOF0_SS1) FM(HRX1_B) FM(RX1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP1SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+-#define IP1SR1_3_0 FM(MSIOF0_SYNC) FM(HCTS1_N_X) FM(CTS1_N_X) FM(CANFD5_TX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR1_7_4 FM(MSIOF0_TXD) FM(HRTS1_N_X) FM(RTS1_N_X) FM(CANFD5_RX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR1_11_8 FM(MSIOF0_SCK) FM(HSCK1_X) FM(SCK1_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR1_3_0 FM(MSIOF0_SYNC) FM(HCTS1_N_B) FM(CTS1_N_B) FM(CANFD5_TX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR1_7_4 FM(MSIOF0_TXD) FM(HRTS1_N_B) FM(RTS1_N_B) FM(CANFD5_RX_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR1_11_8 FM(MSIOF0_SCK) FM(HSCK1_B) FM(SCK1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR1_15_12 FM(MSIOF0_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR1_19_16 FM(HTX0) FM(TX0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR1_23_20 FM(HCTS0_N) FM(CTS0_N) FM(PWM8_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR1_27_24 FM(HRTS0_N) FM(RTS0_N) FM(PWM9_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR1_31_28 FM(HSCK0) FM(SCK0) FM(PWM0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR1_23_20 FM(HCTS0_N) FM(CTS0_N) FM(PWM8) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR1_27_24 FM(HRTS0_N) FM(RTS0_N) FM(PWM9) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR1_31_28 FM(HSCK0) FM(SCK0) FM(PWM0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP2SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+ #define IP2SR1_3_0 FM(HRX0) FM(RX0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP2SR1_7_4 FM(SCIF_CLK) FM(IRQ4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP2SR1_11_8 FM(SSI_SCK) FM(TCLK3) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP2SR1_15_12 FM(SSI_WS) FM(TCLK4) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP2SR1_19_16 FM(SSI_SD) FM(IRQ0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP2SR1_23_20 FM(AUDIO_CLKOUT) FM(IRQ1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR1_11_8 FM(SSI_SCK) FM(TCLK3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR1_15_12 FM(SSI_WS) FM(TCLK4_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR1_19_16 FM(SSI_SD) FM(IRQ0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR1_23_20 FM(AUDIO_CLKOUT) FM(IRQ1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP2SR1_27_24 FM(AUDIO_CLKIN) FM(PWM3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP2SR1_31_28 F_(0, 0) FM(TCLK2) FM(MSIOF4_SS1) FM(IRQ3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP2SR1_31_28 F_(0, 0) FM(TCLK2_A) FM(MSIOF4_SS1) FM(IRQ3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP3SR1 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+-#define IP3SR1_3_0 FM(HRX3) FM(SCK3_A) FM(MSIOF4_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP3SR1_7_4 FM(HSCK3) FM(CTS3_N_A) FM(MSIOF4_SCK) FM(TPU0TO0_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP3SR1_11_8 FM(HRTS3_N) FM(RTS3_N_A) FM(MSIOF4_TXD) FM(TPU0TO1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP3SR1_15_12 FM(HCTS3_N) FM(RX3_A) FM(MSIOF4_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP3SR1_19_16 FM(HTX3) FM(TX3_A) FM(MSIOF4_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP3SR1_3_0 FM(HRX3_A) FM(SCK3_A) FM(MSIOF4_SS2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP3SR1_7_4 FM(HSCK3_A) FM(CTS3_N_A) FM(MSIOF4_SCK) FM(TPU0TO0_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP3SR1_11_8 FM(HRTS3_N_A) FM(RTS3_N_A) FM(MSIOF4_TXD) FM(TPU0TO1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP3SR1_15_12 FM(HCTS3_N_A) FM(RX3_A) FM(MSIOF4_RXD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP3SR1_19_16 FM(HTX3_A) FM(TX3_A) FM(MSIOF4_SYNC) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* SR2 */
+ /* IP0SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+-#define IP0SR2_3_0 FM(FXR_TXDA) FM(CANFD1_TX) FM(TPU0TO2_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR2_7_4 FM(FXR_TXENA_N) FM(CANFD1_RX) FM(TPU0TO3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR2_11_8 FM(RXDA_EXTFXR) FM(CANFD5_TX) FM(IRQ5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR2_15_12 FM(CLK_EXTFXR) FM(CANFD5_RX) FM(IRQ4_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR2_3_0 FM(FXR_TXDA) FM(CANFD1_TX) FM(TPU0TO2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR2_7_4 FM(FXR_TXENA_N_A) FM(CANFD1_RX) FM(TPU0TO3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR2_11_8 FM(RXDA_EXTFXR) FM(CANFD5_TX_A) FM(IRQ5) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR2_15_12 FM(CLK_EXTFXR) FM(CANFD5_RX_A) FM(IRQ4_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP0SR2_19_16 FM(RXDB_EXTFXR) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR2_23_20 FM(FXR_TXENB_N) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR2_23_20 FM(FXR_TXENB_N_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP0SR2_27_24 FM(FXR_TXDB) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP0SR2_31_28 FM(TPU0TO1) FM(CANFD6_TX) F_(0, 0) FM(TCLK2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP0SR2_31_28 FM(TPU0TO1_A) FM(CANFD6_TX) F_(0, 0) FM(TCLK2_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP1SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+-#define IP1SR2_3_0 FM(TPU0TO0) FM(CANFD6_RX) F_(0, 0) FM(TCLK1_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR2_7_4 FM(CAN_CLK) FM(FXR_TXENA_N_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR2_11_8 FM(CANFD0_TX) FM(FXR_TXENB_N_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR2_3_0 FM(TPU0TO0_A) FM(CANFD6_RX) F_(0, 0) FM(TCLK1_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR2_7_4 FM(CAN_CLK) FM(FXR_TXENA_N_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR2_11_8 FM(CANFD0_TX) FM(FXR_TXENB_N_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR2_15_12 FM(CANFD0_RX) FM(STPWT_EXTFXR) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR2_19_16 FM(CANFD2_TX) FM(TPU0TO2) F_(0, 0) FM(TCLK3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR2_23_20 FM(CANFD2_RX) FM(TPU0TO3) FM(PWM1_B) FM(TCLK4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR2_27_24 FM(CANFD3_TX) F_(0, 0) FM(PWM2_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR2_19_16 FM(CANFD2_TX) FM(TPU0TO2_A) F_(0, 0) FM(TCLK3_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR2_23_20 FM(CANFD2_RX) FM(TPU0TO3_A) FM(PWM1_B) FM(TCLK4_C) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR2_27_24 FM(CANFD3_TX) F_(0, 0) FM(PWM2) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR2_31_28 FM(CANFD3_RX) F_(0, 0) FM(PWM3_B) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP2SR2 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+@@ -381,8 +381,8 @@
+ #define IP1SR3_11_8 FM(MMC_SD_CMD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR3_15_12 FM(SD_CD) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR3_19_16 FM(SD_WP) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR3_23_20 FM(IPC_CLKIN) FM(IPC_CLKEN_IN) FM(PWM1_A) FM(TCLK3_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+-#define IP1SR3_27_24 FM(IPC_CLKOUT) FM(IPC_CLKEN_OUT) FM(ERROROUTC_N_A) FM(TCLK4_X) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR3_23_20 FM(IPC_CLKIN) FM(IPC_CLKEN_IN) FM(PWM1_A) FM(TCLK3_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
++#define IP1SR3_27_24 FM(IPC_CLKOUT) FM(IPC_CLKEN_OUT) FM(ERROROUTC_N_A) FM(TCLK4_A) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+ #define IP1SR3_31_28 FM(QSPI0_SSL) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0) F_(0, 0)
+
+ /* IP2SR3 */ /* 0 */ /* 1 */ /* 2 */ /* 3 4 5 6 7 8 9 A B C D E F */
+@@ -718,22 +718,22 @@ static const u16 pinmux_data[] = {
+
+ /* IP0SR0 */
+ PINMUX_IPSR_GPSR(IP0SR0_3_0, ERROROUTC_N_B),
+- PINMUX_IPSR_GPSR(IP0SR0_3_0, TCLK2_A),
++ PINMUX_IPSR_GPSR(IP0SR0_3_0, TCLK2_B),
+
+ PINMUX_IPSR_GPSR(IP0SR0_7_4, MSIOF3_SS1),
+
+ PINMUX_IPSR_GPSR(IP0SR0_11_8, MSIOF3_SS2),
+
+- PINMUX_IPSR_GPSR(IP0SR0_15_12, IRQ3),
++ PINMUX_IPSR_GPSR(IP0SR0_15_12, IRQ3_A),
+ PINMUX_IPSR_GPSR(IP0SR0_15_12, MSIOF3_SCK),
+
+- PINMUX_IPSR_GPSR(IP0SR0_19_16, IRQ2),
++ PINMUX_IPSR_GPSR(IP0SR0_19_16, IRQ2_A),
+ PINMUX_IPSR_GPSR(IP0SR0_19_16, MSIOF3_TXD),
+
+- PINMUX_IPSR_GPSR(IP0SR0_23_20, IRQ1),
++ PINMUX_IPSR_GPSR(IP0SR0_23_20, IRQ1_A),
+ PINMUX_IPSR_GPSR(IP0SR0_23_20, MSIOF3_RXD),
+
+- PINMUX_IPSR_GPSR(IP0SR0_27_24, IRQ0),
++ PINMUX_IPSR_GPSR(IP0SR0_27_24, IRQ0_A),
+ PINMUX_IPSR_GPSR(IP0SR0_27_24, MSIOF3_SYNC),
+
+ PINMUX_IPSR_GPSR(IP0SR0_31_28, MSIOF5_SS2),
+@@ -750,75 +750,75 @@ static const u16 pinmux_data[] = {
+ PINMUX_IPSR_GPSR(IP1SR0_19_16, MSIOF5_RXD),
+
+ PINMUX_IPSR_GPSR(IP1SR0_23_20, MSIOF2_SS2),
+- PINMUX_IPSR_GPSR(IP1SR0_23_20, TCLK1),
+- PINMUX_IPSR_GPSR(IP1SR0_23_20, IRQ2_A),
++ PINMUX_IPSR_GPSR(IP1SR0_23_20, TCLK1_A),
++ PINMUX_IPSR_GPSR(IP1SR0_23_20, IRQ2_B),
+
+ PINMUX_IPSR_GPSR(IP1SR0_27_24, MSIOF2_SS1),
+- PINMUX_IPSR_GPSR(IP1SR0_27_24, HTX1),
+- PINMUX_IPSR_GPSR(IP1SR0_27_24, TX1),
++ PINMUX_IPSR_GPSR(IP1SR0_27_24, HTX1_A),
++ PINMUX_IPSR_GPSR(IP1SR0_27_24, TX1_A),
+
+ PINMUX_IPSR_GPSR(IP1SR0_31_28, MSIOF2_SYNC),
+- PINMUX_IPSR_GPSR(IP1SR0_31_28, HRX1),
+- PINMUX_IPSR_GPSR(IP1SR0_31_28, RX1),
++ PINMUX_IPSR_GPSR(IP1SR0_31_28, HRX1_A),
++ PINMUX_IPSR_GPSR(IP1SR0_31_28, RX1_A),
+
+ /* IP2SR0 */
+ PINMUX_IPSR_GPSR(IP2SR0_3_0, MSIOF2_TXD),
+- PINMUX_IPSR_GPSR(IP2SR0_3_0, HCTS1_N),
+- PINMUX_IPSR_GPSR(IP2SR0_3_0, CTS1_N),
++ PINMUX_IPSR_GPSR(IP2SR0_3_0, HCTS1_N_A),
++ PINMUX_IPSR_GPSR(IP2SR0_3_0, CTS1_N_A),
+
+ PINMUX_IPSR_GPSR(IP2SR0_7_4, MSIOF2_SCK),
+- PINMUX_IPSR_GPSR(IP2SR0_7_4, HRTS1_N),
+- PINMUX_IPSR_GPSR(IP2SR0_7_4, RTS1_N),
++ PINMUX_IPSR_GPSR(IP2SR0_7_4, HRTS1_N_A),
++ PINMUX_IPSR_GPSR(IP2SR0_7_4, RTS1_N_A),
+
+ PINMUX_IPSR_GPSR(IP2SR0_11_8, MSIOF2_RXD),
+- PINMUX_IPSR_GPSR(IP2SR0_11_8, HSCK1),
+- PINMUX_IPSR_GPSR(IP2SR0_11_8, SCK1),
++ PINMUX_IPSR_GPSR(IP2SR0_11_8, HSCK1_A),
++ PINMUX_IPSR_GPSR(IP2SR0_11_8, SCK1_A),
+
+ /* IP0SR1 */
+ PINMUX_IPSR_GPSR(IP0SR1_3_0, MSIOF1_SS2),
+- PINMUX_IPSR_GPSR(IP0SR1_3_0, HTX3_A),
+- PINMUX_IPSR_GPSR(IP0SR1_3_0, TX3),
++ PINMUX_IPSR_GPSR(IP0SR1_3_0, HTX3_B),
++ PINMUX_IPSR_GPSR(IP0SR1_3_0, TX3_B),
+
+ PINMUX_IPSR_GPSR(IP0SR1_7_4, MSIOF1_SS1),
+- PINMUX_IPSR_GPSR(IP0SR1_7_4, HCTS3_N_A),
+- PINMUX_IPSR_GPSR(IP0SR1_7_4, RX3),
++ PINMUX_IPSR_GPSR(IP0SR1_7_4, HCTS3_N_B),
++ PINMUX_IPSR_GPSR(IP0SR1_7_4, RX3_B),
+
+ PINMUX_IPSR_GPSR(IP0SR1_11_8, MSIOF1_SYNC),
+- PINMUX_IPSR_GPSR(IP0SR1_11_8, HRTS3_N_A),
+- PINMUX_IPSR_GPSR(IP0SR1_11_8, RTS3_N),
++ PINMUX_IPSR_GPSR(IP0SR1_11_8, HRTS3_N_B),
++ PINMUX_IPSR_GPSR(IP0SR1_11_8, RTS3_N_B),
+
+ PINMUX_IPSR_GPSR(IP0SR1_15_12, MSIOF1_SCK),
+- PINMUX_IPSR_GPSR(IP0SR1_15_12, HSCK3_A),
+- PINMUX_IPSR_GPSR(IP0SR1_15_12, CTS3_N),
++ PINMUX_IPSR_GPSR(IP0SR1_15_12, HSCK3_B),
++ PINMUX_IPSR_GPSR(IP0SR1_15_12, CTS3_N_B),
+
+ PINMUX_IPSR_GPSR(IP0SR1_19_16, MSIOF1_TXD),
+- PINMUX_IPSR_GPSR(IP0SR1_19_16, HRX3_A),
+- PINMUX_IPSR_GPSR(IP0SR1_19_16, SCK3),
++ PINMUX_IPSR_GPSR(IP0SR1_19_16, HRX3_B),
++ PINMUX_IPSR_GPSR(IP0SR1_19_16, SCK3_B),
+
+ PINMUX_IPSR_GPSR(IP0SR1_23_20, MSIOF1_RXD),
+
+ PINMUX_IPSR_GPSR(IP0SR1_27_24, MSIOF0_SS2),
+- PINMUX_IPSR_GPSR(IP0SR1_27_24, HTX1_X),
+- PINMUX_IPSR_GPSR(IP0SR1_27_24, TX1_X),
++ PINMUX_IPSR_GPSR(IP0SR1_27_24, HTX1_B),
++ PINMUX_IPSR_GPSR(IP0SR1_27_24, TX1_B),
+
+ PINMUX_IPSR_GPSR(IP0SR1_31_28, MSIOF0_SS1),
+- PINMUX_IPSR_GPSR(IP0SR1_31_28, HRX1_X),
+- PINMUX_IPSR_GPSR(IP0SR1_31_28, RX1_X),
++ PINMUX_IPSR_GPSR(IP0SR1_31_28, HRX1_B),
++ PINMUX_IPSR_GPSR(IP0SR1_31_28, RX1_B),
+
+ /* IP1SR1 */
+ PINMUX_IPSR_GPSR(IP1SR1_3_0, MSIOF0_SYNC),
+- PINMUX_IPSR_GPSR(IP1SR1_3_0, HCTS1_N_X),
+- PINMUX_IPSR_GPSR(IP1SR1_3_0, CTS1_N_X),
++ PINMUX_IPSR_GPSR(IP1SR1_3_0, HCTS1_N_B),
++ PINMUX_IPSR_GPSR(IP1SR1_3_0, CTS1_N_B),
+ PINMUX_IPSR_GPSR(IP1SR1_3_0, CANFD5_TX_B),
+
+ PINMUX_IPSR_GPSR(IP1SR1_7_4, MSIOF0_TXD),
+- PINMUX_IPSR_GPSR(IP1SR1_7_4, HRTS1_N_X),
+- PINMUX_IPSR_GPSR(IP1SR1_7_4, RTS1_N_X),
++ PINMUX_IPSR_GPSR(IP1SR1_7_4, HRTS1_N_B),
++ PINMUX_IPSR_GPSR(IP1SR1_7_4, RTS1_N_B),
+ PINMUX_IPSR_GPSR(IP1SR1_7_4, CANFD5_RX_B),
+
+ PINMUX_IPSR_GPSR(IP1SR1_11_8, MSIOF0_SCK),
+- PINMUX_IPSR_GPSR(IP1SR1_11_8, HSCK1_X),
+- PINMUX_IPSR_GPSR(IP1SR1_11_8, SCK1_X),
++ PINMUX_IPSR_GPSR(IP1SR1_11_8, HSCK1_B),
++ PINMUX_IPSR_GPSR(IP1SR1_11_8, SCK1_B),
+
+ PINMUX_IPSR_GPSR(IP1SR1_15_12, MSIOF0_RXD),
+
+@@ -827,15 +827,15 @@ static const u16 pinmux_data[] = {
+
+ PINMUX_IPSR_GPSR(IP1SR1_23_20, HCTS0_N),
+ PINMUX_IPSR_GPSR(IP1SR1_23_20, CTS0_N),
+- PINMUX_IPSR_GPSR(IP1SR1_23_20, PWM8_A),
++ PINMUX_IPSR_GPSR(IP1SR1_23_20, PWM8),
+
+ PINMUX_IPSR_GPSR(IP1SR1_27_24, HRTS0_N),
+ PINMUX_IPSR_GPSR(IP1SR1_27_24, RTS0_N),
+- PINMUX_IPSR_GPSR(IP1SR1_27_24, PWM9_A),
++ PINMUX_IPSR_GPSR(IP1SR1_27_24, PWM9),
+
+ PINMUX_IPSR_GPSR(IP1SR1_31_28, HSCK0),
+ PINMUX_IPSR_GPSR(IP1SR1_31_28, SCK0),
+- PINMUX_IPSR_GPSR(IP1SR1_31_28, PWM0_A),
++ PINMUX_IPSR_GPSR(IP1SR1_31_28, PWM0),
+
+ /* IP2SR1 */
+ PINMUX_IPSR_GPSR(IP2SR1_3_0, HRX0),
+@@ -845,99 +845,99 @@ static const u16 pinmux_data[] = {
+ PINMUX_IPSR_GPSR(IP2SR1_7_4, IRQ4_A),
+
+ PINMUX_IPSR_GPSR(IP2SR1_11_8, SSI_SCK),
+- PINMUX_IPSR_GPSR(IP2SR1_11_8, TCLK3),
++ PINMUX_IPSR_GPSR(IP2SR1_11_8, TCLK3_B),
+
+ PINMUX_IPSR_GPSR(IP2SR1_15_12, SSI_WS),
+- PINMUX_IPSR_GPSR(IP2SR1_15_12, TCLK4),
++ PINMUX_IPSR_GPSR(IP2SR1_15_12, TCLK4_B),
+
+ PINMUX_IPSR_GPSR(IP2SR1_19_16, SSI_SD),
+- PINMUX_IPSR_GPSR(IP2SR1_19_16, IRQ0_A),
++ PINMUX_IPSR_GPSR(IP2SR1_19_16, IRQ0_B),
+
+ PINMUX_IPSR_GPSR(IP2SR1_23_20, AUDIO_CLKOUT),
+- PINMUX_IPSR_GPSR(IP2SR1_23_20, IRQ1_A),
++ PINMUX_IPSR_GPSR(IP2SR1_23_20, IRQ1_B),
+
+ PINMUX_IPSR_GPSR(IP2SR1_27_24, AUDIO_CLKIN),
+ PINMUX_IPSR_GPSR(IP2SR1_27_24, PWM3_A),
+
+- PINMUX_IPSR_GPSR(IP2SR1_31_28, TCLK2),
++ PINMUX_IPSR_GPSR(IP2SR1_31_28, TCLK2_A),
+ PINMUX_IPSR_GPSR(IP2SR1_31_28, MSIOF4_SS1),
+ PINMUX_IPSR_GPSR(IP2SR1_31_28, IRQ3_B),
+
+ /* IP3SR1 */
+- PINMUX_IPSR_GPSR(IP3SR1_3_0, HRX3),
++ PINMUX_IPSR_GPSR(IP3SR1_3_0, HRX3_A),
+ PINMUX_IPSR_GPSR(IP3SR1_3_0, SCK3_A),
+ PINMUX_IPSR_GPSR(IP3SR1_3_0, MSIOF4_SS2),
+
+- PINMUX_IPSR_GPSR(IP3SR1_7_4, HSCK3),
++ PINMUX_IPSR_GPSR(IP3SR1_7_4, HSCK3_A),
+ PINMUX_IPSR_GPSR(IP3SR1_7_4, CTS3_N_A),
+ PINMUX_IPSR_GPSR(IP3SR1_7_4, MSIOF4_SCK),
+- PINMUX_IPSR_GPSR(IP3SR1_7_4, TPU0TO0_A),
++ PINMUX_IPSR_GPSR(IP3SR1_7_4, TPU0TO0_B),
+
+- PINMUX_IPSR_GPSR(IP3SR1_11_8, HRTS3_N),
++ PINMUX_IPSR_GPSR(IP3SR1_11_8, HRTS3_N_A),
+ PINMUX_IPSR_GPSR(IP3SR1_11_8, RTS3_N_A),
+ PINMUX_IPSR_GPSR(IP3SR1_11_8, MSIOF4_TXD),
+- PINMUX_IPSR_GPSR(IP3SR1_11_8, TPU0TO1_A),
++ PINMUX_IPSR_GPSR(IP3SR1_11_8, TPU0TO1_B),
+
+- PINMUX_IPSR_GPSR(IP3SR1_15_12, HCTS3_N),
++ PINMUX_IPSR_GPSR(IP3SR1_15_12, HCTS3_N_A),
+ PINMUX_IPSR_GPSR(IP3SR1_15_12, RX3_A),
+ PINMUX_IPSR_GPSR(IP3SR1_15_12, MSIOF4_RXD),
+
+- PINMUX_IPSR_GPSR(IP3SR1_19_16, HTX3),
++ PINMUX_IPSR_GPSR(IP3SR1_19_16, HTX3_A),
+ PINMUX_IPSR_GPSR(IP3SR1_19_16, TX3_A),
+ PINMUX_IPSR_GPSR(IP3SR1_19_16, MSIOF4_SYNC),
+
+ /* IP0SR2 */
+ PINMUX_IPSR_GPSR(IP0SR2_3_0, FXR_TXDA),
+ PINMUX_IPSR_GPSR(IP0SR2_3_0, CANFD1_TX),
+- PINMUX_IPSR_GPSR(IP0SR2_3_0, TPU0TO2_A),
++ PINMUX_IPSR_GPSR(IP0SR2_3_0, TPU0TO2_B),
+
+- PINMUX_IPSR_GPSR(IP0SR2_7_4, FXR_TXENA_N),
++ PINMUX_IPSR_GPSR(IP0SR2_7_4, FXR_TXENA_N_A),
+ PINMUX_IPSR_GPSR(IP0SR2_7_4, CANFD1_RX),
+- PINMUX_IPSR_GPSR(IP0SR2_7_4, TPU0TO3_A),
++ PINMUX_IPSR_GPSR(IP0SR2_7_4, TPU0TO3_B),
+
+ PINMUX_IPSR_GPSR(IP0SR2_11_8, RXDA_EXTFXR),
+- PINMUX_IPSR_GPSR(IP0SR2_11_8, CANFD5_TX),
++ PINMUX_IPSR_GPSR(IP0SR2_11_8, CANFD5_TX_A),
+ PINMUX_IPSR_GPSR(IP0SR2_11_8, IRQ5),
+
+ PINMUX_IPSR_GPSR(IP0SR2_15_12, CLK_EXTFXR),
+- PINMUX_IPSR_GPSR(IP0SR2_15_12, CANFD5_RX),
++ PINMUX_IPSR_GPSR(IP0SR2_15_12, CANFD5_RX_A),
+ PINMUX_IPSR_GPSR(IP0SR2_15_12, IRQ4_B),
+
+ PINMUX_IPSR_GPSR(IP0SR2_19_16, RXDB_EXTFXR),
+
+- PINMUX_IPSR_GPSR(IP0SR2_23_20, FXR_TXENB_N),
++ PINMUX_IPSR_GPSR(IP0SR2_23_20, FXR_TXENB_N_A),
+
+ PINMUX_IPSR_GPSR(IP0SR2_27_24, FXR_TXDB),
+
+- PINMUX_IPSR_GPSR(IP0SR2_31_28, TPU0TO1),
++ PINMUX_IPSR_GPSR(IP0SR2_31_28, TPU0TO1_A),
+ PINMUX_IPSR_GPSR(IP0SR2_31_28, CANFD6_TX),
+- PINMUX_IPSR_GPSR(IP0SR2_31_28, TCLK2_B),
++ PINMUX_IPSR_GPSR(IP0SR2_31_28, TCLK2_C),
+
+ /* IP1SR2 */
+- PINMUX_IPSR_GPSR(IP1SR2_3_0, TPU0TO0),
++ PINMUX_IPSR_GPSR(IP1SR2_3_0, TPU0TO0_A),
+ PINMUX_IPSR_GPSR(IP1SR2_3_0, CANFD6_RX),
+- PINMUX_IPSR_GPSR(IP1SR2_3_0, TCLK1_A),
++ PINMUX_IPSR_GPSR(IP1SR2_3_0, TCLK1_B),
+
+ PINMUX_IPSR_GPSR(IP1SR2_7_4, CAN_CLK),
+- PINMUX_IPSR_GPSR(IP1SR2_7_4, FXR_TXENA_N_X),
++ PINMUX_IPSR_GPSR(IP1SR2_7_4, FXR_TXENA_N_B),
+
+ PINMUX_IPSR_GPSR(IP1SR2_11_8, CANFD0_TX),
+- PINMUX_IPSR_GPSR(IP1SR2_11_8, FXR_TXENB_N_X),
++ PINMUX_IPSR_GPSR(IP1SR2_11_8, FXR_TXENB_N_B),
+
+ PINMUX_IPSR_GPSR(IP1SR2_15_12, CANFD0_RX),
+ PINMUX_IPSR_GPSR(IP1SR2_15_12, STPWT_EXTFXR),
+
+ PINMUX_IPSR_GPSR(IP1SR2_19_16, CANFD2_TX),
+- PINMUX_IPSR_GPSR(IP1SR2_19_16, TPU0TO2),
+- PINMUX_IPSR_GPSR(IP1SR2_19_16, TCLK3_A),
++ PINMUX_IPSR_GPSR(IP1SR2_19_16, TPU0TO2_A),
++ PINMUX_IPSR_GPSR(IP1SR2_19_16, TCLK3_C),
+
+ PINMUX_IPSR_GPSR(IP1SR2_23_20, CANFD2_RX),
+- PINMUX_IPSR_GPSR(IP1SR2_23_20, TPU0TO3),
++ PINMUX_IPSR_GPSR(IP1SR2_23_20, TPU0TO3_A),
+ PINMUX_IPSR_GPSR(IP1SR2_23_20, PWM1_B),
+- PINMUX_IPSR_GPSR(IP1SR2_23_20, TCLK4_A),
++ PINMUX_IPSR_GPSR(IP1SR2_23_20, TCLK4_C),
+
+ PINMUX_IPSR_GPSR(IP1SR2_27_24, CANFD3_TX),
+- PINMUX_IPSR_GPSR(IP1SR2_27_24, PWM2_B),
++ PINMUX_IPSR_GPSR(IP1SR2_27_24, PWM2),
+
+ PINMUX_IPSR_GPSR(IP1SR2_31_28, CANFD3_RX),
+ PINMUX_IPSR_GPSR(IP1SR2_31_28, PWM3_B),
+@@ -979,12 +979,12 @@ static const u16 pinmux_data[] = {
+ PINMUX_IPSR_GPSR(IP1SR3_23_20, IPC_CLKIN),
+ PINMUX_IPSR_GPSR(IP1SR3_23_20, IPC_CLKEN_IN),
+ PINMUX_IPSR_GPSR(IP1SR3_23_20, PWM1_A),
+- PINMUX_IPSR_GPSR(IP1SR3_23_20, TCLK3_X),
++ PINMUX_IPSR_GPSR(IP1SR3_23_20, TCLK3_A),
+
+ PINMUX_IPSR_GPSR(IP1SR3_27_24, IPC_CLKOUT),
+ PINMUX_IPSR_GPSR(IP1SR3_27_24, IPC_CLKEN_OUT),
+ PINMUX_IPSR_GPSR(IP1SR3_27_24, ERROROUTC_N_A),
+- PINMUX_IPSR_GPSR(IP1SR3_27_24, TCLK4_X),
++ PINMUX_IPSR_GPSR(IP1SR3_27_24, TCLK4_A),
+
+ PINMUX_IPSR_GPSR(IP1SR3_31_28, QSPI0_SSL),
+
+@@ -1531,15 +1531,14 @@ static const unsigned int canfd4_data_mux[] = {
+ };
+
+ /* - CANFD5 ----------------------------------------------------------------- */
+-static const unsigned int canfd5_data_pins[] = {
+- /* CANFD5_TX, CANFD5_RX */
++static const unsigned int canfd5_data_a_pins[] = {
++ /* CANFD5_TX_A, CANFD5_RX_A */
+ RCAR_GP_PIN(2, 2), RCAR_GP_PIN(2, 3),
+ };
+-static const unsigned int canfd5_data_mux[] = {
+- CANFD5_TX_MARK, CANFD5_RX_MARK,
++static const unsigned int canfd5_data_a_mux[] = {
++ CANFD5_TX_A_MARK, CANFD5_RX_A_MARK,
+ };
+
+-/* - CANFD5_B ----------------------------------------------------------------- */
+ static const unsigned int canfd5_data_b_pins[] = {
+ /* CANFD5_TX_B, CANFD5_RX_B */
+ RCAR_GP_PIN(1, 8), RCAR_GP_PIN(1, 9),
+@@ -1599,49 +1598,48 @@ static const unsigned int hscif0_ctrl_mux[] = {
+ };
+
+ /* - HSCIF1 ----------------------------------------------------------------- */
+-static const unsigned int hscif1_data_pins[] = {
+- /* HRX1, HTX1 */
++static const unsigned int hscif1_data_a_pins[] = {
++ /* HRX1_A, HTX1_A */
+ RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14),
+ };
+-static const unsigned int hscif1_data_mux[] = {
+- HRX1_MARK, HTX1_MARK,
++static const unsigned int hscif1_data_a_mux[] = {
++ HRX1_A_MARK, HTX1_A_MARK,
+ };
+-static const unsigned int hscif1_clk_pins[] = {
+- /* HSCK1 */
++static const unsigned int hscif1_clk_a_pins[] = {
++ /* HSCK1_A */
+ RCAR_GP_PIN(0, 18),
+ };
+-static const unsigned int hscif1_clk_mux[] = {
+- HSCK1_MARK,
++static const unsigned int hscif1_clk_a_mux[] = {
++ HSCK1_A_MARK,
+ };
+-static const unsigned int hscif1_ctrl_pins[] = {
+- /* HRTS1_N, HCTS1_N */
++static const unsigned int hscif1_ctrl_a_pins[] = {
++ /* HRTS1_N_A, HCTS1_N_A */
+ RCAR_GP_PIN(0, 17), RCAR_GP_PIN(0, 16),
+ };
+-static const unsigned int hscif1_ctrl_mux[] = {
+- HRTS1_N_MARK, HCTS1_N_MARK,
++static const unsigned int hscif1_ctrl_a_mux[] = {
++ HRTS1_N_A_MARK, HCTS1_N_A_MARK,
+ };
+
+-/* - HSCIF1_X---------------------------------------------------------------- */
+-static const unsigned int hscif1_data_x_pins[] = {
+- /* HRX1_X, HTX1_X */
++static const unsigned int hscif1_data_b_pins[] = {
++ /* HRX1_B, HTX1_B */
+ RCAR_GP_PIN(1, 7), RCAR_GP_PIN(1, 6),
+ };
+-static const unsigned int hscif1_data_x_mux[] = {
+- HRX1_X_MARK, HTX1_X_MARK,
++static const unsigned int hscif1_data_b_mux[] = {
++ HRX1_B_MARK, HTX1_B_MARK,
+ };
+-static const unsigned int hscif1_clk_x_pins[] = {
+- /* HSCK1_X */
++static const unsigned int hscif1_clk_b_pins[] = {
++ /* HSCK1_B */
+ RCAR_GP_PIN(1, 10),
+ };
+-static const unsigned int hscif1_clk_x_mux[] = {
+- HSCK1_X_MARK,
++static const unsigned int hscif1_clk_b_mux[] = {
++ HSCK1_B_MARK,
+ };
+-static const unsigned int hscif1_ctrl_x_pins[] = {
+- /* HRTS1_N_X, HCTS1_N_X */
++static const unsigned int hscif1_ctrl_b_pins[] = {
++ /* HRTS1_N_B, HCTS1_N_B */
+ RCAR_GP_PIN(1, 9), RCAR_GP_PIN(1, 8),
+ };
+-static const unsigned int hscif1_ctrl_x_mux[] = {
+- HRTS1_N_X_MARK, HCTS1_N_X_MARK,
++static const unsigned int hscif1_ctrl_b_mux[] = {
++ HRTS1_N_B_MARK, HCTS1_N_B_MARK,
+ };
+
+ /* - HSCIF2 ----------------------------------------------------------------- */
+@@ -1668,49 +1666,48 @@ static const unsigned int hscif2_ctrl_mux[] = {
+ };
+
+ /* - HSCIF3 ----------------------------------------------------------------- */
+-static const unsigned int hscif3_data_pins[] = {
+- /* HRX3, HTX3 */
++static const unsigned int hscif3_data_a_pins[] = {
++ /* HRX3_A, HTX3_A */
+ RCAR_GP_PIN(1, 24), RCAR_GP_PIN(1, 28),
+ };
+-static const unsigned int hscif3_data_mux[] = {
+- HRX3_MARK, HTX3_MARK,
++static const unsigned int hscif3_data_a_mux[] = {
++ HRX3_A_MARK, HTX3_A_MARK,
+ };
+-static const unsigned int hscif3_clk_pins[] = {
+- /* HSCK3 */
++static const unsigned int hscif3_clk_a_pins[] = {
++ /* HSCK3_A */
+ RCAR_GP_PIN(1, 25),
+ };
+-static const unsigned int hscif3_clk_mux[] = {
+- HSCK3_MARK,
++static const unsigned int hscif3_clk_a_mux[] = {
++ HSCK3_A_MARK,
+ };
+-static const unsigned int hscif3_ctrl_pins[] = {
+- /* HRTS3_N, HCTS3_N */
++static const unsigned int hscif3_ctrl_a_pins[] = {
++ /* HRTS3_N_A, HCTS3_N_A */
+ RCAR_GP_PIN(1, 26), RCAR_GP_PIN(1, 27),
+ };
+-static const unsigned int hscif3_ctrl_mux[] = {
+- HRTS3_N_MARK, HCTS3_N_MARK,
++static const unsigned int hscif3_ctrl_a_mux[] = {
++ HRTS3_N_A_MARK, HCTS3_N_A_MARK,
+ };
+
+-/* - HSCIF3_A ----------------------------------------------------------------- */
+-static const unsigned int hscif3_data_a_pins[] = {
+- /* HRX3_A, HTX3_A */
++static const unsigned int hscif3_data_b_pins[] = {
++ /* HRX3_B, HTX3_B */
+ RCAR_GP_PIN(1, 4), RCAR_GP_PIN(1, 0),
+ };
+-static const unsigned int hscif3_data_a_mux[] = {
+- HRX3_A_MARK, HTX3_A_MARK,
++static const unsigned int hscif3_data_b_mux[] = {
++ HRX3_B_MARK, HTX3_B_MARK,
+ };
+-static const unsigned int hscif3_clk_a_pins[] = {
+- /* HSCK3_A */
++static const unsigned int hscif3_clk_b_pins[] = {
++ /* HSCK3_B */
+ RCAR_GP_PIN(1, 3),
+ };
+-static const unsigned int hscif3_clk_a_mux[] = {
+- HSCK3_A_MARK,
++static const unsigned int hscif3_clk_b_mux[] = {
++ HSCK3_B_MARK,
+ };
+-static const unsigned int hscif3_ctrl_a_pins[] = {
+- /* HRTS3_N_A, HCTS3_N_A */
++static const unsigned int hscif3_ctrl_b_pins[] = {
++ /* HRTS3_N_B, HCTS3_N_B */
+ RCAR_GP_PIN(1, 2), RCAR_GP_PIN(1, 1),
+ };
+-static const unsigned int hscif3_ctrl_a_mux[] = {
+- HRTS3_N_A_MARK, HCTS3_N_A_MARK,
++static const unsigned int hscif3_ctrl_b_mux[] = {
++ HRTS3_N_B_MARK, HCTS3_N_B_MARK,
+ };
+
+ /* - I2C0 ------------------------------------------------------------------- */
+@@ -2093,13 +2090,13 @@ static const unsigned int pcie1_clkreq_n_mux[] = {
+ PCIE1_CLKREQ_N_MARK,
+ };
+
+-/* - PWM0_A ------------------------------------------------------------------- */
+-static const unsigned int pwm0_a_pins[] = {
+- /* PWM0_A */
++/* - PWM0 ------------------------------------------------------------------- */
++static const unsigned int pwm0_pins[] = {
++ /* PWM0 */
+ RCAR_GP_PIN(1, 15),
+ };
+-static const unsigned int pwm0_a_mux[] = {
+- PWM0_A_MARK,
++static const unsigned int pwm0_mux[] = {
++ PWM0_MARK,
+ };
+
+ /* - PWM1_A ------------------------------------------------------------------- */
+@@ -2120,13 +2117,13 @@ static const unsigned int pwm1_b_mux[] = {
+ PWM1_B_MARK,
+ };
+
+-/* - PWM2_B ------------------------------------------------------------------- */
+-static const unsigned int pwm2_b_pins[] = {
+- /* PWM2_B */
++/* - PWM2 ------------------------------------------------------------------- */
++static const unsigned int pwm2_pins[] = {
++ /* PWM2 */
+ RCAR_GP_PIN(2, 14),
+ };
+-static const unsigned int pwm2_b_mux[] = {
+- PWM2_B_MARK,
++static const unsigned int pwm2_mux[] = {
++ PWM2_MARK,
+ };
+
+ /* - PWM3_A ------------------------------------------------------------------- */
+@@ -2183,22 +2180,22 @@ static const unsigned int pwm7_mux[] = {
+ PWM7_MARK,
+ };
+
+-/* - PWM8_A ------------------------------------------------------------------- */
+-static const unsigned int pwm8_a_pins[] = {
+- /* PWM8_A */
++/* - PWM8 ------------------------------------------------------------------- */
++static const unsigned int pwm8_pins[] = {
++ /* PWM8 */
+ RCAR_GP_PIN(1, 13),
+ };
+-static const unsigned int pwm8_a_mux[] = {
+- PWM8_A_MARK,
++static const unsigned int pwm8_mux[] = {
++ PWM8_MARK,
+ };
+
+-/* - PWM9_A ------------------------------------------------------------------- */
+-static const unsigned int pwm9_a_pins[] = {
+- /* PWM9_A */
++/* - PWM9 ------------------------------------------------------------------- */
++static const unsigned int pwm9_pins[] = {
++ /* PWM9 */
+ RCAR_GP_PIN(1, 14),
+ };
+-static const unsigned int pwm9_a_mux[] = {
+- PWM9_A_MARK,
++static const unsigned int pwm9_mux[] = {
++ PWM9_MARK,
+ };
+
+ /* - QSPI0 ------------------------------------------------------------------ */
+@@ -2261,75 +2258,51 @@ static const unsigned int scif0_ctrl_mux[] = {
+ };
+
+ /* - SCIF1 ------------------------------------------------------------------ */
+-static const unsigned int scif1_data_pins[] = {
+- /* RX1, TX1 */
++static const unsigned int scif1_data_a_pins[] = {
++ /* RX1_A, TX1_A */
+ RCAR_GP_PIN(0, 15), RCAR_GP_PIN(0, 14),
+ };
+-static const unsigned int scif1_data_mux[] = {
+- RX1_MARK, TX1_MARK,
++static const unsigned int scif1_data_a_mux[] = {
++ RX1_A_MARK, TX1_A_MARK,
+ };
+-static const unsigned int scif1_clk_pins[] = {
+- /* SCK1 */
++static const unsigned int scif1_clk_a_pins[] = {
++ /* SCK1_A */
+ RCAR_GP_PIN(0, 18),
+ };
+-static const unsigned int scif1_clk_mux[] = {
+- SCK1_MARK,
++static const unsigned int scif1_clk_a_mux[] = {
++ SCK1_A_MARK,
+ };
+-static const unsigned int scif1_ctrl_pins[] = {
+- /* RTS1_N, CTS1_N */
++static const unsigned int scif1_ctrl_a_pins[] = {
++ /* RTS1_N_A, CTS1_N_A */
+ RCAR_GP_PIN(0, 17), RCAR_GP_PIN(0, 16),
+ };
+-static const unsigned int scif1_ctrl_mux[] = {
+- RTS1_N_MARK, CTS1_N_MARK,
++static const unsigned int scif1_ctrl_a_mux[] = {
++ RTS1_N_A_MARK, CTS1_N_A_MARK,
+ };
+
+-/* - SCIF1_X ------------------------------------------------------------------ */
+-static const unsigned int scif1_data_x_pins[] = {
+- /* RX1_X, TX1_X */
++static const unsigned int scif1_data_b_pins[] = {
++ /* RX1_B, TX1_B */
+ RCAR_GP_PIN(1, 7), RCAR_GP_PIN(1, 6),
+ };
+-static const unsigned int scif1_data_x_mux[] = {
+- RX1_X_MARK, TX1_X_MARK,
++static const unsigned int scif1_data_b_mux[] = {
++ RX1_B_MARK, TX1_B_MARK,
+ };
+-static const unsigned int scif1_clk_x_pins[] = {
+- /* SCK1_X */
++static const unsigned int scif1_clk_b_pins[] = {
++ /* SCK1_B */
+ RCAR_GP_PIN(1, 10),
+ };
+-static const unsigned int scif1_clk_x_mux[] = {
+- SCK1_X_MARK,
++static const unsigned int scif1_clk_b_mux[] = {
++ SCK1_B_MARK,
+ };
+-static const unsigned int scif1_ctrl_x_pins[] = {
+- /* RTS1_N_X, CTS1_N_X */
++static const unsigned int scif1_ctrl_b_pins[] = {
++ /* RTS1_N_B, CTS1_N_B */
+ RCAR_GP_PIN(1, 9), RCAR_GP_PIN(1, 8),
+ };
+-static const unsigned int scif1_ctrl_x_mux[] = {
+- RTS1_N_X_MARK, CTS1_N_X_MARK,
++static const unsigned int scif1_ctrl_b_mux[] = {
++ RTS1_N_B_MARK, CTS1_N_B_MARK,
+ };
+
+ /* - SCIF3 ------------------------------------------------------------------ */
+-static const unsigned int scif3_data_pins[] = {
+- /* RX3, TX3 */
+- RCAR_GP_PIN(1, 1), RCAR_GP_PIN(1, 0),
+-};
+-static const unsigned int scif3_data_mux[] = {
+- RX3_MARK, TX3_MARK,
+-};
+-static const unsigned int scif3_clk_pins[] = {
+- /* SCK3 */
+- RCAR_GP_PIN(1, 4),
+-};
+-static const unsigned int scif3_clk_mux[] = {
+- SCK3_MARK,
+-};
+-static const unsigned int scif3_ctrl_pins[] = {
+- /* RTS3_N, CTS3_N */
+- RCAR_GP_PIN(1, 2), RCAR_GP_PIN(1, 3),
+-};
+-static const unsigned int scif3_ctrl_mux[] = {
+- RTS3_N_MARK, CTS3_N_MARK,
+-};
+-
+-/* - SCIF3_A ------------------------------------------------------------------ */
+ static const unsigned int scif3_data_a_pins[] = {
+ /* RX3_A, TX3_A */
+ RCAR_GP_PIN(1, 27), RCAR_GP_PIN(1, 28),
+@@ -2352,6 +2325,28 @@ static const unsigned int scif3_ctrl_a_mux[] = {
+ RTS3_N_A_MARK, CTS3_N_A_MARK,
+ };
+
++static const unsigned int scif3_data_b_pins[] = {
++ /* RX3_B, TX3_B */
++ RCAR_GP_PIN(1, 1), RCAR_GP_PIN(1, 0),
++};
++static const unsigned int scif3_data_b_mux[] = {
++ RX3_B_MARK, TX3_B_MARK,
++};
++static const unsigned int scif3_clk_b_pins[] = {
++ /* SCK3_B */
++ RCAR_GP_PIN(1, 4),
++};
++static const unsigned int scif3_clk_b_mux[] = {
++ SCK3_B_MARK,
++};
++static const unsigned int scif3_ctrl_b_pins[] = {
++ /* RTS3_N_B, CTS3_N_B */
++ RCAR_GP_PIN(1, 2), RCAR_GP_PIN(1, 3),
++};
++static const unsigned int scif3_ctrl_b_mux[] = {
++ RTS3_N_B_MARK, CTS3_N_B_MARK,
++};
++
+ /* - SCIF4 ------------------------------------------------------------------ */
+ static const unsigned int scif4_data_pins[] = {
+ /* RX4, TX4 */
+@@ -2408,64 +2403,63 @@ static const unsigned int ssi_ctrl_mux[] = {
+ SSI_SCK_MARK, SSI_WS_MARK,
+ };
+
+-/* - TPU ------------------------------------------------------------------- */
+-static const unsigned int tpu_to0_pins[] = {
+- /* TPU0TO0 */
++/* - TPU -------------------------------------------------------------------- */
++static const unsigned int tpu_to0_a_pins[] = {
++ /* TPU0TO0_A */
+ RCAR_GP_PIN(2, 8),
+ };
+-static const unsigned int tpu_to0_mux[] = {
+- TPU0TO0_MARK,
++static const unsigned int tpu_to0_a_mux[] = {
++ TPU0TO0_A_MARK,
+ };
+-static const unsigned int tpu_to1_pins[] = {
+- /* TPU0TO1 */
++static const unsigned int tpu_to1_a_pins[] = {
++ /* TPU0TO1_A */
+ RCAR_GP_PIN(2, 7),
+ };
+-static const unsigned int tpu_to1_mux[] = {
+- TPU0TO1_MARK,
++static const unsigned int tpu_to1_a_mux[] = {
++ TPU0TO1_A_MARK,
+ };
+-static const unsigned int tpu_to2_pins[] = {
+- /* TPU0TO2 */
++static const unsigned int tpu_to2_a_pins[] = {
++ /* TPU0TO2_A */
+ RCAR_GP_PIN(2, 12),
+ };
+-static const unsigned int tpu_to2_mux[] = {
+- TPU0TO2_MARK,
++static const unsigned int tpu_to2_a_mux[] = {
++ TPU0TO2_A_MARK,
+ };
+-static const unsigned int tpu_to3_pins[] = {
+- /* TPU0TO3 */
++static const unsigned int tpu_to3_a_pins[] = {
++ /* TPU0TO3_A */
+ RCAR_GP_PIN(2, 13),
+ };
+-static const unsigned int tpu_to3_mux[] = {
+- TPU0TO3_MARK,
++static const unsigned int tpu_to3_a_mux[] = {
++ TPU0TO3_A_MARK,
+ };
+
+-/* - TPU_A ------------------------------------------------------------------- */
+-static const unsigned int tpu_to0_a_pins[] = {
+- /* TPU0TO0_A */
++static const unsigned int tpu_to0_b_pins[] = {
++ /* TPU0TO0_B */
+ RCAR_GP_PIN(1, 25),
+ };
+-static const unsigned int tpu_to0_a_mux[] = {
+- TPU0TO0_A_MARK,
++static const unsigned int tpu_to0_b_mux[] = {
++ TPU0TO0_B_MARK,
+ };
+-static const unsigned int tpu_to1_a_pins[] = {
+- /* TPU0TO1_A */
++static const unsigned int tpu_to1_b_pins[] = {
++ /* TPU0TO1_B */
+ RCAR_GP_PIN(1, 26),
+ };
+-static const unsigned int tpu_to1_a_mux[] = {
+- TPU0TO1_A_MARK,
++static const unsigned int tpu_to1_b_mux[] = {
++ TPU0TO1_B_MARK,
+ };
+-static const unsigned int tpu_to2_a_pins[] = {
+- /* TPU0TO2_A */
++static const unsigned int tpu_to2_b_pins[] = {
++ /* TPU0TO2_B */
+ RCAR_GP_PIN(2, 0),
+ };
+-static const unsigned int tpu_to2_a_mux[] = {
+- TPU0TO2_A_MARK,
++static const unsigned int tpu_to2_b_mux[] = {
++ TPU0TO2_B_MARK,
+ };
+-static const unsigned int tpu_to3_a_pins[] = {
+- /* TPU0TO3_A */
++static const unsigned int tpu_to3_b_pins[] = {
++ /* TPU0TO3_B */
+ RCAR_GP_PIN(2, 1),
+ };
+-static const unsigned int tpu_to3_a_mux[] = {
+- TPU0TO3_A_MARK,
++static const unsigned int tpu_to3_b_mux[] = {
++ TPU0TO3_B_MARK,
+ };
+
+ /* - TSN0 ------------------------------------------------ */
+@@ -2578,8 +2572,8 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
+ SH_PFC_PIN_GROUP(canfd2_data),
+ SH_PFC_PIN_GROUP(canfd3_data),
+ SH_PFC_PIN_GROUP(canfd4_data),
+- SH_PFC_PIN_GROUP(canfd5_data), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(canfd5_data_b), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(canfd5_data_a),
++ SH_PFC_PIN_GROUP(canfd5_data_b),
+ SH_PFC_PIN_GROUP(canfd6_data),
+ SH_PFC_PIN_GROUP(canfd7_data),
+ SH_PFC_PIN_GROUP(can_clk),
+@@ -2587,21 +2581,21 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
+ SH_PFC_PIN_GROUP(hscif0_data),
+ SH_PFC_PIN_GROUP(hscif0_clk),
+ SH_PFC_PIN_GROUP(hscif0_ctrl),
+- SH_PFC_PIN_GROUP(hscif1_data), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif1_clk), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif1_ctrl), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif1_data_x), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif1_clk_x), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif1_ctrl_x), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(hscif1_data_a),
++ SH_PFC_PIN_GROUP(hscif1_clk_a),
++ SH_PFC_PIN_GROUP(hscif1_ctrl_a),
++ SH_PFC_PIN_GROUP(hscif1_data_b),
++ SH_PFC_PIN_GROUP(hscif1_clk_b),
++ SH_PFC_PIN_GROUP(hscif1_ctrl_b),
+ SH_PFC_PIN_GROUP(hscif2_data),
+ SH_PFC_PIN_GROUP(hscif2_clk),
+ SH_PFC_PIN_GROUP(hscif2_ctrl),
+- SH_PFC_PIN_GROUP(hscif3_data), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif3_clk), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif3_ctrl), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif3_data_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif3_clk_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(hscif3_ctrl_a), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(hscif3_data_a),
++ SH_PFC_PIN_GROUP(hscif3_clk_a),
++ SH_PFC_PIN_GROUP(hscif3_ctrl_a),
++ SH_PFC_PIN_GROUP(hscif3_data_b),
++ SH_PFC_PIN_GROUP(hscif3_clk_b),
++ SH_PFC_PIN_GROUP(hscif3_ctrl_b),
+
+ SH_PFC_PIN_GROUP(i2c0),
+ SH_PFC_PIN_GROUP(i2c1),
+@@ -2663,18 +2657,18 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
+ SH_PFC_PIN_GROUP(pcie0_clkreq_n),
+ SH_PFC_PIN_GROUP(pcie1_clkreq_n),
+
+- SH_PFC_PIN_GROUP(pwm0_a), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(pwm0),
+ SH_PFC_PIN_GROUP(pwm1_a),
+ SH_PFC_PIN_GROUP(pwm1_b),
+- SH_PFC_PIN_GROUP(pwm2_b), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(pwm2),
+ SH_PFC_PIN_GROUP(pwm3_a),
+ SH_PFC_PIN_GROUP(pwm3_b),
+ SH_PFC_PIN_GROUP(pwm4),
+ SH_PFC_PIN_GROUP(pwm5),
+ SH_PFC_PIN_GROUP(pwm6),
+ SH_PFC_PIN_GROUP(pwm7),
+- SH_PFC_PIN_GROUP(pwm8_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(pwm9_a), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(pwm8),
++ SH_PFC_PIN_GROUP(pwm9),
+
+ SH_PFC_PIN_GROUP(qspi0_ctrl),
+ BUS_DATA_PIN_GROUP(qspi0_data, 2),
+@@ -2686,18 +2680,18 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
+ SH_PFC_PIN_GROUP(scif0_data),
+ SH_PFC_PIN_GROUP(scif0_clk),
+ SH_PFC_PIN_GROUP(scif0_ctrl),
+- SH_PFC_PIN_GROUP(scif1_data), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif1_clk), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif1_ctrl), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif1_data_x), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif1_clk_x), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif1_ctrl_x), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif3_data), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif3_clk), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif3_ctrl), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif3_data_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif3_clk_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(scif3_ctrl_a), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(scif1_data_a),
++ SH_PFC_PIN_GROUP(scif1_clk_a),
++ SH_PFC_PIN_GROUP(scif1_ctrl_a),
++ SH_PFC_PIN_GROUP(scif1_data_b),
++ SH_PFC_PIN_GROUP(scif1_clk_b),
++ SH_PFC_PIN_GROUP(scif1_ctrl_b),
++ SH_PFC_PIN_GROUP(scif3_data_a),
++ SH_PFC_PIN_GROUP(scif3_clk_a),
++ SH_PFC_PIN_GROUP(scif3_ctrl_a),
++ SH_PFC_PIN_GROUP(scif3_data_b),
++ SH_PFC_PIN_GROUP(scif3_clk_b),
++ SH_PFC_PIN_GROUP(scif3_ctrl_b),
+ SH_PFC_PIN_GROUP(scif4_data),
+ SH_PFC_PIN_GROUP(scif4_clk),
+ SH_PFC_PIN_GROUP(scif4_ctrl),
+@@ -2707,14 +2701,14 @@ static const struct sh_pfc_pin_group pinmux_groups[] = {
+ SH_PFC_PIN_GROUP(ssi_data),
+ SH_PFC_PIN_GROUP(ssi_ctrl),
+
+- SH_PFC_PIN_GROUP(tpu_to0), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(tpu_to0_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(tpu_to1), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(tpu_to1_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(tpu_to2), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(tpu_to2_a), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(tpu_to3), /* suffix might be updated */
+- SH_PFC_PIN_GROUP(tpu_to3_a), /* suffix might be updated */
++ SH_PFC_PIN_GROUP(tpu_to0_a),
++ SH_PFC_PIN_GROUP(tpu_to0_b),
++ SH_PFC_PIN_GROUP(tpu_to1_a),
++ SH_PFC_PIN_GROUP(tpu_to1_b),
++ SH_PFC_PIN_GROUP(tpu_to2_a),
++ SH_PFC_PIN_GROUP(tpu_to2_b),
++ SH_PFC_PIN_GROUP(tpu_to3_a),
++ SH_PFC_PIN_GROUP(tpu_to3_b),
+
+ SH_PFC_PIN_GROUP(tsn0_link),
+ SH_PFC_PIN_GROUP(tsn0_phy_int),
+@@ -2788,8 +2782,7 @@ static const char * const canfd4_groups[] = {
+ };
+
+ static const char * const canfd5_groups[] = {
+- /* suffix might be updated */
+- "canfd5_data",
++ "canfd5_data_a",
+ "canfd5_data_b",
+ };
+
+@@ -2812,13 +2805,12 @@ static const char * const hscif0_groups[] = {
+ };
+
+ static const char * const hscif1_groups[] = {
+- /* suffix might be updated */
+- "hscif1_data",
+- "hscif1_clk",
+- "hscif1_ctrl",
+- "hscif1_data_x",
+- "hscif1_clk_x",
+- "hscif1_ctrl_x",
++ "hscif1_data_a",
++ "hscif1_clk_a",
++ "hscif1_ctrl_a",
++ "hscif1_data_b",
++ "hscif1_clk_b",
++ "hscif1_ctrl_b",
+ };
+
+ static const char * const hscif2_groups[] = {
+@@ -2828,13 +2820,12 @@ static const char * const hscif2_groups[] = {
+ };
+
+ static const char * const hscif3_groups[] = {
+- /* suffix might be updated */
+- "hscif3_data",
+- "hscif3_clk",
+- "hscif3_ctrl",
+ "hscif3_data_a",
+ "hscif3_clk_a",
+ "hscif3_ctrl_a",
++ "hscif3_data_b",
++ "hscif3_clk_b",
++ "hscif3_ctrl_b",
+ };
+
+ static const char * const i2c0_groups[] = {
+@@ -2931,8 +2922,7 @@ static const char * const pcie_groups[] = {
+ };
+
+ static const char * const pwm0_groups[] = {
+- /* suffix might be updated */
+- "pwm0_a",
++ "pwm0",
+ };
+
+ static const char * const pwm1_groups[] = {
+@@ -2941,8 +2931,7 @@ static const char * const pwm1_groups[] = {
+ };
+
+ static const char * const pwm2_groups[] = {
+- /* suffix might be updated */
+- "pwm2_b",
++ "pwm2",
+ };
+
+ static const char * const pwm3_groups[] = {
+@@ -2967,13 +2956,11 @@ static const char * const pwm7_groups[] = {
+ };
+
+ static const char * const pwm8_groups[] = {
+- /* suffix might be updated */
+- "pwm8_a",
++ "pwm8",
+ };
+
+ static const char * const pwm9_groups[] = {
+- /* suffix might be updated */
+- "pwm9_a",
++ "pwm9",
+ };
+
+ static const char * const qspi0_groups[] = {
+@@ -2995,23 +2982,21 @@ static const char * const scif0_groups[] = {
+ };
+
+ static const char * const scif1_groups[] = {
+- /* suffix might be updated */
+- "scif1_data",
+- "scif1_clk",
+- "scif1_ctrl",
+- "scif1_data_x",
+- "scif1_clk_x",
+- "scif1_ctrl_x",
++ "scif1_data_a",
++ "scif1_clk_a",
++ "scif1_ctrl_a",
++ "scif1_data_b",
++ "scif1_clk_b",
++ "scif1_ctrl_b",
+ };
+
+ static const char * const scif3_groups[] = {
+- /* suffix might be updated */
+- "scif3_data",
+- "scif3_clk",
+- "scif3_ctrl",
+ "scif3_data_a",
+ "scif3_clk_a",
+ "scif3_ctrl_a",
++ "scif3_data_b",
++ "scif3_clk_b",
++ "scif3_ctrl_b",
+ };
+
+ static const char * const scif4_groups[] = {
+@@ -3034,15 +3019,14 @@ static const char * const ssi_groups[] = {
+ };
+
+ static const char * const tpu_groups[] = {
+- /* suffix might be updated */
+- "tpu_to0",
+ "tpu_to0_a",
+- "tpu_to1",
++ "tpu_to0_b",
+ "tpu_to1_a",
+- "tpu_to2",
++ "tpu_to1_b",
+ "tpu_to2_a",
+- "tpu_to3",
++ "tpu_to2_b",
+ "tpu_to3_a",
++ "tpu_to3_b",
+ };
+
+ static const char * const tsn0_groups[] = {
+diff --git a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
+index 040f2c46a868d..ef97586385019 100644
+--- a/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
++++ b/drivers/pinctrl/ti/pinctrl-ti-iodelay.c
+@@ -876,7 +876,7 @@ static int ti_iodelay_probe(struct platform_device *pdev)
+ iod->desc.name = dev_name(dev);
+ iod->desc.owner = THIS_MODULE;
+
+- ret = pinctrl_register_and_init(&iod->desc, dev, iod, &iod->pctl);
++ ret = devm_pinctrl_register_and_init(dev, &iod->desc, iod, &iod->pctl);
+ if (ret) {
+ dev_err(dev, "Failed to register pinctrl\n");
+ goto exit_out;
+@@ -884,7 +884,11 @@ static int ti_iodelay_probe(struct platform_device *pdev)
+
+ platform_set_drvdata(pdev, iod);
+
+- return pinctrl_enable(iod->pctl);
++ ret = pinctrl_enable(iod->pctl);
++ if (ret)
++ goto exit_out;
++
++ return 0;
+
+ exit_out:
+ of_node_put(np);
+@@ -899,9 +903,6 @@ static void ti_iodelay_remove(struct platform_device *pdev)
+ {
+ struct ti_iodelay_device *iod = platform_get_drvdata(pdev);
+
+- if (iod->pctl)
+- pinctrl_unregister(iod->pctl);
+-
+ ti_iodelay_pinconf_deinit_dev(iod);
+
+ /* Expect other allocations to be freed by devm */
+diff --git a/drivers/platform/Makefile b/drivers/platform/Makefile
+index fbbe4f77aa5d7..837202842a6f6 100644
+--- a/drivers/platform/Makefile
++++ b/drivers/platform/Makefile
+@@ -11,4 +11,4 @@ obj-$(CONFIG_OLPC_EC) += olpc/
+ obj-$(CONFIG_GOLDFISH) += goldfish/
+ obj-$(CONFIG_CHROME_PLATFORMS) += chrome/
+ obj-$(CONFIG_SURFACE_PLATFORMS) += surface/
+-obj-$(CONFIG_ARM64) += arm64/
++obj-$(CONFIG_ARM64_PLATFORM_DEVICES) += arm64/
+diff --git a/drivers/platform/chrome/cros_ec_debugfs.c b/drivers/platform/chrome/cros_ec_debugfs.c
+index e1d313246beb5..5996e9d53c387 100644
+--- a/drivers/platform/chrome/cros_ec_debugfs.c
++++ b/drivers/platform/chrome/cros_ec_debugfs.c
+@@ -330,6 +330,7 @@ static int ec_read_version_supported(struct cros_ec_dev *ec)
+ if (!msg)
+ return 0;
+
++ msg->version = 1;
+ msg->command = EC_CMD_GET_CMD_VERSIONS + ec->cmd_offset;
+ msg->outsize = sizeof(*params);
+ msg->insize = sizeof(*response);
+diff --git a/drivers/platform/mips/cpu_hwmon.c b/drivers/platform/mips/cpu_hwmon.c
+index d8c5f9195f85f..2ac2f31090f96 100644
+--- a/drivers/platform/mips/cpu_hwmon.c
++++ b/drivers/platform/mips/cpu_hwmon.c
+@@ -139,6 +139,9 @@ static int __init loongson_hwmon_init(void)
+ csr_temp_enable = csr_readl(LOONGSON_CSR_FEATURES) &
+ LOONGSON_CSRF_TEMP;
+
++ if (!csr_temp_enable && !loongson_chiptemp[0])
++ return -ENODEV;
++
+ nr_packages = loongson_sysconf.nr_cpus /
+ loongson_sysconf.cores_per_package;
+
+diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c
+index 3f9b6285c9a66..bc9c5db383244 100644
+--- a/drivers/platform/x86/asus-wmi.c
++++ b/drivers/platform/x86/asus-wmi.c
+@@ -879,10 +879,14 @@ static ssize_t kbd_rgb_mode_store(struct device *dev,
+ struct device_attribute *attr,
+ const char *buf, size_t count)
+ {
+- struct asus_wmi *asus = dev_get_drvdata(dev);
+ u32 cmd, mode, r, g, b, speed;
++ struct led_classdev *led;
++ struct asus_wmi *asus;
+ int err;
+
++ led = dev_get_drvdata(dev);
++ asus = container_of(led, struct asus_wmi, kbd_led);
++
+ if (sscanf(buf, "%d %d %d %d %d %d", &cmd, &mode, &r, &g, &b, &speed) != 6)
+ return -EINVAL;
+
+diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
+index 9b34d1a60f662..4b0ad1b4b4c9b 100644
+--- a/drivers/power/supply/ab8500_charger.c
++++ b/drivers/power/supply/ab8500_charger.c
+@@ -488,8 +488,10 @@ static int ab8500_charger_get_ac_voltage(struct ab8500_charger *di)
+ /* Only measure voltage if the charger is connected */
+ if (di->ac.charger_connected) {
+ ret = iio_read_channel_processed(di->adc_main_charger_v, &vch);
+- if (ret < 0)
++ if (ret < 0) {
+ dev_err(di->dev, "%s ADC conv failed,\n", __func__);
++ return ret;
++ }
+ } else {
+ vch = 0;
+ }
+@@ -540,8 +542,10 @@ static int ab8500_charger_get_vbus_voltage(struct ab8500_charger *di)
+ /* Only measure voltage if the charger is connected */
+ if (di->usb.charger_connected) {
+ ret = iio_read_channel_processed(di->adc_vbus_v, &vch);
+- if (ret < 0)
++ if (ret < 0) {
+ dev_err(di->dev, "%s ADC conv failed,\n", __func__);
++ return ret;
++ }
+ } else {
+ vch = 0;
+ }
+@@ -563,8 +567,10 @@ static int ab8500_charger_get_usb_current(struct ab8500_charger *di)
+ /* Only measure current if the charger is online */
+ if (di->usb.charger_online) {
+ ret = iio_read_channel_processed(di->adc_usb_charger_c, &ich);
+- if (ret < 0)
++ if (ret < 0) {
+ dev_err(di->dev, "%s ADC conv failed,\n", __func__);
++ return ret;
++ }
+ } else {
+ ich = 0;
+ }
+@@ -586,8 +592,10 @@ static int ab8500_charger_get_ac_current(struct ab8500_charger *di)
+ /* Only measure current if the charger is online */
+ if (di->ac.charger_online) {
+ ret = iio_read_channel_processed(di->adc_main_charger_c, &ich);
+- if (ret < 0)
++ if (ret < 0) {
+ dev_err(di->dev, "%s ADC conv failed,\n", __func__);
++ return ret;
++ }
+ } else {
+ ich = 0;
+ }
+diff --git a/drivers/power/supply/ingenic-battery.c b/drivers/power/supply/ingenic-battery.c
+index 2e7fdfde47ece..0a40f425c2772 100644
+--- a/drivers/power/supply/ingenic-battery.c
++++ b/drivers/power/supply/ingenic-battery.c
+@@ -31,8 +31,9 @@ static int ingenic_battery_get_property(struct power_supply *psy,
+
+ switch (psp) {
+ case POWER_SUPPLY_PROP_HEALTH:
+- ret = iio_read_channel_processed(bat->channel, &val->intval);
+- val->intval *= 1000;
++ ret = iio_read_channel_processed_scale(bat->channel,
++ &val->intval,
++ 1000);
+ if (val->intval < info->voltage_min_design_uv)
+ val->intval = POWER_SUPPLY_HEALTH_DEAD;
+ else if (val->intval > info->voltage_max_design_uv)
+@@ -41,8 +42,9 @@ static int ingenic_battery_get_property(struct power_supply *psy,
+ val->intval = POWER_SUPPLY_HEALTH_GOOD;
+ return ret;
+ case POWER_SUPPLY_PROP_VOLTAGE_NOW:
+- ret = iio_read_channel_processed(bat->channel, &val->intval);
+- val->intval *= 1000;
++ ret = iio_read_channel_processed_scale(bat->channel,
++ &val->intval,
++ 1000);
+ return ret;
+ case POWER_SUPPLY_PROP_VOLTAGE_MIN_DESIGN:
+ val->intval = info->voltage_min_design_uv;
+diff --git a/drivers/pwm/pwm-atmel-tcb.c b/drivers/pwm/pwm-atmel-tcb.c
+index 528e54c5999d8..aca11493239a5 100644
+--- a/drivers/pwm/pwm-atmel-tcb.c
++++ b/drivers/pwm/pwm-atmel-tcb.c
+@@ -81,7 +81,8 @@ static int atmel_tcb_pwm_request(struct pwm_chip *chip,
+ tcbpwm->period = 0;
+ tcbpwm->div = 0;
+
+- spin_lock(&tcbpwmc->lock);
++ guard(spinlock)(&tcbpwmc->lock);
++
+ regmap_read(tcbpwmc->regmap, ATMEL_TC_REG(tcbpwmc->channel, CMR), &cmr);
+ /*
+ * Get init config from Timer Counter registers if
+@@ -107,7 +108,6 @@ static int atmel_tcb_pwm_request(struct pwm_chip *chip,
+
+ cmr |= ATMEL_TC_WAVE | ATMEL_TC_WAVESEL_UP_AUTO | ATMEL_TC_EEVT_XC0;
+ regmap_write(tcbpwmc->regmap, ATMEL_TC_REG(tcbpwmc->channel, CMR), cmr);
+- spin_unlock(&tcbpwmc->lock);
+
+ return 0;
+ }
+@@ -137,7 +137,6 @@ static void atmel_tcb_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm,
+ if (tcbpwm->duty == 0)
+ polarity = !polarity;
+
+- spin_lock(&tcbpwmc->lock);
+ regmap_read(tcbpwmc->regmap, ATMEL_TC_REG(tcbpwmc->channel, CMR), &cmr);
+
+ /* flush old setting and set the new one */
+@@ -172,8 +171,6 @@ static void atmel_tcb_pwm_disable(struct pwm_chip *chip, struct pwm_device *pwm,
+ ATMEL_TC_SWTRG);
+ tcbpwmc->bkup.enabled = 0;
+ }
+-
+- spin_unlock(&tcbpwmc->lock);
+ }
+
+ static int atmel_tcb_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm,
+@@ -194,7 +191,6 @@ static int atmel_tcb_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm,
+ if (tcbpwm->duty == 0)
+ polarity = !polarity;
+
+- spin_lock(&tcbpwmc->lock);
+ regmap_read(tcbpwmc->regmap, ATMEL_TC_REG(tcbpwmc->channel, CMR), &cmr);
+
+ /* flush old setting and set the new one */
+@@ -256,7 +252,6 @@ static int atmel_tcb_pwm_enable(struct pwm_chip *chip, struct pwm_device *pwm,
+ regmap_write(tcbpwmc->regmap, ATMEL_TC_REG(tcbpwmc->channel, CCR),
+ ATMEL_TC_SWTRG | ATMEL_TC_CLKEN);
+ tcbpwmc->bkup.enabled = 1;
+- spin_unlock(&tcbpwmc->lock);
+ return 0;
+ }
+
+@@ -341,9 +336,12 @@ static int atmel_tcb_pwm_config(struct pwm_chip *chip, struct pwm_device *pwm,
+ static int atmel_tcb_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+ const struct pwm_state *state)
+ {
++ struct atmel_tcb_pwm_chip *tcbpwmc = to_tcb_chip(chip);
+ int duty_cycle, period;
+ int ret;
+
++ guard(spinlock)(&tcbpwmc->lock);
++
+ if (!state->enabled) {
+ atmel_tcb_pwm_disable(chip, pwm, state->polarity);
+ return 0;
+diff --git a/drivers/pwm/pwm-stm32.c b/drivers/pwm/pwm-stm32.c
+index 8bae3fd2b3306..c586029caf233 100644
+--- a/drivers/pwm/pwm-stm32.c
++++ b/drivers/pwm/pwm-stm32.c
+@@ -452,8 +452,9 @@ static int stm32_pwm_apply(struct pwm_chip *chip, struct pwm_device *pwm,
+
+ enabled = pwm->state.enabled;
+
+- if (enabled && !state->enabled) {
+- stm32_pwm_disable(priv, pwm->hwpwm);
++ if (!state->enabled) {
++ if (enabled)
++ stm32_pwm_disable(priv, pwm->hwpwm);
+ return 0;
+ }
+
+diff --git a/drivers/remoteproc/imx_rproc.c b/drivers/remoteproc/imx_rproc.c
+index 5a3fb902acc9f..144c8e9a642e8 100644
+--- a/drivers/remoteproc/imx_rproc.c
++++ b/drivers/remoteproc/imx_rproc.c
+@@ -726,31 +726,37 @@ static int imx_rproc_addr_init(struct imx_rproc *priv,
+ struct resource res;
+
+ node = of_parse_phandle(np, "memory-region", a);
++ if (!node)
++ continue;
+ /* Not map vdevbuffer, vdevring region */
+ if (!strncmp(node->name, "vdev", strlen("vdev"))) {
+ of_node_put(node);
+ continue;
+ }
+ err = of_address_to_resource(node, 0, &res);
+- of_node_put(node);
+ if (err) {
+ dev_err(dev, "unable to resolve memory region\n");
++ of_node_put(node);
+ return err;
+ }
+
+- if (b >= IMX_RPROC_MEM_MAX)
++ if (b >= IMX_RPROC_MEM_MAX) {
++ of_node_put(node);
+ break;
++ }
+
+ /* Not use resource version, because we might share region */
+ priv->mem[b].cpu_addr = devm_ioremap_wc(&pdev->dev, res.start, resource_size(&res));
+ if (!priv->mem[b].cpu_addr) {
+ dev_err(dev, "failed to remap %pr\n", &res);
++ of_node_put(node);
+ return -ENOMEM;
+ }
+ priv->mem[b].sys_addr = res.start;
+ priv->mem[b].size = resource_size(&res);
+ if (!strcmp(node->name, "rsc-table"))
+ priv->rsc_table = priv->mem[b].cpu_addr;
++ of_node_put(node);
+ b++;
+ }
+
+diff --git a/drivers/remoteproc/mtk_scp.c b/drivers/remoteproc/mtk_scp.c
+index b8498772dba17..abf7b371b8604 100644
+--- a/drivers/remoteproc/mtk_scp.c
++++ b/drivers/remoteproc/mtk_scp.c
+@@ -1344,14 +1344,12 @@ static int scp_probe(struct platform_device *pdev)
+
+ /* l1tcm is an optional memory region */
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "l1tcm");
+- scp_cluster->l1tcm_base = devm_ioremap_resource(dev, res);
+- if (IS_ERR(scp_cluster->l1tcm_base)) {
+- ret = PTR_ERR(scp_cluster->l1tcm_base);
+- if (ret != -EINVAL)
+- return dev_err_probe(dev, ret, "Failed to map l1tcm memory\n");
++ if (res) {
++ scp_cluster->l1tcm_base = devm_ioremap_resource(dev, res);
++ if (IS_ERR(scp_cluster->l1tcm_base))
++ return dev_err_probe(dev, PTR_ERR(scp_cluster->l1tcm_base),
++ "Failed to map l1tcm memory\n");
+
+- scp_cluster->l1tcm_base = NULL;
+- } else {
+ scp_cluster->l1tcm_size = resource_size(res);
+ scp_cluster->l1tcm_phys = res->start;
+ }
+@@ -1390,7 +1388,7 @@ static const struct mtk_scp_sizes_data default_scp_sizes = {
+ };
+
+ static const struct mtk_scp_sizes_data mt8188_scp_sizes = {
+- .max_dram_size = 0x500000,
++ .max_dram_size = 0x800000,
+ .ipi_share_buffer_size = 600,
+ };
+
+@@ -1399,6 +1397,11 @@ static const struct mtk_scp_sizes_data mt8188_scp_c1_sizes = {
+ .ipi_share_buffer_size = 600,
+ };
+
++static const struct mtk_scp_sizes_data mt8195_scp_sizes = {
++ .max_dram_size = 0x800000,
++ .ipi_share_buffer_size = 288,
++};
++
+ static const struct mtk_scp_of_data mt8183_of_data = {
+ .scp_clk_get = mt8183_scp_clk_get,
+ .scp_before_load = mt8183_scp_before_load,
+@@ -1476,7 +1479,7 @@ static const struct mtk_scp_of_data mt8195_of_data = {
+ .scp_da_to_va = mt8192_scp_da_to_va,
+ .host_to_scp_reg = MT8192_GIPC_IN_SET,
+ .host_to_scp_int_bit = MT8192_HOST_IPC_INT_BIT,
+- .scp_sizes = &default_scp_sizes,
++ .scp_sizes = &mt8195_scp_sizes,
+ };
+
+ static const struct mtk_scp_of_data mt8195_of_data_c1 = {
+diff --git a/drivers/remoteproc/stm32_rproc.c b/drivers/remoteproc/stm32_rproc.c
+index 88623df7d0c35..8c7f7950b80ee 100644
+--- a/drivers/remoteproc/stm32_rproc.c
++++ b/drivers/remoteproc/stm32_rproc.c
+@@ -294,7 +294,7 @@ static void stm32_rproc_mb_vq_work(struct work_struct *work)
+
+ mutex_lock(&rproc->lock);
+
+- if (rproc->state != RPROC_RUNNING)
++ if (rproc->state != RPROC_RUNNING && rproc->state != RPROC_ATTACHED)
+ goto unlock_mutex;
+
+ if (rproc_vq_interrupt(rproc, mb->vq_id) == IRQ_NONE)
+diff --git a/drivers/remoteproc/ti_k3_r5_remoteproc.c b/drivers/remoteproc/ti_k3_r5_remoteproc.c
+index 50e486bcfa103..39a47540c5900 100644
+--- a/drivers/remoteproc/ti_k3_r5_remoteproc.c
++++ b/drivers/remoteproc/ti_k3_r5_remoteproc.c
+@@ -1144,6 +1144,7 @@ static int k3_r5_rproc_configure_mode(struct k3_r5_rproc *kproc)
+ u32 atcm_enable, btcm_enable, loczrama;
+ struct k3_r5_core *core0;
+ enum cluster_mode mode = cluster->mode;
++ int reset_ctrl_status;
+ int ret;
+
+ core0 = list_first_entry(&cluster->cores, struct k3_r5_core, elem);
+@@ -1160,11 +1161,11 @@ static int k3_r5_rproc_configure_mode(struct k3_r5_rproc *kproc)
+ r_state, c_state);
+ }
+
+- ret = reset_control_status(core->reset);
+- if (ret < 0) {
++ reset_ctrl_status = reset_control_status(core->reset);
++ if (reset_ctrl_status < 0) {
+ dev_err(cdev, "failed to get initial local reset status, ret = %d\n",
+- ret);
+- return ret;
++ reset_ctrl_status);
++ return reset_ctrl_status;
+ }
+
+ /*
+@@ -1199,7 +1200,7 @@ static int k3_r5_rproc_configure_mode(struct k3_r5_rproc *kproc)
+ * irrelevant if module reset is asserted (POR value has local reset
+ * deasserted), and is deemed as remoteproc mode
+ */
+- if (c_state && !ret && !halted) {
++ if (c_state && !reset_ctrl_status && !halted) {
+ dev_info(cdev, "configured R5F for IPC-only mode\n");
+ kproc->rproc->state = RPROC_DETACHED;
+ ret = 1;
+@@ -1217,7 +1218,7 @@ static int k3_r5_rproc_configure_mode(struct k3_r5_rproc *kproc)
+ ret = 0;
+ } else {
+ dev_err(cdev, "mismatched mode: local_reset = %s, module_reset = %s, core_state = %s\n",
+- !ret ? "deasserted" : "asserted",
++ !reset_ctrl_status ? "deasserted" : "asserted",
+ c_state ? "deasserted" : "asserted",
+ halted ? "halted" : "unhalted");
+ ret = -EINVAL;
+diff --git a/drivers/rtc/interface.c b/drivers/rtc/interface.c
+index 5faafb4aa55cc..cca650b2e0b94 100644
+--- a/drivers/rtc/interface.c
++++ b/drivers/rtc/interface.c
+@@ -274,10 +274,9 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+ return err;
+
+ /* full-function RTCs won't have such missing fields */
+- if (rtc_valid_tm(&alarm->time) == 0) {
+- rtc_add_offset(rtc, &alarm->time);
+- return 0;
+- }
++ err = rtc_valid_tm(&alarm->time);
++ if (!err)
++ goto done;
+
+ /* get the "after" timestamp, to detect wrapped fields */
+ err = rtc_read_time(rtc, &now);
+@@ -379,6 +378,8 @@ int __rtc_read_alarm(struct rtc_device *rtc, struct rtc_wkalrm *alarm)
+ if (err && alarm->enabled)
+ dev_warn(&rtc->dev, "invalid alarm value: %ptR\n",
+ &alarm->time);
++ else
++ rtc_add_offset(rtc, &alarm->time);
+
+ return err;
+ }
+diff --git a/drivers/rtc/rtc-abx80x.c b/drivers/rtc/rtc-abx80x.c
+index fde2b8054c2ea..1298962402ff4 100644
+--- a/drivers/rtc/rtc-abx80x.c
++++ b/drivers/rtc/rtc-abx80x.c
+@@ -705,14 +705,18 @@ static int abx80x_nvmem_xfer(struct abx80x_priv *priv, unsigned int offset,
+ if (ret)
+ return ret;
+
+- if (write)
++ if (write) {
+ ret = i2c_smbus_write_i2c_block_data(priv->client, reg,
+ len, val);
+- else
++ if (ret)
++ return ret;
++ } else {
+ ret = i2c_smbus_read_i2c_block_data(priv->client, reg,
+ len, val);
+- if (ret)
+- return ret;
++ if (ret <= 0)
++ return ret ? ret : -EIO;
++ len = ret;
++ }
+
+ offset += len;
+ val += len;
+diff --git a/drivers/rtc/rtc-cmos.c b/drivers/rtc/rtc-cmos.c
+index 7d99cd2c37a0b..35dca2accbb8d 100644
+--- a/drivers/rtc/rtc-cmos.c
++++ b/drivers/rtc/rtc-cmos.c
+@@ -643,11 +643,10 @@ static int cmos_nvram_read(void *priv, unsigned int off, void *val,
+ size_t count)
+ {
+ unsigned char *buf = val;
+- int retval;
+
+ off += NVRAM_OFFSET;
+ spin_lock_irq(&rtc_lock);
+- for (retval = 0; count; count--, off++, retval++) {
++ for (; count; count--, off++) {
+ if (off < 128)
+ *buf++ = CMOS_READ(off);
+ else if (can_bank2)
+@@ -657,7 +656,7 @@ static int cmos_nvram_read(void *priv, unsigned int off, void *val,
+ }
+ spin_unlock_irq(&rtc_lock);
+
+- return retval;
++ return count ? -EIO : 0;
+ }
+
+ static int cmos_nvram_write(void *priv, unsigned int off, void *val,
+@@ -665,7 +664,6 @@ static int cmos_nvram_write(void *priv, unsigned int off, void *val,
+ {
+ struct cmos_rtc *cmos = priv;
+ unsigned char *buf = val;
+- int retval;
+
+ /* NOTE: on at least PCs and Ataris, the boot firmware uses a
+ * checksum on part of the NVRAM data. That's currently ignored
+@@ -674,7 +672,7 @@ static int cmos_nvram_write(void *priv, unsigned int off, void *val,
+ */
+ off += NVRAM_OFFSET;
+ spin_lock_irq(&rtc_lock);
+- for (retval = 0; count; count--, off++, retval++) {
++ for (; count; count--, off++) {
+ /* don't trash RTC registers */
+ if (off == cmos->day_alrm
+ || off == cmos->mon_alrm
+@@ -689,7 +687,7 @@ static int cmos_nvram_write(void *priv, unsigned int off, void *val,
+ }
+ spin_unlock_irq(&rtc_lock);
+
+- return retval;
++ return count ? -EIO : 0;
+ }
+
+ /*----------------------------------------------------------------*/
+diff --git a/drivers/rtc/rtc-isl1208.c b/drivers/rtc/rtc-isl1208.c
+index e50c23ee1646a..206f96b90f58b 100644
+--- a/drivers/rtc/rtc-isl1208.c
++++ b/drivers/rtc/rtc-isl1208.c
+@@ -775,14 +775,13 @@ static int isl1208_nvmem_read(void *priv, unsigned int off, void *buf,
+ {
+ struct isl1208_state *isl1208 = priv;
+ struct i2c_client *client = to_i2c_client(isl1208->rtc->dev.parent);
+- int ret;
+
+ /* nvmem sanitizes offset/count for us, but count==0 is possible */
+ if (!count)
+ return count;
+- ret = isl1208_i2c_read_regs(client, ISL1208_REG_USR1 + off, buf,
++
++ return isl1208_i2c_read_regs(client, ISL1208_REG_USR1 + off, buf,
+ count);
+- return ret == 0 ? count : ret;
+ }
+
+ static int isl1208_nvmem_write(void *priv, unsigned int off, void *buf,
+@@ -790,15 +789,13 @@ static int isl1208_nvmem_write(void *priv, unsigned int off, void *buf,
+ {
+ struct isl1208_state *isl1208 = priv;
+ struct i2c_client *client = to_i2c_client(isl1208->rtc->dev.parent);
+- int ret;
+
+ /* nvmem sanitizes off/count for us, but count==0 is possible */
+ if (!count)
+ return count;
+- ret = isl1208_i2c_set_regs(client, ISL1208_REG_USR1 + off, buf,
+- count);
+
+- return ret == 0 ? count : ret;
++ return isl1208_i2c_set_regs(client, ISL1208_REG_USR1 + off, buf,
++ count);
+ }
+
+ static const struct nvmem_config isl1208_nvmem_config = {
+diff --git a/drivers/rtc/rtc-tps6594.c b/drivers/rtc/rtc-tps6594.c
+index 838ae8562a351..bc8dc735aa238 100644
+--- a/drivers/rtc/rtc-tps6594.c
++++ b/drivers/rtc/rtc-tps6594.c
+@@ -360,10 +360,6 @@ static int tps6594_rtc_probe(struct platform_device *pdev)
+ int irq;
+ int ret;
+
+- rtc = devm_kzalloc(dev, sizeof(*rtc), GFP_KERNEL);
+- if (!rtc)
+- return -ENOMEM;
+-
+ rtc = devm_rtc_allocate_device(dev);
+ if (IS_ERR(rtc))
+ return PTR_ERR(rtc);
+diff --git a/drivers/s390/block/dasd_devmap.c b/drivers/s390/block/dasd_devmap.c
+index 0316c20823eec..6adaeb985dde1 100644
+--- a/drivers/s390/block/dasd_devmap.c
++++ b/drivers/s390/block/dasd_devmap.c
+@@ -2248,13 +2248,19 @@ static ssize_t dasd_copy_pair_store(struct device *dev,
+
+ /* allocate primary devmap if needed */
+ prim_devmap = dasd_find_busid(prim_busid);
+- if (IS_ERR(prim_devmap))
++ if (IS_ERR(prim_devmap)) {
+ prim_devmap = dasd_add_busid(prim_busid, DASD_FEATURE_DEFAULT);
++ if (IS_ERR(prim_devmap))
++ return PTR_ERR(prim_devmap);
++ }
+
+ /* allocate secondary devmap if needed */
+ sec_devmap = dasd_find_busid(sec_busid);
+- if (IS_ERR(sec_devmap))
++ if (IS_ERR(sec_devmap)) {
+ sec_devmap = dasd_add_busid(sec_busid, DASD_FEATURE_DEFAULT);
++ if (IS_ERR(sec_devmap))
++ return PTR_ERR(sec_devmap);
++ }
+
+ /* setting copy relation is only allowed for offline secondary */
+ if (sec_devmap->device)
+diff --git a/drivers/scsi/lpfc/lpfc_attr.c b/drivers/scsi/lpfc/lpfc_attr.c
+index a46c73e8d7c40..0a9d6978cb0c3 100644
+--- a/drivers/scsi/lpfc/lpfc_attr.c
++++ b/drivers/scsi/lpfc/lpfc_attr.c
+@@ -1907,6 +1907,11 @@ lpfc_xcvr_data_show(struct device *dev, struct device_attribute *attr,
+
+ /* Get transceiver information */
+ rdp_context = kmalloc(sizeof(*rdp_context), GFP_KERNEL);
++ if (!rdp_context) {
++ len = scnprintf(buf, PAGE_SIZE - len,
++ "SPF info NA: alloc failure\n");
++ return len;
++ }
+
+ rc = lpfc_get_sfp_info_wait(phba, rdp_context);
+ if (rc) {
+diff --git a/drivers/scsi/lpfc/lpfc_hbadisc.c b/drivers/scsi/lpfc/lpfc_hbadisc.c
+index 153770bdc56ab..13b08c85440fe 100644
+--- a/drivers/scsi/lpfc/lpfc_hbadisc.c
++++ b/drivers/scsi/lpfc/lpfc_hbadisc.c
+@@ -5725,7 +5725,7 @@ lpfc_setup_disc_node(struct lpfc_vport *vport, uint32_t did)
+ return ndlp;
+
+ if (ndlp->nlp_state > NLP_STE_UNUSED_NODE &&
+- ndlp->nlp_state < NLP_STE_PRLI_ISSUE) {
++ ndlp->nlp_state <= NLP_STE_PRLI_ISSUE) {
+ lpfc_disc_state_machine(vport, ndlp, NULL,
+ NLP_EVT_DEVICE_RECOVERY);
+ }
+diff --git a/drivers/scsi/lpfc/lpfc_sli.c b/drivers/scsi/lpfc/lpfc_sli.c
+index f475e7ece41a4..3e55d5edd60ab 100644
+--- a/drivers/scsi/lpfc/lpfc_sli.c
++++ b/drivers/scsi/lpfc/lpfc_sli.c
+@@ -10579,10 +10579,11 @@ lpfc_prep_embed_io(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
+ {
+ struct lpfc_iocbq *piocb = &lpfc_cmd->cur_iocbq;
+ union lpfc_wqe128 *wqe = &lpfc_cmd->cur_iocbq.wqe;
+- struct sli4_sge *sgl;
++ struct sli4_sge_le *sgl;
++ u32 type_size;
+
+ /* 128 byte wqe support here */
+- sgl = (struct sli4_sge *)lpfc_cmd->dma_sgl;
++ sgl = (struct sli4_sge_le *)lpfc_cmd->dma_sgl;
+
+ if (phba->fcp_embed_io) {
+ struct fcp_cmnd *fcp_cmnd;
+@@ -10591,9 +10592,9 @@ lpfc_prep_embed_io(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
+ fcp_cmnd = lpfc_cmd->fcp_cmnd;
+
+ /* Word 0-2 - FCP_CMND */
+- wqe->generic.bde.tus.f.bdeFlags =
+- BUFF_TYPE_BDE_IMMED;
+- wqe->generic.bde.tus.f.bdeSize = sgl->sge_len;
++ type_size = le32_to_cpu(sgl->sge_len);
++ type_size |= ULP_BDE64_TYPE_BDE_IMMED;
++ wqe->generic.bde.tus.w = type_size;
+ wqe->generic.bde.addrHigh = 0;
+ wqe->generic.bde.addrLow = 72; /* Word 18 */
+
+@@ -10602,13 +10603,13 @@ lpfc_prep_embed_io(struct lpfc_hba *phba, struct lpfc_io_buf *lpfc_cmd)
+
+ /* Word 18-29 FCP CMND Payload */
+ ptr = &wqe->words[18];
+- memcpy(ptr, fcp_cmnd, sgl->sge_len);
++ lpfc_sli_pcimem_bcopy(fcp_cmnd, ptr, le32_to_cpu(sgl->sge_len));
+ } else {
+ /* Word 0-2 - Inline BDE */
+ wqe->generic.bde.tus.f.bdeFlags = BUFF_TYPE_BDE_64;
+- wqe->generic.bde.tus.f.bdeSize = sgl->sge_len;
+- wqe->generic.bde.addrHigh = sgl->addr_hi;
+- wqe->generic.bde.addrLow = sgl->addr_lo;
++ wqe->generic.bde.tus.f.bdeSize = le32_to_cpu(sgl->sge_len);
++ wqe->generic.bde.addrHigh = le32_to_cpu(sgl->addr_hi);
++ wqe->generic.bde.addrLow = le32_to_cpu(sgl->addr_lo);
+
+ /* Word 10 */
+ bf_set(wqe_dbde, &wqe->generic.wqe_com, 1);
+diff --git a/drivers/scsi/qla2xxx/qla_bsg.c b/drivers/scsi/qla2xxx/qla_bsg.c
+index 19bb64bdd88b1..52dc9604f5674 100644
+--- a/drivers/scsi/qla2xxx/qla_bsg.c
++++ b/drivers/scsi/qla2xxx/qla_bsg.c
+@@ -324,7 +324,7 @@ qla2x00_process_els(struct bsg_job *bsg_job)
+ "request_sg_cnt=%x reply_sg_cnt=%x.\n",
+ bsg_job->request_payload.sg_cnt,
+ bsg_job->reply_payload.sg_cnt);
+- rval = -EPERM;
++ rval = -ENOBUFS;
+ goto done;
+ }
+
+@@ -3059,17 +3059,61 @@ qla24xx_bsg_request(struct bsg_job *bsg_job)
+ return ret;
+ }
+
+-int
+-qla24xx_bsg_timeout(struct bsg_job *bsg_job)
++static bool qla_bsg_found(struct qla_qpair *qpair, struct bsg_job *bsg_job)
+ {
++ bool found = false;
+ struct fc_bsg_reply *bsg_reply = bsg_job->reply;
+ scsi_qla_host_t *vha = shost_priv(fc_bsg_to_shost(bsg_job));
+ struct qla_hw_data *ha = vha->hw;
+- srb_t *sp;
+- int cnt, que;
++ srb_t *sp = NULL;
++ int cnt;
+ unsigned long flags;
+ struct req_que *req;
+
++ spin_lock_irqsave(qpair->qp_lock_ptr, flags);
++ req = qpair->req;
++
++ for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
++ sp = req->outstanding_cmds[cnt];
++ if (sp &&
++ (sp->type == SRB_CT_CMD ||
++ sp->type == SRB_ELS_CMD_HST ||
++ sp->type == SRB_ELS_CMD_HST_NOLOGIN) &&
++ sp->u.bsg_job == bsg_job) {
++ req->outstanding_cmds[cnt] = NULL;
++ spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
++
++ if (!ha->flags.eeh_busy && ha->isp_ops->abort_command(sp)) {
++ ql_log(ql_log_warn, vha, 0x7089,
++ "mbx abort_command failed.\n");
++ bsg_reply->result = -EIO;
++ } else {
++ ql_dbg(ql_dbg_user, vha, 0x708a,
++ "mbx abort_command success.\n");
++ bsg_reply->result = 0;
++ }
++ /* ref: INIT */
++ kref_put(&sp->cmd_kref, qla2x00_sp_release);
++
++ found = true;
++ goto done;
++ }
++ }
++ spin_unlock_irqrestore(qpair->qp_lock_ptr, flags);
++
++done:
++ return found;
++}
++
++int
++qla24xx_bsg_timeout(struct bsg_job *bsg_job)
++{
++ struct fc_bsg_reply *bsg_reply = bsg_job->reply;
++ scsi_qla_host_t *vha = shost_priv(fc_bsg_to_shost(bsg_job));
++ struct qla_hw_data *ha = vha->hw;
++ int i;
++ struct qla_qpair *qpair;
++
+ ql_log(ql_log_info, vha, 0x708b, "%s CMD timeout. bsg ptr %p.\n",
+ __func__, bsg_job);
+
+@@ -3079,48 +3123,22 @@ qla24xx_bsg_timeout(struct bsg_job *bsg_job)
+ qla_pci_set_eeh_busy(vha);
+ }
+
++ if (qla_bsg_found(ha->base_qpair, bsg_job))
++ goto done;
++
+ /* find the bsg job from the active list of commands */
+- spin_lock_irqsave(&ha->hardware_lock, flags);
+- for (que = 0; que < ha->max_req_queues; que++) {
+- req = ha->req_q_map[que];
+- if (!req)
++ for (i = 0; i < ha->max_qpairs; i++) {
++ qpair = vha->hw->queue_pair_map[i];
++ if (!qpair)
+ continue;
+-
+- for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
+- sp = req->outstanding_cmds[cnt];
+- if (sp &&
+- (sp->type == SRB_CT_CMD ||
+- sp->type == SRB_ELS_CMD_HST ||
+- sp->type == SRB_ELS_CMD_HST_NOLOGIN ||
+- sp->type == SRB_FXIOCB_BCMD) &&
+- sp->u.bsg_job == bsg_job) {
+- req->outstanding_cmds[cnt] = NULL;
+- spin_unlock_irqrestore(&ha->hardware_lock, flags);
+-
+- if (!ha->flags.eeh_busy && ha->isp_ops->abort_command(sp)) {
+- ql_log(ql_log_warn, vha, 0x7089,
+- "mbx abort_command failed.\n");
+- bsg_reply->result = -EIO;
+- } else {
+- ql_dbg(ql_dbg_user, vha, 0x708a,
+- "mbx abort_command success.\n");
+- bsg_reply->result = 0;
+- }
+- spin_lock_irqsave(&ha->hardware_lock, flags);
+- goto done;
+-
+- }
+- }
++ if (qla_bsg_found(qpair, bsg_job))
++ goto done;
+ }
+- spin_unlock_irqrestore(&ha->hardware_lock, flags);
++
+ ql_log(ql_log_info, vha, 0x708b, "SRB not found to abort.\n");
+ bsg_reply->result = -ENXIO;
+- return 0;
+
+ done:
+- spin_unlock_irqrestore(&ha->hardware_lock, flags);
+- /* ref: INIT */
+- kref_put(&sp->cmd_kref, qla2x00_sp_release);
+ return 0;
+ }
+
+diff --git a/drivers/scsi/qla2xxx/qla_def.h b/drivers/scsi/qla2xxx/qla_def.h
+index 2f49baf131e26..7cf998e3cc681 100644
+--- a/drivers/scsi/qla2xxx/qla_def.h
++++ b/drivers/scsi/qla2xxx/qla_def.h
+@@ -3309,9 +3309,20 @@ struct fab_scan_rp {
+ u8 node_name[8];
+ };
+
++enum scan_step {
++ FAB_SCAN_START,
++ FAB_SCAN_GPNFT_FCP,
++ FAB_SCAN_GNNFT_FCP,
++ FAB_SCAN_GPNFT_NVME,
++ FAB_SCAN_GNNFT_NVME,
++};
++
+ struct fab_scan {
+ struct fab_scan_rp *l;
+ u32 size;
++ u32 rscn_gen_start;
++ u32 rscn_gen_end;
++ enum scan_step step;
+ u16 scan_retry;
+ #define MAX_SCAN_RETRIES 5
+ enum scan_flags_t scan_flags;
+@@ -3537,9 +3548,8 @@ enum qla_work_type {
+ QLA_EVT_RELOGIN,
+ QLA_EVT_ASYNC_PRLO,
+ QLA_EVT_ASYNC_PRLO_DONE,
+- QLA_EVT_GPNFT,
+- QLA_EVT_GPNFT_DONE,
+- QLA_EVT_GNNFT_DONE,
++ QLA_EVT_SCAN_CMD,
++ QLA_EVT_SCAN_FINISH,
+ QLA_EVT_GFPNID,
+ QLA_EVT_SP_RETRY,
+ QLA_EVT_IIDMA,
+@@ -5030,6 +5040,7 @@ typedef struct scsi_qla_host {
+
+ /* Counter to detect races between ELS and RSCN events */
+ atomic_t generation_tick;
++ atomic_t rscn_gen;
+ /* Time when global fcport update has been scheduled */
+ int total_fcport_update_gen;
+ /* List of pending LOGOs, protected by tgt_mutex */
+diff --git a/drivers/scsi/qla2xxx/qla_gbl.h b/drivers/scsi/qla2xxx/qla_gbl.h
+index 7309310d2ab94..cededfda9d0e3 100644
+--- a/drivers/scsi/qla2xxx/qla_gbl.h
++++ b/drivers/scsi/qla2xxx/qla_gbl.h
+@@ -728,9 +728,9 @@ int qla24xx_async_gpsc(scsi_qla_host_t *, fc_port_t *);
+ void qla24xx_handle_gpsc_event(scsi_qla_host_t *, struct event_arg *);
+ int qla2x00_mgmt_svr_login(scsi_qla_host_t *);
+ int qla24xx_async_gffid(scsi_qla_host_t *vha, fc_port_t *fcport, bool);
+-int qla24xx_async_gpnft(scsi_qla_host_t *, u8, srb_t *);
+-void qla24xx_async_gpnft_done(scsi_qla_host_t *, srb_t *);
+-void qla24xx_async_gnnft_done(scsi_qla_host_t *, srb_t *);
++int qla_fab_async_scan(scsi_qla_host_t *, srb_t *);
++void qla_fab_scan_start(struct scsi_qla_host *);
++void qla_fab_scan_finish(scsi_qla_host_t *, srb_t *);
+ int qla24xx_post_gfpnid_work(struct scsi_qla_host *, fc_port_t *);
+ int qla24xx_async_gfpnid(scsi_qla_host_t *, fc_port_t *);
+ void qla24xx_handle_gfpnid_event(scsi_qla_host_t *, struct event_arg *);
+diff --git a/drivers/scsi/qla2xxx/qla_gs.c b/drivers/scsi/qla2xxx/qla_gs.c
+index 1cf9d200d5630..d2bddca7045aa 100644
+--- a/drivers/scsi/qla2xxx/qla_gs.c
++++ b/drivers/scsi/qla2xxx/qla_gs.c
+@@ -1710,7 +1710,7 @@ qla2x00_hba_attributes(scsi_qla_host_t *vha, void *entries,
+ eiter->type = cpu_to_be16(FDMI_HBA_OPTION_ROM_VERSION);
+ alen = scnprintf(
+ eiter->a.orom_version, sizeof(eiter->a.orom_version),
+- "%d.%02d", ha->bios_revision[1], ha->bios_revision[0]);
++ "%d.%02d", ha->efi_revision[1], ha->efi_revision[0]);
+ alen += FDMI_ATTR_ALIGNMENT(alen);
+ alen += FDMI_ATTR_TYPELEN(eiter);
+ eiter->len = cpu_to_be16(alen);
+@@ -3168,7 +3168,30 @@ static int qla2x00_is_a_vp(scsi_qla_host_t *vha, u64 wwn)
+ return rc;
+ }
+
+-void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
++static bool qla_ok_to_clear_rscn(scsi_qla_host_t *vha, fc_port_t *fcport)
++{
++ u32 rscn_gen;
++
++ rscn_gen = atomic_read(&vha->rscn_gen);
++ ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x2017,
++ "%s %d %8phC rscn_gen %x start %x end %x current %x\n",
++ __func__, __LINE__, fcport->port_name, fcport->rscn_gen,
++ vha->scan.rscn_gen_start, vha->scan.rscn_gen_end, rscn_gen);
++
++ if (val_is_in_range(fcport->rscn_gen, vha->scan.rscn_gen_start,
++ vha->scan.rscn_gen_end))
++ /* rscn came in before fabric scan */
++ return true;
++
++ if (val_is_in_range(fcport->rscn_gen, vha->scan.rscn_gen_end, rscn_gen))
++ /* rscn came in after fabric scan */
++ return false;
++
++ /* rare: fcport's scan_needed + rscn_gen must be stale */
++ return true;
++}
++
++void qla_fab_scan_finish(scsi_qla_host_t *vha, srb_t *sp)
+ {
+ fc_port_t *fcport;
+ u32 i, rc;
+@@ -3281,10 +3304,10 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
+ (fcport->scan_needed &&
+ fcport->port_type != FCT_INITIATOR &&
+ fcport->port_type != FCT_NVME_INITIATOR)) {
++ fcport->scan_needed = 0;
+ qlt_schedule_sess_for_deletion(fcport);
+ }
+ fcport->d_id.b24 = rp->id.b24;
+- fcport->scan_needed = 0;
+ break;
+ }
+
+@@ -3325,7 +3348,9 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
+ do_delete = true;
+ }
+
+- fcport->scan_needed = 0;
++ if (qla_ok_to_clear_rscn(vha, fcport))
++ fcport->scan_needed = 0;
++
+ if (((qla_dual_mode_enabled(vha) ||
+ qla_ini_mode_enabled(vha)) &&
+ atomic_read(&fcport->state) == FCS_ONLINE) ||
+@@ -3355,7 +3380,9 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
+ fcport->port_name, fcport->loop_id,
+ fcport->login_retry);
+ }
+- fcport->scan_needed = 0;
++
++ if (qla_ok_to_clear_rscn(vha, fcport))
++ fcport->scan_needed = 0;
+ qla24xx_fcport_handle_login(vha, fcport);
+ }
+ }
+@@ -3379,14 +3406,11 @@ void qla24xx_async_gnnft_done(scsi_qla_host_t *vha, srb_t *sp)
+ }
+ }
+
+-static int qla2x00_post_gnnft_gpnft_done_work(struct scsi_qla_host *vha,
++static int qla2x00_post_next_scan_work(struct scsi_qla_host *vha,
+ srb_t *sp, int cmd)
+ {
+ struct qla_work_evt *e;
+
+- if (cmd != QLA_EVT_GPNFT_DONE && cmd != QLA_EVT_GNNFT_DONE)
+- return QLA_PARAMETER_ERROR;
+-
+ e = qla2x00_alloc_work(vha, cmd);
+ if (!e)
+ return QLA_FUNCTION_FAILED;
+@@ -3396,37 +3420,15 @@ static int qla2x00_post_gnnft_gpnft_done_work(struct scsi_qla_host *vha,
+ return qla2x00_post_work(vha, e);
+ }
+
+-static int qla2x00_post_nvme_gpnft_work(struct scsi_qla_host *vha,
+- srb_t *sp, int cmd)
+-{
+- struct qla_work_evt *e;
+-
+- if (cmd != QLA_EVT_GPNFT)
+- return QLA_PARAMETER_ERROR;
+-
+- e = qla2x00_alloc_work(vha, cmd);
+- if (!e)
+- return QLA_FUNCTION_FAILED;
+-
+- e->u.gpnft.fc4_type = FC4_TYPE_NVME;
+- e->u.gpnft.sp = sp;
+-
+- return qla2x00_post_work(vha, e);
+-}
+-
+ static void qla2x00_find_free_fcp_nvme_slot(struct scsi_qla_host *vha,
+ struct srb *sp)
+ {
+ struct qla_hw_data *ha = vha->hw;
+ int num_fibre_dev = ha->max_fibre_devices;
+- struct ct_sns_req *ct_req =
+- (struct ct_sns_req *)sp->u.iocb_cmd.u.ctarg.req;
+ struct ct_sns_gpnft_rsp *ct_rsp =
+ (struct ct_sns_gpnft_rsp *)sp->u.iocb_cmd.u.ctarg.rsp;
+ struct ct_sns_gpn_ft_data *d;
+ struct fab_scan_rp *rp;
+- u16 cmd = be16_to_cpu(ct_req->command);
+- u8 fc4_type = sp->gen2;
+ int i, j, k;
+ port_id_t id;
+ u8 found;
+@@ -3445,85 +3447,83 @@ static void qla2x00_find_free_fcp_nvme_slot(struct scsi_qla_host *vha,
+ if (id.b24 == 0 || wwn == 0)
+ continue;
+
+- if (fc4_type == FC4_TYPE_FCP_SCSI) {
+- if (cmd == GPN_FT_CMD) {
+- rp = &vha->scan.l[j];
+- rp->id = id;
+- memcpy(rp->port_name, d->port_name, 8);
+- j++;
+- rp->fc4type = FS_FC4TYPE_FCP;
+- } else {
+- for (k = 0; k < num_fibre_dev; k++) {
+- rp = &vha->scan.l[k];
+- if (id.b24 == rp->id.b24) {
+- memcpy(rp->node_name,
+- d->port_name, 8);
+- break;
+- }
++ ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x2025,
++ "%s %06x %8ph \n",
++ __func__, id.b24, d->port_name);
++
++ switch (vha->scan.step) {
++ case FAB_SCAN_GPNFT_FCP:
++ rp = &vha->scan.l[j];
++ rp->id = id;
++ memcpy(rp->port_name, d->port_name, 8);
++ j++;
++ rp->fc4type = FS_FC4TYPE_FCP;
++ break;
++ case FAB_SCAN_GNNFT_FCP:
++ for (k = 0; k < num_fibre_dev; k++) {
++ rp = &vha->scan.l[k];
++ if (id.b24 == rp->id.b24) {
++ memcpy(rp->node_name,
++ d->port_name, 8);
++ break;
+ }
+ }
+- } else {
+- /* Search if the fibre device supports FC4_TYPE_NVME */
+- if (cmd == GPN_FT_CMD) {
+- found = 0;
+-
+- for (k = 0; k < num_fibre_dev; k++) {
+- rp = &vha->scan.l[k];
+- if (!memcmp(rp->port_name,
+- d->port_name, 8)) {
+- /*
+- * Supports FC-NVMe & FCP
+- */
+- rp->fc4type |= FS_FC4TYPE_NVME;
+- found = 1;
+- break;
+- }
++ break;
++ case FAB_SCAN_GPNFT_NVME:
++ found = 0;
++
++ for (k = 0; k < num_fibre_dev; k++) {
++ rp = &vha->scan.l[k];
++ if (!memcmp(rp->port_name, d->port_name, 8)) {
++ /*
++ * Supports FC-NVMe & FCP
++ */
++ rp->fc4type |= FS_FC4TYPE_NVME;
++ found = 1;
++ break;
+ }
++ }
+
+- /* We found new FC-NVMe only port */
+- if (!found) {
+- for (k = 0; k < num_fibre_dev; k++) {
+- rp = &vha->scan.l[k];
+- if (wwn_to_u64(rp->port_name)) {
+- continue;
+- } else {
+- rp->id = id;
+- memcpy(rp->port_name,
+- d->port_name, 8);
+- rp->fc4type =
+- FS_FC4TYPE_NVME;
+- break;
+- }
+- }
+- }
+- } else {
++ /* We found new FC-NVMe only port */
++ if (!found) {
+ for (k = 0; k < num_fibre_dev; k++) {
+ rp = &vha->scan.l[k];
+- if (id.b24 == rp->id.b24) {
+- memcpy(rp->node_name,
+- d->port_name, 8);
++ if (wwn_to_u64(rp->port_name)) {
++ continue;
++ } else {
++ rp->id = id;
++ memcpy(rp->port_name, d->port_name, 8);
++ rp->fc4type = FS_FC4TYPE_NVME;
+ break;
+ }
+ }
+ }
++ break;
++ case FAB_SCAN_GNNFT_NVME:
++ for (k = 0; k < num_fibre_dev; k++) {
++ rp = &vha->scan.l[k];
++ if (id.b24 == rp->id.b24) {
++ memcpy(rp->node_name, d->port_name, 8);
++ break;
++ }
++ }
++ break;
++ default:
++ break;
+ }
+ }
+ }
+
+-static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res)
++static void qla_async_scan_sp_done(srb_t *sp, int res)
+ {
+ struct scsi_qla_host *vha = sp->vha;
+- struct ct_sns_req *ct_req =
+- (struct ct_sns_req *)sp->u.iocb_cmd.u.ctarg.req;
+- u16 cmd = be16_to_cpu(ct_req->command);
+- u8 fc4_type = sp->gen2;
+ unsigned long flags;
+ int rc;
+
+ /* gen2 field is holding the fc4type */
+- ql_dbg(ql_dbg_disc, vha, 0xffff,
+- "Async done-%s res %x FC4Type %x\n",
+- sp->name, res, sp->gen2);
++ ql_dbg(ql_dbg_disc, vha, 0x2026,
++ "Async done-%s res %x step %x\n",
++ sp->name, res, vha->scan.step);
+
+ sp->rc = res;
+ if (res) {
+@@ -3547,8 +3547,7 @@ static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res)
+ * sp for GNNFT_DONE work. This will allow all
+ * the resource to get freed up.
+ */
+- rc = qla2x00_post_gnnft_gpnft_done_work(vha, sp,
+- QLA_EVT_GNNFT_DONE);
++ rc = qla2x00_post_next_scan_work(vha, sp, QLA_EVT_SCAN_FINISH);
+ if (rc) {
+ /* Cleanup here to prevent memory leak */
+ qla24xx_sp_unmap(vha, sp);
+@@ -3573,28 +3572,30 @@ static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res)
+
+ qla2x00_find_free_fcp_nvme_slot(vha, sp);
+
+- if ((fc4_type == FC4_TYPE_FCP_SCSI) && vha->flags.nvme_enabled &&
+- cmd == GNN_FT_CMD) {
+- spin_lock_irqsave(&vha->work_lock, flags);
+- vha->scan.scan_flags &= ~SF_SCANNING;
+- spin_unlock_irqrestore(&vha->work_lock, flags);
++ spin_lock_irqsave(&vha->work_lock, flags);
++ vha->scan.scan_flags &= ~SF_SCANNING;
++ spin_unlock_irqrestore(&vha->work_lock, flags);
+
+- sp->rc = res;
+- rc = qla2x00_post_nvme_gpnft_work(vha, sp, QLA_EVT_GPNFT);
+- if (rc) {
+- qla24xx_sp_unmap(vha, sp);
+- set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+- set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+- }
+- return;
+- }
++ switch (vha->scan.step) {
++ case FAB_SCAN_GPNFT_FCP:
++ case FAB_SCAN_GPNFT_NVME:
++ rc = qla2x00_post_next_scan_work(vha, sp, QLA_EVT_SCAN_CMD);
++ break;
++ case FAB_SCAN_GNNFT_FCP:
++ if (vha->flags.nvme_enabled)
++ rc = qla2x00_post_next_scan_work(vha, sp, QLA_EVT_SCAN_CMD);
++ else
++ rc = qla2x00_post_next_scan_work(vha, sp, QLA_EVT_SCAN_FINISH);
+
+- if (cmd == GPN_FT_CMD) {
+- rc = qla2x00_post_gnnft_gpnft_done_work(vha, sp,
+- QLA_EVT_GPNFT_DONE);
+- } else {
+- rc = qla2x00_post_gnnft_gpnft_done_work(vha, sp,
+- QLA_EVT_GNNFT_DONE);
++ break;
++ case FAB_SCAN_GNNFT_NVME:
++ rc = qla2x00_post_next_scan_work(vha, sp, QLA_EVT_SCAN_FINISH);
++ break;
++ default:
++ /* should not be here */
++ WARN_ON(1);
++ rc = QLA_FUNCTION_FAILED;
++ break;
+ }
+
+ if (rc) {
+@@ -3605,127 +3606,16 @@ static void qla2x00_async_gpnft_gnnft_sp_done(srb_t *sp, int res)
+ }
+ }
+
+-/*
+- * Get WWNN list for fc4_type
+- *
+- * It is assumed the same SRB is re-used from GPNFT to avoid
+- * mem free & re-alloc
+- */
+-static int qla24xx_async_gnnft(scsi_qla_host_t *vha, struct srb *sp,
+- u8 fc4_type)
+-{
+- int rval = QLA_FUNCTION_FAILED;
+- struct ct_sns_req *ct_req;
+- struct ct_sns_pkt *ct_sns;
+- unsigned long flags;
+-
+- if (!vha->flags.online) {
+- spin_lock_irqsave(&vha->work_lock, flags);
+- vha->scan.scan_flags &= ~SF_SCANNING;
+- spin_unlock_irqrestore(&vha->work_lock, flags);
+- goto done_free_sp;
+- }
+-
+- if (!sp->u.iocb_cmd.u.ctarg.req || !sp->u.iocb_cmd.u.ctarg.rsp) {
+- ql_log(ql_log_warn, vha, 0xffff,
+- "%s: req %p rsp %p are not setup\n",
+- __func__, sp->u.iocb_cmd.u.ctarg.req,
+- sp->u.iocb_cmd.u.ctarg.rsp);
+- spin_lock_irqsave(&vha->work_lock, flags);
+- vha->scan.scan_flags &= ~SF_SCANNING;
+- spin_unlock_irqrestore(&vha->work_lock, flags);
+- WARN_ON(1);
+- set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
+- set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
+- goto done_free_sp;
+- }
+-
+- ql_dbg(ql_dbg_disc, vha, 0xfffff,
+- "%s: FC4Type %x, CT-PASSTHRU %s command ctarg rsp size %d, ctarg req size %d\n",
+- __func__, fc4_type, sp->name, sp->u.iocb_cmd.u.ctarg.rsp_size,
+- sp->u.iocb_cmd.u.ctarg.req_size);
+-
+- sp->type = SRB_CT_PTHRU_CMD;
+- sp->name = "gnnft";
+- sp->gen1 = vha->hw->base_qpair->chip_reset;
+- sp->gen2 = fc4_type;
+- qla2x00_init_async_sp(sp, qla2x00_get_async_timeout(vha) + 2,
+- qla2x00_async_gpnft_gnnft_sp_done);
+-
+- memset(sp->u.iocb_cmd.u.ctarg.rsp, 0, sp->u.iocb_cmd.u.ctarg.rsp_size);
+- memset(sp->u.iocb_cmd.u.ctarg.req, 0, sp->u.iocb_cmd.u.ctarg.req_size);
+-
+- ct_sns = (struct ct_sns_pkt *)sp->u.iocb_cmd.u.ctarg.req;
+- /* CT_IU preamble */
+- ct_req = qla2x00_prep_ct_req(ct_sns, GNN_FT_CMD,
+- sp->u.iocb_cmd.u.ctarg.rsp_size);
+-
+- /* GPN_FT req */
+- ct_req->req.gpn_ft.port_type = fc4_type;
+-
+- sp->u.iocb_cmd.u.ctarg.req_size = GNN_FT_REQ_SIZE;
+- sp->u.iocb_cmd.u.ctarg.nport_handle = NPH_SNS;
+-
+- ql_dbg(ql_dbg_disc, vha, 0xffff,
+- "Async-%s hdl=%x FC4Type %x.\n", sp->name,
+- sp->handle, ct_req->req.gpn_ft.port_type);
+-
+- rval = qla2x00_start_sp(sp);
+- if (rval != QLA_SUCCESS) {
+- goto done_free_sp;
+- }
+-
+- return rval;
+-
+-done_free_sp:
+- if (sp->u.iocb_cmd.u.ctarg.req) {
+- dma_free_coherent(&vha->hw->pdev->dev,
+- sp->u.iocb_cmd.u.ctarg.req_allocated_size,
+- sp->u.iocb_cmd.u.ctarg.req,
+- sp->u.iocb_cmd.u.ctarg.req_dma);
+- sp->u.iocb_cmd.u.ctarg.req = NULL;
+- }
+- if (sp->u.iocb_cmd.u.ctarg.rsp) {
+- dma_free_coherent(&vha->hw->pdev->dev,
+- sp->u.iocb_cmd.u.ctarg.rsp_allocated_size,
+- sp->u.iocb_cmd.u.ctarg.rsp,
+- sp->u.iocb_cmd.u.ctarg.rsp_dma);
+- sp->u.iocb_cmd.u.ctarg.rsp = NULL;
+- }
+- /* ref: INIT */
+- kref_put(&sp->cmd_kref, qla2x00_sp_release);
+-
+- spin_lock_irqsave(&vha->work_lock, flags);
+- vha->scan.scan_flags &= ~SF_SCANNING;
+- if (vha->scan.scan_flags == 0) {
+- ql_dbg(ql_dbg_disc, vha, 0xffff,
+- "%s: schedule\n", __func__);
+- vha->scan.scan_flags |= SF_QUEUED;
+- schedule_delayed_work(&vha->scan.scan_work, 5);
+- }
+- spin_unlock_irqrestore(&vha->work_lock, flags);
+-
+-
+- return rval;
+-} /* GNNFT */
+-
+-void qla24xx_async_gpnft_done(scsi_qla_host_t *vha, srb_t *sp)
+-{
+- ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
+- "%s enter\n", __func__);
+- qla24xx_async_gnnft(vha, sp, sp->gen2);
+-}
+-
+ /* Get WWPN list for certain fc4_type */
+-int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
++int qla_fab_async_scan(scsi_qla_host_t *vha, srb_t *sp)
+ {
+ int rval = QLA_FUNCTION_FAILED;
+ struct ct_sns_req *ct_req;
+ struct ct_sns_pkt *ct_sns;
+- u32 rspsz;
++ u32 rspsz = 0;
+ unsigned long flags;
+
+- ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
++ ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x200c,
+ "%s enter\n", __func__);
+
+ if (!vha->flags.online)
+@@ -3734,22 +3624,21 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
+ spin_lock_irqsave(&vha->work_lock, flags);
+ if (vha->scan.scan_flags & SF_SCANNING) {
+ spin_unlock_irqrestore(&vha->work_lock, flags);
+- ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
++ ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x2012,
+ "%s: scan active\n", __func__);
+ return rval;
+ }
+ vha->scan.scan_flags |= SF_SCANNING;
++ if (!sp)
++ vha->scan.step = FAB_SCAN_START;
++
+ spin_unlock_irqrestore(&vha->work_lock, flags);
+
+- if (fc4_type == FC4_TYPE_FCP_SCSI) {
+- ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
++ switch (vha->scan.step) {
++ case FAB_SCAN_START:
++ ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x2018,
+ "%s: Performing FCP Scan\n", __func__);
+
+- if (sp) {
+- /* ref: INIT */
+- kref_put(&sp->cmd_kref, qla2x00_sp_release);
+- }
+-
+ /* ref: INIT */
+ sp = qla2x00_get_sp(vha, NULL, GFP_KERNEL);
+ if (!sp) {
+@@ -3765,7 +3654,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
+ GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.req_allocated_size = sizeof(struct ct_sns_pkt);
+ if (!sp->u.iocb_cmd.u.ctarg.req) {
+- ql_log(ql_log_warn, vha, 0xffff,
++ ql_log(ql_log_warn, vha, 0x201a,
+ "Failed to allocate ct_sns request.\n");
+ spin_lock_irqsave(&vha->work_lock, flags);
+ vha->scan.scan_flags &= ~SF_SCANNING;
+@@ -3773,7 +3662,6 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
+ qla2x00_rel_sp(sp);
+ return rval;
+ }
+- sp->u.iocb_cmd.u.ctarg.req_size = GPN_FT_REQ_SIZE;
+
+ rspsz = sizeof(struct ct_sns_gpnft_rsp) +
+ vha->hw->max_fibre_devices *
+@@ -3785,7 +3673,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
+ GFP_KERNEL);
+ sp->u.iocb_cmd.u.ctarg.rsp_allocated_size = rspsz;
+ if (!sp->u.iocb_cmd.u.ctarg.rsp) {
+- ql_log(ql_log_warn, vha, 0xffff,
++ ql_log(ql_log_warn, vha, 0x201b,
+ "Failed to allocate ct_sns request.\n");
+ spin_lock_irqsave(&vha->work_lock, flags);
+ vha->scan.scan_flags &= ~SF_SCANNING;
+@@ -3805,35 +3693,95 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
+ "%s scan list size %d\n", __func__, vha->scan.size);
+
+ memset(vha->scan.l, 0, vha->scan.size);
+- } else if (!sp) {
+- ql_dbg(ql_dbg_disc, vha, 0xffff,
+- "NVME scan did not provide SP\n");
++
++ vha->scan.step = FAB_SCAN_GPNFT_FCP;
++ break;
++ case FAB_SCAN_GPNFT_FCP:
++ vha->scan.step = FAB_SCAN_GNNFT_FCP;
++ break;
++ case FAB_SCAN_GNNFT_FCP:
++ vha->scan.step = FAB_SCAN_GPNFT_NVME;
++ break;
++ case FAB_SCAN_GPNFT_NVME:
++ vha->scan.step = FAB_SCAN_GNNFT_NVME;
++ break;
++ case FAB_SCAN_GNNFT_NVME:
++ default:
++ /* should not be here */
++ WARN_ON(1);
++ goto done_free_sp;
++ }
++
++ if (!sp) {
++ ql_dbg(ql_dbg_disc, vha, 0x201c,
++ "scan did not provide SP\n");
+ return rval;
+ }
++ if (!sp->u.iocb_cmd.u.ctarg.req || !sp->u.iocb_cmd.u.ctarg.rsp) {
++ ql_log(ql_log_warn, vha, 0x201d,
++ "%s: req %p rsp %p are not setup\n",
++ __func__, sp->u.iocb_cmd.u.ctarg.req,
++ sp->u.iocb_cmd.u.ctarg.rsp);
++ spin_lock_irqsave(&vha->work_lock, flags);
++ vha->scan.scan_flags &= ~SF_SCANNING;
++ spin_unlock_irqrestore(&vha->work_lock, flags);
++ WARN_ON(1);
++ set_bit(LOCAL_LOOP_UPDATE, &vha->dpc_flags);
++ set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
++ goto done_free_sp;
++ }
++
++ rspsz = sp->u.iocb_cmd.u.ctarg.rsp_size;
++ memset(sp->u.iocb_cmd.u.ctarg.req, 0, sp->u.iocb_cmd.u.ctarg.req_size);
++ memset(sp->u.iocb_cmd.u.ctarg.rsp, 0, sp->u.iocb_cmd.u.ctarg.rsp_size);
++
+
+ sp->type = SRB_CT_PTHRU_CMD;
+- sp->name = "gpnft";
+ sp->gen1 = vha->hw->base_qpair->chip_reset;
+- sp->gen2 = fc4_type;
+ qla2x00_init_async_sp(sp, qla2x00_get_async_timeout(vha) + 2,
+- qla2x00_async_gpnft_gnnft_sp_done);
+-
+- rspsz = sp->u.iocb_cmd.u.ctarg.rsp_size;
+- memset(sp->u.iocb_cmd.u.ctarg.rsp, 0, sp->u.iocb_cmd.u.ctarg.rsp_size);
+- memset(sp->u.iocb_cmd.u.ctarg.req, 0, sp->u.iocb_cmd.u.ctarg.req_size);
++ qla_async_scan_sp_done);
+
+ ct_sns = (struct ct_sns_pkt *)sp->u.iocb_cmd.u.ctarg.req;
+- /* CT_IU preamble */
+- ct_req = qla2x00_prep_ct_req(ct_sns, GPN_FT_CMD, rspsz);
+
+- /* GPN_FT req */
+- ct_req->req.gpn_ft.port_type = fc4_type;
++ /* CT_IU preamble */
++ switch (vha->scan.step) {
++ case FAB_SCAN_GPNFT_FCP:
++ sp->name = "gpnft";
++ ct_req = qla2x00_prep_ct_req(ct_sns, GPN_FT_CMD, rspsz);
++ ct_req->req.gpn_ft.port_type = FC4_TYPE_FCP_SCSI;
++ sp->u.iocb_cmd.u.ctarg.req_size = GPN_FT_REQ_SIZE;
++ break;
++ case FAB_SCAN_GNNFT_FCP:
++ sp->name = "gnnft";
++ ct_req = qla2x00_prep_ct_req(ct_sns, GNN_FT_CMD, rspsz);
++ ct_req->req.gpn_ft.port_type = FC4_TYPE_FCP_SCSI;
++ sp->u.iocb_cmd.u.ctarg.req_size = GNN_FT_REQ_SIZE;
++ break;
++ case FAB_SCAN_GPNFT_NVME:
++ sp->name = "gpnft";
++ ct_req = qla2x00_prep_ct_req(ct_sns, GPN_FT_CMD, rspsz);
++ ct_req->req.gpn_ft.port_type = FC4_TYPE_NVME;
++ sp->u.iocb_cmd.u.ctarg.req_size = GPN_FT_REQ_SIZE;
++ break;
++ case FAB_SCAN_GNNFT_NVME:
++ sp->name = "gnnft";
++ ct_req = qla2x00_prep_ct_req(ct_sns, GNN_FT_CMD, rspsz);
++ ct_req->req.gpn_ft.port_type = FC4_TYPE_NVME;
++ sp->u.iocb_cmd.u.ctarg.req_size = GNN_FT_REQ_SIZE;
++ break;
++ default:
++ /* should not be here */
++ WARN_ON(1);
++ goto done_free_sp;
++ }
+
+ sp->u.iocb_cmd.u.ctarg.nport_handle = NPH_SNS;
+
+- ql_dbg(ql_dbg_disc, vha, 0xffff,
+- "Async-%s hdl=%x FC4Type %x.\n", sp->name,
+- sp->handle, ct_req->req.gpn_ft.port_type);
++ ql_dbg(ql_dbg_disc, vha, 0x2003,
++ "%s: step %d, rsp size %d, req size %d hdl %x %s FC4TYPE %x \n",
++ __func__, vha->scan.step, sp->u.iocb_cmd.u.ctarg.rsp_size,
++ sp->u.iocb_cmd.u.ctarg.req_size, sp->handle, sp->name,
++ ct_req->req.gpn_ft.port_type);
+
+ rval = qla2x00_start_sp(sp);
+ if (rval != QLA_SUCCESS) {
+@@ -3864,7 +3812,7 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
+ spin_lock_irqsave(&vha->work_lock, flags);
+ vha->scan.scan_flags &= ~SF_SCANNING;
+ if (vha->scan.scan_flags == 0) {
+- ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0xffff,
++ ql_dbg(ql_dbg_disc + ql_dbg_verbose, vha, 0x2007,
+ "%s: Scan scheduled.\n", __func__);
+ vha->scan.scan_flags |= SF_QUEUED;
+ schedule_delayed_work(&vha->scan.scan_work, 5);
+@@ -3875,6 +3823,15 @@ int qla24xx_async_gpnft(scsi_qla_host_t *vha, u8 fc4_type, srb_t *sp)
+ return rval;
+ }
+
++void qla_fab_scan_start(struct scsi_qla_host *vha)
++{
++ int rval;
++
++ rval = qla_fab_async_scan(vha, NULL);
++ if (rval)
++ set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
++}
++
+ void qla_scan_work_fn(struct work_struct *work)
+ {
+ struct fab_scan *s = container_of(to_delayed_work(work),
+diff --git a/drivers/scsi/qla2xxx/qla_init.c b/drivers/scsi/qla2xxx/qla_init.c
+index 8377624d76c98..eda3bdab934d5 100644
+--- a/drivers/scsi/qla2xxx/qla_init.c
++++ b/drivers/scsi/qla2xxx/qla_init.c
+@@ -1842,10 +1842,18 @@ int qla24xx_post_newsess_work(struct scsi_qla_host *vha, port_id_t *id,
+ return qla2x00_post_work(vha, e);
+ }
+
++static void qla_rscn_gen_tick(scsi_qla_host_t *vha, u32 *ret_rscn_gen)
++{
++ *ret_rscn_gen = atomic_inc_return(&vha->rscn_gen);
++ /* memory barrier */
++ wmb();
++}
++
+ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
+ {
+ fc_port_t *fcport;
+ unsigned long flags;
++ u32 rscn_gen;
+
+ switch (ea->id.b.rsvd_1) {
+ case RSCN_PORT_ADDR:
+@@ -1875,15 +1883,16 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
+ * Otherwise we're already in the middle of a relogin
+ */
+ fcport->scan_needed = 1;
+- fcport->rscn_gen++;
++ qla_rscn_gen_tick(vha, &fcport->rscn_gen);
+ }
+ } else {
+ fcport->scan_needed = 1;
+- fcport->rscn_gen++;
++ qla_rscn_gen_tick(vha, &fcport->rscn_gen);
+ }
+ }
+ break;
+ case RSCN_AREA_ADDR:
++ qla_rscn_gen_tick(vha, &rscn_gen);
+ list_for_each_entry(fcport, &vha->vp_fcports, list) {
+ if (fcport->flags & FCF_FCP2_DEVICE &&
+ atomic_read(&fcport->state) == FCS_ONLINE)
+@@ -1891,11 +1900,12 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
+
+ if ((ea->id.b24 & 0xffff00) == (fcport->d_id.b24 & 0xffff00)) {
+ fcport->scan_needed = 1;
+- fcport->rscn_gen++;
++ fcport->rscn_gen = rscn_gen;
+ }
+ }
+ break;
+ case RSCN_DOM_ADDR:
++ qla_rscn_gen_tick(vha, &rscn_gen);
+ list_for_each_entry(fcport, &vha->vp_fcports, list) {
+ if (fcport->flags & FCF_FCP2_DEVICE &&
+ atomic_read(&fcport->state) == FCS_ONLINE)
+@@ -1903,19 +1913,20 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
+
+ if ((ea->id.b24 & 0xff0000) == (fcport->d_id.b24 & 0xff0000)) {
+ fcport->scan_needed = 1;
+- fcport->rscn_gen++;
++ fcport->rscn_gen = rscn_gen;
+ }
+ }
+ break;
+ case RSCN_FAB_ADDR:
+ default:
++ qla_rscn_gen_tick(vha, &rscn_gen);
+ list_for_each_entry(fcport, &vha->vp_fcports, list) {
+ if (fcport->flags & FCF_FCP2_DEVICE &&
+ atomic_read(&fcport->state) == FCS_ONLINE)
+ continue;
+
+ fcport->scan_needed = 1;
+- fcport->rscn_gen++;
++ fcport->rscn_gen = rscn_gen;
+ }
+ break;
+ }
+@@ -1924,6 +1935,7 @@ void qla2x00_handle_rscn(scsi_qla_host_t *vha, struct event_arg *ea)
+ if (vha->scan.scan_flags == 0) {
+ ql_dbg(ql_dbg_disc, vha, 0xffff, "%s: schedule\n", __func__);
+ vha->scan.scan_flags |= SF_QUEUED;
++ vha->scan.rscn_gen_start = atomic_read(&vha->rscn_gen);
+ schedule_delayed_work(&vha->scan.scan_work, 5);
+ }
+ spin_unlock_irqrestore(&vha->work_lock, flags);
+@@ -6393,10 +6405,9 @@ qla2x00_configure_fabric(scsi_qla_host_t *vha)
+ qlt_do_generation_tick(vha, &discovery_gen);
+
+ if (USE_ASYNC_SCAN(ha)) {
+- rval = qla24xx_async_gpnft(vha, FC4_TYPE_FCP_SCSI,
+- NULL);
+- if (rval)
+- set_bit(LOOP_RESYNC_NEEDED, &vha->dpc_flags);
++ /* start of scan begins here */
++ vha->scan.rscn_gen_end = atomic_read(&vha->rscn_gen);
++ qla_fab_scan_start(vha);
+ } else {
+ list_for_each_entry(fcport, &vha->vp_fcports, list)
+ fcport->scan_state = QLA_FCPORT_SCAN;
+@@ -8207,15 +8218,21 @@ qla28xx_get_aux_images(
+ struct qla27xx_image_status pri_aux_image_status, sec_aux_image_status;
+ bool valid_pri_image = false, valid_sec_image = false;
+ bool active_pri_image = false, active_sec_image = false;
++ int rc;
+
+ if (!ha->flt_region_aux_img_status_pri) {
+ ql_dbg(ql_dbg_init, vha, 0x018a, "Primary aux image not addressed\n");
+ goto check_sec_image;
+ }
+
+- qla24xx_read_flash_data(vha, (uint32_t *)&pri_aux_image_status,
++ rc = qla24xx_read_flash_data(vha, (uint32_t *)&pri_aux_image_status,
+ ha->flt_region_aux_img_status_pri,
+ sizeof(pri_aux_image_status) >> 2);
++ if (rc) {
++ ql_log(ql_log_info, vha, 0x01a1,
++ "Unable to read Primary aux image(%x).\n", rc);
++ goto check_sec_image;
++ }
+ qla27xx_print_image(vha, "Primary aux image", &pri_aux_image_status);
+
+ if (qla28xx_check_aux_image_status_signature(&pri_aux_image_status)) {
+@@ -8246,9 +8263,15 @@ qla28xx_get_aux_images(
+ goto check_valid_image;
+ }
+
+- qla24xx_read_flash_data(vha, (uint32_t *)&sec_aux_image_status,
++ rc = qla24xx_read_flash_data(vha, (uint32_t *)&sec_aux_image_status,
+ ha->flt_region_aux_img_status_sec,
+ sizeof(sec_aux_image_status) >> 2);
++ if (rc) {
++ ql_log(ql_log_info, vha, 0x01a2,
++ "Unable to read Secondary aux image(%x).\n", rc);
++ goto check_valid_image;
++ }
++
+ qla27xx_print_image(vha, "Secondary aux image", &sec_aux_image_status);
+
+ if (qla28xx_check_aux_image_status_signature(&sec_aux_image_status)) {
+@@ -8306,6 +8329,7 @@ qla27xx_get_active_image(struct scsi_qla_host *vha,
+ struct qla27xx_image_status pri_image_status, sec_image_status;
+ bool valid_pri_image = false, valid_sec_image = false;
+ bool active_pri_image = false, active_sec_image = false;
++ int rc;
+
+ if (!ha->flt_region_img_status_pri) {
+ ql_dbg(ql_dbg_init, vha, 0x018a, "Primary image not addressed\n");
+@@ -8347,8 +8371,14 @@ qla27xx_get_active_image(struct scsi_qla_host *vha,
+ goto check_valid_image;
+ }
+
+- qla24xx_read_flash_data(vha, (uint32_t *)(&sec_image_status),
++ rc = qla24xx_read_flash_data(vha, (uint32_t *)(&sec_image_status),
+ ha->flt_region_img_status_sec, sizeof(sec_image_status) >> 2);
++ if (rc) {
++ ql_log(ql_log_info, vha, 0x01a3,
++ "Unable to read Secondary image status(%x).\n", rc);
++ goto check_valid_image;
++ }
++
+ qla27xx_print_image(vha, "Secondary image", &sec_image_status);
+
+ if (qla27xx_check_image_status_signature(&sec_image_status)) {
+@@ -8420,11 +8450,10 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr,
+ "FW: Loading firmware from flash (%x).\n", faddr);
+
+ dcode = (uint32_t *)req->ring;
+- qla24xx_read_flash_data(vha, dcode, faddr, 8);
+- if (qla24xx_risc_firmware_invalid(dcode)) {
++ rval = qla24xx_read_flash_data(vha, dcode, faddr, 8);
++ if (rval || qla24xx_risc_firmware_invalid(dcode)) {
+ ql_log(ql_log_fatal, vha, 0x008c,
+- "Unable to verify the integrity of flash firmware "
+- "image.\n");
++ "Unable to verify the integrity of flash firmware image (rval %x).\n", rval);
+ ql_log(ql_log_fatal, vha, 0x008d,
+ "Firmware data: %08x %08x %08x %08x.\n",
+ dcode[0], dcode[1], dcode[2], dcode[3]);
+@@ -8438,7 +8467,12 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr,
+ for (j = 0; j < segments; j++) {
+ ql_dbg(ql_dbg_init, vha, 0x008d,
+ "-> Loading segment %u...\n", j);
+- qla24xx_read_flash_data(vha, dcode, faddr, 10);
++ rval = qla24xx_read_flash_data(vha, dcode, faddr, 10);
++ if (rval) {
++ ql_log(ql_log_fatal, vha, 0x016a,
++ "-> Unable to read segment addr + size .\n");
++ return QLA_FUNCTION_FAILED;
++ }
+ risc_addr = be32_to_cpu((__force __be32)dcode[2]);
+ risc_size = be32_to_cpu((__force __be32)dcode[3]);
+ if (!*srisc_addr) {
+@@ -8454,7 +8488,13 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr,
+ ql_dbg(ql_dbg_init, vha, 0x008e,
+ "-> Loading fragment %u: %#x <- %#x (%#lx dwords)...\n",
+ fragment, risc_addr, faddr, dlen);
+- qla24xx_read_flash_data(vha, dcode, faddr, dlen);
++ rval = qla24xx_read_flash_data(vha, dcode, faddr, dlen);
++ if (rval) {
++ ql_log(ql_log_fatal, vha, 0x016b,
++ "-> Unable to read fragment(faddr %#x dlen %#lx).\n",
++ faddr, dlen);
++ return QLA_FUNCTION_FAILED;
++ }
+ for (i = 0; i < dlen; i++)
+ dcode[i] = swab32(dcode[i]);
+
+@@ -8483,7 +8523,14 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr,
+ fwdt->length = 0;
+
+ dcode = (uint32_t *)req->ring;
+- qla24xx_read_flash_data(vha, dcode, faddr, 7);
++
++ rval = qla24xx_read_flash_data(vha, dcode, faddr, 7);
++ if (rval) {
++ ql_log(ql_log_fatal, vha, 0x016c,
++ "-> Unable to read template size.\n");
++ goto failed;
++ }
++
+ risc_size = be32_to_cpu((__force __be32)dcode[2]);
+ ql_dbg(ql_dbg_init, vha, 0x0161,
+ "-> fwdt%u template array at %#x (%#x dwords)\n",
+@@ -8509,11 +8556,12 @@ qla24xx_load_risc_flash(scsi_qla_host_t *vha, uint32_t *srisc_addr,
+ }
+
+ dcode = fwdt->template;
+- qla24xx_read_flash_data(vha, dcode, faddr, risc_size);
++ rval = qla24xx_read_flash_data(vha, dcode, faddr, risc_size);
+
+- if (!qla27xx_fwdt_template_valid(dcode)) {
++ if (rval || !qla27xx_fwdt_template_valid(dcode)) {
+ ql_log(ql_log_warn, vha, 0x0165,
+- "-> fwdt%u failed template validate\n", j);
++ "-> fwdt%u failed template validate (rval %x)\n",
++ j, rval);
+ goto failed;
+ }
+
+diff --git a/drivers/scsi/qla2xxx/qla_inline.h b/drivers/scsi/qla2xxx/qla_inline.h
+index a4a56ab0ba747..ef4b3cc1cd77e 100644
+--- a/drivers/scsi/qla2xxx/qla_inline.h
++++ b/drivers/scsi/qla2xxx/qla_inline.h
+@@ -631,3 +631,11 @@ static inline int qla_mapq_alloc_qp_cpu_map(struct qla_hw_data *ha)
+ }
+ return 0;
+ }
++
++static inline bool val_is_in_range(u32 val, u32 start, u32 end)
++{
++ if (val >= start && val <= end)
++ return true;
++ else
++ return false;
++}
+diff --git a/drivers/scsi/qla2xxx/qla_mid.c b/drivers/scsi/qla2xxx/qla_mid.c
+index b67416951a5f7..76703f2706b8e 100644
+--- a/drivers/scsi/qla2xxx/qla_mid.c
++++ b/drivers/scsi/qla2xxx/qla_mid.c
+@@ -180,7 +180,7 @@ qla24xx_disable_vp(scsi_qla_host_t *vha)
+ atomic_set(&vha->loop_state, LOOP_DOWN);
+ atomic_set(&vha->loop_down_timer, LOOP_DOWN_TIME);
+ list_for_each_entry(fcport, &vha->vp_fcports, list)
+- fcport->logout_on_delete = 0;
++ fcport->logout_on_delete = 1;
+
+ if (!vha->hw->flags.edif_enabled)
+ qla2x00_wait_for_sess_deletion(vha);
+diff --git a/drivers/scsi/qla2xxx/qla_nvme.c b/drivers/scsi/qla2xxx/qla_nvme.c
+index a8ddf356e6626..8f4cc136a9c9c 100644
+--- a/drivers/scsi/qla2xxx/qla_nvme.c
++++ b/drivers/scsi/qla2xxx/qla_nvme.c
+@@ -49,7 +49,10 @@ int qla_nvme_register_remote(struct scsi_qla_host *vha, struct fc_port *fcport)
+ return 0;
+ }
+
+- if (!vha->nvme_local_port && qla_nvme_register_hba(vha))
++ if (qla_nvme_register_hba(vha))
++ return 0;
++
++ if (!vha->nvme_local_port)
+ return 0;
+
+ if (!(fcport->nvme_prli_service_param &
+diff --git a/drivers/scsi/qla2xxx/qla_os.c b/drivers/scsi/qla2xxx/qla_os.c
+index fcb06df2ce4e6..bc3b2aea3f8bf 100644
+--- a/drivers/scsi/qla2xxx/qla_os.c
++++ b/drivers/scsi/qla2xxx/qla_os.c
+@@ -1875,14 +1875,9 @@ __qla2x00_abort_all_cmds(struct qla_qpair *qp, int res)
+ for (cnt = 1; cnt < req->num_outstanding_cmds; cnt++) {
+ sp = req->outstanding_cmds[cnt];
+ if (sp) {
+- /*
+- * perform lockless completion during driver unload
+- */
+ if (qla2x00_chip_is_down(vha)) {
+ req->outstanding_cmds[cnt] = NULL;
+- spin_unlock_irqrestore(qp->qp_lock_ptr, flags);
+ sp->done(sp, res);
+- spin_lock_irqsave(qp->qp_lock_ptr, flags);
+ continue;
+ }
+
+@@ -4689,7 +4684,7 @@ static void
+ qla2x00_number_of_exch(scsi_qla_host_t *vha, u32 *ret_cnt, u16 max_cnt)
+ {
+ u32 temp;
+- struct init_cb_81xx *icb = (struct init_cb_81xx *)&vha->hw->init_cb;
++ struct init_cb_81xx *icb = (struct init_cb_81xx *)vha->hw->init_cb;
+ *ret_cnt = FW_DEF_EXCHANGES_CNT;
+
+ if (max_cnt > vha->hw->max_exchg)
+@@ -5563,15 +5558,11 @@ qla2x00_do_work(struct scsi_qla_host *vha)
+ qla2x00_async_prlo_done(vha, e->u.logio.fcport,
+ e->u.logio.data);
+ break;
+- case QLA_EVT_GPNFT:
+- qla24xx_async_gpnft(vha, e->u.gpnft.fc4_type,
+- e->u.gpnft.sp);
+- break;
+- case QLA_EVT_GPNFT_DONE:
+- qla24xx_async_gpnft_done(vha, e->u.iosb.sp);
++ case QLA_EVT_SCAN_CMD:
++ qla_fab_async_scan(vha, e->u.iosb.sp);
+ break;
+- case QLA_EVT_GNNFT_DONE:
+- qla24xx_async_gnnft_done(vha, e->u.iosb.sp);
++ case QLA_EVT_SCAN_FINISH:
++ qla_fab_scan_finish(vha, e->u.iosb.sp);
+ break;
+ case QLA_EVT_GFPNID:
+ qla24xx_async_gfpnid(vha, e->u.fcport.fcport);
+diff --git a/drivers/scsi/qla2xxx/qla_sup.c b/drivers/scsi/qla2xxx/qla_sup.c
+index c092a6b1ced4f..6d16546e17292 100644
+--- a/drivers/scsi/qla2xxx/qla_sup.c
++++ b/drivers/scsi/qla2xxx/qla_sup.c
+@@ -555,6 +555,7 @@ qla2xxx_find_flt_start(scsi_qla_host_t *vha, uint32_t *start)
+ struct qla_flt_location *fltl = (void *)req->ring;
+ uint32_t *dcode = (uint32_t *)req->ring;
+ uint8_t *buf = (void *)req->ring, *bcode, last_image;
++ int rc;
+
+ /*
+ * FLT-location structure resides after the last PCI region.
+@@ -584,14 +585,24 @@ qla2xxx_find_flt_start(scsi_qla_host_t *vha, uint32_t *start)
+ pcihdr = 0;
+ do {
+ /* Verify PCI expansion ROM header. */
+- qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20);
++ rc = qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20);
++ if (rc) {
++ ql_log(ql_log_info, vha, 0x016d,
++ "Unable to read PCI Expansion Rom Header (%x).\n", rc);
++ return QLA_FUNCTION_FAILED;
++ }
+ bcode = buf + (pcihdr % 4);
+ if (bcode[0x0] != 0x55 || bcode[0x1] != 0xaa)
+ goto end;
+
+ /* Locate PCI data structure. */
+ pcids = pcihdr + ((bcode[0x19] << 8) | bcode[0x18]);
+- qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20);
++ rc = qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20);
++ if (rc) {
++ ql_log(ql_log_info, vha, 0x0179,
++ "Unable to read PCI Data Structure (%x).\n", rc);
++ return QLA_FUNCTION_FAILED;
++ }
+ bcode = buf + (pcihdr % 4);
+
+ /* Validate signature of PCI data structure. */
+@@ -606,7 +617,12 @@ qla2xxx_find_flt_start(scsi_qla_host_t *vha, uint32_t *start)
+ } while (!last_image);
+
+ /* Now verify FLT-location structure. */
+- qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, sizeof(*fltl) >> 2);
++ rc = qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, sizeof(*fltl) >> 2);
++ if (rc) {
++ ql_log(ql_log_info, vha, 0x017a,
++ "Unable to read FLT (%x).\n", rc);
++ return QLA_FUNCTION_FAILED;
++ }
+ if (memcmp(fltl->sig, "QFLT", 4))
+ goto end;
+
+@@ -2605,13 +2621,18 @@ qla24xx_read_optrom_data(struct scsi_qla_host *vha, void *buf,
+ uint32_t offset, uint32_t length)
+ {
+ struct qla_hw_data *ha = vha->hw;
++ int rc;
+
+ /* Suspend HBA. */
+ scsi_block_requests(vha->host);
+ set_bit(MBX_UPDATE_FLASH_ACTIVE, &ha->mbx_cmd_flags);
+
+ /* Go with read. */
+- qla24xx_read_flash_data(vha, buf, offset >> 2, length >> 2);
++ rc = qla24xx_read_flash_data(vha, buf, offset >> 2, length >> 2);
++ if (rc) {
++ ql_log(ql_log_info, vha, 0x01a0,
++ "Unable to perform optrom read(%x).\n", rc);
++ }
+
+ /* Resume HBA. */
+ clear_bit(MBX_UPDATE_FLASH_ACTIVE, &ha->mbx_cmd_flags);
+@@ -3412,7 +3433,7 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
+ struct active_regions active_regions = { };
+
+ if (IS_P3P_TYPE(ha))
+- return ret;
++ return QLA_SUCCESS;
+
+ if (!mbuf)
+ return QLA_FUNCTION_FAILED;
+@@ -3432,20 +3453,31 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
+
+ do {
+ /* Verify PCI expansion ROM header. */
+- qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20);
++ ret = qla24xx_read_flash_data(vha, dcode, pcihdr >> 2, 0x20);
++ if (ret) {
++ ql_log(ql_log_info, vha, 0x017d,
++ "Unable to read PCI EXP Rom Header(%x).\n", ret);
++ return QLA_FUNCTION_FAILED;
++ }
++
+ bcode = mbuf + (pcihdr % 4);
+ if (memcmp(bcode, "\x55\xaa", 2)) {
+ /* No signature */
+ ql_log(ql_log_fatal, vha, 0x0059,
+ "No matching ROM signature.\n");
+- ret = QLA_FUNCTION_FAILED;
+- break;
++ return QLA_FUNCTION_FAILED;
+ }
+
+ /* Locate PCI data structure. */
+ pcids = pcihdr + ((bcode[0x19] << 8) | bcode[0x18]);
+
+- qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20);
++ ret = qla24xx_read_flash_data(vha, dcode, pcids >> 2, 0x20);
++ if (ret) {
++ ql_log(ql_log_info, vha, 0x018e,
++ "Unable to read PCI Data Structure (%x).\n", ret);
++ return QLA_FUNCTION_FAILED;
++ }
++
+ bcode = mbuf + (pcihdr % 4);
+
+ /* Validate signature of PCI data structure. */
+@@ -3454,8 +3486,7 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
+ ql_log(ql_log_fatal, vha, 0x005a,
+ "PCI data struct not found pcir_adr=%x.\n", pcids);
+ ql_dump_buffer(ql_dbg_init, vha, 0x0059, dcode, 32);
+- ret = QLA_FUNCTION_FAILED;
+- break;
++ return QLA_FUNCTION_FAILED;
+ }
+
+ /* Read version */
+@@ -3507,20 +3538,26 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
+ faddr = ha->flt_region_fw_sec;
+ }
+
+- qla24xx_read_flash_data(vha, dcode, faddr, 8);
+- if (qla24xx_risc_firmware_invalid(dcode)) {
+- ql_log(ql_log_warn, vha, 0x005f,
+- "Unrecognized fw revision at %x.\n",
+- ha->flt_region_fw * 4);
+- ql_dump_buffer(ql_dbg_init, vha, 0x005f, dcode, 32);
++ ret = qla24xx_read_flash_data(vha, dcode, faddr, 8);
++ if (ret) {
++ ql_log(ql_log_info, vha, 0x019e,
++ "Unable to read FW version (%x).\n", ret);
++ return ret;
+ } else {
+- for (i = 0; i < 4; i++)
+- ha->fw_revision[i] =
++ if (qla24xx_risc_firmware_invalid(dcode)) {
++ ql_log(ql_log_warn, vha, 0x005f,
++ "Unrecognized fw revision at %x.\n",
++ ha->flt_region_fw * 4);
++ ql_dump_buffer(ql_dbg_init, vha, 0x005f, dcode, 32);
++ } else {
++ for (i = 0; i < 4; i++)
++ ha->fw_revision[i] =
+ be32_to_cpu((__force __be32)dcode[4+i]);
+- ql_dbg(ql_dbg_init, vha, 0x0060,
+- "Firmware revision (flash) %u.%u.%u (%x).\n",
+- ha->fw_revision[0], ha->fw_revision[1],
+- ha->fw_revision[2], ha->fw_revision[3]);
++ ql_dbg(ql_dbg_init, vha, 0x0060,
++ "Firmware revision (flash) %u.%u.%u (%x).\n",
++ ha->fw_revision[0], ha->fw_revision[1],
++ ha->fw_revision[2], ha->fw_revision[3]);
++ }
+ }
+
+ /* Check for golden firmware and get version if available */
+@@ -3531,18 +3568,23 @@ qla24xx_get_flash_version(scsi_qla_host_t *vha, void *mbuf)
+
+ memset(ha->gold_fw_version, 0, sizeof(ha->gold_fw_version));
+ faddr = ha->flt_region_gold_fw;
+- qla24xx_read_flash_data(vha, dcode, ha->flt_region_gold_fw, 8);
+- if (qla24xx_risc_firmware_invalid(dcode)) {
+- ql_log(ql_log_warn, vha, 0x0056,
+- "Unrecognized golden fw at %#x.\n", faddr);
+- ql_dump_buffer(ql_dbg_init, vha, 0x0056, dcode, 32);
++ ret = qla24xx_read_flash_data(vha, dcode, ha->flt_region_gold_fw, 8);
++ if (ret) {
++ ql_log(ql_log_info, vha, 0x019f,
++ "Unable to read Gold FW version (%x).\n", ret);
+ return ret;
+- }
+-
+- for (i = 0; i < 4; i++)
+- ha->gold_fw_version[i] =
+- be32_to_cpu((__force __be32)dcode[4+i]);
++ } else {
++ if (qla24xx_risc_firmware_invalid(dcode)) {
++ ql_log(ql_log_warn, vha, 0x0056,
++ "Unrecognized golden fw at %#x.\n", faddr);
++ ql_dump_buffer(ql_dbg_init, vha, 0x0056, dcode, 32);
++ return QLA_FUNCTION_FAILED;
++ }
+
++ for (i = 0; i < 4; i++)
++ ha->gold_fw_version[i] =
++ be32_to_cpu((__force __be32)dcode[4+i]);
++ }
+ return ret;
+ }
+
+diff --git a/drivers/scsi/sr_ioctl.c b/drivers/scsi/sr_ioctl.c
+index a0d2556a27bba..089653018d32c 100644
+--- a/drivers/scsi/sr_ioctl.c
++++ b/drivers/scsi/sr_ioctl.c
+@@ -431,7 +431,7 @@ int sr_select_speed(struct cdrom_device_info *cdi, unsigned long speed)
+ struct packet_command cgc;
+
+ /* avoid exceeding the max speed or overflowing integer bounds */
+- speed = clamp(0, speed, 0xffff / 177);
++ speed = clamp(speed, 0, 0xffff / 177);
+
+ if (speed == 0)
+ speed = 0xffff; /* set to max */
+diff --git a/drivers/soc/mediatek/mtk-mutex.c b/drivers/soc/mediatek/mtk-mutex.c
+index b5af1fb5847ea..01b129caf1eb2 100644
+--- a/drivers/soc/mediatek/mtk-mutex.c
++++ b/drivers/soc/mediatek/mtk-mutex.c
+@@ -524,6 +524,7 @@ static const unsigned int mt8188_mdp_mutex_table_mod[MUTEX_MOD_IDX_MAX] = {
+ [MUTEX_MOD_IDX_MDP_PAD0] = MT8195_MUTEX_MOD_MDP_PAD0,
+ [MUTEX_MOD_IDX_MDP_PAD2] = MT8195_MUTEX_MOD_MDP_PAD2,
+ [MUTEX_MOD_IDX_MDP_PAD3] = MT8195_MUTEX_MOD_MDP_PAD3,
++ [MUTEX_MOD_IDX_MDP_TCC0] = MT8195_MUTEX_MOD_MDP_TCC0,
+ [MUTEX_MOD_IDX_MDP_WROT0] = MT8195_MUTEX_MOD_MDP_WROT0,
+ [MUTEX_MOD_IDX_MDP_WROT2] = MT8195_MUTEX_MOD_MDP_WROT2,
+ [MUTEX_MOD_IDX_MDP_WROT3] = MT8195_MUTEX_MOD_MDP_WROT3,
+diff --git a/drivers/soc/qcom/icc-bwmon.c b/drivers/soc/qcom/icc-bwmon.c
+index fb323b3364db4..ecddb60bd6650 100644
+--- a/drivers/soc/qcom/icc-bwmon.c
++++ b/drivers/soc/qcom/icc-bwmon.c
+@@ -565,7 +565,7 @@ static void bwmon_start(struct icc_bwmon *bwmon)
+ int window;
+
+ /* No need to check for errors, as this must have succeeded before. */
+- dev_pm_opp_find_bw_ceil(bwmon->dev, &bw_low, 0);
++ dev_pm_opp_put(dev_pm_opp_find_bw_ceil(bwmon->dev, &bw_low, 0));
+
+ bwmon_clear_counters(bwmon, true);
+
+@@ -772,11 +772,13 @@ static int bwmon_probe(struct platform_device *pdev)
+ opp = dev_pm_opp_find_bw_floor(dev, &bwmon->max_bw_kbps, 0);
+ if (IS_ERR(opp))
+ return dev_err_probe(dev, PTR_ERR(opp), "failed to find max peak bandwidth\n");
++ dev_pm_opp_put(opp);
+
+ bwmon->min_bw_kbps = 0;
+ opp = dev_pm_opp_find_bw_ceil(dev, &bwmon->min_bw_kbps, 0);
+ if (IS_ERR(opp))
+ return dev_err_probe(dev, PTR_ERR(opp), "failed to find min peak bandwidth\n");
++ dev_pm_opp_put(opp);
+
+ bwmon->dev = dev;
+
+diff --git a/drivers/soc/qcom/pdr_interface.c b/drivers/soc/qcom/pdr_interface.c
+index a1b6a4081dea7..216166e98fae4 100644
+--- a/drivers/soc/qcom/pdr_interface.c
++++ b/drivers/soc/qcom/pdr_interface.c
+@@ -76,12 +76,12 @@ static int pdr_locator_new_server(struct qmi_handle *qmi,
+ locator_hdl);
+ struct pdr_service *pds;
+
++ mutex_lock(&pdr->lock);
+ /* Create a local client port for QMI communication */
+ pdr->locator_addr.sq_family = AF_QIPCRTR;
+ pdr->locator_addr.sq_node = svc->node;
+ pdr->locator_addr.sq_port = svc->port;
+
+- mutex_lock(&pdr->lock);
+ pdr->locator_init_complete = true;
+ mutex_unlock(&pdr->lock);
+
+@@ -104,10 +104,10 @@ static void pdr_locator_del_server(struct qmi_handle *qmi,
+
+ mutex_lock(&pdr->lock);
+ pdr->locator_init_complete = false;
+- mutex_unlock(&pdr->lock);
+
+ pdr->locator_addr.sq_node = 0;
+ pdr->locator_addr.sq_port = 0;
++ mutex_unlock(&pdr->lock);
+ }
+
+ static const struct qmi_ops pdr_locator_ops = {
+@@ -365,12 +365,14 @@ static int pdr_get_domain_list(struct servreg_get_domain_list_req *req,
+ if (ret < 0)
+ return ret;
+
++ mutex_lock(&pdr->lock);
+ ret = qmi_send_request(&pdr->locator_hdl,
+ &pdr->locator_addr,
+ &txn, SERVREG_GET_DOMAIN_LIST_REQ,
+ SERVREG_GET_DOMAIN_LIST_REQ_MAX_LEN,
+ servreg_get_domain_list_req_ei,
+ req);
++ mutex_unlock(&pdr->lock);
+ if (ret < 0) {
+ qmi_txn_cancel(&txn);
+ return ret;
+@@ -415,7 +417,7 @@ static int pdr_locate_service(struct pdr_handle *pdr, struct pdr_service *pds)
+ if (ret < 0)
+ goto out;
+
+- for (i = domains_read; i < resp->domain_list_len; i++) {
++ for (i = 0; i < resp->domain_list_len; i++) {
+ entry = &resp->domain_list[i];
+
+ if (strnlen(entry->name, sizeof(entry->name)) == sizeof(entry->name))
+diff --git a/drivers/soc/qcom/pmic_glink.c b/drivers/soc/qcom/pmic_glink.c
+index 65279243072c3..9ebc0ba359477 100644
+--- a/drivers/soc/qcom/pmic_glink.c
++++ b/drivers/soc/qcom/pmic_glink.c
+@@ -373,8 +373,17 @@ static struct platform_driver pmic_glink_driver = {
+
+ static int pmic_glink_init(void)
+ {
+- platform_driver_register(&pmic_glink_driver);
+- register_rpmsg_driver(&pmic_glink_rpmsg_driver);
++ int ret;
++
++ ret = platform_driver_register(&pmic_glink_driver);
++ if (ret < 0)
++ return ret;
++
++ ret = register_rpmsg_driver(&pmic_glink_rpmsg_driver);
++ if (ret < 0) {
++ platform_driver_unregister(&pmic_glink_driver);
++ return ret;
++ }
+
+ return 0;
+ }
+diff --git a/drivers/soc/qcom/rpmh-rsc.c b/drivers/soc/qcom/rpmh-rsc.c
+index 561d8037b50a0..de86009ecd913 100644
+--- a/drivers/soc/qcom/rpmh-rsc.c
++++ b/drivers/soc/qcom/rpmh-rsc.c
+@@ -646,13 +646,14 @@ int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
+ {
+ struct tcs_group *tcs;
+ int tcs_id;
+- unsigned long flags;
++
++ might_sleep();
+
+ tcs = get_tcs_for_msg(drv, msg);
+ if (IS_ERR(tcs))
+ return PTR_ERR(tcs);
+
+- spin_lock_irqsave(&drv->lock, flags);
++ spin_lock_irq(&drv->lock);
+
+ /* Wait forever for a free tcs. It better be there eventually! */
+ wait_event_lock_irq(drv->tcs_wait,
+@@ -670,7 +671,7 @@ int rpmh_rsc_send_data(struct rsc_drv *drv, const struct tcs_request *msg)
+ write_tcs_reg_sync(drv, drv->regs[RSC_DRV_CMD_ENABLE], tcs_id, 0);
+ enable_tcs_irq(drv, tcs_id, true);
+ }
+- spin_unlock_irqrestore(&drv->lock, flags);
++ spin_unlock_irq(&drv->lock);
+
+ /*
+ * These two can be done after the lock is released because:
+diff --git a/drivers/soc/qcom/rpmh.c b/drivers/soc/qcom/rpmh.c
+index 9f26d7f9b9dc4..8903ed956312d 100644
+--- a/drivers/soc/qcom/rpmh.c
++++ b/drivers/soc/qcom/rpmh.c
+@@ -183,7 +183,6 @@ static int __rpmh_write(const struct device *dev, enum rpmh_state state,
+ }
+
+ if (state == RPMH_ACTIVE_ONLY_STATE) {
+- WARN_ON(irqs_disabled());
+ ret = rpmh_rsc_send_data(ctrlr_to_drv(ctrlr), &rpm_msg->msg);
+ } else {
+ /* Clean up our call by spoofing tx_done */
+diff --git a/drivers/soc/qcom/socinfo.c b/drivers/soc/qcom/socinfo.c
+index 277c07a6603d4..41342c37916ae 100644
+--- a/drivers/soc/qcom/socinfo.c
++++ b/drivers/soc/qcom/socinfo.c
+@@ -133,7 +133,8 @@ static const char *const pmic_models[] = {
+ [72] = "PMR735D",
+ [73] = "PM8550",
+ [74] = "PMK8550",
+- [82] = "SMB2360",
++ [82] = "PMC8380",
++ [83] = "SMB2360",
+ };
+
+ struct socinfo_params {
+diff --git a/drivers/soc/xilinx/xlnx_event_manager.c b/drivers/soc/xilinx/xlnx_event_manager.c
+index 253299e4214d0..366018f6a0ee0 100644
+--- a/drivers/soc/xilinx/xlnx_event_manager.c
++++ b/drivers/soc/xilinx/xlnx_event_manager.c
+@@ -3,6 +3,7 @@
+ * Xilinx Event Management Driver
+ *
+ * Copyright (C) 2021 Xilinx, Inc.
++ * Copyright (C) 2024 Advanced Micro Devices, Inc.
+ *
+ * Abhyuday Godhasara <abhyuday.godhasara@xilinx.com>
+ */
+@@ -19,7 +20,7 @@
+ #include <linux/platform_device.h>
+ #include <linux/slab.h>
+
+-static DEFINE_PER_CPU_READ_MOSTLY(int, cpu_number1);
++static DEFINE_PER_CPU_READ_MOSTLY(int, dummy_cpu_number);
+
+ static int virq_sgi;
+ static int event_manager_availability = -EACCES;
+@@ -570,7 +571,6 @@ static void xlnx_disable_percpu_irq(void *data)
+ static int xlnx_event_init_sgi(struct platform_device *pdev)
+ {
+ int ret = 0;
+- int cpu;
+ /*
+ * IRQ related structures are used for the following:
+ * for each SGI interrupt ensure its mapped by GIC IRQ domain
+@@ -607,11 +607,8 @@ static int xlnx_event_init_sgi(struct platform_device *pdev)
+ sgi_fwspec.param[0] = sgi_num;
+ virq_sgi = irq_create_fwspec_mapping(&sgi_fwspec);
+
+- cpu = get_cpu();
+- per_cpu(cpu_number1, cpu) = cpu;
+ ret = request_percpu_irq(virq_sgi, xlnx_event_handler, "xlnx_event_mgmt",
+- &cpu_number1);
+- put_cpu();
++ &dummy_cpu_number);
+
+ WARN_ON(ret);
+ if (ret) {
+@@ -627,16 +624,12 @@ static int xlnx_event_init_sgi(struct platform_device *pdev)
+
+ static void xlnx_event_cleanup_sgi(struct platform_device *pdev)
+ {
+- int cpu = smp_processor_id();
+-
+- per_cpu(cpu_number1, cpu) = cpu;
+-
+ cpuhp_remove_state(CPUHP_AP_ONLINE_DYN);
+
+ on_each_cpu(xlnx_disable_percpu_irq, NULL, 1);
+
+ irq_clear_status_flags(virq_sgi, IRQ_PER_CPU);
+- free_percpu_irq(virq_sgi, &cpu_number1);
++ free_percpu_irq(virq_sgi, &dummy_cpu_number);
+ irq_dispose_mapping(virq_sgi);
+ }
+
+diff --git a/drivers/soc/xilinx/zynqmp_power.c b/drivers/soc/xilinx/zynqmp_power.c
+index 965b1143936ab..b82c01373f532 100644
+--- a/drivers/soc/xilinx/zynqmp_power.c
++++ b/drivers/soc/xilinx/zynqmp_power.c
+@@ -190,7 +190,9 @@ static int zynqmp_pm_probe(struct platform_device *pdev)
+ u32 pm_api_version;
+ struct mbox_client *client;
+
+- zynqmp_pm_get_api_version(&pm_api_version);
++ ret = zynqmp_pm_get_api_version(&pm_api_version);
++ if (ret)
++ return ret;
+
+ /* Check PM API version number */
+ if (pm_api_version < ZYNQMP_PM_VERSION)
+diff --git a/drivers/spi/atmel-quadspi.c b/drivers/spi/atmel-quadspi.c
+index 370c4d1572ed0..5aaff3bee1b78 100644
+--- a/drivers/spi/atmel-quadspi.c
++++ b/drivers/spi/atmel-quadspi.c
+@@ -756,8 +756,15 @@ static int __maybe_unused atmel_qspi_resume(struct device *dev)
+ struct atmel_qspi *aq = spi_controller_get_devdata(ctrl);
+ int ret;
+
+- clk_prepare(aq->pclk);
+- clk_prepare(aq->qspick);
++ ret = clk_prepare(aq->pclk);
++ if (ret)
++ return ret;
++
++ ret = clk_prepare(aq->qspick);
++ if (ret) {
++ clk_unprepare(aq->pclk);
++ return ret;
++ }
+
+ ret = pm_runtime_force_resume(dev);
+ if (ret < 0)
+diff --git a/drivers/spi/spi-microchip-core.c b/drivers/spi/spi-microchip-core.c
+index 634364c7cfe61..99c25e6a937fd 100644
+--- a/drivers/spi/spi-microchip-core.c
++++ b/drivers/spi/spi-microchip-core.c
+@@ -21,7 +21,7 @@
+ #include <linux/spi/spi.h>
+
+ #define MAX_LEN (0xffff)
+-#define MAX_CS (8)
++#define MAX_CS (1)
+ #define DEFAULT_FRAMESIZE (8)
+ #define FIFO_DEPTH (32)
+ #define CLK_GEN_MODE1_MAX (255)
+@@ -75,6 +75,7 @@
+
+ #define REG_CONTROL (0x00)
+ #define REG_FRAME_SIZE (0x04)
++#define FRAME_SIZE_MASK GENMASK(5, 0)
+ #define REG_STATUS (0x08)
+ #define REG_INT_CLEAR (0x0c)
+ #define REG_RX_DATA (0x10)
+@@ -89,6 +90,9 @@
+ #define REG_RIS (0x24)
+ #define REG_CONTROL2 (0x28)
+ #define REG_COMMAND (0x2c)
++#define COMMAND_CLRFRAMECNT BIT(4)
++#define COMMAND_TXFIFORST BIT(3)
++#define COMMAND_RXFIFORST BIT(2)
+ #define REG_PKTSIZE (0x30)
+ #define REG_CMD_SIZE (0x34)
+ #define REG_HWSTATUS (0x38)
+@@ -103,6 +107,7 @@ struct mchp_corespi {
+ u8 *rx_buf;
+ u32 clk_gen; /* divider for spi output clock generated by the controller */
+ u32 clk_mode;
++ u32 pending_slave_select;
+ int irq;
+ int tx_len;
+ int rx_len;
+@@ -148,62 +153,59 @@ static inline void mchp_corespi_read_fifo(struct mchp_corespi *spi)
+
+ static void mchp_corespi_enable_ints(struct mchp_corespi *spi)
+ {
+- u32 control, mask = INT_ENABLE_MASK;
+-
+- mchp_corespi_disable(spi);
+-
+- control = mchp_corespi_read(spi, REG_CONTROL);
+-
+- control |= mask;
+- mchp_corespi_write(spi, REG_CONTROL, control);
++ u32 control = mchp_corespi_read(spi, REG_CONTROL);
+
+- control |= CONTROL_ENABLE;
++ control |= INT_ENABLE_MASK;
+ mchp_corespi_write(spi, REG_CONTROL, control);
+ }
+
+ static void mchp_corespi_disable_ints(struct mchp_corespi *spi)
+ {
+- u32 control, mask = INT_ENABLE_MASK;
+-
+- mchp_corespi_disable(spi);
+-
+- control = mchp_corespi_read(spi, REG_CONTROL);
+- control &= ~mask;
+- mchp_corespi_write(spi, REG_CONTROL, control);
++ u32 control = mchp_corespi_read(spi, REG_CONTROL);
+
+- control |= CONTROL_ENABLE;
++ control &= ~INT_ENABLE_MASK;
+ mchp_corespi_write(spi, REG_CONTROL, control);
+ }
+
+ static inline void mchp_corespi_set_xfer_size(struct mchp_corespi *spi, int len)
+ {
+ u32 control;
+- u16 lenpart;
++ u32 lenpart;
++ u32 frames = mchp_corespi_read(spi, REG_FRAMESUP);
+
+ /*
+- * Disable the SPI controller. Writes to transfer length have
+- * no effect when the controller is enabled.
++ * Writing to FRAMECNT in REG_CONTROL will reset the frame count, taking
++ * a shortcut requires an explicit clear.
+ */
+- mchp_corespi_disable(spi);
++ if (frames == len) {
++ mchp_corespi_write(spi, REG_COMMAND, COMMAND_CLRFRAMECNT);
++ return;
++ }
+
+ /*
+ * The lower 16 bits of the frame count are stored in the control reg
+ * for legacy reasons, but the upper 16 written to a different register:
+ * FRAMESUP. While both the upper and lower bits can be *READ* from the
+- * FRAMESUP register, writing to the lower 16 bits is a NOP
++ * FRAMESUP register, writing to the lower 16 bits is (supposedly) a NOP.
++ *
++ * The driver used to disable the controller while modifying the frame
++ * count, and mask off the lower 16 bits of len while writing to
++ * FRAMES_UP. When the driver was changed to disable the controller as
++ * infrequently as possible, it was discovered that the logic of
++ * lenpart = len & 0xffff_0000
++ * write(REG_FRAMESUP, lenpart)
++ * would actually write zeros into the lower 16 bits on an mpfs250t-es,
++ * despite documentation stating these bits were read-only.
++ * Writing len unmasked into FRAMES_UP ensures those bits aren't zeroed
++ * on an mpfs250t-es and will be a NOP for the lower 16 bits on hardware
++ * that matches the documentation.
+ */
+ lenpart = len & 0xffff;
+-
+ control = mchp_corespi_read(spi, REG_CONTROL);
+ control &= ~CONTROL_FRAMECNT_MASK;
+ control |= lenpart << CONTROL_FRAMECNT_SHIFT;
+ mchp_corespi_write(spi, REG_CONTROL, control);
+-
+- lenpart = len & 0xffff0000;
+- mchp_corespi_write(spi, REG_FRAMESUP, lenpart);
+-
+- control |= CONTROL_ENABLE;
+- mchp_corespi_write(spi, REG_CONTROL, control);
++ mchp_corespi_write(spi, REG_FRAMESUP, len);
+ }
+
+ static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi)
+@@ -226,17 +228,22 @@ static inline void mchp_corespi_write_fifo(struct mchp_corespi *spi)
+
+ static inline void mchp_corespi_set_framesize(struct mchp_corespi *spi, int bt)
+ {
++ u32 frame_size = mchp_corespi_read(spi, REG_FRAME_SIZE);
+ u32 control;
+
++ if ((frame_size & FRAME_SIZE_MASK) == bt)
++ return;
++
+ /*
+ * Disable the SPI controller. Writes to the frame size have
+ * no effect when the controller is enabled.
+ */
+- mchp_corespi_disable(spi);
++ control = mchp_corespi_read(spi, REG_CONTROL);
++ control &= ~CONTROL_ENABLE;
++ mchp_corespi_write(spi, REG_CONTROL, control);
+
+ mchp_corespi_write(spi, REG_FRAME_SIZE, bt);
+
+- control = mchp_corespi_read(spi, REG_CONTROL);
+ control |= CONTROL_ENABLE;
+ mchp_corespi_write(spi, REG_CONTROL, control);
+ }
+@@ -249,8 +256,18 @@ static void mchp_corespi_set_cs(struct spi_device *spi, bool disable)
+ reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT);
+ reg &= ~BIT(spi_get_chipselect(spi, 0));
+ reg |= !disable << spi_get_chipselect(spi, 0);
++ corespi->pending_slave_select = reg;
+
+- mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
++ /*
++ * Only deassert chip select immediately. Writing to some registers
++ * requires the controller to be disabled, which results in the
++ * output pins being tristated and can cause the SCLK and MOSI lines
++ * to transition. Therefore asserting the chip select is deferred
++ * until just before writing to the TX FIFO, to ensure the device
++ * doesn't see any spurious clock transitions whilst CS is enabled.
++ */
++ if (((spi->mode & SPI_CS_HIGH) == 0) == disable)
++ mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
+ }
+
+ static int mchp_corespi_setup(struct spi_device *spi)
+@@ -266,6 +283,7 @@ static int mchp_corespi_setup(struct spi_device *spi)
+ if (spi->mode & SPI_CS_HIGH) {
+ reg = mchp_corespi_read(corespi, REG_SLAVE_SELECT);
+ reg |= BIT(spi_get_chipselect(spi, 0));
++ corespi->pending_slave_select = reg;
+ mchp_corespi_write(corespi, REG_SLAVE_SELECT, reg);
+ }
+ return 0;
+@@ -276,17 +294,13 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
+ unsigned long clk_hz;
+ u32 control = mchp_corespi_read(spi, REG_CONTROL);
+
+- control |= CONTROL_MASTER;
++ control &= ~CONTROL_ENABLE;
++ mchp_corespi_write(spi, REG_CONTROL, control);
+
++ control |= CONTROL_MASTER;
+ control &= ~CONTROL_MODE_MASK;
+ control |= MOTOROLA_MODE;
+
+- mchp_corespi_set_framesize(spi, DEFAULT_FRAMESIZE);
+-
+- /* max. possible spi clock rate is the apb clock rate */
+- clk_hz = clk_get_rate(spi->clk);
+- host->max_speed_hz = clk_hz;
+-
+ /*
+ * The controller must be configured so that it doesn't remove Chip
+ * Select until the entire message has been transferred, even if at
+@@ -295,11 +309,16 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
+ * BIGFIFO mode is also enabled, which sets the fifo depth to 32 frames
+ * for the 8 bit transfers that this driver uses.
+ */
+- control = mchp_corespi_read(spi, REG_CONTROL);
+ control |= CONTROL_SPS | CONTROL_BIGFIFO;
+
+ mchp_corespi_write(spi, REG_CONTROL, control);
+
++ mchp_corespi_set_framesize(spi, DEFAULT_FRAMESIZE);
++
++ /* max. possible spi clock rate is the apb clock rate */
++ clk_hz = clk_get_rate(spi->clk);
++ host->max_speed_hz = clk_hz;
++
+ mchp_corespi_enable_ints(spi);
+
+ /*
+@@ -307,7 +326,8 @@ static void mchp_corespi_init(struct spi_controller *host, struct mchp_corespi *
+ * select is relinquished to the hardware. SSELOUT is enabled too so we
+ * can deal with active high targets.
+ */
+- mchp_corespi_write(spi, REG_SLAVE_SELECT, SSELOUT | SSEL_DIRECT);
++ spi->pending_slave_select = SSELOUT | SSEL_DIRECT;
++ mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
+
+ control = mchp_corespi_read(spi, REG_CONTROL);
+
+@@ -321,8 +341,6 @@ static inline void mchp_corespi_set_clk_gen(struct mchp_corespi *spi)
+ {
+ u32 control;
+
+- mchp_corespi_disable(spi);
+-
+ control = mchp_corespi_read(spi, REG_CONTROL);
+ if (spi->clk_mode)
+ control |= CONTROL_CLKMODE;
+@@ -331,12 +349,12 @@ static inline void mchp_corespi_set_clk_gen(struct mchp_corespi *spi)
+
+ mchp_corespi_write(spi, REG_CLK_GEN, spi->clk_gen);
+ mchp_corespi_write(spi, REG_CONTROL, control);
+- mchp_corespi_write(spi, REG_CONTROL, control | CONTROL_ENABLE);
+ }
+
+ static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int mode)
+ {
+- u32 control, mode_val;
++ u32 mode_val;
++ u32 control = mchp_corespi_read(spi, REG_CONTROL);
+
+ switch (mode & SPI_MODE_X_MASK) {
+ case SPI_MODE_0:
+@@ -354,12 +372,13 @@ static inline void mchp_corespi_set_mode(struct mchp_corespi *spi, unsigned int
+ }
+
+ /*
+- * Disable the SPI controller. Writes to the frame size have
++ * Disable the SPI controller. Writes to the frame protocol have
+ * no effect when the controller is enabled.
+ */
+- mchp_corespi_disable(spi);
+
+- control = mchp_corespi_read(spi, REG_CONTROL);
++ control &= ~CONTROL_ENABLE;
++ mchp_corespi_write(spi, REG_CONTROL, control);
++
+ control &= ~(SPI_MODE_X_MASK << MODE_X_MASK_SHIFT);
+ control |= mode_val;
+
+@@ -380,21 +399,18 @@ static irqreturn_t mchp_corespi_interrupt(int irq, void *dev_id)
+ if (intfield == 0)
+ return IRQ_NONE;
+
+- if (intfield & INT_TXDONE) {
++ if (intfield & INT_TXDONE)
+ mchp_corespi_write(spi, REG_INT_CLEAR, INT_TXDONE);
+
++ if (intfield & INT_RXRDY) {
++ mchp_corespi_write(spi, REG_INT_CLEAR, INT_RXRDY);
++
+ if (spi->rx_len)
+ mchp_corespi_read_fifo(spi);
+-
+- if (spi->tx_len)
+- mchp_corespi_write_fifo(spi);
+-
+- if (!spi->rx_len)
+- finalise = true;
+ }
+
+- if (intfield & INT_RXRDY)
+- mchp_corespi_write(spi, REG_INT_CLEAR, INT_RXRDY);
++ if (!spi->rx_len && !spi->tx_len)
++ finalise = true;
+
+ if (intfield & INT_RX_CHANNEL_OVERFLOW) {
+ mchp_corespi_write(spi, REG_INT_CLEAR, INT_RX_CHANNEL_OVERFLOW);
+@@ -479,8 +495,13 @@ static int mchp_corespi_transfer_one(struct spi_controller *host,
+ mchp_corespi_set_xfer_size(spi, (spi->tx_len > FIFO_DEPTH)
+ ? FIFO_DEPTH : spi->tx_len);
+
+- if (spi->tx_len)
++ mchp_corespi_write(spi, REG_COMMAND, COMMAND_RXFIFORST | COMMAND_TXFIFORST);
++
++ mchp_corespi_write(spi, REG_SLAVE_SELECT, spi->pending_slave_select);
++
++ while (spi->tx_len)
+ mchp_corespi_write_fifo(spi);
++
+ return 1;
+ }
+
+diff --git a/drivers/spi/spidev.c b/drivers/spi/spidev.c
+index 95fb5f1c91c17..05e6d007f9a7f 100644
+--- a/drivers/spi/spidev.c
++++ b/drivers/spi/spidev.c
+@@ -734,6 +734,7 @@ static const struct of_device_id spidev_dt_ids[] = {
+ { .compatible = "lwn,bk4", .data = &spidev_of_check },
+ { .compatible = "menlo,m53cpld", .data = &spidev_of_check },
+ { .compatible = "micron,spi-authenta", .data = &spidev_of_check },
++ { .compatible = "rohm,bh2228fv", .data = &spidev_of_check },
+ { .compatible = "rohm,dh2228fv", .data = &spidev_of_check },
+ { .compatible = "semtech,sx1301", .data = &spidev_of_check },
+ { .compatible = "silabs,em3581", .data = &spidev_of_check },
+diff --git a/drivers/thermal/broadcom/bcm2835_thermal.c b/drivers/thermal/broadcom/bcm2835_thermal.c
+index 5c1cebe075801..3b1030fc4fbfe 100644
+--- a/drivers/thermal/broadcom/bcm2835_thermal.c
++++ b/drivers/thermal/broadcom/bcm2835_thermal.c
+@@ -185,7 +185,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
+ return err;
+ }
+
+- data->clk = devm_clk_get(&pdev->dev, NULL);
++ data->clk = devm_clk_get_enabled(&pdev->dev, NULL);
+ if (IS_ERR(data->clk)) {
+ err = PTR_ERR(data->clk);
+ if (err != -EPROBE_DEFER)
+@@ -193,10 +193,6 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
+ return err;
+ }
+
+- err = clk_prepare_enable(data->clk);
+- if (err)
+- return err;
+-
+ rate = clk_get_rate(data->clk);
+ if ((rate < 1920000) || (rate > 5000000))
+ dev_warn(&pdev->dev,
+@@ -211,7 +207,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
+ dev_err(&pdev->dev,
+ "Failed to register the thermal device: %d\n",
+ err);
+- goto err_clk;
++ return err;
+ }
+
+ /*
+@@ -236,7 +232,7 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
+ dev_err(&pdev->dev,
+ "Not able to read trip_temp: %d\n",
+ err);
+- goto err_tz;
++ return err;
+ }
+
+ /* set bandgap reference voltage and enable voltage regulator */
+@@ -269,17 +265,11 @@ static int bcm2835_thermal_probe(struct platform_device *pdev)
+ */
+ err = thermal_add_hwmon_sysfs(tz);
+ if (err)
+- goto err_tz;
++ return err;
+
+ bcm2835_thermal_debugfs(pdev);
+
+ return 0;
+-err_tz:
+- devm_thermal_of_zone_unregister(&pdev->dev, tz);
+-err_clk:
+- clk_disable_unprepare(data->clk);
+-
+- return err;
+ }
+
+ static void bcm2835_thermal_remove(struct platform_device *pdev)
+@@ -287,7 +277,6 @@ static void bcm2835_thermal_remove(struct platform_device *pdev)
+ struct bcm2835_thermal_data *data = platform_get_drvdata(pdev);
+
+ debugfs_remove_recursive(data->debugfsdir);
+- clk_disable_unprepare(data->clk);
+ }
+
+ static struct platform_driver bcm2835_thermal_driver = {
+diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
+index 4e7fec406ee59..f2d31bc48f529 100644
+--- a/drivers/thermal/thermal_core.c
++++ b/drivers/thermal/thermal_core.c
+@@ -272,6 +272,44 @@ static int __init thermal_register_governors(void)
+ return ret;
+ }
+
++static int __thermal_zone_device_set_mode(struct thermal_zone_device *tz,
++ enum thermal_device_mode mode)
++{
++ if (tz->ops.change_mode) {
++ int ret;
++
++ ret = tz->ops.change_mode(tz, mode);
++ if (ret)
++ return ret;
++ }
++
++ tz->mode = mode;
++
++ return 0;
++}
++
++static void thermal_zone_broken_disable(struct thermal_zone_device *tz)
++{
++ struct thermal_trip_desc *td;
++
++ dev_err(&tz->device, "Unable to get temperature, disabling!\n");
++ /*
++ * This function only runs for enabled thermal zones, so no need to
++ * check for the current mode.
++ */
++ __thermal_zone_device_set_mode(tz, THERMAL_DEVICE_DISABLED);
++ thermal_notify_tz_disable(tz);
++
++ for_each_trip_desc(tz, td) {
++ if (td->trip.type == THERMAL_TRIP_CRITICAL &&
++ td->trip.temperature > THERMAL_TEMP_INVALID) {
++ dev_crit(&tz->device,
++ "Disabled thermal zone with critical trip point\n");
++ return;
++ }
++ }
++}
++
+ /*
+ * Zone update section: main control loop applied to each zone while monitoring
+ * in polling mode. The monitoring is done using a workqueue.
+@@ -292,6 +330,34 @@ static void thermal_zone_device_set_polling(struct thermal_zone_device *tz,
+ cancel_delayed_work(&tz->poll_queue);
+ }
+
++static void thermal_zone_recheck(struct thermal_zone_device *tz, int error)
++{
++ if (error == -EAGAIN) {
++ thermal_zone_device_set_polling(tz, THERMAL_RECHECK_DELAY);
++ return;
++ }
++
++ /*
++ * Print the message once to reduce log noise. It will be followed by
++ * another one if the temperature cannot be determined after multiple
++ * attempts.
++ */
++ if (tz->recheck_delay_jiffies == THERMAL_RECHECK_DELAY)
++ dev_info(&tz->device, "Temperature check failed (%d)\n", error);
++
++ thermal_zone_device_set_polling(tz, tz->recheck_delay_jiffies);
++
++ tz->recheck_delay_jiffies += max(tz->recheck_delay_jiffies >> 1, 1ULL);
++ if (tz->recheck_delay_jiffies > THERMAL_MAX_RECHECK_DELAY) {
++ thermal_zone_broken_disable(tz);
++ /*
++ * Restore the original recheck delay value to allow the thermal
++ * zone to try to recover when it is reenabled by user space.
++ */
++ tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
++ }
++}
++
+ static void monitor_thermal_zone(struct thermal_zone_device *tz)
+ {
+ if (tz->mode != THERMAL_DEVICE_ENABLED)
+@@ -488,10 +554,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
+
+ ret = __thermal_zone_get_temp(tz, &temp);
+ if (ret) {
+- if (ret != -EAGAIN)
+- dev_info(&tz->device, "Temperature check failed (%d)\n", ret);
+-
+- thermal_zone_device_set_polling(tz, msecs_to_jiffies(THERMAL_RECHECK_DELAY_MS));
++ thermal_zone_recheck(tz, ret);
+ return;
+ } else if (temp <= THERMAL_TEMP_INVALID) {
+ /*
+@@ -503,6 +566,8 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
+ goto monitor;
+ }
+
++ tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
++
+ tz->last_temperature = tz->temperature;
+ tz->temperature = temp;
+
+@@ -537,7 +602,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
+ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
+ enum thermal_device_mode mode)
+ {
+- int ret = 0;
++ int ret;
+
+ mutex_lock(&tz->lock);
+
+@@ -545,14 +610,15 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
+ if (mode == tz->mode) {
+ mutex_unlock(&tz->lock);
+
+- return ret;
++ return 0;
+ }
+
+- if (tz->ops.change_mode)
+- ret = tz->ops.change_mode(tz, mode);
++ ret = __thermal_zone_device_set_mode(tz, mode);
++ if (ret) {
++ mutex_unlock(&tz->lock);
+
+- if (!ret)
+- tz->mode = mode;
++ return ret;
++ }
+
+ __thermal_zone_device_update(tz, THERMAL_EVENT_UNSPECIFIED);
+
+@@ -563,7 +629,7 @@ static int thermal_zone_device_set_mode(struct thermal_zone_device *tz,
+ else
+ thermal_notify_tz_disable(tz);
+
+- return ret;
++ return 0;
+ }
+
+ int thermal_zone_device_enable(struct thermal_zone_device *tz)
+@@ -1433,6 +1499,7 @@ thermal_zone_device_register_with_trips(const char *type,
+
+ thermal_set_delay_jiffies(&tz->passive_delay_jiffies, passive_delay);
+ thermal_set_delay_jiffies(&tz->polling_delay_jiffies, polling_delay);
++ tz->recheck_delay_jiffies = THERMAL_RECHECK_DELAY;
+
+ /* sys I/F */
+ /* Add nodes that are always present via .groups */
+diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
+index 5afd541d54b0b..56113c9db5755 100644
+--- a/drivers/thermal/thermal_core.h
++++ b/drivers/thermal/thermal_core.h
+@@ -67,6 +67,8 @@ struct thermal_governor {
+ * @polling_delay_jiffies: number of jiffies to wait between polls when
+ * checking whether trip points have been crossed (0 for
+ * interrupt driven systems)
++ * @recheck_delay_jiffies: delay after a failed attempt to determine the zone
++ * temperature before trying again
+ * @temperature: current temperature. This is only for core code,
+ * drivers should use thermal_zone_get_temp() to get the
+ * current temperature
+@@ -108,6 +110,7 @@ struct thermal_zone_device {
+ int num_trips;
+ unsigned long passive_delay_jiffies;
+ unsigned long polling_delay_jiffies;
++ unsigned long recheck_delay_jiffies;
+ int temperature;
+ int last_temperature;
+ int emul_temperature;
+@@ -137,10 +140,11 @@ struct thermal_zone_device {
+ #define THERMAL_TEMP_INIT INT_MIN
+
+ /*
+- * Default delay after a failing thermal zone temperature check before
+- * attempting to check it again.
++ * Default and maximum delay after a failed thermal zone temperature check
++ * before attempting to check it again (in jiffies).
+ */
+-#define THERMAL_RECHECK_DELAY_MS 250
++#define THERMAL_RECHECK_DELAY msecs_to_jiffies(250)
++#define THERMAL_MAX_RECHECK_DELAY (120 * HZ)
+
+ /* Default Thermal Governor */
+ #if defined(CONFIG_THERMAL_DEFAULT_GOV_STEP_WISE)
+diff --git a/drivers/ufs/core/ufs-mcq.c b/drivers/ufs/core/ufs-mcq.c
+index c532416aec229..408fef9c6fd66 100644
+--- a/drivers/ufs/core/ufs-mcq.c
++++ b/drivers/ufs/core/ufs-mcq.c
+@@ -230,8 +230,6 @@ int ufshcd_mcq_memory_alloc(struct ufs_hba *hba)
+
+ /* Operation and runtime registers configuration */
+ #define MCQ_CFG_n(r, i) ((r) + MCQ_QCFG_SIZE * (i))
+-#define MCQ_OPR_OFFSET_n(p, i) \
+- (hba->mcq_opr[(p)].offset + hba->mcq_opr[(p)].stride * (i))
+
+ static void __iomem *mcq_opr_base(struct ufs_hba *hba,
+ enum ufshcd_mcq_opr n, int i)
+@@ -342,10 +340,10 @@ void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba)
+ ufsmcq_writelx(hba, upper_32_bits(hwq->sqe_dma_addr),
+ MCQ_CFG_n(REG_SQUBA, i));
+ /* Submission Queue Doorbell Address Offset */
+- ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_SQD, i),
++ ufsmcq_writelx(hba, ufshcd_mcq_opr_offset(hba, OPR_SQD, i),
+ MCQ_CFG_n(REG_SQDAO, i));
+ /* Submission Queue Interrupt Status Address Offset */
+- ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_SQIS, i),
++ ufsmcq_writelx(hba, ufshcd_mcq_opr_offset(hba, OPR_SQIS, i),
+ MCQ_CFG_n(REG_SQISAO, i));
+
+ /* Completion Queue Lower Base Address */
+@@ -355,10 +353,10 @@ void ufshcd_mcq_make_queues_operational(struct ufs_hba *hba)
+ ufsmcq_writelx(hba, upper_32_bits(hwq->cqe_dma_addr),
+ MCQ_CFG_n(REG_CQUBA, i));
+ /* Completion Queue Doorbell Address Offset */
+- ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_CQD, i),
++ ufsmcq_writelx(hba, ufshcd_mcq_opr_offset(hba, OPR_CQD, i),
+ MCQ_CFG_n(REG_CQDAO, i));
+ /* Completion Queue Interrupt Status Address Offset */
+- ufsmcq_writelx(hba, MCQ_OPR_OFFSET_n(OPR_CQIS, i),
++ ufsmcq_writelx(hba, ufshcd_mcq_opr_offset(hba, OPR_CQIS, i),
+ MCQ_CFG_n(REG_CQISAO, i));
+
+ /* Save the base addresses for quicker access */
+diff --git a/drivers/usb/host/xhci-pci.c b/drivers/usb/host/xhci-pci.c
+index 05881153883ec..dc1e345ab67ea 100644
+--- a/drivers/usb/host/xhci-pci.c
++++ b/drivers/usb/host/xhci-pci.c
+@@ -50,6 +50,7 @@
+ #define PCI_DEVICE_ID_INTEL_DENVERTON_XHCI 0x19d0
+ #define PCI_DEVICE_ID_INTEL_ICE_LAKE_XHCI 0x8a13
+ #define PCI_DEVICE_ID_INTEL_TIGER_LAKE_XHCI 0x9a13
++#define PCI_DEVICE_ID_INTEL_TIGER_LAKE_PCH_XHCI 0xa0ed
+ #define PCI_DEVICE_ID_INTEL_COMET_LAKE_XHCI 0xa3af
+ #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI 0x51ed
+ #define PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_PCH_XHCI 0x54ed
+@@ -373,7 +374,8 @@ static void xhci_pci_quirks(struct device *dev, struct xhci_hcd *xhci)
+ xhci->quirks |= XHCI_MISSING_CAS;
+
+ if (pdev->vendor == PCI_VENDOR_ID_INTEL &&
+- (pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI ||
++ (pdev->device == PCI_DEVICE_ID_INTEL_TIGER_LAKE_PCH_XHCI ||
++ pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_PCH_XHCI ||
+ pdev->device == PCI_DEVICE_ID_INTEL_ALDER_LAKE_N_PCH_XHCI))
+ xhci->quirks |= XHCI_RESET_TO_DEFAULT;
+
+diff --git a/drivers/usb/typec/mux/nb7vpq904m.c b/drivers/usb/typec/mux/nb7vpq904m.c
+index b17826713753a..9fe4ce6f62ac0 100644
+--- a/drivers/usb/typec/mux/nb7vpq904m.c
++++ b/drivers/usb/typec/mux/nb7vpq904m.c
+@@ -413,7 +413,7 @@ static int nb7vpq904m_probe(struct i2c_client *client)
+
+ ret = nb7vpq904m_parse_data_lanes_mapping(nb7);
+ if (ret)
+- return ret;
++ goto err_switch_put;
+
+ ret = regulator_enable(nb7->vcc_supply);
+ if (ret)
+@@ -456,6 +456,9 @@ static int nb7vpq904m_probe(struct i2c_client *client)
+ gpiod_set_value(nb7->enable_gpio, 0);
+ regulator_disable(nb7->vcc_supply);
+
++err_switch_put:
++ typec_switch_put(nb7->typec_switch);
++
+ return ret;
+ }
+
+@@ -469,6 +472,8 @@ static void nb7vpq904m_remove(struct i2c_client *client)
+ gpiod_set_value(nb7->enable_gpio, 0);
+
+ regulator_disable(nb7->vcc_supply);
++
++ typec_switch_put(nb7->typec_switch);
+ }
+
+ static const struct i2c_device_id nb7vpq904m_table[] = {
+diff --git a/drivers/usb/typec/mux/ptn36502.c b/drivers/usb/typec/mux/ptn36502.c
+index 0ec86ef32a871..88136a6d6f313 100644
+--- a/drivers/usb/typec/mux/ptn36502.c
++++ b/drivers/usb/typec/mux/ptn36502.c
+@@ -322,8 +322,10 @@ static int ptn36502_probe(struct i2c_client *client)
+ "Failed to acquire orientation-switch\n");
+
+ ret = regulator_enable(ptn->vdd18_supply);
+- if (ret)
+- return dev_err_probe(dev, ret, "Failed to enable vdd18\n");
++ if (ret) {
++ ret = dev_err_probe(dev, ret, "Failed to enable vdd18\n");
++ goto err_switch_put;
++ }
+
+ ret = ptn36502_detect(ptn);
+ if (ret)
+@@ -363,6 +365,9 @@ static int ptn36502_probe(struct i2c_client *client)
+ err_disable_regulator:
+ regulator_disable(ptn->vdd18_supply);
+
++err_switch_put:
++ typec_switch_put(ptn->typec_switch);
++
+ return ret;
+ }
+
+@@ -374,6 +379,8 @@ static void ptn36502_remove(struct i2c_client *client)
+ typec_switch_unregister(ptn->sw);
+
+ regulator_disable(ptn->vdd18_supply);
++
++ typec_switch_put(ptn->typec_switch);
+ }
+
+ static const struct i2c_device_id ptn36502_table[] = {
+diff --git a/drivers/vhost/vsock.c b/drivers/vhost/vsock.c
+index ec20ecff85c7f..bf664ec9341b3 100644
+--- a/drivers/vhost/vsock.c
++++ b/drivers/vhost/vsock.c
+@@ -667,6 +667,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
+ }
+
+ vsock->guest_cid = 0; /* no CID assigned yet */
++ vsock->seqpacket_allow = false;
+
+ atomic_set(&vsock->queued_replies, 0);
+
+@@ -810,8 +811,7 @@ static int vhost_vsock_set_features(struct vhost_vsock *vsock, u64 features)
+ goto err;
+ }
+
+- if (features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET))
+- vsock->seqpacket_allow = true;
++ vsock->seqpacket_allow = features & (1ULL << VIRTIO_VSOCK_F_SEQPACKET);
+
+ for (i = 0; i < ARRAY_SIZE(vsock->vqs); i++) {
+ vq = &vsock->vqs[i];
+diff --git a/drivers/video/fbdev/vesafb.c b/drivers/video/fbdev/vesafb.c
+index 8ab64ae4cad3e..5a161750a3aee 100644
+--- a/drivers/video/fbdev/vesafb.c
++++ b/drivers/video/fbdev/vesafb.c
+@@ -271,7 +271,7 @@ static int vesafb_probe(struct platform_device *dev)
+ if (si->orig_video_isVGA != VIDEO_TYPE_VLFB)
+ return -ENODEV;
+
+- vga_compat = (si->capabilities & 2) ? 0 : 1;
++ vga_compat = !__screen_info_vbe_mode_nonvga(si);
+ vesafb_fix.smem_start = si->lfb_base;
+ vesafb_defined.bits_per_pixel = si->lfb_depth;
+ if (15 == vesafb_defined.bits_per_pixel)
+diff --git a/drivers/watchdog/rzg2l_wdt.c b/drivers/watchdog/rzg2l_wdt.c
+index 1741f98ca67c5..7bce093316c4d 100644
+--- a/drivers/watchdog/rzg2l_wdt.c
++++ b/drivers/watchdog/rzg2l_wdt.c
+@@ -123,8 +123,11 @@ static void rzg2l_wdt_init_timeout(struct watchdog_device *wdev)
+ static int rzg2l_wdt_start(struct watchdog_device *wdev)
+ {
+ struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev);
++ int ret;
+
+- pm_runtime_get_sync(wdev->parent);
++ ret = pm_runtime_resume_and_get(wdev->parent);
++ if (ret)
++ return ret;
+
+ /* Initialize time out */
+ rzg2l_wdt_init_timeout(wdev);
+@@ -141,15 +144,21 @@ static int rzg2l_wdt_start(struct watchdog_device *wdev)
+ static int rzg2l_wdt_stop(struct watchdog_device *wdev)
+ {
+ struct rzg2l_wdt_priv *priv = watchdog_get_drvdata(wdev);
++ int ret;
+
+ rzg2l_wdt_reset(priv);
+- pm_runtime_put(wdev->parent);
++
++ ret = pm_runtime_put(wdev->parent);
++ if (ret < 0)
++ return ret;
+
+ return 0;
+ }
+
+ static int rzg2l_wdt_set_timeout(struct watchdog_device *wdev, unsigned int timeout)
+ {
++ int ret = 0;
++
+ wdev->timeout = timeout;
+
+ /*
+@@ -158,11 +167,14 @@ static int rzg2l_wdt_set_timeout(struct watchdog_device *wdev, unsigned int time
+ * to reset the module) so that it is updated with new timeout values.
+ */
+ if (watchdog_active(wdev)) {
+- rzg2l_wdt_stop(wdev);
+- rzg2l_wdt_start(wdev);
++ ret = rzg2l_wdt_stop(wdev);
++ if (ret)
++ return ret;
++
++ ret = rzg2l_wdt_start(wdev);
+ }
+
+- return 0;
++ return ret;
+ }
+
+ static int rzg2l_wdt_restart(struct watchdog_device *wdev,
+diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
+index 6441e47d8a5e6..7c22f5b8c535f 100644
+--- a/fs/btrfs/compression.c
++++ b/fs/btrfs/compression.c
+@@ -514,6 +514,7 @@ static noinline int add_ra_bio_pages(struct inode *inode,
+ put_page(page);
+ break;
+ }
++ add_size = min(em->start + em->len, page_end + 1) - cur;
+ free_extent_map(em);
+
+ if (page->index == end_index) {
+@@ -526,7 +527,6 @@ static noinline int add_ra_bio_pages(struct inode *inode,
+ }
+ }
+
+- add_size = min(em->start + em->len, page_end + 1) - cur;
+ ret = bio_add_page(orig_bio, page, add_size, offset_in_page(cur));
+ if (ret != add_size) {
+ unlock_extent(tree, cur, page_end, NULL);
+diff --git a/fs/ceph/super.c b/fs/ceph/super.c
+index 885cb5d4e771a..0cdf84cd17912 100644
+--- a/fs/ceph/super.c
++++ b/fs/ceph/super.c
+@@ -961,7 +961,8 @@ static int __init init_caches(void)
+ if (!ceph_mds_request_cachep)
+ goto bad_mds_req;
+
+- ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10, CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT);
++ ceph_wb_pagevec_pool = mempool_create_kmalloc_pool(10,
++ (CEPH_MAX_WRITE_SIZE >> PAGE_SHIFT) * sizeof(struct page *));
+ if (!ceph_wb_pagevec_pool)
+ goto bad_pagevec_pool;
+
+diff --git a/fs/erofs/zutil.c b/fs/erofs/zutil.c
+index b80f612867c2b..9b53883e5caf8 100644
+--- a/fs/erofs/zutil.c
++++ b/fs/erofs/zutil.c
+@@ -38,11 +38,13 @@ void *z_erofs_get_gbuf(unsigned int requiredpages)
+ {
+ struct z_erofs_gbuf *gbuf;
+
++ migrate_disable();
+ gbuf = &z_erofs_gbufpool[z_erofs_gbuf_id()];
+ spin_lock(&gbuf->lock);
+ /* check if the buffer is too small */
+ if (requiredpages > gbuf->nrpages) {
+ spin_unlock(&gbuf->lock);
++ migrate_enable();
+ /* (for sparse checker) pretend gbuf->lock is still taken */
+ __acquire(gbuf->lock);
+ return NULL;
+@@ -57,6 +59,7 @@ void z_erofs_put_gbuf(void *ptr) __releases(gbuf->lock)
+ gbuf = &z_erofs_gbufpool[z_erofs_gbuf_id()];
+ DBG_BUGON(gbuf->ptr != ptr);
+ spin_unlock(&gbuf->lock);
++ migrate_enable();
+ }
+
+ int z_erofs_gbuf_growsize(unsigned int nrpages)
+diff --git a/fs/exfat/dir.c b/fs/exfat/dir.c
+index 84572e11cc05f..7446bf09a04a8 100644
+--- a/fs/exfat/dir.c
++++ b/fs/exfat/dir.c
+@@ -813,7 +813,7 @@ static int __exfat_get_dentry_set(struct exfat_entry_set_cache *es,
+
+ num_bh = EXFAT_B_TO_BLK_ROUND_UP(off + num_entries * DENTRY_SIZE, sb);
+ if (num_bh > ARRAY_SIZE(es->__bh)) {
+- es->bh = kmalloc_array(num_bh, sizeof(*es->bh), GFP_KERNEL);
++ es->bh = kmalloc_array(num_bh, sizeof(*es->bh), GFP_NOFS);
+ if (!es->bh) {
+ brelse(bh);
+ return -ENOMEM;
+diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
+index 1bfd6ab110389..b8cfab8f98b97 100644
+--- a/fs/ext2/balloc.c
++++ b/fs/ext2/balloc.c
+@@ -77,26 +77,33 @@ static int ext2_valid_block_bitmap(struct super_block *sb,
+ ext2_grpblk_t next_zero_bit;
+ ext2_fsblk_t bitmap_blk;
+ ext2_fsblk_t group_first_block;
++ ext2_grpblk_t max_bit;
+
+ group_first_block = ext2_group_first_block_no(sb, block_group);
++ max_bit = ext2_group_last_block_no(sb, block_group) - group_first_block;
+
+ /* check whether block bitmap block number is set */
+ bitmap_blk = le32_to_cpu(desc->bg_block_bitmap);
+ offset = bitmap_blk - group_first_block;
+- if (!ext2_test_bit(offset, bh->b_data))
++ if (offset < 0 || offset > max_bit ||
++ !ext2_test_bit(offset, bh->b_data))
+ /* bad block bitmap */
+ goto err_out;
+
+ /* check whether the inode bitmap block number is set */
+ bitmap_blk = le32_to_cpu(desc->bg_inode_bitmap);
+ offset = bitmap_blk - group_first_block;
+- if (!ext2_test_bit(offset, bh->b_data))
++ if (offset < 0 || offset > max_bit ||
++ !ext2_test_bit(offset, bh->b_data))
+ /* bad block bitmap */
+ goto err_out;
+
+ /* check whether the inode table block number is set */
+ bitmap_blk = le32_to_cpu(desc->bg_inode_table);
+ offset = bitmap_blk - group_first_block;
++ if (offset < 0 || offset > max_bit ||
++ offset + EXT2_SB(sb)->s_itb_per_group - 1 > max_bit)
++ goto err_out;
+ next_zero_bit = ext2_find_next_zero_bit(bh->b_data,
+ offset + EXT2_SB(sb)->s_itb_per_group,
+ offset);
+diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
+index 4a00e2f019d93..3a53dbb85e15b 100644
+--- a/fs/ext4/extents_status.c
++++ b/fs/ext4/extents_status.c
+@@ -310,6 +310,8 @@ void ext4_es_find_extent_range(struct inode *inode,
+ ext4_lblk_t lblk, ext4_lblk_t end,
+ struct extent_status *es)
+ {
++ es->es_lblk = es->es_len = es->es_pblk = 0;
++
+ if (EXT4_SB(inode->i_sb)->s_mount_state & EXT4_FC_REPLAY)
+ return;
+
+diff --git a/fs/ext4/fast_commit.c b/fs/ext4/fast_commit.c
+index 87c009e0c59a5..d3a67bc06d109 100644
+--- a/fs/ext4/fast_commit.c
++++ b/fs/ext4/fast_commit.c
+@@ -649,6 +649,12 @@ void ext4_fc_track_range(handle_t *handle, struct inode *inode, ext4_lblk_t star
+ if (ext4_test_mount_flag(inode->i_sb, EXT4_MF_FC_INELIGIBLE))
+ return;
+
++ if (ext4_has_inline_data(inode)) {
++ ext4_fc_mark_ineligible(inode->i_sb, EXT4_FC_REASON_XATTR,
++ handle);
++ return;
++ }
++
+ args.start = start;
+ args.end = end;
+
+diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
+index a630b27a4cc6e..1311ad0464b2a 100644
+--- a/fs/ext4/namei.c
++++ b/fs/ext4/namei.c
+@@ -151,10 +151,11 @@ static struct buffer_head *__ext4_read_dirblock(struct inode *inode,
+
+ return bh;
+ }
+- if (!bh && (type == INDEX || type == DIRENT_HTREE)) {
++ /* The first directory block must not be a hole. */
++ if (!bh && (type == INDEX || type == DIRENT_HTREE || block == 0)) {
+ ext4_error_inode(inode, func, line, block,
+- "Directory hole found for htree %s block",
+- (type == INDEX) ? "index" : "leaf");
++ "Directory hole found for htree %s block %u",
++ (type == INDEX) ? "index" : "leaf", block);
+ return ERR_PTR(-EFSCORRUPTED);
+ }
+ if (!bh)
+@@ -2217,6 +2218,52 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
+ return err ? err : err2;
+ }
+
++static bool ext4_check_dx_root(struct inode *dir, struct dx_root *root)
++{
++ struct fake_dirent *fde;
++ const char *error_msg;
++ unsigned int rlen;
++ unsigned int blocksize = dir->i_sb->s_blocksize;
++ char *blockend = (char *)root + dir->i_sb->s_blocksize;
++
++ fde = &root->dot;
++ if (unlikely(fde->name_len != 1)) {
++ error_msg = "invalid name_len for '.'";
++ goto corrupted;
++ }
++ if (unlikely(strncmp(root->dot_name, ".", fde->name_len))) {
++ error_msg = "invalid name for '.'";
++ goto corrupted;
++ }
++ rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize);
++ if (unlikely((char *)fde + rlen >= blockend)) {
++ error_msg = "invalid rec_len for '.'";
++ goto corrupted;
++ }
++
++ fde = &root->dotdot;
++ if (unlikely(fde->name_len != 2)) {
++ error_msg = "invalid name_len for '..'";
++ goto corrupted;
++ }
++ if (unlikely(strncmp(root->dotdot_name, "..", fde->name_len))) {
++ error_msg = "invalid name for '..'";
++ goto corrupted;
++ }
++ rlen = ext4_rec_len_from_disk(fde->rec_len, blocksize);
++ if (unlikely((char *)fde + rlen >= blockend)) {
++ error_msg = "invalid rec_len for '..'";
++ goto corrupted;
++ }
++
++ return true;
++
++corrupted:
++ EXT4_ERROR_INODE(dir, "Corrupt dir, %s, running e2fsck is recommended",
++ error_msg);
++ return false;
++}
++
+ /*
+ * This converts a one block unindexed directory to a 3 block indexed
+ * directory, and adds the dentry to the indexed directory.
+@@ -2251,17 +2298,17 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
+ brelse(bh);
+ return retval;
+ }
++
+ root = (struct dx_root *) bh->b_data;
++ if (!ext4_check_dx_root(dir, root)) {
++ brelse(bh);
++ return -EFSCORRUPTED;
++ }
+
+ /* The 0th block becomes the root, move the dirents out */
+ fde = &root->dotdot;
+ de = (struct ext4_dir_entry_2 *)((char *)fde +
+ ext4_rec_len_from_disk(fde->rec_len, blocksize));
+- if ((char *) de >= (((char *) root) + blocksize)) {
+- EXT4_ERROR_INODE(dir, "invalid rec_len for '..'");
+- brelse(bh);
+- return -EFSCORRUPTED;
+- }
+ len = ((char *) root) + (blocksize - csum_size) - (char *) de;
+
+ /* Allocate new block for the 0th block's dirents */
+@@ -3083,10 +3130,7 @@ bool ext4_empty_dir(struct inode *inode)
+ EXT4_ERROR_INODE(inode, "invalid size");
+ return false;
+ }
+- /* The first directory block must not be a hole,
+- * so treat it as DIRENT_HTREE
+- */
+- bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
++ bh = ext4_read_dirblock(inode, 0, EITHER);
+ if (IS_ERR(bh))
+ return false;
+
+@@ -3531,10 +3575,7 @@ static struct buffer_head *ext4_get_first_dir_block(handle_t *handle,
+ struct ext4_dir_entry_2 *de;
+ unsigned int offset;
+
+- /* The first directory block must not be a hole, so
+- * treat it as DIRENT_HTREE
+- */
+- bh = ext4_read_dirblock(inode, 0, DIRENT_HTREE);
++ bh = ext4_read_dirblock(inode, 0, EITHER);
+ if (IS_ERR(bh)) {
+ *retval = PTR_ERR(bh);
+ return NULL;
+diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
+index 6460879b9fcbb..46ce2f21fef9d 100644
+--- a/fs/ext4/xattr.c
++++ b/fs/ext4/xattr.c
+@@ -1433,6 +1433,12 @@ static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
+ goto out;
+
+ memcpy(bh->b_data, buf, csize);
++ /*
++ * Zero out block tail to avoid writing uninitialized memory
++ * to disk.
++ */
++ if (csize < blocksize)
++ memset(bh->b_data + csize, 0, blocksize - csize);
+ set_buffer_uptodate(bh);
+ ext4_handle_dirty_metadata(handle, ea_inode, bh);
+
+diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
+index 55d444bec5c06..b52d10b457fe7 100644
+--- a/fs/f2fs/checkpoint.c
++++ b/fs/f2fs/checkpoint.c
+@@ -1186,6 +1186,11 @@ static void __prepare_cp_block(struct f2fs_sb_info *sbi)
+ ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
+ ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
+ ckpt->next_free_nid = cpu_to_le32(last_nid);
++
++ /* update user_block_counts */
++ sbi->last_valid_block_count = sbi->total_valid_block_count;
++ percpu_counter_set(&sbi->alloc_valid_block_count, 0);
++ percpu_counter_set(&sbi->rf_node_block_count, 0);
+ }
+
+ static bool __need_flush_quota(struct f2fs_sb_info *sbi)
+@@ -1575,11 +1580,6 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+ start_blk += NR_CURSEG_NODE_TYPE;
+ }
+
+- /* update user_block_counts */
+- sbi->last_valid_block_count = sbi->total_valid_block_count;
+- percpu_counter_set(&sbi->alloc_valid_block_count, 0);
+- percpu_counter_set(&sbi->rf_node_block_count, 0);
+-
+ /* Here, we have one bio having CP pack except cp pack 2 page */
+ f2fs_sync_meta_pages(sbi, META, LONG_MAX, FS_CP_META_IO);
+ /* Wait for all dirty meta pages to be submitted for IO */
+diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
+index b9b0debc6b3d3..467f67cf2b380 100644
+--- a/fs/f2fs/data.c
++++ b/fs/f2fs/data.c
+@@ -925,6 +925,7 @@ int f2fs_merge_page_bio(struct f2fs_io_info *fio)
+ #ifdef CONFIG_BLK_DEV_ZONED
+ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
+ {
++ struct block_device *bdev = sbi->sb->s_bdev;
+ int devi = 0;
+
+ if (f2fs_is_multi_device(sbi)) {
+@@ -935,8 +936,9 @@ static bool is_end_zone_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr)
+ return false;
+ }
+ blkaddr -= FDEV(devi).start_blk;
++ bdev = FDEV(devi).bdev;
+ }
+- return bdev_is_zoned(FDEV(devi).bdev) &&
++ return bdev_is_zoned(bdev) &&
+ f2fs_blkz_is_seq(sbi, devi, blkaddr) &&
+ (blkaddr % sbi->blocks_per_blkz == sbi->blocks_per_blkz - 1);
+ }
+@@ -2601,7 +2603,7 @@ bool f2fs_should_update_outplace(struct inode *inode, struct f2fs_io_info *fio)
+ return true;
+ if (IS_NOQUOTA(inode))
+ return true;
+- if (f2fs_is_atomic_file(inode))
++ if (f2fs_used_in_atomic_write(inode))
+ return true;
+ /* rewrite low ratio compress data w/ OPU mode to avoid fragmentation */
+ if (f2fs_compressed_file(inode) &&
+@@ -2688,7 +2690,7 @@ int f2fs_do_write_data_page(struct f2fs_io_info *fio)
+ }
+
+ /* wait for GCed page writeback via META_MAPPING */
+- if (fio->post_read)
++ if (fio->meta_gc)
+ f2fs_wait_on_block_writeback(inode, fio->old_blkaddr);
+
+ /*
+@@ -2783,7 +2785,7 @@ int f2fs_write_single_data_page(struct page *page, int *submitted,
+ .submitted = 0,
+ .compr_blocks = compr_blocks,
+ .need_lock = compr_blocks ? LOCK_DONE : LOCK_RETRY,
+- .post_read = f2fs_post_read_required(inode) ? 1 : 0,
++ .meta_gc = f2fs_meta_inode_gc_required(inode) ? 1 : 0,
+ .io_type = io_type,
+ .io_wbc = wbc,
+ .bio = bio,
+diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
+index 1974b6aff397c..66680159a2968 100644
+--- a/fs/f2fs/f2fs.h
++++ b/fs/f2fs/f2fs.h
+@@ -803,6 +803,7 @@ enum {
+ FI_COW_FILE, /* indicate COW file */
+ FI_ATOMIC_COMMITTED, /* indicate atomic commit completed except disk sync */
+ FI_ATOMIC_REPLACE, /* indicate atomic replace */
++ FI_OPENED_FILE, /* indicate file has been opened */
+ FI_MAX, /* max flag, never be used */
+ };
+
+@@ -842,7 +843,11 @@ struct f2fs_inode_info {
+ struct task_struct *atomic_write_task; /* store atomic write task */
+ struct extent_tree *extent_tree[NR_EXTENT_CACHES];
+ /* cached extent_tree entry */
+- struct inode *cow_inode; /* copy-on-write inode for atomic write */
++ union {
++ struct inode *cow_inode; /* copy-on-write inode for atomic write */
++ struct inode *atomic_inode;
++ /* point to atomic_inode, available only for cow_inode */
++ };
+
+ /* avoid racing between foreground op and gc */
+ struct f2fs_rwsem i_gc_rwsem[2];
+@@ -1210,7 +1215,7 @@ struct f2fs_io_info {
+ unsigned int in_list:1; /* indicate fio is in io_list */
+ unsigned int is_por:1; /* indicate IO is from recovery or not */
+ unsigned int encrypted:1; /* indicate file is encrypted */
+- unsigned int post_read:1; /* require post read */
++ unsigned int meta_gc:1; /* require meta inode GC */
+ enum iostat_type io_type; /* io type */
+ struct writeback_control *io_wbc; /* writeback control */
+ struct bio **bio; /* bio for ipu */
+@@ -4261,6 +4266,16 @@ static inline bool f2fs_post_read_required(struct inode *inode)
+ f2fs_compressed_file(inode);
+ }
+
++static inline bool f2fs_used_in_atomic_write(struct inode *inode)
++{
++ return f2fs_is_atomic_file(inode) || f2fs_is_cow_file(inode);
++}
++
++static inline bool f2fs_meta_inode_gc_required(struct inode *inode)
++{
++ return f2fs_post_read_required(inode) || f2fs_used_in_atomic_write(inode);
++}
++
+ /*
+ * compress.c
+ */
+diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
+index 5c0b281a70f3e..387ce167dda1b 100644
+--- a/fs/f2fs/file.c
++++ b/fs/f2fs/file.c
+@@ -554,6 +554,42 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
+ return 0;
+ }
+
++static int finish_preallocate_blocks(struct inode *inode)
++{
++ int ret;
++
++ inode_lock(inode);
++ if (is_inode_flag_set(inode, FI_OPENED_FILE)) {
++ inode_unlock(inode);
++ return 0;
++ }
++
++ if (!file_should_truncate(inode)) {
++ set_inode_flag(inode, FI_OPENED_FILE);
++ inode_unlock(inode);
++ return 0;
++ }
++
++ f2fs_down_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
++ filemap_invalidate_lock(inode->i_mapping);
++
++ truncate_setsize(inode, i_size_read(inode));
++ ret = f2fs_truncate(inode);
++
++ filemap_invalidate_unlock(inode->i_mapping);
++ f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
++
++ if (!ret)
++ set_inode_flag(inode, FI_OPENED_FILE);
++
++ inode_unlock(inode);
++ if (ret)
++ return ret;
++
++ file_dont_truncate(inode);
++ return 0;
++}
++
+ static int f2fs_file_open(struct inode *inode, struct file *filp)
+ {
+ int err = fscrypt_file_open(inode, filp);
+@@ -571,7 +607,11 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
+ filp->f_mode |= FMODE_NOWAIT;
+ filp->f_mode |= FMODE_CAN_ODIRECT;
+
+- return dquot_file_open(inode, filp);
++ err = dquot_file_open(inode, filp);
++ if (err)
++ return err;
++
++ return finish_preallocate_blocks(inode);
+ }
+
+ void f2fs_truncate_data_blocks_range(struct dnode_of_data *dn, int count)
+@@ -825,6 +865,8 @@ static bool f2fs_force_buffered_io(struct inode *inode, int rw)
+ return true;
+ if (f2fs_compressed_file(inode))
+ return true;
++ if (f2fs_has_inline_data(inode))
++ return true;
+
+ /* disallow direct IO if any of devices has unaligned blksize */
+ if (f2fs_is_multi_device(sbi) && !sbi->aligned_blksize)
+@@ -2141,6 +2183,9 @@ static int f2fs_ioc_start_atomic_write(struct file *filp, bool truncate)
+
+ set_inode_flag(fi->cow_inode, FI_COW_FILE);
+ clear_inode_flag(fi->cow_inode, FI_INLINE_DATA);
++
++ /* Set the COW inode's atomic_inode to the atomic inode */
++ F2FS_I(fi->cow_inode)->atomic_inode = inode;
+ } else {
+ /* Reuse the already created COW inode */
+ ret = f2fs_do_truncate_blocks(fi->cow_inode, 0, true);
+diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
+index 6066c6eecf41d..b2951cd930d80 100644
+--- a/fs/f2fs/gc.c
++++ b/fs/f2fs/gc.c
+@@ -1171,7 +1171,8 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+ static int ra_data_block(struct inode *inode, pgoff_t index)
+ {
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+- struct address_space *mapping = inode->i_mapping;
++ struct address_space *mapping = f2fs_is_cow_file(inode) ?
++ F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping;
+ struct dnode_of_data dn;
+ struct page *page;
+ struct f2fs_io_info fio = {
+@@ -1260,6 +1261,8 @@ static int ra_data_block(struct inode *inode, pgoff_t index)
+ static int move_data_block(struct inode *inode, block_t bidx,
+ int gc_type, unsigned int segno, int off)
+ {
++ struct address_space *mapping = f2fs_is_cow_file(inode) ?
++ F2FS_I(inode)->atomic_inode->i_mapping : inode->i_mapping;
+ struct f2fs_io_info fio = {
+ .sbi = F2FS_I_SB(inode),
+ .ino = inode->i_ino,
+@@ -1282,7 +1285,7 @@ static int move_data_block(struct inode *inode, block_t bidx,
+ CURSEG_ALL_DATA_ATGC : CURSEG_COLD_DATA;
+
+ /* do not read out */
+- page = f2fs_grab_cache_page(inode->i_mapping, bidx, false);
++ page = f2fs_grab_cache_page(mapping, bidx, false);
+ if (!page)
+ return -ENOMEM;
+
+@@ -1579,7 +1582,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+ start_bidx = f2fs_start_bidx_of_node(nofs, inode) +
+ ofs_in_node;
+
+- if (f2fs_post_read_required(inode)) {
++ if (f2fs_meta_inode_gc_required(inode)) {
+ int err = ra_data_block(inode, start_bidx);
+
+ f2fs_up_write(&F2FS_I(inode)->i_gc_rwsem[WRITE]);
+@@ -1630,7 +1633,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+
+ start_bidx = f2fs_start_bidx_of_node(nofs, inode)
+ + ofs_in_node;
+- if (f2fs_post_read_required(inode))
++ if (f2fs_meta_inode_gc_required(inode))
+ err = move_data_block(inode, start_bidx,
+ gc_type, segno, off);
+ else
+@@ -1638,7 +1641,7 @@ static int gc_data_segment(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+ segno, off);
+
+ if (!err && (gc_type == FG_GC ||
+- f2fs_post_read_required(inode)))
++ f2fs_meta_inode_gc_required(inode)))
+ submitted++;
+
+ if (locked) {
+diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
+index 7638d0d7b7eed..215daa71dc18a 100644
+--- a/fs/f2fs/inline.c
++++ b/fs/f2fs/inline.c
+@@ -16,7 +16,7 @@
+
+ static bool support_inline_data(struct inode *inode)
+ {
+- if (f2fs_is_atomic_file(inode))
++ if (f2fs_used_in_atomic_write(inode))
+ return false;
+ if (!S_ISREG(inode->i_mode) && !S_ISLNK(inode->i_mode))
+ return false;
+@@ -203,8 +203,10 @@ int f2fs_convert_inline_inode(struct inode *inode)
+ struct page *ipage, *page;
+ int err = 0;
+
+- if (!f2fs_has_inline_data(inode) ||
+- f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
++ if (f2fs_hw_is_readonly(sbi) || f2fs_readonly(sbi->sb))
++ return -EROFS;
++
++ if (!f2fs_has_inline_data(inode))
+ return 0;
+
+ err = f2fs_dquot_initialize(inode);
+diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
+index 005dde72aff3d..c6b55aedc2762 100644
+--- a/fs/f2fs/inode.c
++++ b/fs/f2fs/inode.c
+@@ -29,6 +29,9 @@ void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync)
+ if (is_inode_flag_set(inode, FI_NEW_INODE))
+ return;
+
++ if (f2fs_readonly(F2FS_I_SB(inode)->sb))
++ return;
++
+ if (f2fs_inode_dirtied(inode, sync))
+ return;
+
+@@ -610,14 +613,6 @@ struct inode *f2fs_iget(struct super_block *sb, unsigned long ino)
+ }
+ f2fs_set_inode_flags(inode);
+
+- if (file_should_truncate(inode) &&
+- !is_sbi_flag_set(sbi, SBI_POR_DOING)) {
+- ret = f2fs_truncate(inode);
+- if (ret)
+- goto bad_inode;
+- file_dont_truncate(inode);
+- }
+-
+ unlock_new_inode(inode);
+ trace_f2fs_iget(inode);
+ return inode;
+@@ -813,8 +808,9 @@ void f2fs_evict_inode(struct inode *inode)
+
+ f2fs_abort_atomic_write(inode, true);
+
+- if (fi->cow_inode) {
++ if (fi->cow_inode && f2fs_is_cow_file(fi->cow_inode)) {
+ clear_inode_flag(fi->cow_inode, FI_COW_FILE);
++ F2FS_I(fi->cow_inode)->atomic_inode = NULL;
+ iput(fi->cow_inode);
+ fi->cow_inode = NULL;
+ }
+diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
+index a0ce3d080f80a..259e235becc59 100644
+--- a/fs/f2fs/segment.c
++++ b/fs/f2fs/segment.c
+@@ -3828,7 +3828,7 @@ int f2fs_inplace_write_data(struct f2fs_io_info *fio)
+ goto drop_bio;
+ }
+
+- if (fio->post_read)
++ if (fio->meta_gc)
+ f2fs_truncate_meta_inode_pages(sbi, fio->new_blkaddr, 1);
+
+ stat_inc_inplace_blocks(fio->sbi);
+@@ -3998,7 +3998,7 @@ void f2fs_wait_on_block_writeback(struct inode *inode, block_t blkaddr)
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ struct page *cpage;
+
+- if (!f2fs_post_read_required(inode))
++ if (!f2fs_meta_inode_gc_required(inode))
+ return;
+
+ if (!__is_valid_data_blkaddr(blkaddr))
+@@ -4017,7 +4017,7 @@ void f2fs_wait_on_block_writeback_range(struct inode *inode, block_t blkaddr,
+ struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+ block_t i;
+
+- if (!f2fs_post_read_required(inode))
++ if (!f2fs_meta_inode_gc_required(inode))
+ return;
+
+ for (i = 0; i < len; i++)
+diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
+index e1c0f418aa11f..bfc01a521cb98 100644
+--- a/fs/f2fs/segment.h
++++ b/fs/f2fs/segment.h
+@@ -347,7 +347,8 @@ static inline unsigned int get_ckpt_valid_blocks(struct f2fs_sb_info *sbi,
+ unsigned int segno, bool use_section)
+ {
+ if (use_section && __is_large_section(sbi)) {
+- unsigned int start_segno = START_SEGNO(segno);
++ unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
++ unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
+ unsigned int blocks = 0;
+ int i;
+
+diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
+index 99e44ea7d8756..32fe6fa72f460 100644
+--- a/fs/fuse/inode.c
++++ b/fs/fuse/inode.c
+@@ -755,6 +755,8 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param)
+ struct fs_parse_result result;
+ struct fuse_fs_context *ctx = fsc->fs_private;
+ int opt;
++ kuid_t kuid;
++ kgid_t kgid;
+
+ if (fsc->purpose == FS_CONTEXT_FOR_RECONFIGURE) {
+ /*
+@@ -799,16 +801,30 @@ static int fuse_parse_param(struct fs_context *fsc, struct fs_parameter *param)
+ break;
+
+ case OPT_USER_ID:
+- ctx->user_id = make_kuid(fsc->user_ns, result.uint_32);
+- if (!uid_valid(ctx->user_id))
++ kuid = make_kuid(fsc->user_ns, result.uint_32);
++ if (!uid_valid(kuid))
+ return invalfc(fsc, "Invalid user_id");
++ /*
++ * The requested uid must be representable in the
++ * filesystem's idmapping.
++ */
++ if (!kuid_has_mapping(fsc->user_ns, kuid))
++ return invalfc(fsc, "Invalid user_id");
++ ctx->user_id = kuid;
+ ctx->user_id_present = true;
+ break;
+
+ case OPT_GROUP_ID:
+- ctx->group_id = make_kgid(fsc->user_ns, result.uint_32);
+- if (!gid_valid(ctx->group_id))
++ kgid = make_kgid(fsc->user_ns, result.uint_32);;
++ if (!gid_valid(kgid))
++ return invalfc(fsc, "Invalid group_id");
++ /*
++ * The requested gid must be representable in the
++ * filesystem's idmapping.
++ */
++ if (!kgid_has_mapping(fsc->user_ns, kgid))
+ return invalfc(fsc, "Invalid group_id");
++ ctx->group_id = kgid;
+ ctx->group_id_present = true;
+ break;
+
+diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
+index 8c34798a07157..744e10b469048 100644
+--- a/fs/hfs/inode.c
++++ b/fs/hfs/inode.c
+@@ -200,6 +200,7 @@ struct inode *hfs_new_inode(struct inode *dir, const struct qstr *name, umode_t
+ HFS_I(inode)->flags = 0;
+ HFS_I(inode)->rsrc_inode = NULL;
+ HFS_I(inode)->fs_blocks = 0;
++ HFS_I(inode)->tz_secondswest = sys_tz.tz_minuteswest * 60;
+ if (S_ISDIR(mode)) {
+ inode->i_size = 2;
+ HFS_SB(sb)->folder_count++;
+@@ -275,6 +276,8 @@ void hfs_inode_read_fork(struct inode *inode, struct hfs_extent *ext,
+ for (count = 0, i = 0; i < 3; i++)
+ count += be16_to_cpu(ext[i].count);
+ HFS_I(inode)->first_blocks = count;
++ HFS_I(inode)->cached_start = 0;
++ HFS_I(inode)->cached_blocks = 0;
+
+ inode->i_size = HFS_I(inode)->phys_size = log_size;
+ HFS_I(inode)->fs_blocks = (log_size + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+diff --git a/fs/hfsplus/bfind.c b/fs/hfsplus/bfind.c
+index ca2ba8c9f82ef..901e83d65d202 100644
+--- a/fs/hfsplus/bfind.c
++++ b/fs/hfsplus/bfind.c
+@@ -25,19 +25,8 @@ int hfs_find_init(struct hfs_btree *tree, struct hfs_find_data *fd)
+ fd->key = ptr + tree->max_key_len + 2;
+ hfs_dbg(BNODE_REFS, "find_init: %d (%p)\n",
+ tree->cnid, __builtin_return_address(0));
+- switch (tree->cnid) {
+- case HFSPLUS_CAT_CNID:
+- mutex_lock_nested(&tree->tree_lock, CATALOG_BTREE_MUTEX);
+- break;
+- case HFSPLUS_EXT_CNID:
+- mutex_lock_nested(&tree->tree_lock, EXTENTS_BTREE_MUTEX);
+- break;
+- case HFSPLUS_ATTR_CNID:
+- mutex_lock_nested(&tree->tree_lock, ATTR_BTREE_MUTEX);
+- break;
+- default:
+- BUG();
+- }
++ mutex_lock_nested(&tree->tree_lock,
++ hfsplus_btree_lock_class(tree));
+ return 0;
+ }
+
+diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
+index 3c572e44f2adf..9c51867dddc51 100644
+--- a/fs/hfsplus/extents.c
++++ b/fs/hfsplus/extents.c
+@@ -430,7 +430,8 @@ int hfsplus_free_fork(struct super_block *sb, u32 cnid,
+ hfsplus_free_extents(sb, ext_entry, total_blocks - start,
+ total_blocks);
+ total_blocks = start;
+- mutex_lock(&fd.tree->tree_lock);
++ mutex_lock_nested(&fd.tree->tree_lock,
++ hfsplus_btree_lock_class(fd.tree));
+ } while (total_blocks > blocks);
+ hfs_find_exit(&fd);
+
+@@ -592,7 +593,8 @@ void hfsplus_file_truncate(struct inode *inode)
+ alloc_cnt, alloc_cnt - blk_cnt);
+ hfsplus_dump_extent(hip->first_extents);
+ hip->first_blocks = blk_cnt;
+- mutex_lock(&fd.tree->tree_lock);
++ mutex_lock_nested(&fd.tree->tree_lock,
++ hfsplus_btree_lock_class(fd.tree));
+ break;
+ }
+ res = __hfsplus_ext_cache_extent(&fd, inode, alloc_cnt);
+@@ -606,7 +608,8 @@ void hfsplus_file_truncate(struct inode *inode)
+ hfsplus_free_extents(sb, hip->cached_extents,
+ alloc_cnt - start, alloc_cnt - blk_cnt);
+ hfsplus_dump_extent(hip->cached_extents);
+- mutex_lock(&fd.tree->tree_lock);
++ mutex_lock_nested(&fd.tree->tree_lock,
++ hfsplus_btree_lock_class(fd.tree));
+ if (blk_cnt > start) {
+ hip->extent_state |= HFSPLUS_EXT_DIRTY;
+ break;
+diff --git a/fs/hfsplus/hfsplus_fs.h b/fs/hfsplus/hfsplus_fs.h
+index 012a3d003fbe6..9e78f181c24f4 100644
+--- a/fs/hfsplus/hfsplus_fs.h
++++ b/fs/hfsplus/hfsplus_fs.h
+@@ -553,6 +553,27 @@ static inline __be32 __hfsp_ut2mt(time64_t ut)
+ return cpu_to_be32(lower_32_bits(ut) + HFSPLUS_UTC_OFFSET);
+ }
+
++static inline enum hfsplus_btree_mutex_classes
++hfsplus_btree_lock_class(struct hfs_btree *tree)
++{
++ enum hfsplus_btree_mutex_classes class;
++
++ switch (tree->cnid) {
++ case HFSPLUS_CAT_CNID:
++ class = CATALOG_BTREE_MUTEX;
++ break;
++ case HFSPLUS_EXT_CNID:
++ class = EXTENTS_BTREE_MUTEX;
++ break;
++ case HFSPLUS_ATTR_CNID:
++ class = ATTR_BTREE_MUTEX;
++ break;
++ default:
++ BUG();
++ }
++ return class;
++}
++
+ /* compatibility */
+ #define hfsp_mt2ut(t) (struct timespec64){ .tv_sec = __hfsp_mt2ut(t) }
+ #define hfsp_ut2mt(t) __hfsp_ut2mt((t).tv_sec)
+diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h
+index 0239e3af39455..8b39c15c408cc 100644
+--- a/fs/hostfs/hostfs.h
++++ b/fs/hostfs/hostfs.h
+@@ -63,9 +63,10 @@ struct hostfs_stat {
+ struct hostfs_timespec atime, mtime, ctime;
+ unsigned int blksize;
+ unsigned long long blocks;
+- unsigned int maj;
+- unsigned int min;
+- dev_t dev;
++ struct {
++ unsigned int maj;
++ unsigned int min;
++ } rdev, dev;
+ };
+
+ extern int stat_file(const char *path, struct hostfs_stat *p, int fd);
+diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c
+index a73d27c4dd583..2c4d503a62e02 100644
+--- a/fs/hostfs/hostfs_kern.c
++++ b/fs/hostfs/hostfs_kern.c
+@@ -530,10 +530,11 @@ static int hostfs_inode_update(struct inode *ino, const struct hostfs_stat *st)
+ static int hostfs_inode_set(struct inode *ino, void *data)
+ {
+ struct hostfs_stat *st = data;
+- dev_t rdev;
++ dev_t dev, rdev;
+
+ /* Reencode maj and min with the kernel encoding.*/
+- rdev = MKDEV(st->maj, st->min);
++ rdev = MKDEV(st->rdev.maj, st->rdev.min);
++ dev = MKDEV(st->dev.maj, st->dev.min);
+
+ switch (st->mode & S_IFMT) {
+ case S_IFLNK:
+@@ -559,7 +560,7 @@ static int hostfs_inode_set(struct inode *ino, void *data)
+ return -EIO;
+ }
+
+- HOSTFS_I(ino)->dev = st->dev;
++ HOSTFS_I(ino)->dev = dev;
+ ino->i_ino = st->ino;
+ ino->i_mode = st->mode;
+ return hostfs_inode_update(ino, st);
+@@ -568,8 +569,9 @@ static int hostfs_inode_set(struct inode *ino, void *data)
+ static int hostfs_inode_test(struct inode *inode, void *data)
+ {
+ const struct hostfs_stat *st = data;
++ dev_t dev = MKDEV(st->dev.maj, st->dev.min);
+
+- return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == st->dev;
++ return inode->i_ino == st->ino && HOSTFS_I(inode)->dev == dev;
+ }
+
+ static struct inode *hostfs_iget(struct super_block *sb, char *name)
+diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c
+index 840619e39a1a6..97e9c40a94488 100644
+--- a/fs/hostfs/hostfs_user.c
++++ b/fs/hostfs/hostfs_user.c
+@@ -34,9 +34,10 @@ static void stat64_to_hostfs(const struct stat64 *buf, struct hostfs_stat *p)
+ p->mtime.tv_nsec = 0;
+ p->blksize = buf->st_blksize;
+ p->blocks = buf->st_blocks;
+- p->maj = os_major(buf->st_rdev);
+- p->min = os_minor(buf->st_rdev);
+- p->dev = buf->st_dev;
++ p->rdev.maj = os_major(buf->st_rdev);
++ p->rdev.min = os_minor(buf->st_rdev);
++ p->dev.maj = os_major(buf->st_dev);
++ p->dev.min = os_minor(buf->st_dev);
+ }
+
+ int stat_file(const char *path, struct hostfs_stat *p, int fd)
+diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
+index 75ea4e9a5cabd..e7fc912693bd7 100644
+--- a/fs/jbd2/commit.c
++++ b/fs/jbd2/commit.c
+@@ -766,7 +766,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
+ if (first_block < journal->j_tail)
+ freed += journal->j_last - journal->j_first;
+ /* Update tail only if we free significant amount of space */
+- if (freed < jbd2_journal_get_max_txn_bufs(journal))
++ if (freed < journal->j_max_transaction_buffers)
+ update_tail = 0;
+ }
+ J_ASSERT(commit_transaction->t_state == T_COMMIT);
+diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
+index 03c4b9214f564..ae5b544ed0cc0 100644
+--- a/fs/jbd2/journal.c
++++ b/fs/jbd2/journal.c
+@@ -1451,6 +1451,48 @@ static int journal_revoke_records_per_block(journal_t *journal)
+ return space / record_size;
+ }
+
++static int jbd2_journal_get_max_txn_bufs(journal_t *journal)
++{
++ return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
++}
++
++/*
++ * Base amount of descriptor blocks we reserve for each transaction.
++ */
++static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
++{
++ int tag_space = journal->j_blocksize - sizeof(journal_header_t);
++ int tags_per_block;
++
++ /* Subtract UUID */
++ tag_space -= 16;
++ if (jbd2_journal_has_csum_v2or3(journal))
++ tag_space -= sizeof(struct jbd2_journal_block_tail);
++ /* Commit code leaves a slack space of 16 bytes at the end of block */
++ tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
++ /*
++ * Revoke descriptors are accounted separately so we need to reserve
++ * space for commit block and normal transaction descriptor blocks.
++ */
++ return 1 + DIV_ROUND_UP(jbd2_journal_get_max_txn_bufs(journal),
++ tags_per_block);
++}
++
++/*
++ * Initialize number of blocks each transaction reserves for its bookkeeping
++ * and maximum number of blocks a transaction can use. This needs to be called
++ * after the journal size and the fastcommit area size are initialized.
++ */
++static void jbd2_journal_init_transaction_limits(journal_t *journal)
++{
++ journal->j_revoke_records_per_block =
++ journal_revoke_records_per_block(journal);
++ journal->j_transaction_overhead_buffers =
++ jbd2_descriptor_blocks_per_trans(journal);
++ journal->j_max_transaction_buffers =
++ jbd2_journal_get_max_txn_bufs(journal);
++}
++
+ /*
+ * Load the on-disk journal superblock and read the key fields into the
+ * journal_t.
+@@ -1492,8 +1534,8 @@ static int journal_load_superblock(journal_t *journal)
+ if (jbd2_journal_has_csum_v2or3(journal))
+ journal->j_csum_seed = jbd2_chksum(journal, ~0, sb->s_uuid,
+ sizeof(sb->s_uuid));
+- journal->j_revoke_records_per_block =
+- journal_revoke_records_per_block(journal);
++ /* After journal features are set, we can compute transaction limits */
++ jbd2_journal_init_transaction_limits(journal);
+
+ if (jbd2_has_feature_fast_commit(journal)) {
+ journal->j_fc_last = be32_to_cpu(sb->s_maxlen);
+@@ -1743,8 +1785,6 @@ static int journal_reset(journal_t *journal)
+ journal->j_commit_sequence = journal->j_transaction_sequence - 1;
+ journal->j_commit_request = journal->j_commit_sequence;
+
+- journal->j_max_transaction_buffers = jbd2_journal_get_max_txn_bufs(journal);
+-
+ /*
+ * Now that journal recovery is done, turn fast commits off here. This
+ * way, if fast commit was enabled before the crash but if now FS has
+@@ -2285,8 +2325,6 @@ jbd2_journal_initialize_fast_commit(journal_t *journal)
+ journal->j_fc_first = journal->j_last + 1;
+ journal->j_fc_off = 0;
+ journal->j_free = journal->j_last - journal->j_first;
+- journal->j_max_transaction_buffers =
+- jbd2_journal_get_max_txn_bufs(journal);
+
+ return 0;
+ }
+@@ -2374,8 +2412,7 @@ int jbd2_journal_set_features(journal_t *journal, unsigned long compat,
+ sb->s_feature_ro_compat |= cpu_to_be32(ro);
+ sb->s_feature_incompat |= cpu_to_be32(incompat);
+ unlock_buffer(journal->j_sb_buffer);
+- journal->j_revoke_records_per_block =
+- journal_revoke_records_per_block(journal);
++ jbd2_journal_init_transaction_limits(journal);
+
+ return 1;
+ #undef COMPAT_FEATURE_ON
+@@ -2406,8 +2443,7 @@ void jbd2_journal_clear_features(journal_t *journal, unsigned long compat,
+ sb->s_feature_compat &= ~cpu_to_be32(compat);
+ sb->s_feature_ro_compat &= ~cpu_to_be32(ro);
+ sb->s_feature_incompat &= ~cpu_to_be32(incompat);
+- journal->j_revoke_records_per_block =
+- journal_revoke_records_per_block(journal);
++ jbd2_journal_init_transaction_limits(journal);
+ }
+ EXPORT_SYMBOL(jbd2_journal_clear_features);
+
+diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
+index cb0b8d6fc0c6d..66513c18ca294 100644
+--- a/fs/jbd2/transaction.c
++++ b/fs/jbd2/transaction.c
+@@ -62,28 +62,6 @@ void jbd2_journal_free_transaction(transaction_t *transaction)
+ kmem_cache_free(transaction_cache, transaction);
+ }
+
+-/*
+- * Base amount of descriptor blocks we reserve for each transaction.
+- */
+-static int jbd2_descriptor_blocks_per_trans(journal_t *journal)
+-{
+- int tag_space = journal->j_blocksize - sizeof(journal_header_t);
+- int tags_per_block;
+-
+- /* Subtract UUID */
+- tag_space -= 16;
+- if (jbd2_journal_has_csum_v2or3(journal))
+- tag_space -= sizeof(struct jbd2_journal_block_tail);
+- /* Commit code leaves a slack space of 16 bytes at the end of block */
+- tags_per_block = (tag_space - 16) / journal_tag_bytes(journal);
+- /*
+- * Revoke descriptors are accounted separately so we need to reserve
+- * space for commit block and normal transaction descriptor blocks.
+- */
+- return 1 + DIV_ROUND_UP(journal->j_max_transaction_buffers,
+- tags_per_block);
+-}
+-
+ /*
+ * jbd2_get_transaction: obtain a new transaction_t object.
+ *
+@@ -109,7 +87,7 @@ static void jbd2_get_transaction(journal_t *journal,
+ transaction->t_expires = jiffies + journal->j_commit_interval;
+ atomic_set(&transaction->t_updates, 0);
+ atomic_set(&transaction->t_outstanding_credits,
+- jbd2_descriptor_blocks_per_trans(journal) +
++ journal->j_transaction_overhead_buffers +
+ atomic_read(&journal->j_reserved_credits));
+ atomic_set(&transaction->t_outstanding_revokes, 0);
+ atomic_set(&transaction->t_handle_count, 0);
+@@ -213,6 +191,13 @@ static void sub_reserved_credits(journal_t *journal, int blocks)
+ wake_up(&journal->j_wait_reserved);
+ }
+
++/* Maximum number of blocks for user transaction payload */
++static int jbd2_max_user_trans_buffers(journal_t *journal)
++{
++ return journal->j_max_transaction_buffers -
++ journal->j_transaction_overhead_buffers;
++}
++
+ /*
+ * Wait until we can add credits for handle to the running transaction. Called
+ * with j_state_lock held for reading. Returns 0 if handle joined the running
+@@ -262,12 +247,12 @@ __must_hold(&journal->j_state_lock)
+ * big to fit this handle? Wait until reserved credits are freed.
+ */
+ if (atomic_read(&journal->j_reserved_credits) + total >
+- journal->j_max_transaction_buffers) {
++ jbd2_max_user_trans_buffers(journal)) {
+ read_unlock(&journal->j_state_lock);
+ jbd2_might_wait_for_commit(journal);
+ wait_event(journal->j_wait_reserved,
+ atomic_read(&journal->j_reserved_credits) + total <=
+- journal->j_max_transaction_buffers);
++ jbd2_max_user_trans_buffers(journal));
+ __acquire(&journal->j_state_lock); /* fake out sparse */
+ return 1;
+ }
+@@ -307,14 +292,14 @@ __must_hold(&journal->j_state_lock)
+
+ needed = atomic_add_return(rsv_blocks, &journal->j_reserved_credits);
+ /* We allow at most half of a transaction to be reserved */
+- if (needed > journal->j_max_transaction_buffers / 2) {
++ if (needed > jbd2_max_user_trans_buffers(journal) / 2) {
+ sub_reserved_credits(journal, rsv_blocks);
+ atomic_sub(total, &t->t_outstanding_credits);
+ read_unlock(&journal->j_state_lock);
+ jbd2_might_wait_for_commit(journal);
+ wait_event(journal->j_wait_reserved,
+ atomic_read(&journal->j_reserved_credits) + rsv_blocks
+- <= journal->j_max_transaction_buffers / 2);
++ <= jbd2_max_user_trans_buffers(journal) / 2);
+ __acquire(&journal->j_state_lock); /* fake out sparse */
+ return 1;
+ }
+@@ -344,12 +329,12 @@ static int start_this_handle(journal_t *journal, handle_t *handle,
+ * size and limit the number of total credits to not exceed maximum
+ * transaction size per operation.
+ */
+- if ((rsv_blocks > journal->j_max_transaction_buffers / 2) ||
+- (rsv_blocks + blocks > journal->j_max_transaction_buffers)) {
++ if (rsv_blocks > jbd2_max_user_trans_buffers(journal) / 2 ||
++ rsv_blocks + blocks > jbd2_max_user_trans_buffers(journal)) {
+ printk(KERN_ERR "JBD2: %s wants too many credits "
+ "credits:%d rsv_credits:%d max:%d\n",
+ current->comm, blocks, rsv_blocks,
+- journal->j_max_transaction_buffers);
++ jbd2_max_user_trans_buffers(journal));
+ WARN_ON(1);
+ return -ENOSPC;
+ }
+diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
+index 2ec35889ad24e..1407feccbc2d0 100644
+--- a/fs/jfs/jfs_imap.c
++++ b/fs/jfs/jfs_imap.c
+@@ -290,7 +290,7 @@ int diSync(struct inode *ipimap)
+ int diRead(struct inode *ip)
+ {
+ struct jfs_sb_info *sbi = JFS_SBI(ip->i_sb);
+- int iagno, ino, extno, rc;
++ int iagno, ino, extno, rc, agno;
+ struct inode *ipimap;
+ struct dinode *dp;
+ struct iag *iagp;
+@@ -339,8 +339,11 @@ int diRead(struct inode *ip)
+
+ /* get the ag for the iag */
+ agstart = le64_to_cpu(iagp->agstart);
++ agno = BLKTOAG(agstart, JFS_SBI(ip->i_sb));
+
+ release_metapage(mp);
++ if (agno >= MAXAG || agno < 0)
++ return -EIO;
+
+ rel_inode = (ino & (INOSPERPAGE - 1));
+ pageno = blkno >> sbi->l2nbperpage;
+diff --git a/fs/netfs/write_issue.c b/fs/netfs/write_issue.c
+index d7c971df88660..32bc88bee5d18 100644
+--- a/fs/netfs/write_issue.c
++++ b/fs/netfs/write_issue.c
+@@ -122,6 +122,7 @@ struct netfs_io_request *netfs_create_write_req(struct address_space *mapping,
+ wreq->io_streams[1].transferred = LONG_MAX;
+ if (fscache_resources_valid(&wreq->cache_resources)) {
+ wreq->io_streams[1].avail = true;
++ wreq->io_streams[1].active = true;
+ wreq->io_streams[1].prepare_write = wreq->cache_resources.ops->prepare_write_subreq;
+ wreq->io_streams[1].issue_write = wreq->cache_resources.ops->issue_write;
+ }
+diff --git a/fs/nfs/file.c b/fs/nfs/file.c
+index 6bd127e6683dc..445db17f1b6c1 100644
+--- a/fs/nfs/file.c
++++ b/fs/nfs/file.c
+@@ -434,7 +434,7 @@ static void nfs_invalidate_folio(struct folio *folio, size_t offset,
+ /* Cancel any unstarted writes on this page */
+ nfs_wb_folio_cancel(inode, folio);
+ folio_wait_private_2(folio); /* [DEPRECATED] */
+- trace_nfs_invalidate_folio(inode, folio);
++ trace_nfs_invalidate_folio(inode, folio_pos(folio) + offset, length);
+ }
+
+ /*
+@@ -502,7 +502,8 @@ static int nfs_launder_folio(struct folio *folio)
+
+ folio_wait_private_2(folio); /* [DEPRECATED] */
+ ret = nfs_wb_folio(inode, folio);
+- trace_nfs_launder_folio_done(inode, folio, ret);
++ trace_nfs_launder_folio_done(inode, folio_pos(folio),
++ folio_size(folio), ret);
+ return ret;
+ }
+
+diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
+index 84573df5cf5ae..83378f69b35ea 100644
+--- a/fs/nfs/nfs4client.c
++++ b/fs/nfs/nfs4client.c
+@@ -231,9 +231,8 @@ struct nfs_client *nfs4_alloc_client(const struct nfs_client_initdata *cl_init)
+ __set_bit(NFS_CS_INFINITE_SLOTS, &clp->cl_flags);
+ __set_bit(NFS_CS_DISCRTRY, &clp->cl_flags);
+ __set_bit(NFS_CS_NO_RETRANS_TIMEOUT, &clp->cl_flags);
+-
+- if (test_bit(NFS_CS_DS, &cl_init->init_flags))
+- __set_bit(NFS_CS_DS, &clp->cl_flags);
++ if (test_bit(NFS_CS_PNFS, &cl_init->init_flags))
++ __set_bit(NFS_CS_PNFS, &clp->cl_flags);
+ /*
+ * Set up the connection to the server before we add add to the
+ * global list.
+@@ -1013,7 +1012,6 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
+ if (mds_srv->flags & NFS_MOUNT_NORESVPORT)
+ __set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
+
+- __set_bit(NFS_CS_DS, &cl_init.init_flags);
+ __set_bit(NFS_CS_PNFS, &cl_init.init_flags);
+ cl_init.max_connect = NFS_MAX_TRANSPORTS;
+ /*
+diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
+index a691fa10b3e95..bff9d6600741e 100644
+--- a/fs/nfs/nfs4proc.c
++++ b/fs/nfs/nfs4proc.c
+@@ -8840,7 +8840,7 @@ nfs4_run_exchange_id(struct nfs_client *clp, const struct cred *cred,
+ #ifdef CONFIG_NFS_V4_1_MIGRATION
+ calldata->args.flags |= EXCHGID4_FLAG_SUPP_MOVED_MIGR;
+ #endif
+- if (test_bit(NFS_CS_DS, &clp->cl_flags))
++ if (test_bit(NFS_CS_PNFS, &clp->cl_flags))
+ calldata->args.flags |= EXCHGID4_FLAG_USE_PNFS_DS;
+ msg.rpc_argp = &calldata->args;
+ msg.rpc_resp = &calldata->res;
+diff --git a/fs/nfs/nfstrace.h b/fs/nfs/nfstrace.h
+index 1e710654af117..352fdaed40754 100644
+--- a/fs/nfs/nfstrace.h
++++ b/fs/nfs/nfstrace.h
+@@ -939,10 +939,11 @@ TRACE_EVENT(nfs_sillyrename_unlink,
+ DECLARE_EVENT_CLASS(nfs_folio_event,
+ TP_PROTO(
+ const struct inode *inode,
+- struct folio *folio
++ loff_t offset,
++ size_t count
+ ),
+
+- TP_ARGS(inode, folio),
++ TP_ARGS(inode, offset, count),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+@@ -950,7 +951,7 @@ DECLARE_EVENT_CLASS(nfs_folio_event,
+ __field(u64, fileid)
+ __field(u64, version)
+ __field(loff_t, offset)
+- __field(u32, count)
++ __field(size_t, count)
+ ),
+
+ TP_fast_assign(
+@@ -960,13 +961,13 @@ DECLARE_EVENT_CLASS(nfs_folio_event,
+ __entry->fileid = nfsi->fileid;
+ __entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+ __entry->version = inode_peek_iversion_raw(inode);
+- __entry->offset = folio_file_pos(folio);
+- __entry->count = nfs_folio_length(folio);
++ __entry->offset = offset,
++ __entry->count = count;
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
+- "offset=%lld count=%u",
++ "offset=%lld count=%zu",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle, __entry->version,
+@@ -978,18 +979,20 @@ DECLARE_EVENT_CLASS(nfs_folio_event,
+ DEFINE_EVENT(nfs_folio_event, name, \
+ TP_PROTO( \
+ const struct inode *inode, \
+- struct folio *folio \
++ loff_t offset, \
++ size_t count \
+ ), \
+- TP_ARGS(inode, folio))
++ TP_ARGS(inode, offset, count))
+
+ DECLARE_EVENT_CLASS(nfs_folio_event_done,
+ TP_PROTO(
+ const struct inode *inode,
+- struct folio *folio,
++ loff_t offset,
++ size_t count,
+ int ret
+ ),
+
+- TP_ARGS(inode, folio, ret),
++ TP_ARGS(inode, offset, count, ret),
+
+ TP_STRUCT__entry(
+ __field(dev_t, dev)
+@@ -998,7 +1001,7 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done,
+ __field(u64, fileid)
+ __field(u64, version)
+ __field(loff_t, offset)
+- __field(u32, count)
++ __field(size_t, count)
+ ),
+
+ TP_fast_assign(
+@@ -1008,14 +1011,14 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done,
+ __entry->fileid = nfsi->fileid;
+ __entry->fhandle = nfs_fhandle_hash(&nfsi->fh);
+ __entry->version = inode_peek_iversion_raw(inode);
+- __entry->offset = folio_file_pos(folio);
+- __entry->count = nfs_folio_length(folio);
++ __entry->offset = offset,
++ __entry->count = count,
+ __entry->ret = ret;
+ ),
+
+ TP_printk(
+ "fileid=%02x:%02x:%llu fhandle=0x%08x version=%llu "
+- "offset=%lld count=%u ret=%d",
++ "offset=%lld count=%zu ret=%d",
+ MAJOR(__entry->dev), MINOR(__entry->dev),
+ (unsigned long long)__entry->fileid,
+ __entry->fhandle, __entry->version,
+@@ -1027,10 +1030,11 @@ DECLARE_EVENT_CLASS(nfs_folio_event_done,
+ DEFINE_EVENT(nfs_folio_event_done, name, \
+ TP_PROTO( \
+ const struct inode *inode, \
+- struct folio *folio, \
++ loff_t offset, \
++ size_t count, \
+ int ret \
+ ), \
+- TP_ARGS(inode, folio, ret))
++ TP_ARGS(inode, offset, count, ret))
+
+ DEFINE_NFS_FOLIO_EVENT(nfs_aop_readpage);
+ DEFINE_NFS_FOLIO_EVENT_DONE(nfs_aop_readpage_done);
+diff --git a/fs/nfs/read.c b/fs/nfs/read.c
+index a142287d86f68..88e6a78d37fb3 100644
+--- a/fs/nfs/read.c
++++ b/fs/nfs/read.c
+@@ -332,13 +332,15 @@ int nfs_read_add_folio(struct nfs_pageio_descriptor *pgio,
+ int nfs_read_folio(struct file *file, struct folio *folio)
+ {
+ struct inode *inode = file_inode(file);
++ loff_t pos = folio_pos(folio);
++ size_t len = folio_size(folio);
+ struct nfs_pageio_descriptor pgio;
+ struct nfs_open_context *ctx;
+ int ret;
+
+- trace_nfs_aop_readpage(inode, folio);
++ trace_nfs_aop_readpage(inode, pos, len);
+ nfs_inc_stats(inode, NFSIOS_VFSREADPAGE);
+- task_io_account_read(folio_size(folio));
++ task_io_account_read(len);
+
+ /*
+ * Try to flush any pending writes to the file..
+@@ -381,7 +383,7 @@ int nfs_read_folio(struct file *file, struct folio *folio)
+ out_put:
+ put_nfs_open_context(ctx);
+ out:
+- trace_nfs_aop_readpage_done(inode, folio, ret);
++ trace_nfs_aop_readpage_done(inode, pos, len, ret);
+ return ret;
+ out_unlock:
+ folio_unlock(folio);
+diff --git a/fs/nfs/write.c b/fs/nfs/write.c
+index 2329cbb0e446b..75c1b3c7faead 100644
+--- a/fs/nfs/write.c
++++ b/fs/nfs/write.c
+@@ -2073,17 +2073,17 @@ int nfs_wb_folio_cancel(struct inode *inode, struct folio *folio)
+ */
+ int nfs_wb_folio(struct inode *inode, struct folio *folio)
+ {
+- loff_t range_start = folio_file_pos(folio);
+- loff_t range_end = range_start + (loff_t)folio_size(folio) - 1;
++ loff_t range_start = folio_pos(folio);
++ size_t len = folio_size(folio);
+ struct writeback_control wbc = {
+ .sync_mode = WB_SYNC_ALL,
+ .nr_to_write = 0,
+ .range_start = range_start,
+- .range_end = range_end,
++ .range_end = range_start + len - 1,
+ };
+ int ret;
+
+- trace_nfs_writeback_folio(inode, folio);
++ trace_nfs_writeback_folio(inode, range_start, len);
+
+ for (;;) {
+ folio_wait_writeback(folio);
+@@ -2101,7 +2101,7 @@ int nfs_wb_folio(struct inode *inode, struct folio *folio)
+ goto out_error;
+ }
+ out_error:
+- trace_nfs_writeback_folio_done(inode, folio, ret);
++ trace_nfs_writeback_folio_done(inode, range_start, len, ret);
+ return ret;
+ }
+
+diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
+index 272ab8d5c4d76..ec2ab6429e00b 100644
+--- a/fs/nfsd/Kconfig
++++ b/fs/nfsd/Kconfig
+@@ -162,7 +162,7 @@ config NFSD_V4_SECURITY_LABEL
+ config NFSD_LEGACY_CLIENT_TRACKING
+ bool "Support legacy NFSv4 client tracking methods (DEPRECATED)"
+ depends on NFSD_V4
+- default n
++ default y
+ help
+ The NFSv4 server needs to store a small amount of information on
+ stable storage in order to handle state recovery after reboot. Most
+diff --git a/fs/nfsd/filecache.c b/fs/nfsd/filecache.c
+index ad9083ca144ba..f4704f5d40867 100644
+--- a/fs/nfsd/filecache.c
++++ b/fs/nfsd/filecache.c
+@@ -664,7 +664,7 @@ static int
+ nfsd_file_lease_notifier_call(struct notifier_block *nb, unsigned long arg,
+ void *data)
+ {
+- struct file_lock *fl = data;
++ struct file_lease *fl = data;
+
+ /* Only close files for F_SETLEASE leases */
+ if (fl->c.flc_flags & FL_LEASE)
+diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
+index 46bd20fe5c0f4..2e39cf2e502a3 100644
+--- a/fs/nfsd/nfs4proc.c
++++ b/fs/nfsd/nfs4proc.c
+@@ -2269,7 +2269,7 @@ nfsd4_layoutget(struct svc_rqst *rqstp,
+ const struct nfsd4_layout_ops *ops;
+ struct nfs4_layout_stateid *ls;
+ __be32 nfserr;
+- int accmode = NFSD_MAY_READ_IF_EXEC;
++ int accmode = NFSD_MAY_READ_IF_EXEC | NFSD_MAY_OWNER_OVERRIDE;
+
+ switch (lgp->lg_seg.iomode) {
+ case IOMODE_READ:
+@@ -2359,7 +2359,8 @@ nfsd4_layoutcommit(struct svc_rqst *rqstp,
+ struct nfs4_layout_stateid *ls;
+ __be32 nfserr;
+
+- nfserr = fh_verify(rqstp, current_fh, 0, NFSD_MAY_WRITE);
++ nfserr = fh_verify(rqstp, current_fh, 0,
++ NFSD_MAY_WRITE | NFSD_MAY_OWNER_OVERRIDE);
+ if (nfserr)
+ goto out;
+
+diff --git a/fs/nfsd/nfs4recover.c b/fs/nfsd/nfs4recover.c
+index 2c060e0b16048..67d8673a9391c 100644
+--- a/fs/nfsd/nfs4recover.c
++++ b/fs/nfsd/nfs4recover.c
+@@ -2086,8 +2086,8 @@ nfsd4_client_tracking_init(struct net *net)
+ status = nn->client_tracking_ops->init(net);
+ out:
+ if (status) {
+- printk(KERN_WARNING "NFSD: Unable to initialize client "
+- "recovery tracking! (%d)\n", status);
++ pr_warn("NFSD: Unable to initialize client recovery tracking! (%d)\n", status);
++ pr_warn("NFSD: Is nfsdcld running? If not, enable CONFIG_NFSD_LEGACY_CLIENT_TRACKING.\n");
+ nn->client_tracking_ops = NULL;
+ }
+ return status;
+diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
+index 0131d83b912de..c034080c334b9 100644
+--- a/fs/nilfs2/btnode.c
++++ b/fs/nilfs2/btnode.c
+@@ -51,12 +51,21 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
+
+ bh = nilfs_grab_buffer(inode, btnc, blocknr, BIT(BH_NILFS_Node));
+ if (unlikely(!bh))
+- return NULL;
++ return ERR_PTR(-ENOMEM);
+
+ if (unlikely(buffer_mapped(bh) || buffer_uptodate(bh) ||
+ buffer_dirty(bh))) {
+- brelse(bh);
+- BUG();
++ /*
++ * The block buffer at the specified new address was already
++ * in use. This can happen if it is a virtual block number
++ * and has been reallocated due to corruption of the bitmap
++ * used to manage its allocation state (if not, the buffer
++ * clearing of an abandoned b-tree node is missing somewhere).
++ */
++ nilfs_error(inode->i_sb,
++ "state inconsistency probably due to duplicate use of b-tree node block address %llu (ino=%lu)",
++ (unsigned long long)blocknr, inode->i_ino);
++ goto failed;
+ }
+ memset(bh->b_data, 0, i_blocksize(inode));
+ bh->b_bdev = inode->i_sb->s_bdev;
+@@ -67,6 +76,12 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
+ folio_unlock(bh->b_folio);
+ folio_put(bh->b_folio);
+ return bh;
++
++failed:
++ folio_unlock(bh->b_folio);
++ folio_put(bh->b_folio);
++ brelse(bh);
++ return ERR_PTR(-EIO);
+ }
+
+ int nilfs_btnode_submit_block(struct address_space *btnc, __u64 blocknr,
+@@ -217,8 +232,8 @@ int nilfs_btnode_prepare_change_key(struct address_space *btnc,
+ }
+
+ nbh = nilfs_btnode_create_block(btnc, newkey);
+- if (!nbh)
+- return -ENOMEM;
++ if (IS_ERR(nbh))
++ return PTR_ERR(nbh);
+
+ BUG_ON(nbh == obh);
+ ctxt->newbh = nbh;
+diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
+index a139970e48041..862bdf23120e8 100644
+--- a/fs/nilfs2/btree.c
++++ b/fs/nilfs2/btree.c
+@@ -63,8 +63,8 @@ static int nilfs_btree_get_new_block(const struct nilfs_bmap *btree,
+ struct buffer_head *bh;
+
+ bh = nilfs_btnode_create_block(btnc, ptr);
+- if (!bh)
+- return -ENOMEM;
++ if (IS_ERR(bh))
++ return PTR_ERR(bh);
+
+ set_buffer_nilfs_volatile(bh);
+ *bhp = bh;
+diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
+index 6ea81f1d50944..d02fd92cdb432 100644
+--- a/fs/nilfs2/segment.c
++++ b/fs/nilfs2/segment.c
+@@ -136,7 +136,7 @@ static void nilfs_dispose_list(struct the_nilfs *, struct list_head *, int);
+
+ #define nilfs_cnt32_ge(a, b) \
+ (typecheck(__u32, a) && typecheck(__u32, b) && \
+- ((__s32)(a) - (__s32)(b) >= 0))
++ ((__s32)((a) - (b)) >= 0))
+
+ static int nilfs_prepare_segment_lock(struct super_block *sb,
+ struct nilfs_transaction_info *ti)
+diff --git a/fs/ntfs3/attrib.c b/fs/ntfs3/attrib.c
+index 8e6bcdf99770f..a810ef547501d 100644
+--- a/fs/ntfs3/attrib.c
++++ b/fs/ntfs3/attrib.c
+@@ -231,7 +231,7 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
+ struct ntfs_sb_info *sbi;
+ struct ATTRIB *attr_s;
+ struct MFT_REC *rec;
+- u32 used, asize, rsize, aoff, align;
++ u32 used, asize, rsize, aoff;
+ bool is_data;
+ CLST len, alen;
+ char *next;
+@@ -252,10 +252,13 @@ int attr_make_nonresident(struct ntfs_inode *ni, struct ATTRIB *attr,
+ rsize = le32_to_cpu(attr->res.data_size);
+ is_data = attr->type == ATTR_DATA && !attr->name_len;
+
+- align = sbi->cluster_size;
+- if (is_attr_compressed(attr))
+- align <<= COMPRESSION_UNIT;
+- len = (rsize + align - 1) >> sbi->cluster_bits;
++ /* len - how many clusters required to store 'rsize' bytes */
++ if (is_attr_compressed(attr)) {
++ u8 shift = sbi->cluster_bits + NTFS_LZNT_CUNIT;
++ len = ((rsize + (1u << shift) - 1) >> shift) << NTFS_LZNT_CUNIT;
++ } else {
++ len = bytes_to_cluster(sbi, rsize);
++ }
+
+ run_init(run);
+
+@@ -670,7 +673,8 @@ int attr_set_size(struct ntfs_inode *ni, enum ATTR_TYPE type,
+ goto undo_2;
+ }
+
+- if (!is_mft)
++ /* keep runs for $MFT::$ATTR_DATA and $MFT::$ATTR_BITMAP. */
++ if (ni->mi.rno != MFT_REC_MFT)
+ run_truncate_head(run, evcn + 1);
+
+ svcn = le64_to_cpu(attr->nres.svcn);
+@@ -972,6 +976,19 @@ int attr_data_get_block(struct ntfs_inode *ni, CLST vcn, CLST clen, CLST *lcn,
+ if (err)
+ goto out;
+
++ /* Check for compressed frame. */
++ err = attr_is_frame_compressed(ni, attr, vcn >> NTFS_LZNT_CUNIT, &hint);
++ if (err)
++ goto out;
++
++ if (hint) {
++ /* if frame is compressed - don't touch it. */
++ *lcn = COMPRESSED_LCN;
++ *len = hint;
++ err = -EOPNOTSUPP;
++ goto out;
++ }
++
+ if (!*len) {
+ if (run_lookup_entry(run, vcn, lcn, len, NULL)) {
+ if (*lcn != SPARSE_LCN || !new)
+@@ -1722,6 +1739,7 @@ int attr_allocate_frame(struct ntfs_inode *ni, CLST frame, size_t compr_size,
+
+ attr_b->nres.total_size = cpu_to_le64(total_size);
+ inode_set_bytes(&ni->vfs_inode, total_size);
++ ni->ni_flags |= NI_FLAG_UPDATE_PARENT;
+
+ mi_b->dirty = true;
+ mark_inode_dirty(&ni->vfs_inode);
+diff --git a/fs/ntfs3/bitmap.c b/fs/ntfs3/bitmap.c
+index c9eb01ccee51b..cf4fe21a50399 100644
+--- a/fs/ntfs3/bitmap.c
++++ b/fs/ntfs3/bitmap.c
+@@ -1382,7 +1382,7 @@ int wnd_extend(struct wnd_bitmap *wnd, size_t new_bits)
+
+ err = ntfs_vbo_to_lbo(sbi, &wnd->run, vbo, &lbo, &bytes);
+ if (err)
+- break;
++ return err;
+
+ bh = ntfs_bread(sb, lbo >> sb->s_blocksize_bits);
+ if (!bh)
+diff --git a/fs/ntfs3/dir.c b/fs/ntfs3/dir.c
+index 1937e8e612f87..858efe255f6f3 100644
+--- a/fs/ntfs3/dir.c
++++ b/fs/ntfs3/dir.c
+@@ -326,7 +326,8 @@ static inline int ntfs_filldir(struct ntfs_sb_info *sbi, struct ntfs_inode *ni,
+ * It does additional locks/reads just to get the type of name.
+ * Should we use additional mount option to enable branch below?
+ */
+- if ((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) &&
++ if (((fname->dup.fa & FILE_ATTRIBUTE_REPARSE_POINT) ||
++ fname->dup.ea_size) &&
+ ino != ni->mi.rno) {
+ struct inode *inode = ntfs_iget5(sbi->sb, &e->ref, NULL);
+ if (!IS_ERR_OR_NULL(inode)) {
+diff --git a/fs/ntfs3/file.c b/fs/ntfs3/file.c
+index 2f903b6ce1570..9ae202901f3c0 100644
+--- a/fs/ntfs3/file.c
++++ b/fs/ntfs3/file.c
+@@ -299,10 +299,7 @@ static int ntfs_file_mmap(struct file *file, struct vm_area_struct *vma)
+ }
+
+ if (ni->i_valid < to) {
+- if (!inode_trylock(inode)) {
+- err = -EAGAIN;
+- goto out;
+- }
++ inode_lock(inode);
+ err = ntfs_extend_initialized_size(file, ni,
+ ni->i_valid, to);
+ inode_unlock(inode);
+diff --git a/fs/ntfs3/frecord.c b/fs/ntfs3/frecord.c
+index 0008670939a4a..4822cfd6351c2 100644
+--- a/fs/ntfs3/frecord.c
++++ b/fs/ntfs3/frecord.c
+@@ -1501,7 +1501,7 @@ int ni_insert_nonresident(struct ntfs_inode *ni, enum ATTR_TYPE type,
+
+ if (is_ext) {
+ if (flags & ATTR_FLAG_COMPRESSED)
+- attr->nres.c_unit = COMPRESSION_UNIT;
++ attr->nres.c_unit = NTFS_LZNT_CUNIT;
+ attr->nres.total_size = attr->nres.alloc_size;
+ }
+
+diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
+index 40926bf392d28..fcb3e49911ad9 100644
+--- a/fs/ntfs3/fslog.c
++++ b/fs/ntfs3/fslog.c
+@@ -2996,7 +2996,7 @@ static struct ATTRIB *attr_create_nonres_log(struct ntfs_sb_info *sbi,
+ if (is_ext) {
+ attr->name_off = SIZEOF_NONRESIDENT_EX_LE;
+ if (is_attr_compressed(attr))
+- attr->nres.c_unit = COMPRESSION_UNIT;
++ attr->nres.c_unit = NTFS_LZNT_CUNIT;
+
+ attr->nres.run_off =
+ cpu_to_le16(SIZEOF_NONRESIDENT_EX + name_size);
+@@ -3922,6 +3922,9 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
+ goto out;
+ }
+
++ log->page_mask = log->page_size - 1;
++ log->page_bits = blksize_bits(log->page_size);
++
+ /* If the file size has shrunk then we won't mount it. */
+ if (log->l_size < le64_to_cpu(ra2->l_size)) {
+ err = -EINVAL;
+diff --git a/fs/ntfs3/index.c b/fs/ntfs3/index.c
+index d0f15bbf78f6c..9089c58a005ce 100644
+--- a/fs/ntfs3/index.c
++++ b/fs/ntfs3/index.c
+@@ -978,7 +978,7 @@ static struct indx_node *indx_new(struct ntfs_index *indx,
+ hdr->used =
+ cpu_to_le32(eo + sizeof(struct NTFS_DE) + sizeof(u64));
+ de_set_vbn_le(e, *sub_vbn);
+- hdr->flags = 1;
++ hdr->flags = NTFS_INDEX_HDR_HAS_SUBNODES;
+ } else {
+ e->size = cpu_to_le16(sizeof(struct NTFS_DE));
+ hdr->used = cpu_to_le32(eo + sizeof(struct NTFS_DE));
+@@ -1683,7 +1683,7 @@ static int indx_insert_into_root(struct ntfs_index *indx, struct ntfs_inode *ni,
+ e->size = cpu_to_le16(sizeof(struct NTFS_DE) + sizeof(u64));
+ e->flags = NTFS_IE_HAS_SUBNODES | NTFS_IE_LAST;
+
+- hdr->flags = 1;
++ hdr->flags = NTFS_INDEX_HDR_HAS_SUBNODES;
+ hdr->used = hdr->total =
+ cpu_to_le32(new_root_size - offsetof(struct INDEX_ROOT, ihdr));
+
+diff --git a/fs/ntfs3/inode.c b/fs/ntfs3/inode.c
+index 0f1664db94ad9..9559d72f86606 100644
+--- a/fs/ntfs3/inode.c
++++ b/fs/ntfs3/inode.c
+@@ -1508,7 +1508,7 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
+ attr->size = cpu_to_le32(SIZEOF_NONRESIDENT_EX + 8);
+ attr->name_off = SIZEOF_NONRESIDENT_EX_LE;
+ attr->flags = ATTR_FLAG_COMPRESSED;
+- attr->nres.c_unit = COMPRESSION_UNIT;
++ attr->nres.c_unit = NTFS_LZNT_CUNIT;
+ asize = SIZEOF_NONRESIDENT_EX + 8;
+ } else {
+ attr->size = cpu_to_le32(SIZEOF_NONRESIDENT + 8);
+@@ -1668,7 +1668,9 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
+ * The packed size of extended attribute is stored in direntry too.
+ * 'fname' here points to inside new_de.
+ */
+- ntfs_save_wsl_perm(inode, &fname->dup.ea_size);
++ err = ntfs_save_wsl_perm(inode, &fname->dup.ea_size);
++ if (err)
++ goto out6;
+
+ /*
+ * update ea_size in file_name attribute too.
+@@ -1712,6 +1714,12 @@ int ntfs_create_inode(struct mnt_idmap *idmap, struct inode *dir,
+ goto out2;
+
+ out6:
++ attr = ni_find_attr(ni, NULL, NULL, ATTR_EA, NULL, 0, NULL, NULL);
++ if (attr && attr->non_res) {
++ /* Delete ATTR_EA, if non-resident. */
++ attr_set_size(ni, ATTR_EA, NULL, 0, NULL, 0, NULL, false, NULL);
++ }
++
+ if (rp_inserted)
+ ntfs_remove_reparse(sbi, IO_REPARSE_TAG_SYMLINK, &new_de->ref);
+
+@@ -2133,5 +2141,6 @@ const struct address_space_operations ntfs_aops = {
+ const struct address_space_operations ntfs_aops_cmpr = {
+ .read_folio = ntfs_read_folio,
+ .readahead = ntfs_readahead,
++ .dirty_folio = block_dirty_folio,
+ };
+ // clang-format on
+diff --git a/fs/ntfs3/ntfs.h b/fs/ntfs3/ntfs.h
+index 3d6143c7abc03..e1889ad092304 100644
+--- a/fs/ntfs3/ntfs.h
++++ b/fs/ntfs3/ntfs.h
+@@ -82,9 +82,6 @@ typedef u32 CLST;
+ #define RESIDENT_LCN ((CLST)-2)
+ #define COMPRESSED_LCN ((CLST)-3)
+
+-#define COMPRESSION_UNIT 4
+-#define COMPRESS_MAX_CLUSTER 0x1000
+-
+ enum RECORD_NUM {
+ MFT_REC_MFT = 0,
+ MFT_REC_MIRR = 1,
+@@ -696,14 +693,15 @@ static inline bool de_has_vcn_ex(const struct NTFS_DE *e)
+ offsetof(struct ATTR_FILE_NAME, name) + \
+ NTFS_NAME_LEN * sizeof(short), 8)
+
++#define NTFS_INDEX_HDR_HAS_SUBNODES cpu_to_le32(1)
++
+ struct INDEX_HDR {
+ __le32 de_off; // 0x00: The offset from the start of this structure
+ // to the first NTFS_DE.
+ __le32 used; // 0x04: The size of this structure plus all
+ // entries (quad-word aligned).
+ __le32 total; // 0x08: The allocated size of for this structure plus all entries.
+- u8 flags; // 0x0C: 0x00 = Small directory, 0x01 = Large directory.
+- u8 res[3];
++ __le32 flags; // 0x0C: 0x00 = Small directory, 0x01 = Large directory.
+
+ //
+ // de_off + used <= total
+@@ -751,7 +749,7 @@ static inline struct NTFS_DE *hdr_next_de(const struct INDEX_HDR *hdr,
+
+ static inline bool hdr_has_subnode(const struct INDEX_HDR *hdr)
+ {
+- return hdr->flags & 1;
++ return hdr->flags & NTFS_INDEX_HDR_HAS_SUBNODES;
+ }
+
+ struct INDEX_BUFFER {
+@@ -771,7 +769,7 @@ static inline bool ib_is_empty(const struct INDEX_BUFFER *ib)
+
+ static inline bool ib_is_leaf(const struct INDEX_BUFFER *ib)
+ {
+- return !(ib->ihdr.flags & 1);
++ return !(ib->ihdr.flags & NTFS_INDEX_HDR_HAS_SUBNODES);
+ }
+
+ /* Index root structure ( 0x90 ). */
+diff --git a/fs/ntfs3/super.c b/fs/ntfs3/super.c
+index 27fbde2701b63..02b6f51ce6503 100644
+--- a/fs/ntfs3/super.c
++++ b/fs/ntfs3/super.c
+@@ -275,7 +275,7 @@ static const struct fs_parameter_spec ntfs_fs_parameters[] = {
+ fsparam_flag_no("acl", Opt_acl),
+ fsparam_string("iocharset", Opt_iocharset),
+ fsparam_flag_no("prealloc", Opt_prealloc),
+- fsparam_flag_no("nocase", Opt_nocase),
++ fsparam_flag_no("case", Opt_nocase),
+ {}
+ };
+ // clang-format on
+@@ -468,7 +468,7 @@ static int ntfs3_volinfo(struct seq_file *m, void *o)
+ struct super_block *sb = m->private;
+ struct ntfs_sb_info *sbi = sb->s_fs_info;
+
+- seq_printf(m, "ntfs%d.%d\n%u\n%zu\n\%zu\n%zu\n%s\n%s\n",
++ seq_printf(m, "ntfs%d.%d\n%u\n%zu\n%zu\n%zu\n%s\n%s\n",
+ sbi->volume.major_ver, sbi->volume.minor_ver,
+ sbi->cluster_size, sbi->used.bitmap.nbits,
+ sbi->mft.bitmap.nbits,
+diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
+index b1c2c0b821161..dd7b462387a00 100644
+--- a/fs/proc/proc_sysctl.c
++++ b/fs/proc/proc_sysctl.c
+@@ -476,12 +476,10 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
+ make_empty_dir_inode(inode);
+ }
+
++ inode->i_uid = GLOBAL_ROOT_UID;
++ inode->i_gid = GLOBAL_ROOT_GID;
+ if (root->set_ownership)
+ root->set_ownership(head, &inode->i_uid, &inode->i_gid);
+- else {
+- inode->i_uid = GLOBAL_ROOT_UID;
+- inode->i_gid = GLOBAL_ROOT_GID;
+- }
+
+ return inode;
+ }
+diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
+index 71e5039d940dc..a45f2da0ada0d 100644
+--- a/fs/proc/task_mmu.c
++++ b/fs/proc/task_mmu.c
+@@ -1418,7 +1418,6 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
+ {
+ u64 frame = 0, flags = 0;
+ struct page *page = NULL;
+- bool migration = false;
+
+ if (pte_present(pte)) {
+ if (pm->show_pfn)
+@@ -1450,7 +1449,6 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
+ (offset << MAX_SWAPFILES_SHIFT);
+ }
+ flags |= PM_SWAP;
+- migration = is_migration_entry(entry);
+ if (is_pfn_swap_entry(entry))
+ page = pfn_swap_entry_to_page(entry);
+ if (pte_marker_entry_uffd_wp(entry))
+@@ -1459,7 +1457,7 @@ static pagemap_entry_t pte_to_pagemap_entry(struct pagemapread *pm,
+
+ if (page && !PageAnon(page))
+ flags |= PM_FILE;
+- if (page && !migration && page_mapcount(page) == 1)
++ if (page && (flags & PM_PRESENT) && page_mapcount(page) == 1)
+ flags |= PM_MMAP_EXCLUSIVE;
+ if (vma->vm_flags & VM_SOFTDIRTY)
+ flags |= PM_SOFT_DIRTY;
+@@ -1476,10 +1474,10 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
+ pte_t *pte, *orig_pte;
+ int err = 0;
+ #ifdef CONFIG_TRANSPARENT_HUGEPAGE
+- bool migration = false;
+
+ ptl = pmd_trans_huge_lock(pmdp, vma);
+ if (ptl) {
++ unsigned int idx = (addr & ~PMD_MASK) >> PAGE_SHIFT;
+ u64 flags = 0, frame = 0;
+ pmd_t pmd = *pmdp;
+ struct page *page = NULL;
+@@ -1496,8 +1494,7 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
+ if (pmd_uffd_wp(pmd))
+ flags |= PM_UFFD_WP;
+ if (pm->show_pfn)
+- frame = pmd_pfn(pmd) +
+- ((addr & ~PMD_MASK) >> PAGE_SHIFT);
++ frame = pmd_pfn(pmd) + idx;
+ }
+ #ifdef CONFIG_ARCH_ENABLE_THP_MIGRATION
+ else if (is_swap_pmd(pmd)) {
+@@ -1506,11 +1503,9 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
+
+ if (pm->show_pfn) {
+ if (is_pfn_swap_entry(entry))
+- offset = swp_offset_pfn(entry);
++ offset = swp_offset_pfn(entry) + idx;
+ else
+- offset = swp_offset(entry);
+- offset = offset +
+- ((addr & ~PMD_MASK) >> PAGE_SHIFT);
++ offset = swp_offset(entry) + idx;
+ frame = swp_type(entry) |
+ (offset << MAX_SWAPFILES_SHIFT);
+ }
+@@ -1520,17 +1515,22 @@ static int pagemap_pmd_range(pmd_t *pmdp, unsigned long addr, unsigned long end,
+ if (pmd_swp_uffd_wp(pmd))
+ flags |= PM_UFFD_WP;
+ VM_BUG_ON(!is_pmd_migration_entry(pmd));
+- migration = is_migration_entry(entry);
+ page = pfn_swap_entry_to_page(entry);
+ }
+ #endif
+
+- if (page && !migration && page_mapcount(page) == 1)
+- flags |= PM_MMAP_EXCLUSIVE;
++ if (page && !PageAnon(page))
++ flags |= PM_FILE;
++
++ for (; addr != end; addr += PAGE_SIZE, idx++) {
++ unsigned long cur_flags = flags;
++ pagemap_entry_t pme;
+
+- for (; addr != end; addr += PAGE_SIZE) {
+- pagemap_entry_t pme = make_pme(frame, flags);
++ if (page && (flags & PM_PRESENT) &&
++ page_mapcount(page + idx) == 1)
++ cur_flags |= PM_MMAP_EXCLUSIVE;
+
++ pme = make_pme(frame, cur_flags);
+ err = add_to_pagemap(&pme, pm);
+ if (err)
+ break;
+diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
+index c92937bed1331..2c4b357d85e22 100644
+--- a/fs/smb/client/cifsfs.c
++++ b/fs/smb/client/cifsfs.c
+@@ -1894,12 +1894,12 @@ init_cifs(void)
+ WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+ if (!serverclose_wq) {
+ rc = -ENOMEM;
+- goto out_destroy_serverclose_wq;
++ goto out_destroy_deferredclose_wq;
+ }
+
+ rc = cifs_init_inodecache();
+ if (rc)
+- goto out_destroy_deferredclose_wq;
++ goto out_destroy_serverclose_wq;
+
+ rc = cifs_init_netfs();
+ if (rc)
+@@ -1967,6 +1967,8 @@ init_cifs(void)
+ cifs_destroy_netfs();
+ out_destroy_inodecache:
+ cifs_destroy_inodecache();
++out_destroy_serverclose_wq:
++ destroy_workqueue(serverclose_wq);
+ out_destroy_deferredclose_wq:
+ destroy_workqueue(deferredclose_wq);
+ out_destroy_cifsoplockd_wq:
+@@ -1977,8 +1979,6 @@ init_cifs(void)
+ destroy_workqueue(decrypt_wq);
+ out_destroy_cifsiod_wq:
+ destroy_workqueue(cifsiod_wq);
+-out_destroy_serverclose_wq:
+- destroy_workqueue(serverclose_wq);
+ out_clean_proc:
+ cifs_proc_clean();
+ return rc;
+diff --git a/fs/smb/client/connect.c b/fs/smb/client/connect.c
+index 7a16e12f5da87..d2307162a2de1 100644
+--- a/fs/smb/client/connect.c
++++ b/fs/smb/client/connect.c
+@@ -2614,6 +2614,13 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb3_fs_context *ctx)
+ cifs_dbg(VFS, "Server does not support mounting with posix SMB3.11 extensions\n");
+ rc = -EOPNOTSUPP;
+ goto out_fail;
++ } else if (ses->server->vals->protocol_id == SMB10_PROT_ID)
++ if (cap_unix(ses))
++ cifs_dbg(FYI, "Unix Extensions requested on SMB1 mount\n");
++ else {
++ cifs_dbg(VFS, "SMB1 Unix Extensions not supported by server\n");
++ rc = -EOPNOTSUPP;
++ goto out_fail;
+ } else {
+ cifs_dbg(VFS,
+ "Check vers= mount option. SMB3.11 disabled but required for POSIX extensions\n");
+@@ -3686,6 +3693,7 @@ int cifs_mount(struct cifs_sb_info *cifs_sb, struct smb3_fs_context *ctx)
+ }
+ #endif
+
++#ifdef CONFIG_CIFS_ALLOW_INSECURE_LEGACY
+ /*
+ * Issue a TREE_CONNECT request.
+ */
+@@ -3807,11 +3815,25 @@ CIFSTCon(const unsigned int xid, struct cifs_ses *ses,
+ else
+ tcon->Flags = 0;
+ cifs_dbg(FYI, "Tcon flags: 0x%x\n", tcon->Flags);
+- }
+
++ /*
++ * reset_cifs_unix_caps calls QFSInfo which requires
++ * need_reconnect to be false, but we would not need to call
++ * reset_caps if this were not a reconnect case so must check
++ * need_reconnect flag here. The caller will also clear
++ * need_reconnect when tcon was successful but needed to be
++ * cleared earlier in the case of unix extensions reconnect
++ */
++ if (tcon->need_reconnect && tcon->unix_ext) {
++ cifs_dbg(FYI, "resetting caps for %s\n", tcon->tree_name);
++ tcon->need_reconnect = false;
++ reset_cifs_unix_caps(xid, tcon, NULL, NULL);
++ }
++ }
+ cifs_buf_release(smb_buffer);
+ return rc;
+ }
++#endif /* CONFIG_CIFS_ALLOW_INSECURE_LEGACY */
+
+ static void delayed_free(struct rcu_head *p)
+ {
+diff --git a/fs/super.c b/fs/super.c
+index 095ba793e10cf..38d72a3cf6fcf 100644
+--- a/fs/super.c
++++ b/fs/super.c
+@@ -736,6 +736,17 @@ struct super_block *sget_fc(struct fs_context *fc,
+ struct user_namespace *user_ns = fc->global ? &init_user_ns : fc->user_ns;
+ int err;
+
++ /*
++ * Never allow s_user_ns != &init_user_ns when FS_USERNS_MOUNT is
++ * not set, as the filesystem is likely unprepared to handle it.
++ * This can happen when fsconfig() is called from init_user_ns with
++ * an fs_fd opened in another user namespace.
++ */
++ if (user_ns != &init_user_ns && !(fc->fs_type->fs_flags & FS_USERNS_MOUNT)) {
++ errorfc(fc, "VFS: Mounting from non-initial user namespace is not allowed");
++ return ERR_PTR(-EPERM);
++ }
++
+ retry:
+ spin_lock(&sb_lock);
+ if (test) {
+diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
+index ab3ffc355949d..558ad046972ad 100644
+--- a/fs/udf/balloc.c
++++ b/fs/udf/balloc.c
+@@ -64,8 +64,12 @@ static int read_block_bitmap(struct super_block *sb,
+ }
+
+ for (i = 0; i < count; i++)
+- if (udf_test_bit(i + off, bh->b_data))
++ if (udf_test_bit(i + off, bh->b_data)) {
++ bitmap->s_block_bitmap[bitmap_nr] =
++ ERR_PTR(-EFSCORRUPTED);
++ brelse(bh);
+ return -EFSCORRUPTED;
++ }
+ return 0;
+ }
+
+@@ -81,8 +85,15 @@ static int __load_block_bitmap(struct super_block *sb,
+ block_group, nr_groups);
+ }
+
+- if (bitmap->s_block_bitmap[block_group])
++ if (bitmap->s_block_bitmap[block_group]) {
++ /*
++ * The bitmap failed verification in the past. No point in
++ * trying again.
++ */
++ if (IS_ERR(bitmap->s_block_bitmap[block_group]))
++ return PTR_ERR(bitmap->s_block_bitmap[block_group]);
+ return block_group;
++ }
+
+ retval = read_block_bitmap(sb, bitmap, block_group, block_group);
+ if (retval < 0)
+diff --git a/fs/udf/file.c b/fs/udf/file.c
+index 97c59585208ca..3a4179de316b4 100644
+--- a/fs/udf/file.c
++++ b/fs/udf/file.c
+@@ -232,7 +232,9 @@ static int udf_setattr(struct mnt_idmap *idmap, struct dentry *dentry,
+
+ if ((attr->ia_valid & ATTR_SIZE) &&
+ attr->ia_size != i_size_read(inode)) {
++ filemap_invalidate_lock(inode->i_mapping);
+ error = udf_setsize(inode, attr->ia_size);
++ filemap_invalidate_unlock(inode->i_mapping);
+ if (error)
+ return error;
+ }
+diff --git a/fs/udf/inode.c b/fs/udf/inode.c
+index 2fb21c5ffccfe..08767bd21eb7f 100644
+--- a/fs/udf/inode.c
++++ b/fs/udf/inode.c
+@@ -1250,7 +1250,6 @@ int udf_setsize(struct inode *inode, loff_t newsize)
+ if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+ return -EPERM;
+
+- filemap_invalidate_lock(inode->i_mapping);
+ iinfo = UDF_I(inode);
+ if (newsize > inode->i_size) {
+ if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
+@@ -1263,11 +1262,11 @@ int udf_setsize(struct inode *inode, loff_t newsize)
+ }
+ err = udf_expand_file_adinicb(inode);
+ if (err)
+- goto out_unlock;
++ return err;
+ }
+ err = udf_extend_file(inode, newsize);
+ if (err)
+- goto out_unlock;
++ return err;
+ set_size:
+ truncate_setsize(inode, newsize);
+ } else {
+@@ -1285,14 +1284,14 @@ int udf_setsize(struct inode *inode, loff_t newsize)
+ err = block_truncate_page(inode->i_mapping, newsize,
+ udf_get_block);
+ if (err)
+- goto out_unlock;
++ return err;
+ truncate_setsize(inode, newsize);
+ down_write(&iinfo->i_data_sem);
+ udf_clear_extent_cache(inode);
+ err = udf_truncate_extents(inode);
+ up_write(&iinfo->i_data_sem);
+ if (err)
+- goto out_unlock;
++ return err;
+ }
+ update_time:
+ inode_set_mtime_to_ts(inode, inode_set_ctime_current(inode));
+@@ -1300,8 +1299,6 @@ int udf_setsize(struct inode *inode, loff_t newsize)
+ udf_sync_inode(inode);
+ else
+ mark_inode_dirty(inode);
+-out_unlock:
+- filemap_invalidate_unlock(inode->i_mapping);
+ return err;
+ }
+
+diff --git a/fs/udf/namei.c b/fs/udf/namei.c
+index 1308109fd42d9..78a603129dd58 100644
+--- a/fs/udf/namei.c
++++ b/fs/udf/namei.c
+@@ -876,8 +876,6 @@ static int udf_rename(struct mnt_idmap *idmap, struct inode *old_dir,
+ if (has_diriter) {
+ diriter.fi.icb.extLocation =
+ cpu_to_lelb(UDF_I(new_dir)->i_location);
+- udf_update_tag((char *)&diriter.fi,
+- udf_dir_entry_len(&diriter.fi));
+ udf_fiiter_write_fi(&diriter, NULL);
+ udf_fiiter_release(&diriter);
+ }
+diff --git a/fs/udf/super.c b/fs/udf/super.c
+index 9381a66c6ce58..92d4770539056 100644
+--- a/fs/udf/super.c
++++ b/fs/udf/super.c
+@@ -336,7 +336,8 @@ static void udf_sb_free_bitmap(struct udf_bitmap *bitmap)
+ int nr_groups = bitmap->s_nr_groups;
+
+ for (i = 0; i < nr_groups; i++)
+- brelse(bitmap->s_block_bitmap[i]);
++ if (!IS_ERR_OR_NULL(bitmap->s_block_bitmap[i]))
++ brelse(bitmap->s_block_bitmap[i]);
+
+ kvfree(bitmap);
+ }
+diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
+index 5703526d6ebf1..70bf1004076b2 100644
+--- a/include/asm-generic/vmlinux.lds.h
++++ b/include/asm-generic/vmlinux.lds.h
+@@ -103,7 +103,7 @@
+ #define DATA_MAIN .data .data.[0-9a-zA-Z_]* .data..L* .data..compoundliteral* .data.$__unnamed_* .data.$L*
+ #define SDATA_MAIN .sdata .sdata.[0-9a-zA-Z_]*
+ #define RODATA_MAIN .rodata .rodata.[0-9a-zA-Z_]* .rodata..L*
+-#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..compoundliteral*
++#define BSS_MAIN .bss .bss.[0-9a-zA-Z_]* .bss..L* .bss..compoundliteral*
+ #define SBSS_MAIN .sbss .sbss.[0-9a-zA-Z_]*
+ #else
+ #define TEXT_MAIN .text
+diff --git a/include/drm/drm_mipi_dsi.h b/include/drm/drm_mipi_dsi.h
+index 82b1cc434ea3f..e0f56564bf975 100644
+--- a/include/drm/drm_mipi_dsi.h
++++ b/include/drm/drm_mipi_dsi.h
+@@ -314,17 +314,17 @@ int mipi_dsi_dcs_get_display_brightness_large(struct mipi_dsi_device *dsi,
+ * @dsi: DSI peripheral device
+ * @seq: buffer containing the payload
+ */
+-#define mipi_dsi_generic_write_seq(dsi, seq...) \
+- do { \
+- static const u8 d[] = { seq }; \
+- struct device *dev = &dsi->dev; \
+- int ret; \
+- ret = mipi_dsi_generic_write(dsi, d, ARRAY_SIZE(d)); \
+- if (ret < 0) { \
+- dev_err_ratelimited(dev, "transmit data failed: %d\n", \
+- ret); \
+- return ret; \
+- } \
++#define mipi_dsi_generic_write_seq(dsi, seq...) \
++ do { \
++ static const u8 d[] = { seq }; \
++ struct device *dev = &dsi->dev; \
++ ssize_t ret; \
++ ret = mipi_dsi_generic_write(dsi, d, ARRAY_SIZE(d)); \
++ if (ret < 0) { \
++ dev_err_ratelimited(dev, "transmit data failed: %zd\n", \
++ ret); \
++ return ret; \
++ } \
+ } while (0)
+
+ /**
+@@ -333,18 +333,18 @@ int mipi_dsi_dcs_get_display_brightness_large(struct mipi_dsi_device *dsi,
+ * @cmd: Command
+ * @seq: buffer containing data to be transmitted
+ */
+-#define mipi_dsi_dcs_write_seq(dsi, cmd, seq...) \
+- do { \
+- static const u8 d[] = { cmd, seq }; \
+- struct device *dev = &dsi->dev; \
+- int ret; \
+- ret = mipi_dsi_dcs_write_buffer(dsi, d, ARRAY_SIZE(d)); \
+- if (ret < 0) { \
+- dev_err_ratelimited( \
+- dev, "sending command %#02x failed: %d\n", \
+- cmd, ret); \
+- return ret; \
+- } \
++#define mipi_dsi_dcs_write_seq(dsi, cmd, seq...) \
++ do { \
++ static const u8 d[] = { cmd, seq }; \
++ struct device *dev = &dsi->dev; \
++ ssize_t ret; \
++ ret = mipi_dsi_dcs_write_buffer(dsi, d, ARRAY_SIZE(d)); \
++ if (ret < 0) { \
++ dev_err_ratelimited( \
++ dev, "sending command %#02x failed: %zd\n", \
++ cmd, ret); \
++ return ret; \
++ } \
+ } while (0)
+
+ /**
+diff --git a/include/linux/alloc_tag.h b/include/linux/alloc_tag.h
+index abd24016a900e..8c61ccd161ba3 100644
+--- a/include/linux/alloc_tag.h
++++ b/include/linux/alloc_tag.h
+@@ -122,7 +122,7 @@ static inline void alloc_tag_add_check(union codetag_ref *ref, struct alloc_tag
+ "alloc_tag was not cleared (got tag for %s:%u)\n",
+ ref->ct->filename, ref->ct->lineno);
+
+- WARN_ONCE(!tag, "current->alloc_tag not set");
++ WARN_ONCE(!tag, "current->alloc_tag not set\n");
+ }
+
+ static inline void alloc_tag_sub_check(union codetag_ref *ref)
+diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
+index e4070fb02b110..ff2a6cdb1fa3f 100644
+--- a/include/linux/bpf_verifier.h
++++ b/include/linux/bpf_verifier.h
+@@ -846,7 +846,7 @@ static inline u32 type_flag(u32 type)
+ /* only use after check_attach_btf_id() */
+ static inline enum bpf_prog_type resolve_prog_type(const struct bpf_prog *prog)
+ {
+- return prog->type == BPF_PROG_TYPE_EXT ?
++ return (prog->type == BPF_PROG_TYPE_EXT && prog->aux->dst_prog) ?
+ prog->aux->dst_prog->type : prog->type;
+ }
+
+diff --git a/include/linux/firewire.h b/include/linux/firewire.h
+index 00abe0e5d602b..1cca14cf56527 100644
+--- a/include/linux/firewire.h
++++ b/include/linux/firewire.h
+@@ -462,9 +462,8 @@ struct fw_iso_packet {
+ /* rx: Sync bit, wait for matching sy */
+ u32 tag:2; /* tx: Tag in packet header */
+ u32 sy:4; /* tx: Sy in packet header */
+- u32 header_length:8; /* Length of immediate header */
+- /* tx: Top of 1394 isoch. data_block */
+- u32 header[] __counted_by(header_length);
++ u32 header_length:8; /* Size of immediate header */
++ u32 header[]; /* tx: Top of 1394 isoch. data_block */
+ };
+
+ #define FW_ISO_CONTEXT_TRANSMIT 0
+diff --git a/include/linux/huge_mm.h b/include/linux/huge_mm.h
+index 2aa986a5cd1b5..c73ad77fa33d3 100644
+--- a/include/linux/huge_mm.h
++++ b/include/linux/huge_mm.h
+@@ -72,14 +72,20 @@ extern struct kobj_attribute shmem_enabled_attr;
+ #define THP_ORDERS_ALL_ANON ((BIT(PMD_ORDER + 1) - 1) & ~(BIT(0) | BIT(1)))
+
+ /*
+- * Mask of all large folio orders supported for file THP.
++ * Mask of all large folio orders supported for file THP. Folios in a DAX
++ * file is never split and the MAX_PAGECACHE_ORDER limit does not apply to
++ * it.
+ */
+-#define THP_ORDERS_ALL_FILE (BIT(PMD_ORDER) | BIT(PUD_ORDER))
++#define THP_ORDERS_ALL_FILE_DAX \
++ (BIT(PMD_ORDER) | BIT(PUD_ORDER))
++#define THP_ORDERS_ALL_FILE_DEFAULT \
++ ((BIT(MAX_PAGECACHE_ORDER + 1) - 1) & ~BIT(0))
+
+ /*
+ * Mask of all large folio orders supported for THP.
+ */
+-#define THP_ORDERS_ALL (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE)
++#define THP_ORDERS_ALL \
++ (THP_ORDERS_ALL_ANON | THP_ORDERS_ALL_FILE_DAX | THP_ORDERS_ALL_FILE_DEFAULT)
+
+ #define TVA_SMAPS (1 << 0) /* Will be used for procfs */
+ #define TVA_IN_PF (1 << 1) /* Page fault handler */
+diff --git a/include/linux/hugetlb.h b/include/linux/hugetlb.h
+index 2b3c3a4047691..8120d1976188c 100644
+--- a/include/linux/hugetlb.h
++++ b/include/linux/hugetlb.h
+@@ -681,6 +681,7 @@ HPAGEFLAG(RawHwpUnreliable, raw_hwp_unreliable)
+ /* Defines one hugetlb page size */
+ struct hstate {
+ struct mutex resize_lock;
++ struct lock_class_key resize_key;
+ int next_nid_to_alloc;
+ int next_nid_to_free;
+ unsigned int order;
+diff --git a/include/linux/interrupt.h b/include/linux/interrupt.h
+index 5c9bdd3ffccc8..dac7466de5f35 100644
+--- a/include/linux/interrupt.h
++++ b/include/linux/interrupt.h
+@@ -168,7 +168,7 @@ static inline int __must_check
+ request_irq(unsigned int irq, irq_handler_t handler, unsigned long flags,
+ const char *name, void *dev)
+ {
+- return request_threaded_irq(irq, handler, NULL, flags, name, dev);
++ return request_threaded_irq(irq, handler, NULL, flags | IRQF_COND_ONESHOT, name, dev);
+ }
+
+ extern int __must_check
+diff --git a/include/linux/jbd2.h b/include/linux/jbd2.h
+index ab04c1c27fae3..b900c642210cd 100644
+--- a/include/linux/jbd2.h
++++ b/include/linux/jbd2.h
+@@ -1085,6 +1085,13 @@ struct journal_s
+ */
+ int j_revoke_records_per_block;
+
++ /**
++ * @j_transaction_overhead:
++ *
++ * Number of blocks each transaction needs for its own bookkeeping
++ */
++ int j_transaction_overhead_buffers;
++
+ /**
+ * @j_commit_interval:
+ *
+@@ -1660,11 +1667,6 @@ int jbd2_wait_inode_data(journal_t *journal, struct jbd2_inode *jinode);
+ int jbd2_fc_wait_bufs(journal_t *journal, int num_blks);
+ int jbd2_fc_release_bufs(journal_t *journal);
+
+-static inline int jbd2_journal_get_max_txn_bufs(journal_t *journal)
+-{
+- return (journal->j_total_len - journal->j_fc_wbufsize) / 4;
+-}
+-
+ /*
+ * is_journal_abort
+ *
+diff --git a/include/linux/lsm_hook_defs.h b/include/linux/lsm_hook_defs.h
+index 44488b1ab9a97..855db460e08bc 100644
+--- a/include/linux/lsm_hook_defs.h
++++ b/include/linux/lsm_hook_defs.h
+@@ -144,6 +144,7 @@ LSM_HOOK(int, 0, inode_setattr, struct mnt_idmap *idmap, struct dentry *dentry,
+ LSM_HOOK(void, LSM_RET_VOID, inode_post_setattr, struct mnt_idmap *idmap,
+ struct dentry *dentry, int ia_valid)
+ LSM_HOOK(int, 0, inode_getattr, const struct path *path)
++LSM_HOOK(int, 0, inode_xattr_skipcap, const char *name)
+ LSM_HOOK(int, 0, inode_setxattr, struct mnt_idmap *idmap,
+ struct dentry *dentry, const char *name, const void *value,
+ size_t size, int flags)
+diff --git a/include/linux/mlx5/qp.h b/include/linux/mlx5/qp.h
+index f0e55bf3ec8b5..ad1ce650146cb 100644
+--- a/include/linux/mlx5/qp.h
++++ b/include/linux/mlx5/qp.h
+@@ -576,9 +576,12 @@ static inline const char *mlx5_qp_state_str(int state)
+
+ static inline int mlx5_get_qp_default_ts(struct mlx5_core_dev *dev)
+ {
+- return !MLX5_CAP_ROCE(dev, qp_ts_format) ?
+- MLX5_TIMESTAMP_FORMAT_FREE_RUNNING :
+- MLX5_TIMESTAMP_FORMAT_DEFAULT;
++ u8 supported_ts_cap = mlx5_get_roce_state(dev) ?
++ MLX5_CAP_ROCE(dev, qp_ts_format) :
++ MLX5_CAP_GEN(dev, sq_ts_format);
++
++ return supported_ts_cap ? MLX5_TIMESTAMP_FORMAT_DEFAULT :
++ MLX5_TIMESTAMP_FORMAT_FREE_RUNNING;
+ }
+
+ #endif /* MLX5_QP_H */
+diff --git a/include/linux/mm.h b/include/linux/mm.h
+index eb7c96d24ac02..b58bad248eefd 100644
+--- a/include/linux/mm.h
++++ b/include/linux/mm.h
+@@ -3177,21 +3177,7 @@ extern void reserve_bootmem_region(phys_addr_t start,
+ phys_addr_t end, int nid);
+
+ /* Free the reserved page into the buddy system, so it gets managed. */
+-static inline void free_reserved_page(struct page *page)
+-{
+- if (mem_alloc_profiling_enabled()) {
+- union codetag_ref *ref = get_page_tag_ref(page);
+-
+- if (ref) {
+- set_codetag_empty(ref);
+- put_page_tag_ref(ref);
+- }
+- }
+- ClearPageReserved(page);
+- init_page_count(page);
+- __free_page(page);
+- adjust_managed_page_count(page, 1);
+-}
++void free_reserved_page(struct page *page);
+ #define free_highmem_page(page) free_reserved_page(page)
+
+ static inline void mark_page_reserved(struct page *page)
+diff --git a/include/linux/objagg.h b/include/linux/objagg.h
+index 78021777df462..6df5b887dc547 100644
+--- a/include/linux/objagg.h
++++ b/include/linux/objagg.h
+@@ -8,7 +8,6 @@ struct objagg_ops {
+ size_t obj_size;
+ bool (*delta_check)(void *priv, const void *parent_obj,
+ const void *obj);
+- int (*hints_obj_cmp)(const void *obj1, const void *obj2);
+ void * (*delta_create)(void *priv, void *parent_obj, void *obj);
+ void (*delta_destroy)(void *priv, void *delta_priv);
+ void * (*root_create)(void *priv, void *obj, unsigned int root_id);
+diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
+index a5304ae8c654f..393fb13733b02 100644
+--- a/include/linux/perf_event.h
++++ b/include/linux/perf_event.h
+@@ -786,6 +786,7 @@ struct perf_event {
+ struct irq_work pending_irq;
+ struct callback_head pending_task;
+ unsigned int pending_work;
++ struct rcuwait pending_work_wait;
+
+ atomic_t event_limit;
+
+diff --git a/include/linux/pgalloc_tag.h b/include/linux/pgalloc_tag.h
+index 9cacadbd61f8c..18cd0c0c73d93 100644
+--- a/include/linux/pgalloc_tag.h
++++ b/include/linux/pgalloc_tag.h
+@@ -15,7 +15,7 @@ extern struct page_ext_operations page_alloc_tagging_ops;
+
+ static inline union codetag_ref *codetag_ref_from_page_ext(struct page_ext *page_ext)
+ {
+- return (void *)page_ext + page_alloc_tagging_ops.offset;
++ return (union codetag_ref *)page_ext_data(page_ext, &page_alloc_tagging_ops);
+ }
+
+ static inline struct page_ext *page_ext_from_codetag_ref(union codetag_ref *ref)
+@@ -71,6 +71,7 @@ static inline void pgalloc_tag_sub(struct page *page, unsigned int nr)
+ static inline void pgalloc_tag_split(struct page *page, unsigned int nr)
+ {
+ int i;
++ struct page_ext *first_page_ext;
+ struct page_ext *page_ext;
+ union codetag_ref *ref;
+ struct alloc_tag *tag;
+@@ -78,7 +79,7 @@ static inline void pgalloc_tag_split(struct page *page, unsigned int nr)
+ if (!mem_alloc_profiling_enabled())
+ return;
+
+- page_ext = page_ext_get(page);
++ first_page_ext = page_ext = page_ext_get(page);
+ if (unlikely(!page_ext))
+ return;
+
+@@ -94,7 +95,7 @@ static inline void pgalloc_tag_split(struct page *page, unsigned int nr)
+ page_ext = page_ext_next(page_ext);
+ }
+ out:
+- page_ext_put(page_ext);
++ page_ext_put(first_page_ext);
+ }
+
+ static inline struct alloc_tag *pgalloc_tag_get(struct page *page)
+diff --git a/include/linux/preempt.h b/include/linux/preempt.h
+index 7233e9cf1bab6..ce76f1a457225 100644
+--- a/include/linux/preempt.h
++++ b/include/linux/preempt.h
+@@ -481,4 +481,45 @@ DEFINE_LOCK_GUARD_0(preempt, preempt_disable(), preempt_enable())
+ DEFINE_LOCK_GUARD_0(preempt_notrace, preempt_disable_notrace(), preempt_enable_notrace())
+ DEFINE_LOCK_GUARD_0(migrate, migrate_disable(), migrate_enable())
+
++#ifdef CONFIG_PREEMPT_DYNAMIC
++
++extern bool preempt_model_none(void);
++extern bool preempt_model_voluntary(void);
++extern bool preempt_model_full(void);
++
++#else
++
++static inline bool preempt_model_none(void)
++{
++ return IS_ENABLED(CONFIG_PREEMPT_NONE);
++}
++static inline bool preempt_model_voluntary(void)
++{
++ return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
++}
++static inline bool preempt_model_full(void)
++{
++ return IS_ENABLED(CONFIG_PREEMPT);
++}
++
++#endif
++
++static inline bool preempt_model_rt(void)
++{
++ return IS_ENABLED(CONFIG_PREEMPT_RT);
++}
++
++/*
++ * Does the preemption model allow non-cooperative preemption?
++ *
++ * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with
++ * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the
++ * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the
++ * PREEMPT_NONE model.
++ */
++static inline bool preempt_model_preemptible(void)
++{
++ return preempt_model_full() || preempt_model_rt();
++}
++
+ #endif /* __LINUX_PREEMPT_H */
+diff --git a/include/linux/sbitmap.h b/include/linux/sbitmap.h
+index d662cf136021d..c09cdcc99471e 100644
+--- a/include/linux/sbitmap.h
++++ b/include/linux/sbitmap.h
+@@ -36,6 +36,11 @@ struct sbitmap_word {
+ * @cleared: word holding cleared bits
+ */
+ unsigned long cleared ____cacheline_aligned_in_smp;
++
++ /**
++ * @swap_lock: serializes simultaneous updates of ->word and ->cleared
++ */
++ spinlock_t swap_lock;
+ } ____cacheline_aligned_in_smp;
+
+ /**
+diff --git a/include/linux/sched.h b/include/linux/sched.h
+index a5f4b48fca184..76214d7c819de 100644
+--- a/include/linux/sched.h
++++ b/include/linux/sched.h
+@@ -2064,47 +2064,6 @@ extern int __cond_resched_rwlock_write(rwlock_t *lock);
+ __cond_resched_rwlock_write(lock); \
+ })
+
+-#ifdef CONFIG_PREEMPT_DYNAMIC
+-
+-extern bool preempt_model_none(void);
+-extern bool preempt_model_voluntary(void);
+-extern bool preempt_model_full(void);
+-
+-#else
+-
+-static inline bool preempt_model_none(void)
+-{
+- return IS_ENABLED(CONFIG_PREEMPT_NONE);
+-}
+-static inline bool preempt_model_voluntary(void)
+-{
+- return IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY);
+-}
+-static inline bool preempt_model_full(void)
+-{
+- return IS_ENABLED(CONFIG_PREEMPT);
+-}
+-
+-#endif
+-
+-static inline bool preempt_model_rt(void)
+-{
+- return IS_ENABLED(CONFIG_PREEMPT_RT);
+-}
+-
+-/*
+- * Does the preemption model allow non-cooperative preemption?
+- *
+- * For !CONFIG_PREEMPT_DYNAMIC kernels this is an exact match with
+- * CONFIG_PREEMPTION; for CONFIG_PREEMPT_DYNAMIC this doesn't work as the
+- * kernel is *built* with CONFIG_PREEMPTION=y but may run with e.g. the
+- * PREEMPT_NONE model.
+- */
+-static inline bool preempt_model_preemptible(void)
+-{
+- return preempt_model_full() || preempt_model_rt();
+-}
+-
+ static __always_inline bool need_resched(void)
+ {
+ return unlikely(tif_need_resched());
+diff --git a/include/linux/screen_info.h b/include/linux/screen_info.h
+index 75303c126285a..6a4a3cec4638b 100644
+--- a/include/linux/screen_info.h
++++ b/include/linux/screen_info.h
+@@ -49,6 +49,16 @@ static inline u64 __screen_info_lfb_size(const struct screen_info *si, unsigned
+ return lfb_size;
+ }
+
++static inline bool __screen_info_vbe_mode_nonvga(const struct screen_info *si)
++{
++ /*
++ * VESA modes typically run on VGA hardware. Set bit 5 signals that this
++ * is not the case. Drivers can then not make use of VGA resources. See
++ * Sec 4.4 of the VBE 2.0 spec.
++ */
++ return si->vesa_attributes & BIT(5);
++}
++
+ static inline unsigned int __screen_info_video_type(unsigned int type)
+ {
+ switch (type) {
+diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
+index 3fcd20de6ca88..63dd8cf3c3c2b 100644
+--- a/include/linux/spinlock.h
++++ b/include/linux/spinlock.h
+@@ -462,11 +462,10 @@ static __always_inline int spin_is_contended(spinlock_t *lock)
+ */
+ static inline int spin_needbreak(spinlock_t *lock)
+ {
+-#ifdef CONFIG_PREEMPTION
++ if (!preempt_model_preemptible())
++ return 0;
++
+ return spin_is_contended(lock);
+-#else
+- return 0;
+-#endif
+ }
+
+ /*
+@@ -479,11 +478,10 @@ static inline int spin_needbreak(spinlock_t *lock)
+ */
+ static inline int rwlock_needbreak(rwlock_t *lock)
+ {
+-#ifdef CONFIG_PREEMPTION
++ if (!preempt_model_preemptible())
++ return 0;
++
+ return rwlock_is_contended(lock);
+-#else
+- return 0;
+-#endif
+ }
+
+ /*
+diff --git a/include/linux/task_work.h b/include/linux/task_work.h
+index 795ef5a684294..26b8a47f41fca 100644
+--- a/include/linux/task_work.h
++++ b/include/linux/task_work.h
+@@ -30,7 +30,8 @@ int task_work_add(struct task_struct *task, struct callback_head *twork,
+
+ struct callback_head *task_work_cancel_match(struct task_struct *task,
+ bool (*match)(struct callback_head *, void *data), void *data);
+-struct callback_head *task_work_cancel(struct task_struct *, task_work_func_t);
++struct callback_head *task_work_cancel_func(struct task_struct *, task_work_func_t);
++bool task_work_cancel(struct task_struct *task, struct callback_head *cb);
+ void task_work_run(void);
+
+ static inline void exit_task_work(struct task_struct *task)
+diff --git a/include/linux/virtio_net.h b/include/linux/virtio_net.h
+index 4dfa9b69ca8d9..d1d7825318c32 100644
+--- a/include/linux/virtio_net.h
++++ b/include/linux/virtio_net.h
+@@ -56,6 +56,7 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+ unsigned int thlen = 0;
+ unsigned int p_off = 0;
+ unsigned int ip_proto;
++ u64 ret, remainder, gso_size;
+
+ if (hdr->gso_type != VIRTIO_NET_HDR_GSO_NONE) {
+ switch (hdr->gso_type & ~VIRTIO_NET_HDR_GSO_ECN) {
+@@ -98,6 +99,16 @@ static inline int virtio_net_hdr_to_skb(struct sk_buff *skb,
+ u32 off = __virtio16_to_cpu(little_endian, hdr->csum_offset);
+ u32 needed = start + max_t(u32, thlen, off + sizeof(__sum16));
+
++ if (hdr->gso_size) {
++ gso_size = __virtio16_to_cpu(little_endian, hdr->gso_size);
++ ret = div64_u64_rem(skb->len, gso_size, &remainder);
++ if (!(ret && (hdr->gso_size > needed) &&
++ ((remainder > needed) || (remainder == 0)))) {
++ return -EINVAL;
++ }
++ skb_shinfo(skb)->tx_flags |= SKBFL_SHARED_FRAG;
++ }
++
+ if (!pskb_may_pull(skb, needed))
+ return -EINVAL;
+
+diff --git a/include/net/bluetooth/hci_core.h b/include/net/bluetooth/hci_core.h
+index c43716edf2056..b15f51ae3bfd9 100644
+--- a/include/net/bluetooth/hci_core.h
++++ b/include/net/bluetooth/hci_core.h
+@@ -91,8 +91,6 @@ struct discovery_state {
+ s8 rssi;
+ u16 uuid_count;
+ u8 (*uuids)[16];
+- unsigned long scan_start;
+- unsigned long scan_duration;
+ unsigned long name_resolve_timeout;
+ };
+
+@@ -890,8 +888,6 @@ static inline void hci_discovery_filter_clear(struct hci_dev *hdev)
+ hdev->discovery.uuid_count = 0;
+ kfree(hdev->discovery.uuids);
+ hdev->discovery.uuids = NULL;
+- hdev->discovery.scan_start = 0;
+- hdev->discovery.scan_duration = 0;
+ }
+
+ bool hci_discovery_active(struct hci_dev *hdev);
+diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h
+index a18ed24fed948..6dbdf60b342f6 100644
+--- a/include/net/ip6_route.h
++++ b/include/net/ip6_route.h
+@@ -127,18 +127,26 @@ void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args,
+
+ static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i,
+ const struct in6_addr *daddr,
+- unsigned int prefs,
++ unsigned int prefs, int l3mdev_index,
+ struct in6_addr *saddr)
+ {
++ struct net_device *l3mdev;
++ struct net_device *dev;
++ bool same_vrf;
+ int err = 0;
+
+- if (f6i && f6i->fib6_prefsrc.plen) {
++ rcu_read_lock();
++
++ l3mdev = dev_get_by_index_rcu(net, l3mdev_index);
++ if (!f6i || !f6i->fib6_prefsrc.plen || l3mdev)
++ dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
++ same_vrf = !l3mdev || l3mdev_master_dev_rcu(dev) == l3mdev;
++ if (f6i && f6i->fib6_prefsrc.plen && same_vrf)
+ *saddr = f6i->fib6_prefsrc.addr;
+- } else {
+- struct net_device *dev = f6i ? fib6_info_nh_dev(f6i) : NULL;
++ else
++ err = ipv6_dev_get_saddr(net, same_vrf ? dev : l3mdev, daddr, prefs, saddr);
+
+- err = ipv6_dev_get_saddr(net, dev, daddr, prefs, saddr);
+- }
++ rcu_read_unlock();
+
+ return err;
+ }
+diff --git a/include/net/ip_fib.h b/include/net/ip_fib.h
+index 9b2f69ba5e498..c29639b4323f3 100644
+--- a/include/net/ip_fib.h
++++ b/include/net/ip_fib.h
+@@ -173,6 +173,7 @@ struct fib_result {
+ unsigned char type;
+ unsigned char scope;
+ u32 tclassid;
++ dscp_t dscp;
+ struct fib_nh_common *nhc;
+ struct fib_info *fi;
+ struct fib_table *table;
+diff --git a/include/net/mana/mana.h b/include/net/mana/mana.h
+index 561f6719fb4ec..f207a6e1042ae 100644
+--- a/include/net/mana/mana.h
++++ b/include/net/mana/mana.h
+@@ -796,4 +796,6 @@ void mana_destroy_wq_obj(struct mana_port_context *apc, u32 wq_type,
+ int mana_cfg_vport(struct mana_port_context *apc, u32 protection_dom_id,
+ u32 doorbell_pg_id);
+ void mana_uncfg_vport(struct mana_port_context *apc);
++
++struct net_device *mana_get_primary_netdev_rcu(struct mana_context *ac, u32 port_index);
+ #endif /* _MANA_H */
+diff --git a/include/net/tcp.h b/include/net/tcp.h
+index 060e95b331a28..32815a40dea16 100644
+--- a/include/net/tcp.h
++++ b/include/net/tcp.h
+@@ -677,6 +677,7 @@ void tcp_skb_collapse_tstamp(struct sk_buff *skb,
+ /* tcp_input.c */
+ void tcp_rearm_rto(struct sock *sk);
+ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req);
++void tcp_done_with_error(struct sock *sk, int err);
+ void tcp_reset(struct sock *sk, struct sk_buff *skb);
+ void tcp_fin(struct sock *sk);
+ void tcp_check_space(struct sock *sk);
+diff --git a/include/net/xfrm.h b/include/net/xfrm.h
+index 77ebf5bcf0b90..7d4c2235252c7 100644
+--- a/include/net/xfrm.h
++++ b/include/net/xfrm.h
+@@ -178,7 +178,10 @@ struct xfrm_state {
+ struct hlist_node gclist;
+ struct hlist_node bydst;
+ };
+- struct hlist_node bysrc;
++ union {
++ struct hlist_node dev_gclist;
++ struct hlist_node bysrc;
++ };
+ struct hlist_node byspi;
+ struct hlist_node byseq;
+
+@@ -1588,7 +1591,7 @@ void xfrm_state_update_stats(struct net *net);
+ static inline void xfrm_dev_state_update_stats(struct xfrm_state *x)
+ {
+ struct xfrm_dev_offload *xdo = &x->xso;
+- struct net_device *dev = xdo->dev;
++ struct net_device *dev = READ_ONCE(xdo->dev);
+
+ if (dev && dev->xfrmdev_ops &&
+ dev->xfrmdev_ops->xdo_dev_state_update_stats)
+@@ -1946,13 +1949,16 @@ int xfrm_dev_policy_add(struct net *net, struct xfrm_policy *xp,
+ struct xfrm_user_offload *xuo, u8 dir,
+ struct netlink_ext_ack *extack);
+ bool xfrm_dev_offload_ok(struct sk_buff *skb, struct xfrm_state *x);
++void xfrm_dev_state_delete(struct xfrm_state *x);
++void xfrm_dev_state_free(struct xfrm_state *x);
+
+ static inline void xfrm_dev_state_advance_esn(struct xfrm_state *x)
+ {
+ struct xfrm_dev_offload *xso = &x->xso;
++ struct net_device *dev = READ_ONCE(xso->dev);
+
+- if (xso->dev && xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn)
+- xso->dev->xfrmdev_ops->xdo_dev_state_advance_esn(x);
++ if (dev && dev->xfrmdev_ops->xdo_dev_state_advance_esn)
++ dev->xfrmdev_ops->xdo_dev_state_advance_esn(x);
+ }
+
+ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
+@@ -1973,28 +1979,6 @@ static inline bool xfrm_dst_offload_ok(struct dst_entry *dst)
+ return false;
+ }
+
+-static inline void xfrm_dev_state_delete(struct xfrm_state *x)
+-{
+- struct xfrm_dev_offload *xso = &x->xso;
+-
+- if (xso->dev)
+- xso->dev->xfrmdev_ops->xdo_dev_state_delete(x);
+-}
+-
+-static inline void xfrm_dev_state_free(struct xfrm_state *x)
+-{
+- struct xfrm_dev_offload *xso = &x->xso;
+- struct net_device *dev = xso->dev;
+-
+- if (dev && dev->xfrmdev_ops) {
+- if (dev->xfrmdev_ops->xdo_dev_state_free)
+- dev->xfrmdev_ops->xdo_dev_state_free(x);
+- xso->dev = NULL;
+- xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
+- netdev_put(dev, &xso->dev_tracker);
+- }
+-}
+-
+ static inline void xfrm_dev_policy_delete(struct xfrm_policy *x)
+ {
+ struct xfrm_dev_offload *xdo = &x->xdo;
+diff --git a/include/sound/tas2781-dsp.h b/include/sound/tas2781-dsp.h
+index 7fba7ea26a4b0..3cda9da14f6d1 100644
+--- a/include/sound/tas2781-dsp.h
++++ b/include/sound/tas2781-dsp.h
+@@ -117,10 +117,17 @@ struct tasdevice_fw {
+ struct device *dev;
+ };
+
+-enum tasdevice_dsp_fw_state {
+- TASDEVICE_DSP_FW_NONE = 0,
++enum tasdevice_fw_state {
++ /* Driver in startup mode, not load any firmware. */
+ TASDEVICE_DSP_FW_PENDING,
++ /* DSP firmware in the system, but parsing error. */
+ TASDEVICE_DSP_FW_FAIL,
++ /*
++ * Only RCA (Reconfigurable Architecture) firmware load
++ * successfully.
++ */
++ TASDEVICE_RCA_FW_OK,
++ /* Both RCA and DSP firmware load successfully. */
+ TASDEVICE_DSP_FW_ALL_OK,
+ };
+
+diff --git a/include/trace/events/rpcgss.h b/include/trace/events/rpcgss.h
+index 7f0c1ceae726b..b0b6300a0cabd 100644
+--- a/include/trace/events/rpcgss.h
++++ b/include/trace/events/rpcgss.h
+@@ -54,7 +54,7 @@ TRACE_DEFINE_ENUM(GSS_S_UNSEQ_TOKEN);
+ TRACE_DEFINE_ENUM(GSS_S_GAP_TOKEN);
+
+ #define show_gss_status(x) \
+- __print_flags(x, "|", \
++ __print_symbolic(x, \
+ { GSS_S_BAD_MECH, "GSS_S_BAD_MECH" }, \
+ { GSS_S_BAD_NAME, "GSS_S_BAD_NAME" }, \
+ { GSS_S_BAD_NAMETYPE, "GSS_S_BAD_NAMETYPE" }, \
+diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
+index 1446c3bae5159..d425b83181df9 100644
+--- a/include/uapi/drm/xe_drm.h
++++ b/include/uapi/drm/xe_drm.h
+@@ -776,7 +776,13 @@ struct drm_xe_gem_create {
+ #define DRM_XE_GEM_CPU_CACHING_WC 2
+ /**
+ * @cpu_caching: The CPU caching mode to select for this object. If
+- * mmaping the object the mode selected here will also be used.
++ * mmaping the object the mode selected here will also be used. The
++ * exception is when mapping system memory (including data evicted
++ * to system) on discrete GPUs. The caching mode selected will
++ * then be overridden to DRM_XE_GEM_CPU_CACHING_WB, and coherency
++ * between GPU- and CPU is guaranteed. The caching mode of
++ * existing CPU-mappings will be updated transparently to
++ * user-space clients.
+ */
+ __u16 cpu_caching;
+ /** @pad: MBZ */
+diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h
+index d316984104107..42ec5ddaab8dc 100644
+--- a/include/uapi/linux/if_xdp.h
++++ b/include/uapi/linux/if_xdp.h
+@@ -41,6 +41,10 @@
+ */
+ #define XDP_UMEM_TX_SW_CSUM (1 << 1)
+
++/* Request to reserve tx_metadata_len bytes of per-chunk metadata.
++ */
++#define XDP_UMEM_TX_METADATA_LEN (1 << 2)
++
+ struct sockaddr_xdp {
+ __u16 sxdp_family;
+ __u16 sxdp_flags;
+diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h
+index aa4094ca2444f..639894ed1b973 100644
+--- a/include/uapi/linux/netfilter/nf_tables.h
++++ b/include/uapi/linux/netfilter/nf_tables.h
+@@ -1376,7 +1376,7 @@ enum nft_secmark_attributes {
+ #define NFTA_SECMARK_MAX (__NFTA_SECMARK_MAX - 1)
+
+ /* Max security context length */
+-#define NFT_SECMARK_CTX_MAXLEN 256
++#define NFT_SECMARK_CTX_MAXLEN 4096
+
+ /**
+ * enum nft_reject_types - nf_tables reject expression reject types
+diff --git a/include/uapi/linux/zorro_ids.h b/include/uapi/linux/zorro_ids.h
+index 6e574d7b7d79c..393f2ee9c0422 100644
+--- a/include/uapi/linux/zorro_ids.h
++++ b/include/uapi/linux/zorro_ids.h
+@@ -449,6 +449,9 @@
+ #define ZORRO_PROD_VMC_ISDN_BLASTER_Z2 ZORRO_ID(VMC, 0x01, 0)
+ #define ZORRO_PROD_VMC_HYPERCOM_4 ZORRO_ID(VMC, 0x02, 0)
+
++#define ZORRO_MANUF_CSLAB 0x1400
++#define ZORRO_PROD_CSLAB_WARP_1260 ZORRO_ID(CSLAB, 0x65, 0)
++
+ #define ZORRO_MANUF_INFORMATION 0x157C
+ #define ZORRO_PROD_INFORMATION_ISDN_ENGINE_I ZORRO_ID(INFORMATION, 0x64, 0)
+
+diff --git a/include/ufs/ufshcd.h b/include/ufs/ufshcd.h
+index bad88bd919951..d965e4d1277e6 100644
+--- a/include/ufs/ufshcd.h
++++ b/include/ufs/ufshcd.h
+@@ -1131,6 +1131,12 @@ static inline bool is_mcq_enabled(struct ufs_hba *hba)
+ return hba->mcq_enabled;
+ }
+
++static inline unsigned int ufshcd_mcq_opr_offset(struct ufs_hba *hba,
++ enum ufshcd_mcq_opr opr, int idx)
++{
++ return hba->mcq_opr[opr].offset + hba->mcq_opr[opr].stride * idx;
++}
++
+ #ifdef CONFIG_SCSI_UFS_VARIABLE_SG_ENTRY_SIZE
+ static inline size_t ufshcd_sg_entry_size(const struct ufs_hba *hba)
+ {
+diff --git a/io_uring/io-wq.c b/io_uring/io-wq.c
+index 7d3316fe9bfc4..22dac5850327f 100644
+--- a/io_uring/io-wq.c
++++ b/io_uring/io-wq.c
+@@ -23,6 +23,7 @@
+ #include "io_uring.h"
+
+ #define WORKER_IDLE_TIMEOUT (5 * HZ)
++#define WORKER_INIT_LIMIT 3
+
+ enum {
+ IO_WORKER_F_UP = 0, /* up and active */
+@@ -58,6 +59,7 @@ struct io_worker {
+
+ unsigned long create_state;
+ struct callback_head create_work;
++ int init_retries;
+
+ union {
+ struct rcu_head rcu;
+@@ -744,7 +746,7 @@ static bool io_wq_work_match_all(struct io_wq_work *work, void *data)
+ return true;
+ }
+
+-static inline bool io_should_retry_thread(long err)
++static inline bool io_should_retry_thread(struct io_worker *worker, long err)
+ {
+ /*
+ * Prevent perpetual task_work retry, if the task (or its group) is
+@@ -752,6 +754,8 @@ static inline bool io_should_retry_thread(long err)
+ */
+ if (fatal_signal_pending(current))
+ return false;
++ if (worker->init_retries++ >= WORKER_INIT_LIMIT)
++ return false;
+
+ switch (err) {
+ case -EAGAIN:
+@@ -778,7 +782,7 @@ static void create_worker_cont(struct callback_head *cb)
+ io_init_new_worker(wq, worker, tsk);
+ io_worker_release(worker);
+ return;
+- } else if (!io_should_retry_thread(PTR_ERR(tsk))) {
++ } else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) {
+ struct io_wq_acct *acct = io_wq_get_acct(worker);
+
+ atomic_dec(&acct->nr_running);
+@@ -845,7 +849,7 @@ static bool create_io_worker(struct io_wq *wq, int index)
+ tsk = create_io_thread(io_wq_worker, worker, NUMA_NO_NODE);
+ if (!IS_ERR(tsk)) {
+ io_init_new_worker(wq, worker, tsk);
+- } else if (!io_should_retry_thread(PTR_ERR(tsk))) {
++ } else if (!io_should_retry_thread(worker, PTR_ERR(tsk))) {
+ kfree(worker);
+ goto fail;
+ } else {
+diff --git a/io_uring/io_uring.c b/io_uring/io_uring.c
+index c326e2127dd4d..896e707e06187 100644
+--- a/io_uring/io_uring.c
++++ b/io_uring/io_uring.c
+@@ -3071,8 +3071,11 @@ __cold void io_uring_cancel_generic(bool cancel_all, struct io_sq_data *sqd)
+ bool loop = false;
+
+ io_uring_drop_tctx_refs(current);
++ if (!tctx_inflight(tctx, !cancel_all))
++ break;
++
+ /* read completions before cancelations */
+- inflight = tctx_inflight(tctx, !cancel_all);
++ inflight = tctx_inflight(tctx, false);
+ if (!inflight)
+ break;
+
+diff --git a/io_uring/napi.c b/io_uring/napi.c
+index 8c18ede595c41..080d10e0e0afd 100644
+--- a/io_uring/napi.c
++++ b/io_uring/napi.c
+@@ -222,6 +222,8 @@ int io_register_napi(struct io_ring_ctx *ctx, void __user *arg)
+ };
+ struct io_uring_napi napi;
+
++ if (ctx->flags & IORING_SETUP_IOPOLL)
++ return -EINVAL;
+ if (copy_from_user(&napi, arg, sizeof(napi)))
+ return -EFAULT;
+ if (napi.pad[0] || napi.pad[1] || napi.pad[2] || napi.resv)
+diff --git a/io_uring/opdef.c b/io_uring/opdef.c
+index 2e3b7b16effb3..760006ccc4083 100644
+--- a/io_uring/opdef.c
++++ b/io_uring/opdef.c
+@@ -725,6 +725,14 @@ const char *io_uring_get_opcode(u8 opcode)
+ return "INVALID";
+ }
+
++bool io_uring_op_supported(u8 opcode)
++{
++ if (opcode < IORING_OP_LAST &&
++ io_issue_defs[opcode].prep != io_eopnotsupp_prep)
++ return true;
++ return false;
++}
++
+ void __init io_uring_optable_init(void)
+ {
+ int i;
+diff --git a/io_uring/opdef.h b/io_uring/opdef.h
+index 7ee6f5aa90aa3..14456436ff74a 100644
+--- a/io_uring/opdef.h
++++ b/io_uring/opdef.h
+@@ -17,8 +17,6 @@ struct io_issue_def {
+ unsigned poll_exclusive : 1;
+ /* op supports buffer selection */
+ unsigned buffer_select : 1;
+- /* opcode is not supported by this kernel */
+- unsigned not_supported : 1;
+ /* skip auditing */
+ unsigned audit_skip : 1;
+ /* supports ioprio */
+@@ -47,5 +45,7 @@ struct io_cold_def {
+ extern const struct io_issue_def io_issue_defs[];
+ extern const struct io_cold_def io_cold_defs[];
+
++bool io_uring_op_supported(u8 opcode);
++
+ void io_uring_optable_init(void);
+ #endif
+diff --git a/io_uring/register.c b/io_uring/register.c
+index c0010a66a6f2c..11517b34cfc8f 100644
+--- a/io_uring/register.c
++++ b/io_uring/register.c
+@@ -113,7 +113,7 @@ static __cold int io_probe(struct io_ring_ctx *ctx, void __user *arg,
+
+ for (i = 0; i < nr_args; i++) {
+ p->ops[i].op = i;
+- if (!io_issue_defs[i].not_supported)
++ if (io_uring_op_supported(i))
+ p->ops[i].flags = IO_URING_OP_SUPPORTED;
+ }
+ p->ops_len = i;
+diff --git a/io_uring/timeout.c b/io_uring/timeout.c
+index 1c9bf07499b19..9973876d91b0e 100644
+--- a/io_uring/timeout.c
++++ b/io_uring/timeout.c
+@@ -639,7 +639,7 @@ void io_queue_linked_timeout(struct io_kiocb *req)
+
+ static bool io_match_task(struct io_kiocb *head, struct task_struct *task,
+ bool cancel_all)
+- __must_hold(&req->ctx->timeout_lock)
++ __must_hold(&head->ctx->timeout_lock)
+ {
+ struct io_kiocb *req;
+
+diff --git a/io_uring/uring_cmd.c b/io_uring/uring_cmd.c
+index 21ac5fb2d5f08..a54163a839686 100644
+--- a/io_uring/uring_cmd.c
++++ b/io_uring/uring_cmd.c
+@@ -265,7 +265,7 @@ int io_uring_cmd(struct io_kiocb *req, unsigned int issue_flags)
+ req_set_fail(req);
+ io_req_uring_cleanup(req, issue_flags);
+ io_req_set_res(req, ret, 0);
+- return ret;
++ return ret < 0 ? ret : IOU_OK;
+ }
+
+ int io_uring_cmd_import_fixed(u64 ubuf, unsigned long len, int rw,
+diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
+index 821063660d9f9..fe360b5b211d1 100644
+--- a/kernel/bpf/btf.c
++++ b/kernel/bpf/btf.c
+@@ -414,7 +414,7 @@ const char *btf_type_str(const struct btf_type *t)
+ struct btf_show {
+ u64 flags;
+ void *target; /* target of show operation (seq file, buffer) */
+- void (*showfn)(struct btf_show *show, const char *fmt, va_list args);
++ __printf(2, 0) void (*showfn)(struct btf_show *show, const char *fmt, va_list args);
+ const struct btf *btf;
+ /* below are used during iteration */
+ struct {
+@@ -7370,8 +7370,8 @@ static void btf_type_show(const struct btf *btf, u32 type_id, void *obj,
+ btf_type_ops(t)->show(btf, t, type_id, obj, 0, show);
+ }
+
+-static void btf_seq_show(struct btf_show *show, const char *fmt,
+- va_list args)
++__printf(2, 0) static void btf_seq_show(struct btf_show *show, const char *fmt,
++ va_list args)
+ {
+ seq_vprintf((struct seq_file *)show->target, fmt, args);
+ }
+@@ -7404,8 +7404,8 @@ struct btf_show_snprintf {
+ int len; /* length we would have written */
+ };
+
+-static void btf_snprintf_show(struct btf_show *show, const char *fmt,
+- va_list args)
++__printf(2, 0) static void btf_snprintf_show(struct btf_show *show, const char *fmt,
++ va_list args)
+ {
+ struct btf_show_snprintf *ssnprintf = (struct btf_show_snprintf *)show;
+ int len;
+diff --git a/kernel/bpf/helpers.c b/kernel/bpf/helpers.c
+index 3243c83ef3e39..7268370600f6e 100644
+--- a/kernel/bpf/helpers.c
++++ b/kernel/bpf/helpers.c
+@@ -2786,7 +2786,7 @@ __bpf_kfunc int bpf_wq_start(struct bpf_wq *wq, unsigned int flags)
+ }
+
+ __bpf_kfunc int bpf_wq_set_callback_impl(struct bpf_wq *wq,
+- int (callback_fn)(void *map, int *key, struct bpf_wq *wq),
++ int (callback_fn)(void *map, int *key, void *value),
+ unsigned int flags,
+ void *aux__ign)
+ {
+diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
+index 214a9fa8c6fb7..6b422c275f78c 100644
+--- a/kernel/bpf/verifier.c
++++ b/kernel/bpf/verifier.c
+@@ -3215,7 +3215,8 @@ static int insn_def_regno(const struct bpf_insn *insn)
+ case BPF_ST:
+ return -1;
+ case BPF_STX:
+- if (BPF_MODE(insn->code) == BPF_ATOMIC &&
++ if ((BPF_MODE(insn->code) == BPF_ATOMIC ||
++ BPF_MODE(insn->code) == BPF_PROBE_ATOMIC) &&
+ (insn->imm & BPF_FETCH)) {
+ if (insn->imm == BPF_CMPXCHG)
+ return BPF_REG_0;
+@@ -18767,7 +18768,7 @@ static int adjust_jmp_off(struct bpf_prog *prog, u32 tgt_idx, u32 delta)
+ } else {
+ if (i + 1 + insn->off != tgt_idx)
+ continue;
+- if (signed_add16_overflows(insn->imm, delta))
++ if (signed_add16_overflows(insn->off, delta))
+ return -ERANGE;
+ insn->off += delta;
+ }
+diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
+index c12b9fdb22a4e..5e468db958104 100644
+--- a/kernel/cgroup/cpuset.c
++++ b/kernel/cgroup/cpuset.c
+@@ -21,6 +21,7 @@
+ * License. See the file COPYING in the main directory of the Linux
+ * distribution for more details.
+ */
++#include "cgroup-internal.h"
+
+ #include <linux/cpu.h>
+ #include <linux/cpumask.h>
+@@ -169,7 +170,7 @@ struct cpuset {
+ /* for custom sched domain */
+ int relax_domain_level;
+
+- /* number of valid sub-partitions */
++ /* number of valid local child partitions */
+ int nr_subparts;
+
+ /* partition root state */
+@@ -957,13 +958,15 @@ static int generate_sched_domains(cpumask_var_t **domains,
+ int nslot; /* next empty doms[] struct cpumask slot */
+ struct cgroup_subsys_state *pos_css;
+ bool root_load_balance = is_sched_load_balance(&top_cpuset);
++ bool cgrpv2 = cgroup_subsys_on_dfl(cpuset_cgrp_subsys);
+
+ doms = NULL;
+ dattr = NULL;
+ csa = NULL;
+
+ /* Special case for the 99% of systems with one, full, sched domain */
+- if (root_load_balance && !top_cpuset.nr_subparts) {
++ if (root_load_balance && cpumask_empty(subpartitions_cpus)) {
++single_root_domain:
+ ndoms = 1;
+ doms = alloc_sched_domains(ndoms);
+ if (!doms)
+@@ -991,16 +994,18 @@ static int generate_sched_domains(cpumask_var_t **domains,
+ cpuset_for_each_descendant_pre(cp, pos_css, &top_cpuset) {
+ if (cp == &top_cpuset)
+ continue;
++
++ if (cgrpv2)
++ goto v2;
++
+ /*
++ * v1:
+ * Continue traversing beyond @cp iff @cp has some CPUs and
+ * isn't load balancing. The former is obvious. The
+ * latter: All child cpusets contain a subset of the
+ * parent's cpus, so just skip them, and then we call
+ * update_domain_attr_tree() to calc relax_domain_level of
+ * the corresponding sched domain.
+- *
+- * If root is load-balancing, we can skip @cp if it
+- * is a subset of the root's effective_cpus.
+ */
+ if (!cpumask_empty(cp->cpus_allowed) &&
+ !(is_sched_load_balance(cp) &&
+@@ -1008,20 +1013,39 @@ static int generate_sched_domains(cpumask_var_t **domains,
+ housekeeping_cpumask(HK_TYPE_DOMAIN))))
+ continue;
+
+- if (root_load_balance &&
+- cpumask_subset(cp->cpus_allowed, top_cpuset.effective_cpus))
+- continue;
+-
+ if (is_sched_load_balance(cp) &&
+ !cpumask_empty(cp->effective_cpus))
+ csa[csn++] = cp;
+
+- /* skip @cp's subtree if not a partition root */
+- if (!is_partition_valid(cp))
++ /* skip @cp's subtree */
++ pos_css = css_rightmost_descendant(pos_css);
++ continue;
++
++v2:
++ /*
++ * Only valid partition roots that are not isolated and with
++ * non-empty effective_cpus will be saved into csn[].
++ */
++ if ((cp->partition_root_state == PRS_ROOT) &&
++ !cpumask_empty(cp->effective_cpus))
++ csa[csn++] = cp;
++
++ /*
++ * Skip @cp's subtree if not a partition root and has no
++ * exclusive CPUs to be granted to child cpusets.
++ */
++ if (!is_partition_valid(cp) && cpumask_empty(cp->exclusive_cpus))
+ pos_css = css_rightmost_descendant(pos_css);
+ }
+ rcu_read_unlock();
+
++ /*
++ * If there are only isolated partitions underneath the cgroup root,
++ * we can optimize out unneeded sched domains scanning.
++ */
++ if (root_load_balance && (csn == 1))
++ goto single_root_domain;
++
+ for (i = 0; i < csn; i++)
+ csa[i]->pn = i;
+ ndoms = csn;
+@@ -1064,6 +1088,20 @@ static int generate_sched_domains(cpumask_var_t **domains,
+ dattr = kmalloc_array(ndoms, sizeof(struct sched_domain_attr),
+ GFP_KERNEL);
+
++ /*
++ * Cgroup v2 doesn't support domain attributes, just set all of them
++ * to SD_ATTR_INIT. Also non-isolating partition root CPUs are a
++ * subset of HK_TYPE_DOMAIN housekeeping CPUs.
++ */
++ if (cgrpv2) {
++ for (i = 0; i < ndoms; i++) {
++ cpumask_copy(doms[i], csa[i]->effective_cpus);
++ if (dattr)
++ dattr[i] = SD_ATTR_INIT;
++ }
++ goto done;
++ }
++
+ for (nslot = 0, i = 0; i < csn; i++) {
+ struct cpuset *a = csa[i];
+ struct cpumask *dp;
+@@ -1223,7 +1261,7 @@ static void rebuild_sched_domains_locked(void)
+ * root should be only a subset of the active CPUs. Since a CPU in any
+ * partition root could be offlined, all must be checked.
+ */
+- if (top_cpuset.nr_subparts) {
++ if (!cpumask_empty(subpartitions_cpus)) {
+ rcu_read_lock();
+ cpuset_for_each_descendant_pre(cs, pos_css, &top_cpuset) {
+ if (!is_partition_valid(cs)) {
+@@ -4571,7 +4609,7 @@ static void cpuset_handle_hotplug(void)
+ * In the rare case that hotplug removes all the cpus in
+ * subpartitions_cpus, we assumed that cpus are updated.
+ */
+- if (!cpus_updated && top_cpuset.nr_subparts)
++ if (!cpus_updated && !cpumask_empty(subpartitions_cpus))
+ cpus_updated = true;
+
+ /* For v1, synchronize cpus_allowed to cpu_active_mask */
+@@ -5051,10 +5089,14 @@ int proc_cpuset_show(struct seq_file *m, struct pid_namespace *ns,
+ if (!buf)
+ goto out;
+
+- css = task_get_css(tsk, cpuset_cgrp_id);
+- retval = cgroup_path_ns(css->cgroup, buf, PATH_MAX,
+- current->nsproxy->cgroup_ns);
+- css_put(css);
++ rcu_read_lock();
++ spin_lock_irq(&css_set_lock);
++ css = task_css(tsk, cpuset_cgrp_id);
++ retval = cgroup_path_ns_locked(css->cgroup, buf, PATH_MAX,
++ current->nsproxy->cgroup_ns);
++ spin_unlock_irq(&css_set_lock);
++ rcu_read_unlock();
++
+ if (retval == -E2BIG)
+ retval = -ENAMETOOLONG;
+ if (retval < 0)
+diff --git a/kernel/debug/kdb/kdb_io.c b/kernel/debug/kdb/kdb_io.c
+index 3131334d7a81c..6a77f1c779c4c 100644
+--- a/kernel/debug/kdb/kdb_io.c
++++ b/kernel/debug/kdb/kdb_io.c
+@@ -206,7 +206,7 @@ char kdb_getchar(void)
+ */
+ static void kdb_position_cursor(char *prompt, char *buffer, char *cp)
+ {
+- kdb_printf("\r%s", kdb_prompt_str);
++ kdb_printf("\r%s", prompt);
+ if (cp > buffer)
+ kdb_printf("%.*s", (int)(cp - buffer), buffer);
+ }
+@@ -362,7 +362,7 @@ static char *kdb_read(char *buffer, size_t bufsize)
+ if (i >= dtab_count)
+ kdb_printf("...");
+ kdb_printf("\n");
+- kdb_printf(kdb_prompt_str);
++ kdb_printf("%s", kdb_prompt_str);
+ kdb_printf("%s", buffer);
+ if (cp != lastchar)
+ kdb_position_cursor(kdb_prompt_str, buffer, cp);
+@@ -453,7 +453,7 @@ char *kdb_getstr(char *buffer, size_t bufsize, const char *prompt)
+ {
+ if (prompt && kdb_prompt_str != prompt)
+ strscpy(kdb_prompt_str, prompt, CMD_BUFLEN);
+- kdb_printf(kdb_prompt_str);
++ kdb_printf("%s", kdb_prompt_str);
+ kdb_nextline = 1; /* Prompt and input resets line number */
+ return kdb_read(buffer, bufsize);
+ }
+diff --git a/kernel/dma/mapping.c b/kernel/dma/mapping.c
+index 81de84318ccc7..b1c18058d55f8 100644
+--- a/kernel/dma/mapping.c
++++ b/kernel/dma/mapping.c
+@@ -67,8 +67,8 @@ void dmam_free_coherent(struct device *dev, size_t size, void *vaddr,
+ {
+ struct dma_devres match_data = { size, vaddr, dma_handle };
+
+- dma_free_coherent(dev, size, vaddr, dma_handle);
+ WARN_ON(devres_destroy(dev, dmam_release, dmam_match, &match_data));
++ dma_free_coherent(dev, size, vaddr, dma_handle);
+ }
+ EXPORT_SYMBOL(dmam_free_coherent);
+
+diff --git a/kernel/events/core.c b/kernel/events/core.c
+index 8f908f0779354..b2a6aec118f3a 100644
+--- a/kernel/events/core.c
++++ b/kernel/events/core.c
+@@ -2284,18 +2284,14 @@ event_sched_out(struct perf_event *event, struct perf_event_context *ctx)
+ }
+
+ if (event->pending_sigtrap) {
+- bool dec = true;
+-
+ event->pending_sigtrap = 0;
+ if (state != PERF_EVENT_STATE_OFF &&
+- !event->pending_work) {
++ !event->pending_work &&
++ !task_work_add(current, &event->pending_task, TWA_RESUME)) {
+ event->pending_work = 1;
+- dec = false;
+- WARN_ON_ONCE(!atomic_long_inc_not_zero(&event->refcount));
+- task_work_add(current, &event->pending_task, TWA_RESUME);
+- }
+- if (dec)
++ } else {
+ local_dec(&event->ctx->nr_pending);
++ }
+ }
+
+ perf_event_set_state(event, state);
+@@ -5206,9 +5202,35 @@ static bool exclusive_event_installable(struct perf_event *event,
+ static void perf_addr_filters_splice(struct perf_event *event,
+ struct list_head *head);
+
++static void perf_pending_task_sync(struct perf_event *event)
++{
++ struct callback_head *head = &event->pending_task;
++
++ if (!event->pending_work)
++ return;
++ /*
++ * If the task is queued to the current task's queue, we
++ * obviously can't wait for it to complete. Simply cancel it.
++ */
++ if (task_work_cancel(current, head)) {
++ event->pending_work = 0;
++ local_dec(&event->ctx->nr_pending);
++ return;
++ }
++
++ /*
++ * All accesses related to the event are within the same
++ * non-preemptible section in perf_pending_task(). The RCU
++ * grace period before the event is freed will make sure all
++ * those accesses are complete by then.
++ */
++ rcuwait_wait_event(&event->pending_work_wait, !event->pending_work, TASK_UNINTERRUPTIBLE);
++}
++
+ static void _free_event(struct perf_event *event)
+ {
+ irq_work_sync(&event->pending_irq);
++ perf_pending_task_sync(event);
+
+ unaccount_event(event);
+
+@@ -6509,6 +6531,8 @@ static int perf_mmap(struct file *file, struct vm_area_struct *vma)
+ return -EINVAL;
+
+ nr_pages = vma_size / PAGE_SIZE;
++ if (nr_pages > INT_MAX)
++ return -ENOMEM;
+
+ mutex_lock(&event->mmap_mutex);
+ ret = -EINVAL;
+@@ -6831,24 +6855,28 @@ static void perf_pending_task(struct callback_head *head)
+ struct perf_event *event = container_of(head, struct perf_event, pending_task);
+ int rctx;
+
++ /*
++ * All accesses to the event must belong to the same implicit RCU read-side
++ * critical section as the ->pending_work reset. See comment in
++ * perf_pending_task_sync().
++ */
++ preempt_disable_notrace();
+ /*
+ * If we 'fail' here, that's OK, it means recursion is already disabled
+ * and we won't recurse 'further'.
+ */
+- preempt_disable_notrace();
+ rctx = perf_swevent_get_recursion_context();
+
+ if (event->pending_work) {
+ event->pending_work = 0;
+ perf_sigtrap(event);
+ local_dec(&event->ctx->nr_pending);
++ rcuwait_wake_up(&event->pending_work_wait);
+ }
+
+ if (rctx >= 0)
+ perf_swevent_put_recursion_context(rctx);
+ preempt_enable_notrace();
+-
+- put_event(event);
+ }
+
+ #ifdef CONFIG_GUEST_PERF_EVENTS
+@@ -9302,21 +9330,19 @@ static void perf_event_bpf_emit_ksymbols(struct bpf_prog *prog,
+ bool unregister = type == PERF_BPF_EVENT_PROG_UNLOAD;
+ int i;
+
+- if (prog->aux->func_cnt == 0) {
+- perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
+- (u64)(unsigned long)prog->bpf_func,
+- prog->jited_len, unregister,
+- prog->aux->ksym.name);
+- } else {
+- for (i = 0; i < prog->aux->func_cnt; i++) {
+- struct bpf_prog *subprog = prog->aux->func[i];
+-
+- perf_event_ksymbol(
+- PERF_RECORD_KSYMBOL_TYPE_BPF,
+- (u64)(unsigned long)subprog->bpf_func,
+- subprog->jited_len, unregister,
+- subprog->aux->ksym.name);
+- }
++ perf_event_ksymbol(PERF_RECORD_KSYMBOL_TYPE_BPF,
++ (u64)(unsigned long)prog->bpf_func,
++ prog->jited_len, unregister,
++ prog->aux->ksym.name);
++
++ for (i = 1; i < prog->aux->func_cnt; i++) {
++ struct bpf_prog *subprog = prog->aux->func[i];
++
++ perf_event_ksymbol(
++ PERF_RECORD_KSYMBOL_TYPE_BPF,
++ (u64)(unsigned long)subprog->bpf_func,
++ subprog->jited_len, unregister,
++ subprog->aux->ksym.name);
+ }
+ }
+
+@@ -11962,6 +11988,7 @@ perf_event_alloc(struct perf_event_attr *attr, int cpu,
+ init_waitqueue_head(&event->waitq);
+ init_irq_work(&event->pending_irq, perf_pending_irq);
+ init_task_work(&event->pending_task, perf_pending_task);
++ rcuwait_init(&event->pending_work_wait);
+
+ mutex_init(&event->mmap_mutex);
+ raw_spin_lock_init(&event->addr_filters.lock);
+diff --git a/kernel/events/internal.h b/kernel/events/internal.h
+index 5150d5f84c033..386d21c7edfa0 100644
+--- a/kernel/events/internal.h
++++ b/kernel/events/internal.h
+@@ -128,7 +128,7 @@ static inline unsigned long perf_data_size(struct perf_buffer *rb)
+
+ static inline unsigned long perf_aux_size(struct perf_buffer *rb)
+ {
+- return rb->aux_nr_pages << PAGE_SHIFT;
++ return (unsigned long)rb->aux_nr_pages << PAGE_SHIFT;
+ }
+
+ #define __DEFINE_OUTPUT_COPY_BODY(advance_buf, memcpy_func, ...) \
+diff --git a/kernel/events/ring_buffer.c b/kernel/events/ring_buffer.c
+index 4013408ce0123..485cf0a66631b 100644
+--- a/kernel/events/ring_buffer.c
++++ b/kernel/events/ring_buffer.c
+@@ -688,7 +688,9 @@ int rb_alloc_aux(struct perf_buffer *rb, struct perf_event *event,
+ * max_order, to aid PMU drivers in double buffering.
+ */
+ if (!watermark)
+- watermark = nr_pages << (PAGE_SHIFT - 1);
++ watermark = min_t(unsigned long,
++ U32_MAX,
++ (unsigned long)nr_pages << (PAGE_SHIFT - 1));
+
+ /*
+ * Use aux_watermark as the basis for chunking to
+diff --git a/kernel/irq/irqdomain.c b/kernel/irq/irqdomain.c
+index aadc8891cc166..efeacf17c239e 100644
+--- a/kernel/irq/irqdomain.c
++++ b/kernel/irq/irqdomain.c
+@@ -155,7 +155,6 @@ static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode,
+ switch (fwid->type) {
+ case IRQCHIP_FWNODE_NAMED:
+ case IRQCHIP_FWNODE_NAMED_ID:
+- domain->fwnode = fwnode;
+ domain->name = kstrdup(fwid->name, GFP_KERNEL);
+ if (!domain->name) {
+ kfree(domain);
+@@ -164,7 +163,6 @@ static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode,
+ domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED;
+ break;
+ default:
+- domain->fwnode = fwnode;
+ domain->name = fwid->name;
+ break;
+ }
+@@ -184,7 +182,6 @@ static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode,
+ }
+
+ domain->name = strreplace(name, '/', ':');
+- domain->fwnode = fwnode;
+ domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED;
+ }
+
+@@ -200,8 +197,8 @@ static struct irq_domain *__irq_domain_create(struct fwnode_handle *fwnode,
+ domain->flags |= IRQ_DOMAIN_NAME_ALLOCATED;
+ }
+
+- fwnode_handle_get(fwnode);
+- fwnode_dev_initialized(fwnode, true);
++ domain->fwnode = fwnode_handle_get(fwnode);
++ fwnode_dev_initialized(domain->fwnode, true);
+
+ /* Fill structure */
+ INIT_RADIX_TREE(&domain->revmap_tree, GFP_KERNEL);
+diff --git a/kernel/irq/manage.c b/kernel/irq/manage.c
+index 71b0fc2d0aeaa..dd53298ef1a5c 100644
+--- a/kernel/irq/manage.c
++++ b/kernel/irq/manage.c
+@@ -1337,7 +1337,7 @@ static int irq_thread(void *data)
+ * synchronize_hardirq(). So neither IRQTF_RUNTHREAD nor the
+ * oneshot mask bit can be set.
+ */
+- task_work_cancel(current, irq_thread_dtor);
++ task_work_cancel_func(current, irq_thread_dtor);
+ return 0;
+ }
+
+diff --git a/kernel/jump_label.c b/kernel/jump_label.c
+index 3218fa5688b93..1f05a19918f47 100644
+--- a/kernel/jump_label.c
++++ b/kernel/jump_label.c
+@@ -131,7 +131,7 @@ bool static_key_fast_inc_not_disabled(struct static_key *key)
+ STATIC_KEY_CHECK_USE(key);
+ /*
+ * Negative key->enabled has a special meaning: it sends
+- * static_key_slow_inc() down the slow path, and it is non-zero
++ * static_key_slow_inc/dec() down the slow path, and it is non-zero
+ * so it counts as "enabled" in jump_label_update(). Note that
+ * atomic_inc_unless_negative() checks >= 0, so roll our own.
+ */
+@@ -150,7 +150,7 @@ bool static_key_slow_inc_cpuslocked(struct static_key *key)
+ lockdep_assert_cpus_held();
+
+ /*
+- * Careful if we get concurrent static_key_slow_inc() calls;
++ * Careful if we get concurrent static_key_slow_inc/dec() calls;
+ * later calls must wait for the first one to _finish_ the
+ * jump_label_update() process. At the same time, however,
+ * the jump_label_update() call below wants to see
+@@ -247,20 +247,32 @@ EXPORT_SYMBOL_GPL(static_key_disable);
+
+ static bool static_key_slow_try_dec(struct static_key *key)
+ {
+- int val;
+-
+- val = atomic_fetch_add_unless(&key->enabled, -1, 1);
+- if (val == 1)
+- return false;
++ int v;
+
+ /*
+- * The negative count check is valid even when a negative
+- * key->enabled is in use by static_key_slow_inc(); a
+- * __static_key_slow_dec() before the first static_key_slow_inc()
+- * returns is unbalanced, because all other static_key_slow_inc()
+- * instances block while the update is in progress.
++ * Go into the slow path if key::enabled is less than or equal than
++ * one. One is valid to shut down the key, anything less than one
++ * is an imbalance, which is handled at the call site.
++ *
++ * That includes the special case of '-1' which is set in
++ * static_key_slow_inc_cpuslocked(), but that's harmless as it is
++ * fully serialized in the slow path below. By the time this task
++ * acquires the jump label lock the value is back to one and the
++ * retry under the lock must succeed.
+ */
+- WARN(val < 0, "jump label: negative count!\n");
++ v = atomic_read(&key->enabled);
++ do {
++ /*
++ * Warn about the '-1' case though; since that means a
++ * decrement is concurrent with a first (0->1) increment. IOW
++ * people are trying to disable something that wasn't yet fully
++ * enabled. This suggests an ordering problem on the user side.
++ */
++ WARN_ON_ONCE(v < 0);
++ if (v <= 1)
++ return false;
++ } while (!likely(atomic_try_cmpxchg(&key->enabled, &v, v - 1)));
++
+ return true;
+ }
+
+@@ -271,10 +283,11 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
+ if (static_key_slow_try_dec(key))
+ return;
+
+- jump_label_lock();
+- if (atomic_dec_and_test(&key->enabled))
++ guard(mutex)(&jump_label_mutex);
++ if (atomic_cmpxchg(&key->enabled, 1, 0))
+ jump_label_update(key);
+- jump_label_unlock();
++ else
++ WARN_ON_ONCE(!static_key_slow_try_dec(key));
+ }
+
+ static void __static_key_slow_dec(struct static_key *key)
+diff --git a/kernel/locking/rwsem.c b/kernel/locking/rwsem.c
+index c6d17aee4209b..33cac79e39946 100644
+--- a/kernel/locking/rwsem.c
++++ b/kernel/locking/rwsem.c
+@@ -1297,7 +1297,7 @@ static inline int __down_read_trylock(struct rw_semaphore *sem)
+ /*
+ * lock for writing
+ */
+-static inline int __down_write_common(struct rw_semaphore *sem, int state)
++static __always_inline int __down_write_common(struct rw_semaphore *sem, int state)
+ {
+ int ret = 0;
+
+@@ -1310,12 +1310,12 @@ static inline int __down_write_common(struct rw_semaphore *sem, int state)
+ return ret;
+ }
+
+-static inline void __down_write(struct rw_semaphore *sem)
++static __always_inline void __down_write(struct rw_semaphore *sem)
+ {
+ __down_write_common(sem, TASK_UNINTERRUPTIBLE);
+ }
+
+-static inline int __down_write_killable(struct rw_semaphore *sem)
++static __always_inline int __down_write_killable(struct rw_semaphore *sem)
+ {
+ return __down_write_common(sem, TASK_KILLABLE);
+ }
+diff --git a/kernel/rcu/tasks.h b/kernel/rcu/tasks.h
+index e1bf33018e6d5..098e82bcc427f 100644
+--- a/kernel/rcu/tasks.h
++++ b/kernel/rcu/tasks.h
+@@ -1757,6 +1757,16 @@ static void rcu_tasks_trace_pregp_step(struct list_head *hop)
+ // allow safe access to the hop list.
+ for_each_online_cpu(cpu) {
+ rcu_read_lock();
++ // Note that cpu_curr_snapshot() picks up the target
++ // CPU's current task while its runqueue is locked with
++ // an smp_mb__after_spinlock(). This ensures that either
++ // the grace-period kthread will see that task's read-side
++ // critical section or the task will see the updater's pre-GP
++ // accesses. The trailing smp_mb() in cpu_curr_snapshot()
++ // does not currently play a role other than simplify
++ // that function's ordering semantics. If these simplified
++ // ordering semantics continue to be redundant, that smp_mb()
++ // might be removed.
+ t = cpu_curr_snapshot(cpu);
+ if (rcu_tasks_trace_pertask_prep(t, true))
+ trc_add_holdout(t, hop);
+diff --git a/kernel/sched/core.c b/kernel/sched/core.c
+index 59ce0841eb1fd..ebf21373f6634 100644
+--- a/kernel/sched/core.c
++++ b/kernel/sched/core.c
+@@ -1326,27 +1326,24 @@ int tg_nop(struct task_group *tg, void *data)
+ static void set_load_weight(struct task_struct *p, bool update_load)
+ {
+ int prio = p->static_prio - MAX_RT_PRIO;
+- struct load_weight *load = &p->se.load;
++ struct load_weight lw;
+
+- /*
+- * SCHED_IDLE tasks get minimal weight:
+- */
+ if (task_has_idle_policy(p)) {
+- load->weight = scale_load(WEIGHT_IDLEPRIO);
+- load->inv_weight = WMULT_IDLEPRIO;
+- return;
++ lw.weight = scale_load(WEIGHT_IDLEPRIO);
++ lw.inv_weight = WMULT_IDLEPRIO;
++ } else {
++ lw.weight = scale_load(sched_prio_to_weight[prio]);
++ lw.inv_weight = sched_prio_to_wmult[prio];
+ }
+
+ /*
+ * SCHED_OTHER tasks have to update their load when changing their
+ * weight
+ */
+- if (update_load && p->sched_class == &fair_sched_class) {
+- reweight_task(p, prio);
+- } else {
+- load->weight = scale_load(sched_prio_to_weight[prio]);
+- load->inv_weight = sched_prio_to_wmult[prio];
+- }
++ if (update_load && p->sched_class == &fair_sched_class)
++ reweight_task(p, &lw);
++ else
++ p->se.load = lw;
+ }
+
+ #ifdef CONFIG_UCLAMP_TASK
+@@ -4466,12 +4463,7 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
+ * @cpu: The CPU on which to snapshot the task.
+ *
+ * Returns the task_struct pointer of the task "currently" running on
+- * the specified CPU. If the same task is running on that CPU throughout,
+- * the return value will be a pointer to that task's task_struct structure.
+- * If the CPU did any context switches even vaguely concurrently with the
+- * execution of this function, the return value will be a pointer to the
+- * task_struct structure of a randomly chosen task that was running on
+- * that CPU somewhere around the time that this function was executing.
++ * the specified CPU.
+ *
+ * If the specified CPU was offline, the return value is whatever it
+ * is, perhaps a pointer to the task_struct structure of that CPU's idle
+@@ -4485,11 +4477,16 @@ int task_call_func(struct task_struct *p, task_call_f func, void *arg)
+ */
+ struct task_struct *cpu_curr_snapshot(int cpu)
+ {
++ struct rq *rq = cpu_rq(cpu);
+ struct task_struct *t;
++ struct rq_flags rf;
+
+- smp_mb(); /* Pairing determined by caller's synchronization design. */
++ rq_lock_irqsave(rq, &rf);
++ smp_mb__after_spinlock(); /* Pairing determined by caller's synchronization design. */
+ t = rcu_dereference(cpu_curr(cpu));
++ rq_unlock_irqrestore(rq, &rf);
+ smp_mb(); /* Pairing determined by caller's synchronization design. */
++
+ return t;
+ }
+
+diff --git a/kernel/sched/fair.c b/kernel/sched/fair.c
+index 24dda708b6993..483c137b9d3d7 100644
+--- a/kernel/sched/fair.c
++++ b/kernel/sched/fair.c
+@@ -3835,15 +3835,14 @@ static void reweight_entity(struct cfs_rq *cfs_rq, struct sched_entity *se,
+ }
+ }
+
+-void reweight_task(struct task_struct *p, int prio)
++void reweight_task(struct task_struct *p, const struct load_weight *lw)
+ {
+ struct sched_entity *se = &p->se;
+ struct cfs_rq *cfs_rq = cfs_rq_of(se);
+ struct load_weight *load = &se->load;
+- unsigned long weight = scale_load(sched_prio_to_weight[prio]);
+
+- reweight_entity(cfs_rq, se, weight);
+- load->inv_weight = sched_prio_to_wmult[prio];
++ reweight_entity(cfs_rq, se, lw->weight);
++ load->inv_weight = lw->inv_weight;
+ }
+
+ static inline int throttled_hierarchy(struct cfs_rq *cfs_rq);
+diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
+index ef20c61004ebf..38aeedd8a6cc8 100644
+--- a/kernel/sched/sched.h
++++ b/kernel/sched/sched.h
+@@ -2464,7 +2464,7 @@ extern void init_sched_dl_class(void);
+ extern void init_sched_rt_class(void);
+ extern void init_sched_fair_class(void);
+
+-extern void reweight_task(struct task_struct *p, int prio);
++extern void reweight_task(struct task_struct *p, const struct load_weight *lw);
+
+ extern void resched_curr(struct rq *rq);
+ extern void resched_cpu(int cpu);
+diff --git a/kernel/signal.c b/kernel/signal.c
+index 1f9dd41c04be2..60c737e423a18 100644
+--- a/kernel/signal.c
++++ b/kernel/signal.c
+@@ -2600,6 +2600,14 @@ static void do_freezer_trap(void)
+ spin_unlock_irq(¤t->sighand->siglock);
+ cgroup_enter_frozen();
+ schedule();
++
++ /*
++ * We could've been woken by task_work, run it to clear
++ * TIF_NOTIFY_SIGNAL. The caller will retry if necessary.
++ */
++ clear_notify_signal();
++ if (unlikely(task_work_pending(current)))
++ task_work_run();
+ }
+
+ static int ptrace_signal(int signr, kernel_siginfo_t *info, enum pid_type type)
+diff --git a/kernel/task_work.c b/kernel/task_work.c
+index 95a7e1b7f1dab..2134ac8057a94 100644
+--- a/kernel/task_work.c
++++ b/kernel/task_work.c
+@@ -120,9 +120,9 @@ static bool task_work_func_match(struct callback_head *cb, void *data)
+ }
+
+ /**
+- * task_work_cancel - cancel a pending work added by task_work_add()
+- * @task: the task which should execute the work
+- * @func: identifies the work to remove
++ * task_work_cancel_func - cancel a pending work matching a function added by task_work_add()
++ * @task: the task which should execute the func's work
++ * @func: identifies the func to match with a work to remove
+ *
+ * Find the last queued pending work with ->func == @func and remove
+ * it from queue.
+@@ -131,11 +131,35 @@ static bool task_work_func_match(struct callback_head *cb, void *data)
+ * The found work or NULL if not found.
+ */
+ struct callback_head *
+-task_work_cancel(struct task_struct *task, task_work_func_t func)
++task_work_cancel_func(struct task_struct *task, task_work_func_t func)
+ {
+ return task_work_cancel_match(task, task_work_func_match, func);
+ }
+
++static bool task_work_match(struct callback_head *cb, void *data)
++{
++ return cb == data;
++}
++
++/**
++ * task_work_cancel - cancel a pending work added by task_work_add()
++ * @task: the task which should execute the work
++ * @cb: the callback to remove if queued
++ *
++ * Remove a callback from a task's queue if queued.
++ *
++ * RETURNS:
++ * True if the callback was queued and got cancelled, false otherwise.
++ */
++bool task_work_cancel(struct task_struct *task, struct callback_head *cb)
++{
++ struct callback_head *ret;
++
++ ret = task_work_cancel_match(task, task_work_match, cb);
++
++ return ret == cb;
++}
++
+ /**
+ * task_work_run - execute the works added by task_work_add()
+ *
+@@ -168,7 +192,7 @@ void task_work_run(void)
+ if (!work)
+ break;
+ /*
+- * Synchronize with task_work_cancel(). It can not remove
++ * Synchronize with task_work_cancel_match(). It can not remove
+ * the first entry == work, cmpxchg(task_works) must fail.
+ * But it can remove another entry from the ->next list.
+ */
+diff --git a/kernel/time/tick-broadcast.c b/kernel/time/tick-broadcast.c
+index 771d1e040303b..b4843099a8da7 100644
+--- a/kernel/time/tick-broadcast.c
++++ b/kernel/time/tick-broadcast.c
+@@ -1141,6 +1141,7 @@ void tick_broadcast_switch_to_oneshot(void)
+ #ifdef CONFIG_HOTPLUG_CPU
+ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+ {
++ struct tick_device *td = this_cpu_ptr(&tick_cpu_device);
+ struct clock_event_device *bc;
+ unsigned long flags;
+
+@@ -1148,6 +1149,28 @@ void hotplug_cpu__broadcast_tick_pull(int deadcpu)
+ bc = tick_broadcast_device.evtdev;
+
+ if (bc && broadcast_needs_cpu(bc, deadcpu)) {
++ /*
++ * If the broadcast force bit of the current CPU is set,
++ * then the current CPU has not yet reprogrammed the local
++ * timer device to avoid a ping-pong race. See
++ * ___tick_broadcast_oneshot_control().
++ *
++ * If the broadcast device is hrtimer based then
++ * programming the broadcast event below does not have any
++ * effect because the local clockevent device is not
++ * running and not programmed because the broadcast event
++ * is not earlier than the pending event of the local clock
++ * event device. As a consequence all CPUs waiting for a
++ * broadcast event are stuck forever.
++ *
++ * Detect this condition and reprogram the cpu local timer
++ * device to avoid the starvation.
++ */
++ if (tick_check_broadcast_expired()) {
++ cpumask_clear_cpu(smp_processor_id(), tick_broadcast_force_mask);
++ tick_program_event(td->evtdev->next_event, 1);
++ }
++
+ /* This moves the broadcast assignment to this CPU: */
+ clockevents_program_event(bc, bc->next_event, 1);
+ }
+diff --git a/kernel/time/timer_migration.c b/kernel/time/timer_migration.c
+index 84413114db5c5..d91efe1dc3bf5 100644
+--- a/kernel/time/timer_migration.c
++++ b/kernel/time/timer_migration.c
+@@ -507,7 +507,14 @@ static void walk_groups(up_f up, void *data, struct tmigr_cpu *tmc)
+ * (get_next_timer_interrupt())
+ * @firstexp: Contains the first event expiry information when last
+ * active CPU of hierarchy is on the way to idle to make
+- * sure CPU will be back in time.
++ * sure CPU will be back in time. It is updated in top
++ * level group only. Be aware, there could occur a new top
++ * level of the hierarchy between the 'top level call' in
++ * tmigr_update_events() and the check for the parent group
++ * in walk_groups(). Then @firstexp might contain a value
++ * != KTIME_MAX even if it was not the final top
++ * level. This is not a problem, as the worst outcome is a
++ * CPU which might wake up a little early.
+ * @evt: Pointer to tmigr_event which needs to be queued (of idle
+ * child group)
+ * @childmask: childmask of child group
+@@ -649,7 +656,7 @@ static bool tmigr_active_up(struct tmigr_group *group,
+
+ } while (!atomic_try_cmpxchg(&group->migr_state, &curstate.state, newstate.state));
+
+- if ((walk_done == false) && group->parent)
++ if (walk_done == false)
+ data->childmask = group->childmask;
+
+ /*
+@@ -1317,20 +1324,9 @@ static bool tmigr_inactive_up(struct tmigr_group *group,
+ /* Event Handling */
+ tmigr_update_events(group, child, data);
+
+- if (group->parent && (walk_done == false))
++ if (walk_done == false)
+ data->childmask = group->childmask;
+
+- /*
+- * data->firstexp was set by tmigr_update_events() and contains the
+- * expiry of the first global event which needs to be handled. It
+- * differs from KTIME_MAX if:
+- * - group is the top level group and
+- * - group is idle (which means CPU was the last active CPU in the
+- * hierarchy) and
+- * - there is a pending event in the hierarchy
+- */
+- WARN_ON_ONCE(data->firstexp != KTIME_MAX && group->parent);
+-
+ trace_tmigr_group_set_cpu_inactive(group, newstate, childmask);
+
+ return walk_done;
+@@ -1552,10 +1548,11 @@ static void tmigr_connect_child_parent(struct tmigr_group *child,
+ data.childmask = child->childmask;
+
+ /*
+- * There is only one new level per time. When connecting the
+- * child and the parent and set the child active when the parent
+- * is inactive, the parent needs to be the uppermost
+- * level. Otherwise there went something wrong!
++ * There is only one new level per time (which is protected by
++ * tmigr_mutex). When connecting the child and the parent and
++ * set the child active when the parent is inactive, the parent
++ * needs to be the uppermost level. Otherwise there went
++ * something wrong!
+ */
+ WARN_ON(!tmigr_active_up(parent, child, &data) && parent->parent);
+ }
+diff --git a/kernel/time/timer_migration.h b/kernel/time/timer_migration.h
+index 6c37d94a37d90..494f68cc13f4b 100644
+--- a/kernel/time/timer_migration.h
++++ b/kernel/time/timer_migration.h
+@@ -22,7 +22,17 @@ struct tmigr_event {
+ * struct tmigr_group - timer migration hierarchy group
+ * @lock: Lock protecting the event information and group hierarchy
+ * information during setup
+- * @parent: Pointer to the parent group
++ * @parent: Pointer to the parent group. Pointer is updated when a
++ * new hierarchy level is added because of a CPU coming
++ * online the first time. Once it is set, the pointer will
++ * not be removed or updated. When accessing parent pointer
++ * lock less to decide whether to abort a propagation or
++ * not, it is not a problem. The worst outcome is an
++ * unnecessary/early CPU wake up. But do not access parent
++ * pointer several times in the same 'action' (like
++ * activation, deactivation, check for remote expiry,...)
++ * without holding the lock as it is not ensured that value
++ * will not change.
+ * @groupevt: Next event of the group which is only used when the
+ * group is !active. The group event is then queued into
+ * the parent timer queue.
+diff --git a/kernel/trace/pid_list.c b/kernel/trace/pid_list.c
+index 95106d02b32d8..85de221c0b6f2 100644
+--- a/kernel/trace/pid_list.c
++++ b/kernel/trace/pid_list.c
+@@ -354,7 +354,7 @@ static void pid_list_refill_irq(struct irq_work *iwork)
+ while (upper_count-- > 0) {
+ union upper_chunk *chunk;
+
+- chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
++ chunk = kzalloc(sizeof(*chunk), GFP_NOWAIT);
+ if (!chunk)
+ break;
+ *upper_next = chunk;
+@@ -365,7 +365,7 @@ static void pid_list_refill_irq(struct irq_work *iwork)
+ while (lower_count-- > 0) {
+ union lower_chunk *chunk;
+
+- chunk = kzalloc(sizeof(*chunk), GFP_KERNEL);
++ chunk = kzalloc(sizeof(*chunk), GFP_NOWAIT);
+ if (!chunk)
+ break;
+ *lower_next = chunk;
+diff --git a/kernel/watchdog_perf.c b/kernel/watchdog_perf.c
+index d577c4a8321ee..59c1d86a73a24 100644
+--- a/kernel/watchdog_perf.c
++++ b/kernel/watchdog_perf.c
+@@ -75,11 +75,15 @@ static bool watchdog_check_timestamp(void)
+ __this_cpu_write(last_timestamp, now);
+ return true;
+ }
+-#else
+-static inline bool watchdog_check_timestamp(void)
++
++static void watchdog_init_timestamp(void)
+ {
+- return true;
++ __this_cpu_write(nmi_rearmed, 0);
++ __this_cpu_write(last_timestamp, ktime_get_mono_fast_ns());
+ }
++#else
++static inline bool watchdog_check_timestamp(void) { return true; }
++static inline void watchdog_init_timestamp(void) { }
+ #endif
+
+ static struct perf_event_attr wd_hw_attr = {
+@@ -161,6 +165,7 @@ void watchdog_hardlockup_enable(unsigned int cpu)
+ if (!atomic_fetch_inc(&watchdog_cpus))
+ pr_info("Enabled. Permanently consumes one hw-PMU counter.\n");
+
++ watchdog_init_timestamp();
+ perf_event_enable(this_cpu_read(watchdog_ev));
+ }
+
+diff --git a/kernel/workqueue.c b/kernel/workqueue.c
+index 3fbaecfc88c28..f98247ec99c20 100644
+--- a/kernel/workqueue.c
++++ b/kernel/workqueue.c
+@@ -2298,9 +2298,13 @@ static void __queue_work(int cpu, struct workqueue_struct *wq,
+ * If @work was previously on a different pool, it might still be
+ * running there, in which case the work needs to be queued on that
+ * pool to guarantee non-reentrancy.
++ *
++ * For ordered workqueue, work items must be queued on the newest pwq
++ * for accurate order management. Guaranteed order also guarantees
++ * non-reentrancy. See the comments above unplug_oldest_pwq().
+ */
+ last_pool = get_work_pool(work);
+- if (last_pool && last_pool != pool) {
++ if (last_pool && last_pool != pool && !(wq->flags & __WQ_ORDERED)) {
+ struct worker *worker;
+
+ raw_spin_lock(&last_pool->lock);
+diff --git a/lib/decompress_bunzip2.c b/lib/decompress_bunzip2.c
+index 3518e7394eca8..ca736166f1000 100644
+--- a/lib/decompress_bunzip2.c
++++ b/lib/decompress_bunzip2.c
+@@ -232,7 +232,8 @@ static int INIT get_next_block(struct bunzip_data *bd)
+ RUNB) */
+ symCount = symTotal+2;
+ for (j = 0; j < groupCount; j++) {
+- unsigned char length[MAX_SYMBOLS], temp[MAX_HUFCODE_BITS+1];
++ unsigned char length[MAX_SYMBOLS];
++ unsigned short temp[MAX_HUFCODE_BITS+1];
+ int minLen, maxLen, pp;
+ /* Read Huffman code lengths for each symbol. They're
+ stored in a way similar to mtf; record a starting
+diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c
+index 03b427e2707e3..b7f2fa08d9c82 100644
+--- a/lib/kobject_uevent.c
++++ b/lib/kobject_uevent.c
+@@ -433,8 +433,23 @@ static void zap_modalias_env(struct kobj_uevent_env *env)
+ len = strlen(env->envp[i]) + 1;
+
+ if (i != env->envp_idx - 1) {
++ /* @env->envp[] contains pointers to @env->buf[]
++ * with @env->buflen chars, and we are removing
++ * variable MODALIAS here pointed by @env->envp[i]
++ * with length @len as shown below:
++ *
++ * 0 @env->buf[] @env->buflen
++ * ---------------------------------------------
++ * ^ ^ ^ ^
++ * | |-> @len <-| target block |
++ * @env->envp[0] @env->envp[i] @env->envp[i + 1]
++ *
++ * so the "target block" indicated above is moved
++ * backward by @len, and its right size is
++ * @env->buflen - (@env->envp[i + 1] - @env->envp[0]).
++ */
+ memmove(env->envp[i], env->envp[i + 1],
+- env->buflen - len);
++ env->buflen - (env->envp[i + 1] - env->envp[0]));
+
+ for (j = i; j < env->envp_idx - 1; j++)
+ env->envp[j] = env->envp[j + 1] - len;
+diff --git a/lib/objagg.c b/lib/objagg.c
+index 1e248629ed643..1608895b009c8 100644
+--- a/lib/objagg.c
++++ b/lib/objagg.c
+@@ -167,6 +167,9 @@ static int objagg_obj_parent_assign(struct objagg *objagg,
+ {
+ void *delta_priv;
+
++ if (WARN_ON(!objagg_obj_is_root(parent)))
++ return -EINVAL;
++
+ delta_priv = objagg->ops->delta_create(objagg->priv, parent->obj,
+ objagg_obj->obj);
+ if (IS_ERR(delta_priv))
+@@ -903,20 +906,6 @@ static const struct objagg_opt_algo *objagg_opt_algos[] = {
+ [OBJAGG_OPT_ALGO_SIMPLE_GREEDY] = &objagg_opt_simple_greedy,
+ };
+
+-static int objagg_hints_obj_cmp(struct rhashtable_compare_arg *arg,
+- const void *obj)
+-{
+- struct rhashtable *ht = arg->ht;
+- struct objagg_hints *objagg_hints =
+- container_of(ht, struct objagg_hints, node_ht);
+- const struct objagg_ops *ops = objagg_hints->ops;
+- const char *ptr = obj;
+-
+- ptr += ht->p.key_offset;
+- return ops->hints_obj_cmp ? ops->hints_obj_cmp(ptr, arg->key) :
+- memcmp(ptr, arg->key, ht->p.key_len);
+-}
+-
+ /**
+ * objagg_hints_get - obtains hints instance
+ * @objagg: objagg instance
+@@ -955,7 +944,6 @@ struct objagg_hints *objagg_hints_get(struct objagg *objagg,
+ offsetof(struct objagg_hints_node, obj);
+ objagg_hints->ht_params.head_offset =
+ offsetof(struct objagg_hints_node, ht_node);
+- objagg_hints->ht_params.obj_cmpfn = objagg_hints_obj_cmp;
+
+ err = rhashtable_init(&objagg_hints->node_ht, &objagg_hints->ht_params);
+ if (err)
+diff --git a/lib/sbitmap.c b/lib/sbitmap.c
+index 1e453f825c05d..5e2e93307f0d0 100644
+--- a/lib/sbitmap.c
++++ b/lib/sbitmap.c
+@@ -60,12 +60,30 @@ static inline void update_alloc_hint_after_get(struct sbitmap *sb,
+ /*
+ * See if we have deferred clears that we can batch move
+ */
+-static inline bool sbitmap_deferred_clear(struct sbitmap_word *map)
++static inline bool sbitmap_deferred_clear(struct sbitmap_word *map,
++ unsigned int depth, unsigned int alloc_hint, bool wrap)
+ {
+- unsigned long mask;
++ unsigned long mask, word_mask;
+
+- if (!READ_ONCE(map->cleared))
+- return false;
++ guard(spinlock_irqsave)(&map->swap_lock);
++
++ if (!map->cleared) {
++ if (depth == 0)
++ return false;
++
++ word_mask = (~0UL) >> (BITS_PER_LONG - depth);
++ /*
++ * The current behavior is to always retry after moving
++ * ->cleared to word, and we change it to retry in case
++ * of any free bits. To avoid an infinite loop, we need
++ * to take wrap & alloc_hint into account, otherwise a
++ * soft lockup may occur.
++ */
++ if (!wrap && alloc_hint)
++ word_mask &= ~((1UL << alloc_hint) - 1);
++
++ return (READ_ONCE(map->word) & word_mask) != word_mask;
++ }
+
+ /*
+ * First get a stable cleared mask, setting the old mask to 0.
+@@ -85,6 +103,7 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
+ bool alloc_hint)
+ {
+ unsigned int bits_per_word;
++ int i;
+
+ if (shift < 0)
+ shift = sbitmap_calculate_shift(depth);
+@@ -116,6 +135,9 @@ int sbitmap_init_node(struct sbitmap *sb, unsigned int depth, int shift,
+ return -ENOMEM;
+ }
+
++ for (i = 0; i < sb->map_nr; i++)
++ spin_lock_init(&sb->map[i].swap_lock);
++
+ return 0;
+ }
+ EXPORT_SYMBOL_GPL(sbitmap_init_node);
+@@ -126,7 +148,7 @@ void sbitmap_resize(struct sbitmap *sb, unsigned int depth)
+ unsigned int i;
+
+ for (i = 0; i < sb->map_nr; i++)
+- sbitmap_deferred_clear(&sb->map[i]);
++ sbitmap_deferred_clear(&sb->map[i], 0, 0, 0);
+
+ sb->depth = depth;
+ sb->map_nr = DIV_ROUND_UP(sb->depth, bits_per_word);
+@@ -179,7 +201,7 @@ static int sbitmap_find_bit_in_word(struct sbitmap_word *map,
+ alloc_hint, wrap);
+ if (nr != -1)
+ break;
+- if (!sbitmap_deferred_clear(map))
++ if (!sbitmap_deferred_clear(map, depth, alloc_hint, wrap))
+ break;
+ } while (1);
+
+@@ -496,7 +518,7 @@ unsigned long __sbitmap_queue_get_batch(struct sbitmap_queue *sbq, int nr_tags,
+ unsigned int map_depth = __map_depth(sb, index);
+ unsigned long val;
+
+- sbitmap_deferred_clear(map);
++ sbitmap_deferred_clear(map, 0, 0, 0);
+ val = READ_ONCE(map->word);
+ if (val == (1UL << (map_depth - 1)) - 1)
+ goto next;
+diff --git a/mm/huge_memory.c b/mm/huge_memory.c
+index 2120f7478e55c..374a0d54b08df 100644
+--- a/mm/huge_memory.c
++++ b/mm/huge_memory.c
+@@ -88,9 +88,17 @@ unsigned long __thp_vma_allowable_orders(struct vm_area_struct *vma,
+ bool smaps = tva_flags & TVA_SMAPS;
+ bool in_pf = tva_flags & TVA_IN_PF;
+ bool enforce_sysfs = tva_flags & TVA_ENFORCE_SYSFS;
++ unsigned long supported_orders;
++
+ /* Check the intersection of requested and supported orders. */
+- orders &= vma_is_anonymous(vma) ?
+- THP_ORDERS_ALL_ANON : THP_ORDERS_ALL_FILE;
++ if (vma_is_anonymous(vma))
++ supported_orders = THP_ORDERS_ALL_ANON;
++ else if (vma_is_dax(vma))
++ supported_orders = THP_ORDERS_ALL_FILE_DAX;
++ else
++ supported_orders = THP_ORDERS_ALL_FILE_DEFAULT;
++
++ orders &= supported_orders;
+ if (!orders)
+ return 0;
+
+@@ -857,7 +865,7 @@ static unsigned long __thp_get_unmapped_area(struct file *filp,
+ loff_t off_align = round_up(off, size);
+ unsigned long len_pad, ret, off_sub;
+
+- if (IS_ENABLED(CONFIG_32BIT) || in_compat_syscall())
++ if (!IS_ENABLED(CONFIG_64BIT) || in_compat_syscall())
+ return 0;
+
+ if (off_end <= off_align || (off_end - off_align) < size)
+diff --git a/mm/hugetlb.c b/mm/hugetlb.c
+index 43e1af868cfdc..92a2e8dcb7965 100644
+--- a/mm/hugetlb.c
++++ b/mm/hugetlb.c
+@@ -2586,6 +2586,23 @@ struct folio *alloc_hugetlb_folio_nodemask(struct hstate *h, int preferred_nid,
+ return alloc_migrate_hugetlb_folio(h, gfp_mask, preferred_nid, nmask);
+ }
+
++static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
++{
++#ifdef CONFIG_NUMA
++ struct mempolicy *mpol = get_task_policy(current);
++
++ /*
++ * Only enforce MPOL_BIND policy which overlaps with cpuset policy
++ * (from policy_nodemask) specifically for hugetlb case
++ */
++ if (mpol->mode == MPOL_BIND &&
++ (apply_policy_zone(mpol, gfp_zone(gfp)) &&
++ cpuset_nodemask_valid_mems_allowed(&mpol->nodes)))
++ return &mpol->nodes;
++#endif
++ return NULL;
++}
++
+ /*
+ * Increase the hugetlb pool such that it can accommodate a reservation
+ * of size 'delta'.
+@@ -2599,6 +2616,8 @@ static int gather_surplus_pages(struct hstate *h, long delta)
+ long i;
+ long needed, allocated;
+ bool alloc_ok = true;
++ int node;
++ nodemask_t *mbind_nodemask = policy_mbind_nodemask(htlb_alloc_mask(h));
+
+ lockdep_assert_held(&hugetlb_lock);
+ needed = (h->resv_huge_pages + delta) - h->free_huge_pages;
+@@ -2613,8 +2632,15 @@ static int gather_surplus_pages(struct hstate *h, long delta)
+ retry:
+ spin_unlock_irq(&hugetlb_lock);
+ for (i = 0; i < needed; i++) {
+- folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
+- NUMA_NO_NODE, NULL);
++ folio = NULL;
++ for_each_node_mask(node, cpuset_current_mems_allowed) {
++ if (!mbind_nodemask || node_isset(node, *mbind_nodemask)) {
++ folio = alloc_surplus_hugetlb_folio(h, htlb_alloc_mask(h),
++ node, NULL);
++ if (folio)
++ break;
++ }
++ }
+ if (!folio) {
+ alloc_ok = false;
+ break;
+@@ -4617,7 +4643,7 @@ void __init hugetlb_add_hstate(unsigned int order)
+ BUG_ON(hugetlb_max_hstate >= HUGE_MAX_HSTATE);
+ BUG_ON(order < order_base_2(__NR_USED_SUBPAGE));
+ h = &hstates[hugetlb_max_hstate++];
+- mutex_init(&h->resize_lock);
++ __mutex_init(&h->resize_lock, "resize mutex", &h->resize_key);
+ h->order = order;
+ h->mask = ~(huge_page_size(h) - 1);
+ for (i = 0; i < MAX_NUMNODES; ++i)
+@@ -4840,23 +4866,6 @@ static int __init default_hugepagesz_setup(char *s)
+ }
+ __setup("default_hugepagesz=", default_hugepagesz_setup);
+
+-static nodemask_t *policy_mbind_nodemask(gfp_t gfp)
+-{
+-#ifdef CONFIG_NUMA
+- struct mempolicy *mpol = get_task_policy(current);
+-
+- /*
+- * Only enforce MPOL_BIND policy which overlaps with cpuset policy
+- * (from policy_nodemask) specifically for hugetlb case
+- */
+- if (mpol->mode == MPOL_BIND &&
+- (apply_policy_zone(mpol, gfp_zone(gfp)) &&
+- cpuset_nodemask_valid_mems_allowed(&mpol->nodes)))
+- return &mpol->nodes;
+-#endif
+- return NULL;
+-}
+-
+ static unsigned int allowed_mems_nr(struct hstate *h)
+ {
+ int node;
+diff --git a/mm/memory.c b/mm/memory.c
+index d10e616d73898..f81760c93801f 100644
+--- a/mm/memory.c
++++ b/mm/memory.c
+@@ -4681,7 +4681,7 @@ void set_pte_range(struct vm_fault *vmf, struct folio *folio,
+ {
+ struct vm_area_struct *vma = vmf->vma;
+ bool write = vmf->flags & FAULT_FLAG_WRITE;
+- bool prefault = in_range(vmf->address, addr, nr * PAGE_SIZE);
++ bool prefault = !in_range(vmf->address, addr, nr * PAGE_SIZE);
+ pte_t entry;
+
+ flush_icache_pages(vma, page, nr);
+diff --git a/mm/mempolicy.c b/mm/mempolicy.c
+index aec756ae56377..a1bf9aa15c337 100644
+--- a/mm/mempolicy.c
++++ b/mm/mempolicy.c
+@@ -3293,8 +3293,9 @@ int mpol_parse_str(char *str, struct mempolicy **mpol)
+ * @pol: pointer to mempolicy to be formatted
+ *
+ * Convert @pol into a string. If @buffer is too short, truncate the string.
+- * Recommend a @maxlen of at least 32 for the longest mode, "interleave", the
+- * longest flag, "relative", and to display at least a few node ids.
++ * Recommend a @maxlen of at least 51 for the longest mode, "weighted
++ * interleave", plus the longest flag flags, "relative|balancing", and to
++ * display at least a few node ids.
+ */
+ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+ {
+@@ -3303,7 +3304,10 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+ unsigned short mode = MPOL_DEFAULT;
+ unsigned short flags = 0;
+
+- if (pol && pol != &default_policy && !(pol->flags & MPOL_F_MORON)) {
++ if (pol &&
++ pol != &default_policy &&
++ !(pol >= &preferred_node_policy[0] &&
++ pol <= &preferred_node_policy[ARRAY_SIZE(preferred_node_policy) - 1])) {
+ mode = pol->mode;
+ flags = pol->flags;
+ }
+@@ -3331,12 +3335,18 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+ p += snprintf(p, buffer + maxlen - p, "=");
+
+ /*
+- * Currently, the only defined flags are mutually exclusive
++ * Static and relative are mutually exclusive.
+ */
+ if (flags & MPOL_F_STATIC_NODES)
+ p += snprintf(p, buffer + maxlen - p, "static");
+ else if (flags & MPOL_F_RELATIVE_NODES)
+ p += snprintf(p, buffer + maxlen - p, "relative");
++
++ if (flags & MPOL_F_NUMA_BALANCING) {
++ if (!is_power_of_2(flags & MPOL_MODE_FLAGS))
++ p += snprintf(p, buffer + maxlen - p, "|");
++ p += snprintf(p, buffer + maxlen - p, "balancing");
++ }
+ }
+
+ if (!nodes_empty(nodes))
+diff --git a/mm/mmap_lock.c b/mm/mmap_lock.c
+index 1854850b4b897..368b840e75082 100644
+--- a/mm/mmap_lock.c
++++ b/mm/mmap_lock.c
+@@ -19,14 +19,7 @@ EXPORT_TRACEPOINT_SYMBOL(mmap_lock_released);
+
+ #ifdef CONFIG_MEMCG
+
+-/*
+- * Our various events all share the same buffer (because we don't want or need
+- * to allocate a set of buffers *per event type*), so we need to protect against
+- * concurrent _reg() and _unreg() calls, and count how many _reg() calls have
+- * been made.
+- */
+-static DEFINE_MUTEX(reg_lock);
+-static int reg_refcount; /* Protected by reg_lock. */
++static atomic_t reg_refcount;
+
+ /*
+ * Size of the buffer for memcg path names. Ignoring stack trace support,
+@@ -34,136 +27,22 @@ static int reg_refcount; /* Protected by reg_lock. */
+ */
+ #define MEMCG_PATH_BUF_SIZE MAX_FILTER_STR_VAL
+
+-/*
+- * How many contexts our trace events might be called in: normal, softirq, irq,
+- * and NMI.
+- */
+-#define CONTEXT_COUNT 4
+-
+-struct memcg_path {
+- local_lock_t lock;
+- char __rcu *buf;
+- local_t buf_idx;
+-};
+-static DEFINE_PER_CPU(struct memcg_path, memcg_paths) = {
+- .lock = INIT_LOCAL_LOCK(lock),
+- .buf_idx = LOCAL_INIT(0),
+-};
+-
+-static char **tmp_bufs;
+-
+-/* Called with reg_lock held. */
+-static void free_memcg_path_bufs(void)
+-{
+- struct memcg_path *memcg_path;
+- int cpu;
+- char **old = tmp_bufs;
+-
+- for_each_possible_cpu(cpu) {
+- memcg_path = per_cpu_ptr(&memcg_paths, cpu);
+- *(old++) = rcu_dereference_protected(memcg_path->buf,
+- lockdep_is_held(®_lock));
+- rcu_assign_pointer(memcg_path->buf, NULL);
+- }
+-
+- /* Wait for inflight memcg_path_buf users to finish. */
+- synchronize_rcu();
+-
+- old = tmp_bufs;
+- for_each_possible_cpu(cpu) {
+- kfree(*(old++));
+- }
+-
+- kfree(tmp_bufs);
+- tmp_bufs = NULL;
+-}
+-
+ int trace_mmap_lock_reg(void)
+ {
+- int cpu;
+- char *new;
+-
+- mutex_lock(®_lock);
+-
+- /* If the refcount is going 0->1, proceed with allocating buffers. */
+- if (reg_refcount++)
+- goto out;
+-
+- tmp_bufs = kmalloc_array(num_possible_cpus(), sizeof(*tmp_bufs),
+- GFP_KERNEL);
+- if (tmp_bufs == NULL)
+- goto out_fail;
+-
+- for_each_possible_cpu(cpu) {
+- new = kmalloc(MEMCG_PATH_BUF_SIZE * CONTEXT_COUNT, GFP_KERNEL);
+- if (new == NULL)
+- goto out_fail_free;
+- rcu_assign_pointer(per_cpu_ptr(&memcg_paths, cpu)->buf, new);
+- /* Don't need to wait for inflights, they'd have gotten NULL. */
+- }
+-
+-out:
+- mutex_unlock(®_lock);
++ atomic_inc(®_refcount);
+ return 0;
+-
+-out_fail_free:
+- free_memcg_path_bufs();
+-out_fail:
+- /* Since we failed, undo the earlier ref increment. */
+- --reg_refcount;
+-
+- mutex_unlock(®_lock);
+- return -ENOMEM;
+ }
+
+ void trace_mmap_lock_unreg(void)
+ {
+- mutex_lock(®_lock);
+-
+- /* If the refcount is going 1->0, proceed with freeing buffers. */
+- if (--reg_refcount)
+- goto out;
+-
+- free_memcg_path_bufs();
+-
+-out:
+- mutex_unlock(®_lock);
+-}
+-
+-static inline char *get_memcg_path_buf(void)
+-{
+- struct memcg_path *memcg_path = this_cpu_ptr(&memcg_paths);
+- char *buf;
+- int idx;
+-
+- rcu_read_lock();
+- buf = rcu_dereference(memcg_path->buf);
+- if (buf == NULL) {
+- rcu_read_unlock();
+- return NULL;
+- }
+- idx = local_add_return(MEMCG_PATH_BUF_SIZE, &memcg_path->buf_idx) -
+- MEMCG_PATH_BUF_SIZE;
+- return &buf[idx];
++ atomic_dec(®_refcount);
+ }
+
+-static inline void put_memcg_path_buf(void)
+-{
+- local_sub(MEMCG_PATH_BUF_SIZE, &this_cpu_ptr(&memcg_paths)->buf_idx);
+- rcu_read_unlock();
+-}
+-
+-#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
+- do { \
+- const char *memcg_path; \
+- local_lock(&memcg_paths.lock); \
+- memcg_path = get_mm_memcg_path(mm); \
+- trace_mmap_lock_##type(mm, \
+- memcg_path != NULL ? memcg_path : "", \
+- ##__VA_ARGS__); \
+- if (likely(memcg_path != NULL)) \
+- put_memcg_path_buf(); \
+- local_unlock(&memcg_paths.lock); \
++#define TRACE_MMAP_LOCK_EVENT(type, mm, ...) \
++ do { \
++ char buf[MEMCG_PATH_BUF_SIZE]; \
++ get_mm_memcg_path(mm, buf, sizeof(buf)); \
++ trace_mmap_lock_##type(mm, buf, ##__VA_ARGS__); \
+ } while (0)
+
+ #else /* !CONFIG_MEMCG */
+@@ -185,37 +64,23 @@ void trace_mmap_lock_unreg(void)
+ #ifdef CONFIG_TRACING
+ #ifdef CONFIG_MEMCG
+ /*
+- * Write the given mm_struct's memcg path to a percpu buffer, and return a
+- * pointer to it. If the path cannot be determined, or no buffer was available
+- * (because the trace event is being unregistered), NULL is returned.
+- *
+- * Note: buffers are allocated per-cpu to avoid locking, so preemption must be
+- * disabled by the caller before calling us, and re-enabled only after the
+- * caller is done with the pointer.
+- *
+- * The caller must call put_memcg_path_buf() once the buffer is no longer
+- * needed. This must be done while preemption is still disabled.
++ * Write the given mm_struct's memcg path to a buffer. If the path cannot be
++ * determined or the trace event is being unregistered, empty string is written.
+ */
+-static const char *get_mm_memcg_path(struct mm_struct *mm)
++static void get_mm_memcg_path(struct mm_struct *mm, char *buf, size_t buflen)
+ {
+- char *buf = NULL;
+- struct mem_cgroup *memcg = get_mem_cgroup_from_mm(mm);
++ struct mem_cgroup *memcg;
+
++ buf[0] = '\0';
++ /* No need to get path if no trace event is registered. */
++ if (!atomic_read(®_refcount))
++ return;
++ memcg = get_mem_cgroup_from_mm(mm);
+ if (memcg == NULL)
+- goto out;
+- if (unlikely(memcg->css.cgroup == NULL))
+- goto out_put;
+-
+- buf = get_memcg_path_buf();
+- if (buf == NULL)
+- goto out_put;
+-
+- cgroup_path(memcg->css.cgroup, buf, MEMCG_PATH_BUF_SIZE);
+-
+-out_put:
++ return;
++ if (memcg->css.cgroup)
++ cgroup_path(memcg->css.cgroup, buf, buflen);
+ css_put(&memcg->css);
+-out:
+- return buf;
+ }
+
+ #endif /* CONFIG_MEMCG */
+diff --git a/mm/page_alloc.c b/mm/page_alloc.c
+index 9ecf99190ea20..df2c442f1c47b 100644
+--- a/mm/page_alloc.c
++++ b/mm/page_alloc.c
+@@ -2323,16 +2323,20 @@ void drain_zone_pages(struct zone *zone, struct per_cpu_pages *pcp)
+ static void drain_pages_zone(unsigned int cpu, struct zone *zone)
+ {
+ struct per_cpu_pages *pcp = per_cpu_ptr(zone->per_cpu_pageset, cpu);
+- int count = READ_ONCE(pcp->count);
+-
+- while (count) {
+- int to_drain = min(count, pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
+- count -= to_drain;
++ int count;
+
++ do {
+ spin_lock(&pcp->lock);
+- free_pcppages_bulk(zone, to_drain, pcp, 0);
++ count = pcp->count;
++ if (count) {
++ int to_drain = min(count,
++ pcp->batch << CONFIG_PCP_BATCH_SCALE_MAX);
++
++ free_pcppages_bulk(zone, to_drain, pcp, 0);
++ count -= to_drain;
++ }
+ spin_unlock(&pcp->lock);
+- }
++ } while (count);
+ }
+
+ /*
+@@ -5805,6 +5809,23 @@ unsigned long free_reserved_area(void *start, void *end, int poison, const char
+ return pages;
+ }
+
++void free_reserved_page(struct page *page)
++{
++ if (mem_alloc_profiling_enabled()) {
++ union codetag_ref *ref = get_page_tag_ref(page);
++
++ if (ref) {
++ set_codetag_empty(ref);
++ put_page_tag_ref(ref);
++ }
++ }
++ ClearPageReserved(page);
++ init_page_count(page);
++ __free_page(page);
++ adjust_managed_page_count(page, 1);
++}
++EXPORT_SYMBOL(free_reserved_page);
++
+ static int page_alloc_cpu_dead(unsigned int cpu)
+ {
+ struct zone *zone;
+diff --git a/mm/vmscan.c b/mm/vmscan.c
+index 2e34de9cd0d4f..68ac33bea3a3c 100644
+--- a/mm/vmscan.c
++++ b/mm/vmscan.c
+@@ -3900,6 +3900,32 @@ static bool try_to_inc_max_seq(struct lruvec *lruvec, unsigned long seq,
+ * working set protection
+ ******************************************************************************/
+
++static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc)
++{
++ int priority;
++ unsigned long reclaimable;
++
++ if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
++ return;
++ /*
++ * Determine the initial priority based on
++ * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
++ * where reclaimed_to_scanned_ratio = inactive / total.
++ */
++ reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
++ if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
++ reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
++
++ /* round down reclaimable and round up sc->nr_to_reclaim */
++ priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
++
++ /*
++ * The estimation is based on LRU pages only, so cap it to prevent
++ * overshoots of shrinker objects by large margins.
++ */
++ sc->priority = clamp(priority, DEF_PRIORITY / 2, DEF_PRIORITY);
++}
++
+ static bool lruvec_is_sizable(struct lruvec *lruvec, struct scan_control *sc)
+ {
+ int gen, type, zone;
+@@ -3933,19 +3959,17 @@ static bool lruvec_is_reclaimable(struct lruvec *lruvec, struct scan_control *sc
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ DEFINE_MIN_SEQ(lruvec);
+
+- /* see the comment on lru_gen_folio */
+- gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
+- birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
+-
+- if (time_is_after_jiffies(birth + min_ttl))
++ if (mem_cgroup_below_min(NULL, memcg))
+ return false;
+
+ if (!lruvec_is_sizable(lruvec, sc))
+ return false;
+
+- mem_cgroup_calculate_protection(NULL, memcg);
++ /* see the comment on lru_gen_folio */
++ gen = lru_gen_from_seq(min_seq[LRU_GEN_FILE]);
++ birth = READ_ONCE(lruvec->lrugen.timestamps[gen]);
+
+- return !mem_cgroup_below_min(NULL, memcg);
++ return time_is_before_jiffies(birth + min_ttl);
+ }
+
+ /* to protect the working set of the last N jiffies */
+@@ -3955,23 +3979,20 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+ {
+ struct mem_cgroup *memcg;
+ unsigned long min_ttl = READ_ONCE(lru_gen_min_ttl);
++ bool reclaimable = !min_ttl;
+
+ VM_WARN_ON_ONCE(!current_is_kswapd());
+
+- /* check the order to exclude compaction-induced reclaim */
+- if (!min_ttl || sc->order || sc->priority == DEF_PRIORITY)
+- return;
++ set_initial_priority(pgdat, sc);
+
+ memcg = mem_cgroup_iter(NULL, NULL, NULL);
+ do {
+ struct lruvec *lruvec = mem_cgroup_lruvec(memcg, pgdat);
+
+- if (lruvec_is_reclaimable(lruvec, sc, min_ttl)) {
+- mem_cgroup_iter_break(NULL, memcg);
+- return;
+- }
++ mem_cgroup_calculate_protection(NULL, memcg);
+
+- cond_resched();
++ if (!reclaimable)
++ reclaimable = lruvec_is_reclaimable(lruvec, sc, min_ttl);
+ } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)));
+
+ /*
+@@ -3979,7 +4000,7 @@ static void lru_gen_age_node(struct pglist_data *pgdat, struct scan_control *sc)
+ * younger than min_ttl. However, another possibility is all memcgs are
+ * either too small or below min.
+ */
+- if (mutex_trylock(&oom_lock)) {
++ if (!reclaimable && mutex_trylock(&oom_lock)) {
+ struct oom_control oc = {
+ .gfp_mask = sc->gfp_mask,
+ };
+@@ -4582,7 +4603,6 @@ static int evict_folios(struct lruvec *lruvec, struct scan_control *sc, int swap
+
+ /* retry folios that may have missed folio_rotate_reclaimable() */
+ list_move(&folio->lru, &clean);
+- sc->nr_scanned -= folio_nr_pages(folio);
+ }
+
+ spin_lock_irq(&lruvec->lru_lock);
+@@ -4772,8 +4792,7 @@ static int shrink_one(struct lruvec *lruvec, struct scan_control *sc)
+ struct mem_cgroup *memcg = lruvec_memcg(lruvec);
+ struct pglist_data *pgdat = lruvec_pgdat(lruvec);
+
+- mem_cgroup_calculate_protection(NULL, memcg);
+-
++ /* lru_gen_age_node() called mem_cgroup_calculate_protection() */
+ if (mem_cgroup_below_min(NULL, memcg))
+ return MEMCG_LRU_YOUNG;
+
+@@ -4897,28 +4916,6 @@ static void lru_gen_shrink_lruvec(struct lruvec *lruvec, struct scan_control *sc
+ blk_finish_plug(&plug);
+ }
+
+-static void set_initial_priority(struct pglist_data *pgdat, struct scan_control *sc)
+-{
+- int priority;
+- unsigned long reclaimable;
+-
+- if (sc->priority != DEF_PRIORITY || sc->nr_to_reclaim < MIN_LRU_BATCH)
+- return;
+- /*
+- * Determine the initial priority based on
+- * (total >> priority) * reclaimed_to_scanned_ratio = nr_to_reclaim,
+- * where reclaimed_to_scanned_ratio = inactive / total.
+- */
+- reclaimable = node_page_state(pgdat, NR_INACTIVE_FILE);
+- if (can_reclaim_anon_pages(NULL, pgdat->node_id, sc))
+- reclaimable += node_page_state(pgdat, NR_INACTIVE_ANON);
+-
+- /* round down reclaimable and round up sc->nr_to_reclaim */
+- priority = fls_long(reclaimable) - 1 - fls_long(sc->nr_to_reclaim - 1);
+-
+- sc->priority = clamp(priority, 0, DEF_PRIORITY);
+-}
+-
+ static void lru_gen_shrink_node(struct pglist_data *pgdat, struct scan_control *sc)
+ {
+ struct blk_plug plug;
+@@ -6702,6 +6699,7 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
+ {
+ struct zone *zone;
+ int z;
++ unsigned long nr_reclaimed = sc->nr_reclaimed;
+
+ /* Reclaim a number of pages proportional to the number of zones */
+ sc->nr_to_reclaim = 0;
+@@ -6729,7 +6727,8 @@ static bool kswapd_shrink_node(pg_data_t *pgdat,
+ if (sc->order && sc->nr_reclaimed >= compact_gap(sc->order))
+ sc->order = 0;
+
+- return sc->nr_scanned >= sc->nr_to_reclaim;
++ /* account for progress from mm_account_reclaimed_pages() */
++ return max(sc->nr_scanned, sc->nr_reclaimed - nr_reclaimed) >= sc->nr_to_reclaim;
+ }
+
+ /* Page allocator PCP high watermark is lowered if reclaim is active. */
+diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c
+index c644b30977bd8..7ae118a6d947b 100644
+--- a/net/bluetooth/hci_core.c
++++ b/net/bluetooth/hci_core.c
+@@ -718,8 +718,8 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
+
+ switch (cmd) {
+ case HCISETAUTH:
+- err = __hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE,
+- 1, &dr.dev_opt, HCI_CMD_TIMEOUT);
++ err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_AUTH_ENABLE,
++ 1, &dr.dev_opt, HCI_CMD_TIMEOUT);
+ break;
+
+ case HCISETENCRYPT:
+@@ -730,23 +730,21 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
+
+ if (!test_bit(HCI_AUTH, &hdev->flags)) {
+ /* Auth must be enabled first */
+- err = __hci_cmd_sync_status(hdev,
+- HCI_OP_WRITE_AUTH_ENABLE,
+- 1, &dr.dev_opt,
+- HCI_CMD_TIMEOUT);
++ err = hci_cmd_sync_status(hdev,
++ HCI_OP_WRITE_AUTH_ENABLE,
++ 1, &dr.dev_opt,
++ HCI_CMD_TIMEOUT);
+ if (err)
+ break;
+ }
+
+- err = __hci_cmd_sync_status(hdev, HCI_OP_WRITE_ENCRYPT_MODE,
+- 1, &dr.dev_opt,
+- HCI_CMD_TIMEOUT);
++ err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_ENCRYPT_MODE,
++ 1, &dr.dev_opt, HCI_CMD_TIMEOUT);
+ break;
+
+ case HCISETSCAN:
+- err = __hci_cmd_sync_status(hdev, HCI_OP_WRITE_SCAN_ENABLE,
+- 1, &dr.dev_opt,
+- HCI_CMD_TIMEOUT);
++ err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_SCAN_ENABLE,
++ 1, &dr.dev_opt, HCI_CMD_TIMEOUT);
+
+ /* Ensure that the connectable and discoverable states
+ * get correctly modified as this was a non-mgmt change.
+@@ -758,9 +756,8 @@ int hci_dev_cmd(unsigned int cmd, void __user *arg)
+ case HCISETLINKPOL:
+ policy = cpu_to_le16(dr.dev_opt);
+
+- err = __hci_cmd_sync_status(hdev, HCI_OP_WRITE_DEF_LINK_POLICY,
+- 2, &policy,
+- HCI_CMD_TIMEOUT);
++ err = hci_cmd_sync_status(hdev, HCI_OP_WRITE_DEF_LINK_POLICY,
++ 2, &policy, HCI_CMD_TIMEOUT);
+ break;
+
+ case HCISETLINKMODE:
+diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c
+index 93f7ac905cece..4611a67d7dcc3 100644
+--- a/net/bluetooth/hci_event.c
++++ b/net/bluetooth/hci_event.c
+@@ -6988,6 +6988,8 @@ static void hci_le_big_info_adv_report_evt(struct hci_dev *hdev, void *data,
+ if (!pa_sync)
+ goto unlock;
+
++ pa_sync->iso_qos.bcast.encryption = ev->encryption;
++
+ /* Notify iso layer */
+ hci_connect_cfm(pa_sync, 0);
+
+diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c
+index eea34e6a236fd..bb704088559fb 100644
+--- a/net/bluetooth/hci_sync.c
++++ b/net/bluetooth/hci_sync.c
+@@ -371,8 +371,6 @@ static void le_scan_disable(struct work_struct *work)
+ goto _return;
+ }
+
+- hdev->discovery.scan_start = 0;
+-
+ /* If we were running LE only scan, change discovery state. If
+ * we were running both LE and BR/EDR inquiry simultaneously,
+ * and BR/EDR inquiry is already finished, stop discovery,
+diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c
+index d97064d460dc7..e19b583ff2c6d 100644
+--- a/net/bridge/br_forward.c
++++ b/net/bridge/br_forward.c
+@@ -25,8 +25,8 @@ static inline int should_deliver(const struct net_bridge_port *p,
+
+ vg = nbp_vlan_group_rcu(p);
+ return ((p->flags & BR_HAIRPIN_MODE) || skb->dev != p->dev) &&
+- p->state == BR_STATE_FORWARDING && br_allowed_egress(vg, skb) &&
+- nbp_switchdev_allowed_egress(p, skb) &&
++ (br_mst_is_enabled(p->br) || p->state == BR_STATE_FORWARDING) &&
++ br_allowed_egress(vg, skb) && nbp_switchdev_allowed_egress(p, skb) &&
+ !br_skb_isolated(p, skb);
+ }
+
+diff --git a/net/core/filter.c b/net/core/filter.c
+index 9933851c685e7..110692c1dd95a 100644
+--- a/net/core/filter.c
++++ b/net/core/filter.c
+@@ -3544,13 +3544,20 @@ static int bpf_skb_net_grow(struct sk_buff *skb, u32 off, u32 len_diff,
+ if (skb_is_gso(skb)) {
+ struct skb_shared_info *shinfo = skb_shinfo(skb);
+
+- /* Due to header grow, MSS needs to be downgraded. */
+- if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO))
+- skb_decrease_gso_size(shinfo, len_diff);
+-
+ /* Header must be checked, and gso_segs recomputed. */
+ shinfo->gso_type |= gso_type;
+ shinfo->gso_segs = 0;
++
++ /* Due to header growth, MSS needs to be downgraded.
++ * There is a BUG_ON() when segmenting the frag_list with
++ * head_frag true, so linearize the skb after downgrading
++ * the MSS.
++ */
++ if (!(flags & BPF_F_ADJ_ROOM_FIXED_GSO)) {
++ skb_decrease_gso_size(shinfo, len_diff);
++ if (shinfo->frag_list)
++ return skb_linearize(skb);
++ }
+ }
+
+ return 0;
+diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c
+index f82e9a7d3b379..7b54f44f5372a 100644
+--- a/net/core/flow_dissector.c
++++ b/net/core/flow_dissector.c
+@@ -1101,7 +1101,7 @@ bool __skb_flow_dissect(const struct net *net,
+ }
+ }
+
+- WARN_ON_ONCE(!net);
++ DEBUG_NET_WARN_ON_ONCE(!net);
+ if (net) {
+ enum netns_bpf_attach_type type = NETNS_BPF_FLOW_DISSECTOR;
+ struct bpf_prog_array *run_array;
+diff --git a/net/core/page_pool.c b/net/core/page_pool.c
+index f4444b4e39e63..3772eb63dcad1 100644
+--- a/net/core/page_pool.c
++++ b/net/core/page_pool.c
+@@ -445,7 +445,7 @@ static bool page_pool_dma_map(struct page_pool *pool, struct page *page)
+ return true;
+
+ unmap_failed:
+- WARN_ON_ONCE("unexpected DMA address, please report to netdev@");
++ WARN_ONCE(1, "unexpected DMA address, please report to netdev@");
+ dma_unmap_page_attrs(pool->p.dev, dma,
+ PAGE_SIZE << pool->p.order, pool->p.dma_dir,
+ DMA_ATTR_SKIP_CPU_SYNC | DMA_ATTR_WEAK_ORDERING);
+diff --git a/net/core/xdp.c b/net/core/xdp.c
+index 022c12059cf2f..bcc5551c6424b 100644
+--- a/net/core/xdp.c
++++ b/net/core/xdp.c
+@@ -127,10 +127,8 @@ void xdp_unreg_mem_model(struct xdp_mem_info *mem)
+ return;
+
+ if (type == MEM_TYPE_PAGE_POOL) {
+- rcu_read_lock();
+- xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params);
++ xa = rhashtable_lookup_fast(mem_id_ht, &id, mem_id_rht_params);
+ page_pool_destroy(xa->page_pool);
+- rcu_read_unlock();
+ }
+ }
+ EXPORT_SYMBOL_GPL(xdp_unreg_mem_model);
+diff --git a/net/ethtool/pse-pd.c b/net/ethtool/pse-pd.c
+index 2c981d443f27e..776ac96cdadc9 100644
+--- a/net/ethtool/pse-pd.c
++++ b/net/ethtool/pse-pd.c
+@@ -178,12 +178,14 @@ ethnl_set_pse(struct ethnl_req_info *req_info, struct genl_info *info)
+
+ phydev = dev->phydev;
+ /* These values are already validated by the ethnl_pse_set_policy */
+- if (pse_has_podl(phydev->psec))
++ if (tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL])
+ config.podl_admin_control = nla_get_u32(tb[ETHTOOL_A_PODL_PSE_ADMIN_CONTROL]);
+- if (pse_has_c33(phydev->psec))
++ if (tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL])
+ config.c33_admin_control = nla_get_u32(tb[ETHTOOL_A_C33_PSE_ADMIN_CONTROL]);
+
+- /* Return errno directly - PSE has no notification */
++ /* Return errno directly - PSE has no notification
++ * pse_ethtool_set_config() will do nothing if the config is null
++ */
+ return pse_ethtool_set_config(phydev->psec, info->extack, &config);
+ }
+
+diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c
+index 3968d3f98e083..619a4df7be1e8 100644
+--- a/net/ipv4/esp4.c
++++ b/net/ipv4/esp4.c
+@@ -239,8 +239,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+ #else
+ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+ {
+- kfree_skb(skb);
+-
++ WARN_ON(1);
+ return -EOPNOTSUPP;
+ }
+ #endif
+diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c
+index b3271957ad9a0..3f28ecbdcaef1 100644
+--- a/net/ipv4/esp4_offload.c
++++ b/net/ipv4/esp4_offload.c
+@@ -56,6 +56,13 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head,
+ x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
+ (xfrm_address_t *)&ip_hdr(skb)->daddr,
+ spi, IPPROTO_ESP, AF_INET);
++
++ if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) {
++ /* non-offload path will record the error and audit log */
++ xfrm_state_put(x);
++ x = NULL;
++ }
++
+ if (!x)
+ goto out_reset;
+
+diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c
+index f669da98d11d8..8956026bc0a2c 100644
+--- a/net/ipv4/fib_semantics.c
++++ b/net/ipv4/fib_semantics.c
+@@ -2270,6 +2270,15 @@ void fib_select_path(struct net *net, struct fib_result *res,
+ fib_select_default(fl4, res);
+
+ check_saddr:
+- if (!fl4->saddr)
+- fl4->saddr = fib_result_prefsrc(net, res);
++ if (!fl4->saddr) {
++ struct net_device *l3mdev;
++
++ l3mdev = dev_get_by_index_rcu(net, fl4->flowi4_l3mdev);
++
++ if (!l3mdev ||
++ l3mdev_master_dev_rcu(FIB_RES_DEV(*res)) == l3mdev)
++ fl4->saddr = fib_result_prefsrc(net, res);
++ else
++ fl4->saddr = inet_select_addr(l3mdev, 0, RT_SCOPE_LINK);
++ }
+ }
+diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c
+index f474106464d2f..8f30e3f00b7f2 100644
+--- a/net/ipv4/fib_trie.c
++++ b/net/ipv4/fib_trie.c
+@@ -1629,6 +1629,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp,
+ res->nhc = nhc;
+ res->type = fa->fa_type;
+ res->scope = fi->fib_scope;
++ res->dscp = fa->fa_dscp;
+ res->fi = fi;
+ res->table = tb;
+ res->fa_head = &n->leaf;
+diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c
+index 535856b0f0edc..6b9787ee86017 100644
+--- a/net/ipv4/nexthop.c
++++ b/net/ipv4/nexthop.c
+@@ -888,9 +888,10 @@ static int nla_put_nh_group(struct sk_buff *skb, struct nexthop *nh,
+
+ p = nla_data(nla);
+ for (i = 0; i < nhg->num_nh; ++i) {
+- p->id = nhg->nh_entries[i].nh->id;
+- p->weight = nhg->nh_entries[i].weight - 1;
+- p += 1;
++ *p++ = (struct nexthop_grp) {
++ .id = nhg->nh_entries[i].nh->id,
++ .weight = nhg->nh_entries[i].weight - 1,
++ };
+ }
+
+ if (nhg->resilient && nla_put_nh_group_res(skb, nhg))
+diff --git a/net/ipv4/route.c b/net/ipv4/route.c
+index b3073d1c8f8f7..990912fa18e85 100644
+--- a/net/ipv4/route.c
++++ b/net/ipv4/route.c
+@@ -1263,7 +1263,7 @@ void ip_rt_get_source(u8 *addr, struct sk_buff *skb, struct rtable *rt)
+ struct flowi4 fl4 = {
+ .daddr = iph->daddr,
+ .saddr = iph->saddr,
+- .flowi4_tos = RT_TOS(iph->tos),
++ .flowi4_tos = iph->tos & IPTOS_RT_MASK,
+ .flowi4_oif = rt->dst.dev->ifindex,
+ .flowi4_iif = skb->dev->ifindex,
+ .flowi4_mark = skb->mark,
+@@ -2868,9 +2868,9 @@ EXPORT_SYMBOL_GPL(ip_route_output_flow);
+
+ /* called with rcu_read_lock held */
+ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
+- struct rtable *rt, u32 table_id, struct flowi4 *fl4,
+- struct sk_buff *skb, u32 portid, u32 seq,
+- unsigned int flags)
++ struct rtable *rt, u32 table_id, dscp_t dscp,
++ struct flowi4 *fl4, struct sk_buff *skb, u32 portid,
++ u32 seq, unsigned int flags)
+ {
+ struct rtmsg *r;
+ struct nlmsghdr *nlh;
+@@ -2886,7 +2886,7 @@ static int rt_fill_info(struct net *net, __be32 dst, __be32 src,
+ r->rtm_family = AF_INET;
+ r->rtm_dst_len = 32;
+ r->rtm_src_len = 0;
+- r->rtm_tos = fl4 ? fl4->flowi4_tos : 0;
++ r->rtm_tos = inet_dscp_to_dsfield(dscp);
+ r->rtm_table = table_id < 256 ? table_id : RT_TABLE_COMPAT;
+ if (nla_put_u32(skb, RTA_TABLE, table_id))
+ goto nla_put_failure;
+@@ -3036,7 +3036,7 @@ static int fnhe_dump_bucket(struct net *net, struct sk_buff *skb,
+ goto next;
+
+ err = rt_fill_info(net, fnhe->fnhe_daddr, 0, rt,
+- table_id, NULL, skb,
++ table_id, 0, NULL, skb,
+ NETLINK_CB(cb->skb).portid,
+ cb->nlh->nlmsg_seq, flags);
+ if (err)
+@@ -3332,7 +3332,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+ fri.tb_id = table_id;
+ fri.dst = res.prefix;
+ fri.dst_len = res.prefixlen;
+- fri.dscp = inet_dsfield_to_dscp(fl4.flowi4_tos);
++ fri.dscp = res.dscp;
+ fri.type = rt->rt_type;
+ fri.offload = 0;
+ fri.trap = 0;
+@@ -3359,8 +3359,8 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh,
+ err = fib_dump_info(skb, NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0);
+ } else {
+- err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb,
+- NETLINK_CB(in_skb).portid,
++ err = rt_fill_info(net, dst, src, rt, table_id, res.dscp, &fl4,
++ skb, NETLINK_CB(in_skb).portid,
+ nlh->nlmsg_seq, 0);
+ }
+ if (err < 0)
+diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
+index e6790ea748773..ec6911034138f 100644
+--- a/net/ipv4/tcp.c
++++ b/net/ipv4/tcp.c
+@@ -598,7 +598,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait)
+ */
+ mask |= EPOLLOUT | EPOLLWRNORM;
+ }
+- /* This barrier is coupled with smp_wmb() in tcp_reset() */
++ /* This barrier is coupled with smp_wmb() in tcp_done_with_error() */
+ smp_rmb();
+ if (READ_ONCE(sk->sk_err) ||
+ !skb_queue_empty_lockless(&sk->sk_error_queue))
+@@ -4583,14 +4583,10 @@ int tcp_abort(struct sock *sk, int err)
+ bh_lock_sock(sk);
+
+ if (!sock_flag(sk, SOCK_DEAD)) {
+- WRITE_ONCE(sk->sk_err, err);
+- /* This barrier is coupled with smp_rmb() in tcp_poll() */
+- smp_wmb();
+- sk_error_report(sk);
+ if (tcp_need_reset(sk->sk_state))
+ tcp_send_active_reset(sk, GFP_ATOMIC,
+ SK_RST_REASON_NOT_SPECIFIED);
+- tcp_done(sk);
++ tcp_done_with_error(sk, err);
+ }
+
+ bh_unlock_sock(sk);
+diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c
+index 38da23f991d60..570e87ad9a56e 100644
+--- a/net/ipv4/tcp_input.c
++++ b/net/ipv4/tcp_input.c
+@@ -4469,9 +4469,26 @@ static enum skb_drop_reason tcp_sequence(const struct tcp_sock *tp,
+ return SKB_NOT_DROPPED_YET;
+ }
+
++
++void tcp_done_with_error(struct sock *sk, int err)
++{
++ /* This barrier is coupled with smp_rmb() in tcp_poll() */
++ WRITE_ONCE(sk->sk_err, err);
++ smp_wmb();
++
++ tcp_write_queue_purge(sk);
++ tcp_done(sk);
++
++ if (!sock_flag(sk, SOCK_DEAD))
++ sk_error_report(sk);
++}
++EXPORT_SYMBOL(tcp_done_with_error);
++
+ /* When we get a reset we do this. */
+ void tcp_reset(struct sock *sk, struct sk_buff *skb)
+ {
++ int err;
++
+ trace_tcp_receive_reset(sk);
+
+ /* mptcp can't tell us to ignore reset pkts,
+@@ -4483,24 +4500,17 @@ void tcp_reset(struct sock *sk, struct sk_buff *skb)
+ /* We want the right error as BSD sees it (and indeed as we do). */
+ switch (sk->sk_state) {
+ case TCP_SYN_SENT:
+- WRITE_ONCE(sk->sk_err, ECONNREFUSED);
++ err = ECONNREFUSED;
+ break;
+ case TCP_CLOSE_WAIT:
+- WRITE_ONCE(sk->sk_err, EPIPE);
++ err = EPIPE;
+ break;
+ case TCP_CLOSE:
+ return;
+ default:
+- WRITE_ONCE(sk->sk_err, ECONNRESET);
++ err = ECONNRESET;
+ }
+- /* This barrier is coupled with smp_rmb() in tcp_poll() */
+- smp_wmb();
+-
+- tcp_write_queue_purge(sk);
+- tcp_done(sk);
+-
+- if (!sock_flag(sk, SOCK_DEAD))
+- sk_error_report(sk);
++ tcp_done_with_error(sk, err);
+ }
+
+ /*
+diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c
+index b710958393e64..a541659b6562b 100644
+--- a/net/ipv4/tcp_ipv4.c
++++ b/net/ipv4/tcp_ipv4.c
+@@ -611,15 +611,10 @@ int tcp_v4_err(struct sk_buff *skb, u32 info)
+
+ ip_icmp_error(sk, skb, err, th->dest, info, (u8 *)th);
+
+- if (!sock_owned_by_user(sk)) {
+- WRITE_ONCE(sk->sk_err, err);
+-
+- sk_error_report(sk);
+-
+- tcp_done(sk);
+- } else {
++ if (!sock_owned_by_user(sk))
++ tcp_done_with_error(sk, err);
++ else
+ WRITE_ONCE(sk->sk_err_soft, err);
+- }
+ goto out;
+ }
+
+diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c
+index 538c06f95918d..0fbebf6266e91 100644
+--- a/net/ipv4/tcp_minisocks.c
++++ b/net/ipv4/tcp_minisocks.c
+@@ -515,9 +515,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
+ const struct tcp_sock *oldtp;
+ struct tcp_sock *newtp;
+ u32 seq;
+-#ifdef CONFIG_TCP_AO
+- struct tcp_ao_key *ao_key;
+-#endif
+
+ if (!newsk)
+ return NULL;
+@@ -608,10 +605,14 @@ struct sock *tcp_create_openreq_child(const struct sock *sk,
+ #endif
+ #ifdef CONFIG_TCP_AO
+ newtp->ao_info = NULL;
+- ao_key = treq->af_specific->ao_lookup(sk, req,
+- tcp_rsk(req)->ao_keyid, -1);
+- if (ao_key)
+- newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
++
++ if (tcp_rsk_used_ao(req)) {
++ struct tcp_ao_key *ao_key;
++
++ ao_key = treq->af_specific->ao_lookup(sk, req, tcp_rsk(req)->ao_keyid, -1);
++ if (ao_key)
++ newtp->tcp_header_len += tcp_ao_len_aligned(ao_key);
++ }
+ #endif
+ if (skb->len >= TCP_MSS_DEFAULT + newtp->tcp_header_len)
+ newicsk->icsk_ack.last_seg_size = skb->len - newtp->tcp_header_len;
+diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c
+index 892c86657fbc2..4d40615dc8fc2 100644
+--- a/net/ipv4/tcp_timer.c
++++ b/net/ipv4/tcp_timer.c
+@@ -74,11 +74,7 @@ u32 tcp_clamp_probe0_to_user_timeout(const struct sock *sk, u32 when)
+
+ static void tcp_write_err(struct sock *sk)
+ {
+- WRITE_ONCE(sk->sk_err, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
+- sk_error_report(sk);
+-
+- tcp_write_queue_purge(sk);
+- tcp_done(sk);
++ tcp_done_with_error(sk, READ_ONCE(sk->sk_err_soft) ? : ETIMEDOUT);
+ __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPABORTONTIMEOUT);
+ }
+
+diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c
+index 5c424a0e7232f..4f2c5cc31015e 100644
+--- a/net/ipv6/addrconf.c
++++ b/net/ipv6/addrconf.c
+@@ -1873,7 +1873,8 @@ int ipv6_dev_get_saddr(struct net *net, const struct net_device *dst_dev,
+ master, &dst,
+ scores, hiscore_idx);
+
+- if (scores[hiscore_idx].ifa)
++ if (scores[hiscore_idx].ifa &&
++ scores[hiscore_idx].scopedist >= 0)
+ goto out;
+ }
+
+diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c
+index 34a9a5b9ed00b..3920e8aa1031e 100644
+--- a/net/ipv6/esp6.c
++++ b/net/ipv6/esp6.c
+@@ -256,8 +256,7 @@ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+ #else
+ static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb)
+ {
+- kfree_skb(skb);
+-
++ WARN_ON(1);
+ return -EOPNOTSUPP;
+ }
+ #endif
+diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c
+index 527b7caddbc68..919ebfabbe4ee 100644
+--- a/net/ipv6/esp6_offload.c
++++ b/net/ipv6/esp6_offload.c
+@@ -83,6 +83,13 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head,
+ x = xfrm_state_lookup(dev_net(skb->dev), skb->mark,
+ (xfrm_address_t *)&ipv6_hdr(skb)->daddr,
+ spi, IPPROTO_ESP, AF_INET6);
++
++ if (unlikely(x && x->dir && x->dir != XFRM_SA_DIR_IN)) {
++ /* non-offload path will record the error and audit log */
++ xfrm_state_put(x);
++ x = NULL;
++ }
++
+ if (!x)
+ goto out_reset;
+
+diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c
+index 27d8725445e35..784424ac41477 100644
+--- a/net/ipv6/ip6_output.c
++++ b/net/ipv6/ip6_output.c
+@@ -1124,6 +1124,7 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk,
+ from = rt ? rcu_dereference(rt->from) : NULL;
+ err = ip6_route_get_saddr(net, from, &fl6->daddr,
+ sk ? READ_ONCE(inet6_sk(sk)->srcprefs) : 0,
++ fl6->flowi6_l3mdev,
+ &fl6->saddr);
+ rcu_read_unlock();
+
+diff --git a/net/ipv6/route.c b/net/ipv6/route.c
+index 8d72ca0b086d7..c9a9506b714d7 100644
+--- a/net/ipv6/route.c
++++ b/net/ipv6/route.c
+@@ -5689,7 +5689,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb,
+ goto nla_put_failure;
+ } else if (dest) {
+ struct in6_addr saddr_buf;
+- if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 &&
++ if (ip6_route_get_saddr(net, rt, dest, 0, 0, &saddr_buf) == 0 &&
+ nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf))
+ goto nla_put_failure;
+ }
+diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c
+index 729faf8bd366a..3385faf1d5dcb 100644
+--- a/net/ipv6/tcp_ipv6.c
++++ b/net/ipv6/tcp_ipv6.c
+@@ -490,14 +490,10 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt,
+
+ ipv6_icmp_error(sk, skb, err, th->dest, ntohl(info), (u8 *)th);
+
+- if (!sock_owned_by_user(sk)) {
+- WRITE_ONCE(sk->sk_err, err);
+- sk_error_report(sk); /* Wake people up to see the error (see connect in sock.c) */
+-
+- tcp_done(sk);
+- } else {
++ if (!sock_owned_by_user(sk))
++ tcp_done_with_error(sk, err);
++ else
+ WRITE_ONCE(sk->sk_err_soft, err);
+- }
+ goto out;
+ case TCP_LISTEN:
+ break;
+diff --git a/net/mac80211/chan.c b/net/mac80211/chan.c
+index 380695fdc32fa..e6a7ff6ca6797 100644
+--- a/net/mac80211/chan.c
++++ b/net/mac80211/chan.c
+@@ -775,13 +775,24 @@ void ieee80211_recalc_chanctx_chantype(struct ieee80211_local *local,
+
+ /* TDLS peers can sometimes affect the chandef width */
+ list_for_each_entry(sta, &local->sta_list, list) {
++ struct ieee80211_sub_if_data *sdata = sta->sdata;
+ struct ieee80211_chan_req tdls_chanreq = {};
++ int tdls_link_id;
++
+ if (!sta->uploaded ||
+ !test_sta_flag(sta, WLAN_STA_TDLS_WIDER_BW) ||
+ !test_sta_flag(sta, WLAN_STA_AUTHORIZED) ||
+ !sta->tdls_chandef.chan)
+ continue;
+
++ tdls_link_id = ieee80211_tdls_sta_link_id(sta);
++ link = sdata_dereference(sdata->link[tdls_link_id], sdata);
++ if (!link)
++ continue;
++
++ if (rcu_access_pointer(link->conf->chanctx_conf) != conf)
++ continue;
++
+ tdls_chanreq.oper = sta->tdls_chandef;
+
+ /* note this always fills and returns &tmp if compat */
+diff --git a/net/mac80211/main.c b/net/mac80211/main.c
+index 0965ad11ec747..7ba329ebdda91 100644
+--- a/net/mac80211/main.c
++++ b/net/mac80211/main.c
+@@ -148,7 +148,7 @@ static u32 ieee80211_calc_hw_conf_chan(struct ieee80211_local *local,
+ offchannel_flag ^= local->hw.conf.flags & IEEE80211_CONF_OFFCHANNEL;
+
+ /* force it also for scanning, since drivers might config differently */
+- if (offchannel_flag || local->scanning ||
++ if (offchannel_flag || local->scanning || local->in_reconfig ||
+ !cfg80211_chandef_identical(&local->hw.conf.chandef, &chandef)) {
+ local->hw.conf.chandef = chandef;
+ changed |= IEEE80211_CONF_CHANGE_CHANNEL;
+diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c
+index a5f2d3cfe60d2..ad2ce9c92ba8a 100644
+--- a/net/mac80211/mlme.c
++++ b/net/mac80211/mlme.c
+@@ -3287,8 +3287,17 @@ static void ieee80211_set_disassoc(struct ieee80211_sub_if_data *sdata,
+ sizeof(sdata->u.mgd.ttlm_info));
+ wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work);
+
++ memset(&sdata->vif.neg_ttlm, 0, sizeof(sdata->vif.neg_ttlm));
+ wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
+ &ifmgd->neg_ttlm_timeout_work);
++
++ sdata->u.mgd.removed_links = 0;
++ wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
++ &sdata->u.mgd.ml_reconf_work);
++
++ wiphy_work_cancel(sdata->local->hw.wiphy,
++ &ifmgd->teardown_ttlm_work);
++
+ ieee80211_vif_set_links(sdata, 0, 0);
+
+ ifmgd->mcast_seq_last = IEEE80211_SN_MODULO;
+@@ -6834,7 +6843,7 @@ static void ieee80211_teardown_ttlm_work(struct wiphy *wiphy,
+ u16 new_dormant_links;
+ struct ieee80211_sub_if_data *sdata =
+ container_of(work, struct ieee80211_sub_if_data,
+- u.mgd.neg_ttlm_timeout_work.work);
++ u.mgd.teardown_ttlm_work);
+
+ if (!sdata->vif.neg_ttlm.valid)
+ return;
+@@ -8704,12 +8713,8 @@ void ieee80211_mgd_stop(struct ieee80211_sub_if_data *sdata)
+ &ifmgd->beacon_connection_loss_work);
+ wiphy_work_cancel(sdata->local->hw.wiphy,
+ &ifmgd->csa_connection_drop_work);
+- wiphy_work_cancel(sdata->local->hw.wiphy,
+- &ifmgd->teardown_ttlm_work);
+ wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
+ &ifmgd->tdls_peer_del_work);
+- wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
+- &ifmgd->ml_reconf_work);
+ wiphy_delayed_work_cancel(sdata->local->hw.wiphy, &ifmgd->ttlm_work);
+ wiphy_delayed_work_cancel(sdata->local->hw.wiphy,
+ &ifmgd->neg_ttlm_timeout_work);
+diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h
+index bd5e2f7146f67..9195d5a2de0a8 100644
+--- a/net/mac80211/sta_info.h
++++ b/net/mac80211/sta_info.h
+@@ -727,6 +727,12 @@ struct sta_info {
+ struct ieee80211_sta sta;
+ };
+
++static inline int ieee80211_tdls_sta_link_id(struct sta_info *sta)
++{
++ /* TDLS STA can only have a single link */
++ return sta->sta.valid_links ? __ffs(sta->sta.valid_links) : 0;
++}
++
+ static inline enum nl80211_plink_state sta_plink_state(struct sta_info *sta)
+ {
+ #ifdef CONFIG_MAC80211_MESH
+diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
+index f861d99e5f055..72a9ba8bc5fd9 100644
+--- a/net/mac80211/tx.c
++++ b/net/mac80211/tx.c
+@@ -2774,8 +2774,7 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata,
+
+ if (tdls_peer) {
+ /* For TDLS only one link can be valid with peer STA */
+- int tdls_link_id = sta->sta.valid_links ?
+- __ffs(sta->sta.valid_links) : 0;
++ int tdls_link_id = ieee80211_tdls_sta_link_id(sta);
+ struct ieee80211_link_data *link;
+
+ /* DA SA BSSID */
+@@ -3101,8 +3100,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta)
+ case NL80211_IFTYPE_STATION:
+ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER)) {
+ /* For TDLS only one link can be valid with peer STA */
+- int tdls_link_id = sta->sta.valid_links ?
+- __ffs(sta->sta.valid_links) : 0;
++ int tdls_link_id = ieee80211_tdls_sta_link_id(sta);
+ struct ieee80211_link_data *link;
+
+ /* DA SA BSSID */
+diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c
+index b6d0dcf3a5c34..f4384e147ee16 100644
+--- a/net/netfilter/ipvs/ip_vs_ctl.c
++++ b/net/netfilter/ipvs/ip_vs_ctl.c
+@@ -1459,18 +1459,18 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u,
+ if (ret < 0)
+ goto out_err;
+
+- /* Bind the ct retriever */
+- RCU_INIT_POINTER(svc->pe, pe);
+- pe = NULL;
+-
+ /* Update the virtual service counters */
+ if (svc->port == FTPPORT)
+ atomic_inc(&ipvs->ftpsvc_counter);
+ else if (svc->port == 0)
+ atomic_inc(&ipvs->nullsvc_counter);
+- if (svc->pe && svc->pe->conn_out)
++ if (pe && pe->conn_out)
+ atomic_inc(&ipvs->conn_out_counter);
+
++ /* Bind the ct retriever */
++ RCU_INIT_POINTER(svc->pe, pe);
++ pe = NULL;
++
+ /* Count only IPv4 services for old get/setsockopt interface */
+ if (svc->af == AF_INET)
+ ipvs->num_services++;
+diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c
+index 1e689c7141271..83e452916403d 100644
+--- a/net/netfilter/ipvs/ip_vs_proto_sctp.c
++++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c
+@@ -126,7 +126,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+ if (sctph->source != cp->vport || payload_csum ||
+ skb->ip_summed == CHECKSUM_PARTIAL) {
+ sctph->source = cp->vport;
+- if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
++ if (!skb_is_gso(skb))
+ sctp_nat_csum(skb, sctph, sctphoff);
+ } else {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+@@ -175,7 +175,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp,
+ (skb->ip_summed == CHECKSUM_PARTIAL &&
+ !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) {
+ sctph->dest = cp->dport;
+- if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb))
++ if (!skb_is_gso(skb))
+ sctp_nat_csum(skb, sctph, sctphoff);
+ } else if (skb->ip_summed != CHECKSUM_PARTIAL) {
+ skb->ip_summed = CHECKSUM_UNNECESSARY;
+diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c
+index 3b846cbdc050d..4cbf71d0786b0 100644
+--- a/net/netfilter/nf_conntrack_netlink.c
++++ b/net/netfilter/nf_conntrack_netlink.c
+@@ -3420,7 +3420,8 @@ static int ctnetlink_del_expect(struct sk_buff *skb,
+
+ if (cda[CTA_EXPECT_ID]) {
+ __be32 id = nla_get_be32(cda[CTA_EXPECT_ID]);
+- if (ntohl(id) != (u32)(unsigned long)exp) {
++
++ if (id != nf_expect_get_id(exp)) {
+ nf_ct_expect_put(exp);
+ return -ENOENT;
+ }
+diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c
+index 15a236bebb46a..eb4c4a4ac7ace 100644
+--- a/net/netfilter/nft_set_pipapo.c
++++ b/net/netfilter/nft_set_pipapo.c
+@@ -434,7 +434,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set,
+ res_map = scratch->map + (map_index ? m->bsize_max : 0);
+ fill_map = scratch->map + (map_index ? 0 : m->bsize_max);
+
+- memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
++ pipapo_resmap_init(m, res_map);
+
+ nft_pipapo_for_each_field(f, i, m) {
+ bool last = i == m->field_count - 1;
+@@ -542,7 +542,7 @@ static struct nft_pipapo_elem *pipapo_get(const struct net *net,
+ goto out;
+ }
+
+- memset(res_map, 0xff, m->bsize_max * sizeof(*res_map));
++ pipapo_resmap_init(m, res_map);
+
+ nft_pipapo_for_each_field(f, i, m) {
+ bool last = i == m->field_count - 1;
+diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h
+index 0d2e40e10f7f5..4a2ff85ce1c43 100644
+--- a/net/netfilter/nft_set_pipapo.h
++++ b/net/netfilter/nft_set_pipapo.h
+@@ -278,4 +278,25 @@ static u64 pipapo_estimate_size(const struct nft_set_desc *desc)
+ return size;
+ }
+
++/**
++ * pipapo_resmap_init() - Initialise result map before first use
++ * @m: Matching data, including mapping table
++ * @res_map: Result map
++ *
++ * Initialize all bits covered by the first field to one, so that after
++ * the first step, only the matching bits of the first bit group remain.
++ *
++ * If other fields have a large bitmap, set remainder of res_map to 0.
++ */
++static inline void pipapo_resmap_init(const struct nft_pipapo_match *m, unsigned long *res_map)
++{
++ const struct nft_pipapo_field *f = m->f;
++ int i;
++
++ for (i = 0; i < f->bsize; i++)
++ res_map[i] = ULONG_MAX;
++
++ for (i = f->bsize; i < m->bsize_max; i++)
++ res_map[i] = 0ul;
++}
+ #endif /* _NFT_SET_PIPAPO_H */
+diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c
+index d08407d589eac..b8d3c3213efee 100644
+--- a/net/netfilter/nft_set_pipapo_avx2.c
++++ b/net/netfilter/nft_set_pipapo_avx2.c
+@@ -1036,6 +1036,7 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill,
+
+ /**
+ * nft_pipapo_avx2_lookup_slow() - Fallback function for uncommon field sizes
++ * @mdata: Matching data, including mapping table
+ * @map: Previous match result, used as initial bitmap
+ * @fill: Destination bitmap to be filled with current match result
+ * @f: Field, containing lookup and mapping tables
+@@ -1051,7 +1052,8 @@ static int nft_pipapo_avx2_lookup_8b_16(unsigned long *map, unsigned long *fill,
+ * Return: -1 on no match, rule index of match if @last, otherwise first long
+ * word index to be checked next (i.e. first filled word).
+ */
+-static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill,
++static int nft_pipapo_avx2_lookup_slow(const struct nft_pipapo_match *mdata,
++ unsigned long *map, unsigned long *fill,
+ const struct nft_pipapo_field *f,
+ int offset, const u8 *pkt,
+ bool first, bool last)
+@@ -1060,7 +1062,7 @@ static int nft_pipapo_avx2_lookup_slow(unsigned long *map, unsigned long *fill,
+ int i, ret = -1, b;
+
+ if (first)
+- memset(map, 0xff, bsize * sizeof(*map));
++ pipapo_resmap_init(mdata, map);
+
+ for (i = offset; i < bsize; i++) {
+ if (f->bb == 8)
+@@ -1137,8 +1139,14 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+ bool map_index;
+ int i, ret = 0;
+
+- if (unlikely(!irq_fpu_usable()))
+- return nft_pipapo_lookup(net, set, key, ext);
++ local_bh_disable();
++
++ if (unlikely(!irq_fpu_usable())) {
++ bool fallback_res = nft_pipapo_lookup(net, set, key, ext);
++
++ local_bh_enable();
++ return fallback_res;
++ }
+
+ m = rcu_dereference(priv->match);
+
+@@ -1153,6 +1161,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+ scratch = *raw_cpu_ptr(m->scratch);
+ if (unlikely(!scratch)) {
+ kernel_fpu_end();
++ local_bh_enable();
+ return false;
+ }
+
+@@ -1186,7 +1195,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+ } else if (f->groups == 16) {
+ NFT_SET_PIPAPO_AVX2_LOOKUP(8, 16);
+ } else {
+- ret = nft_pipapo_avx2_lookup_slow(res, fill, f,
++ ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f,
+ ret, rp,
+ first, last);
+ }
+@@ -1202,7 +1211,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+ } else if (f->groups == 32) {
+ NFT_SET_PIPAPO_AVX2_LOOKUP(4, 32);
+ } else {
+- ret = nft_pipapo_avx2_lookup_slow(res, fill, f,
++ ret = nft_pipapo_avx2_lookup_slow(m, res, fill, f,
+ ret, rp,
+ first, last);
+ }
+@@ -1233,6 +1242,7 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set,
+ if (i % 2)
+ scratch->map_index = !map_index;
+ kernel_fpu_end();
++ local_bh_enable();
+
+ return ret >= 0;
+ }
+diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c
+index ea3ebc160e25c..4692a9ef110bb 100644
+--- a/net/packet/af_packet.c
++++ b/net/packet/af_packet.c
+@@ -538,6 +538,61 @@ static void *packet_current_frame(struct packet_sock *po,
+ return packet_lookup_frame(po, rb, rb->head, status);
+ }
+
++static u16 vlan_get_tci(struct sk_buff *skb, struct net_device *dev)
++{
++ u8 *skb_orig_data = skb->data;
++ int skb_orig_len = skb->len;
++ struct vlan_hdr vhdr, *vh;
++ unsigned int header_len;
++
++ if (!dev)
++ return 0;
++
++ /* In the SOCK_DGRAM scenario, skb data starts at the network
++ * protocol, which is after the VLAN headers. The outer VLAN
++ * header is at the hard_header_len offset in non-variable
++ * length link layer headers. If it's a VLAN device, the
++ * min_header_len should be used to exclude the VLAN header
++ * size.
++ */
++ if (dev->min_header_len == dev->hard_header_len)
++ header_len = dev->hard_header_len;
++ else if (is_vlan_dev(dev))
++ header_len = dev->min_header_len;
++ else
++ return 0;
++
++ skb_push(skb, skb->data - skb_mac_header(skb));
++ vh = skb_header_pointer(skb, header_len, sizeof(vhdr), &vhdr);
++ if (skb_orig_data != skb->data) {
++ skb->data = skb_orig_data;
++ skb->len = skb_orig_len;
++ }
++ if (unlikely(!vh))
++ return 0;
++
++ return ntohs(vh->h_vlan_TCI);
++}
++
++static __be16 vlan_get_protocol_dgram(struct sk_buff *skb)
++{
++ __be16 proto = skb->protocol;
++
++ if (unlikely(eth_type_vlan(proto))) {
++ u8 *skb_orig_data = skb->data;
++ int skb_orig_len = skb->len;
++
++ skb_push(skb, skb->data - skb_mac_header(skb));
++ proto = __vlan_get_protocol(skb, proto, NULL);
++ if (skb_orig_data != skb->data) {
++ skb->data = skb_orig_data;
++ skb->len = skb_orig_len;
++ }
++ }
++
++ return proto;
++}
++
+ static void prb_del_retire_blk_timer(struct tpacket_kbdq_core *pkc)
+ {
+ del_timer_sync(&pkc->retire_blk_timer);
+@@ -1007,10 +1062,16 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *pkc,
+ static void prb_fill_vlan_info(struct tpacket_kbdq_core *pkc,
+ struct tpacket3_hdr *ppd)
+ {
++ struct packet_sock *po = container_of(pkc, struct packet_sock, rx_ring.prb_bdqc);
++
+ if (skb_vlan_tag_present(pkc->skb)) {
+ ppd->hv1.tp_vlan_tci = skb_vlan_tag_get(pkc->skb);
+ ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->vlan_proto);
+ ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
++ } else if (unlikely(po->sk.sk_type == SOCK_DGRAM && eth_type_vlan(pkc->skb->protocol))) {
++ ppd->hv1.tp_vlan_tci = vlan_get_tci(pkc->skb, pkc->skb->dev);
++ ppd->hv1.tp_vlan_tpid = ntohs(pkc->skb->protocol);
++ ppd->tp_status = TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+ } else {
+ ppd->hv1.tp_vlan_tci = 0;
+ ppd->hv1.tp_vlan_tpid = 0;
+@@ -2428,6 +2489,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
+ h.h2->tp_vlan_tci = skb_vlan_tag_get(skb);
+ h.h2->tp_vlan_tpid = ntohs(skb->vlan_proto);
+ status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
++ } else if (unlikely(sk->sk_type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
++ h.h2->tp_vlan_tci = vlan_get_tci(skb, skb->dev);
++ h.h2->tp_vlan_tpid = ntohs(skb->protocol);
++ status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
+ } else {
+ h.h2->tp_vlan_tci = 0;
+ h.h2->tp_vlan_tpid = 0;
+@@ -2457,7 +2522,8 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev,
+ sll->sll_halen = dev_parse_header(skb, sll->sll_addr);
+ sll->sll_family = AF_PACKET;
+ sll->sll_hatype = dev->type;
+- sll->sll_protocol = skb->protocol;
++ sll->sll_protocol = (sk->sk_type == SOCK_DGRAM) ?
++ vlan_get_protocol_dgram(skb) : skb->protocol;
+ sll->sll_pkttype = skb->pkt_type;
+ if (unlikely(packet_sock_flag(po, PACKET_SOCK_ORIGDEV)))
+ sll->sll_ifindex = orig_dev->ifindex;
+@@ -3482,7 +3548,8 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ /* Original length was stored in sockaddr_ll fields */
+ origlen = PACKET_SKB_CB(skb)->sa.origlen;
+ sll->sll_family = AF_PACKET;
+- sll->sll_protocol = skb->protocol;
++ sll->sll_protocol = (sock->type == SOCK_DGRAM) ?
++ vlan_get_protocol_dgram(skb) : skb->protocol;
+ }
+
+ sock_recv_cmsgs(msg, sk, skb);
+@@ -3539,6 +3606,21 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len,
+ aux.tp_vlan_tci = skb_vlan_tag_get(skb);
+ aux.tp_vlan_tpid = ntohs(skb->vlan_proto);
+ aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
++ } else if (unlikely(sock->type == SOCK_DGRAM && eth_type_vlan(skb->protocol))) {
++ struct sockaddr_ll *sll = &PACKET_SKB_CB(skb)->sa.ll;
++ struct net_device *dev;
++
++ rcu_read_lock();
++ dev = dev_get_by_index_rcu(sock_net(sk), sll->sll_ifindex);
++ if (dev) {
++ aux.tp_vlan_tci = vlan_get_tci(skb, dev);
++ aux.tp_vlan_tpid = ntohs(skb->protocol);
++ aux.tp_status |= TP_STATUS_VLAN_VALID | TP_STATUS_VLAN_TPID_VALID;
++ } else {
++ aux.tp_vlan_tci = 0;
++ aux.tp_vlan_tpid = 0;
++ }
++ rcu_read_unlock();
+ } else {
+ aux.tp_vlan_tci = 0;
+ aux.tp_vlan_tpid = 0;
+diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c
+index fafdb97adfad9..acca3b1a068f0 100644
+--- a/net/smc/smc_core.c
++++ b/net/smc/smc_core.c
+@@ -2015,7 +2015,6 @@ int smc_conn_create(struct smc_sock *smc, struct smc_init_info *ini)
+ */
+ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb)
+ {
+- const unsigned int max_scat = SG_MAX_SINGLE_ALLOC * PAGE_SIZE;
+ u8 compressed;
+
+ if (size <= SMC_BUF_MIN_SIZE)
+@@ -2025,9 +2024,11 @@ static u8 smc_compress_bufsize(int size, bool is_smcd, bool is_rmb)
+ compressed = min_t(u8, ilog2(size) + 1,
+ is_smcd ? SMCD_DMBE_SIZES : SMCR_RMBE_SIZES);
+
++#ifdef CONFIG_ARCH_NO_SG_CHAIN
+ if (!is_smcd && is_rmb)
+ /* RMBs are backed by & limited to max size of scatterlists */
+- compressed = min_t(u8, compressed, ilog2(max_scat >> 14));
++ compressed = min_t(u8, compressed, ilog2((SG_MAX_SINGLE_ALLOC * PAGE_SIZE) >> 14));
++#endif
+
+ return compressed;
+ }
+diff --git a/net/sunrpc/auth_gss/gss_krb5_keys.c b/net/sunrpc/auth_gss/gss_krb5_keys.c
+index 06d8ee0db000f..4eb19c3a54c70 100644
+--- a/net/sunrpc/auth_gss/gss_krb5_keys.c
++++ b/net/sunrpc/auth_gss/gss_krb5_keys.c
+@@ -168,7 +168,7 @@ static int krb5_DK(const struct gss_krb5_enctype *gk5e,
+ goto err_return;
+ blocksize = crypto_sync_skcipher_blocksize(cipher);
+ if (crypto_sync_skcipher_setkey(cipher, inkey->data, inkey->len))
+- goto err_return;
++ goto err_free_cipher;
+
+ ret = -ENOMEM;
+ inblockdata = kmalloc(blocksize, gfp_mask);
+diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c
+index cfd1b1bf7e351..09f29a95f2bc3 100644
+--- a/net/sunrpc/clnt.c
++++ b/net/sunrpc/clnt.c
+@@ -2326,12 +2326,13 @@ call_transmit_status(struct rpc_task *task)
+ task->tk_action = call_transmit;
+ task->tk_status = 0;
+ break;
+- case -ECONNREFUSED:
+ case -EHOSTDOWN:
+ case -ENETDOWN:
+ case -EHOSTUNREACH:
+ case -ENETUNREACH:
+ case -EPERM:
++ break;
++ case -ECONNREFUSED:
+ if (RPC_IS_SOFTCONN(task)) {
+ if (!task->tk_msg.rpc_proc->p_proc)
+ trace_xprt_ping(task->tk_xprt,
+diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c
+index ffbf99894970e..47f33bb7bff81 100644
+--- a/net/sunrpc/xprtrdma/frwr_ops.c
++++ b/net/sunrpc/xprtrdma/frwr_ops.c
+@@ -92,7 +92,8 @@ static void frwr_mr_put(struct rpcrdma_mr *mr)
+ rpcrdma_mr_push(mr, &mr->mr_req->rl_free_mrs);
+ }
+
+-/* frwr_reset - Place MRs back on the free list
++/**
++ * frwr_reset - Place MRs back on @req's free list
+ * @req: request to reset
+ *
+ * Used after a failed marshal. For FRWR, this means the MRs
+diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c
+index 432557a553e7e..a0b071089e159 100644
+--- a/net/sunrpc/xprtrdma/verbs.c
++++ b/net/sunrpc/xprtrdma/verbs.c
+@@ -897,6 +897,8 @@ static int rpcrdma_reqs_setup(struct rpcrdma_xprt *r_xprt)
+
+ static void rpcrdma_req_reset(struct rpcrdma_req *req)
+ {
++ struct rpcrdma_mr *mr;
++
+ /* Credits are valid for only one connection */
+ req->rl_slot.rq_cong = 0;
+
+@@ -906,7 +908,19 @@ static void rpcrdma_req_reset(struct rpcrdma_req *req)
+ rpcrdma_regbuf_dma_unmap(req->rl_sendbuf);
+ rpcrdma_regbuf_dma_unmap(req->rl_recvbuf);
+
+- frwr_reset(req);
++ /* The verbs consumer can't know the state of an MR on the
++ * req->rl_registered list unless a successful completion
++ * has occurred, so they cannot be re-used.
++ */
++ while ((mr = rpcrdma_mr_pop(&req->rl_registered))) {
++ struct rpcrdma_buffer *buf = &mr->mr_xprt->rx_buf;
++
++ spin_lock(&buf->rb_lock);
++ list_del(&mr->mr_all);
++ spin_unlock(&buf->rb_lock);
++
++ frwr_mr_release(mr);
++ }
+ }
+
+ /* ASSUMPTION: the rb_allreqs list is stable for the duration,
+diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c
+index b849a3d133a01..439f755399772 100644
+--- a/net/tipc/udp_media.c
++++ b/net/tipc/udp_media.c
+@@ -135,8 +135,11 @@ static int tipc_udp_addr2str(struct tipc_media_addr *a, char *buf, int size)
+ snprintf(buf, size, "%pI4:%u", &ua->ipv4, ntohs(ua->port));
+ else if (ntohs(ua->proto) == ETH_P_IPV6)
+ snprintf(buf, size, "%pI6:%u", &ua->ipv6, ntohs(ua->port));
+- else
++ else {
+ pr_err("Invalid UDP media address\n");
++ return 1;
++ }
++
+ return 0;
+ }
+
+diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
+index 142f56770b77f..11cb5badafb6d 100644
+--- a/net/unix/af_unix.c
++++ b/net/unix/af_unix.c
+@@ -2667,10 +2667,49 @@ static struct sk_buff *manage_oob(struct sk_buff *skb, struct sock *sk,
+
+ static int unix_stream_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
+ {
++ struct unix_sock *u = unix_sk(sk);
++ struct sk_buff *skb;
++ int err;
++
+ if (unlikely(READ_ONCE(sk->sk_state) != TCP_ESTABLISHED))
+ return -ENOTCONN;
+
+- return unix_read_skb(sk, recv_actor);
++ mutex_lock(&u->iolock);
++ skb = skb_recv_datagram(sk, MSG_DONTWAIT, &err);
++ mutex_unlock(&u->iolock);
++ if (!skb)
++ return err;
++
++#if IS_ENABLED(CONFIG_AF_UNIX_OOB)
++ if (unlikely(skb == READ_ONCE(u->oob_skb))) {
++ bool drop = false;
++
++ unix_state_lock(sk);
++
++ if (sock_flag(sk, SOCK_DEAD)) {
++ unix_state_unlock(sk);
++ kfree_skb(skb);
++ return -ECONNRESET;
++ }
++
++ spin_lock(&sk->sk_receive_queue.lock);
++ if (likely(skb == u->oob_skb)) {
++ WRITE_ONCE(u->oob_skb, NULL);
++ drop = true;
++ }
++ spin_unlock(&sk->sk_receive_queue.lock);
++
++ unix_state_unlock(sk);
++
++ if (drop) {
++ WARN_ON_ONCE(skb_unref(skb));
++ kfree_skb(skb);
++ return -EAGAIN;
++ }
++ }
++#endif
++
++ return recv_actor(sk, skb);
+ }
+
+ static int unix_stream_read_generic(struct unix_stream_read_state *state,
+diff --git a/net/unix/unix_bpf.c b/net/unix/unix_bpf.c
+index bd84785bf8d6c..bca2d86ba97d8 100644
+--- a/net/unix/unix_bpf.c
++++ b/net/unix/unix_bpf.c
+@@ -54,6 +54,9 @@ static int unix_bpf_recvmsg(struct sock *sk, struct msghdr *msg,
+ struct sk_psock *psock;
+ int copied;
+
++ if (flags & MSG_OOB)
++ return -EOPNOTSUPP;
++
+ if (!len)
+ return 0;
+
+diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c
+index 72c7bf5585816..0fd075238fc74 100644
+--- a/net/wireless/nl80211.c
++++ b/net/wireless/nl80211.c
+@@ -1208,6 +1208,9 @@ static int nl80211_msg_put_channel(struct sk_buff *msg, struct wiphy *wiphy,
+ if ((chan->flags & IEEE80211_CHAN_NO_6GHZ_AFC_CLIENT) &&
+ nla_put_flag(msg, NL80211_FREQUENCY_ATTR_NO_6GHZ_AFC_CLIENT))
+ goto nla_put_failure;
++ if ((chan->flags & IEEE80211_CHAN_CAN_MONITOR) &&
++ nla_put_flag(msg, NL80211_FREQUENCY_ATTR_CAN_MONITOR))
++ goto nla_put_failure;
+ }
+
+ if (nla_put_u32(msg, NL80211_FREQUENCY_ATTR_MAX_TX_POWER,
+diff --git a/net/wireless/util.c b/net/wireless/util.c
+index 082c6f9c5416e..af6ec719567fc 100644
+--- a/net/wireless/util.c
++++ b/net/wireless/util.c
+@@ -1504,7 +1504,7 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
+ 5120, /* 0.833333... */
+ };
+ u32 rates_160M[3] = { 960777777, 907400000, 816666666 };
+- u32 rates_969[3] = { 480388888, 453700000, 408333333 };
++ u32 rates_996[3] = { 480388888, 453700000, 408333333 };
+ u32 rates_484[3] = { 229411111, 216666666, 195000000 };
+ u32 rates_242[3] = { 114711111, 108333333, 97500000 };
+ u32 rates_106[3] = { 40000000, 37777777, 34000000 };
+@@ -1524,12 +1524,14 @@ static u32 cfg80211_calculate_bitrate_he(struct rate_info *rate)
+ if (WARN_ON_ONCE(rate->nss < 1 || rate->nss > 8))
+ return 0;
+
+- if (rate->bw == RATE_INFO_BW_160)
++ if (rate->bw == RATE_INFO_BW_160 ||
++ (rate->bw == RATE_INFO_BW_HE_RU &&
++ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_2x996))
+ result = rates_160M[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_80 ||
+ (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_996))
+- result = rates_969[rate->he_gi];
++ result = rates_996[rate->he_gi];
+ else if (rate->bw == RATE_INFO_BW_40 ||
+ (rate->bw == RATE_INFO_BW_HE_RU &&
+ rate->he_ru_alloc == NL80211_RATE_INFO_HE_RU_ALLOC_484))
+diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c
+index caa340134b0e1..9f76ca591d54f 100644
+--- a/net/xdp/xdp_umem.c
++++ b/net/xdp/xdp_umem.c
+@@ -151,6 +151,7 @@ static int xdp_umem_account_pages(struct xdp_umem *umem)
+ #define XDP_UMEM_FLAGS_VALID ( \
+ XDP_UMEM_UNALIGNED_CHUNK_FLAG | \
+ XDP_UMEM_TX_SW_CSUM | \
++ XDP_UMEM_TX_METADATA_LEN | \
+ 0)
+
+ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
+@@ -204,8 +205,11 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
+ if (headroom >= chunk_size - XDP_PACKET_HEADROOM)
+ return -EINVAL;
+
+- if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
+- return -EINVAL;
++ if (mr->flags & XDP_UMEM_TX_METADATA_LEN) {
++ if (mr->tx_metadata_len >= 256 || mr->tx_metadata_len % 8)
++ return -EINVAL;
++ umem->tx_metadata_len = mr->tx_metadata_len;
++ }
+
+ umem->size = size;
+ umem->headroom = headroom;
+@@ -215,7 +219,6 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr)
+ umem->pgs = NULL;
+ umem->user = NULL;
+ umem->flags = mr->flags;
+- umem->tx_metadata_len = mr->tx_metadata_len;
+
+ INIT_LIST_HEAD(&umem->xsk_dma_list);
+ refcount_set(&umem->users, 1);
+diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c
+index d2ea18dcb0cb5..e95462b982b0f 100644
+--- a/net/xfrm/xfrm_input.c
++++ b/net/xfrm/xfrm_input.c
+@@ -474,11 +474,6 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+ if (encap_type < 0 || (xo && xo->flags & XFRM_GRO)) {
+ x = xfrm_input_state(skb);
+
+- if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) {
+- XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR);
+- goto drop;
+- }
+-
+ if (unlikely(x->km.state != XFRM_STATE_VALID)) {
+ if (x->km.state == XFRM_STATE_ACQ)
+ XFRM_INC_STATS(net, LINUX_MIB_XFRMACQUIREERROR);
+@@ -585,8 +580,11 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type)
+ }
+
+ if (unlikely(x->dir && x->dir != XFRM_SA_DIR_IN)) {
++ secpath_reset(skb);
+ XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEDIRERROR);
++ xfrm_audit_state_notfound(skb, family, spi, seq);
+ xfrm_state_put(x);
++ x = NULL;
+ goto drop;
+ }
+
+diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c
+index 66e07de2de35c..56b88ad88db6f 100644
+--- a/net/xfrm/xfrm_policy.c
++++ b/net/xfrm/xfrm_policy.c
+@@ -452,6 +452,8 @@ EXPORT_SYMBOL(xfrm_policy_destroy);
+
+ static void xfrm_policy_kill(struct xfrm_policy *policy)
+ {
++ xfrm_dev_policy_delete(policy);
++
+ write_lock_bh(&policy->lock);
+ policy->walk.dead = 1;
+ write_unlock_bh(&policy->lock);
+@@ -1850,7 +1852,6 @@ int xfrm_policy_flush(struct net *net, u8 type, bool task_valid)
+
+ __xfrm_policy_unlink(pol, dir);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+- xfrm_dev_policy_delete(pol);
+ cnt++;
+ xfrm_audit_policy_delete(pol, 1, task_valid);
+ xfrm_policy_kill(pol);
+@@ -1891,7 +1892,6 @@ int xfrm_dev_policy_flush(struct net *net, struct net_device *dev,
+
+ __xfrm_policy_unlink(pol, dir);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+- xfrm_dev_policy_delete(pol);
+ cnt++;
+ xfrm_audit_policy_delete(pol, 1, task_valid);
+ xfrm_policy_kill(pol);
+@@ -2342,7 +2342,6 @@ int xfrm_policy_delete(struct xfrm_policy *pol, int dir)
+ pol = __xfrm_policy_unlink(pol, dir);
+ spin_unlock_bh(&net->xfrm.xfrm_policy_lock);
+ if (pol) {
+- xfrm_dev_policy_delete(pol);
+ xfrm_policy_kill(pol);
+ return 0;
+ }
+diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c
+index 649bb739df0dd..67b2a399a48a7 100644
+--- a/net/xfrm/xfrm_state.c
++++ b/net/xfrm/xfrm_state.c
+@@ -49,6 +49,7 @@ static struct kmem_cache *xfrm_state_cache __ro_after_init;
+
+ static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task);
+ static HLIST_HEAD(xfrm_state_gc_list);
++static HLIST_HEAD(xfrm_state_dev_gc_list);
+
+ static inline bool xfrm_state_hold_rcu(struct xfrm_state __rcu *x)
+ {
+@@ -214,6 +215,7 @@ static DEFINE_SPINLOCK(xfrm_state_afinfo_lock);
+ static struct xfrm_state_afinfo __rcu *xfrm_state_afinfo[NPROTO];
+
+ static DEFINE_SPINLOCK(xfrm_state_gc_lock);
++static DEFINE_SPINLOCK(xfrm_state_dev_gc_lock);
+
+ int __xfrm_state_delete(struct xfrm_state *x);
+
+@@ -683,6 +685,41 @@ struct xfrm_state *xfrm_state_alloc(struct net *net)
+ }
+ EXPORT_SYMBOL(xfrm_state_alloc);
+
++#ifdef CONFIG_XFRM_OFFLOAD
++void xfrm_dev_state_delete(struct xfrm_state *x)
++{
++ struct xfrm_dev_offload *xso = &x->xso;
++ struct net_device *dev = READ_ONCE(xso->dev);
++
++ if (dev) {
++ dev->xfrmdev_ops->xdo_dev_state_delete(x);
++ spin_lock_bh(&xfrm_state_dev_gc_lock);
++ hlist_add_head(&x->dev_gclist, &xfrm_state_dev_gc_list);
++ spin_unlock_bh(&xfrm_state_dev_gc_lock);
++ }
++}
++EXPORT_SYMBOL_GPL(xfrm_dev_state_delete);
++
++void xfrm_dev_state_free(struct xfrm_state *x)
++{
++ struct xfrm_dev_offload *xso = &x->xso;
++ struct net_device *dev = READ_ONCE(xso->dev);
++
++ if (dev && dev->xfrmdev_ops) {
++ spin_lock_bh(&xfrm_state_dev_gc_lock);
++ if (!hlist_unhashed(&x->dev_gclist))
++ hlist_del(&x->dev_gclist);
++ spin_unlock_bh(&xfrm_state_dev_gc_lock);
++
++ if (dev->xfrmdev_ops->xdo_dev_state_free)
++ dev->xfrmdev_ops->xdo_dev_state_free(x);
++ WRITE_ONCE(xso->dev, NULL);
++ xso->type = XFRM_DEV_OFFLOAD_UNSPECIFIED;
++ netdev_put(dev, &xso->dev_tracker);
++ }
++}
++#endif
++
+ void __xfrm_state_destroy(struct xfrm_state *x, bool sync)
+ {
+ WARN_ON(x->km.state != XFRM_STATE_DEAD);
+@@ -848,6 +885,9 @@ EXPORT_SYMBOL(xfrm_state_flush);
+
+ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_valid)
+ {
++ struct xfrm_state *x;
++ struct hlist_node *tmp;
++ struct xfrm_dev_offload *xso;
+ int i, err = 0, cnt = 0;
+
+ spin_lock_bh(&net->xfrm.xfrm_state_lock);
+@@ -857,8 +897,6 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
+
+ err = -ESRCH;
+ for (i = 0; i <= net->xfrm.state_hmask; i++) {
+- struct xfrm_state *x;
+- struct xfrm_dev_offload *xso;
+ restart:
+ hlist_for_each_entry(x, net->xfrm.state_bydst+i, bydst) {
+ xso = &x->xso;
+@@ -868,6 +906,8 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
+
+ err = xfrm_state_delete(x);
++ xfrm_dev_state_free(x);
++
+ xfrm_audit_state_delete(x, err ? 0 : 1,
+ task_valid);
+ xfrm_state_put(x);
+@@ -884,6 +924,24 @@ int xfrm_dev_state_flush(struct net *net, struct net_device *dev, bool task_vali
+
+ out:
+ spin_unlock_bh(&net->xfrm.xfrm_state_lock);
++
++ spin_lock_bh(&xfrm_state_dev_gc_lock);
++restart_gc:
++ hlist_for_each_entry_safe(x, tmp, &xfrm_state_dev_gc_list, dev_gclist) {
++ xso = &x->xso;
++
++ if (xso->dev == dev) {
++ spin_unlock_bh(&xfrm_state_dev_gc_lock);
++ xfrm_dev_state_free(x);
++ spin_lock_bh(&xfrm_state_dev_gc_lock);
++ goto restart_gc;
++ }
++
++ }
++ spin_unlock_bh(&xfrm_state_dev_gc_lock);
++
++ xfrm_flush_gc();
++
+ return err;
+ }
+ EXPORT_SYMBOL(xfrm_dev_state_flush);
+@@ -1273,8 +1331,7 @@ xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr,
+ xso->dev = xdo->dev;
+ xso->real_dev = xdo->real_dev;
+ xso->flags = XFRM_DEV_OFFLOAD_FLAG_ACQ;
+- netdev_tracker_alloc(xso->dev, &xso->dev_tracker,
+- GFP_ATOMIC);
++ netdev_hold(xso->dev, &xso->dev_tracker, GFP_ATOMIC);
+ error = xso->dev->xfrmdev_ops->xdo_dev_state_add(x, NULL);
+ if (error) {
+ xso->dir = 0;
+diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c
+index e83c687bd64ee..77355422ce82a 100644
+--- a/net/xfrm/xfrm_user.c
++++ b/net/xfrm/xfrm_user.c
+@@ -2455,7 +2455,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh,
+ NETLINK_CB(skb).portid);
+ }
+ } else {
+- xfrm_dev_policy_delete(xp);
+ xfrm_audit_policy_delete(xp, err ? 0 : 1, true);
+
+ if (err != 0)
+diff --git a/scripts/Kconfig.include b/scripts/Kconfig.include
+index 3ee8ecfb8c044..3500a3d62f0df 100644
+--- a/scripts/Kconfig.include
++++ b/scripts/Kconfig.include
+@@ -33,7 +33,8 @@ ld-option = $(success,$(LD) -v $(1))
+
+ # $(as-instr,<instr>)
+ # Return y if the assembler supports <instr>, n otherwise
+-as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -)
++as-instr = $(success,printf "%b\n" "$(1)" | $(CC) $(CLANG_FLAGS) $(2) -Wa$(comma)--fatal-warnings -c -x assembler-with-cpp -o /dev/null -)
++as-instr64 = $(as-instr,$(1),$(m64-flag))
+
+ # check if $(CC) and $(LD) exist
+ $(error-if,$(failure,command -v $(CC)),C compiler '$(CC)' not found)
+diff --git a/scripts/Makefile.lib b/scripts/Makefile.lib
+index 9f06f6aaf7fcb..7f8ec77bf35c9 100644
+--- a/scripts/Makefile.lib
++++ b/scripts/Makefile.lib
+@@ -407,8 +407,12 @@ cmd_dtc = $(HOSTCC) -E $(dtc_cpp_flags) -x assembler-with-cpp -o $(dtc-tmp) $< ;
+ -d $(depfile).dtc.tmp $(dtc-tmp) ; \
+ cat $(depfile).pre.tmp $(depfile).dtc.tmp > $(depfile)
+
++# NOTE:
++# Do not replace $(filter %.dtb %.dtbo, $^) with $(real-prereqs). When a single
++# DTB is turned into a multi-blob DTB, $^ will contain header file dependencies
++# recorded in the .*.cmd file.
+ quiet_cmd_fdtoverlay = DTOVL $@
+- cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(real-prereqs)
++ cmd_fdtoverlay = $(objtree)/scripts/dtc/fdtoverlay -o $@ -i $(filter %.dtb %.dtbo, $^)
+
+ $(multi-dtb-y): FORCE
+ $(call if_changed,fdtoverlay)
+diff --git a/scripts/gcc-x86_32-has-stack-protector.sh b/scripts/gcc-x86_32-has-stack-protector.sh
+index 825c75c5b7150..9459ca4f0f11f 100755
+--- a/scripts/gcc-x86_32-has-stack-protector.sh
++++ b/scripts/gcc-x86_32-has-stack-protector.sh
+@@ -5,4 +5,4 @@
+ # -mstack-protector-guard-reg, added by
+ # https://gcc.gnu.org/bugzilla/show_bug.cgi?id=81708
+
+-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"
++echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m32 -O0 -fstack-protector -mstack-protector-guard-reg=fs -mstack-protector-guard-symbol=__stack_chk_guard - -o - 2> /dev/null | grep -q "%fs"
+diff --git a/scripts/gcc-x86_64-has-stack-protector.sh b/scripts/gcc-x86_64-has-stack-protector.sh
+index 75e4e22b986ad..f680bb01aeeb3 100755
+--- a/scripts/gcc-x86_64-has-stack-protector.sh
++++ b/scripts/gcc-x86_64-has-stack-protector.sh
+@@ -1,4 +1,4 @@
+ #!/bin/sh
+ # SPDX-License-Identifier: GPL-2.0
+
+-echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
++echo "int foo(void) { char X[200]; return 3; }" | $* -S -x c -m64 -O0 -mcmodel=kernel -fno-PIE -fstack-protector - -o - 2> /dev/null | grep -q "%gs"
+diff --git a/scripts/syscalltbl.sh b/scripts/syscalltbl.sh
+index 6abe143889ef6..6a903b87a7c21 100755
+--- a/scripts/syscalltbl.sh
++++ b/scripts/syscalltbl.sh
+@@ -54,7 +54,7 @@ nxt=0
+
+ grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | {
+
+- while read nr abi name native compat ; do
++ while read nr abi name native compat noreturn; do
+
+ if [ $nxt -gt $nr ]; then
+ echo "error: $infile: syscall table is not sorted or duplicates the same syscall number" >&2
+@@ -66,7 +66,21 @@ grep -E "^[0-9]+[[:space:]]+$abis" "$infile" | {
+ nxt=$((nxt + 1))
+ done
+
+- if [ -n "$compat" ]; then
++ if [ "$compat" = "-" ]; then
++ unset compat
++ fi
++
++ if [ -n "$noreturn" ]; then
++ if [ "$noreturn" != "noreturn" ]; then
++ echo "error: $infile: invalid string \"$noreturn\" in 'noreturn' column"
++ exit 1
++ fi
++ if [ -n "$compat" ]; then
++ echo "__SYSCALL_COMPAT_NORETURN($nr, $native, $compat)"
++ else
++ echo "__SYSCALL_NORETURN($nr, $native)"
++ fi
++ elif [ -n "$compat" ]; then
+ echo "__SYSCALL_WITH_COMPAT($nr, $native, $compat)"
+ elif [ -n "$native" ]; then
+ echo "__SYSCALL($nr, $native)"
+diff --git a/security/apparmor/lsm.c b/security/apparmor/lsm.c
+index 6239777090c43..4373b914acf20 100644
+--- a/security/apparmor/lsm.c
++++ b/security/apparmor/lsm.c
+@@ -1304,6 +1304,13 @@ static int apparmor_socket_sock_rcv_skb(struct sock *sk, struct sk_buff *skb)
+ if (!skb->secmark)
+ return 0;
+
++ /*
++ * If reach here before socket_post_create hook is called, in which
++ * case label is null, drop the packet.
++ */
++ if (!ctx->label)
++ return -EACCES;
++
+ return apparmor_secmark_check(ctx->label, OP_RECVMSG, AA_MAY_RECEIVE,
+ skb->secmark, sk);
+ }
+diff --git a/security/apparmor/policy.c b/security/apparmor/policy.c
+index 957654d253dd7..14df15e356952 100644
+--- a/security/apparmor/policy.c
++++ b/security/apparmor/policy.c
+@@ -225,7 +225,7 @@ static void aa_free_data(void *ptr, void *arg)
+ {
+ struct aa_data *data = ptr;
+
+- kfree_sensitive(data->data);
++ kvfree_sensitive(data->data, data->size);
+ kfree_sensitive(data->key);
+ kfree_sensitive(data);
+ }
+diff --git a/security/apparmor/policy_unpack.c b/security/apparmor/policy_unpack.c
+index 5e578ef0ddffb..5a570235427d8 100644
+--- a/security/apparmor/policy_unpack.c
++++ b/security/apparmor/policy_unpack.c
+@@ -747,34 +747,42 @@ static int unpack_pdb(struct aa_ext *e, struct aa_policydb **policy,
+ *info = "missing required dfa";
+ goto fail;
+ }
+- goto out;
++ } else {
++ /*
++ * only unpack the following if a dfa is present
++ *
++ * sadly start was given different names for file and policydb
++ * but since it is optional we can try both
++ */
++ if (!aa_unpack_u32(e, &pdb->start[0], "start"))
++ /* default start state */
++ pdb->start[0] = DFA_START;
++ if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) {
++ /* default start state for xmatch and file dfa */
++ pdb->start[AA_CLASS_FILE] = DFA_START;
++ } /* setup class index */
++ for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) {
++ pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0],
++ i);
++ }
+ }
+
+ /*
+- * only unpack the following if a dfa is present
+- *
+- * sadly start was given different names for file and policydb
+- * but since it is optional we can try both
++ * Unfortunately due to a bug in earlier userspaces, a
++ * transition table may be present even when the dfa is
++ * not. For compatibility reasons unpack and discard.
+ */
+- if (!aa_unpack_u32(e, &pdb->start[0], "start"))
+- /* default start state */
+- pdb->start[0] = DFA_START;
+- if (!aa_unpack_u32(e, &pdb->start[AA_CLASS_FILE], "dfa_start")) {
+- /* default start state for xmatch and file dfa */
+- pdb->start[AA_CLASS_FILE] = DFA_START;
+- } /* setup class index */
+- for (i = AA_CLASS_FILE + 1; i <= AA_CLASS_LAST; i++) {
+- pdb->start[i] = aa_dfa_next(pdb->dfa, pdb->start[0],
+- i);
+- }
+ if (!unpack_trans_table(e, &pdb->trans) && required_trans) {
+ *info = "failed to unpack profile transition table";
+ goto fail;
+ }
+
++ if (!pdb->dfa && pdb->trans.table)
++ aa_free_str_table(&pdb->trans);
++
+ /* TODO: move compat mapping here, requires dfa merging first */
+ /* TODO: move verify here, it has to be done after compat mappings */
+-out:
++
+ *policy = pdb;
+ return 0;
+
+@@ -1071,6 +1079,7 @@ static struct aa_profile *unpack_profile(struct aa_ext *e, char **ns_name)
+
+ if (rhashtable_insert_fast(profile->data, &data->head,
+ profile->data->p)) {
++ kvfree_sensitive(data->data, data->size);
+ kfree_sensitive(data->key);
+ kfree_sensitive(data);
+ info = "failed to insert data to table";
+diff --git a/security/keys/keyctl.c b/security/keys/keyctl.c
+index 4bc3e9398ee3d..ab927a142f515 100644
+--- a/security/keys/keyctl.c
++++ b/security/keys/keyctl.c
+@@ -1694,7 +1694,7 @@ long keyctl_session_to_parent(void)
+ goto unlock;
+
+ /* cancel an already pending keyring replacement */
+- oldwork = task_work_cancel(parent, key_change_session_keyring);
++ oldwork = task_work_cancel_func(parent, key_change_session_keyring);
+
+ /* the replacement session keyring is applied just prior to userspace
+ * restarting */
+diff --git a/security/landlock/cred.c b/security/landlock/cred.c
+index 786af18c4a1ca..db9fe7d906ba6 100644
+--- a/security/landlock/cred.c
++++ b/security/landlock/cred.c
+@@ -14,8 +14,8 @@
+ #include "ruleset.h"
+ #include "setup.h"
+
+-static int hook_cred_prepare(struct cred *const new,
+- const struct cred *const old, const gfp_t gfp)
++static void hook_cred_transfer(struct cred *const new,
++ const struct cred *const old)
+ {
+ struct landlock_ruleset *const old_dom = landlock_cred(old)->domain;
+
+@@ -23,6 +23,12 @@ static int hook_cred_prepare(struct cred *const new,
+ landlock_get_ruleset(old_dom);
+ landlock_cred(new)->domain = old_dom;
+ }
++}
++
++static int hook_cred_prepare(struct cred *const new,
++ const struct cred *const old, const gfp_t gfp)
++{
++ hook_cred_transfer(new, old);
+ return 0;
+ }
+
+@@ -36,6 +42,7 @@ static void hook_cred_free(struct cred *const cred)
+
+ static struct security_hook_list landlock_hooks[] __ro_after_init = {
+ LSM_HOOK_INIT(cred_prepare, hook_cred_prepare),
++ LSM_HOOK_INIT(cred_transfer, hook_cred_transfer),
+ LSM_HOOK_INIT(cred_free, hook_cred_free),
+ };
+
+diff --git a/security/security.c b/security/security.c
+index e5ca08789f741..8cee5b6c6e6d5 100644
+--- a/security/security.c
++++ b/security/security.c
+@@ -2278,7 +2278,20 @@ int security_inode_getattr(const struct path *path)
+ * @size: size of xattr value
+ * @flags: flags
+ *
+- * Check permission before setting the extended attributes.
++ * This hook performs the desired permission checks before setting the extended
++ * attributes (xattrs) on @dentry. It is important to note that we have some
++ * additional logic before the main LSM implementation calls to detect if we
++ * need to perform an additional capability check at the LSM layer.
++ *
++ * Normally we enforce a capability check prior to executing the various LSM
++ * hook implementations, but if a LSM wants to avoid this capability check,
++ * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for
++ * xattrs that it wants to avoid the capability check, leaving the LSM fully
++ * responsible for enforcing the access control for the specific xattr. If all
++ * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook,
++ * or return a 0 (the default return value), the capability check is still
++ * performed. If no 'inode_xattr_skipcap' hooks are registered the capability
++ * check is performed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+@@ -2286,20 +2299,20 @@ int security_inode_setxattr(struct mnt_idmap *idmap,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+ {
+- int ret;
++ int rc;
+
+ if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+ return 0;
+- /*
+- * SELinux and Smack integrate the cap call,
+- * so assume that all LSMs supplying this call do so.
+- */
+- ret = call_int_hook(inode_setxattr, idmap, dentry, name, value, size,
+- flags);
+
+- if (ret == 1)
+- ret = cap_inode_setxattr(dentry, name, value, size, flags);
+- return ret;
++ /* enforce the capability checks at the lsm layer, if needed */
++ if (!call_int_hook(inode_xattr_skipcap, name)) {
++ rc = cap_inode_setxattr(dentry, name, value, size, flags);
++ if (rc)
++ return rc;
++ }
++
++ return call_int_hook(inode_setxattr, idmap, dentry, name, value, size,
++ flags);
+ }
+
+ /**
+@@ -2452,26 +2465,39 @@ int security_inode_listxattr(struct dentry *dentry)
+ * @dentry: file
+ * @name: xattr name
+ *
+- * Check permission before removing the extended attribute identified by @name
+- * for @dentry.
++ * This hook performs the desired permission checks before setting the extended
++ * attributes (xattrs) on @dentry. It is important to note that we have some
++ * additional logic before the main LSM implementation calls to detect if we
++ * need to perform an additional capability check at the LSM layer.
++ *
++ * Normally we enforce a capability check prior to executing the various LSM
++ * hook implementations, but if a LSM wants to avoid this capability check,
++ * it can register a 'inode_xattr_skipcap' hook and return a value of 1 for
++ * xattrs that it wants to avoid the capability check, leaving the LSM fully
++ * responsible for enforcing the access control for the specific xattr. If all
++ * of the enabled LSMs refrain from registering a 'inode_xattr_skipcap' hook,
++ * or return a 0 (the default return value), the capability check is still
++ * performed. If no 'inode_xattr_skipcap' hooks are registered the capability
++ * check is performed.
+ *
+ * Return: Returns 0 if permission is granted.
+ */
+ int security_inode_removexattr(struct mnt_idmap *idmap,
+ struct dentry *dentry, const char *name)
+ {
+- int ret;
++ int rc;
+
+ if (unlikely(IS_PRIVATE(d_backing_inode(dentry))))
+ return 0;
+- /*
+- * SELinux and Smack integrate the cap call,
+- * so assume that all LSMs supplying this call do so.
+- */
+- ret = call_int_hook(inode_removexattr, idmap, dentry, name);
+- if (ret == 1)
+- ret = cap_inode_removexattr(idmap, dentry, name);
+- return ret;
++
++ /* enforce the capability checks at the lsm layer, if needed */
++ if (!call_int_hook(inode_xattr_skipcap, name)) {
++ rc = cap_inode_removexattr(idmap, dentry, name);
++ if (rc)
++ return rc;
++ }
++
++ return call_int_hook(inode_removexattr, idmap, dentry, name);
+ }
+
+ /**
+diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c
+index 7eed331e90f08..55c78c318ccd7 100644
+--- a/security/selinux/hooks.c
++++ b/security/selinux/hooks.c
+@@ -3177,6 +3177,23 @@ static bool has_cap_mac_admin(bool audit)
+ return true;
+ }
+
++/**
++ * selinux_inode_xattr_skipcap - Skip the xattr capability checks?
++ * @name: name of the xattr
++ *
++ * Returns 1 to indicate that SELinux "owns" the access control rights to xattrs
++ * named @name; the LSM layer should avoid enforcing any traditional
++ * capability based access controls on this xattr. Returns 0 to indicate that
++ * SELinux does not "own" the access control rights to xattrs named @name and is
++ * deferring to the LSM layer for further access controls, including capability
++ * based controls.
++ */
++static int selinux_inode_xattr_skipcap(const char *name)
++{
++ /* require capability check if not a selinux xattr */
++ return !strcmp(name, XATTR_NAME_SELINUX);
++}
++
+ static int selinux_inode_setxattr(struct mnt_idmap *idmap,
+ struct dentry *dentry, const char *name,
+ const void *value, size_t size, int flags)
+@@ -3188,15 +3205,9 @@ static int selinux_inode_setxattr(struct mnt_idmap *idmap,
+ u32 newsid, sid = current_sid();
+ int rc = 0;
+
+- if (strcmp(name, XATTR_NAME_SELINUX)) {
+- rc = cap_inode_setxattr(dentry, name, value, size, flags);
+- if (rc)
+- return rc;
+-
+- /* Not an attribute we recognize, so just check the
+- ordinary setattr permission. */
++ /* if not a selinux xattr, only check the ordinary setattr perm */
++ if (strcmp(name, XATTR_NAME_SELINUX))
+ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
+- }
+
+ if (!selinux_initialized())
+ return (inode_owner_or_capable(idmap, inode) ? 0 : -EPERM);
+@@ -3345,15 +3356,9 @@ static int selinux_inode_listxattr(struct dentry *dentry)
+ static int selinux_inode_removexattr(struct mnt_idmap *idmap,
+ struct dentry *dentry, const char *name)
+ {
+- if (strcmp(name, XATTR_NAME_SELINUX)) {
+- int rc = cap_inode_removexattr(idmap, dentry, name);
+- if (rc)
+- return rc;
+-
+- /* Not an attribute we recognize, so just check the
+- ordinary setattr permission. */
++ /* if not a selinux xattr, only check the ordinary setattr perm */
++ if (strcmp(name, XATTR_NAME_SELINUX))
+ return dentry_has_perm(current_cred(), dentry, FILE__SETATTR);
+- }
+
+ if (!selinux_initialized())
+ return 0;
+@@ -7175,6 +7180,7 @@ static struct security_hook_list selinux_hooks[] __ro_after_init = {
+ LSM_HOOK_INIT(inode_permission, selinux_inode_permission),
+ LSM_HOOK_INIT(inode_setattr, selinux_inode_setattr),
+ LSM_HOOK_INIT(inode_getattr, selinux_inode_getattr),
++ LSM_HOOK_INIT(inode_xattr_skipcap, selinux_inode_xattr_skipcap),
+ LSM_HOOK_INIT(inode_setxattr, selinux_inode_setxattr),
+ LSM_HOOK_INIT(inode_post_setxattr, selinux_inode_post_setxattr),
+ LSM_HOOK_INIT(inode_getxattr, selinux_inode_getxattr),
+diff --git a/security/smack/smack_lsm.c b/security/smack/smack_lsm.c
+index f5cbec1e6a923..c1fe422cfbe19 100644
+--- a/security/smack/smack_lsm.c
++++ b/security/smack/smack_lsm.c
+@@ -1282,6 +1282,33 @@ static int smack_inode_getattr(const struct path *path)
+ return rc;
+ }
+
++/**
++ * smack_inode_xattr_skipcap - Skip the xattr capability checks?
++ * @name: name of the xattr
++ *
++ * Returns 1 to indicate that Smack "owns" the access control rights to xattrs
++ * named @name; the LSM layer should avoid enforcing any traditional
++ * capability based access controls on this xattr. Returns 0 to indicate that
++ * Smack does not "own" the access control rights to xattrs named @name and is
++ * deferring to the LSM layer for further access controls, including capability
++ * based controls.
++ */
++static int smack_inode_xattr_skipcap(const char *name)
++{
++ if (strncmp(name, XATTR_SMACK_SUFFIX, strlen(XATTR_SMACK_SUFFIX)))
++ return 0;
++
++ if (strcmp(name, XATTR_NAME_SMACK) == 0 ||
++ strcmp(name, XATTR_NAME_SMACKIPIN) == 0 ||
++ strcmp(name, XATTR_NAME_SMACKIPOUT) == 0 ||
++ strcmp(name, XATTR_NAME_SMACKEXEC) == 0 ||
++ strcmp(name, XATTR_NAME_SMACKMMAP) == 0 ||
++ strcmp(name, XATTR_NAME_SMACKTRANSMUTE) == 0)
++ return 1;
++
++ return 0;
++}
++
+ /**
+ * smack_inode_setxattr - Smack check for setting xattrs
+ * @idmap: idmap of the mount
+@@ -1325,8 +1352,7 @@ static int smack_inode_setxattr(struct mnt_idmap *idmap,
+ size != TRANS_TRUE_SIZE ||
+ strncmp(value, TRANS_TRUE, TRANS_TRUE_SIZE) != 0)
+ rc = -EINVAL;
+- } else
+- rc = cap_inode_setxattr(dentry, name, value, size, flags);
++ }
+
+ if (check_priv && !smack_privileged(CAP_MAC_ADMIN))
+ rc = -EPERM;
+@@ -1435,8 +1461,7 @@ static int smack_inode_removexattr(struct mnt_idmap *idmap,
+ strcmp(name, XATTR_NAME_SMACKMMAP) == 0) {
+ if (!smack_privileged(CAP_MAC_ADMIN))
+ rc = -EPERM;
+- } else
+- rc = cap_inode_removexattr(idmap, dentry, name);
++ }
+
+ if (rc != 0)
+ return rc;
+@@ -5053,6 +5078,7 @@ static struct security_hook_list smack_hooks[] __ro_after_init = {
+ LSM_HOOK_INIT(inode_permission, smack_inode_permission),
+ LSM_HOOK_INIT(inode_setattr, smack_inode_setattr),
+ LSM_HOOK_INIT(inode_getattr, smack_inode_getattr),
++ LSM_HOOK_INIT(inode_xattr_skipcap, smack_inode_xattr_skipcap),
+ LSM_HOOK_INIT(inode_setxattr, smack_inode_setxattr),
+ LSM_HOOK_INIT(inode_post_setxattr, smack_inode_post_setxattr),
+ LSM_HOOK_INIT(inode_getxattr, smack_inode_getxattr),
+diff --git a/sound/core/ump.c b/sound/core/ump.c
+index 3f61220c23b4e..0f0d7e895c5aa 100644
+--- a/sound/core/ump.c
++++ b/sound/core/ump.c
+@@ -733,6 +733,12 @@ static void fill_fb_info(struct snd_ump_endpoint *ump,
+ info->block_id, info->direction, info->active,
+ info->first_group, info->num_groups, info->midi_ci_version,
+ info->sysex8_streams, info->flags);
++
++ if ((info->flags & SNDRV_UMP_BLOCK_IS_MIDI1) && info->num_groups != 1) {
++ info->num_groups = 1;
++ ump_dbg(ump, "FB %d: corrected groups to 1 for MIDI1\n",
++ info->block_id);
++ }
+ }
+
+ /* check whether the FB info gets updated by the current message */
+@@ -806,6 +812,13 @@ static int ump_handle_fb_name_msg(struct snd_ump_endpoint *ump,
+ if (!fb)
+ return -ENODEV;
+
++ if (ump->parsed &&
++ (ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS)) {
++ ump_dbg(ump, "Skipping static FB name update (blk#%d)\n",
++ fb->info.block_id);
++ return 0;
++ }
++
+ ret = ump_append_string(ump, fb->info.name, sizeof(fb->info.name),
+ buf->raw, 3);
+ /* notify the FB name update to sequencer, too */
+diff --git a/sound/firewire/amdtp-stream.c b/sound/firewire/amdtp-stream.c
+index d35d0a420ee08..1a163bbcabd79 100644
+--- a/sound/firewire/amdtp-stream.c
++++ b/sound/firewire/amdtp-stream.c
+@@ -1180,8 +1180,7 @@ static void process_rx_packets(struct fw_iso_context *context, u32 tstamp, size_
+ (void)fw_card_read_cycle_time(fw_parent_device(s->unit)->card, &curr_cycle_time);
+
+ for (i = 0; i < packets; ++i) {
+- DEFINE_FLEX(struct fw_iso_packet, template, header,
+- header_length, CIP_HEADER_QUADLETS);
++ DEFINE_RAW_FLEX(struct fw_iso_packet, template, header, CIP_HEADER_QUADLETS);
+ bool sched_irq = false;
+
+ build_it_pkt_header(s, desc->cycle, template, pkt_header_length,
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index 6f4512b598eaa..d749769438ea5 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -10360,10 +10360,10 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x1043, 0x1f62, "ASUS UX7602ZM", ALC245_FIXUP_CS35L41_SPI_2),
+ SND_PCI_QUIRK(0x1043, 0x1f92, "ASUS ROG Flow X16", ALC289_FIXUP_ASUS_GA401),
+ SND_PCI_QUIRK(0x1043, 0x3030, "ASUS ZN270IE", ALC256_FIXUP_ASUS_AIO_GPIO2),
+- SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC245_FIXUP_CS35L41_SPI_2),
+- SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC245_FIXUP_CS35L41_SPI_2),
++ SND_PCI_QUIRK(0x1043, 0x3a20, "ASUS G614JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
++ SND_PCI_QUIRK(0x1043, 0x3a30, "ASUS G814JVR/JIR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+ SND_PCI_QUIRK(0x1043, 0x3a40, "ASUS G814JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+- SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC245_FIXUP_CS35L41_SPI_2),
++ SND_PCI_QUIRK(0x1043, 0x3a50, "ASUS G834JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+ SND_PCI_QUIRK(0x1043, 0x3a60, "ASUS G634JYR/JZR", ALC285_FIXUP_ASUS_SPI_REAR_SPEAKERS),
+ SND_PCI_QUIRK(0x1043, 0x831a, "ASUS P901", ALC269_FIXUP_STEREO_DMIC),
+ SND_PCI_QUIRK(0x1043, 0x834a, "ASUS S101", ALC269_FIXUP_STEREO_DMIC),
+diff --git a/sound/soc/amd/acp-es8336.c b/sound/soc/amd/acp-es8336.c
+index e079b3218c6f4..3756b8bef17bc 100644
+--- a/sound/soc/amd/acp-es8336.c
++++ b/sound/soc/amd/acp-es8336.c
+@@ -203,8 +203,10 @@ static int st_es8336_late_probe(struct snd_soc_card *card)
+
+ codec_dev = acpi_get_first_physical_node(adev);
+ acpi_dev_put(adev);
+- if (!codec_dev)
++ if (!codec_dev) {
+ dev_err(card->dev, "can not find codec dev\n");
++ return -ENODEV;
++ }
+
+ ret = devm_acpi_dev_add_driver_gpios(codec_dev, acpi_es8336_gpios);
+ if (ret)
+diff --git a/sound/soc/amd/yc/acp6x-mach.c b/sound/soc/amd/yc/acp6x-mach.c
+index 4e3a8ce690a45..36dddf230c2c4 100644
+--- a/sound/soc/amd/yc/acp6x-mach.c
++++ b/sound/soc/amd/yc/acp6x-mach.c
+@@ -220,6 +220,13 @@ static const struct dmi_system_id yc_acp_quirk_table[] = {
+ DMI_MATCH(DMI_PRODUCT_NAME, "21J6"),
+ }
+ },
++ {
++ .driver_data = &acp6x_card,
++ .matches = {
++ DMI_MATCH(DMI_BOARD_VENDOR, "LENOVO"),
++ DMI_MATCH(DMI_PRODUCT_NAME, "21M5"),
++ }
++ },
+ {
+ .driver_data = &acp6x_card,
+ .matches = {
+diff --git a/sound/soc/codecs/cs35l56-shared.c b/sound/soc/codecs/cs35l56-shared.c
+index 30497152e02a7..f609cade805d7 100644
+--- a/sound/soc/codecs/cs35l56-shared.c
++++ b/sound/soc/codecs/cs35l56-shared.c
+@@ -397,7 +397,7 @@ int cs35l56_irq_request(struct cs35l56_base *cs35l56_base, int irq)
+ {
+ int ret;
+
+- if (!irq)
++ if (irq < 1)
+ return 0;
+
+ ret = devm_request_threaded_irq(cs35l56_base->dev, irq, NULL, cs35l56_irq,
+diff --git a/sound/soc/codecs/max98088.c b/sound/soc/codecs/max98088.c
+index 8b56ee550c09e..8b0645c634620 100644
+--- a/sound/soc/codecs/max98088.c
++++ b/sound/soc/codecs/max98088.c
+@@ -1318,6 +1318,7 @@ static int max98088_set_bias_level(struct snd_soc_component *component,
+ enum snd_soc_bias_level level)
+ {
+ struct max98088_priv *max98088 = snd_soc_component_get_drvdata(component);
++ int ret;
+
+ switch (level) {
+ case SND_SOC_BIAS_ON:
+@@ -1333,10 +1334,13 @@ static int max98088_set_bias_level(struct snd_soc_component *component,
+ */
+ if (!IS_ERR(max98088->mclk)) {
+ if (snd_soc_component_get_bias_level(component) ==
+- SND_SOC_BIAS_ON)
++ SND_SOC_BIAS_ON) {
+ clk_disable_unprepare(max98088->mclk);
+- else
+- clk_prepare_enable(max98088->mclk);
++ } else {
++ ret = clk_prepare_enable(max98088->mclk);
++ if (ret)
++ return ret;
++ }
+ }
+ break;
+
+diff --git a/sound/soc/codecs/pcm6240.c b/sound/soc/codecs/pcm6240.c
+index 86e126783a1df..8f7057e689fbf 100644
+--- a/sound/soc/codecs/pcm6240.c
++++ b/sound/soc/codecs/pcm6240.c
+@@ -2087,10 +2087,8 @@ static int pcmdevice_i2c_probe(struct i2c_client *i2c)
+ #endif
+
+ pcm_dev = devm_kzalloc(&i2c->dev, sizeof(*pcm_dev), GFP_KERNEL);
+- if (!pcm_dev) {
+- ret = -ENOMEM;
+- goto out;
+- }
++ if (!pcm_dev)
++ return -ENOMEM;
+
+ pcm_dev->chip_id = (id != NULL) ? id->driver_data : 0;
+
+diff --git a/sound/soc/codecs/tas2781-fmwlib.c b/sound/soc/codecs/tas2781-fmwlib.c
+index 265a8ca25cbbe..08082806d5892 100644
+--- a/sound/soc/codecs/tas2781-fmwlib.c
++++ b/sound/soc/codecs/tas2781-fmwlib.c
+@@ -2163,7 +2163,7 @@ static void tasdev_load_calibrated_data(struct tasdevice_priv *priv, int i)
+ return;
+
+ cal = cal_fmw->calibrations;
+- if (cal)
++ if (!cal)
+ return;
+
+ load_calib_data(priv, &cal->dev_data);
+@@ -2324,14 +2324,21 @@ void tasdevice_tuning_switch(void *context, int state)
+ struct tasdevice_fw *tas_fmw = tas_priv->fmw;
+ int profile_cfg_id = tas_priv->rcabin.profile_cfg_id;
+
+- if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) {
+- dev_err(tas_priv->dev, "DSP bin file not loaded\n");
++ /*
++ * Only RCA-based Playback can still work with no dsp program running
++ * inside the chip.
++ */
++ switch (tas_priv->fw_state) {
++ case TASDEVICE_RCA_FW_OK:
++ case TASDEVICE_DSP_FW_ALL_OK:
++ break;
++ default:
+ return;
+ }
+
+ if (state == 0) {
+- if (tas_priv->cur_prog < tas_fmw->nr_programs) {
+- /*dsp mode or tuning mode*/
++ if (tas_fmw && tas_priv->cur_prog < tas_fmw->nr_programs) {
++ /* dsp mode or tuning mode */
+ profile_cfg_id = tas_priv->rcabin.profile_cfg_id;
+ tasdevice_select_tuningprm_cfg(tas_priv,
+ tas_priv->cur_prog, tas_priv->cur_conf,
+@@ -2340,9 +2347,10 @@ void tasdevice_tuning_switch(void *context, int state)
+
+ tasdevice_select_cfg_blk(tas_priv, profile_cfg_id,
+ TASDEVICE_BIN_BLK_PRE_POWER_UP);
+- } else
++ } else {
+ tasdevice_select_cfg_blk(tas_priv, profile_cfg_id,
+ TASDEVICE_BIN_BLK_PRE_SHUTDOWN);
++ }
+ }
+ EXPORT_SYMBOL_NS_GPL(tasdevice_tuning_switch,
+ SND_SOC_TAS2781_FMWLIB);
+diff --git a/sound/soc/codecs/tas2781-i2c.c b/sound/soc/codecs/tas2781-i2c.c
+index 9350972dfefe7..c64d458e524e2 100644
+--- a/sound/soc/codecs/tas2781-i2c.c
++++ b/sound/soc/codecs/tas2781-i2c.c
+@@ -380,23 +380,37 @@ static void tasdevice_fw_ready(const struct firmware *fmw,
+ mutex_lock(&tas_priv->codec_lock);
+
+ ret = tasdevice_rca_parser(tas_priv, fmw);
+- if (ret)
++ if (ret) {
++ tasdevice_config_info_remove(tas_priv);
+ goto out;
++ }
+ tasdevice_create_control(tas_priv);
+
+ tasdevice_dsp_remove(tas_priv);
+ tasdevice_calbin_remove(tas_priv);
+- tas_priv->fw_state = TASDEVICE_DSP_FW_PENDING;
++ /*
++ * The baseline is the RCA-only case, and then the code attempts to
++ * load DSP firmware but in case of failures just keep going, i.e.
++ * failing to load DSP firmware is NOT an error.
++ */
++ tas_priv->fw_state = TASDEVICE_RCA_FW_OK;
+ scnprintf(tas_priv->coef_binaryname, 64, "%s_coef.bin",
+ tas_priv->dev_name);
+ ret = tasdevice_dsp_parser(tas_priv);
+ if (ret) {
+ dev_err(tas_priv->dev, "dspfw load %s error\n",
+ tas_priv->coef_binaryname);
+- tas_priv->fw_state = TASDEVICE_DSP_FW_FAIL;
+ goto out;
+ }
+- tasdevice_dsp_create_ctrls(tas_priv);
++
++ /*
++ * If no dsp-related kcontrol created, the dsp resource will be freed.
++ */
++ ret = tasdevice_dsp_create_ctrls(tas_priv);
++ if (ret) {
++ dev_err(tas_priv->dev, "dsp controls error\n");
++ goto out;
++ }
+
+ tas_priv->fw_state = TASDEVICE_DSP_FW_ALL_OK;
+
+@@ -417,9 +431,8 @@ static void tasdevice_fw_ready(const struct firmware *fmw,
+ tasdevice_prmg_load(tas_priv, 0);
+ tas_priv->cur_prog = 0;
+ out:
+- if (tas_priv->fw_state == TASDEVICE_DSP_FW_FAIL) {
+- /*If DSP FW fail, kcontrol won't be created */
+- tasdevice_config_info_remove(tas_priv);
++ if (tas_priv->fw_state == TASDEVICE_RCA_FW_OK) {
++ /* If DSP FW fail, DSP kcontrol won't be created. */
+ tasdevice_dsp_remove(tas_priv);
+ }
+ mutex_unlock(&tas_priv->codec_lock);
+@@ -466,14 +479,14 @@ static int tasdevice_startup(struct snd_pcm_substream *substream,
+ {
+ struct snd_soc_component *codec = dai->component;
+ struct tasdevice_priv *tas_priv = snd_soc_component_get_drvdata(codec);
+- int ret = 0;
+
+- if (tas_priv->fw_state != TASDEVICE_DSP_FW_ALL_OK) {
+- dev_err(tas_priv->dev, "DSP bin file not loaded\n");
+- ret = -EINVAL;
++ switch (tas_priv->fw_state) {
++ case TASDEVICE_RCA_FW_OK:
++ case TASDEVICE_DSP_FW_ALL_OK:
++ return 0;
++ default:
++ return -EINVAL;
+ }
+-
+- return ret;
+ }
+
+ static int tasdevice_hw_params(struct snd_pcm_substream *substream,
+diff --git a/sound/soc/codecs/wcd939x.c b/sound/soc/codecs/wcd939x.c
+index c49894aad8a54..97fd75a935b68 100644
+--- a/sound/soc/codecs/wcd939x.c
++++ b/sound/soc/codecs/wcd939x.c
+@@ -182,8 +182,6 @@ struct wcd939x_priv {
+ /* typec handling */
+ bool typec_analog_mux;
+ #if IS_ENABLED(CONFIG_TYPEC)
+- struct typec_mux_dev *typec_mux;
+- struct typec_switch_dev *typec_sw;
+ enum typec_orientation typec_orientation;
+ unsigned long typec_mode;
+ struct typec_switch *typec_switch;
+@@ -3528,6 +3526,68 @@ static const struct component_master_ops wcd939x_comp_ops = {
+ .unbind = wcd939x_unbind,
+ };
+
++static void __maybe_unused wcd939x_typec_mux_unregister(void *data)
++{
++ struct typec_mux_dev *typec_mux = data;
++
++ typec_mux_unregister(typec_mux);
++}
++
++static void __maybe_unused wcd939x_typec_switch_unregister(void *data)
++{
++ struct typec_switch_dev *typec_sw = data;
++
++ typec_switch_unregister(typec_sw);
++}
++
++static int wcd939x_add_typec(struct wcd939x_priv *wcd939x, struct device *dev)
++{
++#if IS_ENABLED(CONFIG_TYPEC)
++ int ret;
++ struct typec_mux_dev *typec_mux;
++ struct typec_switch_dev *typec_sw;
++ struct typec_mux_desc mux_desc = {
++ .drvdata = wcd939x,
++ .fwnode = dev_fwnode(dev),
++ .set = wcd939x_typec_mux_set,
++ };
++ struct typec_switch_desc sw_desc = {
++ .drvdata = wcd939x,
++ .fwnode = dev_fwnode(dev),
++ .set = wcd939x_typec_switch_set,
++ };
++
++ /*
++ * Is USBSS is used to mux analog lines,
++ * register a typec mux/switch to get typec events
++ */
++ if (!wcd939x->typec_analog_mux)
++ return 0;
++
++ typec_mux = typec_mux_register(dev, &mux_desc);
++ if (IS_ERR(typec_mux))
++ return dev_err_probe(dev, PTR_ERR(typec_mux),
++ "failed to register typec mux\n");
++
++ ret = devm_add_action_or_reset(dev, wcd939x_typec_mux_unregister,
++ typec_mux);
++ if (ret)
++ return ret;
++
++ typec_sw = typec_switch_register(dev, &sw_desc);
++ if (IS_ERR(typec_sw))
++ return dev_err_probe(dev, PTR_ERR(typec_sw),
++ "failed to register typec switch\n");
++
++ ret = devm_add_action_or_reset(dev, wcd939x_typec_switch_unregister,
++ typec_sw);
++ if (ret)
++ return ret;
++#endif
++
++ return 0;
++}
++
+ static int wcd939x_add_slave_components(struct wcd939x_priv *wcd939x,
+ struct device *dev,
+ struct component_match **matchptr)
+@@ -3576,42 +3636,13 @@ static int wcd939x_probe(struct platform_device *pdev)
+ return -EINVAL;
+ }
+
+-#if IS_ENABLED(CONFIG_TYPEC)
+- /*
+- * Is USBSS is used to mux analog lines,
+- * register a typec mux/switch to get typec events
+- */
+- if (wcd939x->typec_analog_mux) {
+- struct typec_mux_desc mux_desc = {
+- .drvdata = wcd939x,
+- .fwnode = dev_fwnode(dev),
+- .set = wcd939x_typec_mux_set,
+- };
+- struct typec_switch_desc sw_desc = {
+- .drvdata = wcd939x,
+- .fwnode = dev_fwnode(dev),
+- .set = wcd939x_typec_switch_set,
+- };
+-
+- wcd939x->typec_mux = typec_mux_register(dev, &mux_desc);
+- if (IS_ERR(wcd939x->typec_mux)) {
+- ret = dev_err_probe(dev, PTR_ERR(wcd939x->typec_mux),
+- "failed to register typec mux\n");
+- goto err_disable_regulators;
+- }
+-
+- wcd939x->typec_sw = typec_switch_register(dev, &sw_desc);
+- if (IS_ERR(wcd939x->typec_sw)) {
+- ret = dev_err_probe(dev, PTR_ERR(wcd939x->typec_sw),
+- "failed to register typec switch\n");
+- goto err_unregister_typec_mux;
+- }
+- }
+-#endif /* CONFIG_TYPEC */
++ ret = wcd939x_add_typec(wcd939x, dev);
++ if (ret)
++ goto err_disable_regulators;
+
+ ret = wcd939x_add_slave_components(wcd939x, dev, &match);
+ if (ret)
+- goto err_unregister_typec_switch;
++ goto err_disable_regulators;
+
+ wcd939x_reset(wcd939x);
+
+@@ -3628,18 +3659,6 @@ static int wcd939x_probe(struct platform_device *pdev)
+
+ return 0;
+
+-#if IS_ENABLED(CONFIG_TYPEC)
+-err_unregister_typec_mux:
+- if (wcd939x->typec_analog_mux)
+- typec_mux_unregister(wcd939x->typec_mux);
+-#endif /* CONFIG_TYPEC */
+-
+-err_unregister_typec_switch:
+-#if IS_ENABLED(CONFIG_TYPEC)
+- if (wcd939x->typec_analog_mux)
+- typec_switch_unregister(wcd939x->typec_sw);
+-#endif /* CONFIG_TYPEC */
+-
+ err_disable_regulators:
+ regulator_bulk_disable(WCD939X_MAX_SUPPLY, wcd939x->supplies);
+ regulator_bulk_free(WCD939X_MAX_SUPPLY, wcd939x->supplies);
+diff --git a/sound/soc/fsl/fsl_qmc_audio.c b/sound/soc/fsl/fsl_qmc_audio.c
+index bfaaa451735b8..dd90ef16fa973 100644
+--- a/sound/soc/fsl/fsl_qmc_audio.c
++++ b/sound/soc/fsl/fsl_qmc_audio.c
+@@ -604,6 +604,8 @@ static int qmc_audio_dai_parse(struct qmc_audio *qmc_audio, struct device_node *
+
+ qmc_dai->name = devm_kasprintf(qmc_audio->dev, GFP_KERNEL, "%s.%d",
+ np->parent->name, qmc_dai->id);
++ if (!qmc_dai->name)
++ return -ENOMEM;
+
+ qmc_dai->qmc_chan = devm_qmc_chan_get_byphandle(qmc_audio->dev, np,
+ "fsl,qmc-chan");
+diff --git a/sound/soc/intel/common/soc-acpi-intel-ssp-common.c b/sound/soc/intel/common/soc-acpi-intel-ssp-common.c
+index 75d0b931d895d..de7a3f7f47f10 100644
+--- a/sound/soc/intel/common/soc-acpi-intel-ssp-common.c
++++ b/sound/soc/intel/common/soc-acpi-intel-ssp-common.c
+@@ -64,6 +64,15 @@ static const struct codec_map amps[] = {
+ CODEC_MAP_ENTRY("RT1015P", "rt1015", RT1015P_ACPI_HID, CODEC_RT1015P),
+ CODEC_MAP_ENTRY("RT1019P", "rt1019", RT1019P_ACPI_HID, CODEC_RT1019P),
+ CODEC_MAP_ENTRY("RT1308", "rt1308", RT1308_ACPI_HID, CODEC_RT1308),
++
++ /*
++ * Monolithic components
++ *
++ * Only put components that can serve as both the amp and the codec below this line.
++ * This will ensure that if the part is used just as a codec and there is an amp as well
++ * then the amp will be selected properly.
++ */
++ CODEC_MAP_ENTRY("RT5650", "rt5650", RT5650_ACPI_HID, CODEC_RT5650),
+ };
+
+ enum snd_soc_acpi_intel_codec
+diff --git a/sound/soc/intel/common/soc-intel-quirks.h b/sound/soc/intel/common/soc-intel-quirks.h
+index de4e550c5b34d..42bd51456b945 100644
+--- a/sound/soc/intel/common/soc-intel-quirks.h
++++ b/sound/soc/intel/common/soc-intel-quirks.h
+@@ -11,7 +11,7 @@
+
+ #include <linux/platform_data/x86/soc.h>
+
+-#if IS_ENABLED(CONFIG_X86)
++#if IS_REACHABLE(CONFIG_IOSF_MBI)
+
+ #include <linux/dmi.h>
+ #include <asm/iosf_mbi.h>
+diff --git a/sound/soc/qcom/lpass-cpu.c b/sound/soc/qcom/lpass-cpu.c
+index b0f3e02cb043c..5a47f661e0c6f 100644
+--- a/sound/soc/qcom/lpass-cpu.c
++++ b/sound/soc/qcom/lpass-cpu.c
+@@ -1166,9 +1166,13 @@ int asoc_qcom_lpass_cpu_platform_probe(struct platform_device *pdev)
+ }
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "lpass-rxtx-cdc-dma-lpm");
++ if (!res)
++ return -EINVAL;
+ drvdata->rxtx_cdc_dma_lpm_buf = res->start;
+
+ res = platform_get_resource_byname(pdev, IORESOURCE_MEM, "lpass-va-cdc-dma-lpm");
++ if (!res)
++ return -EINVAL;
+ drvdata->va_cdc_dma_lpm_buf = res->start;
+ }
+
+diff --git a/sound/soc/sof/amd/pci-vangogh.c b/sound/soc/sof/amd/pci-vangogh.c
+index 16eb2994fbab9..eba5808401003 100644
+--- a/sound/soc/sof/amd/pci-vangogh.c
++++ b/sound/soc/sof/amd/pci-vangogh.c
+@@ -34,7 +34,6 @@ static const struct sof_amd_acp_desc vangogh_chip_info = {
+ .dsp_intr_base = ACP5X_DSP_SW_INTR_BASE,
+ .sram_pte_offset = ACP5X_SRAM_PTE_OFFSET,
+ .hw_semaphore_offset = ACP5X_AXI2DAGB_SEM_0,
+- .acp_clkmux_sel = ACP5X_CLKMUX_SEL,
+ .probe_reg_offset = ACP5X_FUTURE_REG_ACLK_0,
+ };
+
+diff --git a/sound/soc/sof/imx/imx8m.c b/sound/soc/sof/imx/imx8m.c
+index 1c7019c3cbd38..cdd1e79ef9f6a 100644
+--- a/sound/soc/sof/imx/imx8m.c
++++ b/sound/soc/sof/imx/imx8m.c
+@@ -234,7 +234,7 @@ static int imx8m_probe(struct snd_sof_dev *sdev)
+ /* set default mailbox offset for FW ready message */
+ sdev->dsp_box.offset = MBOX_OFFSET;
+
+- priv->regmap = syscon_regmap_lookup_by_compatible("fsl,dsp-ctrl");
++ priv->regmap = syscon_regmap_lookup_by_phandle(np, "fsl,dsp-ctrl");
+ if (IS_ERR(priv->regmap)) {
+ dev_err(sdev->dev, "cannot find dsp-ctrl registers");
+ ret = PTR_ERR(priv->regmap);
+diff --git a/sound/soc/sof/intel/hda-loader.c b/sound/soc/sof/intel/hda-loader.c
+index b8b914eaf7e05..75f6240cf3e1d 100644
+--- a/sound/soc/sof/intel/hda-loader.c
++++ b/sound/soc/sof/intel/hda-loader.c
+@@ -310,15 +310,19 @@ int hda_cl_copy_fw(struct snd_sof_dev *sdev, struct hdac_ext_stream *hext_stream
+ return ret;
+ }
+
+- /* Wait for completion of transfer */
+- time_left = wait_for_completion_timeout(&hda_stream->ioc,
+- msecs_to_jiffies(HDA_CL_DMA_IOC_TIMEOUT_MS));
+-
+- if (!time_left) {
+- dev_err(sdev->dev, "Code loader DMA did not complete\n");
+- return -ETIMEDOUT;
++ if (sdev->pdata->ipc_type == SOF_IPC_TYPE_4) {
++ /* Wait for completion of transfer */
++ time_left = wait_for_completion_timeout(&hda_stream->ioc,
++ msecs_to_jiffies(HDA_CL_DMA_IOC_TIMEOUT_MS));
++
++ if (!time_left) {
++ dev_err(sdev->dev, "Code loader DMA did not complete\n");
++ return -ETIMEDOUT;
++ }
++ dev_dbg(sdev->dev, "Code loader DMA done\n");
+ }
+- dev_dbg(sdev->dev, "Code loader DMA done, waiting for FW_ENTERED status\n");
++
++ dev_dbg(sdev->dev, "waiting for FW_ENTERED status\n");
+
+ status = snd_sof_dsp_read_poll_timeout(sdev, HDA_DSP_BAR,
+ chip->rom_status_reg, reg,
+diff --git a/sound/soc/sof/intel/hda.c b/sound/soc/sof/intel/hda.c
+index dead1c19558bb..81647ddac8cbc 100644
+--- a/sound/soc/sof/intel/hda.c
++++ b/sound/soc/sof/intel/hda.c
+@@ -1307,9 +1307,10 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
+ const struct sof_dev_desc *desc = sof_pdata->desc;
+ struct hdac_bus *bus = sof_to_bus(sdev);
+ struct snd_soc_acpi_mach *mach = NULL;
+- enum snd_soc_acpi_intel_codec codec_type;
++ enum snd_soc_acpi_intel_codec codec_type, amp_type;
+ const char *tplg_filename;
+ const char *tplg_suffix;
++ bool amp_name_valid;
+
+ /* Try I2S or DMIC if it is supported */
+ if (interface_mask & (BIT(SOF_DAI_INTEL_SSP) | BIT(SOF_DAI_INTEL_DMIC)))
+@@ -1413,15 +1414,16 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
+ }
+ }
+
+- codec_type = snd_soc_acpi_intel_detect_amp_type(sdev->dev);
++ amp_type = snd_soc_acpi_intel_detect_amp_type(sdev->dev);
++ codec_type = snd_soc_acpi_intel_detect_codec_type(sdev->dev);
++ amp_name_valid = amp_type != CODEC_NONE && amp_type != codec_type;
+
+- if (tplg_fixup &&
+- mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_AMP_NAME &&
+- codec_type != CODEC_NONE) {
+- tplg_suffix = snd_soc_acpi_intel_get_amp_tplg_suffix(codec_type);
++ if (tplg_fixup && amp_name_valid &&
++ mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_AMP_NAME) {
++ tplg_suffix = snd_soc_acpi_intel_get_amp_tplg_suffix(amp_type);
+ if (!tplg_suffix) {
+ dev_err(sdev->dev, "no tplg suffix found, amp %d\n",
+- codec_type);
++ amp_type);
+ return NULL;
+ }
+
+@@ -1436,7 +1438,6 @@ struct snd_soc_acpi_mach *hda_machine_select(struct snd_sof_dev *sdev)
+ add_extension = true;
+ }
+
+- codec_type = snd_soc_acpi_intel_detect_codec_type(sdev->dev);
+
+ if (tplg_fixup &&
+ mach->tplg_quirk_mask & SND_SOC_ACPI_TPLG_INTEL_CODEC_NAME &&
+diff --git a/sound/soc/sof/ipc4-topology.c b/sound/soc/sof/ipc4-topology.c
+index 00987039c9720..4d261b9e6d7ec 100644
+--- a/sound/soc/sof/ipc4-topology.c
++++ b/sound/soc/sof/ipc4-topology.c
+@@ -1358,7 +1358,13 @@ static void sof_ipc4_unprepare_copier_module(struct snd_sof_widget *swidget)
+ ipc4_copier = dai->private;
+
+ if (pipeline->use_chain_dma) {
+- pipeline->msg.primary = 0;
++ /*
++ * Preserve the DMA Link ID and clear other bits since
++ * the DMA Link ID is only configured once during
++ * dai_config, other fields are expected to be 0 for
++ * re-configuration
++ */
++ pipeline->msg.primary &= SOF_IPC4_GLB_CHAIN_DMA_LINK_ID_MASK;
+ pipeline->msg.extension = 0;
+ }
+
+@@ -2869,7 +2875,7 @@ static void sof_ipc4_put_queue_id(struct snd_sof_widget *swidget, int queue_id,
+ static int sof_ipc4_set_copier_sink_format(struct snd_sof_dev *sdev,
+ struct snd_sof_widget *src_widget,
+ struct snd_sof_widget *sink_widget,
+- int sink_id)
++ struct snd_sof_route *sroute)
+ {
+ struct sof_ipc4_copier_config_set_sink_format format;
+ const struct sof_ipc_ops *iops = sdev->ipc->ops;
+@@ -2878,9 +2884,6 @@ static int sof_ipc4_set_copier_sink_format(struct snd_sof_dev *sdev,
+ struct sof_ipc4_fw_module *fw_module;
+ struct sof_ipc4_msg msg = {{ 0 }};
+
+- dev_dbg(sdev->dev, "%s set copier sink %d format\n",
+- src_widget->widget->name, sink_id);
+-
+ if (WIDGET_IS_DAI(src_widget->id)) {
+ struct snd_sof_dai *dai = src_widget->private;
+
+@@ -2891,13 +2894,15 @@ static int sof_ipc4_set_copier_sink_format(struct snd_sof_dev *sdev,
+
+ fw_module = src_widget->module_info;
+
+- format.sink_id = sink_id;
++ format.sink_id = sroute->src_queue_id;
+ memcpy(&format.source_fmt, &src_config->audio_fmt, sizeof(format.source_fmt));
+
+- pin_fmt = sof_ipc4_get_input_pin_audio_fmt(sink_widget, sink_id);
++ pin_fmt = sof_ipc4_get_input_pin_audio_fmt(sink_widget, sroute->dst_queue_id);
+ if (!pin_fmt) {
+- dev_err(sdev->dev, "Unable to get pin %d format for %s",
+- sink_id, sink_widget->widget->name);
++ dev_err(sdev->dev,
++ "Failed to get input audio format of %s:%d for output of %s:%d\n",
++ sink_widget->widget->name, sroute->dst_queue_id,
++ src_widget->widget->name, sroute->src_queue_id);
+ return -EINVAL;
+ }
+
+@@ -2955,7 +2960,8 @@ static int sof_ipc4_route_setup(struct snd_sof_dev *sdev, struct snd_sof_route *
+ sroute->src_queue_id = sof_ipc4_get_queue_id(src_widget, sink_widget,
+ SOF_PIN_TYPE_OUTPUT);
+ if (sroute->src_queue_id < 0) {
+- dev_err(sdev->dev, "failed to get queue ID for source widget: %s\n",
++ dev_err(sdev->dev,
++ "failed to get src_queue_id ID from source widget %s\n",
+ src_widget->widget->name);
+ return sroute->src_queue_id;
+ }
+@@ -2963,7 +2969,8 @@ static int sof_ipc4_route_setup(struct snd_sof_dev *sdev, struct snd_sof_route *
+ sroute->dst_queue_id = sof_ipc4_get_queue_id(src_widget, sink_widget,
+ SOF_PIN_TYPE_INPUT);
+ if (sroute->dst_queue_id < 0) {
+- dev_err(sdev->dev, "failed to get queue ID for sink widget: %s\n",
++ dev_err(sdev->dev,
++ "failed to get dst_queue_id ID from sink widget %s\n",
+ sink_widget->widget->name);
+ sof_ipc4_put_queue_id(src_widget, sroute->src_queue_id,
+ SOF_PIN_TYPE_OUTPUT);
+@@ -2972,10 +2979,11 @@ static int sof_ipc4_route_setup(struct snd_sof_dev *sdev, struct snd_sof_route *
+
+ /* Pin 0 format is already set during copier module init */
+ if (sroute->src_queue_id > 0 && WIDGET_IS_COPIER(src_widget->id)) {
+- ret = sof_ipc4_set_copier_sink_format(sdev, src_widget, sink_widget,
+- sroute->src_queue_id);
++ ret = sof_ipc4_set_copier_sink_format(sdev, src_widget,
++ sink_widget, sroute);
+ if (ret < 0) {
+- dev_err(sdev->dev, "failed to set sink format for %s source queue ID %d\n",
++ dev_err(sdev->dev,
++ "failed to set sink format for source %s:%d\n",
+ src_widget->widget->name, sroute->src_queue_id);
+ goto out;
+ }
+@@ -3093,8 +3101,14 @@ static int sof_ipc4_dai_config(struct snd_sof_dev *sdev, struct snd_sof_widget *
+ return 0;
+
+ if (pipeline->use_chain_dma) {
+- pipeline->msg.primary &= ~SOF_IPC4_GLB_CHAIN_DMA_LINK_ID_MASK;
+- pipeline->msg.primary |= SOF_IPC4_GLB_CHAIN_DMA_LINK_ID(data->dai_data);
++ /*
++ * Only configure the DMA Link ID for ChainDMA when this op is
++ * invoked with SOF_DAI_CONFIG_FLAGS_HW_PARAMS
++ */
++ if (flags & SOF_DAI_CONFIG_FLAGS_HW_PARAMS) {
++ pipeline->msg.primary &= ~SOF_IPC4_GLB_CHAIN_DMA_LINK_ID_MASK;
++ pipeline->msg.primary |= SOF_IPC4_GLB_CHAIN_DMA_LINK_ID(data->dai_data);
++ }
+ return 0;
+ }
+
+diff --git a/sound/usb/mixer.c b/sound/usb/mixer.c
+index 409fc11646948..d1bdb0b93bda0 100644
+--- a/sound/usb/mixer.c
++++ b/sound/usb/mixer.c
+@@ -1211,6 +1211,13 @@ static void volume_control_quirks(struct usb_mixer_elem_info *cval,
+ cval->res = 16;
+ }
+ break;
++ case USB_ID(0x1bcf, 0x2281): /* HD Webcam */
++ if (!strcmp(kctl->id.name, "Mic Capture Volume")) {
++ usb_audio_info(chip,
++ "set resolution quirk: cval->res = 16\n");
++ cval->res = 16;
++ }
++ break;
+ }
+ }
+
+diff --git a/sound/usb/quirks.c b/sound/usb/quirks.c
+index 58156fbca02c7..ea063a14cdd8f 100644
+--- a/sound/usb/quirks.c
++++ b/sound/usb/quirks.c
+@@ -2125,6 +2125,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
+ QUIRK_FLAG_CTL_MSG_DELAY_1M),
+ DEVICE_FLG(0x0b0e, 0x0349, /* Jabra 550a */
+ QUIRK_FLAG_CTL_MSG_DELAY_1M),
++ DEVICE_FLG(0x0c45, 0x6340, /* Sonix HD USB Camera */
++ QUIRK_FLAG_GET_SAMPLE_RATE),
+ DEVICE_FLG(0x0ecb, 0x205c, /* JBL Quantum610 Wireless */
+ QUIRK_FLAG_FIXED_RATE),
+ DEVICE_FLG(0x0ecb, 0x2069, /* JBL Quantum810 Wireless */
+@@ -2167,6 +2169,8 @@ static const struct usb_audio_quirk_flags_table quirk_flags_table[] = {
+ QUIRK_FLAG_GET_SAMPLE_RATE),
+ DEVICE_FLG(0x19f7, 0x0035, /* RODE NT-USB+ */
+ QUIRK_FLAG_GET_SAMPLE_RATE),
++ DEVICE_FLG(0x1bcf, 0x2281, /* HD Webcam */
++ QUIRK_FLAG_GET_SAMPLE_RATE),
+ DEVICE_FLG(0x1bcf, 0x2283, /* NexiGo N930AF FHD Webcam */
+ QUIRK_FLAG_GET_SAMPLE_RATE),
+ DEVICE_FLG(0x2040, 0x7200, /* Hauppauge HVR-950Q */
+diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c
+index 958e92acca8e2..9b75639434b81 100644
+--- a/tools/bpf/bpftool/common.c
++++ b/tools/bpf/bpftool/common.c
+@@ -410,7 +410,7 @@ void get_prog_full_name(const struct bpf_prog_info *prog_info, int prog_fd,
+ {
+ const char *prog_name = prog_info->name;
+ const struct btf_type *func_type;
+- const struct bpf_func_info finfo = {};
++ struct bpf_func_info finfo = {};
+ struct bpf_prog_info info = {};
+ __u32 info_len = sizeof(info);
+ struct btf *prog_btf = NULL;
+diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c
+index 1a501cf09e782..40ea743d139fd 100644
+--- a/tools/bpf/bpftool/prog.c
++++ b/tools/bpf/bpftool/prog.c
+@@ -1813,6 +1813,10 @@ static int load_with_options(int argc, char **argv, bool first_prog_only)
+ }
+
+ if (pinmaps) {
++ err = create_and_mount_bpffs_dir(pinmaps);
++ if (err)
++ goto err_unpin;
++
+ err = bpf_object__pin_maps(obj, pinmaps);
+ if (err) {
+ p_err("failed to pin all maps");
+diff --git a/tools/bpf/resolve_btfids/main.c b/tools/bpf/resolve_btfids/main.c
+index af393c7dee1f1..b3edc239fe562 100644
+--- a/tools/bpf/resolve_btfids/main.c
++++ b/tools/bpf/resolve_btfids/main.c
+@@ -696,7 +696,7 @@ static int sets_patch(struct object *obj)
+ * Make sure id is at the beginning of the pairs
+ * struct, otherwise the below qsort would not work.
+ */
+- BUILD_BUG_ON(set8->pairs != &set8->pairs[0].id);
++ BUILD_BUG_ON((u32 *)set8->pairs != &set8->pairs[0].id);
+ qsort(set8->pairs, set8->cnt, sizeof(set8->pairs[0]), cmp_id);
+
+ /*
+diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
+index 2d0840ef599af..142060bbce0a0 100644
+--- a/tools/lib/bpf/btf.c
++++ b/tools/lib/bpf/btf.c
+@@ -598,7 +598,7 @@ static int btf_sanity_check(const struct btf *btf)
+ __u32 i, n = btf__type_cnt(btf);
+ int err;
+
+- for (i = 1; i < n; i++) {
++ for (i = btf->start_id; i < n; i++) {
+ t = btf_type_by_id(btf, i);
+ err = btf_validate_type(btf, t, i);
+ if (err)
+diff --git a/tools/lib/bpf/btf_dump.c b/tools/lib/bpf/btf_dump.c
+index 5dbca76b953f4..894860111ddb2 100644
+--- a/tools/lib/bpf/btf_dump.c
++++ b/tools/lib/bpf/btf_dump.c
+@@ -1559,10 +1559,12 @@ static void btf_dump_emit_type_chain(struct btf_dump *d,
+ * Clang for BPF target generates func_proto with no
+ * args as a func_proto with a single void arg (e.g.,
+ * `int (*f)(void)` vs just `int (*f)()`). We are
+- * going to pretend there are no args for such case.
++ * going to emit valid empty args (void) syntax for
++ * such case. Similarly and conveniently, valid
++ * no args case can be special-cased here as well.
+ */
+- if (vlen == 1 && p->type == 0) {
+- btf_dump_printf(d, ")");
++ if (vlen == 0 || (vlen == 1 && p->type == 0)) {
++ btf_dump_printf(d, "void)");
+ return;
+ }
+
+diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
+index a0dcfb82e455d..7e7e686008c62 100644
+--- a/tools/lib/bpf/libbpf_internal.h
++++ b/tools/lib/bpf/libbpf_internal.h
+@@ -597,13 +597,9 @@ static inline int ensure_good_fd(int fd)
+ return fd;
+ }
+
+-static inline int sys_dup2(int oldfd, int newfd)
++static inline int sys_dup3(int oldfd, int newfd, int flags)
+ {
+-#ifdef __NR_dup2
+- return syscall(__NR_dup2, oldfd, newfd);
+-#else
+- return syscall(__NR_dup3, oldfd, newfd, 0);
+-#endif
++ return syscall(__NR_dup3, oldfd, newfd, flags);
+ }
+
+ /* Point *fixed_fd* to the same file that *tmp_fd* points to.
+@@ -614,7 +610,7 @@ static inline int reuse_fd(int fixed_fd, int tmp_fd)
+ {
+ int err;
+
+- err = sys_dup2(tmp_fd, fixed_fd);
++ err = sys_dup3(tmp_fd, fixed_fd, O_CLOEXEC);
+ err = err < 0 ? -errno : 0;
+ close(tmp_fd); /* clean up temporary FD */
+ return err;
+diff --git a/tools/lib/bpf/linker.c b/tools/lib/bpf/linker.c
+index 0d4be829551b5..5a583053e3119 100644
+--- a/tools/lib/bpf/linker.c
++++ b/tools/lib/bpf/linker.c
+@@ -2213,10 +2213,17 @@ static int linker_fixup_btf(struct src_obj *obj)
+ vi = btf_var_secinfos(t);
+ for (j = 0, m = btf_vlen(t); j < m; j++, vi++) {
+ const struct btf_type *vt = btf__type_by_id(obj->btf, vi->type);
+- const char *var_name = btf__str_by_offset(obj->btf, vt->name_off);
+- int var_linkage = btf_var(vt)->linkage;
++ const char *var_name;
++ int var_linkage;
+ Elf64_Sym *sym;
+
++ /* could be a variable or function */
++ if (!btf_is_var(vt))
++ continue;
++
++ var_name = btf__str_by_offset(obj->btf, vt->name_off);
++ var_linkage = btf_var(vt)->linkage;
++
+ /* no need to patch up static or extern vars */
+ if (var_linkage != BTF_VAR_GLOBAL_ALLOCATED)
+ continue;
+diff --git a/tools/memory-model/lock.cat b/tools/memory-model/lock.cat
+index 53b5a492739d0..21ba650869383 100644
+--- a/tools/memory-model/lock.cat
++++ b/tools/memory-model/lock.cat
+@@ -102,19 +102,19 @@ let rf-lf = rfe-lf | rfi-lf
+ * within one of the lock's critical sections returns False.
+ *)
+
+-(* rfi for RU events: an RU may read from the last po-previous UL *)
+-let rfi-ru = ([UL] ; po-loc ; [RU]) \ ([UL] ; po-loc ; [LKW] ; po-loc)
+-
+-(* rfe for RU events: an RU may read from an external UL or the initial write *)
+-let all-possible-rfe-ru =
+- let possible-rfe-ru r =
++(*
++ * rf for RU events: an RU may read from an external UL or the initial write,
++ * or from the last po-previous UL
++ *)
++let all-possible-rf-ru =
++ let possible-rf-ru r =
+ let pair-to-relation p = p ++ 0
+- in map pair-to-relation (((UL | IW) * {r}) & loc & ext)
+- in map possible-rfe-ru RU
++ in map pair-to-relation ((((UL | IW) * {r}) & loc & ext) |
++ (((UL * {r}) & po-loc) \ ([UL] ; po-loc ; [LKW] ; po-loc)))
++ in map possible-rf-ru RU
+
+ (* Generate all rf relations for RU events *)
+-with rfe-ru from cross(all-possible-rfe-ru)
+-let rf-ru = rfe-ru | rfi-ru
++with rf-ru from cross(all-possible-rf-ru)
+
+ (* Final rf relation *)
+ let rf = rf | rf-lf | rf-ru
+diff --git a/tools/objtool/noreturns.h b/tools/objtool/noreturns.h
+index 7ebf29c911849..1e8141ef1b15d 100644
+--- a/tools/objtool/noreturns.h
++++ b/tools/objtool/noreturns.h
+@@ -7,12 +7,16 @@
+ * Yes, this is unfortunate. A better solution is in the works.
+ */
+ NORETURN(__fortify_panic)
++NORETURN(__ia32_sys_exit)
++NORETURN(__ia32_sys_exit_group)
+ NORETURN(__kunit_abort)
+ NORETURN(__module_put_and_kthread_exit)
+ NORETURN(__reiserfs_panic)
+ NORETURN(__stack_chk_fail)
+ NORETURN(__tdx_hypercall_failed)
+ NORETURN(__ubsan_handle_builtin_unreachable)
++NORETURN(__x64_sys_exit)
++NORETURN(__x64_sys_exit_group)
+ NORETURN(arch_cpu_idle_dead)
+ NORETURN(bch2_trans_in_restart_error)
+ NORETURN(bch2_trans_restart_error)
+diff --git a/tools/perf/arch/powerpc/util/skip-callchain-idx.c b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+index 5f3edb3004d84..356786432fd3c 100644
+--- a/tools/perf/arch/powerpc/util/skip-callchain-idx.c
++++ b/tools/perf/arch/powerpc/util/skip-callchain-idx.c
+@@ -159,9 +159,9 @@ static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc)
+ Dwarf_Addr start = pc;
+ Dwarf_Addr end = pc;
+ bool signalp;
+- const char *exec_file = dso->long_name;
++ const char *exec_file = dso__long_name(dso);
+
+- dwfl = dso->dwfl;
++ dwfl = RC_CHK_ACCESS(dso)->dwfl;
+
+ if (!dwfl) {
+ dwfl = dwfl_begin(&offline_callbacks);
+@@ -183,7 +183,7 @@ static int check_return_addr(struct dso *dso, u64 map_start, Dwarf_Addr pc)
+ dwfl_end(dwfl);
+ goto out;
+ }
+- dso->dwfl = dwfl;
++ RC_CHK_ACCESS(dso)->dwfl = dwfl;
+ }
+
+ mod = dwfl_addrmodule(dwfl, pc);
+@@ -267,7 +267,7 @@ int arch_skip_callchain_idx(struct thread *thread, struct ip_callchain *chain)
+ rc = check_return_addr(dso, map__start(al.map), ip);
+
+ pr_debug("[DSO %s, sym %s, ip 0x%" PRIx64 "] rc %d\n",
+- dso->long_name, al.sym->name, ip, rc);
++ dso__long_name(dso), al.sym->name, ip, rc);
+
+ if (rc == 0) {
+ /*
+diff --git a/tools/perf/arch/x86/util/intel-pt.c b/tools/perf/arch/x86/util/intel-pt.c
+index 6de7e2d210756..4b710e875953a 100644
+--- a/tools/perf/arch/x86/util/intel-pt.c
++++ b/tools/perf/arch/x86/util/intel-pt.c
+@@ -32,6 +32,7 @@
+ #include "../../../util/tsc.h"
+ #include <internal/lib.h> // page_size
+ #include "../../../util/intel-pt.h"
++#include <api/fs/fs.h>
+
+ #define KiB(x) ((x) * 1024)
+ #define MiB(x) ((x) * 1024 * 1024)
+@@ -428,6 +429,16 @@ static int intel_pt_track_switches(struct evlist *evlist)
+ }
+ #endif
+
++static bool intel_pt_exclude_guest(void)
++{
++ int pt_mode;
++
++ if (sysfs__read_int("module/kvm_intel/parameters/pt_mode", &pt_mode))
++ pt_mode = 0;
++
++ return pt_mode == 1;
++}
++
+ static void intel_pt_valid_str(char *str, size_t len, u64 valid)
+ {
+ unsigned int val, last = 0, state = 1;
+@@ -620,6 +631,7 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
+ }
+ evsel->core.attr.freq = 0;
+ evsel->core.attr.sample_period = 1;
++ evsel->core.attr.exclude_guest = intel_pt_exclude_guest();
+ evsel->no_aux_samples = true;
+ evsel->needs_auxtrace_mmap = true;
+ intel_pt_evsel = evsel;
+@@ -758,7 +770,8 @@ static int intel_pt_recording_options(struct auxtrace_record *itr,
+ }
+
+ if (!opts->auxtrace_snapshot_mode && !opts->auxtrace_sample_mode) {
+- u32 aux_watermark = opts->auxtrace_mmap_pages * page_size / 4;
++ size_t aw = opts->auxtrace_mmap_pages * (size_t)page_size / 4;
++ u32 aux_watermark = aw > UINT_MAX ? UINT_MAX : aw;
+
+ intel_pt_evsel->core.attr.aux_watermark = aux_watermark;
+ }
+diff --git a/tools/perf/tests/shell/test_arm_callgraph_fp.sh b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+index 61898e2566160..9caa361301759 100755
+--- a/tools/perf/tests/shell/test_arm_callgraph_fp.sh
++++ b/tools/perf/tests/shell/test_arm_callgraph_fp.sh
+@@ -28,28 +28,21 @@ cleanup_files()
+
+ trap cleanup_files EXIT TERM INT
+
+-# Add a 1 second delay to skip samples that are not in the leaf() function
+ # shellcheck disable=SC2086
+-perf record -o "$PERF_DATA" --call-graph fp -e cycles//u -D 1000 --user-callchains -- $TEST_PROGRAM 2> /dev/null &
+-PID=$!
++perf record -o "$PERF_DATA" --call-graph fp -e cycles//u --user-callchains -- $TEST_PROGRAM
+
+-echo " + Recording (PID=$PID)..."
+-sleep 2
+-echo " + Stopping perf-record..."
+-
+-kill $PID
+-wait $PID
++# Try opening the file so any immediate errors are visible in the log
++perf script -i "$PERF_DATA" -F comm,ip,sym | head -n4
+
+-# expected perf-script output:
++# expected perf-script output if 'leaf' has been inserted correctly:
+ #
+-# program
++# perf
+ # 728 leaf
+ # 753 parent
+ # 76c leafloop
+-# ...
++# ... remaining stack to main() ...
+
+-perf script -i "$PERF_DATA" -F comm,ip,sym | head -n4
+-perf script -i "$PERF_DATA" -F comm,ip,sym | head -n4 | \
+- awk '{ if ($2 != "") sym[i++] = $2 } END { if (sym[0] != "leaf" ||
+- sym[1] != "parent" ||
+- sym[2] != "leafloop") exit 1 }'
++# Each frame is separated by a tab, some spaces and an address
++SEP="[[:space:]]+ [[:xdigit:]]+"
++perf script -i "$PERF_DATA" -F comm,ip,sym | tr '\n' ' ' | \
++ grep -E -q "perf $SEP leaf $SEP parent $SEP leafloop"
+diff --git a/tools/perf/tests/workloads/leafloop.c b/tools/perf/tests/workloads/leafloop.c
+index 1bf5cc97649b0..f7561767e32cd 100644
+--- a/tools/perf/tests/workloads/leafloop.c
++++ b/tools/perf/tests/workloads/leafloop.c
+@@ -1,6 +1,8 @@
+ /* SPDX-License-Identifier: GPL-2.0 */
++#include <signal.h>
+ #include <stdlib.h>
+ #include <linux/compiler.h>
++#include <unistd.h>
+ #include "../tests.h"
+
+ /* We want to check these symbols in perf script */
+@@ -8,10 +10,16 @@ noinline void leaf(volatile int b);
+ noinline void parent(volatile int b);
+
+ static volatile int a;
++static volatile sig_atomic_t done;
++
++static void sighandler(int sig __maybe_unused)
++{
++ done = 1;
++}
+
+ noinline void leaf(volatile int b)
+ {
+- for (;;)
++ while (!done)
+ a += b;
+ }
+
+@@ -22,12 +30,16 @@ noinline void parent(volatile int b)
+
+ static int leafloop(int argc, const char **argv)
+ {
+- int c = 1;
++ int sec = 1;
+
+ if (argc > 0)
+- c = atoi(argv[0]);
++ sec = atoi(argv[0]);
++
++ signal(SIGINT, sighandler);
++ signal(SIGALRM, sighandler);
++ alarm(sec);
+
+- parent(c);
++ parent(sec);
+ return 0;
+ }
+
+diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
+index 93ce3d47e47e6..6da24aa039ebb 100644
+--- a/tools/perf/ui/gtk/annotate.c
++++ b/tools/perf/ui/gtk/annotate.c
+@@ -180,13 +180,14 @@ static int symbol__gtk_annotate(struct map_symbol *ms, struct evsel *evsel,
+ GtkWidget *tab_label;
+ int err;
+
+- if (dso->annotate_warned)
++ if (dso__annotate_warned(dso))
+ return -1;
+
+ err = symbol__annotate(ms, evsel, NULL);
+ if (err) {
+ char msg[BUFSIZ];
+- dso->annotate_warned = true;
++
++ dso__set_annotate_warned(dso);
+ symbol__strerror_disassemble(ms, err, msg, sizeof(msg));
+ ui__error("Couldn't annotate %s: %s\n", sym->name, msg);
+ return -1;
+diff --git a/tools/perf/util/cs-etm.c b/tools/perf/util/cs-etm.c
+index 32818bd7cd177..5e9fbcfad7d44 100644
+--- a/tools/perf/util/cs-etm.c
++++ b/tools/perf/util/cs-etm.c
+@@ -1013,7 +1013,7 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
+ if (!dso)
+ goto out;
+
+- if (dso->data.status == DSO_DATA_STATUS_ERROR &&
++ if (dso__data(dso)->status == DSO_DATA_STATUS_ERROR &&
+ dso__data_status_seen(dso, DSO_DATA_STATUS_SEEN_ITRACE))
+ goto out;
+
+@@ -1027,11 +1027,11 @@ static u32 cs_etm__mem_access(struct cs_etm_queue *etmq, u8 trace_chan_id,
+ if (len <= 0) {
+ ui__warning_once("CS ETM Trace: Missing DSO. Use 'perf archive' or debuginfod to export data from the traced system.\n"
+ " Enable CONFIG_PROC_KCORE or use option '-k /path/to/vmlinux' for kernel symbols.\n");
+- if (!dso->auxtrace_warned) {
++ if (!dso__auxtrace_warned(dso)) {
+ pr_err("CS ETM Trace: Debug data not found for address %#"PRIx64" in %s\n",
+- address,
+- dso->long_name ? dso->long_name : "Unknown");
+- dso->auxtrace_warned = true;
++ address,
++ dso__long_name(dso) ? dso__long_name(dso) : "Unknown");
++ dso__set_auxtrace_warned(dso);
+ }
+ goto out;
+ }
+diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
+index 72aec8f61b944..e10558b79504b 100644
+--- a/tools/perf/util/disasm.c
++++ b/tools/perf/util/disasm.c
+@@ -1199,7 +1199,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
+ int ret;
+ FILE *s;
+
+- if (dso->binary_type != DSO_BINARY_TYPE__BPF_PROG_INFO)
++ if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO)
+ return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
+
+ pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
+@@ -1226,14 +1226,14 @@ static int symbol__disassemble_bpf(struct symbol *sym,
+ info.arch = bfd_get_arch(bfdf);
+ info.mach = bfd_get_mach(bfdf);
+
+- info_node = perf_env__find_bpf_prog_info(dso->bpf_prog.env,
+- dso->bpf_prog.id);
++ info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env,
++ dso__bpf_prog(dso)->id);
+ if (!info_node) {
+ ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
+ goto out;
+ }
+ info_linear = info_node->info_linear;
+- sub_id = dso->bpf_prog.sub_id;
++ sub_id = dso__bpf_prog(dso)->sub_id;
+
+ info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
+ info.buffer_length = info_linear->info.jited_prog_len;
+@@ -1244,7 +1244,7 @@ static int symbol__disassemble_bpf(struct symbol *sym,
+ if (info_linear->info.btf_id) {
+ struct btf_node *node;
+
+- node = perf_env__find_btf(dso->bpf_prog.env,
++ node = perf_env__find_btf(dso__bpf_prog(dso)->env,
+ info_linear->info.btf_id);
+ if (node)
+ btf = btf__new((__u8 *)(node->data),
+diff --git a/tools/perf/util/dso.c b/tools/perf/util/dso.c
+index dde706b71da7b..67414944f2457 100644
+--- a/tools/perf/util/dso.c
++++ b/tools/perf/util/dso.c
+@@ -1501,7 +1501,7 @@ void dso__delete(struct dso *dso)
+ auxtrace_cache__free(RC_CHK_ACCESS(dso)->auxtrace_cache);
+ dso_cache__free(dso);
+ dso__free_a2l(dso);
+- zfree(&RC_CHK_ACCESS(dso)->symsrc_filename);
++ dso__free_symsrc_filename(dso);
+ nsinfo__zput(RC_CHK_ACCESS(dso)->nsinfo);
+ mutex_destroy(dso__lock(dso));
+ RC_CHK_FREE(dso);
+@@ -1652,3 +1652,15 @@ int dso__strerror_load(struct dso *dso, char *buf, size_t buflen)
+ scnprintf(buf, buflen, "%s", dso_load__error_str[idx]);
+ return 0;
+ }
++
++bool perf_pid_map_tid(const char *dso_name, int *tid)
++{
++ return sscanf(dso_name, "/tmp/perf-%d.map", tid) == 1;
++}
++
++bool is_perf_pid_map_name(const char *dso_name)
++{
++ int tid;
++
++ return perf_pid_map_tid(dso_name, &tid);
++}
+diff --git a/tools/perf/util/dso.h b/tools/perf/util/dso.h
+index df2c98402af3e..ed0068251c655 100644
+--- a/tools/perf/util/dso.h
++++ b/tools/perf/util/dso.h
+@@ -280,6 +280,16 @@ static inline void dso__set_annotate_warned(struct dso *dso)
+ RC_CHK_ACCESS(dso)->annotate_warned = 1;
+ }
+
++static inline bool dso__auxtrace_warned(const struct dso *dso)
++{
++ return RC_CHK_ACCESS(dso)->auxtrace_warned;
++}
++
++static inline void dso__set_auxtrace_warned(struct dso *dso)
++{
++ RC_CHK_ACCESS(dso)->auxtrace_warned = 1;
++}
++
+ static inline struct auxtrace_cache *dso__auxtrace_cache(struct dso *dso)
+ {
+ return RC_CHK_ACCESS(dso)->auxtrace_cache;
+@@ -592,6 +602,11 @@ static inline void dso__set_symsrc_filename(struct dso *dso, char *val)
+ RC_CHK_ACCESS(dso)->symsrc_filename = val;
+ }
+
++static inline void dso__free_symsrc_filename(struct dso *dso)
++{
++ zfree(&RC_CHK_ACCESS(dso)->symsrc_filename);
++}
++
+ static inline enum dso_binary_type dso__symtab_type(const struct dso *dso)
+ {
+ return RC_CHK_ACCESS(dso)->symtab_type;
+@@ -809,4 +824,8 @@ void reset_fd_limit(void);
+ u64 dso__find_global_type(struct dso *dso, u64 addr);
+ u64 dso__findnew_global_type(struct dso *dso, u64 addr, u64 offset);
+
++/* Check if dso name is of format "/tmp/perf-%d.map" */
++bool perf_pid_map_tid(const char *dso_name, int *tid);
++bool is_perf_pid_map_name(const char *dso_name);
++
+ #endif /* __PERF_DSO */
+diff --git a/tools/perf/util/maps.c b/tools/perf/util/maps.c
+index 16b39db594f4c..eaada3e0f5b4e 100644
+--- a/tools/perf/util/maps.c
++++ b/tools/perf/util/maps.c
+@@ -741,7 +741,6 @@ static unsigned int first_ending_after(struct maps *maps, const struct map *map)
+ */
+ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
+ {
+- struct map **maps_by_address;
+ int err = 0;
+ FILE *fp = debug_file();
+
+@@ -749,12 +748,12 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
+ if (!maps__maps_by_address_sorted(maps))
+ __maps__sort_by_address(maps);
+
+- maps_by_address = maps__maps_by_address(maps);
+ /*
+ * Iterate through entries where the end of the existing entry is
+ * greater-than the new map's start.
+ */
+ for (unsigned int i = first_ending_after(maps, new); i < maps__nr_maps(maps); ) {
++ struct map **maps_by_address = maps__maps_by_address(maps);
+ struct map *pos = maps_by_address[i];
+ struct map *before = NULL, *after = NULL;
+
+@@ -821,8 +820,10 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
+ /* Maps are still ordered, go to next one. */
+ i++;
+ if (after) {
+- __maps__insert(maps, after);
++ err = __maps__insert(maps, after);
+ map__put(after);
++ if (err)
++ goto out_err;
+ if (!maps__maps_by_address_sorted(maps)) {
+ /*
+ * Sorting broken so invariants don't
+@@ -851,7 +852,7 @@ static int __maps__fixup_overlap_and_insert(struct maps *maps, struct map *new)
+ check_invariants(maps);
+ }
+ /* Add the map. */
+- __maps__insert(maps, new);
++ err = __maps__insert(maps, new);
+ out_err:
+ return err;
+ }
+diff --git a/tools/perf/util/pmus.c b/tools/perf/util/pmus.c
+index b9b4c5eb50027..6907e3e7fbd16 100644
+--- a/tools/perf/util/pmus.c
++++ b/tools/perf/util/pmus.c
+@@ -477,8 +477,8 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
+ qsort(aliases, len, sizeof(struct sevent), cmp_sevent);
+ for (int j = 0; j < len; j++) {
+ /* Skip duplicates */
+- if (j > 0 && pmu_alias_is_duplicate(&aliases[j], &aliases[j - 1]))
+- continue;
++ if (j < len - 1 && pmu_alias_is_duplicate(&aliases[j], &aliases[j + 1]))
++ goto free;
+
+ print_cb->print_event(print_state,
+ aliases[j].pmu_name,
+@@ -491,6 +491,7 @@ void perf_pmus__print_pmu_events(const struct print_callbacks *print_cb, void *p
+ aliases[j].desc,
+ aliases[j].long_desc,
+ aliases[j].encoding_desc);
++free:
+ zfree(&aliases[j].name);
+ zfree(&aliases[j].alias);
+ zfree(&aliases[j].scale_unit);
+diff --git a/tools/perf/util/sort.c b/tools/perf/util/sort.c
+index cd39ea9721937..ab7c7ff35f9bb 100644
+--- a/tools/perf/util/sort.c
++++ b/tools/perf/util/sort.c
+@@ -334,7 +334,7 @@ sort__sym_cmp(struct hist_entry *left, struct hist_entry *right)
+ * comparing symbol address alone is not enough since it's a
+ * relative address within a dso.
+ */
+- if (!hists__has(left->hists, dso) || hists__has(right->hists, dso)) {
++ if (!hists__has(left->hists, dso)) {
+ ret = sort__dso_cmp(left, right);
+ if (ret != 0)
+ return ret;
+diff --git a/tools/perf/util/srcline.c b/tools/perf/util/srcline.c
+index 9d670d8c1c089..4d67c1e095a18 100644
+--- a/tools/perf/util/srcline.c
++++ b/tools/perf/util/srcline.c
+@@ -288,7 +288,7 @@ static int inline_list__append_dso_a2l(struct dso *dso,
+ struct inline_node *node,
+ struct symbol *sym)
+ {
+- struct a2l_data *a2l = dso->a2l;
++ struct a2l_data *a2l = dso__a2l(dso);
+ struct symbol *inline_sym = new_inline_sym(dso, sym, a2l->funcname);
+ char *srcline = NULL;
+
+@@ -304,11 +304,11 @@ static int addr2line(const char *dso_name, u64 addr,
+ struct symbol *sym)
+ {
+ int ret = 0;
+- struct a2l_data *a2l = dso->a2l;
++ struct a2l_data *a2l = dso__a2l(dso);
+
+ if (!a2l) {
+- dso->a2l = addr2line_init(dso_name);
+- a2l = dso->a2l;
++ a2l = addr2line_init(dso_name);
++ dso__set_a2l(dso, a2l);
+ }
+
+ if (a2l == NULL) {
+@@ -360,14 +360,14 @@ static int addr2line(const char *dso_name, u64 addr,
+
+ void dso__free_a2l(struct dso *dso)
+ {
+- struct a2l_data *a2l = dso->a2l;
++ struct a2l_data *a2l = dso__a2l(dso);
+
+ if (!a2l)
+ return;
+
+ addr2line_cleanup(a2l);
+
+- dso->a2l = NULL;
++ dso__set_a2l(dso, NULL);
+ }
+
+ #else /* HAVE_LIBBFD_SUPPORT */
+diff --git a/tools/perf/util/stat-display.c b/tools/perf/util/stat-display.c
+index 91d2f7f65df74..186305fd2d0ef 100644
+--- a/tools/perf/util/stat-display.c
++++ b/tools/perf/util/stat-display.c
+@@ -38,6 +38,7 @@
+ static int aggr_header_lens[] = {
+ [AGGR_CORE] = 18,
+ [AGGR_CACHE] = 22,
++ [AGGR_CLUSTER] = 20,
+ [AGGR_DIE] = 12,
+ [AGGR_SOCKET] = 6,
+ [AGGR_NODE] = 6,
+@@ -49,6 +50,7 @@ static int aggr_header_lens[] = {
+ static const char *aggr_header_csv[] = {
+ [AGGR_CORE] = "core,cpus,",
+ [AGGR_CACHE] = "cache,cpus,",
++ [AGGR_CLUSTER] = "cluster,cpus,",
+ [AGGR_DIE] = "die,cpus,",
+ [AGGR_SOCKET] = "socket,cpus,",
+ [AGGR_NONE] = "cpu,",
+@@ -60,6 +62,7 @@ static const char *aggr_header_csv[] = {
+ static const char *aggr_header_std[] = {
+ [AGGR_CORE] = "core",
+ [AGGR_CACHE] = "cache",
++ [AGGR_CLUSTER] = "cluster",
+ [AGGR_DIE] = "die",
+ [AGGR_SOCKET] = "socket",
+ [AGGR_NONE] = "cpu",
+diff --git a/tools/perf/util/stat-shadow.c b/tools/perf/util/stat-shadow.c
+index 3466aa9524421..6bb975e46de37 100644
+--- a/tools/perf/util/stat-shadow.c
++++ b/tools/perf/util/stat-shadow.c
+@@ -176,6 +176,13 @@ static double find_stat(const struct evsel *evsel, int aggr_idx, enum stat_type
+ if (type != evsel__stat_type(cur))
+ continue;
+
++ /*
++ * Except the SW CLOCK events,
++ * ignore if not the PMU we're looking for.
++ */
++ if ((type != STAT_NSECS) && (evsel->pmu != cur->pmu))
++ continue;
++
+ aggr = &cur->stats->aggr[aggr_idx];
+ if (type == STAT_NSECS)
+ return aggr->counts.val;
+diff --git a/tools/perf/util/symbol.c b/tools/perf/util/symbol.c
+index 9e5940b5bc591..22646f0cca7da 100644
+--- a/tools/perf/util/symbol.c
++++ b/tools/perf/util/symbol.c
+@@ -1607,7 +1607,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
+
+ if (!bfd_check_format(abfd, bfd_object)) {
+ pr_debug2("%s: cannot read %s bfd file.\n", __func__,
+- dso->long_name);
++ dso__long_name(dso));
+ goto out_close;
+ }
+
+@@ -1640,12 +1640,13 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
+ }
+ if (i < symbols_count) {
+ /* PE symbols can only have 4 bytes, so use .text high bits */
+- dso->text_offset = section->vma - (u32)section->vma;
+- dso->text_offset += (u32)bfd_asymbol_value(symbols[i]);
+- dso->text_end = (section->vma - dso->text_offset) + section->size;
++ u64 text_offset = (section->vma - (u32)section->vma)
++ + (u32)bfd_asymbol_value(symbols[i]);
++ dso__set_text_offset(dso, text_offset);
++ dso__set_text_end(dso, (section->vma - text_offset) + section->size);
+ } else {
+- dso->text_offset = section->vma - section->filepos;
+- dso->text_end = section->filepos + section->size;
++ dso__set_text_offset(dso, section->vma - section->filepos);
++ dso__set_text_end(dso, section->filepos + section->size);
+ }
+ }
+
+@@ -1671,7 +1672,7 @@ int dso__load_bfd_symbols(struct dso *dso, const char *debugfile)
+ else
+ len = section->size - sym->value;
+
+- start = bfd_asymbol_value(sym) - dso->text_offset;
++ start = bfd_asymbol_value(sym) - dso__text_offset(dso);
+ symbol = symbol__new(start, len, bfd2elf_binding(sym), STT_FUNC,
+ bfd_asymbol_name(sym));
+ if (!symbol)
+@@ -1799,7 +1800,8 @@ int dso__load(struct dso *dso, struct map *map)
+ const char *map_path = dso__long_name(dso);
+
+ mutex_lock(dso__lock(dso));
+- perfmap = strncmp(dso__name(dso), "/tmp/perf-", 10) == 0;
++ perfmap = is_perf_pid_map_name(map_path);
++
+ if (perfmap) {
+ if (dso__nsinfo(dso) &&
+ (dso__find_perf_map(newmapname, sizeof(newmapname),
+diff --git a/tools/perf/util/unwind-libdw.c b/tools/perf/util/unwind-libdw.c
+index b38d322734b4a..bde216e630d29 100644
+--- a/tools/perf/util/unwind-libdw.c
++++ b/tools/perf/util/unwind-libdw.c
+@@ -29,8 +29,8 @@ static int __find_debuginfo(Dwfl_Module *mod __maybe_unused, void **userdata,
+ const struct dso *dso = *userdata;
+
+ assert(dso);
+- if (dso->symsrc_filename && strcmp (file_name, dso->symsrc_filename))
+- *debuginfo_file_name = strdup(dso->symsrc_filename);
++ if (dso__symsrc_filename(dso) && strcmp(file_name, dso__symsrc_filename(dso)))
++ *debuginfo_file_name = strdup(dso__symsrc_filename(dso));
+ return -1;
+ }
+
+@@ -66,7 +66,7 @@ static int __report_module(struct addr_location *al, u64 ip,
+ * a different code in another DSO. So just use the map->start
+ * directly to pick the correct one.
+ */
+- if (!strncmp(dso->long_name, "/tmp/jitted-", 12))
++ if (!strncmp(dso__long_name(dso), "/tmp/jitted-", 12))
+ base = map__start(al->map);
+ else
+ base = map__start(al->map) - map__pgoff(al->map);
+@@ -83,15 +83,15 @@ static int __report_module(struct addr_location *al, u64 ip,
+ if (!mod) {
+ char filename[PATH_MAX];
+
+- __symbol__join_symfs(filename, sizeof(filename), dso->long_name);
+- mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
++ __symbol__join_symfs(filename, sizeof(filename), dso__long_name(dso));
++ mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
+ base, false);
+ }
+ if (!mod) {
+ char filename[PATH_MAX];
+
+ if (dso__build_id_filename(dso, filename, sizeof(filename), false))
+- mod = dwfl_report_elf(ui->dwfl, dso->short_name, filename, -1,
++ mod = dwfl_report_elf(ui->dwfl, dso__short_name(dso), filename, -1,
+ base, false);
+ }
+
+diff --git a/tools/perf/util/unwind-libunwind-local.c b/tools/perf/util/unwind-libunwind-local.c
+index cde267ea3e99e..7460bb96bd225 100644
+--- a/tools/perf/util/unwind-libunwind-local.c
++++ b/tools/perf/util/unwind-libunwind-local.c
+@@ -363,7 +363,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
+ struct machine *machine, u64 *offset)
+ {
+ int fd;
+- u64 ofs = dso->data.debug_frame_offset;
++ u64 ofs = dso__data(dso)->debug_frame_offset;
+
+ /* debug_frame can reside in:
+ * - dso
+@@ -379,7 +379,7 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
+ }
+
+ if (ofs <= 0) {
+- fd = open(dso->symsrc_filename, O_RDONLY);
++ fd = open(dso__symsrc_filename(dso), O_RDONLY);
+ if (fd >= 0) {
+ ofs = elf_section_offset(fd, ".debug_frame");
+ close(fd);
+@@ -402,21 +402,21 @@ static int read_unwind_spec_debug_frame(struct dso *dso,
+ }
+ }
+ if (ofs > 0) {
+- if (dso->symsrc_filename != NULL) {
++ if (dso__symsrc_filename(dso) != NULL) {
+ pr_warning(
+ "%s: overwrite symsrc(%s,%s)\n",
+ __func__,
+- dso->symsrc_filename,
++ dso__symsrc_filename(dso),
+ debuglink);
+- zfree(&dso->symsrc_filename);
++ dso__free_symsrc_filename(dso);
+ }
+- dso->symsrc_filename = debuglink;
++ dso__set_symsrc_filename(dso, debuglink);
+ } else {
+ free(debuglink);
+ }
+ }
+
+- dso->data.debug_frame_offset = ofs;
++ dso__data(dso)->debug_frame_offset = ofs;
+ }
+
+ *offset = ofs;
+@@ -481,7 +481,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+ if (ret < 0 &&
+ !read_unwind_spec_debug_frame(dso, ui->machine, &segbase)) {
+ int fd = dso__data_get_fd(dso, ui->machine);
+- int is_exec = elf_is_exec(fd, dso->name);
++ int is_exec = elf_is_exec(fd, dso__name(dso));
+ u64 start = map__start(map);
+ unw_word_t base = is_exec ? 0 : start;
+ const char *symfile;
+@@ -489,7 +489,7 @@ find_proc_info(unw_addr_space_t as, unw_word_t ip, unw_proc_info_t *pi,
+ if (fd >= 0)
+ dso__data_put_fd(dso);
+
+- symfile = dso->symsrc_filename ?: dso->name;
++ symfile = dso__symsrc_filename(dso) ?: dso__name(dso);
+
+ memset(&di, 0, sizeof(di));
+ if (dwarf_find_debug_frame(0, &di, ip, base, symfile, start, map__end(map)))
+diff --git a/tools/testing/selftests/bpf/bpf_kfuncs.h b/tools/testing/selftests/bpf/bpf_kfuncs.h
+index be91a69193158..3b6675ab40861 100644
+--- a/tools/testing/selftests/bpf/bpf_kfuncs.h
++++ b/tools/testing/selftests/bpf/bpf_kfuncs.h
+@@ -77,5 +77,5 @@ extern int bpf_verify_pkcs7_signature(struct bpf_dynptr *data_ptr,
+ struct bpf_key *trusted_keyring) __ksym;
+
+ extern bool bpf_session_is_return(void) __ksym __weak;
+-extern long *bpf_session_cookie(void) __ksym __weak;
++extern __u64 *bpf_session_cookie(void) __ksym __weak;
+ #endif
+diff --git a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+index 0aca025327948..3f0daf660703f 100644
+--- a/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
++++ b/tools/testing/selftests/bpf/prog_tests/bpf_tcp_ca.c
+@@ -307,7 +307,8 @@ static void test_update_ca(void)
+ return;
+
+ link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+- ASSERT_OK_PTR(link, "attach_struct_ops");
++ if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
++ goto out;
+
+ do_test("tcp_ca_update", NULL);
+ saved_ca1_cnt = skel->bss->ca1_cnt;
+@@ -321,6 +322,7 @@ static void test_update_ca(void)
+ ASSERT_GT(skel->bss->ca2_cnt, 0, "ca2_ca2_cnt");
+
+ bpf_link__destroy(link);
++out:
+ tcp_ca_update__destroy(skel);
+ }
+
+@@ -336,7 +338,8 @@ static void test_update_wrong(void)
+ return;
+
+ link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+- ASSERT_OK_PTR(link, "attach_struct_ops");
++ if (!ASSERT_OK_PTR(link, "attach_struct_ops"))
++ goto out;
+
+ do_test("tcp_ca_update", NULL);
+ saved_ca1_cnt = skel->bss->ca1_cnt;
+@@ -349,6 +352,7 @@ static void test_update_wrong(void)
+ ASSERT_GT(skel->bss->ca1_cnt, saved_ca1_cnt, "ca2_ca1_cnt");
+
+ bpf_link__destroy(link);
++out:
+ tcp_ca_update__destroy(skel);
+ }
+
+@@ -363,7 +367,8 @@ static void test_mixed_links(void)
+ return;
+
+ link_nl = bpf_map__attach_struct_ops(skel->maps.ca_no_link);
+- ASSERT_OK_PTR(link_nl, "attach_struct_ops_nl");
++ if (!ASSERT_OK_PTR(link_nl, "attach_struct_ops_nl"))
++ goto out;
+
+ link = bpf_map__attach_struct_ops(skel->maps.ca_update_1);
+ ASSERT_OK_PTR(link, "attach_struct_ops");
+@@ -376,6 +381,7 @@ static void test_mixed_links(void)
+
+ bpf_link__destroy(link);
+ bpf_link__destroy(link_nl);
++out:
+ tcp_ca_update__destroy(skel);
+ }
+
+@@ -418,7 +424,8 @@ static void test_link_replace(void)
+ bpf_link__destroy(link);
+
+ link = bpf_map__attach_struct_ops(skel->maps.ca_update_2);
+- ASSERT_OK_PTR(link, "attach_struct_ops_2nd");
++ if (!ASSERT_OK_PTR(link, "attach_struct_ops_2nd"))
++ goto out;
+
+ /* BPF_F_REPLACE with a wrong old map Fd. It should fail!
+ *
+@@ -441,6 +448,7 @@ static void test_link_replace(void)
+
+ bpf_link__destroy(link);
+
++out:
+ tcp_ca_update__destroy(skel);
+ }
+
+diff --git a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+index f949647dbbc21..552a0875ca6db 100644
+--- a/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
++++ b/tools/testing/selftests/bpf/prog_tests/fexit_sleep.c
+@@ -21,13 +21,13 @@ static int do_sleep(void *skel)
+ }
+
+ #define STACK_SIZE (1024 * 1024)
+-static char child_stack[STACK_SIZE];
+
+ void test_fexit_sleep(void)
+ {
+ struct fexit_sleep_lskel *fexit_skel = NULL;
+ int wstatus, duration = 0;
+ pid_t cpid;
++ char *child_stack = NULL;
+ int err, fexit_cnt;
+
+ fexit_skel = fexit_sleep_lskel__open_and_load();
+@@ -38,6 +38,11 @@ void test_fexit_sleep(void)
+ if (CHECK(err, "fexit_attach", "fexit attach failed: %d\n", err))
+ goto cleanup;
+
++ child_stack = mmap(NULL, STACK_SIZE, PROT_READ | PROT_WRITE, MAP_PRIVATE |
++ MAP_ANONYMOUS | MAP_STACK, -1, 0);
++ if (!ASSERT_NEQ(child_stack, MAP_FAILED, "mmap"))
++ goto cleanup;
++
+ cpid = clone(do_sleep, child_stack + STACK_SIZE, CLONE_FILES | SIGCHLD, fexit_skel);
+ if (CHECK(cpid == -1, "clone", "%s\n", strerror(errno)))
+ goto cleanup;
+@@ -78,5 +83,6 @@ void test_fexit_sleep(void)
+ goto cleanup;
+
+ cleanup:
++ munmap(child_stack, STACK_SIZE);
+ fexit_sleep_lskel__destroy(fexit_skel);
+ }
+diff --git a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+index 597d0467a9267..de2466547efe0 100644
+--- a/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
++++ b/tools/testing/selftests/bpf/prog_tests/sk_lookup.c
+@@ -994,7 +994,7 @@ static void drop_on_reuseport(const struct test *t)
+
+ err = update_lookup_map(t->sock_map, SERVER_A, server1);
+ if (err)
+- goto detach;
++ goto close_srv1;
+
+ /* second server on destination address we should never reach */
+ server2 = make_server(t->sotype, t->connect_to.ip, t->connect_to.port,
+diff --git a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+index f09505f8b0386..53d6ad8c2257e 100644
+--- a/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
++++ b/tools/testing/selftests/bpf/prog_tests/xdp_adjust_tail.c
+@@ -222,7 +222,7 @@ static void test_xdp_adjust_frags_tail_grow(void)
+
+ prog = bpf_object__next_program(obj, NULL);
+ if (bpf_object__load(obj))
+- return;
++ goto out;
+
+ prog_fd = bpf_program__fd(prog);
+
+diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
+index ba97165bdb282..a657651eba523 100644
+--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
++++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_multidim.c
+@@ -14,9 +14,9 @@ typedef int *ptr_arr_t[6];
+
+ typedef int *ptr_multiarr_t[7][8][9][10];
+
+-typedef int * (*fn_ptr_arr_t[11])();
++typedef int * (*fn_ptr_arr_t[11])(void);
+
+-typedef int * (*fn_ptr_multiarr_t[12][13])();
++typedef int * (*fn_ptr_multiarr_t[12][13])(void);
+
+ struct root_struct {
+ arr_t _1;
+diff --git a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+index ad21ee8c7e234..29d01fff32bd2 100644
+--- a/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
++++ b/tools/testing/selftests/bpf/progs/btf_dump_test_case_syntax.c
+@@ -100,7 +100,7 @@ typedef void (*printf_fn_t)(const char *, ...);
+ * `int -> char *` function and returns pointer to a char. Equivalent:
+ * typedef char * (*fn_input_t)(int);
+ * typedef char * (*fn_output_outer_t)(fn_input_t);
+- * typedef const fn_output_outer_t (* fn_output_inner_t)();
++ * typedef const fn_output_outer_t (* fn_output_inner_t)(void);
+ * typedef const fn_output_inner_t fn_ptr_arr2_t[5];
+ */
+ /* ----- START-EXPECTED-OUTPUT ----- */
+@@ -127,7 +127,7 @@ typedef void (* (*signal_t)(int, void (*)(int)))(int);
+
+ typedef char * (*fn_ptr_arr1_t[10])(int **);
+
+-typedef char * (* (* const fn_ptr_arr2_t[5])())(char * (*)(int));
++typedef char * (* (* const fn_ptr_arr2_t[5])(void))(char * (*)(int));
+
+ struct struct_w_typedefs {
+ int_t a;
+diff --git a/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
+index d49070803e221..0835b5edf6858 100644
+--- a/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
++++ b/tools/testing/selftests/bpf/progs/kprobe_multi_session_cookie.c
+@@ -25,7 +25,7 @@ int BPF_PROG(trigger)
+
+ static int check_cookie(__u64 val, __u64 *result)
+ {
+- long *cookie;
++ __u64 *cookie;
+
+ if (bpf_get_current_pid_tgid() >> 32 != pid)
+ return 1;
+diff --git a/tools/testing/selftests/bpf/test_sockmap.c b/tools/testing/selftests/bpf/test_sockmap.c
+index 92752f5eededf..a709911cddd2f 100644
+--- a/tools/testing/selftests/bpf/test_sockmap.c
++++ b/tools/testing/selftests/bpf/test_sockmap.c
+@@ -63,7 +63,7 @@ int passed;
+ int failed;
+ int map_fd[9];
+ struct bpf_map *maps[9];
+-int prog_fd[11];
++int prog_fd[9];
+
+ int txmsg_pass;
+ int txmsg_redir;
+@@ -680,7 +680,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt,
+ }
+ }
+
+- s->bytes_recvd += recv;
++ if (recv > 0)
++ s->bytes_recvd += recv;
+
+ if (opt->check_recved_len && s->bytes_recvd > total_bytes) {
+ errno = EMSGSIZE;
+@@ -1793,8 +1794,6 @@ int prog_attach_type[] = {
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+ BPF_SK_MSG_VERDICT,
+- BPF_SK_MSG_VERDICT,
+- BPF_SK_MSG_VERDICT,
+ };
+
+ int prog_type[] = {
+@@ -1807,8 +1806,6 @@ int prog_type[] = {
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+ BPF_PROG_TYPE_SK_MSG,
+- BPF_PROG_TYPE_SK_MSG,
+- BPF_PROG_TYPE_SK_MSG,
+ };
+
+ static int populate_progs(char *bpf_file)
+diff --git a/tools/testing/selftests/damon/access_memory.c b/tools/testing/selftests/damon/access_memory.c
+index 585a2fa543295..56b17e8fe1be8 100644
+--- a/tools/testing/selftests/damon/access_memory.c
++++ b/tools/testing/selftests/damon/access_memory.c
+@@ -35,7 +35,7 @@ int main(int argc, char *argv[])
+ start_clock = clock();
+ while ((clock() - start_clock) * 1000 / CLOCKS_PER_SEC <
+ access_time_ms)
+- memset(regions[i], i, 1024 * 1024 * 10);
++ memset(regions[i], i, sz_region);
+ }
+ return 0;
+ }
+diff --git a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+index 31252bc8775e0..4994bea5daf80 100755
+--- a/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
++++ b/tools/testing/selftests/drivers/net/mlxsw/spectrum-2/tc_flower.sh
+@@ -11,7 +11,7 @@ ALL_TESTS="single_mask_test identical_filters_test two_masks_test \
+ multiple_masks_test ctcam_edge_cases_test delta_simple_test \
+ delta_two_masks_one_key_test delta_simple_rehash_test \
+ bloom_simple_test bloom_complex_test bloom_delta_test \
+- max_erp_entries_test max_group_size_test"
++ max_erp_entries_test max_group_size_test collision_test"
+ NUM_NETIFS=2
+ source $lib_dir/lib.sh
+ source $lib_dir/tc_common.sh
+@@ -457,7 +457,7 @@ delta_two_masks_one_key_test()
+ {
+ # If 2 keys are the same and only differ in mask in a way that
+ # they belong under the same ERP (second is delta of the first),
+- # there should be no C-TCAM spill.
++ # there should be C-TCAM spill.
+
+ RET=0
+
+@@ -474,8 +474,8 @@ delta_two_masks_one_key_test()
+ tp_record "mlxsw:*" "tc filter add dev $h2 ingress protocol ip \
+ pref 2 handle 102 flower $tcflags dst_ip 192.0.2.2 \
+ action drop"
+- tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 0
+- check_err $? "incorrect C-TCAM spill while inserting the second rule"
++ tp_check_hits "mlxsw:mlxsw_sp_acl_atcam_entry_add_ctcam_spill" 1
++ check_err $? "C-TCAM spill did not happen while inserting the second rule"
+
+ $MZ $h1 -c 1 -p 64 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \
+ -t ip -q
+@@ -1087,6 +1087,53 @@ max_group_size_test()
+ log_test "max ACL group size test ($tcflags). max size $max_size"
+ }
+
++collision_test()
++{
++ # Filters cannot share an eRP if in the common unmasked part (i.e.,
++ # without the delta bits) they have the same values. If the driver does
++ # not prevent such configuration (by spilling into the C-TCAM), then
++ # multiple entries will be present in the device with the same key,
++ # leading to collisions and a reduced scale.
++ #
++ # Create such a scenario and make sure all the filters are successfully
++ # added.
++
++ RET=0
++
++ local ret
++
++ if [[ "$tcflags" != "skip_sw" ]]; then
++ return 0;
++ fi
++
++ # Add a single dst_ip/24 filter and multiple dst_ip/32 filters that all
++ # have the same values in the common unmasked part (dst_ip/24).
++
++ tc filter add dev $h2 ingress pref 1 proto ipv4 handle 101 \
++ flower $tcflags dst_ip 198.51.100.0/24 \
++ action drop
++
++ for i in {0..255}; do
++ tc filter add dev $h2 ingress pref 2 proto ipv4 \
++ handle $((102 + i)) \
++ flower $tcflags dst_ip 198.51.100.${i}/32 \
++ action drop
++ ret=$?
++ [[ $ret -ne 0 ]] && break
++ done
++
++ check_err $ret "failed to add all the filters"
++
++ for i in {255..0}; do
++ tc filter del dev $h2 ingress pref 2 proto ipv4 \
++ handle $((102 + i)) flower
++ done
++
++ tc filter del dev $h2 ingress pref 1 proto ipv4 handle 101 flower
++
++ log_test "collision test ($tcflags)"
++}
++
+ setup_prepare()
+ {
+ h1=${NETIFS[p1]}
+diff --git a/tools/testing/selftests/iommu/iommufd.c b/tools/testing/selftests/iommu/iommufd.c
+index edf1c99c9936c..5f7d5a5ba89b0 100644
+--- a/tools/testing/selftests/iommu/iommufd.c
++++ b/tools/testing/selftests/iommu/iommufd.c
+@@ -1722,10 +1722,17 @@ FIXTURE_VARIANT(iommufd_dirty_tracking)
+
+ FIXTURE_SETUP(iommufd_dirty_tracking)
+ {
++ unsigned long size;
+ int mmap_flags;
+ void *vrc;
+ int rc;
+
++ if (variant->buffer_size < MOCK_PAGE_SIZE) {
++ SKIP(return,
++ "Skipping buffer_size=%lu, less than MOCK_PAGE_SIZE=%lu",
++ variant->buffer_size, MOCK_PAGE_SIZE);
++ }
++
+ self->fd = open("/dev/iommu", O_RDWR);
+ ASSERT_NE(-1, self->fd);
+
+@@ -1749,12 +1756,11 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
+ assert(vrc == self->buffer);
+
+ self->page_size = MOCK_PAGE_SIZE;
+- self->bitmap_size =
+- variant->buffer_size / self->page_size / BITS_PER_BYTE;
++ self->bitmap_size = variant->buffer_size / self->page_size;
+
+ /* Provision with an extra (PAGE_SIZE) for the unaligned case */
+- rc = posix_memalign(&self->bitmap, PAGE_SIZE,
+- self->bitmap_size + PAGE_SIZE);
++ size = DIV_ROUND_UP(self->bitmap_size, BITS_PER_BYTE);
++ rc = posix_memalign(&self->bitmap, PAGE_SIZE, size + PAGE_SIZE);
+ assert(!rc);
+ assert(self->bitmap);
+ assert((uintptr_t)self->bitmap % PAGE_SIZE == 0);
+@@ -1775,51 +1781,63 @@ FIXTURE_SETUP(iommufd_dirty_tracking)
+ FIXTURE_TEARDOWN(iommufd_dirty_tracking)
+ {
+ munmap(self->buffer, variant->buffer_size);
+- munmap(self->bitmap, self->bitmap_size);
++ munmap(self->bitmap, DIV_ROUND_UP(self->bitmap_size, BITS_PER_BYTE));
+ teardown_iommufd(self->fd, _metadata);
+ }
+
+-FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128k)
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty8k)
++{
++ /* half of an u8 index bitmap */
++ .buffer_size = 8UL * 1024UL,
++};
++
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty16k)
++{
++ /* one u8 index bitmap */
++ .buffer_size = 16UL * 1024UL,
++};
++
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty64k)
+ {
+ /* one u32 index bitmap */
+- .buffer_size = 128UL * 1024UL,
++ .buffer_size = 64UL * 1024UL,
+ };
+
+-FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256k)
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128k)
+ {
+ /* one u64 index bitmap */
+- .buffer_size = 256UL * 1024UL,
++ .buffer_size = 128UL * 1024UL,
+ };
+
+-FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty640k)
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty320k)
+ {
+ /* two u64 index and trailing end bitmap */
+- .buffer_size = 640UL * 1024UL,
++ .buffer_size = 320UL * 1024UL,
+ };
+
+-FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M)
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty64M)
+ {
+- /* 4K bitmap (128M IOVA range) */
+- .buffer_size = 128UL * 1024UL * 1024UL,
++ /* 4K bitmap (64M IOVA range) */
++ .buffer_size = 64UL * 1024UL * 1024UL,
+ };
+
+-FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M_huge)
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty64M_huge)
+ {
+- /* 4K bitmap (128M IOVA range) */
+- .buffer_size = 128UL * 1024UL * 1024UL,
++ /* 4K bitmap (64M IOVA range) */
++ .buffer_size = 64UL * 1024UL * 1024UL,
+ .hugepages = true,
+ };
+
+-FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M)
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M)
+ {
+- /* 8K bitmap (256M IOVA range) */
+- .buffer_size = 256UL * 1024UL * 1024UL,
++ /* 8K bitmap (128M IOVA range) */
++ .buffer_size = 128UL * 1024UL * 1024UL,
+ };
+
+-FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty256M_huge)
++FIXTURE_VARIANT_ADD(iommufd_dirty_tracking, domain_dirty128M_huge)
+ {
+- /* 8K bitmap (256M IOVA range) */
+- .buffer_size = 256UL * 1024UL * 1024UL,
++ /* 8K bitmap (128M IOVA range) */
++ .buffer_size = 128UL * 1024UL * 1024UL,
+ .hugepages = true,
+ };
+
+diff --git a/tools/testing/selftests/iommu/iommufd_utils.h b/tools/testing/selftests/iommu/iommufd_utils.h
+index 8d2b46b2114da..c612fbf0195ba 100644
+--- a/tools/testing/selftests/iommu/iommufd_utils.h
++++ b/tools/testing/selftests/iommu/iommufd_utils.h
+@@ -22,6 +22,8 @@
+ #define BIT_MASK(nr) (1UL << ((nr) % __BITS_PER_LONG))
+ #define BIT_WORD(nr) ((nr) / __BITS_PER_LONG)
+
++#define DIV_ROUND_UP(n, d) (((n) + (d) - 1) / (d))
++
+ static inline void set_bit(unsigned int nr, unsigned long *addr)
+ {
+ unsigned long mask = BIT_MASK(nr);
+@@ -346,12 +348,12 @@ static int _test_cmd_mock_domain_set_dirty(int fd, __u32 hwpt_id, size_t length,
+ static int _test_mock_dirty_bitmaps(int fd, __u32 hwpt_id, size_t length,
+ __u64 iova, size_t page_size,
+ size_t pte_page_size, __u64 *bitmap,
+- __u64 bitmap_size, __u32 flags,
++ __u64 nbits, __u32 flags,
+ struct __test_metadata *_metadata)
+ {
+ unsigned long npte = pte_page_size / page_size, pteset = 2 * npte;
+- unsigned long nbits = bitmap_size * BITS_PER_BYTE;
+ unsigned long j, i, nr = nbits / pteset ?: 1;
++ unsigned long bitmap_size = DIV_ROUND_UP(nbits, BITS_PER_BYTE);
+ __u64 out_dirty = 0;
+
+ /* Mark all even bits as dirty in the mock domain */
+diff --git a/tools/testing/selftests/landlock/base_test.c b/tools/testing/selftests/landlock/base_test.c
+index 3c1e9f35b5312..3b26bf3cf5b9a 100644
+--- a/tools/testing/selftests/landlock/base_test.c
++++ b/tools/testing/selftests/landlock/base_test.c
+@@ -9,6 +9,7 @@
+ #define _GNU_SOURCE
+ #include <errno.h>
+ #include <fcntl.h>
++#include <linux/keyctl.h>
+ #include <linux/landlock.h>
+ #include <string.h>
+ #include <sys/prctl.h>
+@@ -326,4 +327,77 @@ TEST(ruleset_fd_transfer)
+ ASSERT_EQ(EXIT_SUCCESS, WEXITSTATUS(status));
+ }
+
++TEST(cred_transfer)
++{
++ struct landlock_ruleset_attr ruleset_attr = {
++ .handled_access_fs = LANDLOCK_ACCESS_FS_READ_DIR,
++ };
++ int ruleset_fd, dir_fd;
++ pid_t child;
++ int status;
++
++ drop_caps(_metadata);
++
++ dir_fd = open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC);
++ EXPECT_LE(0, dir_fd);
++ EXPECT_EQ(0, close(dir_fd));
++
++ /* Denies opening directories. */
++ ruleset_fd =
++ landlock_create_ruleset(&ruleset_attr, sizeof(ruleset_attr), 0);
++ ASSERT_LE(0, ruleset_fd);
++ EXPECT_EQ(0, prctl(PR_SET_NO_NEW_PRIVS, 1, 0, 0, 0));
++ ASSERT_EQ(0, landlock_restrict_self(ruleset_fd, 0));
++ EXPECT_EQ(0, close(ruleset_fd));
++
++ /* Checks ruleset enforcement. */
++ EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
++ EXPECT_EQ(EACCES, errno);
++
++ /* Needed for KEYCTL_SESSION_TO_PARENT permission checks */
++ EXPECT_NE(-1, syscall(__NR_keyctl, KEYCTL_JOIN_SESSION_KEYRING, NULL, 0,
++ 0, 0))
++ {
++ TH_LOG("Failed to join session keyring: %s", strerror(errno));
++ }
++
++ child = fork();
++ ASSERT_LE(0, child);
++ if (child == 0) {
++ /* Checks ruleset enforcement. */
++ EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
++ EXPECT_EQ(EACCES, errno);
++
++ /*
++ * KEYCTL_SESSION_TO_PARENT is a no-op unless we have a
++ * different session keyring in the child, so make that happen.
++ */
++ EXPECT_NE(-1, syscall(__NR_keyctl, KEYCTL_JOIN_SESSION_KEYRING,
++ NULL, 0, 0, 0));
++
++ /*
++ * KEYCTL_SESSION_TO_PARENT installs credentials on the parent
++ * that never go through the cred_prepare hook, this path uses
++ * cred_transfer instead.
++ */
++ EXPECT_EQ(0, syscall(__NR_keyctl, KEYCTL_SESSION_TO_PARENT, 0,
++ 0, 0, 0));
++
++ /* Re-checks ruleset enforcement. */
++ EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
++ EXPECT_EQ(EACCES, errno);
++
++ _exit(_metadata->exit_code);
++ return;
++ }
++
++ EXPECT_EQ(child, waitpid(child, &status, 0));
++ EXPECT_EQ(1, WIFEXITED(status));
++ EXPECT_EQ(EXIT_SUCCESS, WEXITSTATUS(status));
++
++ /* Re-checks ruleset enforcement. */
++ EXPECT_EQ(-1, open("/", O_RDONLY | O_DIRECTORY | O_CLOEXEC));
++ EXPECT_EQ(EACCES, errno);
++}
++
+ TEST_HARNESS_MAIN
+diff --git a/tools/testing/selftests/landlock/config b/tools/testing/selftests/landlock/config
+index 0086efaa7b681..29af19c4e9f98 100644
+--- a/tools/testing/selftests/landlock/config
++++ b/tools/testing/selftests/landlock/config
+@@ -2,6 +2,7 @@ CONFIG_CGROUPS=y
+ CONFIG_CGROUP_SCHED=y
+ CONFIG_INET=y
+ CONFIG_IPV6=y
++CONFIG_KEYS=y
+ CONFIG_NET=y
+ CONFIG_NET_NS=y
+ CONFIG_OVERLAY_FS=y
+diff --git a/tools/testing/selftests/net/fib_tests.sh b/tools/testing/selftests/net/fib_tests.sh
+index 73895711cdf42..5f3c28fc86249 100755
+--- a/tools/testing/selftests/net/fib_tests.sh
++++ b/tools/testing/selftests/net/fib_tests.sh
+@@ -1737,53 +1737,53 @@ ipv4_rt_dsfield()
+
+ # DSCP 0x10 should match the specific route, no matter the ECN bits
+ $IP route get fibmatch 172.16.102.1 dsfield 0x10 | \
+- grep -q "via 172.16.103.2"
++ grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
+ log_test $? 0 "IPv4 route with DSCP and ECN:Not-ECT"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x11 | \
+- grep -q "via 172.16.103.2"
++ grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
+ log_test $? 0 "IPv4 route with DSCP and ECN:ECT(1)"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x12 | \
+- grep -q "via 172.16.103.2"
++ grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
+ log_test $? 0 "IPv4 route with DSCP and ECN:ECT(0)"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x13 | \
+- grep -q "via 172.16.103.2"
++ grep -q "172.16.102.0/24 tos 0x10 via 172.16.103.2"
+ log_test $? 0 "IPv4 route with DSCP and ECN:CE"
+
+ # Unknown DSCP should match the generic route, no matter the ECN bits
+ $IP route get fibmatch 172.16.102.1 dsfield 0x14 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with unknown DSCP and ECN:Not-ECT"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x15 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(1)"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x16 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with unknown DSCP and ECN:ECT(0)"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x17 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with unknown DSCP and ECN:CE"
+
+ # Null DSCP should match the generic route, no matter the ECN bits
+ $IP route get fibmatch 172.16.102.1 dsfield 0x00 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with no DSCP and ECN:Not-ECT"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x01 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(1)"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x02 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with no DSCP and ECN:ECT(0)"
+
+ $IP route get fibmatch 172.16.102.1 dsfield 0x03 | \
+- grep -q "via 172.16.101.2"
++ grep -q "172.16.102.0/24 via 172.16.101.2"
+ log_test $? 0 "IPv4 route with no DSCP and ECN:CE"
+ }
+
+diff --git a/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh b/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
+index 0760a34b71146..a21b7085da2e9 100755
+--- a/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
++++ b/tools/testing/selftests/net/forwarding/bridge_fdb_learning_limit.sh
+@@ -178,6 +178,22 @@ fdb_del()
+ check_err $? "Failed to remove a FDB entry of type ${type}"
+ }
+
++check_fdb_n_learned_support()
++{
++ if ! ip link help bridge 2>&1 | grep -q "fdb_max_learned"; then
++ echo "SKIP: iproute2 too old, missing bridge max learned support"
++ exit $ksft_skip
++ fi
++
++ ip link add dev br0 type bridge
++ local learned=$(fdb_get_n_learned)
++ ip link del dev br0
++ if [ "$learned" == "null" ]; then
++ echo "SKIP: kernel too old; bridge fdb_n_learned feature not supported."
++ exit $ksft_skip
++ fi
++}
++
+ check_accounting_one_type()
+ {
+ local type=$1 is_counted=$2 overrides_learned=$3
+@@ -274,6 +290,8 @@ check_limit()
+ done
+ }
+
++check_fdb_n_learned_support
++
+ trap cleanup EXIT
+
+ setup_prepare
+diff --git a/tools/testing/selftests/net/forwarding/devlink_lib.sh b/tools/testing/selftests/net/forwarding/devlink_lib.sh
+index f1de525cfa55b..62a05bca1e825 100644
+--- a/tools/testing/selftests/net/forwarding/devlink_lib.sh
++++ b/tools/testing/selftests/net/forwarding/devlink_lib.sh
+@@ -122,6 +122,8 @@ devlink_reload()
+ still_pending=$(devlink resource show "$DEVLINK_DEV" | \
+ grep -c "size_new")
+ check_err $still_pending "Failed reload - There are still unset sizes"
++
++ udevadm settle
+ }
+
+ declare -A DEVLINK_ORIG
+diff --git a/tools/testing/selftests/nolibc/nolibc-test.c b/tools/testing/selftests/nolibc/nolibc-test.c
+index 94bb6e11c16f0..994477ee87bef 100644
+--- a/tools/testing/selftests/nolibc/nolibc-test.c
++++ b/tools/testing/selftests/nolibc/nolibc-test.c
+@@ -607,7 +607,7 @@ int expect_strne(const char *expr, int llen, const char *cmp)
+ static __attribute__((unused))
+ int expect_str_buf_eq(size_t expr, const char *buf, size_t val, int llen, const char *cmp)
+ {
+- llen += printf(" = %lu <%s> ", expr, buf);
++ llen += printf(" = %lu <%s> ", (unsigned long)expr, buf);
+ if (strcmp(buf, cmp) != 0) {
+ result(llen, FAIL);
+ return 1;
+diff --git a/tools/testing/selftests/resctrl/resctrl_val.c b/tools/testing/selftests/resctrl/resctrl_val.c
+index 445f306d4c2fa..f55f5989de72b 100644
+--- a/tools/testing/selftests/resctrl/resctrl_val.c
++++ b/tools/testing/selftests/resctrl/resctrl_val.c
+@@ -293,6 +293,18 @@ static int initialize_mem_bw_imc(void)
+ return 0;
+ }
+
++static void perf_close_imc_mem_bw(void)
++{
++ int mc;
++
++ for (mc = 0; mc < imcs; mc++) {
++ if (imc_counters_config[mc][READ].fd != -1)
++ close(imc_counters_config[mc][READ].fd);
++ if (imc_counters_config[mc][WRITE].fd != -1)
++ close(imc_counters_config[mc][WRITE].fd);
++ }
++}
++
+ /*
+ * get_mem_bw_imc: Memory band width as reported by iMC counters
+ * @cpu_no: CPU number that the benchmark PID is binded to
+@@ -306,26 +318,33 @@ static int initialize_mem_bw_imc(void)
+ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
+ {
+ float reads, writes, of_mul_read, of_mul_write;
+- int imc, j, ret;
++ int imc, ret;
++
++ for (imc = 0; imc < imcs; imc++) {
++ imc_counters_config[imc][READ].fd = -1;
++ imc_counters_config[imc][WRITE].fd = -1;
++ }
+
+ /* Start all iMC counters to log values (both read and write) */
+ reads = 0, writes = 0, of_mul_read = 1, of_mul_write = 1;
+ for (imc = 0; imc < imcs; imc++) {
+- for (j = 0; j < 2; j++) {
+- ret = open_perf_event(imc, cpu_no, j);
+- if (ret)
+- return -1;
+- }
+- for (j = 0; j < 2; j++)
+- membw_ioctl_perf_event_ioc_reset_enable(imc, j);
++ ret = open_perf_event(imc, cpu_no, READ);
++ if (ret)
++ goto close_fds;
++ ret = open_perf_event(imc, cpu_no, WRITE);
++ if (ret)
++ goto close_fds;
++
++ membw_ioctl_perf_event_ioc_reset_enable(imc, READ);
++ membw_ioctl_perf_event_ioc_reset_enable(imc, WRITE);
+ }
+
+ sleep(1);
+
+ /* Stop counters after a second to get results (both read and write) */
+ for (imc = 0; imc < imcs; imc++) {
+- for (j = 0; j < 2; j++)
+- membw_ioctl_perf_event_ioc_disable(imc, j);
++ membw_ioctl_perf_event_ioc_disable(imc, READ);
++ membw_ioctl_perf_event_ioc_disable(imc, WRITE);
+ }
+
+ /*
+@@ -341,15 +360,13 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
+ if (read(r->fd, &r->return_value,
+ sizeof(struct membw_read_format)) == -1) {
+ ksft_perror("Couldn't get read b/w through iMC");
+-
+- return -1;
++ goto close_fds;
+ }
+
+ if (read(w->fd, &w->return_value,
+ sizeof(struct membw_read_format)) == -1) {
+ ksft_perror("Couldn't get write bw through iMC");
+-
+- return -1;
++ goto close_fds;
+ }
+
+ __u64 r_time_enabled = r->return_value.time_enabled;
+@@ -369,10 +386,7 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
+ writes += w->return_value.value * of_mul_write * SCALE;
+ }
+
+- for (imc = 0; imc < imcs; imc++) {
+- close(imc_counters_config[imc][READ].fd);
+- close(imc_counters_config[imc][WRITE].fd);
+- }
++ perf_close_imc_mem_bw();
+
+ if (strcmp(bw_report, "reads") == 0) {
+ *bw_imc = reads;
+@@ -386,6 +400,10 @@ static int get_mem_bw_imc(int cpu_no, char *bw_report, float *bw_imc)
+
+ *bw_imc = reads + writes;
+ return 0;
++
++close_fds:
++ perf_close_imc_mem_bw();
++ return -1;
+ }
+
+ void set_mbm_path(const char *ctrlgrp, const char *mongrp, int domain_id)
+diff --git a/tools/testing/selftests/sigaltstack/current_stack_pointer.h b/tools/testing/selftests/sigaltstack/current_stack_pointer.h
+index ea9bdf3a90b16..09da8f1011ce4 100644
+--- a/tools/testing/selftests/sigaltstack/current_stack_pointer.h
++++ b/tools/testing/selftests/sigaltstack/current_stack_pointer.h
+@@ -8,7 +8,7 @@ register unsigned long sp asm("sp");
+ register unsigned long sp asm("esp");
+ #elif __loongarch64
+ register unsigned long sp asm("$sp");
+-#elif __ppc__
++#elif __powerpc__
+ register unsigned long sp asm("r1");
+ #elif __s390x__
+ register unsigned long sp asm("%15");
diff --git a/2950_jump-label-fix.patch b/2950_jump-label-fix.patch
new file mode 100644
index 00000000..1a5fdf7a
--- /dev/null
+++ b/2950_jump-label-fix.patch
@@ -0,0 +1,57 @@
+From 224fa3552029a3d14bec7acf72ded8171d551b88 Mon Sep 17 00:00:00 2001
+From: Peter Zijlstra <peterz@infradead.org>
+Date: Wed, 31 Jul 2024 12:43:21 +0200
+Subject: jump_label: Fix the fix, brown paper bags galore
+
+Per the example of:
+
+ !atomic_cmpxchg(&key->enabled, 0, 1)
+
+the inverse was written as:
+
+ atomic_cmpxchg(&key->enabled, 1, 0)
+
+except of course, that while !old is only true for old == 0, old is
+true for everything except old == 0.
+
+Fix it to read:
+
+ atomic_cmpxchg(&key->enabled, 1, 0) == 1
+
+such that only the 1->0 transition returns true and goes on to disable
+the keys.
+
+Fixes: 83ab38ef0a0b ("jump_label: Fix concurrency issues in static_key_slow_dec()")
+Reported-by: Darrick J. Wong <djwong@kernel.org>
+Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
+Tested-by: Darrick J. Wong <djwong@kernel.org>
+Link: https://lkml.kernel.org/r/20240731105557.GY33588@noisy.programming.kicks-ass.net
+---
+ kernel/jump_label.c | 4 ++--
+ 1 file changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/kernel/jump_label.c b/kernel/jump_label.c
+index 4ad5ed8adf9691..6dc76b590703ed 100644
+--- a/kernel/jump_label.c
++++ b/kernel/jump_label.c
+@@ -236,7 +236,7 @@ void static_key_disable_cpuslocked(struct static_key *key)
+ }
+
+ jump_label_lock();
+- if (atomic_cmpxchg(&key->enabled, 1, 0))
++ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
+ jump_label_update(key);
+ jump_label_unlock();
+ }
+@@ -289,7 +289,7 @@ static void __static_key_slow_dec_cpuslocked(struct static_key *key)
+ return;
+
+ guard(mutex)(&jump_label_mutex);
+- if (atomic_cmpxchg(&key->enabled, 1, 0))
++ if (atomic_cmpxchg(&key->enabled, 1, 0) == 1)
+ jump_label_update(key);
+ else
+ WARN_ON_ONCE(!static_key_slow_try_dec(key));
+--
+cgit 1.2.3-korg
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-27 22:16 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-27 22:16 UTC (permalink / raw
To: gentoo-commits
commit: 1b430d349fc20344677df4edb1d368863aa97642
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Jul 27 22:15:05 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Jul 27 22:15:05 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=1b430d34
Update cpu optimization patch. use=experimental
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
5010_enable-cpu-optimizations-universal.patch | 88 ++++++++++++++++-----------
1 file changed, 51 insertions(+), 37 deletions(-)
diff --git a/5010_enable-cpu-optimizations-universal.patch b/5010_enable-cpu-optimizations-universal.patch
index 75c48bf1..b5382da3 100644
--- a/5010_enable-cpu-optimizations-universal.patch
+++ b/5010_enable-cpu-optimizations-universal.patch
@@ -1,4 +1,4 @@
-From 71dd30c3e2ab2852b0290ae1f34ce1c7f8655040 Mon Sep 17 00:00:00 2001
+rom 86977b5357d9212d57841bc325e80f43081bb333 Mon Sep 17 00:00:00 2001
From: graysky <therealgraysky@proton.me>
Date: Wed, 21 Feb 2024 08:38:13 -0500
@@ -32,8 +32,9 @@ CPU-specific microarchitectures include:
• AMD Family 15h (Excavator)
• AMD Family 17h (Zen)
• AMD Family 17h (Zen 2)
-• AMD Family 19h (Zen 3)†
-• AMD Family 19h (Zen 4)§
+• AMD Family 19h (Zen 3)**
+• AMD Family 19h (Zen 4)‡
+• AMD Family 1Ah (Zen 5)§
• Intel Silvermont low-power processors
• Intel Goldmont low-power processors (Apollo Lake and Denverton)
• Intel Goldmont Plus low-power processors (Gemini Lake)
@@ -50,18 +51,20 @@ CPU-specific microarchitectures include:
• Intel Xeon (Cascade Lake)
• Intel Xeon (Cooper Lake)*
• Intel 3rd Gen 10nm++ i3/i5/i7/i9-family (Tiger Lake)*
-• Intel 4th Gen 10nm++ Xeon (Sapphire Rapids)‡
-• Intel 11th Gen i3/i5/i7/i9-family (Rocket Lake)‡
-• Intel 12th Gen i3/i5/i7/i9-family (Alder Lake)‡
-• Intel 13th Gen i3/i5/i7/i9-family (Raptor Lake)§
-• Intel 14th Gen i3/i5/i7/i9-family (Meteor Lake)§
-• Intel 5th Gen 10nm++ Xeon (Emerald Rapids)§
+• Intel 4th Gen 10nm++ Xeon (Sapphire Rapids)†
+• Intel 11th Gen i3/i5/i7/i9-family (Rocket Lake)†
+• Intel 12th Gen i3/i5/i7/i9-family (Alder Lake)†
+• Intel 13th Gen i3/i5/i7/i9-family (Raptor Lake)‡
+• Intel 14th Gen i3/i5/i7/i9-family (Meteor Lake)‡
+• Intel 5th Gen 10nm++ Xeon (Emerald Rapids)‡
Notes: If not otherwise noted, gcc >=9.1 is required for support.
*Requires gcc >=10.1 or clang >=10.0
- †Required gcc >=10.3 or clang >=12.0
- ‡Required gcc >=11.1 or clang >=12.0
- §Required gcc >=13.0 or clang >=15.0.5
+ **Required gcc >=10.3 or clang >=12.0
+ †Required gcc >=11.1 or clang >=12.0
+ ‡Required gcc >=13.0 or clang >=15.0.5
+ §Required gcc >=14.1 or clang >=19.0?
+
It also offers to compile passing the 'native' option which, "selects the CPU
to generate code for at compilation time by determining the processor type of
@@ -101,13 +104,13 @@ REFERENCES
4. https://github.com/graysky2/kernel_gcc_patch/issues/15
5. http://www.linuxforge.net/docs/linux/linux-gcc.php
---
- arch/x86/Kconfig.cpu | 424 ++++++++++++++++++++++++++++++--
- arch/x86/Makefile | 44 +++-
- arch/x86/include/asm/vermagic.h | 74 ++++++
- 3 files changed, 526 insertions(+), 16 deletions(-)
+ arch/x86/Kconfig.cpu | 432 ++++++++++++++++++++++++++++++--
+ arch/x86/Makefile | 45 +++-
+ arch/x86/include/asm/vermagic.h | 76 ++++++
+ 3 files changed, 537 insertions(+), 16 deletions(-)
diff --git a/arch/x86/Kconfig.cpu b/arch/x86/Kconfig.cpu
-index 2a7279d80460a..6924a0f5f1c26 100644
+index 2a7279d80460a..55941c31ade35 100644
--- a/arch/x86/Kconfig.cpu
+++ b/arch/x86/Kconfig.cpu
@@ -157,7 +157,7 @@ config MPENTIUM4
@@ -128,7 +131,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
depends on X86_32
help
Select this for an AMD Athlon K7-family processor. Enables use of
-@@ -173,12 +173,106 @@ config MK7
+@@ -173,12 +173,114 @@ config MK7
flags to GCC.
config MK8
@@ -232,11 +235,19 @@ index 2a7279d80460a..6924a0f5f1c26 100644
+ Select this for AMD Family 19h Zen 4 processors.
+
+ Enables -march=znver4
++
++config MZEN5
++ bool "AMD Zen 5"
++ depends on (CC_IS_GCC && GCC_VERSION >= 141000) || (CC_IS_CLANG && CLANG_VERSION >= 180000)
++ help
++ Select this for AMD Family 19h Zen 5 processors.
++
++ Enables -march=znver5
+
config MCRUSOE
bool "Crusoe"
depends on X86_32
-@@ -270,7 +364,7 @@ config MPSC
+@@ -270,7 +372,7 @@ config MPSC
in /proc/cpuinfo. Family 15 is an older Xeon, Family 6 a newer one.
config MCORE2
@@ -245,7 +256,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
help
Select this for Intel Core 2 and newer Core 2 Xeons (Xeon 51xx and
-@@ -278,6 +372,8 @@ config MCORE2
+@@ -278,6 +380,8 @@ config MCORE2
family in /proc/cpuinfo. Newer ones have 6 and older ones 15
(not a typo)
@@ -254,7 +265,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
config MATOM
bool "Intel Atom"
help
-@@ -287,6 +383,212 @@ config MATOM
+@@ -287,6 +391,212 @@ config MATOM
accordingly optimized code. Use a recent GCC with specific Atom
support in order to fully benefit from selecting this option.
@@ -467,7 +478,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
config GENERIC_CPU
bool "Generic-x86-64"
depends on X86_64
-@@ -294,6 +596,50 @@ config GENERIC_CPU
+@@ -294,6 +604,50 @@ config GENERIC_CPU
Generic x86-64 CPU.
Run equally well on all x86-64 CPUs.
@@ -518,14 +529,14 @@ index 2a7279d80460a..6924a0f5f1c26 100644
endchoice
config X86_GENERIC
-@@ -318,9 +664,17 @@ config X86_INTERNODE_CACHE_SHIFT
+@@ -318,9 +672,17 @@ config X86_INTERNODE_CACHE_SHIFT
config X86_L1_CACHE_SHIFT
int
default "7" if MPENTIUM4 || MPSC
- default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || X86_GENERIC || GENERIC_CPU
+ default "6" if MK7 || MK8 || MPENTIUMM || MCORE2 || MATOM || MVIAC7 || MK8SSE3 || MK10 \
+ || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER \
-+ || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MNEHALEM || MWESTMERE || MSILVERMONT \
++ || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MZEN5 || MNEHALEM || MWESTMERE || MSILVERMONT \
+ || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL \
+ || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE \
+ || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE \
@@ -538,7 +549,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
config X86_F00F_BUG
def_bool y
-@@ -332,15 +686,27 @@ config X86_INVD_BUG
+@@ -332,15 +694,27 @@ config X86_INVD_BUG
config X86_ALIGNMENT_16
def_bool y
@@ -561,7 +572,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
+ depends on MWINCHIP3D || MWINCHIPC6 || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM \
+ || MPENTIUMIII || MPENTIUMII || M686 || MK8 || MVIAC3_2 || MVIAC7 || MEFFICEON || MGEODE_LX \
+ || MCORE2 || MATOM || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER \
-+ || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MNEHALEM \
++ || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MZEN5 || MNEHALEM \
+ || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE \
+ || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE \
+ || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE \
@@ -569,7 +580,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
#
# P6_NOPs are a relatively minor optimization that require a family >=
-@@ -356,11 +722,22 @@ config X86_USE_PPRO_CHECKSUM
+@@ -356,11 +730,22 @@ config X86_USE_PPRO_CHECKSUM
config X86_P6_NOP
def_bool y
depends on X86_64
@@ -586,7 +597,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
+ depends on (MWINCHIP3D || MCRUSOE || MEFFICEON || MCYRIXIII || MK7 || MK6 || MPENTIUM4 || MPENTIUMM \
+ || MPENTIUMIII || MPENTIUMII || M686 || M586MMX || M586TSC || MK8 || MVIAC3_2 || MVIAC7 || MGEODEGX1 \
+ || MGEODE_LX || MCORE2 || MATOM || MK8SSE3 || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER \
-+ || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MNEHALEM \
++ || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MZEN5 || MNEHALEM \
+ || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL \
+ || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE \
+ || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS \
@@ -594,7 +605,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
config X86_HAVE_PAE
def_bool y
-@@ -368,18 +745,37 @@ config X86_HAVE_PAE
+@@ -368,18 +753,37 @@ config X86_HAVE_PAE
config X86_CMPXCHG64
def_bool y
@@ -602,7 +613,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
+ depends on X86_PAE || X86_64 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 \
+ || M586TSC || M586MMX || MATOM || MGEODE_LX || MGEODEGX1 || MK6 || MK7 || MK8 || MK8SSE3 || MK10 \
+ || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR || MZEN \
-+ || MZEN2 || MZEN3 || MZEN4 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS \
++ || MZEN2 || MZEN3 || MZEN4 || MZEN5 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT || MGOLDMONTPLUS \
+ || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX || MCANNONLAKE \
+ || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE \
+ || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS || MNATIVE_INTEL || MNATIVE_AMD
@@ -615,7 +626,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
+ depends on (MK8 || MK7 || MCORE2 || MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 \
+ || MVIAC3_2 || MVIAC7 || MCRUSOE || MEFFICEON || X86_64 || MATOM || MGEODE_LX || MK8SSE3 || MK10 \
+ || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER || MEXCAVATOR \
-+ || MZEN || MZEN2 || MZEN3 || MZEN4 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT \
++ || MZEN || MZEN2 || MZEN3 || MZEN4 || MZEN5 || MNEHALEM || MWESTMERE || MSILVERMONT || MGOLDMONT \
+ || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL || MSKYLAKE || MSKYLAKEX \
+ || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE || MTIGERLAKE || MSAPPHIRERAPIDS \
+ || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MMETEORLAKE || MEMERALDRAPIDS || MNATIVE_INTEL || MNATIVE_AMD)
@@ -627,7 +638,7 @@ index 2a7279d80460a..6924a0f5f1c26 100644
+ default "6" if X86_32 && (MPENTIUM4 || MPENTIUMM || MPENTIUMIII || MPENTIUMII || M686 \
+ || MVIAC3_2 || MVIAC7 || MEFFICEON || MATOM || MCORE2 || MK7 || MK8 || MK8SSE3 \
+ || MK10 || MBARCELONA || MBOBCAT || MJAGUAR || MBULLDOZER || MPILEDRIVER || MSTEAMROLLER \
-+ || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MNEHALEM || MWESTMERE || MSILVERMONT \
++ || MEXCAVATOR || MZEN || MZEN2 || MZEN3 || MZEN4 || MZEN5 || MNEHALEM || MWESTMERE || MSILVERMONT \
+ || MGOLDMONT || MGOLDMONTPLUS || MSANDYBRIDGE || MIVYBRIDGE || MHASWELL || MBROADWELL \
+ || MSKYLAKE || MSKYLAKEX || MCANNONLAKE || MICELAKE || MCASCADELAKE || MCOOPERLAKE \
+ || MTIGERLAKE || MSAPPHIRERAPIDS || MROCKETLAKE || MALDERLAKE || MRAPTORLAKE || MRAPTORLAKE \
@@ -636,10 +647,10 @@ index 2a7279d80460a..6924a0f5f1c26 100644
default "4"
diff --git a/arch/x86/Makefile b/arch/x86/Makefile
-index da8f3caf27815..c873d10df15d0 100644
+index 5ab93fcdd691d..ac203b599befd 100644
--- a/arch/x86/Makefile
+++ b/arch/x86/Makefile
-@@ -152,8 +152,48 @@ else
+@@ -156,8 +156,49 @@ else
# FIXME - should be integrated in Makefile.cpu (Makefile_32.cpu)
cflags-$(CONFIG_MK8) += -march=k8
cflags-$(CONFIG_MPSC) += -march=nocona
@@ -658,6 +669,7 @@ index da8f3caf27815..c873d10df15d0 100644
+ cflags-$(CONFIG_MZEN2) += -march=znver2
+ cflags-$(CONFIG_MZEN3) += -march=znver3
+ cflags-$(CONFIG_MZEN4) += -march=znver4
++ cflags-$(CONFIG_MZEN5) += -march=znver5
+ cflags-$(CONFIG_MNATIVE_INTEL) += -march=native
+ cflags-$(CONFIG_MNATIVE_AMD) += -march=native
+ cflags-$(CONFIG_MATOM) += -march=bonnell
@@ -691,7 +703,7 @@ index da8f3caf27815..c873d10df15d0 100644
KBUILD_CFLAGS += $(cflags-y)
diff --git a/arch/x86/include/asm/vermagic.h b/arch/x86/include/asm/vermagic.h
-index 75884d2cdec37..02c1386eb653e 100644
+index 75884d2cdec37..7acca9b5a9d56 100644
--- a/arch/x86/include/asm/vermagic.h
+++ b/arch/x86/include/asm/vermagic.h
@@ -17,6 +17,54 @@
@@ -749,7 +761,7 @@ index 75884d2cdec37..02c1386eb653e 100644
#elif defined CONFIG_MATOM
#define MODULE_PROC_FAMILY "ATOM "
#elif defined CONFIG_M686
-@@ -35,6 +83,32 @@
+@@ -35,6 +83,34 @@
#define MODULE_PROC_FAMILY "K7 "
#elif defined CONFIG_MK8
#define MODULE_PROC_FAMILY "K8 "
@@ -779,9 +791,11 @@ index 75884d2cdec37..02c1386eb653e 100644
+#define MODULE_PROC_FAMILY "ZEN3 "
+#elif defined CONFIG_MZEN4
+#define MODULE_PROC_FAMILY "ZEN4 "
++#elif defined CONFIG_MZEN5
++#define MODULE_PROC_FAMILY "ZEN5 "
#elif defined CONFIG_MELAN
#define MODULE_PROC_FAMILY "ELAN "
#elif defined CONFIG_MCRUSOE
--
-2.43.2
+2.45.0
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-27 22:04 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-27 22:04 UTC (permalink / raw
To: gentoo-commits
commit: 0c10794820c6ae659983deb3128623ef16eb4e7b
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Jul 27 22:04:00 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Jul 27 22:04:00 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=0c107948
BMQ(BitMap Queue) Scheduler. use=experimental
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 8 +
5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch | 11474 +++++++++++++++++++++++++
5021_BMQ-and-PDS-gentoo-defaults.patch | 12 +
3 files changed, 11494 insertions(+)
diff --git a/0000_README b/0000_README
index f3d968e8..f2aa0e92 100644
--- a/0000_README
+++ b/0000_README
@@ -90,3 +90,11 @@ Desc: Add Gentoo Linux support config settings and defaults.
Patch: 5010_enable-cpu-optimizations-universal.patch
From: https://github.com/graysky2/kernel_compiler_patch
Desc: Kernel >= 5.15 patch enables gcc = v11.1+ optimizations for additional CPUs.
+
+Patch: 5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch
+From: https://github.com/Frogging-Family/linux-tkg
+Desc: BMQ(BitMap Queue) Scheduler. A new CPU scheduler developed from PDS(incld). Inspired by the scheduler in zircon.
+
+Patch: 5021_BMQ-and-PDS-gentoo-defaults.patch
+From: https://gitweb.gentoo.org/proj/linux-patches.git/
+Desc: Set defaults for BMQ. default to n
diff --git a/5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch b/5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch
new file mode 100644
index 00000000..5f577d24
--- /dev/null
+++ b/5020_BMQ-and-PDS-io-scheduler-v6.10-r0.patch
@@ -0,0 +1,11474 @@
+diff --git a/Documentation/admin-guide/sysctl/kernel.rst b/Documentation/admin-guide/sysctl/kernel.rst
+--- a/Documentation/admin-guide/sysctl/kernel.rst 2024-07-15 00:43:32.000000000 +0200
++++ b/Documentation/admin-guide/sysctl/kernel.rst 2024-07-16 11:57:40.064869171 +0200
+@@ -1673,3 +1673,12 @@ is 10 seconds.
+
+ The softlockup threshold is (``2 * watchdog_thresh``). Setting this
+ tunable to zero will disable lockup detection altogether.
++
++yield_type:
++===========
++
++BMQ/PDS CPU scheduler only. This determines what type of yield calls
++to sched_yield() will be performed.
++
++ 0 - No yield.
++ 1 - Requeue task. (default)
+diff --git a/Documentation/scheduler/sched-BMQ.txt b/Documentation/scheduler/sched-BMQ.txt
+--- a/Documentation/scheduler/sched-BMQ.txt 1970-01-01 01:00:00.000000000 +0100
++++ b/Documentation/scheduler/sched-BMQ.txt 2024-07-16 11:57:40.268882498 +0200
+@@ -0,0 +1,110 @@
++ BitMap queue CPU Scheduler
++ --------------------------
++
++CONTENT
++========
++
++ Background
++ Design
++ Overview
++ Task policy
++ Priority management
++ BitMap Queue
++ CPU Assignment and Migration
++
++
++Background
++==========
++
++BitMap Queue CPU scheduler, referred to as BMQ from here on, is an evolution
++of previous Priority and Deadline based Skiplist multiple queue scheduler(PDS),
++and inspired by Zircon scheduler. The goal of it is to keep the scheduler code
++simple, while efficiency and scalable for interactive tasks, such as desktop,
++movie playback and gaming etc.
++
++Design
++======
++
++Overview
++--------
++
++BMQ use per CPU run queue design, each CPU(logical) has it's own run queue,
++each CPU is responsible for scheduling the tasks that are putting into it's
++run queue.
++
++The run queue is a set of priority queues. Note that these queues are fifo
++queue for non-rt tasks or priority queue for rt tasks in data structure. See
++BitMap Queue below for details. BMQ is optimized for non-rt tasks in the fact
++that most applications are non-rt tasks. No matter the queue is fifo or
++priority, In each queue is an ordered list of runnable tasks awaiting execution
++and the data structures are the same. When it is time for a new task to run,
++the scheduler simply looks the lowest numbered queueue that contains a task,
++and runs the first task from the head of that queue. And per CPU idle task is
++also in the run queue, so the scheduler can always find a task to run on from
++its run queue.
++
++Each task will assigned the same timeslice(default 4ms) when it is picked to
++start running. Task will be reinserted at the end of the appropriate priority
++queue when it uses its whole timeslice. When the scheduler selects a new task
++from the priority queue it sets the CPU's preemption timer for the remainder of
++the previous timeslice. When that timer fires the scheduler will stop execution
++on that task, select another task and start over again.
++
++If a task blocks waiting for a shared resource then it's taken out of its
++priority queue and is placed in a wait queue for the shared resource. When it
++is unblocked it will be reinserted in the appropriate priority queue of an
++eligible CPU.
++
++Task policy
++-----------
++
++BMQ supports DEADLINE, FIFO, RR, NORMAL, BATCH and IDLE task policy like the
++mainline CFS scheduler. But BMQ is heavy optimized for non-rt task, that's
++NORMAL/BATCH/IDLE policy tasks. Below is the implementation detail of each
++policy.
++
++DEADLINE
++ It is squashed as priority 0 FIFO task.
++
++FIFO/RR
++ All RT tasks share one single priority queue in BMQ run queue designed. The
++complexity of insert operation is O(n). BMQ is not designed for system runs
++with major rt policy tasks.
++
++NORMAL/BATCH/IDLE
++ BATCH and IDLE tasks are treated as the same policy. They compete CPU with
++NORMAL policy tasks, but they just don't boost. To control the priority of
++NORMAL/BATCH/IDLE tasks, simply use nice level.
++
++ISO
++ ISO policy is not supported in BMQ. Please use nice level -20 NORMAL policy
++task instead.
++
++Priority management
++-------------------
++
++RT tasks have priority from 0-99. For non-rt tasks, there are three different
++factors used to determine the effective priority of a task. The effective
++priority being what is used to determine which queue it will be in.
++
++The first factor is simply the task’s static priority. Which is assigned from
++task's nice level, within [-20, 19] in userland's point of view and [0, 39]
++internally.
++
++The second factor is the priority boost. This is a value bounded between
++[-MAX_PRIORITY_ADJ, MAX_PRIORITY_ADJ] used to offset the base priority, it is
++modified by the following cases:
++
++*When a thread has used up its entire timeslice, always deboost its boost by
++increasing by one.
++*When a thread gives up cpu control(voluntary or non-voluntary) to reschedule,
++and its switch-in time(time after last switch and run) below the thredhold
++based on its priority boost, will boost its boost by decreasing by one buti is
++capped at 0 (won’t go negative).
++
++The intent in this system is to ensure that interactive threads are serviced
++quickly. These are usually the threads that interact directly with the user
++and cause user-perceivable latency. These threads usually do little work and
++spend most of their time blocked awaiting another user event. So they get the
++priority boost from unblocking while background threads that do most of the
++processing receive the priority penalty for using their entire timeslice.
+diff --git a/fs/proc/base.c b/fs/proc/base.c
+--- a/fs/proc/base.c 2024-07-15 00:43:32.000000000 +0200
++++ b/fs/proc/base.c 2024-07-16 11:57:44.113126230 +0200
+@@ -481,7 +481,7 @@ static int proc_pid_schedstat(struct seq
+ seq_puts(m, "0 0 0\n");
+ else
+ seq_printf(m, "%llu %llu %lu\n",
+- (unsigned long long)task->se.sum_exec_runtime,
++ (unsigned long long)tsk_seruntime(task),
+ (unsigned long long)task->sched_info.run_delay,
+ task->sched_info.pcount);
+
+diff --git a/include/asm-generic/resource.h b/include/asm-generic/resource.h
+--- a/include/asm-generic/resource.h 2024-07-15 00:43:32.000000000 +0200
++++ b/include/asm-generic/resource.h 2024-07-16 11:57:44.173129878 +0200
+@@ -23,7 +23,7 @@
+ [RLIMIT_LOCKS] = { RLIM_INFINITY, RLIM_INFINITY }, \
+ [RLIMIT_SIGPENDING] = { 0, 0 }, \
+ [RLIMIT_MSGQUEUE] = { MQ_BYTES_MAX, MQ_BYTES_MAX }, \
+- [RLIMIT_NICE] = { 0, 0 }, \
++ [RLIMIT_NICE] = { 30, 30 }, \
+ [RLIMIT_RTPRIO] = { 0, 0 }, \
+ [RLIMIT_RTTIME] = { RLIM_INFINITY, RLIM_INFINITY }, \
+ }
+diff --git a/include/linux/sched/deadline.h b/include/linux/sched/deadline.h
+--- a/include/linux/sched/deadline.h 2024-07-15 00:43:32.000000000 +0200
++++ b/include/linux/sched/deadline.h 2024-07-16 11:57:44.289136930 +0200
+@@ -2,6 +2,25 @@
+ #ifndef _LINUX_SCHED_DEADLINE_H
+ #define _LINUX_SCHED_DEADLINE_H
+
++#ifdef CONFIG_SCHED_ALT
++
++static inline int dl_task(struct task_struct *p)
++{
++ return 0;
++}
++
++#ifdef CONFIG_SCHED_BMQ
++#define __tsk_deadline(p) (0UL)
++#endif
++
++#ifdef CONFIG_SCHED_PDS
++#define __tsk_deadline(p) ((((u64) ((p)->prio))<<56) | (p)->deadline)
++#endif
++
++#else
++
++#define __tsk_deadline(p) ((p)->dl.deadline)
++
+ /*
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+@@ -23,6 +42,7 @@ static inline int dl_task(struct task_st
+ {
+ return dl_prio(p->prio);
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ static inline bool dl_time_before(u64 a, u64 b)
+ {
+diff --git a/include/linux/sched/prio.h b/include/linux/sched/prio.h
+--- a/include/linux/sched/prio.h 2024-07-15 00:43:32.000000000 +0200
++++ b/include/linux/sched/prio.h 2024-07-16 11:57:44.289136930 +0200
+@@ -18,6 +18,28 @@
+ #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH)
+ #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2)
+
++#ifdef CONFIG_SCHED_ALT
++
++/* Undefine MAX_PRIO and DEFAULT_PRIO */
++#undef MAX_PRIO
++#undef DEFAULT_PRIO
++
++/* +/- priority levels from the base priority */
++#ifdef CONFIG_SCHED_BMQ
++#define MAX_PRIORITY_ADJ (12)
++#endif
++
++#ifdef CONFIG_SCHED_PDS
++#define MAX_PRIORITY_ADJ (0)
++#endif
++
++#define MIN_NORMAL_PRIO (128)
++#define NORMAL_PRIO_NUM (64)
++#define MAX_PRIO (MIN_NORMAL_PRIO + NORMAL_PRIO_NUM)
++#define DEFAULT_PRIO (MAX_PRIO - MAX_PRIORITY_ADJ - NICE_WIDTH / 2)
++
++#endif /* CONFIG_SCHED_ALT */
++
+ /*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+diff --git a/include/linux/sched/rt.h b/include/linux/sched/rt.h
+--- a/include/linux/sched/rt.h 2024-07-15 00:43:32.000000000 +0200
++++ b/include/linux/sched/rt.h 2024-07-16 11:57:44.289136930 +0200
+@@ -24,8 +24,10 @@ static inline bool task_is_realtime(stru
+
+ if (policy == SCHED_FIFO || policy == SCHED_RR)
+ return true;
++#ifndef CONFIG_SCHED_ALT
+ if (policy == SCHED_DEADLINE)
+ return true;
++#endif
+ return false;
+ }
+
+diff --git a/include/linux/sched/topology.h b/include/linux/sched/topology.h
+--- a/include/linux/sched/topology.h 2024-07-15 00:43:32.000000000 +0200
++++ b/include/linux/sched/topology.h 2024-07-16 11:57:44.289136930 +0200
+@@ -244,7 +244,8 @@ static inline bool cpus_share_resources(
+
+ #endif /* !CONFIG_SMP */
+
+-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
++#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) && \
++ !defined(CONFIG_SCHED_ALT)
+ extern void rebuild_sched_domains_energy(void);
+ #else
+ static inline void rebuild_sched_domains_energy(void)
+diff --git a/include/linux/sched.h b/include/linux/sched.h
+--- a/include/linux/sched.h 2024-07-15 00:43:32.000000000 +0200
++++ b/include/linux/sched.h 2024-07-16 11:57:44.285136688 +0200
+@@ -774,9 +774,16 @@ struct task_struct {
+ struct alloc_tag *alloc_tag;
+ #endif
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_ALT)
+ int on_cpu;
++#endif
++
++#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_ALT)
+ struct __call_single_node wake_entry;
++#endif
++
++#ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ unsigned int wakee_flips;
+ unsigned long wakee_flip_decay_ts;
+ struct task_struct *last_wakee;
+@@ -790,6 +797,7 @@ struct task_struct {
+ */
+ int recent_used_cpu;
+ int wake_cpu;
++#endif /* !CONFIG_SCHED_ALT */
+ #endif
+ int on_rq;
+
+@@ -798,6 +806,19 @@ struct task_struct {
+ int normal_prio;
+ unsigned int rt_priority;
+
++#ifdef CONFIG_SCHED_ALT
++ u64 last_ran;
++ s64 time_slice;
++ struct list_head sq_node;
++#ifdef CONFIG_SCHED_BMQ
++ int boost_prio;
++#endif /* CONFIG_SCHED_BMQ */
++#ifdef CONFIG_SCHED_PDS
++ u64 deadline;
++#endif /* CONFIG_SCHED_PDS */
++ /* sched_clock time spent running */
++ u64 sched_time;
++#else /* !CONFIG_SCHED_ALT */
+ struct sched_entity se;
+ struct sched_rt_entity rt;
+ struct sched_dl_entity dl;
+@@ -809,6 +830,7 @@ struct task_struct {
+ unsigned long core_cookie;
+ unsigned int core_occupation;
+ #endif
++#endif /* !CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_CGROUP_SCHED
+ struct task_group *sched_task_group;
+@@ -1571,6 +1593,15 @@ struct task_struct {
+ */
+ };
+
++#ifdef CONFIG_SCHED_ALT
++#define tsk_seruntime(t) ((t)->sched_time)
++/* replace the uncertian rt_timeout with 0UL */
++#define tsk_rttimeout(t) (0UL)
++#else /* CFS */
++#define tsk_seruntime(t) ((t)->se.sum_exec_runtime)
++#define tsk_rttimeout(t) ((t)->rt.timeout)
++#endif /* !CONFIG_SCHED_ALT */
++
+ #define TASK_REPORT_IDLE (TASK_REPORT + 1)
+ #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
+
+diff --git a/init/init_task.c b/init/init_task.c
+--- a/init/init_task.c 2024-07-15 00:43:32.000000000 +0200
++++ b/init/init_task.c 2024-07-16 11:57:44.401143740 +0200
+@@ -70,9 +70,15 @@ struct task_struct init_task __aligned(L
+ .stack = init_stack,
+ .usage = REFCOUNT_INIT(2),
+ .flags = PF_KTHREAD,
++#ifdef CONFIG_SCHED_ALT
++ .prio = DEFAULT_PRIO,
++ .static_prio = DEFAULT_PRIO,
++ .normal_prio = DEFAULT_PRIO,
++#else
+ .prio = MAX_PRIO - 20,
+ .static_prio = MAX_PRIO - 20,
+ .normal_prio = MAX_PRIO - 20,
++#endif
+ .policy = SCHED_NORMAL,
+ .cpus_ptr = &init_task.cpus_mask,
+ .user_cpus_ptr = NULL,
+@@ -85,6 +91,16 @@ struct task_struct init_task __aligned(L
+ .restart_block = {
+ .fn = do_no_restart_syscall,
+ },
++#ifdef CONFIG_SCHED_ALT
++ .sq_node = LIST_HEAD_INIT(init_task.sq_node),
++#ifdef CONFIG_SCHED_BMQ
++ .boost_prio = 0,
++#endif
++#ifdef CONFIG_SCHED_PDS
++ .deadline = 0,
++#endif
++ .time_slice = HZ,
++#else
+ .se = {
+ .group_node = LIST_HEAD_INIT(init_task.se.group_node),
+ },
+@@ -92,6 +108,7 @@ struct task_struct init_task __aligned(L
+ .run_list = LIST_HEAD_INIT(init_task.rt.run_list),
+ .time_slice = RR_TIMESLICE,
+ },
++#endif
+ .tasks = LIST_HEAD_INIT(init_task.tasks),
+ #ifdef CONFIG_SMP
+ .pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
+diff --git a/init/Kconfig b/init/Kconfig
+--- a/init/Kconfig 2024-07-15 00:43:32.000000000 +0200
++++ b/init/Kconfig 2024-07-16 11:57:44.401143740 +0200
+@@ -638,6 +638,7 @@ config TASK_IO_ACCOUNTING
+
+ config PSI
+ bool "Pressure stall information tracking"
++ depends on !SCHED_ALT
+ select KERNFS
+ help
+ Collect metrics that indicate how overcommitted the CPU, memory,
+@@ -803,6 +804,7 @@ menu "Scheduler features"
+ config UCLAMP_TASK
+ bool "Enable utilization clamping for RT/FAIR tasks"
+ depends on CPU_FREQ_GOV_SCHEDUTIL
++ depends on !SCHED_ALT
+ help
+ This feature enables the scheduler to track the clamped utilization
+ of each CPU based on RUNNABLE tasks scheduled on that CPU.
+@@ -849,6 +851,35 @@ config UCLAMP_BUCKETS_COUNT
+
+ If in doubt, use the default value.
+
++menuconfig SCHED_ALT
++ bool "Alternative CPU Schedulers"
++ default y
++ help
++ This feature enable alternative CPU scheduler"
++
++if SCHED_ALT
++
++choice
++ prompt "Alternative CPU Scheduler"
++ default SCHED_BMQ
++
++config SCHED_BMQ
++ bool "BMQ CPU scheduler"
++ help
++ The BitMap Queue CPU scheduler for excellent interactivity and
++ responsiveness on the desktop and solid scalability on normal
++ hardware and commodity servers.
++
++config SCHED_PDS
++ bool "PDS CPU scheduler"
++ help
++ The Priority and Deadline based Skip list multiple queue CPU
++ Scheduler.
++
++endchoice
++
++endif
++
+ endmenu
+
+ #
+@@ -914,6 +945,7 @@ config NUMA_BALANCING
+ depends on ARCH_SUPPORTS_NUMA_BALANCING
+ depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+ depends on SMP && NUMA && MIGRATION && !PREEMPT_RT
++ depends on !SCHED_ALT
+ help
+ This option adds support for automatic NUMA aware memory/task placement.
+ The mechanism is quite primitive and is based on migrating memory when
+@@ -1015,6 +1047,7 @@ config FAIR_GROUP_SCHED
+ depends on CGROUP_SCHED
+ default CGROUP_SCHED
+
++if !SCHED_ALT
+ config CFS_BANDWIDTH
+ bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
+ depends on FAIR_GROUP_SCHED
+@@ -1037,6 +1070,7 @@ config RT_GROUP_SCHED
+ realtime bandwidth for them.
+ See Documentation/scheduler/sched-rt-group.rst for more information.
+
++endif #!SCHED_ALT
+ endif #CGROUP_SCHED
+
+ config SCHED_MM_CID
+@@ -1285,6 +1319,7 @@ config CHECKPOINT_RESTORE
+
+ config SCHED_AUTOGROUP
+ bool "Automatic process group scheduling"
++ depends on !SCHED_ALT
+ select CGROUPS
+ select CGROUP_SCHED
+ select FAIR_GROUP_SCHED
+diff --git a/kernel/cgroup/cpuset.c b/kernel/cgroup/cpuset.c
+--- a/kernel/cgroup/cpuset.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/cgroup/cpuset.c 2024-07-16 11:57:44.421144957 +0200
+@@ -846,7 +846,7 @@ out:
+ return ret;
+ }
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_ALT)
+ /*
+ * Helper routine for generate_sched_domains().
+ * Do cpusets a, b have overlapping effective cpus_allowed masks?
+@@ -1245,7 +1245,7 @@ static void rebuild_sched_domains_locked
+ /* Have scheduler rebuild the domains */
+ partition_and_rebuild_sched_domains(ndoms, doms, attr);
+ }
+-#else /* !CONFIG_SMP */
++#else /* !CONFIG_SMP || CONFIG_SCHED_ALT */
+ static void rebuild_sched_domains_locked(void)
+ {
+ }
+@@ -3301,12 +3301,15 @@ static int cpuset_can_attach(struct cgro
+ goto out_unlock;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(task)) {
+ cs->nr_migrate_dl_tasks++;
+ cs->sum_migrate_dl_bw += task->dl.dl_bw;
+ }
++#endif
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (!cs->nr_migrate_dl_tasks)
+ goto out_success;
+
+@@ -3327,6 +3330,7 @@ static int cpuset_can_attach(struct cgro
+ }
+
+ out_success:
++#endif
+ /*
+ * Mark attach is in progress. This makes validate_change() fail
+ * changes which zero cpus/mems_allowed.
+@@ -3350,12 +3354,14 @@ static void cpuset_cancel_attach(struct
+ if (!cs->attach_in_progress)
+ wake_up(&cpuset_attach_wq);
+
++#ifndef CONFIG_SCHED_ALT
+ if (cs->nr_migrate_dl_tasks) {
+ int cpu = cpumask_any(cs->effective_cpus);
+
+ dl_bw_free(cpu, cs->sum_migrate_dl_bw);
+ reset_migrate_dl_data(cs);
+ }
++#endif
+
+ mutex_unlock(&cpuset_mutex);
+ }
+diff --git a/kernel/delayacct.c b/kernel/delayacct.c
+--- a/kernel/delayacct.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/delayacct.c 2024-07-16 11:57:44.421144957 +0200
+@@ -149,7 +149,7 @@ int delayacct_add_tsk(struct taskstats *
+ */
+ t1 = tsk->sched_info.pcount;
+ t2 = tsk->sched_info.run_delay;
+- t3 = tsk->se.sum_exec_runtime;
++ t3 = tsk_seruntime(tsk);
+
+ d->cpu_count += t1;
+
+diff --git a/kernel/exit.c b/kernel/exit.c
+--- a/kernel/exit.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/exit.c 2024-07-16 11:57:44.425145200 +0200
+@@ -175,7 +175,7 @@ static void __exit_signal(struct task_st
+ sig->curr_target = next_thread(tsk);
+ }
+
+- add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
++ add_device_randomness((const void*) &tsk_seruntime(tsk),
+ sizeof(unsigned long long));
+
+ /*
+@@ -196,7 +196,7 @@ static void __exit_signal(struct task_st
+ sig->inblock += task_io_get_inblock(tsk);
+ sig->oublock += task_io_get_oublock(tsk);
+ task_io_accounting_add(&sig->ioac, &tsk->ioac);
+- sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
++ sig->sum_sched_runtime += tsk_seruntime(tsk);
+ sig->nr_threads--;
+ __unhash_process(tsk, group_dead);
+ write_sequnlock(&sig->stats_lock);
+diff --git a/kernel/Kconfig.preempt b/kernel/Kconfig.preempt
+--- a/kernel/Kconfig.preempt 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/Kconfig.preempt 2024-07-16 11:57:44.409144227 +0200
+@@ -117,7 +117,7 @@ config PREEMPT_DYNAMIC
+
+ config SCHED_CORE
+ bool "Core Scheduling for SMT"
+- depends on SCHED_SMT
++ depends on SCHED_SMT && !SCHED_ALT
+ help
+ This option permits Core Scheduling, a means of coordinated task
+ selection across SMT siblings. When enabled -- see
+diff --git a/kernel/locking/rtmutex.c b/kernel/locking/rtmutex.c
+--- a/kernel/locking/rtmutex.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/locking/rtmutex.c 2024-07-16 11:57:44.433145686 +0200
+@@ -363,7 +363,7 @@ waiter_update_prio(struct rt_mutex_waite
+ lockdep_assert(RB_EMPTY_NODE(&waiter->tree.entry));
+
+ waiter->tree.prio = __waiter_prio(task);
+- waiter->tree.deadline = task->dl.deadline;
++ waiter->tree.deadline = __tsk_deadline(task);
+ }
+
+ /*
+@@ -384,16 +384,20 @@ waiter_clone_prio(struct rt_mutex_waiter
+ * Only use with rt_waiter_node_{less,equal}()
+ */
+ #define task_to_waiter_node(p) \
+- &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
++ &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = __tsk_deadline(p) }
+ #define task_to_waiter(p) \
+ &(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
+
+ static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
+ {
++#ifdef CONFIG_SCHED_PDS
++ return (left->deadline < right->deadline);
++#else
+ if (left->prio < right->prio)
+ return 1;
+
++#ifndef CONFIG_SCHED_BMQ
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+@@ -402,16 +406,22 @@ static __always_inline int rt_waiter_nod
+ */
+ if (dl_prio(left->prio))
+ return dl_time_before(left->deadline, right->deadline);
++#endif
+
+ return 0;
++#endif
+ }
+
+ static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
+ {
++#ifdef CONFIG_SCHED_PDS
++ return (left->deadline == right->deadline);
++#else
+ if (left->prio != right->prio)
+ return 0;
+
++#ifndef CONFIG_SCHED_BMQ
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+@@ -420,8 +430,10 @@ static __always_inline int rt_waiter_nod
+ */
+ if (dl_prio(left->prio))
+ return left->deadline == right->deadline;
++#endif
+
+ return 1;
++#endif
+ }
+
+ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
+diff --git a/kernel/sched/alt_core.c b/kernel/sched/alt_core.c
+--- a/kernel/sched/alt_core.c 1970-01-01 01:00:00.000000000 +0100
++++ b/kernel/sched/alt_core.c 2024-07-16 11:57:44.445146416 +0200
+@@ -0,0 +1,8963 @@
++/*
++ * kernel/sched/alt_core.c
++ *
++ * Core alternative kernel scheduler code and related syscalls
++ *
++ * Copyright (C) 1991-2002 Linus Torvalds
++ *
++ * 2009-08-13 Brainfuck deadline scheduling policy by Con Kolivas deletes
++ * a whole lot of those previous things.
++ * 2017-09-06 Priority and Deadline based Skip list multiple queue kernel
++ * scheduler by Alfred Chen.
++ * 2019-02-20 BMQ(BitMap Queue) kernel scheduler by Alfred Chen.
++ */
++#include <linux/sched/clock.h>
++#include <linux/sched/cputime.h>
++#include <linux/sched/debug.h>
++#include <linux/sched/hotplug.h>
++#include <linux/sched/init.h>
++#include <linux/sched/isolation.h>
++#include <linux/sched/loadavg.h>
++#include <linux/sched/mm.h>
++#include <linux/sched/nohz.h>
++#include <linux/sched/stat.h>
++#include <linux/sched/wake_q.h>
++
++#include <linux/blkdev.h>
++#include <linux/context_tracking.h>
++#include <linux/cpuset.h>
++#include <linux/delayacct.h>
++#include <linux/init_task.h>
++#include <linux/kcov.h>
++#include <linux/kprobes.h>
++#include <linux/nmi.h>
++#include <linux/rseq.h>
++#include <linux/scs.h>
++
++#include <uapi/linux/sched/types.h>
++
++#include <asm/irq_regs.h>
++#include <asm/switch_to.h>
++
++#define CREATE_TRACE_POINTS
++#include <trace/events/sched.h>
++#include <trace/events/ipi.h>
++#undef CREATE_TRACE_POINTS
++
++#include "sched.h"
++#include "smp.h"
++
++#include "pelt.h"
++
++#include "../../io_uring/io-wq.h"
++#include "../smpboot.h"
++
++EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu);
++EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask);
++
++/*
++ * Export tracepoints that act as a bare tracehook (ie: have no trace event
++ * associated with them) to allow external modules to probe them.
++ */
++EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
++
++#ifdef CONFIG_SCHED_DEBUG
++#define sched_feat(x) (1)
++/*
++ * Print a warning if need_resched is set for the given duration (if
++ * LATENCY_WARN is enabled).
++ *
++ * If sysctl_resched_latency_warn_once is set, only one warning will be shown
++ * per boot.
++ */
++__read_mostly int sysctl_resched_latency_warn_ms = 100;
++__read_mostly int sysctl_resched_latency_warn_once = 1;
++#else
++#define sched_feat(x) (0)
++#endif /* CONFIG_SCHED_DEBUG */
++
++#define ALT_SCHED_VERSION "v6.10-r0"
++
++/*
++ * Compile time debug macro
++ * #define ALT_SCHED_DEBUG
++ */
++
++/* rt_prio(prio) defined in include/linux/sched/rt.h */
++#define rt_task(p) rt_prio((p)->prio)
++#define rt_policy(policy) ((policy) == SCHED_FIFO || (policy) == SCHED_RR)
++#define task_has_rt_policy(p) (rt_policy((p)->policy))
++
++#define STOP_PRIO (MAX_RT_PRIO - 1)
++
++/*
++ * Time slice
++ * (default: 4 msec, units: nanoseconds)
++ */
++unsigned int sysctl_sched_base_slice __read_mostly = (4 << 20);
++
++#ifdef CONFIG_SCHED_BMQ
++#include "bmq.h"
++#endif
++#ifdef CONFIG_SCHED_PDS
++#include "pds.h"
++#endif
++
++struct affinity_context {
++ const struct cpumask *new_mask;
++ struct cpumask *user_mask;
++ unsigned int flags;
++};
++
++/* Reschedule if less than this many μs left */
++#define RESCHED_NS (100 << 10)
++
++/**
++ * sched_yield_type - Type of sched_yield() will be performed.
++ * 0: No yield.
++ * 1: Requeue task. (default)
++ */
++int sched_yield_type __read_mostly = 1;
++
++#ifdef CONFIG_SMP
++static cpumask_t sched_rq_pending_mask ____cacheline_aligned_in_smp;
++
++DEFINE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
++DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_llc_mask);
++DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_topo_end_mask);
++
++#ifdef CONFIG_SCHED_SMT
++DEFINE_STATIC_KEY_FALSE(sched_smt_present);
++EXPORT_SYMBOL_GPL(sched_smt_present);
++#endif
++
++/*
++ * Keep a unique ID per domain (we use the first CPUs number in the cpumask of
++ * the domain), this allows us to quickly tell if two cpus are in the same cache
++ * domain, see cpus_share_cache().
++ */
++DEFINE_PER_CPU(int, sd_llc_id);
++#endif /* CONFIG_SMP */
++
++static DEFINE_MUTEX(sched_hotcpu_mutex);
++
++DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
++
++#ifndef prepare_arch_switch
++# define prepare_arch_switch(next) do { } while (0)
++#endif
++#ifndef finish_arch_post_lock_switch
++# define finish_arch_post_lock_switch() do { } while (0)
++#endif
++
++static cpumask_t sched_preempt_mask[SCHED_QUEUE_BITS + 1] ____cacheline_aligned_in_smp;
++
++static cpumask_t *const sched_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS - 1];
++#ifdef CONFIG_SCHED_SMT
++static cpumask_t *const sched_sg_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS];
++#endif
++
++/* task function */
++static inline const struct cpumask *task_user_cpus(struct task_struct *p)
++{
++ if (!p->user_cpus_ptr)
++ return cpu_possible_mask; /* &init_task.cpus_mask */
++ return p->user_cpus_ptr;
++}
++
++/* sched_queue related functions */
++static inline void sched_queue_init(struct sched_queue *q)
++{
++ int i;
++
++ bitmap_zero(q->bitmap, SCHED_QUEUE_BITS);
++ for(i = 0; i < SCHED_LEVELS; i++)
++ INIT_LIST_HEAD(&q->heads[i]);
++}
++
++/*
++ * Init idle task and put into queue structure of rq
++ * IMPORTANT: may be called multiple times for a single cpu
++ */
++static inline void sched_queue_init_idle(struct sched_queue *q,
++ struct task_struct *idle)
++{
++ INIT_LIST_HEAD(&q->heads[IDLE_TASK_SCHED_PRIO]);
++ list_add_tail(&idle->sq_node, &q->heads[IDLE_TASK_SCHED_PRIO]);
++ idle->on_rq = TASK_ON_RQ_QUEUED;
++}
++
++#define CLEAR_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
++ if (low < pr && pr <= high) \
++ cpumask_clear_cpu(cpu, sched_preempt_mask + pr);
++
++#define SET_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
++ if (low < pr && pr <= high) \
++ cpumask_set_cpu(cpu, sched_preempt_mask + pr);
++
++static atomic_t sched_prio_record = ATOMIC_INIT(0);
++
++/* water mark related functions */
++static inline void update_sched_preempt_mask(struct rq *rq)
++{
++ int prio = find_first_bit(rq->queue.bitmap, SCHED_QUEUE_BITS);
++ int last_prio = rq->prio;
++ int cpu, pr;
++
++ if (prio == last_prio)
++ return;
++
++ rq->prio = prio;
++#ifdef CONFIG_SCHED_PDS
++ rq->prio_idx = sched_prio2idx(rq->prio, rq);
++#endif
++ cpu = cpu_of(rq);
++ pr = atomic_read(&sched_prio_record);
++
++ if (prio < last_prio) {
++ if (IDLE_TASK_SCHED_PRIO == last_prio) {
++#ifdef CONFIG_SCHED_SMT
++ if (static_branch_likely(&sched_smt_present))
++ cpumask_andnot(sched_sg_idle_mask,
++ sched_sg_idle_mask, cpu_smt_mask(cpu));
++#endif
++ cpumask_clear_cpu(cpu, sched_idle_mask);
++ last_prio -= 2;
++ }
++ CLEAR_CACHED_PREEMPT_MASK(pr, prio, last_prio, cpu);
++
++ return;
++ }
++ /* last_prio < prio */
++ if (IDLE_TASK_SCHED_PRIO == prio) {
++#ifdef CONFIG_SCHED_SMT
++ if (static_branch_likely(&sched_smt_present) &&
++ cpumask_intersects(cpu_smt_mask(cpu), sched_idle_mask))
++ cpumask_or(sched_sg_idle_mask, sched_sg_idle_mask, cpu_smt_mask(cpu));
++#endif
++ cpumask_set_cpu(cpu, sched_idle_mask);
++ prio -= 2;
++ }
++ SET_CACHED_PREEMPT_MASK(pr, last_prio, prio, cpu);
++}
++
++/*
++ * This routine assume that the idle task always in queue
++ */
++static inline struct task_struct *sched_rq_first_task(struct rq *rq)
++{
++ const struct list_head *head = &rq->queue.heads[sched_rq_prio_idx(rq)];
++
++ return list_first_entry(head, struct task_struct, sq_node);
++}
++
++static inline struct task_struct * sched_rq_next_task(struct task_struct *p, struct rq *rq)
++{
++ struct list_head *next = p->sq_node.next;
++
++ if (&rq->queue.heads[0] <= next && next < &rq->queue.heads[SCHED_LEVELS]) {
++ struct list_head *head;
++ unsigned long idx = next - &rq->queue.heads[0];
++
++ idx = find_next_bit(rq->queue.bitmap, SCHED_QUEUE_BITS,
++ sched_idx2prio(idx, rq) + 1);
++ head = &rq->queue.heads[sched_prio2idx(idx, rq)];
++
++ return list_first_entry(head, struct task_struct, sq_node);
++ }
++
++ return list_next_entry(p, sq_node);
++}
++
++/*
++ * Serialization rules:
++ *
++ * Lock order:
++ *
++ * p->pi_lock
++ * rq->lock
++ * hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
++ *
++ * rq1->lock
++ * rq2->lock where: rq1 < rq2
++ *
++ * Regular state:
++ *
++ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
++ * local CPU's rq->lock, it optionally removes the task from the runqueue and
++ * always looks at the local rq data structures to find the most eligible task
++ * to run next.
++ *
++ * Task enqueue is also under rq->lock, possibly taken from another CPU.
++ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
++ * the local CPU to avoid bouncing the runqueue state around [ see
++ * ttwu_queue_wakelist() ]
++ *
++ * Task wakeup, specifically wakeups that involve migration, are horribly
++ * complicated to avoid having to take two rq->locks.
++ *
++ * Special state:
++ *
++ * System-calls and anything external will use task_rq_lock() which acquires
++ * both p->pi_lock and rq->lock. As a consequence the state they change is
++ * stable while holding either lock:
++ *
++ * - sched_setaffinity()/
++ * set_cpus_allowed_ptr(): p->cpus_ptr, p->nr_cpus_allowed
++ * - set_user_nice(): p->se.load, p->*prio
++ * - __sched_setscheduler(): p->sched_class, p->policy, p->*prio,
++ * p->se.load, p->rt_priority,
++ * p->dl.dl_{runtime, deadline, period, flags, bw, density}
++ * - sched_setnuma(): p->numa_preferred_nid
++ * - sched_move_task(): p->sched_task_group
++ * - uclamp_update_active() p->uclamp*
++ *
++ * p->state <- TASK_*:
++ *
++ * is changed locklessly using set_current_state(), __set_current_state() or
++ * set_special_state(), see their respective comments, or by
++ * try_to_wake_up(). This latter uses p->pi_lock to serialize against
++ * concurrent self.
++ *
++ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
++ *
++ * is set by activate_task() and cleared by deactivate_task(), under
++ * rq->lock. Non-zero indicates the task is runnable, the special
++ * ON_RQ_MIGRATING state is used for migration without holding both
++ * rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
++ *
++ * p->on_cpu <- { 0, 1 }:
++ *
++ * is set by prepare_task() and cleared by finish_task() such that it will be
++ * set before p is scheduled-in and cleared after p is scheduled-out, both
++ * under rq->lock. Non-zero indicates the task is running on its CPU.
++ *
++ * [ The astute reader will observe that it is possible for two tasks on one
++ * CPU to have ->on_cpu = 1 at the same time. ]
++ *
++ * task_cpu(p): is changed by set_task_cpu(), the rules are:
++ *
++ * - Don't call set_task_cpu() on a blocked task:
++ *
++ * We don't care what CPU we're not running on, this simplifies hotplug,
++ * the CPU assignment of blocked tasks isn't required to be valid.
++ *
++ * - for try_to_wake_up(), called under p->pi_lock:
++ *
++ * This allows try_to_wake_up() to only take one rq->lock, see its comment.
++ *
++ * - for migration called under rq->lock:
++ * [ see task_on_rq_migrating() in task_rq_lock() ]
++ *
++ * o move_queued_task()
++ * o detach_task()
++ *
++ * - for migration called under double_rq_lock():
++ *
++ * o __migrate_swap_task()
++ * o push_rt_task() / pull_rt_task()
++ * o push_dl_task() / pull_dl_task()
++ * o dl_task_offline_migration()
++ *
++ */
++
++/*
++ * Context: p->pi_lock
++ */
++static inline struct rq *__task_access_lock(struct task_struct *p, raw_spinlock_t **plock)
++{
++ struct rq *rq;
++ for (;;) {
++ rq = task_rq(p);
++ if (p->on_cpu || task_on_rq_queued(p)) {
++ raw_spin_lock(&rq->lock);
++ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
++ *plock = &rq->lock;
++ return rq;
++ }
++ raw_spin_unlock(&rq->lock);
++ } else if (task_on_rq_migrating(p)) {
++ do {
++ cpu_relax();
++ } while (unlikely(task_on_rq_migrating(p)));
++ } else {
++ *plock = NULL;
++ return rq;
++ }
++ }
++}
++
++static inline void __task_access_unlock(struct task_struct *p, raw_spinlock_t *lock)
++{
++ if (NULL != lock)
++ raw_spin_unlock(lock);
++}
++
++static inline struct rq *
++task_access_lock_irqsave(struct task_struct *p, raw_spinlock_t **plock, unsigned long *flags)
++{
++ struct rq *rq;
++ for (;;) {
++ rq = task_rq(p);
++ if (p->on_cpu || task_on_rq_queued(p)) {
++ raw_spin_lock_irqsave(&rq->lock, *flags);
++ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
++ *plock = &rq->lock;
++ return rq;
++ }
++ raw_spin_unlock_irqrestore(&rq->lock, *flags);
++ } else if (task_on_rq_migrating(p)) {
++ do {
++ cpu_relax();
++ } while (unlikely(task_on_rq_migrating(p)));
++ } else {
++ raw_spin_lock_irqsave(&p->pi_lock, *flags);
++ if (likely(!p->on_cpu && !p->on_rq && rq == task_rq(p))) {
++ *plock = &p->pi_lock;
++ return rq;
++ }
++ raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
++ }
++ }
++}
++
++static inline void
++task_access_unlock_irqrestore(struct task_struct *p, raw_spinlock_t *lock, unsigned long *flags)
++{
++ raw_spin_unlock_irqrestore(lock, *flags);
++}
++
++/*
++ * __task_rq_lock - lock the rq @p resides on.
++ */
++struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ lockdep_assert_held(&p->pi_lock);
++
++ for (;;) {
++ rq = task_rq(p);
++ raw_spin_lock(&rq->lock);
++ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
++ return rq;
++ raw_spin_unlock(&rq->lock);
++
++ while (unlikely(task_on_rq_migrating(p)))
++ cpu_relax();
++ }
++}
++
++/*
++ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
++ */
++struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(p->pi_lock)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ for (;;) {
++ raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
++ rq = task_rq(p);
++ raw_spin_lock(&rq->lock);
++ /*
++ * move_queued_task() task_rq_lock()
++ *
++ * ACQUIRE (rq->lock)
++ * [S] ->on_rq = MIGRATING [L] rq = task_rq()
++ * WMB (__set_task_cpu()) ACQUIRE (rq->lock);
++ * [S] ->cpu = new_cpu [L] task_rq()
++ * [L] ->on_rq
++ * RELEASE (rq->lock)
++ *
++ * If we observe the old CPU in task_rq_lock(), the acquire of
++ * the old rq->lock will fully serialize against the stores.
++ *
++ * If we observe the new CPU in task_rq_lock(), the address
++ * dependency headed by '[L] rq = task_rq()' and the acquire
++ * will pair with the WMB to ensure we then also see migrating.
++ */
++ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
++ return rq;
++ }
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
++
++ while (unlikely(task_on_rq_migrating(p)))
++ cpu_relax();
++ }
++}
++
++static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock_irqsave(&rq->lock, rf->flags);
++}
++
++static inline void rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
++}
++
++DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
++ rq_lock_irqsave(_T->lock, &_T->rf),
++ rq_unlock_irqrestore(_T->lock, &_T->rf),
++ struct rq_flags rf)
++
++void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
++{
++ raw_spinlock_t *lock;
++
++ /* Matches synchronize_rcu() in __sched_core_enable() */
++ preempt_disable();
++
++ for (;;) {
++ lock = __rq_lockp(rq);
++ raw_spin_lock_nested(lock, subclass);
++ if (likely(lock == __rq_lockp(rq))) {
++ /* preempt_count *MUST* be > 1 */
++ preempt_enable_no_resched();
++ return;
++ }
++ raw_spin_unlock(lock);
++ }
++}
++
++void raw_spin_rq_unlock(struct rq *rq)
++{
++ raw_spin_unlock(rq_lockp(rq));
++}
++
++/*
++ * RQ-clock updating methods:
++ */
++
++static void update_rq_clock_task(struct rq *rq, s64 delta)
++{
++/*
++ * In theory, the compile should just see 0 here, and optimize out the call
++ * to sched_rt_avg_update. But I don't trust it...
++ */
++ s64 __maybe_unused steal = 0, irq_delta = 0;
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
++
++ /*
++ * Since irq_time is only updated on {soft,}irq_exit, we might run into
++ * this case when a previous update_rq_clock() happened inside a
++ * {soft,}irq region.
++ *
++ * When this happens, we stop ->clock_task and only update the
++ * prev_irq_time stamp to account for the part that fit, so that a next
++ * update will consume the rest. This ensures ->clock_task is
++ * monotonic.
++ *
++ * It does however cause some slight miss-attribution of {soft,}irq
++ * time, a more accurate solution would be to update the irq_time using
++ * the current rq->clock timestamp, except that would require using
++ * atomic ops.
++ */
++ if (irq_delta > delta)
++ irq_delta = delta;
++
++ rq->prev_irq_time += irq_delta;
++ delta -= irq_delta;
++ delayacct_irq(rq->curr, irq_delta);
++#endif
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ if (static_key_false((¶virt_steal_rq_enabled))) {
++ steal = paravirt_steal_clock(cpu_of(rq));
++ steal -= rq->prev_steal_time_rq;
++
++ if (unlikely(steal > delta))
++ steal = delta;
++
++ rq->prev_steal_time_rq += steal;
++ delta -= steal;
++ }
++#endif
++
++ rq->clock_task += delta;
++
++#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
++ if ((irq_delta + steal))
++ update_irq_load_avg(rq, irq_delta + steal);
++#endif
++}
++
++static inline void update_rq_clock(struct rq *rq)
++{
++ s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
++
++ if (unlikely(delta <= 0))
++ return;
++ rq->clock += delta;
++ sched_update_rq_clock(rq);
++ update_rq_clock_task(rq, delta);
++}
++
++/*
++ * RQ Load update routine
++ */
++#define RQ_LOAD_HISTORY_BITS (sizeof(s32) * 8ULL)
++#define RQ_UTIL_SHIFT (8)
++#define RQ_LOAD_HISTORY_TO_UTIL(l) (((l) >> (RQ_LOAD_HISTORY_BITS - 1 - RQ_UTIL_SHIFT)) & 0xff)
++
++#define LOAD_BLOCK(t) ((t) >> 17)
++#define LOAD_HALF_BLOCK(t) ((t) >> 16)
++#define BLOCK_MASK(t) ((t) & ((0x01 << 18) - 1))
++#define LOAD_BLOCK_BIT(b) (1UL << (RQ_LOAD_HISTORY_BITS - 1 - (b)))
++#define CURRENT_LOAD_BIT LOAD_BLOCK_BIT(0)
++
++static inline void rq_load_update(struct rq *rq)
++{
++ u64 time = rq->clock;
++ u64 delta = min(LOAD_BLOCK(time) - LOAD_BLOCK(rq->load_stamp), RQ_LOAD_HISTORY_BITS - 1);
++ u64 prev = !!(rq->load_history & CURRENT_LOAD_BIT);
++ u64 curr = !!rq->nr_running;
++
++ if (delta) {
++ rq->load_history = rq->load_history >> delta;
++
++ if (delta < RQ_UTIL_SHIFT) {
++ rq->load_block += (~BLOCK_MASK(rq->load_stamp)) * prev;
++ if (!!LOAD_HALF_BLOCK(rq->load_block) ^ curr)
++ rq->load_history ^= LOAD_BLOCK_BIT(delta);
++ }
++
++ rq->load_block = BLOCK_MASK(time) * prev;
++ } else {
++ rq->load_block += (time - rq->load_stamp) * prev;
++ }
++ if (prev ^ curr)
++ rq->load_history ^= CURRENT_LOAD_BIT;
++ rq->load_stamp = time;
++}
++
++unsigned long rq_load_util(struct rq *rq, unsigned long max)
++{
++ return RQ_LOAD_HISTORY_TO_UTIL(rq->load_history) * (max >> RQ_UTIL_SHIFT);
++}
++
++#ifdef CONFIG_SMP
++unsigned long sched_cpu_util(int cpu)
++{
++ return rq_load_util(cpu_rq(cpu), arch_scale_cpu_capacity(cpu));
++}
++#endif /* CONFIG_SMP */
++
++#ifdef CONFIG_CPU_FREQ
++/**
++ * cpufreq_update_util - Take a note about CPU utilization changes.
++ * @rq: Runqueue to carry out the update for.
++ * @flags: Update reason flags.
++ *
++ * This function is called by the scheduler on the CPU whose utilization is
++ * being updated.
++ *
++ * It can only be called from RCU-sched read-side critical sections.
++ *
++ * The way cpufreq is currently arranged requires it to evaluate the CPU
++ * performance state (frequency/voltage) on a regular basis to prevent it from
++ * being stuck in a completely inadequate performance level for too long.
++ * That is not guaranteed to happen if the updates are only triggered from CFS
++ * and DL, though, because they may not be coming in if only RT tasks are
++ * active all the time (or there are RT tasks only).
++ *
++ * As a workaround for that issue, this function is called periodically by the
++ * RT sched class to trigger extra cpufreq updates to prevent it from stalling,
++ * but that really is a band-aid. Going forward it should be replaced with
++ * solutions targeted more specifically at RT tasks.
++ */
++static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
++{
++ struct update_util_data *data;
++
++#ifdef CONFIG_SMP
++ rq_load_update(rq);
++#endif
++ data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, cpu_of(rq)));
++ if (data)
++ data->func(data, rq_clock(rq), flags);
++}
++#else
++static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
++{
++#ifdef CONFIG_SMP
++ rq_load_update(rq);
++#endif
++}
++#endif /* CONFIG_CPU_FREQ */
++
++#ifdef CONFIG_NO_HZ_FULL
++/*
++ * Tick may be needed by tasks in the runqueue depending on their policy and
++ * requirements. If tick is needed, lets send the target an IPI to kick it out
++ * of nohz mode if necessary.
++ */
++static inline void sched_update_tick_dependency(struct rq *rq)
++{
++ int cpu = cpu_of(rq);
++
++ if (!tick_nohz_full_cpu(cpu))
++ return;
++
++ if (rq->nr_running < 2)
++ tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
++ else
++ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
++}
++#else /* !CONFIG_NO_HZ_FULL */
++static inline void sched_update_tick_dependency(struct rq *rq) { }
++#endif
++
++bool sched_task_on_rq(struct task_struct *p)
++{
++ return task_on_rq_queued(p);
++}
++
++unsigned long get_wchan(struct task_struct *p)
++{
++ unsigned long ip = 0;
++ unsigned int state;
++
++ if (!p || p == current)
++ return 0;
++
++ /* Only get wchan if task is blocked and we can keep it that way. */
++ raw_spin_lock_irq(&p->pi_lock);
++ state = READ_ONCE(p->__state);
++ smp_rmb(); /* see try_to_wake_up() */
++ if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq)
++ ip = __get_wchan(p);
++ raw_spin_unlock_irq(&p->pi_lock);
++
++ return ip;
++}
++
++/*
++ * Add/Remove/Requeue task to/from the runqueue routines
++ * Context: rq->lock
++ */
++#define __SCHED_DEQUEUE_TASK(p, rq, flags, func) \
++ sched_info_dequeue(rq, p); \
++ \
++ __list_del_entry(&p->sq_node); \
++ if (p->sq_node.prev == p->sq_node.next) { \
++ clear_bit(sched_idx2prio(p->sq_node.next - &rq->queue.heads[0], rq), \
++ rq->queue.bitmap); \
++ func; \
++ }
++
++#define __SCHED_ENQUEUE_TASK(p, rq, flags, func) \
++ sched_info_enqueue(rq, p); \
++ { \
++ int idx, prio; \
++ TASK_SCHED_PRIO_IDX(p, rq, idx, prio); \
++ list_add_tail(&p->sq_node, &rq->queue.heads[idx]); \
++ if (list_is_first(&p->sq_node, &rq->queue.heads[idx])) { \
++ set_bit(prio, rq->queue.bitmap); \
++ func; \
++ } \
++ }
++
++static inline void dequeue_task(struct task_struct *p, struct rq *rq, int flags)
++{
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++
++ /*printk(KERN_INFO "sched: dequeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: dequeue task reside on cpu%d from cpu%d\n",
++ task_cpu(p), cpu_of(rq));
++#endif
++
++ __SCHED_DEQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
++ --rq->nr_running;
++#ifdef CONFIG_SMP
++ if (1 == rq->nr_running)
++ cpumask_clear_cpu(cpu_of(rq), &sched_rq_pending_mask);
++#endif
++
++ sched_update_tick_dependency(rq);
++}
++
++static inline void enqueue_task(struct task_struct *p, struct rq *rq, int flags)
++{
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++
++ /*printk(KERN_INFO "sched: enqueue(%d) %px %d\n", cpu_of(rq), p, p->prio);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: enqueue task reside on cpu%d to cpu%d\n",
++ task_cpu(p), cpu_of(rq));
++#endif
++
++ __SCHED_ENQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
++ ++rq->nr_running;
++#ifdef CONFIG_SMP
++ if (2 == rq->nr_running)
++ cpumask_set_cpu(cpu_of(rq), &sched_rq_pending_mask);
++#endif
++
++ sched_update_tick_dependency(rq);
++}
++
++static inline void requeue_task(struct task_struct *p, struct rq *rq)
++{
++ struct list_head *node = &p->sq_node;
++ int deq_idx, idx, prio;
++
++ TASK_SCHED_PRIO_IDX(p, rq, idx, prio);
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++ /*printk(KERN_INFO "sched: requeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: cpu[%d] requeue task reside on cpu%d\n",
++ cpu_of(rq), task_cpu(p));
++#endif
++ if (list_is_last(node, &rq->queue.heads[idx]))
++ return;
++
++ __list_del_entry(node);
++ if (node->prev == node->next && (deq_idx = node->next - &rq->queue.heads[0]) != idx)
++ clear_bit(sched_idx2prio(deq_idx, rq), rq->queue.bitmap);
++
++ list_add_tail(node, &rq->queue.heads[idx]);
++ if (list_is_first(node, &rq->queue.heads[idx]))
++ set_bit(prio, rq->queue.bitmap);
++ update_sched_preempt_mask(rq);
++}
++
++/*
++ * cmpxchg based fetch_or, macro so it works for different integer types
++ */
++#define fetch_or(ptr, mask) \
++ ({ \
++ typeof(ptr) _ptr = (ptr); \
++ typeof(mask) _mask = (mask); \
++ typeof(*_ptr) _val = *_ptr; \
++ \
++ do { \
++ } while (!try_cmpxchg(_ptr, &_val, _val | _mask)); \
++ _val; \
++})
++
++#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
++/*
++ * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
++ * this avoids any races wrt polling state changes and thereby avoids
++ * spurious IPIs.
++ */
++static inline bool set_nr_and_not_polling(struct task_struct *p)
++{
++ struct thread_info *ti = task_thread_info(p);
++ return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
++}
++
++/*
++ * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
++ *
++ * If this returns true, then the idle task promises to call
++ * sched_ttwu_pending() and reschedule soon.
++ */
++static bool set_nr_if_polling(struct task_struct *p)
++{
++ struct thread_info *ti = task_thread_info(p);
++ typeof(ti->flags) val = READ_ONCE(ti->flags);
++
++ do {
++ if (!(val & _TIF_POLLING_NRFLAG))
++ return false;
++ if (val & _TIF_NEED_RESCHED)
++ return true;
++ } while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
++
++ return true;
++}
++
++#else
++static inline bool set_nr_and_not_polling(struct task_struct *p)
++{
++ set_tsk_need_resched(p);
++ return true;
++}
++
++#ifdef CONFIG_SMP
++static inline bool set_nr_if_polling(struct task_struct *p)
++{
++ return false;
++}
++#endif
++#endif
++
++static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
++{
++ struct wake_q_node *node = &task->wake_q;
++
++ /*
++ * Atomically grab the task, if ->wake_q is !nil already it means
++ * it's already queued (either by us or someone else) and will get the
++ * wakeup due to that.
++ *
++ * In order to ensure that a pending wakeup will observe our pending
++ * state, even in the failed case, an explicit smp_mb() must be used.
++ */
++ smp_mb__before_atomic();
++ if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
++ return false;
++
++ /*
++ * The head is context local, there can be no concurrency.
++ */
++ *head->lastp = node;
++ head->lastp = &node->next;
++ return true;
++}
++
++/**
++ * wake_q_add() - queue a wakeup for 'later' waking.
++ * @head: the wake_q_head to add @task to
++ * @task: the task to queue for 'later' wakeup
++ *
++ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
++ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
++ * instantly.
++ *
++ * This function must be used as-if it were wake_up_process(); IOW the task
++ * must be ready to be woken at this location.
++ */
++void wake_q_add(struct wake_q_head *head, struct task_struct *task)
++{
++ if (__wake_q_add(head, task))
++ get_task_struct(task);
++}
++
++/**
++ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
++ * @head: the wake_q_head to add @task to
++ * @task: the task to queue for 'later' wakeup
++ *
++ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
++ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
++ * instantly.
++ *
++ * This function must be used as-if it were wake_up_process(); IOW the task
++ * must be ready to be woken at this location.
++ *
++ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
++ * that already hold reference to @task can call the 'safe' version and trust
++ * wake_q to do the right thing depending whether or not the @task is already
++ * queued for wakeup.
++ */
++void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
++{
++ if (!__wake_q_add(head, task))
++ put_task_struct(task);
++}
++
++void wake_up_q(struct wake_q_head *head)
++{
++ struct wake_q_node *node = head->first;
++
++ while (node != WAKE_Q_TAIL) {
++ struct task_struct *task;
++
++ task = container_of(node, struct task_struct, wake_q);
++ /* task can safely be re-inserted now: */
++ node = node->next;
++ task->wake_q.next = NULL;
++
++ /*
++ * wake_up_process() executes a full barrier, which pairs with
++ * the queueing in wake_q_add() so as not to miss wakeups.
++ */
++ wake_up_process(task);
++ put_task_struct(task);
++ }
++}
++
++/*
++ * resched_curr - mark rq's current task 'to be rescheduled now'.
++ *
++ * On UP this means the setting of the need_resched flag, on SMP it
++ * might also involve a cross-CPU call to trigger the scheduler on
++ * the target CPU.
++ */
++static inline void resched_curr(struct rq *rq)
++{
++ struct task_struct *curr = rq->curr;
++ int cpu;
++
++ lockdep_assert_held(&rq->lock);
++
++ if (test_tsk_need_resched(curr))
++ return;
++
++ cpu = cpu_of(rq);
++ if (cpu == smp_processor_id()) {
++ set_tsk_need_resched(curr);
++ set_preempt_need_resched();
++ return;
++ }
++
++ if (set_nr_and_not_polling(curr))
++ smp_send_reschedule(cpu);
++ else
++ trace_sched_wake_idle_without_ipi(cpu);
++}
++
++void resched_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ if (cpu_online(cpu) || cpu == smp_processor_id())
++ resched_curr(cpu_rq(cpu));
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++}
++
++#ifdef CONFIG_SMP
++#ifdef CONFIG_NO_HZ_COMMON
++/*
++ * This routine will record that the CPU is going idle with tick stopped.
++ * This info will be used in performing idle load balancing in the future.
++ */
++void nohz_balance_enter_idle(int cpu) {}
++
++/*
++ * In the semi idle case, use the nearest busy CPU for migrating timers
++ * from an idle CPU. This is good for power-savings.
++ *
++ * We don't do similar optimization for completely idle system, as
++ * selecting an idle CPU will add more delays to the timers than intended
++ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
++ */
++int get_nohz_timer_target(void)
++{
++ int i, cpu = smp_processor_id(), default_cpu = -1;
++ struct cpumask *mask;
++ const struct cpumask *hk_mask;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
++ if (!idle_cpu(cpu))
++ return cpu;
++ default_cpu = cpu;
++ }
++
++ hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
++
++ for (mask = per_cpu(sched_cpu_topo_masks, cpu);
++ mask < per_cpu(sched_cpu_topo_end_mask, cpu); mask++)
++ for_each_cpu_and(i, mask, hk_mask)
++ if (!idle_cpu(i))
++ return i;
++
++ if (default_cpu == -1)
++ default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
++ cpu = default_cpu;
++
++ return cpu;
++}
++
++/*
++ * When add_timer_on() enqueues a timer into the timer wheel of an
++ * idle CPU then this timer might expire before the next timer event
++ * which is scheduled to wake up that CPU. In case of a completely
++ * idle system the next event might even be infinite time into the
++ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
++ * leaves the inner idle loop so the newly added timer is taken into
++ * account when the CPU goes back to idle and evaluates the timer
++ * wheel for the next timer event.
++ */
++static inline void wake_up_idle_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (cpu == smp_processor_id())
++ return;
++
++ /*
++ * Set TIF_NEED_RESCHED and send an IPI if in the non-polling
++ * part of the idle loop. This forces an exit from the idle loop
++ * and a round trip to schedule(). Now this could be optimized
++ * because a simple new idle loop iteration is enough to
++ * re-evaluate the next tick. Provided some re-ordering of tick
++ * nohz functions that would need to follow TIF_NR_POLLING
++ * clearing:
++ *
++ * - On most archs, a simple fetch_or on ti::flags with a
++ * "0" value would be enough to know if an IPI needs to be sent.
++ *
++ * - x86 needs to perform a last need_resched() check between
++ * monitor and mwait which doesn't take timers into account.
++ * There a dedicated TIF_TIMER flag would be required to
++ * fetch_or here and be checked along with TIF_NEED_RESCHED
++ * before mwait().
++ *
++ * However, remote timer enqueue is not such a frequent event
++ * and testing of the above solutions didn't appear to report
++ * much benefits.
++ */
++ if (set_nr_and_not_polling(rq->idle))
++ smp_send_reschedule(cpu);
++ else
++ trace_sched_wake_idle_without_ipi(cpu);
++}
++
++static inline bool wake_up_full_nohz_cpu(int cpu)
++{
++ /*
++ * We just need the target to call irq_exit() and re-evaluate
++ * the next tick. The nohz full kick at least implies that.
++ * If needed we can still optimize that later with an
++ * empty IRQ.
++ */
++ if (cpu_is_offline(cpu))
++ return true; /* Don't try to wake offline CPUs. */
++ if (tick_nohz_full_cpu(cpu)) {
++ if (cpu != smp_processor_id() ||
++ tick_nohz_tick_stopped())
++ tick_nohz_full_kick_cpu(cpu);
++ return true;
++ }
++
++ return false;
++}
++
++void wake_up_nohz_cpu(int cpu)
++{
++ if (!wake_up_full_nohz_cpu(cpu))
++ wake_up_idle_cpu(cpu);
++}
++
++static void nohz_csd_func(void *info)
++{
++ struct rq *rq = info;
++ int cpu = cpu_of(rq);
++ unsigned int flags;
++
++ /*
++ * Release the rq::nohz_csd.
++ */
++ flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
++ WARN_ON(!(flags & NOHZ_KICK_MASK));
++
++ rq->idle_balance = idle_cpu(cpu);
++ if (rq->idle_balance && !need_resched()) {
++ rq->nohz_idle_balance = flags;
++ raise_softirq_irqoff(SCHED_SOFTIRQ);
++ }
++}
++
++#endif /* CONFIG_NO_HZ_COMMON */
++#endif /* CONFIG_SMP */
++
++static inline void wakeup_preempt(struct rq *rq)
++{
++ if (sched_rq_first_task(rq) != rq->curr)
++ resched_curr(rq);
++}
++
++static __always_inline
++int __task_state_match(struct task_struct *p, unsigned int state)
++{
++ if (READ_ONCE(p->__state) & state)
++ return 1;
++
++ if (READ_ONCE(p->saved_state) & state)
++ return -1;
++
++ return 0;
++}
++
++static __always_inline
++int task_state_match(struct task_struct *p, unsigned int state)
++{
++ /*
++ * Serialize against current_save_and_set_rtlock_wait_state(),
++ * current_restore_rtlock_saved_state(), and __refrigerator().
++ */
++ guard(raw_spinlock_irq)(&p->pi_lock);
++
++ return __task_state_match(p, state);
++}
++
++/*
++ * wait_task_inactive - wait for a thread to unschedule.
++ *
++ * Wait for the thread to block in any of the states set in @match_state.
++ * If it changes, i.e. @p might have woken up, then return zero. When we
++ * succeed in waiting for @p to be off its CPU, we return a positive number
++ * (its total switch count). If a second call a short while later returns the
++ * same number, the caller can be sure that @p has remained unscheduled the
++ * whole time.
++ *
++ * The caller must ensure that the task *will* unschedule sometime soon,
++ * else this function might spin for a *long* time. This function can't
++ * be called with interrupts off, or it may introduce deadlock with
++ * smp_call_function() if an IPI is sent by the same process we are
++ * waiting to become inactive.
++ */
++unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
++{
++ unsigned long flags;
++ int running, queued, match;
++ unsigned long ncsw;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ for (;;) {
++ rq = task_rq(p);
++
++ /*
++ * If the task is actively running on another CPU
++ * still, just relax and busy-wait without holding
++ * any locks.
++ *
++ * NOTE! Since we don't hold any locks, it's not
++ * even sure that "rq" stays as the right runqueue!
++ * But we don't care, since this will return false
++ * if the runqueue has changed and p is actually now
++ * running somewhere else!
++ */
++ while (task_on_cpu(p)) {
++ if (!task_state_match(p, match_state))
++ return 0;
++ cpu_relax();
++ }
++
++ /*
++ * Ok, time to look more closely! We need the rq
++ * lock now, to be *sure*. If we're wrong, we'll
++ * just go back and repeat.
++ */
++ task_access_lock_irqsave(p, &lock, &flags);
++ trace_sched_wait_task(p);
++ running = task_on_cpu(p);
++ queued = p->on_rq;
++ ncsw = 0;
++ if ((match = __task_state_match(p, match_state))) {
++ /*
++ * When matching on p->saved_state, consider this task
++ * still queued so it will wait.
++ */
++ if (match < 0)
++ queued = 1;
++ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
++ }
++ task_access_unlock_irqrestore(p, lock, &flags);
++
++ /*
++ * If it changed from the expected state, bail out now.
++ */
++ if (unlikely(!ncsw))
++ break;
++
++ /*
++ * Was it really running after all now that we
++ * checked with the proper locks actually held?
++ *
++ * Oops. Go back and try again..
++ */
++ if (unlikely(running)) {
++ cpu_relax();
++ continue;
++ }
++
++ /*
++ * It's not enough that it's not actively running,
++ * it must be off the runqueue _entirely_, and not
++ * preempted!
++ *
++ * So if it was still runnable (but just not actively
++ * running right now), it's preempted, and we should
++ * yield - it could be a while.
++ */
++ if (unlikely(queued)) {
++ ktime_t to = NSEC_PER_SEC / HZ;
++
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
++ continue;
++ }
++
++ /*
++ * Ahh, all good. It wasn't running, and it wasn't
++ * runnable, which means that it will never become
++ * running in the future either. We're all done!
++ */
++ break;
++ }
++
++ return ncsw;
++}
++
++#ifdef CONFIG_SCHED_HRTICK
++/*
++ * Use HR-timers to deliver accurate preemption points.
++ */
++
++static void hrtick_clear(struct rq *rq)
++{
++ if (hrtimer_active(&rq->hrtick_timer))
++ hrtimer_cancel(&rq->hrtick_timer);
++}
++
++/*
++ * High-resolution timer tick.
++ * Runs from hardirq context with interrupts disabled.
++ */
++static enum hrtimer_restart hrtick(struct hrtimer *timer)
++{
++ struct rq *rq = container_of(timer, struct rq, hrtick_timer);
++
++ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
++
++ raw_spin_lock(&rq->lock);
++ resched_curr(rq);
++ raw_spin_unlock(&rq->lock);
++
++ return HRTIMER_NORESTART;
++}
++
++/*
++ * Use hrtick when:
++ * - enabled by features
++ * - hrtimer is actually high res
++ */
++static inline int hrtick_enabled(struct rq *rq)
++{
++ /**
++ * Alt schedule FW doesn't support sched_feat yet
++ if (!sched_feat(HRTICK))
++ return 0;
++ */
++ if (!cpu_active(cpu_of(rq)))
++ return 0;
++ return hrtimer_is_hres_active(&rq->hrtick_timer);
++}
++
++#ifdef CONFIG_SMP
++
++static void __hrtick_restart(struct rq *rq)
++{
++ struct hrtimer *timer = &rq->hrtick_timer;
++ ktime_t time = rq->hrtick_time;
++
++ hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
++}
++
++/*
++ * called from hardirq (IPI) context
++ */
++static void __hrtick_start(void *arg)
++{
++ struct rq *rq = arg;
++
++ raw_spin_lock(&rq->lock);
++ __hrtick_restart(rq);
++ raw_spin_unlock(&rq->lock);
++}
++
++/*
++ * Called to set the hrtick timer state.
++ *
++ * called with rq->lock held and irqs disabled
++ */
++static inline void hrtick_start(struct rq *rq, u64 delay)
++{
++ struct hrtimer *timer = &rq->hrtick_timer;
++ s64 delta;
++
++ /*
++ * Don't schedule slices shorter than 10000ns, that just
++ * doesn't make sense and can cause timer DoS.
++ */
++ delta = max_t(s64, delay, 10000LL);
++
++ rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
++
++ if (rq == this_rq())
++ __hrtick_restart(rq);
++ else
++ smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
++}
++
++#else
++/*
++ * Called to set the hrtick timer state.
++ *
++ * called with rq->lock held and irqs disabled
++ */
++static inline void hrtick_start(struct rq *rq, u64 delay)
++{
++ /*
++ * Don't schedule slices shorter than 10000ns, that just
++ * doesn't make sense. Rely on vruntime for fairness.
++ */
++ delay = max_t(u64, delay, 10000LL);
++ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
++ HRTIMER_MODE_REL_PINNED_HARD);
++}
++#endif /* CONFIG_SMP */
++
++static void hrtick_rq_init(struct rq *rq)
++{
++#ifdef CONFIG_SMP
++ INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
++#endif
++
++ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
++ rq->hrtick_timer.function = hrtick;
++}
++#else /* CONFIG_SCHED_HRTICK */
++static inline int hrtick_enabled(struct rq *rq)
++{
++ return 0;
++}
++
++static inline void hrtick_clear(struct rq *rq)
++{
++}
++
++static inline void hrtick_rq_init(struct rq *rq)
++{
++}
++#endif /* CONFIG_SCHED_HRTICK */
++
++static inline int __normal_prio(int policy, int rt_prio, int static_prio)
++{
++ return rt_policy(policy) ? (MAX_RT_PRIO - 1 - rt_prio) : static_prio;
++}
++
++/*
++ * Calculate the expected normal priority: i.e. priority
++ * without taking RT-inheritance into account. Might be
++ * boosted by interactivity modifiers. Changes upon fork,
++ * setprio syscalls, and whenever the interactivity
++ * estimator recalculates.
++ */
++static inline int normal_prio(struct task_struct *p)
++{
++ return __normal_prio(p->policy, p->rt_priority, p->static_prio);
++}
++
++/*
++ * Calculate the current priority, i.e. the priority
++ * taken into account by the scheduler. This value might
++ * be boosted by RT tasks as it will be RT if the task got
++ * RT-boosted. If not then it returns p->normal_prio.
++ */
++static int effective_prio(struct task_struct *p)
++{
++ p->normal_prio = normal_prio(p);
++ /*
++ * If we are RT tasks or we were boosted to RT priority,
++ * keep the priority unchanged. Otherwise, update priority
++ * to the normal priority:
++ */
++ if (!rt_prio(p->prio))
++ return p->normal_prio;
++ return p->prio;
++}
++
++/*
++ * activate_task - move a task to the runqueue.
++ *
++ * Context: rq->lock
++ */
++static void activate_task(struct task_struct *p, struct rq *rq)
++{
++ enqueue_task(p, rq, ENQUEUE_WAKEUP);
++
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
++ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
++
++ /*
++ * If in_iowait is set, the code below may not trigger any cpufreq
++ * utilization updates, so do it here explicitly with the IOWAIT flag
++ * passed.
++ */
++ cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT * p->in_iowait);
++}
++
++/*
++ * deactivate_task - remove a task from the runqueue.
++ *
++ * Context: rq->lock
++ */
++static inline void deactivate_task(struct task_struct *p, struct rq *rq)
++{
++ WRITE_ONCE(p->on_rq, 0);
++ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
++
++ dequeue_task(p, rq, DEQUEUE_SLEEP);
++
++ cpufreq_update_util(rq, 0);
++}
++
++static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
++{
++#ifdef CONFIG_SMP
++ /*
++ * After ->cpu is set up to a new value, task_access_lock(p, ...) can be
++ * successfully executed on another CPU. We must ensure that updates of
++ * per-task data have been completed by this moment.
++ */
++ smp_wmb();
++
++ WRITE_ONCE(task_thread_info(p)->cpu, cpu);
++#endif
++}
++
++static inline bool is_migration_disabled(struct task_struct *p)
++{
++#ifdef CONFIG_SMP
++ return p->migration_disabled;
++#else
++ return false;
++#endif
++}
++
++#define SCA_CHECK 0x01
++#define SCA_USER 0x08
++
++#ifdef CONFIG_SMP
++
++void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
++{
++#ifdef CONFIG_SCHED_DEBUG
++ unsigned int state = READ_ONCE(p->__state);
++
++ /*
++ * We should never call set_task_cpu() on a blocked task,
++ * ttwu() will sort out the placement.
++ */
++ WARN_ON_ONCE(state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq);
++
++#ifdef CONFIG_LOCKDEP
++ /*
++ * The caller should hold either p->pi_lock or rq->lock, when changing
++ * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
++ *
++ * sched_move_task() holds both and thus holding either pins the cgroup,
++ * see task_group().
++ */
++ WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
++ lockdep_is_held(&task_rq(p)->lock)));
++#endif
++ /*
++ * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
++ */
++ WARN_ON_ONCE(!cpu_online(new_cpu));
++
++ WARN_ON_ONCE(is_migration_disabled(p));
++#endif
++ trace_sched_migrate_task(p, new_cpu);
++
++ if (task_cpu(p) != new_cpu)
++ {
++ rseq_migrate(p);
++ perf_event_task_migrate(p);
++ }
++
++ __set_task_cpu(p, new_cpu);
++}
++
++#define MDF_FORCE_ENABLED 0x80
++
++static void
++__do_set_cpus_ptr(struct task_struct *p, const struct cpumask *new_mask)
++{
++ /*
++ * This here violates the locking rules for affinity, since we're only
++ * supposed to change these variables while holding both rq->lock and
++ * p->pi_lock.
++ *
++ * HOWEVER, it magically works, because ttwu() is the only code that
++ * accesses these variables under p->pi_lock and only does so after
++ * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
++ * before finish_task().
++ *
++ * XXX do further audits, this smells like something putrid.
++ */
++ SCHED_WARN_ON(!p->on_cpu);
++ p->cpus_ptr = new_mask;
++}
++
++void migrate_disable(void)
++{
++ struct task_struct *p = current;
++ int cpu;
++
++ if (p->migration_disabled) {
++ p->migration_disabled++;
++ return;
++ }
++
++ guard(preempt)();
++ cpu = smp_processor_id();
++ if (cpumask_test_cpu(cpu, &p->cpus_mask)) {
++ cpu_rq(cpu)->nr_pinned++;
++ p->migration_disabled = 1;
++ p->migration_flags &= ~MDF_FORCE_ENABLED;
++
++ /*
++ * Violates locking rules! see comment in __do_set_cpus_ptr().
++ */
++ if (p->cpus_ptr == &p->cpus_mask)
++ __do_set_cpus_ptr(p, cpumask_of(cpu));
++ }
++}
++EXPORT_SYMBOL_GPL(migrate_disable);
++
++void migrate_enable(void)
++{
++ struct task_struct *p = current;
++
++ if (0 == p->migration_disabled)
++ return;
++
++ if (p->migration_disabled > 1) {
++ p->migration_disabled--;
++ return;
++ }
++
++ if (WARN_ON_ONCE(!p->migration_disabled))
++ return;
++
++ /*
++ * Ensure stop_task runs either before or after this, and that
++ * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
++ */
++ guard(preempt)();
++ /*
++ * Assumption: current should be running on allowed cpu
++ */
++ WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &p->cpus_mask));
++ if (p->cpus_ptr != &p->cpus_mask)
++ __do_set_cpus_ptr(p, &p->cpus_mask);
++ /*
++ * Mustn't clear migration_disabled() until cpus_ptr points back at the
++ * regular cpus_mask, otherwise things that race (eg.
++ * select_fallback_rq) get confused.
++ */
++ barrier();
++ p->migration_disabled = 0;
++ this_rq()->nr_pinned--;
++}
++EXPORT_SYMBOL_GPL(migrate_enable);
++
++static inline bool rq_has_pinned_tasks(struct rq *rq)
++{
++ return rq->nr_pinned;
++}
++
++/*
++ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
++ * __set_cpus_allowed_ptr() and select_fallback_rq().
++ */
++static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
++{
++ /* When not in the task's cpumask, no point in looking further. */
++ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
++ return false;
++
++ /* migrate_disabled() must be allowed to finish. */
++ if (is_migration_disabled(p))
++ return cpu_online(cpu);
++
++ /* Non kernel threads are not allowed during either online or offline. */
++ if (!(p->flags & PF_KTHREAD))
++ return cpu_active(cpu) && task_cpu_possible(cpu, p);
++
++ /* KTHREAD_IS_PER_CPU is always allowed. */
++ if (kthread_is_per_cpu(p))
++ return cpu_online(cpu);
++
++ /* Regular kernel threads don't get to stay during offline. */
++ if (cpu_dying(cpu))
++ return false;
++
++ /* But are allowed during online. */
++ return cpu_online(cpu);
++}
++
++/*
++ * This is how migration works:
++ *
++ * 1) we invoke migration_cpu_stop() on the target CPU using
++ * stop_one_cpu().
++ * 2) stopper starts to run (implicitly forcing the migrated thread
++ * off the CPU)
++ * 3) it checks whether the migrated task is still in the wrong runqueue.
++ * 4) if it's in the wrong runqueue then the migration thread removes
++ * it and puts it into the right queue.
++ * 5) stopper completes and stop_one_cpu() returns and the migration
++ * is done.
++ */
++
++/*
++ * move_queued_task - move a queued task to new rq.
++ *
++ * Returns (locked) new rq. Old rq's lock is released.
++ */
++static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
++{
++ int src_cpu;
++
++ lockdep_assert_held(&rq->lock);
++
++ src_cpu = cpu_of(rq);
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
++ dequeue_task(p, rq, 0);
++ set_task_cpu(p, new_cpu);
++ raw_spin_unlock(&rq->lock);
++
++ rq = cpu_rq(new_cpu);
++
++ raw_spin_lock(&rq->lock);
++ WARN_ON_ONCE(task_cpu(p) != new_cpu);
++
++ sched_mm_cid_migrate_to(rq, p, src_cpu);
++
++ sched_task_sanity_check(p, rq);
++ enqueue_task(p, rq, 0);
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
++ wakeup_preempt(rq);
++
++ return rq;
++}
++
++struct migration_arg {
++ struct task_struct *task;
++ int dest_cpu;
++};
++
++/*
++ * Move (not current) task off this CPU, onto the destination CPU. We're doing
++ * this because either it can't run here any more (set_cpus_allowed()
++ * away from this CPU, or CPU going down), or because we're
++ * attempting to rebalance this task on exec (sched_exec).
++ *
++ * So we race with normal scheduler movements, but that's OK, as long
++ * as the task is no longer on this CPU.
++ */
++static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
++{
++ /* Affinity changed (again). */
++ if (!is_cpu_allowed(p, dest_cpu))
++ return rq;
++
++ return move_queued_task(rq, p, dest_cpu);
++}
++
++/*
++ * migration_cpu_stop - this will be executed by a highprio stopper thread
++ * and performs thread migration by bumping thread off CPU then
++ * 'pushing' onto another runqueue.
++ */
++static int migration_cpu_stop(void *data)
++{
++ struct migration_arg *arg = data;
++ struct task_struct *p = arg->task;
++ struct rq *rq = this_rq();
++ unsigned long flags;
++
++ /*
++ * The original target CPU might have gone down and we might
++ * be on another CPU but it doesn't matter.
++ */
++ local_irq_save(flags);
++ /*
++ * We need to explicitly wake pending tasks before running
++ * __migrate_task() such that we will not miss enforcing cpus_ptr
++ * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
++ */
++ flush_smp_call_function_queue();
++
++ raw_spin_lock(&p->pi_lock);
++ raw_spin_lock(&rq->lock);
++ /*
++ * If task_rq(p) != rq, it cannot be migrated here, because we're
++ * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
++ * we're holding p->pi_lock.
++ */
++ if (task_rq(p) == rq && task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ rq = __migrate_task(rq, p, arg->dest_cpu);
++ }
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ return 0;
++}
++
++static inline void
++set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx)
++{
++ cpumask_copy(&p->cpus_mask, ctx->new_mask);
++ p->nr_cpus_allowed = cpumask_weight(ctx->new_mask);
++
++ /*
++ * Swap in a new user_cpus_ptr if SCA_USER flag set
++ */
++ if (ctx->flags & SCA_USER)
++ swap(p->user_cpus_ptr, ctx->user_mask);
++}
++
++static void
++__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
++{
++ lockdep_assert_held(&p->pi_lock);
++ set_cpus_allowed_common(p, ctx);
++}
++
++/*
++ * Used for kthread_bind() and select_fallback_rq(), in both cases the user
++ * affinity (if any) should be destroyed too.
++ */
++void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .user_mask = NULL,
++ .flags = SCA_USER, /* clear the user requested mask */
++ };
++ union cpumask_rcuhead {
++ cpumask_t cpumask;
++ struct rcu_head rcu;
++ };
++
++ __do_set_cpus_allowed(p, &ac);
++
++ /*
++ * Because this is called with p->pi_lock held, it is not possible
++ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
++ * kfree_rcu().
++ */
++ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
++}
++
++static cpumask_t *alloc_user_cpus_ptr(int node)
++{
++ /*
++ * See do_set_cpus_allowed() above for the rcu_head usage.
++ */
++ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
++
++ return kmalloc_node(size, GFP_KERNEL, node);
++}
++
++int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
++ int node)
++{
++ cpumask_t *user_mask;
++ unsigned long flags;
++
++ /*
++ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
++ * may differ by now due to racing.
++ */
++ dst->user_cpus_ptr = NULL;
++
++ /*
++ * This check is racy and losing the race is a valid situation.
++ * It is not worth the extra overhead of taking the pi_lock on
++ * every fork/clone.
++ */
++ if (data_race(!src->user_cpus_ptr))
++ return 0;
++
++ user_mask = alloc_user_cpus_ptr(node);
++ if (!user_mask)
++ return -ENOMEM;
++
++ /*
++ * Use pi_lock to protect content of user_cpus_ptr
++ *
++ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
++ * do_set_cpus_allowed().
++ */
++ raw_spin_lock_irqsave(&src->pi_lock, flags);
++ if (src->user_cpus_ptr) {
++ swap(dst->user_cpus_ptr, user_mask);
++ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
++ }
++ raw_spin_unlock_irqrestore(&src->pi_lock, flags);
++
++ if (unlikely(user_mask))
++ kfree(user_mask);
++
++ return 0;
++}
++
++static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
++{
++ struct cpumask *user_mask = NULL;
++
++ swap(p->user_cpus_ptr, user_mask);
++
++ return user_mask;
++}
++
++void release_user_cpus_ptr(struct task_struct *p)
++{
++ kfree(clear_user_cpus_ptr(p));
++}
++
++#endif
++
++/**
++ * task_curr - is this task currently executing on a CPU?
++ * @p: the task in question.
++ *
++ * Return: 1 if the task is currently executing. 0 otherwise.
++ */
++inline int task_curr(const struct task_struct *p)
++{
++ return cpu_curr(task_cpu(p)) == p;
++}
++
++#ifdef CONFIG_SMP
++/***
++ * kick_process - kick a running thread to enter/exit the kernel
++ * @p: the to-be-kicked thread
++ *
++ * Cause a process which is running on another CPU to enter
++ * kernel-mode, without any delay. (to get signals handled.)
++ *
++ * NOTE: this function doesn't have to take the runqueue lock,
++ * because all it wants to ensure is that the remote task enters
++ * the kernel. If the IPI races and the task has been migrated
++ * to another CPU then no harm is done and the purpose has been
++ * achieved as well.
++ */
++void kick_process(struct task_struct *p)
++{
++ guard(preempt)();
++ int cpu = task_cpu(p);
++
++ if ((cpu != smp_processor_id()) && task_curr(p))
++ smp_send_reschedule(cpu);
++}
++EXPORT_SYMBOL_GPL(kick_process);
++
++/*
++ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
++ *
++ * A few notes on cpu_active vs cpu_online:
++ *
++ * - cpu_active must be a subset of cpu_online
++ *
++ * - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
++ * see __set_cpus_allowed_ptr(). At this point the newly online
++ * CPU isn't yet part of the sched domains, and balancing will not
++ * see it.
++ *
++ * - on cpu-down we clear cpu_active() to mask the sched domains and
++ * avoid the load balancer to place new tasks on the to be removed
++ * CPU. Existing tasks will remain running there and will be taken
++ * off.
++ *
++ * This means that fallback selection must not select !active CPUs.
++ * And can assume that any active CPU must be online. Conversely
++ * select_task_rq() below may allow selection of !active CPUs in order
++ * to satisfy the above rules.
++ */
++static int select_fallback_rq(int cpu, struct task_struct *p)
++{
++ int nid = cpu_to_node(cpu);
++ const struct cpumask *nodemask = NULL;
++ enum { cpuset, possible, fail } state = cpuset;
++ int dest_cpu;
++
++ /*
++ * If the node that the CPU is on has been offlined, cpu_to_node()
++ * will return -1. There is no CPU on the node, and we should
++ * select the CPU on the other node.
++ */
++ if (nid != -1) {
++ nodemask = cpumask_of_node(nid);
++
++ /* Look for allowed, online CPU in same node. */
++ for_each_cpu(dest_cpu, nodemask) {
++ if (is_cpu_allowed(p, dest_cpu))
++ return dest_cpu;
++ }
++ }
++
++ for (;;) {
++ /* Any allowed, online CPU? */
++ for_each_cpu(dest_cpu, p->cpus_ptr) {
++ if (!is_cpu_allowed(p, dest_cpu))
++ continue;
++ goto out;
++ }
++
++ /* No more Mr. Nice Guy. */
++ switch (state) {
++ case cpuset:
++ if (cpuset_cpus_allowed_fallback(p)) {
++ state = possible;
++ break;
++ }
++ fallthrough;
++ case possible:
++ /*
++ * XXX When called from select_task_rq() we only
++ * hold p->pi_lock and again violate locking order.
++ *
++ * More yuck to audit.
++ */
++ do_set_cpus_allowed(p, task_cpu_possible_mask(p));
++ state = fail;
++ break;
++
++ case fail:
++ BUG();
++ break;
++ }
++ }
++
++out:
++ if (state != cpuset) {
++ /*
++ * Don't tell them about moving exiting tasks or
++ * kernel threads (both mm NULL), since they never
++ * leave kernel.
++ */
++ if (p->mm && printk_ratelimit()) {
++ printk_deferred("process %d (%s) no longer affine to cpu%d\n",
++ task_pid_nr(p), p->comm, cpu);
++ }
++ }
++
++ return dest_cpu;
++}
++
++static inline void
++sched_preempt_mask_flush(cpumask_t *mask, int prio, int ref)
++{
++ int cpu;
++
++ cpumask_copy(mask, sched_preempt_mask + ref);
++ if (prio < ref) {
++ for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) {
++ if (prio < cpu_rq(cpu)->prio)
++ cpumask_set_cpu(cpu, mask);
++ }
++ } else {
++ for_each_cpu_andnot(cpu, mask, sched_idle_mask) {
++ if (prio >= cpu_rq(cpu)->prio)
++ cpumask_clear_cpu(cpu, mask);
++ }
++ }
++}
++
++static inline int
++preempt_mask_check(cpumask_t *preempt_mask, cpumask_t *allow_mask, int prio)
++{
++ cpumask_t *mask = sched_preempt_mask + prio;
++ int pr = atomic_read(&sched_prio_record);
++
++ if (pr != prio && SCHED_QUEUE_BITS - 1 != prio) {
++ sched_preempt_mask_flush(mask, prio, pr);
++ atomic_set(&sched_prio_record, prio);
++ }
++
++ return cpumask_and(preempt_mask, allow_mask, mask);
++}
++
++static inline int select_task_rq(struct task_struct *p)
++{
++ cpumask_t allow_mask, mask;
++
++ if (unlikely(!cpumask_and(&allow_mask, p->cpus_ptr, cpu_active_mask)))
++ return select_fallback_rq(task_cpu(p), p);
++
++ if (
++#ifdef CONFIG_SCHED_SMT
++ cpumask_and(&mask, &allow_mask, sched_sg_idle_mask) ||
++#endif
++ cpumask_and(&mask, &allow_mask, sched_idle_mask) ||
++ preempt_mask_check(&mask, &allow_mask, task_sched_prio(p)))
++ return best_mask_cpu(task_cpu(p), &mask);
++
++ return best_mask_cpu(task_cpu(p), &allow_mask);
++}
++
++void sched_set_stop_task(int cpu, struct task_struct *stop)
++{
++ static struct lock_class_key stop_pi_lock;
++ struct sched_param stop_param = { .sched_priority = STOP_PRIO };
++ struct sched_param start_param = { .sched_priority = 0 };
++ struct task_struct *old_stop = cpu_rq(cpu)->stop;
++
++ if (stop) {
++ /*
++ * Make it appear like a SCHED_FIFO task, its something
++ * userspace knows about and won't get confused about.
++ *
++ * Also, it will make PI more or less work without too
++ * much confusion -- but then, stop work should not
++ * rely on PI working anyway.
++ */
++ sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param);
++
++ /*
++ * The PI code calls rt_mutex_setprio() with ->pi_lock held to
++ * adjust the effective priority of a task. As a result,
++ * rt_mutex_setprio() can trigger (RT) balancing operations,
++ * which can then trigger wakeups of the stop thread to push
++ * around the current task.
++ *
++ * The stop task itself will never be part of the PI-chain, it
++ * never blocks, therefore that ->pi_lock recursion is safe.
++ * Tell lockdep about this by placing the stop->pi_lock in its
++ * own class.
++ */
++ lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
++ }
++
++ cpu_rq(cpu)->stop = stop;
++
++ if (old_stop) {
++ /*
++ * Reset it back to a normal scheduling policy so that
++ * it can die in pieces.
++ */
++ sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param);
++ }
++}
++
++static int affine_move_task(struct rq *rq, struct task_struct *p, int dest_cpu,
++ raw_spinlock_t *lock, unsigned long irq_flags)
++ __releases(rq->lock)
++ __releases(p->pi_lock)
++{
++ /* Can the task run on the task's current CPU? If so, we're done */
++ if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
++ if (p->migration_disabled) {
++ if (likely(p->cpus_ptr != &p->cpus_mask))
++ __do_set_cpus_ptr(p, &p->cpus_mask);
++ p->migration_disabled = 0;
++ p->migration_flags |= MDF_FORCE_ENABLED;
++ /* When p is migrate_disabled, rq->lock should be held */
++ rq->nr_pinned--;
++ }
++
++ if (task_on_cpu(p) || READ_ONCE(p->__state) == TASK_WAKING) {
++ struct migration_arg arg = { p, dest_cpu };
++
++ /* Need help from migration thread: drop lock and wait. */
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
++ return 0;
++ }
++ if (task_on_rq_queued(p)) {
++ /*
++ * OK, since we're going to drop the lock immediately
++ * afterwards anyway.
++ */
++ update_rq_clock(rq);
++ rq = move_queued_task(rq, p, dest_cpu);
++ lock = &rq->lock;
++ }
++ }
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ return 0;
++}
++
++static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
++ struct affinity_context *ctx,
++ struct rq *rq,
++ raw_spinlock_t *lock,
++ unsigned long irq_flags)
++{
++ const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
++ const struct cpumask *cpu_valid_mask = cpu_active_mask;
++ bool kthread = p->flags & PF_KTHREAD;
++ int dest_cpu;
++ int ret = 0;
++
++ if (kthread || is_migration_disabled(p)) {
++ /*
++ * Kernel threads are allowed on online && !active CPUs,
++ * however, during cpu-hot-unplug, even these might get pushed
++ * away if not KTHREAD_IS_PER_CPU.
++ *
++ * Specifically, migration_disabled() tasks must not fail the
++ * cpumask_any_and_distribute() pick below, esp. so on
++ * SCA_MIGRATE_ENABLE, otherwise we'll not call
++ * set_cpus_allowed_common() and actually reset p->cpus_ptr.
++ */
++ cpu_valid_mask = cpu_online_mask;
++ }
++
++ if (!kthread && !cpumask_subset(ctx->new_mask, cpu_allowed_mask)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ /*
++ * Must re-check here, to close a race against __kthread_bind(),
++ * sched_setaffinity() is not guaranteed to observe the flag.
++ */
++ if ((ctx->flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
++ goto out;
++
++ dest_cpu = cpumask_any_and(cpu_valid_mask, ctx->new_mask);
++ if (dest_cpu >= nr_cpu_ids) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ __do_set_cpus_allowed(p, ctx);
++
++ return affine_move_task(rq, p, dest_cpu, lock, irq_flags);
++
++out:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++
++ return ret;
++}
++
++/*
++ * Change a given task's CPU affinity. Migrate the thread to a
++ * is removed from the allowed bitmask.
++ *
++ * NOTE: the caller must have a valid reference to the task, the
++ * task must not exit() & deallocate itself prematurely. The
++ * call is not atomic; no spinlocks may be held.
++ */
++static int __set_cpus_allowed_ptr(struct task_struct *p,
++ struct affinity_context *ctx)
++{
++ unsigned long irq_flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
++ rq = __task_access_lock(p, &lock);
++ /*
++ * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
++ * flags are set.
++ */
++ if (p->user_cpus_ptr &&
++ !(ctx->flags & SCA_USER) &&
++ cpumask_and(rq->scratch_mask, ctx->new_mask, p->user_cpus_ptr))
++ ctx->new_mask = rq->scratch_mask;
++
++
++ return __set_cpus_allowed_ptr_locked(p, ctx, rq, lock, irq_flags);
++}
++
++int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .flags = 0,
++ };
++
++ return __set_cpus_allowed_ptr(p, &ac);
++}
++EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
++
++/*
++ * Change a given task's CPU affinity to the intersection of its current
++ * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
++ * If user_cpus_ptr is defined, use it as the basis for restricting CPU
++ * affinity or use cpu_online_mask instead.
++ *
++ * If the resulting mask is empty, leave the affinity unchanged and return
++ * -EINVAL.
++ */
++static int restrict_cpus_allowed_ptr(struct task_struct *p,
++ struct cpumask *new_mask,
++ const struct cpumask *subset_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .flags = 0,
++ };
++ unsigned long irq_flags;
++ raw_spinlock_t *lock;
++ struct rq *rq;
++ int err;
++
++ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
++ rq = __task_access_lock(p, &lock);
++
++ if (!cpumask_and(new_mask, task_user_cpus(p), subset_mask)) {
++ err = -EINVAL;
++ goto err_unlock;
++ }
++
++ return __set_cpus_allowed_ptr_locked(p, &ac, rq, lock, irq_flags);
++
++err_unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ return err;
++}
++
++/*
++ * Restrict the CPU affinity of task @p so that it is a subset of
++ * task_cpu_possible_mask() and point @p->user_cpus_ptr to a copy of the
++ * old affinity mask. If the resulting mask is empty, we warn and walk
++ * up the cpuset hierarchy until we find a suitable mask.
++ */
++void force_compatible_cpus_allowed_ptr(struct task_struct *p)
++{
++ cpumask_var_t new_mask;
++ const struct cpumask *override_mask = task_cpu_possible_mask(p);
++
++ alloc_cpumask_var(&new_mask, GFP_KERNEL);
++
++ /*
++ * __migrate_task() can fail silently in the face of concurrent
++ * offlining of the chosen destination CPU, so take the hotplug
++ * lock to ensure that the migration succeeds.
++ */
++ cpus_read_lock();
++ if (!cpumask_available(new_mask))
++ goto out_set_mask;
++
++ if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
++ goto out_free_mask;
++
++ /*
++ * We failed to find a valid subset of the affinity mask for the
++ * task, so override it based on its cpuset hierarchy.
++ */
++ cpuset_cpus_allowed(p, new_mask);
++ override_mask = new_mask;
++
++out_set_mask:
++ if (printk_ratelimit()) {
++ printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
++ task_pid_nr(p), p->comm,
++ cpumask_pr_args(override_mask));
++ }
++
++ WARN_ON(set_cpus_allowed_ptr(p, override_mask));
++out_free_mask:
++ cpus_read_unlock();
++ free_cpumask_var(new_mask);
++}
++
++static int
++__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
++
++/*
++ * Restore the affinity of a task @p which was previously restricted by a
++ * call to force_compatible_cpus_allowed_ptr().
++ *
++ * It is the caller's responsibility to serialise this with any calls to
++ * force_compatible_cpus_allowed_ptr(@p).
++ */
++void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
++{
++ struct affinity_context ac = {
++ .new_mask = task_user_cpus(p),
++ .flags = 0,
++ };
++ int ret;
++
++ /*
++ * Try to restore the old affinity mask with __sched_setaffinity().
++ * Cpuset masking will be done there too.
++ */
++ ret = __sched_setaffinity(p, &ac);
++ WARN_ON_ONCE(ret);
++}
++
++#else /* CONFIG_SMP */
++
++static inline int select_task_rq(struct task_struct *p)
++{
++ return 0;
++}
++
++static inline int
++__set_cpus_allowed_ptr(struct task_struct *p,
++ struct affinity_context *ctx)
++{
++ return set_cpus_allowed_ptr(p, ctx->new_mask);
++}
++
++static inline bool rq_has_pinned_tasks(struct rq *rq)
++{
++ return false;
++}
++
++static inline cpumask_t *alloc_user_cpus_ptr(int node)
++{
++ return NULL;
++}
++
++#endif /* !CONFIG_SMP */
++
++static void
++ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq;
++
++ if (!schedstat_enabled())
++ return;
++
++ rq = this_rq();
++
++#ifdef CONFIG_SMP
++ if (cpu == rq->cpu) {
++ __schedstat_inc(rq->ttwu_local);
++ __schedstat_inc(p->stats.nr_wakeups_local);
++ } else {
++ /** Alt schedule FW ToDo:
++ * How to do ttwu_wake_remote
++ */
++ }
++#endif /* CONFIG_SMP */
++
++ __schedstat_inc(rq->ttwu_count);
++ __schedstat_inc(p->stats.nr_wakeups);
++}
++
++/*
++ * Mark the task runnable.
++ */
++static inline void ttwu_do_wakeup(struct task_struct *p)
++{
++ WRITE_ONCE(p->__state, TASK_RUNNING);
++ trace_sched_wakeup(p);
++}
++
++static inline void
++ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
++{
++ if (p->sched_contributes_to_load)
++ rq->nr_uninterruptible--;
++
++ if (
++#ifdef CONFIG_SMP
++ !(wake_flags & WF_MIGRATED) &&
++#endif
++ p->in_iowait) {
++ delayacct_blkio_end(p);
++ atomic_dec(&task_rq(p)->nr_iowait);
++ }
++
++ activate_task(p, rq);
++ wakeup_preempt(rq);
++
++ ttwu_do_wakeup(p);
++}
++
++/*
++ * Consider @p being inside a wait loop:
++ *
++ * for (;;) {
++ * set_current_state(TASK_UNINTERRUPTIBLE);
++ *
++ * if (CONDITION)
++ * break;
++ *
++ * schedule();
++ * }
++ * __set_current_state(TASK_RUNNING);
++ *
++ * between set_current_state() and schedule(). In this case @p is still
++ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
++ * an atomic manner.
++ *
++ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
++ * then schedule() must still happen and p->state can be changed to
++ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
++ * need to do a full wakeup with enqueue.
++ *
++ * Returns: %true when the wakeup is done,
++ * %false otherwise.
++ */
++static int ttwu_runnable(struct task_struct *p, int wake_flags)
++{
++ struct rq *rq;
++ raw_spinlock_t *lock;
++ int ret = 0;
++
++ rq = __task_access_lock(p, &lock);
++ if (task_on_rq_queued(p)) {
++ if (!task_on_cpu(p)) {
++ /*
++ * When on_rq && !on_cpu the task is preempted, see if
++ * it should preempt the task that is current now.
++ */
++ update_rq_clock(rq);
++ wakeup_preempt(rq);
++ }
++ ttwu_do_wakeup(p);
++ ret = 1;
++ }
++ __task_access_unlock(p, lock);
++
++ return ret;
++}
++
++#ifdef CONFIG_SMP
++void sched_ttwu_pending(void *arg)
++{
++ struct llist_node *llist = arg;
++ struct rq *rq = this_rq();
++ struct task_struct *p, *t;
++ struct rq_flags rf;
++
++ if (!llist)
++ return;
++
++ rq_lock_irqsave(rq, &rf);
++ update_rq_clock(rq);
++
++ llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
++ if (WARN_ON_ONCE(p->on_cpu))
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++
++ if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
++ set_task_cpu(p, cpu_of(rq));
++
++ ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0);
++ }
++
++ /*
++ * Must be after enqueueing at least once task such that
++ * idle_cpu() does not observe a false-negative -- if it does,
++ * it is possible for select_idle_siblings() to stack a number
++ * of tasks on this CPU during that window.
++ *
++ * It is ok to clear ttwu_pending when another task pending.
++ * We will receive IPI after local irq enabled and then enqueue it.
++ * Since now nr_running > 0, idle_cpu() will always get correct result.
++ */
++ WRITE_ONCE(rq->ttwu_pending, 0);
++ rq_unlock_irqrestore(rq, &rf);
++}
++
++/*
++ * Prepare the scene for sending an IPI for a remote smp_call
++ *
++ * Returns true if the caller can proceed with sending the IPI.
++ * Returns false otherwise.
++ */
++bool call_function_single_prep_ipi(int cpu)
++{
++ if (set_nr_if_polling(cpu_rq(cpu)->idle)) {
++ trace_sched_wake_idle_without_ipi(cpu);
++ return false;
++ }
++
++ return true;
++}
++
++/*
++ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
++ * necessary. The wakee CPU on receipt of the IPI will queue the task
++ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
++ * of the wakeup instead of the waker.
++ */
++static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
++
++ WRITE_ONCE(rq->ttwu_pending, 1);
++ __smp_call_single_queue(cpu, &p->wake_entry.llist);
++}
++
++static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
++{
++ /*
++ * Do not complicate things with the async wake_list while the CPU is
++ * in hotplug state.
++ */
++ if (!cpu_active(cpu))
++ return false;
++
++ /* Ensure the task will still be allowed to run on the CPU. */
++ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
++ return false;
++
++ /*
++ * If the CPU does not share cache, then queue the task on the
++ * remote rqs wakelist to avoid accessing remote data.
++ */
++ if (!cpus_share_cache(smp_processor_id(), cpu))
++ return true;
++
++ if (cpu == smp_processor_id())
++ return false;
++
++ /*
++ * If the wakee cpu is idle, or the task is descheduling and the
++ * only running task on the CPU, then use the wakelist to offload
++ * the task activation to the idle (or soon-to-be-idle) CPU as
++ * the current CPU is likely busy. nr_running is checked to
++ * avoid unnecessary task stacking.
++ *
++ * Note that we can only get here with (wakee) p->on_rq=0,
++ * p->on_cpu can be whatever, we've done the dequeue, so
++ * the wakee has been accounted out of ->nr_running.
++ */
++ if (!cpu_rq(cpu)->nr_running)
++ return true;
++
++ return false;
++}
++
++static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ if (__is_defined(ALT_SCHED_TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
++ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
++ __ttwu_queue_wakelist(p, cpu, wake_flags);
++ return true;
++ }
++
++ return false;
++}
++
++void wake_up_if_idle(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ guard(rcu)();
++ if (is_idle_task(rcu_dereference(rq->curr))) {
++ guard(raw_spinlock_irqsave)(&rq->lock);
++ if (is_idle_task(rq->curr))
++ resched_curr(rq);
++ }
++}
++
++extern struct static_key_false sched_asym_cpucapacity;
++
++static __always_inline bool sched_asym_cpucap_active(void)
++{
++ return static_branch_unlikely(&sched_asym_cpucapacity);
++}
++
++bool cpus_equal_capacity(int this_cpu, int that_cpu)
++{
++ if (!sched_asym_cpucap_active())
++ return true;
++
++ if (this_cpu == that_cpu)
++ return true;
++
++ return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu);
++}
++
++bool cpus_share_cache(int this_cpu, int that_cpu)
++{
++ if (this_cpu == that_cpu)
++ return true;
++
++ return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
++}
++#else /* !CONFIG_SMP */
++
++static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ return false;
++}
++
++#endif /* CONFIG_SMP */
++
++static inline void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (ttwu_queue_wakelist(p, cpu, wake_flags))
++ return;
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++ ttwu_do_activate(rq, p, wake_flags);
++ raw_spin_unlock(&rq->lock);
++}
++
++/*
++ * Invoked from try_to_wake_up() to check whether the task can be woken up.
++ *
++ * The caller holds p::pi_lock if p != current or has preemption
++ * disabled when p == current.
++ *
++ * The rules of saved_state:
++ *
++ * The related locking code always holds p::pi_lock when updating
++ * p::saved_state, which means the code is fully serialized in both cases.
++ *
++ * For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
++ * No other bits set. This allows to distinguish all wakeup scenarios.
++ *
++ * For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
++ * allows us to prevent early wakeup of tasks before they can be run on
++ * asymmetric ISA architectures (eg ARMv9).
++ */
++static __always_inline
++bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
++{
++ int match;
++
++ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
++ WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
++ state != TASK_RTLOCK_WAIT);
++ }
++
++ *success = !!(match = __task_state_match(p, state));
++
++ /*
++ * Saved state preserves the task state across blocking on
++ * an RT lock or TASK_FREEZABLE tasks. If the state matches,
++ * set p::saved_state to TASK_RUNNING, but do not wake the task
++ * because it waits for a lock wakeup or __thaw_task(). Also
++ * indicate success because from the regular waker's point of
++ * view this has succeeded.
++ *
++ * After acquiring the lock the task will restore p::__state
++ * from p::saved_state which ensures that the regular
++ * wakeup is not lost. The restore will also set
++ * p::saved_state to TASK_RUNNING so any further tests will
++ * not result in false positives vs. @success
++ */
++ if (match < 0)
++ p->saved_state = TASK_RUNNING;
++
++ return match > 0;
++}
++
++/*
++ * Notes on Program-Order guarantees on SMP systems.
++ *
++ * MIGRATION
++ *
++ * The basic program-order guarantee on SMP systems is that when a task [t]
++ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
++ * execution on its new CPU [c1].
++ *
++ * For migration (of runnable tasks) this is provided by the following means:
++ *
++ * A) UNLOCK of the rq(c0)->lock scheduling out task t
++ * B) migration for t is required to synchronize *both* rq(c0)->lock and
++ * rq(c1)->lock (if not at the same time, then in that order).
++ * C) LOCK of the rq(c1)->lock scheduling in task
++ *
++ * Transitivity guarantees that B happens after A and C after B.
++ * Note: we only require RCpc transitivity.
++ * Note: the CPU doing B need not be c0 or c1
++ *
++ * Example:
++ *
++ * CPU0 CPU1 CPU2
++ *
++ * LOCK rq(0)->lock
++ * sched-out X
++ * sched-in Y
++ * UNLOCK rq(0)->lock
++ *
++ * LOCK rq(0)->lock // orders against CPU0
++ * dequeue X
++ * UNLOCK rq(0)->lock
++ *
++ * LOCK rq(1)->lock
++ * enqueue X
++ * UNLOCK rq(1)->lock
++ *
++ * LOCK rq(1)->lock // orders against CPU2
++ * sched-out Z
++ * sched-in X
++ * UNLOCK rq(1)->lock
++ *
++ *
++ * BLOCKING -- aka. SLEEP + WAKEUP
++ *
++ * For blocking we (obviously) need to provide the same guarantee as for
++ * migration. However the means are completely different as there is no lock
++ * chain to provide order. Instead we do:
++ *
++ * 1) smp_store_release(X->on_cpu, 0) -- finish_task()
++ * 2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
++ *
++ * Example:
++ *
++ * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule)
++ *
++ * LOCK rq(0)->lock LOCK X->pi_lock
++ * dequeue X
++ * sched-out X
++ * smp_store_release(X->on_cpu, 0);
++ *
++ * smp_cond_load_acquire(&X->on_cpu, !VAL);
++ * X->state = WAKING
++ * set_task_cpu(X,2)
++ *
++ * LOCK rq(2)->lock
++ * enqueue X
++ * X->state = RUNNING
++ * UNLOCK rq(2)->lock
++ *
++ * LOCK rq(2)->lock // orders against CPU1
++ * sched-out Z
++ * sched-in X
++ * UNLOCK rq(2)->lock
++ *
++ * UNLOCK X->pi_lock
++ * UNLOCK rq(0)->lock
++ *
++ *
++ * However; for wakeups there is a second guarantee we must provide, namely we
++ * must observe the state that lead to our wakeup. That is, not only must our
++ * task observe its own prior state, it must also observe the stores prior to
++ * its wakeup.
++ *
++ * This means that any means of doing remote wakeups must order the CPU doing
++ * the wakeup against the CPU the task is going to end up running on. This,
++ * however, is already required for the regular Program-Order guarantee above,
++ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
++ *
++ */
++
++/**
++ * try_to_wake_up - wake up a thread
++ * @p: the thread to be awakened
++ * @state: the mask of task states that can be woken
++ * @wake_flags: wake modifier flags (WF_*)
++ *
++ * Conceptually does:
++ *
++ * If (@state & @p->state) @p->state = TASK_RUNNING.
++ *
++ * If the task was not queued/runnable, also place it back on a runqueue.
++ *
++ * This function is atomic against schedule() which would dequeue the task.
++ *
++ * It issues a full memory barrier before accessing @p->state, see the comment
++ * with set_current_state().
++ *
++ * Uses p->pi_lock to serialize against concurrent wake-ups.
++ *
++ * Relies on p->pi_lock stabilizing:
++ * - p->sched_class
++ * - p->cpus_ptr
++ * - p->sched_task_group
++ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
++ *
++ * Tries really hard to only take one task_rq(p)->lock for performance.
++ * Takes rq->lock in:
++ * - ttwu_runnable() -- old rq, unavoidable, see comment there;
++ * - ttwu_queue() -- new rq, for enqueue of the task;
++ * - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
++ *
++ * As a consequence we race really badly with just about everything. See the
++ * many memory barriers and their comments for details.
++ *
++ * Return: %true if @p->state changes (an actual wakeup was done),
++ * %false otherwise.
++ */
++int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
++{
++ guard(preempt)();
++ int cpu, success = 0;
++
++ if (p == current) {
++ /*
++ * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
++ * == smp_processor_id()'. Together this means we can special
++ * case the whole 'p->on_rq && ttwu_runnable()' case below
++ * without taking any locks.
++ *
++ * In particular:
++ * - we rely on Program-Order guarantees for all the ordering,
++ * - we're serialized against set_special_state() by virtue of
++ * it disabling IRQs (this allows not taking ->pi_lock).
++ */
++ if (!ttwu_state_match(p, state, &success))
++ goto out;
++
++ trace_sched_waking(p);
++ ttwu_do_wakeup(p);
++ goto out;
++ }
++
++ /*
++ * If we are going to wake up a thread waiting for CONDITION we
++ * need to ensure that CONDITION=1 done by the caller can not be
++ * reordered with p->state check below. This pairs with smp_store_mb()
++ * in set_current_state() that the waiting thread does.
++ */
++ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
++ smp_mb__after_spinlock();
++ if (!ttwu_state_match(p, state, &success))
++ break;
++
++ trace_sched_waking(p);
++
++ /*
++ * Ensure we load p->on_rq _after_ p->state, otherwise it would
++ * be possible to, falsely, observe p->on_rq == 0 and get stuck
++ * in smp_cond_load_acquire() below.
++ *
++ * sched_ttwu_pending() try_to_wake_up()
++ * STORE p->on_rq = 1 LOAD p->state
++ * UNLOCK rq->lock
++ *
++ * __schedule() (switch to task 'p')
++ * LOCK rq->lock smp_rmb();
++ * smp_mb__after_spinlock();
++ * UNLOCK rq->lock
++ *
++ * [task p]
++ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
++ *
++ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
++ * __schedule(). See the comment for smp_mb__after_spinlock().
++ *
++ * A similar smp_rmb() lives in __task_needs_rq_lock().
++ */
++ smp_rmb();
++ if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
++ break;
++
++#ifdef CONFIG_SMP
++ /*
++ * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
++ * possible to, falsely, observe p->on_cpu == 0.
++ *
++ * One must be running (->on_cpu == 1) in order to remove oneself
++ * from the runqueue.
++ *
++ * __schedule() (switch to task 'p') try_to_wake_up()
++ * STORE p->on_cpu = 1 LOAD p->on_rq
++ * UNLOCK rq->lock
++ *
++ * __schedule() (put 'p' to sleep)
++ * LOCK rq->lock smp_rmb();
++ * smp_mb__after_spinlock();
++ * STORE p->on_rq = 0 LOAD p->on_cpu
++ *
++ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
++ * __schedule(). See the comment for smp_mb__after_spinlock().
++ *
++ * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
++ * schedule()'s deactivate_task() has 'happened' and p will no longer
++ * care about it's own p->state. See the comment in __schedule().
++ */
++ smp_acquire__after_ctrl_dep();
++
++ /*
++ * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
++ * == 0), which means we need to do an enqueue, change p->state to
++ * TASK_WAKING such that we can unlock p->pi_lock before doing the
++ * enqueue, such as ttwu_queue_wakelist().
++ */
++ WRITE_ONCE(p->__state, TASK_WAKING);
++
++ /*
++ * If the owning (remote) CPU is still in the middle of schedule() with
++ * this task as prev, considering queueing p on the remote CPUs wake_list
++ * which potentially sends an IPI instead of spinning on p->on_cpu to
++ * let the waker make forward progress. This is safe because IRQs are
++ * disabled and the IPI will deliver after on_cpu is cleared.
++ *
++ * Ensure we load task_cpu(p) after p->on_cpu:
++ *
++ * set_task_cpu(p, cpu);
++ * STORE p->cpu = @cpu
++ * __schedule() (switch to task 'p')
++ * LOCK rq->lock
++ * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
++ * STORE p->on_cpu = 1 LOAD p->cpu
++ *
++ * to ensure we observe the correct CPU on which the task is currently
++ * scheduling.
++ */
++ if (smp_load_acquire(&p->on_cpu) &&
++ ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
++ break;
++
++ /*
++ * If the owning (remote) CPU is still in the middle of schedule() with
++ * this task as prev, wait until it's done referencing the task.
++ *
++ * Pairs with the smp_store_release() in finish_task().
++ *
++ * This ensures that tasks getting woken will be fully ordered against
++ * their previous state and preserve Program Order.
++ */
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++
++ sched_task_ttwu(p);
++
++ if ((wake_flags & WF_CURRENT_CPU) &&
++ cpumask_test_cpu(smp_processor_id(), p->cpus_ptr))
++ cpu = smp_processor_id();
++ else
++ cpu = select_task_rq(p);
++
++ if (cpu != task_cpu(p)) {
++ if (p->in_iowait) {
++ delayacct_blkio_end(p);
++ atomic_dec(&task_rq(p)->nr_iowait);
++ }
++
++ wake_flags |= WF_MIGRATED;
++ set_task_cpu(p, cpu);
++ }
++#else
++ sched_task_ttwu(p);
++
++ cpu = task_cpu(p);
++#endif /* CONFIG_SMP */
++
++ ttwu_queue(p, cpu, wake_flags);
++ }
++out:
++ if (success)
++ ttwu_stat(p, task_cpu(p), wake_flags);
++
++ return success;
++}
++
++static bool __task_needs_rq_lock(struct task_struct *p)
++{
++ unsigned int state = READ_ONCE(p->__state);
++
++ /*
++ * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
++ * the task is blocked. Make sure to check @state since ttwu() can drop
++ * locks at the end, see ttwu_queue_wakelist().
++ */
++ if (state == TASK_RUNNING || state == TASK_WAKING)
++ return true;
++
++ /*
++ * Ensure we load p->on_rq after p->__state, otherwise it would be
++ * possible to, falsely, observe p->on_rq == 0.
++ *
++ * See try_to_wake_up() for a longer comment.
++ */
++ smp_rmb();
++ if (p->on_rq)
++ return true;
++
++#ifdef CONFIG_SMP
++ /*
++ * Ensure the task has finished __schedule() and will not be referenced
++ * anymore. Again, see try_to_wake_up() for a longer comment.
++ */
++ smp_rmb();
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++#endif
++
++ return false;
++}
++
++/**
++ * task_call_func - Invoke a function on task in fixed state
++ * @p: Process for which the function is to be invoked, can be @current.
++ * @func: Function to invoke.
++ * @arg: Argument to function.
++ *
++ * Fix the task in it's current state by avoiding wakeups and or rq operations
++ * and call @func(@arg) on it. This function can use ->on_rq and task_curr()
++ * to work out what the state is, if required. Given that @func can be invoked
++ * with a runqueue lock held, it had better be quite lightweight.
++ *
++ * Returns:
++ * Whatever @func returns
++ */
++int task_call_func(struct task_struct *p, task_call_f func, void *arg)
++{
++ struct rq *rq = NULL;
++ struct rq_flags rf;
++ int ret;
++
++ raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
++
++ if (__task_needs_rq_lock(p))
++ rq = __task_rq_lock(p, &rf);
++
++ /*
++ * At this point the task is pinned; either:
++ * - blocked and we're holding off wakeups (pi->lock)
++ * - woken, and we're holding off enqueue (rq->lock)
++ * - queued, and we're holding off schedule (rq->lock)
++ * - running, and we're holding off de-schedule (rq->lock)
++ *
++ * The called function (@func) can use: task_curr(), p->on_rq and
++ * p->__state to differentiate between these states.
++ */
++ ret = func(p, arg);
++
++ if (rq)
++ __task_rq_unlock(rq, &rf);
++
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
++ return ret;
++}
++
++/**
++ * cpu_curr_snapshot - Return a snapshot of the currently running task
++ * @cpu: The CPU on which to snapshot the task.
++ *
++ * Returns the task_struct pointer of the task "currently" running on
++ * the specified CPU. If the same task is running on that CPU throughout,
++ * the return value will be a pointer to that task's task_struct structure.
++ * If the CPU did any context switches even vaguely concurrently with the
++ * execution of this function, the return value will be a pointer to the
++ * task_struct structure of a randomly chosen task that was running on
++ * that CPU somewhere around the time that this function was executing.
++ *
++ * If the specified CPU was offline, the return value is whatever it
++ * is, perhaps a pointer to the task_struct structure of that CPU's idle
++ * task, but there is no guarantee. Callers wishing a useful return
++ * value must take some action to ensure that the specified CPU remains
++ * online throughout.
++ *
++ * This function executes full memory barriers before and after fetching
++ * the pointer, which permits the caller to confine this function's fetch
++ * with respect to the caller's accesses to other shared variables.
++ */
++struct task_struct *cpu_curr_snapshot(int cpu)
++{
++ struct task_struct *t;
++
++ smp_mb(); /* Pairing determined by caller's synchronization design. */
++ t = rcu_dereference(cpu_curr(cpu));
++ smp_mb(); /* Pairing determined by caller's synchronization design. */
++ return t;
++}
++
++/**
++ * wake_up_process - Wake up a specific process
++ * @p: The process to be woken up.
++ *
++ * Attempt to wake up the nominated process and move it to the set of runnable
++ * processes.
++ *
++ * Return: 1 if the process was woken up, 0 if it was already running.
++ *
++ * This function executes a full memory barrier before accessing the task state.
++ */
++int wake_up_process(struct task_struct *p)
++{
++ return try_to_wake_up(p, TASK_NORMAL, 0);
++}
++EXPORT_SYMBOL(wake_up_process);
++
++int wake_up_state(struct task_struct *p, unsigned int state)
++{
++ return try_to_wake_up(p, state, 0);
++}
++
++/*
++ * Perform scheduler related setup for a newly forked process p.
++ * p is forked by current.
++ *
++ * __sched_fork() is basic setup used by init_idle() too:
++ */
++static inline void __sched_fork(unsigned long clone_flags, struct task_struct *p)
++{
++ p->on_rq = 0;
++ p->on_cpu = 0;
++ p->utime = 0;
++ p->stime = 0;
++ p->sched_time = 0;
++
++#ifdef CONFIG_SCHEDSTATS
++ /* Even if schedstat is disabled, there should not be garbage */
++ memset(&p->stats, 0, sizeof(p->stats));
++#endif
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++ INIT_HLIST_HEAD(&p->preempt_notifiers);
++#endif
++
++#ifdef CONFIG_COMPACTION
++ p->capture_control = NULL;
++#endif
++#ifdef CONFIG_SMP
++ p->wake_entry.u_flags = CSD_TYPE_TTWU;
++#endif
++ init_sched_mm_cid(p);
++}
++
++/*
++ * fork()/clone()-time setup:
++ */
++int sched_fork(unsigned long clone_flags, struct task_struct *p)
++{
++ __sched_fork(clone_flags, p);
++ /*
++ * We mark the process as NEW here. This guarantees that
++ * nobody will actually run it, and a signal or other external
++ * event cannot wake it up and insert it on the runqueue either.
++ */
++ p->__state = TASK_NEW;
++
++ /*
++ * Make sure we do not leak PI boosting priority to the child.
++ */
++ p->prio = current->normal_prio;
++
++ /*
++ * Revert to default priority/policy on fork if requested.
++ */
++ if (unlikely(p->sched_reset_on_fork)) {
++ if (task_has_rt_policy(p)) {
++ p->policy = SCHED_NORMAL;
++ p->static_prio = NICE_TO_PRIO(0);
++ p->rt_priority = 0;
++ } else if (PRIO_TO_NICE(p->static_prio) < 0)
++ p->static_prio = NICE_TO_PRIO(0);
++
++ p->prio = p->normal_prio = p->static_prio;
++
++ /*
++ * We don't need the reset flag anymore after the fork. It has
++ * fulfilled its duty:
++ */
++ p->sched_reset_on_fork = 0;
++ }
++
++#ifdef CONFIG_SCHED_INFO
++ if (unlikely(sched_info_on()))
++ memset(&p->sched_info, 0, sizeof(p->sched_info));
++#endif
++ init_task_preempt_count(p);
++
++ return 0;
++}
++
++void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
++{
++ unsigned long flags;
++ struct rq *rq;
++
++ /*
++ * Because we're not yet on the pid-hash, p->pi_lock isn't strictly
++ * required yet, but lockdep gets upset if rules are violated.
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ /*
++ * Share the timeslice between parent and child, thus the
++ * total amount of pending timeslices in the system doesn't change,
++ * resulting in more scheduling fairness.
++ */
++ rq = this_rq();
++ raw_spin_lock(&rq->lock);
++
++ rq->curr->time_slice /= 2;
++ p->time_slice = rq->curr->time_slice;
++#ifdef CONFIG_SCHED_HRTICK
++ hrtick_start(rq, rq->curr->time_slice);
++#endif
++
++ if (p->time_slice < RESCHED_NS) {
++ p->time_slice = sysctl_sched_base_slice;
++ resched_curr(rq);
++ }
++ sched_task_fork(p, rq);
++ raw_spin_unlock(&rq->lock);
++
++ rseq_migrate(p);
++ /*
++ * We're setting the CPU for the first time, we don't migrate,
++ * so use __set_task_cpu().
++ */
++ __set_task_cpu(p, smp_processor_id());
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++
++void sched_post_fork(struct task_struct *p)
++{
++}
++
++#ifdef CONFIG_SCHEDSTATS
++
++DEFINE_STATIC_KEY_FALSE(sched_schedstats);
++
++static void set_schedstats(bool enabled)
++{
++ if (enabled)
++ static_branch_enable(&sched_schedstats);
++ else
++ static_branch_disable(&sched_schedstats);
++}
++
++void force_schedstat_enabled(void)
++{
++ if (!schedstat_enabled()) {
++ pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
++ static_branch_enable(&sched_schedstats);
++ }
++}
++
++static int __init setup_schedstats(char *str)
++{
++ int ret = 0;
++ if (!str)
++ goto out;
++
++ if (!strcmp(str, "enable")) {
++ set_schedstats(true);
++ ret = 1;
++ } else if (!strcmp(str, "disable")) {
++ set_schedstats(false);
++ ret = 1;
++ }
++out:
++ if (!ret)
++ pr_warn("Unable to parse schedstats=\n");
++
++ return ret;
++}
++__setup("schedstats=", setup_schedstats);
++
++#ifdef CONFIG_PROC_SYSCTL
++static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
++ size_t *lenp, loff_t *ppos)
++{
++ struct ctl_table t;
++ int err;
++ int state = static_branch_likely(&sched_schedstats);
++
++ if (write && !capable(CAP_SYS_ADMIN))
++ return -EPERM;
++
++ t = *table;
++ t.data = &state;
++ err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
++ if (err < 0)
++ return err;
++ if (write)
++ set_schedstats(state);
++ return err;
++}
++
++static struct ctl_table sched_core_sysctls[] = {
++ {
++ .procname = "sched_schedstats",
++ .data = NULL,
++ .maxlen = sizeof(unsigned int),
++ .mode = 0644,
++ .proc_handler = sysctl_schedstats,
++ .extra1 = SYSCTL_ZERO,
++ .extra2 = SYSCTL_ONE,
++ },
++};
++static int __init sched_core_sysctl_init(void)
++{
++ register_sysctl_init("kernel", sched_core_sysctls);
++ return 0;
++}
++late_initcall(sched_core_sysctl_init);
++#endif /* CONFIG_PROC_SYSCTL */
++#endif /* CONFIG_SCHEDSTATS */
++
++/*
++ * wake_up_new_task - wake up a newly created task for the first time.
++ *
++ * This function will do some initial scheduler statistics housekeeping
++ * that must be done for every newly created context, then puts the task
++ * on the runqueue and wakes it.
++ */
++void wake_up_new_task(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ WRITE_ONCE(p->__state, TASK_RUNNING);
++ rq = cpu_rq(select_task_rq(p));
++#ifdef CONFIG_SMP
++ rseq_migrate(p);
++ /*
++ * Fork balancing, do it here and not earlier because:
++ * - cpus_ptr can change in the fork path
++ * - any previously selected CPU might disappear through hotplug
++ *
++ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
++ * as we're not fully set-up yet.
++ */
++ __set_task_cpu(p, cpu_of(rq));
++#endif
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++
++ activate_task(p, rq);
++ trace_sched_wakeup_new(p);
++ wakeup_preempt(rq);
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++
++static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
++
++void preempt_notifier_inc(void)
++{
++ static_branch_inc(&preempt_notifier_key);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_inc);
++
++void preempt_notifier_dec(void)
++{
++ static_branch_dec(&preempt_notifier_key);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_dec);
++
++/**
++ * preempt_notifier_register - tell me when current is being preempted & rescheduled
++ * @notifier: notifier struct to register
++ */
++void preempt_notifier_register(struct preempt_notifier *notifier)
++{
++ if (!static_branch_unlikely(&preempt_notifier_key))
++ WARN(1, "registering preempt_notifier while notifiers disabled\n");
++
++ hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_register);
++
++/**
++ * preempt_notifier_unregister - no longer interested in preemption notifications
++ * @notifier: notifier struct to unregister
++ *
++ * This is *not* safe to call from within a preemption notifier.
++ */
++void preempt_notifier_unregister(struct preempt_notifier *notifier)
++{
++ hlist_del(¬ifier->link);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
++
++static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_in(notifier, raw_smp_processor_id());
++}
++
++static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++ if (static_branch_unlikely(&preempt_notifier_key))
++ __fire_sched_in_preempt_notifiers(curr);
++}
++
++static void
++__fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_out(notifier, next);
++}
++
++static __always_inline void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++ if (static_branch_unlikely(&preempt_notifier_key))
++ __fire_sched_out_preempt_notifiers(curr, next);
++}
++
++#else /* !CONFIG_PREEMPT_NOTIFIERS */
++
++static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++}
++
++static inline void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++}
++
++#endif /* CONFIG_PREEMPT_NOTIFIERS */
++
++static inline void prepare_task(struct task_struct *next)
++{
++ /*
++ * Claim the task as running, we do this before switching to it
++ * such that any running task will have this set.
++ *
++ * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
++ * its ordering comment.
++ */
++ WRITE_ONCE(next->on_cpu, 1);
++}
++
++static inline void finish_task(struct task_struct *prev)
++{
++#ifdef CONFIG_SMP
++ /*
++ * This must be the very last reference to @prev from this CPU. After
++ * p->on_cpu is cleared, the task can be moved to a different CPU. We
++ * must ensure this doesn't happen until the switch is completely
++ * finished.
++ *
++ * In particular, the load of prev->state in finish_task_switch() must
++ * happen before this.
++ *
++ * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
++ */
++ smp_store_release(&prev->on_cpu, 0);
++#else
++ prev->on_cpu = 0;
++#endif
++}
++
++#ifdef CONFIG_SMP
++
++static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++ void (*func)(struct rq *rq);
++ struct balance_callback *next;
++
++ lockdep_assert_held(&rq->lock);
++
++ while (head) {
++ func = (void (*)(struct rq *))head->func;
++ next = head->next;
++ head->next = NULL;
++ head = next;
++
++ func(rq);
++ }
++}
++
++static void balance_push(struct rq *rq);
++
++/*
++ * balance_push_callback is a right abuse of the callback interface and plays
++ * by significantly different rules.
++ *
++ * Where the normal balance_callback's purpose is to be ran in the same context
++ * that queued it (only later, when it's safe to drop rq->lock again),
++ * balance_push_callback is specifically targeted at __schedule().
++ *
++ * This abuse is tolerated because it places all the unlikely/odd cases behind
++ * a single test, namely: rq->balance_callback == NULL.
++ */
++struct balance_callback balance_push_callback = {
++ .next = NULL,
++ .func = balance_push,
++};
++
++static inline struct balance_callback *
++__splice_balance_callbacks(struct rq *rq, bool split)
++{
++ struct balance_callback *head = rq->balance_callback;
++
++ if (likely(!head))
++ return NULL;
++
++ lockdep_assert_rq_held(rq);
++ /*
++ * Must not take balance_push_callback off the list when
++ * splice_balance_callbacks() and balance_callbacks() are not
++ * in the same rq->lock section.
++ *
++ * In that case it would be possible for __schedule() to interleave
++ * and observe the list empty.
++ */
++ if (split && head == &balance_push_callback)
++ head = NULL;
++ else
++ rq->balance_callback = NULL;
++
++ return head;
++}
++
++static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
++{
++ return __splice_balance_callbacks(rq, true);
++}
++
++static void __balance_callbacks(struct rq *rq)
++{
++ do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
++}
++
++static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++ unsigned long flags;
++
++ if (unlikely(head)) {
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ do_balance_callbacks(rq, head);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++ }
++}
++
++#else
++
++static inline void __balance_callbacks(struct rq *rq)
++{
++}
++
++static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
++{
++ return NULL;
++}
++
++static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++}
++
++#endif
++
++static inline void
++prepare_lock_switch(struct rq *rq, struct task_struct *next)
++{
++ /*
++ * Since the runqueue lock will be released by the next
++ * task (which is an invalid locking op but in the case
++ * of the scheduler it's an obvious special-case), so we
++ * do an early lockdep release here:
++ */
++ spin_release(&rq->lock.dep_map, _THIS_IP_);
++#ifdef CONFIG_DEBUG_SPINLOCK
++ /* this is a valid case when another task releases the spinlock */
++ rq->lock.owner = next;
++#endif
++}
++
++static inline void finish_lock_switch(struct rq *rq)
++{
++ /*
++ * If we are tracking spinlock dependencies then we have to
++ * fix up the runqueue lock - which gets 'carried over' from
++ * prev into current:
++ */
++ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
++ __balance_callbacks(rq);
++ raw_spin_unlock_irq(&rq->lock);
++}
++
++/*
++ * NOP if the arch has not defined these:
++ */
++
++#ifndef prepare_arch_switch
++# define prepare_arch_switch(next) do { } while (0)
++#endif
++
++#ifndef finish_arch_post_lock_switch
++# define finish_arch_post_lock_switch() do { } while (0)
++#endif
++
++static inline void kmap_local_sched_out(void)
++{
++#ifdef CONFIG_KMAP_LOCAL
++ if (unlikely(current->kmap_ctrl.idx))
++ __kmap_local_sched_out();
++#endif
++}
++
++static inline void kmap_local_sched_in(void)
++{
++#ifdef CONFIG_KMAP_LOCAL
++ if (unlikely(current->kmap_ctrl.idx))
++ __kmap_local_sched_in();
++#endif
++}
++
++/**
++ * prepare_task_switch - prepare to switch tasks
++ * @rq: the runqueue preparing to switch
++ * @next: the task we are going to switch to.
++ *
++ * This is called with the rq lock held and interrupts off. It must
++ * be paired with a subsequent finish_task_switch after the context
++ * switch.
++ *
++ * prepare_task_switch sets up locking and calls architecture specific
++ * hooks.
++ */
++static inline void
++prepare_task_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ kcov_prepare_switch(prev);
++ sched_info_switch(rq, prev, next);
++ perf_event_task_sched_out(prev, next);
++ rseq_preempt(prev);
++ fire_sched_out_preempt_notifiers(prev, next);
++ kmap_local_sched_out();
++ prepare_task(next);
++ prepare_arch_switch(next);
++}
++
++/**
++ * finish_task_switch - clean up after a task-switch
++ * @rq: runqueue associated with task-switch
++ * @prev: the thread we just switched away from.
++ *
++ * finish_task_switch must be called after the context switch, paired
++ * with a prepare_task_switch call before the context switch.
++ * finish_task_switch will reconcile locking set up by prepare_task_switch,
++ * and do any other architecture-specific cleanup actions.
++ *
++ * Note that we may have delayed dropping an mm in context_switch(). If
++ * so, we finish that here outside of the runqueue lock. (Doing it
++ * with the lock held can cause deadlocks; see schedule() for
++ * details.)
++ *
++ * The context switch have flipped the stack from under us and restored the
++ * local variables which were saved when this task called schedule() in the
++ * past. prev == current is still correct but we need to recalculate this_rq
++ * because prev may have moved to another CPU.
++ */
++static struct rq *finish_task_switch(struct task_struct *prev)
++ __releases(rq->lock)
++{
++ struct rq *rq = this_rq();
++ struct mm_struct *mm = rq->prev_mm;
++ unsigned int prev_state;
++
++ /*
++ * The previous task will have left us with a preempt_count of 2
++ * because it left us after:
++ *
++ * schedule()
++ * preempt_disable(); // 1
++ * __schedule()
++ * raw_spin_lock_irq(&rq->lock) // 2
++ *
++ * Also, see FORK_PREEMPT_COUNT.
++ */
++ if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
++ "corrupted preempt_count: %s/%d/0x%x\n",
++ current->comm, current->pid, preempt_count()))
++ preempt_count_set(FORK_PREEMPT_COUNT);
++
++ rq->prev_mm = NULL;
++
++ /*
++ * A task struct has one reference for the use as "current".
++ * If a task dies, then it sets TASK_DEAD in tsk->state and calls
++ * schedule one last time. The schedule call will never return, and
++ * the scheduled task must drop that reference.
++ *
++ * We must observe prev->state before clearing prev->on_cpu (in
++ * finish_task), otherwise a concurrent wakeup can get prev
++ * running on another CPU and we could rave with its RUNNING -> DEAD
++ * transition, resulting in a double drop.
++ */
++ prev_state = READ_ONCE(prev->__state);
++ vtime_task_switch(prev);
++ perf_event_task_sched_in(prev, current);
++ finish_task(prev);
++ tick_nohz_task_switch();
++ finish_lock_switch(rq);
++ finish_arch_post_lock_switch();
++ kcov_finish_switch(current);
++ /*
++ * kmap_local_sched_out() is invoked with rq::lock held and
++ * interrupts disabled. There is no requirement for that, but the
++ * sched out code does not have an interrupt enabled section.
++ * Restoring the maps on sched in does not require interrupts being
++ * disabled either.
++ */
++ kmap_local_sched_in();
++
++ fire_sched_in_preempt_notifiers(current);
++ /*
++ * When switching through a kernel thread, the loop in
++ * membarrier_{private,global}_expedited() may have observed that
++ * kernel thread and not issued an IPI. It is therefore possible to
++ * schedule between user->kernel->user threads without passing though
++ * switch_mm(). Membarrier requires a barrier after storing to
++ * rq->curr, before returning to userspace, so provide them here:
++ *
++ * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
++ * provided by mmdrop(),
++ * - a sync_core for SYNC_CORE.
++ */
++ if (mm) {
++ membarrier_mm_sync_core_before_usermode(mm);
++ mmdrop_sched(mm);
++ }
++ if (unlikely(prev_state == TASK_DEAD)) {
++ /* Task is done with its stack. */
++ put_task_stack(prev);
++
++ put_task_struct_rcu_user(prev);
++ }
++
++ return rq;
++}
++
++/**
++ * schedule_tail - first thing a freshly forked thread must call.
++ * @prev: the thread we just switched away from.
++ */
++asmlinkage __visible void schedule_tail(struct task_struct *prev)
++ __releases(rq->lock)
++{
++ /*
++ * New tasks start with FORK_PREEMPT_COUNT, see there and
++ * finish_task_switch() for details.
++ *
++ * finish_task_switch() will drop rq->lock() and lower preempt_count
++ * and the preempt_enable() will end up enabling preemption (on
++ * PREEMPT_COUNT kernels).
++ */
++
++ finish_task_switch(prev);
++ preempt_enable();
++
++ if (current->set_child_tid)
++ put_user(task_pid_vnr(current), current->set_child_tid);
++
++ calculate_sigpending();
++}
++
++/*
++ * context_switch - switch to the new MM and the new thread's register state.
++ */
++static __always_inline struct rq *
++context_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ prepare_task_switch(rq, prev, next);
++
++ /*
++ * For paravirt, this is coupled with an exit in switch_to to
++ * combine the page table reload and the switch backend into
++ * one hypercall.
++ */
++ arch_start_context_switch(prev);
++
++ /*
++ * kernel -> kernel lazy + transfer active
++ * user -> kernel lazy + mmgrab() active
++ *
++ * kernel -> user switch + mmdrop() active
++ * user -> user switch
++ *
++ * switch_mm_cid() needs to be updated if the barriers provided
++ * by context_switch() are modified.
++ */
++ if (!next->mm) { // to kernel
++ enter_lazy_tlb(prev->active_mm, next);
++
++ next->active_mm = prev->active_mm;
++ if (prev->mm) // from user
++ mmgrab(prev->active_mm);
++ else
++ prev->active_mm = NULL;
++ } else { // to user
++ membarrier_switch_mm(rq, prev->active_mm, next->mm);
++ /*
++ * sys_membarrier() requires an smp_mb() between setting
++ * rq->curr / membarrier_switch_mm() and returning to userspace.
++ *
++ * The below provides this either through switch_mm(), or in
++ * case 'prev->active_mm == next->mm' through
++ * finish_task_switch()'s mmdrop().
++ */
++ switch_mm_irqs_off(prev->active_mm, next->mm, next);
++ lru_gen_use_mm(next->mm);
++
++ if (!prev->mm) { // from kernel
++ /* will mmdrop() in finish_task_switch(). */
++ rq->prev_mm = prev->active_mm;
++ prev->active_mm = NULL;
++ }
++ }
++
++ /* switch_mm_cid() requires the memory barriers above. */
++ switch_mm_cid(rq, prev, next);
++
++ prepare_lock_switch(rq, next);
++
++ /* Here we just switch the register state and the stack. */
++ switch_to(prev, next, prev);
++ barrier();
++
++ return finish_task_switch(prev);
++}
++
++/*
++ * nr_running, nr_uninterruptible and nr_context_switches:
++ *
++ * externally visible scheduler statistics: current number of runnable
++ * threads, total number of context switches performed since bootup.
++ */
++unsigned int nr_running(void)
++{
++ unsigned int i, sum = 0;
++
++ for_each_online_cpu(i)
++ sum += cpu_rq(i)->nr_running;
++
++ return sum;
++}
++
++/*
++ * Check if only the current task is running on the CPU.
++ *
++ * Caution: this function does not check that the caller has disabled
++ * preemption, thus the result might have a time-of-check-to-time-of-use
++ * race. The caller is responsible to use it correctly, for example:
++ *
++ * - from a non-preemptible section (of course)
++ *
++ * - from a thread that is bound to a single CPU
++ *
++ * - in a loop with very short iterations (e.g. a polling loop)
++ */
++bool single_task_running(void)
++{
++ return raw_rq()->nr_running == 1;
++}
++EXPORT_SYMBOL(single_task_running);
++
++unsigned long long nr_context_switches_cpu(int cpu)
++{
++ return cpu_rq(cpu)->nr_switches;
++}
++
++unsigned long long nr_context_switches(void)
++{
++ int i;
++ unsigned long long sum = 0;
++
++ for_each_possible_cpu(i)
++ sum += cpu_rq(i)->nr_switches;
++
++ return sum;
++}
++
++/*
++ * Consumers of these two interfaces, like for example the cpuidle menu
++ * governor, are using nonsensical data. Preferring shallow idle state selection
++ * for a CPU that has IO-wait which might not even end up running the task when
++ * it does become runnable.
++ */
++
++unsigned int nr_iowait_cpu(int cpu)
++{
++ return atomic_read(&cpu_rq(cpu)->nr_iowait);
++}
++
++/*
++ * IO-wait accounting, and how it's mostly bollocks (on SMP).
++ *
++ * The idea behind IO-wait account is to account the idle time that we could
++ * have spend running if it were not for IO. That is, if we were to improve the
++ * storage performance, we'd have a proportional reduction in IO-wait time.
++ *
++ * This all works nicely on UP, where, when a task blocks on IO, we account
++ * idle time as IO-wait, because if the storage were faster, it could've been
++ * running and we'd not be idle.
++ *
++ * This has been extended to SMP, by doing the same for each CPU. This however
++ * is broken.
++ *
++ * Imagine for instance the case where two tasks block on one CPU, only the one
++ * CPU will have IO-wait accounted, while the other has regular idle. Even
++ * though, if the storage were faster, both could've ran at the same time,
++ * utilising both CPUs.
++ *
++ * This means, that when looking globally, the current IO-wait accounting on
++ * SMP is a lower bound, by reason of under accounting.
++ *
++ * Worse, since the numbers are provided per CPU, they are sometimes
++ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
++ * associated with any one particular CPU, it can wake to another CPU than it
++ * blocked on. This means the per CPU IO-wait number is meaningless.
++ *
++ * Task CPU affinities can make all that even more 'interesting'.
++ */
++
++unsigned int nr_iowait(void)
++{
++ unsigned int i, sum = 0;
++
++ for_each_possible_cpu(i)
++ sum += nr_iowait_cpu(i);
++
++ return sum;
++}
++
++#ifdef CONFIG_SMP
++
++/*
++ * sched_exec - execve() is a valuable balancing opportunity, because at
++ * this point the task has the smallest effective memory and cache
++ * footprint.
++ */
++void sched_exec(void)
++{
++}
++
++#endif
++
++DEFINE_PER_CPU(struct kernel_stat, kstat);
++DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
++
++EXPORT_PER_CPU_SYMBOL(kstat);
++EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
++
++static inline void update_curr(struct rq *rq, struct task_struct *p)
++{
++ s64 ns = rq->clock_task - p->last_ran;
++
++ p->sched_time += ns;
++ cgroup_account_cputime(p, ns);
++ account_group_exec_runtime(p, ns);
++
++ p->time_slice -= ns;
++ p->last_ran = rq->clock_task;
++}
++
++/*
++ * Return accounted runtime for the task.
++ * Return separately the current's pending runtime that have not been
++ * accounted yet.
++ */
++unsigned long long task_sched_runtime(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++ u64 ns;
++
++#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
++ /*
++ * 64-bit doesn't need locks to atomically read a 64-bit value.
++ * So we have a optimization chance when the task's delta_exec is 0.
++ * Reading ->on_cpu is racy, but this is ok.
++ *
++ * If we race with it leaving CPU, we'll take a lock. So we're correct.
++ * If we race with it entering CPU, unaccounted time is 0. This is
++ * indistinguishable from the read occurring a few cycles earlier.
++ * If we see ->on_cpu without ->on_rq, the task is leaving, and has
++ * been accounted, so we're correct here as well.
++ */
++ if (!p->on_cpu || !task_on_rq_queued(p))
++ return tsk_seruntime(p);
++#endif
++
++ rq = task_access_lock_irqsave(p, &lock, &flags);
++ /*
++ * Must be ->curr _and_ ->on_rq. If dequeued, we would
++ * project cycles that may never be accounted to this
++ * thread, breaking clock_gettime().
++ */
++ if (p == rq->curr && task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ update_curr(rq, p);
++ }
++ ns = tsk_seruntime(p);
++ task_access_unlock_irqrestore(p, lock, &flags);
++
++ return ns;
++}
++
++/* This manages tasks that have run out of timeslice during a scheduler_tick */
++static inline void scheduler_task_tick(struct rq *rq)
++{
++ struct task_struct *p = rq->curr;
++
++ if (is_idle_task(p))
++ return;
++
++ update_curr(rq, p);
++ cpufreq_update_util(rq, 0);
++
++ /*
++ * Tasks have less than RESCHED_NS of time slice left they will be
++ * rescheduled.
++ */
++ if (p->time_slice >= RESCHED_NS)
++ return;
++ set_tsk_need_resched(p);
++ set_preempt_need_resched();
++}
++
++#ifdef CONFIG_SCHED_DEBUG
++static u64 cpu_resched_latency(struct rq *rq)
++{
++ int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
++ u64 resched_latency, now = rq_clock(rq);
++ static bool warned_once;
++
++ if (sysctl_resched_latency_warn_once && warned_once)
++ return 0;
++
++ if (!need_resched() || !latency_warn_ms)
++ return 0;
++
++ if (system_state == SYSTEM_BOOTING)
++ return 0;
++
++ if (!rq->last_seen_need_resched_ns) {
++ rq->last_seen_need_resched_ns = now;
++ rq->ticks_without_resched = 0;
++ return 0;
++ }
++
++ rq->ticks_without_resched++;
++ resched_latency = now - rq->last_seen_need_resched_ns;
++ if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC)
++ return 0;
++
++ warned_once = true;
++
++ return resched_latency;
++}
++
++static int __init setup_resched_latency_warn_ms(char *str)
++{
++ long val;
++
++ if ((kstrtol(str, 0, &val))) {
++ pr_warn("Unable to set resched_latency_warn_ms\n");
++ return 1;
++ }
++
++ sysctl_resched_latency_warn_ms = val;
++ return 1;
++}
++__setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
++#else
++static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
++#endif /* CONFIG_SCHED_DEBUG */
++
++/*
++ * This function gets called by the timer code, with HZ frequency.
++ * We call it with interrupts disabled.
++ */
++void sched_tick(void)
++{
++ int cpu __maybe_unused = smp_processor_id();
++ struct rq *rq = cpu_rq(cpu);
++ struct task_struct *curr = rq->curr;
++ u64 resched_latency;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ arch_scale_freq_tick();
++
++ sched_clock_tick();
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++
++ scheduler_task_tick(rq);
++ if (sched_feat(LATENCY_WARN))
++ resched_latency = cpu_resched_latency(rq);
++ calc_global_load_tick(rq);
++
++ task_tick_mm_cid(rq, rq->curr);
++
++ raw_spin_unlock(&rq->lock);
++
++ if (sched_feat(LATENCY_WARN) && resched_latency)
++ resched_latency_warn(cpu, resched_latency);
++
++ perf_event_task_tick();
++
++ if (curr->flags & PF_WQ_WORKER)
++ wq_worker_tick(curr);
++}
++
++#ifdef CONFIG_SMP
++
++static int active_balance_cpu_stop(void *data)
++{
++ struct balance_arg *arg = data;
++ struct task_struct *p = arg->task;
++ struct rq *rq = this_rq();
++ unsigned long flags;
++ cpumask_t tmp;
++
++ local_irq_save(flags);
++
++ raw_spin_lock(&p->pi_lock);
++ raw_spin_lock(&rq->lock);
++
++ arg->active = 0;
++
++ if (task_on_rq_queued(p) && task_rq(p) == rq &&
++ cpumask_and(&tmp, p->cpus_ptr, arg->cpumask) &&
++ !is_migration_disabled(p)) {
++ int dcpu = __best_mask_cpu(&tmp, per_cpu(sched_cpu_llc_mask, cpu_of(rq)));
++ rq = move_queued_task(rq, p, dcpu);
++ }
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ return 0;
++}
++
++/* trigger_active_balance - for @cpu/@rq */
++static inline int
++trigger_active_balance(struct rq *src_rq, struct rq *rq, struct balance_arg *arg)
++{
++ unsigned long flags;
++ struct task_struct *p;
++ int res;
++
++ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
++ return 0;
++
++ res = (1 == rq->nr_running) && \
++ !is_migration_disabled((p = sched_rq_first_task(rq))) && \
++ cpumask_intersects(p->cpus_ptr, arg->cpumask) && \
++ !arg->active;
++ if (res) {
++ arg->task = p;
++
++ arg->active = 1;
++ }
++
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ if (res) {
++ preempt_disable();
++ raw_spin_unlock(&src_rq->lock);
++
++ stop_one_cpu_nowait(cpu_of(rq), active_balance_cpu_stop,
++ arg, &rq->active_balance_work);
++
++ preempt_enable();
++ raw_spin_lock(&src_rq->lock);
++ }
++
++ return res;
++}
++
++#ifdef CONFIG_SCHED_SMT
++/*
++ * sg_balance - slibing group balance check for run queue @rq
++ */
++static inline void sg_balance(struct rq *rq)
++{
++ cpumask_t chk;
++
++ if (cpumask_andnot(&chk, cpu_active_mask, sched_idle_mask) &&
++ cpumask_andnot(&chk, &chk, &sched_rq_pending_mask)) {
++ int i, cpu = cpu_of(rq);
++
++ for_each_cpu_wrap(i, &chk, cpu) {
++ if (cpumask_subset(cpu_smt_mask(i), &chk)) {
++ struct rq *target_rq = cpu_rq(i);
++ if (trigger_active_balance(rq, target_rq, &target_rq->sg_balance_arg))
++ return;
++ }
++ }
++ }
++}
++
++static DEFINE_PER_CPU(struct balance_callback, sg_balance_head) = {
++ .func = sg_balance,
++};
++#endif /* CONFIG_SCHED_SMT */
++
++#endif /* CONFIG_SMP */
++
++#ifdef CONFIG_NO_HZ_FULL
++
++struct tick_work {
++ int cpu;
++ atomic_t state;
++ struct delayed_work work;
++};
++/* Values for ->state, see diagram below. */
++#define TICK_SCHED_REMOTE_OFFLINE 0
++#define TICK_SCHED_REMOTE_OFFLINING 1
++#define TICK_SCHED_REMOTE_RUNNING 2
++
++/*
++ * State diagram for ->state:
++ *
++ *
++ * TICK_SCHED_REMOTE_OFFLINE
++ * | ^
++ * | |
++ * | | sched_tick_remote()
++ * | |
++ * | |
++ * +--TICK_SCHED_REMOTE_OFFLINING
++ * | ^
++ * | |
++ * sched_tick_start() | | sched_tick_stop()
++ * | |
++ * V |
++ * TICK_SCHED_REMOTE_RUNNING
++ *
++ *
++ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
++ * and sched_tick_start() are happy to leave the state in RUNNING.
++ */
++
++static struct tick_work __percpu *tick_work_cpu;
++
++static void sched_tick_remote(struct work_struct *work)
++{
++ struct delayed_work *dwork = to_delayed_work(work);
++ struct tick_work *twork = container_of(dwork, struct tick_work, work);
++ int cpu = twork->cpu;
++ struct rq *rq = cpu_rq(cpu);
++ int os;
++
++ /*
++ * Handle the tick only if it appears the remote CPU is running in full
++ * dynticks mode. The check is racy by nature, but missing a tick or
++ * having one too much is no big deal because the scheduler tick updates
++ * statistics and checks timeslices in a time-independent way, regardless
++ * of when exactly it is running.
++ */
++ if (tick_nohz_tick_stopped_cpu(cpu)) {
++ guard(raw_spinlock_irqsave)(&rq->lock);
++ struct task_struct *curr = rq->curr;
++
++ if (cpu_online(cpu)) {
++ update_rq_clock(rq);
++
++ if (!is_idle_task(curr)) {
++ /*
++ * Make sure the next tick runs within a
++ * reasonable amount of time.
++ */
++ u64 delta = rq_clock_task(rq) - curr->last_ran;
++ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
++ }
++ scheduler_task_tick(rq);
++
++ calc_load_nohz_remote(rq);
++ }
++ }
++
++ /*
++ * Run the remote tick once per second (1Hz). This arbitrary
++ * frequency is large enough to avoid overload but short enough
++ * to keep scheduler internal stats reasonably up to date. But
++ * first update state to reflect hotplug activity if required.
++ */
++ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
++ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
++ if (os == TICK_SCHED_REMOTE_RUNNING)
++ queue_delayed_work(system_unbound_wq, dwork, HZ);
++}
++
++static void sched_tick_start(int cpu)
++{
++ int os;
++ struct tick_work *twork;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ return;
++
++ WARN_ON_ONCE(!tick_work_cpu);
++
++ twork = per_cpu_ptr(tick_work_cpu, cpu);
++ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
++ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
++ if (os == TICK_SCHED_REMOTE_OFFLINE) {
++ twork->cpu = cpu;
++ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
++ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
++ }
++}
++
++#ifdef CONFIG_HOTPLUG_CPU
++static void sched_tick_stop(int cpu)
++{
++ struct tick_work *twork;
++ int os;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ return;
++
++ WARN_ON_ONCE(!tick_work_cpu);
++
++ twork = per_cpu_ptr(tick_work_cpu, cpu);
++ /* There cannot be competing actions, but don't rely on stop-machine. */
++ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
++ WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
++ /* Don't cancel, as this would mess up the state machine. */
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
++int __init sched_tick_offload_init(void)
++{
++ tick_work_cpu = alloc_percpu(struct tick_work);
++ BUG_ON(!tick_work_cpu);
++ return 0;
++}
++
++#else /* !CONFIG_NO_HZ_FULL */
++static inline void sched_tick_start(int cpu) { }
++static inline void sched_tick_stop(int cpu) { }
++#endif
++
++#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
++ defined(CONFIG_PREEMPT_TRACER))
++/*
++ * If the value passed in is equal to the current preempt count
++ * then we just disabled preemption. Start timing the latency.
++ */
++static inline void preempt_latency_start(int val)
++{
++ if (preempt_count() == val) {
++ unsigned long ip = get_lock_parent_ip();
++#ifdef CONFIG_DEBUG_PREEMPT
++ current->preempt_disable_ip = ip;
++#endif
++ trace_preempt_off(CALLER_ADDR0, ip);
++ }
++}
++
++void preempt_count_add(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
++ return;
++#endif
++ __preempt_count_add(val);
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Spinlock count overflowing soon?
++ */
++ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
++ PREEMPT_MASK - 10);
++#endif
++ preempt_latency_start(val);
++}
++EXPORT_SYMBOL(preempt_count_add);
++NOKPROBE_SYMBOL(preempt_count_add);
++
++/*
++ * If the value passed in equals to the current preempt count
++ * then we just enabled preemption. Stop timing the latency.
++ */
++static inline void preempt_latency_stop(int val)
++{
++ if (preempt_count() == val)
++ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
++}
++
++void preempt_count_sub(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
++ return;
++ /*
++ * Is the spinlock portion underflowing?
++ */
++ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
++ !(preempt_count() & PREEMPT_MASK)))
++ return;
++#endif
++
++ preempt_latency_stop(val);
++ __preempt_count_sub(val);
++}
++EXPORT_SYMBOL(preempt_count_sub);
++NOKPROBE_SYMBOL(preempt_count_sub);
++
++#else
++static inline void preempt_latency_start(int val) { }
++static inline void preempt_latency_stop(int val) { }
++#endif
++
++static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ return p->preempt_disable_ip;
++#else
++ return 0;
++#endif
++}
++
++/*
++ * Print scheduling while atomic bug:
++ */
++static noinline void __schedule_bug(struct task_struct *prev)
++{
++ /* Save this before calling printk(), since that will clobber it */
++ unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
++
++ if (oops_in_progress)
++ return;
++
++ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
++ prev->comm, prev->pid, preempt_count());
++
++ debug_show_held_locks(prev);
++ print_modules();
++ if (irqs_disabled())
++ print_irqtrace_events(prev);
++ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
++ pr_err("Preemption disabled at:");
++ print_ip_sym(KERN_ERR, preempt_disable_ip);
++ }
++ check_panic_on_warn("scheduling while atomic");
++
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++
++/*
++ * Various schedule()-time debugging checks and statistics:
++ */
++static inline void schedule_debug(struct task_struct *prev, bool preempt)
++{
++#ifdef CONFIG_SCHED_STACK_END_CHECK
++ if (task_stack_end_corrupted(prev))
++ panic("corrupted stack end detected inside scheduler\n");
++
++ if (task_scs_end_corrupted(prev))
++ panic("corrupted shadow stack detected inside scheduler\n");
++#endif
++
++#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
++ if (!preempt && READ_ONCE(prev->__state) && prev->non_block_count) {
++ printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
++ prev->comm, prev->pid, prev->non_block_count);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++ }
++#endif
++
++ if (unlikely(in_atomic_preempt_off())) {
++ __schedule_bug(prev);
++ preempt_count_set(PREEMPT_DISABLED);
++ }
++ rcu_sleep_check();
++ SCHED_WARN_ON(ct_state() == CONTEXT_USER);
++
++ profile_hit(SCHED_PROFILING, __builtin_return_address(0));
++
++ schedstat_inc(this_rq()->sched_count);
++}
++
++#ifdef ALT_SCHED_DEBUG
++void alt_sched_debug(void)
++{
++ printk(KERN_INFO "sched: pending: 0x%04lx, idle: 0x%04lx, sg_idle: 0x%04lx\n",
++ sched_rq_pending_mask.bits[0],
++ sched_idle_mask->bits[0],
++ sched_sg_idle_mask.bits[0]);
++}
++#else
++inline void alt_sched_debug(void) {}
++#endif
++
++#ifdef CONFIG_SMP
++
++#ifdef CONFIG_PREEMPT_RT
++#define SCHED_NR_MIGRATE_BREAK 8
++#else
++#define SCHED_NR_MIGRATE_BREAK 32
++#endif
++
++const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
++
++/*
++ * Migrate pending tasks in @rq to @dest_cpu
++ */
++static inline int
++migrate_pending_tasks(struct rq *rq, struct rq *dest_rq, const int dest_cpu)
++{
++ struct task_struct *p, *skip = rq->curr;
++ int nr_migrated = 0;
++ int nr_tries = min(rq->nr_running / 2, sysctl_sched_nr_migrate);
++
++ /* WA to check rq->curr is still on rq */
++ if (!task_on_rq_queued(skip))
++ return 0;
++
++ while (skip != rq->idle && nr_tries &&
++ (p = sched_rq_next_task(skip, rq)) != rq->idle) {
++ skip = sched_rq_next_task(p, rq);
++ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) {
++ __SCHED_DEQUEUE_TASK(p, rq, 0, );
++ set_task_cpu(p, dest_cpu);
++ sched_task_sanity_check(p, dest_rq);
++ sched_mm_cid_migrate_to(dest_rq, p, cpu_of(rq));
++ __SCHED_ENQUEUE_TASK(p, dest_rq, 0, );
++ nr_migrated++;
++ }
++ nr_tries--;
++ }
++
++ return nr_migrated;
++}
++
++static inline int take_other_rq_tasks(struct rq *rq, int cpu)
++{
++ cpumask_t *topo_mask, *end_mask, chk;
++
++ if (unlikely(!rq->online))
++ return 0;
++
++ if (cpumask_empty(&sched_rq_pending_mask))
++ return 0;
++
++ topo_mask = per_cpu(sched_cpu_topo_masks, cpu);
++ end_mask = per_cpu(sched_cpu_topo_end_mask, cpu);
++ do {
++ int i;
++
++ if (!cpumask_and(&chk, &sched_rq_pending_mask, topo_mask))
++ continue;
++
++ for_each_cpu_wrap(i, &chk, cpu) {
++ int nr_migrated;
++ struct rq *src_rq;
++
++ src_rq = cpu_rq(i);
++ if (!do_raw_spin_trylock(&src_rq->lock))
++ continue;
++ spin_acquire(&src_rq->lock.dep_map,
++ SINGLE_DEPTH_NESTING, 1, _RET_IP_);
++
++ if ((nr_migrated = migrate_pending_tasks(src_rq, rq, cpu))) {
++ src_rq->nr_running -= nr_migrated;
++ if (src_rq->nr_running < 2)
++ cpumask_clear_cpu(i, &sched_rq_pending_mask);
++
++ spin_release(&src_rq->lock.dep_map, _RET_IP_);
++ do_raw_spin_unlock(&src_rq->lock);
++
++ rq->nr_running += nr_migrated;
++ if (rq->nr_running > 1)
++ cpumask_set_cpu(cpu, &sched_rq_pending_mask);
++
++ update_sched_preempt_mask(rq);
++ cpufreq_update_util(rq, 0);
++
++ return 1;
++ }
++
++ spin_release(&src_rq->lock.dep_map, _RET_IP_);
++ do_raw_spin_unlock(&src_rq->lock);
++ }
++ } while (++topo_mask < end_mask);
++
++ return 0;
++}
++#endif
++
++static inline void time_slice_expired(struct task_struct *p, struct rq *rq)
++{
++ p->time_slice = sysctl_sched_base_slice;
++
++ sched_task_renew(p, rq);
++
++ if (SCHED_FIFO != p->policy && task_on_rq_queued(p))
++ requeue_task(p, rq);
++}
++
++/*
++ * Timeslices below RESCHED_NS are considered as good as expired as there's no
++ * point rescheduling when there's so little time left.
++ */
++static inline void check_curr(struct task_struct *p, struct rq *rq)
++{
++ if (unlikely(rq->idle == p))
++ return;
++
++ update_curr(rq, p);
++
++ if (p->time_slice < RESCHED_NS)
++ time_slice_expired(p, rq);
++}
++
++static inline struct task_struct *
++choose_next_task(struct rq *rq, int cpu)
++{
++ struct task_struct *next = sched_rq_first_task(rq);
++
++ if (next == rq->idle) {
++#ifdef CONFIG_SMP
++ if (!take_other_rq_tasks(rq, cpu)) {
++#endif
++
++#ifdef CONFIG_SCHED_SMT
++ if (static_key_count(&sched_smt_present.key) > 1 &&
++ cpumask_test_cpu(cpu, sched_sg_idle_mask) &&
++ rq->online)
++ __queue_balance_callback(rq, &per_cpu(sg_balance_head, cpu));
++#endif
++ schedstat_inc(rq->sched_goidle);
++ /*printk(KERN_INFO "sched: choose_next_task(%d) idle %px\n", cpu, next);*/
++ return next;
++#ifdef CONFIG_SMP
++ }
++ next = sched_rq_first_task(rq);
++#endif
++ }
++#ifdef CONFIG_HIGH_RES_TIMERS
++ hrtick_start(rq, next->time_slice);
++#endif
++ /*printk(KERN_INFO "sched: choose_next_task(%d) next %px\n", cpu, next);*/
++ return next;
++}
++
++/*
++ * Constants for the sched_mode argument of __schedule().
++ *
++ * The mode argument allows RT enabled kernels to differentiate a
++ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
++ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
++ * optimize the AND operation out and just check for zero.
++ */
++#define SM_NONE 0x0
++#define SM_PREEMPT 0x1
++#define SM_RTLOCK_WAIT 0x2
++
++#ifndef CONFIG_PREEMPT_RT
++# define SM_MASK_PREEMPT (~0U)
++#else
++# define SM_MASK_PREEMPT SM_PREEMPT
++#endif
++
++/*
++ * schedule() is the main scheduler function.
++ *
++ * The main means of driving the scheduler and thus entering this function are:
++ *
++ * 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
++ *
++ * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
++ * paths. For example, see arch/x86/entry_64.S.
++ *
++ * To drive preemption between tasks, the scheduler sets the flag in timer
++ * interrupt handler sched_tick().
++ *
++ * 3. Wakeups don't really cause entry into schedule(). They add a
++ * task to the run-queue and that's it.
++ *
++ * Now, if the new task added to the run-queue preempts the current
++ * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
++ * called on the nearest possible occasion:
++ *
++ * - If the kernel is preemptible (CONFIG_PREEMPTION=y):
++ *
++ * - in syscall or exception context, at the next outmost
++ * preempt_enable(). (this might be as soon as the wake_up()'s
++ * spin_unlock()!)
++ *
++ * - in IRQ context, return from interrupt-handler to
++ * preemptible context
++ *
++ * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
++ * then at the next:
++ *
++ * - cond_resched() call
++ * - explicit schedule() call
++ * - return from syscall or exception to user-space
++ * - return from interrupt-handler to user-space
++ *
++ * WARNING: must be called with preemption disabled!
++ */
++static void __sched notrace __schedule(unsigned int sched_mode)
++{
++ struct task_struct *prev, *next;
++ unsigned long *switch_count;
++ unsigned long prev_state;
++ struct rq *rq;
++ int cpu;
++
++ cpu = smp_processor_id();
++ rq = cpu_rq(cpu);
++ prev = rq->curr;
++
++ schedule_debug(prev, !!sched_mode);
++
++ /* by passing sched_feat(HRTICK) checking which Alt schedule FW doesn't support */
++ hrtick_clear(rq);
++
++ local_irq_disable();
++ rcu_note_context_switch(!!sched_mode);
++
++ /*
++ * Make sure that signal_pending_state()->signal_pending() below
++ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
++ * done by the caller to avoid the race with signal_wake_up():
++ *
++ * __set_current_state(@state) signal_wake_up()
++ * schedule() set_tsk_thread_flag(p, TIF_SIGPENDING)
++ * wake_up_state(p, state)
++ * LOCK rq->lock LOCK p->pi_state
++ * smp_mb__after_spinlock() smp_mb__after_spinlock()
++ * if (signal_pending_state()) if (p->state & @state)
++ *
++ * Also, the membarrier system call requires a full memory barrier
++ * after coming from user-space, before storing to rq->curr; this
++ * barrier matches a full barrier in the proximity of the membarrier
++ * system call exit.
++ */
++ raw_spin_lock(&rq->lock);
++ smp_mb__after_spinlock();
++
++ update_rq_clock(rq);
++
++ switch_count = &prev->nivcsw;
++ /*
++ * We must load prev->state once (task_struct::state is volatile), such
++ * that we form a control dependency vs deactivate_task() below.
++ */
++ prev_state = READ_ONCE(prev->__state);
++ if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
++ if (signal_pending_state(prev_state, prev)) {
++ WRITE_ONCE(prev->__state, TASK_RUNNING);
++ } else {
++ prev->sched_contributes_to_load =
++ (prev_state & TASK_UNINTERRUPTIBLE) &&
++ !(prev_state & TASK_NOLOAD) &&
++ !(prev_state & TASK_FROZEN);
++
++ if (prev->sched_contributes_to_load)
++ rq->nr_uninterruptible++;
++
++ /*
++ * __schedule() ttwu()
++ * prev_state = prev->state; if (p->on_rq && ...)
++ * if (prev_state) goto out;
++ * p->on_rq = 0; smp_acquire__after_ctrl_dep();
++ * p->state = TASK_WAKING
++ *
++ * Where __schedule() and ttwu() have matching control dependencies.
++ *
++ * After this, schedule() must not care about p->state any more.
++ */
++ sched_task_deactivate(prev, rq);
++ deactivate_task(prev, rq);
++
++ if (prev->in_iowait) {
++ atomic_inc(&rq->nr_iowait);
++ delayacct_blkio_start();
++ }
++ }
++ switch_count = &prev->nvcsw;
++ }
++
++ check_curr(prev, rq);
++
++ next = choose_next_task(rq, cpu);
++ clear_tsk_need_resched(prev);
++ clear_preempt_need_resched();
++#ifdef CONFIG_SCHED_DEBUG
++ rq->last_seen_need_resched_ns = 0;
++#endif
++
++ if (likely(prev != next)) {
++ next->last_ran = rq->clock_task;
++
++ /*printk(KERN_INFO "sched: %px -> %px\n", prev, next);*/
++ rq->nr_switches++;
++ /*
++ * RCU users of rcu_dereference(rq->curr) may not see
++ * changes to task_struct made by pick_next_task().
++ */
++ RCU_INIT_POINTER(rq->curr, next);
++ /*
++ * The membarrier system call requires each architecture
++ * to have a full memory barrier after updating
++ * rq->curr, before returning to user-space.
++ *
++ * Here are the schemes providing that barrier on the
++ * various architectures:
++ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC,
++ * RISC-V. switch_mm() relies on membarrier_arch_switch_mm()
++ * on PowerPC and on RISC-V.
++ * - finish_lock_switch() for weakly-ordered
++ * architectures where spin_unlock is a full barrier,
++ * - switch_to() for arm64 (weakly-ordered, spin_unlock
++ * is a RELEASE barrier),
++ *
++ * The barrier matches a full barrier in the proximity of
++ * the membarrier system call entry.
++ *
++ * On RISC-V, this barrier pairing is also needed for the
++ * SYNC_CORE command when switching between processes, cf.
++ * the inline comments in membarrier_arch_switch_mm().
++ */
++ ++*switch_count;
++
++ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
++
++ /* Also unlocks the rq: */
++ rq = context_switch(rq, prev, next);
++
++ cpu = cpu_of(rq);
++ } else {
++ __balance_callbacks(rq);
++ raw_spin_unlock_irq(&rq->lock);
++ }
++}
++
++void __noreturn do_task_dead(void)
++{
++ /* Causes final put_task_struct in finish_task_switch(): */
++ set_special_state(TASK_DEAD);
++
++ /* Tell freezer to ignore us: */
++ current->flags |= PF_NOFREEZE;
++
++ __schedule(SM_NONE);
++ BUG();
++
++ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
++ for (;;)
++ cpu_relax();
++}
++
++static inline void sched_submit_work(struct task_struct *tsk)
++{
++ static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
++ unsigned int task_flags;
++
++ /*
++ * Establish LD_WAIT_CONFIG context to ensure none of the code called
++ * will use a blocking primitive -- which would lead to recursion.
++ */
++ lock_map_acquire_try(&sched_map);
++
++ task_flags = tsk->flags;
++ /*
++ * If a worker goes to sleep, notify and ask workqueue whether it
++ * wants to wake up a task to maintain concurrency.
++ */
++ if (task_flags & PF_WQ_WORKER)
++ wq_worker_sleeping(tsk);
++ else if (task_flags & PF_IO_WORKER)
++ io_wq_worker_sleeping(tsk);
++
++ /*
++ * spinlock and rwlock must not flush block requests. This will
++ * deadlock if the callback attempts to acquire a lock which is
++ * already acquired.
++ */
++ SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
++
++ /*
++ * If we are going to sleep and we have plugged IO queued,
++ * make sure to submit it to avoid deadlocks.
++ */
++ blk_flush_plug(tsk->plug, true);
++
++ lock_map_release(&sched_map);
++}
++
++static void sched_update_worker(struct task_struct *tsk)
++{
++ if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
++ if (tsk->flags & PF_BLOCK_TS)
++ blk_plug_invalidate_ts(tsk);
++ if (tsk->flags & PF_WQ_WORKER)
++ wq_worker_running(tsk);
++ else if (tsk->flags & PF_IO_WORKER)
++ io_wq_worker_running(tsk);
++ }
++}
++
++static __always_inline void __schedule_loop(unsigned int sched_mode)
++{
++ do {
++ preempt_disable();
++ __schedule(sched_mode);
++ sched_preempt_enable_no_resched();
++ } while (need_resched());
++}
++
++asmlinkage __visible void __sched schedule(void)
++{
++ struct task_struct *tsk = current;
++
++#ifdef CONFIG_RT_MUTEXES
++ lockdep_assert(!tsk->sched_rt_mutex);
++#endif
++
++ if (!task_is_running(tsk))
++ sched_submit_work(tsk);
++ __schedule_loop(SM_NONE);
++ sched_update_worker(tsk);
++}
++EXPORT_SYMBOL(schedule);
++
++/*
++ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
++ * state (have scheduled out non-voluntarily) by making sure that all
++ * tasks have either left the run queue or have gone into user space.
++ * As idle tasks do not do either, they must not ever be preempted
++ * (schedule out non-voluntarily).
++ *
++ * schedule_idle() is similar to schedule_preempt_disable() except that it
++ * never enables preemption because it does not call sched_submit_work().
++ */
++void __sched schedule_idle(void)
++{
++ /*
++ * As this skips calling sched_submit_work(), which the idle task does
++ * regardless because that function is a nop when the task is in a
++ * TASK_RUNNING state, make sure this isn't used someplace that the
++ * current task can be in any other state. Note, idle is always in the
++ * TASK_RUNNING state.
++ */
++ WARN_ON_ONCE(current->__state);
++ do {
++ __schedule(SM_NONE);
++ } while (need_resched());
++}
++
++#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK)
++asmlinkage __visible void __sched schedule_user(void)
++{
++ /*
++ * If we come here after a random call to set_need_resched(),
++ * or we have been woken up remotely but the IPI has not yet arrived,
++ * we haven't yet exited the RCU idle mode. Do it here manually until
++ * we find a better solution.
++ *
++ * NB: There are buggy callers of this function. Ideally we
++ * should warn if prev_state != CONTEXT_USER, but that will trigger
++ * too frequently to make sense yet.
++ */
++ enum ctx_state prev_state = exception_enter();
++ schedule();
++ exception_exit(prev_state);
++}
++#endif
++
++/**
++ * schedule_preempt_disabled - called with preemption disabled
++ *
++ * Returns with preemption disabled. Note: preempt_count must be 1
++ */
++void __sched schedule_preempt_disabled(void)
++{
++ sched_preempt_enable_no_resched();
++ schedule();
++ preempt_disable();
++}
++
++#ifdef CONFIG_PREEMPT_RT
++void __sched notrace schedule_rtlock(void)
++{
++ __schedule_loop(SM_RTLOCK_WAIT);
++}
++NOKPROBE_SYMBOL(schedule_rtlock);
++#endif
++
++static void __sched notrace preempt_schedule_common(void)
++{
++ do {
++ /*
++ * Because the function tracer can trace preempt_count_sub()
++ * and it also uses preempt_enable/disable_notrace(), if
++ * NEED_RESCHED is set, the preempt_enable_notrace() called
++ * by the function tracer will call this function again and
++ * cause infinite recursion.
++ *
++ * Preemption must be disabled here before the function
++ * tracer can trace. Break up preempt_disable() into two
++ * calls. One to disable preemption without fear of being
++ * traced. The other to still record the preemption latency,
++ * which can also be traced by the function tracer.
++ */
++ preempt_disable_notrace();
++ preempt_latency_start(1);
++ __schedule(SM_PREEMPT);
++ preempt_latency_stop(1);
++ preempt_enable_no_resched_notrace();
++
++ /*
++ * Check again in case we missed a preemption opportunity
++ * between schedule and now.
++ */
++ } while (need_resched());
++}
++
++#ifdef CONFIG_PREEMPTION
++/*
++ * This is the entry point to schedule() from in-kernel preemption
++ * off of preempt_enable.
++ */
++asmlinkage __visible void __sched notrace preempt_schedule(void)
++{
++ /*
++ * If there is a non-zero preempt_count or interrupts are disabled,
++ * we do not want to preempt the current task. Just return..
++ */
++ if (likely(!preemptible()))
++ return;
++
++ preempt_schedule_common();
++}
++NOKPROBE_SYMBOL(preempt_schedule);
++EXPORT_SYMBOL(preempt_schedule);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#ifndef preempt_schedule_dynamic_enabled
++#define preempt_schedule_dynamic_enabled preempt_schedule
++#define preempt_schedule_dynamic_disabled NULL
++#endif
++DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
++EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
++void __sched notrace dynamic_preempt_schedule(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
++ return;
++ preempt_schedule();
++}
++NOKPROBE_SYMBOL(dynamic_preempt_schedule);
++EXPORT_SYMBOL(dynamic_preempt_schedule);
++#endif
++#endif
++
++/**
++ * preempt_schedule_notrace - preempt_schedule called by tracing
++ *
++ * The tracing infrastructure uses preempt_enable_notrace to prevent
++ * recursion and tracing preempt enabling caused by the tracing
++ * infrastructure itself. But as tracing can happen in areas coming
++ * from userspace or just about to enter userspace, a preempt enable
++ * can occur before user_exit() is called. This will cause the scheduler
++ * to be called when the system is still in usermode.
++ *
++ * To prevent this, the preempt_enable_notrace will use this function
++ * instead of preempt_schedule() to exit user context if needed before
++ * calling the scheduler.
++ */
++asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
++{
++ enum ctx_state prev_ctx;
++
++ if (likely(!preemptible()))
++ return;
++
++ do {
++ /*
++ * Because the function tracer can trace preempt_count_sub()
++ * and it also uses preempt_enable/disable_notrace(), if
++ * NEED_RESCHED is set, the preempt_enable_notrace() called
++ * by the function tracer will call this function again and
++ * cause infinite recursion.
++ *
++ * Preemption must be disabled here before the function
++ * tracer can trace. Break up preempt_disable() into two
++ * calls. One to disable preemption without fear of being
++ * traced. The other to still record the preemption latency,
++ * which can also be traced by the function tracer.
++ */
++ preempt_disable_notrace();
++ preempt_latency_start(1);
++ /*
++ * Needs preempt disabled in case user_exit() is traced
++ * and the tracer calls preempt_enable_notrace() causing
++ * an infinite recursion.
++ */
++ prev_ctx = exception_enter();
++ __schedule(SM_PREEMPT);
++ exception_exit(prev_ctx);
++
++ preempt_latency_stop(1);
++ preempt_enable_no_resched_notrace();
++ } while (need_resched());
++}
++EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#ifndef preempt_schedule_notrace_dynamic_enabled
++#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace
++#define preempt_schedule_notrace_dynamic_disabled NULL
++#endif
++DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
++EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
++void __sched notrace dynamic_preempt_schedule_notrace(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
++ return;
++ preempt_schedule_notrace();
++}
++NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
++EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
++#endif
++#endif
++
++#endif /* CONFIG_PREEMPTION */
++
++/*
++ * This is the entry point to schedule() from kernel preemption
++ * off of irq context.
++ * Note, that this is called and return with irqs disabled. This will
++ * protect us against recursive calling from irq.
++ */
++asmlinkage __visible void __sched preempt_schedule_irq(void)
++{
++ enum ctx_state prev_state;
++
++ /* Catch callers which need to be fixed */
++ BUG_ON(preempt_count() || !irqs_disabled());
++
++ prev_state = exception_enter();
++
++ do {
++ preempt_disable();
++ local_irq_enable();
++ __schedule(SM_PREEMPT);
++ local_irq_disable();
++ sched_preempt_enable_no_resched();
++ } while (need_resched());
++
++ exception_exit(prev_state);
++}
++
++int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
++ void *key)
++{
++ WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
++ return try_to_wake_up(curr->private, mode, wake_flags);
++}
++EXPORT_SYMBOL(default_wake_function);
++
++static inline void check_task_changed(struct task_struct *p, struct rq *rq)
++{
++ /* Trigger resched if task sched_prio has been modified. */
++ if (task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ requeue_task(p, rq);
++ wakeup_preempt(rq);
++ }
++}
++
++static void __setscheduler_prio(struct task_struct *p, int prio)
++{
++ p->prio = prio;
++}
++
++#ifdef CONFIG_RT_MUTEXES
++
++/*
++ * Would be more useful with typeof()/auto_type but they don't mix with
++ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
++ * name such that if someone were to implement this function we get to compare
++ * notes.
++ */
++#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
++
++void rt_mutex_pre_schedule(void)
++{
++ lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
++ sched_submit_work(current);
++}
++
++void rt_mutex_schedule(void)
++{
++ lockdep_assert(current->sched_rt_mutex);
++ __schedule_loop(SM_NONE);
++}
++
++void rt_mutex_post_schedule(void)
++{
++ sched_update_worker(current);
++ lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
++}
++
++static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
++{
++ if (pi_task)
++ prio = min(prio, pi_task->prio);
++
++ return prio;
++}
++
++static inline int rt_effective_prio(struct task_struct *p, int prio)
++{
++ struct task_struct *pi_task = rt_mutex_get_top_task(p);
++
++ return __rt_effective_prio(pi_task, prio);
++}
++
++/*
++ * rt_mutex_setprio - set the current priority of a task
++ * @p: task to boost
++ * @pi_task: donor task
++ *
++ * This function changes the 'effective' priority of a task. It does
++ * not touch ->normal_prio like __setscheduler().
++ *
++ * Used by the rt_mutex code to implement priority inheritance
++ * logic. Call site only calls if the priority of the task changed.
++ */
++void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
++{
++ int prio;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ /* XXX used to be waiter->prio, not waiter->task->prio */
++ prio = __rt_effective_prio(pi_task, p->normal_prio);
++
++ /*
++ * If nothing changed; bail early.
++ */
++ if (p->pi_top_task == pi_task && prio == p->prio)
++ return;
++
++ rq = __task_access_lock(p, &lock);
++ /*
++ * Set under pi_lock && rq->lock, such that the value can be used under
++ * either lock.
++ *
++ * Note that there is loads of tricky to make this pointer cache work
++ * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
++ * ensure a task is de-boosted (pi_task is set to NULL) before the
++ * task is allowed to run again (and can exit). This ensures the pointer
++ * points to a blocked task -- which guarantees the task is present.
++ */
++ p->pi_top_task = pi_task;
++
++ /*
++ * For FIFO/RR we only need to set prio, if that matches we're done.
++ */
++ if (prio == p->prio)
++ goto out_unlock;
++
++ /*
++ * Idle task boosting is a nono in general. There is one
++ * exception, when PREEMPT_RT and NOHZ is active:
++ *
++ * The idle task calls get_next_timer_interrupt() and holds
++ * the timer wheel base->lock on the CPU and another CPU wants
++ * to access the timer (probably to cancel it). We can safely
++ * ignore the boosting request, as the idle CPU runs this code
++ * with interrupts disabled and will complete the lock
++ * protected section without being interrupted. So there is no
++ * real need to boost.
++ */
++ if (unlikely(p == rq->idle)) {
++ WARN_ON(p != rq->curr);
++ WARN_ON(p->pi_blocked_on);
++ goto out_unlock;
++ }
++
++ trace_sched_pi_setprio(p, pi_task);
++
++ __setscheduler_prio(p, prio);
++
++ check_task_changed(p, rq);
++out_unlock:
++ /* Avoid rq from going away on us: */
++ preempt_disable();
++
++ if (task_on_rq_queued(p))
++ __balance_callbacks(rq);
++ __task_access_unlock(p, lock);
++
++ preempt_enable();
++}
++#else
++static inline int rt_effective_prio(struct task_struct *p, int prio)
++{
++ return prio;
++}
++#endif
++
++void set_user_nice(struct task_struct *p, long nice)
++{
++ unsigned long flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
++ return;
++ /*
++ * We have to be careful, if called from sys_setpriority(),
++ * the task might be in the middle of scheduling on another CPU.
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ rq = __task_access_lock(p, &lock);
++
++ p->static_prio = NICE_TO_PRIO(nice);
++ /*
++ * The RT priorities are set via sched_setscheduler(), but we still
++ * allow the 'normal' nice value to be set - but as expected
++ * it won't have any effect on scheduling until the task is
++ * not SCHED_NORMAL/SCHED_BATCH:
++ */
++ if (task_has_rt_policy(p))
++ goto out_unlock;
++
++ p->prio = effective_prio(p);
++
++ check_task_changed(p, rq);
++out_unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++EXPORT_SYMBOL(set_user_nice);
++
++/*
++ * is_nice_reduction - check if nice value is an actual reduction
++ *
++ * Similar to can_nice() but does not perform a capability check.
++ *
++ * @p: task
++ * @nice: nice value
++ */
++static bool is_nice_reduction(const struct task_struct *p, const int nice)
++{
++ /* Convert nice value [19,-20] to rlimit style value [1,40]: */
++ int nice_rlim = nice_to_rlimit(nice);
++
++ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));
++}
++
++/*
++ * can_nice - check if a task can reduce its nice value
++ * @p: task
++ * @nice: nice value
++ */
++int can_nice(const struct task_struct *p, const int nice)
++{
++ return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);
++}
++
++#ifdef __ARCH_WANT_SYS_NICE
++
++/*
++ * sys_nice - change the priority of the current process.
++ * @increment: priority increment
++ *
++ * sys_setpriority is a more generic, but much slower function that
++ * does similar things.
++ */
++SYSCALL_DEFINE1(nice, int, increment)
++{
++ long nice, retval;
++
++ /*
++ * Setpriority might change our priority at the same moment.
++ * We don't have to worry. Conceptually one call occurs first
++ * and we have a single winner.
++ */
++
++ increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
++ nice = task_nice(current) + increment;
++
++ nice = clamp_val(nice, MIN_NICE, MAX_NICE);
++ if (increment < 0 && !can_nice(current, nice))
++ return -EPERM;
++
++ retval = security_task_setnice(current, nice);
++ if (retval)
++ return retval;
++
++ set_user_nice(current, nice);
++ return 0;
++}
++
++#endif
++
++/**
++ * task_prio - return the priority value of a given task.
++ * @p: the task in question.
++ *
++ * Return: The priority value as seen by users in /proc.
++ *
++ * sched policy return value kernel prio user prio/nice
++ *
++ * (BMQ)normal, batch, idle[0 ... 53] [100 ... 139] 0/[-20 ... 19]/[-7 ... 7]
++ * (PDS)normal, batch, idle[0 ... 39] 100 0/[-20 ... 19]
++ * fifo, rr [-1 ... -100] [99 ... 0] [0 ... 99]
++ */
++int task_prio(const struct task_struct *p)
++{
++ return (p->prio < MAX_RT_PRIO) ? p->prio - MAX_RT_PRIO :
++ task_sched_prio_normal(p, task_rq(p));
++}
++
++/**
++ * idle_cpu - is a given CPU idle currently?
++ * @cpu: the processor in question.
++ *
++ * Return: 1 if the CPU is currently idle. 0 otherwise.
++ */
++int idle_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (rq->curr != rq->idle)
++ return 0;
++
++ if (rq->nr_running)
++ return 0;
++
++#ifdef CONFIG_SMP
++ if (rq->ttwu_pending)
++ return 0;
++#endif
++
++ return 1;
++}
++
++/**
++ * idle_task - return the idle task for a given CPU.
++ * @cpu: the processor in question.
++ *
++ * Return: The idle task for the cpu @cpu.
++ */
++struct task_struct *idle_task(int cpu)
++{
++ return cpu_rq(cpu)->idle;
++}
++
++/**
++ * find_process_by_pid - find a process with a matching PID value.
++ * @pid: the pid in question.
++ *
++ * The task of @pid, if found. %NULL otherwise.
++ */
++static inline struct task_struct *find_process_by_pid(pid_t pid)
++{
++ return pid ? find_task_by_vpid(pid) : current;
++}
++
++static struct task_struct *find_get_task(pid_t pid)
++{
++ struct task_struct *p;
++ guard(rcu)();
++
++ p = find_process_by_pid(pid);
++ if (likely(p))
++ get_task_struct(p);
++
++ return p;
++}
++
++DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
++ find_get_task(pid), pid_t pid)
++
++/*
++ * sched_setparam() passes in -1 for its policy, to let the functions
++ * it calls know not to change it.
++ */
++#define SETPARAM_POLICY -1
++
++static void __setscheduler_params(struct task_struct *p,
++ const struct sched_attr *attr)
++{
++ int policy = attr->sched_policy;
++
++ if (policy == SETPARAM_POLICY)
++ policy = p->policy;
++
++ p->policy = policy;
++
++ /*
++ * allow normal nice value to be set, but will not have any
++ * effect on scheduling until the task not SCHED_NORMAL/
++ * SCHED_BATCH
++ */
++ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
++
++ /*
++ * __sched_setscheduler() ensures attr->sched_priority == 0 when
++ * !rt_policy. Always setting this ensures that things like
++ * getparam()/getattr() don't report silly values for !rt tasks.
++ */
++ p->rt_priority = attr->sched_priority;
++ p->normal_prio = normal_prio(p);
++}
++
++/*
++ * check the target process has a UID that matches the current process's
++ */
++static bool check_same_owner(struct task_struct *p)
++{
++ const struct cred *cred = current_cred(), *pcred;
++ guard(rcu)();
++
++ pcred = __task_cred(p);
++ return (uid_eq(cred->euid, pcred->euid) ||
++ uid_eq(cred->euid, pcred->uid));
++}
++
++/*
++ * Allow unprivileged RT tasks to decrease priority.
++ * Only issue a capable test if needed and only once to avoid an audit
++ * event on permitted non-privileged operations:
++ */
++static int user_check_sched_setscheduler(struct task_struct *p,
++ const struct sched_attr *attr,
++ int policy, int reset_on_fork)
++{
++ if (rt_policy(policy)) {
++ unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
++
++ /* Can't set/change the rt policy: */
++ if (policy != p->policy && !rlim_rtprio)
++ goto req_priv;
++
++ /* Can't increase priority: */
++ if (attr->sched_priority > p->rt_priority &&
++ attr->sched_priority > rlim_rtprio)
++ goto req_priv;
++ }
++
++ /* Can't change other user's priorities: */
++ if (!check_same_owner(p))
++ goto req_priv;
++
++ /* Normal users shall not reset the sched_reset_on_fork flag: */
++ if (p->sched_reset_on_fork && !reset_on_fork)
++ goto req_priv;
++
++ return 0;
++
++req_priv:
++ if (!capable(CAP_SYS_NICE))
++ return -EPERM;
++
++ return 0;
++}
++
++static int __sched_setscheduler(struct task_struct *p,
++ const struct sched_attr *attr,
++ bool user, bool pi)
++{
++ const struct sched_attr dl_squash_attr = {
++ .size = sizeof(struct sched_attr),
++ .sched_policy = SCHED_FIFO,
++ .sched_nice = 0,
++ .sched_priority = 99,
++ };
++ int oldpolicy = -1, policy = attr->sched_policy;
++ int retval, newprio;
++ struct balance_callback *head;
++ unsigned long flags;
++ struct rq *rq;
++ int reset_on_fork;
++ raw_spinlock_t *lock;
++
++ /* The pi code expects interrupts enabled */
++ BUG_ON(pi && in_interrupt());
++
++ /*
++ * Alt schedule FW supports SCHED_DEADLINE by squash it as prio 0 SCHED_FIFO
++ */
++ if (unlikely(SCHED_DEADLINE == policy)) {
++ attr = &dl_squash_attr;
++ policy = attr->sched_policy;
++ }
++recheck:
++ /* Double check policy once rq lock held */
++ if (policy < 0) {
++ reset_on_fork = p->sched_reset_on_fork;
++ policy = oldpolicy = p->policy;
++ } else {
++ reset_on_fork = !!(attr->sched_flags & SCHED_RESET_ON_FORK);
++
++ if (policy > SCHED_IDLE)
++ return -EINVAL;
++ }
++
++ if (attr->sched_flags & ~(SCHED_FLAG_ALL))
++ return -EINVAL;
++
++ /*
++ * Valid priorities for SCHED_FIFO and SCHED_RR are
++ * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL and
++ * SCHED_BATCH and SCHED_IDLE is 0.
++ */
++ if (attr->sched_priority < 0 ||
++ (p->mm && attr->sched_priority > MAX_RT_PRIO - 1) ||
++ (!p->mm && attr->sched_priority > MAX_RT_PRIO - 1))
++ return -EINVAL;
++ if ((SCHED_RR == policy || SCHED_FIFO == policy) !=
++ (attr->sched_priority != 0))
++ return -EINVAL;
++
++ if (user) {
++ retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork);
++ if (retval)
++ return retval;
++
++ retval = security_task_setscheduler(p);
++ if (retval)
++ return retval;
++ }
++
++ /*
++ * Make sure no PI-waiters arrive (or leave) while we are
++ * changing the priority of the task:
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++
++ /*
++ * To be able to change p->policy safely, task_access_lock()
++ * must be called.
++ * IF use task_access_lock() here:
++ * For the task p which is not running, reading rq->stop is
++ * racy but acceptable as ->stop doesn't change much.
++ * An enhancemnet can be made to read rq->stop saftly.
++ */
++ rq = __task_access_lock(p, &lock);
++
++ /*
++ * Changing the policy of the stop threads its a very bad idea
++ */
++ if (p == rq->stop) {
++ retval = -EINVAL;
++ goto unlock;
++ }
++
++ /*
++ * If not changing anything there's no need to proceed further:
++ */
++ if (unlikely(policy == p->policy)) {
++ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
++ goto change;
++ if (!rt_policy(policy) &&
++ NICE_TO_PRIO(attr->sched_nice) != p->static_prio)
++ goto change;
++
++ p->sched_reset_on_fork = reset_on_fork;
++ retval = 0;
++ goto unlock;
++ }
++change:
++
++ /* Re-check policy now with rq lock held */
++ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
++ policy = oldpolicy = -1;
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ goto recheck;
++ }
++
++ p->sched_reset_on_fork = reset_on_fork;
++
++ newprio = __normal_prio(policy, attr->sched_priority, NICE_TO_PRIO(attr->sched_nice));
++ if (pi) {
++ /*
++ * Take priority boosted tasks into account. If the new
++ * effective priority is unchanged, we just store the new
++ * normal parameters and do not touch the scheduler class and
++ * the runqueue. This will be done when the task deboost
++ * itself.
++ */
++ newprio = rt_effective_prio(p, newprio);
++ }
++
++ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
++ __setscheduler_params(p, attr);
++ __setscheduler_prio(p, newprio);
++ }
++
++ check_task_changed(p, rq);
++
++ /* Avoid rq from going away on us: */
++ preempt_disable();
++ head = splice_balance_callbacks(rq);
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ if (pi)
++ rt_mutex_adjust_pi(p);
++
++ /* Run balance callbacks after we've adjusted the PI chain: */
++ balance_callbacks(rq, head);
++ preempt_enable();
++
++ return 0;
++
++unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ return retval;
++}
++
++static int _sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param, bool check)
++{
++ struct sched_attr attr = {
++ .sched_policy = policy,
++ .sched_priority = param->sched_priority,
++ .sched_nice = PRIO_TO_NICE(p->static_prio),
++ };
++
++ /* Fixup the legacy SCHED_RESET_ON_FORK hack. */
++ if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
++ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
++ policy &= ~SCHED_RESET_ON_FORK;
++ attr.sched_policy = policy;
++ }
++
++ return __sched_setscheduler(p, &attr, check, true);
++}
++
++/**
++ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * Use sched_set_fifo(), read its comment.
++ *
++ * Return: 0 on success. An error code otherwise.
++ *
++ * NOTE that the task may be already dead.
++ */
++int sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return _sched_setscheduler(p, policy, param, true);
++}
++
++int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
++{
++ return __sched_setscheduler(p, attr, true, true);
++}
++
++int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
++{
++ return __sched_setscheduler(p, attr, false, true);
++}
++EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
++
++/**
++ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * Just like sched_setscheduler, only don't bother checking if the
++ * current context has permission. For example, this is needed in
++ * stop_machine(): we create temporary high priority worker threads,
++ * but our caller might not have that capability.
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++int sched_setscheduler_nocheck(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return _sched_setscheduler(p, policy, param, false);
++}
++
++/*
++ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
++ * incapable of resource management, which is the one thing an OS really should
++ * be doing.
++ *
++ * This is of course the reason it is limited to privileged users only.
++ *
++ * Worse still; it is fundamentally impossible to compose static priority
++ * workloads. You cannot take two correctly working static prio workloads
++ * and smash them together and still expect them to work.
++ *
++ * For this reason 'all' FIFO tasks the kernel creates are basically at:
++ *
++ * MAX_RT_PRIO / 2
++ *
++ * The administrator _MUST_ configure the system, the kernel simply doesn't
++ * know enough information to make a sensible choice.
++ */
++void sched_set_fifo(struct task_struct *p)
++{
++ struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
++ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_fifo);
++
++/*
++ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
++ */
++void sched_set_fifo_low(struct task_struct *p)
++{
++ struct sched_param sp = { .sched_priority = 1 };
++ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_fifo_low);
++
++void sched_set_normal(struct task_struct *p, int nice)
++{
++ struct sched_attr attr = {
++ .sched_policy = SCHED_NORMAL,
++ .sched_nice = nice,
++ };
++ WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_normal);
++
++static int
++do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
++{
++ struct sched_param lparam;
++
++ if (!param || pid < 0)
++ return -EINVAL;
++ if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
++ return -EFAULT;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ return sched_setscheduler(p, policy, &lparam);
++}
++
++/*
++ * Mimics kernel/events/core.c perf_copy_attr().
++ */
++static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
++{
++ u32 size;
++ int ret;
++
++ /* Zero the full structure, so that a short copy will be nice: */
++ memset(attr, 0, sizeof(*attr));
++
++ ret = get_user(size, &uattr->size);
++ if (ret)
++ return ret;
++
++ /* ABI compatibility quirk: */
++ if (!size)
++ size = SCHED_ATTR_SIZE_VER0;
++
++ if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
++ goto err_size;
++
++ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
++ if (ret) {
++ if (ret == -E2BIG)
++ goto err_size;
++ return ret;
++ }
++
++ /*
++ * XXX: Do we want to be lenient like existing syscalls; or do we want
++ * to be strict and return an error on out-of-bounds values?
++ */
++ attr->sched_nice = clamp(attr->sched_nice, -20, 19);
++
++ /* sched/core.c uses zero here but we already know ret is zero */
++ return 0;
++
++err_size:
++ put_user(sizeof(*attr), &uattr->size);
++ return -E2BIG;
++}
++
++/**
++ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
++ * @pid: the pid in question.
++ * @policy: new policy.
++ *
++ * Return: 0 on success. An error code otherwise.
++ * @param: structure containing the new RT priority.
++ */
++SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
++{
++ if (policy < 0)
++ return -EINVAL;
++
++ return do_sched_setscheduler(pid, policy, param);
++}
++
++/**
++ * sys_sched_setparam - set/change the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the new RT priority.
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
++{
++ return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
++}
++
++static void get_params(struct task_struct *p, struct sched_attr *attr)
++{
++ if (task_has_rt_policy(p))
++ attr->sched_priority = p->rt_priority;
++ else
++ attr->sched_nice = task_nice(p);
++}
++
++/**
++ * sys_sched_setattr - same as above, but with extended sched_attr
++ * @pid: the pid in question.
++ * @uattr: structure containing the extended parameters.
++ */
++SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
++ unsigned int, flags)
++{
++ struct sched_attr attr;
++ int retval;
++
++ if (!uattr || pid < 0 || flags)
++ return -EINVAL;
++
++ retval = sched_copy_attr(uattr, &attr);
++ if (retval)
++ return retval;
++
++ if ((int)attr.sched_policy < 0)
++ return -EINVAL;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
++ get_params(p, &attr);
++
++ return sched_setattr(p, &attr);
++}
++
++/**
++ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
++ * @pid: the pid in question.
++ *
++ * Return: On success, the policy of the thread. Otherwise, a negative error
++ * code.
++ */
++SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
++{
++ struct task_struct *p;
++ int retval = -EINVAL;
++
++ if (pid < 0)
++ return -ESRCH;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (!retval)
++ retval = p->policy;
++
++ return retval;
++}
++
++/**
++ * sys_sched_getscheduler - get the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the RT priority.
++ *
++ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
++ * code.
++ */
++SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
++{
++ struct sched_param lp = { .sched_priority = 0 };
++ struct task_struct *p;
++
++ if (!param || pid < 0)
++ return -EINVAL;
++
++ scoped_guard (rcu) {
++ int retval;
++
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -EINVAL;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ if (task_has_rt_policy(p))
++ lp.sched_priority = p->rt_priority;
++ }
++
++ /*
++ * This one might sleep, we cannot do it with a spinlock held ...
++ */
++ return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
++}
++
++/*
++ * Copy the kernel size attribute structure (which might be larger
++ * than what user-space knows about) to user-space.
++ *
++ * Note that all cases are valid: user-space buffer can be larger or
++ * smaller than the kernel-space buffer. The usual case is that both
++ * have the same size.
++ */
++static int
++sched_attr_copy_to_user(struct sched_attr __user *uattr,
++ struct sched_attr *kattr,
++ unsigned int usize)
++{
++ unsigned int ksize = sizeof(*kattr);
++
++ if (!access_ok(uattr, usize))
++ return -EFAULT;
++
++ /*
++ * sched_getattr() ABI forwards and backwards compatibility:
++ *
++ * If usize == ksize then we just copy everything to user-space and all is good.
++ *
++ * If usize < ksize then we only copy as much as user-space has space for,
++ * this keeps ABI compatibility as well. We skip the rest.
++ *
++ * If usize > ksize then user-space is using a newer version of the ABI,
++ * which part the kernel doesn't know about. Just ignore it - tooling can
++ * detect the kernel's knowledge of attributes from the attr->size value
++ * which is set to ksize in this case.
++ */
++ kattr->size = min(usize, ksize);
++
++ if (copy_to_user(uattr, kattr, kattr->size))
++ return -EFAULT;
++
++ return 0;
++}
++
++/**
++ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
++ * @pid: the pid in question.
++ * @uattr: structure containing the extended parameters.
++ * @usize: sizeof(attr) for fwd/bwd comp.
++ * @flags: for future extension.
++ */
++SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
++ unsigned int, usize, unsigned int, flags)
++{
++ struct sched_attr kattr = { };
++ struct task_struct *p;
++ int retval;
++
++ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
++ usize < SCHED_ATTR_SIZE_VER0 || flags)
++ return -EINVAL;
++
++ scoped_guard (rcu) {
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ kattr.sched_policy = p->policy;
++ if (p->sched_reset_on_fork)
++ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
++ get_params(p, &kattr);
++ kattr.sched_flags &= SCHED_FLAG_ALL;
++
++#ifdef CONFIG_UCLAMP_TASK
++ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
++ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
++#endif
++ }
++
++ return sched_attr_copy_to_user(uattr, &kattr, usize);
++}
++
++#ifdef CONFIG_SMP
++int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
++{
++ return 0;
++}
++#endif
++
++static int
++__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
++{
++ int retval;
++ cpumask_var_t cpus_allowed, new_mask;
++
++ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
++ return -ENOMEM;
++
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
++ retval = -ENOMEM;
++ goto out_free_cpus_allowed;
++ }
++
++ cpuset_cpus_allowed(p, cpus_allowed);
++ cpumask_and(new_mask, ctx->new_mask, cpus_allowed);
++
++ ctx->new_mask = new_mask;
++ ctx->flags |= SCA_CHECK;
++
++ retval = __set_cpus_allowed_ptr(p, ctx);
++ if (retval)
++ goto out_free_new_mask;
++
++ cpuset_cpus_allowed(p, cpus_allowed);
++ if (!cpumask_subset(new_mask, cpus_allowed)) {
++ /*
++ * We must have raced with a concurrent cpuset
++ * update. Just reset the cpus_allowed to the
++ * cpuset's cpus_allowed
++ */
++ cpumask_copy(new_mask, cpus_allowed);
++
++ /*
++ * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr()
++ * will restore the previous user_cpus_ptr value.
++ *
++ * In the unlikely event a previous user_cpus_ptr exists,
++ * we need to further restrict the mask to what is allowed
++ * by that old user_cpus_ptr.
++ */
++ if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) {
++ bool empty = !cpumask_and(new_mask, new_mask,
++ ctx->user_mask);
++
++ if (WARN_ON_ONCE(empty))
++ cpumask_copy(new_mask, cpus_allowed);
++ }
++ __set_cpus_allowed_ptr(p, ctx);
++ retval = -EINVAL;
++ }
++
++out_free_new_mask:
++ free_cpumask_var(new_mask);
++out_free_cpus_allowed:
++ free_cpumask_var(cpus_allowed);
++ return retval;
++}
++
++long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
++{
++ struct affinity_context ac;
++ struct cpumask *user_mask;
++ int retval;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ if (p->flags & PF_NO_SETAFFINITY)
++ return -EINVAL;
++
++ if (!check_same_owner(p)) {
++ guard(rcu)();
++ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
++ return -EPERM;
++ }
++
++ retval = security_task_setscheduler(p);
++ if (retval)
++ return retval;
++
++ /*
++ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
++ * alloc_user_cpus_ptr() returns NULL.
++ */
++ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
++ if (user_mask) {
++ cpumask_copy(user_mask, in_mask);
++ } else if (IS_ENABLED(CONFIG_SMP)) {
++ return -ENOMEM;
++ }
++
++ ac = (struct affinity_context){
++ .new_mask = in_mask,
++ .user_mask = user_mask,
++ .flags = SCA_USER,
++ };
++
++ retval = __sched_setaffinity(p, &ac);
++ kfree(ac.user_mask);
++
++ return retval;
++}
++
++static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
++ struct cpumask *new_mask)
++{
++ if (len < cpumask_size())
++ cpumask_clear(new_mask);
++ else if (len > cpumask_size())
++ len = cpumask_size();
++
++ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
++}
++
++/**
++ * sys_sched_setaffinity - set the CPU affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to the new CPU mask
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ cpumask_var_t new_mask;
++ int retval;
++
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
++ if (retval == 0)
++ retval = sched_setaffinity(pid, new_mask);
++ free_cpumask_var(new_mask);
++ return retval;
++}
++
++long sched_getaffinity(pid_t pid, cpumask_t *mask)
++{
++ struct task_struct *p;
++ int retval;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ guard(raw_spinlock_irqsave)(&p->pi_lock);
++ cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
++
++ return retval;
++}
++
++/**
++ * sys_sched_getaffinity - get the CPU affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to hold the current CPU mask
++ *
++ * Return: size of CPU mask copied to user_mask_ptr on success. An
++ * error code otherwise.
++ */
++SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ int ret;
++ cpumask_var_t mask;
++
++ if ((len * BITS_PER_BYTE) < nr_cpu_ids)
++ return -EINVAL;
++ if (len & (sizeof(unsigned long)-1))
++ return -EINVAL;
++
++ if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ ret = sched_getaffinity(pid, mask);
++ if (ret == 0) {
++ unsigned int retlen = min(len, cpumask_size());
++
++ if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen))
++ ret = -EFAULT;
++ else
++ ret = retlen;
++ }
++ free_cpumask_var(mask);
++
++ return ret;
++}
++
++static void do_sched_yield(void)
++{
++ struct rq *rq;
++ struct rq_flags rf;
++ struct task_struct *p;
++
++ if (!sched_yield_type)
++ return;
++
++ rq = this_rq_lock_irq(&rf);
++
++ schedstat_inc(rq->yld_count);
++
++ p = current;
++ if (rt_task(p)) {
++ if (task_on_rq_queued(p))
++ requeue_task(p, rq);
++ } else if (rq->nr_running > 1) {
++ do_sched_yield_type_1(p, rq);
++ if (task_on_rq_queued(p))
++ requeue_task(p, rq);
++ }
++
++ preempt_disable();
++ raw_spin_unlock_irq(&rq->lock);
++ sched_preempt_enable_no_resched();
++
++ schedule();
++}
++
++/**
++ * sys_sched_yield - yield the current processor to other threads.
++ *
++ * This function yields the current CPU to other tasks. If there are no
++ * other threads running on this CPU then this function will return.
++ *
++ * Return: 0.
++ */
++SYSCALL_DEFINE0(sched_yield)
++{
++ do_sched_yield();
++ return 0;
++}
++
++#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
++int __sched __cond_resched(void)
++{
++ if (should_resched(0)) {
++ preempt_schedule_common();
++ return 1;
++ }
++ /*
++ * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
++ * whether the current CPU is in an RCU read-side critical section,
++ * so the tick can report quiescent states even for CPUs looping
++ * in kernel context. In contrast, in non-preemptible kernels,
++ * RCU readers leave no in-memory hints, which means that CPU-bound
++ * processes executing in kernel context might never report an
++ * RCU quiescent state. Therefore, the following code causes
++ * cond_resched() to report a quiescent state, but only when RCU
++ * is in urgent need of one.
++ */
++#ifndef CONFIG_PREEMPT_RCU
++ rcu_all_qs();
++#endif
++ return 0;
++}
++EXPORT_SYMBOL(__cond_resched);
++#endif
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#define cond_resched_dynamic_enabled __cond_resched
++#define cond_resched_dynamic_disabled ((void *)&__static_call_return0)
++DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
++EXPORT_STATIC_CALL_TRAMP(cond_resched);
++
++#define might_resched_dynamic_enabled __cond_resched
++#define might_resched_dynamic_disabled ((void *)&__static_call_return0)
++DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
++EXPORT_STATIC_CALL_TRAMP(might_resched);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
++int __sched dynamic_cond_resched(void)
++{
++ klp_sched_try_switch();
++ if (!static_branch_unlikely(&sk_dynamic_cond_resched))
++ return 0;
++ return __cond_resched();
++}
++EXPORT_SYMBOL(dynamic_cond_resched);
++
++static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
++int __sched dynamic_might_resched(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_might_resched))
++ return 0;
++ return __cond_resched();
++}
++EXPORT_SYMBOL(dynamic_might_resched);
++#endif
++#endif
++
++/*
++ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
++ * call schedule, and on return reacquire the lock.
++ *
++ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
++ * operations here to prevent schedule() from being called twice (once via
++ * spin_unlock(), once by hand).
++ */
++int __cond_resched_lock(spinlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held(lock);
++
++ if (spin_needbreak(lock) || resched) {
++ spin_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ spin_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_lock);
++
++int __cond_resched_rwlock_read(rwlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held_read(lock);
++
++ if (rwlock_needbreak(lock) || resched) {
++ read_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ read_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_rwlock_read);
++
++int __cond_resched_rwlock_write(rwlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held_write(lock);
++
++ if (rwlock_needbreak(lock) || resched) {
++ write_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ write_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_rwlock_write);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++
++#ifdef CONFIG_GENERIC_ENTRY
++#include <linux/entry-common.h>
++#endif
++
++/*
++ * SC:cond_resched
++ * SC:might_resched
++ * SC:preempt_schedule
++ * SC:preempt_schedule_notrace
++ * SC:irqentry_exit_cond_resched
++ *
++ *
++ * NONE:
++ * cond_resched <- __cond_resched
++ * might_resched <- RET0
++ * preempt_schedule <- NOP
++ * preempt_schedule_notrace <- NOP
++ * irqentry_exit_cond_resched <- NOP
++ *
++ * VOLUNTARY:
++ * cond_resched <- __cond_resched
++ * might_resched <- __cond_resched
++ * preempt_schedule <- NOP
++ * preempt_schedule_notrace <- NOP
++ * irqentry_exit_cond_resched <- NOP
++ *
++ * FULL:
++ * cond_resched <- RET0
++ * might_resched <- RET0
++ * preempt_schedule <- preempt_schedule
++ * preempt_schedule_notrace <- preempt_schedule_notrace
++ * irqentry_exit_cond_resched <- irqentry_exit_cond_resched
++ */
++
++enum {
++ preempt_dynamic_undefined = -1,
++ preempt_dynamic_none,
++ preempt_dynamic_voluntary,
++ preempt_dynamic_full,
++};
++
++int preempt_dynamic_mode = preempt_dynamic_undefined;
++
++int sched_dynamic_mode(const char *str)
++{
++ if (!strcmp(str, "none"))
++ return preempt_dynamic_none;
++
++ if (!strcmp(str, "voluntary"))
++ return preempt_dynamic_voluntary;
++
++ if (!strcmp(str, "full"))
++ return preempt_dynamic_full;
++
++ return -EINVAL;
++}
++
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled)
++#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled)
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key)
++#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key)
++#else
++#error "Unsupported PREEMPT_DYNAMIC mechanism"
++#endif
++
++static DEFINE_MUTEX(sched_dynamic_mutex);
++static bool klp_override;
++
++static void __sched_dynamic_update(int mode)
++{
++ /*
++ * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
++ * the ZERO state, which is invalid.
++ */
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(might_resched);
++ preempt_dynamic_enable(preempt_schedule);
++ preempt_dynamic_enable(preempt_schedule_notrace);
++ preempt_dynamic_enable(irqentry_exit_cond_resched);
++
++ switch (mode) {
++ case preempt_dynamic_none:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_disable(might_resched);
++ preempt_dynamic_disable(preempt_schedule);
++ preempt_dynamic_disable(preempt_schedule_notrace);
++ preempt_dynamic_disable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: none\n");
++ break;
++
++ case preempt_dynamic_voluntary:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(might_resched);
++ preempt_dynamic_disable(preempt_schedule);
++ preempt_dynamic_disable(preempt_schedule_notrace);
++ preempt_dynamic_disable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: voluntary\n");
++ break;
++
++ case preempt_dynamic_full:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_disable(might_resched);
++ preempt_dynamic_enable(preempt_schedule);
++ preempt_dynamic_enable(preempt_schedule_notrace);
++ preempt_dynamic_enable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: full\n");
++ break;
++ }
++
++ preempt_dynamic_mode = mode;
++}
++
++void sched_dynamic_update(int mode)
++{
++ mutex_lock(&sched_dynamic_mutex);
++ __sched_dynamic_update(mode);
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
++
++static int klp_cond_resched(void)
++{
++ __klp_sched_try_switch();
++ return __cond_resched();
++}
++
++void sched_dynamic_klp_enable(void)
++{
++ mutex_lock(&sched_dynamic_mutex);
++
++ klp_override = true;
++ static_call_update(cond_resched, klp_cond_resched);
++
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++void sched_dynamic_klp_disable(void)
++{
++ mutex_lock(&sched_dynamic_mutex);
++
++ klp_override = false;
++ __sched_dynamic_update(preempt_dynamic_mode);
++
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
++
++
++static int __init setup_preempt_mode(char *str)
++{
++ int mode = sched_dynamic_mode(str);
++ if (mode < 0) {
++ pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
++ return 0;
++ }
++
++ sched_dynamic_update(mode);
++ return 1;
++}
++__setup("preempt=", setup_preempt_mode);
++
++static void __init preempt_dynamic_init(void)
++{
++ if (preempt_dynamic_mode == preempt_dynamic_undefined) {
++ if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
++ sched_dynamic_update(preempt_dynamic_none);
++ } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
++ sched_dynamic_update(preempt_dynamic_voluntary);
++ } else {
++ /* Default static call setting, nothing to do */
++ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
++ preempt_dynamic_mode = preempt_dynamic_full;
++ pr_info("Dynamic Preempt: full\n");
++ }
++ }
++}
++
++#define PREEMPT_MODEL_ACCESSOR(mode) \
++ bool preempt_model_##mode(void) \
++ { \
++ WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
++ return preempt_dynamic_mode == preempt_dynamic_##mode; \
++ } \
++ EXPORT_SYMBOL_GPL(preempt_model_##mode)
++
++PREEMPT_MODEL_ACCESSOR(none);
++PREEMPT_MODEL_ACCESSOR(voluntary);
++PREEMPT_MODEL_ACCESSOR(full);
++
++#else /* !CONFIG_PREEMPT_DYNAMIC */
++
++static inline void preempt_dynamic_init(void) { }
++
++#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
++
++/**
++ * yield - yield the current processor to other threads.
++ *
++ * Do not ever use this function, there's a 99% chance you're doing it wrong.
++ *
++ * The scheduler is at all times free to pick the calling task as the most
++ * eligible task to run, if removing the yield() call from your code breaks
++ * it, it's already broken.
++ *
++ * Typical broken usage is:
++ *
++ * while (!event)
++ * yield();
++ *
++ * where one assumes that yield() will let 'the other' process run that will
++ * make event true. If the current task is a SCHED_FIFO task that will never
++ * happen. Never use yield() as a progress guarantee!!
++ *
++ * If you want to use yield() to wait for something, use wait_event().
++ * If you want to use yield() to be 'nice' for others, use cond_resched().
++ * If you still want to use yield(), do not!
++ */
++void __sched yield(void)
++{
++ set_current_state(TASK_RUNNING);
++ do_sched_yield();
++}
++EXPORT_SYMBOL(yield);
++
++/**
++ * yield_to - yield the current processor to another thread in
++ * your thread group, or accelerate that thread toward the
++ * processor it's on.
++ * @p: target task
++ * @preempt: whether task preemption is allowed or not
++ *
++ * It's the caller's job to ensure that the target task struct
++ * can't go away on us before we can do any checks.
++ *
++ * In Alt schedule FW, yield_to is not supported.
++ *
++ * Return:
++ * true (>0) if we indeed boosted the target task.
++ * false (0) if we failed to boost the target.
++ * -ESRCH if there's no task to yield to.
++ */
++int __sched yield_to(struct task_struct *p, bool preempt)
++{
++ return 0;
++}
++EXPORT_SYMBOL_GPL(yield_to);
++
++int io_schedule_prepare(void)
++{
++ int old_iowait = current->in_iowait;
++
++ current->in_iowait = 1;
++ blk_flush_plug(current->plug, true);
++ return old_iowait;
++}
++
++void io_schedule_finish(int token)
++{
++ current->in_iowait = token;
++}
++
++/*
++ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
++ * that process accounting knows that this is a task in IO wait state.
++ *
++ * But don't do that if it is a deliberate, throttling IO wait (this task
++ * has set its backing_dev_info: the queue against which it should throttle)
++ */
++
++long __sched io_schedule_timeout(long timeout)
++{
++ int token;
++ long ret;
++
++ token = io_schedule_prepare();
++ ret = schedule_timeout(timeout);
++ io_schedule_finish(token);
++
++ return ret;
++}
++EXPORT_SYMBOL(io_schedule_timeout);
++
++void __sched io_schedule(void)
++{
++ int token;
++
++ token = io_schedule_prepare();
++ schedule();
++ io_schedule_finish(token);
++}
++EXPORT_SYMBOL(io_schedule);
++
++/**
++ * sys_sched_get_priority_max - return maximum RT priority.
++ * @policy: scheduling class.
++ *
++ * Return: On success, this syscall returns the maximum
++ * rt_priority that can be used by a given scheduling class.
++ * On failure, a negative error code is returned.
++ */
++SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = MAX_RT_PRIO - 1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_IDLE:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++/**
++ * sys_sched_get_priority_min - return minimum RT priority.
++ * @policy: scheduling class.
++ *
++ * Return: On success, this syscall returns the minimum
++ * rt_priority that can be used by a given scheduling class.
++ * On failure, a negative error code is returned.
++ */
++SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = 1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_IDLE:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
++{
++ struct task_struct *p;
++ int retval;
++
++ alt_sched_debug();
++
++ if (pid < 0)
++ return -EINVAL;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -EINVAL;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ *t = ns_to_timespec64(sysctl_sched_base_slice);
++ return 0;
++}
++
++/**
++ * sys_sched_rr_get_interval - return the default timeslice of a process.
++ * @pid: pid of the process.
++ * @interval: userspace pointer to the timeslice value.
++ *
++ *
++ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
++ * an error code.
++ */
++SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
++ struct __kernel_timespec __user *, interval)
++{
++ struct timespec64 t;
++ int retval = sched_rr_get_interval(pid, &t);
++
++ if (retval == 0)
++ retval = put_timespec64(&t, interval);
++
++ return retval;
++}
++
++#ifdef CONFIG_COMPAT_32BIT_TIME
++SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
++ struct old_timespec32 __user *, interval)
++{
++ struct timespec64 t;
++ int retval = sched_rr_get_interval(pid, &t);
++
++ if (retval == 0)
++ retval = put_old_timespec32(&t, interval);
++ return retval;
++}
++#endif
++
++void sched_show_task(struct task_struct *p)
++{
++ unsigned long free = 0;
++ int ppid;
++
++ if (!try_get_task_stack(p))
++ return;
++
++ pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
++
++ if (task_is_running(p))
++ pr_cont(" running task ");
++#ifdef CONFIG_DEBUG_STACK_USAGE
++ free = stack_not_used(p);
++#endif
++ ppid = 0;
++ rcu_read_lock();
++ if (pid_alive(p))
++ ppid = task_pid_nr(rcu_dereference(p->real_parent));
++ rcu_read_unlock();
++ pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
++ free, task_pid_nr(p), task_tgid_nr(p),
++ ppid, read_task_thread_flags(p));
++
++ print_worker_info(KERN_INFO, p);
++ print_stop_info(KERN_INFO, p);
++ show_stack(p, NULL, KERN_INFO);
++ put_task_stack(p);
++}
++EXPORT_SYMBOL_GPL(sched_show_task);
++
++static inline bool
++state_filter_match(unsigned long state_filter, struct task_struct *p)
++{
++ unsigned int state = READ_ONCE(p->__state);
++
++ /* no filter, everything matches */
++ if (!state_filter)
++ return true;
++
++ /* filter, but doesn't match */
++ if (!(state & state_filter))
++ return false;
++
++ /*
++ * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
++ * TASK_KILLABLE).
++ */
++ if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD))
++ return false;
++
++ return true;
++}
++
++
++void show_state_filter(unsigned int state_filter)
++{
++ struct task_struct *g, *p;
++
++ rcu_read_lock();
++ for_each_process_thread(g, p) {
++ /*
++ * reset the NMI-timeout, listing all files on a slow
++ * console might take a lot of time:
++ * Also, reset softlockup watchdogs on all CPUs, because
++ * another CPU might be blocked waiting for us to process
++ * an IPI.
++ */
++ touch_nmi_watchdog();
++ touch_all_softlockup_watchdogs();
++ if (state_filter_match(state_filter, p))
++ sched_show_task(p);
++ }
++
++#ifdef CONFIG_SCHED_DEBUG
++ /* TODO: Alt schedule FW should support this
++ if (!state_filter)
++ sysrq_sched_debug_show();
++ */
++#endif
++ rcu_read_unlock();
++ /*
++ * Only show locks if all tasks are dumped:
++ */
++ if (!state_filter)
++ debug_show_all_locks();
++}
++
++void dump_cpu_task(int cpu)
++{
++ if (cpu == smp_processor_id() && in_hardirq()) {
++ struct pt_regs *regs;
++
++ regs = get_irq_regs();
++ if (regs) {
++ show_regs(regs);
++ return;
++ }
++ }
++
++ if (trigger_single_cpu_backtrace(cpu))
++ return;
++
++ pr_info("Task dump for CPU %d:\n", cpu);
++ sched_show_task(cpu_curr(cpu));
++}
++
++/**
++ * init_idle - set up an idle thread for a given CPU
++ * @idle: task in question
++ * @cpu: CPU the idle task belongs to
++ *
++ * NOTE: this function does not set the idle thread's NEED_RESCHED
++ * flag, to make booting more robust.
++ */
++void __init init_idle(struct task_struct *idle, int cpu)
++{
++#ifdef CONFIG_SMP
++ struct affinity_context ac = (struct affinity_context) {
++ .new_mask = cpumask_of(cpu),
++ .flags = 0,
++ };
++#endif
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ __sched_fork(0, idle);
++
++ raw_spin_lock_irqsave(&idle->pi_lock, flags);
++ raw_spin_lock(&rq->lock);
++
++ idle->last_ran = rq->clock_task;
++ idle->__state = TASK_RUNNING;
++ /*
++ * PF_KTHREAD should already be set at this point; regardless, make it
++ * look like a proper per-CPU kthread.
++ */
++ idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
++ kthread_set_per_cpu(idle, cpu);
++
++ sched_queue_init_idle(&rq->queue, idle);
++
++#ifdef CONFIG_SMP
++ /*
++ * It's possible that init_idle() gets called multiple times on a task,
++ * in that case do_set_cpus_allowed() will not do the right thing.
++ *
++ * And since this is boot we can forgo the serialisation.
++ */
++ set_cpus_allowed_common(idle, &ac);
++#endif
++
++ /* Silence PROVE_RCU */
++ rcu_read_lock();
++ __set_task_cpu(idle, cpu);
++ rcu_read_unlock();
++
++ rq->idle = idle;
++ rcu_assign_pointer(rq->curr, idle);
++ idle->on_cpu = 1;
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
++
++ /* Set the preempt count _outside_ the spinlocks! */
++ init_idle_preempt_count(idle, cpu);
++
++ ftrace_graph_init_idle_task(idle, cpu);
++ vtime_init_idle(idle, cpu);
++#ifdef CONFIG_SMP
++ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
++#endif
++}
++
++#ifdef CONFIG_SMP
++
++int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur,
++ const struct cpumask __maybe_unused *trial)
++{
++ return 1;
++}
++
++int task_can_attach(struct task_struct *p)
++{
++ int ret = 0;
++
++ /*
++ * Kthreads which disallow setaffinity shouldn't be moved
++ * to a new cpuset; we don't want to change their CPU
++ * affinity and isolating such threads by their set of
++ * allowed nodes is unnecessary. Thus, cpusets are not
++ * applicable for such threads. This prevents checking for
++ * success of set_cpus_allowed_ptr() on all attached tasks
++ * before cpus_mask may be changed.
++ */
++ if (p->flags & PF_NO_SETAFFINITY)
++ ret = -EINVAL;
++
++ return ret;
++}
++
++bool sched_smp_initialized __read_mostly;
++
++#ifdef CONFIG_HOTPLUG_CPU
++/*
++ * Ensures that the idle task is using init_mm right before its CPU goes
++ * offline.
++ */
++void idle_task_exit(void)
++{
++ struct mm_struct *mm = current->active_mm;
++
++ BUG_ON(current != this_rq()->idle);
++
++ if (mm != &init_mm) {
++ switch_mm(mm, &init_mm, current);
++ finish_arch_post_lock_switch();
++ }
++
++ /* finish_cpu(), as ran on the BP, will clean up the active_mm state */
++}
++
++static int __balance_push_cpu_stop(void *arg)
++{
++ struct task_struct *p = arg;
++ struct rq *rq = this_rq();
++ struct rq_flags rf;
++ int cpu;
++
++ raw_spin_lock_irq(&p->pi_lock);
++ rq_lock(rq, &rf);
++
++ update_rq_clock(rq);
++
++ if (task_rq(p) == rq && task_on_rq_queued(p)) {
++ cpu = select_fallback_rq(rq->cpu, p);
++ rq = __migrate_task(rq, p, cpu);
++ }
++
++ rq_unlock(rq, &rf);
++ raw_spin_unlock_irq(&p->pi_lock);
++
++ put_task_struct(p);
++
++ return 0;
++}
++
++static DEFINE_PER_CPU(struct cpu_stop_work, push_work);
++
++/*
++ * This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only
++ * effective when the hotplug motion is down.
++ */
++static void balance_push(struct rq *rq)
++{
++ struct task_struct *push_task = rq->curr;
++
++ lockdep_assert_held(&rq->lock);
++
++ /*
++ * Ensure the thing is persistent until balance_push_set(.on = false);
++ */
++ rq->balance_callback = &balance_push_callback;
++
++ /*
++ * Only active while going offline and when invoked on the outgoing
++ * CPU.
++ */
++ if (!cpu_dying(rq->cpu) || rq != this_rq())
++ return;
++
++ /*
++ * Both the cpu-hotplug and stop task are in this case and are
++ * required to complete the hotplug process.
++ */
++ if (kthread_is_per_cpu(push_task) ||
++ is_migration_disabled(push_task)) {
++
++ /*
++ * If this is the idle task on the outgoing CPU try to wake
++ * up the hotplug control thread which might wait for the
++ * last task to vanish. The rcuwait_active() check is
++ * accurate here because the waiter is pinned on this CPU
++ * and can't obviously be running in parallel.
++ *
++ * On RT kernels this also has to check whether there are
++ * pinned and scheduled out tasks on the runqueue. They
++ * need to leave the migrate disabled section first.
++ */
++ if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
++ rcuwait_active(&rq->hotplug_wait)) {
++ raw_spin_unlock(&rq->lock);
++ rcuwait_wake_up(&rq->hotplug_wait);
++ raw_spin_lock(&rq->lock);
++ }
++ return;
++ }
++
++ get_task_struct(push_task);
++ /*
++ * Temporarily drop rq->lock such that we can wake-up the stop task.
++ * Both preemption and IRQs are still disabled.
++ */
++ preempt_disable();
++ raw_spin_unlock(&rq->lock);
++ stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
++ this_cpu_ptr(&push_work));
++ preempt_enable();
++ /*
++ * At this point need_resched() is true and we'll take the loop in
++ * schedule(). The next pick is obviously going to be the stop task
++ * which kthread_is_per_cpu() and will push this task away.
++ */
++ raw_spin_lock(&rq->lock);
++}
++
++static void balance_push_set(int cpu, bool on)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct rq_flags rf;
++
++ rq_lock_irqsave(rq, &rf);
++ if (on) {
++ WARN_ON_ONCE(rq->balance_callback);
++ rq->balance_callback = &balance_push_callback;
++ } else if (rq->balance_callback == &balance_push_callback) {
++ rq->balance_callback = NULL;
++ }
++ rq_unlock_irqrestore(rq, &rf);
++}
++
++/*
++ * Invoked from a CPUs hotplug control thread after the CPU has been marked
++ * inactive. All tasks which are not per CPU kernel threads are either
++ * pushed off this CPU now via balance_push() or placed on a different CPU
++ * during wakeup. Wait until the CPU is quiescent.
++ */
++static void balance_hotplug_wait(void)
++{
++ struct rq *rq = this_rq();
++
++ rcuwait_wait_event(&rq->hotplug_wait,
++ rq->nr_running == 1 && !rq_has_pinned_tasks(rq),
++ TASK_UNINTERRUPTIBLE);
++}
++
++#else
++
++static void balance_push(struct rq *rq)
++{
++}
++
++static void balance_push_set(int cpu, bool on)
++{
++}
++
++static inline void balance_hotplug_wait(void)
++{
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
++static void set_rq_offline(struct rq *rq)
++{
++ if (rq->online) {
++ update_rq_clock(rq);
++ rq->online = false;
++ }
++}
++
++static void set_rq_online(struct rq *rq)
++{
++ if (!rq->online)
++ rq->online = true;
++}
++
++/*
++ * used to mark begin/end of suspend/resume:
++ */
++static int num_cpus_frozen;
++
++/*
++ * Update cpusets according to cpu_active mask. If cpusets are
++ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
++ * around partition_sched_domains().
++ *
++ * If we come here as part of a suspend/resume, don't touch cpusets because we
++ * want to restore it back to its original state upon resume anyway.
++ */
++static void cpuset_cpu_active(void)
++{
++ if (cpuhp_tasks_frozen) {
++ /*
++ * num_cpus_frozen tracks how many CPUs are involved in suspend
++ * resume sequence. As long as this is not the last online
++ * operation in the resume sequence, just build a single sched
++ * domain, ignoring cpusets.
++ */
++ partition_sched_domains(1, NULL, NULL);
++ if (--num_cpus_frozen)
++ return;
++ /*
++ * This is the last CPU online operation. So fall through and
++ * restore the original sched domains by considering the
++ * cpuset configurations.
++ */
++ cpuset_force_rebuild();
++ }
++
++ cpuset_update_active_cpus();
++}
++
++static int cpuset_cpu_inactive(unsigned int cpu)
++{
++ if (!cpuhp_tasks_frozen) {
++ cpuset_update_active_cpus();
++ } else {
++ num_cpus_frozen++;
++ partition_sched_domains(1, NULL, NULL);
++ }
++ return 0;
++}
++
++int sched_cpu_activate(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ /*
++ * Clear the balance_push callback and prepare to schedule
++ * regular tasks.
++ */
++ balance_push_set(cpu, false);
++
++#ifdef CONFIG_SCHED_SMT
++ /*
++ * When going up, increment the number of cores with SMT present.
++ */
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
++ static_branch_inc_cpuslocked(&sched_smt_present);
++#endif
++ set_cpu_active(cpu, true);
++
++ if (sched_smp_initialized)
++ cpuset_cpu_active();
++
++ /*
++ * Put the rq online, if not already. This happens:
++ *
++ * 1) In the early boot process, because we build the real domains
++ * after all cpus have been brought up.
++ *
++ * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
++ * domains.
++ */
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ set_rq_online(rq);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ return 0;
++}
++
++int sched_cpu_deactivate(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++ int ret;
++
++ set_cpu_active(cpu, false);
++
++ /*
++ * From this point forward, this CPU will refuse to run any task that
++ * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively
++ * push those tasks away until this gets cleared, see
++ * sched_cpu_dying().
++ */
++ balance_push_set(cpu, true);
++
++ /*
++ * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
++ * users of this state to go away such that all new such users will
++ * observe it.
++ *
++ * Specifically, we rely on ttwu to no longer target this CPU, see
++ * ttwu_queue_cond() and is_cpu_allowed().
++ *
++ * Do sync before park smpboot threads to take care the rcu boost case.
++ */
++ synchronize_rcu();
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ set_rq_offline(rq);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++#ifdef CONFIG_SCHED_SMT
++ /*
++ * When going down, decrement the number of cores with SMT present.
++ */
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) {
++ static_branch_dec_cpuslocked(&sched_smt_present);
++ if (!static_branch_likely(&sched_smt_present))
++ cpumask_clear(sched_sg_idle_mask);
++ }
++#endif
++
++ if (!sched_smp_initialized)
++ return 0;
++
++ ret = cpuset_cpu_inactive(cpu);
++ if (ret) {
++ balance_push_set(cpu, false);
++ set_cpu_active(cpu, true);
++ return ret;
++ }
++
++ return 0;
++}
++
++static void sched_rq_cpu_starting(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ rq->calc_load_update = calc_load_update;
++}
++
++int sched_cpu_starting(unsigned int cpu)
++{
++ sched_rq_cpu_starting(cpu);
++ sched_tick_start(cpu);
++ return 0;
++}
++
++#ifdef CONFIG_HOTPLUG_CPU
++
++/*
++ * Invoked immediately before the stopper thread is invoked to bring the
++ * CPU down completely. At this point all per CPU kthreads except the
++ * hotplug thread (current) and the stopper thread (inactive) have been
++ * either parked or have been unbound from the outgoing CPU. Ensure that
++ * any of those which might be on the way out are gone.
++ *
++ * If after this point a bound task is being woken on this CPU then the
++ * responsible hotplug callback has failed to do it's job.
++ * sched_cpu_dying() will catch it with the appropriate fireworks.
++ */
++int sched_cpu_wait_empty(unsigned int cpu)
++{
++ balance_hotplug_wait();
++ return 0;
++}
++
++/*
++ * Since this CPU is going 'away' for a while, fold any nr_active delta we
++ * might have. Called from the CPU stopper task after ensuring that the
++ * stopper is the last running task on the CPU, so nr_active count is
++ * stable. We need to take the teardown thread which is calling this into
++ * account, so we hand in adjust = 1 to the load calculation.
++ *
++ * Also see the comment "Global load-average calculations".
++ */
++static void calc_load_migrate(struct rq *rq)
++{
++ long delta = calc_load_fold_active(rq, 1);
++
++ if (delta)
++ atomic_long_add(delta, &calc_load_tasks);
++}
++
++static void dump_rq_tasks(struct rq *rq, const char *loglvl)
++{
++ struct task_struct *g, *p;
++ int cpu = cpu_of(rq);
++
++ lockdep_assert_held(&rq->lock);
++
++ printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
++ for_each_process_thread(g, p) {
++ if (task_cpu(p) != cpu)
++ continue;
++
++ if (!task_on_rq_queued(p))
++ continue;
++
++ printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm);
++ }
++}
++
++int sched_cpu_dying(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ /* Handle pending wakeups and then migrate everything off */
++ sched_tick_stop(cpu);
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
++ WARN(true, "Dying CPU not properly vacated!");
++ dump_rq_tasks(rq, KERN_WARNING);
++ }
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ calc_load_migrate(rq);
++ hrtick_clear(rq);
++ return 0;
++}
++#endif
++
++#ifdef CONFIG_SMP
++static void sched_init_topology_cpumask_early(void)
++{
++ int cpu;
++ cpumask_t *tmp;
++
++ for_each_possible_cpu(cpu) {
++ /* init topo masks */
++ tmp = per_cpu(sched_cpu_topo_masks, cpu);
++
++ cpumask_copy(tmp, cpu_possible_mask);
++ per_cpu(sched_cpu_llc_mask, cpu) = tmp;
++ per_cpu(sched_cpu_topo_end_mask, cpu) = ++tmp;
++ }
++}
++
++#define TOPOLOGY_CPUMASK(name, mask, last)\
++ if (cpumask_and(topo, topo, mask)) { \
++ cpumask_copy(topo, mask); \
++ printk(KERN_INFO "sched: cpu#%02d topo: 0x%08lx - "#name, \
++ cpu, (topo++)->bits[0]); \
++ } \
++ if (!last) \
++ bitmap_complement(cpumask_bits(topo), cpumask_bits(mask), \
++ nr_cpumask_bits);
++
++static void sched_init_topology_cpumask(void)
++{
++ int cpu;
++ cpumask_t *topo;
++
++ for_each_online_cpu(cpu) {
++ /* take chance to reset time slice for idle tasks */
++ cpu_rq(cpu)->idle->time_slice = sysctl_sched_base_slice;
++
++ topo = per_cpu(sched_cpu_topo_masks, cpu);
++
++ bitmap_complement(cpumask_bits(topo), cpumask_bits(cpumask_of(cpu)),
++ nr_cpumask_bits);
++#ifdef CONFIG_SCHED_SMT
++ TOPOLOGY_CPUMASK(smt, topology_sibling_cpumask(cpu), false);
++#endif
++ TOPOLOGY_CPUMASK(cluster, topology_cluster_cpumask(cpu), false);
++
++ per_cpu(sd_llc_id, cpu) = cpumask_first(cpu_coregroup_mask(cpu));
++ per_cpu(sched_cpu_llc_mask, cpu) = topo;
++ TOPOLOGY_CPUMASK(coregroup, cpu_coregroup_mask(cpu), false);
++
++ TOPOLOGY_CPUMASK(core, topology_core_cpumask(cpu), false);
++
++ TOPOLOGY_CPUMASK(others, cpu_online_mask, true);
++
++ per_cpu(sched_cpu_topo_end_mask, cpu) = topo;
++ printk(KERN_INFO "sched: cpu#%02d llc_id = %d, llc_mask idx = %d\n",
++ cpu, per_cpu(sd_llc_id, cpu),
++ (int) (per_cpu(sched_cpu_llc_mask, cpu) -
++ per_cpu(sched_cpu_topo_masks, cpu)));
++ }
++}
++#endif
++
++void __init sched_init_smp(void)
++{
++ /* Move init over to a non-isolated CPU */
++ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
++ BUG();
++ current->flags &= ~PF_NO_SETAFFINITY;
++
++ sched_init_topology_cpumask();
++
++ sched_smp_initialized = true;
++}
++
++static int __init migration_init(void)
++{
++ sched_cpu_starting(smp_processor_id());
++ return 0;
++}
++early_initcall(migration_init);
++
++#else
++void __init sched_init_smp(void)
++{
++ cpu_rq(0)->idle->time_slice = sysctl_sched_base_slice;
++}
++#endif /* CONFIG_SMP */
++
++int in_sched_functions(unsigned long addr)
++{
++ return in_lock_functions(addr) ||
++ (addr >= (unsigned long)__sched_text_start
++ && addr < (unsigned long)__sched_text_end);
++}
++
++#ifdef CONFIG_CGROUP_SCHED
++/*
++ * Default task group.
++ * Every task in system belongs to this group at bootup.
++ */
++struct task_group root_task_group;
++LIST_HEAD(task_groups);
++
++/* Cacheline aligned slab cache for task_group */
++static struct kmem_cache *task_group_cache __ro_after_init;
++#endif /* CONFIG_CGROUP_SCHED */
++
++void __init sched_init(void)
++{
++ int i;
++ struct rq *rq;
++#ifdef CONFIG_SCHED_SMT
++ struct balance_arg balance_arg = {.cpumask = sched_sg_idle_mask, .active = 0};
++#endif
++
++ printk(KERN_INFO "sched/alt: "ALT_SCHED_NAME" CPU Scheduler "ALT_SCHED_VERSION\
++ " by Alfred Chen.\n");
++
++ wait_bit_init();
++
++#ifdef CONFIG_SMP
++ for (i = 0; i < SCHED_QUEUE_BITS; i++)
++ cpumask_copy(sched_preempt_mask + i, cpu_present_mask);
++#endif
++
++#ifdef CONFIG_CGROUP_SCHED
++ task_group_cache = KMEM_CACHE(task_group, 0);
++
++ list_add(&root_task_group.list, &task_groups);
++ INIT_LIST_HEAD(&root_task_group.children);
++ INIT_LIST_HEAD(&root_task_group.siblings);
++#endif /* CONFIG_CGROUP_SCHED */
++ for_each_possible_cpu(i) {
++ rq = cpu_rq(i);
++
++ sched_queue_init(&rq->queue);
++ rq->prio = IDLE_TASK_SCHED_PRIO;
++#ifdef CONFIG_SCHED_PDS
++ rq->prio_idx = rq->prio;
++#endif
++
++ raw_spin_lock_init(&rq->lock);
++ rq->nr_running = rq->nr_uninterruptible = 0;
++ rq->calc_load_active = 0;
++ rq->calc_load_update = jiffies + LOAD_FREQ;
++#ifdef CONFIG_SMP
++ rq->online = false;
++ rq->cpu = i;
++
++#ifdef CONFIG_SCHED_SMT
++ rq->sg_balance_arg = balance_arg;
++#endif
++
++#ifdef CONFIG_NO_HZ_COMMON
++ INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
++#endif
++ rq->balance_callback = &balance_push_callback;
++#ifdef CONFIG_HOTPLUG_CPU
++ rcuwait_init(&rq->hotplug_wait);
++#endif
++#endif /* CONFIG_SMP */
++ rq->nr_switches = 0;
++
++ hrtick_rq_init(rq);
++ atomic_set(&rq->nr_iowait, 0);
++
++ zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
++ }
++#ifdef CONFIG_SMP
++ /* Set rq->online for cpu 0 */
++ cpu_rq(0)->online = true;
++#endif
++ /*
++ * The boot idle thread does lazy MMU switching as well:
++ */
++ mmgrab(&init_mm);
++ enter_lazy_tlb(&init_mm, current);
++
++ /*
++ * The idle task doesn't need the kthread struct to function, but it
++ * is dressed up as a per-CPU kthread and thus needs to play the part
++ * if we want to avoid special-casing it in code that deals with per-CPU
++ * kthreads.
++ */
++ WARN_ON(!set_kthread_struct(current));
++
++ /*
++ * Make us the idle thread. Technically, schedule() should not be
++ * called from this thread, however somewhere below it might be,
++ * but because we are the idle thread, we just pick up running again
++ * when this runqueue becomes "idle".
++ */
++ init_idle(current, smp_processor_id());
++
++ calc_load_update = jiffies + LOAD_FREQ;
++
++#ifdef CONFIG_SMP
++ idle_thread_set_boot_cpu();
++ balance_push_set(smp_processor_id(), false);
++
++ sched_init_topology_cpumask_early();
++#endif /* SMP */
++
++ preempt_dynamic_init();
++}
++
++#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
++
++void __might_sleep(const char *file, int line)
++{
++ unsigned int state = get_current_state();
++ /*
++ * Blocking primitives will set (and therefore destroy) current->state,
++ * since we will exit with TASK_RUNNING make sure we enter with it,
++ * otherwise we will destroy state.
++ */
++ WARN_ONCE(state != TASK_RUNNING && current->task_state_change,
++ "do not call blocking ops when !TASK_RUNNING; "
++ "state=%x set at [<%p>] %pS\n", state,
++ (void *)current->task_state_change,
++ (void *)current->task_state_change);
++
++ __might_resched(file, line, 0);
++}
++EXPORT_SYMBOL(__might_sleep);
++
++static void print_preempt_disable_ip(int preempt_offset, unsigned long ip)
++{
++ if (!IS_ENABLED(CONFIG_DEBUG_PREEMPT))
++ return;
++
++ if (preempt_count() == preempt_offset)
++ return;
++
++ pr_err("Preemption disabled at:");
++ print_ip_sym(KERN_ERR, ip);
++}
++
++static inline bool resched_offsets_ok(unsigned int offsets)
++{
++ unsigned int nested = preempt_count();
++
++ nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT;
++
++ return nested == offsets;
++}
++
++void __might_resched(const char *file, int line, unsigned int offsets)
++{
++ /* Ratelimiting timestamp: */
++ static unsigned long prev_jiffy;
++
++ unsigned long preempt_disable_ip;
++
++ /* WARN_ON_ONCE() by default, no rate limit required: */
++ rcu_sleep_check();
++
++ if ((resched_offsets_ok(offsets) && !irqs_disabled() &&
++ !is_idle_task(current) && !current->non_block_count) ||
++ system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
++ oops_in_progress)
++ return;
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ /* Save this before calling printk(), since that will clobber it: */
++ preempt_disable_ip = get_preempt_disable_ip(current);
++
++ pr_err("BUG: sleeping function called from invalid context at %s:%d\n",
++ file, line);
++ pr_err("in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(), current->non_block_count,
++ current->pid, current->comm);
++ pr_err("preempt_count: %x, expected: %x\n", preempt_count(),
++ offsets & MIGHT_RESCHED_PREEMPT_MASK);
++
++ if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
++ pr_err("RCU nest depth: %d, expected: %u\n",
++ rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT);
++ }
++
++ if (task_stack_end_corrupted(current))
++ pr_emerg("Thread overran stack, or stack corrupted\n");
++
++ debug_show_held_locks(current);
++ if (irqs_disabled())
++ print_irqtrace_events(current);
++
++ print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK,
++ preempt_disable_ip);
++
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL(__might_resched);
++
++void __cant_sleep(const char *file, int line, int preempt_offset)
++{
++ static unsigned long prev_jiffy;
++
++ if (irqs_disabled())
++ return;
++
++ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
++ return;
++
++ if (preempt_count() > preempt_offset)
++ return;
++
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
++ printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(),
++ current->pid, current->comm);
++
++ debug_show_held_locks(current);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL_GPL(__cant_sleep);
++
++#ifdef CONFIG_SMP
++void __cant_migrate(const char *file, int line)
++{
++ static unsigned long prev_jiffy;
++
++ if (irqs_disabled())
++ return;
++
++ if (is_migration_disabled(current))
++ return;
++
++ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
++ return;
++
++ if (preempt_count() > 0)
++ return;
++
++ if (current->migration_flags & MDF_FORCE_ENABLED)
++ return;
++
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
++ pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(), is_migration_disabled(current),
++ current->pid, current->comm);
++
++ debug_show_held_locks(current);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL_GPL(__cant_migrate);
++#endif
++#endif
++
++#ifdef CONFIG_MAGIC_SYSRQ
++void normalize_rt_tasks(void)
++{
++ struct task_struct *g, *p;
++ struct sched_attr attr = {
++ .sched_policy = SCHED_NORMAL,
++ };
++
++ read_lock(&tasklist_lock);
++ for_each_process_thread(g, p) {
++ /*
++ * Only normalize user tasks:
++ */
++ if (p->flags & PF_KTHREAD)
++ continue;
++
++ schedstat_set(p->stats.wait_start, 0);
++ schedstat_set(p->stats.sleep_start, 0);
++ schedstat_set(p->stats.block_start, 0);
++
++ if (!rt_task(p)) {
++ /*
++ * Renice negative nice level userspace
++ * tasks back to 0:
++ */
++ if (task_nice(p) < 0)
++ set_user_nice(p, 0);
++ continue;
++ }
++
++ __sched_setscheduler(p, &attr, false, false);
++ }
++ read_unlock(&tasklist_lock);
++}
++#endif /* CONFIG_MAGIC_SYSRQ */
++
++#if defined(CONFIG_KGDB_KDB)
++/*
++ * These functions are only useful for kdb.
++ *
++ * They can only be called when the whole system has been
++ * stopped - every CPU needs to be quiescent, and no scheduling
++ * activity can take place. Using them for anything else would
++ * be a serious bug, and as a result, they aren't even visible
++ * under any other configuration.
++ */
++
++/**
++ * curr_task - return the current task for a given CPU.
++ * @cpu: the processor in question.
++ *
++ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
++ *
++ * Return: The current task for @cpu.
++ */
++struct task_struct *curr_task(int cpu)
++{
++ return cpu_curr(cpu);
++}
++
++#endif /* defined(CONFIG_KGDB_KDB) */
++
++#ifdef CONFIG_CGROUP_SCHED
++static void sched_free_group(struct task_group *tg)
++{
++ kmem_cache_free(task_group_cache, tg);
++}
++
++static void sched_free_group_rcu(struct rcu_head *rhp)
++{
++ sched_free_group(container_of(rhp, struct task_group, rcu));
++}
++
++static void sched_unregister_group(struct task_group *tg)
++{
++ /*
++ * We have to wait for yet another RCU grace period to expire, as
++ * print_cfs_stats() might run concurrently.
++ */
++ call_rcu(&tg->rcu, sched_free_group_rcu);
++}
++
++/* allocate runqueue etc for a new task group */
++struct task_group *sched_create_group(struct task_group *parent)
++{
++ struct task_group *tg;
++
++ tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
++ if (!tg)
++ return ERR_PTR(-ENOMEM);
++
++ return tg;
++}
++
++void sched_online_group(struct task_group *tg, struct task_group *parent)
++{
++}
++
++/* rcu callback to free various structures associated with a task group */
++static void sched_unregister_group_rcu(struct rcu_head *rhp)
++{
++ /* Now it should be safe to free those cfs_rqs: */
++ sched_unregister_group(container_of(rhp, struct task_group, rcu));
++}
++
++void sched_destroy_group(struct task_group *tg)
++{
++ /* Wait for possible concurrent references to cfs_rqs complete: */
++ call_rcu(&tg->rcu, sched_unregister_group_rcu);
++}
++
++void sched_release_group(struct task_group *tg)
++{
++}
++
++static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
++{
++ return css ? container_of(css, struct task_group, css) : NULL;
++}
++
++static struct cgroup_subsys_state *
++cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
++{
++ struct task_group *parent = css_tg(parent_css);
++ struct task_group *tg;
++
++ if (!parent) {
++ /* This is early initialization for the top cgroup */
++ return &root_task_group.css;
++ }
++
++ tg = sched_create_group(parent);
++ if (IS_ERR(tg))
++ return ERR_PTR(-ENOMEM);
++ return &tg->css;
++}
++
++/* Expose task group only after completing cgroup initialization */
++static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++ struct task_group *parent = css_tg(css->parent);
++
++ if (parent)
++ sched_online_group(tg, parent);
++ return 0;
++}
++
++static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++
++ sched_release_group(tg);
++}
++
++static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++
++ /*
++ * Relies on the RCU grace period between css_released() and this.
++ */
++ sched_unregister_group(tg);
++}
++
++#ifdef CONFIG_RT_GROUP_SCHED
++static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
++{
++ return 0;
++}
++#endif
++
++static void cpu_cgroup_attach(struct cgroup_taskset *tset)
++{
++}
++
++#ifdef CONFIG_FAIR_GROUP_SCHED
++static DEFINE_MUTEX(shares_mutex);
++
++static int sched_group_set_shares(struct task_group *tg, unsigned long shares)
++{
++ /*
++ * We can't change the weight of the root cgroup.
++ */
++ if (&root_task_group == tg)
++ return -EINVAL;
++
++ shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
++
++ mutex_lock(&shares_mutex);
++ if (tg->shares == shares)
++ goto done;
++
++ tg->shares = shares;
++done:
++ mutex_unlock(&shares_mutex);
++ return 0;
++}
++
++static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 shareval)
++{
++ if (shareval > scale_load_down(ULONG_MAX))
++ shareval = MAX_SHARES;
++ return sched_group_set_shares(css_tg(css), scale_load(shareval));
++}
++
++static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ struct task_group *tg = css_tg(css);
++
++ return (u64) scale_load_down(tg->shares);
++}
++#endif
++
++static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, s64 cfs_quota_us)
++{
++ return 0;
++}
++
++static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 cfs_period_us)
++{
++ return 0;
++}
++
++static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 cfs_burst_us)
++{
++ return 0;
++}
++
++static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 val)
++{
++ return 0;
++}
++
++static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 rt_period_us)
++{
++ return 0;
++}
++
++static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes,
++ loff_t off)
++{
++ return nbytes;
++}
++
++static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes,
++ loff_t off)
++{
++ return nbytes;
++}
++
++static struct cftype cpu_legacy_files[] = {
++#ifdef CONFIG_FAIR_GROUP_SCHED
++ {
++ .name = "shares",
++ .read_u64 = cpu_shares_read_u64,
++ .write_u64 = cpu_shares_write_u64,
++ },
++#endif
++ {
++ .name = "cfs_quota_us",
++ .read_s64 = cpu_cfs_quota_read_s64,
++ .write_s64 = cpu_cfs_quota_write_s64,
++ },
++ {
++ .name = "cfs_period_us",
++ .read_u64 = cpu_cfs_period_read_u64,
++ .write_u64 = cpu_cfs_period_write_u64,
++ },
++ {
++ .name = "cfs_burst_us",
++ .read_u64 = cpu_cfs_burst_read_u64,
++ .write_u64 = cpu_cfs_burst_write_u64,
++ },
++ {
++ .name = "stat",
++ .seq_show = cpu_cfs_stat_show,
++ },
++ {
++ .name = "stat.local",
++ .seq_show = cpu_cfs_local_stat_show,
++ },
++ {
++ .name = "rt_runtime_us",
++ .read_s64 = cpu_rt_runtime_read,
++ .write_s64 = cpu_rt_runtime_write,
++ },
++ {
++ .name = "rt_period_us",
++ .read_u64 = cpu_rt_period_read_uint,
++ .write_u64 = cpu_rt_period_write_uint,
++ },
++ {
++ .name = "uclamp.min",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_min_show,
++ .write = cpu_uclamp_min_write,
++ },
++ {
++ .name = "uclamp.max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_max_show,
++ .write = cpu_uclamp_max_write,
++ },
++ { } /* Terminate */
++};
++
++static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft, u64 weight)
++{
++ return 0;
++}
++
++static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 nice)
++{
++ return 0;
++}
++
++static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 idle)
++{
++ return 0;
++}
++
++static int cpu_max_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static ssize_t cpu_max_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes, loff_t off)
++{
++ return nbytes;
++}
++
++static struct cftype cpu_files[] = {
++ {
++ .name = "weight",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_u64 = cpu_weight_read_u64,
++ .write_u64 = cpu_weight_write_u64,
++ },
++ {
++ .name = "weight.nice",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_s64 = cpu_weight_nice_read_s64,
++ .write_s64 = cpu_weight_nice_write_s64,
++ },
++ {
++ .name = "idle",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_s64 = cpu_idle_read_s64,
++ .write_s64 = cpu_idle_write_s64,
++ },
++ {
++ .name = "max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_max_show,
++ .write = cpu_max_write,
++ },
++ {
++ .name = "max.burst",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_u64 = cpu_cfs_burst_read_u64,
++ .write_u64 = cpu_cfs_burst_write_u64,
++ },
++ {
++ .name = "uclamp.min",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_min_show,
++ .write = cpu_uclamp_min_write,
++ },
++ {
++ .name = "uclamp.max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_max_show,
++ .write = cpu_uclamp_max_write,
++ },
++ { } /* terminate */
++};
++
++static int cpu_extra_stat_show(struct seq_file *sf,
++ struct cgroup_subsys_state *css)
++{
++ return 0;
++}
++
++static int cpu_local_stat_show(struct seq_file *sf,
++ struct cgroup_subsys_state *css)
++{
++ return 0;
++}
++
++struct cgroup_subsys cpu_cgrp_subsys = {
++ .css_alloc = cpu_cgroup_css_alloc,
++ .css_online = cpu_cgroup_css_online,
++ .css_released = cpu_cgroup_css_released,
++ .css_free = cpu_cgroup_css_free,
++ .css_extra_stat_show = cpu_extra_stat_show,
++ .css_local_stat_show = cpu_local_stat_show,
++#ifdef CONFIG_RT_GROUP_SCHED
++ .can_attach = cpu_cgroup_can_attach,
++#endif
++ .attach = cpu_cgroup_attach,
++ .legacy_cftypes = cpu_legacy_files,
++ .dfl_cftypes = cpu_files,
++ .early_init = true,
++ .threaded = true,
++};
++#endif /* CONFIG_CGROUP_SCHED */
++
++#undef CREATE_TRACE_POINTS
++
++#ifdef CONFIG_SCHED_MM_CID
++
++#
++/*
++ * @cid_lock: Guarantee forward-progress of cid allocation.
++ *
++ * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock
++ * is only used when contention is detected by the lock-free allocation so
++ * forward progress can be guaranteed.
++ */
++DEFINE_RAW_SPINLOCK(cid_lock);
++
++/*
++ * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock.
++ *
++ * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is
++ * detected, it is set to 1 to ensure that all newly coming allocations are
++ * serialized by @cid_lock until the allocation which detected contention
++ * completes and sets @use_cid_lock back to 0. This guarantees forward progress
++ * of a cid allocation.
++ */
++int use_cid_lock;
++
++/*
++ * mm_cid remote-clear implements a lock-free algorithm to clear per-mm/cpu cid
++ * concurrently with respect to the execution of the source runqueue context
++ * switch.
++ *
++ * There is one basic properties we want to guarantee here:
++ *
++ * (1) Remote-clear should _never_ mark a per-cpu cid UNSET when it is actively
++ * used by a task. That would lead to concurrent allocation of the cid and
++ * userspace corruption.
++ *
++ * Provide this guarantee by introducing a Dekker memory ordering to guarantee
++ * that a pair of loads observe at least one of a pair of stores, which can be
++ * shown as:
++ *
++ * X = Y = 0
++ *
++ * w[X]=1 w[Y]=1
++ * MB MB
++ * r[Y]=y r[X]=x
++ *
++ * Which guarantees that x==0 && y==0 is impossible. But rather than using
++ * values 0 and 1, this algorithm cares about specific state transitions of the
++ * runqueue current task (as updated by the scheduler context switch), and the
++ * per-mm/cpu cid value.
++ *
++ * Let's introduce task (Y) which has task->mm == mm and task (N) which has
++ * task->mm != mm for the rest of the discussion. There are two scheduler state
++ * transitions on context switch we care about:
++ *
++ * (TSA) Store to rq->curr with transition from (N) to (Y)
++ *
++ * (TSB) Store to rq->curr with transition from (Y) to (N)
++ *
++ * On the remote-clear side, there is one transition we care about:
++ *
++ * (TMA) cmpxchg to *pcpu_cid to set the LAZY flag
++ *
++ * There is also a transition to UNSET state which can be performed from all
++ * sides (scheduler, remote-clear). It is always performed with a cmpxchg which
++ * guarantees that only a single thread will succeed:
++ *
++ * (TMB) cmpxchg to *pcpu_cid to mark UNSET
++ *
++ * Just to be clear, what we do _not_ want to happen is a transition to UNSET
++ * when a thread is actively using the cid (property (1)).
++ *
++ * Let's looks at the relevant combinations of TSA/TSB, and TMA transitions.
++ *
++ * Scenario A) (TSA)+(TMA) (from next task perspective)
++ *
++ * CPU0 CPU1
++ *
++ * Context switch CS-1 Remote-clear
++ * - store to rq->curr: (N)->(Y) (TSA) - cmpxchg to *pcpu_id to LAZY (TMA)
++ * (implied barrier after cmpxchg)
++ * - switch_mm_cid()
++ * - memory barrier (see switch_mm_cid()
++ * comment explaining how this barrier
++ * is combined with other scheduler
++ * barriers)
++ * - mm_cid_get (next)
++ * - READ_ONCE(*pcpu_cid) - rcu_dereference(src_rq->curr)
++ *
++ * This Dekker ensures that either task (Y) is observed by the
++ * rcu_dereference() or the LAZY flag is observed by READ_ONCE(), or both are
++ * observed.
++ *
++ * If task (Y) store is observed by rcu_dereference(), it means that there is
++ * still an active task on the cpu. Remote-clear will therefore not transition
++ * to UNSET, which fulfills property (1).
++ *
++ * If task (Y) is not observed, but the lazy flag is observed by READ_ONCE(),
++ * it will move its state to UNSET, which clears the percpu cid perhaps
++ * uselessly (which is not an issue for correctness). Because task (Y) is not
++ * observed, CPU1 can move ahead to set the state to UNSET. Because moving
++ * state to UNSET is done with a cmpxchg expecting that the old state has the
++ * LAZY flag set, only one thread will successfully UNSET.
++ *
++ * If both states (LAZY flag and task (Y)) are observed, the thread on CPU0
++ * will observe the LAZY flag and transition to UNSET (perhaps uselessly), and
++ * CPU1 will observe task (Y) and do nothing more, which is fine.
++ *
++ * What we are effectively preventing with this Dekker is a scenario where
++ * neither LAZY flag nor store (Y) are observed, which would fail property (1)
++ * because this would UNSET a cid which is actively used.
++ */
++
++void sched_mm_cid_migrate_from(struct task_struct *t)
++{
++ t->migrate_from_cpu = task_cpu(t);
++}
++
++static
++int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
++ struct task_struct *t,
++ struct mm_cid *src_pcpu_cid)
++{
++ struct mm_struct *mm = t->mm;
++ struct task_struct *src_task;
++ int src_cid, last_mm_cid;
++
++ if (!mm)
++ return -1;
++
++ last_mm_cid = t->last_mm_cid;
++ /*
++ * If the migrated task has no last cid, or if the current
++ * task on src rq uses the cid, it means the source cid does not need
++ * to be moved to the destination cpu.
++ */
++ if (last_mm_cid == -1)
++ return -1;
++ src_cid = READ_ONCE(src_pcpu_cid->cid);
++ if (!mm_cid_is_valid(src_cid) || last_mm_cid != src_cid)
++ return -1;
++
++ /*
++ * If we observe an active task using the mm on this rq, it means we
++ * are not the last task to be migrated from this cpu for this mm, so
++ * there is no need to move src_cid to the destination cpu.
++ */
++ rcu_read_lock();
++ src_task = rcu_dereference(src_rq->curr);
++ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
++ rcu_read_unlock();
++ t->last_mm_cid = -1;
++ return -1;
++ }
++ rcu_read_unlock();
++
++ return src_cid;
++}
++
++static
++int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
++ struct task_struct *t,
++ struct mm_cid *src_pcpu_cid,
++ int src_cid)
++{
++ struct task_struct *src_task;
++ struct mm_struct *mm = t->mm;
++ int lazy_cid;
++
++ if (src_cid == -1)
++ return -1;
++
++ /*
++ * Attempt to clear the source cpu cid to move it to the destination
++ * cpu.
++ */
++ lazy_cid = mm_cid_set_lazy_put(src_cid);
++ if (!try_cmpxchg(&src_pcpu_cid->cid, &src_cid, lazy_cid))
++ return -1;
++
++ /*
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm matches the scheduler barrier in context_switch()
++ * between store to rq->curr and load of prev and next task's
++ * per-mm/cpu cid.
++ *
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm_cid_active matches the barrier in
++ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
++ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
++ * load of per-mm/cpu cid.
++ */
++
++ /*
++ * If we observe an active task using the mm on this rq after setting
++ * the lazy-put flag, this task will be responsible for transitioning
++ * from lazy-put flag set to MM_CID_UNSET.
++ */
++ scoped_guard (rcu) {
++ src_task = rcu_dereference(src_rq->curr);
++ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
++ rcu_read_unlock();
++ /*
++ * We observed an active task for this mm, there is therefore
++ * no point in moving this cid to the destination cpu.
++ */
++ t->last_mm_cid = -1;
++ return -1;
++ }
++ }
++
++ /*
++ * The src_cid is unused, so it can be unset.
++ */
++ if (!try_cmpxchg(&src_pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
++ return -1;
++ return src_cid;
++}
++
++/*
++ * Migration to dst cpu. Called with dst_rq lock held.
++ * Interrupts are disabled, which keeps the window of cid ownership without the
++ * source rq lock held small.
++ */
++void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu)
++{
++ struct mm_cid *src_pcpu_cid, *dst_pcpu_cid;
++ struct mm_struct *mm = t->mm;
++ int src_cid, dst_cid;
++ struct rq *src_rq;
++
++ lockdep_assert_rq_held(dst_rq);
++
++ if (!mm)
++ return;
++ if (src_cpu == -1) {
++ t->last_mm_cid = -1;
++ return;
++ }
++ /*
++ * Move the src cid if the dst cid is unset. This keeps id
++ * allocation closest to 0 in cases where few threads migrate around
++ * many cpus.
++ *
++ * If destination cid is already set, we may have to just clear
++ * the src cid to ensure compactness in frequent migrations
++ * scenarios.
++ *
++ * It is not useful to clear the src cid when the number of threads is
++ * greater or equal to the number of allowed cpus, because user-space
++ * can expect that the number of allowed cids can reach the number of
++ * allowed cpus.
++ */
++ dst_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(dst_rq));
++ dst_cid = READ_ONCE(dst_pcpu_cid->cid);
++ if (!mm_cid_is_unset(dst_cid) &&
++ atomic_read(&mm->mm_users) >= t->nr_cpus_allowed)
++ return;
++ src_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, src_cpu);
++ src_rq = cpu_rq(src_cpu);
++ src_cid = __sched_mm_cid_migrate_from_fetch_cid(src_rq, t, src_pcpu_cid);
++ if (src_cid == -1)
++ return;
++ src_cid = __sched_mm_cid_migrate_from_try_steal_cid(src_rq, t, src_pcpu_cid,
++ src_cid);
++ if (src_cid == -1)
++ return;
++ if (!mm_cid_is_unset(dst_cid)) {
++ __mm_cid_put(mm, src_cid);
++ return;
++ }
++ /* Move src_cid to dst cpu. */
++ mm_cid_snapshot_time(dst_rq, mm);
++ WRITE_ONCE(dst_pcpu_cid->cid, src_cid);
++}
++
++static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_cid,
++ int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct task_struct *t;
++ int cid, lazy_cid;
++
++ cid = READ_ONCE(pcpu_cid->cid);
++ if (!mm_cid_is_valid(cid))
++ return;
++
++ /*
++ * Clear the cpu cid if it is set to keep cid allocation compact. If
++ * there happens to be other tasks left on the source cpu using this
++ * mm, the next task using this mm will reallocate its cid on context
++ * switch.
++ */
++ lazy_cid = mm_cid_set_lazy_put(cid);
++ if (!try_cmpxchg(&pcpu_cid->cid, &cid, lazy_cid))
++ return;
++
++ /*
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm matches the scheduler barrier in context_switch()
++ * between store to rq->curr and load of prev and next task's
++ * per-mm/cpu cid.
++ *
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm_cid_active matches the barrier in
++ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
++ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
++ * load of per-mm/cpu cid.
++ */
++
++ /*
++ * If we observe an active task using the mm on this rq after setting
++ * the lazy-put flag, that task will be responsible for transitioning
++ * from lazy-put flag set to MM_CID_UNSET.
++ */
++ scoped_guard (rcu) {
++ t = rcu_dereference(rq->curr);
++ if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
++ return;
++ }
++
++ /*
++ * The cid is unused, so it can be unset.
++ * Disable interrupts to keep the window of cid ownership without rq
++ * lock small.
++ */
++ scoped_guard (irqsave) {
++ if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
++ __mm_cid_put(mm, cid);
++ }
++}
++
++static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct mm_cid *pcpu_cid;
++ struct task_struct *curr;
++ u64 rq_clock;
++
++ /*
++ * rq->clock load is racy on 32-bit but one spurious clear once in a
++ * while is irrelevant.
++ */
++ rq_clock = READ_ONCE(rq->clock);
++ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
++
++ /*
++ * In order to take care of infrequently scheduled tasks, bump the time
++ * snapshot associated with this cid if an active task using the mm is
++ * observed on this rq.
++ */
++ scoped_guard (rcu) {
++ curr = rcu_dereference(rq->curr);
++ if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
++ WRITE_ONCE(pcpu_cid->time, rq_clock);
++ return;
++ }
++ }
++
++ if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
++ return;
++ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
++}
++
++static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu,
++ int weight)
++{
++ struct mm_cid *pcpu_cid;
++ int cid;
++
++ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
++ cid = READ_ONCE(pcpu_cid->cid);
++ if (!mm_cid_is_valid(cid) || cid < weight)
++ return;
++ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
++}
++
++static void task_mm_cid_work(struct callback_head *work)
++{
++ unsigned long now = jiffies, old_scan, next_scan;
++ struct task_struct *t = current;
++ struct cpumask *cidmask;
++ struct mm_struct *mm;
++ int weight, cpu;
++
++ SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work));
++
++ work->next = work; /* Prevent double-add */
++ if (t->flags & PF_EXITING)
++ return;
++ mm = t->mm;
++ if (!mm)
++ return;
++ old_scan = READ_ONCE(mm->mm_cid_next_scan);
++ next_scan = now + msecs_to_jiffies(MM_CID_SCAN_DELAY);
++ if (!old_scan) {
++ unsigned long res;
++
++ res = cmpxchg(&mm->mm_cid_next_scan, old_scan, next_scan);
++ if (res != old_scan)
++ old_scan = res;
++ else
++ old_scan = next_scan;
++ }
++ if (time_before(now, old_scan))
++ return;
++ if (!try_cmpxchg(&mm->mm_cid_next_scan, &old_scan, next_scan))
++ return;
++ cidmask = mm_cidmask(mm);
++ /* Clear cids that were not recently used. */
++ for_each_possible_cpu(cpu)
++ sched_mm_cid_remote_clear_old(mm, cpu);
++ weight = cpumask_weight(cidmask);
++ /*
++ * Clear cids that are greater or equal to the cidmask weight to
++ * recompact it.
++ */
++ for_each_possible_cpu(cpu)
++ sched_mm_cid_remote_clear_weight(mm, cpu, weight);
++}
++
++void init_sched_mm_cid(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ int mm_users = 0;
++
++ if (mm) {
++ mm_users = atomic_read(&mm->mm_users);
++ if (mm_users == 1)
++ mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY);
++ }
++ t->cid_work.next = &t->cid_work; /* Protect against double add */
++ init_task_work(&t->cid_work, task_mm_cid_work);
++}
++
++void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
++{
++ struct callback_head *work = &curr->cid_work;
++ unsigned long now = jiffies;
++
++ if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) ||
++ work->next != work)
++ return;
++ if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan)))
++ return;
++ task_work_add(curr, work, TWA_RESUME);
++}
++
++void sched_mm_cid_exit_signals(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ guard(rq_lock_irqsave)(rq);
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 0);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ mm_cid_put(mm);
++ t->last_mm_cid = t->mm_cid = -1;
++}
++
++void sched_mm_cid_before_execve(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ guard(rq_lock_irqsave)(rq);
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 0);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ mm_cid_put(mm);
++ t->last_mm_cid = t->mm_cid = -1;
++}
++
++void sched_mm_cid_after_execve(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ scoped_guard (rq_lock_irqsave, rq) {
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 1);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
++ }
++ rseq_set_notify_resume(t);
++}
++
++void sched_mm_cid_fork(struct task_struct *t)
++{
++ WARN_ON_ONCE(!t->mm || t->mm_cid != -1);
++ t->mm_cid_active = 1;
++}
++#endif
+diff --git a/kernel/sched/alt_debug.c b/kernel/sched/alt_debug.c
+--- a/kernel/sched/alt_debug.c 1970-01-01 01:00:00.000000000 +0100
++++ b/kernel/sched/alt_debug.c 2024-07-16 11:57:44.445146416 +0200
+@@ -0,0 +1,32 @@
++/*
++ * kernel/sched/alt_debug.c
++ *
++ * Print the alt scheduler debugging details
++ *
++ * Author: Alfred Chen
++ * Date : 2020
++ */
++#include "sched.h"
++#include "linux/sched/debug.h"
++
++/*
++ * This allows printing both to /proc/sched_debug and
++ * to the console
++ */
++#define SEQ_printf(m, x...) \
++ do { \
++ if (m) \
++ seq_printf(m, x); \
++ else \
++ pr_cont(x); \
++ } while (0)
++
++void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
++ struct seq_file *m)
++{
++ SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns),
++ get_nr_threads(p));
++}
++
++void proc_sched_set_task(struct task_struct *p)
++{}
+diff --git a/kernel/sched/alt_sched.h b/kernel/sched/alt_sched.h
+--- a/kernel/sched/alt_sched.h 1970-01-01 01:00:00.000000000 +0100
++++ b/kernel/sched/alt_sched.h 2024-07-16 11:57:44.445146416 +0200
+@@ -0,0 +1,976 @@
++#ifndef ALT_SCHED_H
++#define ALT_SCHED_H
++
++#include <linux/context_tracking.h>
++#include <linux/profile.h>
++#include <linux/stop_machine.h>
++#include <linux/syscalls.h>
++#include <linux/tick.h>
++
++#include <trace/events/power.h>
++#include <trace/events/sched.h>
++
++#include "../workqueue_internal.h"
++
++#include "cpupri.h"
++
++#ifdef CONFIG_CGROUP_SCHED
++/* task group related information */
++struct task_group {
++ struct cgroup_subsys_state css;
++
++ struct rcu_head rcu;
++ struct list_head list;
++
++ struct task_group *parent;
++ struct list_head siblings;
++ struct list_head children;
++#ifdef CONFIG_FAIR_GROUP_SCHED
++ unsigned long shares;
++#endif
++};
++
++extern struct task_group *sched_create_group(struct task_group *parent);
++extern void sched_online_group(struct task_group *tg,
++ struct task_group *parent);
++extern void sched_destroy_group(struct task_group *tg);
++extern void sched_release_group(struct task_group *tg);
++#endif /* CONFIG_CGROUP_SCHED */
++
++#define MIN_SCHED_NORMAL_PRIO (32)
++/*
++ * levels: RT(0-24), reserved(25-31), NORMAL(32-63), cpu idle task(64)
++ *
++ * -- BMQ --
++ * NORMAL: (lower boost range 12, NICE_WIDTH 40, higher boost range 12) / 2
++ * -- PDS --
++ * NORMAL: SCHED_EDGE_DELTA + ((NICE_WIDTH 40) / 2)
++ */
++#define SCHED_LEVELS (64 + 1)
++
++#define IDLE_TASK_SCHED_PRIO (SCHED_LEVELS - 1)
++
++#ifdef CONFIG_SCHED_DEBUG
++# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
++extern void resched_latency_warn(int cpu, u64 latency);
++#else
++# define SCHED_WARN_ON(x) ({ (void)(x), 0; })
++static inline void resched_latency_warn(int cpu, u64 latency) {}
++#endif
++
++/*
++ * Increase resolution of nice-level calculations for 64-bit architectures.
++ * The extra resolution improves shares distribution and load balancing of
++ * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
++ * hierarchies, especially on larger systems. This is not a user-visible change
++ * and does not change the user-interface for setting shares/weights.
++ *
++ * We increase resolution only if we have enough bits to allow this increased
++ * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
++ * are pretty high and the returns do not justify the increased costs.
++ *
++ * Really only required when CONFIG_FAIR_GROUP_SCHED=y is also set, but to
++ * increase coverage and consistency always enable it on 64-bit platforms.
++ */
++#ifdef CONFIG_64BIT
++# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
++# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
++# define scale_load_down(w) \
++({ \
++ unsigned long __w = (w); \
++ if (__w) \
++ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
++ __w; \
++})
++#else
++# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
++# define scale_load(w) (w)
++# define scale_load_down(w) (w)
++#endif
++
++#ifdef CONFIG_FAIR_GROUP_SCHED
++#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
++
++/*
++ * A weight of 0 or 1 can cause arithmetics problems.
++ * A weight of a cfs_rq is the sum of weights of which entities
++ * are queued on this cfs_rq, so a weight of a entity should not be
++ * too large, so as the shares value of a task group.
++ * (The default weight is 1024 - so there's no practical
++ * limitation from this.)
++ */
++#define MIN_SHARES (1UL << 1)
++#define MAX_SHARES (1UL << 18)
++#endif
++
++/*
++ * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
++ */
++#ifdef CONFIG_SCHED_DEBUG
++# define const_debug __read_mostly
++#else
++# define const_debug const
++#endif
++
++/* task_struct::on_rq states: */
++#define TASK_ON_RQ_QUEUED 1
++#define TASK_ON_RQ_MIGRATING 2
++
++static inline int task_on_rq_queued(struct task_struct *p)
++{
++ return p->on_rq == TASK_ON_RQ_QUEUED;
++}
++
++static inline int task_on_rq_migrating(struct task_struct *p)
++{
++ return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
++}
++
++/* Wake flags. The first three directly map to some SD flag value */
++#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
++#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
++#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
++
++#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
++#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
++#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
++
++#ifdef CONFIG_SMP
++static_assert(WF_EXEC == SD_BALANCE_EXEC);
++static_assert(WF_FORK == SD_BALANCE_FORK);
++static_assert(WF_TTWU == SD_BALANCE_WAKE);
++#endif
++
++#define SCHED_QUEUE_BITS (SCHED_LEVELS - 1)
++
++struct sched_queue {
++ DECLARE_BITMAP(bitmap, SCHED_QUEUE_BITS);
++ struct list_head heads[SCHED_LEVELS];
++};
++
++struct rq;
++struct cpuidle_state;
++
++struct balance_callback {
++ struct balance_callback *next;
++ void (*func)(struct rq *rq);
++};
++
++struct balance_arg {
++ struct task_struct *task;
++ int active;
++ cpumask_t *cpumask;
++};
++
++/*
++ * This is the main, per-CPU runqueue data structure.
++ * This data should only be modified by the local cpu.
++ */
++struct rq {
++ /* runqueue lock: */
++ raw_spinlock_t lock;
++
++ struct task_struct __rcu *curr;
++ struct task_struct *idle;
++ struct task_struct *stop;
++ struct mm_struct *prev_mm;
++
++ struct sched_queue queue ____cacheline_aligned;
++
++ int prio;
++#ifdef CONFIG_SCHED_PDS
++ int prio_idx;
++ u64 time_edge;
++#endif
++
++ /* switch count */
++ u64 nr_switches;
++
++ atomic_t nr_iowait;
++
++#ifdef CONFIG_SCHED_DEBUG
++ u64 last_seen_need_resched_ns;
++ int ticks_without_resched;
++#endif
++
++#ifdef CONFIG_MEMBARRIER
++ int membarrier_state;
++#endif
++
++#ifdef CONFIG_SMP
++ int cpu; /* cpu of this runqueue */
++ bool online;
++
++ unsigned int ttwu_pending;
++ unsigned char nohz_idle_balance;
++ unsigned char idle_balance;
++
++#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
++ struct sched_avg avg_irq;
++#endif
++
++#ifdef CONFIG_SCHED_SMT
++ struct balance_arg sg_balance_arg ____cacheline_aligned;
++#endif
++ struct cpu_stop_work active_balance_work;
++
++ struct balance_callback *balance_callback;
++#ifdef CONFIG_HOTPLUG_CPU
++ struct rcuwait hotplug_wait;
++#endif
++ unsigned int nr_pinned;
++
++#endif /* CONFIG_SMP */
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ u64 prev_irq_time;
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++#ifdef CONFIG_PARAVIRT
++ u64 prev_steal_time;
++#endif /* CONFIG_PARAVIRT */
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ u64 prev_steal_time_rq;
++#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */
++
++ /* For genenal cpu load util */
++ s32 load_history;
++ u64 load_block;
++ u64 load_stamp;
++
++ /* calc_load related fields */
++ unsigned long calc_load_update;
++ long calc_load_active;
++
++ /* Ensure that all clocks are in the same cache line */
++ u64 clock ____cacheline_aligned;
++ u64 clock_task;
++
++ unsigned int nr_running;
++ unsigned long nr_uninterruptible;
++
++#ifdef CONFIG_SCHED_HRTICK
++#ifdef CONFIG_SMP
++ call_single_data_t hrtick_csd;
++#endif
++ struct hrtimer hrtick_timer;
++ ktime_t hrtick_time;
++#endif
++
++#ifdef CONFIG_SCHEDSTATS
++
++ /* latency stats */
++ struct sched_info rq_sched_info;
++ unsigned long long rq_cpu_time;
++ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
++
++ /* sys_sched_yield() stats */
++ unsigned int yld_count;
++
++ /* schedule() stats */
++ unsigned int sched_switch;
++ unsigned int sched_count;
++ unsigned int sched_goidle;
++
++ /* try_to_wake_up() stats */
++ unsigned int ttwu_count;
++ unsigned int ttwu_local;
++#endif /* CONFIG_SCHEDSTATS */
++
++#ifdef CONFIG_CPU_IDLE
++ /* Must be inspected within a rcu lock section */
++ struct cpuidle_state *idle_state;
++#endif
++
++#ifdef CONFIG_NO_HZ_COMMON
++#ifdef CONFIG_SMP
++ call_single_data_t nohz_csd;
++#endif
++ atomic_t nohz_flags;
++#endif /* CONFIG_NO_HZ_COMMON */
++
++ /* Scratch cpumask to be temporarily used under rq_lock */
++ cpumask_var_t scratch_mask;
++};
++
++extern unsigned int sysctl_sched_base_slice;
++
++extern unsigned long rq_load_util(struct rq *rq, unsigned long max);
++
++extern unsigned long calc_load_update;
++extern atomic_long_t calc_load_tasks;
++
++extern void calc_global_load_tick(struct rq *this_rq);
++extern long calc_load_fold_active(struct rq *this_rq, long adjust);
++
++DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
++#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
++#define this_rq() this_cpu_ptr(&runqueues)
++#define task_rq(p) cpu_rq(task_cpu(p))
++#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
++#define raw_rq() raw_cpu_ptr(&runqueues)
++
++#ifdef CONFIG_SMP
++#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
++void register_sched_domain_sysctl(void);
++void unregister_sched_domain_sysctl(void);
++#else
++static inline void register_sched_domain_sysctl(void)
++{
++}
++static inline void unregister_sched_domain_sysctl(void)
++{
++}
++#endif
++
++extern bool sched_smp_initialized;
++
++enum {
++#ifdef CONFIG_SCHED_SMT
++ SMT_LEVEL_SPACE_HOLDER,
++#endif
++ COREGROUP_LEVEL_SPACE_HOLDER,
++ CORE_LEVEL_SPACE_HOLDER,
++ OTHER_LEVEL_SPACE_HOLDER,
++ NR_CPU_AFFINITY_LEVELS
++};
++
++DECLARE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
++
++static inline int
++__best_mask_cpu(const cpumask_t *cpumask, const cpumask_t *mask)
++{
++ int cpu;
++
++ while ((cpu = cpumask_any_and(cpumask, mask)) >= nr_cpu_ids)
++ mask++;
++
++ return cpu;
++}
++
++static inline int best_mask_cpu(int cpu, const cpumask_t *mask)
++{
++ return __best_mask_cpu(mask, per_cpu(sched_cpu_topo_masks, cpu));
++}
++
++#endif
++
++#ifndef arch_scale_freq_tick
++static __always_inline
++void arch_scale_freq_tick(void)
++{
++}
++#endif
++
++#ifndef arch_scale_freq_capacity
++static __always_inline
++unsigned long arch_scale_freq_capacity(int cpu)
++{
++ return SCHED_CAPACITY_SCALE;
++}
++#endif
++
++static inline u64 __rq_clock_broken(struct rq *rq)
++{
++ return READ_ONCE(rq->clock);
++}
++
++static inline u64 rq_clock(struct rq *rq)
++{
++ /*
++ * Relax lockdep_assert_held() checking as in VRQ, call to
++ * sched_info_xxxx() may not held rq->lock
++ * lockdep_assert_held(&rq->lock);
++ */
++ return rq->clock;
++}
++
++static inline u64 rq_clock_task(struct rq *rq)
++{
++ /*
++ * Relax lockdep_assert_held() checking as in VRQ, call to
++ * sched_info_xxxx() may not held rq->lock
++ * lockdep_assert_held(&rq->lock);
++ */
++ return rq->clock_task;
++}
++
++/*
++ * {de,en}queue flags:
++ *
++ * DEQUEUE_SLEEP - task is no longer runnable
++ * ENQUEUE_WAKEUP - task just became runnable
++ *
++ */
++
++#define DEQUEUE_SLEEP 0x01
++
++#define ENQUEUE_WAKEUP 0x01
++
++
++/*
++ * Below are scheduler API which using in other kernel code
++ * It use the dummy rq_flags
++ * ToDo : BMQ need to support these APIs for compatibility with mainline
++ * scheduler code.
++ */
++struct rq_flags {
++ unsigned long flags;
++};
++
++struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(rq->lock);
++
++struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(p->pi_lock)
++ __acquires(rq->lock);
++
++static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock(&rq->lock);
++}
++
++static inline void
++task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
++ __releases(rq->lock)
++ __releases(p->pi_lock)
++{
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
++}
++
++static inline void
++rq_lock(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock(&rq->lock);
++}
++
++static inline void
++rq_unlock(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock(&rq->lock);
++}
++
++static inline void
++rq_lock_irq(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock_irq(&rq->lock);
++}
++
++static inline void
++rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock_irq(&rq->lock);
++}
++
++static inline struct rq *
++this_rq_lock_irq(struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ local_irq_disable();
++ rq = this_rq();
++ raw_spin_lock(&rq->lock);
++
++ return rq;
++}
++
++static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
++{
++ return &rq->lock;
++}
++
++static inline raw_spinlock_t *rq_lockp(struct rq *rq)
++{
++ return __rq_lockp(rq);
++}
++
++static inline void lockdep_assert_rq_held(struct rq *rq)
++{
++ lockdep_assert_held(__rq_lockp(rq));
++}
++
++extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
++extern void raw_spin_rq_unlock(struct rq *rq);
++
++static inline void raw_spin_rq_lock(struct rq *rq)
++{
++ raw_spin_rq_lock_nested(rq, 0);
++}
++
++static inline void raw_spin_rq_lock_irq(struct rq *rq)
++{
++ local_irq_disable();
++ raw_spin_rq_lock(rq);
++}
++
++static inline void raw_spin_rq_unlock_irq(struct rq *rq)
++{
++ raw_spin_rq_unlock(rq);
++ local_irq_enable();
++}
++
++static inline int task_current(struct rq *rq, struct task_struct *p)
++{
++ return rq->curr == p;
++}
++
++static inline bool task_on_cpu(struct task_struct *p)
++{
++ return p->on_cpu;
++}
++
++extern int task_running_nice(struct task_struct *p);
++
++extern struct static_key_false sched_schedstats;
++
++#ifdef CONFIG_CPU_IDLE
++static inline void idle_set_state(struct rq *rq,
++ struct cpuidle_state *idle_state)
++{
++ rq->idle_state = idle_state;
++}
++
++static inline struct cpuidle_state *idle_get_state(struct rq *rq)
++{
++ WARN_ON(!rcu_read_lock_held());
++ return rq->idle_state;
++}
++#else
++static inline void idle_set_state(struct rq *rq,
++ struct cpuidle_state *idle_state)
++{
++}
++
++static inline struct cpuidle_state *idle_get_state(struct rq *rq)
++{
++ return NULL;
++}
++#endif
++
++static inline int cpu_of(const struct rq *rq)
++{
++#ifdef CONFIG_SMP
++ return rq->cpu;
++#else
++ return 0;
++#endif
++}
++
++extern void resched_cpu(int cpu);
++
++#include "stats.h"
++
++#ifdef CONFIG_NO_HZ_COMMON
++#define NOHZ_BALANCE_KICK_BIT 0
++#define NOHZ_STATS_KICK_BIT 1
++
++#define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT)
++#define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT)
++
++#define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
++
++#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
++
++/* TODO: needed?
++extern void nohz_balance_exit_idle(struct rq *rq);
++#else
++static inline void nohz_balance_exit_idle(struct rq *rq) { }
++*/
++#endif
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++struct irqtime {
++ u64 total;
++ u64 tick_delta;
++ u64 irq_start_time;
++ struct u64_stats_sync sync;
++};
++
++DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
++
++/*
++ * Returns the irqtime minus the softirq time computed by ksoftirqd.
++ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
++ * and never move forward.
++ */
++static inline u64 irq_time_read(int cpu)
++{
++ struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
++ unsigned int seq;
++ u64 total;
++
++ do {
++ seq = __u64_stats_fetch_begin(&irqtime->sync);
++ total = irqtime->total;
++ } while (__u64_stats_fetch_retry(&irqtime->sync, seq));
++
++ return total;
++}
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++
++#ifdef CONFIG_CPU_FREQ
++DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
++#endif /* CONFIG_CPU_FREQ */
++
++#ifdef CONFIG_NO_HZ_FULL
++extern int __init sched_tick_offload_init(void);
++#else
++static inline int sched_tick_offload_init(void) { return 0; }
++#endif
++
++#ifdef arch_scale_freq_capacity
++#ifndef arch_scale_freq_invariant
++#define arch_scale_freq_invariant() (true)
++#endif
++#else /* arch_scale_freq_capacity */
++#define arch_scale_freq_invariant() (false)
++#endif
++
++#ifdef CONFIG_SMP
++unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
++ unsigned long min,
++ unsigned long max);
++#endif /* CONFIG_SMP */
++
++extern void schedule_idle(void);
++
++#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
++
++/*
++ * !! For sched_setattr_nocheck() (kernel) only !!
++ *
++ * This is actually gross. :(
++ *
++ * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE
++ * tasks, but still be able to sleep. We need this on platforms that cannot
++ * atomically change clock frequency. Remove once fast switching will be
++ * available on such platforms.
++ *
++ * SUGOV stands for SchedUtil GOVernor.
++ */
++#define SCHED_FLAG_SUGOV 0x10000000
++
++#ifdef CONFIG_MEMBARRIER
++/*
++ * The scheduler provides memory barriers required by membarrier between:
++ * - prior user-space memory accesses and store to rq->membarrier_state,
++ * - store to rq->membarrier_state and following user-space memory accesses.
++ * In the same way it provides those guarantees around store to rq->curr.
++ */
++static inline void membarrier_switch_mm(struct rq *rq,
++ struct mm_struct *prev_mm,
++ struct mm_struct *next_mm)
++{
++ int membarrier_state;
++
++ if (prev_mm == next_mm)
++ return;
++
++ membarrier_state = atomic_read(&next_mm->membarrier_state);
++ if (READ_ONCE(rq->membarrier_state) == membarrier_state)
++ return;
++
++ WRITE_ONCE(rq->membarrier_state, membarrier_state);
++}
++#else
++static inline void membarrier_switch_mm(struct rq *rq,
++ struct mm_struct *prev_mm,
++ struct mm_struct *next_mm)
++{
++}
++#endif
++
++#ifdef CONFIG_NUMA
++extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
++#else
++static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
++{
++ return nr_cpu_ids;
++}
++#endif
++
++extern void swake_up_all_locked(struct swait_queue_head *q);
++extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
++
++extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++extern int preempt_dynamic_mode;
++extern int sched_dynamic_mode(const char *str);
++extern void sched_dynamic_update(int mode);
++#endif
++
++static inline void nohz_run_idle_balance(int cpu) { }
++
++static inline
++unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
++ struct task_struct *p)
++{
++ return util;
++}
++
++static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
++
++#ifdef CONFIG_SCHED_MM_CID
++
++#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */
++#define MM_CID_SCAN_DELAY 100 /* 100ms */
++
++extern raw_spinlock_t cid_lock;
++extern int use_cid_lock;
++
++extern void sched_mm_cid_migrate_from(struct task_struct *t);
++extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu);
++extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr);
++extern void init_sched_mm_cid(struct task_struct *t);
++
++static inline void __mm_cid_put(struct mm_struct *mm, int cid)
++{
++ if (cid < 0)
++ return;
++ cpumask_clear_cpu(cid, mm_cidmask(mm));
++}
++
++/*
++ * The per-mm/cpu cid can have the MM_CID_LAZY_PUT flag set or transition to
++ * the MM_CID_UNSET state without holding the rq lock, but the rq lock needs to
++ * be held to transition to other states.
++ *
++ * State transitions synchronized with cmpxchg or try_cmpxchg need to be
++ * consistent across cpus, which prevents use of this_cpu_cmpxchg.
++ */
++static inline void mm_cid_put_lazy(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ int cid;
++
++ lockdep_assert_irqs_disabled();
++ cid = __this_cpu_read(pcpu_cid->cid);
++ if (!mm_cid_is_lazy_put(cid) ||
++ !try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
++ return;
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++}
++
++static inline int mm_cid_pcpu_unset(struct mm_struct *mm)
++{
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ int cid, res;
++
++ lockdep_assert_irqs_disabled();
++ cid = __this_cpu_read(pcpu_cid->cid);
++ for (;;) {
++ if (mm_cid_is_unset(cid))
++ return MM_CID_UNSET;
++ /*
++ * Attempt transition from valid or lazy-put to unset.
++ */
++ res = cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, cid, MM_CID_UNSET);
++ if (res == cid)
++ break;
++ cid = res;
++ }
++ return cid;
++}
++
++static inline void mm_cid_put(struct mm_struct *mm)
++{
++ int cid;
++
++ lockdep_assert_irqs_disabled();
++ cid = mm_cid_pcpu_unset(mm);
++ if (cid == MM_CID_UNSET)
++ return;
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++}
++
++static inline int __mm_cid_try_get(struct mm_struct *mm)
++{
++ struct cpumask *cpumask;
++ int cid;
++
++ cpumask = mm_cidmask(mm);
++ /*
++ * Retry finding first zero bit if the mask is temporarily
++ * filled. This only happens during concurrent remote-clear
++ * which owns a cid without holding a rq lock.
++ */
++ for (;;) {
++ cid = cpumask_first_zero(cpumask);
++ if (cid < nr_cpu_ids)
++ break;
++ cpu_relax();
++ }
++ if (cpumask_test_and_set_cpu(cid, cpumask))
++ return -1;
++ return cid;
++}
++
++/*
++ * Save a snapshot of the current runqueue time of this cpu
++ * with the per-cpu cid value, allowing to estimate how recently it was used.
++ */
++static inline void mm_cid_snapshot_time(struct rq *rq, struct mm_struct *mm)
++{
++ struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(rq));
++
++ lockdep_assert_rq_held(rq);
++ WRITE_ONCE(pcpu_cid->time, rq->clock);
++}
++
++static inline int __mm_cid_get(struct rq *rq, struct mm_struct *mm)
++{
++ int cid;
++
++ /*
++ * All allocations (even those using the cid_lock) are lock-free. If
++ * use_cid_lock is set, hold the cid_lock to perform cid allocation to
++ * guarantee forward progress.
++ */
++ if (!READ_ONCE(use_cid_lock)) {
++ cid = __mm_cid_try_get(mm);
++ if (cid >= 0)
++ goto end;
++ raw_spin_lock(&cid_lock);
++ } else {
++ raw_spin_lock(&cid_lock);
++ cid = __mm_cid_try_get(mm);
++ if (cid >= 0)
++ goto unlock;
++ }
++
++ /*
++ * cid concurrently allocated. Retry while forcing following
++ * allocations to use the cid_lock to ensure forward progress.
++ */
++ WRITE_ONCE(use_cid_lock, 1);
++ /*
++ * Set use_cid_lock before allocation. Only care about program order
++ * because this is only required for forward progress.
++ */
++ barrier();
++ /*
++ * Retry until it succeeds. It is guaranteed to eventually succeed once
++ * all newcoming allocations observe the use_cid_lock flag set.
++ */
++ do {
++ cid = __mm_cid_try_get(mm);
++ cpu_relax();
++ } while (cid < 0);
++ /*
++ * Allocate before clearing use_cid_lock. Only care about
++ * program order because this is for forward progress.
++ */
++ barrier();
++ WRITE_ONCE(use_cid_lock, 0);
++unlock:
++ raw_spin_unlock(&cid_lock);
++end:
++ mm_cid_snapshot_time(rq, mm);
++ return cid;
++}
++
++static inline int mm_cid_get(struct rq *rq, struct mm_struct *mm)
++{
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ struct cpumask *cpumask;
++ int cid;
++
++ lockdep_assert_rq_held(rq);
++ cpumask = mm_cidmask(mm);
++ cid = __this_cpu_read(pcpu_cid->cid);
++ if (mm_cid_is_valid(cid)) {
++ mm_cid_snapshot_time(rq, mm);
++ return cid;
++ }
++ if (mm_cid_is_lazy_put(cid)) {
++ if (try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++ }
++ cid = __mm_cid_get(rq, mm);
++ __this_cpu_write(pcpu_cid->cid, cid);
++ return cid;
++}
++
++static inline void switch_mm_cid(struct rq *rq,
++ struct task_struct *prev,
++ struct task_struct *next)
++{
++ /*
++ * Provide a memory barrier between rq->curr store and load of
++ * {prev,next}->mm->pcpu_cid[cpu] on rq->curr->mm transition.
++ *
++ * Should be adapted if context_switch() is modified.
++ */
++ if (!next->mm) { // to kernel
++ /*
++ * user -> kernel transition does not guarantee a barrier, but
++ * we can use the fact that it performs an atomic operation in
++ * mmgrab().
++ */
++ if (prev->mm) // from user
++ smp_mb__after_mmgrab();
++ /*
++ * kernel -> kernel transition does not change rq->curr->mm
++ * state. It stays NULL.
++ */
++ } else { // to user
++ /*
++ * kernel -> user transition does not provide a barrier
++ * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
++ * Provide it here.
++ */
++ if (!prev->mm) // from kernel
++ smp_mb();
++ /*
++ * user -> user transition guarantees a memory barrier through
++ * switch_mm() when current->mm changes. If current->mm is
++ * unchanged, no barrier is needed.
++ */
++ }
++ if (prev->mm_cid_active) {
++ mm_cid_snapshot_time(rq, prev->mm);
++ mm_cid_put_lazy(prev);
++ prev->mm_cid = -1;
++ }
++ if (next->mm_cid_active)
++ next->last_mm_cid = next->mm_cid = mm_cid_get(rq, next->mm);
++}
++
++#else
++static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { }
++static inline void sched_mm_cid_migrate_from(struct task_struct *t) { }
++static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu) { }
++static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
++static inline void init_sched_mm_cid(struct task_struct *t) { }
++#endif
++
++#ifdef CONFIG_SMP
++extern struct balance_callback balance_push_callback;
++
++static inline void
++__queue_balance_callback(struct rq *rq,
++ struct balance_callback *head)
++{
++ lockdep_assert_rq_held(rq);
++
++ /*
++ * Don't (re)queue an already queued item; nor queue anything when
++ * balance_push() is active, see the comment with
++ * balance_push_callback.
++ */
++ if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
++ return;
++
++ head->next = rq->balance_callback;
++ rq->balance_callback = head;
++}
++#endif /* CONFIG_SMP */
++
++#endif /* ALT_SCHED_H */
+diff --git a/kernel/sched/bmq.h b/kernel/sched/bmq.h
+--- a/kernel/sched/bmq.h 1970-01-01 01:00:00.000000000 +0100
++++ b/kernel/sched/bmq.h 2024-07-16 11:57:44.445146416 +0200
+@@ -0,0 +1,98 @@
++#define ALT_SCHED_NAME "BMQ"
++
++/*
++ * BMQ only routines
++ */
++static inline void boost_task(struct task_struct *p, int n)
++{
++ int limit;
++
++ switch (p->policy) {
++ case SCHED_NORMAL:
++ limit = -MAX_PRIORITY_ADJ;
++ break;
++ case SCHED_BATCH:
++ limit = 0;
++ break;
++ default:
++ return;
++ }
++
++ p->boost_prio = max(limit, p->boost_prio - n);
++}
++
++static inline void deboost_task(struct task_struct *p)
++{
++ if (p->boost_prio < MAX_PRIORITY_ADJ)
++ p->boost_prio++;
++}
++
++/*
++ * Common interfaces
++ */
++static inline void sched_timeslice_imp(const int timeslice_ms) {}
++
++/* This API is used in task_prio(), return value readed by human users */
++static inline int
++task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
++{
++ return p->prio + p->boost_prio - MIN_NORMAL_PRIO;
++}
++
++static inline int task_sched_prio(const struct task_struct *p)
++{
++ return (p->prio < MIN_NORMAL_PRIO)? (p->prio >> 2) :
++ MIN_SCHED_NORMAL_PRIO + (p->prio + p->boost_prio - MIN_NORMAL_PRIO) / 2;
++}
++
++#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
++ prio = task_sched_prio(p); \
++ idx = prio;
++
++static inline int sched_prio2idx(int prio, struct rq *rq)
++{
++ return prio;
++}
++
++static inline int sched_idx2prio(int idx, struct rq *rq)
++{
++ return idx;
++}
++
++static inline int sched_rq_prio_idx(struct rq *rq)
++{
++ return rq->prio;
++}
++
++inline int task_running_nice(struct task_struct *p)
++{
++ return (p->prio + p->boost_prio > DEFAULT_PRIO);
++}
++
++static inline void sched_update_rq_clock(struct rq *rq) {}
++
++static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
++{
++ deboost_task(p);
++}
++
++static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq) {}
++static void sched_task_fork(struct task_struct *p, struct rq *rq) {}
++
++static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
++{
++ p->boost_prio = MAX_PRIORITY_ADJ;
++}
++
++static inline void sched_task_ttwu(struct task_struct *p)
++{
++ s64 delta = this_rq()->clock_task > p->last_ran;
++
++ if (likely(delta > 0))
++ boost_task(p, delta >> 22);
++}
++
++static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq)
++{
++ boost_task(p, 1);
++}
+diff --git a/kernel/sched/build_policy.c b/kernel/sched/build_policy.c
+--- a/kernel/sched/build_policy.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/build_policy.c 2024-07-16 11:57:44.445146416 +0200
+@@ -42,13 +42,19 @@
+
+ #include "idle.c"
+
++#ifndef CONFIG_SCHED_ALT
+ #include "rt.c"
++#endif
+
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ # include "cpudeadline.c"
++#endif
+ # include "pelt.c"
+ #endif
+
+ #include "cputime.c"
+-#include "deadline.c"
+
++#ifndef CONFIG_SCHED_ALT
++#include "deadline.c"
++#endif
+diff --git a/kernel/sched/build_utility.c b/kernel/sched/build_utility.c
+--- a/kernel/sched/build_utility.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/build_utility.c 2024-07-16 11:57:44.445146416 +0200
+@@ -84,7 +84,9 @@
+
+ #ifdef CONFIG_SMP
+ # include "cpupri.c"
++#ifndef CONFIG_SCHED_ALT
+ # include "stop_task.c"
++#endif
+ # include "topology.c"
+ #endif
+
+diff --git a/kernel/sched/cpufreq_schedutil.c b/kernel/sched/cpufreq_schedutil.c
+--- a/kernel/sched/cpufreq_schedutil.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/cpufreq_schedutil.c 2024-07-16 11:57:44.445146416 +0200
+@@ -197,12 +197,17 @@ unsigned long sugov_effective_cpu_perf(i
+
+ static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
+ {
++#ifndef CONFIG_SCHED_ALT
+ unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
+
+ util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
+ util = max(util, boost);
+ sg_cpu->bw_min = min;
+ sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
++#else /* CONFIG_SCHED_ALT */
++ sg_cpu->bw_min = 0;
++ sg_cpu->util = rq_load_util(cpu_rq(sg_cpu->cpu), arch_scale_cpu_capacity(sg_cpu->cpu));
++#endif /* CONFIG_SCHED_ALT */
+ }
+
+ /**
+@@ -343,8 +348,10 @@ static inline bool sugov_cpu_is_busy(str
+ */
+ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
+ {
++#ifndef CONFIG_SCHED_ALT
+ if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
+ sg_cpu->sg_policy->limits_changed = true;
++#endif
+ }
+
+ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
+@@ -676,6 +683,7 @@ static int sugov_kthread_create(struct s
+ }
+
+ ret = sched_setattr_nocheck(thread, &attr);
++
+ if (ret) {
+ kthread_stop(thread);
+ pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
+diff --git a/kernel/sched/cputime.c b/kernel/sched/cputime.c
+--- a/kernel/sched/cputime.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/cputime.c 2024-07-16 11:57:44.445146416 +0200
+@@ -126,7 +126,7 @@ void account_user_time(struct task_struc
+ p->utime += cputime;
+ account_group_user_time(p, cputime);
+
+- index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
++ index = task_running_nice(p) ? CPUTIME_NICE : CPUTIME_USER;
+
+ /* Add user time to cpustat. */
+ task_group_account_field(p, index, cputime);
+@@ -150,7 +150,7 @@ void account_guest_time(struct task_stru
+ p->gtime += cputime;
+
+ /* Add guest time to cpustat. */
+- if (task_nice(p) > 0) {
++ if (task_running_nice(p)) {
+ task_group_account_field(p, CPUTIME_NICE, cputime);
+ cpustat[CPUTIME_GUEST_NICE] += cputime;
+ } else {
+@@ -288,7 +288,7 @@ static inline u64 account_other_time(u64
+ #ifdef CONFIG_64BIT
+ static inline u64 read_sum_exec_runtime(struct task_struct *t)
+ {
+- return t->se.sum_exec_runtime;
++ return tsk_seruntime(t);
+ }
+ #else
+ static u64 read_sum_exec_runtime(struct task_struct *t)
+@@ -298,7 +298,7 @@ static u64 read_sum_exec_runtime(struct
+ struct rq *rq;
+
+ rq = task_rq_lock(t, &rf);
+- ns = t->se.sum_exec_runtime;
++ ns = tsk_seruntime(t);
+ task_rq_unlock(rq, t, &rf);
+
+ return ns;
+@@ -617,7 +617,7 @@ out:
+ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
+ {
+ struct task_cputime cputime = {
+- .sum_exec_runtime = p->se.sum_exec_runtime,
++ .sum_exec_runtime = tsk_seruntime(p),
+ };
+
+ if (task_cputime(p, &cputime.utime, &cputime.stime))
+diff --git a/kernel/sched/debug.c b/kernel/sched/debug.c
+--- a/kernel/sched/debug.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/debug.c 2024-07-16 11:57:44.445146416 +0200
+@@ -7,6 +7,7 @@
+ * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
+ */
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * This allows printing both to /sys/kernel/debug/sched/debug and
+ * to the console
+@@ -215,6 +216,7 @@ static const struct file_operations sche
+ };
+
+ #endif /* SMP */
++#endif /* !CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_PREEMPT_DYNAMIC
+
+@@ -278,6 +280,7 @@ static const struct file_operations sche
+
+ #endif /* CONFIG_PREEMPT_DYNAMIC */
+
++#ifndef CONFIG_SCHED_ALT
+ __read_mostly bool sched_debug_verbose;
+
+ #ifdef CONFIG_SMP
+@@ -332,6 +335,7 @@ static const struct file_operations sche
+ .llseek = seq_lseek,
+ .release = seq_release,
+ };
++#endif /* !CONFIG_SCHED_ALT */
+
+ static struct dentry *debugfs_sched;
+
+@@ -341,14 +345,17 @@ static __init int sched_init_debug(void)
+
+ debugfs_sched = debugfs_create_dir("sched", NULL);
+
++#ifndef CONFIG_SCHED_ALT
+ debugfs_create_file("features", 0644, debugfs_sched, NULL, &sched_feat_fops);
+ debugfs_create_file_unsafe("verbose", 0644, debugfs_sched, &sched_debug_verbose, &sched_verbose_fops);
++#endif /* !CONFIG_SCHED_ALT */
+ #ifdef CONFIG_PREEMPT_DYNAMIC
+ debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
+ #endif
+
+ debugfs_create_u32("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
+
++#ifndef CONFIG_SCHED_ALT
+ debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
+ debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
+
+@@ -373,11 +380,13 @@ static __init int sched_init_debug(void)
+ #endif
+
+ debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
++#endif /* !CONFIG_SCHED_ALT */
+
+ return 0;
+ }
+ late_initcall(sched_init_debug);
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_SMP
+
+ static cpumask_var_t sd_sysctl_cpus;
+@@ -1111,6 +1120,7 @@ void proc_sched_set_task(struct task_str
+ memset(&p->stats, 0, sizeof(p->stats));
+ #endif
+ }
++#endif /* !CONFIG_SCHED_ALT */
+
+ void resched_latency_warn(int cpu, u64 latency)
+ {
+diff --git a/kernel/sched/idle.c b/kernel/sched/idle.c
+--- a/kernel/sched/idle.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/idle.c 2024-07-16 11:57:44.449146659 +0200
+@@ -430,6 +430,7 @@ void cpu_startup_entry(enum cpuhp_state
+ do_idle();
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * idle-task scheduling class.
+ */
+@@ -551,3 +552,4 @@ DEFINE_SCHED_CLASS(idle) = {
+ .switched_to = switched_to_idle,
+ .update_curr = update_curr_idle,
+ };
++#endif
+diff --git a/kernel/sched/Makefile b/kernel/sched/Makefile
+--- a/kernel/sched/Makefile 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/Makefile 2024-07-16 11:57:44.441146173 +0200
+@@ -28,7 +28,12 @@ endif
+ # These compilation units have roughly the same size and complexity - so their
+ # build parallelizes well and finishes roughly at once:
+ #
++ifdef CONFIG_SCHED_ALT
++obj-y += alt_core.o
++obj-$(CONFIG_SCHED_DEBUG) += alt_debug.o
++else
+ obj-y += core.o
+ obj-y += fair.o
++endif
+ obj-y += build_policy.o
+ obj-y += build_utility.o
+diff --git a/kernel/sched/pds.h b/kernel/sched/pds.h
+--- a/kernel/sched/pds.h 1970-01-01 01:00:00.000000000 +0100
++++ b/kernel/sched/pds.h 2024-07-16 11:57:44.449146659 +0200
+@@ -0,0 +1,134 @@
++#define ALT_SCHED_NAME "PDS"
++
++static const u64 RT_MASK = ((1ULL << MIN_SCHED_NORMAL_PRIO) - 1);
++
++#define SCHED_NORMAL_PRIO_NUM (32)
++#define SCHED_EDGE_DELTA (SCHED_NORMAL_PRIO_NUM - NICE_WIDTH / 2)
++
++/* PDS assume SCHED_NORMAL_PRIO_NUM is power of 2 */
++#define SCHED_NORMAL_PRIO_MOD(x) ((x) & (SCHED_NORMAL_PRIO_NUM - 1))
++
++/* default time slice 4ms -> shift 22, 2 time slice slots -> shift 23 */
++static __read_mostly int sched_timeslice_shift = 23;
++
++/*
++ * Common interfaces
++ */
++static inline int
++task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
++{
++ u64 sched_dl = max(p->deadline, rq->time_edge);
++
++#ifdef ALT_SCHED_DEBUG
++ if (WARN_ONCE(sched_dl - rq->time_edge > NORMAL_PRIO_NUM - 1,
++ "pds: task_sched_prio_normal() delta %lld\n", sched_dl - rq->time_edge))
++ return SCHED_NORMAL_PRIO_NUM - 1;
++#endif
++
++ return sched_dl - rq->time_edge;
++}
++
++static inline int task_sched_prio(const struct task_struct *p)
++{
++ return (p->prio < MIN_NORMAL_PRIO) ? (p->prio >> 2) :
++ MIN_SCHED_NORMAL_PRIO + task_sched_prio_normal(p, task_rq(p));
++}
++
++#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
++ if (p->prio < MIN_NORMAL_PRIO) { \
++ prio = p->prio >> 2; \
++ idx = prio; \
++ } else { \
++ u64 sched_dl = max(p->deadline, rq->time_edge); \
++ prio = MIN_SCHED_NORMAL_PRIO + sched_dl - rq->time_edge; \
++ idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_dl); \
++ }
++
++static inline int sched_prio2idx(int sched_prio, struct rq *rq)
++{
++ return (IDLE_TASK_SCHED_PRIO == sched_prio || sched_prio < MIN_SCHED_NORMAL_PRIO) ?
++ sched_prio :
++ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_prio + rq->time_edge);
++}
++
++static inline int sched_idx2prio(int sched_idx, struct rq *rq)
++{
++ return (sched_idx < MIN_SCHED_NORMAL_PRIO) ?
++ sched_idx :
++ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_idx - rq->time_edge);
++}
++
++static inline int sched_rq_prio_idx(struct rq *rq)
++{
++ return rq->prio_idx;
++}
++
++int task_running_nice(struct task_struct *p)
++{
++ return (p->prio > DEFAULT_PRIO);
++}
++
++static inline void sched_update_rq_clock(struct rq *rq)
++{
++ struct list_head head;
++ u64 old = rq->time_edge;
++ u64 now = rq->clock >> sched_timeslice_shift;
++ u64 prio, delta;
++ DECLARE_BITMAP(normal, SCHED_QUEUE_BITS);
++
++ if (now == old)
++ return;
++
++ rq->time_edge = now;
++ delta = min_t(u64, SCHED_NORMAL_PRIO_NUM, now - old);
++ INIT_LIST_HEAD(&head);
++
++ prio = MIN_SCHED_NORMAL_PRIO;
++ for_each_set_bit_from(prio, rq->queue.bitmap, MIN_SCHED_NORMAL_PRIO + delta)
++ list_splice_tail_init(rq->queue.heads + MIN_SCHED_NORMAL_PRIO +
++ SCHED_NORMAL_PRIO_MOD(prio + old), &head);
++
++ bitmap_shift_right(normal, rq->queue.bitmap, delta, SCHED_QUEUE_BITS);
++ if (!list_empty(&head)) {
++ u64 idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(now);
++
++ __list_splice(&head, rq->queue.heads + idx, rq->queue.heads[idx].next);
++ set_bit(MIN_SCHED_NORMAL_PRIO, normal);
++ }
++ bitmap_replace(rq->queue.bitmap, normal, rq->queue.bitmap,
++ (const unsigned long *)&RT_MASK, SCHED_QUEUE_BITS);
++
++ if (rq->prio < MIN_SCHED_NORMAL_PRIO || IDLE_TASK_SCHED_PRIO == rq->prio)
++ return;
++
++ rq->prio = max_t(u64, MIN_SCHED_NORMAL_PRIO, rq->prio - delta);
++ rq->prio_idx = sched_prio2idx(rq->prio, rq);
++}
++
++static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
++{
++ if (p->prio >= MIN_NORMAL_PRIO)
++ p->deadline = rq->time_edge + SCHED_EDGE_DELTA +
++ (p->static_prio - (MAX_PRIO - NICE_WIDTH)) / 2;
++}
++
++static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq)
++{
++ u64 max_dl = rq->time_edge + SCHED_EDGE_DELTA + NICE_WIDTH / 2 - 1;
++ if (unlikely(p->deadline > max_dl))
++ p->deadline = max_dl;
++}
++
++static void sched_task_fork(struct task_struct *p, struct rq *rq)
++{
++ sched_task_renew(p, rq);
++}
++
++static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
++{
++ p->time_slice = sysctl_sched_base_slice;
++ sched_task_renew(p, rq);
++}
++
++static inline void sched_task_ttwu(struct task_struct *p) {}
++static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq) {}
+diff --git a/kernel/sched/pelt.c b/kernel/sched/pelt.c
+--- a/kernel/sched/pelt.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/pelt.c 2024-07-16 11:57:44.449146659 +0200
+@@ -266,6 +266,7 @@ ___update_load_avg(struct sched_avg *sa,
+ WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * sched_entity:
+ *
+@@ -383,8 +384,9 @@ int update_dl_rq_load_avg(u64 now, struc
+
+ return 0;
+ }
++#endif
+
+-#ifdef CONFIG_SCHED_HW_PRESSURE
++#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
+ /*
+ * hardware:
+ *
+diff --git a/kernel/sched/pelt.h b/kernel/sched/pelt.h
+--- a/kernel/sched/pelt.h 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/pelt.h 2024-07-16 11:57:44.449146659 +0200
+@@ -1,13 +1,15 @@
+ #ifdef CONFIG_SMP
+ #include "sched-pelt.h"
+
++#ifndef CONFIG_SCHED_ALT
+ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
+ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
+ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
+ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
++#endif
+
+-#ifdef CONFIG_SCHED_HW_PRESSURE
++#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
+ int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity);
+
+ static inline u64 hw_load_avg(struct rq *rq)
+@@ -44,6 +46,7 @@ static inline u32 get_pelt_divider(struc
+ return PELT_MIN_DIVIDER + avg->period_contrib;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ static inline void cfs_se_util_change(struct sched_avg *avg)
+ {
+ unsigned int enqueued;
+@@ -180,9 +183,11 @@ static inline u64 cfs_rq_clock_pelt(stru
+ return rq_clock_pelt(rq_of(cfs_rq));
+ }
+ #endif
++#endif /* CONFIG_SCHED_ALT */
+
+ #else
+
++#ifndef CONFIG_SCHED_ALT
+ static inline int
+ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+ {
+@@ -200,6 +205,7 @@ update_dl_rq_load_avg(u64 now, struct rq
+ {
+ return 0;
+ }
++#endif
+
+ static inline int
+ update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
+diff --git a/kernel/sched/sched.h b/kernel/sched/sched.h
+--- a/kernel/sched/sched.h 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/sched.h 2024-07-16 11:57:44.449146659 +0200
+@@ -5,6 +5,10 @@
+ #ifndef _KERNEL_SCHED_SCHED_H
+ #define _KERNEL_SCHED_SCHED_H
+
++#ifdef CONFIG_SCHED_ALT
++#include "alt_sched.h"
++#else
++
+ #include <linux/sched/affinity.h>
+ #include <linux/sched/autogroup.h>
+ #include <linux/sched/cpufreq.h>
+@@ -3481,4 +3485,9 @@ static inline void init_sched_mm_cid(str
+ extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
+ extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
++static inline int task_running_nice(struct task_struct *p)
++{
++ return (task_nice(p) > 0);
++}
++#endif /* !CONFIG_SCHED_ALT */
+ #endif /* _KERNEL_SCHED_SCHED_H */
+diff --git a/kernel/sched/stats.c b/kernel/sched/stats.c
+--- a/kernel/sched/stats.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/stats.c 2024-07-16 11:57:44.449146659 +0200
+@@ -125,9 +125,11 @@ static int show_schedstat(struct seq_fil
+ } else {
+ struct rq *rq;
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ struct sched_domain *sd;
+ int dcount = 0;
+ #endif
++#endif
+ cpu = (unsigned long)(v - 2);
+ rq = cpu_rq(cpu);
+
+@@ -143,6 +145,7 @@ static int show_schedstat(struct seq_fil
+ seq_printf(seq, "\n");
+
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ /* domain-specific stats */
+ rcu_read_lock();
+ for_each_domain(cpu, sd) {
+@@ -171,6 +174,7 @@ static int show_schedstat(struct seq_fil
+ }
+ rcu_read_unlock();
+ #endif
++#endif
+ }
+ return 0;
+ }
+diff --git a/kernel/sched/stats.h b/kernel/sched/stats.h
+--- a/kernel/sched/stats.h 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/stats.h 2024-07-16 11:57:44.449146659 +0200
+@@ -89,6 +89,7 @@ static inline void rq_sched_info_depart
+
+ #endif /* CONFIG_SCHEDSTATS */
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_FAIR_GROUP_SCHED
+ struct sched_entity_stats {
+ struct sched_entity se;
+@@ -105,6 +106,7 @@ __schedstats_from_se(struct sched_entity
+ #endif
+ return &task_of(se)->stats;
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_PSI
+ void psi_task_change(struct task_struct *task, int clear, int set);
+diff --git a/kernel/sched/topology.c b/kernel/sched/topology.c
+--- a/kernel/sched/topology.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sched/topology.c 2024-07-16 11:57:44.449146659 +0200
+@@ -3,6 +3,7 @@
+ * Scheduler topology setup/handling methods
+ */
+
++#ifndef CONFIG_SCHED_ALT
+ #include <linux/bsearch.h>
+
+ DEFINE_MUTEX(sched_domains_mutex);
+@@ -1451,8 +1452,10 @@ static void asym_cpu_capacity_scan(void)
+ */
+
+ static int default_relax_domain_level = -1;
++#endif /* CONFIG_SCHED_ALT */
+ int sched_domain_level_max;
+
++#ifndef CONFIG_SCHED_ALT
+ static int __init setup_relax_domain_level(char *str)
+ {
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+@@ -1687,6 +1690,7 @@ sd_init(struct sched_domain_topology_lev
+
+ return sd;
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ /*
+ * Topology list, bottom-up.
+@@ -1723,6 +1727,7 @@ void __init set_sched_topology(struct sc
+ sched_domain_topology_saved = NULL;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_NUMA
+
+ static const struct cpumask *sd_numa_mask(int cpu)
+@@ -2789,3 +2794,28 @@ void partition_sched_domains(int ndoms_n
+ partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
+ mutex_unlock(&sched_domains_mutex);
+ }
++#else /* CONFIG_SCHED_ALT */
++DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
++
++void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
++ struct sched_domain_attr *dattr_new)
++{}
++
++#ifdef CONFIG_NUMA
++int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
++{
++ return best_mask_cpu(cpu, cpus);
++}
++
++int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
++{
++ return cpumask_nth(cpu, cpus);
++}
++
++const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops)
++{
++ return ERR_PTR(-EOPNOTSUPP);
++}
++EXPORT_SYMBOL_GPL(sched_numa_hop_mask);
++#endif /* CONFIG_NUMA */
++#endif
+diff --git a/kernel/sysctl.c b/kernel/sysctl.c
+--- a/kernel/sysctl.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/sysctl.c 2024-07-16 11:57:44.449146659 +0200
+@@ -92,6 +92,10 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals);
+
+ /* Constants used for minimum and maximum */
+
++#ifdef CONFIG_SCHED_ALT
++extern int sched_yield_type;
++#endif
++
+ #ifdef CONFIG_PERF_EVENTS
+ static const int six_hundred_forty_kb = 640 * 1024;
+ #endif
+@@ -1912,6 +1916,17 @@ static struct ctl_table kern_table[] = {
+ .proc_handler = proc_dointvec,
+ },
+ #endif
++#ifdef CONFIG_SCHED_ALT
++ {
++ .procname = "yield_type",
++ .data = &sched_yield_type,
++ .maxlen = sizeof (int),
++ .mode = 0644,
++ .proc_handler = &proc_dointvec_minmax,
++ .extra1 = SYSCTL_ZERO,
++ .extra2 = SYSCTL_TWO,
++ },
++#endif
+ #if defined(CONFIG_S390) && defined(CONFIG_SMP)
+ {
+ .procname = "spin_retry",
+diff --git a/kernel/time/hrtimer.c b/kernel/time/hrtimer.c
+--- a/kernel/time/hrtimer.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/time/hrtimer.c 2024-07-16 11:57:44.453146902 +0200
+@@ -2074,8 +2074,10 @@ long hrtimer_nanosleep(ktime_t rqtp, con
+ int ret = 0;
+ u64 slack;
+
++#ifndef CONFIG_SCHED_ALT
+ slack = current->timer_slack_ns;
+- if (rt_task(current))
++ if (dl_task(current) || rt_task(current))
++#endif
+ slack = 0;
+
+ hrtimer_init_sleeper_on_stack(&t, clockid, mode);
+diff --git a/kernel/time/posix-cpu-timers.c b/kernel/time/posix-cpu-timers.c
+--- a/kernel/time/posix-cpu-timers.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/time/posix-cpu-timers.c 2024-07-16 11:57:44.453146902 +0200
+@@ -223,7 +223,7 @@ static void task_sample_cputime(struct t
+ u64 stime, utime;
+
+ task_cputime(p, &utime, &stime);
+- store_samples(samples, stime, utime, p->se.sum_exec_runtime);
++ store_samples(samples, stime, utime, tsk_seruntime(p));
+ }
+
+ static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
+@@ -867,6 +867,7 @@ static void collect_posix_cputimers(stru
+ }
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ static inline void check_dl_overrun(struct task_struct *tsk)
+ {
+ if (tsk->dl.dl_overrun) {
+@@ -874,6 +875,7 @@ static inline void check_dl_overrun(stru
+ send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
+ }
+ }
++#endif
+
+ static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
+ {
+@@ -901,8 +903,10 @@ static void check_thread_timers(struct t
+ u64 samples[CPUCLOCK_MAX];
+ unsigned long soft;
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(tsk))
+ check_dl_overrun(tsk);
++#endif
+
+ if (expiry_cache_is_inactive(pct))
+ return;
+@@ -916,7 +920,7 @@ static void check_thread_timers(struct t
+ soft = task_rlimit(tsk, RLIMIT_RTTIME);
+ if (soft != RLIM_INFINITY) {
+ /* Task RT timeout is accounted in jiffies. RTTIME is usec */
+- unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ);
++ unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ);
+ unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
+
+ /* At the hard limit, send SIGKILL. No further action. */
+@@ -1152,8 +1156,10 @@ static inline bool fastpath_timer_check(
+ return true;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(tsk) && tsk->dl.dl_overrun)
+ return true;
++#endif
+
+ return false;
+ }
+diff --git a/kernel/trace/trace_selftest.c b/kernel/trace/trace_selftest.c
+--- a/kernel/trace/trace_selftest.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/trace/trace_selftest.c 2024-07-16 11:57:44.461147389 +0200
+@@ -1155,10 +1155,15 @@ static int trace_wakeup_test_thread(void
+ {
+ /* Make this a -deadline thread */
+ static const struct sched_attr attr = {
++#ifdef CONFIG_SCHED_ALT
++ /* No deadline on BMQ/PDS, use RR */
++ .sched_policy = SCHED_RR,
++#else
+ .sched_policy = SCHED_DEADLINE,
+ .sched_runtime = 100000ULL,
+ .sched_deadline = 10000000ULL,
+ .sched_period = 10000000ULL
++#endif
+ };
+ struct wakeup_test_data *x = data;
+
+diff --git a/kernel/workqueue.c b/kernel/workqueue.c
+--- a/kernel/workqueue.c 2024-07-15 00:43:32.000000000 +0200
++++ b/kernel/workqueue.c 2024-07-16 11:57:44.465147632 +0200
+@@ -1248,6 +1248,7 @@ static bool kick_pool(struct worker_pool
+
+ p = worker->task;
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_SMP
+ /*
+ * Idle @worker is about to execute @work and waking up provides an
+@@ -1277,6 +1278,8 @@ static bool kick_pool(struct worker_pool
+ }
+ }
+ #endif
++#endif /* !CONFIG_SCHED_ALT */
++
+ wake_up_process(p);
+ return true;
+ }
+@@ -1405,7 +1408,11 @@ void wq_worker_running(struct task_struc
+ * CPU intensive auto-detection cares about how long a work item hogged
+ * CPU without sleeping. Reset the starting timestamp on wakeup.
+ */
++#ifdef CONFIG_SCHED_ALT
++ worker->current_at = worker->task->sched_time;
++#else
+ worker->current_at = worker->task->se.sum_exec_runtime;
++#endif
+
+ WRITE_ONCE(worker->sleeping, 0);
+ }
+@@ -1490,7 +1497,11 @@ void wq_worker_tick(struct task_struct *
+ * We probably want to make this prettier in the future.
+ */
+ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) ||
++#ifdef CONFIG_SCHED_ALT
++ worker->task->sched_time - worker->current_at <
++#else
+ worker->task->se.sum_exec_runtime - worker->current_at <
++#endif
+ wq_cpu_intensive_thresh_us * NSEC_PER_USEC)
+ return;
+
+@@ -3176,7 +3187,11 @@ __acquires(&pool->lock)
+ worker->current_func = work->func;
+ worker->current_pwq = pwq;
+ if (worker->task)
++#ifdef CONFIG_SCHED_ALT
++ worker->current_at = worker->task->sched_time;
++#else
+ worker->current_at = worker->task->se.sum_exec_runtime;
++#endif
+ work_data = *work_data_bits(work);
+ worker->current_color = get_work_color(work_data);
+
diff --git a/5021_BMQ-and-PDS-gentoo-defaults.patch b/5021_BMQ-and-PDS-gentoo-defaults.patch
new file mode 100644
index 00000000..409dda6b
--- /dev/null
+++ b/5021_BMQ-and-PDS-gentoo-defaults.patch
@@ -0,0 +1,12 @@
+--- a/init/Kconfig 2023-02-13 08:16:09.534315265 -0500
++++ b/init/Kconfig 2023-02-13 08:17:24.130237204 -0500
+@@ -867,8 +867,9 @@ config UCLAMP_BUCKETS_COUNT
+ If in doubt, use the default value.
+
+ menuconfig SCHED_ALT
++ depends on X86_64
+ bool "Alternative CPU Schedulers"
+- default y
++ default n
+ help
+ This feature enable alternative CPU scheduler"
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-27 13:45 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-27 13:45 UTC (permalink / raw
To: gentoo-commits
commit: 4cbee0c6502f56a8b994cf6e55c28fe99dc5094c
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Sat Jul 27 13:45:10 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Sat Jul 27 13:45:10 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=4cbee0c6
Linux patch 6.10.2
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1001_linux-6.10.2.patch | 908 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 912 insertions(+)
diff --git a/0000_README b/0000_README
index d91abe89..f3d968e8 100644
--- a/0000_README
+++ b/0000_README
@@ -47,6 +47,10 @@ Patch: 1000_linux-6.10.1.patch
From: https://www.kernel.org
Desc: Linux 6.10.1
+Patch: 1001_linux-6.10.2.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.2
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1001_linux-6.10.2.patch b/1001_linux-6.10.2.patch
new file mode 100644
index 00000000..0b87c2e6
--- /dev/null
+++ b/1001_linux-6.10.2.patch
@@ -0,0 +1,908 @@
+diff --git a/Makefile b/Makefile
+index 9ae12a6c0ece2..07e1aec72c171 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 1
++SUBLEVEL = 2
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/arch/arm64/boot/dts/qcom/ipq6018.dtsi b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
+index 17ab6c4759580..625abd976cac2 100644
+--- a/arch/arm64/boot/dts/qcom/ipq6018.dtsi
++++ b/arch/arm64/boot/dts/qcom/ipq6018.dtsi
+@@ -685,6 +685,7 @@ dwc_0: usb@8a00000 {
+ clocks = <&xo>;
+ clock-names = "ref";
+ tx-fifo-resize;
++ snps,parkmode-disable-ss-quirk;
+ snps,is-utmi-l1-suspend;
+ snps,hird-threshold = /bits/ 8 <0x0>;
+ snps,dis_u2_susphy_quirk;
+diff --git a/arch/arm64/boot/dts/qcom/ipq8074.dtsi b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
+index 5d42de829e75f..ca75b7de7bf37 100644
+--- a/arch/arm64/boot/dts/qcom/ipq8074.dtsi
++++ b/arch/arm64/boot/dts/qcom/ipq8074.dtsi
+@@ -666,6 +666,7 @@ dwc_0: usb@8a00000 {
+ interrupts = <GIC_SPI 140 IRQ_TYPE_LEVEL_HIGH>;
+ phys = <&qusb_phy_0>, <&ssphy_0>;
+ phy-names = "usb2-phy", "usb3-phy";
++ snps,parkmode-disable-ss-quirk;
+ snps,is-utmi-l1-suspend;
+ snps,hird-threshold = /bits/ 8 <0x0>;
+ snps,dis_u2_susphy_quirk;
+@@ -715,6 +716,7 @@ dwc_1: usb@8c00000 {
+ interrupts = <GIC_SPI 99 IRQ_TYPE_LEVEL_HIGH>;
+ phys = <&qusb_phy_1>, <&ssphy_1>;
+ phy-names = "usb2-phy", "usb3-phy";
++ snps,parkmode-disable-ss-quirk;
+ snps,is-utmi-l1-suspend;
+ snps,hird-threshold = /bits/ 8 <0x0>;
+ snps,dis_u2_susphy_quirk;
+diff --git a/arch/arm64/boot/dts/qcom/msm8996.dtsi b/arch/arm64/boot/dts/qcom/msm8996.dtsi
+index 8d2cb6f410956..6e7a4bb08b35c 100644
+--- a/arch/arm64/boot/dts/qcom/msm8996.dtsi
++++ b/arch/arm64/boot/dts/qcom/msm8996.dtsi
+@@ -3091,6 +3091,7 @@ usb3_dwc3: usb@6a00000 {
+ snps,dis_u2_susphy_quirk;
+ snps,dis_enblslpm_quirk;
+ snps,is-utmi-l1-suspend;
++ snps,parkmode-disable-ss-quirk;
+ tx-fifo-resize;
+ };
+ };
+diff --git a/arch/arm64/boot/dts/qcom/msm8998.dtsi b/arch/arm64/boot/dts/qcom/msm8998.dtsi
+index d795b2bbe1330..2dbef4b526ab7 100644
+--- a/arch/arm64/boot/dts/qcom/msm8998.dtsi
++++ b/arch/arm64/boot/dts/qcom/msm8998.dtsi
+@@ -2164,6 +2164,7 @@ usb3_dwc3: usb@a800000 {
+ interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
+ snps,dis_u2_susphy_quirk;
+ snps,dis_enblslpm_quirk;
++ snps,parkmode-disable-ss-quirk;
+ phys = <&qusb2phy>, <&usb3phy>;
+ phy-names = "usb2-phy", "usb3-phy";
+ snps,has-lpm-erratum;
+diff --git a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
+index bb5191422660b..8c27d52139a1b 100644
+--- a/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
++++ b/arch/arm64/boot/dts/qcom/qrb2210-rb1.dts
+@@ -59,6 +59,17 @@ hdmi_con: endpoint {
+ };
+ };
+
++ i2c2_gpio: i2c {
++ compatible = "i2c-gpio";
++
++ sda-gpios = <&tlmm 6 GPIO_ACTIVE_HIGH>;
++ scl-gpios = <&tlmm 7 GPIO_ACTIVE_HIGH>;
++ #address-cells = <1>;
++ #size-cells = <0>;
++
++ status = "disabled";
++ };
++
+ leds {
+ compatible = "gpio-leds";
+
+@@ -199,7 +210,7 @@ &gpi_dma0 {
+ status = "okay";
+ };
+
+-&i2c2 {
++&i2c2_gpio {
+ clock-frequency = <400000>;
+ status = "okay";
+
+diff --git a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
+index 2c39bb1b97db5..cb8a62714a302 100644
+--- a/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
++++ b/arch/arm64/boot/dts/qcom/qrb4210-rb2.dts
+@@ -60,6 +60,17 @@ hdmi_con: endpoint {
+ };
+ };
+
++ i2c2_gpio: i2c {
++ compatible = "i2c-gpio";
++
++ sda-gpios = <&tlmm 6 GPIO_ACTIVE_HIGH>;
++ scl-gpios = <&tlmm 7 GPIO_ACTIVE_HIGH>;
++ #address-cells = <1>;
++ #size-cells = <0>;
++
++ status = "disabled";
++ };
++
+ leds {
+ compatible = "gpio-leds";
+
+@@ -190,7 +201,7 @@ zap-shader {
+ };
+ };
+
+-&i2c2 {
++&i2c2_gpio {
+ clock-frequency = <400000>;
+ status = "okay";
+
+diff --git a/arch/arm64/boot/dts/qcom/sc7180.dtsi b/arch/arm64/boot/dts/qcom/sc7180.dtsi
+index 4774a859bd7ea..e9deffe3aaf6c 100644
+--- a/arch/arm64/boot/dts/qcom/sc7180.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc7180.dtsi
+@@ -3067,6 +3067,7 @@ usb_1_dwc3: usb@a600000 {
+ iommus = <&apps_smmu 0x540 0>;
+ snps,dis_u2_susphy_quirk;
+ snps,dis_enblslpm_quirk;
++ snps,parkmode-disable-ss-quirk;
+ phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
+ phy-names = "usb2-phy", "usb3-phy";
+ maximum-speed = "super-speed";
+diff --git a/arch/arm64/boot/dts/qcom/sc7280.dtsi b/arch/arm64/boot/dts/qcom/sc7280.dtsi
+index fc9ec367e3a5a..2f7780f629ac5 100644
+--- a/arch/arm64/boot/dts/qcom/sc7280.dtsi
++++ b/arch/arm64/boot/dts/qcom/sc7280.dtsi
+@@ -4150,6 +4150,7 @@ usb_1_dwc3: usb@a600000 {
+ iommus = <&apps_smmu 0xe0 0x0>;
+ snps,dis_u2_susphy_quirk;
+ snps,dis_enblslpm_quirk;
++ snps,parkmode-disable-ss-quirk;
+ phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
+ phy-names = "usb2-phy", "usb3-phy";
+ maximum-speed = "super-speed";
+diff --git a/arch/arm64/boot/dts/qcom/sdm630.dtsi b/arch/arm64/boot/dts/qcom/sdm630.dtsi
+index f5921b80ef943..5f6884b2367d9 100644
+--- a/arch/arm64/boot/dts/qcom/sdm630.dtsi
++++ b/arch/arm64/boot/dts/qcom/sdm630.dtsi
+@@ -1302,6 +1302,7 @@ usb3_dwc3: usb@a800000 {
+ interrupts = <GIC_SPI 131 IRQ_TYPE_LEVEL_HIGH>;
+ snps,dis_u2_susphy_quirk;
+ snps,dis_enblslpm_quirk;
++ snps,parkmode-disable-ss-quirk;
+
+ phys = <&qusb2phy0>, <&usb3_qmpphy>;
+ phy-names = "usb2-phy", "usb3-phy";
+diff --git a/arch/arm64/boot/dts/qcom/sdm845.dtsi b/arch/arm64/boot/dts/qcom/sdm845.dtsi
+index 10de2bd46ffcc..d817a7751086e 100644
+--- a/arch/arm64/boot/dts/qcom/sdm845.dtsi
++++ b/arch/arm64/boot/dts/qcom/sdm845.dtsi
+@@ -4106,6 +4106,7 @@ usb_1_dwc3: usb@a600000 {
+ iommus = <&apps_smmu 0x740 0>;
+ snps,dis_u2_susphy_quirk;
+ snps,dis_enblslpm_quirk;
++ snps,parkmode-disable-ss-quirk;
+ phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
+ phy-names = "usb2-phy", "usb3-phy";
+ };
+@@ -4161,6 +4162,7 @@ usb_2_dwc3: usb@a800000 {
+ iommus = <&apps_smmu 0x760 0>;
+ snps,dis_u2_susphy_quirk;
+ snps,dis_enblslpm_quirk;
++ snps,parkmode-disable-ss-quirk;
+ phys = <&usb_2_hsphy>, <&usb_2_qmpphy>;
+ phy-names = "usb2-phy", "usb3-phy";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/sm6115.dtsi b/arch/arm64/boot/dts/qcom/sm6115.dtsi
+index 9ed062150aaf2..b4ce5a322107e 100644
+--- a/arch/arm64/boot/dts/qcom/sm6115.dtsi
++++ b/arch/arm64/boot/dts/qcom/sm6115.dtsi
+@@ -1656,6 +1656,7 @@ usb_dwc3: usb@4e00000 {
+ snps,has-lpm-erratum;
+ snps,hird-threshold = /bits/ 8 <0x10>;
+ snps,usb3_lpm_capable;
++ snps,parkmode-disable-ss-quirk;
+
+ usb-role-switch;
+
+diff --git a/arch/arm64/boot/dts/qcom/sm6350.dtsi b/arch/arm64/boot/dts/qcom/sm6350.dtsi
+index 84ff20a96c838..6c7eac0110ba1 100644
+--- a/arch/arm64/boot/dts/qcom/sm6350.dtsi
++++ b/arch/arm64/boot/dts/qcom/sm6350.dtsi
+@@ -1890,6 +1890,7 @@ usb_1_dwc3: usb@a600000 {
+ snps,dis_enblslpm_quirk;
+ snps,has-lpm-erratum;
+ snps,hird-threshold = /bits/ 8 <0x10>;
++ snps,parkmode-disable-ss-quirk;
+ phys = <&usb_1_hsphy>, <&usb_1_qmpphy QMP_USB43DP_USB3_PHY>;
+ phy-names = "usb2-phy", "usb3-phy";
+ };
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+index be6b1e7d07ce3..7618ae1f8b1c9 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-crd.dts
+@@ -659,7 +659,7 @@ &pcie6a {
+ };
+
+ &pcie6a_phy {
+- vdda-phy-supply = <&vreg_l3j_0p8>;
++ vdda-phy-supply = <&vreg_l1d_0p8>;
+ vdda-pll-supply = <&vreg_l2j_1p2>;
+
+ status = "okay";
+@@ -841,7 +841,7 @@ &uart21 {
+
+ &usb_1_ss0_hsphy {
+ vdd-supply = <&vreg_l2e_0p8>;
+- vdda12-supply = <&vreg_l3e_1p2>;
++ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_0_eusb2_repeater>;
+
+@@ -849,6 +849,9 @@ &usb_1_ss0_hsphy {
+ };
+
+ &usb_1_ss0_qmpphy {
++ vdda-phy-supply = <&vreg_l3e_1p2>;
++ vdda-pll-supply = <&vreg_l1j_0p8>;
++
+ status = "okay";
+ };
+
+@@ -863,7 +866,7 @@ &usb_1_ss0_dwc3 {
+
+ &usb_1_ss1_hsphy {
+ vdd-supply = <&vreg_l2e_0p8>;
+- vdda12-supply = <&vreg_l3e_1p2>;
++ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_1_eusb2_repeater>;
+
+@@ -871,6 +874,9 @@ &usb_1_ss1_hsphy {
+ };
+
+ &usb_1_ss1_qmpphy {
++ vdda-phy-supply = <&vreg_l3e_1p2>;
++ vdda-pll-supply = <&vreg_l2d_0p9>;
++
+ status = "okay";
+ };
+
+@@ -885,7 +891,7 @@ &usb_1_ss1_dwc3 {
+
+ &usb_1_ss2_hsphy {
+ vdd-supply = <&vreg_l2e_0p8>;
+- vdda12-supply = <&vreg_l3e_1p2>;
++ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_2_eusb2_repeater>;
+
+@@ -893,6 +899,9 @@ &usb_1_ss2_hsphy {
+ };
+
+ &usb_1_ss2_qmpphy {
++ vdda-phy-supply = <&vreg_l3e_1p2>;
++ vdda-pll-supply = <&vreg_l2d_0p9>;
++
+ status = "okay";
+ };
+
+diff --git a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+index 8f67c393b871b..5567636c8b27f 100644
+--- a/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
++++ b/arch/arm64/boot/dts/qcom/x1e80100-qcp.dts
+@@ -470,7 +470,7 @@ &pcie6a {
+ };
+
+ &pcie6a_phy {
+- vdda-phy-supply = <&vreg_l3j_0p8>;
++ vdda-phy-supply = <&vreg_l1d_0p8>;
+ vdda-pll-supply = <&vreg_l2j_1p2>;
+
+ status = "okay";
+@@ -537,7 +537,7 @@ &uart21 {
+
+ &usb_1_ss0_hsphy {
+ vdd-supply = <&vreg_l2e_0p8>;
+- vdda12-supply = <&vreg_l3e_1p2>;
++ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_0_eusb2_repeater>;
+
+@@ -545,6 +545,9 @@ &usb_1_ss0_hsphy {
+ };
+
+ &usb_1_ss0_qmpphy {
++ vdda-phy-supply = <&vreg_l3e_1p2>;
++ vdda-pll-supply = <&vreg_l1j_0p8>;
++
+ status = "okay";
+ };
+
+@@ -559,7 +562,7 @@ &usb_1_ss0_dwc3 {
+
+ &usb_1_ss1_hsphy {
+ vdd-supply = <&vreg_l2e_0p8>;
+- vdda12-supply = <&vreg_l3e_1p2>;
++ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_1_eusb2_repeater>;
+
+@@ -567,6 +570,9 @@ &usb_1_ss1_hsphy {
+ };
+
+ &usb_1_ss1_qmpphy {
++ vdda-phy-supply = <&vreg_l3e_1p2>;
++ vdda-pll-supply = <&vreg_l2d_0p9>;
++
+ status = "okay";
+ };
+
+@@ -581,7 +587,7 @@ &usb_1_ss1_dwc3 {
+
+ &usb_1_ss2_hsphy {
+ vdd-supply = <&vreg_l2e_0p8>;
+- vdda12-supply = <&vreg_l3e_1p2>;
++ vdda12-supply = <&vreg_l2j_1p2>;
+
+ phys = <&smb2360_2_eusb2_repeater>;
+
+@@ -589,6 +595,9 @@ &usb_1_ss2_hsphy {
+ };
+
+ &usb_1_ss2_qmpphy {
++ vdda-phy-supply = <&vreg_l3e_1p2>;
++ vdda-pll-supply = <&vreg_l2d_0p9>;
++
+ status = "okay";
+ };
+
+diff --git a/arch/s390/mm/fault.c b/arch/s390/mm/fault.c
+index 65747f15dbec4..c848966ed1759 100644
+--- a/arch/s390/mm/fault.c
++++ b/arch/s390/mm/fault.c
+@@ -433,12 +433,13 @@ static void do_exception(struct pt_regs *regs, int access)
+ handle_fault_error_nolock(regs, 0);
+ else
+ do_sigsegv(regs, SEGV_MAPERR);
+- } else if (fault & VM_FAULT_SIGBUS) {
++ } else if (fault & (VM_FAULT_SIGBUS | VM_FAULT_HWPOISON)) {
+ if (!user_mode(regs))
+ handle_fault_error_nolock(regs, 0);
+ else
+ do_sigbus(regs);
+ } else {
++ pr_emerg("Unexpected fault flags: %08x\n", fault);
+ BUG();
+ }
+ }
+diff --git a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+index 101038395c3b4..772604feb6acd 100644
+--- a/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
++++ b/drivers/gpu/drm/amd/amdgpu/sdma_v4_0.c
+@@ -2017,7 +2017,7 @@ static int sdma_v4_0_process_trap_irq(struct amdgpu_device *adev,
+ struct amdgpu_irq_src *source,
+ struct amdgpu_iv_entry *entry)
+ {
+- uint32_t instance;
++ int instance;
+
+ DRM_DEBUG("IH: SDMA trap\n");
+ instance = sdma_v4_0_irq_id_to_seq(entry->client_id);
+diff --git a/drivers/net/tap.c b/drivers/net/tap.c
+index bfdd3875fe865..77574f7a3bd45 100644
+--- a/drivers/net/tap.c
++++ b/drivers/net/tap.c
+@@ -1177,6 +1177,11 @@ static int tap_get_user_xdp(struct tap_queue *q, struct xdp_buff *xdp)
+ struct sk_buff *skb;
+ int err, depth;
+
++ if (unlikely(xdp->data_end - xdp->data < ETH_HLEN)) {
++ err = -EINVAL;
++ goto err;
++ }
++
+ if (q->flags & IFF_VNET_HDR)
+ vnet_hdr_len = READ_ONCE(q->vnet_hdr_sz);
+
+diff --git a/drivers/net/tun.c b/drivers/net/tun.c
+index 9254bca2813dc..4a5107117b4a6 100644
+--- a/drivers/net/tun.c
++++ b/drivers/net/tun.c
+@@ -2451,6 +2451,9 @@ static int tun_xdp_one(struct tun_struct *tun,
+ bool skb_xdp = false;
+ struct page *page;
+
++ if (unlikely(datasize < ETH_HLEN))
++ return -EINVAL;
++
+ xdp_prog = rcu_dereference(tun->xdp_prog);
+ if (xdp_prog) {
+ if (gso->gso_type) {
+diff --git a/drivers/usb/gadget/function/f_midi2.c b/drivers/usb/gadget/function/f_midi2.c
+index ec8cd7c7bbfc1..0e38bb145e8f5 100644
+--- a/drivers/usb/gadget/function/f_midi2.c
++++ b/drivers/usb/gadget/function/f_midi2.c
+@@ -150,6 +150,9 @@ struct f_midi2 {
+
+ #define func_to_midi2(f) container_of(f, struct f_midi2, func)
+
++/* convert from MIDI protocol number (1 or 2) to SNDRV_UMP_EP_INFO_PROTO_* */
++#define to_ump_protocol(v) (((v) & 3) << 8)
++
+ /* get EP name string */
+ static const char *ump_ep_name(const struct f_midi2_ep *ep)
+ {
+@@ -564,8 +567,7 @@ static void reply_ump_stream_ep_config(struct f_midi2_ep *ep)
+ .status = UMP_STREAM_MSG_STATUS_STREAM_CFG,
+ };
+
+- if ((ep->info.protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI_MASK) ==
+- SNDRV_UMP_EP_INFO_PROTO_MIDI2)
++ if (ep->info.protocol == 2)
+ rep.protocol = UMP_STREAM_MSG_EP_INFO_CAP_MIDI2 >> 8;
+ else
+ rep.protocol = UMP_STREAM_MSG_EP_INFO_CAP_MIDI1 >> 8;
+@@ -627,13 +629,13 @@ static void process_ump_stream_msg(struct f_midi2_ep *ep, const u32 *data)
+ return;
+ case UMP_STREAM_MSG_STATUS_STREAM_CFG_REQUEST:
+ if (*data & UMP_STREAM_MSG_EP_INFO_CAP_MIDI2) {
+- ep->info.protocol = SNDRV_UMP_EP_INFO_PROTO_MIDI2;
++ ep->info.protocol = 2;
+ DBG(midi2, "Switching Protocol to MIDI2\n");
+ } else {
+- ep->info.protocol = SNDRV_UMP_EP_INFO_PROTO_MIDI1;
++ ep->info.protocol = 1;
+ DBG(midi2, "Switching Protocol to MIDI1\n");
+ }
+- snd_ump_switch_protocol(ep->ump, ep->info.protocol);
++ snd_ump_switch_protocol(ep->ump, to_ump_protocol(ep->info.protocol));
+ reply_ump_stream_ep_config(ep);
+ return;
+ case UMP_STREAM_MSG_STATUS_FB_DISCOVERY:
+@@ -1065,7 +1067,8 @@ static void f_midi2_midi1_ep_out_complete(struct usb_ep *usb_ep,
+ group = midi2->out_cable_mapping[cable].group;
+ bytes = midi1_packet_bytes[*buf & 0x0f];
+ for (c = 0; c < bytes; c++) {
+- snd_ump_convert_to_ump(cvt, group, ep->info.protocol,
++ snd_ump_convert_to_ump(cvt, group,
++ to_ump_protocol(ep->info.protocol),
+ buf[c + 1]);
+ if (cvt->ump_bytes) {
+ snd_ump_receive(ep->ump, cvt->ump,
+@@ -1375,7 +1378,7 @@ static void assign_block_descriptors(struct f_midi2 *midi2,
+ desc->nNumGroupTrm = b->num_groups;
+ desc->iBlockItem = ep->blks[blk].string_id;
+
+- if (ep->info.protocol & SNDRV_UMP_EP_INFO_PROTO_MIDI2)
++ if (ep->info.protocol == 2)
+ desc->bMIDIProtocol = USB_MS_MIDI_PROTO_2_0;
+ else
+ desc->bMIDIProtocol = USB_MS_MIDI_PROTO_1_0_128;
+@@ -1552,7 +1555,7 @@ static int f_midi2_create_card(struct f_midi2 *midi2)
+ if (midi2->info.static_block)
+ ump->info.flags |= SNDRV_UMP_EP_INFO_STATIC_BLOCKS;
+ ump->info.protocol_caps = (ep->info.protocol_caps & 3) << 8;
+- ump->info.protocol = (ep->info.protocol & 3) << 8;
++ ump->info.protocol = to_ump_protocol(ep->info.protocol);
+ ump->info.version = 0x0101;
+ ump->info.family_id = ep->info.family;
+ ump->info.model_id = ep->info.model;
+diff --git a/fs/jfs/xattr.c b/fs/jfs/xattr.c
+index 9987055293b35..2999ed5d83f5e 100644
+--- a/fs/jfs/xattr.c
++++ b/fs/jfs/xattr.c
+@@ -797,7 +797,7 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data,
+ size_t buf_size)
+ {
+ struct jfs_ea_list *ealist;
+- struct jfs_ea *ea;
++ struct jfs_ea *ea, *ealist_end;
+ struct ea_buffer ea_buf;
+ int xattr_size;
+ ssize_t size;
+@@ -817,9 +817,16 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data,
+ goto not_found;
+
+ ealist = (struct jfs_ea_list *) ea_buf.xattr;
++ ealist_end = END_EALIST(ealist);
+
+ /* Find the named attribute */
+- for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea))
++ for (ea = FIRST_EA(ealist); ea < ealist_end; ea = NEXT_EA(ea)) {
++ if (unlikely(ea + 1 > ealist_end) ||
++ unlikely(NEXT_EA(ea) > ealist_end)) {
++ size = -EUCLEAN;
++ goto release;
++ }
++
+ if ((namelen == ea->namelen) &&
+ memcmp(name, ea->name, namelen) == 0) {
+ /* Found it */
+@@ -834,6 +841,7 @@ ssize_t __jfs_getxattr(struct inode *inode, const char *name, void *data,
+ memcpy(data, value, size);
+ goto release;
+ }
++ }
+ not_found:
+ size = -ENODATA;
+ release:
+@@ -861,7 +869,7 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size)
+ ssize_t size = 0;
+ int xattr_size;
+ struct jfs_ea_list *ealist;
+- struct jfs_ea *ea;
++ struct jfs_ea *ea, *ealist_end;
+ struct ea_buffer ea_buf;
+
+ down_read(&JFS_IP(inode)->xattr_sem);
+@@ -876,9 +884,16 @@ ssize_t jfs_listxattr(struct dentry * dentry, char *data, size_t buf_size)
+ goto release;
+
+ ealist = (struct jfs_ea_list *) ea_buf.xattr;
++ ealist_end = END_EALIST(ealist);
+
+ /* compute required size of list */
+- for (ea = FIRST_EA(ealist); ea < END_EALIST(ealist); ea = NEXT_EA(ea)) {
++ for (ea = FIRST_EA(ealist); ea < ealist_end; ea = NEXT_EA(ea)) {
++ if (unlikely(ea + 1 > ealist_end) ||
++ unlikely(NEXT_EA(ea) > ealist_end)) {
++ size = -EUCLEAN;
++ goto release;
++ }
++
+ if (can_list(ea))
+ size += name_size(ea) + 1;
+ }
+diff --git a/fs/locks.c b/fs/locks.c
+index bdd94c32256f5..9afb16e0683ff 100644
+--- a/fs/locks.c
++++ b/fs/locks.c
+@@ -2570,8 +2570,9 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
+ error = do_lock_file_wait(filp, cmd, file_lock);
+
+ /*
+- * Attempt to detect a close/fcntl race and recover by releasing the
+- * lock that was just acquired. There is no need to do that when we're
++ * Detect close/fcntl races and recover by zapping all POSIX locks
++ * associated with this file and our files_struct, just like on
++ * filp_flush(). There is no need to do that when we're
+ * unlocking though, or for OFD locks.
+ */
+ if (!error && file_lock->c.flc_type != F_UNLCK &&
+@@ -2586,9 +2587,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
+ f = files_lookup_fd_locked(files, fd);
+ spin_unlock(&files->file_lock);
+ if (f != filp) {
+- file_lock->c.flc_type = F_UNLCK;
+- error = do_lock_file_wait(filp, cmd, file_lock);
+- WARN_ON_ONCE(error);
++ locks_remove_posix(filp, files);
+ error = -EBADF;
+ }
+ }
+diff --git a/fs/ntfs3/fslog.c b/fs/ntfs3/fslog.c
+index d7807d255dfe2..40926bf392d28 100644
+--- a/fs/ntfs3/fslog.c
++++ b/fs/ntfs3/fslog.c
+@@ -724,7 +724,8 @@ static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes)
+
+ if (!rsize || rsize > bytes ||
+ rsize + sizeof(struct RESTART_TABLE) > bytes || bytes < ts ||
+- le16_to_cpu(rt->total) > ne || ff > ts || lf > ts ||
++ le16_to_cpu(rt->total) > ne ||
++ ff > ts - sizeof(__le32) || lf > ts - sizeof(__le32) ||
+ (ff && ff < sizeof(struct RESTART_TABLE)) ||
+ (lf && lf < sizeof(struct RESTART_TABLE))) {
+ return false;
+@@ -754,6 +755,9 @@ static bool check_rstbl(const struct RESTART_TABLE *rt, size_t bytes)
+ return false;
+
+ off = le32_to_cpu(*(__le32 *)Add2Ptr(rt, off));
++
++ if (off > ts - sizeof(__le32))
++ return false;
+ }
+
+ return true;
+@@ -3722,6 +3726,8 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
+
+ u64 rec_lsn, checkpt_lsn = 0, rlsn = 0;
+ struct ATTR_NAME_ENTRY *attr_names = NULL;
++ u32 attr_names_bytes = 0;
++ u32 oatbl_bytes = 0;
+ struct RESTART_TABLE *dptbl = NULL;
+ struct RESTART_TABLE *trtbl = NULL;
+ const struct RESTART_TABLE *rt;
+@@ -3736,6 +3742,7 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
+ struct NTFS_RESTART *rst = NULL;
+ struct lcb *lcb = NULL;
+ struct OPEN_ATTR_ENRTY *oe;
++ struct ATTR_NAME_ENTRY *ane;
+ struct TRANSACTION_ENTRY *tr;
+ struct DIR_PAGE_ENTRY *dp;
+ u32 i, bytes_per_attr_entry;
+@@ -4314,17 +4321,40 @@ int log_replay(struct ntfs_inode *ni, bool *initialized)
+ lcb = NULL;
+
+ check_attribute_names2:
+- if (rst->attr_names_len && oatbl) {
+- struct ATTR_NAME_ENTRY *ane = attr_names;
+- while (ane->off) {
++ if (attr_names && oatbl) {
++ off = 0;
++ for (;;) {
++ /* Check we can use attribute name entry 'ane'. */
++ static_assert(sizeof(*ane) == 4);
++ if (off + sizeof(*ane) > attr_names_bytes) {
++ /* just ignore the rest. */
++ break;
++ }
++
++ ane = Add2Ptr(attr_names, off);
++ t16 = le16_to_cpu(ane->off);
++ if (!t16) {
++ /* this is the only valid exit. */
++ break;
++ }
++
++ /* Check we can use open attribute entry 'oe'. */
++ if (t16 + sizeof(*oe) > oatbl_bytes) {
++ /* just ignore the rest. */
++ break;
++ }
++
+ /* TODO: Clear table on exit! */
+- oe = Add2Ptr(oatbl, le16_to_cpu(ane->off));
++ oe = Add2Ptr(oatbl, t16);
+ t16 = le16_to_cpu(ane->name_bytes);
++ off += t16 + sizeof(*ane);
++ if (off > attr_names_bytes) {
++ /* just ignore the rest. */
++ break;
++ }
+ oe->name_len = t16 / sizeof(short);
+ oe->ptr = ane->name;
+ oe->is_attr_name = 2;
+- ane = Add2Ptr(ane,
+- sizeof(struct ATTR_NAME_ENTRY) + t16);
+ }
+ }
+
+diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
+index d620d4c53c6fa..f0beb173dbba2 100644
+--- a/fs/ocfs2/dir.c
++++ b/fs/ocfs2/dir.c
+@@ -294,13 +294,16 @@ static void ocfs2_dx_dir_name_hash(struct inode *dir, const char *name, int len,
+ * bh passed here can be an inode block or a dir data block, depending
+ * on the inode inline data flag.
+ */
+-static int ocfs2_check_dir_entry(struct inode * dir,
+- struct ocfs2_dir_entry * de,
+- struct buffer_head * bh,
++static int ocfs2_check_dir_entry(struct inode *dir,
++ struct ocfs2_dir_entry *de,
++ struct buffer_head *bh,
++ char *buf,
++ unsigned int size,
+ unsigned long offset)
+ {
+ const char *error_msg = NULL;
+ const int rlen = le16_to_cpu(de->rec_len);
++ const unsigned long next_offset = ((char *) de - buf) + rlen;
+
+ if (unlikely(rlen < OCFS2_DIR_REC_LEN(1)))
+ error_msg = "rec_len is smaller than minimal";
+@@ -308,9 +311,11 @@ static int ocfs2_check_dir_entry(struct inode * dir,
+ error_msg = "rec_len % 4 != 0";
+ else if (unlikely(rlen < OCFS2_DIR_REC_LEN(de->name_len)))
+ error_msg = "rec_len is too small for name_len";
+- else if (unlikely(
+- ((char *) de - bh->b_data) + rlen > dir->i_sb->s_blocksize))
+- error_msg = "directory entry across blocks";
++ else if (unlikely(next_offset > size))
++ error_msg = "directory entry overrun";
++ else if (unlikely(next_offset > size - OCFS2_DIR_REC_LEN(1)) &&
++ next_offset != size)
++ error_msg = "directory entry too close to end";
+
+ if (unlikely(error_msg != NULL))
+ mlog(ML_ERROR, "bad entry in directory #%llu: %s - "
+@@ -352,16 +357,17 @@ static inline int ocfs2_search_dirblock(struct buffer_head *bh,
+ de_buf = first_de;
+ dlimit = de_buf + bytes;
+
+- while (de_buf < dlimit) {
++ while (de_buf < dlimit - OCFS2_DIR_MEMBER_LEN) {
+ /* this code is executed quadratically often */
+ /* do minimal checking `by hand' */
+
+ de = (struct ocfs2_dir_entry *) de_buf;
+
+- if (de_buf + namelen <= dlimit &&
++ if (de->name + namelen <= dlimit &&
+ ocfs2_match(namelen, name, de)) {
+ /* found a match - just to be sure, do a full check */
+- if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
++ if (!ocfs2_check_dir_entry(dir, de, bh, first_de,
++ bytes, offset)) {
+ ret = -1;
+ goto bail;
+ }
+@@ -1138,7 +1144,7 @@ static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
+ pde = NULL;
+ de = (struct ocfs2_dir_entry *) first_de;
+ while (i < bytes) {
+- if (!ocfs2_check_dir_entry(dir, de, bh, i)) {
++ if (!ocfs2_check_dir_entry(dir, de, bh, first_de, bytes, i)) {
+ status = -EIO;
+ mlog_errno(status);
+ goto bail;
+@@ -1635,7 +1641,8 @@ int __ocfs2_add_entry(handle_t *handle,
+ /* These checks should've already been passed by the
+ * prepare function, but I guess we can leave them
+ * here anyway. */
+- if (!ocfs2_check_dir_entry(dir, de, insert_bh, offset)) {
++ if (!ocfs2_check_dir_entry(dir, de, insert_bh, data_start,
++ size, offset)) {
+ retval = -ENOENT;
+ goto bail;
+ }
+@@ -1774,7 +1781,8 @@ static int ocfs2_dir_foreach_blk_id(struct inode *inode,
+ }
+
+ de = (struct ocfs2_dir_entry *) (data->id_data + ctx->pos);
+- if (!ocfs2_check_dir_entry(inode, de, di_bh, ctx->pos)) {
++ if (!ocfs2_check_dir_entry(inode, de, di_bh, (char *)data->id_data,
++ i_size_read(inode), ctx->pos)) {
+ /* On error, skip the f_pos to the end. */
+ ctx->pos = i_size_read(inode);
+ break;
+@@ -1867,7 +1875,8 @@ static int ocfs2_dir_foreach_blk_el(struct inode *inode,
+ while (ctx->pos < i_size_read(inode)
+ && offset < sb->s_blocksize) {
+ de = (struct ocfs2_dir_entry *) (bh->b_data + offset);
+- if (!ocfs2_check_dir_entry(inode, de, bh, offset)) {
++ if (!ocfs2_check_dir_entry(inode, de, bh, bh->b_data,
++ sb->s_blocksize, offset)) {
+ /* On error, skip the f_pos to the
+ next block. */
+ ctx->pos = (ctx->pos | (sb->s_blocksize - 1)) + 1;
+@@ -3339,7 +3348,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
+ struct super_block *sb = dir->i_sb;
+ struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+ struct ocfs2_dir_entry *de, *last_de = NULL;
+- char *de_buf, *limit;
++ char *first_de, *de_buf, *limit;
+ unsigned long offset = 0;
+ unsigned int rec_len, new_rec_len, free_space;
+
+@@ -3352,14 +3361,16 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
+ else
+ free_space = dir->i_sb->s_blocksize - i_size_read(dir);
+
+- de_buf = di->id2.i_data.id_data;
++ first_de = di->id2.i_data.id_data;
++ de_buf = first_de;
+ limit = de_buf + i_size_read(dir);
+ rec_len = OCFS2_DIR_REC_LEN(namelen);
+
+ while (de_buf < limit) {
+ de = (struct ocfs2_dir_entry *)de_buf;
+
+- if (!ocfs2_check_dir_entry(dir, de, di_bh, offset)) {
++ if (!ocfs2_check_dir_entry(dir, de, di_bh, first_de,
++ i_size_read(dir), offset)) {
+ ret = -ENOENT;
+ goto out;
+ }
+@@ -3441,7 +3452,8 @@ static int ocfs2_find_dir_space_el(struct inode *dir, const char *name,
+ /* move to next block */
+ de = (struct ocfs2_dir_entry *) bh->b_data;
+ }
+- if (!ocfs2_check_dir_entry(dir, de, bh, offset)) {
++ if (!ocfs2_check_dir_entry(dir, de, bh, bh->b_data, blocksize,
++ offset)) {
+ status = -ENOENT;
+ goto bail;
+ }
+diff --git a/sound/core/pcm_dmaengine.c b/sound/core/pcm_dmaengine.c
+index cc5db93b9132c..4786b5a0b984f 100644
+--- a/sound/core/pcm_dmaengine.c
++++ b/sound/core/pcm_dmaengine.c
+@@ -352,8 +352,12 @@ EXPORT_SYMBOL_GPL(snd_dmaengine_pcm_open_request_chan);
+ int snd_dmaengine_pcm_sync_stop(struct snd_pcm_substream *substream)
+ {
+ struct dmaengine_pcm_runtime_data *prtd = substream_to_prtd(substream);
++ struct dma_tx_state state;
++ enum dma_status status;
+
+- dmaengine_synchronize(prtd->dma_chan);
++ status = dmaengine_tx_status(prtd->dma_chan, prtd->cookie, &state);
++ if (status != DMA_PAUSED)
++ dmaengine_synchronize(prtd->dma_chan);
+
+ return 0;
+ }
+diff --git a/sound/core/seq/seq_ump_client.c b/sound/core/seq/seq_ump_client.c
+index c627d72f7fe20..9cdfbeae3ed59 100644
+--- a/sound/core/seq/seq_ump_client.c
++++ b/sound/core/seq/seq_ump_client.c
+@@ -28,6 +28,7 @@ struct seq_ump_group {
+ int group; /* group index (0-based) */
+ unsigned int dir_bits; /* directions */
+ bool active; /* activeness */
++ bool valid; /* valid group (referred by blocks) */
+ char name[64]; /* seq port name */
+ };
+
+@@ -210,6 +211,13 @@ static void fill_port_info(struct snd_seq_port_info *port,
+ sprintf(port->name, "Group %d", group->group + 1);
+ }
+
++/* skip non-existing group for static blocks */
++static bool skip_group(struct seq_ump_client *client, struct seq_ump_group *group)
++{
++ return !group->valid &&
++ (client->ump->info.flags & SNDRV_UMP_EP_INFO_STATIC_BLOCKS);
++}
++
+ /* create a new sequencer port per UMP group */
+ static int seq_ump_group_init(struct seq_ump_client *client, int group_index)
+ {
+@@ -217,6 +225,9 @@ static int seq_ump_group_init(struct seq_ump_client *client, int group_index)
+ struct snd_seq_port_info *port __free(kfree) = NULL;
+ struct snd_seq_port_callback pcallbacks;
+
++ if (skip_group(client, group))
++ return 0;
++
+ port = kzalloc(sizeof(*port), GFP_KERNEL);
+ if (!port)
+ return -ENOMEM;
+@@ -250,6 +261,9 @@ static void update_port_infos(struct seq_ump_client *client)
+ return;
+
+ for (i = 0; i < SNDRV_UMP_MAX_GROUPS; i++) {
++ if (skip_group(client, &client->groups[i]))
++ continue;
++
+ old->addr.client = client->seq_client;
+ old->addr.port = i;
+ err = snd_seq_kernel_client_ctl(client->seq_client,
+@@ -284,6 +298,7 @@ static void update_group_attrs(struct seq_ump_client *client)
+ group->dir_bits = 0;
+ group->active = 0;
+ group->group = i;
++ group->valid = false;
+ }
+
+ list_for_each_entry(fb, &client->ump->block_list, list) {
+@@ -291,6 +306,7 @@ static void update_group_attrs(struct seq_ump_client *client)
+ break;
+ group = &client->groups[fb->info.first_group];
+ for (i = 0; i < fb->info.num_groups; i++, group++) {
++ group->valid = true;
+ if (fb->info.active)
+ group->active = 1;
+ switch (fb->info.direction) {
+diff --git a/sound/pci/hda/patch_realtek.c b/sound/pci/hda/patch_realtek.c
+index 766f0b1d3e9d6..6f4512b598eaa 100644
+--- a/sound/pci/hda/patch_realtek.c
++++ b/sound/pci/hda/patch_realtek.c
+@@ -10384,6 +10384,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x10cf, 0x1845, "Lifebook U904", ALC269_FIXUP_LIFEBOOK_EXTMIC),
+ SND_PCI_QUIRK(0x10ec, 0x10f2, "Intel Reference board", ALC700_FIXUP_INTEL_REFERENCE),
+ SND_PCI_QUIRK(0x10ec, 0x118c, "Medion EE4254 MD62100", ALC256_FIXUP_MEDION_HEADSET_NO_PRESENCE),
++ SND_PCI_QUIRK(0x10ec, 0x119e, "Positivo SU C1400", ALC269_FIXUP_ASPIRE_HEADSET_MIC),
+ SND_PCI_QUIRK(0x10ec, 0x11bc, "VAIO VJFE-IL", ALC269_FIXUP_LIMIT_INT_MIC_BOOST),
+ SND_PCI_QUIRK(0x10ec, 0x1230, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+ SND_PCI_QUIRK(0x10ec, 0x124c, "Intel Reference board", ALC295_FIXUP_CHROME_BOOK),
+@@ -10398,6 +10399,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x144d, 0xc189, "Samsung Galaxy Flex Book (NT950QCG-X716)", ALC298_FIXUP_SAMSUNG_AMP),
+ SND_PCI_QUIRK(0x144d, 0xc18a, "Samsung Galaxy Book Ion (NP930XCJ-K01US)", ALC298_FIXUP_SAMSUNG_AMP),
+ SND_PCI_QUIRK(0x144d, 0xc1a3, "Samsung Galaxy Book Pro (NP935XDB-KC1SE)", ALC298_FIXUP_SAMSUNG_AMP),
++ SND_PCI_QUIRK(0x144d, 0xc1a4, "Samsung Galaxy Book Pro 360 (NT935QBD)", ALC298_FIXUP_SAMSUNG_AMP),
+ SND_PCI_QUIRK(0x144d, 0xc1a6, "Samsung Galaxy Book Pro 360 (NP930QBD)", ALC298_FIXUP_SAMSUNG_AMP),
+ SND_PCI_QUIRK(0x144d, 0xc740, "Samsung Ativ book 8 (NP870Z5G)", ALC269_FIXUP_ATIV_BOOK_8),
+ SND_PCI_QUIRK(0x144d, 0xc812, "Samsung Notebook Pen S (NT950SBE-X58)", ALC298_FIXUP_SAMSUNG_AMP),
+@@ -10539,6 +10541,7 @@ static const struct snd_pci_quirk alc269_fixup_tbl[] = {
+ SND_PCI_QUIRK(0x17aa, 0x231a, "Thinkpad Z16 Gen2", ALC287_FIXUP_MG_RTKC_CSAMP_CS35L41_I2C_THINKPAD),
+ SND_PCI_QUIRK(0x17aa, 0x231e, "Thinkpad", ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318),
+ SND_PCI_QUIRK(0x17aa, 0x231f, "Thinkpad", ALC287_FIXUP_LENOVO_THKPAD_WH_ALC1318),
++ SND_PCI_QUIRK(0x17aa, 0x2326, "Hera2", ALC287_FIXUP_TAS2781_I2C),
+ SND_PCI_QUIRK(0x17aa, 0x30bb, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
+ SND_PCI_QUIRK(0x17aa, 0x30e2, "ThinkCentre AIO", ALC233_FIXUP_LENOVO_LINE2_MIC_HOTKEY),
+ SND_PCI_QUIRK(0x17aa, 0x310c, "ThinkCentre Station", ALC294_FIXUP_LENOVO_MIC_LOCATION),
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-24 16:59 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-24 16:59 UTC (permalink / raw
To: gentoo-commits
commit: 08313eaadefe3db6afdc29c1020c20543980ad33
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Jul 24 16:58:34 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Jul 24 16:58:34 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=08313eaa
Removal of BMQ due to compilation error
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 8 -
...BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch | 11474 -------------------
5021_BMQ-and-PDS-gentoo-defaults.patch | 13 -
3 files changed, 11495 deletions(-)
diff --git a/0000_README b/0000_README
index 2560b5da..d91abe89 100644
--- a/0000_README
+++ b/0000_README
@@ -86,11 +86,3 @@ Desc: Add Gentoo Linux support config settings and defaults.
Patch: 5010_enable-cpu-optimizations-universal.patch
From: https://github.com/graysky2/kernel_compiler_patch
Desc: Kernel >= 5.15 patch enables gcc = v11.1+ optimizations for additional CPUs.
-
-Patch: 5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch
-From: https://github.com/hhoffstaette/kernel-patches
-Desc: BMQ(BitMap Queue) Scheduler. A new CPU scheduler developed from PDS(incld). Inspired by the scheduler in zircon.
-
-Patch: 5021_BMQ-and-PDS-gentoo-defaults.patch
-From: https://gitweb.gentoo.org/proj/linux-patches.git/
-Desc: Set defaults for BMQ. default to n
diff --git a/5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch b/5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch
deleted file mode 100644
index 4ebad9ef..00000000
--- a/5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch
+++ /dev/null
@@ -1,11474 +0,0 @@
-diff --new-file -rup linux-6.10/Documentation/admin-guide/sysctl/kernel.rst linux-prjc-linux-6.10.y-prjc/Documentation/admin-guide/sysctl/kernel.rst
---- linux-6.10/Documentation/admin-guide/sysctl/kernel.rst 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/Documentation/admin-guide/sysctl/kernel.rst 2024-07-15 16:47:37.000000000 +0200
-@@ -1673,3 +1673,12 @@ is 10 seconds.
-
- The softlockup threshold is (``2 * watchdog_thresh``). Setting this
- tunable to zero will disable lockup detection altogether.
-+
-+yield_type:
-+===========
-+
-+BMQ/PDS CPU scheduler only. This determines what type of yield calls
-+to sched_yield() will be performed.
-+
-+ 0 - No yield.
-+ 1 - Requeue task. (default)
-diff --new-file -rup linux-6.10/Documentation/scheduler/sched-BMQ.txt linux-prjc-linux-6.10.y-prjc/Documentation/scheduler/sched-BMQ.txt
---- linux-6.10/Documentation/scheduler/sched-BMQ.txt 1970-01-01 01:00:00.000000000 +0100
-+++ linux-prjc-linux-6.10.y-prjc/Documentation/scheduler/sched-BMQ.txt 2024-07-15 16:47:37.000000000 +0200
-@@ -0,0 +1,110 @@
-+ BitMap queue CPU Scheduler
-+ --------------------------
-+
-+CONTENT
-+========
-+
-+ Background
-+ Design
-+ Overview
-+ Task policy
-+ Priority management
-+ BitMap Queue
-+ CPU Assignment and Migration
-+
-+
-+Background
-+==========
-+
-+BitMap Queue CPU scheduler, referred to as BMQ from here on, is an evolution
-+of previous Priority and Deadline based Skiplist multiple queue scheduler(PDS),
-+and inspired by Zircon scheduler. The goal of it is to keep the scheduler code
-+simple, while efficiency and scalable for interactive tasks, such as desktop,
-+movie playback and gaming etc.
-+
-+Design
-+======
-+
-+Overview
-+--------
-+
-+BMQ use per CPU run queue design, each CPU(logical) has it's own run queue,
-+each CPU is responsible for scheduling the tasks that are putting into it's
-+run queue.
-+
-+The run queue is a set of priority queues. Note that these queues are fifo
-+queue for non-rt tasks or priority queue for rt tasks in data structure. See
-+BitMap Queue below for details. BMQ is optimized for non-rt tasks in the fact
-+that most applications are non-rt tasks. No matter the queue is fifo or
-+priority, In each queue is an ordered list of runnable tasks awaiting execution
-+and the data structures are the same. When it is time for a new task to run,
-+the scheduler simply looks the lowest numbered queueue that contains a task,
-+and runs the first task from the head of that queue. And per CPU idle task is
-+also in the run queue, so the scheduler can always find a task to run on from
-+its run queue.
-+
-+Each task will assigned the same timeslice(default 4ms) when it is picked to
-+start running. Task will be reinserted at the end of the appropriate priority
-+queue when it uses its whole timeslice. When the scheduler selects a new task
-+from the priority queue it sets the CPU's preemption timer for the remainder of
-+the previous timeslice. When that timer fires the scheduler will stop execution
-+on that task, select another task and start over again.
-+
-+If a task blocks waiting for a shared resource then it's taken out of its
-+priority queue and is placed in a wait queue for the shared resource. When it
-+is unblocked it will be reinserted in the appropriate priority queue of an
-+eligible CPU.
-+
-+Task policy
-+-----------
-+
-+BMQ supports DEADLINE, FIFO, RR, NORMAL, BATCH and IDLE task policy like the
-+mainline CFS scheduler. But BMQ is heavy optimized for non-rt task, that's
-+NORMAL/BATCH/IDLE policy tasks. Below is the implementation detail of each
-+policy.
-+
-+DEADLINE
-+ It is squashed as priority 0 FIFO task.
-+
-+FIFO/RR
-+ All RT tasks share one single priority queue in BMQ run queue designed. The
-+complexity of insert operation is O(n). BMQ is not designed for system runs
-+with major rt policy tasks.
-+
-+NORMAL/BATCH/IDLE
-+ BATCH and IDLE tasks are treated as the same policy. They compete CPU with
-+NORMAL policy tasks, but they just don't boost. To control the priority of
-+NORMAL/BATCH/IDLE tasks, simply use nice level.
-+
-+ISO
-+ ISO policy is not supported in BMQ. Please use nice level -20 NORMAL policy
-+task instead.
-+
-+Priority management
-+-------------------
-+
-+RT tasks have priority from 0-99. For non-rt tasks, there are three different
-+factors used to determine the effective priority of a task. The effective
-+priority being what is used to determine which queue it will be in.
-+
-+The first factor is simply the task’s static priority. Which is assigned from
-+task's nice level, within [-20, 19] in userland's point of view and [0, 39]
-+internally.
-+
-+The second factor is the priority boost. This is a value bounded between
-+[-MAX_PRIORITY_ADJ, MAX_PRIORITY_ADJ] used to offset the base priority, it is
-+modified by the following cases:
-+
-+*When a thread has used up its entire timeslice, always deboost its boost by
-+increasing by one.
-+*When a thread gives up cpu control(voluntary or non-voluntary) to reschedule,
-+and its switch-in time(time after last switch and run) below the thredhold
-+based on its priority boost, will boost its boost by decreasing by one buti is
-+capped at 0 (won’t go negative).
-+
-+The intent in this system is to ensure that interactive threads are serviced
-+quickly. These are usually the threads that interact directly with the user
-+and cause user-perceivable latency. These threads usually do little work and
-+spend most of their time blocked awaiting another user event. So they get the
-+priority boost from unblocking while background threads that do most of the
-+processing receive the priority penalty for using their entire timeslice.
-diff --new-file -rup linux-6.10/fs/proc/base.c linux-prjc-linux-6.10.y-prjc/fs/proc/base.c
---- linux-6.10/fs/proc/base.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/fs/proc/base.c 2024-07-15 16:47:37.000000000 +0200
-@@ -481,7 +481,7 @@ static int proc_pid_schedstat(struct seq
- seq_puts(m, "0 0 0\n");
- else
- seq_printf(m, "%llu %llu %lu\n",
-- (unsigned long long)task->se.sum_exec_runtime,
-+ (unsigned long long)tsk_seruntime(task),
- (unsigned long long)task->sched_info.run_delay,
- task->sched_info.pcount);
-
-diff --new-file -rup linux-6.10/include/asm-generic/resource.h linux-prjc-linux-6.10.y-prjc/include/asm-generic/resource.h
---- linux-6.10/include/asm-generic/resource.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/include/asm-generic/resource.h 2024-07-15 16:47:37.000000000 +0200
-@@ -23,7 +23,7 @@
- [RLIMIT_LOCKS] = { RLIM_INFINITY, RLIM_INFINITY }, \
- [RLIMIT_SIGPENDING] = { 0, 0 }, \
- [RLIMIT_MSGQUEUE] = { MQ_BYTES_MAX, MQ_BYTES_MAX }, \
-- [RLIMIT_NICE] = { 0, 0 }, \
-+ [RLIMIT_NICE] = { 30, 30 }, \
- [RLIMIT_RTPRIO] = { 0, 0 }, \
- [RLIMIT_RTTIME] = { RLIM_INFINITY, RLIM_INFINITY }, \
- }
-diff --new-file -rup linux-6.10/include/linux/sched/deadline.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/deadline.h
---- linux-6.10/include/linux/sched/deadline.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/deadline.h 2024-07-15 16:47:37.000000000 +0200
-@@ -2,6 +2,25 @@
- #ifndef _LINUX_SCHED_DEADLINE_H
- #define _LINUX_SCHED_DEADLINE_H
-
-+#ifdef CONFIG_SCHED_ALT
-+
-+static inline int dl_task(struct task_struct *p)
-+{
-+ return 0;
-+}
-+
-+#ifdef CONFIG_SCHED_BMQ
-+#define __tsk_deadline(p) (0UL)
-+#endif
-+
-+#ifdef CONFIG_SCHED_PDS
-+#define __tsk_deadline(p) ((((u64) ((p)->prio))<<56) | (p)->deadline)
-+#endif
-+
-+#else
-+
-+#define __tsk_deadline(p) ((p)->dl.deadline)
-+
- /*
- * SCHED_DEADLINE tasks has negative priorities, reflecting
- * the fact that any of them has higher prio than RT and
-@@ -23,6 +42,7 @@ static inline int dl_task(struct task_st
- {
- return dl_prio(p->prio);
- }
-+#endif /* CONFIG_SCHED_ALT */
-
- static inline bool dl_time_before(u64 a, u64 b)
- {
-diff --new-file -rup linux-6.10/include/linux/sched/prio.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/prio.h
---- linux-6.10/include/linux/sched/prio.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/prio.h 2024-07-15 16:47:37.000000000 +0200
-@@ -18,6 +18,28 @@
- #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH)
- #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2)
-
-+#ifdef CONFIG_SCHED_ALT
-+
-+/* Undefine MAX_PRIO and DEFAULT_PRIO */
-+#undef MAX_PRIO
-+#undef DEFAULT_PRIO
-+
-+/* +/- priority levels from the base priority */
-+#ifdef CONFIG_SCHED_BMQ
-+#define MAX_PRIORITY_ADJ (12)
-+#endif
-+
-+#ifdef CONFIG_SCHED_PDS
-+#define MAX_PRIORITY_ADJ (0)
-+#endif
-+
-+#define MIN_NORMAL_PRIO (128)
-+#define NORMAL_PRIO_NUM (64)
-+#define MAX_PRIO (MIN_NORMAL_PRIO + NORMAL_PRIO_NUM)
-+#define DEFAULT_PRIO (MAX_PRIO - MAX_PRIORITY_ADJ - NICE_WIDTH / 2)
-+
-+#endif /* CONFIG_SCHED_ALT */
-+
- /*
- * Convert user-nice values [ -20 ... 0 ... 19 ]
- * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
-diff --new-file -rup linux-6.10/include/linux/sched/rt.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/rt.h
---- linux-6.10/include/linux/sched/rt.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/rt.h 2024-07-15 16:47:37.000000000 +0200
-@@ -24,8 +24,10 @@ static inline bool task_is_realtime(stru
-
- if (policy == SCHED_FIFO || policy == SCHED_RR)
- return true;
-+#ifndef CONFIG_SCHED_ALT
- if (policy == SCHED_DEADLINE)
- return true;
-+#endif
- return false;
- }
-
-diff --new-file -rup linux-6.10/include/linux/sched/topology.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/topology.h
---- linux-6.10/include/linux/sched/topology.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/topology.h 2024-07-15 16:47:37.000000000 +0200
-@@ -244,7 +244,8 @@ static inline bool cpus_share_resources(
-
- #endif /* !CONFIG_SMP */
-
--#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
-+#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) && \
-+ !defined(CONFIG_SCHED_ALT)
- extern void rebuild_sched_domains_energy(void);
- #else
- static inline void rebuild_sched_domains_energy(void)
-diff --new-file -rup linux-6.10/include/linux/sched.h linux-prjc-linux-6.10.y-prjc/include/linux/sched.h
---- linux-6.10/include/linux/sched.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/include/linux/sched.h 2024-07-15 16:47:37.000000000 +0200
-@@ -774,9 +774,16 @@ struct task_struct {
- struct alloc_tag *alloc_tag;
- #endif
-
--#ifdef CONFIG_SMP
-+#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_ALT)
- int on_cpu;
-+#endif
-+
-+#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_ALT)
- struct __call_single_node wake_entry;
-+#endif
-+
-+#ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- unsigned int wakee_flips;
- unsigned long wakee_flip_decay_ts;
- struct task_struct *last_wakee;
-@@ -790,6 +797,7 @@ struct task_struct {
- */
- int recent_used_cpu;
- int wake_cpu;
-+#endif /* !CONFIG_SCHED_ALT */
- #endif
- int on_rq;
-
-@@ -798,6 +806,19 @@ struct task_struct {
- int normal_prio;
- unsigned int rt_priority;
-
-+#ifdef CONFIG_SCHED_ALT
-+ u64 last_ran;
-+ s64 time_slice;
-+ struct list_head sq_node;
-+#ifdef CONFIG_SCHED_BMQ
-+ int boost_prio;
-+#endif /* CONFIG_SCHED_BMQ */
-+#ifdef CONFIG_SCHED_PDS
-+ u64 deadline;
-+#endif /* CONFIG_SCHED_PDS */
-+ /* sched_clock time spent running */
-+ u64 sched_time;
-+#else /* !CONFIG_SCHED_ALT */
- struct sched_entity se;
- struct sched_rt_entity rt;
- struct sched_dl_entity dl;
-@@ -809,6 +830,7 @@ struct task_struct {
- unsigned long core_cookie;
- unsigned int core_occupation;
- #endif
-+#endif /* !CONFIG_SCHED_ALT */
-
- #ifdef CONFIG_CGROUP_SCHED
- struct task_group *sched_task_group;
-@@ -1571,6 +1593,15 @@ struct task_struct {
- */
- };
-
-+#ifdef CONFIG_SCHED_ALT
-+#define tsk_seruntime(t) ((t)->sched_time)
-+/* replace the uncertian rt_timeout with 0UL */
-+#define tsk_rttimeout(t) (0UL)
-+#else /* CFS */
-+#define tsk_seruntime(t) ((t)->se.sum_exec_runtime)
-+#define tsk_rttimeout(t) ((t)->rt.timeout)
-+#endif /* !CONFIG_SCHED_ALT */
-+
- #define TASK_REPORT_IDLE (TASK_REPORT + 1)
- #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
-
-diff --new-file -rup linux-6.10/init/Kconfig linux-prjc-linux-6.10.y-prjc/init/Kconfig
---- linux-6.10/init/Kconfig 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/init/Kconfig 2024-07-15 16:47:37.000000000 +0200
-@@ -638,6 +638,7 @@ config TASK_IO_ACCOUNTING
-
- config PSI
- bool "Pressure stall information tracking"
-+ depends on !SCHED_ALT
- select KERNFS
- help
- Collect metrics that indicate how overcommitted the CPU, memory,
-@@ -803,6 +804,7 @@ menu "Scheduler features"
- config UCLAMP_TASK
- bool "Enable utilization clamping for RT/FAIR tasks"
- depends on CPU_FREQ_GOV_SCHEDUTIL
-+ depends on !SCHED_ALT
- help
- This feature enables the scheduler to track the clamped utilization
- of each CPU based on RUNNABLE tasks scheduled on that CPU.
-@@ -849,6 +851,35 @@ config UCLAMP_BUCKETS_COUNT
-
- If in doubt, use the default value.
-
-+menuconfig SCHED_ALT
-+ bool "Alternative CPU Schedulers"
-+ default y
-+ help
-+ This feature enable alternative CPU scheduler"
-+
-+if SCHED_ALT
-+
-+choice
-+ prompt "Alternative CPU Scheduler"
-+ default SCHED_BMQ
-+
-+config SCHED_BMQ
-+ bool "BMQ CPU scheduler"
-+ help
-+ The BitMap Queue CPU scheduler for excellent interactivity and
-+ responsiveness on the desktop and solid scalability on normal
-+ hardware and commodity servers.
-+
-+config SCHED_PDS
-+ bool "PDS CPU scheduler"
-+ help
-+ The Priority and Deadline based Skip list multiple queue CPU
-+ Scheduler.
-+
-+endchoice
-+
-+endif
-+
- endmenu
-
- #
-@@ -914,6 +945,7 @@ config NUMA_BALANCING
- depends on ARCH_SUPPORTS_NUMA_BALANCING
- depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
- depends on SMP && NUMA && MIGRATION && !PREEMPT_RT
-+ depends on !SCHED_ALT
- help
- This option adds support for automatic NUMA aware memory/task placement.
- The mechanism is quite primitive and is based on migrating memory when
-@@ -1015,6 +1047,7 @@ config FAIR_GROUP_SCHED
- depends on CGROUP_SCHED
- default CGROUP_SCHED
-
-+if !SCHED_ALT
- config CFS_BANDWIDTH
- bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
- depends on FAIR_GROUP_SCHED
-@@ -1037,6 +1070,7 @@ config RT_GROUP_SCHED
- realtime bandwidth for them.
- See Documentation/scheduler/sched-rt-group.rst for more information.
-
-+endif #!SCHED_ALT
- endif #CGROUP_SCHED
-
- config SCHED_MM_CID
-@@ -1285,6 +1319,7 @@ config CHECKPOINT_RESTORE
-
- config SCHED_AUTOGROUP
- bool "Automatic process group scheduling"
-+ depends on !SCHED_ALT
- select CGROUPS
- select CGROUP_SCHED
- select FAIR_GROUP_SCHED
-diff --new-file -rup linux-6.10/init/init_task.c linux-prjc-linux-6.10.y-prjc/init/init_task.c
---- linux-6.10/init/init_task.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/init/init_task.c 2024-07-15 16:47:37.000000000 +0200
-@@ -70,9 +70,15 @@ struct task_struct init_task __aligned(L
- .stack = init_stack,
- .usage = REFCOUNT_INIT(2),
- .flags = PF_KTHREAD,
-+#ifdef CONFIG_SCHED_ALT
-+ .prio = DEFAULT_PRIO,
-+ .static_prio = DEFAULT_PRIO,
-+ .normal_prio = DEFAULT_PRIO,
-+#else
- .prio = MAX_PRIO - 20,
- .static_prio = MAX_PRIO - 20,
- .normal_prio = MAX_PRIO - 20,
-+#endif
- .policy = SCHED_NORMAL,
- .cpus_ptr = &init_task.cpus_mask,
- .user_cpus_ptr = NULL,
-@@ -85,6 +91,16 @@ struct task_struct init_task __aligned(L
- .restart_block = {
- .fn = do_no_restart_syscall,
- },
-+#ifdef CONFIG_SCHED_ALT
-+ .sq_node = LIST_HEAD_INIT(init_task.sq_node),
-+#ifdef CONFIG_SCHED_BMQ
-+ .boost_prio = 0,
-+#endif
-+#ifdef CONFIG_SCHED_PDS
-+ .deadline = 0,
-+#endif
-+ .time_slice = HZ,
-+#else
- .se = {
- .group_node = LIST_HEAD_INIT(init_task.se.group_node),
- },
-@@ -92,6 +108,7 @@ struct task_struct init_task __aligned(L
- .run_list = LIST_HEAD_INIT(init_task.rt.run_list),
- .time_slice = RR_TIMESLICE,
- },
-+#endif
- .tasks = LIST_HEAD_INIT(init_task.tasks),
- #ifdef CONFIG_SMP
- .pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
-diff --new-file -rup linux-6.10/kernel/Kconfig.preempt linux-prjc-linux-6.10.y-prjc/kernel/Kconfig.preempt
---- linux-6.10/kernel/Kconfig.preempt 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/Kconfig.preempt 2024-07-15 16:47:37.000000000 +0200
-@@ -117,7 +117,7 @@ config PREEMPT_DYNAMIC
-
- config SCHED_CORE
- bool "Core Scheduling for SMT"
-- depends on SCHED_SMT
-+ depends on SCHED_SMT && !SCHED_ALT
- help
- This option permits Core Scheduling, a means of coordinated task
- selection across SMT siblings. When enabled -- see
-diff --new-file -rup linux-6.10/kernel/cgroup/cpuset.c linux-prjc-linux-6.10.y-prjc/kernel/cgroup/cpuset.c
---- linux-6.10/kernel/cgroup/cpuset.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/cgroup/cpuset.c 2024-07-15 16:47:37.000000000 +0200
-@@ -846,7 +846,7 @@ out:
- return ret;
- }
-
--#ifdef CONFIG_SMP
-+#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_ALT)
- /*
- * Helper routine for generate_sched_domains().
- * Do cpusets a, b have overlapping effective cpus_allowed masks?
-@@ -1245,7 +1245,7 @@ static void rebuild_sched_domains_locked
- /* Have scheduler rebuild the domains */
- partition_and_rebuild_sched_domains(ndoms, doms, attr);
- }
--#else /* !CONFIG_SMP */
-+#else /* !CONFIG_SMP || CONFIG_SCHED_ALT */
- static void rebuild_sched_domains_locked(void)
- {
- }
-@@ -3301,12 +3301,15 @@ static int cpuset_can_attach(struct cgro
- goto out_unlock;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- if (dl_task(task)) {
- cs->nr_migrate_dl_tasks++;
- cs->sum_migrate_dl_bw += task->dl.dl_bw;
- }
-+#endif
- }
-
-+#ifndef CONFIG_SCHED_ALT
- if (!cs->nr_migrate_dl_tasks)
- goto out_success;
-
-@@ -3327,6 +3330,7 @@ static int cpuset_can_attach(struct cgro
- }
-
- out_success:
-+#endif
- /*
- * Mark attach is in progress. This makes validate_change() fail
- * changes which zero cpus/mems_allowed.
-@@ -3350,12 +3354,14 @@ static void cpuset_cancel_attach(struct
- if (!cs->attach_in_progress)
- wake_up(&cpuset_attach_wq);
-
-+#ifndef CONFIG_SCHED_ALT
- if (cs->nr_migrate_dl_tasks) {
- int cpu = cpumask_any(cs->effective_cpus);
-
- dl_bw_free(cpu, cs->sum_migrate_dl_bw);
- reset_migrate_dl_data(cs);
- }
-+#endif
-
- mutex_unlock(&cpuset_mutex);
- }
-diff --new-file -rup linux-6.10/kernel/delayacct.c linux-prjc-linux-6.10.y-prjc/kernel/delayacct.c
---- linux-6.10/kernel/delayacct.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/delayacct.c 2024-07-15 16:47:37.000000000 +0200
-@@ -149,7 +149,7 @@ int delayacct_add_tsk(struct taskstats *
- */
- t1 = tsk->sched_info.pcount;
- t2 = tsk->sched_info.run_delay;
-- t3 = tsk->se.sum_exec_runtime;
-+ t3 = tsk_seruntime(tsk);
-
- d->cpu_count += t1;
-
-diff --new-file -rup linux-6.10/kernel/exit.c linux-prjc-linux-6.10.y-prjc/kernel/exit.c
---- linux-6.10/kernel/exit.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/exit.c 2024-07-15 16:47:37.000000000 +0200
-@@ -175,7 +175,7 @@ static void __exit_signal(struct task_st
- sig->curr_target = next_thread(tsk);
- }
-
-- add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
-+ add_device_randomness((const void*) &tsk_seruntime(tsk),
- sizeof(unsigned long long));
-
- /*
-@@ -196,7 +196,7 @@ static void __exit_signal(struct task_st
- sig->inblock += task_io_get_inblock(tsk);
- sig->oublock += task_io_get_oublock(tsk);
- task_io_accounting_add(&sig->ioac, &tsk->ioac);
-- sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
-+ sig->sum_sched_runtime += tsk_seruntime(tsk);
- sig->nr_threads--;
- __unhash_process(tsk, group_dead);
- write_sequnlock(&sig->stats_lock);
-diff --new-file -rup linux-6.10/kernel/locking/rtmutex.c linux-prjc-linux-6.10.y-prjc/kernel/locking/rtmutex.c
---- linux-6.10/kernel/locking/rtmutex.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/locking/rtmutex.c 2024-07-15 16:47:37.000000000 +0200
-@@ -363,7 +363,7 @@ waiter_update_prio(struct rt_mutex_waite
- lockdep_assert(RB_EMPTY_NODE(&waiter->tree.entry));
-
- waiter->tree.prio = __waiter_prio(task);
-- waiter->tree.deadline = task->dl.deadline;
-+ waiter->tree.deadline = __tsk_deadline(task);
- }
-
- /*
-@@ -384,16 +384,20 @@ waiter_clone_prio(struct rt_mutex_waiter
- * Only use with rt_waiter_node_{less,equal}()
- */
- #define task_to_waiter_node(p) \
-- &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
-+ &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = __tsk_deadline(p) }
- #define task_to_waiter(p) \
- &(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
-
- static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
- struct rt_waiter_node *right)
- {
-+#ifdef CONFIG_SCHED_PDS
-+ return (left->deadline < right->deadline);
-+#else
- if (left->prio < right->prio)
- return 1;
-
-+#ifndef CONFIG_SCHED_BMQ
- /*
- * If both waiters have dl_prio(), we check the deadlines of the
- * associated tasks.
-@@ -402,16 +406,22 @@ static __always_inline int rt_waiter_nod
- */
- if (dl_prio(left->prio))
- return dl_time_before(left->deadline, right->deadline);
-+#endif
-
- return 0;
-+#endif
- }
-
- static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
- struct rt_waiter_node *right)
- {
-+#ifdef CONFIG_SCHED_PDS
-+ return (left->deadline == right->deadline);
-+#else
- if (left->prio != right->prio)
- return 0;
-
-+#ifndef CONFIG_SCHED_BMQ
- /*
- * If both waiters have dl_prio(), we check the deadlines of the
- * associated tasks.
-@@ -420,8 +430,10 @@ static __always_inline int rt_waiter_nod
- */
- if (dl_prio(left->prio))
- return left->deadline == right->deadline;
-+#endif
-
- return 1;
-+#endif
- }
-
- static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
-diff --new-file -rup linux-6.10/kernel/sched/Makefile linux-prjc-linux-6.10.y-prjc/kernel/sched/Makefile
---- linux-6.10/kernel/sched/Makefile 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/Makefile 2024-07-15 16:47:37.000000000 +0200
-@@ -28,7 +28,12 @@ endif
- # These compilation units have roughly the same size and complexity - so their
- # build parallelizes well and finishes roughly at once:
- #
-+ifdef CONFIG_SCHED_ALT
-+obj-y += alt_core.o
-+obj-$(CONFIG_SCHED_DEBUG) += alt_debug.o
-+else
- obj-y += core.o
- obj-y += fair.o
-+endif
- obj-y += build_policy.o
- obj-y += build_utility.o
-diff --new-file -rup linux-6.10/kernel/sched/alt_core.c linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_core.c
---- linux-6.10/kernel/sched/alt_core.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_core.c 2024-07-15 16:47:37.000000000 +0200
-@@ -0,0 +1,8963 @@
-+/*
-+ * kernel/sched/alt_core.c
-+ *
-+ * Core alternative kernel scheduler code and related syscalls
-+ *
-+ * Copyright (C) 1991-2002 Linus Torvalds
-+ *
-+ * 2009-08-13 Brainfuck deadline scheduling policy by Con Kolivas deletes
-+ * a whole lot of those previous things.
-+ * 2017-09-06 Priority and Deadline based Skip list multiple queue kernel
-+ * scheduler by Alfred Chen.
-+ * 2019-02-20 BMQ(BitMap Queue) kernel scheduler by Alfred Chen.
-+ */
-+#include <linux/sched/clock.h>
-+#include <linux/sched/cputime.h>
-+#include <linux/sched/debug.h>
-+#include <linux/sched/hotplug.h>
-+#include <linux/sched/init.h>
-+#include <linux/sched/isolation.h>
-+#include <linux/sched/loadavg.h>
-+#include <linux/sched/mm.h>
-+#include <linux/sched/nohz.h>
-+#include <linux/sched/stat.h>
-+#include <linux/sched/wake_q.h>
-+
-+#include <linux/blkdev.h>
-+#include <linux/context_tracking.h>
-+#include <linux/cpuset.h>
-+#include <linux/delayacct.h>
-+#include <linux/init_task.h>
-+#include <linux/kcov.h>
-+#include <linux/kprobes.h>
-+#include <linux/nmi.h>
-+#include <linux/rseq.h>
-+#include <linux/scs.h>
-+
-+#include <uapi/linux/sched/types.h>
-+
-+#include <asm/irq_regs.h>
-+#include <asm/switch_to.h>
-+
-+#define CREATE_TRACE_POINTS
-+#include <trace/events/sched.h>
-+#include <trace/events/ipi.h>
-+#undef CREATE_TRACE_POINTS
-+
-+#include "sched.h"
-+#include "smp.h"
-+
-+#include "pelt.h"
-+
-+#include "../../io_uring/io-wq.h"
-+#include "../smpboot.h"
-+
-+EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu);
-+EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask);
-+
-+/*
-+ * Export tracepoints that act as a bare tracehook (ie: have no trace event
-+ * associated with them) to allow external modules to probe them.
-+ */
-+EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+#define sched_feat(x) (1)
-+/*
-+ * Print a warning if need_resched is set for the given duration (if
-+ * LATENCY_WARN is enabled).
-+ *
-+ * If sysctl_resched_latency_warn_once is set, only one warning will be shown
-+ * per boot.
-+ */
-+__read_mostly int sysctl_resched_latency_warn_ms = 100;
-+__read_mostly int sysctl_resched_latency_warn_once = 1;
-+#else
-+#define sched_feat(x) (0)
-+#endif /* CONFIG_SCHED_DEBUG */
-+
-+#define ALT_SCHED_VERSION "v6.10-r0"
-+
-+/*
-+ * Compile time debug macro
-+ * #define ALT_SCHED_DEBUG
-+ */
-+
-+/* rt_prio(prio) defined in include/linux/sched/rt.h */
-+#define rt_task(p) rt_prio((p)->prio)
-+#define rt_policy(policy) ((policy) == SCHED_FIFO || (policy) == SCHED_RR)
-+#define task_has_rt_policy(p) (rt_policy((p)->policy))
-+
-+#define STOP_PRIO (MAX_RT_PRIO - 1)
-+
-+/*
-+ * Time slice
-+ * (default: 4 msec, units: nanoseconds)
-+ */
-+unsigned int sysctl_sched_base_slice __read_mostly = (4 << 20);
-+
-+#ifdef CONFIG_SCHED_BMQ
-+#include "bmq.h"
-+#endif
-+#ifdef CONFIG_SCHED_PDS
-+#include "pds.h"
-+#endif
-+
-+struct affinity_context {
-+ const struct cpumask *new_mask;
-+ struct cpumask *user_mask;
-+ unsigned int flags;
-+};
-+
-+/* Reschedule if less than this many μs left */
-+#define RESCHED_NS (100 << 10)
-+
-+/**
-+ * sched_yield_type - Type of sched_yield() will be performed.
-+ * 0: No yield.
-+ * 1: Requeue task. (default)
-+ */
-+int sched_yield_type __read_mostly = 1;
-+
-+#ifdef CONFIG_SMP
-+static cpumask_t sched_rq_pending_mask ____cacheline_aligned_in_smp;
-+
-+DEFINE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
-+DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_llc_mask);
-+DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_topo_end_mask);
-+
-+#ifdef CONFIG_SCHED_SMT
-+DEFINE_STATIC_KEY_FALSE(sched_smt_present);
-+EXPORT_SYMBOL_GPL(sched_smt_present);
-+#endif
-+
-+/*
-+ * Keep a unique ID per domain (we use the first CPUs number in the cpumask of
-+ * the domain), this allows us to quickly tell if two cpus are in the same cache
-+ * domain, see cpus_share_cache().
-+ */
-+DEFINE_PER_CPU(int, sd_llc_id);
-+#endif /* CONFIG_SMP */
-+
-+static DEFINE_MUTEX(sched_hotcpu_mutex);
-+
-+DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-+
-+#ifndef prepare_arch_switch
-+# define prepare_arch_switch(next) do { } while (0)
-+#endif
-+#ifndef finish_arch_post_lock_switch
-+# define finish_arch_post_lock_switch() do { } while (0)
-+#endif
-+
-+static cpumask_t sched_preempt_mask[SCHED_QUEUE_BITS + 1] ____cacheline_aligned_in_smp;
-+
-+static cpumask_t *const sched_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS - 1];
-+#ifdef CONFIG_SCHED_SMT
-+static cpumask_t *const sched_sg_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS];
-+#endif
-+
-+/* task function */
-+static inline const struct cpumask *task_user_cpus(struct task_struct *p)
-+{
-+ if (!p->user_cpus_ptr)
-+ return cpu_possible_mask; /* &init_task.cpus_mask */
-+ return p->user_cpus_ptr;
-+}
-+
-+/* sched_queue related functions */
-+static inline void sched_queue_init(struct sched_queue *q)
-+{
-+ int i;
-+
-+ bitmap_zero(q->bitmap, SCHED_QUEUE_BITS);
-+ for(i = 0; i < SCHED_LEVELS; i++)
-+ INIT_LIST_HEAD(&q->heads[i]);
-+}
-+
-+/*
-+ * Init idle task and put into queue structure of rq
-+ * IMPORTANT: may be called multiple times for a single cpu
-+ */
-+static inline void sched_queue_init_idle(struct sched_queue *q,
-+ struct task_struct *idle)
-+{
-+ INIT_LIST_HEAD(&q->heads[IDLE_TASK_SCHED_PRIO]);
-+ list_add_tail(&idle->sq_node, &q->heads[IDLE_TASK_SCHED_PRIO]);
-+ idle->on_rq = TASK_ON_RQ_QUEUED;
-+}
-+
-+#define CLEAR_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
-+ if (low < pr && pr <= high) \
-+ cpumask_clear_cpu(cpu, sched_preempt_mask + pr);
-+
-+#define SET_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
-+ if (low < pr && pr <= high) \
-+ cpumask_set_cpu(cpu, sched_preempt_mask + pr);
-+
-+static atomic_t sched_prio_record = ATOMIC_INIT(0);
-+
-+/* water mark related functions */
-+static inline void update_sched_preempt_mask(struct rq *rq)
-+{
-+ int prio = find_first_bit(rq->queue.bitmap, SCHED_QUEUE_BITS);
-+ int last_prio = rq->prio;
-+ int cpu, pr;
-+
-+ if (prio == last_prio)
-+ return;
-+
-+ rq->prio = prio;
-+#ifdef CONFIG_SCHED_PDS
-+ rq->prio_idx = sched_prio2idx(rq->prio, rq);
-+#endif
-+ cpu = cpu_of(rq);
-+ pr = atomic_read(&sched_prio_record);
-+
-+ if (prio < last_prio) {
-+ if (IDLE_TASK_SCHED_PRIO == last_prio) {
-+#ifdef CONFIG_SCHED_SMT
-+ if (static_branch_likely(&sched_smt_present))
-+ cpumask_andnot(sched_sg_idle_mask,
-+ sched_sg_idle_mask, cpu_smt_mask(cpu));
-+#endif
-+ cpumask_clear_cpu(cpu, sched_idle_mask);
-+ last_prio -= 2;
-+ }
-+ CLEAR_CACHED_PREEMPT_MASK(pr, prio, last_prio, cpu);
-+
-+ return;
-+ }
-+ /* last_prio < prio */
-+ if (IDLE_TASK_SCHED_PRIO == prio) {
-+#ifdef CONFIG_SCHED_SMT
-+ if (static_branch_likely(&sched_smt_present) &&
-+ cpumask_intersects(cpu_smt_mask(cpu), sched_idle_mask))
-+ cpumask_or(sched_sg_idle_mask, sched_sg_idle_mask, cpu_smt_mask(cpu));
-+#endif
-+ cpumask_set_cpu(cpu, sched_idle_mask);
-+ prio -= 2;
-+ }
-+ SET_CACHED_PREEMPT_MASK(pr, last_prio, prio, cpu);
-+}
-+
-+/*
-+ * This routine assume that the idle task always in queue
-+ */
-+static inline struct task_struct *sched_rq_first_task(struct rq *rq)
-+{
-+ const struct list_head *head = &rq->queue.heads[sched_rq_prio_idx(rq)];
-+
-+ return list_first_entry(head, struct task_struct, sq_node);
-+}
-+
-+static inline struct task_struct * sched_rq_next_task(struct task_struct *p, struct rq *rq)
-+{
-+ struct list_head *next = p->sq_node.next;
-+
-+ if (&rq->queue.heads[0] <= next && next < &rq->queue.heads[SCHED_LEVELS]) {
-+ struct list_head *head;
-+ unsigned long idx = next - &rq->queue.heads[0];
-+
-+ idx = find_next_bit(rq->queue.bitmap, SCHED_QUEUE_BITS,
-+ sched_idx2prio(idx, rq) + 1);
-+ head = &rq->queue.heads[sched_prio2idx(idx, rq)];
-+
-+ return list_first_entry(head, struct task_struct, sq_node);
-+ }
-+
-+ return list_next_entry(p, sq_node);
-+}
-+
-+/*
-+ * Serialization rules:
-+ *
-+ * Lock order:
-+ *
-+ * p->pi_lock
-+ * rq->lock
-+ * hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
-+ *
-+ * rq1->lock
-+ * rq2->lock where: rq1 < rq2
-+ *
-+ * Regular state:
-+ *
-+ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
-+ * local CPU's rq->lock, it optionally removes the task from the runqueue and
-+ * always looks at the local rq data structures to find the most eligible task
-+ * to run next.
-+ *
-+ * Task enqueue is also under rq->lock, possibly taken from another CPU.
-+ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
-+ * the local CPU to avoid bouncing the runqueue state around [ see
-+ * ttwu_queue_wakelist() ]
-+ *
-+ * Task wakeup, specifically wakeups that involve migration, are horribly
-+ * complicated to avoid having to take two rq->locks.
-+ *
-+ * Special state:
-+ *
-+ * System-calls and anything external will use task_rq_lock() which acquires
-+ * both p->pi_lock and rq->lock. As a consequence the state they change is
-+ * stable while holding either lock:
-+ *
-+ * - sched_setaffinity()/
-+ * set_cpus_allowed_ptr(): p->cpus_ptr, p->nr_cpus_allowed
-+ * - set_user_nice(): p->se.load, p->*prio
-+ * - __sched_setscheduler(): p->sched_class, p->policy, p->*prio,
-+ * p->se.load, p->rt_priority,
-+ * p->dl.dl_{runtime, deadline, period, flags, bw, density}
-+ * - sched_setnuma(): p->numa_preferred_nid
-+ * - sched_move_task(): p->sched_task_group
-+ * - uclamp_update_active() p->uclamp*
-+ *
-+ * p->state <- TASK_*:
-+ *
-+ * is changed locklessly using set_current_state(), __set_current_state() or
-+ * set_special_state(), see their respective comments, or by
-+ * try_to_wake_up(). This latter uses p->pi_lock to serialize against
-+ * concurrent self.
-+ *
-+ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
-+ *
-+ * is set by activate_task() and cleared by deactivate_task(), under
-+ * rq->lock. Non-zero indicates the task is runnable, the special
-+ * ON_RQ_MIGRATING state is used for migration without holding both
-+ * rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
-+ *
-+ * p->on_cpu <- { 0, 1 }:
-+ *
-+ * is set by prepare_task() and cleared by finish_task() such that it will be
-+ * set before p is scheduled-in and cleared after p is scheduled-out, both
-+ * under rq->lock. Non-zero indicates the task is running on its CPU.
-+ *
-+ * [ The astute reader will observe that it is possible for two tasks on one
-+ * CPU to have ->on_cpu = 1 at the same time. ]
-+ *
-+ * task_cpu(p): is changed by set_task_cpu(), the rules are:
-+ *
-+ * - Don't call set_task_cpu() on a blocked task:
-+ *
-+ * We don't care what CPU we're not running on, this simplifies hotplug,
-+ * the CPU assignment of blocked tasks isn't required to be valid.
-+ *
-+ * - for try_to_wake_up(), called under p->pi_lock:
-+ *
-+ * This allows try_to_wake_up() to only take one rq->lock, see its comment.
-+ *
-+ * - for migration called under rq->lock:
-+ * [ see task_on_rq_migrating() in task_rq_lock() ]
-+ *
-+ * o move_queued_task()
-+ * o detach_task()
-+ *
-+ * - for migration called under double_rq_lock():
-+ *
-+ * o __migrate_swap_task()
-+ * o push_rt_task() / pull_rt_task()
-+ * o push_dl_task() / pull_dl_task()
-+ * o dl_task_offline_migration()
-+ *
-+ */
-+
-+/*
-+ * Context: p->pi_lock
-+ */
-+static inline struct rq *__task_access_lock(struct task_struct *p, raw_spinlock_t **plock)
-+{
-+ struct rq *rq;
-+ for (;;) {
-+ rq = task_rq(p);
-+ if (p->on_cpu || task_on_rq_queued(p)) {
-+ raw_spin_lock(&rq->lock);
-+ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
-+ *plock = &rq->lock;
-+ return rq;
-+ }
-+ raw_spin_unlock(&rq->lock);
-+ } else if (task_on_rq_migrating(p)) {
-+ do {
-+ cpu_relax();
-+ } while (unlikely(task_on_rq_migrating(p)));
-+ } else {
-+ *plock = NULL;
-+ return rq;
-+ }
-+ }
-+}
-+
-+static inline void __task_access_unlock(struct task_struct *p, raw_spinlock_t *lock)
-+{
-+ if (NULL != lock)
-+ raw_spin_unlock(lock);
-+}
-+
-+static inline struct rq *
-+task_access_lock_irqsave(struct task_struct *p, raw_spinlock_t **plock, unsigned long *flags)
-+{
-+ struct rq *rq;
-+ for (;;) {
-+ rq = task_rq(p);
-+ if (p->on_cpu || task_on_rq_queued(p)) {
-+ raw_spin_lock_irqsave(&rq->lock, *flags);
-+ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
-+ *plock = &rq->lock;
-+ return rq;
-+ }
-+ raw_spin_unlock_irqrestore(&rq->lock, *flags);
-+ } else if (task_on_rq_migrating(p)) {
-+ do {
-+ cpu_relax();
-+ } while (unlikely(task_on_rq_migrating(p)));
-+ } else {
-+ raw_spin_lock_irqsave(&p->pi_lock, *flags);
-+ if (likely(!p->on_cpu && !p->on_rq && rq == task_rq(p))) {
-+ *plock = &p->pi_lock;
-+ return rq;
-+ }
-+ raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
-+ }
-+ }
-+}
-+
-+static inline void
-+task_access_unlock_irqrestore(struct task_struct *p, raw_spinlock_t *lock, unsigned long *flags)
-+{
-+ raw_spin_unlock_irqrestore(lock, *flags);
-+}
-+
-+/*
-+ * __task_rq_lock - lock the rq @p resides on.
-+ */
-+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ struct rq *rq;
-+
-+ lockdep_assert_held(&p->pi_lock);
-+
-+ for (;;) {
-+ rq = task_rq(p);
-+ raw_spin_lock(&rq->lock);
-+ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
-+ return rq;
-+ raw_spin_unlock(&rq->lock);
-+
-+ while (unlikely(task_on_rq_migrating(p)))
-+ cpu_relax();
-+ }
-+}
-+
-+/*
-+ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
-+ */
-+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(p->pi_lock)
-+ __acquires(rq->lock)
-+{
-+ struct rq *rq;
-+
-+ for (;;) {
-+ raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
-+ rq = task_rq(p);
-+ raw_spin_lock(&rq->lock);
-+ /*
-+ * move_queued_task() task_rq_lock()
-+ *
-+ * ACQUIRE (rq->lock)
-+ * [S] ->on_rq = MIGRATING [L] rq = task_rq()
-+ * WMB (__set_task_cpu()) ACQUIRE (rq->lock);
-+ * [S] ->cpu = new_cpu [L] task_rq()
-+ * [L] ->on_rq
-+ * RELEASE (rq->lock)
-+ *
-+ * If we observe the old CPU in task_rq_lock(), the acquire of
-+ * the old rq->lock will fully serialize against the stores.
-+ *
-+ * If we observe the new CPU in task_rq_lock(), the address
-+ * dependency headed by '[L] rq = task_rq()' and the acquire
-+ * will pair with the WMB to ensure we then also see migrating.
-+ */
-+ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
-+ return rq;
-+ }
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
-+
-+ while (unlikely(task_on_rq_migrating(p)))
-+ cpu_relax();
-+ }
-+}
-+
-+static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ raw_spin_lock_irqsave(&rq->lock, rf->flags);
-+}
-+
-+static inline void rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
-+}
-+
-+DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
-+ rq_lock_irqsave(_T->lock, &_T->rf),
-+ rq_unlock_irqrestore(_T->lock, &_T->rf),
-+ struct rq_flags rf)
-+
-+void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
-+{
-+ raw_spinlock_t *lock;
-+
-+ /* Matches synchronize_rcu() in __sched_core_enable() */
-+ preempt_disable();
-+
-+ for (;;) {
-+ lock = __rq_lockp(rq);
-+ raw_spin_lock_nested(lock, subclass);
-+ if (likely(lock == __rq_lockp(rq))) {
-+ /* preempt_count *MUST* be > 1 */
-+ preempt_enable_no_resched();
-+ return;
-+ }
-+ raw_spin_unlock(lock);
-+ }
-+}
-+
-+void raw_spin_rq_unlock(struct rq *rq)
-+{
-+ raw_spin_unlock(rq_lockp(rq));
-+}
-+
-+/*
-+ * RQ-clock updating methods:
-+ */
-+
-+static void update_rq_clock_task(struct rq *rq, s64 delta)
-+{
-+/*
-+ * In theory, the compile should just see 0 here, and optimize out the call
-+ * to sched_rt_avg_update. But I don't trust it...
-+ */
-+ s64 __maybe_unused steal = 0, irq_delta = 0;
-+
-+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-+ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
-+
-+ /*
-+ * Since irq_time is only updated on {soft,}irq_exit, we might run into
-+ * this case when a previous update_rq_clock() happened inside a
-+ * {soft,}irq region.
-+ *
-+ * When this happens, we stop ->clock_task and only update the
-+ * prev_irq_time stamp to account for the part that fit, so that a next
-+ * update will consume the rest. This ensures ->clock_task is
-+ * monotonic.
-+ *
-+ * It does however cause some slight miss-attribution of {soft,}irq
-+ * time, a more accurate solution would be to update the irq_time using
-+ * the current rq->clock timestamp, except that would require using
-+ * atomic ops.
-+ */
-+ if (irq_delta > delta)
-+ irq_delta = delta;
-+
-+ rq->prev_irq_time += irq_delta;
-+ delta -= irq_delta;
-+ delayacct_irq(rq->curr, irq_delta);
-+#endif
-+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-+ if (static_key_false((¶virt_steal_rq_enabled))) {
-+ steal = paravirt_steal_clock(cpu_of(rq));
-+ steal -= rq->prev_steal_time_rq;
-+
-+ if (unlikely(steal > delta))
-+ steal = delta;
-+
-+ rq->prev_steal_time_rq += steal;
-+ delta -= steal;
-+ }
-+#endif
-+
-+ rq->clock_task += delta;
-+
-+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
-+ if ((irq_delta + steal))
-+ update_irq_load_avg(rq, irq_delta + steal);
-+#endif
-+}
-+
-+static inline void update_rq_clock(struct rq *rq)
-+{
-+ s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
-+
-+ if (unlikely(delta <= 0))
-+ return;
-+ rq->clock += delta;
-+ sched_update_rq_clock(rq);
-+ update_rq_clock_task(rq, delta);
-+}
-+
-+/*
-+ * RQ Load update routine
-+ */
-+#define RQ_LOAD_HISTORY_BITS (sizeof(s32) * 8ULL)
-+#define RQ_UTIL_SHIFT (8)
-+#define RQ_LOAD_HISTORY_TO_UTIL(l) (((l) >> (RQ_LOAD_HISTORY_BITS - 1 - RQ_UTIL_SHIFT)) & 0xff)
-+
-+#define LOAD_BLOCK(t) ((t) >> 17)
-+#define LOAD_HALF_BLOCK(t) ((t) >> 16)
-+#define BLOCK_MASK(t) ((t) & ((0x01 << 18) - 1))
-+#define LOAD_BLOCK_BIT(b) (1UL << (RQ_LOAD_HISTORY_BITS - 1 - (b)))
-+#define CURRENT_LOAD_BIT LOAD_BLOCK_BIT(0)
-+
-+static inline void rq_load_update(struct rq *rq)
-+{
-+ u64 time = rq->clock;
-+ u64 delta = min(LOAD_BLOCK(time) - LOAD_BLOCK(rq->load_stamp), RQ_LOAD_HISTORY_BITS - 1);
-+ u64 prev = !!(rq->load_history & CURRENT_LOAD_BIT);
-+ u64 curr = !!rq->nr_running;
-+
-+ if (delta) {
-+ rq->load_history = rq->load_history >> delta;
-+
-+ if (delta < RQ_UTIL_SHIFT) {
-+ rq->load_block += (~BLOCK_MASK(rq->load_stamp)) * prev;
-+ if (!!LOAD_HALF_BLOCK(rq->load_block) ^ curr)
-+ rq->load_history ^= LOAD_BLOCK_BIT(delta);
-+ }
-+
-+ rq->load_block = BLOCK_MASK(time) * prev;
-+ } else {
-+ rq->load_block += (time - rq->load_stamp) * prev;
-+ }
-+ if (prev ^ curr)
-+ rq->load_history ^= CURRENT_LOAD_BIT;
-+ rq->load_stamp = time;
-+}
-+
-+unsigned long rq_load_util(struct rq *rq, unsigned long max)
-+{
-+ return RQ_LOAD_HISTORY_TO_UTIL(rq->load_history) * (max >> RQ_UTIL_SHIFT);
-+}
-+
-+#ifdef CONFIG_SMP
-+unsigned long sched_cpu_util(int cpu)
-+{
-+ return rq_load_util(cpu_rq(cpu), arch_scale_cpu_capacity(cpu));
-+}
-+#endif /* CONFIG_SMP */
-+
-+#ifdef CONFIG_CPU_FREQ
-+/**
-+ * cpufreq_update_util - Take a note about CPU utilization changes.
-+ * @rq: Runqueue to carry out the update for.
-+ * @flags: Update reason flags.
-+ *
-+ * This function is called by the scheduler on the CPU whose utilization is
-+ * being updated.
-+ *
-+ * It can only be called from RCU-sched read-side critical sections.
-+ *
-+ * The way cpufreq is currently arranged requires it to evaluate the CPU
-+ * performance state (frequency/voltage) on a regular basis to prevent it from
-+ * being stuck in a completely inadequate performance level for too long.
-+ * That is not guaranteed to happen if the updates are only triggered from CFS
-+ * and DL, though, because they may not be coming in if only RT tasks are
-+ * active all the time (or there are RT tasks only).
-+ *
-+ * As a workaround for that issue, this function is called periodically by the
-+ * RT sched class to trigger extra cpufreq updates to prevent it from stalling,
-+ * but that really is a band-aid. Going forward it should be replaced with
-+ * solutions targeted more specifically at RT tasks.
-+ */
-+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
-+{
-+ struct update_util_data *data;
-+
-+#ifdef CONFIG_SMP
-+ rq_load_update(rq);
-+#endif
-+ data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, cpu_of(rq)));
-+ if (data)
-+ data->func(data, rq_clock(rq), flags);
-+}
-+#else
-+static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
-+{
-+#ifdef CONFIG_SMP
-+ rq_load_update(rq);
-+#endif
-+}
-+#endif /* CONFIG_CPU_FREQ */
-+
-+#ifdef CONFIG_NO_HZ_FULL
-+/*
-+ * Tick may be needed by tasks in the runqueue depending on their policy and
-+ * requirements. If tick is needed, lets send the target an IPI to kick it out
-+ * of nohz mode if necessary.
-+ */
-+static inline void sched_update_tick_dependency(struct rq *rq)
-+{
-+ int cpu = cpu_of(rq);
-+
-+ if (!tick_nohz_full_cpu(cpu))
-+ return;
-+
-+ if (rq->nr_running < 2)
-+ tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
-+ else
-+ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
-+}
-+#else /* !CONFIG_NO_HZ_FULL */
-+static inline void sched_update_tick_dependency(struct rq *rq) { }
-+#endif
-+
-+bool sched_task_on_rq(struct task_struct *p)
-+{
-+ return task_on_rq_queued(p);
-+}
-+
-+unsigned long get_wchan(struct task_struct *p)
-+{
-+ unsigned long ip = 0;
-+ unsigned int state;
-+
-+ if (!p || p == current)
-+ return 0;
-+
-+ /* Only get wchan if task is blocked and we can keep it that way. */
-+ raw_spin_lock_irq(&p->pi_lock);
-+ state = READ_ONCE(p->__state);
-+ smp_rmb(); /* see try_to_wake_up() */
-+ if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq)
-+ ip = __get_wchan(p);
-+ raw_spin_unlock_irq(&p->pi_lock);
-+
-+ return ip;
-+}
-+
-+/*
-+ * Add/Remove/Requeue task to/from the runqueue routines
-+ * Context: rq->lock
-+ */
-+#define __SCHED_DEQUEUE_TASK(p, rq, flags, func) \
-+ sched_info_dequeue(rq, p); \
-+ \
-+ __list_del_entry(&p->sq_node); \
-+ if (p->sq_node.prev == p->sq_node.next) { \
-+ clear_bit(sched_idx2prio(p->sq_node.next - &rq->queue.heads[0], rq), \
-+ rq->queue.bitmap); \
-+ func; \
-+ }
-+
-+#define __SCHED_ENQUEUE_TASK(p, rq, flags, func) \
-+ sched_info_enqueue(rq, p); \
-+ { \
-+ int idx, prio; \
-+ TASK_SCHED_PRIO_IDX(p, rq, idx, prio); \
-+ list_add_tail(&p->sq_node, &rq->queue.heads[idx]); \
-+ if (list_is_first(&p->sq_node, &rq->queue.heads[idx])) { \
-+ set_bit(prio, rq->queue.bitmap); \
-+ func; \
-+ } \
-+ }
-+
-+static inline void dequeue_task(struct task_struct *p, struct rq *rq, int flags)
-+{
-+#ifdef ALT_SCHED_DEBUG
-+ lockdep_assert_held(&rq->lock);
-+
-+ /*printk(KERN_INFO "sched: dequeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
-+ WARN_ONCE(task_rq(p) != rq, "sched: dequeue task reside on cpu%d from cpu%d\n",
-+ task_cpu(p), cpu_of(rq));
-+#endif
-+
-+ __SCHED_DEQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
-+ --rq->nr_running;
-+#ifdef CONFIG_SMP
-+ if (1 == rq->nr_running)
-+ cpumask_clear_cpu(cpu_of(rq), &sched_rq_pending_mask);
-+#endif
-+
-+ sched_update_tick_dependency(rq);
-+}
-+
-+static inline void enqueue_task(struct task_struct *p, struct rq *rq, int flags)
-+{
-+#ifdef ALT_SCHED_DEBUG
-+ lockdep_assert_held(&rq->lock);
-+
-+ /*printk(KERN_INFO "sched: enqueue(%d) %px %d\n", cpu_of(rq), p, p->prio);*/
-+ WARN_ONCE(task_rq(p) != rq, "sched: enqueue task reside on cpu%d to cpu%d\n",
-+ task_cpu(p), cpu_of(rq));
-+#endif
-+
-+ __SCHED_ENQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
-+ ++rq->nr_running;
-+#ifdef CONFIG_SMP
-+ if (2 == rq->nr_running)
-+ cpumask_set_cpu(cpu_of(rq), &sched_rq_pending_mask);
-+#endif
-+
-+ sched_update_tick_dependency(rq);
-+}
-+
-+static inline void requeue_task(struct task_struct *p, struct rq *rq)
-+{
-+ struct list_head *node = &p->sq_node;
-+ int deq_idx, idx, prio;
-+
-+ TASK_SCHED_PRIO_IDX(p, rq, idx, prio);
-+#ifdef ALT_SCHED_DEBUG
-+ lockdep_assert_held(&rq->lock);
-+ /*printk(KERN_INFO "sched: requeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
-+ WARN_ONCE(task_rq(p) != rq, "sched: cpu[%d] requeue task reside on cpu%d\n",
-+ cpu_of(rq), task_cpu(p));
-+#endif
-+ if (list_is_last(node, &rq->queue.heads[idx]))
-+ return;
-+
-+ __list_del_entry(node);
-+ if (node->prev == node->next && (deq_idx = node->next - &rq->queue.heads[0]) != idx)
-+ clear_bit(sched_idx2prio(deq_idx, rq), rq->queue.bitmap);
-+
-+ list_add_tail(node, &rq->queue.heads[idx]);
-+ if (list_is_first(node, &rq->queue.heads[idx]))
-+ set_bit(prio, rq->queue.bitmap);
-+ update_sched_preempt_mask(rq);
-+}
-+
-+/*
-+ * cmpxchg based fetch_or, macro so it works for different integer types
-+ */
-+#define fetch_or(ptr, mask) \
-+ ({ \
-+ typeof(ptr) _ptr = (ptr); \
-+ typeof(mask) _mask = (mask); \
-+ typeof(*_ptr) _val = *_ptr; \
-+ \
-+ do { \
-+ } while (!try_cmpxchg(_ptr, &_val, _val | _mask)); \
-+ _val; \
-+})
-+
-+#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
-+/*
-+ * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
-+ * this avoids any races wrt polling state changes and thereby avoids
-+ * spurious IPIs.
-+ */
-+static inline bool set_nr_and_not_polling(struct task_struct *p)
-+{
-+ struct thread_info *ti = task_thread_info(p);
-+ return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
-+}
-+
-+/*
-+ * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
-+ *
-+ * If this returns true, then the idle task promises to call
-+ * sched_ttwu_pending() and reschedule soon.
-+ */
-+static bool set_nr_if_polling(struct task_struct *p)
-+{
-+ struct thread_info *ti = task_thread_info(p);
-+ typeof(ti->flags) val = READ_ONCE(ti->flags);
-+
-+ do {
-+ if (!(val & _TIF_POLLING_NRFLAG))
-+ return false;
-+ if (val & _TIF_NEED_RESCHED)
-+ return true;
-+ } while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
-+
-+ return true;
-+}
-+
-+#else
-+static inline bool set_nr_and_not_polling(struct task_struct *p)
-+{
-+ set_tsk_need_resched(p);
-+ return true;
-+}
-+
-+#ifdef CONFIG_SMP
-+static inline bool set_nr_if_polling(struct task_struct *p)
-+{
-+ return false;
-+}
-+#endif
-+#endif
-+
-+static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
-+{
-+ struct wake_q_node *node = &task->wake_q;
-+
-+ /*
-+ * Atomically grab the task, if ->wake_q is !nil already it means
-+ * it's already queued (either by us or someone else) and will get the
-+ * wakeup due to that.
-+ *
-+ * In order to ensure that a pending wakeup will observe our pending
-+ * state, even in the failed case, an explicit smp_mb() must be used.
-+ */
-+ smp_mb__before_atomic();
-+ if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
-+ return false;
-+
-+ /*
-+ * The head is context local, there can be no concurrency.
-+ */
-+ *head->lastp = node;
-+ head->lastp = &node->next;
-+ return true;
-+}
-+
-+/**
-+ * wake_q_add() - queue a wakeup for 'later' waking.
-+ * @head: the wake_q_head to add @task to
-+ * @task: the task to queue for 'later' wakeup
-+ *
-+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
-+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
-+ * instantly.
-+ *
-+ * This function must be used as-if it were wake_up_process(); IOW the task
-+ * must be ready to be woken at this location.
-+ */
-+void wake_q_add(struct wake_q_head *head, struct task_struct *task)
-+{
-+ if (__wake_q_add(head, task))
-+ get_task_struct(task);
-+}
-+
-+/**
-+ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
-+ * @head: the wake_q_head to add @task to
-+ * @task: the task to queue for 'later' wakeup
-+ *
-+ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
-+ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
-+ * instantly.
-+ *
-+ * This function must be used as-if it were wake_up_process(); IOW the task
-+ * must be ready to be woken at this location.
-+ *
-+ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
-+ * that already hold reference to @task can call the 'safe' version and trust
-+ * wake_q to do the right thing depending whether or not the @task is already
-+ * queued for wakeup.
-+ */
-+void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
-+{
-+ if (!__wake_q_add(head, task))
-+ put_task_struct(task);
-+}
-+
-+void wake_up_q(struct wake_q_head *head)
-+{
-+ struct wake_q_node *node = head->first;
-+
-+ while (node != WAKE_Q_TAIL) {
-+ struct task_struct *task;
-+
-+ task = container_of(node, struct task_struct, wake_q);
-+ /* task can safely be re-inserted now: */
-+ node = node->next;
-+ task->wake_q.next = NULL;
-+
-+ /*
-+ * wake_up_process() executes a full barrier, which pairs with
-+ * the queueing in wake_q_add() so as not to miss wakeups.
-+ */
-+ wake_up_process(task);
-+ put_task_struct(task);
-+ }
-+}
-+
-+/*
-+ * resched_curr - mark rq's current task 'to be rescheduled now'.
-+ *
-+ * On UP this means the setting of the need_resched flag, on SMP it
-+ * might also involve a cross-CPU call to trigger the scheduler on
-+ * the target CPU.
-+ */
-+static inline void resched_curr(struct rq *rq)
-+{
-+ struct task_struct *curr = rq->curr;
-+ int cpu;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ if (test_tsk_need_resched(curr))
-+ return;
-+
-+ cpu = cpu_of(rq);
-+ if (cpu == smp_processor_id()) {
-+ set_tsk_need_resched(curr);
-+ set_preempt_need_resched();
-+ return;
-+ }
-+
-+ if (set_nr_and_not_polling(curr))
-+ smp_send_reschedule(cpu);
-+ else
-+ trace_sched_wake_idle_without_ipi(cpu);
-+}
-+
-+void resched_cpu(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ if (cpu_online(cpu) || cpu == smp_processor_id())
-+ resched_curr(cpu_rq(cpu));
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+}
-+
-+#ifdef CONFIG_SMP
-+#ifdef CONFIG_NO_HZ_COMMON
-+/*
-+ * This routine will record that the CPU is going idle with tick stopped.
-+ * This info will be used in performing idle load balancing in the future.
-+ */
-+void nohz_balance_enter_idle(int cpu) {}
-+
-+/*
-+ * In the semi idle case, use the nearest busy CPU for migrating timers
-+ * from an idle CPU. This is good for power-savings.
-+ *
-+ * We don't do similar optimization for completely idle system, as
-+ * selecting an idle CPU will add more delays to the timers than intended
-+ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
-+ */
-+int get_nohz_timer_target(void)
-+{
-+ int i, cpu = smp_processor_id(), default_cpu = -1;
-+ struct cpumask *mask;
-+ const struct cpumask *hk_mask;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
-+ if (!idle_cpu(cpu))
-+ return cpu;
-+ default_cpu = cpu;
-+ }
-+
-+ hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
-+
-+ for (mask = per_cpu(sched_cpu_topo_masks, cpu);
-+ mask < per_cpu(sched_cpu_topo_end_mask, cpu); mask++)
-+ for_each_cpu_and(i, mask, hk_mask)
-+ if (!idle_cpu(i))
-+ return i;
-+
-+ if (default_cpu == -1)
-+ default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
-+ cpu = default_cpu;
-+
-+ return cpu;
-+}
-+
-+/*
-+ * When add_timer_on() enqueues a timer into the timer wheel of an
-+ * idle CPU then this timer might expire before the next timer event
-+ * which is scheduled to wake up that CPU. In case of a completely
-+ * idle system the next event might even be infinite time into the
-+ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
-+ * leaves the inner idle loop so the newly added timer is taken into
-+ * account when the CPU goes back to idle and evaluates the timer
-+ * wheel for the next timer event.
-+ */
-+static inline void wake_up_idle_cpu(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ if (cpu == smp_processor_id())
-+ return;
-+
-+ /*
-+ * Set TIF_NEED_RESCHED and send an IPI if in the non-polling
-+ * part of the idle loop. This forces an exit from the idle loop
-+ * and a round trip to schedule(). Now this could be optimized
-+ * because a simple new idle loop iteration is enough to
-+ * re-evaluate the next tick. Provided some re-ordering of tick
-+ * nohz functions that would need to follow TIF_NR_POLLING
-+ * clearing:
-+ *
-+ * - On most archs, a simple fetch_or on ti::flags with a
-+ * "0" value would be enough to know if an IPI needs to be sent.
-+ *
-+ * - x86 needs to perform a last need_resched() check between
-+ * monitor and mwait which doesn't take timers into account.
-+ * There a dedicated TIF_TIMER flag would be required to
-+ * fetch_or here and be checked along with TIF_NEED_RESCHED
-+ * before mwait().
-+ *
-+ * However, remote timer enqueue is not such a frequent event
-+ * and testing of the above solutions didn't appear to report
-+ * much benefits.
-+ */
-+ if (set_nr_and_not_polling(rq->idle))
-+ smp_send_reschedule(cpu);
-+ else
-+ trace_sched_wake_idle_without_ipi(cpu);
-+}
-+
-+static inline bool wake_up_full_nohz_cpu(int cpu)
-+{
-+ /*
-+ * We just need the target to call irq_exit() and re-evaluate
-+ * the next tick. The nohz full kick at least implies that.
-+ * If needed we can still optimize that later with an
-+ * empty IRQ.
-+ */
-+ if (cpu_is_offline(cpu))
-+ return true; /* Don't try to wake offline CPUs. */
-+ if (tick_nohz_full_cpu(cpu)) {
-+ if (cpu != smp_processor_id() ||
-+ tick_nohz_tick_stopped())
-+ tick_nohz_full_kick_cpu(cpu);
-+ return true;
-+ }
-+
-+ return false;
-+}
-+
-+void wake_up_nohz_cpu(int cpu)
-+{
-+ if (!wake_up_full_nohz_cpu(cpu))
-+ wake_up_idle_cpu(cpu);
-+}
-+
-+static void nohz_csd_func(void *info)
-+{
-+ struct rq *rq = info;
-+ int cpu = cpu_of(rq);
-+ unsigned int flags;
-+
-+ /*
-+ * Release the rq::nohz_csd.
-+ */
-+ flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
-+ WARN_ON(!(flags & NOHZ_KICK_MASK));
-+
-+ rq->idle_balance = idle_cpu(cpu);
-+ if (rq->idle_balance && !need_resched()) {
-+ rq->nohz_idle_balance = flags;
-+ raise_softirq_irqoff(SCHED_SOFTIRQ);
-+ }
-+}
-+
-+#endif /* CONFIG_NO_HZ_COMMON */
-+#endif /* CONFIG_SMP */
-+
-+static inline void wakeup_preempt(struct rq *rq)
-+{
-+ if (sched_rq_first_task(rq) != rq->curr)
-+ resched_curr(rq);
-+}
-+
-+static __always_inline
-+int __task_state_match(struct task_struct *p, unsigned int state)
-+{
-+ if (READ_ONCE(p->__state) & state)
-+ return 1;
-+
-+ if (READ_ONCE(p->saved_state) & state)
-+ return -1;
-+
-+ return 0;
-+}
-+
-+static __always_inline
-+int task_state_match(struct task_struct *p, unsigned int state)
-+{
-+ /*
-+ * Serialize against current_save_and_set_rtlock_wait_state(),
-+ * current_restore_rtlock_saved_state(), and __refrigerator().
-+ */
-+ guard(raw_spinlock_irq)(&p->pi_lock);
-+
-+ return __task_state_match(p, state);
-+}
-+
-+/*
-+ * wait_task_inactive - wait for a thread to unschedule.
-+ *
-+ * Wait for the thread to block in any of the states set in @match_state.
-+ * If it changes, i.e. @p might have woken up, then return zero. When we
-+ * succeed in waiting for @p to be off its CPU, we return a positive number
-+ * (its total switch count). If a second call a short while later returns the
-+ * same number, the caller can be sure that @p has remained unscheduled the
-+ * whole time.
-+ *
-+ * The caller must ensure that the task *will* unschedule sometime soon,
-+ * else this function might spin for a *long* time. This function can't
-+ * be called with interrupts off, or it may introduce deadlock with
-+ * smp_call_function() if an IPI is sent by the same process we are
-+ * waiting to become inactive.
-+ */
-+unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
-+{
-+ unsigned long flags;
-+ int running, queued, match;
-+ unsigned long ncsw;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ for (;;) {
-+ rq = task_rq(p);
-+
-+ /*
-+ * If the task is actively running on another CPU
-+ * still, just relax and busy-wait without holding
-+ * any locks.
-+ *
-+ * NOTE! Since we don't hold any locks, it's not
-+ * even sure that "rq" stays as the right runqueue!
-+ * But we don't care, since this will return false
-+ * if the runqueue has changed and p is actually now
-+ * running somewhere else!
-+ */
-+ while (task_on_cpu(p)) {
-+ if (!task_state_match(p, match_state))
-+ return 0;
-+ cpu_relax();
-+ }
-+
-+ /*
-+ * Ok, time to look more closely! We need the rq
-+ * lock now, to be *sure*. If we're wrong, we'll
-+ * just go back and repeat.
-+ */
-+ task_access_lock_irqsave(p, &lock, &flags);
-+ trace_sched_wait_task(p);
-+ running = task_on_cpu(p);
-+ queued = p->on_rq;
-+ ncsw = 0;
-+ if ((match = __task_state_match(p, match_state))) {
-+ /*
-+ * When matching on p->saved_state, consider this task
-+ * still queued so it will wait.
-+ */
-+ if (match < 0)
-+ queued = 1;
-+ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
-+ }
-+ task_access_unlock_irqrestore(p, lock, &flags);
-+
-+ /*
-+ * If it changed from the expected state, bail out now.
-+ */
-+ if (unlikely(!ncsw))
-+ break;
-+
-+ /*
-+ * Was it really running after all now that we
-+ * checked with the proper locks actually held?
-+ *
-+ * Oops. Go back and try again..
-+ */
-+ if (unlikely(running)) {
-+ cpu_relax();
-+ continue;
-+ }
-+
-+ /*
-+ * It's not enough that it's not actively running,
-+ * it must be off the runqueue _entirely_, and not
-+ * preempted!
-+ *
-+ * So if it was still runnable (but just not actively
-+ * running right now), it's preempted, and we should
-+ * yield - it could be a while.
-+ */
-+ if (unlikely(queued)) {
-+ ktime_t to = NSEC_PER_SEC / HZ;
-+
-+ set_current_state(TASK_UNINTERRUPTIBLE);
-+ schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
-+ continue;
-+ }
-+
-+ /*
-+ * Ahh, all good. It wasn't running, and it wasn't
-+ * runnable, which means that it will never become
-+ * running in the future either. We're all done!
-+ */
-+ break;
-+ }
-+
-+ return ncsw;
-+}
-+
-+#ifdef CONFIG_SCHED_HRTICK
-+/*
-+ * Use HR-timers to deliver accurate preemption points.
-+ */
-+
-+static void hrtick_clear(struct rq *rq)
-+{
-+ if (hrtimer_active(&rq->hrtick_timer))
-+ hrtimer_cancel(&rq->hrtick_timer);
-+}
-+
-+/*
-+ * High-resolution timer tick.
-+ * Runs from hardirq context with interrupts disabled.
-+ */
-+static enum hrtimer_restart hrtick(struct hrtimer *timer)
-+{
-+ struct rq *rq = container_of(timer, struct rq, hrtick_timer);
-+
-+ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
-+
-+ raw_spin_lock(&rq->lock);
-+ resched_curr(rq);
-+ raw_spin_unlock(&rq->lock);
-+
-+ return HRTIMER_NORESTART;
-+}
-+
-+/*
-+ * Use hrtick when:
-+ * - enabled by features
-+ * - hrtimer is actually high res
-+ */
-+static inline int hrtick_enabled(struct rq *rq)
-+{
-+ /**
-+ * Alt schedule FW doesn't support sched_feat yet
-+ if (!sched_feat(HRTICK))
-+ return 0;
-+ */
-+ if (!cpu_active(cpu_of(rq)))
-+ return 0;
-+ return hrtimer_is_hres_active(&rq->hrtick_timer);
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+static void __hrtick_restart(struct rq *rq)
-+{
-+ struct hrtimer *timer = &rq->hrtick_timer;
-+ ktime_t time = rq->hrtick_time;
-+
-+ hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
-+}
-+
-+/*
-+ * called from hardirq (IPI) context
-+ */
-+static void __hrtick_start(void *arg)
-+{
-+ struct rq *rq = arg;
-+
-+ raw_spin_lock(&rq->lock);
-+ __hrtick_restart(rq);
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+/*
-+ * Called to set the hrtick timer state.
-+ *
-+ * called with rq->lock held and irqs disabled
-+ */
-+static inline void hrtick_start(struct rq *rq, u64 delay)
-+{
-+ struct hrtimer *timer = &rq->hrtick_timer;
-+ s64 delta;
-+
-+ /*
-+ * Don't schedule slices shorter than 10000ns, that just
-+ * doesn't make sense and can cause timer DoS.
-+ */
-+ delta = max_t(s64, delay, 10000LL);
-+
-+ rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
-+
-+ if (rq == this_rq())
-+ __hrtick_restart(rq);
-+ else
-+ smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
-+}
-+
-+#else
-+/*
-+ * Called to set the hrtick timer state.
-+ *
-+ * called with rq->lock held and irqs disabled
-+ */
-+static inline void hrtick_start(struct rq *rq, u64 delay)
-+{
-+ /*
-+ * Don't schedule slices shorter than 10000ns, that just
-+ * doesn't make sense. Rely on vruntime for fairness.
-+ */
-+ delay = max_t(u64, delay, 10000LL);
-+ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
-+ HRTIMER_MODE_REL_PINNED_HARD);
-+}
-+#endif /* CONFIG_SMP */
-+
-+static void hrtick_rq_init(struct rq *rq)
-+{
-+#ifdef CONFIG_SMP
-+ INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
-+#endif
-+
-+ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
-+ rq->hrtick_timer.function = hrtick;
-+}
-+#else /* CONFIG_SCHED_HRTICK */
-+static inline int hrtick_enabled(struct rq *rq)
-+{
-+ return 0;
-+}
-+
-+static inline void hrtick_clear(struct rq *rq)
-+{
-+}
-+
-+static inline void hrtick_rq_init(struct rq *rq)
-+{
-+}
-+#endif /* CONFIG_SCHED_HRTICK */
-+
-+static inline int __normal_prio(int policy, int rt_prio, int static_prio)
-+{
-+ return rt_policy(policy) ? (MAX_RT_PRIO - 1 - rt_prio) : static_prio;
-+}
-+
-+/*
-+ * Calculate the expected normal priority: i.e. priority
-+ * without taking RT-inheritance into account. Might be
-+ * boosted by interactivity modifiers. Changes upon fork,
-+ * setprio syscalls, and whenever the interactivity
-+ * estimator recalculates.
-+ */
-+static inline int normal_prio(struct task_struct *p)
-+{
-+ return __normal_prio(p->policy, p->rt_priority, p->static_prio);
-+}
-+
-+/*
-+ * Calculate the current priority, i.e. the priority
-+ * taken into account by the scheduler. This value might
-+ * be boosted by RT tasks as it will be RT if the task got
-+ * RT-boosted. If not then it returns p->normal_prio.
-+ */
-+static int effective_prio(struct task_struct *p)
-+{
-+ p->normal_prio = normal_prio(p);
-+ /*
-+ * If we are RT tasks or we were boosted to RT priority,
-+ * keep the priority unchanged. Otherwise, update priority
-+ * to the normal priority:
-+ */
-+ if (!rt_prio(p->prio))
-+ return p->normal_prio;
-+ return p->prio;
-+}
-+
-+/*
-+ * activate_task - move a task to the runqueue.
-+ *
-+ * Context: rq->lock
-+ */
-+static void activate_task(struct task_struct *p, struct rq *rq)
-+{
-+ enqueue_task(p, rq, ENQUEUE_WAKEUP);
-+
-+ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
-+ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
-+
-+ /*
-+ * If in_iowait is set, the code below may not trigger any cpufreq
-+ * utilization updates, so do it here explicitly with the IOWAIT flag
-+ * passed.
-+ */
-+ cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT * p->in_iowait);
-+}
-+
-+/*
-+ * deactivate_task - remove a task from the runqueue.
-+ *
-+ * Context: rq->lock
-+ */
-+static inline void deactivate_task(struct task_struct *p, struct rq *rq)
-+{
-+ WRITE_ONCE(p->on_rq, 0);
-+ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
-+
-+ dequeue_task(p, rq, DEQUEUE_SLEEP);
-+
-+ cpufreq_update_util(rq, 0);
-+}
-+
-+static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
-+{
-+#ifdef CONFIG_SMP
-+ /*
-+ * After ->cpu is set up to a new value, task_access_lock(p, ...) can be
-+ * successfully executed on another CPU. We must ensure that updates of
-+ * per-task data have been completed by this moment.
-+ */
-+ smp_wmb();
-+
-+ WRITE_ONCE(task_thread_info(p)->cpu, cpu);
-+#endif
-+}
-+
-+static inline bool is_migration_disabled(struct task_struct *p)
-+{
-+#ifdef CONFIG_SMP
-+ return p->migration_disabled;
-+#else
-+ return false;
-+#endif
-+}
-+
-+#define SCA_CHECK 0x01
-+#define SCA_USER 0x08
-+
-+#ifdef CONFIG_SMP
-+
-+void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
-+{
-+#ifdef CONFIG_SCHED_DEBUG
-+ unsigned int state = READ_ONCE(p->__state);
-+
-+ /*
-+ * We should never call set_task_cpu() on a blocked task,
-+ * ttwu() will sort out the placement.
-+ */
-+ WARN_ON_ONCE(state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq);
-+
-+#ifdef CONFIG_LOCKDEP
-+ /*
-+ * The caller should hold either p->pi_lock or rq->lock, when changing
-+ * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
-+ *
-+ * sched_move_task() holds both and thus holding either pins the cgroup,
-+ * see task_group().
-+ */
-+ WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
-+ lockdep_is_held(&task_rq(p)->lock)));
-+#endif
-+ /*
-+ * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
-+ */
-+ WARN_ON_ONCE(!cpu_online(new_cpu));
-+
-+ WARN_ON_ONCE(is_migration_disabled(p));
-+#endif
-+ trace_sched_migrate_task(p, new_cpu);
-+
-+ if (task_cpu(p) != new_cpu)
-+ {
-+ rseq_migrate(p);
-+ perf_event_task_migrate(p);
-+ }
-+
-+ __set_task_cpu(p, new_cpu);
-+}
-+
-+#define MDF_FORCE_ENABLED 0x80
-+
-+static void
-+__do_set_cpus_ptr(struct task_struct *p, const struct cpumask *new_mask)
-+{
-+ /*
-+ * This here violates the locking rules for affinity, since we're only
-+ * supposed to change these variables while holding both rq->lock and
-+ * p->pi_lock.
-+ *
-+ * HOWEVER, it magically works, because ttwu() is the only code that
-+ * accesses these variables under p->pi_lock and only does so after
-+ * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
-+ * before finish_task().
-+ *
-+ * XXX do further audits, this smells like something putrid.
-+ */
-+ SCHED_WARN_ON(!p->on_cpu);
-+ p->cpus_ptr = new_mask;
-+}
-+
-+void migrate_disable(void)
-+{
-+ struct task_struct *p = current;
-+ int cpu;
-+
-+ if (p->migration_disabled) {
-+ p->migration_disabled++;
-+ return;
-+ }
-+
-+ guard(preempt)();
-+ cpu = smp_processor_id();
-+ if (cpumask_test_cpu(cpu, &p->cpus_mask)) {
-+ cpu_rq(cpu)->nr_pinned++;
-+ p->migration_disabled = 1;
-+ p->migration_flags &= ~MDF_FORCE_ENABLED;
-+
-+ /*
-+ * Violates locking rules! see comment in __do_set_cpus_ptr().
-+ */
-+ if (p->cpus_ptr == &p->cpus_mask)
-+ __do_set_cpus_ptr(p, cpumask_of(cpu));
-+ }
-+}
-+EXPORT_SYMBOL_GPL(migrate_disable);
-+
-+void migrate_enable(void)
-+{
-+ struct task_struct *p = current;
-+
-+ if (0 == p->migration_disabled)
-+ return;
-+
-+ if (p->migration_disabled > 1) {
-+ p->migration_disabled--;
-+ return;
-+ }
-+
-+ if (WARN_ON_ONCE(!p->migration_disabled))
-+ return;
-+
-+ /*
-+ * Ensure stop_task runs either before or after this, and that
-+ * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
-+ */
-+ guard(preempt)();
-+ /*
-+ * Assumption: current should be running on allowed cpu
-+ */
-+ WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &p->cpus_mask));
-+ if (p->cpus_ptr != &p->cpus_mask)
-+ __do_set_cpus_ptr(p, &p->cpus_mask);
-+ /*
-+ * Mustn't clear migration_disabled() until cpus_ptr points back at the
-+ * regular cpus_mask, otherwise things that race (eg.
-+ * select_fallback_rq) get confused.
-+ */
-+ barrier();
-+ p->migration_disabled = 0;
-+ this_rq()->nr_pinned--;
-+}
-+EXPORT_SYMBOL_GPL(migrate_enable);
-+
-+static inline bool rq_has_pinned_tasks(struct rq *rq)
-+{
-+ return rq->nr_pinned;
-+}
-+
-+/*
-+ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
-+ * __set_cpus_allowed_ptr() and select_fallback_rq().
-+ */
-+static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
-+{
-+ /* When not in the task's cpumask, no point in looking further. */
-+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
-+ return false;
-+
-+ /* migrate_disabled() must be allowed to finish. */
-+ if (is_migration_disabled(p))
-+ return cpu_online(cpu);
-+
-+ /* Non kernel threads are not allowed during either online or offline. */
-+ if (!(p->flags & PF_KTHREAD))
-+ return cpu_active(cpu) && task_cpu_possible(cpu, p);
-+
-+ /* KTHREAD_IS_PER_CPU is always allowed. */
-+ if (kthread_is_per_cpu(p))
-+ return cpu_online(cpu);
-+
-+ /* Regular kernel threads don't get to stay during offline. */
-+ if (cpu_dying(cpu))
-+ return false;
-+
-+ /* But are allowed during online. */
-+ return cpu_online(cpu);
-+}
-+
-+/*
-+ * This is how migration works:
-+ *
-+ * 1) we invoke migration_cpu_stop() on the target CPU using
-+ * stop_one_cpu().
-+ * 2) stopper starts to run (implicitly forcing the migrated thread
-+ * off the CPU)
-+ * 3) it checks whether the migrated task is still in the wrong runqueue.
-+ * 4) if it's in the wrong runqueue then the migration thread removes
-+ * it and puts it into the right queue.
-+ * 5) stopper completes and stop_one_cpu() returns and the migration
-+ * is done.
-+ */
-+
-+/*
-+ * move_queued_task - move a queued task to new rq.
-+ *
-+ * Returns (locked) new rq. Old rq's lock is released.
-+ */
-+static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
-+{
-+ int src_cpu;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ src_cpu = cpu_of(rq);
-+ WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
-+ dequeue_task(p, rq, 0);
-+ set_task_cpu(p, new_cpu);
-+ raw_spin_unlock(&rq->lock);
-+
-+ rq = cpu_rq(new_cpu);
-+
-+ raw_spin_lock(&rq->lock);
-+ WARN_ON_ONCE(task_cpu(p) != new_cpu);
-+
-+ sched_mm_cid_migrate_to(rq, p, src_cpu);
-+
-+ sched_task_sanity_check(p, rq);
-+ enqueue_task(p, rq, 0);
-+ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
-+ wakeup_preempt(rq);
-+
-+ return rq;
-+}
-+
-+struct migration_arg {
-+ struct task_struct *task;
-+ int dest_cpu;
-+};
-+
-+/*
-+ * Move (not current) task off this CPU, onto the destination CPU. We're doing
-+ * this because either it can't run here any more (set_cpus_allowed()
-+ * away from this CPU, or CPU going down), or because we're
-+ * attempting to rebalance this task on exec (sched_exec).
-+ *
-+ * So we race with normal scheduler movements, but that's OK, as long
-+ * as the task is no longer on this CPU.
-+ */
-+static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
-+{
-+ /* Affinity changed (again). */
-+ if (!is_cpu_allowed(p, dest_cpu))
-+ return rq;
-+
-+ return move_queued_task(rq, p, dest_cpu);
-+}
-+
-+/*
-+ * migration_cpu_stop - this will be executed by a highprio stopper thread
-+ * and performs thread migration by bumping thread off CPU then
-+ * 'pushing' onto another runqueue.
-+ */
-+static int migration_cpu_stop(void *data)
-+{
-+ struct migration_arg *arg = data;
-+ struct task_struct *p = arg->task;
-+ struct rq *rq = this_rq();
-+ unsigned long flags;
-+
-+ /*
-+ * The original target CPU might have gone down and we might
-+ * be on another CPU but it doesn't matter.
-+ */
-+ local_irq_save(flags);
-+ /*
-+ * We need to explicitly wake pending tasks before running
-+ * __migrate_task() such that we will not miss enforcing cpus_ptr
-+ * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
-+ */
-+ flush_smp_call_function_queue();
-+
-+ raw_spin_lock(&p->pi_lock);
-+ raw_spin_lock(&rq->lock);
-+ /*
-+ * If task_rq(p) != rq, it cannot be migrated here, because we're
-+ * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
-+ * we're holding p->pi_lock.
-+ */
-+ if (task_rq(p) == rq && task_on_rq_queued(p)) {
-+ update_rq_clock(rq);
-+ rq = __migrate_task(rq, p, arg->dest_cpu);
-+ }
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+
-+ return 0;
-+}
-+
-+static inline void
-+set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx)
-+{
-+ cpumask_copy(&p->cpus_mask, ctx->new_mask);
-+ p->nr_cpus_allowed = cpumask_weight(ctx->new_mask);
-+
-+ /*
-+ * Swap in a new user_cpus_ptr if SCA_USER flag set
-+ */
-+ if (ctx->flags & SCA_USER)
-+ swap(p->user_cpus_ptr, ctx->user_mask);
-+}
-+
-+static void
-+__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
-+{
-+ lockdep_assert_held(&p->pi_lock);
-+ set_cpus_allowed_common(p, ctx);
-+}
-+
-+/*
-+ * Used for kthread_bind() and select_fallback_rq(), in both cases the user
-+ * affinity (if any) should be destroyed too.
-+ */
-+void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = new_mask,
-+ .user_mask = NULL,
-+ .flags = SCA_USER, /* clear the user requested mask */
-+ };
-+ union cpumask_rcuhead {
-+ cpumask_t cpumask;
-+ struct rcu_head rcu;
-+ };
-+
-+ __do_set_cpus_allowed(p, &ac);
-+
-+ /*
-+ * Because this is called with p->pi_lock held, it is not possible
-+ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
-+ * kfree_rcu().
-+ */
-+ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
-+}
-+
-+static cpumask_t *alloc_user_cpus_ptr(int node)
-+{
-+ /*
-+ * See do_set_cpus_allowed() above for the rcu_head usage.
-+ */
-+ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
-+
-+ return kmalloc_node(size, GFP_KERNEL, node);
-+}
-+
-+int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
-+ int node)
-+{
-+ cpumask_t *user_mask;
-+ unsigned long flags;
-+
-+ /*
-+ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
-+ * may differ by now due to racing.
-+ */
-+ dst->user_cpus_ptr = NULL;
-+
-+ /*
-+ * This check is racy and losing the race is a valid situation.
-+ * It is not worth the extra overhead of taking the pi_lock on
-+ * every fork/clone.
-+ */
-+ if (data_race(!src->user_cpus_ptr))
-+ return 0;
-+
-+ user_mask = alloc_user_cpus_ptr(node);
-+ if (!user_mask)
-+ return -ENOMEM;
-+
-+ /*
-+ * Use pi_lock to protect content of user_cpus_ptr
-+ *
-+ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
-+ * do_set_cpus_allowed().
-+ */
-+ raw_spin_lock_irqsave(&src->pi_lock, flags);
-+ if (src->user_cpus_ptr) {
-+ swap(dst->user_cpus_ptr, user_mask);
-+ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
-+ }
-+ raw_spin_unlock_irqrestore(&src->pi_lock, flags);
-+
-+ if (unlikely(user_mask))
-+ kfree(user_mask);
-+
-+ return 0;
-+}
-+
-+static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
-+{
-+ struct cpumask *user_mask = NULL;
-+
-+ swap(p->user_cpus_ptr, user_mask);
-+
-+ return user_mask;
-+}
-+
-+void release_user_cpus_ptr(struct task_struct *p)
-+{
-+ kfree(clear_user_cpus_ptr(p));
-+}
-+
-+#endif
-+
-+/**
-+ * task_curr - is this task currently executing on a CPU?
-+ * @p: the task in question.
-+ *
-+ * Return: 1 if the task is currently executing. 0 otherwise.
-+ */
-+inline int task_curr(const struct task_struct *p)
-+{
-+ return cpu_curr(task_cpu(p)) == p;
-+}
-+
-+#ifdef CONFIG_SMP
-+/***
-+ * kick_process - kick a running thread to enter/exit the kernel
-+ * @p: the to-be-kicked thread
-+ *
-+ * Cause a process which is running on another CPU to enter
-+ * kernel-mode, without any delay. (to get signals handled.)
-+ *
-+ * NOTE: this function doesn't have to take the runqueue lock,
-+ * because all it wants to ensure is that the remote task enters
-+ * the kernel. If the IPI races and the task has been migrated
-+ * to another CPU then no harm is done and the purpose has been
-+ * achieved as well.
-+ */
-+void kick_process(struct task_struct *p)
-+{
-+ guard(preempt)();
-+ int cpu = task_cpu(p);
-+
-+ if ((cpu != smp_processor_id()) && task_curr(p))
-+ smp_send_reschedule(cpu);
-+}
-+EXPORT_SYMBOL_GPL(kick_process);
-+
-+/*
-+ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
-+ *
-+ * A few notes on cpu_active vs cpu_online:
-+ *
-+ * - cpu_active must be a subset of cpu_online
-+ *
-+ * - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
-+ * see __set_cpus_allowed_ptr(). At this point the newly online
-+ * CPU isn't yet part of the sched domains, and balancing will not
-+ * see it.
-+ *
-+ * - on cpu-down we clear cpu_active() to mask the sched domains and
-+ * avoid the load balancer to place new tasks on the to be removed
-+ * CPU. Existing tasks will remain running there and will be taken
-+ * off.
-+ *
-+ * This means that fallback selection must not select !active CPUs.
-+ * And can assume that any active CPU must be online. Conversely
-+ * select_task_rq() below may allow selection of !active CPUs in order
-+ * to satisfy the above rules.
-+ */
-+static int select_fallback_rq(int cpu, struct task_struct *p)
-+{
-+ int nid = cpu_to_node(cpu);
-+ const struct cpumask *nodemask = NULL;
-+ enum { cpuset, possible, fail } state = cpuset;
-+ int dest_cpu;
-+
-+ /*
-+ * If the node that the CPU is on has been offlined, cpu_to_node()
-+ * will return -1. There is no CPU on the node, and we should
-+ * select the CPU on the other node.
-+ */
-+ if (nid != -1) {
-+ nodemask = cpumask_of_node(nid);
-+
-+ /* Look for allowed, online CPU in same node. */
-+ for_each_cpu(dest_cpu, nodemask) {
-+ if (is_cpu_allowed(p, dest_cpu))
-+ return dest_cpu;
-+ }
-+ }
-+
-+ for (;;) {
-+ /* Any allowed, online CPU? */
-+ for_each_cpu(dest_cpu, p->cpus_ptr) {
-+ if (!is_cpu_allowed(p, dest_cpu))
-+ continue;
-+ goto out;
-+ }
-+
-+ /* No more Mr. Nice Guy. */
-+ switch (state) {
-+ case cpuset:
-+ if (cpuset_cpus_allowed_fallback(p)) {
-+ state = possible;
-+ break;
-+ }
-+ fallthrough;
-+ case possible:
-+ /*
-+ * XXX When called from select_task_rq() we only
-+ * hold p->pi_lock and again violate locking order.
-+ *
-+ * More yuck to audit.
-+ */
-+ do_set_cpus_allowed(p, task_cpu_possible_mask(p));
-+ state = fail;
-+ break;
-+
-+ case fail:
-+ BUG();
-+ break;
-+ }
-+ }
-+
-+out:
-+ if (state != cpuset) {
-+ /*
-+ * Don't tell them about moving exiting tasks or
-+ * kernel threads (both mm NULL), since they never
-+ * leave kernel.
-+ */
-+ if (p->mm && printk_ratelimit()) {
-+ printk_deferred("process %d (%s) no longer affine to cpu%d\n",
-+ task_pid_nr(p), p->comm, cpu);
-+ }
-+ }
-+
-+ return dest_cpu;
-+}
-+
-+static inline void
-+sched_preempt_mask_flush(cpumask_t *mask, int prio, int ref)
-+{
-+ int cpu;
-+
-+ cpumask_copy(mask, sched_preempt_mask + ref);
-+ if (prio < ref) {
-+ for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) {
-+ if (prio < cpu_rq(cpu)->prio)
-+ cpumask_set_cpu(cpu, mask);
-+ }
-+ } else {
-+ for_each_cpu_andnot(cpu, mask, sched_idle_mask) {
-+ if (prio >= cpu_rq(cpu)->prio)
-+ cpumask_clear_cpu(cpu, mask);
-+ }
-+ }
-+}
-+
-+static inline int
-+preempt_mask_check(cpumask_t *preempt_mask, cpumask_t *allow_mask, int prio)
-+{
-+ cpumask_t *mask = sched_preempt_mask + prio;
-+ int pr = atomic_read(&sched_prio_record);
-+
-+ if (pr != prio && SCHED_QUEUE_BITS - 1 != prio) {
-+ sched_preempt_mask_flush(mask, prio, pr);
-+ atomic_set(&sched_prio_record, prio);
-+ }
-+
-+ return cpumask_and(preempt_mask, allow_mask, mask);
-+}
-+
-+static inline int select_task_rq(struct task_struct *p)
-+{
-+ cpumask_t allow_mask, mask;
-+
-+ if (unlikely(!cpumask_and(&allow_mask, p->cpus_ptr, cpu_active_mask)))
-+ return select_fallback_rq(task_cpu(p), p);
-+
-+ if (
-+#ifdef CONFIG_SCHED_SMT
-+ cpumask_and(&mask, &allow_mask, sched_sg_idle_mask) ||
-+#endif
-+ cpumask_and(&mask, &allow_mask, sched_idle_mask) ||
-+ preempt_mask_check(&mask, &allow_mask, task_sched_prio(p)))
-+ return best_mask_cpu(task_cpu(p), &mask);
-+
-+ return best_mask_cpu(task_cpu(p), &allow_mask);
-+}
-+
-+void sched_set_stop_task(int cpu, struct task_struct *stop)
-+{
-+ static struct lock_class_key stop_pi_lock;
-+ struct sched_param stop_param = { .sched_priority = STOP_PRIO };
-+ struct sched_param start_param = { .sched_priority = 0 };
-+ struct task_struct *old_stop = cpu_rq(cpu)->stop;
-+
-+ if (stop) {
-+ /*
-+ * Make it appear like a SCHED_FIFO task, its something
-+ * userspace knows about and won't get confused about.
-+ *
-+ * Also, it will make PI more or less work without too
-+ * much confusion -- but then, stop work should not
-+ * rely on PI working anyway.
-+ */
-+ sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param);
-+
-+ /*
-+ * The PI code calls rt_mutex_setprio() with ->pi_lock held to
-+ * adjust the effective priority of a task. As a result,
-+ * rt_mutex_setprio() can trigger (RT) balancing operations,
-+ * which can then trigger wakeups of the stop thread to push
-+ * around the current task.
-+ *
-+ * The stop task itself will never be part of the PI-chain, it
-+ * never blocks, therefore that ->pi_lock recursion is safe.
-+ * Tell lockdep about this by placing the stop->pi_lock in its
-+ * own class.
-+ */
-+ lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
-+ }
-+
-+ cpu_rq(cpu)->stop = stop;
-+
-+ if (old_stop) {
-+ /*
-+ * Reset it back to a normal scheduling policy so that
-+ * it can die in pieces.
-+ */
-+ sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param);
-+ }
-+}
-+
-+static int affine_move_task(struct rq *rq, struct task_struct *p, int dest_cpu,
-+ raw_spinlock_t *lock, unsigned long irq_flags)
-+ __releases(rq->lock)
-+ __releases(p->pi_lock)
-+{
-+ /* Can the task run on the task's current CPU? If so, we're done */
-+ if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
-+ if (p->migration_disabled) {
-+ if (likely(p->cpus_ptr != &p->cpus_mask))
-+ __do_set_cpus_ptr(p, &p->cpus_mask);
-+ p->migration_disabled = 0;
-+ p->migration_flags |= MDF_FORCE_ENABLED;
-+ /* When p is migrate_disabled, rq->lock should be held */
-+ rq->nr_pinned--;
-+ }
-+
-+ if (task_on_cpu(p) || READ_ONCE(p->__state) == TASK_WAKING) {
-+ struct migration_arg arg = { p, dest_cpu };
-+
-+ /* Need help from migration thread: drop lock and wait. */
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
-+ return 0;
-+ }
-+ if (task_on_rq_queued(p)) {
-+ /*
-+ * OK, since we're going to drop the lock immediately
-+ * afterwards anyway.
-+ */
-+ update_rq_clock(rq);
-+ rq = move_queued_task(rq, p, dest_cpu);
-+ lock = &rq->lock;
-+ }
-+ }
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+ return 0;
-+}
-+
-+static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
-+ struct affinity_context *ctx,
-+ struct rq *rq,
-+ raw_spinlock_t *lock,
-+ unsigned long irq_flags)
-+{
-+ const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
-+ const struct cpumask *cpu_valid_mask = cpu_active_mask;
-+ bool kthread = p->flags & PF_KTHREAD;
-+ int dest_cpu;
-+ int ret = 0;
-+
-+ if (kthread || is_migration_disabled(p)) {
-+ /*
-+ * Kernel threads are allowed on online && !active CPUs,
-+ * however, during cpu-hot-unplug, even these might get pushed
-+ * away if not KTHREAD_IS_PER_CPU.
-+ *
-+ * Specifically, migration_disabled() tasks must not fail the
-+ * cpumask_any_and_distribute() pick below, esp. so on
-+ * SCA_MIGRATE_ENABLE, otherwise we'll not call
-+ * set_cpus_allowed_common() and actually reset p->cpus_ptr.
-+ */
-+ cpu_valid_mask = cpu_online_mask;
-+ }
-+
-+ if (!kthread && !cpumask_subset(ctx->new_mask, cpu_allowed_mask)) {
-+ ret = -EINVAL;
-+ goto out;
-+ }
-+
-+ /*
-+ * Must re-check here, to close a race against __kthread_bind(),
-+ * sched_setaffinity() is not guaranteed to observe the flag.
-+ */
-+ if ((ctx->flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
-+ ret = -EINVAL;
-+ goto out;
-+ }
-+
-+ if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
-+ goto out;
-+
-+ dest_cpu = cpumask_any_and(cpu_valid_mask, ctx->new_mask);
-+ if (dest_cpu >= nr_cpu_ids) {
-+ ret = -EINVAL;
-+ goto out;
-+ }
-+
-+ __do_set_cpus_allowed(p, ctx);
-+
-+ return affine_move_task(rq, p, dest_cpu, lock, irq_flags);
-+
-+out:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+
-+ return ret;
-+}
-+
-+/*
-+ * Change a given task's CPU affinity. Migrate the thread to a
-+ * is removed from the allowed bitmask.
-+ *
-+ * NOTE: the caller must have a valid reference to the task, the
-+ * task must not exit() & deallocate itself prematurely. The
-+ * call is not atomic; no spinlocks may be held.
-+ */
-+static int __set_cpus_allowed_ptr(struct task_struct *p,
-+ struct affinity_context *ctx)
-+{
-+ unsigned long irq_flags;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
-+ rq = __task_access_lock(p, &lock);
-+ /*
-+ * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
-+ * flags are set.
-+ */
-+ if (p->user_cpus_ptr &&
-+ !(ctx->flags & SCA_USER) &&
-+ cpumask_and(rq->scratch_mask, ctx->new_mask, p->user_cpus_ptr))
-+ ctx->new_mask = rq->scratch_mask;
-+
-+
-+ return __set_cpus_allowed_ptr_locked(p, ctx, rq, lock, irq_flags);
-+}
-+
-+int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = new_mask,
-+ .flags = 0,
-+ };
-+
-+ return __set_cpus_allowed_ptr(p, &ac);
-+}
-+EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
-+
-+/*
-+ * Change a given task's CPU affinity to the intersection of its current
-+ * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
-+ * If user_cpus_ptr is defined, use it as the basis for restricting CPU
-+ * affinity or use cpu_online_mask instead.
-+ *
-+ * If the resulting mask is empty, leave the affinity unchanged and return
-+ * -EINVAL.
-+ */
-+static int restrict_cpus_allowed_ptr(struct task_struct *p,
-+ struct cpumask *new_mask,
-+ const struct cpumask *subset_mask)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = new_mask,
-+ .flags = 0,
-+ };
-+ unsigned long irq_flags;
-+ raw_spinlock_t *lock;
-+ struct rq *rq;
-+ int err;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
-+ rq = __task_access_lock(p, &lock);
-+
-+ if (!cpumask_and(new_mask, task_user_cpus(p), subset_mask)) {
-+ err = -EINVAL;
-+ goto err_unlock;
-+ }
-+
-+ return __set_cpus_allowed_ptr_locked(p, &ac, rq, lock, irq_flags);
-+
-+err_unlock:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
-+ return err;
-+}
-+
-+/*
-+ * Restrict the CPU affinity of task @p so that it is a subset of
-+ * task_cpu_possible_mask() and point @p->user_cpus_ptr to a copy of the
-+ * old affinity mask. If the resulting mask is empty, we warn and walk
-+ * up the cpuset hierarchy until we find a suitable mask.
-+ */
-+void force_compatible_cpus_allowed_ptr(struct task_struct *p)
-+{
-+ cpumask_var_t new_mask;
-+ const struct cpumask *override_mask = task_cpu_possible_mask(p);
-+
-+ alloc_cpumask_var(&new_mask, GFP_KERNEL);
-+
-+ /*
-+ * __migrate_task() can fail silently in the face of concurrent
-+ * offlining of the chosen destination CPU, so take the hotplug
-+ * lock to ensure that the migration succeeds.
-+ */
-+ cpus_read_lock();
-+ if (!cpumask_available(new_mask))
-+ goto out_set_mask;
-+
-+ if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
-+ goto out_free_mask;
-+
-+ /*
-+ * We failed to find a valid subset of the affinity mask for the
-+ * task, so override it based on its cpuset hierarchy.
-+ */
-+ cpuset_cpus_allowed(p, new_mask);
-+ override_mask = new_mask;
-+
-+out_set_mask:
-+ if (printk_ratelimit()) {
-+ printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
-+ task_pid_nr(p), p->comm,
-+ cpumask_pr_args(override_mask));
-+ }
-+
-+ WARN_ON(set_cpus_allowed_ptr(p, override_mask));
-+out_free_mask:
-+ cpus_read_unlock();
-+ free_cpumask_var(new_mask);
-+}
-+
-+static int
-+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
-+
-+/*
-+ * Restore the affinity of a task @p which was previously restricted by a
-+ * call to force_compatible_cpus_allowed_ptr().
-+ *
-+ * It is the caller's responsibility to serialise this with any calls to
-+ * force_compatible_cpus_allowed_ptr(@p).
-+ */
-+void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
-+{
-+ struct affinity_context ac = {
-+ .new_mask = task_user_cpus(p),
-+ .flags = 0,
-+ };
-+ int ret;
-+
-+ /*
-+ * Try to restore the old affinity mask with __sched_setaffinity().
-+ * Cpuset masking will be done there too.
-+ */
-+ ret = __sched_setaffinity(p, &ac);
-+ WARN_ON_ONCE(ret);
-+}
-+
-+#else /* CONFIG_SMP */
-+
-+static inline int select_task_rq(struct task_struct *p)
-+{
-+ return 0;
-+}
-+
-+static inline int
-+__set_cpus_allowed_ptr(struct task_struct *p,
-+ struct affinity_context *ctx)
-+{
-+ return set_cpus_allowed_ptr(p, ctx->new_mask);
-+}
-+
-+static inline bool rq_has_pinned_tasks(struct rq *rq)
-+{
-+ return false;
-+}
-+
-+static inline cpumask_t *alloc_user_cpus_ptr(int node)
-+{
-+ return NULL;
-+}
-+
-+#endif /* !CONFIG_SMP */
-+
-+static void
-+ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ struct rq *rq;
-+
-+ if (!schedstat_enabled())
-+ return;
-+
-+ rq = this_rq();
-+
-+#ifdef CONFIG_SMP
-+ if (cpu == rq->cpu) {
-+ __schedstat_inc(rq->ttwu_local);
-+ __schedstat_inc(p->stats.nr_wakeups_local);
-+ } else {
-+ /** Alt schedule FW ToDo:
-+ * How to do ttwu_wake_remote
-+ */
-+ }
-+#endif /* CONFIG_SMP */
-+
-+ __schedstat_inc(rq->ttwu_count);
-+ __schedstat_inc(p->stats.nr_wakeups);
-+}
-+
-+/*
-+ * Mark the task runnable.
-+ */
-+static inline void ttwu_do_wakeup(struct task_struct *p)
-+{
-+ WRITE_ONCE(p->__state, TASK_RUNNING);
-+ trace_sched_wakeup(p);
-+}
-+
-+static inline void
-+ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
-+{
-+ if (p->sched_contributes_to_load)
-+ rq->nr_uninterruptible--;
-+
-+ if (
-+#ifdef CONFIG_SMP
-+ !(wake_flags & WF_MIGRATED) &&
-+#endif
-+ p->in_iowait) {
-+ delayacct_blkio_end(p);
-+ atomic_dec(&task_rq(p)->nr_iowait);
-+ }
-+
-+ activate_task(p, rq);
-+ wakeup_preempt(rq);
-+
-+ ttwu_do_wakeup(p);
-+}
-+
-+/*
-+ * Consider @p being inside a wait loop:
-+ *
-+ * for (;;) {
-+ * set_current_state(TASK_UNINTERRUPTIBLE);
-+ *
-+ * if (CONDITION)
-+ * break;
-+ *
-+ * schedule();
-+ * }
-+ * __set_current_state(TASK_RUNNING);
-+ *
-+ * between set_current_state() and schedule(). In this case @p is still
-+ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
-+ * an atomic manner.
-+ *
-+ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
-+ * then schedule() must still happen and p->state can be changed to
-+ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
-+ * need to do a full wakeup with enqueue.
-+ *
-+ * Returns: %true when the wakeup is done,
-+ * %false otherwise.
-+ */
-+static int ttwu_runnable(struct task_struct *p, int wake_flags)
-+{
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+ int ret = 0;
-+
-+ rq = __task_access_lock(p, &lock);
-+ if (task_on_rq_queued(p)) {
-+ if (!task_on_cpu(p)) {
-+ /*
-+ * When on_rq && !on_cpu the task is preempted, see if
-+ * it should preempt the task that is current now.
-+ */
-+ update_rq_clock(rq);
-+ wakeup_preempt(rq);
-+ }
-+ ttwu_do_wakeup(p);
-+ ret = 1;
-+ }
-+ __task_access_unlock(p, lock);
-+
-+ return ret;
-+}
-+
-+#ifdef CONFIG_SMP
-+void sched_ttwu_pending(void *arg)
-+{
-+ struct llist_node *llist = arg;
-+ struct rq *rq = this_rq();
-+ struct task_struct *p, *t;
-+ struct rq_flags rf;
-+
-+ if (!llist)
-+ return;
-+
-+ rq_lock_irqsave(rq, &rf);
-+ update_rq_clock(rq);
-+
-+ llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
-+ if (WARN_ON_ONCE(p->on_cpu))
-+ smp_cond_load_acquire(&p->on_cpu, !VAL);
-+
-+ if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
-+ set_task_cpu(p, cpu_of(rq));
-+
-+ ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0);
-+ }
-+
-+ /*
-+ * Must be after enqueueing at least once task such that
-+ * idle_cpu() does not observe a false-negative -- if it does,
-+ * it is possible for select_idle_siblings() to stack a number
-+ * of tasks on this CPU during that window.
-+ *
-+ * It is ok to clear ttwu_pending when another task pending.
-+ * We will receive IPI after local irq enabled and then enqueue it.
-+ * Since now nr_running > 0, idle_cpu() will always get correct result.
-+ */
-+ WRITE_ONCE(rq->ttwu_pending, 0);
-+ rq_unlock_irqrestore(rq, &rf);
-+}
-+
-+/*
-+ * Prepare the scene for sending an IPI for a remote smp_call
-+ *
-+ * Returns true if the caller can proceed with sending the IPI.
-+ * Returns false otherwise.
-+ */
-+bool call_function_single_prep_ipi(int cpu)
-+{
-+ if (set_nr_if_polling(cpu_rq(cpu)->idle)) {
-+ trace_sched_wake_idle_without_ipi(cpu);
-+ return false;
-+ }
-+
-+ return true;
-+}
-+
-+/*
-+ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
-+ * necessary. The wakee CPU on receipt of the IPI will queue the task
-+ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
-+ * of the wakeup instead of the waker.
-+ */
-+static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
-+
-+ WRITE_ONCE(rq->ttwu_pending, 1);
-+ __smp_call_single_queue(cpu, &p->wake_entry.llist);
-+}
-+
-+static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
-+{
-+ /*
-+ * Do not complicate things with the async wake_list while the CPU is
-+ * in hotplug state.
-+ */
-+ if (!cpu_active(cpu))
-+ return false;
-+
-+ /* Ensure the task will still be allowed to run on the CPU. */
-+ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
-+ return false;
-+
-+ /*
-+ * If the CPU does not share cache, then queue the task on the
-+ * remote rqs wakelist to avoid accessing remote data.
-+ */
-+ if (!cpus_share_cache(smp_processor_id(), cpu))
-+ return true;
-+
-+ if (cpu == smp_processor_id())
-+ return false;
-+
-+ /*
-+ * If the wakee cpu is idle, or the task is descheduling and the
-+ * only running task on the CPU, then use the wakelist to offload
-+ * the task activation to the idle (or soon-to-be-idle) CPU as
-+ * the current CPU is likely busy. nr_running is checked to
-+ * avoid unnecessary task stacking.
-+ *
-+ * Note that we can only get here with (wakee) p->on_rq=0,
-+ * p->on_cpu can be whatever, we've done the dequeue, so
-+ * the wakee has been accounted out of ->nr_running.
-+ */
-+ if (!cpu_rq(cpu)->nr_running)
-+ return true;
-+
-+ return false;
-+}
-+
-+static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ if (__is_defined(ALT_SCHED_TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
-+ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
-+ __ttwu_queue_wakelist(p, cpu, wake_flags);
-+ return true;
-+ }
-+
-+ return false;
-+}
-+
-+void wake_up_if_idle(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ guard(rcu)();
-+ if (is_idle_task(rcu_dereference(rq->curr))) {
-+ guard(raw_spinlock_irqsave)(&rq->lock);
-+ if (is_idle_task(rq->curr))
-+ resched_curr(rq);
-+ }
-+}
-+
-+extern struct static_key_false sched_asym_cpucapacity;
-+
-+static __always_inline bool sched_asym_cpucap_active(void)
-+{
-+ return static_branch_unlikely(&sched_asym_cpucapacity);
-+}
-+
-+bool cpus_equal_capacity(int this_cpu, int that_cpu)
-+{
-+ if (!sched_asym_cpucap_active())
-+ return true;
-+
-+ if (this_cpu == that_cpu)
-+ return true;
-+
-+ return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu);
-+}
-+
-+bool cpus_share_cache(int this_cpu, int that_cpu)
-+{
-+ if (this_cpu == that_cpu)
-+ return true;
-+
-+ return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
-+}
-+#else /* !CONFIG_SMP */
-+
-+static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ return false;
-+}
-+
-+#endif /* CONFIG_SMP */
-+
-+static inline void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ if (ttwu_queue_wakelist(p, cpu, wake_flags))
-+ return;
-+
-+ raw_spin_lock(&rq->lock);
-+ update_rq_clock(rq);
-+ ttwu_do_activate(rq, p, wake_flags);
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+/*
-+ * Invoked from try_to_wake_up() to check whether the task can be woken up.
-+ *
-+ * The caller holds p::pi_lock if p != current or has preemption
-+ * disabled when p == current.
-+ *
-+ * The rules of saved_state:
-+ *
-+ * The related locking code always holds p::pi_lock when updating
-+ * p::saved_state, which means the code is fully serialized in both cases.
-+ *
-+ * For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
-+ * No other bits set. This allows to distinguish all wakeup scenarios.
-+ *
-+ * For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
-+ * allows us to prevent early wakeup of tasks before they can be run on
-+ * asymmetric ISA architectures (eg ARMv9).
-+ */
-+static __always_inline
-+bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
-+{
-+ int match;
-+
-+ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
-+ WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
-+ state != TASK_RTLOCK_WAIT);
-+ }
-+
-+ *success = !!(match = __task_state_match(p, state));
-+
-+ /*
-+ * Saved state preserves the task state across blocking on
-+ * an RT lock or TASK_FREEZABLE tasks. If the state matches,
-+ * set p::saved_state to TASK_RUNNING, but do not wake the task
-+ * because it waits for a lock wakeup or __thaw_task(). Also
-+ * indicate success because from the regular waker's point of
-+ * view this has succeeded.
-+ *
-+ * After acquiring the lock the task will restore p::__state
-+ * from p::saved_state which ensures that the regular
-+ * wakeup is not lost. The restore will also set
-+ * p::saved_state to TASK_RUNNING so any further tests will
-+ * not result in false positives vs. @success
-+ */
-+ if (match < 0)
-+ p->saved_state = TASK_RUNNING;
-+
-+ return match > 0;
-+}
-+
-+/*
-+ * Notes on Program-Order guarantees on SMP systems.
-+ *
-+ * MIGRATION
-+ *
-+ * The basic program-order guarantee on SMP systems is that when a task [t]
-+ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
-+ * execution on its new CPU [c1].
-+ *
-+ * For migration (of runnable tasks) this is provided by the following means:
-+ *
-+ * A) UNLOCK of the rq(c0)->lock scheduling out task t
-+ * B) migration for t is required to synchronize *both* rq(c0)->lock and
-+ * rq(c1)->lock (if not at the same time, then in that order).
-+ * C) LOCK of the rq(c1)->lock scheduling in task
-+ *
-+ * Transitivity guarantees that B happens after A and C after B.
-+ * Note: we only require RCpc transitivity.
-+ * Note: the CPU doing B need not be c0 or c1
-+ *
-+ * Example:
-+ *
-+ * CPU0 CPU1 CPU2
-+ *
-+ * LOCK rq(0)->lock
-+ * sched-out X
-+ * sched-in Y
-+ * UNLOCK rq(0)->lock
-+ *
-+ * LOCK rq(0)->lock // orders against CPU0
-+ * dequeue X
-+ * UNLOCK rq(0)->lock
-+ *
-+ * LOCK rq(1)->lock
-+ * enqueue X
-+ * UNLOCK rq(1)->lock
-+ *
-+ * LOCK rq(1)->lock // orders against CPU2
-+ * sched-out Z
-+ * sched-in X
-+ * UNLOCK rq(1)->lock
-+ *
-+ *
-+ * BLOCKING -- aka. SLEEP + WAKEUP
-+ *
-+ * For blocking we (obviously) need to provide the same guarantee as for
-+ * migration. However the means are completely different as there is no lock
-+ * chain to provide order. Instead we do:
-+ *
-+ * 1) smp_store_release(X->on_cpu, 0) -- finish_task()
-+ * 2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
-+ *
-+ * Example:
-+ *
-+ * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule)
-+ *
-+ * LOCK rq(0)->lock LOCK X->pi_lock
-+ * dequeue X
-+ * sched-out X
-+ * smp_store_release(X->on_cpu, 0);
-+ *
-+ * smp_cond_load_acquire(&X->on_cpu, !VAL);
-+ * X->state = WAKING
-+ * set_task_cpu(X,2)
-+ *
-+ * LOCK rq(2)->lock
-+ * enqueue X
-+ * X->state = RUNNING
-+ * UNLOCK rq(2)->lock
-+ *
-+ * LOCK rq(2)->lock // orders against CPU1
-+ * sched-out Z
-+ * sched-in X
-+ * UNLOCK rq(2)->lock
-+ *
-+ * UNLOCK X->pi_lock
-+ * UNLOCK rq(0)->lock
-+ *
-+ *
-+ * However; for wakeups there is a second guarantee we must provide, namely we
-+ * must observe the state that lead to our wakeup. That is, not only must our
-+ * task observe its own prior state, it must also observe the stores prior to
-+ * its wakeup.
-+ *
-+ * This means that any means of doing remote wakeups must order the CPU doing
-+ * the wakeup against the CPU the task is going to end up running on. This,
-+ * however, is already required for the regular Program-Order guarantee above,
-+ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
-+ *
-+ */
-+
-+/**
-+ * try_to_wake_up - wake up a thread
-+ * @p: the thread to be awakened
-+ * @state: the mask of task states that can be woken
-+ * @wake_flags: wake modifier flags (WF_*)
-+ *
-+ * Conceptually does:
-+ *
-+ * If (@state & @p->state) @p->state = TASK_RUNNING.
-+ *
-+ * If the task was not queued/runnable, also place it back on a runqueue.
-+ *
-+ * This function is atomic against schedule() which would dequeue the task.
-+ *
-+ * It issues a full memory barrier before accessing @p->state, see the comment
-+ * with set_current_state().
-+ *
-+ * Uses p->pi_lock to serialize against concurrent wake-ups.
-+ *
-+ * Relies on p->pi_lock stabilizing:
-+ * - p->sched_class
-+ * - p->cpus_ptr
-+ * - p->sched_task_group
-+ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
-+ *
-+ * Tries really hard to only take one task_rq(p)->lock for performance.
-+ * Takes rq->lock in:
-+ * - ttwu_runnable() -- old rq, unavoidable, see comment there;
-+ * - ttwu_queue() -- new rq, for enqueue of the task;
-+ * - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
-+ *
-+ * As a consequence we race really badly with just about everything. See the
-+ * many memory barriers and their comments for details.
-+ *
-+ * Return: %true if @p->state changes (an actual wakeup was done),
-+ * %false otherwise.
-+ */
-+int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
-+{
-+ guard(preempt)();
-+ int cpu, success = 0;
-+
-+ if (p == current) {
-+ /*
-+ * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
-+ * == smp_processor_id()'. Together this means we can special
-+ * case the whole 'p->on_rq && ttwu_runnable()' case below
-+ * without taking any locks.
-+ *
-+ * In particular:
-+ * - we rely on Program-Order guarantees for all the ordering,
-+ * - we're serialized against set_special_state() by virtue of
-+ * it disabling IRQs (this allows not taking ->pi_lock).
-+ */
-+ if (!ttwu_state_match(p, state, &success))
-+ goto out;
-+
-+ trace_sched_waking(p);
-+ ttwu_do_wakeup(p);
-+ goto out;
-+ }
-+
-+ /*
-+ * If we are going to wake up a thread waiting for CONDITION we
-+ * need to ensure that CONDITION=1 done by the caller can not be
-+ * reordered with p->state check below. This pairs with smp_store_mb()
-+ * in set_current_state() that the waiting thread does.
-+ */
-+ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
-+ smp_mb__after_spinlock();
-+ if (!ttwu_state_match(p, state, &success))
-+ break;
-+
-+ trace_sched_waking(p);
-+
-+ /*
-+ * Ensure we load p->on_rq _after_ p->state, otherwise it would
-+ * be possible to, falsely, observe p->on_rq == 0 and get stuck
-+ * in smp_cond_load_acquire() below.
-+ *
-+ * sched_ttwu_pending() try_to_wake_up()
-+ * STORE p->on_rq = 1 LOAD p->state
-+ * UNLOCK rq->lock
-+ *
-+ * __schedule() (switch to task 'p')
-+ * LOCK rq->lock smp_rmb();
-+ * smp_mb__after_spinlock();
-+ * UNLOCK rq->lock
-+ *
-+ * [task p]
-+ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
-+ *
-+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
-+ * __schedule(). See the comment for smp_mb__after_spinlock().
-+ *
-+ * A similar smp_rmb() lives in __task_needs_rq_lock().
-+ */
-+ smp_rmb();
-+ if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
-+ break;
-+
-+#ifdef CONFIG_SMP
-+ /*
-+ * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
-+ * possible to, falsely, observe p->on_cpu == 0.
-+ *
-+ * One must be running (->on_cpu == 1) in order to remove oneself
-+ * from the runqueue.
-+ *
-+ * __schedule() (switch to task 'p') try_to_wake_up()
-+ * STORE p->on_cpu = 1 LOAD p->on_rq
-+ * UNLOCK rq->lock
-+ *
-+ * __schedule() (put 'p' to sleep)
-+ * LOCK rq->lock smp_rmb();
-+ * smp_mb__after_spinlock();
-+ * STORE p->on_rq = 0 LOAD p->on_cpu
-+ *
-+ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
-+ * __schedule(). See the comment for smp_mb__after_spinlock().
-+ *
-+ * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
-+ * schedule()'s deactivate_task() has 'happened' and p will no longer
-+ * care about it's own p->state. See the comment in __schedule().
-+ */
-+ smp_acquire__after_ctrl_dep();
-+
-+ /*
-+ * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
-+ * == 0), which means we need to do an enqueue, change p->state to
-+ * TASK_WAKING such that we can unlock p->pi_lock before doing the
-+ * enqueue, such as ttwu_queue_wakelist().
-+ */
-+ WRITE_ONCE(p->__state, TASK_WAKING);
-+
-+ /*
-+ * If the owning (remote) CPU is still in the middle of schedule() with
-+ * this task as prev, considering queueing p on the remote CPUs wake_list
-+ * which potentially sends an IPI instead of spinning on p->on_cpu to
-+ * let the waker make forward progress. This is safe because IRQs are
-+ * disabled and the IPI will deliver after on_cpu is cleared.
-+ *
-+ * Ensure we load task_cpu(p) after p->on_cpu:
-+ *
-+ * set_task_cpu(p, cpu);
-+ * STORE p->cpu = @cpu
-+ * __schedule() (switch to task 'p')
-+ * LOCK rq->lock
-+ * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
-+ * STORE p->on_cpu = 1 LOAD p->cpu
-+ *
-+ * to ensure we observe the correct CPU on which the task is currently
-+ * scheduling.
-+ */
-+ if (smp_load_acquire(&p->on_cpu) &&
-+ ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
-+ break;
-+
-+ /*
-+ * If the owning (remote) CPU is still in the middle of schedule() with
-+ * this task as prev, wait until it's done referencing the task.
-+ *
-+ * Pairs with the smp_store_release() in finish_task().
-+ *
-+ * This ensures that tasks getting woken will be fully ordered against
-+ * their previous state and preserve Program Order.
-+ */
-+ smp_cond_load_acquire(&p->on_cpu, !VAL);
-+
-+ sched_task_ttwu(p);
-+
-+ if ((wake_flags & WF_CURRENT_CPU) &&
-+ cpumask_test_cpu(smp_processor_id(), p->cpus_ptr))
-+ cpu = smp_processor_id();
-+ else
-+ cpu = select_task_rq(p);
-+
-+ if (cpu != task_cpu(p)) {
-+ if (p->in_iowait) {
-+ delayacct_blkio_end(p);
-+ atomic_dec(&task_rq(p)->nr_iowait);
-+ }
-+
-+ wake_flags |= WF_MIGRATED;
-+ set_task_cpu(p, cpu);
-+ }
-+#else
-+ sched_task_ttwu(p);
-+
-+ cpu = task_cpu(p);
-+#endif /* CONFIG_SMP */
-+
-+ ttwu_queue(p, cpu, wake_flags);
-+ }
-+out:
-+ if (success)
-+ ttwu_stat(p, task_cpu(p), wake_flags);
-+
-+ return success;
-+}
-+
-+static bool __task_needs_rq_lock(struct task_struct *p)
-+{
-+ unsigned int state = READ_ONCE(p->__state);
-+
-+ /*
-+ * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
-+ * the task is blocked. Make sure to check @state since ttwu() can drop
-+ * locks at the end, see ttwu_queue_wakelist().
-+ */
-+ if (state == TASK_RUNNING || state == TASK_WAKING)
-+ return true;
-+
-+ /*
-+ * Ensure we load p->on_rq after p->__state, otherwise it would be
-+ * possible to, falsely, observe p->on_rq == 0.
-+ *
-+ * See try_to_wake_up() for a longer comment.
-+ */
-+ smp_rmb();
-+ if (p->on_rq)
-+ return true;
-+
-+#ifdef CONFIG_SMP
-+ /*
-+ * Ensure the task has finished __schedule() and will not be referenced
-+ * anymore. Again, see try_to_wake_up() for a longer comment.
-+ */
-+ smp_rmb();
-+ smp_cond_load_acquire(&p->on_cpu, !VAL);
-+#endif
-+
-+ return false;
-+}
-+
-+/**
-+ * task_call_func - Invoke a function on task in fixed state
-+ * @p: Process for which the function is to be invoked, can be @current.
-+ * @func: Function to invoke.
-+ * @arg: Argument to function.
-+ *
-+ * Fix the task in it's current state by avoiding wakeups and or rq operations
-+ * and call @func(@arg) on it. This function can use ->on_rq and task_curr()
-+ * to work out what the state is, if required. Given that @func can be invoked
-+ * with a runqueue lock held, it had better be quite lightweight.
-+ *
-+ * Returns:
-+ * Whatever @func returns
-+ */
-+int task_call_func(struct task_struct *p, task_call_f func, void *arg)
-+{
-+ struct rq *rq = NULL;
-+ struct rq_flags rf;
-+ int ret;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
-+
-+ if (__task_needs_rq_lock(p))
-+ rq = __task_rq_lock(p, &rf);
-+
-+ /*
-+ * At this point the task is pinned; either:
-+ * - blocked and we're holding off wakeups (pi->lock)
-+ * - woken, and we're holding off enqueue (rq->lock)
-+ * - queued, and we're holding off schedule (rq->lock)
-+ * - running, and we're holding off de-schedule (rq->lock)
-+ *
-+ * The called function (@func) can use: task_curr(), p->on_rq and
-+ * p->__state to differentiate between these states.
-+ */
-+ ret = func(p, arg);
-+
-+ if (rq)
-+ __task_rq_unlock(rq, &rf);
-+
-+ raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
-+ return ret;
-+}
-+
-+/**
-+ * cpu_curr_snapshot - Return a snapshot of the currently running task
-+ * @cpu: The CPU on which to snapshot the task.
-+ *
-+ * Returns the task_struct pointer of the task "currently" running on
-+ * the specified CPU. If the same task is running on that CPU throughout,
-+ * the return value will be a pointer to that task's task_struct structure.
-+ * If the CPU did any context switches even vaguely concurrently with the
-+ * execution of this function, the return value will be a pointer to the
-+ * task_struct structure of a randomly chosen task that was running on
-+ * that CPU somewhere around the time that this function was executing.
-+ *
-+ * If the specified CPU was offline, the return value is whatever it
-+ * is, perhaps a pointer to the task_struct structure of that CPU's idle
-+ * task, but there is no guarantee. Callers wishing a useful return
-+ * value must take some action to ensure that the specified CPU remains
-+ * online throughout.
-+ *
-+ * This function executes full memory barriers before and after fetching
-+ * the pointer, which permits the caller to confine this function's fetch
-+ * with respect to the caller's accesses to other shared variables.
-+ */
-+struct task_struct *cpu_curr_snapshot(int cpu)
-+{
-+ struct task_struct *t;
-+
-+ smp_mb(); /* Pairing determined by caller's synchronization design. */
-+ t = rcu_dereference(cpu_curr(cpu));
-+ smp_mb(); /* Pairing determined by caller's synchronization design. */
-+ return t;
-+}
-+
-+/**
-+ * wake_up_process - Wake up a specific process
-+ * @p: The process to be woken up.
-+ *
-+ * Attempt to wake up the nominated process and move it to the set of runnable
-+ * processes.
-+ *
-+ * Return: 1 if the process was woken up, 0 if it was already running.
-+ *
-+ * This function executes a full memory barrier before accessing the task state.
-+ */
-+int wake_up_process(struct task_struct *p)
-+{
-+ return try_to_wake_up(p, TASK_NORMAL, 0);
-+}
-+EXPORT_SYMBOL(wake_up_process);
-+
-+int wake_up_state(struct task_struct *p, unsigned int state)
-+{
-+ return try_to_wake_up(p, state, 0);
-+}
-+
-+/*
-+ * Perform scheduler related setup for a newly forked process p.
-+ * p is forked by current.
-+ *
-+ * __sched_fork() is basic setup used by init_idle() too:
-+ */
-+static inline void __sched_fork(unsigned long clone_flags, struct task_struct *p)
-+{
-+ p->on_rq = 0;
-+ p->on_cpu = 0;
-+ p->utime = 0;
-+ p->stime = 0;
-+ p->sched_time = 0;
-+
-+#ifdef CONFIG_SCHEDSTATS
-+ /* Even if schedstat is disabled, there should not be garbage */
-+ memset(&p->stats, 0, sizeof(p->stats));
-+#endif
-+
-+#ifdef CONFIG_PREEMPT_NOTIFIERS
-+ INIT_HLIST_HEAD(&p->preempt_notifiers);
-+#endif
-+
-+#ifdef CONFIG_COMPACTION
-+ p->capture_control = NULL;
-+#endif
-+#ifdef CONFIG_SMP
-+ p->wake_entry.u_flags = CSD_TYPE_TTWU;
-+#endif
-+ init_sched_mm_cid(p);
-+}
-+
-+/*
-+ * fork()/clone()-time setup:
-+ */
-+int sched_fork(unsigned long clone_flags, struct task_struct *p)
-+{
-+ __sched_fork(clone_flags, p);
-+ /*
-+ * We mark the process as NEW here. This guarantees that
-+ * nobody will actually run it, and a signal or other external
-+ * event cannot wake it up and insert it on the runqueue either.
-+ */
-+ p->__state = TASK_NEW;
-+
-+ /*
-+ * Make sure we do not leak PI boosting priority to the child.
-+ */
-+ p->prio = current->normal_prio;
-+
-+ /*
-+ * Revert to default priority/policy on fork if requested.
-+ */
-+ if (unlikely(p->sched_reset_on_fork)) {
-+ if (task_has_rt_policy(p)) {
-+ p->policy = SCHED_NORMAL;
-+ p->static_prio = NICE_TO_PRIO(0);
-+ p->rt_priority = 0;
-+ } else if (PRIO_TO_NICE(p->static_prio) < 0)
-+ p->static_prio = NICE_TO_PRIO(0);
-+
-+ p->prio = p->normal_prio = p->static_prio;
-+
-+ /*
-+ * We don't need the reset flag anymore after the fork. It has
-+ * fulfilled its duty:
-+ */
-+ p->sched_reset_on_fork = 0;
-+ }
-+
-+#ifdef CONFIG_SCHED_INFO
-+ if (unlikely(sched_info_on()))
-+ memset(&p->sched_info, 0, sizeof(p->sched_info));
-+#endif
-+ init_task_preempt_count(p);
-+
-+ return 0;
-+}
-+
-+void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+
-+ /*
-+ * Because we're not yet on the pid-hash, p->pi_lock isn't strictly
-+ * required yet, but lockdep gets upset if rules are violated.
-+ */
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+ /*
-+ * Share the timeslice between parent and child, thus the
-+ * total amount of pending timeslices in the system doesn't change,
-+ * resulting in more scheduling fairness.
-+ */
-+ rq = this_rq();
-+ raw_spin_lock(&rq->lock);
-+
-+ rq->curr->time_slice /= 2;
-+ p->time_slice = rq->curr->time_slice;
-+#ifdef CONFIG_SCHED_HRTICK
-+ hrtick_start(rq, rq->curr->time_slice);
-+#endif
-+
-+ if (p->time_slice < RESCHED_NS) {
-+ p->time_slice = sysctl_sched_base_slice;
-+ resched_curr(rq);
-+ }
-+ sched_task_fork(p, rq);
-+ raw_spin_unlock(&rq->lock);
-+
-+ rseq_migrate(p);
-+ /*
-+ * We're setting the CPU for the first time, we don't migrate,
-+ * so use __set_task_cpu().
-+ */
-+ __set_task_cpu(p, smp_processor_id());
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+}
-+
-+void sched_post_fork(struct task_struct *p)
-+{
-+}
-+
-+#ifdef CONFIG_SCHEDSTATS
-+
-+DEFINE_STATIC_KEY_FALSE(sched_schedstats);
-+
-+static void set_schedstats(bool enabled)
-+{
-+ if (enabled)
-+ static_branch_enable(&sched_schedstats);
-+ else
-+ static_branch_disable(&sched_schedstats);
-+}
-+
-+void force_schedstat_enabled(void)
-+{
-+ if (!schedstat_enabled()) {
-+ pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
-+ static_branch_enable(&sched_schedstats);
-+ }
-+}
-+
-+static int __init setup_schedstats(char *str)
-+{
-+ int ret = 0;
-+ if (!str)
-+ goto out;
-+
-+ if (!strcmp(str, "enable")) {
-+ set_schedstats(true);
-+ ret = 1;
-+ } else if (!strcmp(str, "disable")) {
-+ set_schedstats(false);
-+ ret = 1;
-+ }
-+out:
-+ if (!ret)
-+ pr_warn("Unable to parse schedstats=\n");
-+
-+ return ret;
-+}
-+__setup("schedstats=", setup_schedstats);
-+
-+#ifdef CONFIG_PROC_SYSCTL
-+static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
-+ size_t *lenp, loff_t *ppos)
-+{
-+ struct ctl_table t;
-+ int err;
-+ int state = static_branch_likely(&sched_schedstats);
-+
-+ if (write && !capable(CAP_SYS_ADMIN))
-+ return -EPERM;
-+
-+ t = *table;
-+ t.data = &state;
-+ err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
-+ if (err < 0)
-+ return err;
-+ if (write)
-+ set_schedstats(state);
-+ return err;
-+}
-+
-+static struct ctl_table sched_core_sysctls[] = {
-+ {
-+ .procname = "sched_schedstats",
-+ .data = NULL,
-+ .maxlen = sizeof(unsigned int),
-+ .mode = 0644,
-+ .proc_handler = sysctl_schedstats,
-+ .extra1 = SYSCTL_ZERO,
-+ .extra2 = SYSCTL_ONE,
-+ },
-+};
-+static int __init sched_core_sysctl_init(void)
-+{
-+ register_sysctl_init("kernel", sched_core_sysctls);
-+ return 0;
-+}
-+late_initcall(sched_core_sysctl_init);
-+#endif /* CONFIG_PROC_SYSCTL */
-+#endif /* CONFIG_SCHEDSTATS */
-+
-+/*
-+ * wake_up_new_task - wake up a newly created task for the first time.
-+ *
-+ * This function will do some initial scheduler statistics housekeeping
-+ * that must be done for every newly created context, then puts the task
-+ * on the runqueue and wakes it.
-+ */
-+void wake_up_new_task(struct task_struct *p)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+ WRITE_ONCE(p->__state, TASK_RUNNING);
-+ rq = cpu_rq(select_task_rq(p));
-+#ifdef CONFIG_SMP
-+ rseq_migrate(p);
-+ /*
-+ * Fork balancing, do it here and not earlier because:
-+ * - cpus_ptr can change in the fork path
-+ * - any previously selected CPU might disappear through hotplug
-+ *
-+ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
-+ * as we're not fully set-up yet.
-+ */
-+ __set_task_cpu(p, cpu_of(rq));
-+#endif
-+
-+ raw_spin_lock(&rq->lock);
-+ update_rq_clock(rq);
-+
-+ activate_task(p, rq);
-+ trace_sched_wakeup_new(p);
-+ wakeup_preempt(rq);
-+
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+}
-+
-+#ifdef CONFIG_PREEMPT_NOTIFIERS
-+
-+static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
-+
-+void preempt_notifier_inc(void)
-+{
-+ static_branch_inc(&preempt_notifier_key);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_inc);
-+
-+void preempt_notifier_dec(void)
-+{
-+ static_branch_dec(&preempt_notifier_key);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_dec);
-+
-+/**
-+ * preempt_notifier_register - tell me when current is being preempted & rescheduled
-+ * @notifier: notifier struct to register
-+ */
-+void preempt_notifier_register(struct preempt_notifier *notifier)
-+{
-+ if (!static_branch_unlikely(&preempt_notifier_key))
-+ WARN(1, "registering preempt_notifier while notifiers disabled\n");
-+
-+ hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_register);
-+
-+/**
-+ * preempt_notifier_unregister - no longer interested in preemption notifications
-+ * @notifier: notifier struct to unregister
-+ *
-+ * This is *not* safe to call from within a preemption notifier.
-+ */
-+void preempt_notifier_unregister(struct preempt_notifier *notifier)
-+{
-+ hlist_del(¬ifier->link);
-+}
-+EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
-+
-+static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
-+{
-+ struct preempt_notifier *notifier;
-+
-+ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
-+ notifier->ops->sched_in(notifier, raw_smp_processor_id());
-+}
-+
-+static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
-+{
-+ if (static_branch_unlikely(&preempt_notifier_key))
-+ __fire_sched_in_preempt_notifiers(curr);
-+}
-+
-+static void
-+__fire_sched_out_preempt_notifiers(struct task_struct *curr,
-+ struct task_struct *next)
-+{
-+ struct preempt_notifier *notifier;
-+
-+ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
-+ notifier->ops->sched_out(notifier, next);
-+}
-+
-+static __always_inline void
-+fire_sched_out_preempt_notifiers(struct task_struct *curr,
-+ struct task_struct *next)
-+{
-+ if (static_branch_unlikely(&preempt_notifier_key))
-+ __fire_sched_out_preempt_notifiers(curr, next);
-+}
-+
-+#else /* !CONFIG_PREEMPT_NOTIFIERS */
-+
-+static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
-+{
-+}
-+
-+static inline void
-+fire_sched_out_preempt_notifiers(struct task_struct *curr,
-+ struct task_struct *next)
-+{
-+}
-+
-+#endif /* CONFIG_PREEMPT_NOTIFIERS */
-+
-+static inline void prepare_task(struct task_struct *next)
-+{
-+ /*
-+ * Claim the task as running, we do this before switching to it
-+ * such that any running task will have this set.
-+ *
-+ * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
-+ * its ordering comment.
-+ */
-+ WRITE_ONCE(next->on_cpu, 1);
-+}
-+
-+static inline void finish_task(struct task_struct *prev)
-+{
-+#ifdef CONFIG_SMP
-+ /*
-+ * This must be the very last reference to @prev from this CPU. After
-+ * p->on_cpu is cleared, the task can be moved to a different CPU. We
-+ * must ensure this doesn't happen until the switch is completely
-+ * finished.
-+ *
-+ * In particular, the load of prev->state in finish_task_switch() must
-+ * happen before this.
-+ *
-+ * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
-+ */
-+ smp_store_release(&prev->on_cpu, 0);
-+#else
-+ prev->on_cpu = 0;
-+#endif
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
-+{
-+ void (*func)(struct rq *rq);
-+ struct balance_callback *next;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ while (head) {
-+ func = (void (*)(struct rq *))head->func;
-+ next = head->next;
-+ head->next = NULL;
-+ head = next;
-+
-+ func(rq);
-+ }
-+}
-+
-+static void balance_push(struct rq *rq);
-+
-+/*
-+ * balance_push_callback is a right abuse of the callback interface and plays
-+ * by significantly different rules.
-+ *
-+ * Where the normal balance_callback's purpose is to be ran in the same context
-+ * that queued it (only later, when it's safe to drop rq->lock again),
-+ * balance_push_callback is specifically targeted at __schedule().
-+ *
-+ * This abuse is tolerated because it places all the unlikely/odd cases behind
-+ * a single test, namely: rq->balance_callback == NULL.
-+ */
-+struct balance_callback balance_push_callback = {
-+ .next = NULL,
-+ .func = balance_push,
-+};
-+
-+static inline struct balance_callback *
-+__splice_balance_callbacks(struct rq *rq, bool split)
-+{
-+ struct balance_callback *head = rq->balance_callback;
-+
-+ if (likely(!head))
-+ return NULL;
-+
-+ lockdep_assert_rq_held(rq);
-+ /*
-+ * Must not take balance_push_callback off the list when
-+ * splice_balance_callbacks() and balance_callbacks() are not
-+ * in the same rq->lock section.
-+ *
-+ * In that case it would be possible for __schedule() to interleave
-+ * and observe the list empty.
-+ */
-+ if (split && head == &balance_push_callback)
-+ head = NULL;
-+ else
-+ rq->balance_callback = NULL;
-+
-+ return head;
-+}
-+
-+static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
-+{
-+ return __splice_balance_callbacks(rq, true);
-+}
-+
-+static void __balance_callbacks(struct rq *rq)
-+{
-+ do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
-+}
-+
-+static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
-+{
-+ unsigned long flags;
-+
-+ if (unlikely(head)) {
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ do_balance_callbacks(rq, head);
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+ }
-+}
-+
-+#else
-+
-+static inline void __balance_callbacks(struct rq *rq)
-+{
-+}
-+
-+static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
-+{
-+ return NULL;
-+}
-+
-+static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
-+{
-+}
-+
-+#endif
-+
-+static inline void
-+prepare_lock_switch(struct rq *rq, struct task_struct *next)
-+{
-+ /*
-+ * Since the runqueue lock will be released by the next
-+ * task (which is an invalid locking op but in the case
-+ * of the scheduler it's an obvious special-case), so we
-+ * do an early lockdep release here:
-+ */
-+ spin_release(&rq->lock.dep_map, _THIS_IP_);
-+#ifdef CONFIG_DEBUG_SPINLOCK
-+ /* this is a valid case when another task releases the spinlock */
-+ rq->lock.owner = next;
-+#endif
-+}
-+
-+static inline void finish_lock_switch(struct rq *rq)
-+{
-+ /*
-+ * If we are tracking spinlock dependencies then we have to
-+ * fix up the runqueue lock - which gets 'carried over' from
-+ * prev into current:
-+ */
-+ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
-+ __balance_callbacks(rq);
-+ raw_spin_unlock_irq(&rq->lock);
-+}
-+
-+/*
-+ * NOP if the arch has not defined these:
-+ */
-+
-+#ifndef prepare_arch_switch
-+# define prepare_arch_switch(next) do { } while (0)
-+#endif
-+
-+#ifndef finish_arch_post_lock_switch
-+# define finish_arch_post_lock_switch() do { } while (0)
-+#endif
-+
-+static inline void kmap_local_sched_out(void)
-+{
-+#ifdef CONFIG_KMAP_LOCAL
-+ if (unlikely(current->kmap_ctrl.idx))
-+ __kmap_local_sched_out();
-+#endif
-+}
-+
-+static inline void kmap_local_sched_in(void)
-+{
-+#ifdef CONFIG_KMAP_LOCAL
-+ if (unlikely(current->kmap_ctrl.idx))
-+ __kmap_local_sched_in();
-+#endif
-+}
-+
-+/**
-+ * prepare_task_switch - prepare to switch tasks
-+ * @rq: the runqueue preparing to switch
-+ * @next: the task we are going to switch to.
-+ *
-+ * This is called with the rq lock held and interrupts off. It must
-+ * be paired with a subsequent finish_task_switch after the context
-+ * switch.
-+ *
-+ * prepare_task_switch sets up locking and calls architecture specific
-+ * hooks.
-+ */
-+static inline void
-+prepare_task_switch(struct rq *rq, struct task_struct *prev,
-+ struct task_struct *next)
-+{
-+ kcov_prepare_switch(prev);
-+ sched_info_switch(rq, prev, next);
-+ perf_event_task_sched_out(prev, next);
-+ rseq_preempt(prev);
-+ fire_sched_out_preempt_notifiers(prev, next);
-+ kmap_local_sched_out();
-+ prepare_task(next);
-+ prepare_arch_switch(next);
-+}
-+
-+/**
-+ * finish_task_switch - clean up after a task-switch
-+ * @rq: runqueue associated with task-switch
-+ * @prev: the thread we just switched away from.
-+ *
-+ * finish_task_switch must be called after the context switch, paired
-+ * with a prepare_task_switch call before the context switch.
-+ * finish_task_switch will reconcile locking set up by prepare_task_switch,
-+ * and do any other architecture-specific cleanup actions.
-+ *
-+ * Note that we may have delayed dropping an mm in context_switch(). If
-+ * so, we finish that here outside of the runqueue lock. (Doing it
-+ * with the lock held can cause deadlocks; see schedule() for
-+ * details.)
-+ *
-+ * The context switch have flipped the stack from under us and restored the
-+ * local variables which were saved when this task called schedule() in the
-+ * past. prev == current is still correct but we need to recalculate this_rq
-+ * because prev may have moved to another CPU.
-+ */
-+static struct rq *finish_task_switch(struct task_struct *prev)
-+ __releases(rq->lock)
-+{
-+ struct rq *rq = this_rq();
-+ struct mm_struct *mm = rq->prev_mm;
-+ unsigned int prev_state;
-+
-+ /*
-+ * The previous task will have left us with a preempt_count of 2
-+ * because it left us after:
-+ *
-+ * schedule()
-+ * preempt_disable(); // 1
-+ * __schedule()
-+ * raw_spin_lock_irq(&rq->lock) // 2
-+ *
-+ * Also, see FORK_PREEMPT_COUNT.
-+ */
-+ if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
-+ "corrupted preempt_count: %s/%d/0x%x\n",
-+ current->comm, current->pid, preempt_count()))
-+ preempt_count_set(FORK_PREEMPT_COUNT);
-+
-+ rq->prev_mm = NULL;
-+
-+ /*
-+ * A task struct has one reference for the use as "current".
-+ * If a task dies, then it sets TASK_DEAD in tsk->state and calls
-+ * schedule one last time. The schedule call will never return, and
-+ * the scheduled task must drop that reference.
-+ *
-+ * We must observe prev->state before clearing prev->on_cpu (in
-+ * finish_task), otherwise a concurrent wakeup can get prev
-+ * running on another CPU and we could rave with its RUNNING -> DEAD
-+ * transition, resulting in a double drop.
-+ */
-+ prev_state = READ_ONCE(prev->__state);
-+ vtime_task_switch(prev);
-+ perf_event_task_sched_in(prev, current);
-+ finish_task(prev);
-+ tick_nohz_task_switch();
-+ finish_lock_switch(rq);
-+ finish_arch_post_lock_switch();
-+ kcov_finish_switch(current);
-+ /*
-+ * kmap_local_sched_out() is invoked with rq::lock held and
-+ * interrupts disabled. There is no requirement for that, but the
-+ * sched out code does not have an interrupt enabled section.
-+ * Restoring the maps on sched in does not require interrupts being
-+ * disabled either.
-+ */
-+ kmap_local_sched_in();
-+
-+ fire_sched_in_preempt_notifiers(current);
-+ /*
-+ * When switching through a kernel thread, the loop in
-+ * membarrier_{private,global}_expedited() may have observed that
-+ * kernel thread and not issued an IPI. It is therefore possible to
-+ * schedule between user->kernel->user threads without passing though
-+ * switch_mm(). Membarrier requires a barrier after storing to
-+ * rq->curr, before returning to userspace, so provide them here:
-+ *
-+ * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
-+ * provided by mmdrop(),
-+ * - a sync_core for SYNC_CORE.
-+ */
-+ if (mm) {
-+ membarrier_mm_sync_core_before_usermode(mm);
-+ mmdrop_sched(mm);
-+ }
-+ if (unlikely(prev_state == TASK_DEAD)) {
-+ /* Task is done with its stack. */
-+ put_task_stack(prev);
-+
-+ put_task_struct_rcu_user(prev);
-+ }
-+
-+ return rq;
-+}
-+
-+/**
-+ * schedule_tail - first thing a freshly forked thread must call.
-+ * @prev: the thread we just switched away from.
-+ */
-+asmlinkage __visible void schedule_tail(struct task_struct *prev)
-+ __releases(rq->lock)
-+{
-+ /*
-+ * New tasks start with FORK_PREEMPT_COUNT, see there and
-+ * finish_task_switch() for details.
-+ *
-+ * finish_task_switch() will drop rq->lock() and lower preempt_count
-+ * and the preempt_enable() will end up enabling preemption (on
-+ * PREEMPT_COUNT kernels).
-+ */
-+
-+ finish_task_switch(prev);
-+ preempt_enable();
-+
-+ if (current->set_child_tid)
-+ put_user(task_pid_vnr(current), current->set_child_tid);
-+
-+ calculate_sigpending();
-+}
-+
-+/*
-+ * context_switch - switch to the new MM and the new thread's register state.
-+ */
-+static __always_inline struct rq *
-+context_switch(struct rq *rq, struct task_struct *prev,
-+ struct task_struct *next)
-+{
-+ prepare_task_switch(rq, prev, next);
-+
-+ /*
-+ * For paravirt, this is coupled with an exit in switch_to to
-+ * combine the page table reload and the switch backend into
-+ * one hypercall.
-+ */
-+ arch_start_context_switch(prev);
-+
-+ /*
-+ * kernel -> kernel lazy + transfer active
-+ * user -> kernel lazy + mmgrab() active
-+ *
-+ * kernel -> user switch + mmdrop() active
-+ * user -> user switch
-+ *
-+ * switch_mm_cid() needs to be updated if the barriers provided
-+ * by context_switch() are modified.
-+ */
-+ if (!next->mm) { // to kernel
-+ enter_lazy_tlb(prev->active_mm, next);
-+
-+ next->active_mm = prev->active_mm;
-+ if (prev->mm) // from user
-+ mmgrab(prev->active_mm);
-+ else
-+ prev->active_mm = NULL;
-+ } else { // to user
-+ membarrier_switch_mm(rq, prev->active_mm, next->mm);
-+ /*
-+ * sys_membarrier() requires an smp_mb() between setting
-+ * rq->curr / membarrier_switch_mm() and returning to userspace.
-+ *
-+ * The below provides this either through switch_mm(), or in
-+ * case 'prev->active_mm == next->mm' through
-+ * finish_task_switch()'s mmdrop().
-+ */
-+ switch_mm_irqs_off(prev->active_mm, next->mm, next);
-+ lru_gen_use_mm(next->mm);
-+
-+ if (!prev->mm) { // from kernel
-+ /* will mmdrop() in finish_task_switch(). */
-+ rq->prev_mm = prev->active_mm;
-+ prev->active_mm = NULL;
-+ }
-+ }
-+
-+ /* switch_mm_cid() requires the memory barriers above. */
-+ switch_mm_cid(rq, prev, next);
-+
-+ prepare_lock_switch(rq, next);
-+
-+ /* Here we just switch the register state and the stack. */
-+ switch_to(prev, next, prev);
-+ barrier();
-+
-+ return finish_task_switch(prev);
-+}
-+
-+/*
-+ * nr_running, nr_uninterruptible and nr_context_switches:
-+ *
-+ * externally visible scheduler statistics: current number of runnable
-+ * threads, total number of context switches performed since bootup.
-+ */
-+unsigned int nr_running(void)
-+{
-+ unsigned int i, sum = 0;
-+
-+ for_each_online_cpu(i)
-+ sum += cpu_rq(i)->nr_running;
-+
-+ return sum;
-+}
-+
-+/*
-+ * Check if only the current task is running on the CPU.
-+ *
-+ * Caution: this function does not check that the caller has disabled
-+ * preemption, thus the result might have a time-of-check-to-time-of-use
-+ * race. The caller is responsible to use it correctly, for example:
-+ *
-+ * - from a non-preemptible section (of course)
-+ *
-+ * - from a thread that is bound to a single CPU
-+ *
-+ * - in a loop with very short iterations (e.g. a polling loop)
-+ */
-+bool single_task_running(void)
-+{
-+ return raw_rq()->nr_running == 1;
-+}
-+EXPORT_SYMBOL(single_task_running);
-+
-+unsigned long long nr_context_switches_cpu(int cpu)
-+{
-+ return cpu_rq(cpu)->nr_switches;
-+}
-+
-+unsigned long long nr_context_switches(void)
-+{
-+ int i;
-+ unsigned long long sum = 0;
-+
-+ for_each_possible_cpu(i)
-+ sum += cpu_rq(i)->nr_switches;
-+
-+ return sum;
-+}
-+
-+/*
-+ * Consumers of these two interfaces, like for example the cpuidle menu
-+ * governor, are using nonsensical data. Preferring shallow idle state selection
-+ * for a CPU that has IO-wait which might not even end up running the task when
-+ * it does become runnable.
-+ */
-+
-+unsigned int nr_iowait_cpu(int cpu)
-+{
-+ return atomic_read(&cpu_rq(cpu)->nr_iowait);
-+}
-+
-+/*
-+ * IO-wait accounting, and how it's mostly bollocks (on SMP).
-+ *
-+ * The idea behind IO-wait account is to account the idle time that we could
-+ * have spend running if it were not for IO. That is, if we were to improve the
-+ * storage performance, we'd have a proportional reduction in IO-wait time.
-+ *
-+ * This all works nicely on UP, where, when a task blocks on IO, we account
-+ * idle time as IO-wait, because if the storage were faster, it could've been
-+ * running and we'd not be idle.
-+ *
-+ * This has been extended to SMP, by doing the same for each CPU. This however
-+ * is broken.
-+ *
-+ * Imagine for instance the case where two tasks block on one CPU, only the one
-+ * CPU will have IO-wait accounted, while the other has regular idle. Even
-+ * though, if the storage were faster, both could've ran at the same time,
-+ * utilising both CPUs.
-+ *
-+ * This means, that when looking globally, the current IO-wait accounting on
-+ * SMP is a lower bound, by reason of under accounting.
-+ *
-+ * Worse, since the numbers are provided per CPU, they are sometimes
-+ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
-+ * associated with any one particular CPU, it can wake to another CPU than it
-+ * blocked on. This means the per CPU IO-wait number is meaningless.
-+ *
-+ * Task CPU affinities can make all that even more 'interesting'.
-+ */
-+
-+unsigned int nr_iowait(void)
-+{
-+ unsigned int i, sum = 0;
-+
-+ for_each_possible_cpu(i)
-+ sum += nr_iowait_cpu(i);
-+
-+ return sum;
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+/*
-+ * sched_exec - execve() is a valuable balancing opportunity, because at
-+ * this point the task has the smallest effective memory and cache
-+ * footprint.
-+ */
-+void sched_exec(void)
-+{
-+}
-+
-+#endif
-+
-+DEFINE_PER_CPU(struct kernel_stat, kstat);
-+DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
-+
-+EXPORT_PER_CPU_SYMBOL(kstat);
-+EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
-+
-+static inline void update_curr(struct rq *rq, struct task_struct *p)
-+{
-+ s64 ns = rq->clock_task - p->last_ran;
-+
-+ p->sched_time += ns;
-+ cgroup_account_cputime(p, ns);
-+ account_group_exec_runtime(p, ns);
-+
-+ p->time_slice -= ns;
-+ p->last_ran = rq->clock_task;
-+}
-+
-+/*
-+ * Return accounted runtime for the task.
-+ * Return separately the current's pending runtime that have not been
-+ * accounted yet.
-+ */
-+unsigned long long task_sched_runtime(struct task_struct *p)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+ u64 ns;
-+
-+#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
-+ /*
-+ * 64-bit doesn't need locks to atomically read a 64-bit value.
-+ * So we have a optimization chance when the task's delta_exec is 0.
-+ * Reading ->on_cpu is racy, but this is ok.
-+ *
-+ * If we race with it leaving CPU, we'll take a lock. So we're correct.
-+ * If we race with it entering CPU, unaccounted time is 0. This is
-+ * indistinguishable from the read occurring a few cycles earlier.
-+ * If we see ->on_cpu without ->on_rq, the task is leaving, and has
-+ * been accounted, so we're correct here as well.
-+ */
-+ if (!p->on_cpu || !task_on_rq_queued(p))
-+ return tsk_seruntime(p);
-+#endif
-+
-+ rq = task_access_lock_irqsave(p, &lock, &flags);
-+ /*
-+ * Must be ->curr _and_ ->on_rq. If dequeued, we would
-+ * project cycles that may never be accounted to this
-+ * thread, breaking clock_gettime().
-+ */
-+ if (p == rq->curr && task_on_rq_queued(p)) {
-+ update_rq_clock(rq);
-+ update_curr(rq, p);
-+ }
-+ ns = tsk_seruntime(p);
-+ task_access_unlock_irqrestore(p, lock, &flags);
-+
-+ return ns;
-+}
-+
-+/* This manages tasks that have run out of timeslice during a scheduler_tick */
-+static inline void scheduler_task_tick(struct rq *rq)
-+{
-+ struct task_struct *p = rq->curr;
-+
-+ if (is_idle_task(p))
-+ return;
-+
-+ update_curr(rq, p);
-+ cpufreq_update_util(rq, 0);
-+
-+ /*
-+ * Tasks have less than RESCHED_NS of time slice left they will be
-+ * rescheduled.
-+ */
-+ if (p->time_slice >= RESCHED_NS)
-+ return;
-+ set_tsk_need_resched(p);
-+ set_preempt_need_resched();
-+}
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+static u64 cpu_resched_latency(struct rq *rq)
-+{
-+ int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
-+ u64 resched_latency, now = rq_clock(rq);
-+ static bool warned_once;
-+
-+ if (sysctl_resched_latency_warn_once && warned_once)
-+ return 0;
-+
-+ if (!need_resched() || !latency_warn_ms)
-+ return 0;
-+
-+ if (system_state == SYSTEM_BOOTING)
-+ return 0;
-+
-+ if (!rq->last_seen_need_resched_ns) {
-+ rq->last_seen_need_resched_ns = now;
-+ rq->ticks_without_resched = 0;
-+ return 0;
-+ }
-+
-+ rq->ticks_without_resched++;
-+ resched_latency = now - rq->last_seen_need_resched_ns;
-+ if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC)
-+ return 0;
-+
-+ warned_once = true;
-+
-+ return resched_latency;
-+}
-+
-+static int __init setup_resched_latency_warn_ms(char *str)
-+{
-+ long val;
-+
-+ if ((kstrtol(str, 0, &val))) {
-+ pr_warn("Unable to set resched_latency_warn_ms\n");
-+ return 1;
-+ }
-+
-+ sysctl_resched_latency_warn_ms = val;
-+ return 1;
-+}
-+__setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
-+#else
-+static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
-+#endif /* CONFIG_SCHED_DEBUG */
-+
-+/*
-+ * This function gets called by the timer code, with HZ frequency.
-+ * We call it with interrupts disabled.
-+ */
-+void sched_tick(void)
-+{
-+ int cpu __maybe_unused = smp_processor_id();
-+ struct rq *rq = cpu_rq(cpu);
-+ struct task_struct *curr = rq->curr;
-+ u64 resched_latency;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
-+ arch_scale_freq_tick();
-+
-+ sched_clock_tick();
-+
-+ raw_spin_lock(&rq->lock);
-+ update_rq_clock(rq);
-+
-+ scheduler_task_tick(rq);
-+ if (sched_feat(LATENCY_WARN))
-+ resched_latency = cpu_resched_latency(rq);
-+ calc_global_load_tick(rq);
-+
-+ task_tick_mm_cid(rq, rq->curr);
-+
-+ raw_spin_unlock(&rq->lock);
-+
-+ if (sched_feat(LATENCY_WARN) && resched_latency)
-+ resched_latency_warn(cpu, resched_latency);
-+
-+ perf_event_task_tick();
-+
-+ if (curr->flags & PF_WQ_WORKER)
-+ wq_worker_tick(curr);
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+static int active_balance_cpu_stop(void *data)
-+{
-+ struct balance_arg *arg = data;
-+ struct task_struct *p = arg->task;
-+ struct rq *rq = this_rq();
-+ unsigned long flags;
-+ cpumask_t tmp;
-+
-+ local_irq_save(flags);
-+
-+ raw_spin_lock(&p->pi_lock);
-+ raw_spin_lock(&rq->lock);
-+
-+ arg->active = 0;
-+
-+ if (task_on_rq_queued(p) && task_rq(p) == rq &&
-+ cpumask_and(&tmp, p->cpus_ptr, arg->cpumask) &&
-+ !is_migration_disabled(p)) {
-+ int dcpu = __best_mask_cpu(&tmp, per_cpu(sched_cpu_llc_mask, cpu_of(rq)));
-+ rq = move_queued_task(rq, p, dcpu);
-+ }
-+
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+
-+ return 0;
-+}
-+
-+/* trigger_active_balance - for @cpu/@rq */
-+static inline int
-+trigger_active_balance(struct rq *src_rq, struct rq *rq, struct balance_arg *arg)
-+{
-+ unsigned long flags;
-+ struct task_struct *p;
-+ int res;
-+
-+ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
-+ return 0;
-+
-+ res = (1 == rq->nr_running) && \
-+ !is_migration_disabled((p = sched_rq_first_task(rq))) && \
-+ cpumask_intersects(p->cpus_ptr, arg->cpumask) && \
-+ !arg->active;
-+ if (res) {
-+ arg->task = p;
-+
-+ arg->active = 1;
-+ }
-+
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+ if (res) {
-+ preempt_disable();
-+ raw_spin_unlock(&src_rq->lock);
-+
-+ stop_one_cpu_nowait(cpu_of(rq), active_balance_cpu_stop,
-+ arg, &rq->active_balance_work);
-+
-+ preempt_enable();
-+ raw_spin_lock(&src_rq->lock);
-+ }
-+
-+ return res;
-+}
-+
-+#ifdef CONFIG_SCHED_SMT
-+/*
-+ * sg_balance - slibing group balance check for run queue @rq
-+ */
-+static inline void sg_balance(struct rq *rq)
-+{
-+ cpumask_t chk;
-+
-+ if (cpumask_andnot(&chk, cpu_active_mask, sched_idle_mask) &&
-+ cpumask_andnot(&chk, &chk, &sched_rq_pending_mask)) {
-+ int i, cpu = cpu_of(rq);
-+
-+ for_each_cpu_wrap(i, &chk, cpu) {
-+ if (cpumask_subset(cpu_smt_mask(i), &chk)) {
-+ struct rq *target_rq = cpu_rq(i);
-+ if (trigger_active_balance(rq, target_rq, &target_rq->sg_balance_arg))
-+ return;
-+ }
-+ }
-+ }
-+}
-+
-+static DEFINE_PER_CPU(struct balance_callback, sg_balance_head) = {
-+ .func = sg_balance,
-+};
-+#endif /* CONFIG_SCHED_SMT */
-+
-+#endif /* CONFIG_SMP */
-+
-+#ifdef CONFIG_NO_HZ_FULL
-+
-+struct tick_work {
-+ int cpu;
-+ atomic_t state;
-+ struct delayed_work work;
-+};
-+/* Values for ->state, see diagram below. */
-+#define TICK_SCHED_REMOTE_OFFLINE 0
-+#define TICK_SCHED_REMOTE_OFFLINING 1
-+#define TICK_SCHED_REMOTE_RUNNING 2
-+
-+/*
-+ * State diagram for ->state:
-+ *
-+ *
-+ * TICK_SCHED_REMOTE_OFFLINE
-+ * | ^
-+ * | |
-+ * | | sched_tick_remote()
-+ * | |
-+ * | |
-+ * +--TICK_SCHED_REMOTE_OFFLINING
-+ * | ^
-+ * | |
-+ * sched_tick_start() | | sched_tick_stop()
-+ * | |
-+ * V |
-+ * TICK_SCHED_REMOTE_RUNNING
-+ *
-+ *
-+ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
-+ * and sched_tick_start() are happy to leave the state in RUNNING.
-+ */
-+
-+static struct tick_work __percpu *tick_work_cpu;
-+
-+static void sched_tick_remote(struct work_struct *work)
-+{
-+ struct delayed_work *dwork = to_delayed_work(work);
-+ struct tick_work *twork = container_of(dwork, struct tick_work, work);
-+ int cpu = twork->cpu;
-+ struct rq *rq = cpu_rq(cpu);
-+ int os;
-+
-+ /*
-+ * Handle the tick only if it appears the remote CPU is running in full
-+ * dynticks mode. The check is racy by nature, but missing a tick or
-+ * having one too much is no big deal because the scheduler tick updates
-+ * statistics and checks timeslices in a time-independent way, regardless
-+ * of when exactly it is running.
-+ */
-+ if (tick_nohz_tick_stopped_cpu(cpu)) {
-+ guard(raw_spinlock_irqsave)(&rq->lock);
-+ struct task_struct *curr = rq->curr;
-+
-+ if (cpu_online(cpu)) {
-+ update_rq_clock(rq);
-+
-+ if (!is_idle_task(curr)) {
-+ /*
-+ * Make sure the next tick runs within a
-+ * reasonable amount of time.
-+ */
-+ u64 delta = rq_clock_task(rq) - curr->last_ran;
-+ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
-+ }
-+ scheduler_task_tick(rq);
-+
-+ calc_load_nohz_remote(rq);
-+ }
-+ }
-+
-+ /*
-+ * Run the remote tick once per second (1Hz). This arbitrary
-+ * frequency is large enough to avoid overload but short enough
-+ * to keep scheduler internal stats reasonably up to date. But
-+ * first update state to reflect hotplug activity if required.
-+ */
-+ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
-+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
-+ if (os == TICK_SCHED_REMOTE_RUNNING)
-+ queue_delayed_work(system_unbound_wq, dwork, HZ);
-+}
-+
-+static void sched_tick_start(int cpu)
-+{
-+ int os;
-+ struct tick_work *twork;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
-+ return;
-+
-+ WARN_ON_ONCE(!tick_work_cpu);
-+
-+ twork = per_cpu_ptr(tick_work_cpu, cpu);
-+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
-+ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
-+ if (os == TICK_SCHED_REMOTE_OFFLINE) {
-+ twork->cpu = cpu;
-+ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
-+ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
-+ }
-+}
-+
-+#ifdef CONFIG_HOTPLUG_CPU
-+static void sched_tick_stop(int cpu)
-+{
-+ struct tick_work *twork;
-+ int os;
-+
-+ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
-+ return;
-+
-+ WARN_ON_ONCE(!tick_work_cpu);
-+
-+ twork = per_cpu_ptr(tick_work_cpu, cpu);
-+ /* There cannot be competing actions, but don't rely on stop-machine. */
-+ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
-+ WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
-+ /* Don't cancel, as this would mess up the state machine. */
-+}
-+#endif /* CONFIG_HOTPLUG_CPU */
-+
-+int __init sched_tick_offload_init(void)
-+{
-+ tick_work_cpu = alloc_percpu(struct tick_work);
-+ BUG_ON(!tick_work_cpu);
-+ return 0;
-+}
-+
-+#else /* !CONFIG_NO_HZ_FULL */
-+static inline void sched_tick_start(int cpu) { }
-+static inline void sched_tick_stop(int cpu) { }
-+#endif
-+
-+#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
-+ defined(CONFIG_PREEMPT_TRACER))
-+/*
-+ * If the value passed in is equal to the current preempt count
-+ * then we just disabled preemption. Start timing the latency.
-+ */
-+static inline void preempt_latency_start(int val)
-+{
-+ if (preempt_count() == val) {
-+ unsigned long ip = get_lock_parent_ip();
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ current->preempt_disable_ip = ip;
-+#endif
-+ trace_preempt_off(CALLER_ADDR0, ip);
-+ }
-+}
-+
-+void preempt_count_add(int val)
-+{
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ /*
-+ * Underflow?
-+ */
-+ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
-+ return;
-+#endif
-+ __preempt_count_add(val);
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ /*
-+ * Spinlock count overflowing soon?
-+ */
-+ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
-+ PREEMPT_MASK - 10);
-+#endif
-+ preempt_latency_start(val);
-+}
-+EXPORT_SYMBOL(preempt_count_add);
-+NOKPROBE_SYMBOL(preempt_count_add);
-+
-+/*
-+ * If the value passed in equals to the current preempt count
-+ * then we just enabled preemption. Stop timing the latency.
-+ */
-+static inline void preempt_latency_stop(int val)
-+{
-+ if (preempt_count() == val)
-+ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
-+}
-+
-+void preempt_count_sub(int val)
-+{
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ /*
-+ * Underflow?
-+ */
-+ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
-+ return;
-+ /*
-+ * Is the spinlock portion underflowing?
-+ */
-+ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
-+ !(preempt_count() & PREEMPT_MASK)))
-+ return;
-+#endif
-+
-+ preempt_latency_stop(val);
-+ __preempt_count_sub(val);
-+}
-+EXPORT_SYMBOL(preempt_count_sub);
-+NOKPROBE_SYMBOL(preempt_count_sub);
-+
-+#else
-+static inline void preempt_latency_start(int val) { }
-+static inline void preempt_latency_stop(int val) { }
-+#endif
-+
-+static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
-+{
-+#ifdef CONFIG_DEBUG_PREEMPT
-+ return p->preempt_disable_ip;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+/*
-+ * Print scheduling while atomic bug:
-+ */
-+static noinline void __schedule_bug(struct task_struct *prev)
-+{
-+ /* Save this before calling printk(), since that will clobber it */
-+ unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
-+
-+ if (oops_in_progress)
-+ return;
-+
-+ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
-+ prev->comm, prev->pid, preempt_count());
-+
-+ debug_show_held_locks(prev);
-+ print_modules();
-+ if (irqs_disabled())
-+ print_irqtrace_events(prev);
-+ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
-+ pr_err("Preemption disabled at:");
-+ print_ip_sym(KERN_ERR, preempt_disable_ip);
-+ }
-+ check_panic_on_warn("scheduling while atomic");
-+
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+
-+/*
-+ * Various schedule()-time debugging checks and statistics:
-+ */
-+static inline void schedule_debug(struct task_struct *prev, bool preempt)
-+{
-+#ifdef CONFIG_SCHED_STACK_END_CHECK
-+ if (task_stack_end_corrupted(prev))
-+ panic("corrupted stack end detected inside scheduler\n");
-+
-+ if (task_scs_end_corrupted(prev))
-+ panic("corrupted shadow stack detected inside scheduler\n");
-+#endif
-+
-+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-+ if (!preempt && READ_ONCE(prev->__state) && prev->non_block_count) {
-+ printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
-+ prev->comm, prev->pid, prev->non_block_count);
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+ }
-+#endif
-+
-+ if (unlikely(in_atomic_preempt_off())) {
-+ __schedule_bug(prev);
-+ preempt_count_set(PREEMPT_DISABLED);
-+ }
-+ rcu_sleep_check();
-+ SCHED_WARN_ON(ct_state() == CONTEXT_USER);
-+
-+ profile_hit(SCHED_PROFILING, __builtin_return_address(0));
-+
-+ schedstat_inc(this_rq()->sched_count);
-+}
-+
-+#ifdef ALT_SCHED_DEBUG
-+void alt_sched_debug(void)
-+{
-+ printk(KERN_INFO "sched: pending: 0x%04lx, idle: 0x%04lx, sg_idle: 0x%04lx\n",
-+ sched_rq_pending_mask.bits[0],
-+ sched_idle_mask->bits[0],
-+ sched_sg_idle_mask.bits[0]);
-+}
-+#else
-+inline void alt_sched_debug(void) {}
-+#endif
-+
-+#ifdef CONFIG_SMP
-+
-+#ifdef CONFIG_PREEMPT_RT
-+#define SCHED_NR_MIGRATE_BREAK 8
-+#else
-+#define SCHED_NR_MIGRATE_BREAK 32
-+#endif
-+
-+const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
-+
-+/*
-+ * Migrate pending tasks in @rq to @dest_cpu
-+ */
-+static inline int
-+migrate_pending_tasks(struct rq *rq, struct rq *dest_rq, const int dest_cpu)
-+{
-+ struct task_struct *p, *skip = rq->curr;
-+ int nr_migrated = 0;
-+ int nr_tries = min(rq->nr_running / 2, sysctl_sched_nr_migrate);
-+
-+ /* WA to check rq->curr is still on rq */
-+ if (!task_on_rq_queued(skip))
-+ return 0;
-+
-+ while (skip != rq->idle && nr_tries &&
-+ (p = sched_rq_next_task(skip, rq)) != rq->idle) {
-+ skip = sched_rq_next_task(p, rq);
-+ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) {
-+ __SCHED_DEQUEUE_TASK(p, rq, 0, );
-+ set_task_cpu(p, dest_cpu);
-+ sched_task_sanity_check(p, dest_rq);
-+ sched_mm_cid_migrate_to(dest_rq, p, cpu_of(rq));
-+ __SCHED_ENQUEUE_TASK(p, dest_rq, 0, );
-+ nr_migrated++;
-+ }
-+ nr_tries--;
-+ }
-+
-+ return nr_migrated;
-+}
-+
-+static inline int take_other_rq_tasks(struct rq *rq, int cpu)
-+{
-+ cpumask_t *topo_mask, *end_mask, chk;
-+
-+ if (unlikely(!rq->online))
-+ return 0;
-+
-+ if (cpumask_empty(&sched_rq_pending_mask))
-+ return 0;
-+
-+ topo_mask = per_cpu(sched_cpu_topo_masks, cpu);
-+ end_mask = per_cpu(sched_cpu_topo_end_mask, cpu);
-+ do {
-+ int i;
-+
-+ if (!cpumask_and(&chk, &sched_rq_pending_mask, topo_mask))
-+ continue;
-+
-+ for_each_cpu_wrap(i, &chk, cpu) {
-+ int nr_migrated;
-+ struct rq *src_rq;
-+
-+ src_rq = cpu_rq(i);
-+ if (!do_raw_spin_trylock(&src_rq->lock))
-+ continue;
-+ spin_acquire(&src_rq->lock.dep_map,
-+ SINGLE_DEPTH_NESTING, 1, _RET_IP_);
-+
-+ if ((nr_migrated = migrate_pending_tasks(src_rq, rq, cpu))) {
-+ src_rq->nr_running -= nr_migrated;
-+ if (src_rq->nr_running < 2)
-+ cpumask_clear_cpu(i, &sched_rq_pending_mask);
-+
-+ spin_release(&src_rq->lock.dep_map, _RET_IP_);
-+ do_raw_spin_unlock(&src_rq->lock);
-+
-+ rq->nr_running += nr_migrated;
-+ if (rq->nr_running > 1)
-+ cpumask_set_cpu(cpu, &sched_rq_pending_mask);
-+
-+ update_sched_preempt_mask(rq);
-+ cpufreq_update_util(rq, 0);
-+
-+ return 1;
-+ }
-+
-+ spin_release(&src_rq->lock.dep_map, _RET_IP_);
-+ do_raw_spin_unlock(&src_rq->lock);
-+ }
-+ } while (++topo_mask < end_mask);
-+
-+ return 0;
-+}
-+#endif
-+
-+static inline void time_slice_expired(struct task_struct *p, struct rq *rq)
-+{
-+ p->time_slice = sysctl_sched_base_slice;
-+
-+ sched_task_renew(p, rq);
-+
-+ if (SCHED_FIFO != p->policy && task_on_rq_queued(p))
-+ requeue_task(p, rq);
-+}
-+
-+/*
-+ * Timeslices below RESCHED_NS are considered as good as expired as there's no
-+ * point rescheduling when there's so little time left.
-+ */
-+static inline void check_curr(struct task_struct *p, struct rq *rq)
-+{
-+ if (unlikely(rq->idle == p))
-+ return;
-+
-+ update_curr(rq, p);
-+
-+ if (p->time_slice < RESCHED_NS)
-+ time_slice_expired(p, rq);
-+}
-+
-+static inline struct task_struct *
-+choose_next_task(struct rq *rq, int cpu)
-+{
-+ struct task_struct *next = sched_rq_first_task(rq);
-+
-+ if (next == rq->idle) {
-+#ifdef CONFIG_SMP
-+ if (!take_other_rq_tasks(rq, cpu)) {
-+#endif
-+
-+#ifdef CONFIG_SCHED_SMT
-+ if (static_key_count(&sched_smt_present.key) > 1 &&
-+ cpumask_test_cpu(cpu, sched_sg_idle_mask) &&
-+ rq->online)
-+ __queue_balance_callback(rq, &per_cpu(sg_balance_head, cpu));
-+#endif
-+ schedstat_inc(rq->sched_goidle);
-+ /*printk(KERN_INFO "sched: choose_next_task(%d) idle %px\n", cpu, next);*/
-+ return next;
-+#ifdef CONFIG_SMP
-+ }
-+ next = sched_rq_first_task(rq);
-+#endif
-+ }
-+#ifdef CONFIG_HIGH_RES_TIMERS
-+ hrtick_start(rq, next->time_slice);
-+#endif
-+ /*printk(KERN_INFO "sched: choose_next_task(%d) next %px\n", cpu, next);*/
-+ return next;
-+}
-+
-+/*
-+ * Constants for the sched_mode argument of __schedule().
-+ *
-+ * The mode argument allows RT enabled kernels to differentiate a
-+ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
-+ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
-+ * optimize the AND operation out and just check for zero.
-+ */
-+#define SM_NONE 0x0
-+#define SM_PREEMPT 0x1
-+#define SM_RTLOCK_WAIT 0x2
-+
-+#ifndef CONFIG_PREEMPT_RT
-+# define SM_MASK_PREEMPT (~0U)
-+#else
-+# define SM_MASK_PREEMPT SM_PREEMPT
-+#endif
-+
-+/*
-+ * schedule() is the main scheduler function.
-+ *
-+ * The main means of driving the scheduler and thus entering this function are:
-+ *
-+ * 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
-+ *
-+ * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
-+ * paths. For example, see arch/x86/entry_64.S.
-+ *
-+ * To drive preemption between tasks, the scheduler sets the flag in timer
-+ * interrupt handler sched_tick().
-+ *
-+ * 3. Wakeups don't really cause entry into schedule(). They add a
-+ * task to the run-queue and that's it.
-+ *
-+ * Now, if the new task added to the run-queue preempts the current
-+ * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
-+ * called on the nearest possible occasion:
-+ *
-+ * - If the kernel is preemptible (CONFIG_PREEMPTION=y):
-+ *
-+ * - in syscall or exception context, at the next outmost
-+ * preempt_enable(). (this might be as soon as the wake_up()'s
-+ * spin_unlock()!)
-+ *
-+ * - in IRQ context, return from interrupt-handler to
-+ * preemptible context
-+ *
-+ * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
-+ * then at the next:
-+ *
-+ * - cond_resched() call
-+ * - explicit schedule() call
-+ * - return from syscall or exception to user-space
-+ * - return from interrupt-handler to user-space
-+ *
-+ * WARNING: must be called with preemption disabled!
-+ */
-+static void __sched notrace __schedule(unsigned int sched_mode)
-+{
-+ struct task_struct *prev, *next;
-+ unsigned long *switch_count;
-+ unsigned long prev_state;
-+ struct rq *rq;
-+ int cpu;
-+
-+ cpu = smp_processor_id();
-+ rq = cpu_rq(cpu);
-+ prev = rq->curr;
-+
-+ schedule_debug(prev, !!sched_mode);
-+
-+ /* by passing sched_feat(HRTICK) checking which Alt schedule FW doesn't support */
-+ hrtick_clear(rq);
-+
-+ local_irq_disable();
-+ rcu_note_context_switch(!!sched_mode);
-+
-+ /*
-+ * Make sure that signal_pending_state()->signal_pending() below
-+ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
-+ * done by the caller to avoid the race with signal_wake_up():
-+ *
-+ * __set_current_state(@state) signal_wake_up()
-+ * schedule() set_tsk_thread_flag(p, TIF_SIGPENDING)
-+ * wake_up_state(p, state)
-+ * LOCK rq->lock LOCK p->pi_state
-+ * smp_mb__after_spinlock() smp_mb__after_spinlock()
-+ * if (signal_pending_state()) if (p->state & @state)
-+ *
-+ * Also, the membarrier system call requires a full memory barrier
-+ * after coming from user-space, before storing to rq->curr; this
-+ * barrier matches a full barrier in the proximity of the membarrier
-+ * system call exit.
-+ */
-+ raw_spin_lock(&rq->lock);
-+ smp_mb__after_spinlock();
-+
-+ update_rq_clock(rq);
-+
-+ switch_count = &prev->nivcsw;
-+ /*
-+ * We must load prev->state once (task_struct::state is volatile), such
-+ * that we form a control dependency vs deactivate_task() below.
-+ */
-+ prev_state = READ_ONCE(prev->__state);
-+ if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
-+ if (signal_pending_state(prev_state, prev)) {
-+ WRITE_ONCE(prev->__state, TASK_RUNNING);
-+ } else {
-+ prev->sched_contributes_to_load =
-+ (prev_state & TASK_UNINTERRUPTIBLE) &&
-+ !(prev_state & TASK_NOLOAD) &&
-+ !(prev_state & TASK_FROZEN);
-+
-+ if (prev->sched_contributes_to_load)
-+ rq->nr_uninterruptible++;
-+
-+ /*
-+ * __schedule() ttwu()
-+ * prev_state = prev->state; if (p->on_rq && ...)
-+ * if (prev_state) goto out;
-+ * p->on_rq = 0; smp_acquire__after_ctrl_dep();
-+ * p->state = TASK_WAKING
-+ *
-+ * Where __schedule() and ttwu() have matching control dependencies.
-+ *
-+ * After this, schedule() must not care about p->state any more.
-+ */
-+ sched_task_deactivate(prev, rq);
-+ deactivate_task(prev, rq);
-+
-+ if (prev->in_iowait) {
-+ atomic_inc(&rq->nr_iowait);
-+ delayacct_blkio_start();
-+ }
-+ }
-+ switch_count = &prev->nvcsw;
-+ }
-+
-+ check_curr(prev, rq);
-+
-+ next = choose_next_task(rq, cpu);
-+ clear_tsk_need_resched(prev);
-+ clear_preempt_need_resched();
-+#ifdef CONFIG_SCHED_DEBUG
-+ rq->last_seen_need_resched_ns = 0;
-+#endif
-+
-+ if (likely(prev != next)) {
-+ next->last_ran = rq->clock_task;
-+
-+ /*printk(KERN_INFO "sched: %px -> %px\n", prev, next);*/
-+ rq->nr_switches++;
-+ /*
-+ * RCU users of rcu_dereference(rq->curr) may not see
-+ * changes to task_struct made by pick_next_task().
-+ */
-+ RCU_INIT_POINTER(rq->curr, next);
-+ /*
-+ * The membarrier system call requires each architecture
-+ * to have a full memory barrier after updating
-+ * rq->curr, before returning to user-space.
-+ *
-+ * Here are the schemes providing that barrier on the
-+ * various architectures:
-+ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC,
-+ * RISC-V. switch_mm() relies on membarrier_arch_switch_mm()
-+ * on PowerPC and on RISC-V.
-+ * - finish_lock_switch() for weakly-ordered
-+ * architectures where spin_unlock is a full barrier,
-+ * - switch_to() for arm64 (weakly-ordered, spin_unlock
-+ * is a RELEASE barrier),
-+ *
-+ * The barrier matches a full barrier in the proximity of
-+ * the membarrier system call entry.
-+ *
-+ * On RISC-V, this barrier pairing is also needed for the
-+ * SYNC_CORE command when switching between processes, cf.
-+ * the inline comments in membarrier_arch_switch_mm().
-+ */
-+ ++*switch_count;
-+
-+ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
-+
-+ /* Also unlocks the rq: */
-+ rq = context_switch(rq, prev, next);
-+
-+ cpu = cpu_of(rq);
-+ } else {
-+ __balance_callbacks(rq);
-+ raw_spin_unlock_irq(&rq->lock);
-+ }
-+}
-+
-+void __noreturn do_task_dead(void)
-+{
-+ /* Causes final put_task_struct in finish_task_switch(): */
-+ set_special_state(TASK_DEAD);
-+
-+ /* Tell freezer to ignore us: */
-+ current->flags |= PF_NOFREEZE;
-+
-+ __schedule(SM_NONE);
-+ BUG();
-+
-+ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
-+ for (;;)
-+ cpu_relax();
-+}
-+
-+static inline void sched_submit_work(struct task_struct *tsk)
-+{
-+ static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
-+ unsigned int task_flags;
-+
-+ /*
-+ * Establish LD_WAIT_CONFIG context to ensure none of the code called
-+ * will use a blocking primitive -- which would lead to recursion.
-+ */
-+ lock_map_acquire_try(&sched_map);
-+
-+ task_flags = tsk->flags;
-+ /*
-+ * If a worker goes to sleep, notify and ask workqueue whether it
-+ * wants to wake up a task to maintain concurrency.
-+ */
-+ if (task_flags & PF_WQ_WORKER)
-+ wq_worker_sleeping(tsk);
-+ else if (task_flags & PF_IO_WORKER)
-+ io_wq_worker_sleeping(tsk);
-+
-+ /*
-+ * spinlock and rwlock must not flush block requests. This will
-+ * deadlock if the callback attempts to acquire a lock which is
-+ * already acquired.
-+ */
-+ SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
-+
-+ /*
-+ * If we are going to sleep and we have plugged IO queued,
-+ * make sure to submit it to avoid deadlocks.
-+ */
-+ blk_flush_plug(tsk->plug, true);
-+
-+ lock_map_release(&sched_map);
-+}
-+
-+static void sched_update_worker(struct task_struct *tsk)
-+{
-+ if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
-+ if (tsk->flags & PF_BLOCK_TS)
-+ blk_plug_invalidate_ts(tsk);
-+ if (tsk->flags & PF_WQ_WORKER)
-+ wq_worker_running(tsk);
-+ else if (tsk->flags & PF_IO_WORKER)
-+ io_wq_worker_running(tsk);
-+ }
-+}
-+
-+static __always_inline void __schedule_loop(unsigned int sched_mode)
-+{
-+ do {
-+ preempt_disable();
-+ __schedule(sched_mode);
-+ sched_preempt_enable_no_resched();
-+ } while (need_resched());
-+}
-+
-+asmlinkage __visible void __sched schedule(void)
-+{
-+ struct task_struct *tsk = current;
-+
-+#ifdef CONFIG_RT_MUTEXES
-+ lockdep_assert(!tsk->sched_rt_mutex);
-+#endif
-+
-+ if (!task_is_running(tsk))
-+ sched_submit_work(tsk);
-+ __schedule_loop(SM_NONE);
-+ sched_update_worker(tsk);
-+}
-+EXPORT_SYMBOL(schedule);
-+
-+/*
-+ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
-+ * state (have scheduled out non-voluntarily) by making sure that all
-+ * tasks have either left the run queue or have gone into user space.
-+ * As idle tasks do not do either, they must not ever be preempted
-+ * (schedule out non-voluntarily).
-+ *
-+ * schedule_idle() is similar to schedule_preempt_disable() except that it
-+ * never enables preemption because it does not call sched_submit_work().
-+ */
-+void __sched schedule_idle(void)
-+{
-+ /*
-+ * As this skips calling sched_submit_work(), which the idle task does
-+ * regardless because that function is a nop when the task is in a
-+ * TASK_RUNNING state, make sure this isn't used someplace that the
-+ * current task can be in any other state. Note, idle is always in the
-+ * TASK_RUNNING state.
-+ */
-+ WARN_ON_ONCE(current->__state);
-+ do {
-+ __schedule(SM_NONE);
-+ } while (need_resched());
-+}
-+
-+#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK)
-+asmlinkage __visible void __sched schedule_user(void)
-+{
-+ /*
-+ * If we come here after a random call to set_need_resched(),
-+ * or we have been woken up remotely but the IPI has not yet arrived,
-+ * we haven't yet exited the RCU idle mode. Do it here manually until
-+ * we find a better solution.
-+ *
-+ * NB: There are buggy callers of this function. Ideally we
-+ * should warn if prev_state != CONTEXT_USER, but that will trigger
-+ * too frequently to make sense yet.
-+ */
-+ enum ctx_state prev_state = exception_enter();
-+ schedule();
-+ exception_exit(prev_state);
-+}
-+#endif
-+
-+/**
-+ * schedule_preempt_disabled - called with preemption disabled
-+ *
-+ * Returns with preemption disabled. Note: preempt_count must be 1
-+ */
-+void __sched schedule_preempt_disabled(void)
-+{
-+ sched_preempt_enable_no_resched();
-+ schedule();
-+ preempt_disable();
-+}
-+
-+#ifdef CONFIG_PREEMPT_RT
-+void __sched notrace schedule_rtlock(void)
-+{
-+ __schedule_loop(SM_RTLOCK_WAIT);
-+}
-+NOKPROBE_SYMBOL(schedule_rtlock);
-+#endif
-+
-+static void __sched notrace preempt_schedule_common(void)
-+{
-+ do {
-+ /*
-+ * Because the function tracer can trace preempt_count_sub()
-+ * and it also uses preempt_enable/disable_notrace(), if
-+ * NEED_RESCHED is set, the preempt_enable_notrace() called
-+ * by the function tracer will call this function again and
-+ * cause infinite recursion.
-+ *
-+ * Preemption must be disabled here before the function
-+ * tracer can trace. Break up preempt_disable() into two
-+ * calls. One to disable preemption without fear of being
-+ * traced. The other to still record the preemption latency,
-+ * which can also be traced by the function tracer.
-+ */
-+ preempt_disable_notrace();
-+ preempt_latency_start(1);
-+ __schedule(SM_PREEMPT);
-+ preempt_latency_stop(1);
-+ preempt_enable_no_resched_notrace();
-+
-+ /*
-+ * Check again in case we missed a preemption opportunity
-+ * between schedule and now.
-+ */
-+ } while (need_resched());
-+}
-+
-+#ifdef CONFIG_PREEMPTION
-+/*
-+ * This is the entry point to schedule() from in-kernel preemption
-+ * off of preempt_enable.
-+ */
-+asmlinkage __visible void __sched notrace preempt_schedule(void)
-+{
-+ /*
-+ * If there is a non-zero preempt_count or interrupts are disabled,
-+ * we do not want to preempt the current task. Just return..
-+ */
-+ if (likely(!preemptible()))
-+ return;
-+
-+ preempt_schedule_common();
-+}
-+NOKPROBE_SYMBOL(preempt_schedule);
-+EXPORT_SYMBOL(preempt_schedule);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#ifndef preempt_schedule_dynamic_enabled
-+#define preempt_schedule_dynamic_enabled preempt_schedule
-+#define preempt_schedule_dynamic_disabled NULL
-+#endif
-+DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
-+EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
-+void __sched notrace dynamic_preempt_schedule(void)
-+{
-+ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
-+ return;
-+ preempt_schedule();
-+}
-+NOKPROBE_SYMBOL(dynamic_preempt_schedule);
-+EXPORT_SYMBOL(dynamic_preempt_schedule);
-+#endif
-+#endif
-+
-+/**
-+ * preempt_schedule_notrace - preempt_schedule called by tracing
-+ *
-+ * The tracing infrastructure uses preempt_enable_notrace to prevent
-+ * recursion and tracing preempt enabling caused by the tracing
-+ * infrastructure itself. But as tracing can happen in areas coming
-+ * from userspace or just about to enter userspace, a preempt enable
-+ * can occur before user_exit() is called. This will cause the scheduler
-+ * to be called when the system is still in usermode.
-+ *
-+ * To prevent this, the preempt_enable_notrace will use this function
-+ * instead of preempt_schedule() to exit user context if needed before
-+ * calling the scheduler.
-+ */
-+asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
-+{
-+ enum ctx_state prev_ctx;
-+
-+ if (likely(!preemptible()))
-+ return;
-+
-+ do {
-+ /*
-+ * Because the function tracer can trace preempt_count_sub()
-+ * and it also uses preempt_enable/disable_notrace(), if
-+ * NEED_RESCHED is set, the preempt_enable_notrace() called
-+ * by the function tracer will call this function again and
-+ * cause infinite recursion.
-+ *
-+ * Preemption must be disabled here before the function
-+ * tracer can trace. Break up preempt_disable() into two
-+ * calls. One to disable preemption without fear of being
-+ * traced. The other to still record the preemption latency,
-+ * which can also be traced by the function tracer.
-+ */
-+ preempt_disable_notrace();
-+ preempt_latency_start(1);
-+ /*
-+ * Needs preempt disabled in case user_exit() is traced
-+ * and the tracer calls preempt_enable_notrace() causing
-+ * an infinite recursion.
-+ */
-+ prev_ctx = exception_enter();
-+ __schedule(SM_PREEMPT);
-+ exception_exit(prev_ctx);
-+
-+ preempt_latency_stop(1);
-+ preempt_enable_no_resched_notrace();
-+ } while (need_resched());
-+}
-+EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#ifndef preempt_schedule_notrace_dynamic_enabled
-+#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace
-+#define preempt_schedule_notrace_dynamic_disabled NULL
-+#endif
-+DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
-+EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
-+void __sched notrace dynamic_preempt_schedule_notrace(void)
-+{
-+ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
-+ return;
-+ preempt_schedule_notrace();
-+}
-+NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
-+EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
-+#endif
-+#endif
-+
-+#endif /* CONFIG_PREEMPTION */
-+
-+/*
-+ * This is the entry point to schedule() from kernel preemption
-+ * off of irq context.
-+ * Note, that this is called and return with irqs disabled. This will
-+ * protect us against recursive calling from irq.
-+ */
-+asmlinkage __visible void __sched preempt_schedule_irq(void)
-+{
-+ enum ctx_state prev_state;
-+
-+ /* Catch callers which need to be fixed */
-+ BUG_ON(preempt_count() || !irqs_disabled());
-+
-+ prev_state = exception_enter();
-+
-+ do {
-+ preempt_disable();
-+ local_irq_enable();
-+ __schedule(SM_PREEMPT);
-+ local_irq_disable();
-+ sched_preempt_enable_no_resched();
-+ } while (need_resched());
-+
-+ exception_exit(prev_state);
-+}
-+
-+int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
-+ void *key)
-+{
-+ WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
-+ return try_to_wake_up(curr->private, mode, wake_flags);
-+}
-+EXPORT_SYMBOL(default_wake_function);
-+
-+static inline void check_task_changed(struct task_struct *p, struct rq *rq)
-+{
-+ /* Trigger resched if task sched_prio has been modified. */
-+ if (task_on_rq_queued(p)) {
-+ update_rq_clock(rq);
-+ requeue_task(p, rq);
-+ wakeup_preempt(rq);
-+ }
-+}
-+
-+static void __setscheduler_prio(struct task_struct *p, int prio)
-+{
-+ p->prio = prio;
-+}
-+
-+#ifdef CONFIG_RT_MUTEXES
-+
-+/*
-+ * Would be more useful with typeof()/auto_type but they don't mix with
-+ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
-+ * name such that if someone were to implement this function we get to compare
-+ * notes.
-+ */
-+#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
-+
-+void rt_mutex_pre_schedule(void)
-+{
-+ lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
-+ sched_submit_work(current);
-+}
-+
-+void rt_mutex_schedule(void)
-+{
-+ lockdep_assert(current->sched_rt_mutex);
-+ __schedule_loop(SM_NONE);
-+}
-+
-+void rt_mutex_post_schedule(void)
-+{
-+ sched_update_worker(current);
-+ lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
-+}
-+
-+static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
-+{
-+ if (pi_task)
-+ prio = min(prio, pi_task->prio);
-+
-+ return prio;
-+}
-+
-+static inline int rt_effective_prio(struct task_struct *p, int prio)
-+{
-+ struct task_struct *pi_task = rt_mutex_get_top_task(p);
-+
-+ return __rt_effective_prio(pi_task, prio);
-+}
-+
-+/*
-+ * rt_mutex_setprio - set the current priority of a task
-+ * @p: task to boost
-+ * @pi_task: donor task
-+ *
-+ * This function changes the 'effective' priority of a task. It does
-+ * not touch ->normal_prio like __setscheduler().
-+ *
-+ * Used by the rt_mutex code to implement priority inheritance
-+ * logic. Call site only calls if the priority of the task changed.
-+ */
-+void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
-+{
-+ int prio;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ /* XXX used to be waiter->prio, not waiter->task->prio */
-+ prio = __rt_effective_prio(pi_task, p->normal_prio);
-+
-+ /*
-+ * If nothing changed; bail early.
-+ */
-+ if (p->pi_top_task == pi_task && prio == p->prio)
-+ return;
-+
-+ rq = __task_access_lock(p, &lock);
-+ /*
-+ * Set under pi_lock && rq->lock, such that the value can be used under
-+ * either lock.
-+ *
-+ * Note that there is loads of tricky to make this pointer cache work
-+ * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
-+ * ensure a task is de-boosted (pi_task is set to NULL) before the
-+ * task is allowed to run again (and can exit). This ensures the pointer
-+ * points to a blocked task -- which guarantees the task is present.
-+ */
-+ p->pi_top_task = pi_task;
-+
-+ /*
-+ * For FIFO/RR we only need to set prio, if that matches we're done.
-+ */
-+ if (prio == p->prio)
-+ goto out_unlock;
-+
-+ /*
-+ * Idle task boosting is a nono in general. There is one
-+ * exception, when PREEMPT_RT and NOHZ is active:
-+ *
-+ * The idle task calls get_next_timer_interrupt() and holds
-+ * the timer wheel base->lock on the CPU and another CPU wants
-+ * to access the timer (probably to cancel it). We can safely
-+ * ignore the boosting request, as the idle CPU runs this code
-+ * with interrupts disabled and will complete the lock
-+ * protected section without being interrupted. So there is no
-+ * real need to boost.
-+ */
-+ if (unlikely(p == rq->idle)) {
-+ WARN_ON(p != rq->curr);
-+ WARN_ON(p->pi_blocked_on);
-+ goto out_unlock;
-+ }
-+
-+ trace_sched_pi_setprio(p, pi_task);
-+
-+ __setscheduler_prio(p, prio);
-+
-+ check_task_changed(p, rq);
-+out_unlock:
-+ /* Avoid rq from going away on us: */
-+ preempt_disable();
-+
-+ if (task_on_rq_queued(p))
-+ __balance_callbacks(rq);
-+ __task_access_unlock(p, lock);
-+
-+ preempt_enable();
-+}
-+#else
-+static inline int rt_effective_prio(struct task_struct *p, int prio)
-+{
-+ return prio;
-+}
-+#endif
-+
-+void set_user_nice(struct task_struct *p, long nice)
-+{
-+ unsigned long flags;
-+ struct rq *rq;
-+ raw_spinlock_t *lock;
-+
-+ if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
-+ return;
-+ /*
-+ * We have to be careful, if called from sys_setpriority(),
-+ * the task might be in the middle of scheduling on another CPU.
-+ */
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+ rq = __task_access_lock(p, &lock);
-+
-+ p->static_prio = NICE_TO_PRIO(nice);
-+ /*
-+ * The RT priorities are set via sched_setscheduler(), but we still
-+ * allow the 'normal' nice value to be set - but as expected
-+ * it won't have any effect on scheduling until the task is
-+ * not SCHED_NORMAL/SCHED_BATCH:
-+ */
-+ if (task_has_rt_policy(p))
-+ goto out_unlock;
-+
-+ p->prio = effective_prio(p);
-+
-+ check_task_changed(p, rq);
-+out_unlock:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+}
-+EXPORT_SYMBOL(set_user_nice);
-+
-+/*
-+ * is_nice_reduction - check if nice value is an actual reduction
-+ *
-+ * Similar to can_nice() but does not perform a capability check.
-+ *
-+ * @p: task
-+ * @nice: nice value
-+ */
-+static bool is_nice_reduction(const struct task_struct *p, const int nice)
-+{
-+ /* Convert nice value [19,-20] to rlimit style value [1,40]: */
-+ int nice_rlim = nice_to_rlimit(nice);
-+
-+ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));
-+}
-+
-+/*
-+ * can_nice - check if a task can reduce its nice value
-+ * @p: task
-+ * @nice: nice value
-+ */
-+int can_nice(const struct task_struct *p, const int nice)
-+{
-+ return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);
-+}
-+
-+#ifdef __ARCH_WANT_SYS_NICE
-+
-+/*
-+ * sys_nice - change the priority of the current process.
-+ * @increment: priority increment
-+ *
-+ * sys_setpriority is a more generic, but much slower function that
-+ * does similar things.
-+ */
-+SYSCALL_DEFINE1(nice, int, increment)
-+{
-+ long nice, retval;
-+
-+ /*
-+ * Setpriority might change our priority at the same moment.
-+ * We don't have to worry. Conceptually one call occurs first
-+ * and we have a single winner.
-+ */
-+
-+ increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
-+ nice = task_nice(current) + increment;
-+
-+ nice = clamp_val(nice, MIN_NICE, MAX_NICE);
-+ if (increment < 0 && !can_nice(current, nice))
-+ return -EPERM;
-+
-+ retval = security_task_setnice(current, nice);
-+ if (retval)
-+ return retval;
-+
-+ set_user_nice(current, nice);
-+ return 0;
-+}
-+
-+#endif
-+
-+/**
-+ * task_prio - return the priority value of a given task.
-+ * @p: the task in question.
-+ *
-+ * Return: The priority value as seen by users in /proc.
-+ *
-+ * sched policy return value kernel prio user prio/nice
-+ *
-+ * (BMQ)normal, batch, idle[0 ... 53] [100 ... 139] 0/[-20 ... 19]/[-7 ... 7]
-+ * (PDS)normal, batch, idle[0 ... 39] 100 0/[-20 ... 19]
-+ * fifo, rr [-1 ... -100] [99 ... 0] [0 ... 99]
-+ */
-+int task_prio(const struct task_struct *p)
-+{
-+ return (p->prio < MAX_RT_PRIO) ? p->prio - MAX_RT_PRIO :
-+ task_sched_prio_normal(p, task_rq(p));
-+}
-+
-+/**
-+ * idle_cpu - is a given CPU idle currently?
-+ * @cpu: the processor in question.
-+ *
-+ * Return: 1 if the CPU is currently idle. 0 otherwise.
-+ */
-+int idle_cpu(int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ if (rq->curr != rq->idle)
-+ return 0;
-+
-+ if (rq->nr_running)
-+ return 0;
-+
-+#ifdef CONFIG_SMP
-+ if (rq->ttwu_pending)
-+ return 0;
-+#endif
-+
-+ return 1;
-+}
-+
-+/**
-+ * idle_task - return the idle task for a given CPU.
-+ * @cpu: the processor in question.
-+ *
-+ * Return: The idle task for the cpu @cpu.
-+ */
-+struct task_struct *idle_task(int cpu)
-+{
-+ return cpu_rq(cpu)->idle;
-+}
-+
-+/**
-+ * find_process_by_pid - find a process with a matching PID value.
-+ * @pid: the pid in question.
-+ *
-+ * The task of @pid, if found. %NULL otherwise.
-+ */
-+static inline struct task_struct *find_process_by_pid(pid_t pid)
-+{
-+ return pid ? find_task_by_vpid(pid) : current;
-+}
-+
-+static struct task_struct *find_get_task(pid_t pid)
-+{
-+ struct task_struct *p;
-+ guard(rcu)();
-+
-+ p = find_process_by_pid(pid);
-+ if (likely(p))
-+ get_task_struct(p);
-+
-+ return p;
-+}
-+
-+DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
-+ find_get_task(pid), pid_t pid)
-+
-+/*
-+ * sched_setparam() passes in -1 for its policy, to let the functions
-+ * it calls know not to change it.
-+ */
-+#define SETPARAM_POLICY -1
-+
-+static void __setscheduler_params(struct task_struct *p,
-+ const struct sched_attr *attr)
-+{
-+ int policy = attr->sched_policy;
-+
-+ if (policy == SETPARAM_POLICY)
-+ policy = p->policy;
-+
-+ p->policy = policy;
-+
-+ /*
-+ * allow normal nice value to be set, but will not have any
-+ * effect on scheduling until the task not SCHED_NORMAL/
-+ * SCHED_BATCH
-+ */
-+ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
-+
-+ /*
-+ * __sched_setscheduler() ensures attr->sched_priority == 0 when
-+ * !rt_policy. Always setting this ensures that things like
-+ * getparam()/getattr() don't report silly values for !rt tasks.
-+ */
-+ p->rt_priority = attr->sched_priority;
-+ p->normal_prio = normal_prio(p);
-+}
-+
-+/*
-+ * check the target process has a UID that matches the current process's
-+ */
-+static bool check_same_owner(struct task_struct *p)
-+{
-+ const struct cred *cred = current_cred(), *pcred;
-+ guard(rcu)();
-+
-+ pcred = __task_cred(p);
-+ return (uid_eq(cred->euid, pcred->euid) ||
-+ uid_eq(cred->euid, pcred->uid));
-+}
-+
-+/*
-+ * Allow unprivileged RT tasks to decrease priority.
-+ * Only issue a capable test if needed and only once to avoid an audit
-+ * event on permitted non-privileged operations:
-+ */
-+static int user_check_sched_setscheduler(struct task_struct *p,
-+ const struct sched_attr *attr,
-+ int policy, int reset_on_fork)
-+{
-+ if (rt_policy(policy)) {
-+ unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
-+
-+ /* Can't set/change the rt policy: */
-+ if (policy != p->policy && !rlim_rtprio)
-+ goto req_priv;
-+
-+ /* Can't increase priority: */
-+ if (attr->sched_priority > p->rt_priority &&
-+ attr->sched_priority > rlim_rtprio)
-+ goto req_priv;
-+ }
-+
-+ /* Can't change other user's priorities: */
-+ if (!check_same_owner(p))
-+ goto req_priv;
-+
-+ /* Normal users shall not reset the sched_reset_on_fork flag: */
-+ if (p->sched_reset_on_fork && !reset_on_fork)
-+ goto req_priv;
-+
-+ return 0;
-+
-+req_priv:
-+ if (!capable(CAP_SYS_NICE))
-+ return -EPERM;
-+
-+ return 0;
-+}
-+
-+static int __sched_setscheduler(struct task_struct *p,
-+ const struct sched_attr *attr,
-+ bool user, bool pi)
-+{
-+ const struct sched_attr dl_squash_attr = {
-+ .size = sizeof(struct sched_attr),
-+ .sched_policy = SCHED_FIFO,
-+ .sched_nice = 0,
-+ .sched_priority = 99,
-+ };
-+ int oldpolicy = -1, policy = attr->sched_policy;
-+ int retval, newprio;
-+ struct balance_callback *head;
-+ unsigned long flags;
-+ struct rq *rq;
-+ int reset_on_fork;
-+ raw_spinlock_t *lock;
-+
-+ /* The pi code expects interrupts enabled */
-+ BUG_ON(pi && in_interrupt());
-+
-+ /*
-+ * Alt schedule FW supports SCHED_DEADLINE by squash it as prio 0 SCHED_FIFO
-+ */
-+ if (unlikely(SCHED_DEADLINE == policy)) {
-+ attr = &dl_squash_attr;
-+ policy = attr->sched_policy;
-+ }
-+recheck:
-+ /* Double check policy once rq lock held */
-+ if (policy < 0) {
-+ reset_on_fork = p->sched_reset_on_fork;
-+ policy = oldpolicy = p->policy;
-+ } else {
-+ reset_on_fork = !!(attr->sched_flags & SCHED_RESET_ON_FORK);
-+
-+ if (policy > SCHED_IDLE)
-+ return -EINVAL;
-+ }
-+
-+ if (attr->sched_flags & ~(SCHED_FLAG_ALL))
-+ return -EINVAL;
-+
-+ /*
-+ * Valid priorities for SCHED_FIFO and SCHED_RR are
-+ * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL and
-+ * SCHED_BATCH and SCHED_IDLE is 0.
-+ */
-+ if (attr->sched_priority < 0 ||
-+ (p->mm && attr->sched_priority > MAX_RT_PRIO - 1) ||
-+ (!p->mm && attr->sched_priority > MAX_RT_PRIO - 1))
-+ return -EINVAL;
-+ if ((SCHED_RR == policy || SCHED_FIFO == policy) !=
-+ (attr->sched_priority != 0))
-+ return -EINVAL;
-+
-+ if (user) {
-+ retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork);
-+ if (retval)
-+ return retval;
-+
-+ retval = security_task_setscheduler(p);
-+ if (retval)
-+ return retval;
-+ }
-+
-+ /*
-+ * Make sure no PI-waiters arrive (or leave) while we are
-+ * changing the priority of the task:
-+ */
-+ raw_spin_lock_irqsave(&p->pi_lock, flags);
-+
-+ /*
-+ * To be able to change p->policy safely, task_access_lock()
-+ * must be called.
-+ * IF use task_access_lock() here:
-+ * For the task p which is not running, reading rq->stop is
-+ * racy but acceptable as ->stop doesn't change much.
-+ * An enhancemnet can be made to read rq->stop saftly.
-+ */
-+ rq = __task_access_lock(p, &lock);
-+
-+ /*
-+ * Changing the policy of the stop threads its a very bad idea
-+ */
-+ if (p == rq->stop) {
-+ retval = -EINVAL;
-+ goto unlock;
-+ }
-+
-+ /*
-+ * If not changing anything there's no need to proceed further:
-+ */
-+ if (unlikely(policy == p->policy)) {
-+ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
-+ goto change;
-+ if (!rt_policy(policy) &&
-+ NICE_TO_PRIO(attr->sched_nice) != p->static_prio)
-+ goto change;
-+
-+ p->sched_reset_on_fork = reset_on_fork;
-+ retval = 0;
-+ goto unlock;
-+ }
-+change:
-+
-+ /* Re-check policy now with rq lock held */
-+ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
-+ policy = oldpolicy = -1;
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+ goto recheck;
-+ }
-+
-+ p->sched_reset_on_fork = reset_on_fork;
-+
-+ newprio = __normal_prio(policy, attr->sched_priority, NICE_TO_PRIO(attr->sched_nice));
-+ if (pi) {
-+ /*
-+ * Take priority boosted tasks into account. If the new
-+ * effective priority is unchanged, we just store the new
-+ * normal parameters and do not touch the scheduler class and
-+ * the runqueue. This will be done when the task deboost
-+ * itself.
-+ */
-+ newprio = rt_effective_prio(p, newprio);
-+ }
-+
-+ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
-+ __setscheduler_params(p, attr);
-+ __setscheduler_prio(p, newprio);
-+ }
-+
-+ check_task_changed(p, rq);
-+
-+ /* Avoid rq from going away on us: */
-+ preempt_disable();
-+ head = splice_balance_callbacks(rq);
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+
-+ if (pi)
-+ rt_mutex_adjust_pi(p);
-+
-+ /* Run balance callbacks after we've adjusted the PI chain: */
-+ balance_callbacks(rq, head);
-+ preempt_enable();
-+
-+ return 0;
-+
-+unlock:
-+ __task_access_unlock(p, lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
-+ return retval;
-+}
-+
-+static int _sched_setscheduler(struct task_struct *p, int policy,
-+ const struct sched_param *param, bool check)
-+{
-+ struct sched_attr attr = {
-+ .sched_policy = policy,
-+ .sched_priority = param->sched_priority,
-+ .sched_nice = PRIO_TO_NICE(p->static_prio),
-+ };
-+
-+ /* Fixup the legacy SCHED_RESET_ON_FORK hack. */
-+ if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
-+ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-+ policy &= ~SCHED_RESET_ON_FORK;
-+ attr.sched_policy = policy;
-+ }
-+
-+ return __sched_setscheduler(p, &attr, check, true);
-+}
-+
-+/**
-+ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
-+ * @p: the task in question.
-+ * @policy: new policy.
-+ * @param: structure containing the new RT priority.
-+ *
-+ * Use sched_set_fifo(), read its comment.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ *
-+ * NOTE that the task may be already dead.
-+ */
-+int sched_setscheduler(struct task_struct *p, int policy,
-+ const struct sched_param *param)
-+{
-+ return _sched_setscheduler(p, policy, param, true);
-+}
-+
-+int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
-+{
-+ return __sched_setscheduler(p, attr, true, true);
-+}
-+
-+int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
-+{
-+ return __sched_setscheduler(p, attr, false, true);
-+}
-+EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
-+
-+/**
-+ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
-+ * @p: the task in question.
-+ * @policy: new policy.
-+ * @param: structure containing the new RT priority.
-+ *
-+ * Just like sched_setscheduler, only don't bother checking if the
-+ * current context has permission. For example, this is needed in
-+ * stop_machine(): we create temporary high priority worker threads,
-+ * but our caller might not have that capability.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ */
-+int sched_setscheduler_nocheck(struct task_struct *p, int policy,
-+ const struct sched_param *param)
-+{
-+ return _sched_setscheduler(p, policy, param, false);
-+}
-+
-+/*
-+ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
-+ * incapable of resource management, which is the one thing an OS really should
-+ * be doing.
-+ *
-+ * This is of course the reason it is limited to privileged users only.
-+ *
-+ * Worse still; it is fundamentally impossible to compose static priority
-+ * workloads. You cannot take two correctly working static prio workloads
-+ * and smash them together and still expect them to work.
-+ *
-+ * For this reason 'all' FIFO tasks the kernel creates are basically at:
-+ *
-+ * MAX_RT_PRIO / 2
-+ *
-+ * The administrator _MUST_ configure the system, the kernel simply doesn't
-+ * know enough information to make a sensible choice.
-+ */
-+void sched_set_fifo(struct task_struct *p)
-+{
-+ struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
-+ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
-+}
-+EXPORT_SYMBOL_GPL(sched_set_fifo);
-+
-+/*
-+ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
-+ */
-+void sched_set_fifo_low(struct task_struct *p)
-+{
-+ struct sched_param sp = { .sched_priority = 1 };
-+ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
-+}
-+EXPORT_SYMBOL_GPL(sched_set_fifo_low);
-+
-+void sched_set_normal(struct task_struct *p, int nice)
-+{
-+ struct sched_attr attr = {
-+ .sched_policy = SCHED_NORMAL,
-+ .sched_nice = nice,
-+ };
-+ WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
-+}
-+EXPORT_SYMBOL_GPL(sched_set_normal);
-+
-+static int
-+do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
-+{
-+ struct sched_param lparam;
-+
-+ if (!param || pid < 0)
-+ return -EINVAL;
-+ if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
-+ return -EFAULT;
-+
-+ CLASS(find_get_task, p)(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ return sched_setscheduler(p, policy, &lparam);
-+}
-+
-+/*
-+ * Mimics kernel/events/core.c perf_copy_attr().
-+ */
-+static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
-+{
-+ u32 size;
-+ int ret;
-+
-+ /* Zero the full structure, so that a short copy will be nice: */
-+ memset(attr, 0, sizeof(*attr));
-+
-+ ret = get_user(size, &uattr->size);
-+ if (ret)
-+ return ret;
-+
-+ /* ABI compatibility quirk: */
-+ if (!size)
-+ size = SCHED_ATTR_SIZE_VER0;
-+
-+ if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
-+ goto err_size;
-+
-+ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
-+ if (ret) {
-+ if (ret == -E2BIG)
-+ goto err_size;
-+ return ret;
-+ }
-+
-+ /*
-+ * XXX: Do we want to be lenient like existing syscalls; or do we want
-+ * to be strict and return an error on out-of-bounds values?
-+ */
-+ attr->sched_nice = clamp(attr->sched_nice, -20, 19);
-+
-+ /* sched/core.c uses zero here but we already know ret is zero */
-+ return 0;
-+
-+err_size:
-+ put_user(sizeof(*attr), &uattr->size);
-+ return -E2BIG;
-+}
-+
-+/**
-+ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
-+ * @pid: the pid in question.
-+ * @policy: new policy.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ * @param: structure containing the new RT priority.
-+ */
-+SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
-+{
-+ if (policy < 0)
-+ return -EINVAL;
-+
-+ return do_sched_setscheduler(pid, policy, param);
-+}
-+
-+/**
-+ * sys_sched_setparam - set/change the RT priority of a thread
-+ * @pid: the pid in question.
-+ * @param: structure containing the new RT priority.
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ */
-+SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
-+{
-+ return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
-+}
-+
-+static void get_params(struct task_struct *p, struct sched_attr *attr)
-+{
-+ if (task_has_rt_policy(p))
-+ attr->sched_priority = p->rt_priority;
-+ else
-+ attr->sched_nice = task_nice(p);
-+}
-+
-+/**
-+ * sys_sched_setattr - same as above, but with extended sched_attr
-+ * @pid: the pid in question.
-+ * @uattr: structure containing the extended parameters.
-+ */
-+SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
-+ unsigned int, flags)
-+{
-+ struct sched_attr attr;
-+ int retval;
-+
-+ if (!uattr || pid < 0 || flags)
-+ return -EINVAL;
-+
-+ retval = sched_copy_attr(uattr, &attr);
-+ if (retval)
-+ return retval;
-+
-+ if ((int)attr.sched_policy < 0)
-+ return -EINVAL;
-+
-+ CLASS(find_get_task, p)(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
-+ get_params(p, &attr);
-+
-+ return sched_setattr(p, &attr);
-+}
-+
-+/**
-+ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
-+ * @pid: the pid in question.
-+ *
-+ * Return: On success, the policy of the thread. Otherwise, a negative error
-+ * code.
-+ */
-+SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
-+{
-+ struct task_struct *p;
-+ int retval = -EINVAL;
-+
-+ if (pid < 0)
-+ return -ESRCH;
-+
-+ guard(rcu)();
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ retval = security_task_getscheduler(p);
-+ if (!retval)
-+ retval = p->policy;
-+
-+ return retval;
-+}
-+
-+/**
-+ * sys_sched_getscheduler - get the RT priority of a thread
-+ * @pid: the pid in question.
-+ * @param: structure containing the RT priority.
-+ *
-+ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
-+ * code.
-+ */
-+SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
-+{
-+ struct sched_param lp = { .sched_priority = 0 };
-+ struct task_struct *p;
-+
-+ if (!param || pid < 0)
-+ return -EINVAL;
-+
-+ scoped_guard (rcu) {
-+ int retval;
-+
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -EINVAL;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ if (task_has_rt_policy(p))
-+ lp.sched_priority = p->rt_priority;
-+ }
-+
-+ /*
-+ * This one might sleep, we cannot do it with a spinlock held ...
-+ */
-+ return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
-+}
-+
-+/*
-+ * Copy the kernel size attribute structure (which might be larger
-+ * than what user-space knows about) to user-space.
-+ *
-+ * Note that all cases are valid: user-space buffer can be larger or
-+ * smaller than the kernel-space buffer. The usual case is that both
-+ * have the same size.
-+ */
-+static int
-+sched_attr_copy_to_user(struct sched_attr __user *uattr,
-+ struct sched_attr *kattr,
-+ unsigned int usize)
-+{
-+ unsigned int ksize = sizeof(*kattr);
-+
-+ if (!access_ok(uattr, usize))
-+ return -EFAULT;
-+
-+ /*
-+ * sched_getattr() ABI forwards and backwards compatibility:
-+ *
-+ * If usize == ksize then we just copy everything to user-space and all is good.
-+ *
-+ * If usize < ksize then we only copy as much as user-space has space for,
-+ * this keeps ABI compatibility as well. We skip the rest.
-+ *
-+ * If usize > ksize then user-space is using a newer version of the ABI,
-+ * which part the kernel doesn't know about. Just ignore it - tooling can
-+ * detect the kernel's knowledge of attributes from the attr->size value
-+ * which is set to ksize in this case.
-+ */
-+ kattr->size = min(usize, ksize);
-+
-+ if (copy_to_user(uattr, kattr, kattr->size))
-+ return -EFAULT;
-+
-+ return 0;
-+}
-+
-+/**
-+ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
-+ * @pid: the pid in question.
-+ * @uattr: structure containing the extended parameters.
-+ * @usize: sizeof(attr) for fwd/bwd comp.
-+ * @flags: for future extension.
-+ */
-+SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
-+ unsigned int, usize, unsigned int, flags)
-+{
-+ struct sched_attr kattr = { };
-+ struct task_struct *p;
-+ int retval;
-+
-+ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
-+ usize < SCHED_ATTR_SIZE_VER0 || flags)
-+ return -EINVAL;
-+
-+ scoped_guard (rcu) {
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ kattr.sched_policy = p->policy;
-+ if (p->sched_reset_on_fork)
-+ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
-+ get_params(p, &kattr);
-+ kattr.sched_flags &= SCHED_FLAG_ALL;
-+
-+#ifdef CONFIG_UCLAMP_TASK
-+ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
-+ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
-+#endif
-+ }
-+
-+ return sched_attr_copy_to_user(uattr, &kattr, usize);
-+}
-+
-+#ifdef CONFIG_SMP
-+int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
-+{
-+ return 0;
-+}
-+#endif
-+
-+static int
-+__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
-+{
-+ int retval;
-+ cpumask_var_t cpus_allowed, new_mask;
-+
-+ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
-+ return -ENOMEM;
-+
-+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
-+ retval = -ENOMEM;
-+ goto out_free_cpus_allowed;
-+ }
-+
-+ cpuset_cpus_allowed(p, cpus_allowed);
-+ cpumask_and(new_mask, ctx->new_mask, cpus_allowed);
-+
-+ ctx->new_mask = new_mask;
-+ ctx->flags |= SCA_CHECK;
-+
-+ retval = __set_cpus_allowed_ptr(p, ctx);
-+ if (retval)
-+ goto out_free_new_mask;
-+
-+ cpuset_cpus_allowed(p, cpus_allowed);
-+ if (!cpumask_subset(new_mask, cpus_allowed)) {
-+ /*
-+ * We must have raced with a concurrent cpuset
-+ * update. Just reset the cpus_allowed to the
-+ * cpuset's cpus_allowed
-+ */
-+ cpumask_copy(new_mask, cpus_allowed);
-+
-+ /*
-+ * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr()
-+ * will restore the previous user_cpus_ptr value.
-+ *
-+ * In the unlikely event a previous user_cpus_ptr exists,
-+ * we need to further restrict the mask to what is allowed
-+ * by that old user_cpus_ptr.
-+ */
-+ if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) {
-+ bool empty = !cpumask_and(new_mask, new_mask,
-+ ctx->user_mask);
-+
-+ if (WARN_ON_ONCE(empty))
-+ cpumask_copy(new_mask, cpus_allowed);
-+ }
-+ __set_cpus_allowed_ptr(p, ctx);
-+ retval = -EINVAL;
-+ }
-+
-+out_free_new_mask:
-+ free_cpumask_var(new_mask);
-+out_free_cpus_allowed:
-+ free_cpumask_var(cpus_allowed);
-+ return retval;
-+}
-+
-+long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
-+{
-+ struct affinity_context ac;
-+ struct cpumask *user_mask;
-+ int retval;
-+
-+ CLASS(find_get_task, p)(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ if (p->flags & PF_NO_SETAFFINITY)
-+ return -EINVAL;
-+
-+ if (!check_same_owner(p)) {
-+ guard(rcu)();
-+ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
-+ return -EPERM;
-+ }
-+
-+ retval = security_task_setscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ /*
-+ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
-+ * alloc_user_cpus_ptr() returns NULL.
-+ */
-+ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
-+ if (user_mask) {
-+ cpumask_copy(user_mask, in_mask);
-+ } else if (IS_ENABLED(CONFIG_SMP)) {
-+ return -ENOMEM;
-+ }
-+
-+ ac = (struct affinity_context){
-+ .new_mask = in_mask,
-+ .user_mask = user_mask,
-+ .flags = SCA_USER,
-+ };
-+
-+ retval = __sched_setaffinity(p, &ac);
-+ kfree(ac.user_mask);
-+
-+ return retval;
-+}
-+
-+static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
-+ struct cpumask *new_mask)
-+{
-+ if (len < cpumask_size())
-+ cpumask_clear(new_mask);
-+ else if (len > cpumask_size())
-+ len = cpumask_size();
-+
-+ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
-+}
-+
-+/**
-+ * sys_sched_setaffinity - set the CPU affinity of a process
-+ * @pid: pid of the process
-+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
-+ * @user_mask_ptr: user-space pointer to the new CPU mask
-+ *
-+ * Return: 0 on success. An error code otherwise.
-+ */
-+SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
-+ unsigned long __user *, user_mask_ptr)
-+{
-+ cpumask_var_t new_mask;
-+ int retval;
-+
-+ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
-+ return -ENOMEM;
-+
-+ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
-+ if (retval == 0)
-+ retval = sched_setaffinity(pid, new_mask);
-+ free_cpumask_var(new_mask);
-+ return retval;
-+}
-+
-+long sched_getaffinity(pid_t pid, cpumask_t *mask)
-+{
-+ struct task_struct *p;
-+ int retval;
-+
-+ guard(rcu)();
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -ESRCH;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ guard(raw_spinlock_irqsave)(&p->pi_lock);
-+ cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
-+
-+ return retval;
-+}
-+
-+/**
-+ * sys_sched_getaffinity - get the CPU affinity of a process
-+ * @pid: pid of the process
-+ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
-+ * @user_mask_ptr: user-space pointer to hold the current CPU mask
-+ *
-+ * Return: size of CPU mask copied to user_mask_ptr on success. An
-+ * error code otherwise.
-+ */
-+SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
-+ unsigned long __user *, user_mask_ptr)
-+{
-+ int ret;
-+ cpumask_var_t mask;
-+
-+ if ((len * BITS_PER_BYTE) < nr_cpu_ids)
-+ return -EINVAL;
-+ if (len & (sizeof(unsigned long)-1))
-+ return -EINVAL;
-+
-+ if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
-+ return -ENOMEM;
-+
-+ ret = sched_getaffinity(pid, mask);
-+ if (ret == 0) {
-+ unsigned int retlen = min(len, cpumask_size());
-+
-+ if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen))
-+ ret = -EFAULT;
-+ else
-+ ret = retlen;
-+ }
-+ free_cpumask_var(mask);
-+
-+ return ret;
-+}
-+
-+static void do_sched_yield(void)
-+{
-+ struct rq *rq;
-+ struct rq_flags rf;
-+ struct task_struct *p;
-+
-+ if (!sched_yield_type)
-+ return;
-+
-+ rq = this_rq_lock_irq(&rf);
-+
-+ schedstat_inc(rq->yld_count);
-+
-+ p = current;
-+ if (rt_task(p)) {
-+ if (task_on_rq_queued(p))
-+ requeue_task(p, rq);
-+ } else if (rq->nr_running > 1) {
-+ do_sched_yield_type_1(p, rq);
-+ if (task_on_rq_queued(p))
-+ requeue_task(p, rq);
-+ }
-+
-+ preempt_disable();
-+ raw_spin_unlock_irq(&rq->lock);
-+ sched_preempt_enable_no_resched();
-+
-+ schedule();
-+}
-+
-+/**
-+ * sys_sched_yield - yield the current processor to other threads.
-+ *
-+ * This function yields the current CPU to other tasks. If there are no
-+ * other threads running on this CPU then this function will return.
-+ *
-+ * Return: 0.
-+ */
-+SYSCALL_DEFINE0(sched_yield)
-+{
-+ do_sched_yield();
-+ return 0;
-+}
-+
-+#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
-+int __sched __cond_resched(void)
-+{
-+ if (should_resched(0)) {
-+ preempt_schedule_common();
-+ return 1;
-+ }
-+ /*
-+ * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
-+ * whether the current CPU is in an RCU read-side critical section,
-+ * so the tick can report quiescent states even for CPUs looping
-+ * in kernel context. In contrast, in non-preemptible kernels,
-+ * RCU readers leave no in-memory hints, which means that CPU-bound
-+ * processes executing in kernel context might never report an
-+ * RCU quiescent state. Therefore, the following code causes
-+ * cond_resched() to report a quiescent state, but only when RCU
-+ * is in urgent need of one.
-+ */
-+#ifndef CONFIG_PREEMPT_RCU
-+ rcu_all_qs();
-+#endif
-+ return 0;
-+}
-+EXPORT_SYMBOL(__cond_resched);
-+#endif
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#define cond_resched_dynamic_enabled __cond_resched
-+#define cond_resched_dynamic_disabled ((void *)&__static_call_return0)
-+DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
-+EXPORT_STATIC_CALL_TRAMP(cond_resched);
-+
-+#define might_resched_dynamic_enabled __cond_resched
-+#define might_resched_dynamic_disabled ((void *)&__static_call_return0)
-+DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
-+EXPORT_STATIC_CALL_TRAMP(might_resched);
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
-+int __sched dynamic_cond_resched(void)
-+{
-+ klp_sched_try_switch();
-+ if (!static_branch_unlikely(&sk_dynamic_cond_resched))
-+ return 0;
-+ return __cond_resched();
-+}
-+EXPORT_SYMBOL(dynamic_cond_resched);
-+
-+static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
-+int __sched dynamic_might_resched(void)
-+{
-+ if (!static_branch_unlikely(&sk_dynamic_might_resched))
-+ return 0;
-+ return __cond_resched();
-+}
-+EXPORT_SYMBOL(dynamic_might_resched);
-+#endif
-+#endif
-+
-+/*
-+ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
-+ * call schedule, and on return reacquire the lock.
-+ *
-+ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
-+ * operations here to prevent schedule() from being called twice (once via
-+ * spin_unlock(), once by hand).
-+ */
-+int __cond_resched_lock(spinlock_t *lock)
-+{
-+ int resched = should_resched(PREEMPT_LOCK_OFFSET);
-+ int ret = 0;
-+
-+ lockdep_assert_held(lock);
-+
-+ if (spin_needbreak(lock) || resched) {
-+ spin_unlock(lock);
-+ if (!_cond_resched())
-+ cpu_relax();
-+ ret = 1;
-+ spin_lock(lock);
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL(__cond_resched_lock);
-+
-+int __cond_resched_rwlock_read(rwlock_t *lock)
-+{
-+ int resched = should_resched(PREEMPT_LOCK_OFFSET);
-+ int ret = 0;
-+
-+ lockdep_assert_held_read(lock);
-+
-+ if (rwlock_needbreak(lock) || resched) {
-+ read_unlock(lock);
-+ if (!_cond_resched())
-+ cpu_relax();
-+ ret = 1;
-+ read_lock(lock);
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL(__cond_resched_rwlock_read);
-+
-+int __cond_resched_rwlock_write(rwlock_t *lock)
-+{
-+ int resched = should_resched(PREEMPT_LOCK_OFFSET);
-+ int ret = 0;
-+
-+ lockdep_assert_held_write(lock);
-+
-+ if (rwlock_needbreak(lock) || resched) {
-+ write_unlock(lock);
-+ if (!_cond_resched())
-+ cpu_relax();
-+ ret = 1;
-+ write_lock(lock);
-+ }
-+ return ret;
-+}
-+EXPORT_SYMBOL(__cond_resched_rwlock_write);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+
-+#ifdef CONFIG_GENERIC_ENTRY
-+#include <linux/entry-common.h>
-+#endif
-+
-+/*
-+ * SC:cond_resched
-+ * SC:might_resched
-+ * SC:preempt_schedule
-+ * SC:preempt_schedule_notrace
-+ * SC:irqentry_exit_cond_resched
-+ *
-+ *
-+ * NONE:
-+ * cond_resched <- __cond_resched
-+ * might_resched <- RET0
-+ * preempt_schedule <- NOP
-+ * preempt_schedule_notrace <- NOP
-+ * irqentry_exit_cond_resched <- NOP
-+ *
-+ * VOLUNTARY:
-+ * cond_resched <- __cond_resched
-+ * might_resched <- __cond_resched
-+ * preempt_schedule <- NOP
-+ * preempt_schedule_notrace <- NOP
-+ * irqentry_exit_cond_resched <- NOP
-+ *
-+ * FULL:
-+ * cond_resched <- RET0
-+ * might_resched <- RET0
-+ * preempt_schedule <- preempt_schedule
-+ * preempt_schedule_notrace <- preempt_schedule_notrace
-+ * irqentry_exit_cond_resched <- irqentry_exit_cond_resched
-+ */
-+
-+enum {
-+ preempt_dynamic_undefined = -1,
-+ preempt_dynamic_none,
-+ preempt_dynamic_voluntary,
-+ preempt_dynamic_full,
-+};
-+
-+int preempt_dynamic_mode = preempt_dynamic_undefined;
-+
-+int sched_dynamic_mode(const char *str)
-+{
-+ if (!strcmp(str, "none"))
-+ return preempt_dynamic_none;
-+
-+ if (!strcmp(str, "voluntary"))
-+ return preempt_dynamic_voluntary;
-+
-+ if (!strcmp(str, "full"))
-+ return preempt_dynamic_full;
-+
-+ return -EINVAL;
-+}
-+
-+#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
-+#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled)
-+#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled)
-+#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
-+#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key)
-+#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key)
-+#else
-+#error "Unsupported PREEMPT_DYNAMIC mechanism"
-+#endif
-+
-+static DEFINE_MUTEX(sched_dynamic_mutex);
-+static bool klp_override;
-+
-+static void __sched_dynamic_update(int mode)
-+{
-+ /*
-+ * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
-+ * the ZERO state, which is invalid.
-+ */
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_enable(might_resched);
-+ preempt_dynamic_enable(preempt_schedule);
-+ preempt_dynamic_enable(preempt_schedule_notrace);
-+ preempt_dynamic_enable(irqentry_exit_cond_resched);
-+
-+ switch (mode) {
-+ case preempt_dynamic_none:
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_disable(might_resched);
-+ preempt_dynamic_disable(preempt_schedule);
-+ preempt_dynamic_disable(preempt_schedule_notrace);
-+ preempt_dynamic_disable(irqentry_exit_cond_resched);
-+ if (mode != preempt_dynamic_mode)
-+ pr_info("Dynamic Preempt: none\n");
-+ break;
-+
-+ case preempt_dynamic_voluntary:
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_enable(might_resched);
-+ preempt_dynamic_disable(preempt_schedule);
-+ preempt_dynamic_disable(preempt_schedule_notrace);
-+ preempt_dynamic_disable(irqentry_exit_cond_resched);
-+ if (mode != preempt_dynamic_mode)
-+ pr_info("Dynamic Preempt: voluntary\n");
-+ break;
-+
-+ case preempt_dynamic_full:
-+ if (!klp_override)
-+ preempt_dynamic_enable(cond_resched);
-+ preempt_dynamic_disable(might_resched);
-+ preempt_dynamic_enable(preempt_schedule);
-+ preempt_dynamic_enable(preempt_schedule_notrace);
-+ preempt_dynamic_enable(irqentry_exit_cond_resched);
-+ if (mode != preempt_dynamic_mode)
-+ pr_info("Dynamic Preempt: full\n");
-+ break;
-+ }
-+
-+ preempt_dynamic_mode = mode;
-+}
-+
-+void sched_dynamic_update(int mode)
-+{
-+ mutex_lock(&sched_dynamic_mutex);
-+ __sched_dynamic_update(mode);
-+ mutex_unlock(&sched_dynamic_mutex);
-+}
-+
-+#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
-+
-+static int klp_cond_resched(void)
-+{
-+ __klp_sched_try_switch();
-+ return __cond_resched();
-+}
-+
-+void sched_dynamic_klp_enable(void)
-+{
-+ mutex_lock(&sched_dynamic_mutex);
-+
-+ klp_override = true;
-+ static_call_update(cond_resched, klp_cond_resched);
-+
-+ mutex_unlock(&sched_dynamic_mutex);
-+}
-+
-+void sched_dynamic_klp_disable(void)
-+{
-+ mutex_lock(&sched_dynamic_mutex);
-+
-+ klp_override = false;
-+ __sched_dynamic_update(preempt_dynamic_mode);
-+
-+ mutex_unlock(&sched_dynamic_mutex);
-+}
-+
-+#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
-+
-+
-+static int __init setup_preempt_mode(char *str)
-+{
-+ int mode = sched_dynamic_mode(str);
-+ if (mode < 0) {
-+ pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
-+ return 0;
-+ }
-+
-+ sched_dynamic_update(mode);
-+ return 1;
-+}
-+__setup("preempt=", setup_preempt_mode);
-+
-+static void __init preempt_dynamic_init(void)
-+{
-+ if (preempt_dynamic_mode == preempt_dynamic_undefined) {
-+ if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
-+ sched_dynamic_update(preempt_dynamic_none);
-+ } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
-+ sched_dynamic_update(preempt_dynamic_voluntary);
-+ } else {
-+ /* Default static call setting, nothing to do */
-+ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
-+ preempt_dynamic_mode = preempt_dynamic_full;
-+ pr_info("Dynamic Preempt: full\n");
-+ }
-+ }
-+}
-+
-+#define PREEMPT_MODEL_ACCESSOR(mode) \
-+ bool preempt_model_##mode(void) \
-+ { \
-+ WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
-+ return preempt_dynamic_mode == preempt_dynamic_##mode; \
-+ } \
-+ EXPORT_SYMBOL_GPL(preempt_model_##mode)
-+
-+PREEMPT_MODEL_ACCESSOR(none);
-+PREEMPT_MODEL_ACCESSOR(voluntary);
-+PREEMPT_MODEL_ACCESSOR(full);
-+
-+#else /* !CONFIG_PREEMPT_DYNAMIC */
-+
-+static inline void preempt_dynamic_init(void) { }
-+
-+#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
-+
-+/**
-+ * yield - yield the current processor to other threads.
-+ *
-+ * Do not ever use this function, there's a 99% chance you're doing it wrong.
-+ *
-+ * The scheduler is at all times free to pick the calling task as the most
-+ * eligible task to run, if removing the yield() call from your code breaks
-+ * it, it's already broken.
-+ *
-+ * Typical broken usage is:
-+ *
-+ * while (!event)
-+ * yield();
-+ *
-+ * where one assumes that yield() will let 'the other' process run that will
-+ * make event true. If the current task is a SCHED_FIFO task that will never
-+ * happen. Never use yield() as a progress guarantee!!
-+ *
-+ * If you want to use yield() to wait for something, use wait_event().
-+ * If you want to use yield() to be 'nice' for others, use cond_resched().
-+ * If you still want to use yield(), do not!
-+ */
-+void __sched yield(void)
-+{
-+ set_current_state(TASK_RUNNING);
-+ do_sched_yield();
-+}
-+EXPORT_SYMBOL(yield);
-+
-+/**
-+ * yield_to - yield the current processor to another thread in
-+ * your thread group, or accelerate that thread toward the
-+ * processor it's on.
-+ * @p: target task
-+ * @preempt: whether task preemption is allowed or not
-+ *
-+ * It's the caller's job to ensure that the target task struct
-+ * can't go away on us before we can do any checks.
-+ *
-+ * In Alt schedule FW, yield_to is not supported.
-+ *
-+ * Return:
-+ * true (>0) if we indeed boosted the target task.
-+ * false (0) if we failed to boost the target.
-+ * -ESRCH if there's no task to yield to.
-+ */
-+int __sched yield_to(struct task_struct *p, bool preempt)
-+{
-+ return 0;
-+}
-+EXPORT_SYMBOL_GPL(yield_to);
-+
-+int io_schedule_prepare(void)
-+{
-+ int old_iowait = current->in_iowait;
-+
-+ current->in_iowait = 1;
-+ blk_flush_plug(current->plug, true);
-+ return old_iowait;
-+}
-+
-+void io_schedule_finish(int token)
-+{
-+ current->in_iowait = token;
-+}
-+
-+/*
-+ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
-+ * that process accounting knows that this is a task in IO wait state.
-+ *
-+ * But don't do that if it is a deliberate, throttling IO wait (this task
-+ * has set its backing_dev_info: the queue against which it should throttle)
-+ */
-+
-+long __sched io_schedule_timeout(long timeout)
-+{
-+ int token;
-+ long ret;
-+
-+ token = io_schedule_prepare();
-+ ret = schedule_timeout(timeout);
-+ io_schedule_finish(token);
-+
-+ return ret;
-+}
-+EXPORT_SYMBOL(io_schedule_timeout);
-+
-+void __sched io_schedule(void)
-+{
-+ int token;
-+
-+ token = io_schedule_prepare();
-+ schedule();
-+ io_schedule_finish(token);
-+}
-+EXPORT_SYMBOL(io_schedule);
-+
-+/**
-+ * sys_sched_get_priority_max - return maximum RT priority.
-+ * @policy: scheduling class.
-+ *
-+ * Return: On success, this syscall returns the maximum
-+ * rt_priority that can be used by a given scheduling class.
-+ * On failure, a negative error code is returned.
-+ */
-+SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
-+{
-+ int ret = -EINVAL;
-+
-+ switch (policy) {
-+ case SCHED_FIFO:
-+ case SCHED_RR:
-+ ret = MAX_RT_PRIO - 1;
-+ break;
-+ case SCHED_NORMAL:
-+ case SCHED_BATCH:
-+ case SCHED_IDLE:
-+ ret = 0;
-+ break;
-+ }
-+ return ret;
-+}
-+
-+/**
-+ * sys_sched_get_priority_min - return minimum RT priority.
-+ * @policy: scheduling class.
-+ *
-+ * Return: On success, this syscall returns the minimum
-+ * rt_priority that can be used by a given scheduling class.
-+ * On failure, a negative error code is returned.
-+ */
-+SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
-+{
-+ int ret = -EINVAL;
-+
-+ switch (policy) {
-+ case SCHED_FIFO:
-+ case SCHED_RR:
-+ ret = 1;
-+ break;
-+ case SCHED_NORMAL:
-+ case SCHED_BATCH:
-+ case SCHED_IDLE:
-+ ret = 0;
-+ break;
-+ }
-+ return ret;
-+}
-+
-+static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
-+{
-+ struct task_struct *p;
-+ int retval;
-+
-+ alt_sched_debug();
-+
-+ if (pid < 0)
-+ return -EINVAL;
-+
-+ guard(rcu)();
-+ p = find_process_by_pid(pid);
-+ if (!p)
-+ return -EINVAL;
-+
-+ retval = security_task_getscheduler(p);
-+ if (retval)
-+ return retval;
-+
-+ *t = ns_to_timespec64(sysctl_sched_base_slice);
-+ return 0;
-+}
-+
-+/**
-+ * sys_sched_rr_get_interval - return the default timeslice of a process.
-+ * @pid: pid of the process.
-+ * @interval: userspace pointer to the timeslice value.
-+ *
-+ *
-+ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
-+ * an error code.
-+ */
-+SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
-+ struct __kernel_timespec __user *, interval)
-+{
-+ struct timespec64 t;
-+ int retval = sched_rr_get_interval(pid, &t);
-+
-+ if (retval == 0)
-+ retval = put_timespec64(&t, interval);
-+
-+ return retval;
-+}
-+
-+#ifdef CONFIG_COMPAT_32BIT_TIME
-+SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
-+ struct old_timespec32 __user *, interval)
-+{
-+ struct timespec64 t;
-+ int retval = sched_rr_get_interval(pid, &t);
-+
-+ if (retval == 0)
-+ retval = put_old_timespec32(&t, interval);
-+ return retval;
-+}
-+#endif
-+
-+void sched_show_task(struct task_struct *p)
-+{
-+ unsigned long free = 0;
-+ int ppid;
-+
-+ if (!try_get_task_stack(p))
-+ return;
-+
-+ pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
-+
-+ if (task_is_running(p))
-+ pr_cont(" running task ");
-+#ifdef CONFIG_DEBUG_STACK_USAGE
-+ free = stack_not_used(p);
-+#endif
-+ ppid = 0;
-+ rcu_read_lock();
-+ if (pid_alive(p))
-+ ppid = task_pid_nr(rcu_dereference(p->real_parent));
-+ rcu_read_unlock();
-+ pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
-+ free, task_pid_nr(p), task_tgid_nr(p),
-+ ppid, read_task_thread_flags(p));
-+
-+ print_worker_info(KERN_INFO, p);
-+ print_stop_info(KERN_INFO, p);
-+ show_stack(p, NULL, KERN_INFO);
-+ put_task_stack(p);
-+}
-+EXPORT_SYMBOL_GPL(sched_show_task);
-+
-+static inline bool
-+state_filter_match(unsigned long state_filter, struct task_struct *p)
-+{
-+ unsigned int state = READ_ONCE(p->__state);
-+
-+ /* no filter, everything matches */
-+ if (!state_filter)
-+ return true;
-+
-+ /* filter, but doesn't match */
-+ if (!(state & state_filter))
-+ return false;
-+
-+ /*
-+ * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
-+ * TASK_KILLABLE).
-+ */
-+ if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD))
-+ return false;
-+
-+ return true;
-+}
-+
-+
-+void show_state_filter(unsigned int state_filter)
-+{
-+ struct task_struct *g, *p;
-+
-+ rcu_read_lock();
-+ for_each_process_thread(g, p) {
-+ /*
-+ * reset the NMI-timeout, listing all files on a slow
-+ * console might take a lot of time:
-+ * Also, reset softlockup watchdogs on all CPUs, because
-+ * another CPU might be blocked waiting for us to process
-+ * an IPI.
-+ */
-+ touch_nmi_watchdog();
-+ touch_all_softlockup_watchdogs();
-+ if (state_filter_match(state_filter, p))
-+ sched_show_task(p);
-+ }
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+ /* TODO: Alt schedule FW should support this
-+ if (!state_filter)
-+ sysrq_sched_debug_show();
-+ */
-+#endif
-+ rcu_read_unlock();
-+ /*
-+ * Only show locks if all tasks are dumped:
-+ */
-+ if (!state_filter)
-+ debug_show_all_locks();
-+}
-+
-+void dump_cpu_task(int cpu)
-+{
-+ if (cpu == smp_processor_id() && in_hardirq()) {
-+ struct pt_regs *regs;
-+
-+ regs = get_irq_regs();
-+ if (regs) {
-+ show_regs(regs);
-+ return;
-+ }
-+ }
-+
-+ if (trigger_single_cpu_backtrace(cpu))
-+ return;
-+
-+ pr_info("Task dump for CPU %d:\n", cpu);
-+ sched_show_task(cpu_curr(cpu));
-+}
-+
-+/**
-+ * init_idle - set up an idle thread for a given CPU
-+ * @idle: task in question
-+ * @cpu: CPU the idle task belongs to
-+ *
-+ * NOTE: this function does not set the idle thread's NEED_RESCHED
-+ * flag, to make booting more robust.
-+ */
-+void __init init_idle(struct task_struct *idle, int cpu)
-+{
-+#ifdef CONFIG_SMP
-+ struct affinity_context ac = (struct affinity_context) {
-+ .new_mask = cpumask_of(cpu),
-+ .flags = 0,
-+ };
-+#endif
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ __sched_fork(0, idle);
-+
-+ raw_spin_lock_irqsave(&idle->pi_lock, flags);
-+ raw_spin_lock(&rq->lock);
-+
-+ idle->last_ran = rq->clock_task;
-+ idle->__state = TASK_RUNNING;
-+ /*
-+ * PF_KTHREAD should already be set at this point; regardless, make it
-+ * look like a proper per-CPU kthread.
-+ */
-+ idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
-+ kthread_set_per_cpu(idle, cpu);
-+
-+ sched_queue_init_idle(&rq->queue, idle);
-+
-+#ifdef CONFIG_SMP
-+ /*
-+ * It's possible that init_idle() gets called multiple times on a task,
-+ * in that case do_set_cpus_allowed() will not do the right thing.
-+ *
-+ * And since this is boot we can forgo the serialisation.
-+ */
-+ set_cpus_allowed_common(idle, &ac);
-+#endif
-+
-+ /* Silence PROVE_RCU */
-+ rcu_read_lock();
-+ __set_task_cpu(idle, cpu);
-+ rcu_read_unlock();
-+
-+ rq->idle = idle;
-+ rcu_assign_pointer(rq->curr, idle);
-+ idle->on_cpu = 1;
-+
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
-+
-+ /* Set the preempt count _outside_ the spinlocks! */
-+ init_idle_preempt_count(idle, cpu);
-+
-+ ftrace_graph_init_idle_task(idle, cpu);
-+ vtime_init_idle(idle, cpu);
-+#ifdef CONFIG_SMP
-+ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
-+#endif
-+}
-+
-+#ifdef CONFIG_SMP
-+
-+int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur,
-+ const struct cpumask __maybe_unused *trial)
-+{
-+ return 1;
-+}
-+
-+int task_can_attach(struct task_struct *p)
-+{
-+ int ret = 0;
-+
-+ /*
-+ * Kthreads which disallow setaffinity shouldn't be moved
-+ * to a new cpuset; we don't want to change their CPU
-+ * affinity and isolating such threads by their set of
-+ * allowed nodes is unnecessary. Thus, cpusets are not
-+ * applicable for such threads. This prevents checking for
-+ * success of set_cpus_allowed_ptr() on all attached tasks
-+ * before cpus_mask may be changed.
-+ */
-+ if (p->flags & PF_NO_SETAFFINITY)
-+ ret = -EINVAL;
-+
-+ return ret;
-+}
-+
-+bool sched_smp_initialized __read_mostly;
-+
-+#ifdef CONFIG_HOTPLUG_CPU
-+/*
-+ * Ensures that the idle task is using init_mm right before its CPU goes
-+ * offline.
-+ */
-+void idle_task_exit(void)
-+{
-+ struct mm_struct *mm = current->active_mm;
-+
-+ BUG_ON(current != this_rq()->idle);
-+
-+ if (mm != &init_mm) {
-+ switch_mm(mm, &init_mm, current);
-+ finish_arch_post_lock_switch();
-+ }
-+
-+ /* finish_cpu(), as ran on the BP, will clean up the active_mm state */
-+}
-+
-+static int __balance_push_cpu_stop(void *arg)
-+{
-+ struct task_struct *p = arg;
-+ struct rq *rq = this_rq();
-+ struct rq_flags rf;
-+ int cpu;
-+
-+ raw_spin_lock_irq(&p->pi_lock);
-+ rq_lock(rq, &rf);
-+
-+ update_rq_clock(rq);
-+
-+ if (task_rq(p) == rq && task_on_rq_queued(p)) {
-+ cpu = select_fallback_rq(rq->cpu, p);
-+ rq = __migrate_task(rq, p, cpu);
-+ }
-+
-+ rq_unlock(rq, &rf);
-+ raw_spin_unlock_irq(&p->pi_lock);
-+
-+ put_task_struct(p);
-+
-+ return 0;
-+}
-+
-+static DEFINE_PER_CPU(struct cpu_stop_work, push_work);
-+
-+/*
-+ * This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only
-+ * effective when the hotplug motion is down.
-+ */
-+static void balance_push(struct rq *rq)
-+{
-+ struct task_struct *push_task = rq->curr;
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ /*
-+ * Ensure the thing is persistent until balance_push_set(.on = false);
-+ */
-+ rq->balance_callback = &balance_push_callback;
-+
-+ /*
-+ * Only active while going offline and when invoked on the outgoing
-+ * CPU.
-+ */
-+ if (!cpu_dying(rq->cpu) || rq != this_rq())
-+ return;
-+
-+ /*
-+ * Both the cpu-hotplug and stop task are in this case and are
-+ * required to complete the hotplug process.
-+ */
-+ if (kthread_is_per_cpu(push_task) ||
-+ is_migration_disabled(push_task)) {
-+
-+ /*
-+ * If this is the idle task on the outgoing CPU try to wake
-+ * up the hotplug control thread which might wait for the
-+ * last task to vanish. The rcuwait_active() check is
-+ * accurate here because the waiter is pinned on this CPU
-+ * and can't obviously be running in parallel.
-+ *
-+ * On RT kernels this also has to check whether there are
-+ * pinned and scheduled out tasks on the runqueue. They
-+ * need to leave the migrate disabled section first.
-+ */
-+ if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
-+ rcuwait_active(&rq->hotplug_wait)) {
-+ raw_spin_unlock(&rq->lock);
-+ rcuwait_wake_up(&rq->hotplug_wait);
-+ raw_spin_lock(&rq->lock);
-+ }
-+ return;
-+ }
-+
-+ get_task_struct(push_task);
-+ /*
-+ * Temporarily drop rq->lock such that we can wake-up the stop task.
-+ * Both preemption and IRQs are still disabled.
-+ */
-+ preempt_disable();
-+ raw_spin_unlock(&rq->lock);
-+ stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
-+ this_cpu_ptr(&push_work));
-+ preempt_enable();
-+ /*
-+ * At this point need_resched() is true and we'll take the loop in
-+ * schedule(). The next pick is obviously going to be the stop task
-+ * which kthread_is_per_cpu() and will push this task away.
-+ */
-+ raw_spin_lock(&rq->lock);
-+}
-+
-+static void balance_push_set(int cpu, bool on)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ struct rq_flags rf;
-+
-+ rq_lock_irqsave(rq, &rf);
-+ if (on) {
-+ WARN_ON_ONCE(rq->balance_callback);
-+ rq->balance_callback = &balance_push_callback;
-+ } else if (rq->balance_callback == &balance_push_callback) {
-+ rq->balance_callback = NULL;
-+ }
-+ rq_unlock_irqrestore(rq, &rf);
-+}
-+
-+/*
-+ * Invoked from a CPUs hotplug control thread after the CPU has been marked
-+ * inactive. All tasks which are not per CPU kernel threads are either
-+ * pushed off this CPU now via balance_push() or placed on a different CPU
-+ * during wakeup. Wait until the CPU is quiescent.
-+ */
-+static void balance_hotplug_wait(void)
-+{
-+ struct rq *rq = this_rq();
-+
-+ rcuwait_wait_event(&rq->hotplug_wait,
-+ rq->nr_running == 1 && !rq_has_pinned_tasks(rq),
-+ TASK_UNINTERRUPTIBLE);
-+}
-+
-+#else
-+
-+static void balance_push(struct rq *rq)
-+{
-+}
-+
-+static void balance_push_set(int cpu, bool on)
-+{
-+}
-+
-+static inline void balance_hotplug_wait(void)
-+{
-+}
-+#endif /* CONFIG_HOTPLUG_CPU */
-+
-+static void set_rq_offline(struct rq *rq)
-+{
-+ if (rq->online) {
-+ update_rq_clock(rq);
-+ rq->online = false;
-+ }
-+}
-+
-+static void set_rq_online(struct rq *rq)
-+{
-+ if (!rq->online)
-+ rq->online = true;
-+}
-+
-+/*
-+ * used to mark begin/end of suspend/resume:
-+ */
-+static int num_cpus_frozen;
-+
-+/*
-+ * Update cpusets according to cpu_active mask. If cpusets are
-+ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
-+ * around partition_sched_domains().
-+ *
-+ * If we come here as part of a suspend/resume, don't touch cpusets because we
-+ * want to restore it back to its original state upon resume anyway.
-+ */
-+static void cpuset_cpu_active(void)
-+{
-+ if (cpuhp_tasks_frozen) {
-+ /*
-+ * num_cpus_frozen tracks how many CPUs are involved in suspend
-+ * resume sequence. As long as this is not the last online
-+ * operation in the resume sequence, just build a single sched
-+ * domain, ignoring cpusets.
-+ */
-+ partition_sched_domains(1, NULL, NULL);
-+ if (--num_cpus_frozen)
-+ return;
-+ /*
-+ * This is the last CPU online operation. So fall through and
-+ * restore the original sched domains by considering the
-+ * cpuset configurations.
-+ */
-+ cpuset_force_rebuild();
-+ }
-+
-+ cpuset_update_active_cpus();
-+}
-+
-+static int cpuset_cpu_inactive(unsigned int cpu)
-+{
-+ if (!cpuhp_tasks_frozen) {
-+ cpuset_update_active_cpus();
-+ } else {
-+ num_cpus_frozen++;
-+ partition_sched_domains(1, NULL, NULL);
-+ }
-+ return 0;
-+}
-+
-+int sched_cpu_activate(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ /*
-+ * Clear the balance_push callback and prepare to schedule
-+ * regular tasks.
-+ */
-+ balance_push_set(cpu, false);
-+
-+#ifdef CONFIG_SCHED_SMT
-+ /*
-+ * When going up, increment the number of cores with SMT present.
-+ */
-+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
-+ static_branch_inc_cpuslocked(&sched_smt_present);
-+#endif
-+ set_cpu_active(cpu, true);
-+
-+ if (sched_smp_initialized)
-+ cpuset_cpu_active();
-+
-+ /*
-+ * Put the rq online, if not already. This happens:
-+ *
-+ * 1) In the early boot process, because we build the real domains
-+ * after all cpus have been brought up.
-+ *
-+ * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
-+ * domains.
-+ */
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ set_rq_online(rq);
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+ return 0;
-+}
-+
-+int sched_cpu_deactivate(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+ int ret;
-+
-+ set_cpu_active(cpu, false);
-+
-+ /*
-+ * From this point forward, this CPU will refuse to run any task that
-+ * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively
-+ * push those tasks away until this gets cleared, see
-+ * sched_cpu_dying().
-+ */
-+ balance_push_set(cpu, true);
-+
-+ /*
-+ * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
-+ * users of this state to go away such that all new such users will
-+ * observe it.
-+ *
-+ * Specifically, we rely on ttwu to no longer target this CPU, see
-+ * ttwu_queue_cond() and is_cpu_allowed().
-+ *
-+ * Do sync before park smpboot threads to take care the rcu boost case.
-+ */
-+ synchronize_rcu();
-+
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ set_rq_offline(rq);
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+#ifdef CONFIG_SCHED_SMT
-+ /*
-+ * When going down, decrement the number of cores with SMT present.
-+ */
-+ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) {
-+ static_branch_dec_cpuslocked(&sched_smt_present);
-+ if (!static_branch_likely(&sched_smt_present))
-+ cpumask_clear(sched_sg_idle_mask);
-+ }
-+#endif
-+
-+ if (!sched_smp_initialized)
-+ return 0;
-+
-+ ret = cpuset_cpu_inactive(cpu);
-+ if (ret) {
-+ balance_push_set(cpu, false);
-+ set_cpu_active(cpu, true);
-+ return ret;
-+ }
-+
-+ return 0;
-+}
-+
-+static void sched_rq_cpu_starting(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+
-+ rq->calc_load_update = calc_load_update;
-+}
-+
-+int sched_cpu_starting(unsigned int cpu)
-+{
-+ sched_rq_cpu_starting(cpu);
-+ sched_tick_start(cpu);
-+ return 0;
-+}
-+
-+#ifdef CONFIG_HOTPLUG_CPU
-+
-+/*
-+ * Invoked immediately before the stopper thread is invoked to bring the
-+ * CPU down completely. At this point all per CPU kthreads except the
-+ * hotplug thread (current) and the stopper thread (inactive) have been
-+ * either parked or have been unbound from the outgoing CPU. Ensure that
-+ * any of those which might be on the way out are gone.
-+ *
-+ * If after this point a bound task is being woken on this CPU then the
-+ * responsible hotplug callback has failed to do it's job.
-+ * sched_cpu_dying() will catch it with the appropriate fireworks.
-+ */
-+int sched_cpu_wait_empty(unsigned int cpu)
-+{
-+ balance_hotplug_wait();
-+ return 0;
-+}
-+
-+/*
-+ * Since this CPU is going 'away' for a while, fold any nr_active delta we
-+ * might have. Called from the CPU stopper task after ensuring that the
-+ * stopper is the last running task on the CPU, so nr_active count is
-+ * stable. We need to take the teardown thread which is calling this into
-+ * account, so we hand in adjust = 1 to the load calculation.
-+ *
-+ * Also see the comment "Global load-average calculations".
-+ */
-+static void calc_load_migrate(struct rq *rq)
-+{
-+ long delta = calc_load_fold_active(rq, 1);
-+
-+ if (delta)
-+ atomic_long_add(delta, &calc_load_tasks);
-+}
-+
-+static void dump_rq_tasks(struct rq *rq, const char *loglvl)
-+{
-+ struct task_struct *g, *p;
-+ int cpu = cpu_of(rq);
-+
-+ lockdep_assert_held(&rq->lock);
-+
-+ printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
-+ for_each_process_thread(g, p) {
-+ if (task_cpu(p) != cpu)
-+ continue;
-+
-+ if (!task_on_rq_queued(p))
-+ continue;
-+
-+ printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm);
-+ }
-+}
-+
-+int sched_cpu_dying(unsigned int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ unsigned long flags;
-+
-+ /* Handle pending wakeups and then migrate everything off */
-+ sched_tick_stop(cpu);
-+
-+ raw_spin_lock_irqsave(&rq->lock, flags);
-+ if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
-+ WARN(true, "Dying CPU not properly vacated!");
-+ dump_rq_tasks(rq, KERN_WARNING);
-+ }
-+ raw_spin_unlock_irqrestore(&rq->lock, flags);
-+
-+ calc_load_migrate(rq);
-+ hrtick_clear(rq);
-+ return 0;
-+}
-+#endif
-+
-+#ifdef CONFIG_SMP
-+static void sched_init_topology_cpumask_early(void)
-+{
-+ int cpu;
-+ cpumask_t *tmp;
-+
-+ for_each_possible_cpu(cpu) {
-+ /* init topo masks */
-+ tmp = per_cpu(sched_cpu_topo_masks, cpu);
-+
-+ cpumask_copy(tmp, cpu_possible_mask);
-+ per_cpu(sched_cpu_llc_mask, cpu) = tmp;
-+ per_cpu(sched_cpu_topo_end_mask, cpu) = ++tmp;
-+ }
-+}
-+
-+#define TOPOLOGY_CPUMASK(name, mask, last)\
-+ if (cpumask_and(topo, topo, mask)) { \
-+ cpumask_copy(topo, mask); \
-+ printk(KERN_INFO "sched: cpu#%02d topo: 0x%08lx - "#name, \
-+ cpu, (topo++)->bits[0]); \
-+ } \
-+ if (!last) \
-+ bitmap_complement(cpumask_bits(topo), cpumask_bits(mask), \
-+ nr_cpumask_bits);
-+
-+static void sched_init_topology_cpumask(void)
-+{
-+ int cpu;
-+ cpumask_t *topo;
-+
-+ for_each_online_cpu(cpu) {
-+ /* take chance to reset time slice for idle tasks */
-+ cpu_rq(cpu)->idle->time_slice = sysctl_sched_base_slice;
-+
-+ topo = per_cpu(sched_cpu_topo_masks, cpu);
-+
-+ bitmap_complement(cpumask_bits(topo), cpumask_bits(cpumask_of(cpu)),
-+ nr_cpumask_bits);
-+#ifdef CONFIG_SCHED_SMT
-+ TOPOLOGY_CPUMASK(smt, topology_sibling_cpumask(cpu), false);
-+#endif
-+ TOPOLOGY_CPUMASK(cluster, topology_cluster_cpumask(cpu), false);
-+
-+ per_cpu(sd_llc_id, cpu) = cpumask_first(cpu_coregroup_mask(cpu));
-+ per_cpu(sched_cpu_llc_mask, cpu) = topo;
-+ TOPOLOGY_CPUMASK(coregroup, cpu_coregroup_mask(cpu), false);
-+
-+ TOPOLOGY_CPUMASK(core, topology_core_cpumask(cpu), false);
-+
-+ TOPOLOGY_CPUMASK(others, cpu_online_mask, true);
-+
-+ per_cpu(sched_cpu_topo_end_mask, cpu) = topo;
-+ printk(KERN_INFO "sched: cpu#%02d llc_id = %d, llc_mask idx = %d\n",
-+ cpu, per_cpu(sd_llc_id, cpu),
-+ (int) (per_cpu(sched_cpu_llc_mask, cpu) -
-+ per_cpu(sched_cpu_topo_masks, cpu)));
-+ }
-+}
-+#endif
-+
-+void __init sched_init_smp(void)
-+{
-+ /* Move init over to a non-isolated CPU */
-+ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
-+ BUG();
-+ current->flags &= ~PF_NO_SETAFFINITY;
-+
-+ sched_init_topology_cpumask();
-+
-+ sched_smp_initialized = true;
-+}
-+
-+static int __init migration_init(void)
-+{
-+ sched_cpu_starting(smp_processor_id());
-+ return 0;
-+}
-+early_initcall(migration_init);
-+
-+#else
-+void __init sched_init_smp(void)
-+{
-+ cpu_rq(0)->idle->time_slice = sysctl_sched_base_slice;
-+}
-+#endif /* CONFIG_SMP */
-+
-+int in_sched_functions(unsigned long addr)
-+{
-+ return in_lock_functions(addr) ||
-+ (addr >= (unsigned long)__sched_text_start
-+ && addr < (unsigned long)__sched_text_end);
-+}
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+/*
-+ * Default task group.
-+ * Every task in system belongs to this group at bootup.
-+ */
-+struct task_group root_task_group;
-+LIST_HEAD(task_groups);
-+
-+/* Cacheline aligned slab cache for task_group */
-+static struct kmem_cache *task_group_cache __ro_after_init;
-+#endif /* CONFIG_CGROUP_SCHED */
-+
-+void __init sched_init(void)
-+{
-+ int i;
-+ struct rq *rq;
-+#ifdef CONFIG_SCHED_SMT
-+ struct balance_arg balance_arg = {.cpumask = sched_sg_idle_mask, .active = 0};
-+#endif
-+
-+ printk(KERN_INFO "sched/alt: "ALT_SCHED_NAME" CPU Scheduler "ALT_SCHED_VERSION\
-+ " by Alfred Chen.\n");
-+
-+ wait_bit_init();
-+
-+#ifdef CONFIG_SMP
-+ for (i = 0; i < SCHED_QUEUE_BITS; i++)
-+ cpumask_copy(sched_preempt_mask + i, cpu_present_mask);
-+#endif
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+ task_group_cache = KMEM_CACHE(task_group, 0);
-+
-+ list_add(&root_task_group.list, &task_groups);
-+ INIT_LIST_HEAD(&root_task_group.children);
-+ INIT_LIST_HEAD(&root_task_group.siblings);
-+#endif /* CONFIG_CGROUP_SCHED */
-+ for_each_possible_cpu(i) {
-+ rq = cpu_rq(i);
-+
-+ sched_queue_init(&rq->queue);
-+ rq->prio = IDLE_TASK_SCHED_PRIO;
-+#ifdef CONFIG_SCHED_PDS
-+ rq->prio_idx = rq->prio;
-+#endif
-+
-+ raw_spin_lock_init(&rq->lock);
-+ rq->nr_running = rq->nr_uninterruptible = 0;
-+ rq->calc_load_active = 0;
-+ rq->calc_load_update = jiffies + LOAD_FREQ;
-+#ifdef CONFIG_SMP
-+ rq->online = false;
-+ rq->cpu = i;
-+
-+#ifdef CONFIG_SCHED_SMT
-+ rq->sg_balance_arg = balance_arg;
-+#endif
-+
-+#ifdef CONFIG_NO_HZ_COMMON
-+ INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
-+#endif
-+ rq->balance_callback = &balance_push_callback;
-+#ifdef CONFIG_HOTPLUG_CPU
-+ rcuwait_init(&rq->hotplug_wait);
-+#endif
-+#endif /* CONFIG_SMP */
-+ rq->nr_switches = 0;
-+
-+ hrtick_rq_init(rq);
-+ atomic_set(&rq->nr_iowait, 0);
-+
-+ zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
-+ }
-+#ifdef CONFIG_SMP
-+ /* Set rq->online for cpu 0 */
-+ cpu_rq(0)->online = true;
-+#endif
-+ /*
-+ * The boot idle thread does lazy MMU switching as well:
-+ */
-+ mmgrab(&init_mm);
-+ enter_lazy_tlb(&init_mm, current);
-+
-+ /*
-+ * The idle task doesn't need the kthread struct to function, but it
-+ * is dressed up as a per-CPU kthread and thus needs to play the part
-+ * if we want to avoid special-casing it in code that deals with per-CPU
-+ * kthreads.
-+ */
-+ WARN_ON(!set_kthread_struct(current));
-+
-+ /*
-+ * Make us the idle thread. Technically, schedule() should not be
-+ * called from this thread, however somewhere below it might be,
-+ * but because we are the idle thread, we just pick up running again
-+ * when this runqueue becomes "idle".
-+ */
-+ init_idle(current, smp_processor_id());
-+
-+ calc_load_update = jiffies + LOAD_FREQ;
-+
-+#ifdef CONFIG_SMP
-+ idle_thread_set_boot_cpu();
-+ balance_push_set(smp_processor_id(), false);
-+
-+ sched_init_topology_cpumask_early();
-+#endif /* SMP */
-+
-+ preempt_dynamic_init();
-+}
-+
-+#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
-+
-+void __might_sleep(const char *file, int line)
-+{
-+ unsigned int state = get_current_state();
-+ /*
-+ * Blocking primitives will set (and therefore destroy) current->state,
-+ * since we will exit with TASK_RUNNING make sure we enter with it,
-+ * otherwise we will destroy state.
-+ */
-+ WARN_ONCE(state != TASK_RUNNING && current->task_state_change,
-+ "do not call blocking ops when !TASK_RUNNING; "
-+ "state=%x set at [<%p>] %pS\n", state,
-+ (void *)current->task_state_change,
-+ (void *)current->task_state_change);
-+
-+ __might_resched(file, line, 0);
-+}
-+EXPORT_SYMBOL(__might_sleep);
-+
-+static void print_preempt_disable_ip(int preempt_offset, unsigned long ip)
-+{
-+ if (!IS_ENABLED(CONFIG_DEBUG_PREEMPT))
-+ return;
-+
-+ if (preempt_count() == preempt_offset)
-+ return;
-+
-+ pr_err("Preemption disabled at:");
-+ print_ip_sym(KERN_ERR, ip);
-+}
-+
-+static inline bool resched_offsets_ok(unsigned int offsets)
-+{
-+ unsigned int nested = preempt_count();
-+
-+ nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT;
-+
-+ return nested == offsets;
-+}
-+
-+void __might_resched(const char *file, int line, unsigned int offsets)
-+{
-+ /* Ratelimiting timestamp: */
-+ static unsigned long prev_jiffy;
-+
-+ unsigned long preempt_disable_ip;
-+
-+ /* WARN_ON_ONCE() by default, no rate limit required: */
-+ rcu_sleep_check();
-+
-+ if ((resched_offsets_ok(offsets) && !irqs_disabled() &&
-+ !is_idle_task(current) && !current->non_block_count) ||
-+ system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
-+ oops_in_progress)
-+ return;
-+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-+ return;
-+ prev_jiffy = jiffies;
-+
-+ /* Save this before calling printk(), since that will clobber it: */
-+ preempt_disable_ip = get_preempt_disable_ip(current);
-+
-+ pr_err("BUG: sleeping function called from invalid context at %s:%d\n",
-+ file, line);
-+ pr_err("in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
-+ in_atomic(), irqs_disabled(), current->non_block_count,
-+ current->pid, current->comm);
-+ pr_err("preempt_count: %x, expected: %x\n", preempt_count(),
-+ offsets & MIGHT_RESCHED_PREEMPT_MASK);
-+
-+ if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
-+ pr_err("RCU nest depth: %d, expected: %u\n",
-+ rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT);
-+ }
-+
-+ if (task_stack_end_corrupted(current))
-+ pr_emerg("Thread overran stack, or stack corrupted\n");
-+
-+ debug_show_held_locks(current);
-+ if (irqs_disabled())
-+ print_irqtrace_events(current);
-+
-+ print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK,
-+ preempt_disable_ip);
-+
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+EXPORT_SYMBOL(__might_resched);
-+
-+void __cant_sleep(const char *file, int line, int preempt_offset)
-+{
-+ static unsigned long prev_jiffy;
-+
-+ if (irqs_disabled())
-+ return;
-+
-+ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
-+ return;
-+
-+ if (preempt_count() > preempt_offset)
-+ return;
-+
-+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-+ return;
-+ prev_jiffy = jiffies;
-+
-+ printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
-+ printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
-+ in_atomic(), irqs_disabled(),
-+ current->pid, current->comm);
-+
-+ debug_show_held_locks(current);
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+EXPORT_SYMBOL_GPL(__cant_sleep);
-+
-+#ifdef CONFIG_SMP
-+void __cant_migrate(const char *file, int line)
-+{
-+ static unsigned long prev_jiffy;
-+
-+ if (irqs_disabled())
-+ return;
-+
-+ if (is_migration_disabled(current))
-+ return;
-+
-+ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
-+ return;
-+
-+ if (preempt_count() > 0)
-+ return;
-+
-+ if (current->migration_flags & MDF_FORCE_ENABLED)
-+ return;
-+
-+ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
-+ return;
-+ prev_jiffy = jiffies;
-+
-+ pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
-+ pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
-+ in_atomic(), irqs_disabled(), is_migration_disabled(current),
-+ current->pid, current->comm);
-+
-+ debug_show_held_locks(current);
-+ dump_stack();
-+ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
-+}
-+EXPORT_SYMBOL_GPL(__cant_migrate);
-+#endif
-+#endif
-+
-+#ifdef CONFIG_MAGIC_SYSRQ
-+void normalize_rt_tasks(void)
-+{
-+ struct task_struct *g, *p;
-+ struct sched_attr attr = {
-+ .sched_policy = SCHED_NORMAL,
-+ };
-+
-+ read_lock(&tasklist_lock);
-+ for_each_process_thread(g, p) {
-+ /*
-+ * Only normalize user tasks:
-+ */
-+ if (p->flags & PF_KTHREAD)
-+ continue;
-+
-+ schedstat_set(p->stats.wait_start, 0);
-+ schedstat_set(p->stats.sleep_start, 0);
-+ schedstat_set(p->stats.block_start, 0);
-+
-+ if (!rt_task(p)) {
-+ /*
-+ * Renice negative nice level userspace
-+ * tasks back to 0:
-+ */
-+ if (task_nice(p) < 0)
-+ set_user_nice(p, 0);
-+ continue;
-+ }
-+
-+ __sched_setscheduler(p, &attr, false, false);
-+ }
-+ read_unlock(&tasklist_lock);
-+}
-+#endif /* CONFIG_MAGIC_SYSRQ */
-+
-+#if defined(CONFIG_KGDB_KDB)
-+/*
-+ * These functions are only useful for kdb.
-+ *
-+ * They can only be called when the whole system has been
-+ * stopped - every CPU needs to be quiescent, and no scheduling
-+ * activity can take place. Using them for anything else would
-+ * be a serious bug, and as a result, they aren't even visible
-+ * under any other configuration.
-+ */
-+
-+/**
-+ * curr_task - return the current task for a given CPU.
-+ * @cpu: the processor in question.
-+ *
-+ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
-+ *
-+ * Return: The current task for @cpu.
-+ */
-+struct task_struct *curr_task(int cpu)
-+{
-+ return cpu_curr(cpu);
-+}
-+
-+#endif /* defined(CONFIG_KGDB_KDB) */
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+static void sched_free_group(struct task_group *tg)
-+{
-+ kmem_cache_free(task_group_cache, tg);
-+}
-+
-+static void sched_free_group_rcu(struct rcu_head *rhp)
-+{
-+ sched_free_group(container_of(rhp, struct task_group, rcu));
-+}
-+
-+static void sched_unregister_group(struct task_group *tg)
-+{
-+ /*
-+ * We have to wait for yet another RCU grace period to expire, as
-+ * print_cfs_stats() might run concurrently.
-+ */
-+ call_rcu(&tg->rcu, sched_free_group_rcu);
-+}
-+
-+/* allocate runqueue etc for a new task group */
-+struct task_group *sched_create_group(struct task_group *parent)
-+{
-+ struct task_group *tg;
-+
-+ tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
-+ if (!tg)
-+ return ERR_PTR(-ENOMEM);
-+
-+ return tg;
-+}
-+
-+void sched_online_group(struct task_group *tg, struct task_group *parent)
-+{
-+}
-+
-+/* rcu callback to free various structures associated with a task group */
-+static void sched_unregister_group_rcu(struct rcu_head *rhp)
-+{
-+ /* Now it should be safe to free those cfs_rqs: */
-+ sched_unregister_group(container_of(rhp, struct task_group, rcu));
-+}
-+
-+void sched_destroy_group(struct task_group *tg)
-+{
-+ /* Wait for possible concurrent references to cfs_rqs complete: */
-+ call_rcu(&tg->rcu, sched_unregister_group_rcu);
-+}
-+
-+void sched_release_group(struct task_group *tg)
-+{
-+}
-+
-+static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
-+{
-+ return css ? container_of(css, struct task_group, css) : NULL;
-+}
-+
-+static struct cgroup_subsys_state *
-+cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
-+{
-+ struct task_group *parent = css_tg(parent_css);
-+ struct task_group *tg;
-+
-+ if (!parent) {
-+ /* This is early initialization for the top cgroup */
-+ return &root_task_group.css;
-+ }
-+
-+ tg = sched_create_group(parent);
-+ if (IS_ERR(tg))
-+ return ERR_PTR(-ENOMEM);
-+ return &tg->css;
-+}
-+
-+/* Expose task group only after completing cgroup initialization */
-+static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
-+{
-+ struct task_group *tg = css_tg(css);
-+ struct task_group *parent = css_tg(css->parent);
-+
-+ if (parent)
-+ sched_online_group(tg, parent);
-+ return 0;
-+}
-+
-+static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
-+{
-+ struct task_group *tg = css_tg(css);
-+
-+ sched_release_group(tg);
-+}
-+
-+static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
-+{
-+ struct task_group *tg = css_tg(css);
-+
-+ /*
-+ * Relies on the RCU grace period between css_released() and this.
-+ */
-+ sched_unregister_group(tg);
-+}
-+
-+#ifdef CONFIG_RT_GROUP_SCHED
-+static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
-+{
-+ return 0;
-+}
-+#endif
-+
-+static void cpu_cgroup_attach(struct cgroup_taskset *tset)
-+{
-+}
-+
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+static DEFINE_MUTEX(shares_mutex);
-+
-+static int sched_group_set_shares(struct task_group *tg, unsigned long shares)
-+{
-+ /*
-+ * We can't change the weight of the root cgroup.
-+ */
-+ if (&root_task_group == tg)
-+ return -EINVAL;
-+
-+ shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
-+
-+ mutex_lock(&shares_mutex);
-+ if (tg->shares == shares)
-+ goto done;
-+
-+ tg->shares = shares;
-+done:
-+ mutex_unlock(&shares_mutex);
-+ return 0;
-+}
-+
-+static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 shareval)
-+{
-+ if (shareval > scale_load_down(ULONG_MAX))
-+ shareval = MAX_SHARES;
-+ return sched_group_set_shares(css_tg(css), scale_load(shareval));
-+}
-+
-+static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ struct task_group *tg = css_tg(css);
-+
-+ return (u64) scale_load_down(tg->shares);
-+}
-+#endif
-+
-+static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, s64 cfs_quota_us)
-+{
-+ return 0;
-+}
-+
-+static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 cfs_period_us)
-+{
-+ return 0;
-+}
-+
-+static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 cfs_burst_us)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
-+ struct cftype *cft, s64 val)
-+{
-+ return 0;
-+}
-+
-+static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
-+ struct cftype *cftype, u64 rt_period_us)
-+{
-+ return 0;
-+}
-+
-+static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
-+ char *buf, size_t nbytes,
-+ loff_t off)
-+{
-+ return nbytes;
-+}
-+
-+static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
-+ char *buf, size_t nbytes,
-+ loff_t off)
-+{
-+ return nbytes;
-+}
-+
-+static struct cftype cpu_legacy_files[] = {
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+ {
-+ .name = "shares",
-+ .read_u64 = cpu_shares_read_u64,
-+ .write_u64 = cpu_shares_write_u64,
-+ },
-+#endif
-+ {
-+ .name = "cfs_quota_us",
-+ .read_s64 = cpu_cfs_quota_read_s64,
-+ .write_s64 = cpu_cfs_quota_write_s64,
-+ },
-+ {
-+ .name = "cfs_period_us",
-+ .read_u64 = cpu_cfs_period_read_u64,
-+ .write_u64 = cpu_cfs_period_write_u64,
-+ },
-+ {
-+ .name = "cfs_burst_us",
-+ .read_u64 = cpu_cfs_burst_read_u64,
-+ .write_u64 = cpu_cfs_burst_write_u64,
-+ },
-+ {
-+ .name = "stat",
-+ .seq_show = cpu_cfs_stat_show,
-+ },
-+ {
-+ .name = "stat.local",
-+ .seq_show = cpu_cfs_local_stat_show,
-+ },
-+ {
-+ .name = "rt_runtime_us",
-+ .read_s64 = cpu_rt_runtime_read,
-+ .write_s64 = cpu_rt_runtime_write,
-+ },
-+ {
-+ .name = "rt_period_us",
-+ .read_u64 = cpu_rt_period_read_uint,
-+ .write_u64 = cpu_rt_period_write_uint,
-+ },
-+ {
-+ .name = "uclamp.min",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_min_show,
-+ .write = cpu_uclamp_min_write,
-+ },
-+ {
-+ .name = "uclamp.max",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_max_show,
-+ .write = cpu_uclamp_max_write,
-+ },
-+ { } /* Terminate */
-+};
-+
-+static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
-+ struct cftype *cft, u64 weight)
-+{
-+ return 0;
-+}
-+
-+static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft, s64 nice)
-+{
-+ return 0;
-+}
-+
-+static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft)
-+{
-+ return 0;
-+}
-+
-+static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
-+ struct cftype *cft, s64 idle)
-+{
-+ return 0;
-+}
-+
-+static int cpu_max_show(struct seq_file *sf, void *v)
-+{
-+ return 0;
-+}
-+
-+static ssize_t cpu_max_write(struct kernfs_open_file *of,
-+ char *buf, size_t nbytes, loff_t off)
-+{
-+ return nbytes;
-+}
-+
-+static struct cftype cpu_files[] = {
-+ {
-+ .name = "weight",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_u64 = cpu_weight_read_u64,
-+ .write_u64 = cpu_weight_write_u64,
-+ },
-+ {
-+ .name = "weight.nice",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_s64 = cpu_weight_nice_read_s64,
-+ .write_s64 = cpu_weight_nice_write_s64,
-+ },
-+ {
-+ .name = "idle",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_s64 = cpu_idle_read_s64,
-+ .write_s64 = cpu_idle_write_s64,
-+ },
-+ {
-+ .name = "max",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_max_show,
-+ .write = cpu_max_write,
-+ },
-+ {
-+ .name = "max.burst",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .read_u64 = cpu_cfs_burst_read_u64,
-+ .write_u64 = cpu_cfs_burst_write_u64,
-+ },
-+ {
-+ .name = "uclamp.min",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_min_show,
-+ .write = cpu_uclamp_min_write,
-+ },
-+ {
-+ .name = "uclamp.max",
-+ .flags = CFTYPE_NOT_ON_ROOT,
-+ .seq_show = cpu_uclamp_max_show,
-+ .write = cpu_uclamp_max_write,
-+ },
-+ { } /* terminate */
-+};
-+
-+static int cpu_extra_stat_show(struct seq_file *sf,
-+ struct cgroup_subsys_state *css)
-+{
-+ return 0;
-+}
-+
-+static int cpu_local_stat_show(struct seq_file *sf,
-+ struct cgroup_subsys_state *css)
-+{
-+ return 0;
-+}
-+
-+struct cgroup_subsys cpu_cgrp_subsys = {
-+ .css_alloc = cpu_cgroup_css_alloc,
-+ .css_online = cpu_cgroup_css_online,
-+ .css_released = cpu_cgroup_css_released,
-+ .css_free = cpu_cgroup_css_free,
-+ .css_extra_stat_show = cpu_extra_stat_show,
-+ .css_local_stat_show = cpu_local_stat_show,
-+#ifdef CONFIG_RT_GROUP_SCHED
-+ .can_attach = cpu_cgroup_can_attach,
-+#endif
-+ .attach = cpu_cgroup_attach,
-+ .legacy_cftypes = cpu_legacy_files,
-+ .dfl_cftypes = cpu_files,
-+ .early_init = true,
-+ .threaded = true,
-+};
-+#endif /* CONFIG_CGROUP_SCHED */
-+
-+#undef CREATE_TRACE_POINTS
-+
-+#ifdef CONFIG_SCHED_MM_CID
-+
-+#
-+/*
-+ * @cid_lock: Guarantee forward-progress of cid allocation.
-+ *
-+ * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock
-+ * is only used when contention is detected by the lock-free allocation so
-+ * forward progress can be guaranteed.
-+ */
-+DEFINE_RAW_SPINLOCK(cid_lock);
-+
-+/*
-+ * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock.
-+ *
-+ * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is
-+ * detected, it is set to 1 to ensure that all newly coming allocations are
-+ * serialized by @cid_lock until the allocation which detected contention
-+ * completes and sets @use_cid_lock back to 0. This guarantees forward progress
-+ * of a cid allocation.
-+ */
-+int use_cid_lock;
-+
-+/*
-+ * mm_cid remote-clear implements a lock-free algorithm to clear per-mm/cpu cid
-+ * concurrently with respect to the execution of the source runqueue context
-+ * switch.
-+ *
-+ * There is one basic properties we want to guarantee here:
-+ *
-+ * (1) Remote-clear should _never_ mark a per-cpu cid UNSET when it is actively
-+ * used by a task. That would lead to concurrent allocation of the cid and
-+ * userspace corruption.
-+ *
-+ * Provide this guarantee by introducing a Dekker memory ordering to guarantee
-+ * that a pair of loads observe at least one of a pair of stores, which can be
-+ * shown as:
-+ *
-+ * X = Y = 0
-+ *
-+ * w[X]=1 w[Y]=1
-+ * MB MB
-+ * r[Y]=y r[X]=x
-+ *
-+ * Which guarantees that x==0 && y==0 is impossible. But rather than using
-+ * values 0 and 1, this algorithm cares about specific state transitions of the
-+ * runqueue current task (as updated by the scheduler context switch), and the
-+ * per-mm/cpu cid value.
-+ *
-+ * Let's introduce task (Y) which has task->mm == mm and task (N) which has
-+ * task->mm != mm for the rest of the discussion. There are two scheduler state
-+ * transitions on context switch we care about:
-+ *
-+ * (TSA) Store to rq->curr with transition from (N) to (Y)
-+ *
-+ * (TSB) Store to rq->curr with transition from (Y) to (N)
-+ *
-+ * On the remote-clear side, there is one transition we care about:
-+ *
-+ * (TMA) cmpxchg to *pcpu_cid to set the LAZY flag
-+ *
-+ * There is also a transition to UNSET state which can be performed from all
-+ * sides (scheduler, remote-clear). It is always performed with a cmpxchg which
-+ * guarantees that only a single thread will succeed:
-+ *
-+ * (TMB) cmpxchg to *pcpu_cid to mark UNSET
-+ *
-+ * Just to be clear, what we do _not_ want to happen is a transition to UNSET
-+ * when a thread is actively using the cid (property (1)).
-+ *
-+ * Let's looks at the relevant combinations of TSA/TSB, and TMA transitions.
-+ *
-+ * Scenario A) (TSA)+(TMA) (from next task perspective)
-+ *
-+ * CPU0 CPU1
-+ *
-+ * Context switch CS-1 Remote-clear
-+ * - store to rq->curr: (N)->(Y) (TSA) - cmpxchg to *pcpu_id to LAZY (TMA)
-+ * (implied barrier after cmpxchg)
-+ * - switch_mm_cid()
-+ * - memory barrier (see switch_mm_cid()
-+ * comment explaining how this barrier
-+ * is combined with other scheduler
-+ * barriers)
-+ * - mm_cid_get (next)
-+ * - READ_ONCE(*pcpu_cid) - rcu_dereference(src_rq->curr)
-+ *
-+ * This Dekker ensures that either task (Y) is observed by the
-+ * rcu_dereference() or the LAZY flag is observed by READ_ONCE(), or both are
-+ * observed.
-+ *
-+ * If task (Y) store is observed by rcu_dereference(), it means that there is
-+ * still an active task on the cpu. Remote-clear will therefore not transition
-+ * to UNSET, which fulfills property (1).
-+ *
-+ * If task (Y) is not observed, but the lazy flag is observed by READ_ONCE(),
-+ * it will move its state to UNSET, which clears the percpu cid perhaps
-+ * uselessly (which is not an issue for correctness). Because task (Y) is not
-+ * observed, CPU1 can move ahead to set the state to UNSET. Because moving
-+ * state to UNSET is done with a cmpxchg expecting that the old state has the
-+ * LAZY flag set, only one thread will successfully UNSET.
-+ *
-+ * If both states (LAZY flag and task (Y)) are observed, the thread on CPU0
-+ * will observe the LAZY flag and transition to UNSET (perhaps uselessly), and
-+ * CPU1 will observe task (Y) and do nothing more, which is fine.
-+ *
-+ * What we are effectively preventing with this Dekker is a scenario where
-+ * neither LAZY flag nor store (Y) are observed, which would fail property (1)
-+ * because this would UNSET a cid which is actively used.
-+ */
-+
-+void sched_mm_cid_migrate_from(struct task_struct *t)
-+{
-+ t->migrate_from_cpu = task_cpu(t);
-+}
-+
-+static
-+int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
-+ struct task_struct *t,
-+ struct mm_cid *src_pcpu_cid)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct task_struct *src_task;
-+ int src_cid, last_mm_cid;
-+
-+ if (!mm)
-+ return -1;
-+
-+ last_mm_cid = t->last_mm_cid;
-+ /*
-+ * If the migrated task has no last cid, or if the current
-+ * task on src rq uses the cid, it means the source cid does not need
-+ * to be moved to the destination cpu.
-+ */
-+ if (last_mm_cid == -1)
-+ return -1;
-+ src_cid = READ_ONCE(src_pcpu_cid->cid);
-+ if (!mm_cid_is_valid(src_cid) || last_mm_cid != src_cid)
-+ return -1;
-+
-+ /*
-+ * If we observe an active task using the mm on this rq, it means we
-+ * are not the last task to be migrated from this cpu for this mm, so
-+ * there is no need to move src_cid to the destination cpu.
-+ */
-+ rcu_read_lock();
-+ src_task = rcu_dereference(src_rq->curr);
-+ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-+ rcu_read_unlock();
-+ t->last_mm_cid = -1;
-+ return -1;
-+ }
-+ rcu_read_unlock();
-+
-+ return src_cid;
-+}
-+
-+static
-+int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
-+ struct task_struct *t,
-+ struct mm_cid *src_pcpu_cid,
-+ int src_cid)
-+{
-+ struct task_struct *src_task;
-+ struct mm_struct *mm = t->mm;
-+ int lazy_cid;
-+
-+ if (src_cid == -1)
-+ return -1;
-+
-+ /*
-+ * Attempt to clear the source cpu cid to move it to the destination
-+ * cpu.
-+ */
-+ lazy_cid = mm_cid_set_lazy_put(src_cid);
-+ if (!try_cmpxchg(&src_pcpu_cid->cid, &src_cid, lazy_cid))
-+ return -1;
-+
-+ /*
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm matches the scheduler barrier in context_switch()
-+ * between store to rq->curr and load of prev and next task's
-+ * per-mm/cpu cid.
-+ *
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm_cid_active matches the barrier in
-+ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
-+ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
-+ * load of per-mm/cpu cid.
-+ */
-+
-+ /*
-+ * If we observe an active task using the mm on this rq after setting
-+ * the lazy-put flag, this task will be responsible for transitioning
-+ * from lazy-put flag set to MM_CID_UNSET.
-+ */
-+ scoped_guard (rcu) {
-+ src_task = rcu_dereference(src_rq->curr);
-+ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
-+ rcu_read_unlock();
-+ /*
-+ * We observed an active task for this mm, there is therefore
-+ * no point in moving this cid to the destination cpu.
-+ */
-+ t->last_mm_cid = -1;
-+ return -1;
-+ }
-+ }
-+
-+ /*
-+ * The src_cid is unused, so it can be unset.
-+ */
-+ if (!try_cmpxchg(&src_pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
-+ return -1;
-+ return src_cid;
-+}
-+
-+/*
-+ * Migration to dst cpu. Called with dst_rq lock held.
-+ * Interrupts are disabled, which keeps the window of cid ownership without the
-+ * source rq lock held small.
-+ */
-+void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu)
-+{
-+ struct mm_cid *src_pcpu_cid, *dst_pcpu_cid;
-+ struct mm_struct *mm = t->mm;
-+ int src_cid, dst_cid;
-+ struct rq *src_rq;
-+
-+ lockdep_assert_rq_held(dst_rq);
-+
-+ if (!mm)
-+ return;
-+ if (src_cpu == -1) {
-+ t->last_mm_cid = -1;
-+ return;
-+ }
-+ /*
-+ * Move the src cid if the dst cid is unset. This keeps id
-+ * allocation closest to 0 in cases where few threads migrate around
-+ * many cpus.
-+ *
-+ * If destination cid is already set, we may have to just clear
-+ * the src cid to ensure compactness in frequent migrations
-+ * scenarios.
-+ *
-+ * It is not useful to clear the src cid when the number of threads is
-+ * greater or equal to the number of allowed cpus, because user-space
-+ * can expect that the number of allowed cids can reach the number of
-+ * allowed cpus.
-+ */
-+ dst_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(dst_rq));
-+ dst_cid = READ_ONCE(dst_pcpu_cid->cid);
-+ if (!mm_cid_is_unset(dst_cid) &&
-+ atomic_read(&mm->mm_users) >= t->nr_cpus_allowed)
-+ return;
-+ src_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, src_cpu);
-+ src_rq = cpu_rq(src_cpu);
-+ src_cid = __sched_mm_cid_migrate_from_fetch_cid(src_rq, t, src_pcpu_cid);
-+ if (src_cid == -1)
-+ return;
-+ src_cid = __sched_mm_cid_migrate_from_try_steal_cid(src_rq, t, src_pcpu_cid,
-+ src_cid);
-+ if (src_cid == -1)
-+ return;
-+ if (!mm_cid_is_unset(dst_cid)) {
-+ __mm_cid_put(mm, src_cid);
-+ return;
-+ }
-+ /* Move src_cid to dst cpu. */
-+ mm_cid_snapshot_time(dst_rq, mm);
-+ WRITE_ONCE(dst_pcpu_cid->cid, src_cid);
-+}
-+
-+static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_cid,
-+ int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ struct task_struct *t;
-+ int cid, lazy_cid;
-+
-+ cid = READ_ONCE(pcpu_cid->cid);
-+ if (!mm_cid_is_valid(cid))
-+ return;
-+
-+ /*
-+ * Clear the cpu cid if it is set to keep cid allocation compact. If
-+ * there happens to be other tasks left on the source cpu using this
-+ * mm, the next task using this mm will reallocate its cid on context
-+ * switch.
-+ */
-+ lazy_cid = mm_cid_set_lazy_put(cid);
-+ if (!try_cmpxchg(&pcpu_cid->cid, &cid, lazy_cid))
-+ return;
-+
-+ /*
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm matches the scheduler barrier in context_switch()
-+ * between store to rq->curr and load of prev and next task's
-+ * per-mm/cpu cid.
-+ *
-+ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
-+ * rq->curr->mm_cid_active matches the barrier in
-+ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
-+ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
-+ * load of per-mm/cpu cid.
-+ */
-+
-+ /*
-+ * If we observe an active task using the mm on this rq after setting
-+ * the lazy-put flag, that task will be responsible for transitioning
-+ * from lazy-put flag set to MM_CID_UNSET.
-+ */
-+ scoped_guard (rcu) {
-+ t = rcu_dereference(rq->curr);
-+ if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
-+ return;
-+ }
-+
-+ /*
-+ * The cid is unused, so it can be unset.
-+ * Disable interrupts to keep the window of cid ownership without rq
-+ * lock small.
-+ */
-+ scoped_guard (irqsave) {
-+ if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
-+ __mm_cid_put(mm, cid);
-+ }
-+}
-+
-+static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
-+{
-+ struct rq *rq = cpu_rq(cpu);
-+ struct mm_cid *pcpu_cid;
-+ struct task_struct *curr;
-+ u64 rq_clock;
-+
-+ /*
-+ * rq->clock load is racy on 32-bit but one spurious clear once in a
-+ * while is irrelevant.
-+ */
-+ rq_clock = READ_ONCE(rq->clock);
-+ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
-+
-+ /*
-+ * In order to take care of infrequently scheduled tasks, bump the time
-+ * snapshot associated with this cid if an active task using the mm is
-+ * observed on this rq.
-+ */
-+ scoped_guard (rcu) {
-+ curr = rcu_dereference(rq->curr);
-+ if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
-+ WRITE_ONCE(pcpu_cid->time, rq_clock);
-+ return;
-+ }
-+ }
-+
-+ if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
-+ return;
-+ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
-+}
-+
-+static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu,
-+ int weight)
-+{
-+ struct mm_cid *pcpu_cid;
-+ int cid;
-+
-+ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
-+ cid = READ_ONCE(pcpu_cid->cid);
-+ if (!mm_cid_is_valid(cid) || cid < weight)
-+ return;
-+ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
-+}
-+
-+static void task_mm_cid_work(struct callback_head *work)
-+{
-+ unsigned long now = jiffies, old_scan, next_scan;
-+ struct task_struct *t = current;
-+ struct cpumask *cidmask;
-+ struct mm_struct *mm;
-+ int weight, cpu;
-+
-+ SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work));
-+
-+ work->next = work; /* Prevent double-add */
-+ if (t->flags & PF_EXITING)
-+ return;
-+ mm = t->mm;
-+ if (!mm)
-+ return;
-+ old_scan = READ_ONCE(mm->mm_cid_next_scan);
-+ next_scan = now + msecs_to_jiffies(MM_CID_SCAN_DELAY);
-+ if (!old_scan) {
-+ unsigned long res;
-+
-+ res = cmpxchg(&mm->mm_cid_next_scan, old_scan, next_scan);
-+ if (res != old_scan)
-+ old_scan = res;
-+ else
-+ old_scan = next_scan;
-+ }
-+ if (time_before(now, old_scan))
-+ return;
-+ if (!try_cmpxchg(&mm->mm_cid_next_scan, &old_scan, next_scan))
-+ return;
-+ cidmask = mm_cidmask(mm);
-+ /* Clear cids that were not recently used. */
-+ for_each_possible_cpu(cpu)
-+ sched_mm_cid_remote_clear_old(mm, cpu);
-+ weight = cpumask_weight(cidmask);
-+ /*
-+ * Clear cids that are greater or equal to the cidmask weight to
-+ * recompact it.
-+ */
-+ for_each_possible_cpu(cpu)
-+ sched_mm_cid_remote_clear_weight(mm, cpu, weight);
-+}
-+
-+void init_sched_mm_cid(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ int mm_users = 0;
-+
-+ if (mm) {
-+ mm_users = atomic_read(&mm->mm_users);
-+ if (mm_users == 1)
-+ mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY);
-+ }
-+ t->cid_work.next = &t->cid_work; /* Protect against double add */
-+ init_task_work(&t->cid_work, task_mm_cid_work);
-+}
-+
-+void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
-+{
-+ struct callback_head *work = &curr->cid_work;
-+ unsigned long now = jiffies;
-+
-+ if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) ||
-+ work->next != work)
-+ return;
-+ if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan)))
-+ return;
-+ task_work_add(curr, work, TWA_RESUME);
-+}
-+
-+void sched_mm_cid_exit_signals(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct rq *rq;
-+
-+ if (!mm)
-+ return;
-+
-+ preempt_disable();
-+ rq = this_rq();
-+ guard(rq_lock_irqsave)(rq);
-+ preempt_enable_no_resched(); /* holding spinlock */
-+ WRITE_ONCE(t->mm_cid_active, 0);
-+ /*
-+ * Store t->mm_cid_active before loading per-mm/cpu cid.
-+ * Matches barrier in sched_mm_cid_remote_clear_old().
-+ */
-+ smp_mb();
-+ mm_cid_put(mm);
-+ t->last_mm_cid = t->mm_cid = -1;
-+}
-+
-+void sched_mm_cid_before_execve(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct rq *rq;
-+
-+ if (!mm)
-+ return;
-+
-+ preempt_disable();
-+ rq = this_rq();
-+ guard(rq_lock_irqsave)(rq);
-+ preempt_enable_no_resched(); /* holding spinlock */
-+ WRITE_ONCE(t->mm_cid_active, 0);
-+ /*
-+ * Store t->mm_cid_active before loading per-mm/cpu cid.
-+ * Matches barrier in sched_mm_cid_remote_clear_old().
-+ */
-+ smp_mb();
-+ mm_cid_put(mm);
-+ t->last_mm_cid = t->mm_cid = -1;
-+}
-+
-+void sched_mm_cid_after_execve(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct rq *rq;
-+
-+ if (!mm)
-+ return;
-+
-+ preempt_disable();
-+ rq = this_rq();
-+ scoped_guard (rq_lock_irqsave, rq) {
-+ preempt_enable_no_resched(); /* holding spinlock */
-+ WRITE_ONCE(t->mm_cid_active, 1);
-+ /*
-+ * Store t->mm_cid_active before loading per-mm/cpu cid.
-+ * Matches barrier in sched_mm_cid_remote_clear_old().
-+ */
-+ smp_mb();
-+ t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
-+ }
-+ rseq_set_notify_resume(t);
-+}
-+
-+void sched_mm_cid_fork(struct task_struct *t)
-+{
-+ WARN_ON_ONCE(!t->mm || t->mm_cid != -1);
-+ t->mm_cid_active = 1;
-+}
-+#endif
-diff --new-file -rup linux-6.10/kernel/sched/alt_debug.c linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_debug.c
---- linux-6.10/kernel/sched/alt_debug.c 1970-01-01 01:00:00.000000000 +0100
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_debug.c 2024-07-15 16:47:37.000000000 +0200
-@@ -0,0 +1,32 @@
-+/*
-+ * kernel/sched/alt_debug.c
-+ *
-+ * Print the alt scheduler debugging details
-+ *
-+ * Author: Alfred Chen
-+ * Date : 2020
-+ */
-+#include "sched.h"
-+#include "linux/sched/debug.h"
-+
-+/*
-+ * This allows printing both to /proc/sched_debug and
-+ * to the console
-+ */
-+#define SEQ_printf(m, x...) \
-+ do { \
-+ if (m) \
-+ seq_printf(m, x); \
-+ else \
-+ pr_cont(x); \
-+ } while (0)
-+
-+void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
-+ struct seq_file *m)
-+{
-+ SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns),
-+ get_nr_threads(p));
-+}
-+
-+void proc_sched_set_task(struct task_struct *p)
-+{}
-diff --new-file -rup linux-6.10/kernel/sched/alt_sched.h linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_sched.h
---- linux-6.10/kernel/sched/alt_sched.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_sched.h 2024-07-15 16:47:37.000000000 +0200
-@@ -0,0 +1,976 @@
-+#ifndef ALT_SCHED_H
-+#define ALT_SCHED_H
-+
-+#include <linux/context_tracking.h>
-+#include <linux/profile.h>
-+#include <linux/stop_machine.h>
-+#include <linux/syscalls.h>
-+#include <linux/tick.h>
-+
-+#include <trace/events/power.h>
-+#include <trace/events/sched.h>
-+
-+#include "../workqueue_internal.h"
-+
-+#include "cpupri.h"
-+
-+#ifdef CONFIG_CGROUP_SCHED
-+/* task group related information */
-+struct task_group {
-+ struct cgroup_subsys_state css;
-+
-+ struct rcu_head rcu;
-+ struct list_head list;
-+
-+ struct task_group *parent;
-+ struct list_head siblings;
-+ struct list_head children;
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+ unsigned long shares;
-+#endif
-+};
-+
-+extern struct task_group *sched_create_group(struct task_group *parent);
-+extern void sched_online_group(struct task_group *tg,
-+ struct task_group *parent);
-+extern void sched_destroy_group(struct task_group *tg);
-+extern void sched_release_group(struct task_group *tg);
-+#endif /* CONFIG_CGROUP_SCHED */
-+
-+#define MIN_SCHED_NORMAL_PRIO (32)
-+/*
-+ * levels: RT(0-24), reserved(25-31), NORMAL(32-63), cpu idle task(64)
-+ *
-+ * -- BMQ --
-+ * NORMAL: (lower boost range 12, NICE_WIDTH 40, higher boost range 12) / 2
-+ * -- PDS --
-+ * NORMAL: SCHED_EDGE_DELTA + ((NICE_WIDTH 40) / 2)
-+ */
-+#define SCHED_LEVELS (64 + 1)
-+
-+#define IDLE_TASK_SCHED_PRIO (SCHED_LEVELS - 1)
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
-+extern void resched_latency_warn(int cpu, u64 latency);
-+#else
-+# define SCHED_WARN_ON(x) ({ (void)(x), 0; })
-+static inline void resched_latency_warn(int cpu, u64 latency) {}
-+#endif
-+
-+/*
-+ * Increase resolution of nice-level calculations for 64-bit architectures.
-+ * The extra resolution improves shares distribution and load balancing of
-+ * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
-+ * hierarchies, especially on larger systems. This is not a user-visible change
-+ * and does not change the user-interface for setting shares/weights.
-+ *
-+ * We increase resolution only if we have enough bits to allow this increased
-+ * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
-+ * are pretty high and the returns do not justify the increased costs.
-+ *
-+ * Really only required when CONFIG_FAIR_GROUP_SCHED=y is also set, but to
-+ * increase coverage and consistency always enable it on 64-bit platforms.
-+ */
-+#ifdef CONFIG_64BIT
-+# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
-+# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
-+# define scale_load_down(w) \
-+({ \
-+ unsigned long __w = (w); \
-+ if (__w) \
-+ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
-+ __w; \
-+})
-+#else
-+# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
-+# define scale_load(w) (w)
-+# define scale_load_down(w) (w)
-+#endif
-+
-+#ifdef CONFIG_FAIR_GROUP_SCHED
-+#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
-+
-+/*
-+ * A weight of 0 or 1 can cause arithmetics problems.
-+ * A weight of a cfs_rq is the sum of weights of which entities
-+ * are queued on this cfs_rq, so a weight of a entity should not be
-+ * too large, so as the shares value of a task group.
-+ * (The default weight is 1024 - so there's no practical
-+ * limitation from this.)
-+ */
-+#define MIN_SHARES (1UL << 1)
-+#define MAX_SHARES (1UL << 18)
-+#endif
-+
-+/*
-+ * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
-+ */
-+#ifdef CONFIG_SCHED_DEBUG
-+# define const_debug __read_mostly
-+#else
-+# define const_debug const
-+#endif
-+
-+/* task_struct::on_rq states: */
-+#define TASK_ON_RQ_QUEUED 1
-+#define TASK_ON_RQ_MIGRATING 2
-+
-+static inline int task_on_rq_queued(struct task_struct *p)
-+{
-+ return p->on_rq == TASK_ON_RQ_QUEUED;
-+}
-+
-+static inline int task_on_rq_migrating(struct task_struct *p)
-+{
-+ return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
-+}
-+
-+/* Wake flags. The first three directly map to some SD flag value */
-+#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
-+#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
-+#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
-+
-+#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
-+#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
-+#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
-+
-+#ifdef CONFIG_SMP
-+static_assert(WF_EXEC == SD_BALANCE_EXEC);
-+static_assert(WF_FORK == SD_BALANCE_FORK);
-+static_assert(WF_TTWU == SD_BALANCE_WAKE);
-+#endif
-+
-+#define SCHED_QUEUE_BITS (SCHED_LEVELS - 1)
-+
-+struct sched_queue {
-+ DECLARE_BITMAP(bitmap, SCHED_QUEUE_BITS);
-+ struct list_head heads[SCHED_LEVELS];
-+};
-+
-+struct rq;
-+struct cpuidle_state;
-+
-+struct balance_callback {
-+ struct balance_callback *next;
-+ void (*func)(struct rq *rq);
-+};
-+
-+struct balance_arg {
-+ struct task_struct *task;
-+ int active;
-+ cpumask_t *cpumask;
-+};
-+
-+/*
-+ * This is the main, per-CPU runqueue data structure.
-+ * This data should only be modified by the local cpu.
-+ */
-+struct rq {
-+ /* runqueue lock: */
-+ raw_spinlock_t lock;
-+
-+ struct task_struct __rcu *curr;
-+ struct task_struct *idle;
-+ struct task_struct *stop;
-+ struct mm_struct *prev_mm;
-+
-+ struct sched_queue queue ____cacheline_aligned;
-+
-+ int prio;
-+#ifdef CONFIG_SCHED_PDS
-+ int prio_idx;
-+ u64 time_edge;
-+#endif
-+
-+ /* switch count */
-+ u64 nr_switches;
-+
-+ atomic_t nr_iowait;
-+
-+#ifdef CONFIG_SCHED_DEBUG
-+ u64 last_seen_need_resched_ns;
-+ int ticks_without_resched;
-+#endif
-+
-+#ifdef CONFIG_MEMBARRIER
-+ int membarrier_state;
-+#endif
-+
-+#ifdef CONFIG_SMP
-+ int cpu; /* cpu of this runqueue */
-+ bool online;
-+
-+ unsigned int ttwu_pending;
-+ unsigned char nohz_idle_balance;
-+ unsigned char idle_balance;
-+
-+#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
-+ struct sched_avg avg_irq;
-+#endif
-+
-+#ifdef CONFIG_SCHED_SMT
-+ struct balance_arg sg_balance_arg ____cacheline_aligned;
-+#endif
-+ struct cpu_stop_work active_balance_work;
-+
-+ struct balance_callback *balance_callback;
-+#ifdef CONFIG_HOTPLUG_CPU
-+ struct rcuwait hotplug_wait;
-+#endif
-+ unsigned int nr_pinned;
-+
-+#endif /* CONFIG_SMP */
-+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-+ u64 prev_irq_time;
-+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-+#ifdef CONFIG_PARAVIRT
-+ u64 prev_steal_time;
-+#endif /* CONFIG_PARAVIRT */
-+#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
-+ u64 prev_steal_time_rq;
-+#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */
-+
-+ /* For genenal cpu load util */
-+ s32 load_history;
-+ u64 load_block;
-+ u64 load_stamp;
-+
-+ /* calc_load related fields */
-+ unsigned long calc_load_update;
-+ long calc_load_active;
-+
-+ /* Ensure that all clocks are in the same cache line */
-+ u64 clock ____cacheline_aligned;
-+ u64 clock_task;
-+
-+ unsigned int nr_running;
-+ unsigned long nr_uninterruptible;
-+
-+#ifdef CONFIG_SCHED_HRTICK
-+#ifdef CONFIG_SMP
-+ call_single_data_t hrtick_csd;
-+#endif
-+ struct hrtimer hrtick_timer;
-+ ktime_t hrtick_time;
-+#endif
-+
-+#ifdef CONFIG_SCHEDSTATS
-+
-+ /* latency stats */
-+ struct sched_info rq_sched_info;
-+ unsigned long long rq_cpu_time;
-+ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
-+
-+ /* sys_sched_yield() stats */
-+ unsigned int yld_count;
-+
-+ /* schedule() stats */
-+ unsigned int sched_switch;
-+ unsigned int sched_count;
-+ unsigned int sched_goidle;
-+
-+ /* try_to_wake_up() stats */
-+ unsigned int ttwu_count;
-+ unsigned int ttwu_local;
-+#endif /* CONFIG_SCHEDSTATS */
-+
-+#ifdef CONFIG_CPU_IDLE
-+ /* Must be inspected within a rcu lock section */
-+ struct cpuidle_state *idle_state;
-+#endif
-+
-+#ifdef CONFIG_NO_HZ_COMMON
-+#ifdef CONFIG_SMP
-+ call_single_data_t nohz_csd;
-+#endif
-+ atomic_t nohz_flags;
-+#endif /* CONFIG_NO_HZ_COMMON */
-+
-+ /* Scratch cpumask to be temporarily used under rq_lock */
-+ cpumask_var_t scratch_mask;
-+};
-+
-+extern unsigned int sysctl_sched_base_slice;
-+
-+extern unsigned long rq_load_util(struct rq *rq, unsigned long max);
-+
-+extern unsigned long calc_load_update;
-+extern atomic_long_t calc_load_tasks;
-+
-+extern void calc_global_load_tick(struct rq *this_rq);
-+extern long calc_load_fold_active(struct rq *this_rq, long adjust);
-+
-+DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
-+#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
-+#define this_rq() this_cpu_ptr(&runqueues)
-+#define task_rq(p) cpu_rq(task_cpu(p))
-+#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
-+#define raw_rq() raw_cpu_ptr(&runqueues)
-+
-+#ifdef CONFIG_SMP
-+#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
-+void register_sched_domain_sysctl(void);
-+void unregister_sched_domain_sysctl(void);
-+#else
-+static inline void register_sched_domain_sysctl(void)
-+{
-+}
-+static inline void unregister_sched_domain_sysctl(void)
-+{
-+}
-+#endif
-+
-+extern bool sched_smp_initialized;
-+
-+enum {
-+#ifdef CONFIG_SCHED_SMT
-+ SMT_LEVEL_SPACE_HOLDER,
-+#endif
-+ COREGROUP_LEVEL_SPACE_HOLDER,
-+ CORE_LEVEL_SPACE_HOLDER,
-+ OTHER_LEVEL_SPACE_HOLDER,
-+ NR_CPU_AFFINITY_LEVELS
-+};
-+
-+DECLARE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
-+
-+static inline int
-+__best_mask_cpu(const cpumask_t *cpumask, const cpumask_t *mask)
-+{
-+ int cpu;
-+
-+ while ((cpu = cpumask_any_and(cpumask, mask)) >= nr_cpu_ids)
-+ mask++;
-+
-+ return cpu;
-+}
-+
-+static inline int best_mask_cpu(int cpu, const cpumask_t *mask)
-+{
-+ return __best_mask_cpu(mask, per_cpu(sched_cpu_topo_masks, cpu));
-+}
-+
-+#endif
-+
-+#ifndef arch_scale_freq_tick
-+static __always_inline
-+void arch_scale_freq_tick(void)
-+{
-+}
-+#endif
-+
-+#ifndef arch_scale_freq_capacity
-+static __always_inline
-+unsigned long arch_scale_freq_capacity(int cpu)
-+{
-+ return SCHED_CAPACITY_SCALE;
-+}
-+#endif
-+
-+static inline u64 __rq_clock_broken(struct rq *rq)
-+{
-+ return READ_ONCE(rq->clock);
-+}
-+
-+static inline u64 rq_clock(struct rq *rq)
-+{
-+ /*
-+ * Relax lockdep_assert_held() checking as in VRQ, call to
-+ * sched_info_xxxx() may not held rq->lock
-+ * lockdep_assert_held(&rq->lock);
-+ */
-+ return rq->clock;
-+}
-+
-+static inline u64 rq_clock_task(struct rq *rq)
-+{
-+ /*
-+ * Relax lockdep_assert_held() checking as in VRQ, call to
-+ * sched_info_xxxx() may not held rq->lock
-+ * lockdep_assert_held(&rq->lock);
-+ */
-+ return rq->clock_task;
-+}
-+
-+/*
-+ * {de,en}queue flags:
-+ *
-+ * DEQUEUE_SLEEP - task is no longer runnable
-+ * ENQUEUE_WAKEUP - task just became runnable
-+ *
-+ */
-+
-+#define DEQUEUE_SLEEP 0x01
-+
-+#define ENQUEUE_WAKEUP 0x01
-+
-+
-+/*
-+ * Below are scheduler API which using in other kernel code
-+ * It use the dummy rq_flags
-+ * ToDo : BMQ need to support these APIs for compatibility with mainline
-+ * scheduler code.
-+ */
-+struct rq_flags {
-+ unsigned long flags;
-+};
-+
-+struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(rq->lock);
-+
-+struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
-+ __acquires(p->pi_lock)
-+ __acquires(rq->lock);
-+
-+static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+static inline void
-+task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
-+ __releases(rq->lock)
-+ __releases(p->pi_lock)
-+{
-+ raw_spin_unlock(&rq->lock);
-+ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
-+}
-+
-+static inline void
-+rq_lock(struct rq *rq, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ raw_spin_lock(&rq->lock);
-+}
-+
-+static inline void
-+rq_unlock(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock(&rq->lock);
-+}
-+
-+static inline void
-+rq_lock_irq(struct rq *rq, struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ raw_spin_lock_irq(&rq->lock);
-+}
-+
-+static inline void
-+rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
-+ __releases(rq->lock)
-+{
-+ raw_spin_unlock_irq(&rq->lock);
-+}
-+
-+static inline struct rq *
-+this_rq_lock_irq(struct rq_flags *rf)
-+ __acquires(rq->lock)
-+{
-+ struct rq *rq;
-+
-+ local_irq_disable();
-+ rq = this_rq();
-+ raw_spin_lock(&rq->lock);
-+
-+ return rq;
-+}
-+
-+static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
-+{
-+ return &rq->lock;
-+}
-+
-+static inline raw_spinlock_t *rq_lockp(struct rq *rq)
-+{
-+ return __rq_lockp(rq);
-+}
-+
-+static inline void lockdep_assert_rq_held(struct rq *rq)
-+{
-+ lockdep_assert_held(__rq_lockp(rq));
-+}
-+
-+extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
-+extern void raw_spin_rq_unlock(struct rq *rq);
-+
-+static inline void raw_spin_rq_lock(struct rq *rq)
-+{
-+ raw_spin_rq_lock_nested(rq, 0);
-+}
-+
-+static inline void raw_spin_rq_lock_irq(struct rq *rq)
-+{
-+ local_irq_disable();
-+ raw_spin_rq_lock(rq);
-+}
-+
-+static inline void raw_spin_rq_unlock_irq(struct rq *rq)
-+{
-+ raw_spin_rq_unlock(rq);
-+ local_irq_enable();
-+}
-+
-+static inline int task_current(struct rq *rq, struct task_struct *p)
-+{
-+ return rq->curr == p;
-+}
-+
-+static inline bool task_on_cpu(struct task_struct *p)
-+{
-+ return p->on_cpu;
-+}
-+
-+extern int task_running_nice(struct task_struct *p);
-+
-+extern struct static_key_false sched_schedstats;
-+
-+#ifdef CONFIG_CPU_IDLE
-+static inline void idle_set_state(struct rq *rq,
-+ struct cpuidle_state *idle_state)
-+{
-+ rq->idle_state = idle_state;
-+}
-+
-+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
-+{
-+ WARN_ON(!rcu_read_lock_held());
-+ return rq->idle_state;
-+}
-+#else
-+static inline void idle_set_state(struct rq *rq,
-+ struct cpuidle_state *idle_state)
-+{
-+}
-+
-+static inline struct cpuidle_state *idle_get_state(struct rq *rq)
-+{
-+ return NULL;
-+}
-+#endif
-+
-+static inline int cpu_of(const struct rq *rq)
-+{
-+#ifdef CONFIG_SMP
-+ return rq->cpu;
-+#else
-+ return 0;
-+#endif
-+}
-+
-+extern void resched_cpu(int cpu);
-+
-+#include "stats.h"
-+
-+#ifdef CONFIG_NO_HZ_COMMON
-+#define NOHZ_BALANCE_KICK_BIT 0
-+#define NOHZ_STATS_KICK_BIT 1
-+
-+#define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT)
-+#define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT)
-+
-+#define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
-+
-+#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
-+
-+/* TODO: needed?
-+extern void nohz_balance_exit_idle(struct rq *rq);
-+#else
-+static inline void nohz_balance_exit_idle(struct rq *rq) { }
-+*/
-+#endif
-+
-+#ifdef CONFIG_IRQ_TIME_ACCOUNTING
-+struct irqtime {
-+ u64 total;
-+ u64 tick_delta;
-+ u64 irq_start_time;
-+ struct u64_stats_sync sync;
-+};
-+
-+DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
-+
-+/*
-+ * Returns the irqtime minus the softirq time computed by ksoftirqd.
-+ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
-+ * and never move forward.
-+ */
-+static inline u64 irq_time_read(int cpu)
-+{
-+ struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
-+ unsigned int seq;
-+ u64 total;
-+
-+ do {
-+ seq = __u64_stats_fetch_begin(&irqtime->sync);
-+ total = irqtime->total;
-+ } while (__u64_stats_fetch_retry(&irqtime->sync, seq));
-+
-+ return total;
-+}
-+#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
-+
-+#ifdef CONFIG_CPU_FREQ
-+DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
-+#endif /* CONFIG_CPU_FREQ */
-+
-+#ifdef CONFIG_NO_HZ_FULL
-+extern int __init sched_tick_offload_init(void);
-+#else
-+static inline int sched_tick_offload_init(void) { return 0; }
-+#endif
-+
-+#ifdef arch_scale_freq_capacity
-+#ifndef arch_scale_freq_invariant
-+#define arch_scale_freq_invariant() (true)
-+#endif
-+#else /* arch_scale_freq_capacity */
-+#define arch_scale_freq_invariant() (false)
-+#endif
-+
-+#ifdef CONFIG_SMP
-+unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
-+ unsigned long min,
-+ unsigned long max);
-+#endif /* CONFIG_SMP */
-+
-+extern void schedule_idle(void);
-+
-+#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
-+
-+/*
-+ * !! For sched_setattr_nocheck() (kernel) only !!
-+ *
-+ * This is actually gross. :(
-+ *
-+ * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE
-+ * tasks, but still be able to sleep. We need this on platforms that cannot
-+ * atomically change clock frequency. Remove once fast switching will be
-+ * available on such platforms.
-+ *
-+ * SUGOV stands for SchedUtil GOVernor.
-+ */
-+#define SCHED_FLAG_SUGOV 0x10000000
-+
-+#ifdef CONFIG_MEMBARRIER
-+/*
-+ * The scheduler provides memory barriers required by membarrier between:
-+ * - prior user-space memory accesses and store to rq->membarrier_state,
-+ * - store to rq->membarrier_state and following user-space memory accesses.
-+ * In the same way it provides those guarantees around store to rq->curr.
-+ */
-+static inline void membarrier_switch_mm(struct rq *rq,
-+ struct mm_struct *prev_mm,
-+ struct mm_struct *next_mm)
-+{
-+ int membarrier_state;
-+
-+ if (prev_mm == next_mm)
-+ return;
-+
-+ membarrier_state = atomic_read(&next_mm->membarrier_state);
-+ if (READ_ONCE(rq->membarrier_state) == membarrier_state)
-+ return;
-+
-+ WRITE_ONCE(rq->membarrier_state, membarrier_state);
-+}
-+#else
-+static inline void membarrier_switch_mm(struct rq *rq,
-+ struct mm_struct *prev_mm,
-+ struct mm_struct *next_mm)
-+{
-+}
-+#endif
-+
-+#ifdef CONFIG_NUMA
-+extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
-+#else
-+static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
-+{
-+ return nr_cpu_ids;
-+}
-+#endif
-+
-+extern void swake_up_all_locked(struct swait_queue_head *q);
-+extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
-+
-+extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
-+
-+#ifdef CONFIG_PREEMPT_DYNAMIC
-+extern int preempt_dynamic_mode;
-+extern int sched_dynamic_mode(const char *str);
-+extern void sched_dynamic_update(int mode);
-+#endif
-+
-+static inline void nohz_run_idle_balance(int cpu) { }
-+
-+static inline
-+unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
-+ struct task_struct *p)
-+{
-+ return util;
-+}
-+
-+static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
-+
-+#ifdef CONFIG_SCHED_MM_CID
-+
-+#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */
-+#define MM_CID_SCAN_DELAY 100 /* 100ms */
-+
-+extern raw_spinlock_t cid_lock;
-+extern int use_cid_lock;
-+
-+extern void sched_mm_cid_migrate_from(struct task_struct *t);
-+extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu);
-+extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr);
-+extern void init_sched_mm_cid(struct task_struct *t);
-+
-+static inline void __mm_cid_put(struct mm_struct *mm, int cid)
-+{
-+ if (cid < 0)
-+ return;
-+ cpumask_clear_cpu(cid, mm_cidmask(mm));
-+}
-+
-+/*
-+ * The per-mm/cpu cid can have the MM_CID_LAZY_PUT flag set or transition to
-+ * the MM_CID_UNSET state without holding the rq lock, but the rq lock needs to
-+ * be held to transition to other states.
-+ *
-+ * State transitions synchronized with cmpxchg or try_cmpxchg need to be
-+ * consistent across cpus, which prevents use of this_cpu_cmpxchg.
-+ */
-+static inline void mm_cid_put_lazy(struct task_struct *t)
-+{
-+ struct mm_struct *mm = t->mm;
-+ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-+ int cid;
-+
-+ lockdep_assert_irqs_disabled();
-+ cid = __this_cpu_read(pcpu_cid->cid);
-+ if (!mm_cid_is_lazy_put(cid) ||
-+ !try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
-+ return;
-+ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
-+}
-+
-+static inline int mm_cid_pcpu_unset(struct mm_struct *mm)
-+{
-+ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-+ int cid, res;
-+
-+ lockdep_assert_irqs_disabled();
-+ cid = __this_cpu_read(pcpu_cid->cid);
-+ for (;;) {
-+ if (mm_cid_is_unset(cid))
-+ return MM_CID_UNSET;
-+ /*
-+ * Attempt transition from valid or lazy-put to unset.
-+ */
-+ res = cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, cid, MM_CID_UNSET);
-+ if (res == cid)
-+ break;
-+ cid = res;
-+ }
-+ return cid;
-+}
-+
-+static inline void mm_cid_put(struct mm_struct *mm)
-+{
-+ int cid;
-+
-+ lockdep_assert_irqs_disabled();
-+ cid = mm_cid_pcpu_unset(mm);
-+ if (cid == MM_CID_UNSET)
-+ return;
-+ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
-+}
-+
-+static inline int __mm_cid_try_get(struct mm_struct *mm)
-+{
-+ struct cpumask *cpumask;
-+ int cid;
-+
-+ cpumask = mm_cidmask(mm);
-+ /*
-+ * Retry finding first zero bit if the mask is temporarily
-+ * filled. This only happens during concurrent remote-clear
-+ * which owns a cid without holding a rq lock.
-+ */
-+ for (;;) {
-+ cid = cpumask_first_zero(cpumask);
-+ if (cid < nr_cpu_ids)
-+ break;
-+ cpu_relax();
-+ }
-+ if (cpumask_test_and_set_cpu(cid, cpumask))
-+ return -1;
-+ return cid;
-+}
-+
-+/*
-+ * Save a snapshot of the current runqueue time of this cpu
-+ * with the per-cpu cid value, allowing to estimate how recently it was used.
-+ */
-+static inline void mm_cid_snapshot_time(struct rq *rq, struct mm_struct *mm)
-+{
-+ struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(rq));
-+
-+ lockdep_assert_rq_held(rq);
-+ WRITE_ONCE(pcpu_cid->time, rq->clock);
-+}
-+
-+static inline int __mm_cid_get(struct rq *rq, struct mm_struct *mm)
-+{
-+ int cid;
-+
-+ /*
-+ * All allocations (even those using the cid_lock) are lock-free. If
-+ * use_cid_lock is set, hold the cid_lock to perform cid allocation to
-+ * guarantee forward progress.
-+ */
-+ if (!READ_ONCE(use_cid_lock)) {
-+ cid = __mm_cid_try_get(mm);
-+ if (cid >= 0)
-+ goto end;
-+ raw_spin_lock(&cid_lock);
-+ } else {
-+ raw_spin_lock(&cid_lock);
-+ cid = __mm_cid_try_get(mm);
-+ if (cid >= 0)
-+ goto unlock;
-+ }
-+
-+ /*
-+ * cid concurrently allocated. Retry while forcing following
-+ * allocations to use the cid_lock to ensure forward progress.
-+ */
-+ WRITE_ONCE(use_cid_lock, 1);
-+ /*
-+ * Set use_cid_lock before allocation. Only care about program order
-+ * because this is only required for forward progress.
-+ */
-+ barrier();
-+ /*
-+ * Retry until it succeeds. It is guaranteed to eventually succeed once
-+ * all newcoming allocations observe the use_cid_lock flag set.
-+ */
-+ do {
-+ cid = __mm_cid_try_get(mm);
-+ cpu_relax();
-+ } while (cid < 0);
-+ /*
-+ * Allocate before clearing use_cid_lock. Only care about
-+ * program order because this is for forward progress.
-+ */
-+ barrier();
-+ WRITE_ONCE(use_cid_lock, 0);
-+unlock:
-+ raw_spin_unlock(&cid_lock);
-+end:
-+ mm_cid_snapshot_time(rq, mm);
-+ return cid;
-+}
-+
-+static inline int mm_cid_get(struct rq *rq, struct mm_struct *mm)
-+{
-+ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
-+ struct cpumask *cpumask;
-+ int cid;
-+
-+ lockdep_assert_rq_held(rq);
-+ cpumask = mm_cidmask(mm);
-+ cid = __this_cpu_read(pcpu_cid->cid);
-+ if (mm_cid_is_valid(cid)) {
-+ mm_cid_snapshot_time(rq, mm);
-+ return cid;
-+ }
-+ if (mm_cid_is_lazy_put(cid)) {
-+ if (try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
-+ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
-+ }
-+ cid = __mm_cid_get(rq, mm);
-+ __this_cpu_write(pcpu_cid->cid, cid);
-+ return cid;
-+}
-+
-+static inline void switch_mm_cid(struct rq *rq,
-+ struct task_struct *prev,
-+ struct task_struct *next)
-+{
-+ /*
-+ * Provide a memory barrier between rq->curr store and load of
-+ * {prev,next}->mm->pcpu_cid[cpu] on rq->curr->mm transition.
-+ *
-+ * Should be adapted if context_switch() is modified.
-+ */
-+ if (!next->mm) { // to kernel
-+ /*
-+ * user -> kernel transition does not guarantee a barrier, but
-+ * we can use the fact that it performs an atomic operation in
-+ * mmgrab().
-+ */
-+ if (prev->mm) // from user
-+ smp_mb__after_mmgrab();
-+ /*
-+ * kernel -> kernel transition does not change rq->curr->mm
-+ * state. It stays NULL.
-+ */
-+ } else { // to user
-+ /*
-+ * kernel -> user transition does not provide a barrier
-+ * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
-+ * Provide it here.
-+ */
-+ if (!prev->mm) // from kernel
-+ smp_mb();
-+ /*
-+ * user -> user transition guarantees a memory barrier through
-+ * switch_mm() when current->mm changes. If current->mm is
-+ * unchanged, no barrier is needed.
-+ */
-+ }
-+ if (prev->mm_cid_active) {
-+ mm_cid_snapshot_time(rq, prev->mm);
-+ mm_cid_put_lazy(prev);
-+ prev->mm_cid = -1;
-+ }
-+ if (next->mm_cid_active)
-+ next->last_mm_cid = next->mm_cid = mm_cid_get(rq, next->mm);
-+}
-+
-+#else
-+static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { }
-+static inline void sched_mm_cid_migrate_from(struct task_struct *t) { }
-+static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu) { }
-+static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
-+static inline void init_sched_mm_cid(struct task_struct *t) { }
-+#endif
-+
-+#ifdef CONFIG_SMP
-+extern struct balance_callback balance_push_callback;
-+
-+static inline void
-+__queue_balance_callback(struct rq *rq,
-+ struct balance_callback *head)
-+{
-+ lockdep_assert_rq_held(rq);
-+
-+ /*
-+ * Don't (re)queue an already queued item; nor queue anything when
-+ * balance_push() is active, see the comment with
-+ * balance_push_callback.
-+ */
-+ if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
-+ return;
-+
-+ head->next = rq->balance_callback;
-+ rq->balance_callback = head;
-+}
-+#endif /* CONFIG_SMP */
-+
-+#endif /* ALT_SCHED_H */
-diff --new-file -rup linux-6.10/kernel/sched/bmq.h linux-prjc-linux-6.10.y-prjc/kernel/sched/bmq.h
---- linux-6.10/kernel/sched/bmq.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/bmq.h 2024-07-15 16:47:37.000000000 +0200
-@@ -0,0 +1,98 @@
-+#define ALT_SCHED_NAME "BMQ"
-+
-+/*
-+ * BMQ only routines
-+ */
-+static inline void boost_task(struct task_struct *p, int n)
-+{
-+ int limit;
-+
-+ switch (p->policy) {
-+ case SCHED_NORMAL:
-+ limit = -MAX_PRIORITY_ADJ;
-+ break;
-+ case SCHED_BATCH:
-+ limit = 0;
-+ break;
-+ default:
-+ return;
-+ }
-+
-+ p->boost_prio = max(limit, p->boost_prio - n);
-+}
-+
-+static inline void deboost_task(struct task_struct *p)
-+{
-+ if (p->boost_prio < MAX_PRIORITY_ADJ)
-+ p->boost_prio++;
-+}
-+
-+/*
-+ * Common interfaces
-+ */
-+static inline void sched_timeslice_imp(const int timeslice_ms) {}
-+
-+/* This API is used in task_prio(), return value readed by human users */
-+static inline int
-+task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
-+{
-+ return p->prio + p->boost_prio - MIN_NORMAL_PRIO;
-+}
-+
-+static inline int task_sched_prio(const struct task_struct *p)
-+{
-+ return (p->prio < MIN_NORMAL_PRIO)? (p->prio >> 2) :
-+ MIN_SCHED_NORMAL_PRIO + (p->prio + p->boost_prio - MIN_NORMAL_PRIO) / 2;
-+}
-+
-+#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
-+ prio = task_sched_prio(p); \
-+ idx = prio;
-+
-+static inline int sched_prio2idx(int prio, struct rq *rq)
-+{
-+ return prio;
-+}
-+
-+static inline int sched_idx2prio(int idx, struct rq *rq)
-+{
-+ return idx;
-+}
-+
-+static inline int sched_rq_prio_idx(struct rq *rq)
-+{
-+ return rq->prio;
-+}
-+
-+inline int task_running_nice(struct task_struct *p)
-+{
-+ return (p->prio + p->boost_prio > DEFAULT_PRIO);
-+}
-+
-+static inline void sched_update_rq_clock(struct rq *rq) {}
-+
-+static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
-+{
-+ deboost_task(p);
-+}
-+
-+static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq) {}
-+static void sched_task_fork(struct task_struct *p, struct rq *rq) {}
-+
-+static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
-+{
-+ p->boost_prio = MAX_PRIORITY_ADJ;
-+}
-+
-+static inline void sched_task_ttwu(struct task_struct *p)
-+{
-+ s64 delta = this_rq()->clock_task > p->last_ran;
-+
-+ if (likely(delta > 0))
-+ boost_task(p, delta >> 22);
-+}
-+
-+static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq)
-+{
-+ boost_task(p, 1);
-+}
-diff --new-file -rup linux-6.10/kernel/sched/build_policy.c linux-prjc-linux-6.10.y-prjc/kernel/sched/build_policy.c
---- linux-6.10/kernel/sched/build_policy.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/build_policy.c 2024-07-15 16:47:37.000000000 +0200
-@@ -42,13 +42,19 @@
-
- #include "idle.c"
-
-+#ifndef CONFIG_SCHED_ALT
- #include "rt.c"
-+#endif
-
- #ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- # include "cpudeadline.c"
-+#endif
- # include "pelt.c"
- #endif
-
- #include "cputime.c"
--#include "deadline.c"
-
-+#ifndef CONFIG_SCHED_ALT
-+#include "deadline.c"
-+#endif
-diff --new-file -rup linux-6.10/kernel/sched/build_utility.c linux-prjc-linux-6.10.y-prjc/kernel/sched/build_utility.c
---- linux-6.10/kernel/sched/build_utility.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/build_utility.c 2024-07-15 16:47:37.000000000 +0200
-@@ -84,7 +84,9 @@
-
- #ifdef CONFIG_SMP
- # include "cpupri.c"
-+#ifndef CONFIG_SCHED_ALT
- # include "stop_task.c"
-+#endif
- # include "topology.c"
- #endif
-
-diff --new-file -rup linux-6.10/kernel/sched/cpufreq_schedutil.c linux-prjc-linux-6.10.y-prjc/kernel/sched/cpufreq_schedutil.c
---- linux-6.10/kernel/sched/cpufreq_schedutil.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/cpufreq_schedutil.c 2024-07-15 16:47:37.000000000 +0200
-@@ -197,12 +197,17 @@ unsigned long sugov_effective_cpu_perf(i
-
- static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
- {
-+#ifndef CONFIG_SCHED_ALT
- unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
-
- util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
- util = max(util, boost);
- sg_cpu->bw_min = min;
- sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
-+#else /* CONFIG_SCHED_ALT */
-+ sg_cpu->bw_min = 0;
-+ sg_cpu->util = rq_load_util(cpu_rq(sg_cpu->cpu), arch_scale_cpu_capacity(sg_cpu->cpu));
-+#endif /* CONFIG_SCHED_ALT */
- }
-
- /**
-@@ -343,8 +348,10 @@ static inline bool sugov_cpu_is_busy(str
- */
- static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
- {
-+#ifndef CONFIG_SCHED_ALT
- if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
- sg_cpu->sg_policy->limits_changed = true;
-+#endif
- }
-
- static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
-@@ -676,6 +683,7 @@ static int sugov_kthread_create(struct s
- }
-
- ret = sched_setattr_nocheck(thread, &attr);
-+
- if (ret) {
- kthread_stop(thread);
- pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
-diff --new-file -rup linux-6.10/kernel/sched/cputime.c linux-prjc-linux-6.10.y-prjc/kernel/sched/cputime.c
---- linux-6.10/kernel/sched/cputime.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/cputime.c 2024-07-15 16:47:37.000000000 +0200
-@@ -126,7 +126,7 @@ void account_user_time(struct task_struc
- p->utime += cputime;
- account_group_user_time(p, cputime);
-
-- index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
-+ index = task_running_nice(p) ? CPUTIME_NICE : CPUTIME_USER;
-
- /* Add user time to cpustat. */
- task_group_account_field(p, index, cputime);
-@@ -150,7 +150,7 @@ void account_guest_time(struct task_stru
- p->gtime += cputime;
-
- /* Add guest time to cpustat. */
-- if (task_nice(p) > 0) {
-+ if (task_running_nice(p)) {
- task_group_account_field(p, CPUTIME_NICE, cputime);
- cpustat[CPUTIME_GUEST_NICE] += cputime;
- } else {
-@@ -288,7 +288,7 @@ static inline u64 account_other_time(u64
- #ifdef CONFIG_64BIT
- static inline u64 read_sum_exec_runtime(struct task_struct *t)
- {
-- return t->se.sum_exec_runtime;
-+ return tsk_seruntime(t);
- }
- #else
- static u64 read_sum_exec_runtime(struct task_struct *t)
-@@ -298,7 +298,7 @@ static u64 read_sum_exec_runtime(struct
- struct rq *rq;
-
- rq = task_rq_lock(t, &rf);
-- ns = t->se.sum_exec_runtime;
-+ ns = tsk_seruntime(t);
- task_rq_unlock(rq, t, &rf);
-
- return ns;
-@@ -617,7 +617,7 @@ out:
- void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
- {
- struct task_cputime cputime = {
-- .sum_exec_runtime = p->se.sum_exec_runtime,
-+ .sum_exec_runtime = tsk_seruntime(p),
- };
-
- if (task_cputime(p, &cputime.utime, &cputime.stime))
-diff --new-file -rup linux-6.10/kernel/sched/debug.c linux-prjc-linux-6.10.y-prjc/kernel/sched/debug.c
---- linux-6.10/kernel/sched/debug.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/debug.c 2024-07-15 16:47:37.000000000 +0200
-@@ -7,6 +7,7 @@
- * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
- */
-
-+#ifndef CONFIG_SCHED_ALT
- /*
- * This allows printing both to /sys/kernel/debug/sched/debug and
- * to the console
-@@ -215,6 +216,7 @@ static const struct file_operations sche
- };
-
- #endif /* SMP */
-+#endif /* !CONFIG_SCHED_ALT */
-
- #ifdef CONFIG_PREEMPT_DYNAMIC
-
-@@ -278,6 +280,7 @@ static const struct file_operations sche
-
- #endif /* CONFIG_PREEMPT_DYNAMIC */
-
-+#ifndef CONFIG_SCHED_ALT
- __read_mostly bool sched_debug_verbose;
-
- #ifdef CONFIG_SMP
-@@ -332,6 +335,7 @@ static const struct file_operations sche
- .llseek = seq_lseek,
- .release = seq_release,
- };
-+#endif /* !CONFIG_SCHED_ALT */
-
- static struct dentry *debugfs_sched;
-
-@@ -341,14 +345,17 @@ static __init int sched_init_debug(void)
-
- debugfs_sched = debugfs_create_dir("sched", NULL);
-
-+#ifndef CONFIG_SCHED_ALT
- debugfs_create_file("features", 0644, debugfs_sched, NULL, &sched_feat_fops);
- debugfs_create_file_unsafe("verbose", 0644, debugfs_sched, &sched_debug_verbose, &sched_verbose_fops);
-+#endif /* !CONFIG_SCHED_ALT */
- #ifdef CONFIG_PREEMPT_DYNAMIC
- debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
- #endif
-
- debugfs_create_u32("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
-
-+#ifndef CONFIG_SCHED_ALT
- debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
- debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
-
-@@ -373,11 +380,13 @@ static __init int sched_init_debug(void)
- #endif
-
- debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
-+#endif /* !CONFIG_SCHED_ALT */
-
- return 0;
- }
- late_initcall(sched_init_debug);
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_SMP
-
- static cpumask_var_t sd_sysctl_cpus;
-@@ -1111,6 +1120,7 @@ void proc_sched_set_task(struct task_str
- memset(&p->stats, 0, sizeof(p->stats));
- #endif
- }
-+#endif /* !CONFIG_SCHED_ALT */
-
- void resched_latency_warn(int cpu, u64 latency)
- {
-diff --new-file -rup linux-6.10/kernel/sched/idle.c linux-prjc-linux-6.10.y-prjc/kernel/sched/idle.c
---- linux-6.10/kernel/sched/idle.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/idle.c 2024-07-15 16:47:37.000000000 +0200
-@@ -430,6 +430,7 @@ void cpu_startup_entry(enum cpuhp_state
- do_idle();
- }
-
-+#ifndef CONFIG_SCHED_ALT
- /*
- * idle-task scheduling class.
- */
-@@ -551,3 +552,4 @@ DEFINE_SCHED_CLASS(idle) = {
- .switched_to = switched_to_idle,
- .update_curr = update_curr_idle,
- };
-+#endif
-diff --new-file -rup linux-6.10/kernel/sched/pds.h linux-prjc-linux-6.10.y-prjc/kernel/sched/pds.h
---- linux-6.10/kernel/sched/pds.h 1970-01-01 01:00:00.000000000 +0100
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/pds.h 2024-07-15 16:47:37.000000000 +0200
-@@ -0,0 +1,134 @@
-+#define ALT_SCHED_NAME "PDS"
-+
-+static const u64 RT_MASK = ((1ULL << MIN_SCHED_NORMAL_PRIO) - 1);
-+
-+#define SCHED_NORMAL_PRIO_NUM (32)
-+#define SCHED_EDGE_DELTA (SCHED_NORMAL_PRIO_NUM - NICE_WIDTH / 2)
-+
-+/* PDS assume SCHED_NORMAL_PRIO_NUM is power of 2 */
-+#define SCHED_NORMAL_PRIO_MOD(x) ((x) & (SCHED_NORMAL_PRIO_NUM - 1))
-+
-+/* default time slice 4ms -> shift 22, 2 time slice slots -> shift 23 */
-+static __read_mostly int sched_timeslice_shift = 23;
-+
-+/*
-+ * Common interfaces
-+ */
-+static inline int
-+task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
-+{
-+ u64 sched_dl = max(p->deadline, rq->time_edge);
-+
-+#ifdef ALT_SCHED_DEBUG
-+ if (WARN_ONCE(sched_dl - rq->time_edge > NORMAL_PRIO_NUM - 1,
-+ "pds: task_sched_prio_normal() delta %lld\n", sched_dl - rq->time_edge))
-+ return SCHED_NORMAL_PRIO_NUM - 1;
-+#endif
-+
-+ return sched_dl - rq->time_edge;
-+}
-+
-+static inline int task_sched_prio(const struct task_struct *p)
-+{
-+ return (p->prio < MIN_NORMAL_PRIO) ? (p->prio >> 2) :
-+ MIN_SCHED_NORMAL_PRIO + task_sched_prio_normal(p, task_rq(p));
-+}
-+
-+#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
-+ if (p->prio < MIN_NORMAL_PRIO) { \
-+ prio = p->prio >> 2; \
-+ idx = prio; \
-+ } else { \
-+ u64 sched_dl = max(p->deadline, rq->time_edge); \
-+ prio = MIN_SCHED_NORMAL_PRIO + sched_dl - rq->time_edge; \
-+ idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_dl); \
-+ }
-+
-+static inline int sched_prio2idx(int sched_prio, struct rq *rq)
-+{
-+ return (IDLE_TASK_SCHED_PRIO == sched_prio || sched_prio < MIN_SCHED_NORMAL_PRIO) ?
-+ sched_prio :
-+ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_prio + rq->time_edge);
-+}
-+
-+static inline int sched_idx2prio(int sched_idx, struct rq *rq)
-+{
-+ return (sched_idx < MIN_SCHED_NORMAL_PRIO) ?
-+ sched_idx :
-+ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_idx - rq->time_edge);
-+}
-+
-+static inline int sched_rq_prio_idx(struct rq *rq)
-+{
-+ return rq->prio_idx;
-+}
-+
-+int task_running_nice(struct task_struct *p)
-+{
-+ return (p->prio > DEFAULT_PRIO);
-+}
-+
-+static inline void sched_update_rq_clock(struct rq *rq)
-+{
-+ struct list_head head;
-+ u64 old = rq->time_edge;
-+ u64 now = rq->clock >> sched_timeslice_shift;
-+ u64 prio, delta;
-+ DECLARE_BITMAP(normal, SCHED_QUEUE_BITS);
-+
-+ if (now == old)
-+ return;
-+
-+ rq->time_edge = now;
-+ delta = min_t(u64, SCHED_NORMAL_PRIO_NUM, now - old);
-+ INIT_LIST_HEAD(&head);
-+
-+ prio = MIN_SCHED_NORMAL_PRIO;
-+ for_each_set_bit_from(prio, rq->queue.bitmap, MIN_SCHED_NORMAL_PRIO + delta)
-+ list_splice_tail_init(rq->queue.heads + MIN_SCHED_NORMAL_PRIO +
-+ SCHED_NORMAL_PRIO_MOD(prio + old), &head);
-+
-+ bitmap_shift_right(normal, rq->queue.bitmap, delta, SCHED_QUEUE_BITS);
-+ if (!list_empty(&head)) {
-+ u64 idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(now);
-+
-+ __list_splice(&head, rq->queue.heads + idx, rq->queue.heads[idx].next);
-+ set_bit(MIN_SCHED_NORMAL_PRIO, normal);
-+ }
-+ bitmap_replace(rq->queue.bitmap, normal, rq->queue.bitmap,
-+ (const unsigned long *)&RT_MASK, SCHED_QUEUE_BITS);
-+
-+ if (rq->prio < MIN_SCHED_NORMAL_PRIO || IDLE_TASK_SCHED_PRIO == rq->prio)
-+ return;
-+
-+ rq->prio = max_t(u64, MIN_SCHED_NORMAL_PRIO, rq->prio - delta);
-+ rq->prio_idx = sched_prio2idx(rq->prio, rq);
-+}
-+
-+static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
-+{
-+ if (p->prio >= MIN_NORMAL_PRIO)
-+ p->deadline = rq->time_edge + SCHED_EDGE_DELTA +
-+ (p->static_prio - (MAX_PRIO - NICE_WIDTH)) / 2;
-+}
-+
-+static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq)
-+{
-+ u64 max_dl = rq->time_edge + SCHED_EDGE_DELTA + NICE_WIDTH / 2 - 1;
-+ if (unlikely(p->deadline > max_dl))
-+ p->deadline = max_dl;
-+}
-+
-+static void sched_task_fork(struct task_struct *p, struct rq *rq)
-+{
-+ sched_task_renew(p, rq);
-+}
-+
-+static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
-+{
-+ p->time_slice = sysctl_sched_base_slice;
-+ sched_task_renew(p, rq);
-+}
-+
-+static inline void sched_task_ttwu(struct task_struct *p) {}
-+static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq) {}
-diff --new-file -rup linux-6.10/kernel/sched/pelt.c linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.c
---- linux-6.10/kernel/sched/pelt.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.c 2024-07-15 16:47:37.000000000 +0200
-@@ -266,6 +266,7 @@ ___update_load_avg(struct sched_avg *sa,
- WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
- }
-
-+#ifndef CONFIG_SCHED_ALT
- /*
- * sched_entity:
- *
-@@ -383,8 +384,9 @@ int update_dl_rq_load_avg(u64 now, struc
-
- return 0;
- }
-+#endif
-
--#ifdef CONFIG_SCHED_HW_PRESSURE
-+#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
- /*
- * hardware:
- *
-diff --new-file -rup linux-6.10/kernel/sched/pelt.h linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.h
---- linux-6.10/kernel/sched/pelt.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.h 2024-07-15 16:47:37.000000000 +0200
-@@ -1,13 +1,15 @@
- #ifdef CONFIG_SMP
- #include "sched-pelt.h"
-
-+#ifndef CONFIG_SCHED_ALT
- int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
- int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
- int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
- int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
- int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
-+#endif
-
--#ifdef CONFIG_SCHED_HW_PRESSURE
-+#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
- int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity);
-
- static inline u64 hw_load_avg(struct rq *rq)
-@@ -44,6 +46,7 @@ static inline u32 get_pelt_divider(struc
- return PELT_MIN_DIVIDER + avg->period_contrib;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- static inline void cfs_se_util_change(struct sched_avg *avg)
- {
- unsigned int enqueued;
-@@ -180,9 +183,11 @@ static inline u64 cfs_rq_clock_pelt(stru
- return rq_clock_pelt(rq_of(cfs_rq));
- }
- #endif
-+#endif /* CONFIG_SCHED_ALT */
-
- #else
-
-+#ifndef CONFIG_SCHED_ALT
- static inline int
- update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
- {
-@@ -200,6 +205,7 @@ update_dl_rq_load_avg(u64 now, struct rq
- {
- return 0;
- }
-+#endif
-
- static inline int
- update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
-diff --new-file -rup linux-6.10/kernel/sched/sched.h linux-prjc-linux-6.10.y-prjc/kernel/sched/sched.h
---- linux-6.10/kernel/sched/sched.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/sched.h 2024-07-15 16:47:37.000000000 +0200
-@@ -5,6 +5,10 @@
- #ifndef _KERNEL_SCHED_SCHED_H
- #define _KERNEL_SCHED_SCHED_H
-
-+#ifdef CONFIG_SCHED_ALT
-+#include "alt_sched.h"
-+#else
-+
- #include <linux/sched/affinity.h>
- #include <linux/sched/autogroup.h>
- #include <linux/sched/cpufreq.h>
-@@ -3481,4 +3485,9 @@ static inline void init_sched_mm_cid(str
- extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
- extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
-
-+static inline int task_running_nice(struct task_struct *p)
-+{
-+ return (task_nice(p) > 0);
-+}
-+#endif /* !CONFIG_SCHED_ALT */
- #endif /* _KERNEL_SCHED_SCHED_H */
-diff --new-file -rup linux-6.10/kernel/sched/stats.c linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.c
---- linux-6.10/kernel/sched/stats.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.c 2024-07-15 16:47:37.000000000 +0200
-@@ -125,9 +125,11 @@ static int show_schedstat(struct seq_fil
- } else {
- struct rq *rq;
- #ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- struct sched_domain *sd;
- int dcount = 0;
- #endif
-+#endif
- cpu = (unsigned long)(v - 2);
- rq = cpu_rq(cpu);
-
-@@ -143,6 +145,7 @@ static int show_schedstat(struct seq_fil
- seq_printf(seq, "\n");
-
- #ifdef CONFIG_SMP
-+#ifndef CONFIG_SCHED_ALT
- /* domain-specific stats */
- rcu_read_lock();
- for_each_domain(cpu, sd) {
-@@ -171,6 +174,7 @@ static int show_schedstat(struct seq_fil
- }
- rcu_read_unlock();
- #endif
-+#endif
- }
- return 0;
- }
-diff --new-file -rup linux-6.10/kernel/sched/stats.h linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.h
---- linux-6.10/kernel/sched/stats.h 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.h 2024-07-15 16:47:37.000000000 +0200
-@@ -89,6 +89,7 @@ static inline void rq_sched_info_depart
-
- #endif /* CONFIG_SCHEDSTATS */
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_FAIR_GROUP_SCHED
- struct sched_entity_stats {
- struct sched_entity se;
-@@ -105,6 +106,7 @@ __schedstats_from_se(struct sched_entity
- #endif
- return &task_of(se)->stats;
- }
-+#endif /* CONFIG_SCHED_ALT */
-
- #ifdef CONFIG_PSI
- void psi_task_change(struct task_struct *task, int clear, int set);
-diff --new-file -rup linux-6.10/kernel/sched/topology.c linux-prjc-linux-6.10.y-prjc/kernel/sched/topology.c
---- linux-6.10/kernel/sched/topology.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sched/topology.c 2024-07-15 16:47:37.000000000 +0200
-@@ -3,6 +3,7 @@
- * Scheduler topology setup/handling methods
- */
-
-+#ifndef CONFIG_SCHED_ALT
- #include <linux/bsearch.h>
-
- DEFINE_MUTEX(sched_domains_mutex);
-@@ -1451,8 +1452,10 @@ static void asym_cpu_capacity_scan(void)
- */
-
- static int default_relax_domain_level = -1;
-+#endif /* CONFIG_SCHED_ALT */
- int sched_domain_level_max;
-
-+#ifndef CONFIG_SCHED_ALT
- static int __init setup_relax_domain_level(char *str)
- {
- if (kstrtoint(str, 0, &default_relax_domain_level))
-@@ -1687,6 +1690,7 @@ sd_init(struct sched_domain_topology_lev
-
- return sd;
- }
-+#endif /* CONFIG_SCHED_ALT */
-
- /*
- * Topology list, bottom-up.
-@@ -1723,6 +1727,7 @@ void __init set_sched_topology(struct sc
- sched_domain_topology_saved = NULL;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_NUMA
-
- static const struct cpumask *sd_numa_mask(int cpu)
-@@ -2789,3 +2794,28 @@ void partition_sched_domains(int ndoms_n
- partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
- mutex_unlock(&sched_domains_mutex);
- }
-+#else /* CONFIG_SCHED_ALT */
-+DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
-+
-+void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
-+ struct sched_domain_attr *dattr_new)
-+{}
-+
-+#ifdef CONFIG_NUMA
-+int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
-+{
-+ return best_mask_cpu(cpu, cpus);
-+}
-+
-+int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
-+{
-+ return cpumask_nth(cpu, cpus);
-+}
-+
-+const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops)
-+{
-+ return ERR_PTR(-EOPNOTSUPP);
-+}
-+EXPORT_SYMBOL_GPL(sched_numa_hop_mask);
-+#endif /* CONFIG_NUMA */
-+#endif
-diff --new-file -rup linux-6.10/kernel/sysctl.c linux-prjc-linux-6.10.y-prjc/kernel/sysctl.c
---- linux-6.10/kernel/sysctl.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/sysctl.c 2024-07-15 16:47:37.000000000 +0200
-@@ -92,6 +92,10 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals);
-
- /* Constants used for minimum and maximum */
-
-+#ifdef CONFIG_SCHED_ALT
-+extern int sched_yield_type;
-+#endif
-+
- #ifdef CONFIG_PERF_EVENTS
- static const int six_hundred_forty_kb = 640 * 1024;
- #endif
-@@ -1912,6 +1916,17 @@ static struct ctl_table kern_table[] = {
- .proc_handler = proc_dointvec,
- },
- #endif
-+#ifdef CONFIG_SCHED_ALT
-+ {
-+ .procname = "yield_type",
-+ .data = &sched_yield_type,
-+ .maxlen = sizeof (int),
-+ .mode = 0644,
-+ .proc_handler = &proc_dointvec_minmax,
-+ .extra1 = SYSCTL_ZERO,
-+ .extra2 = SYSCTL_TWO,
-+ },
-+#endif
- #if defined(CONFIG_S390) && defined(CONFIG_SMP)
- {
- .procname = "spin_retry",
-diff --new-file -rup linux-6.10/kernel/time/hrtimer.c linux-prjc-linux-6.10.y-prjc/kernel/time/hrtimer.c
---- linux-6.10/kernel/time/hrtimer.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/time/hrtimer.c 2024-07-15 16:47:37.000000000 +0200
-@@ -2074,8 +2074,10 @@ long hrtimer_nanosleep(ktime_t rqtp, con
- int ret = 0;
- u64 slack;
-
-+#ifndef CONFIG_SCHED_ALT
- slack = current->timer_slack_ns;
-- if (rt_task(current))
-+ if (dl_task(current) || rt_task(current))
-+#endif
- slack = 0;
-
- hrtimer_init_sleeper_on_stack(&t, clockid, mode);
-diff --new-file -rup linux-6.10/kernel/time/posix-cpu-timers.c linux-prjc-linux-6.10.y-prjc/kernel/time/posix-cpu-timers.c
---- linux-6.10/kernel/time/posix-cpu-timers.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/time/posix-cpu-timers.c 2024-07-15 16:47:37.000000000 +0200
-@@ -223,7 +223,7 @@ static void task_sample_cputime(struct t
- u64 stime, utime;
-
- task_cputime(p, &utime, &stime);
-- store_samples(samples, stime, utime, p->se.sum_exec_runtime);
-+ store_samples(samples, stime, utime, tsk_seruntime(p));
- }
-
- static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
-@@ -867,6 +867,7 @@ static void collect_posix_cputimers(stru
- }
- }
-
-+#ifndef CONFIG_SCHED_ALT
- static inline void check_dl_overrun(struct task_struct *tsk)
- {
- if (tsk->dl.dl_overrun) {
-@@ -874,6 +875,7 @@ static inline void check_dl_overrun(stru
- send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
- }
- }
-+#endif
-
- static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
- {
-@@ -901,8 +903,10 @@ static void check_thread_timers(struct t
- u64 samples[CPUCLOCK_MAX];
- unsigned long soft;
-
-+#ifndef CONFIG_SCHED_ALT
- if (dl_task(tsk))
- check_dl_overrun(tsk);
-+#endif
-
- if (expiry_cache_is_inactive(pct))
- return;
-@@ -916,7 +920,7 @@ static void check_thread_timers(struct t
- soft = task_rlimit(tsk, RLIMIT_RTTIME);
- if (soft != RLIM_INFINITY) {
- /* Task RT timeout is accounted in jiffies. RTTIME is usec */
-- unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ);
-+ unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ);
- unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
-
- /* At the hard limit, send SIGKILL. No further action. */
-@@ -1152,8 +1156,10 @@ static inline bool fastpath_timer_check(
- return true;
- }
-
-+#ifndef CONFIG_SCHED_ALT
- if (dl_task(tsk) && tsk->dl.dl_overrun)
- return true;
-+#endif
-
- return false;
- }
-diff --new-file -rup linux-6.10/kernel/trace/trace_selftest.c linux-prjc-linux-6.10.y-prjc/kernel/trace/trace_selftest.c
---- linux-6.10/kernel/trace/trace_selftest.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/trace/trace_selftest.c 2024-07-15 16:47:37.000000000 +0200
-@@ -1155,10 +1155,15 @@ static int trace_wakeup_test_thread(void
- {
- /* Make this a -deadline thread */
- static const struct sched_attr attr = {
-+#ifdef CONFIG_SCHED_ALT
-+ /* No deadline on BMQ/PDS, use RR */
-+ .sched_policy = SCHED_RR,
-+#else
- .sched_policy = SCHED_DEADLINE,
- .sched_runtime = 100000ULL,
- .sched_deadline = 10000000ULL,
- .sched_period = 10000000ULL
-+#endif
- };
- struct wakeup_test_data *x = data;
-
-diff --new-file -rup linux-6.10/kernel/workqueue.c linux-prjc-linux-6.10.y-prjc/kernel/workqueue.c
---- linux-6.10/kernel/workqueue.c 2024-07-15 00:43:32.000000000 +0200
-+++ linux-prjc-linux-6.10.y-prjc/kernel/workqueue.c 2024-07-15 16:47:37.000000000 +0200
-@@ -1248,6 +1248,7 @@ static bool kick_pool(struct worker_pool
-
- p = worker->task;
-
-+#ifndef CONFIG_SCHED_ALT
- #ifdef CONFIG_SMP
- /*
- * Idle @worker is about to execute @work and waking up provides an
-@@ -1277,6 +1278,8 @@ static bool kick_pool(struct worker_pool
- }
- }
- #endif
-+#endif /* !CONFIG_SCHED_ALT */
-+
- wake_up_process(p);
- return true;
- }
-@@ -1405,7 +1408,11 @@ void wq_worker_running(struct task_struc
- * CPU intensive auto-detection cares about how long a work item hogged
- * CPU without sleeping. Reset the starting timestamp on wakeup.
- */
-+#ifdef CONFIG_SCHED_ALT
-+ worker->current_at = worker->task->sched_time;
-+#else
- worker->current_at = worker->task->se.sum_exec_runtime;
-+#endif
-
- WRITE_ONCE(worker->sleeping, 0);
- }
-@@ -1490,7 +1497,11 @@ void wq_worker_tick(struct task_struct *
- * We probably want to make this prettier in the future.
- */
- if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) ||
-+#ifdef CONFIG_SCHED_ALT
-+ worker->task->sched_time - worker->current_at <
-+#else
- worker->task->se.sum_exec_runtime - worker->current_at <
-+#endif
- wq_cpu_intensive_thresh_us * NSEC_PER_USEC)
- return;
-
-@@ -3176,7 +3187,11 @@ __acquires(&pool->lock)
- worker->current_func = work->func;
- worker->current_pwq = pwq;
- if (worker->task)
-+#ifdef CONFIG_SCHED_ALT
-+ worker->current_at = worker->task->sched_time;
-+#else
- worker->current_at = worker->task->se.sum_exec_runtime;
-+#endif
- work_data = *work_data_bits(work);
- worker->current_color = get_work_color(work_data);
-
diff --git a/5021_BMQ-and-PDS-gentoo-defaults.patch b/5021_BMQ-and-PDS-gentoo-defaults.patch
deleted file mode 100644
index 6dc48eec..00000000
--- a/5021_BMQ-and-PDS-gentoo-defaults.patch
+++ /dev/null
@@ -1,13 +0,0 @@
---- a/init/Kconfig 2023-02-13 08:16:09.534315265 -0500
-+++ b/init/Kconfig 2023-02-13 08:17:24.130237204 -0500
-@@ -867,8 +867,9 @@ config UCLAMP_BUCKETS_COUNT
- If in doubt, use the default value.
-
- menuconfig SCHED_ALT
-+ depends on X86_64
- bool "Alternative CPU Schedulers"
-- default y
-+ default n
- help
- This feature enable alternative CPU scheduler"
-
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-24 16:44 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-24 16:44 UTC (permalink / raw
To: gentoo-commits
commit: ca2aa06ff25b1445c67ec2d8940a1336dc5e216f
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Jul 24 16:44:29 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Jul 24 16:44:29 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=ca2aa06f
Remove redundant patch
Removed:
1900_ext4-memtostr_pad-fix.patch
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 ----
1900_ext4-memtostr_pad-fix.patch | 51 ----------------------------------------
2 files changed, 55 deletions(-)
diff --git a/0000_README b/0000_README
index b671bc06..2560b5da 100644
--- a/0000_README
+++ b/0000_README
@@ -59,10 +59,6 @@ Patch: 1730_parisc-Disable-prctl.patch
From: https://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
Desc: prctl: Temporarily disable prctl(PR_SET_MDWE) on parisc
-Patch: 1900_ext4-memtostr_pad-fix.patch
-From: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
-Desc: ext4: use memtostr_pad() for s_volume_name
-
Patch: 2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch
From: https://lore.kernel.org/linux-bluetooth/20190522070540.48895-1-marcel@holtmann.org/raw
Desc: Bluetooth: Check key sizes only when Secure Simple Pairing is enabled. See bug #686758
diff --git a/1900_ext4-memtostr_pad-fix.patch b/1900_ext4-memtostr_pad-fix.patch
deleted file mode 100644
index 1c32fc0c..00000000
--- a/1900_ext4-memtostr_pad-fix.patch
+++ /dev/null
@@ -1,51 +0,0 @@
-From be27cd64461c45a6088a91a04eba5cd44e1767ef Mon Sep 17 00:00:00 2001
-From: Kees Cook <keescook@chromium.org>
-Date: Thu, 23 May 2024 15:54:12 -0700
-Subject: ext4: use memtostr_pad() for s_volume_name
-
-As with the other strings in struct ext4_super_block, s_volume_name is
-not NUL terminated. The other strings were marked in commit 072ebb3bffe6
-("ext4: add nonstring annotations to ext4.h"). Using strscpy() isn't
-the right replacement for strncpy(); it should use memtostr_pad()
-instead.
-
-Reported-by: syzbot+50835f73143cc2905b9e@syzkaller.appspotmail.com
-Closes: https://lore.kernel.org/all/00000000000019f4c00619192c05@google.com/
-Fixes: 744a56389f73 ("ext4: replace deprecated strncpy with alternatives")
-Signed-off-by: Kees Cook <keescook@chromium.org>
-Link: https://patch.msgid.link/20240523225408.work.904-kees@kernel.org
-Signed-off-by: Theodore Ts'o <tytso@mit.edu>
----
- fs/ext4/ext4.h | 2 +-
- fs/ext4/ioctl.c | 2 +-
- 2 files changed, 2 insertions(+), 2 deletions(-)
-
-diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
-index 983dad8c07ecd1..efed7f09876de9 100644
---- a/fs/ext4/ext4.h
-+++ b/fs/ext4/ext4.h
-@@ -1347,7 +1347,7 @@ struct ext4_super_block {
- /*60*/ __le32 s_feature_incompat; /* incompatible feature set */
- __le32 s_feature_ro_compat; /* readonly-compatible feature set */
- /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */
--/*78*/ char s_volume_name[EXT4_LABEL_MAX]; /* volume name */
-+/*78*/ char s_volume_name[EXT4_LABEL_MAX] __nonstring; /* volume name */
- /*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */
- /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */
- /*
-diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
-index dab7acd4970923..e8bf5972dd47bf 100644
---- a/fs/ext4/ioctl.c
-+++ b/fs/ext4/ioctl.c
-@@ -1151,7 +1151,7 @@ static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label
- BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX);
-
- lock_buffer(sbi->s_sbh);
-- strscpy_pad(label, sbi->s_es->s_volume_name);
-+ memtostr_pad(label, sbi->s_es->s_volume_name);
- unlock_buffer(sbi->s_sbh);
-
- if (copy_to_user(user_label, label, sizeof(label)))
---
-cgit 1.2.3-korg
-
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-24 16:43 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-24 16:43 UTC (permalink / raw
To: gentoo-commits
commit: ec4e6ed176fc62390cc62641acf5ad2a33517c8b
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Wed Jul 24 16:42:59 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Wed Jul 24 16:42:59 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=ec4e6ed1
Linux patch 6.10.1
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 +
1001_linux-6.10.1.patch | 342 ++++++++++++++++++++++++++++++++++++++++++++++++
2 files changed, 346 insertions(+)
diff --git a/0000_README b/0000_README
index f46d7e17..b671bc06 100644
--- a/0000_README
+++ b/0000_README
@@ -43,6 +43,10 @@ EXPERIMENTAL
Individual Patch Descriptions:
--------------------------------------------------------------------------
+Patch: 1000_linux-6.10.1.patch
+From: https://www.kernel.org
+Desc: Linux 6.10.1
+
Patch: 1510_fs-enable-link-security-restrictions-by-default.patch
From: http://sources.debian.net/src/linux/3.16.7-ckt4-3/debian/patches/debian/fs-enable-link-security-restrictions-by-default.patch/
Desc: Enable link security restrictions by default.
diff --git a/1001_linux-6.10.1.patch b/1001_linux-6.10.1.patch
new file mode 100644
index 00000000..f0878e5d
--- /dev/null
+++ b/1001_linux-6.10.1.patch
@@ -0,0 +1,342 @@
+diff --git a/Makefile b/Makefile
+index 3d10e3aadeda2..9ae12a6c0ece2 100644
+--- a/Makefile
++++ b/Makefile
+@@ -1,7 +1,7 @@
+ # SPDX-License-Identifier: GPL-2.0
+ VERSION = 6
+ PATCHLEVEL = 10
+-SUBLEVEL = 0
++SUBLEVEL = 1
+ EXTRAVERSION =
+ NAME = Baby Opossum Posse
+
+diff --git a/drivers/char/tpm/tpm2-sessions.c b/drivers/char/tpm/tpm2-sessions.c
+index 2281d55df5456..d3521aadd43ee 100644
+--- a/drivers/char/tpm/tpm2-sessions.c
++++ b/drivers/char/tpm/tpm2-sessions.c
+@@ -746,15 +746,16 @@ int tpm_buf_check_hmac_response(struct tpm_chip *chip, struct tpm_buf *buf,
+ struct tpm2_auth *auth = chip->auth;
+ off_t offset_s, offset_p;
+ u8 rphash[SHA256_DIGEST_SIZE];
+- u32 attrs;
++ u32 attrs, cc;
+ struct sha256_state sctx;
+ u16 tag = be16_to_cpu(head->tag);
+- u32 cc = be32_to_cpu(auth->ordinal);
+ int parm_len, len, i, handles;
+
+ if (!auth)
+ return rc;
+
++ cc = be32_to_cpu(auth->ordinal);
++
+ if (auth->session >= TPM_HEADER_SIZE) {
+ WARN(1, "tpm session not filled correctly\n");
+ goto out;
+diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+index 61a4638d1be2f..237cb1ef79759 100644
+--- a/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
++++ b/drivers/net/wireless/intel/iwlwifi/mvm/tt.c
+@@ -622,7 +622,12 @@ static int iwl_mvm_tzone_get_temp(struct thermal_zone_device *device,
+
+ if (!iwl_mvm_firmware_running(mvm) ||
+ mvm->fwrt.cur_fw_img != IWL_UCODE_REGULAR) {
+- ret = -ENODATA;
++ /*
++ * Tell the core that there is no valid temperature value to
++ * return, but it need not worry about this.
++ */
++ *temperature = THERMAL_TEMP_INVALID;
++ ret = 0;
+ goto out;
+ }
+
+diff --git a/drivers/thermal/thermal_core.c b/drivers/thermal/thermal_core.c
+index ecc748d15eb7c..4e7fec406ee59 100644
+--- a/drivers/thermal/thermal_core.c
++++ b/drivers/thermal/thermal_core.c
+@@ -300,8 +300,6 @@ static void monitor_thermal_zone(struct thermal_zone_device *tz)
+ thermal_zone_device_set_polling(tz, tz->passive_delay_jiffies);
+ else if (tz->polling_delay_jiffies)
+ thermal_zone_device_set_polling(tz, tz->polling_delay_jiffies);
+- else if (tz->temperature == THERMAL_TEMP_INVALID)
+- thermal_zone_device_set_polling(tz, msecs_to_jiffies(THERMAL_RECHECK_DELAY_MS));
+ }
+
+ static struct thermal_governor *thermal_get_tz_governor(struct thermal_zone_device *tz)
+@@ -382,7 +380,7 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
+ td->threshold = trip->temperature;
+
+ if (tz->last_temperature >= old_threshold &&
+- tz->last_temperature != THERMAL_TEMP_INVALID) {
++ tz->last_temperature != THERMAL_TEMP_INIT) {
+ /*
+ * Mitigation is under way, so it needs to stop if the zone
+ * temperature falls below the low temperature of the trip.
+@@ -417,27 +415,6 @@ static void handle_thermal_trip(struct thermal_zone_device *tz,
+ }
+ }
+
+-static void update_temperature(struct thermal_zone_device *tz)
+-{
+- int temp, ret;
+-
+- ret = __thermal_zone_get_temp(tz, &temp);
+- if (ret) {
+- if (ret != -EAGAIN)
+- dev_warn(&tz->device,
+- "failed to read out thermal zone (%d)\n",
+- ret);
+- return;
+- }
+-
+- tz->last_temperature = tz->temperature;
+- tz->temperature = temp;
+-
+- trace_thermal_temperature(tz);
+-
+- thermal_genl_sampling_temp(tz->id, temp);
+-}
+-
+ static void thermal_zone_device_check(struct work_struct *work)
+ {
+ struct thermal_zone_device *tz = container_of(work, struct
+@@ -452,7 +429,7 @@ static void thermal_zone_device_init(struct thermal_zone_device *tz)
+
+ INIT_DELAYED_WORK(&tz->poll_queue, thermal_zone_device_check);
+
+- tz->temperature = THERMAL_TEMP_INVALID;
++ tz->temperature = THERMAL_TEMP_INIT;
+ tz->passive = 0;
+ tz->prev_low_trip = -INT_MAX;
+ tz->prev_high_trip = INT_MAX;
+@@ -501,6 +478,7 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
+ struct thermal_trip_desc *td;
+ LIST_HEAD(way_down_list);
+ LIST_HEAD(way_up_list);
++ int temp, ret;
+
+ if (tz->suspended)
+ return;
+@@ -508,10 +486,29 @@ void __thermal_zone_device_update(struct thermal_zone_device *tz,
+ if (!thermal_zone_device_is_enabled(tz))
+ return;
+
+- update_temperature(tz);
++ ret = __thermal_zone_get_temp(tz, &temp);
++ if (ret) {
++ if (ret != -EAGAIN)
++ dev_info(&tz->device, "Temperature check failed (%d)\n", ret);
+
+- if (tz->temperature == THERMAL_TEMP_INVALID)
++ thermal_zone_device_set_polling(tz, msecs_to_jiffies(THERMAL_RECHECK_DELAY_MS));
++ return;
++ } else if (temp <= THERMAL_TEMP_INVALID) {
++ /*
++ * Special case: No valid temperature value is available, but
++ * the zone owner does not want the core to do anything about
++ * it. Continue regular zone polling if needed, so that this
++ * function can be called again, but skip everything else.
++ */
+ goto monitor;
++ }
++
++ tz->last_temperature = tz->temperature;
++ tz->temperature = temp;
++
++ trace_thermal_temperature(tz);
++
++ thermal_genl_sampling_temp(tz->id, temp);
+
+ __thermal_zone_set_trips(tz);
+
+diff --git a/drivers/thermal/thermal_core.h b/drivers/thermal/thermal_core.h
+index 94eeb4011a481..5afd541d54b0b 100644
+--- a/drivers/thermal/thermal_core.h
++++ b/drivers/thermal/thermal_core.h
+@@ -133,6 +133,9 @@ struct thermal_zone_device {
+ struct thermal_trip_desc trips[] __counted_by(num_trips);
+ };
+
++/* Initial thermal zone temperature. */
++#define THERMAL_TEMP_INIT INT_MIN
++
+ /*
+ * Default delay after a failing thermal zone temperature check before
+ * attempting to check it again.
+diff --git a/drivers/thermal/thermal_helpers.c b/drivers/thermal/thermal_helpers.c
+index d9f4e26ec1257..36f872b840ba8 100644
+--- a/drivers/thermal/thermal_helpers.c
++++ b/drivers/thermal/thermal_helpers.c
+@@ -140,6 +140,8 @@ int thermal_zone_get_temp(struct thermal_zone_device *tz, int *temp)
+ }
+
+ ret = __thermal_zone_get_temp(tz, temp);
++ if (!ret && *temp <= THERMAL_TEMP_INVALID)
++ ret = -ENODATA;
+
+ unlock:
+ mutex_unlock(&tz->lock);
+diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
+index 983dad8c07ecd..efed7f09876de 100644
+--- a/fs/ext4/ext4.h
++++ b/fs/ext4/ext4.h
+@@ -1347,7 +1347,7 @@ struct ext4_super_block {
+ /*60*/ __le32 s_feature_incompat; /* incompatible feature set */
+ __le32 s_feature_ro_compat; /* readonly-compatible feature set */
+ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */
+-/*78*/ char s_volume_name[EXT4_LABEL_MAX]; /* volume name */
++/*78*/ char s_volume_name[EXT4_LABEL_MAX] __nonstring; /* volume name */
+ /*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */
+ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */
+ /*
+diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
+index dab7acd497092..e8bf5972dd47b 100644
+--- a/fs/ext4/ioctl.c
++++ b/fs/ext4/ioctl.c
+@@ -1151,7 +1151,7 @@ static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label
+ BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX);
+
+ lock_buffer(sbi->s_sbh);
+- strscpy_pad(label, sbi->s_es->s_volume_name);
++ memtostr_pad(label, sbi->s_es->s_volume_name);
+ unlock_buffer(sbi->s_sbh);
+
+ if (copy_to_user(user_label, label, sizeof(label)))
+diff --git a/fs/smb/client/cifsfs.c b/fs/smb/client/cifsfs.c
+index 6397fdefd876d..c92937bed1331 100644
+--- a/fs/smb/client/cifsfs.c
++++ b/fs/smb/client/cifsfs.c
+@@ -1359,7 +1359,7 @@ ssize_t cifs_file_copychunk_range(unsigned int xid,
+ target_tcon = tlink_tcon(smb_file_target->tlink);
+
+ if (src_tcon->ses != target_tcon->ses) {
+- cifs_dbg(VFS, "source and target of copy not on same server\n");
++ cifs_dbg(FYI, "source and target of copy not on same server\n");
+ goto out;
+ }
+
+diff --git a/fs/smb/client/file.c b/fs/smb/client/file.c
+index 1374635e89fae..04ec1b9737a89 100644
+--- a/fs/smb/client/file.c
++++ b/fs/smb/client/file.c
+@@ -123,6 +123,11 @@ static void cifs_issue_write(struct netfs_io_subrequest *subreq)
+ goto out;
+ }
+
++static void cifs_netfs_invalidate_cache(struct netfs_io_request *wreq)
++{
++ cifs_invalidate_cache(wreq->inode, 0);
++}
++
+ /*
+ * Split the read up according to how many credits we can get for each piece.
+ * It's okay to sleep here if we need to wait for more credit to become
+@@ -307,6 +312,7 @@ const struct netfs_request_ops cifs_req_ops = {
+ .begin_writeback = cifs_begin_writeback,
+ .prepare_write = cifs_prepare_write,
+ .issue_write = cifs_issue_write,
++ .invalidate_cache = cifs_netfs_invalidate_cache,
+ };
+
+ /*
+@@ -2358,13 +2364,18 @@ void cifs_write_subrequest_terminated(struct cifs_io_subrequest *wdata, ssize_t
+ bool was_async)
+ {
+ struct netfs_io_request *wreq = wdata->rreq;
+- loff_t new_server_eof;
++ struct netfs_inode *ictx = netfs_inode(wreq->inode);
++ loff_t wrend;
+
+ if (result > 0) {
+- new_server_eof = wdata->subreq.start + wdata->subreq.transferred + result;
++ wrend = wdata->subreq.start + wdata->subreq.transferred + result;
+
+- if (new_server_eof > netfs_inode(wreq->inode)->remote_i_size)
+- netfs_resize_file(netfs_inode(wreq->inode), new_server_eof, true);
++ if (wrend > ictx->zero_point &&
++ (wdata->rreq->origin == NETFS_UNBUFFERED_WRITE ||
++ wdata->rreq->origin == NETFS_DIO_WRITE))
++ ictx->zero_point = wrend;
++ if (wrend > ictx->remote_i_size)
++ netfs_resize_file(ictx, wrend, true);
+ }
+
+ netfs_write_subrequest_terminated(&wdata->subreq, result, was_async);
+@@ -2877,6 +2888,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
+ rc = netfs_start_io_direct(inode);
+ if (rc < 0)
+ goto out;
++ rc = -EACCES;
+ down_read(&cinode->lock_sem);
+ if (!cifs_find_lock_conflict(
+ cfile, iocb->ki_pos, iov_iter_count(to),
+@@ -2889,6 +2901,7 @@ cifs_strict_readv(struct kiocb *iocb, struct iov_iter *to)
+ rc = netfs_start_io_read(inode);
+ if (rc < 0)
+ goto out;
++ rc = -EACCES;
+ down_read(&cinode->lock_sem);
+ if (!cifs_find_lock_conflict(
+ cfile, iocb->ki_pos, iov_iter_count(to),
+diff --git a/fs/smb/client/smb2pdu.c b/fs/smb/client/smb2pdu.c
+index 2ae2dbb6202b3..bb84a89e59059 100644
+--- a/fs/smb/client/smb2pdu.c
++++ b/fs/smb/client/smb2pdu.c
+@@ -4859,9 +4859,6 @@ smb2_async_writev(struct cifs_io_subrequest *wdata)
+ struct cifs_io_parms *io_parms = NULL;
+ int credit_request;
+
+- if (!wdata->server || test_bit(NETFS_SREQ_RETRYING, &wdata->subreq.flags))
+- server = wdata->server = cifs_pick_channel(tcon->ses);
+-
+ /*
+ * in future we may get cifs_io_parms passed in from the caller,
+ * but for now we construct it here...
+diff --git a/include/sound/cs35l56.h b/include/sound/cs35l56.h
+index 1a3c6f66f6205..dc627ebf01df8 100644
+--- a/include/sound/cs35l56.h
++++ b/include/sound/cs35l56.h
+@@ -209,7 +209,7 @@
+
+ /* CS35L56_MAIN_RENDER_USER_VOLUME */
+ #define CS35L56_MAIN_RENDER_USER_VOLUME_MIN -400
+-#define CS35L56_MAIN_RENDER_USER_VOLUME_MAX 400
++#define CS35L56_MAIN_RENDER_USER_VOLUME_MAX 48
+ #define CS35L56_MAIN_RENDER_USER_VOLUME_MASK 0x0000FFC0
+ #define CS35L56_MAIN_RENDER_USER_VOLUME_SHIFT 6
+ #define CS35L56_MAIN_RENDER_USER_VOLUME_SIGNBIT 9
+diff --git a/io_uring/kbuf.c b/io_uring/kbuf.c
+index d2945c9c812b5..c95dc1736dd93 100644
+--- a/io_uring/kbuf.c
++++ b/io_uring/kbuf.c
+@@ -657,8 +657,10 @@ static int io_alloc_pbuf_ring(struct io_ring_ctx *ctx,
+ ring_size = reg->ring_entries * sizeof(struct io_uring_buf_ring);
+
+ bl->buf_ring = io_pages_map(&bl->buf_pages, &bl->buf_nr_pages, ring_size);
+- if (!bl->buf_ring)
++ if (IS_ERR(bl->buf_ring)) {
++ bl->buf_ring = NULL;
+ return -ENOMEM;
++ }
+
+ bl->is_buf_ring = 1;
+ bl->is_mmap = 1;
+diff --git a/sound/soc/codecs/cs35l56.c b/sound/soc/codecs/cs35l56.c
+index 758dfdf9d3eac..7f2f2f8c13fae 100644
+--- a/sound/soc/codecs/cs35l56.c
++++ b/sound/soc/codecs/cs35l56.c
+@@ -196,7 +196,11 @@ static const struct snd_kcontrol_new cs35l56_controls[] = {
+ cs35l56_dspwait_get_volsw, cs35l56_dspwait_put_volsw),
+ SOC_SINGLE_S_EXT_TLV("Speaker Volume",
+ CS35L56_MAIN_RENDER_USER_VOLUME,
+- 6, -400, 400, 9, 0,
++ CS35L56_MAIN_RENDER_USER_VOLUME_SHIFT,
++ CS35L56_MAIN_RENDER_USER_VOLUME_MIN,
++ CS35L56_MAIN_RENDER_USER_VOLUME_MAX,
++ CS35L56_MAIN_RENDER_USER_VOLUME_SIGNBIT,
++ 0,
+ cs35l56_dspwait_get_volsw,
+ cs35l56_dspwait_put_volsw,
+ vol_tlv),
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-19 22:35 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-19 22:35 UTC (permalink / raw
To: gentoo-commits
commit: f54ffc75e5aac69d195787d1cebb939136f28b28
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Fri Jul 19 22:35:08 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Fri Jul 19 22:35:08 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=f54ffc75
ext4: use memtostr_pad() for s_volume_name
Bug: https://bugs.gentoo.org/936269
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 4 ++++
1900_ext4-memtostr_pad-fix.patch | 51 ++++++++++++++++++++++++++++++++++++++++
2 files changed, 55 insertions(+)
diff --git a/0000_README b/0000_README
index e017d0cb..f46d7e17 100644
--- a/0000_README
+++ b/0000_README
@@ -55,6 +55,10 @@ Patch: 1730_parisc-Disable-prctl.patch
From: https://git.kernel.org/pub/scm/linux/kernel/git/deller/parisc-linux.git
Desc: prctl: Temporarily disable prctl(PR_SET_MDWE) on parisc
+Patch: 1900_ext4-memtostr_pad-fix.patch
+From: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
+Desc: ext4: use memtostr_pad() for s_volume_name
+
Patch: 2000_BT-Check-key-sizes-only-if-Secure-Simple-Pairing-enabled.patch
From: https://lore.kernel.org/linux-bluetooth/20190522070540.48895-1-marcel@holtmann.org/raw
Desc: Bluetooth: Check key sizes only when Secure Simple Pairing is enabled. See bug #686758
diff --git a/1900_ext4-memtostr_pad-fix.patch b/1900_ext4-memtostr_pad-fix.patch
new file mode 100644
index 00000000..1c32fc0c
--- /dev/null
+++ b/1900_ext4-memtostr_pad-fix.patch
@@ -0,0 +1,51 @@
+From be27cd64461c45a6088a91a04eba5cd44e1767ef Mon Sep 17 00:00:00 2001
+From: Kees Cook <keescook@chromium.org>
+Date: Thu, 23 May 2024 15:54:12 -0700
+Subject: ext4: use memtostr_pad() for s_volume_name
+
+As with the other strings in struct ext4_super_block, s_volume_name is
+not NUL terminated. The other strings were marked in commit 072ebb3bffe6
+("ext4: add nonstring annotations to ext4.h"). Using strscpy() isn't
+the right replacement for strncpy(); it should use memtostr_pad()
+instead.
+
+Reported-by: syzbot+50835f73143cc2905b9e@syzkaller.appspotmail.com
+Closes: https://lore.kernel.org/all/00000000000019f4c00619192c05@google.com/
+Fixes: 744a56389f73 ("ext4: replace deprecated strncpy with alternatives")
+Signed-off-by: Kees Cook <keescook@chromium.org>
+Link: https://patch.msgid.link/20240523225408.work.904-kees@kernel.org
+Signed-off-by: Theodore Ts'o <tytso@mit.edu>
+---
+ fs/ext4/ext4.h | 2 +-
+ fs/ext4/ioctl.c | 2 +-
+ 2 files changed, 2 insertions(+), 2 deletions(-)
+
+diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
+index 983dad8c07ecd1..efed7f09876de9 100644
+--- a/fs/ext4/ext4.h
++++ b/fs/ext4/ext4.h
+@@ -1347,7 +1347,7 @@ struct ext4_super_block {
+ /*60*/ __le32 s_feature_incompat; /* incompatible feature set */
+ __le32 s_feature_ro_compat; /* readonly-compatible feature set */
+ /*68*/ __u8 s_uuid[16]; /* 128-bit uuid for volume */
+-/*78*/ char s_volume_name[EXT4_LABEL_MAX]; /* volume name */
++/*78*/ char s_volume_name[EXT4_LABEL_MAX] __nonstring; /* volume name */
+ /*88*/ char s_last_mounted[64] __nonstring; /* directory where last mounted */
+ /*C8*/ __le32 s_algorithm_usage_bitmap; /* For compression */
+ /*
+diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
+index dab7acd4970923..e8bf5972dd47bf 100644
+--- a/fs/ext4/ioctl.c
++++ b/fs/ext4/ioctl.c
+@@ -1151,7 +1151,7 @@ static int ext4_ioctl_getlabel(struct ext4_sb_info *sbi, char __user *user_label
+ BUILD_BUG_ON(EXT4_LABEL_MAX >= FSLABEL_MAX);
+
+ lock_buffer(sbi->s_sbh);
+- strscpy_pad(label, sbi->s_es->s_volume_name);
++ memtostr_pad(label, sbi->s_es->s_volume_name);
+ unlock_buffer(sbi->s_sbh);
+
+ if (copy_to_user(user_label, label, sizeof(label)))
+--
+cgit 1.2.3-korg
+
^ permalink raw reply related [flat|nested] 37+ messages in thread* [gentoo-commits] proj/linux-patches:6.10 commit in: /
@ 2024-07-15 22:24 Mike Pagano
0 siblings, 0 replies; 37+ messages in thread
From: Mike Pagano @ 2024-07-15 22:24 UTC (permalink / raw
To: gentoo-commits
commit: ebdae207babbfb5ca502863cbc0331dbe5d94a5e
Author: Mike Pagano <mpagano <AT> gentoo <DOT> org>
AuthorDate: Mon Jul 15 22:23:52 2024 +0000
Commit: Mike Pagano <mpagano <AT> gentoo <DOT> org>
CommitDate: Mon Jul 15 22:23:52 2024 +0000
URL: https://gitweb.gentoo.org/proj/linux-patches.git/commit/?id=ebdae207
BMQ Ported to 6.10, thanks to Holger Hoffstätte
Signed-off-by: Mike Pagano <mpagano <AT> gentoo.org>
0000_README | 8 +
...BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch | 11474 +++++++++++++++++++
5021_BMQ-and-PDS-gentoo-defaults.patch | 13 +
3 files changed, 11495 insertions(+)
diff --git a/0000_README b/0000_README
index 887cea4c..e017d0cb 100644
--- a/0000_README
+++ b/0000_README
@@ -82,3 +82,11 @@ Desc: Add Gentoo Linux support config settings and defaults.
Patch: 5010_enable-cpu-optimizations-universal.patch
From: https://github.com/graysky2/kernel_compiler_patch
Desc: Kernel >= 5.15 patch enables gcc = v11.1+ optimizations for additional CPUs.
+
+Patch: 5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch
+From: https://github.com/hhoffstaette/kernel-patches
+Desc: BMQ(BitMap Queue) Scheduler. A new CPU scheduler developed from PDS(incld). Inspired by the scheduler in zircon.
+
+Patch: 5021_BMQ-and-PDS-gentoo-defaults.patch
+From: https://gitweb.gentoo.org/proj/linux-patches.git/
+Desc: Set defaults for BMQ. default to n
diff --git a/5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch b/5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch
new file mode 100644
index 00000000..4ebad9ef
--- /dev/null
+++ b/5020_BMQ-and-PDS-io-scheduler-holgerh-v6.10-r0.patch
@@ -0,0 +1,11474 @@
+diff --new-file -rup linux-6.10/Documentation/admin-guide/sysctl/kernel.rst linux-prjc-linux-6.10.y-prjc/Documentation/admin-guide/sysctl/kernel.rst
+--- linux-6.10/Documentation/admin-guide/sysctl/kernel.rst 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/Documentation/admin-guide/sysctl/kernel.rst 2024-07-15 16:47:37.000000000 +0200
+@@ -1673,3 +1673,12 @@ is 10 seconds.
+
+ The softlockup threshold is (``2 * watchdog_thresh``). Setting this
+ tunable to zero will disable lockup detection altogether.
++
++yield_type:
++===========
++
++BMQ/PDS CPU scheduler only. This determines what type of yield calls
++to sched_yield() will be performed.
++
++ 0 - No yield.
++ 1 - Requeue task. (default)
+diff --new-file -rup linux-6.10/Documentation/scheduler/sched-BMQ.txt linux-prjc-linux-6.10.y-prjc/Documentation/scheduler/sched-BMQ.txt
+--- linux-6.10/Documentation/scheduler/sched-BMQ.txt 1970-01-01 01:00:00.000000000 +0100
++++ linux-prjc-linux-6.10.y-prjc/Documentation/scheduler/sched-BMQ.txt 2024-07-15 16:47:37.000000000 +0200
+@@ -0,0 +1,110 @@
++ BitMap queue CPU Scheduler
++ --------------------------
++
++CONTENT
++========
++
++ Background
++ Design
++ Overview
++ Task policy
++ Priority management
++ BitMap Queue
++ CPU Assignment and Migration
++
++
++Background
++==========
++
++BitMap Queue CPU scheduler, referred to as BMQ from here on, is an evolution
++of previous Priority and Deadline based Skiplist multiple queue scheduler(PDS),
++and inspired by Zircon scheduler. The goal of it is to keep the scheduler code
++simple, while efficiency and scalable for interactive tasks, such as desktop,
++movie playback and gaming etc.
++
++Design
++======
++
++Overview
++--------
++
++BMQ use per CPU run queue design, each CPU(logical) has it's own run queue,
++each CPU is responsible for scheduling the tasks that are putting into it's
++run queue.
++
++The run queue is a set of priority queues. Note that these queues are fifo
++queue for non-rt tasks or priority queue for rt tasks in data structure. See
++BitMap Queue below for details. BMQ is optimized for non-rt tasks in the fact
++that most applications are non-rt tasks. No matter the queue is fifo or
++priority, In each queue is an ordered list of runnable tasks awaiting execution
++and the data structures are the same. When it is time for a new task to run,
++the scheduler simply looks the lowest numbered queueue that contains a task,
++and runs the first task from the head of that queue. And per CPU idle task is
++also in the run queue, so the scheduler can always find a task to run on from
++its run queue.
++
++Each task will assigned the same timeslice(default 4ms) when it is picked to
++start running. Task will be reinserted at the end of the appropriate priority
++queue when it uses its whole timeslice. When the scheduler selects a new task
++from the priority queue it sets the CPU's preemption timer for the remainder of
++the previous timeslice. When that timer fires the scheduler will stop execution
++on that task, select another task and start over again.
++
++If a task blocks waiting for a shared resource then it's taken out of its
++priority queue and is placed in a wait queue for the shared resource. When it
++is unblocked it will be reinserted in the appropriate priority queue of an
++eligible CPU.
++
++Task policy
++-----------
++
++BMQ supports DEADLINE, FIFO, RR, NORMAL, BATCH and IDLE task policy like the
++mainline CFS scheduler. But BMQ is heavy optimized for non-rt task, that's
++NORMAL/BATCH/IDLE policy tasks. Below is the implementation detail of each
++policy.
++
++DEADLINE
++ It is squashed as priority 0 FIFO task.
++
++FIFO/RR
++ All RT tasks share one single priority queue in BMQ run queue designed. The
++complexity of insert operation is O(n). BMQ is not designed for system runs
++with major rt policy tasks.
++
++NORMAL/BATCH/IDLE
++ BATCH and IDLE tasks are treated as the same policy. They compete CPU with
++NORMAL policy tasks, but they just don't boost. To control the priority of
++NORMAL/BATCH/IDLE tasks, simply use nice level.
++
++ISO
++ ISO policy is not supported in BMQ. Please use nice level -20 NORMAL policy
++task instead.
++
++Priority management
++-------------------
++
++RT tasks have priority from 0-99. For non-rt tasks, there are three different
++factors used to determine the effective priority of a task. The effective
++priority being what is used to determine which queue it will be in.
++
++The first factor is simply the task’s static priority. Which is assigned from
++task's nice level, within [-20, 19] in userland's point of view and [0, 39]
++internally.
++
++The second factor is the priority boost. This is a value bounded between
++[-MAX_PRIORITY_ADJ, MAX_PRIORITY_ADJ] used to offset the base priority, it is
++modified by the following cases:
++
++*When a thread has used up its entire timeslice, always deboost its boost by
++increasing by one.
++*When a thread gives up cpu control(voluntary or non-voluntary) to reschedule,
++and its switch-in time(time after last switch and run) below the thredhold
++based on its priority boost, will boost its boost by decreasing by one buti is
++capped at 0 (won’t go negative).
++
++The intent in this system is to ensure that interactive threads are serviced
++quickly. These are usually the threads that interact directly with the user
++and cause user-perceivable latency. These threads usually do little work and
++spend most of their time blocked awaiting another user event. So they get the
++priority boost from unblocking while background threads that do most of the
++processing receive the priority penalty for using their entire timeslice.
+diff --new-file -rup linux-6.10/fs/proc/base.c linux-prjc-linux-6.10.y-prjc/fs/proc/base.c
+--- linux-6.10/fs/proc/base.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/fs/proc/base.c 2024-07-15 16:47:37.000000000 +0200
+@@ -481,7 +481,7 @@ static int proc_pid_schedstat(struct seq
+ seq_puts(m, "0 0 0\n");
+ else
+ seq_printf(m, "%llu %llu %lu\n",
+- (unsigned long long)task->se.sum_exec_runtime,
++ (unsigned long long)tsk_seruntime(task),
+ (unsigned long long)task->sched_info.run_delay,
+ task->sched_info.pcount);
+
+diff --new-file -rup linux-6.10/include/asm-generic/resource.h linux-prjc-linux-6.10.y-prjc/include/asm-generic/resource.h
+--- linux-6.10/include/asm-generic/resource.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/include/asm-generic/resource.h 2024-07-15 16:47:37.000000000 +0200
+@@ -23,7 +23,7 @@
+ [RLIMIT_LOCKS] = { RLIM_INFINITY, RLIM_INFINITY }, \
+ [RLIMIT_SIGPENDING] = { 0, 0 }, \
+ [RLIMIT_MSGQUEUE] = { MQ_BYTES_MAX, MQ_BYTES_MAX }, \
+- [RLIMIT_NICE] = { 0, 0 }, \
++ [RLIMIT_NICE] = { 30, 30 }, \
+ [RLIMIT_RTPRIO] = { 0, 0 }, \
+ [RLIMIT_RTTIME] = { RLIM_INFINITY, RLIM_INFINITY }, \
+ }
+diff --new-file -rup linux-6.10/include/linux/sched/deadline.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/deadline.h
+--- linux-6.10/include/linux/sched/deadline.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/deadline.h 2024-07-15 16:47:37.000000000 +0200
+@@ -2,6 +2,25 @@
+ #ifndef _LINUX_SCHED_DEADLINE_H
+ #define _LINUX_SCHED_DEADLINE_H
+
++#ifdef CONFIG_SCHED_ALT
++
++static inline int dl_task(struct task_struct *p)
++{
++ return 0;
++}
++
++#ifdef CONFIG_SCHED_BMQ
++#define __tsk_deadline(p) (0UL)
++#endif
++
++#ifdef CONFIG_SCHED_PDS
++#define __tsk_deadline(p) ((((u64) ((p)->prio))<<56) | (p)->deadline)
++#endif
++
++#else
++
++#define __tsk_deadline(p) ((p)->dl.deadline)
++
+ /*
+ * SCHED_DEADLINE tasks has negative priorities, reflecting
+ * the fact that any of them has higher prio than RT and
+@@ -23,6 +42,7 @@ static inline int dl_task(struct task_st
+ {
+ return dl_prio(p->prio);
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ static inline bool dl_time_before(u64 a, u64 b)
+ {
+diff --new-file -rup linux-6.10/include/linux/sched/prio.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/prio.h
+--- linux-6.10/include/linux/sched/prio.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/prio.h 2024-07-15 16:47:37.000000000 +0200
+@@ -18,6 +18,28 @@
+ #define MAX_PRIO (MAX_RT_PRIO + NICE_WIDTH)
+ #define DEFAULT_PRIO (MAX_RT_PRIO + NICE_WIDTH / 2)
+
++#ifdef CONFIG_SCHED_ALT
++
++/* Undefine MAX_PRIO and DEFAULT_PRIO */
++#undef MAX_PRIO
++#undef DEFAULT_PRIO
++
++/* +/- priority levels from the base priority */
++#ifdef CONFIG_SCHED_BMQ
++#define MAX_PRIORITY_ADJ (12)
++#endif
++
++#ifdef CONFIG_SCHED_PDS
++#define MAX_PRIORITY_ADJ (0)
++#endif
++
++#define MIN_NORMAL_PRIO (128)
++#define NORMAL_PRIO_NUM (64)
++#define MAX_PRIO (MIN_NORMAL_PRIO + NORMAL_PRIO_NUM)
++#define DEFAULT_PRIO (MAX_PRIO - MAX_PRIORITY_ADJ - NICE_WIDTH / 2)
++
++#endif /* CONFIG_SCHED_ALT */
++
+ /*
+ * Convert user-nice values [ -20 ... 0 ... 19 ]
+ * to static priority [ MAX_RT_PRIO..MAX_PRIO-1 ],
+diff --new-file -rup linux-6.10/include/linux/sched/rt.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/rt.h
+--- linux-6.10/include/linux/sched/rt.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/rt.h 2024-07-15 16:47:37.000000000 +0200
+@@ -24,8 +24,10 @@ static inline bool task_is_realtime(stru
+
+ if (policy == SCHED_FIFO || policy == SCHED_RR)
+ return true;
++#ifndef CONFIG_SCHED_ALT
+ if (policy == SCHED_DEADLINE)
+ return true;
++#endif
+ return false;
+ }
+
+diff --new-file -rup linux-6.10/include/linux/sched/topology.h linux-prjc-linux-6.10.y-prjc/include/linux/sched/topology.h
+--- linux-6.10/include/linux/sched/topology.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/include/linux/sched/topology.h 2024-07-15 16:47:37.000000000 +0200
+@@ -244,7 +244,8 @@ static inline bool cpus_share_resources(
+
+ #endif /* !CONFIG_SMP */
+
+-#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL)
++#if defined(CONFIG_ENERGY_MODEL) && defined(CONFIG_CPU_FREQ_GOV_SCHEDUTIL) && \
++ !defined(CONFIG_SCHED_ALT)
+ extern void rebuild_sched_domains_energy(void);
+ #else
+ static inline void rebuild_sched_domains_energy(void)
+diff --new-file -rup linux-6.10/include/linux/sched.h linux-prjc-linux-6.10.y-prjc/include/linux/sched.h
+--- linux-6.10/include/linux/sched.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/include/linux/sched.h 2024-07-15 16:47:37.000000000 +0200
+@@ -774,9 +774,16 @@ struct task_struct {
+ struct alloc_tag *alloc_tag;
+ #endif
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) || defined(CONFIG_SCHED_ALT)
+ int on_cpu;
++#endif
++
++#if defined(CONFIG_SMP) && defined(CONFIG_SCHED_ALT)
+ struct __call_single_node wake_entry;
++#endif
++
++#ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ unsigned int wakee_flips;
+ unsigned long wakee_flip_decay_ts;
+ struct task_struct *last_wakee;
+@@ -790,6 +797,7 @@ struct task_struct {
+ */
+ int recent_used_cpu;
+ int wake_cpu;
++#endif /* !CONFIG_SCHED_ALT */
+ #endif
+ int on_rq;
+
+@@ -798,6 +806,19 @@ struct task_struct {
+ int normal_prio;
+ unsigned int rt_priority;
+
++#ifdef CONFIG_SCHED_ALT
++ u64 last_ran;
++ s64 time_slice;
++ struct list_head sq_node;
++#ifdef CONFIG_SCHED_BMQ
++ int boost_prio;
++#endif /* CONFIG_SCHED_BMQ */
++#ifdef CONFIG_SCHED_PDS
++ u64 deadline;
++#endif /* CONFIG_SCHED_PDS */
++ /* sched_clock time spent running */
++ u64 sched_time;
++#else /* !CONFIG_SCHED_ALT */
+ struct sched_entity se;
+ struct sched_rt_entity rt;
+ struct sched_dl_entity dl;
+@@ -809,6 +830,7 @@ struct task_struct {
+ unsigned long core_cookie;
+ unsigned int core_occupation;
+ #endif
++#endif /* !CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_CGROUP_SCHED
+ struct task_group *sched_task_group;
+@@ -1571,6 +1593,15 @@ struct task_struct {
+ */
+ };
+
++#ifdef CONFIG_SCHED_ALT
++#define tsk_seruntime(t) ((t)->sched_time)
++/* replace the uncertian rt_timeout with 0UL */
++#define tsk_rttimeout(t) (0UL)
++#else /* CFS */
++#define tsk_seruntime(t) ((t)->se.sum_exec_runtime)
++#define tsk_rttimeout(t) ((t)->rt.timeout)
++#endif /* !CONFIG_SCHED_ALT */
++
+ #define TASK_REPORT_IDLE (TASK_REPORT + 1)
+ #define TASK_REPORT_MAX (TASK_REPORT_IDLE << 1)
+
+diff --new-file -rup linux-6.10/init/Kconfig linux-prjc-linux-6.10.y-prjc/init/Kconfig
+--- linux-6.10/init/Kconfig 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/init/Kconfig 2024-07-15 16:47:37.000000000 +0200
+@@ -638,6 +638,7 @@ config TASK_IO_ACCOUNTING
+
+ config PSI
+ bool "Pressure stall information tracking"
++ depends on !SCHED_ALT
+ select KERNFS
+ help
+ Collect metrics that indicate how overcommitted the CPU, memory,
+@@ -803,6 +804,7 @@ menu "Scheduler features"
+ config UCLAMP_TASK
+ bool "Enable utilization clamping for RT/FAIR tasks"
+ depends on CPU_FREQ_GOV_SCHEDUTIL
++ depends on !SCHED_ALT
+ help
+ This feature enables the scheduler to track the clamped utilization
+ of each CPU based on RUNNABLE tasks scheduled on that CPU.
+@@ -849,6 +851,35 @@ config UCLAMP_BUCKETS_COUNT
+
+ If in doubt, use the default value.
+
++menuconfig SCHED_ALT
++ bool "Alternative CPU Schedulers"
++ default y
++ help
++ This feature enable alternative CPU scheduler"
++
++if SCHED_ALT
++
++choice
++ prompt "Alternative CPU Scheduler"
++ default SCHED_BMQ
++
++config SCHED_BMQ
++ bool "BMQ CPU scheduler"
++ help
++ The BitMap Queue CPU scheduler for excellent interactivity and
++ responsiveness on the desktop and solid scalability on normal
++ hardware and commodity servers.
++
++config SCHED_PDS
++ bool "PDS CPU scheduler"
++ help
++ The Priority and Deadline based Skip list multiple queue CPU
++ Scheduler.
++
++endchoice
++
++endif
++
+ endmenu
+
+ #
+@@ -914,6 +945,7 @@ config NUMA_BALANCING
+ depends on ARCH_SUPPORTS_NUMA_BALANCING
+ depends on !ARCH_WANT_NUMA_VARIABLE_LOCALITY
+ depends on SMP && NUMA && MIGRATION && !PREEMPT_RT
++ depends on !SCHED_ALT
+ help
+ This option adds support for automatic NUMA aware memory/task placement.
+ The mechanism is quite primitive and is based on migrating memory when
+@@ -1015,6 +1047,7 @@ config FAIR_GROUP_SCHED
+ depends on CGROUP_SCHED
+ default CGROUP_SCHED
+
++if !SCHED_ALT
+ config CFS_BANDWIDTH
+ bool "CPU bandwidth provisioning for FAIR_GROUP_SCHED"
+ depends on FAIR_GROUP_SCHED
+@@ -1037,6 +1070,7 @@ config RT_GROUP_SCHED
+ realtime bandwidth for them.
+ See Documentation/scheduler/sched-rt-group.rst for more information.
+
++endif #!SCHED_ALT
+ endif #CGROUP_SCHED
+
+ config SCHED_MM_CID
+@@ -1285,6 +1319,7 @@ config CHECKPOINT_RESTORE
+
+ config SCHED_AUTOGROUP
+ bool "Automatic process group scheduling"
++ depends on !SCHED_ALT
+ select CGROUPS
+ select CGROUP_SCHED
+ select FAIR_GROUP_SCHED
+diff --new-file -rup linux-6.10/init/init_task.c linux-prjc-linux-6.10.y-prjc/init/init_task.c
+--- linux-6.10/init/init_task.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/init/init_task.c 2024-07-15 16:47:37.000000000 +0200
+@@ -70,9 +70,15 @@ struct task_struct init_task __aligned(L
+ .stack = init_stack,
+ .usage = REFCOUNT_INIT(2),
+ .flags = PF_KTHREAD,
++#ifdef CONFIG_SCHED_ALT
++ .prio = DEFAULT_PRIO,
++ .static_prio = DEFAULT_PRIO,
++ .normal_prio = DEFAULT_PRIO,
++#else
+ .prio = MAX_PRIO - 20,
+ .static_prio = MAX_PRIO - 20,
+ .normal_prio = MAX_PRIO - 20,
++#endif
+ .policy = SCHED_NORMAL,
+ .cpus_ptr = &init_task.cpus_mask,
+ .user_cpus_ptr = NULL,
+@@ -85,6 +91,16 @@ struct task_struct init_task __aligned(L
+ .restart_block = {
+ .fn = do_no_restart_syscall,
+ },
++#ifdef CONFIG_SCHED_ALT
++ .sq_node = LIST_HEAD_INIT(init_task.sq_node),
++#ifdef CONFIG_SCHED_BMQ
++ .boost_prio = 0,
++#endif
++#ifdef CONFIG_SCHED_PDS
++ .deadline = 0,
++#endif
++ .time_slice = HZ,
++#else
+ .se = {
+ .group_node = LIST_HEAD_INIT(init_task.se.group_node),
+ },
+@@ -92,6 +108,7 @@ struct task_struct init_task __aligned(L
+ .run_list = LIST_HEAD_INIT(init_task.rt.run_list),
+ .time_slice = RR_TIMESLICE,
+ },
++#endif
+ .tasks = LIST_HEAD_INIT(init_task.tasks),
+ #ifdef CONFIG_SMP
+ .pushable_tasks = PLIST_NODE_INIT(init_task.pushable_tasks, MAX_PRIO),
+diff --new-file -rup linux-6.10/kernel/Kconfig.preempt linux-prjc-linux-6.10.y-prjc/kernel/Kconfig.preempt
+--- linux-6.10/kernel/Kconfig.preempt 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/Kconfig.preempt 2024-07-15 16:47:37.000000000 +0200
+@@ -117,7 +117,7 @@ config PREEMPT_DYNAMIC
+
+ config SCHED_CORE
+ bool "Core Scheduling for SMT"
+- depends on SCHED_SMT
++ depends on SCHED_SMT && !SCHED_ALT
+ help
+ This option permits Core Scheduling, a means of coordinated task
+ selection across SMT siblings. When enabled -- see
+diff --new-file -rup linux-6.10/kernel/cgroup/cpuset.c linux-prjc-linux-6.10.y-prjc/kernel/cgroup/cpuset.c
+--- linux-6.10/kernel/cgroup/cpuset.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/cgroup/cpuset.c 2024-07-15 16:47:37.000000000 +0200
+@@ -846,7 +846,7 @@ out:
+ return ret;
+ }
+
+-#ifdef CONFIG_SMP
++#if defined(CONFIG_SMP) && !defined(CONFIG_SCHED_ALT)
+ /*
+ * Helper routine for generate_sched_domains().
+ * Do cpusets a, b have overlapping effective cpus_allowed masks?
+@@ -1245,7 +1245,7 @@ static void rebuild_sched_domains_locked
+ /* Have scheduler rebuild the domains */
+ partition_and_rebuild_sched_domains(ndoms, doms, attr);
+ }
+-#else /* !CONFIG_SMP */
++#else /* !CONFIG_SMP || CONFIG_SCHED_ALT */
+ static void rebuild_sched_domains_locked(void)
+ {
+ }
+@@ -3301,12 +3301,15 @@ static int cpuset_can_attach(struct cgro
+ goto out_unlock;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(task)) {
+ cs->nr_migrate_dl_tasks++;
+ cs->sum_migrate_dl_bw += task->dl.dl_bw;
+ }
++#endif
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (!cs->nr_migrate_dl_tasks)
+ goto out_success;
+
+@@ -3327,6 +3330,7 @@ static int cpuset_can_attach(struct cgro
+ }
+
+ out_success:
++#endif
+ /*
+ * Mark attach is in progress. This makes validate_change() fail
+ * changes which zero cpus/mems_allowed.
+@@ -3350,12 +3354,14 @@ static void cpuset_cancel_attach(struct
+ if (!cs->attach_in_progress)
+ wake_up(&cpuset_attach_wq);
+
++#ifndef CONFIG_SCHED_ALT
+ if (cs->nr_migrate_dl_tasks) {
+ int cpu = cpumask_any(cs->effective_cpus);
+
+ dl_bw_free(cpu, cs->sum_migrate_dl_bw);
+ reset_migrate_dl_data(cs);
+ }
++#endif
+
+ mutex_unlock(&cpuset_mutex);
+ }
+diff --new-file -rup linux-6.10/kernel/delayacct.c linux-prjc-linux-6.10.y-prjc/kernel/delayacct.c
+--- linux-6.10/kernel/delayacct.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/delayacct.c 2024-07-15 16:47:37.000000000 +0200
+@@ -149,7 +149,7 @@ int delayacct_add_tsk(struct taskstats *
+ */
+ t1 = tsk->sched_info.pcount;
+ t2 = tsk->sched_info.run_delay;
+- t3 = tsk->se.sum_exec_runtime;
++ t3 = tsk_seruntime(tsk);
+
+ d->cpu_count += t1;
+
+diff --new-file -rup linux-6.10/kernel/exit.c linux-prjc-linux-6.10.y-prjc/kernel/exit.c
+--- linux-6.10/kernel/exit.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/exit.c 2024-07-15 16:47:37.000000000 +0200
+@@ -175,7 +175,7 @@ static void __exit_signal(struct task_st
+ sig->curr_target = next_thread(tsk);
+ }
+
+- add_device_randomness((const void*) &tsk->se.sum_exec_runtime,
++ add_device_randomness((const void*) &tsk_seruntime(tsk),
+ sizeof(unsigned long long));
+
+ /*
+@@ -196,7 +196,7 @@ static void __exit_signal(struct task_st
+ sig->inblock += task_io_get_inblock(tsk);
+ sig->oublock += task_io_get_oublock(tsk);
+ task_io_accounting_add(&sig->ioac, &tsk->ioac);
+- sig->sum_sched_runtime += tsk->se.sum_exec_runtime;
++ sig->sum_sched_runtime += tsk_seruntime(tsk);
+ sig->nr_threads--;
+ __unhash_process(tsk, group_dead);
+ write_sequnlock(&sig->stats_lock);
+diff --new-file -rup linux-6.10/kernel/locking/rtmutex.c linux-prjc-linux-6.10.y-prjc/kernel/locking/rtmutex.c
+--- linux-6.10/kernel/locking/rtmutex.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/locking/rtmutex.c 2024-07-15 16:47:37.000000000 +0200
+@@ -363,7 +363,7 @@ waiter_update_prio(struct rt_mutex_waite
+ lockdep_assert(RB_EMPTY_NODE(&waiter->tree.entry));
+
+ waiter->tree.prio = __waiter_prio(task);
+- waiter->tree.deadline = task->dl.deadline;
++ waiter->tree.deadline = __tsk_deadline(task);
+ }
+
+ /*
+@@ -384,16 +384,20 @@ waiter_clone_prio(struct rt_mutex_waiter
+ * Only use with rt_waiter_node_{less,equal}()
+ */
+ #define task_to_waiter_node(p) \
+- &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = (p)->dl.deadline }
++ &(struct rt_waiter_node){ .prio = __waiter_prio(p), .deadline = __tsk_deadline(p) }
+ #define task_to_waiter(p) \
+ &(struct rt_mutex_waiter){ .tree = *task_to_waiter_node(p) }
+
+ static __always_inline int rt_waiter_node_less(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
+ {
++#ifdef CONFIG_SCHED_PDS
++ return (left->deadline < right->deadline);
++#else
+ if (left->prio < right->prio)
+ return 1;
+
++#ifndef CONFIG_SCHED_BMQ
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+@@ -402,16 +406,22 @@ static __always_inline int rt_waiter_nod
+ */
+ if (dl_prio(left->prio))
+ return dl_time_before(left->deadline, right->deadline);
++#endif
+
+ return 0;
++#endif
+ }
+
+ static __always_inline int rt_waiter_node_equal(struct rt_waiter_node *left,
+ struct rt_waiter_node *right)
+ {
++#ifdef CONFIG_SCHED_PDS
++ return (left->deadline == right->deadline);
++#else
+ if (left->prio != right->prio)
+ return 0;
+
++#ifndef CONFIG_SCHED_BMQ
+ /*
+ * If both waiters have dl_prio(), we check the deadlines of the
+ * associated tasks.
+@@ -420,8 +430,10 @@ static __always_inline int rt_waiter_nod
+ */
+ if (dl_prio(left->prio))
+ return left->deadline == right->deadline;
++#endif
+
+ return 1;
++#endif
+ }
+
+ static inline bool rt_mutex_steal(struct rt_mutex_waiter *waiter,
+diff --new-file -rup linux-6.10/kernel/sched/Makefile linux-prjc-linux-6.10.y-prjc/kernel/sched/Makefile
+--- linux-6.10/kernel/sched/Makefile 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/Makefile 2024-07-15 16:47:37.000000000 +0200
+@@ -28,7 +28,12 @@ endif
+ # These compilation units have roughly the same size and complexity - so their
+ # build parallelizes well and finishes roughly at once:
+ #
++ifdef CONFIG_SCHED_ALT
++obj-y += alt_core.o
++obj-$(CONFIG_SCHED_DEBUG) += alt_debug.o
++else
+ obj-y += core.o
+ obj-y += fair.o
++endif
+ obj-y += build_policy.o
+ obj-y += build_utility.o
+diff --new-file -rup linux-6.10/kernel/sched/alt_core.c linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_core.c
+--- linux-6.10/kernel/sched/alt_core.c 1970-01-01 01:00:00.000000000 +0100
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_core.c 2024-07-15 16:47:37.000000000 +0200
+@@ -0,0 +1,8963 @@
++/*
++ * kernel/sched/alt_core.c
++ *
++ * Core alternative kernel scheduler code and related syscalls
++ *
++ * Copyright (C) 1991-2002 Linus Torvalds
++ *
++ * 2009-08-13 Brainfuck deadline scheduling policy by Con Kolivas deletes
++ * a whole lot of those previous things.
++ * 2017-09-06 Priority and Deadline based Skip list multiple queue kernel
++ * scheduler by Alfred Chen.
++ * 2019-02-20 BMQ(BitMap Queue) kernel scheduler by Alfred Chen.
++ */
++#include <linux/sched/clock.h>
++#include <linux/sched/cputime.h>
++#include <linux/sched/debug.h>
++#include <linux/sched/hotplug.h>
++#include <linux/sched/init.h>
++#include <linux/sched/isolation.h>
++#include <linux/sched/loadavg.h>
++#include <linux/sched/mm.h>
++#include <linux/sched/nohz.h>
++#include <linux/sched/stat.h>
++#include <linux/sched/wake_q.h>
++
++#include <linux/blkdev.h>
++#include <linux/context_tracking.h>
++#include <linux/cpuset.h>
++#include <linux/delayacct.h>
++#include <linux/init_task.h>
++#include <linux/kcov.h>
++#include <linux/kprobes.h>
++#include <linux/nmi.h>
++#include <linux/rseq.h>
++#include <linux/scs.h>
++
++#include <uapi/linux/sched/types.h>
++
++#include <asm/irq_regs.h>
++#include <asm/switch_to.h>
++
++#define CREATE_TRACE_POINTS
++#include <trace/events/sched.h>
++#include <trace/events/ipi.h>
++#undef CREATE_TRACE_POINTS
++
++#include "sched.h"
++#include "smp.h"
++
++#include "pelt.h"
++
++#include "../../io_uring/io-wq.h"
++#include "../smpboot.h"
++
++EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpu);
++EXPORT_TRACEPOINT_SYMBOL_GPL(ipi_send_cpumask);
++
++/*
++ * Export tracepoints that act as a bare tracehook (ie: have no trace event
++ * associated with them) to allow external modules to probe them.
++ */
++EXPORT_TRACEPOINT_SYMBOL_GPL(pelt_irq_tp);
++
++#ifdef CONFIG_SCHED_DEBUG
++#define sched_feat(x) (1)
++/*
++ * Print a warning if need_resched is set for the given duration (if
++ * LATENCY_WARN is enabled).
++ *
++ * If sysctl_resched_latency_warn_once is set, only one warning will be shown
++ * per boot.
++ */
++__read_mostly int sysctl_resched_latency_warn_ms = 100;
++__read_mostly int sysctl_resched_latency_warn_once = 1;
++#else
++#define sched_feat(x) (0)
++#endif /* CONFIG_SCHED_DEBUG */
++
++#define ALT_SCHED_VERSION "v6.10-r0"
++
++/*
++ * Compile time debug macro
++ * #define ALT_SCHED_DEBUG
++ */
++
++/* rt_prio(prio) defined in include/linux/sched/rt.h */
++#define rt_task(p) rt_prio((p)->prio)
++#define rt_policy(policy) ((policy) == SCHED_FIFO || (policy) == SCHED_RR)
++#define task_has_rt_policy(p) (rt_policy((p)->policy))
++
++#define STOP_PRIO (MAX_RT_PRIO - 1)
++
++/*
++ * Time slice
++ * (default: 4 msec, units: nanoseconds)
++ */
++unsigned int sysctl_sched_base_slice __read_mostly = (4 << 20);
++
++#ifdef CONFIG_SCHED_BMQ
++#include "bmq.h"
++#endif
++#ifdef CONFIG_SCHED_PDS
++#include "pds.h"
++#endif
++
++struct affinity_context {
++ const struct cpumask *new_mask;
++ struct cpumask *user_mask;
++ unsigned int flags;
++};
++
++/* Reschedule if less than this many μs left */
++#define RESCHED_NS (100 << 10)
++
++/**
++ * sched_yield_type - Type of sched_yield() will be performed.
++ * 0: No yield.
++ * 1: Requeue task. (default)
++ */
++int sched_yield_type __read_mostly = 1;
++
++#ifdef CONFIG_SMP
++static cpumask_t sched_rq_pending_mask ____cacheline_aligned_in_smp;
++
++DEFINE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
++DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_llc_mask);
++DEFINE_PER_CPU_ALIGNED(cpumask_t *, sched_cpu_topo_end_mask);
++
++#ifdef CONFIG_SCHED_SMT
++DEFINE_STATIC_KEY_FALSE(sched_smt_present);
++EXPORT_SYMBOL_GPL(sched_smt_present);
++#endif
++
++/*
++ * Keep a unique ID per domain (we use the first CPUs number in the cpumask of
++ * the domain), this allows us to quickly tell if two cpus are in the same cache
++ * domain, see cpus_share_cache().
++ */
++DEFINE_PER_CPU(int, sd_llc_id);
++#endif /* CONFIG_SMP */
++
++static DEFINE_MUTEX(sched_hotcpu_mutex);
++
++DEFINE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
++
++#ifndef prepare_arch_switch
++# define prepare_arch_switch(next) do { } while (0)
++#endif
++#ifndef finish_arch_post_lock_switch
++# define finish_arch_post_lock_switch() do { } while (0)
++#endif
++
++static cpumask_t sched_preempt_mask[SCHED_QUEUE_BITS + 1] ____cacheline_aligned_in_smp;
++
++static cpumask_t *const sched_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS - 1];
++#ifdef CONFIG_SCHED_SMT
++static cpumask_t *const sched_sg_idle_mask = &sched_preempt_mask[SCHED_QUEUE_BITS];
++#endif
++
++/* task function */
++static inline const struct cpumask *task_user_cpus(struct task_struct *p)
++{
++ if (!p->user_cpus_ptr)
++ return cpu_possible_mask; /* &init_task.cpus_mask */
++ return p->user_cpus_ptr;
++}
++
++/* sched_queue related functions */
++static inline void sched_queue_init(struct sched_queue *q)
++{
++ int i;
++
++ bitmap_zero(q->bitmap, SCHED_QUEUE_BITS);
++ for(i = 0; i < SCHED_LEVELS; i++)
++ INIT_LIST_HEAD(&q->heads[i]);
++}
++
++/*
++ * Init idle task and put into queue structure of rq
++ * IMPORTANT: may be called multiple times for a single cpu
++ */
++static inline void sched_queue_init_idle(struct sched_queue *q,
++ struct task_struct *idle)
++{
++ INIT_LIST_HEAD(&q->heads[IDLE_TASK_SCHED_PRIO]);
++ list_add_tail(&idle->sq_node, &q->heads[IDLE_TASK_SCHED_PRIO]);
++ idle->on_rq = TASK_ON_RQ_QUEUED;
++}
++
++#define CLEAR_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
++ if (low < pr && pr <= high) \
++ cpumask_clear_cpu(cpu, sched_preempt_mask + pr);
++
++#define SET_CACHED_PREEMPT_MASK(pr, low, high, cpu) \
++ if (low < pr && pr <= high) \
++ cpumask_set_cpu(cpu, sched_preempt_mask + pr);
++
++static atomic_t sched_prio_record = ATOMIC_INIT(0);
++
++/* water mark related functions */
++static inline void update_sched_preempt_mask(struct rq *rq)
++{
++ int prio = find_first_bit(rq->queue.bitmap, SCHED_QUEUE_BITS);
++ int last_prio = rq->prio;
++ int cpu, pr;
++
++ if (prio == last_prio)
++ return;
++
++ rq->prio = prio;
++#ifdef CONFIG_SCHED_PDS
++ rq->prio_idx = sched_prio2idx(rq->prio, rq);
++#endif
++ cpu = cpu_of(rq);
++ pr = atomic_read(&sched_prio_record);
++
++ if (prio < last_prio) {
++ if (IDLE_TASK_SCHED_PRIO == last_prio) {
++#ifdef CONFIG_SCHED_SMT
++ if (static_branch_likely(&sched_smt_present))
++ cpumask_andnot(sched_sg_idle_mask,
++ sched_sg_idle_mask, cpu_smt_mask(cpu));
++#endif
++ cpumask_clear_cpu(cpu, sched_idle_mask);
++ last_prio -= 2;
++ }
++ CLEAR_CACHED_PREEMPT_MASK(pr, prio, last_prio, cpu);
++
++ return;
++ }
++ /* last_prio < prio */
++ if (IDLE_TASK_SCHED_PRIO == prio) {
++#ifdef CONFIG_SCHED_SMT
++ if (static_branch_likely(&sched_smt_present) &&
++ cpumask_intersects(cpu_smt_mask(cpu), sched_idle_mask))
++ cpumask_or(sched_sg_idle_mask, sched_sg_idle_mask, cpu_smt_mask(cpu));
++#endif
++ cpumask_set_cpu(cpu, sched_idle_mask);
++ prio -= 2;
++ }
++ SET_CACHED_PREEMPT_MASK(pr, last_prio, prio, cpu);
++}
++
++/*
++ * This routine assume that the idle task always in queue
++ */
++static inline struct task_struct *sched_rq_first_task(struct rq *rq)
++{
++ const struct list_head *head = &rq->queue.heads[sched_rq_prio_idx(rq)];
++
++ return list_first_entry(head, struct task_struct, sq_node);
++}
++
++static inline struct task_struct * sched_rq_next_task(struct task_struct *p, struct rq *rq)
++{
++ struct list_head *next = p->sq_node.next;
++
++ if (&rq->queue.heads[0] <= next && next < &rq->queue.heads[SCHED_LEVELS]) {
++ struct list_head *head;
++ unsigned long idx = next - &rq->queue.heads[0];
++
++ idx = find_next_bit(rq->queue.bitmap, SCHED_QUEUE_BITS,
++ sched_idx2prio(idx, rq) + 1);
++ head = &rq->queue.heads[sched_prio2idx(idx, rq)];
++
++ return list_first_entry(head, struct task_struct, sq_node);
++ }
++
++ return list_next_entry(p, sq_node);
++}
++
++/*
++ * Serialization rules:
++ *
++ * Lock order:
++ *
++ * p->pi_lock
++ * rq->lock
++ * hrtimer_cpu_base->lock (hrtimer_start() for bandwidth controls)
++ *
++ * rq1->lock
++ * rq2->lock where: rq1 < rq2
++ *
++ * Regular state:
++ *
++ * Normal scheduling state is serialized by rq->lock. __schedule() takes the
++ * local CPU's rq->lock, it optionally removes the task from the runqueue and
++ * always looks at the local rq data structures to find the most eligible task
++ * to run next.
++ *
++ * Task enqueue is also under rq->lock, possibly taken from another CPU.
++ * Wakeups from another LLC domain might use an IPI to transfer the enqueue to
++ * the local CPU to avoid bouncing the runqueue state around [ see
++ * ttwu_queue_wakelist() ]
++ *
++ * Task wakeup, specifically wakeups that involve migration, are horribly
++ * complicated to avoid having to take two rq->locks.
++ *
++ * Special state:
++ *
++ * System-calls and anything external will use task_rq_lock() which acquires
++ * both p->pi_lock and rq->lock. As a consequence the state they change is
++ * stable while holding either lock:
++ *
++ * - sched_setaffinity()/
++ * set_cpus_allowed_ptr(): p->cpus_ptr, p->nr_cpus_allowed
++ * - set_user_nice(): p->se.load, p->*prio
++ * - __sched_setscheduler(): p->sched_class, p->policy, p->*prio,
++ * p->se.load, p->rt_priority,
++ * p->dl.dl_{runtime, deadline, period, flags, bw, density}
++ * - sched_setnuma(): p->numa_preferred_nid
++ * - sched_move_task(): p->sched_task_group
++ * - uclamp_update_active() p->uclamp*
++ *
++ * p->state <- TASK_*:
++ *
++ * is changed locklessly using set_current_state(), __set_current_state() or
++ * set_special_state(), see their respective comments, or by
++ * try_to_wake_up(). This latter uses p->pi_lock to serialize against
++ * concurrent self.
++ *
++ * p->on_rq <- { 0, 1 = TASK_ON_RQ_QUEUED, 2 = TASK_ON_RQ_MIGRATING }:
++ *
++ * is set by activate_task() and cleared by deactivate_task(), under
++ * rq->lock. Non-zero indicates the task is runnable, the special
++ * ON_RQ_MIGRATING state is used for migration without holding both
++ * rq->locks. It indicates task_cpu() is not stable, see task_rq_lock().
++ *
++ * p->on_cpu <- { 0, 1 }:
++ *
++ * is set by prepare_task() and cleared by finish_task() such that it will be
++ * set before p is scheduled-in and cleared after p is scheduled-out, both
++ * under rq->lock. Non-zero indicates the task is running on its CPU.
++ *
++ * [ The astute reader will observe that it is possible for two tasks on one
++ * CPU to have ->on_cpu = 1 at the same time. ]
++ *
++ * task_cpu(p): is changed by set_task_cpu(), the rules are:
++ *
++ * - Don't call set_task_cpu() on a blocked task:
++ *
++ * We don't care what CPU we're not running on, this simplifies hotplug,
++ * the CPU assignment of blocked tasks isn't required to be valid.
++ *
++ * - for try_to_wake_up(), called under p->pi_lock:
++ *
++ * This allows try_to_wake_up() to only take one rq->lock, see its comment.
++ *
++ * - for migration called under rq->lock:
++ * [ see task_on_rq_migrating() in task_rq_lock() ]
++ *
++ * o move_queued_task()
++ * o detach_task()
++ *
++ * - for migration called under double_rq_lock():
++ *
++ * o __migrate_swap_task()
++ * o push_rt_task() / pull_rt_task()
++ * o push_dl_task() / pull_dl_task()
++ * o dl_task_offline_migration()
++ *
++ */
++
++/*
++ * Context: p->pi_lock
++ */
++static inline struct rq *__task_access_lock(struct task_struct *p, raw_spinlock_t **plock)
++{
++ struct rq *rq;
++ for (;;) {
++ rq = task_rq(p);
++ if (p->on_cpu || task_on_rq_queued(p)) {
++ raw_spin_lock(&rq->lock);
++ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
++ *plock = &rq->lock;
++ return rq;
++ }
++ raw_spin_unlock(&rq->lock);
++ } else if (task_on_rq_migrating(p)) {
++ do {
++ cpu_relax();
++ } while (unlikely(task_on_rq_migrating(p)));
++ } else {
++ *plock = NULL;
++ return rq;
++ }
++ }
++}
++
++static inline void __task_access_unlock(struct task_struct *p, raw_spinlock_t *lock)
++{
++ if (NULL != lock)
++ raw_spin_unlock(lock);
++}
++
++static inline struct rq *
++task_access_lock_irqsave(struct task_struct *p, raw_spinlock_t **plock, unsigned long *flags)
++{
++ struct rq *rq;
++ for (;;) {
++ rq = task_rq(p);
++ if (p->on_cpu || task_on_rq_queued(p)) {
++ raw_spin_lock_irqsave(&rq->lock, *flags);
++ if (likely((p->on_cpu || task_on_rq_queued(p)) && rq == task_rq(p))) {
++ *plock = &rq->lock;
++ return rq;
++ }
++ raw_spin_unlock_irqrestore(&rq->lock, *flags);
++ } else if (task_on_rq_migrating(p)) {
++ do {
++ cpu_relax();
++ } while (unlikely(task_on_rq_migrating(p)));
++ } else {
++ raw_spin_lock_irqsave(&p->pi_lock, *flags);
++ if (likely(!p->on_cpu && !p->on_rq && rq == task_rq(p))) {
++ *plock = &p->pi_lock;
++ return rq;
++ }
++ raw_spin_unlock_irqrestore(&p->pi_lock, *flags);
++ }
++ }
++}
++
++static inline void
++task_access_unlock_irqrestore(struct task_struct *p, raw_spinlock_t *lock, unsigned long *flags)
++{
++ raw_spin_unlock_irqrestore(lock, *flags);
++}
++
++/*
++ * __task_rq_lock - lock the rq @p resides on.
++ */
++struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ lockdep_assert_held(&p->pi_lock);
++
++ for (;;) {
++ rq = task_rq(p);
++ raw_spin_lock(&rq->lock);
++ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p)))
++ return rq;
++ raw_spin_unlock(&rq->lock);
++
++ while (unlikely(task_on_rq_migrating(p)))
++ cpu_relax();
++ }
++}
++
++/*
++ * task_rq_lock - lock p->pi_lock and lock the rq @p resides on.
++ */
++struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(p->pi_lock)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ for (;;) {
++ raw_spin_lock_irqsave(&p->pi_lock, rf->flags);
++ rq = task_rq(p);
++ raw_spin_lock(&rq->lock);
++ /*
++ * move_queued_task() task_rq_lock()
++ *
++ * ACQUIRE (rq->lock)
++ * [S] ->on_rq = MIGRATING [L] rq = task_rq()
++ * WMB (__set_task_cpu()) ACQUIRE (rq->lock);
++ * [S] ->cpu = new_cpu [L] task_rq()
++ * [L] ->on_rq
++ * RELEASE (rq->lock)
++ *
++ * If we observe the old CPU in task_rq_lock(), the acquire of
++ * the old rq->lock will fully serialize against the stores.
++ *
++ * If we observe the new CPU in task_rq_lock(), the address
++ * dependency headed by '[L] rq = task_rq()' and the acquire
++ * will pair with the WMB to ensure we then also see migrating.
++ */
++ if (likely(rq == task_rq(p) && !task_on_rq_migrating(p))) {
++ return rq;
++ }
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
++
++ while (unlikely(task_on_rq_migrating(p)))
++ cpu_relax();
++ }
++}
++
++static inline void rq_lock_irqsave(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock_irqsave(&rq->lock, rf->flags);
++}
++
++static inline void rq_unlock_irqrestore(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock_irqrestore(&rq->lock, rf->flags);
++}
++
++DEFINE_LOCK_GUARD_1(rq_lock_irqsave, struct rq,
++ rq_lock_irqsave(_T->lock, &_T->rf),
++ rq_unlock_irqrestore(_T->lock, &_T->rf),
++ struct rq_flags rf)
++
++void raw_spin_rq_lock_nested(struct rq *rq, int subclass)
++{
++ raw_spinlock_t *lock;
++
++ /* Matches synchronize_rcu() in __sched_core_enable() */
++ preempt_disable();
++
++ for (;;) {
++ lock = __rq_lockp(rq);
++ raw_spin_lock_nested(lock, subclass);
++ if (likely(lock == __rq_lockp(rq))) {
++ /* preempt_count *MUST* be > 1 */
++ preempt_enable_no_resched();
++ return;
++ }
++ raw_spin_unlock(lock);
++ }
++}
++
++void raw_spin_rq_unlock(struct rq *rq)
++{
++ raw_spin_unlock(rq_lockp(rq));
++}
++
++/*
++ * RQ-clock updating methods:
++ */
++
++static void update_rq_clock_task(struct rq *rq, s64 delta)
++{
++/*
++ * In theory, the compile should just see 0 here, and optimize out the call
++ * to sched_rt_avg_update. But I don't trust it...
++ */
++ s64 __maybe_unused steal = 0, irq_delta = 0;
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ irq_delta = irq_time_read(cpu_of(rq)) - rq->prev_irq_time;
++
++ /*
++ * Since irq_time is only updated on {soft,}irq_exit, we might run into
++ * this case when a previous update_rq_clock() happened inside a
++ * {soft,}irq region.
++ *
++ * When this happens, we stop ->clock_task and only update the
++ * prev_irq_time stamp to account for the part that fit, so that a next
++ * update will consume the rest. This ensures ->clock_task is
++ * monotonic.
++ *
++ * It does however cause some slight miss-attribution of {soft,}irq
++ * time, a more accurate solution would be to update the irq_time using
++ * the current rq->clock timestamp, except that would require using
++ * atomic ops.
++ */
++ if (irq_delta > delta)
++ irq_delta = delta;
++
++ rq->prev_irq_time += irq_delta;
++ delta -= irq_delta;
++ delayacct_irq(rq->curr, irq_delta);
++#endif
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ if (static_key_false((¶virt_steal_rq_enabled))) {
++ steal = paravirt_steal_clock(cpu_of(rq));
++ steal -= rq->prev_steal_time_rq;
++
++ if (unlikely(steal > delta))
++ steal = delta;
++
++ rq->prev_steal_time_rq += steal;
++ delta -= steal;
++ }
++#endif
++
++ rq->clock_task += delta;
++
++#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
++ if ((irq_delta + steal))
++ update_irq_load_avg(rq, irq_delta + steal);
++#endif
++}
++
++static inline void update_rq_clock(struct rq *rq)
++{
++ s64 delta = sched_clock_cpu(cpu_of(rq)) - rq->clock;
++
++ if (unlikely(delta <= 0))
++ return;
++ rq->clock += delta;
++ sched_update_rq_clock(rq);
++ update_rq_clock_task(rq, delta);
++}
++
++/*
++ * RQ Load update routine
++ */
++#define RQ_LOAD_HISTORY_BITS (sizeof(s32) * 8ULL)
++#define RQ_UTIL_SHIFT (8)
++#define RQ_LOAD_HISTORY_TO_UTIL(l) (((l) >> (RQ_LOAD_HISTORY_BITS - 1 - RQ_UTIL_SHIFT)) & 0xff)
++
++#define LOAD_BLOCK(t) ((t) >> 17)
++#define LOAD_HALF_BLOCK(t) ((t) >> 16)
++#define BLOCK_MASK(t) ((t) & ((0x01 << 18) - 1))
++#define LOAD_BLOCK_BIT(b) (1UL << (RQ_LOAD_HISTORY_BITS - 1 - (b)))
++#define CURRENT_LOAD_BIT LOAD_BLOCK_BIT(0)
++
++static inline void rq_load_update(struct rq *rq)
++{
++ u64 time = rq->clock;
++ u64 delta = min(LOAD_BLOCK(time) - LOAD_BLOCK(rq->load_stamp), RQ_LOAD_HISTORY_BITS - 1);
++ u64 prev = !!(rq->load_history & CURRENT_LOAD_BIT);
++ u64 curr = !!rq->nr_running;
++
++ if (delta) {
++ rq->load_history = rq->load_history >> delta;
++
++ if (delta < RQ_UTIL_SHIFT) {
++ rq->load_block += (~BLOCK_MASK(rq->load_stamp)) * prev;
++ if (!!LOAD_HALF_BLOCK(rq->load_block) ^ curr)
++ rq->load_history ^= LOAD_BLOCK_BIT(delta);
++ }
++
++ rq->load_block = BLOCK_MASK(time) * prev;
++ } else {
++ rq->load_block += (time - rq->load_stamp) * prev;
++ }
++ if (prev ^ curr)
++ rq->load_history ^= CURRENT_LOAD_BIT;
++ rq->load_stamp = time;
++}
++
++unsigned long rq_load_util(struct rq *rq, unsigned long max)
++{
++ return RQ_LOAD_HISTORY_TO_UTIL(rq->load_history) * (max >> RQ_UTIL_SHIFT);
++}
++
++#ifdef CONFIG_SMP
++unsigned long sched_cpu_util(int cpu)
++{
++ return rq_load_util(cpu_rq(cpu), arch_scale_cpu_capacity(cpu));
++}
++#endif /* CONFIG_SMP */
++
++#ifdef CONFIG_CPU_FREQ
++/**
++ * cpufreq_update_util - Take a note about CPU utilization changes.
++ * @rq: Runqueue to carry out the update for.
++ * @flags: Update reason flags.
++ *
++ * This function is called by the scheduler on the CPU whose utilization is
++ * being updated.
++ *
++ * It can only be called from RCU-sched read-side critical sections.
++ *
++ * The way cpufreq is currently arranged requires it to evaluate the CPU
++ * performance state (frequency/voltage) on a regular basis to prevent it from
++ * being stuck in a completely inadequate performance level for too long.
++ * That is not guaranteed to happen if the updates are only triggered from CFS
++ * and DL, though, because they may not be coming in if only RT tasks are
++ * active all the time (or there are RT tasks only).
++ *
++ * As a workaround for that issue, this function is called periodically by the
++ * RT sched class to trigger extra cpufreq updates to prevent it from stalling,
++ * but that really is a band-aid. Going forward it should be replaced with
++ * solutions targeted more specifically at RT tasks.
++ */
++static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
++{
++ struct update_util_data *data;
++
++#ifdef CONFIG_SMP
++ rq_load_update(rq);
++#endif
++ data = rcu_dereference_sched(*per_cpu_ptr(&cpufreq_update_util_data, cpu_of(rq)));
++ if (data)
++ data->func(data, rq_clock(rq), flags);
++}
++#else
++static inline void cpufreq_update_util(struct rq *rq, unsigned int flags)
++{
++#ifdef CONFIG_SMP
++ rq_load_update(rq);
++#endif
++}
++#endif /* CONFIG_CPU_FREQ */
++
++#ifdef CONFIG_NO_HZ_FULL
++/*
++ * Tick may be needed by tasks in the runqueue depending on their policy and
++ * requirements. If tick is needed, lets send the target an IPI to kick it out
++ * of nohz mode if necessary.
++ */
++static inline void sched_update_tick_dependency(struct rq *rq)
++{
++ int cpu = cpu_of(rq);
++
++ if (!tick_nohz_full_cpu(cpu))
++ return;
++
++ if (rq->nr_running < 2)
++ tick_nohz_dep_clear_cpu(cpu, TICK_DEP_BIT_SCHED);
++ else
++ tick_nohz_dep_set_cpu(cpu, TICK_DEP_BIT_SCHED);
++}
++#else /* !CONFIG_NO_HZ_FULL */
++static inline void sched_update_tick_dependency(struct rq *rq) { }
++#endif
++
++bool sched_task_on_rq(struct task_struct *p)
++{
++ return task_on_rq_queued(p);
++}
++
++unsigned long get_wchan(struct task_struct *p)
++{
++ unsigned long ip = 0;
++ unsigned int state;
++
++ if (!p || p == current)
++ return 0;
++
++ /* Only get wchan if task is blocked and we can keep it that way. */
++ raw_spin_lock_irq(&p->pi_lock);
++ state = READ_ONCE(p->__state);
++ smp_rmb(); /* see try_to_wake_up() */
++ if (state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq)
++ ip = __get_wchan(p);
++ raw_spin_unlock_irq(&p->pi_lock);
++
++ return ip;
++}
++
++/*
++ * Add/Remove/Requeue task to/from the runqueue routines
++ * Context: rq->lock
++ */
++#define __SCHED_DEQUEUE_TASK(p, rq, flags, func) \
++ sched_info_dequeue(rq, p); \
++ \
++ __list_del_entry(&p->sq_node); \
++ if (p->sq_node.prev == p->sq_node.next) { \
++ clear_bit(sched_idx2prio(p->sq_node.next - &rq->queue.heads[0], rq), \
++ rq->queue.bitmap); \
++ func; \
++ }
++
++#define __SCHED_ENQUEUE_TASK(p, rq, flags, func) \
++ sched_info_enqueue(rq, p); \
++ { \
++ int idx, prio; \
++ TASK_SCHED_PRIO_IDX(p, rq, idx, prio); \
++ list_add_tail(&p->sq_node, &rq->queue.heads[idx]); \
++ if (list_is_first(&p->sq_node, &rq->queue.heads[idx])) { \
++ set_bit(prio, rq->queue.bitmap); \
++ func; \
++ } \
++ }
++
++static inline void dequeue_task(struct task_struct *p, struct rq *rq, int flags)
++{
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++
++ /*printk(KERN_INFO "sched: dequeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: dequeue task reside on cpu%d from cpu%d\n",
++ task_cpu(p), cpu_of(rq));
++#endif
++
++ __SCHED_DEQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
++ --rq->nr_running;
++#ifdef CONFIG_SMP
++ if (1 == rq->nr_running)
++ cpumask_clear_cpu(cpu_of(rq), &sched_rq_pending_mask);
++#endif
++
++ sched_update_tick_dependency(rq);
++}
++
++static inline void enqueue_task(struct task_struct *p, struct rq *rq, int flags)
++{
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++
++ /*printk(KERN_INFO "sched: enqueue(%d) %px %d\n", cpu_of(rq), p, p->prio);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: enqueue task reside on cpu%d to cpu%d\n",
++ task_cpu(p), cpu_of(rq));
++#endif
++
++ __SCHED_ENQUEUE_TASK(p, rq, flags, update_sched_preempt_mask(rq));
++ ++rq->nr_running;
++#ifdef CONFIG_SMP
++ if (2 == rq->nr_running)
++ cpumask_set_cpu(cpu_of(rq), &sched_rq_pending_mask);
++#endif
++
++ sched_update_tick_dependency(rq);
++}
++
++static inline void requeue_task(struct task_struct *p, struct rq *rq)
++{
++ struct list_head *node = &p->sq_node;
++ int deq_idx, idx, prio;
++
++ TASK_SCHED_PRIO_IDX(p, rq, idx, prio);
++#ifdef ALT_SCHED_DEBUG
++ lockdep_assert_held(&rq->lock);
++ /*printk(KERN_INFO "sched: requeue(%d) %px %016llx\n", cpu_of(rq), p, p->deadline);*/
++ WARN_ONCE(task_rq(p) != rq, "sched: cpu[%d] requeue task reside on cpu%d\n",
++ cpu_of(rq), task_cpu(p));
++#endif
++ if (list_is_last(node, &rq->queue.heads[idx]))
++ return;
++
++ __list_del_entry(node);
++ if (node->prev == node->next && (deq_idx = node->next - &rq->queue.heads[0]) != idx)
++ clear_bit(sched_idx2prio(deq_idx, rq), rq->queue.bitmap);
++
++ list_add_tail(node, &rq->queue.heads[idx]);
++ if (list_is_first(node, &rq->queue.heads[idx]))
++ set_bit(prio, rq->queue.bitmap);
++ update_sched_preempt_mask(rq);
++}
++
++/*
++ * cmpxchg based fetch_or, macro so it works for different integer types
++ */
++#define fetch_or(ptr, mask) \
++ ({ \
++ typeof(ptr) _ptr = (ptr); \
++ typeof(mask) _mask = (mask); \
++ typeof(*_ptr) _val = *_ptr; \
++ \
++ do { \
++ } while (!try_cmpxchg(_ptr, &_val, _val | _mask)); \
++ _val; \
++})
++
++#if defined(CONFIG_SMP) && defined(TIF_POLLING_NRFLAG)
++/*
++ * Atomically set TIF_NEED_RESCHED and test for TIF_POLLING_NRFLAG,
++ * this avoids any races wrt polling state changes and thereby avoids
++ * spurious IPIs.
++ */
++static inline bool set_nr_and_not_polling(struct task_struct *p)
++{
++ struct thread_info *ti = task_thread_info(p);
++ return !(fetch_or(&ti->flags, _TIF_NEED_RESCHED) & _TIF_POLLING_NRFLAG);
++}
++
++/*
++ * Atomically set TIF_NEED_RESCHED if TIF_POLLING_NRFLAG is set.
++ *
++ * If this returns true, then the idle task promises to call
++ * sched_ttwu_pending() and reschedule soon.
++ */
++static bool set_nr_if_polling(struct task_struct *p)
++{
++ struct thread_info *ti = task_thread_info(p);
++ typeof(ti->flags) val = READ_ONCE(ti->flags);
++
++ do {
++ if (!(val & _TIF_POLLING_NRFLAG))
++ return false;
++ if (val & _TIF_NEED_RESCHED)
++ return true;
++ } while (!try_cmpxchg(&ti->flags, &val, val | _TIF_NEED_RESCHED));
++
++ return true;
++}
++
++#else
++static inline bool set_nr_and_not_polling(struct task_struct *p)
++{
++ set_tsk_need_resched(p);
++ return true;
++}
++
++#ifdef CONFIG_SMP
++static inline bool set_nr_if_polling(struct task_struct *p)
++{
++ return false;
++}
++#endif
++#endif
++
++static bool __wake_q_add(struct wake_q_head *head, struct task_struct *task)
++{
++ struct wake_q_node *node = &task->wake_q;
++
++ /*
++ * Atomically grab the task, if ->wake_q is !nil already it means
++ * it's already queued (either by us or someone else) and will get the
++ * wakeup due to that.
++ *
++ * In order to ensure that a pending wakeup will observe our pending
++ * state, even in the failed case, an explicit smp_mb() must be used.
++ */
++ smp_mb__before_atomic();
++ if (unlikely(cmpxchg_relaxed(&node->next, NULL, WAKE_Q_TAIL)))
++ return false;
++
++ /*
++ * The head is context local, there can be no concurrency.
++ */
++ *head->lastp = node;
++ head->lastp = &node->next;
++ return true;
++}
++
++/**
++ * wake_q_add() - queue a wakeup for 'later' waking.
++ * @head: the wake_q_head to add @task to
++ * @task: the task to queue for 'later' wakeup
++ *
++ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
++ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
++ * instantly.
++ *
++ * This function must be used as-if it were wake_up_process(); IOW the task
++ * must be ready to be woken at this location.
++ */
++void wake_q_add(struct wake_q_head *head, struct task_struct *task)
++{
++ if (__wake_q_add(head, task))
++ get_task_struct(task);
++}
++
++/**
++ * wake_q_add_safe() - safely queue a wakeup for 'later' waking.
++ * @head: the wake_q_head to add @task to
++ * @task: the task to queue for 'later' wakeup
++ *
++ * Queue a task for later wakeup, most likely by the wake_up_q() call in the
++ * same context, _HOWEVER_ this is not guaranteed, the wakeup can come
++ * instantly.
++ *
++ * This function must be used as-if it were wake_up_process(); IOW the task
++ * must be ready to be woken at this location.
++ *
++ * This function is essentially a task-safe equivalent to wake_q_add(). Callers
++ * that already hold reference to @task can call the 'safe' version and trust
++ * wake_q to do the right thing depending whether or not the @task is already
++ * queued for wakeup.
++ */
++void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task)
++{
++ if (!__wake_q_add(head, task))
++ put_task_struct(task);
++}
++
++void wake_up_q(struct wake_q_head *head)
++{
++ struct wake_q_node *node = head->first;
++
++ while (node != WAKE_Q_TAIL) {
++ struct task_struct *task;
++
++ task = container_of(node, struct task_struct, wake_q);
++ /* task can safely be re-inserted now: */
++ node = node->next;
++ task->wake_q.next = NULL;
++
++ /*
++ * wake_up_process() executes a full barrier, which pairs with
++ * the queueing in wake_q_add() so as not to miss wakeups.
++ */
++ wake_up_process(task);
++ put_task_struct(task);
++ }
++}
++
++/*
++ * resched_curr - mark rq's current task 'to be rescheduled now'.
++ *
++ * On UP this means the setting of the need_resched flag, on SMP it
++ * might also involve a cross-CPU call to trigger the scheduler on
++ * the target CPU.
++ */
++static inline void resched_curr(struct rq *rq)
++{
++ struct task_struct *curr = rq->curr;
++ int cpu;
++
++ lockdep_assert_held(&rq->lock);
++
++ if (test_tsk_need_resched(curr))
++ return;
++
++ cpu = cpu_of(rq);
++ if (cpu == smp_processor_id()) {
++ set_tsk_need_resched(curr);
++ set_preempt_need_resched();
++ return;
++ }
++
++ if (set_nr_and_not_polling(curr))
++ smp_send_reschedule(cpu);
++ else
++ trace_sched_wake_idle_without_ipi(cpu);
++}
++
++void resched_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ if (cpu_online(cpu) || cpu == smp_processor_id())
++ resched_curr(cpu_rq(cpu));
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++}
++
++#ifdef CONFIG_SMP
++#ifdef CONFIG_NO_HZ_COMMON
++/*
++ * This routine will record that the CPU is going idle with tick stopped.
++ * This info will be used in performing idle load balancing in the future.
++ */
++void nohz_balance_enter_idle(int cpu) {}
++
++/*
++ * In the semi idle case, use the nearest busy CPU for migrating timers
++ * from an idle CPU. This is good for power-savings.
++ *
++ * We don't do similar optimization for completely idle system, as
++ * selecting an idle CPU will add more delays to the timers than intended
++ * (as that CPU's timer base may not be uptodate wrt jiffies etc).
++ */
++int get_nohz_timer_target(void)
++{
++ int i, cpu = smp_processor_id(), default_cpu = -1;
++ struct cpumask *mask;
++ const struct cpumask *hk_mask;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TIMER)) {
++ if (!idle_cpu(cpu))
++ return cpu;
++ default_cpu = cpu;
++ }
++
++ hk_mask = housekeeping_cpumask(HK_TYPE_TIMER);
++
++ for (mask = per_cpu(sched_cpu_topo_masks, cpu);
++ mask < per_cpu(sched_cpu_topo_end_mask, cpu); mask++)
++ for_each_cpu_and(i, mask, hk_mask)
++ if (!idle_cpu(i))
++ return i;
++
++ if (default_cpu == -1)
++ default_cpu = housekeeping_any_cpu(HK_TYPE_TIMER);
++ cpu = default_cpu;
++
++ return cpu;
++}
++
++/*
++ * When add_timer_on() enqueues a timer into the timer wheel of an
++ * idle CPU then this timer might expire before the next timer event
++ * which is scheduled to wake up that CPU. In case of a completely
++ * idle system the next event might even be infinite time into the
++ * future. wake_up_idle_cpu() ensures that the CPU is woken up and
++ * leaves the inner idle loop so the newly added timer is taken into
++ * account when the CPU goes back to idle and evaluates the timer
++ * wheel for the next timer event.
++ */
++static inline void wake_up_idle_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (cpu == smp_processor_id())
++ return;
++
++ /*
++ * Set TIF_NEED_RESCHED and send an IPI if in the non-polling
++ * part of the idle loop. This forces an exit from the idle loop
++ * and a round trip to schedule(). Now this could be optimized
++ * because a simple new idle loop iteration is enough to
++ * re-evaluate the next tick. Provided some re-ordering of tick
++ * nohz functions that would need to follow TIF_NR_POLLING
++ * clearing:
++ *
++ * - On most archs, a simple fetch_or on ti::flags with a
++ * "0" value would be enough to know if an IPI needs to be sent.
++ *
++ * - x86 needs to perform a last need_resched() check between
++ * monitor and mwait which doesn't take timers into account.
++ * There a dedicated TIF_TIMER flag would be required to
++ * fetch_or here and be checked along with TIF_NEED_RESCHED
++ * before mwait().
++ *
++ * However, remote timer enqueue is not such a frequent event
++ * and testing of the above solutions didn't appear to report
++ * much benefits.
++ */
++ if (set_nr_and_not_polling(rq->idle))
++ smp_send_reschedule(cpu);
++ else
++ trace_sched_wake_idle_without_ipi(cpu);
++}
++
++static inline bool wake_up_full_nohz_cpu(int cpu)
++{
++ /*
++ * We just need the target to call irq_exit() and re-evaluate
++ * the next tick. The nohz full kick at least implies that.
++ * If needed we can still optimize that later with an
++ * empty IRQ.
++ */
++ if (cpu_is_offline(cpu))
++ return true; /* Don't try to wake offline CPUs. */
++ if (tick_nohz_full_cpu(cpu)) {
++ if (cpu != smp_processor_id() ||
++ tick_nohz_tick_stopped())
++ tick_nohz_full_kick_cpu(cpu);
++ return true;
++ }
++
++ return false;
++}
++
++void wake_up_nohz_cpu(int cpu)
++{
++ if (!wake_up_full_nohz_cpu(cpu))
++ wake_up_idle_cpu(cpu);
++}
++
++static void nohz_csd_func(void *info)
++{
++ struct rq *rq = info;
++ int cpu = cpu_of(rq);
++ unsigned int flags;
++
++ /*
++ * Release the rq::nohz_csd.
++ */
++ flags = atomic_fetch_andnot(NOHZ_KICK_MASK, nohz_flags(cpu));
++ WARN_ON(!(flags & NOHZ_KICK_MASK));
++
++ rq->idle_balance = idle_cpu(cpu);
++ if (rq->idle_balance && !need_resched()) {
++ rq->nohz_idle_balance = flags;
++ raise_softirq_irqoff(SCHED_SOFTIRQ);
++ }
++}
++
++#endif /* CONFIG_NO_HZ_COMMON */
++#endif /* CONFIG_SMP */
++
++static inline void wakeup_preempt(struct rq *rq)
++{
++ if (sched_rq_first_task(rq) != rq->curr)
++ resched_curr(rq);
++}
++
++static __always_inline
++int __task_state_match(struct task_struct *p, unsigned int state)
++{
++ if (READ_ONCE(p->__state) & state)
++ return 1;
++
++ if (READ_ONCE(p->saved_state) & state)
++ return -1;
++
++ return 0;
++}
++
++static __always_inline
++int task_state_match(struct task_struct *p, unsigned int state)
++{
++ /*
++ * Serialize against current_save_and_set_rtlock_wait_state(),
++ * current_restore_rtlock_saved_state(), and __refrigerator().
++ */
++ guard(raw_spinlock_irq)(&p->pi_lock);
++
++ return __task_state_match(p, state);
++}
++
++/*
++ * wait_task_inactive - wait for a thread to unschedule.
++ *
++ * Wait for the thread to block in any of the states set in @match_state.
++ * If it changes, i.e. @p might have woken up, then return zero. When we
++ * succeed in waiting for @p to be off its CPU, we return a positive number
++ * (its total switch count). If a second call a short while later returns the
++ * same number, the caller can be sure that @p has remained unscheduled the
++ * whole time.
++ *
++ * The caller must ensure that the task *will* unschedule sometime soon,
++ * else this function might spin for a *long* time. This function can't
++ * be called with interrupts off, or it may introduce deadlock with
++ * smp_call_function() if an IPI is sent by the same process we are
++ * waiting to become inactive.
++ */
++unsigned long wait_task_inactive(struct task_struct *p, unsigned int match_state)
++{
++ unsigned long flags;
++ int running, queued, match;
++ unsigned long ncsw;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ for (;;) {
++ rq = task_rq(p);
++
++ /*
++ * If the task is actively running on another CPU
++ * still, just relax and busy-wait without holding
++ * any locks.
++ *
++ * NOTE! Since we don't hold any locks, it's not
++ * even sure that "rq" stays as the right runqueue!
++ * But we don't care, since this will return false
++ * if the runqueue has changed and p is actually now
++ * running somewhere else!
++ */
++ while (task_on_cpu(p)) {
++ if (!task_state_match(p, match_state))
++ return 0;
++ cpu_relax();
++ }
++
++ /*
++ * Ok, time to look more closely! We need the rq
++ * lock now, to be *sure*. If we're wrong, we'll
++ * just go back and repeat.
++ */
++ task_access_lock_irqsave(p, &lock, &flags);
++ trace_sched_wait_task(p);
++ running = task_on_cpu(p);
++ queued = p->on_rq;
++ ncsw = 0;
++ if ((match = __task_state_match(p, match_state))) {
++ /*
++ * When matching on p->saved_state, consider this task
++ * still queued so it will wait.
++ */
++ if (match < 0)
++ queued = 1;
++ ncsw = p->nvcsw | LONG_MIN; /* sets MSB */
++ }
++ task_access_unlock_irqrestore(p, lock, &flags);
++
++ /*
++ * If it changed from the expected state, bail out now.
++ */
++ if (unlikely(!ncsw))
++ break;
++
++ /*
++ * Was it really running after all now that we
++ * checked with the proper locks actually held?
++ *
++ * Oops. Go back and try again..
++ */
++ if (unlikely(running)) {
++ cpu_relax();
++ continue;
++ }
++
++ /*
++ * It's not enough that it's not actively running,
++ * it must be off the runqueue _entirely_, and not
++ * preempted!
++ *
++ * So if it was still runnable (but just not actively
++ * running right now), it's preempted, and we should
++ * yield - it could be a while.
++ */
++ if (unlikely(queued)) {
++ ktime_t to = NSEC_PER_SEC / HZ;
++
++ set_current_state(TASK_UNINTERRUPTIBLE);
++ schedule_hrtimeout(&to, HRTIMER_MODE_REL_HARD);
++ continue;
++ }
++
++ /*
++ * Ahh, all good. It wasn't running, and it wasn't
++ * runnable, which means that it will never become
++ * running in the future either. We're all done!
++ */
++ break;
++ }
++
++ return ncsw;
++}
++
++#ifdef CONFIG_SCHED_HRTICK
++/*
++ * Use HR-timers to deliver accurate preemption points.
++ */
++
++static void hrtick_clear(struct rq *rq)
++{
++ if (hrtimer_active(&rq->hrtick_timer))
++ hrtimer_cancel(&rq->hrtick_timer);
++}
++
++/*
++ * High-resolution timer tick.
++ * Runs from hardirq context with interrupts disabled.
++ */
++static enum hrtimer_restart hrtick(struct hrtimer *timer)
++{
++ struct rq *rq = container_of(timer, struct rq, hrtick_timer);
++
++ WARN_ON_ONCE(cpu_of(rq) != smp_processor_id());
++
++ raw_spin_lock(&rq->lock);
++ resched_curr(rq);
++ raw_spin_unlock(&rq->lock);
++
++ return HRTIMER_NORESTART;
++}
++
++/*
++ * Use hrtick when:
++ * - enabled by features
++ * - hrtimer is actually high res
++ */
++static inline int hrtick_enabled(struct rq *rq)
++{
++ /**
++ * Alt schedule FW doesn't support sched_feat yet
++ if (!sched_feat(HRTICK))
++ return 0;
++ */
++ if (!cpu_active(cpu_of(rq)))
++ return 0;
++ return hrtimer_is_hres_active(&rq->hrtick_timer);
++}
++
++#ifdef CONFIG_SMP
++
++static void __hrtick_restart(struct rq *rq)
++{
++ struct hrtimer *timer = &rq->hrtick_timer;
++ ktime_t time = rq->hrtick_time;
++
++ hrtimer_start(timer, time, HRTIMER_MODE_ABS_PINNED_HARD);
++}
++
++/*
++ * called from hardirq (IPI) context
++ */
++static void __hrtick_start(void *arg)
++{
++ struct rq *rq = arg;
++
++ raw_spin_lock(&rq->lock);
++ __hrtick_restart(rq);
++ raw_spin_unlock(&rq->lock);
++}
++
++/*
++ * Called to set the hrtick timer state.
++ *
++ * called with rq->lock held and irqs disabled
++ */
++static inline void hrtick_start(struct rq *rq, u64 delay)
++{
++ struct hrtimer *timer = &rq->hrtick_timer;
++ s64 delta;
++
++ /*
++ * Don't schedule slices shorter than 10000ns, that just
++ * doesn't make sense and can cause timer DoS.
++ */
++ delta = max_t(s64, delay, 10000LL);
++
++ rq->hrtick_time = ktime_add_ns(timer->base->get_time(), delta);
++
++ if (rq == this_rq())
++ __hrtick_restart(rq);
++ else
++ smp_call_function_single_async(cpu_of(rq), &rq->hrtick_csd);
++}
++
++#else
++/*
++ * Called to set the hrtick timer state.
++ *
++ * called with rq->lock held and irqs disabled
++ */
++static inline void hrtick_start(struct rq *rq, u64 delay)
++{
++ /*
++ * Don't schedule slices shorter than 10000ns, that just
++ * doesn't make sense. Rely on vruntime for fairness.
++ */
++ delay = max_t(u64, delay, 10000LL);
++ hrtimer_start(&rq->hrtick_timer, ns_to_ktime(delay),
++ HRTIMER_MODE_REL_PINNED_HARD);
++}
++#endif /* CONFIG_SMP */
++
++static void hrtick_rq_init(struct rq *rq)
++{
++#ifdef CONFIG_SMP
++ INIT_CSD(&rq->hrtick_csd, __hrtick_start, rq);
++#endif
++
++ hrtimer_init(&rq->hrtick_timer, CLOCK_MONOTONIC, HRTIMER_MODE_REL_HARD);
++ rq->hrtick_timer.function = hrtick;
++}
++#else /* CONFIG_SCHED_HRTICK */
++static inline int hrtick_enabled(struct rq *rq)
++{
++ return 0;
++}
++
++static inline void hrtick_clear(struct rq *rq)
++{
++}
++
++static inline void hrtick_rq_init(struct rq *rq)
++{
++}
++#endif /* CONFIG_SCHED_HRTICK */
++
++static inline int __normal_prio(int policy, int rt_prio, int static_prio)
++{
++ return rt_policy(policy) ? (MAX_RT_PRIO - 1 - rt_prio) : static_prio;
++}
++
++/*
++ * Calculate the expected normal priority: i.e. priority
++ * without taking RT-inheritance into account. Might be
++ * boosted by interactivity modifiers. Changes upon fork,
++ * setprio syscalls, and whenever the interactivity
++ * estimator recalculates.
++ */
++static inline int normal_prio(struct task_struct *p)
++{
++ return __normal_prio(p->policy, p->rt_priority, p->static_prio);
++}
++
++/*
++ * Calculate the current priority, i.e. the priority
++ * taken into account by the scheduler. This value might
++ * be boosted by RT tasks as it will be RT if the task got
++ * RT-boosted. If not then it returns p->normal_prio.
++ */
++static int effective_prio(struct task_struct *p)
++{
++ p->normal_prio = normal_prio(p);
++ /*
++ * If we are RT tasks or we were boosted to RT priority,
++ * keep the priority unchanged. Otherwise, update priority
++ * to the normal priority:
++ */
++ if (!rt_prio(p->prio))
++ return p->normal_prio;
++ return p->prio;
++}
++
++/*
++ * activate_task - move a task to the runqueue.
++ *
++ * Context: rq->lock
++ */
++static void activate_task(struct task_struct *p, struct rq *rq)
++{
++ enqueue_task(p, rq, ENQUEUE_WAKEUP);
++
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
++ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
++
++ /*
++ * If in_iowait is set, the code below may not trigger any cpufreq
++ * utilization updates, so do it here explicitly with the IOWAIT flag
++ * passed.
++ */
++ cpufreq_update_util(rq, SCHED_CPUFREQ_IOWAIT * p->in_iowait);
++}
++
++/*
++ * deactivate_task - remove a task from the runqueue.
++ *
++ * Context: rq->lock
++ */
++static inline void deactivate_task(struct task_struct *p, struct rq *rq)
++{
++ WRITE_ONCE(p->on_rq, 0);
++ ASSERT_EXCLUSIVE_WRITER(p->on_rq);
++
++ dequeue_task(p, rq, DEQUEUE_SLEEP);
++
++ cpufreq_update_util(rq, 0);
++}
++
++static inline void __set_task_cpu(struct task_struct *p, unsigned int cpu)
++{
++#ifdef CONFIG_SMP
++ /*
++ * After ->cpu is set up to a new value, task_access_lock(p, ...) can be
++ * successfully executed on another CPU. We must ensure that updates of
++ * per-task data have been completed by this moment.
++ */
++ smp_wmb();
++
++ WRITE_ONCE(task_thread_info(p)->cpu, cpu);
++#endif
++}
++
++static inline bool is_migration_disabled(struct task_struct *p)
++{
++#ifdef CONFIG_SMP
++ return p->migration_disabled;
++#else
++ return false;
++#endif
++}
++
++#define SCA_CHECK 0x01
++#define SCA_USER 0x08
++
++#ifdef CONFIG_SMP
++
++void set_task_cpu(struct task_struct *p, unsigned int new_cpu)
++{
++#ifdef CONFIG_SCHED_DEBUG
++ unsigned int state = READ_ONCE(p->__state);
++
++ /*
++ * We should never call set_task_cpu() on a blocked task,
++ * ttwu() will sort out the placement.
++ */
++ WARN_ON_ONCE(state != TASK_RUNNING && state != TASK_WAKING && !p->on_rq);
++
++#ifdef CONFIG_LOCKDEP
++ /*
++ * The caller should hold either p->pi_lock or rq->lock, when changing
++ * a task's CPU. ->pi_lock for waking tasks, rq->lock for runnable tasks.
++ *
++ * sched_move_task() holds both and thus holding either pins the cgroup,
++ * see task_group().
++ */
++ WARN_ON_ONCE(debug_locks && !(lockdep_is_held(&p->pi_lock) ||
++ lockdep_is_held(&task_rq(p)->lock)));
++#endif
++ /*
++ * Clearly, migrating tasks to offline CPUs is a fairly daft thing.
++ */
++ WARN_ON_ONCE(!cpu_online(new_cpu));
++
++ WARN_ON_ONCE(is_migration_disabled(p));
++#endif
++ trace_sched_migrate_task(p, new_cpu);
++
++ if (task_cpu(p) != new_cpu)
++ {
++ rseq_migrate(p);
++ perf_event_task_migrate(p);
++ }
++
++ __set_task_cpu(p, new_cpu);
++}
++
++#define MDF_FORCE_ENABLED 0x80
++
++static void
++__do_set_cpus_ptr(struct task_struct *p, const struct cpumask *new_mask)
++{
++ /*
++ * This here violates the locking rules for affinity, since we're only
++ * supposed to change these variables while holding both rq->lock and
++ * p->pi_lock.
++ *
++ * HOWEVER, it magically works, because ttwu() is the only code that
++ * accesses these variables under p->pi_lock and only does so after
++ * smp_cond_load_acquire(&p->on_cpu, !VAL), and we're in __schedule()
++ * before finish_task().
++ *
++ * XXX do further audits, this smells like something putrid.
++ */
++ SCHED_WARN_ON(!p->on_cpu);
++ p->cpus_ptr = new_mask;
++}
++
++void migrate_disable(void)
++{
++ struct task_struct *p = current;
++ int cpu;
++
++ if (p->migration_disabled) {
++ p->migration_disabled++;
++ return;
++ }
++
++ guard(preempt)();
++ cpu = smp_processor_id();
++ if (cpumask_test_cpu(cpu, &p->cpus_mask)) {
++ cpu_rq(cpu)->nr_pinned++;
++ p->migration_disabled = 1;
++ p->migration_flags &= ~MDF_FORCE_ENABLED;
++
++ /*
++ * Violates locking rules! see comment in __do_set_cpus_ptr().
++ */
++ if (p->cpus_ptr == &p->cpus_mask)
++ __do_set_cpus_ptr(p, cpumask_of(cpu));
++ }
++}
++EXPORT_SYMBOL_GPL(migrate_disable);
++
++void migrate_enable(void)
++{
++ struct task_struct *p = current;
++
++ if (0 == p->migration_disabled)
++ return;
++
++ if (p->migration_disabled > 1) {
++ p->migration_disabled--;
++ return;
++ }
++
++ if (WARN_ON_ONCE(!p->migration_disabled))
++ return;
++
++ /*
++ * Ensure stop_task runs either before or after this, and that
++ * __set_cpus_allowed_ptr(SCA_MIGRATE_ENABLE) doesn't schedule().
++ */
++ guard(preempt)();
++ /*
++ * Assumption: current should be running on allowed cpu
++ */
++ WARN_ON_ONCE(!cpumask_test_cpu(smp_processor_id(), &p->cpus_mask));
++ if (p->cpus_ptr != &p->cpus_mask)
++ __do_set_cpus_ptr(p, &p->cpus_mask);
++ /*
++ * Mustn't clear migration_disabled() until cpus_ptr points back at the
++ * regular cpus_mask, otherwise things that race (eg.
++ * select_fallback_rq) get confused.
++ */
++ barrier();
++ p->migration_disabled = 0;
++ this_rq()->nr_pinned--;
++}
++EXPORT_SYMBOL_GPL(migrate_enable);
++
++static inline bool rq_has_pinned_tasks(struct rq *rq)
++{
++ return rq->nr_pinned;
++}
++
++/*
++ * Per-CPU kthreads are allowed to run on !active && online CPUs, see
++ * __set_cpus_allowed_ptr() and select_fallback_rq().
++ */
++static inline bool is_cpu_allowed(struct task_struct *p, int cpu)
++{
++ /* When not in the task's cpumask, no point in looking further. */
++ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
++ return false;
++
++ /* migrate_disabled() must be allowed to finish. */
++ if (is_migration_disabled(p))
++ return cpu_online(cpu);
++
++ /* Non kernel threads are not allowed during either online or offline. */
++ if (!(p->flags & PF_KTHREAD))
++ return cpu_active(cpu) && task_cpu_possible(cpu, p);
++
++ /* KTHREAD_IS_PER_CPU is always allowed. */
++ if (kthread_is_per_cpu(p))
++ return cpu_online(cpu);
++
++ /* Regular kernel threads don't get to stay during offline. */
++ if (cpu_dying(cpu))
++ return false;
++
++ /* But are allowed during online. */
++ return cpu_online(cpu);
++}
++
++/*
++ * This is how migration works:
++ *
++ * 1) we invoke migration_cpu_stop() on the target CPU using
++ * stop_one_cpu().
++ * 2) stopper starts to run (implicitly forcing the migrated thread
++ * off the CPU)
++ * 3) it checks whether the migrated task is still in the wrong runqueue.
++ * 4) if it's in the wrong runqueue then the migration thread removes
++ * it and puts it into the right queue.
++ * 5) stopper completes and stop_one_cpu() returns and the migration
++ * is done.
++ */
++
++/*
++ * move_queued_task - move a queued task to new rq.
++ *
++ * Returns (locked) new rq. Old rq's lock is released.
++ */
++static struct rq *move_queued_task(struct rq *rq, struct task_struct *p, int new_cpu)
++{
++ int src_cpu;
++
++ lockdep_assert_held(&rq->lock);
++
++ src_cpu = cpu_of(rq);
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_MIGRATING);
++ dequeue_task(p, rq, 0);
++ set_task_cpu(p, new_cpu);
++ raw_spin_unlock(&rq->lock);
++
++ rq = cpu_rq(new_cpu);
++
++ raw_spin_lock(&rq->lock);
++ WARN_ON_ONCE(task_cpu(p) != new_cpu);
++
++ sched_mm_cid_migrate_to(rq, p, src_cpu);
++
++ sched_task_sanity_check(p, rq);
++ enqueue_task(p, rq, 0);
++ WRITE_ONCE(p->on_rq, TASK_ON_RQ_QUEUED);
++ wakeup_preempt(rq);
++
++ return rq;
++}
++
++struct migration_arg {
++ struct task_struct *task;
++ int dest_cpu;
++};
++
++/*
++ * Move (not current) task off this CPU, onto the destination CPU. We're doing
++ * this because either it can't run here any more (set_cpus_allowed()
++ * away from this CPU, or CPU going down), or because we're
++ * attempting to rebalance this task on exec (sched_exec).
++ *
++ * So we race with normal scheduler movements, but that's OK, as long
++ * as the task is no longer on this CPU.
++ */
++static struct rq *__migrate_task(struct rq *rq, struct task_struct *p, int dest_cpu)
++{
++ /* Affinity changed (again). */
++ if (!is_cpu_allowed(p, dest_cpu))
++ return rq;
++
++ return move_queued_task(rq, p, dest_cpu);
++}
++
++/*
++ * migration_cpu_stop - this will be executed by a highprio stopper thread
++ * and performs thread migration by bumping thread off CPU then
++ * 'pushing' onto another runqueue.
++ */
++static int migration_cpu_stop(void *data)
++{
++ struct migration_arg *arg = data;
++ struct task_struct *p = arg->task;
++ struct rq *rq = this_rq();
++ unsigned long flags;
++
++ /*
++ * The original target CPU might have gone down and we might
++ * be on another CPU but it doesn't matter.
++ */
++ local_irq_save(flags);
++ /*
++ * We need to explicitly wake pending tasks before running
++ * __migrate_task() such that we will not miss enforcing cpus_ptr
++ * during wakeups, see set_cpus_allowed_ptr()'s TASK_WAKING test.
++ */
++ flush_smp_call_function_queue();
++
++ raw_spin_lock(&p->pi_lock);
++ raw_spin_lock(&rq->lock);
++ /*
++ * If task_rq(p) != rq, it cannot be migrated here, because we're
++ * holding rq->lock, if p->on_rq == 0 it cannot get enqueued because
++ * we're holding p->pi_lock.
++ */
++ if (task_rq(p) == rq && task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ rq = __migrate_task(rq, p, arg->dest_cpu);
++ }
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ return 0;
++}
++
++static inline void
++set_cpus_allowed_common(struct task_struct *p, struct affinity_context *ctx)
++{
++ cpumask_copy(&p->cpus_mask, ctx->new_mask);
++ p->nr_cpus_allowed = cpumask_weight(ctx->new_mask);
++
++ /*
++ * Swap in a new user_cpus_ptr if SCA_USER flag set
++ */
++ if (ctx->flags & SCA_USER)
++ swap(p->user_cpus_ptr, ctx->user_mask);
++}
++
++static void
++__do_set_cpus_allowed(struct task_struct *p, struct affinity_context *ctx)
++{
++ lockdep_assert_held(&p->pi_lock);
++ set_cpus_allowed_common(p, ctx);
++}
++
++/*
++ * Used for kthread_bind() and select_fallback_rq(), in both cases the user
++ * affinity (if any) should be destroyed too.
++ */
++void do_set_cpus_allowed(struct task_struct *p, const struct cpumask *new_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .user_mask = NULL,
++ .flags = SCA_USER, /* clear the user requested mask */
++ };
++ union cpumask_rcuhead {
++ cpumask_t cpumask;
++ struct rcu_head rcu;
++ };
++
++ __do_set_cpus_allowed(p, &ac);
++
++ /*
++ * Because this is called with p->pi_lock held, it is not possible
++ * to use kfree() here (when PREEMPT_RT=y), therefore punt to using
++ * kfree_rcu().
++ */
++ kfree_rcu((union cpumask_rcuhead *)ac.user_mask, rcu);
++}
++
++static cpumask_t *alloc_user_cpus_ptr(int node)
++{
++ /*
++ * See do_set_cpus_allowed() above for the rcu_head usage.
++ */
++ int size = max_t(int, cpumask_size(), sizeof(struct rcu_head));
++
++ return kmalloc_node(size, GFP_KERNEL, node);
++}
++
++int dup_user_cpus_ptr(struct task_struct *dst, struct task_struct *src,
++ int node)
++{
++ cpumask_t *user_mask;
++ unsigned long flags;
++
++ /*
++ * Always clear dst->user_cpus_ptr first as their user_cpus_ptr's
++ * may differ by now due to racing.
++ */
++ dst->user_cpus_ptr = NULL;
++
++ /*
++ * This check is racy and losing the race is a valid situation.
++ * It is not worth the extra overhead of taking the pi_lock on
++ * every fork/clone.
++ */
++ if (data_race(!src->user_cpus_ptr))
++ return 0;
++
++ user_mask = alloc_user_cpus_ptr(node);
++ if (!user_mask)
++ return -ENOMEM;
++
++ /*
++ * Use pi_lock to protect content of user_cpus_ptr
++ *
++ * Though unlikely, user_cpus_ptr can be reset to NULL by a concurrent
++ * do_set_cpus_allowed().
++ */
++ raw_spin_lock_irqsave(&src->pi_lock, flags);
++ if (src->user_cpus_ptr) {
++ swap(dst->user_cpus_ptr, user_mask);
++ cpumask_copy(dst->user_cpus_ptr, src->user_cpus_ptr);
++ }
++ raw_spin_unlock_irqrestore(&src->pi_lock, flags);
++
++ if (unlikely(user_mask))
++ kfree(user_mask);
++
++ return 0;
++}
++
++static inline struct cpumask *clear_user_cpus_ptr(struct task_struct *p)
++{
++ struct cpumask *user_mask = NULL;
++
++ swap(p->user_cpus_ptr, user_mask);
++
++ return user_mask;
++}
++
++void release_user_cpus_ptr(struct task_struct *p)
++{
++ kfree(clear_user_cpus_ptr(p));
++}
++
++#endif
++
++/**
++ * task_curr - is this task currently executing on a CPU?
++ * @p: the task in question.
++ *
++ * Return: 1 if the task is currently executing. 0 otherwise.
++ */
++inline int task_curr(const struct task_struct *p)
++{
++ return cpu_curr(task_cpu(p)) == p;
++}
++
++#ifdef CONFIG_SMP
++/***
++ * kick_process - kick a running thread to enter/exit the kernel
++ * @p: the to-be-kicked thread
++ *
++ * Cause a process which is running on another CPU to enter
++ * kernel-mode, without any delay. (to get signals handled.)
++ *
++ * NOTE: this function doesn't have to take the runqueue lock,
++ * because all it wants to ensure is that the remote task enters
++ * the kernel. If the IPI races and the task has been migrated
++ * to another CPU then no harm is done and the purpose has been
++ * achieved as well.
++ */
++void kick_process(struct task_struct *p)
++{
++ guard(preempt)();
++ int cpu = task_cpu(p);
++
++ if ((cpu != smp_processor_id()) && task_curr(p))
++ smp_send_reschedule(cpu);
++}
++EXPORT_SYMBOL_GPL(kick_process);
++
++/*
++ * ->cpus_ptr is protected by both rq->lock and p->pi_lock
++ *
++ * A few notes on cpu_active vs cpu_online:
++ *
++ * - cpu_active must be a subset of cpu_online
++ *
++ * - on CPU-up we allow per-CPU kthreads on the online && !active CPU,
++ * see __set_cpus_allowed_ptr(). At this point the newly online
++ * CPU isn't yet part of the sched domains, and balancing will not
++ * see it.
++ *
++ * - on cpu-down we clear cpu_active() to mask the sched domains and
++ * avoid the load balancer to place new tasks on the to be removed
++ * CPU. Existing tasks will remain running there and will be taken
++ * off.
++ *
++ * This means that fallback selection must not select !active CPUs.
++ * And can assume that any active CPU must be online. Conversely
++ * select_task_rq() below may allow selection of !active CPUs in order
++ * to satisfy the above rules.
++ */
++static int select_fallback_rq(int cpu, struct task_struct *p)
++{
++ int nid = cpu_to_node(cpu);
++ const struct cpumask *nodemask = NULL;
++ enum { cpuset, possible, fail } state = cpuset;
++ int dest_cpu;
++
++ /*
++ * If the node that the CPU is on has been offlined, cpu_to_node()
++ * will return -1. There is no CPU on the node, and we should
++ * select the CPU on the other node.
++ */
++ if (nid != -1) {
++ nodemask = cpumask_of_node(nid);
++
++ /* Look for allowed, online CPU in same node. */
++ for_each_cpu(dest_cpu, nodemask) {
++ if (is_cpu_allowed(p, dest_cpu))
++ return dest_cpu;
++ }
++ }
++
++ for (;;) {
++ /* Any allowed, online CPU? */
++ for_each_cpu(dest_cpu, p->cpus_ptr) {
++ if (!is_cpu_allowed(p, dest_cpu))
++ continue;
++ goto out;
++ }
++
++ /* No more Mr. Nice Guy. */
++ switch (state) {
++ case cpuset:
++ if (cpuset_cpus_allowed_fallback(p)) {
++ state = possible;
++ break;
++ }
++ fallthrough;
++ case possible:
++ /*
++ * XXX When called from select_task_rq() we only
++ * hold p->pi_lock and again violate locking order.
++ *
++ * More yuck to audit.
++ */
++ do_set_cpus_allowed(p, task_cpu_possible_mask(p));
++ state = fail;
++ break;
++
++ case fail:
++ BUG();
++ break;
++ }
++ }
++
++out:
++ if (state != cpuset) {
++ /*
++ * Don't tell them about moving exiting tasks or
++ * kernel threads (both mm NULL), since they never
++ * leave kernel.
++ */
++ if (p->mm && printk_ratelimit()) {
++ printk_deferred("process %d (%s) no longer affine to cpu%d\n",
++ task_pid_nr(p), p->comm, cpu);
++ }
++ }
++
++ return dest_cpu;
++}
++
++static inline void
++sched_preempt_mask_flush(cpumask_t *mask, int prio, int ref)
++{
++ int cpu;
++
++ cpumask_copy(mask, sched_preempt_mask + ref);
++ if (prio < ref) {
++ for_each_clear_bit(cpu, cpumask_bits(mask), nr_cpumask_bits) {
++ if (prio < cpu_rq(cpu)->prio)
++ cpumask_set_cpu(cpu, mask);
++ }
++ } else {
++ for_each_cpu_andnot(cpu, mask, sched_idle_mask) {
++ if (prio >= cpu_rq(cpu)->prio)
++ cpumask_clear_cpu(cpu, mask);
++ }
++ }
++}
++
++static inline int
++preempt_mask_check(cpumask_t *preempt_mask, cpumask_t *allow_mask, int prio)
++{
++ cpumask_t *mask = sched_preempt_mask + prio;
++ int pr = atomic_read(&sched_prio_record);
++
++ if (pr != prio && SCHED_QUEUE_BITS - 1 != prio) {
++ sched_preempt_mask_flush(mask, prio, pr);
++ atomic_set(&sched_prio_record, prio);
++ }
++
++ return cpumask_and(preempt_mask, allow_mask, mask);
++}
++
++static inline int select_task_rq(struct task_struct *p)
++{
++ cpumask_t allow_mask, mask;
++
++ if (unlikely(!cpumask_and(&allow_mask, p->cpus_ptr, cpu_active_mask)))
++ return select_fallback_rq(task_cpu(p), p);
++
++ if (
++#ifdef CONFIG_SCHED_SMT
++ cpumask_and(&mask, &allow_mask, sched_sg_idle_mask) ||
++#endif
++ cpumask_and(&mask, &allow_mask, sched_idle_mask) ||
++ preempt_mask_check(&mask, &allow_mask, task_sched_prio(p)))
++ return best_mask_cpu(task_cpu(p), &mask);
++
++ return best_mask_cpu(task_cpu(p), &allow_mask);
++}
++
++void sched_set_stop_task(int cpu, struct task_struct *stop)
++{
++ static struct lock_class_key stop_pi_lock;
++ struct sched_param stop_param = { .sched_priority = STOP_PRIO };
++ struct sched_param start_param = { .sched_priority = 0 };
++ struct task_struct *old_stop = cpu_rq(cpu)->stop;
++
++ if (stop) {
++ /*
++ * Make it appear like a SCHED_FIFO task, its something
++ * userspace knows about and won't get confused about.
++ *
++ * Also, it will make PI more or less work without too
++ * much confusion -- but then, stop work should not
++ * rely on PI working anyway.
++ */
++ sched_setscheduler_nocheck(stop, SCHED_FIFO, &stop_param);
++
++ /*
++ * The PI code calls rt_mutex_setprio() with ->pi_lock held to
++ * adjust the effective priority of a task. As a result,
++ * rt_mutex_setprio() can trigger (RT) balancing operations,
++ * which can then trigger wakeups of the stop thread to push
++ * around the current task.
++ *
++ * The stop task itself will never be part of the PI-chain, it
++ * never blocks, therefore that ->pi_lock recursion is safe.
++ * Tell lockdep about this by placing the stop->pi_lock in its
++ * own class.
++ */
++ lockdep_set_class(&stop->pi_lock, &stop_pi_lock);
++ }
++
++ cpu_rq(cpu)->stop = stop;
++
++ if (old_stop) {
++ /*
++ * Reset it back to a normal scheduling policy so that
++ * it can die in pieces.
++ */
++ sched_setscheduler_nocheck(old_stop, SCHED_NORMAL, &start_param);
++ }
++}
++
++static int affine_move_task(struct rq *rq, struct task_struct *p, int dest_cpu,
++ raw_spinlock_t *lock, unsigned long irq_flags)
++ __releases(rq->lock)
++ __releases(p->pi_lock)
++{
++ /* Can the task run on the task's current CPU? If so, we're done */
++ if (!cpumask_test_cpu(task_cpu(p), &p->cpus_mask)) {
++ if (p->migration_disabled) {
++ if (likely(p->cpus_ptr != &p->cpus_mask))
++ __do_set_cpus_ptr(p, &p->cpus_mask);
++ p->migration_disabled = 0;
++ p->migration_flags |= MDF_FORCE_ENABLED;
++ /* When p is migrate_disabled, rq->lock should be held */
++ rq->nr_pinned--;
++ }
++
++ if (task_on_cpu(p) || READ_ONCE(p->__state) == TASK_WAKING) {
++ struct migration_arg arg = { p, dest_cpu };
++
++ /* Need help from migration thread: drop lock and wait. */
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ stop_one_cpu(cpu_of(rq), migration_cpu_stop, &arg);
++ return 0;
++ }
++ if (task_on_rq_queued(p)) {
++ /*
++ * OK, since we're going to drop the lock immediately
++ * afterwards anyway.
++ */
++ update_rq_clock(rq);
++ rq = move_queued_task(rq, p, dest_cpu);
++ lock = &rq->lock;
++ }
++ }
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ return 0;
++}
++
++static int __set_cpus_allowed_ptr_locked(struct task_struct *p,
++ struct affinity_context *ctx,
++ struct rq *rq,
++ raw_spinlock_t *lock,
++ unsigned long irq_flags)
++{
++ const struct cpumask *cpu_allowed_mask = task_cpu_possible_mask(p);
++ const struct cpumask *cpu_valid_mask = cpu_active_mask;
++ bool kthread = p->flags & PF_KTHREAD;
++ int dest_cpu;
++ int ret = 0;
++
++ if (kthread || is_migration_disabled(p)) {
++ /*
++ * Kernel threads are allowed on online && !active CPUs,
++ * however, during cpu-hot-unplug, even these might get pushed
++ * away if not KTHREAD_IS_PER_CPU.
++ *
++ * Specifically, migration_disabled() tasks must not fail the
++ * cpumask_any_and_distribute() pick below, esp. so on
++ * SCA_MIGRATE_ENABLE, otherwise we'll not call
++ * set_cpus_allowed_common() and actually reset p->cpus_ptr.
++ */
++ cpu_valid_mask = cpu_online_mask;
++ }
++
++ if (!kthread && !cpumask_subset(ctx->new_mask, cpu_allowed_mask)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ /*
++ * Must re-check here, to close a race against __kthread_bind(),
++ * sched_setaffinity() is not guaranteed to observe the flag.
++ */
++ if ((ctx->flags & SCA_CHECK) && (p->flags & PF_NO_SETAFFINITY)) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ if (cpumask_equal(&p->cpus_mask, ctx->new_mask))
++ goto out;
++
++ dest_cpu = cpumask_any_and(cpu_valid_mask, ctx->new_mask);
++ if (dest_cpu >= nr_cpu_ids) {
++ ret = -EINVAL;
++ goto out;
++ }
++
++ __do_set_cpus_allowed(p, ctx);
++
++ return affine_move_task(rq, p, dest_cpu, lock, irq_flags);
++
++out:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++
++ return ret;
++}
++
++/*
++ * Change a given task's CPU affinity. Migrate the thread to a
++ * is removed from the allowed bitmask.
++ *
++ * NOTE: the caller must have a valid reference to the task, the
++ * task must not exit() & deallocate itself prematurely. The
++ * call is not atomic; no spinlocks may be held.
++ */
++static int __set_cpus_allowed_ptr(struct task_struct *p,
++ struct affinity_context *ctx)
++{
++ unsigned long irq_flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
++ rq = __task_access_lock(p, &lock);
++ /*
++ * Masking should be skipped if SCA_USER or any of the SCA_MIGRATE_*
++ * flags are set.
++ */
++ if (p->user_cpus_ptr &&
++ !(ctx->flags & SCA_USER) &&
++ cpumask_and(rq->scratch_mask, ctx->new_mask, p->user_cpus_ptr))
++ ctx->new_mask = rq->scratch_mask;
++
++
++ return __set_cpus_allowed_ptr_locked(p, ctx, rq, lock, irq_flags);
++}
++
++int set_cpus_allowed_ptr(struct task_struct *p, const struct cpumask *new_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .flags = 0,
++ };
++
++ return __set_cpus_allowed_ptr(p, &ac);
++}
++EXPORT_SYMBOL_GPL(set_cpus_allowed_ptr);
++
++/*
++ * Change a given task's CPU affinity to the intersection of its current
++ * affinity mask and @subset_mask, writing the resulting mask to @new_mask.
++ * If user_cpus_ptr is defined, use it as the basis for restricting CPU
++ * affinity or use cpu_online_mask instead.
++ *
++ * If the resulting mask is empty, leave the affinity unchanged and return
++ * -EINVAL.
++ */
++static int restrict_cpus_allowed_ptr(struct task_struct *p,
++ struct cpumask *new_mask,
++ const struct cpumask *subset_mask)
++{
++ struct affinity_context ac = {
++ .new_mask = new_mask,
++ .flags = 0,
++ };
++ unsigned long irq_flags;
++ raw_spinlock_t *lock;
++ struct rq *rq;
++ int err;
++
++ raw_spin_lock_irqsave(&p->pi_lock, irq_flags);
++ rq = __task_access_lock(p, &lock);
++
++ if (!cpumask_and(new_mask, task_user_cpus(p), subset_mask)) {
++ err = -EINVAL;
++ goto err_unlock;
++ }
++
++ return __set_cpus_allowed_ptr_locked(p, &ac, rq, lock, irq_flags);
++
++err_unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, irq_flags);
++ return err;
++}
++
++/*
++ * Restrict the CPU affinity of task @p so that it is a subset of
++ * task_cpu_possible_mask() and point @p->user_cpus_ptr to a copy of the
++ * old affinity mask. If the resulting mask is empty, we warn and walk
++ * up the cpuset hierarchy until we find a suitable mask.
++ */
++void force_compatible_cpus_allowed_ptr(struct task_struct *p)
++{
++ cpumask_var_t new_mask;
++ const struct cpumask *override_mask = task_cpu_possible_mask(p);
++
++ alloc_cpumask_var(&new_mask, GFP_KERNEL);
++
++ /*
++ * __migrate_task() can fail silently in the face of concurrent
++ * offlining of the chosen destination CPU, so take the hotplug
++ * lock to ensure that the migration succeeds.
++ */
++ cpus_read_lock();
++ if (!cpumask_available(new_mask))
++ goto out_set_mask;
++
++ if (!restrict_cpus_allowed_ptr(p, new_mask, override_mask))
++ goto out_free_mask;
++
++ /*
++ * We failed to find a valid subset of the affinity mask for the
++ * task, so override it based on its cpuset hierarchy.
++ */
++ cpuset_cpus_allowed(p, new_mask);
++ override_mask = new_mask;
++
++out_set_mask:
++ if (printk_ratelimit()) {
++ printk_deferred("Overriding affinity for process %d (%s) to CPUs %*pbl\n",
++ task_pid_nr(p), p->comm,
++ cpumask_pr_args(override_mask));
++ }
++
++ WARN_ON(set_cpus_allowed_ptr(p, override_mask));
++out_free_mask:
++ cpus_read_unlock();
++ free_cpumask_var(new_mask);
++}
++
++static int
++__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx);
++
++/*
++ * Restore the affinity of a task @p which was previously restricted by a
++ * call to force_compatible_cpus_allowed_ptr().
++ *
++ * It is the caller's responsibility to serialise this with any calls to
++ * force_compatible_cpus_allowed_ptr(@p).
++ */
++void relax_compatible_cpus_allowed_ptr(struct task_struct *p)
++{
++ struct affinity_context ac = {
++ .new_mask = task_user_cpus(p),
++ .flags = 0,
++ };
++ int ret;
++
++ /*
++ * Try to restore the old affinity mask with __sched_setaffinity().
++ * Cpuset masking will be done there too.
++ */
++ ret = __sched_setaffinity(p, &ac);
++ WARN_ON_ONCE(ret);
++}
++
++#else /* CONFIG_SMP */
++
++static inline int select_task_rq(struct task_struct *p)
++{
++ return 0;
++}
++
++static inline int
++__set_cpus_allowed_ptr(struct task_struct *p,
++ struct affinity_context *ctx)
++{
++ return set_cpus_allowed_ptr(p, ctx->new_mask);
++}
++
++static inline bool rq_has_pinned_tasks(struct rq *rq)
++{
++ return false;
++}
++
++static inline cpumask_t *alloc_user_cpus_ptr(int node)
++{
++ return NULL;
++}
++
++#endif /* !CONFIG_SMP */
++
++static void
++ttwu_stat(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq;
++
++ if (!schedstat_enabled())
++ return;
++
++ rq = this_rq();
++
++#ifdef CONFIG_SMP
++ if (cpu == rq->cpu) {
++ __schedstat_inc(rq->ttwu_local);
++ __schedstat_inc(p->stats.nr_wakeups_local);
++ } else {
++ /** Alt schedule FW ToDo:
++ * How to do ttwu_wake_remote
++ */
++ }
++#endif /* CONFIG_SMP */
++
++ __schedstat_inc(rq->ttwu_count);
++ __schedstat_inc(p->stats.nr_wakeups);
++}
++
++/*
++ * Mark the task runnable.
++ */
++static inline void ttwu_do_wakeup(struct task_struct *p)
++{
++ WRITE_ONCE(p->__state, TASK_RUNNING);
++ trace_sched_wakeup(p);
++}
++
++static inline void
++ttwu_do_activate(struct rq *rq, struct task_struct *p, int wake_flags)
++{
++ if (p->sched_contributes_to_load)
++ rq->nr_uninterruptible--;
++
++ if (
++#ifdef CONFIG_SMP
++ !(wake_flags & WF_MIGRATED) &&
++#endif
++ p->in_iowait) {
++ delayacct_blkio_end(p);
++ atomic_dec(&task_rq(p)->nr_iowait);
++ }
++
++ activate_task(p, rq);
++ wakeup_preempt(rq);
++
++ ttwu_do_wakeup(p);
++}
++
++/*
++ * Consider @p being inside a wait loop:
++ *
++ * for (;;) {
++ * set_current_state(TASK_UNINTERRUPTIBLE);
++ *
++ * if (CONDITION)
++ * break;
++ *
++ * schedule();
++ * }
++ * __set_current_state(TASK_RUNNING);
++ *
++ * between set_current_state() and schedule(). In this case @p is still
++ * runnable, so all that needs doing is change p->state back to TASK_RUNNING in
++ * an atomic manner.
++ *
++ * By taking task_rq(p)->lock we serialize against schedule(), if @p->on_rq
++ * then schedule() must still happen and p->state can be changed to
++ * TASK_RUNNING. Otherwise we lost the race, schedule() has happened, and we
++ * need to do a full wakeup with enqueue.
++ *
++ * Returns: %true when the wakeup is done,
++ * %false otherwise.
++ */
++static int ttwu_runnable(struct task_struct *p, int wake_flags)
++{
++ struct rq *rq;
++ raw_spinlock_t *lock;
++ int ret = 0;
++
++ rq = __task_access_lock(p, &lock);
++ if (task_on_rq_queued(p)) {
++ if (!task_on_cpu(p)) {
++ /*
++ * When on_rq && !on_cpu the task is preempted, see if
++ * it should preempt the task that is current now.
++ */
++ update_rq_clock(rq);
++ wakeup_preempt(rq);
++ }
++ ttwu_do_wakeup(p);
++ ret = 1;
++ }
++ __task_access_unlock(p, lock);
++
++ return ret;
++}
++
++#ifdef CONFIG_SMP
++void sched_ttwu_pending(void *arg)
++{
++ struct llist_node *llist = arg;
++ struct rq *rq = this_rq();
++ struct task_struct *p, *t;
++ struct rq_flags rf;
++
++ if (!llist)
++ return;
++
++ rq_lock_irqsave(rq, &rf);
++ update_rq_clock(rq);
++
++ llist_for_each_entry_safe(p, t, llist, wake_entry.llist) {
++ if (WARN_ON_ONCE(p->on_cpu))
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++
++ if (WARN_ON_ONCE(task_cpu(p) != cpu_of(rq)))
++ set_task_cpu(p, cpu_of(rq));
++
++ ttwu_do_activate(rq, p, p->sched_remote_wakeup ? WF_MIGRATED : 0);
++ }
++
++ /*
++ * Must be after enqueueing at least once task such that
++ * idle_cpu() does not observe a false-negative -- if it does,
++ * it is possible for select_idle_siblings() to stack a number
++ * of tasks on this CPU during that window.
++ *
++ * It is ok to clear ttwu_pending when another task pending.
++ * We will receive IPI after local irq enabled and then enqueue it.
++ * Since now nr_running > 0, idle_cpu() will always get correct result.
++ */
++ WRITE_ONCE(rq->ttwu_pending, 0);
++ rq_unlock_irqrestore(rq, &rf);
++}
++
++/*
++ * Prepare the scene for sending an IPI for a remote smp_call
++ *
++ * Returns true if the caller can proceed with sending the IPI.
++ * Returns false otherwise.
++ */
++bool call_function_single_prep_ipi(int cpu)
++{
++ if (set_nr_if_polling(cpu_rq(cpu)->idle)) {
++ trace_sched_wake_idle_without_ipi(cpu);
++ return false;
++ }
++
++ return true;
++}
++
++/*
++ * Queue a task on the target CPUs wake_list and wake the CPU via IPI if
++ * necessary. The wakee CPU on receipt of the IPI will queue the task
++ * via sched_ttwu_wakeup() for activation so the wakee incurs the cost
++ * of the wakeup instead of the waker.
++ */
++static void __ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ p->sched_remote_wakeup = !!(wake_flags & WF_MIGRATED);
++
++ WRITE_ONCE(rq->ttwu_pending, 1);
++ __smp_call_single_queue(cpu, &p->wake_entry.llist);
++}
++
++static inline bool ttwu_queue_cond(struct task_struct *p, int cpu)
++{
++ /*
++ * Do not complicate things with the async wake_list while the CPU is
++ * in hotplug state.
++ */
++ if (!cpu_active(cpu))
++ return false;
++
++ /* Ensure the task will still be allowed to run on the CPU. */
++ if (!cpumask_test_cpu(cpu, p->cpus_ptr))
++ return false;
++
++ /*
++ * If the CPU does not share cache, then queue the task on the
++ * remote rqs wakelist to avoid accessing remote data.
++ */
++ if (!cpus_share_cache(smp_processor_id(), cpu))
++ return true;
++
++ if (cpu == smp_processor_id())
++ return false;
++
++ /*
++ * If the wakee cpu is idle, or the task is descheduling and the
++ * only running task on the CPU, then use the wakelist to offload
++ * the task activation to the idle (or soon-to-be-idle) CPU as
++ * the current CPU is likely busy. nr_running is checked to
++ * avoid unnecessary task stacking.
++ *
++ * Note that we can only get here with (wakee) p->on_rq=0,
++ * p->on_cpu can be whatever, we've done the dequeue, so
++ * the wakee has been accounted out of ->nr_running.
++ */
++ if (!cpu_rq(cpu)->nr_running)
++ return true;
++
++ return false;
++}
++
++static bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ if (__is_defined(ALT_SCHED_TTWU_QUEUE) && ttwu_queue_cond(p, cpu)) {
++ sched_clock_cpu(cpu); /* Sync clocks across CPUs */
++ __ttwu_queue_wakelist(p, cpu, wake_flags);
++ return true;
++ }
++
++ return false;
++}
++
++void wake_up_if_idle(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ guard(rcu)();
++ if (is_idle_task(rcu_dereference(rq->curr))) {
++ guard(raw_spinlock_irqsave)(&rq->lock);
++ if (is_idle_task(rq->curr))
++ resched_curr(rq);
++ }
++}
++
++extern struct static_key_false sched_asym_cpucapacity;
++
++static __always_inline bool sched_asym_cpucap_active(void)
++{
++ return static_branch_unlikely(&sched_asym_cpucapacity);
++}
++
++bool cpus_equal_capacity(int this_cpu, int that_cpu)
++{
++ if (!sched_asym_cpucap_active())
++ return true;
++
++ if (this_cpu == that_cpu)
++ return true;
++
++ return arch_scale_cpu_capacity(this_cpu) == arch_scale_cpu_capacity(that_cpu);
++}
++
++bool cpus_share_cache(int this_cpu, int that_cpu)
++{
++ if (this_cpu == that_cpu)
++ return true;
++
++ return per_cpu(sd_llc_id, this_cpu) == per_cpu(sd_llc_id, that_cpu);
++}
++#else /* !CONFIG_SMP */
++
++static inline bool ttwu_queue_wakelist(struct task_struct *p, int cpu, int wake_flags)
++{
++ return false;
++}
++
++#endif /* CONFIG_SMP */
++
++static inline void ttwu_queue(struct task_struct *p, int cpu, int wake_flags)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (ttwu_queue_wakelist(p, cpu, wake_flags))
++ return;
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++ ttwu_do_activate(rq, p, wake_flags);
++ raw_spin_unlock(&rq->lock);
++}
++
++/*
++ * Invoked from try_to_wake_up() to check whether the task can be woken up.
++ *
++ * The caller holds p::pi_lock if p != current or has preemption
++ * disabled when p == current.
++ *
++ * The rules of saved_state:
++ *
++ * The related locking code always holds p::pi_lock when updating
++ * p::saved_state, which means the code is fully serialized in both cases.
++ *
++ * For PREEMPT_RT, the lock wait and lock wakeups happen via TASK_RTLOCK_WAIT.
++ * No other bits set. This allows to distinguish all wakeup scenarios.
++ *
++ * For FREEZER, the wakeup happens via TASK_FROZEN. No other bits set. This
++ * allows us to prevent early wakeup of tasks before they can be run on
++ * asymmetric ISA architectures (eg ARMv9).
++ */
++static __always_inline
++bool ttwu_state_match(struct task_struct *p, unsigned int state, int *success)
++{
++ int match;
++
++ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
++ WARN_ON_ONCE((state & TASK_RTLOCK_WAIT) &&
++ state != TASK_RTLOCK_WAIT);
++ }
++
++ *success = !!(match = __task_state_match(p, state));
++
++ /*
++ * Saved state preserves the task state across blocking on
++ * an RT lock or TASK_FREEZABLE tasks. If the state matches,
++ * set p::saved_state to TASK_RUNNING, but do not wake the task
++ * because it waits for a lock wakeup or __thaw_task(). Also
++ * indicate success because from the regular waker's point of
++ * view this has succeeded.
++ *
++ * After acquiring the lock the task will restore p::__state
++ * from p::saved_state which ensures that the regular
++ * wakeup is not lost. The restore will also set
++ * p::saved_state to TASK_RUNNING so any further tests will
++ * not result in false positives vs. @success
++ */
++ if (match < 0)
++ p->saved_state = TASK_RUNNING;
++
++ return match > 0;
++}
++
++/*
++ * Notes on Program-Order guarantees on SMP systems.
++ *
++ * MIGRATION
++ *
++ * The basic program-order guarantee on SMP systems is that when a task [t]
++ * migrates, all its activity on its old CPU [c0] happens-before any subsequent
++ * execution on its new CPU [c1].
++ *
++ * For migration (of runnable tasks) this is provided by the following means:
++ *
++ * A) UNLOCK of the rq(c0)->lock scheduling out task t
++ * B) migration for t is required to synchronize *both* rq(c0)->lock and
++ * rq(c1)->lock (if not at the same time, then in that order).
++ * C) LOCK of the rq(c1)->lock scheduling in task
++ *
++ * Transitivity guarantees that B happens after A and C after B.
++ * Note: we only require RCpc transitivity.
++ * Note: the CPU doing B need not be c0 or c1
++ *
++ * Example:
++ *
++ * CPU0 CPU1 CPU2
++ *
++ * LOCK rq(0)->lock
++ * sched-out X
++ * sched-in Y
++ * UNLOCK rq(0)->lock
++ *
++ * LOCK rq(0)->lock // orders against CPU0
++ * dequeue X
++ * UNLOCK rq(0)->lock
++ *
++ * LOCK rq(1)->lock
++ * enqueue X
++ * UNLOCK rq(1)->lock
++ *
++ * LOCK rq(1)->lock // orders against CPU2
++ * sched-out Z
++ * sched-in X
++ * UNLOCK rq(1)->lock
++ *
++ *
++ * BLOCKING -- aka. SLEEP + WAKEUP
++ *
++ * For blocking we (obviously) need to provide the same guarantee as for
++ * migration. However the means are completely different as there is no lock
++ * chain to provide order. Instead we do:
++ *
++ * 1) smp_store_release(X->on_cpu, 0) -- finish_task()
++ * 2) smp_cond_load_acquire(!X->on_cpu) -- try_to_wake_up()
++ *
++ * Example:
++ *
++ * CPU0 (schedule) CPU1 (try_to_wake_up) CPU2 (schedule)
++ *
++ * LOCK rq(0)->lock LOCK X->pi_lock
++ * dequeue X
++ * sched-out X
++ * smp_store_release(X->on_cpu, 0);
++ *
++ * smp_cond_load_acquire(&X->on_cpu, !VAL);
++ * X->state = WAKING
++ * set_task_cpu(X,2)
++ *
++ * LOCK rq(2)->lock
++ * enqueue X
++ * X->state = RUNNING
++ * UNLOCK rq(2)->lock
++ *
++ * LOCK rq(2)->lock // orders against CPU1
++ * sched-out Z
++ * sched-in X
++ * UNLOCK rq(2)->lock
++ *
++ * UNLOCK X->pi_lock
++ * UNLOCK rq(0)->lock
++ *
++ *
++ * However; for wakeups there is a second guarantee we must provide, namely we
++ * must observe the state that lead to our wakeup. That is, not only must our
++ * task observe its own prior state, it must also observe the stores prior to
++ * its wakeup.
++ *
++ * This means that any means of doing remote wakeups must order the CPU doing
++ * the wakeup against the CPU the task is going to end up running on. This,
++ * however, is already required for the regular Program-Order guarantee above,
++ * since the waking CPU is the one issueing the ACQUIRE (smp_cond_load_acquire).
++ *
++ */
++
++/**
++ * try_to_wake_up - wake up a thread
++ * @p: the thread to be awakened
++ * @state: the mask of task states that can be woken
++ * @wake_flags: wake modifier flags (WF_*)
++ *
++ * Conceptually does:
++ *
++ * If (@state & @p->state) @p->state = TASK_RUNNING.
++ *
++ * If the task was not queued/runnable, also place it back on a runqueue.
++ *
++ * This function is atomic against schedule() which would dequeue the task.
++ *
++ * It issues a full memory barrier before accessing @p->state, see the comment
++ * with set_current_state().
++ *
++ * Uses p->pi_lock to serialize against concurrent wake-ups.
++ *
++ * Relies on p->pi_lock stabilizing:
++ * - p->sched_class
++ * - p->cpus_ptr
++ * - p->sched_task_group
++ * in order to do migration, see its use of select_task_rq()/set_task_cpu().
++ *
++ * Tries really hard to only take one task_rq(p)->lock for performance.
++ * Takes rq->lock in:
++ * - ttwu_runnable() -- old rq, unavoidable, see comment there;
++ * - ttwu_queue() -- new rq, for enqueue of the task;
++ * - psi_ttwu_dequeue() -- much sadness :-( accounting will kill us.
++ *
++ * As a consequence we race really badly with just about everything. See the
++ * many memory barriers and their comments for details.
++ *
++ * Return: %true if @p->state changes (an actual wakeup was done),
++ * %false otherwise.
++ */
++int try_to_wake_up(struct task_struct *p, unsigned int state, int wake_flags)
++{
++ guard(preempt)();
++ int cpu, success = 0;
++
++ if (p == current) {
++ /*
++ * We're waking current, this means 'p->on_rq' and 'task_cpu(p)
++ * == smp_processor_id()'. Together this means we can special
++ * case the whole 'p->on_rq && ttwu_runnable()' case below
++ * without taking any locks.
++ *
++ * In particular:
++ * - we rely on Program-Order guarantees for all the ordering,
++ * - we're serialized against set_special_state() by virtue of
++ * it disabling IRQs (this allows not taking ->pi_lock).
++ */
++ if (!ttwu_state_match(p, state, &success))
++ goto out;
++
++ trace_sched_waking(p);
++ ttwu_do_wakeup(p);
++ goto out;
++ }
++
++ /*
++ * If we are going to wake up a thread waiting for CONDITION we
++ * need to ensure that CONDITION=1 done by the caller can not be
++ * reordered with p->state check below. This pairs with smp_store_mb()
++ * in set_current_state() that the waiting thread does.
++ */
++ scoped_guard (raw_spinlock_irqsave, &p->pi_lock) {
++ smp_mb__after_spinlock();
++ if (!ttwu_state_match(p, state, &success))
++ break;
++
++ trace_sched_waking(p);
++
++ /*
++ * Ensure we load p->on_rq _after_ p->state, otherwise it would
++ * be possible to, falsely, observe p->on_rq == 0 and get stuck
++ * in smp_cond_load_acquire() below.
++ *
++ * sched_ttwu_pending() try_to_wake_up()
++ * STORE p->on_rq = 1 LOAD p->state
++ * UNLOCK rq->lock
++ *
++ * __schedule() (switch to task 'p')
++ * LOCK rq->lock smp_rmb();
++ * smp_mb__after_spinlock();
++ * UNLOCK rq->lock
++ *
++ * [task p]
++ * STORE p->state = UNINTERRUPTIBLE LOAD p->on_rq
++ *
++ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
++ * __schedule(). See the comment for smp_mb__after_spinlock().
++ *
++ * A similar smp_rmb() lives in __task_needs_rq_lock().
++ */
++ smp_rmb();
++ if (READ_ONCE(p->on_rq) && ttwu_runnable(p, wake_flags))
++ break;
++
++#ifdef CONFIG_SMP
++ /*
++ * Ensure we load p->on_cpu _after_ p->on_rq, otherwise it would be
++ * possible to, falsely, observe p->on_cpu == 0.
++ *
++ * One must be running (->on_cpu == 1) in order to remove oneself
++ * from the runqueue.
++ *
++ * __schedule() (switch to task 'p') try_to_wake_up()
++ * STORE p->on_cpu = 1 LOAD p->on_rq
++ * UNLOCK rq->lock
++ *
++ * __schedule() (put 'p' to sleep)
++ * LOCK rq->lock smp_rmb();
++ * smp_mb__after_spinlock();
++ * STORE p->on_rq = 0 LOAD p->on_cpu
++ *
++ * Pairs with the LOCK+smp_mb__after_spinlock() on rq->lock in
++ * __schedule(). See the comment for smp_mb__after_spinlock().
++ *
++ * Form a control-dep-acquire with p->on_rq == 0 above, to ensure
++ * schedule()'s deactivate_task() has 'happened' and p will no longer
++ * care about it's own p->state. See the comment in __schedule().
++ */
++ smp_acquire__after_ctrl_dep();
++
++ /*
++ * We're doing the wakeup (@success == 1), they did a dequeue (p->on_rq
++ * == 0), which means we need to do an enqueue, change p->state to
++ * TASK_WAKING such that we can unlock p->pi_lock before doing the
++ * enqueue, such as ttwu_queue_wakelist().
++ */
++ WRITE_ONCE(p->__state, TASK_WAKING);
++
++ /*
++ * If the owning (remote) CPU is still in the middle of schedule() with
++ * this task as prev, considering queueing p on the remote CPUs wake_list
++ * which potentially sends an IPI instead of spinning on p->on_cpu to
++ * let the waker make forward progress. This is safe because IRQs are
++ * disabled and the IPI will deliver after on_cpu is cleared.
++ *
++ * Ensure we load task_cpu(p) after p->on_cpu:
++ *
++ * set_task_cpu(p, cpu);
++ * STORE p->cpu = @cpu
++ * __schedule() (switch to task 'p')
++ * LOCK rq->lock
++ * smp_mb__after_spin_lock() smp_cond_load_acquire(&p->on_cpu)
++ * STORE p->on_cpu = 1 LOAD p->cpu
++ *
++ * to ensure we observe the correct CPU on which the task is currently
++ * scheduling.
++ */
++ if (smp_load_acquire(&p->on_cpu) &&
++ ttwu_queue_wakelist(p, task_cpu(p), wake_flags))
++ break;
++
++ /*
++ * If the owning (remote) CPU is still in the middle of schedule() with
++ * this task as prev, wait until it's done referencing the task.
++ *
++ * Pairs with the smp_store_release() in finish_task().
++ *
++ * This ensures that tasks getting woken will be fully ordered against
++ * their previous state and preserve Program Order.
++ */
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++
++ sched_task_ttwu(p);
++
++ if ((wake_flags & WF_CURRENT_CPU) &&
++ cpumask_test_cpu(smp_processor_id(), p->cpus_ptr))
++ cpu = smp_processor_id();
++ else
++ cpu = select_task_rq(p);
++
++ if (cpu != task_cpu(p)) {
++ if (p->in_iowait) {
++ delayacct_blkio_end(p);
++ atomic_dec(&task_rq(p)->nr_iowait);
++ }
++
++ wake_flags |= WF_MIGRATED;
++ set_task_cpu(p, cpu);
++ }
++#else
++ sched_task_ttwu(p);
++
++ cpu = task_cpu(p);
++#endif /* CONFIG_SMP */
++
++ ttwu_queue(p, cpu, wake_flags);
++ }
++out:
++ if (success)
++ ttwu_stat(p, task_cpu(p), wake_flags);
++
++ return success;
++}
++
++static bool __task_needs_rq_lock(struct task_struct *p)
++{
++ unsigned int state = READ_ONCE(p->__state);
++
++ /*
++ * Since pi->lock blocks try_to_wake_up(), we don't need rq->lock when
++ * the task is blocked. Make sure to check @state since ttwu() can drop
++ * locks at the end, see ttwu_queue_wakelist().
++ */
++ if (state == TASK_RUNNING || state == TASK_WAKING)
++ return true;
++
++ /*
++ * Ensure we load p->on_rq after p->__state, otherwise it would be
++ * possible to, falsely, observe p->on_rq == 0.
++ *
++ * See try_to_wake_up() for a longer comment.
++ */
++ smp_rmb();
++ if (p->on_rq)
++ return true;
++
++#ifdef CONFIG_SMP
++ /*
++ * Ensure the task has finished __schedule() and will not be referenced
++ * anymore. Again, see try_to_wake_up() for a longer comment.
++ */
++ smp_rmb();
++ smp_cond_load_acquire(&p->on_cpu, !VAL);
++#endif
++
++ return false;
++}
++
++/**
++ * task_call_func - Invoke a function on task in fixed state
++ * @p: Process for which the function is to be invoked, can be @current.
++ * @func: Function to invoke.
++ * @arg: Argument to function.
++ *
++ * Fix the task in it's current state by avoiding wakeups and or rq operations
++ * and call @func(@arg) on it. This function can use ->on_rq and task_curr()
++ * to work out what the state is, if required. Given that @func can be invoked
++ * with a runqueue lock held, it had better be quite lightweight.
++ *
++ * Returns:
++ * Whatever @func returns
++ */
++int task_call_func(struct task_struct *p, task_call_f func, void *arg)
++{
++ struct rq *rq = NULL;
++ struct rq_flags rf;
++ int ret;
++
++ raw_spin_lock_irqsave(&p->pi_lock, rf.flags);
++
++ if (__task_needs_rq_lock(p))
++ rq = __task_rq_lock(p, &rf);
++
++ /*
++ * At this point the task is pinned; either:
++ * - blocked and we're holding off wakeups (pi->lock)
++ * - woken, and we're holding off enqueue (rq->lock)
++ * - queued, and we're holding off schedule (rq->lock)
++ * - running, and we're holding off de-schedule (rq->lock)
++ *
++ * The called function (@func) can use: task_curr(), p->on_rq and
++ * p->__state to differentiate between these states.
++ */
++ ret = func(p, arg);
++
++ if (rq)
++ __task_rq_unlock(rq, &rf);
++
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf.flags);
++ return ret;
++}
++
++/**
++ * cpu_curr_snapshot - Return a snapshot of the currently running task
++ * @cpu: The CPU on which to snapshot the task.
++ *
++ * Returns the task_struct pointer of the task "currently" running on
++ * the specified CPU. If the same task is running on that CPU throughout,
++ * the return value will be a pointer to that task's task_struct structure.
++ * If the CPU did any context switches even vaguely concurrently with the
++ * execution of this function, the return value will be a pointer to the
++ * task_struct structure of a randomly chosen task that was running on
++ * that CPU somewhere around the time that this function was executing.
++ *
++ * If the specified CPU was offline, the return value is whatever it
++ * is, perhaps a pointer to the task_struct structure of that CPU's idle
++ * task, but there is no guarantee. Callers wishing a useful return
++ * value must take some action to ensure that the specified CPU remains
++ * online throughout.
++ *
++ * This function executes full memory barriers before and after fetching
++ * the pointer, which permits the caller to confine this function's fetch
++ * with respect to the caller's accesses to other shared variables.
++ */
++struct task_struct *cpu_curr_snapshot(int cpu)
++{
++ struct task_struct *t;
++
++ smp_mb(); /* Pairing determined by caller's synchronization design. */
++ t = rcu_dereference(cpu_curr(cpu));
++ smp_mb(); /* Pairing determined by caller's synchronization design. */
++ return t;
++}
++
++/**
++ * wake_up_process - Wake up a specific process
++ * @p: The process to be woken up.
++ *
++ * Attempt to wake up the nominated process and move it to the set of runnable
++ * processes.
++ *
++ * Return: 1 if the process was woken up, 0 if it was already running.
++ *
++ * This function executes a full memory barrier before accessing the task state.
++ */
++int wake_up_process(struct task_struct *p)
++{
++ return try_to_wake_up(p, TASK_NORMAL, 0);
++}
++EXPORT_SYMBOL(wake_up_process);
++
++int wake_up_state(struct task_struct *p, unsigned int state)
++{
++ return try_to_wake_up(p, state, 0);
++}
++
++/*
++ * Perform scheduler related setup for a newly forked process p.
++ * p is forked by current.
++ *
++ * __sched_fork() is basic setup used by init_idle() too:
++ */
++static inline void __sched_fork(unsigned long clone_flags, struct task_struct *p)
++{
++ p->on_rq = 0;
++ p->on_cpu = 0;
++ p->utime = 0;
++ p->stime = 0;
++ p->sched_time = 0;
++
++#ifdef CONFIG_SCHEDSTATS
++ /* Even if schedstat is disabled, there should not be garbage */
++ memset(&p->stats, 0, sizeof(p->stats));
++#endif
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++ INIT_HLIST_HEAD(&p->preempt_notifiers);
++#endif
++
++#ifdef CONFIG_COMPACTION
++ p->capture_control = NULL;
++#endif
++#ifdef CONFIG_SMP
++ p->wake_entry.u_flags = CSD_TYPE_TTWU;
++#endif
++ init_sched_mm_cid(p);
++}
++
++/*
++ * fork()/clone()-time setup:
++ */
++int sched_fork(unsigned long clone_flags, struct task_struct *p)
++{
++ __sched_fork(clone_flags, p);
++ /*
++ * We mark the process as NEW here. This guarantees that
++ * nobody will actually run it, and a signal or other external
++ * event cannot wake it up and insert it on the runqueue either.
++ */
++ p->__state = TASK_NEW;
++
++ /*
++ * Make sure we do not leak PI boosting priority to the child.
++ */
++ p->prio = current->normal_prio;
++
++ /*
++ * Revert to default priority/policy on fork if requested.
++ */
++ if (unlikely(p->sched_reset_on_fork)) {
++ if (task_has_rt_policy(p)) {
++ p->policy = SCHED_NORMAL;
++ p->static_prio = NICE_TO_PRIO(0);
++ p->rt_priority = 0;
++ } else if (PRIO_TO_NICE(p->static_prio) < 0)
++ p->static_prio = NICE_TO_PRIO(0);
++
++ p->prio = p->normal_prio = p->static_prio;
++
++ /*
++ * We don't need the reset flag anymore after the fork. It has
++ * fulfilled its duty:
++ */
++ p->sched_reset_on_fork = 0;
++ }
++
++#ifdef CONFIG_SCHED_INFO
++ if (unlikely(sched_info_on()))
++ memset(&p->sched_info, 0, sizeof(p->sched_info));
++#endif
++ init_task_preempt_count(p);
++
++ return 0;
++}
++
++void sched_cgroup_fork(struct task_struct *p, struct kernel_clone_args *kargs)
++{
++ unsigned long flags;
++ struct rq *rq;
++
++ /*
++ * Because we're not yet on the pid-hash, p->pi_lock isn't strictly
++ * required yet, but lockdep gets upset if rules are violated.
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ /*
++ * Share the timeslice between parent and child, thus the
++ * total amount of pending timeslices in the system doesn't change,
++ * resulting in more scheduling fairness.
++ */
++ rq = this_rq();
++ raw_spin_lock(&rq->lock);
++
++ rq->curr->time_slice /= 2;
++ p->time_slice = rq->curr->time_slice;
++#ifdef CONFIG_SCHED_HRTICK
++ hrtick_start(rq, rq->curr->time_slice);
++#endif
++
++ if (p->time_slice < RESCHED_NS) {
++ p->time_slice = sysctl_sched_base_slice;
++ resched_curr(rq);
++ }
++ sched_task_fork(p, rq);
++ raw_spin_unlock(&rq->lock);
++
++ rseq_migrate(p);
++ /*
++ * We're setting the CPU for the first time, we don't migrate,
++ * so use __set_task_cpu().
++ */
++ __set_task_cpu(p, smp_processor_id());
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++
++void sched_post_fork(struct task_struct *p)
++{
++}
++
++#ifdef CONFIG_SCHEDSTATS
++
++DEFINE_STATIC_KEY_FALSE(sched_schedstats);
++
++static void set_schedstats(bool enabled)
++{
++ if (enabled)
++ static_branch_enable(&sched_schedstats);
++ else
++ static_branch_disable(&sched_schedstats);
++}
++
++void force_schedstat_enabled(void)
++{
++ if (!schedstat_enabled()) {
++ pr_info("kernel profiling enabled schedstats, disable via kernel.sched_schedstats.\n");
++ static_branch_enable(&sched_schedstats);
++ }
++}
++
++static int __init setup_schedstats(char *str)
++{
++ int ret = 0;
++ if (!str)
++ goto out;
++
++ if (!strcmp(str, "enable")) {
++ set_schedstats(true);
++ ret = 1;
++ } else if (!strcmp(str, "disable")) {
++ set_schedstats(false);
++ ret = 1;
++ }
++out:
++ if (!ret)
++ pr_warn("Unable to parse schedstats=\n");
++
++ return ret;
++}
++__setup("schedstats=", setup_schedstats);
++
++#ifdef CONFIG_PROC_SYSCTL
++static int sysctl_schedstats(struct ctl_table *table, int write, void *buffer,
++ size_t *lenp, loff_t *ppos)
++{
++ struct ctl_table t;
++ int err;
++ int state = static_branch_likely(&sched_schedstats);
++
++ if (write && !capable(CAP_SYS_ADMIN))
++ return -EPERM;
++
++ t = *table;
++ t.data = &state;
++ err = proc_dointvec_minmax(&t, write, buffer, lenp, ppos);
++ if (err < 0)
++ return err;
++ if (write)
++ set_schedstats(state);
++ return err;
++}
++
++static struct ctl_table sched_core_sysctls[] = {
++ {
++ .procname = "sched_schedstats",
++ .data = NULL,
++ .maxlen = sizeof(unsigned int),
++ .mode = 0644,
++ .proc_handler = sysctl_schedstats,
++ .extra1 = SYSCTL_ZERO,
++ .extra2 = SYSCTL_ONE,
++ },
++};
++static int __init sched_core_sysctl_init(void)
++{
++ register_sysctl_init("kernel", sched_core_sysctls);
++ return 0;
++}
++late_initcall(sched_core_sysctl_init);
++#endif /* CONFIG_PROC_SYSCTL */
++#endif /* CONFIG_SCHEDSTATS */
++
++/*
++ * wake_up_new_task - wake up a newly created task for the first time.
++ *
++ * This function will do some initial scheduler statistics housekeeping
++ * that must be done for every newly created context, then puts the task
++ * on the runqueue and wakes it.
++ */
++void wake_up_new_task(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ WRITE_ONCE(p->__state, TASK_RUNNING);
++ rq = cpu_rq(select_task_rq(p));
++#ifdef CONFIG_SMP
++ rseq_migrate(p);
++ /*
++ * Fork balancing, do it here and not earlier because:
++ * - cpus_ptr can change in the fork path
++ * - any previously selected CPU might disappear through hotplug
++ *
++ * Use __set_task_cpu() to avoid calling sched_class::migrate_task_rq,
++ * as we're not fully set-up yet.
++ */
++ __set_task_cpu(p, cpu_of(rq));
++#endif
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++
++ activate_task(p, rq);
++ trace_sched_wakeup_new(p);
++ wakeup_preempt(rq);
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++
++#ifdef CONFIG_PREEMPT_NOTIFIERS
++
++static DEFINE_STATIC_KEY_FALSE(preempt_notifier_key);
++
++void preempt_notifier_inc(void)
++{
++ static_branch_inc(&preempt_notifier_key);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_inc);
++
++void preempt_notifier_dec(void)
++{
++ static_branch_dec(&preempt_notifier_key);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_dec);
++
++/**
++ * preempt_notifier_register - tell me when current is being preempted & rescheduled
++ * @notifier: notifier struct to register
++ */
++void preempt_notifier_register(struct preempt_notifier *notifier)
++{
++ if (!static_branch_unlikely(&preempt_notifier_key))
++ WARN(1, "registering preempt_notifier while notifiers disabled\n");
++
++ hlist_add_head(¬ifier->link, ¤t->preempt_notifiers);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_register);
++
++/**
++ * preempt_notifier_unregister - no longer interested in preemption notifications
++ * @notifier: notifier struct to unregister
++ *
++ * This is *not* safe to call from within a preemption notifier.
++ */
++void preempt_notifier_unregister(struct preempt_notifier *notifier)
++{
++ hlist_del(¬ifier->link);
++}
++EXPORT_SYMBOL_GPL(preempt_notifier_unregister);
++
++static void __fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_in(notifier, raw_smp_processor_id());
++}
++
++static __always_inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++ if (static_branch_unlikely(&preempt_notifier_key))
++ __fire_sched_in_preempt_notifiers(curr);
++}
++
++static void
++__fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++ struct preempt_notifier *notifier;
++
++ hlist_for_each_entry(notifier, &curr->preempt_notifiers, link)
++ notifier->ops->sched_out(notifier, next);
++}
++
++static __always_inline void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++ if (static_branch_unlikely(&preempt_notifier_key))
++ __fire_sched_out_preempt_notifiers(curr, next);
++}
++
++#else /* !CONFIG_PREEMPT_NOTIFIERS */
++
++static inline void fire_sched_in_preempt_notifiers(struct task_struct *curr)
++{
++}
++
++static inline void
++fire_sched_out_preempt_notifiers(struct task_struct *curr,
++ struct task_struct *next)
++{
++}
++
++#endif /* CONFIG_PREEMPT_NOTIFIERS */
++
++static inline void prepare_task(struct task_struct *next)
++{
++ /*
++ * Claim the task as running, we do this before switching to it
++ * such that any running task will have this set.
++ *
++ * See the smp_load_acquire(&p->on_cpu) case in ttwu() and
++ * its ordering comment.
++ */
++ WRITE_ONCE(next->on_cpu, 1);
++}
++
++static inline void finish_task(struct task_struct *prev)
++{
++#ifdef CONFIG_SMP
++ /*
++ * This must be the very last reference to @prev from this CPU. After
++ * p->on_cpu is cleared, the task can be moved to a different CPU. We
++ * must ensure this doesn't happen until the switch is completely
++ * finished.
++ *
++ * In particular, the load of prev->state in finish_task_switch() must
++ * happen before this.
++ *
++ * Pairs with the smp_cond_load_acquire() in try_to_wake_up().
++ */
++ smp_store_release(&prev->on_cpu, 0);
++#else
++ prev->on_cpu = 0;
++#endif
++}
++
++#ifdef CONFIG_SMP
++
++static void do_balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++ void (*func)(struct rq *rq);
++ struct balance_callback *next;
++
++ lockdep_assert_held(&rq->lock);
++
++ while (head) {
++ func = (void (*)(struct rq *))head->func;
++ next = head->next;
++ head->next = NULL;
++ head = next;
++
++ func(rq);
++ }
++}
++
++static void balance_push(struct rq *rq);
++
++/*
++ * balance_push_callback is a right abuse of the callback interface and plays
++ * by significantly different rules.
++ *
++ * Where the normal balance_callback's purpose is to be ran in the same context
++ * that queued it (only later, when it's safe to drop rq->lock again),
++ * balance_push_callback is specifically targeted at __schedule().
++ *
++ * This abuse is tolerated because it places all the unlikely/odd cases behind
++ * a single test, namely: rq->balance_callback == NULL.
++ */
++struct balance_callback balance_push_callback = {
++ .next = NULL,
++ .func = balance_push,
++};
++
++static inline struct balance_callback *
++__splice_balance_callbacks(struct rq *rq, bool split)
++{
++ struct balance_callback *head = rq->balance_callback;
++
++ if (likely(!head))
++ return NULL;
++
++ lockdep_assert_rq_held(rq);
++ /*
++ * Must not take balance_push_callback off the list when
++ * splice_balance_callbacks() and balance_callbacks() are not
++ * in the same rq->lock section.
++ *
++ * In that case it would be possible for __schedule() to interleave
++ * and observe the list empty.
++ */
++ if (split && head == &balance_push_callback)
++ head = NULL;
++ else
++ rq->balance_callback = NULL;
++
++ return head;
++}
++
++static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
++{
++ return __splice_balance_callbacks(rq, true);
++}
++
++static void __balance_callbacks(struct rq *rq)
++{
++ do_balance_callbacks(rq, __splice_balance_callbacks(rq, false));
++}
++
++static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++ unsigned long flags;
++
++ if (unlikely(head)) {
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ do_balance_callbacks(rq, head);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++ }
++}
++
++#else
++
++static inline void __balance_callbacks(struct rq *rq)
++{
++}
++
++static inline struct balance_callback *splice_balance_callbacks(struct rq *rq)
++{
++ return NULL;
++}
++
++static inline void balance_callbacks(struct rq *rq, struct balance_callback *head)
++{
++}
++
++#endif
++
++static inline void
++prepare_lock_switch(struct rq *rq, struct task_struct *next)
++{
++ /*
++ * Since the runqueue lock will be released by the next
++ * task (which is an invalid locking op but in the case
++ * of the scheduler it's an obvious special-case), so we
++ * do an early lockdep release here:
++ */
++ spin_release(&rq->lock.dep_map, _THIS_IP_);
++#ifdef CONFIG_DEBUG_SPINLOCK
++ /* this is a valid case when another task releases the spinlock */
++ rq->lock.owner = next;
++#endif
++}
++
++static inline void finish_lock_switch(struct rq *rq)
++{
++ /*
++ * If we are tracking spinlock dependencies then we have to
++ * fix up the runqueue lock - which gets 'carried over' from
++ * prev into current:
++ */
++ spin_acquire(&rq->lock.dep_map, 0, 0, _THIS_IP_);
++ __balance_callbacks(rq);
++ raw_spin_unlock_irq(&rq->lock);
++}
++
++/*
++ * NOP if the arch has not defined these:
++ */
++
++#ifndef prepare_arch_switch
++# define prepare_arch_switch(next) do { } while (0)
++#endif
++
++#ifndef finish_arch_post_lock_switch
++# define finish_arch_post_lock_switch() do { } while (0)
++#endif
++
++static inline void kmap_local_sched_out(void)
++{
++#ifdef CONFIG_KMAP_LOCAL
++ if (unlikely(current->kmap_ctrl.idx))
++ __kmap_local_sched_out();
++#endif
++}
++
++static inline void kmap_local_sched_in(void)
++{
++#ifdef CONFIG_KMAP_LOCAL
++ if (unlikely(current->kmap_ctrl.idx))
++ __kmap_local_sched_in();
++#endif
++}
++
++/**
++ * prepare_task_switch - prepare to switch tasks
++ * @rq: the runqueue preparing to switch
++ * @next: the task we are going to switch to.
++ *
++ * This is called with the rq lock held and interrupts off. It must
++ * be paired with a subsequent finish_task_switch after the context
++ * switch.
++ *
++ * prepare_task_switch sets up locking and calls architecture specific
++ * hooks.
++ */
++static inline void
++prepare_task_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ kcov_prepare_switch(prev);
++ sched_info_switch(rq, prev, next);
++ perf_event_task_sched_out(prev, next);
++ rseq_preempt(prev);
++ fire_sched_out_preempt_notifiers(prev, next);
++ kmap_local_sched_out();
++ prepare_task(next);
++ prepare_arch_switch(next);
++}
++
++/**
++ * finish_task_switch - clean up after a task-switch
++ * @rq: runqueue associated with task-switch
++ * @prev: the thread we just switched away from.
++ *
++ * finish_task_switch must be called after the context switch, paired
++ * with a prepare_task_switch call before the context switch.
++ * finish_task_switch will reconcile locking set up by prepare_task_switch,
++ * and do any other architecture-specific cleanup actions.
++ *
++ * Note that we may have delayed dropping an mm in context_switch(). If
++ * so, we finish that here outside of the runqueue lock. (Doing it
++ * with the lock held can cause deadlocks; see schedule() for
++ * details.)
++ *
++ * The context switch have flipped the stack from under us and restored the
++ * local variables which were saved when this task called schedule() in the
++ * past. prev == current is still correct but we need to recalculate this_rq
++ * because prev may have moved to another CPU.
++ */
++static struct rq *finish_task_switch(struct task_struct *prev)
++ __releases(rq->lock)
++{
++ struct rq *rq = this_rq();
++ struct mm_struct *mm = rq->prev_mm;
++ unsigned int prev_state;
++
++ /*
++ * The previous task will have left us with a preempt_count of 2
++ * because it left us after:
++ *
++ * schedule()
++ * preempt_disable(); // 1
++ * __schedule()
++ * raw_spin_lock_irq(&rq->lock) // 2
++ *
++ * Also, see FORK_PREEMPT_COUNT.
++ */
++ if (WARN_ONCE(preempt_count() != 2*PREEMPT_DISABLE_OFFSET,
++ "corrupted preempt_count: %s/%d/0x%x\n",
++ current->comm, current->pid, preempt_count()))
++ preempt_count_set(FORK_PREEMPT_COUNT);
++
++ rq->prev_mm = NULL;
++
++ /*
++ * A task struct has one reference for the use as "current".
++ * If a task dies, then it sets TASK_DEAD in tsk->state and calls
++ * schedule one last time. The schedule call will never return, and
++ * the scheduled task must drop that reference.
++ *
++ * We must observe prev->state before clearing prev->on_cpu (in
++ * finish_task), otherwise a concurrent wakeup can get prev
++ * running on another CPU and we could rave with its RUNNING -> DEAD
++ * transition, resulting in a double drop.
++ */
++ prev_state = READ_ONCE(prev->__state);
++ vtime_task_switch(prev);
++ perf_event_task_sched_in(prev, current);
++ finish_task(prev);
++ tick_nohz_task_switch();
++ finish_lock_switch(rq);
++ finish_arch_post_lock_switch();
++ kcov_finish_switch(current);
++ /*
++ * kmap_local_sched_out() is invoked with rq::lock held and
++ * interrupts disabled. There is no requirement for that, but the
++ * sched out code does not have an interrupt enabled section.
++ * Restoring the maps on sched in does not require interrupts being
++ * disabled either.
++ */
++ kmap_local_sched_in();
++
++ fire_sched_in_preempt_notifiers(current);
++ /*
++ * When switching through a kernel thread, the loop in
++ * membarrier_{private,global}_expedited() may have observed that
++ * kernel thread and not issued an IPI. It is therefore possible to
++ * schedule between user->kernel->user threads without passing though
++ * switch_mm(). Membarrier requires a barrier after storing to
++ * rq->curr, before returning to userspace, so provide them here:
++ *
++ * - a full memory barrier for {PRIVATE,GLOBAL}_EXPEDITED, implicitly
++ * provided by mmdrop(),
++ * - a sync_core for SYNC_CORE.
++ */
++ if (mm) {
++ membarrier_mm_sync_core_before_usermode(mm);
++ mmdrop_sched(mm);
++ }
++ if (unlikely(prev_state == TASK_DEAD)) {
++ /* Task is done with its stack. */
++ put_task_stack(prev);
++
++ put_task_struct_rcu_user(prev);
++ }
++
++ return rq;
++}
++
++/**
++ * schedule_tail - first thing a freshly forked thread must call.
++ * @prev: the thread we just switched away from.
++ */
++asmlinkage __visible void schedule_tail(struct task_struct *prev)
++ __releases(rq->lock)
++{
++ /*
++ * New tasks start with FORK_PREEMPT_COUNT, see there and
++ * finish_task_switch() for details.
++ *
++ * finish_task_switch() will drop rq->lock() and lower preempt_count
++ * and the preempt_enable() will end up enabling preemption (on
++ * PREEMPT_COUNT kernels).
++ */
++
++ finish_task_switch(prev);
++ preempt_enable();
++
++ if (current->set_child_tid)
++ put_user(task_pid_vnr(current), current->set_child_tid);
++
++ calculate_sigpending();
++}
++
++/*
++ * context_switch - switch to the new MM and the new thread's register state.
++ */
++static __always_inline struct rq *
++context_switch(struct rq *rq, struct task_struct *prev,
++ struct task_struct *next)
++{
++ prepare_task_switch(rq, prev, next);
++
++ /*
++ * For paravirt, this is coupled with an exit in switch_to to
++ * combine the page table reload and the switch backend into
++ * one hypercall.
++ */
++ arch_start_context_switch(prev);
++
++ /*
++ * kernel -> kernel lazy + transfer active
++ * user -> kernel lazy + mmgrab() active
++ *
++ * kernel -> user switch + mmdrop() active
++ * user -> user switch
++ *
++ * switch_mm_cid() needs to be updated if the barriers provided
++ * by context_switch() are modified.
++ */
++ if (!next->mm) { // to kernel
++ enter_lazy_tlb(prev->active_mm, next);
++
++ next->active_mm = prev->active_mm;
++ if (prev->mm) // from user
++ mmgrab(prev->active_mm);
++ else
++ prev->active_mm = NULL;
++ } else { // to user
++ membarrier_switch_mm(rq, prev->active_mm, next->mm);
++ /*
++ * sys_membarrier() requires an smp_mb() between setting
++ * rq->curr / membarrier_switch_mm() and returning to userspace.
++ *
++ * The below provides this either through switch_mm(), or in
++ * case 'prev->active_mm == next->mm' through
++ * finish_task_switch()'s mmdrop().
++ */
++ switch_mm_irqs_off(prev->active_mm, next->mm, next);
++ lru_gen_use_mm(next->mm);
++
++ if (!prev->mm) { // from kernel
++ /* will mmdrop() in finish_task_switch(). */
++ rq->prev_mm = prev->active_mm;
++ prev->active_mm = NULL;
++ }
++ }
++
++ /* switch_mm_cid() requires the memory barriers above. */
++ switch_mm_cid(rq, prev, next);
++
++ prepare_lock_switch(rq, next);
++
++ /* Here we just switch the register state and the stack. */
++ switch_to(prev, next, prev);
++ barrier();
++
++ return finish_task_switch(prev);
++}
++
++/*
++ * nr_running, nr_uninterruptible and nr_context_switches:
++ *
++ * externally visible scheduler statistics: current number of runnable
++ * threads, total number of context switches performed since bootup.
++ */
++unsigned int nr_running(void)
++{
++ unsigned int i, sum = 0;
++
++ for_each_online_cpu(i)
++ sum += cpu_rq(i)->nr_running;
++
++ return sum;
++}
++
++/*
++ * Check if only the current task is running on the CPU.
++ *
++ * Caution: this function does not check that the caller has disabled
++ * preemption, thus the result might have a time-of-check-to-time-of-use
++ * race. The caller is responsible to use it correctly, for example:
++ *
++ * - from a non-preemptible section (of course)
++ *
++ * - from a thread that is bound to a single CPU
++ *
++ * - in a loop with very short iterations (e.g. a polling loop)
++ */
++bool single_task_running(void)
++{
++ return raw_rq()->nr_running == 1;
++}
++EXPORT_SYMBOL(single_task_running);
++
++unsigned long long nr_context_switches_cpu(int cpu)
++{
++ return cpu_rq(cpu)->nr_switches;
++}
++
++unsigned long long nr_context_switches(void)
++{
++ int i;
++ unsigned long long sum = 0;
++
++ for_each_possible_cpu(i)
++ sum += cpu_rq(i)->nr_switches;
++
++ return sum;
++}
++
++/*
++ * Consumers of these two interfaces, like for example the cpuidle menu
++ * governor, are using nonsensical data. Preferring shallow idle state selection
++ * for a CPU that has IO-wait which might not even end up running the task when
++ * it does become runnable.
++ */
++
++unsigned int nr_iowait_cpu(int cpu)
++{
++ return atomic_read(&cpu_rq(cpu)->nr_iowait);
++}
++
++/*
++ * IO-wait accounting, and how it's mostly bollocks (on SMP).
++ *
++ * The idea behind IO-wait account is to account the idle time that we could
++ * have spend running if it were not for IO. That is, if we were to improve the
++ * storage performance, we'd have a proportional reduction in IO-wait time.
++ *
++ * This all works nicely on UP, where, when a task blocks on IO, we account
++ * idle time as IO-wait, because if the storage were faster, it could've been
++ * running and we'd not be idle.
++ *
++ * This has been extended to SMP, by doing the same for each CPU. This however
++ * is broken.
++ *
++ * Imagine for instance the case where two tasks block on one CPU, only the one
++ * CPU will have IO-wait accounted, while the other has regular idle. Even
++ * though, if the storage were faster, both could've ran at the same time,
++ * utilising both CPUs.
++ *
++ * This means, that when looking globally, the current IO-wait accounting on
++ * SMP is a lower bound, by reason of under accounting.
++ *
++ * Worse, since the numbers are provided per CPU, they are sometimes
++ * interpreted per CPU, and that is nonsensical. A blocked task isn't strictly
++ * associated with any one particular CPU, it can wake to another CPU than it
++ * blocked on. This means the per CPU IO-wait number is meaningless.
++ *
++ * Task CPU affinities can make all that even more 'interesting'.
++ */
++
++unsigned int nr_iowait(void)
++{
++ unsigned int i, sum = 0;
++
++ for_each_possible_cpu(i)
++ sum += nr_iowait_cpu(i);
++
++ return sum;
++}
++
++#ifdef CONFIG_SMP
++
++/*
++ * sched_exec - execve() is a valuable balancing opportunity, because at
++ * this point the task has the smallest effective memory and cache
++ * footprint.
++ */
++void sched_exec(void)
++{
++}
++
++#endif
++
++DEFINE_PER_CPU(struct kernel_stat, kstat);
++DEFINE_PER_CPU(struct kernel_cpustat, kernel_cpustat);
++
++EXPORT_PER_CPU_SYMBOL(kstat);
++EXPORT_PER_CPU_SYMBOL(kernel_cpustat);
++
++static inline void update_curr(struct rq *rq, struct task_struct *p)
++{
++ s64 ns = rq->clock_task - p->last_ran;
++
++ p->sched_time += ns;
++ cgroup_account_cputime(p, ns);
++ account_group_exec_runtime(p, ns);
++
++ p->time_slice -= ns;
++ p->last_ran = rq->clock_task;
++}
++
++/*
++ * Return accounted runtime for the task.
++ * Return separately the current's pending runtime that have not been
++ * accounted yet.
++ */
++unsigned long long task_sched_runtime(struct task_struct *p)
++{
++ unsigned long flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++ u64 ns;
++
++#if defined(CONFIG_64BIT) && defined(CONFIG_SMP)
++ /*
++ * 64-bit doesn't need locks to atomically read a 64-bit value.
++ * So we have a optimization chance when the task's delta_exec is 0.
++ * Reading ->on_cpu is racy, but this is ok.
++ *
++ * If we race with it leaving CPU, we'll take a lock. So we're correct.
++ * If we race with it entering CPU, unaccounted time is 0. This is
++ * indistinguishable from the read occurring a few cycles earlier.
++ * If we see ->on_cpu without ->on_rq, the task is leaving, and has
++ * been accounted, so we're correct here as well.
++ */
++ if (!p->on_cpu || !task_on_rq_queued(p))
++ return tsk_seruntime(p);
++#endif
++
++ rq = task_access_lock_irqsave(p, &lock, &flags);
++ /*
++ * Must be ->curr _and_ ->on_rq. If dequeued, we would
++ * project cycles that may never be accounted to this
++ * thread, breaking clock_gettime().
++ */
++ if (p == rq->curr && task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ update_curr(rq, p);
++ }
++ ns = tsk_seruntime(p);
++ task_access_unlock_irqrestore(p, lock, &flags);
++
++ return ns;
++}
++
++/* This manages tasks that have run out of timeslice during a scheduler_tick */
++static inline void scheduler_task_tick(struct rq *rq)
++{
++ struct task_struct *p = rq->curr;
++
++ if (is_idle_task(p))
++ return;
++
++ update_curr(rq, p);
++ cpufreq_update_util(rq, 0);
++
++ /*
++ * Tasks have less than RESCHED_NS of time slice left they will be
++ * rescheduled.
++ */
++ if (p->time_slice >= RESCHED_NS)
++ return;
++ set_tsk_need_resched(p);
++ set_preempt_need_resched();
++}
++
++#ifdef CONFIG_SCHED_DEBUG
++static u64 cpu_resched_latency(struct rq *rq)
++{
++ int latency_warn_ms = READ_ONCE(sysctl_resched_latency_warn_ms);
++ u64 resched_latency, now = rq_clock(rq);
++ static bool warned_once;
++
++ if (sysctl_resched_latency_warn_once && warned_once)
++ return 0;
++
++ if (!need_resched() || !latency_warn_ms)
++ return 0;
++
++ if (system_state == SYSTEM_BOOTING)
++ return 0;
++
++ if (!rq->last_seen_need_resched_ns) {
++ rq->last_seen_need_resched_ns = now;
++ rq->ticks_without_resched = 0;
++ return 0;
++ }
++
++ rq->ticks_without_resched++;
++ resched_latency = now - rq->last_seen_need_resched_ns;
++ if (resched_latency <= latency_warn_ms * NSEC_PER_MSEC)
++ return 0;
++
++ warned_once = true;
++
++ return resched_latency;
++}
++
++static int __init setup_resched_latency_warn_ms(char *str)
++{
++ long val;
++
++ if ((kstrtol(str, 0, &val))) {
++ pr_warn("Unable to set resched_latency_warn_ms\n");
++ return 1;
++ }
++
++ sysctl_resched_latency_warn_ms = val;
++ return 1;
++}
++__setup("resched_latency_warn_ms=", setup_resched_latency_warn_ms);
++#else
++static inline u64 cpu_resched_latency(struct rq *rq) { return 0; }
++#endif /* CONFIG_SCHED_DEBUG */
++
++/*
++ * This function gets called by the timer code, with HZ frequency.
++ * We call it with interrupts disabled.
++ */
++void sched_tick(void)
++{
++ int cpu __maybe_unused = smp_processor_id();
++ struct rq *rq = cpu_rq(cpu);
++ struct task_struct *curr = rq->curr;
++ u64 resched_latency;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ arch_scale_freq_tick();
++
++ sched_clock_tick();
++
++ raw_spin_lock(&rq->lock);
++ update_rq_clock(rq);
++
++ scheduler_task_tick(rq);
++ if (sched_feat(LATENCY_WARN))
++ resched_latency = cpu_resched_latency(rq);
++ calc_global_load_tick(rq);
++
++ task_tick_mm_cid(rq, rq->curr);
++
++ raw_spin_unlock(&rq->lock);
++
++ if (sched_feat(LATENCY_WARN) && resched_latency)
++ resched_latency_warn(cpu, resched_latency);
++
++ perf_event_task_tick();
++
++ if (curr->flags & PF_WQ_WORKER)
++ wq_worker_tick(curr);
++}
++
++#ifdef CONFIG_SMP
++
++static int active_balance_cpu_stop(void *data)
++{
++ struct balance_arg *arg = data;
++ struct task_struct *p = arg->task;
++ struct rq *rq = this_rq();
++ unsigned long flags;
++ cpumask_t tmp;
++
++ local_irq_save(flags);
++
++ raw_spin_lock(&p->pi_lock);
++ raw_spin_lock(&rq->lock);
++
++ arg->active = 0;
++
++ if (task_on_rq_queued(p) && task_rq(p) == rq &&
++ cpumask_and(&tmp, p->cpus_ptr, arg->cpumask) &&
++ !is_migration_disabled(p)) {
++ int dcpu = __best_mask_cpu(&tmp, per_cpu(sched_cpu_llc_mask, cpu_of(rq)));
++ rq = move_queued_task(rq, p, dcpu);
++ }
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ return 0;
++}
++
++/* trigger_active_balance - for @cpu/@rq */
++static inline int
++trigger_active_balance(struct rq *src_rq, struct rq *rq, struct balance_arg *arg)
++{
++ unsigned long flags;
++ struct task_struct *p;
++ int res;
++
++ if (!raw_spin_trylock_irqsave(&rq->lock, flags))
++ return 0;
++
++ res = (1 == rq->nr_running) && \
++ !is_migration_disabled((p = sched_rq_first_task(rq))) && \
++ cpumask_intersects(p->cpus_ptr, arg->cpumask) && \
++ !arg->active;
++ if (res) {
++ arg->task = p;
++
++ arg->active = 1;
++ }
++
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ if (res) {
++ preempt_disable();
++ raw_spin_unlock(&src_rq->lock);
++
++ stop_one_cpu_nowait(cpu_of(rq), active_balance_cpu_stop,
++ arg, &rq->active_balance_work);
++
++ preempt_enable();
++ raw_spin_lock(&src_rq->lock);
++ }
++
++ return res;
++}
++
++#ifdef CONFIG_SCHED_SMT
++/*
++ * sg_balance - slibing group balance check for run queue @rq
++ */
++static inline void sg_balance(struct rq *rq)
++{
++ cpumask_t chk;
++
++ if (cpumask_andnot(&chk, cpu_active_mask, sched_idle_mask) &&
++ cpumask_andnot(&chk, &chk, &sched_rq_pending_mask)) {
++ int i, cpu = cpu_of(rq);
++
++ for_each_cpu_wrap(i, &chk, cpu) {
++ if (cpumask_subset(cpu_smt_mask(i), &chk)) {
++ struct rq *target_rq = cpu_rq(i);
++ if (trigger_active_balance(rq, target_rq, &target_rq->sg_balance_arg))
++ return;
++ }
++ }
++ }
++}
++
++static DEFINE_PER_CPU(struct balance_callback, sg_balance_head) = {
++ .func = sg_balance,
++};
++#endif /* CONFIG_SCHED_SMT */
++
++#endif /* CONFIG_SMP */
++
++#ifdef CONFIG_NO_HZ_FULL
++
++struct tick_work {
++ int cpu;
++ atomic_t state;
++ struct delayed_work work;
++};
++/* Values for ->state, see diagram below. */
++#define TICK_SCHED_REMOTE_OFFLINE 0
++#define TICK_SCHED_REMOTE_OFFLINING 1
++#define TICK_SCHED_REMOTE_RUNNING 2
++
++/*
++ * State diagram for ->state:
++ *
++ *
++ * TICK_SCHED_REMOTE_OFFLINE
++ * | ^
++ * | |
++ * | | sched_tick_remote()
++ * | |
++ * | |
++ * +--TICK_SCHED_REMOTE_OFFLINING
++ * | ^
++ * | |
++ * sched_tick_start() | | sched_tick_stop()
++ * | |
++ * V |
++ * TICK_SCHED_REMOTE_RUNNING
++ *
++ *
++ * Other transitions get WARN_ON_ONCE(), except that sched_tick_remote()
++ * and sched_tick_start() are happy to leave the state in RUNNING.
++ */
++
++static struct tick_work __percpu *tick_work_cpu;
++
++static void sched_tick_remote(struct work_struct *work)
++{
++ struct delayed_work *dwork = to_delayed_work(work);
++ struct tick_work *twork = container_of(dwork, struct tick_work, work);
++ int cpu = twork->cpu;
++ struct rq *rq = cpu_rq(cpu);
++ int os;
++
++ /*
++ * Handle the tick only if it appears the remote CPU is running in full
++ * dynticks mode. The check is racy by nature, but missing a tick or
++ * having one too much is no big deal because the scheduler tick updates
++ * statistics and checks timeslices in a time-independent way, regardless
++ * of when exactly it is running.
++ */
++ if (tick_nohz_tick_stopped_cpu(cpu)) {
++ guard(raw_spinlock_irqsave)(&rq->lock);
++ struct task_struct *curr = rq->curr;
++
++ if (cpu_online(cpu)) {
++ update_rq_clock(rq);
++
++ if (!is_idle_task(curr)) {
++ /*
++ * Make sure the next tick runs within a
++ * reasonable amount of time.
++ */
++ u64 delta = rq_clock_task(rq) - curr->last_ran;
++ WARN_ON_ONCE(delta > (u64)NSEC_PER_SEC * 3);
++ }
++ scheduler_task_tick(rq);
++
++ calc_load_nohz_remote(rq);
++ }
++ }
++
++ /*
++ * Run the remote tick once per second (1Hz). This arbitrary
++ * frequency is large enough to avoid overload but short enough
++ * to keep scheduler internal stats reasonably up to date. But
++ * first update state to reflect hotplug activity if required.
++ */
++ os = atomic_fetch_add_unless(&twork->state, -1, TICK_SCHED_REMOTE_RUNNING);
++ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_OFFLINE);
++ if (os == TICK_SCHED_REMOTE_RUNNING)
++ queue_delayed_work(system_unbound_wq, dwork, HZ);
++}
++
++static void sched_tick_start(int cpu)
++{
++ int os;
++ struct tick_work *twork;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ return;
++
++ WARN_ON_ONCE(!tick_work_cpu);
++
++ twork = per_cpu_ptr(tick_work_cpu, cpu);
++ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_RUNNING);
++ WARN_ON_ONCE(os == TICK_SCHED_REMOTE_RUNNING);
++ if (os == TICK_SCHED_REMOTE_OFFLINE) {
++ twork->cpu = cpu;
++ INIT_DELAYED_WORK(&twork->work, sched_tick_remote);
++ queue_delayed_work(system_unbound_wq, &twork->work, HZ);
++ }
++}
++
++#ifdef CONFIG_HOTPLUG_CPU
++static void sched_tick_stop(int cpu)
++{
++ struct tick_work *twork;
++ int os;
++
++ if (housekeeping_cpu(cpu, HK_TYPE_TICK))
++ return;
++
++ WARN_ON_ONCE(!tick_work_cpu);
++
++ twork = per_cpu_ptr(tick_work_cpu, cpu);
++ /* There cannot be competing actions, but don't rely on stop-machine. */
++ os = atomic_xchg(&twork->state, TICK_SCHED_REMOTE_OFFLINING);
++ WARN_ON_ONCE(os != TICK_SCHED_REMOTE_RUNNING);
++ /* Don't cancel, as this would mess up the state machine. */
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
++int __init sched_tick_offload_init(void)
++{
++ tick_work_cpu = alloc_percpu(struct tick_work);
++ BUG_ON(!tick_work_cpu);
++ return 0;
++}
++
++#else /* !CONFIG_NO_HZ_FULL */
++static inline void sched_tick_start(int cpu) { }
++static inline void sched_tick_stop(int cpu) { }
++#endif
++
++#if defined(CONFIG_PREEMPTION) && (defined(CONFIG_DEBUG_PREEMPT) || \
++ defined(CONFIG_PREEMPT_TRACER))
++/*
++ * If the value passed in is equal to the current preempt count
++ * then we just disabled preemption. Start timing the latency.
++ */
++static inline void preempt_latency_start(int val)
++{
++ if (preempt_count() == val) {
++ unsigned long ip = get_lock_parent_ip();
++#ifdef CONFIG_DEBUG_PREEMPT
++ current->preempt_disable_ip = ip;
++#endif
++ trace_preempt_off(CALLER_ADDR0, ip);
++ }
++}
++
++void preempt_count_add(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON((preempt_count() < 0)))
++ return;
++#endif
++ __preempt_count_add(val);
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Spinlock count overflowing soon?
++ */
++ DEBUG_LOCKS_WARN_ON((preempt_count() & PREEMPT_MASK) >=
++ PREEMPT_MASK - 10);
++#endif
++ preempt_latency_start(val);
++}
++EXPORT_SYMBOL(preempt_count_add);
++NOKPROBE_SYMBOL(preempt_count_add);
++
++/*
++ * If the value passed in equals to the current preempt count
++ * then we just enabled preemption. Stop timing the latency.
++ */
++static inline void preempt_latency_stop(int val)
++{
++ if (preempt_count() == val)
++ trace_preempt_on(CALLER_ADDR0, get_lock_parent_ip());
++}
++
++void preempt_count_sub(int val)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ /*
++ * Underflow?
++ */
++ if (DEBUG_LOCKS_WARN_ON(val > preempt_count()))
++ return;
++ /*
++ * Is the spinlock portion underflowing?
++ */
++ if (DEBUG_LOCKS_WARN_ON((val < PREEMPT_MASK) &&
++ !(preempt_count() & PREEMPT_MASK)))
++ return;
++#endif
++
++ preempt_latency_stop(val);
++ __preempt_count_sub(val);
++}
++EXPORT_SYMBOL(preempt_count_sub);
++NOKPROBE_SYMBOL(preempt_count_sub);
++
++#else
++static inline void preempt_latency_start(int val) { }
++static inline void preempt_latency_stop(int val) { }
++#endif
++
++static inline unsigned long get_preempt_disable_ip(struct task_struct *p)
++{
++#ifdef CONFIG_DEBUG_PREEMPT
++ return p->preempt_disable_ip;
++#else
++ return 0;
++#endif
++}
++
++/*
++ * Print scheduling while atomic bug:
++ */
++static noinline void __schedule_bug(struct task_struct *prev)
++{
++ /* Save this before calling printk(), since that will clobber it */
++ unsigned long preempt_disable_ip = get_preempt_disable_ip(current);
++
++ if (oops_in_progress)
++ return;
++
++ printk(KERN_ERR "BUG: scheduling while atomic: %s/%d/0x%08x\n",
++ prev->comm, prev->pid, preempt_count());
++
++ debug_show_held_locks(prev);
++ print_modules();
++ if (irqs_disabled())
++ print_irqtrace_events(prev);
++ if (IS_ENABLED(CONFIG_DEBUG_PREEMPT)) {
++ pr_err("Preemption disabled at:");
++ print_ip_sym(KERN_ERR, preempt_disable_ip);
++ }
++ check_panic_on_warn("scheduling while atomic");
++
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++
++/*
++ * Various schedule()-time debugging checks and statistics:
++ */
++static inline void schedule_debug(struct task_struct *prev, bool preempt)
++{
++#ifdef CONFIG_SCHED_STACK_END_CHECK
++ if (task_stack_end_corrupted(prev))
++ panic("corrupted stack end detected inside scheduler\n");
++
++ if (task_scs_end_corrupted(prev))
++ panic("corrupted shadow stack detected inside scheduler\n");
++#endif
++
++#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
++ if (!preempt && READ_ONCE(prev->__state) && prev->non_block_count) {
++ printk(KERN_ERR "BUG: scheduling in a non-blocking section: %s/%d/%i\n",
++ prev->comm, prev->pid, prev->non_block_count);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++ }
++#endif
++
++ if (unlikely(in_atomic_preempt_off())) {
++ __schedule_bug(prev);
++ preempt_count_set(PREEMPT_DISABLED);
++ }
++ rcu_sleep_check();
++ SCHED_WARN_ON(ct_state() == CONTEXT_USER);
++
++ profile_hit(SCHED_PROFILING, __builtin_return_address(0));
++
++ schedstat_inc(this_rq()->sched_count);
++}
++
++#ifdef ALT_SCHED_DEBUG
++void alt_sched_debug(void)
++{
++ printk(KERN_INFO "sched: pending: 0x%04lx, idle: 0x%04lx, sg_idle: 0x%04lx\n",
++ sched_rq_pending_mask.bits[0],
++ sched_idle_mask->bits[0],
++ sched_sg_idle_mask.bits[0]);
++}
++#else
++inline void alt_sched_debug(void) {}
++#endif
++
++#ifdef CONFIG_SMP
++
++#ifdef CONFIG_PREEMPT_RT
++#define SCHED_NR_MIGRATE_BREAK 8
++#else
++#define SCHED_NR_MIGRATE_BREAK 32
++#endif
++
++const_debug unsigned int sysctl_sched_nr_migrate = SCHED_NR_MIGRATE_BREAK;
++
++/*
++ * Migrate pending tasks in @rq to @dest_cpu
++ */
++static inline int
++migrate_pending_tasks(struct rq *rq, struct rq *dest_rq, const int dest_cpu)
++{
++ struct task_struct *p, *skip = rq->curr;
++ int nr_migrated = 0;
++ int nr_tries = min(rq->nr_running / 2, sysctl_sched_nr_migrate);
++
++ /* WA to check rq->curr is still on rq */
++ if (!task_on_rq_queued(skip))
++ return 0;
++
++ while (skip != rq->idle && nr_tries &&
++ (p = sched_rq_next_task(skip, rq)) != rq->idle) {
++ skip = sched_rq_next_task(p, rq);
++ if (cpumask_test_cpu(dest_cpu, p->cpus_ptr)) {
++ __SCHED_DEQUEUE_TASK(p, rq, 0, );
++ set_task_cpu(p, dest_cpu);
++ sched_task_sanity_check(p, dest_rq);
++ sched_mm_cid_migrate_to(dest_rq, p, cpu_of(rq));
++ __SCHED_ENQUEUE_TASK(p, dest_rq, 0, );
++ nr_migrated++;
++ }
++ nr_tries--;
++ }
++
++ return nr_migrated;
++}
++
++static inline int take_other_rq_tasks(struct rq *rq, int cpu)
++{
++ cpumask_t *topo_mask, *end_mask, chk;
++
++ if (unlikely(!rq->online))
++ return 0;
++
++ if (cpumask_empty(&sched_rq_pending_mask))
++ return 0;
++
++ topo_mask = per_cpu(sched_cpu_topo_masks, cpu);
++ end_mask = per_cpu(sched_cpu_topo_end_mask, cpu);
++ do {
++ int i;
++
++ if (!cpumask_and(&chk, &sched_rq_pending_mask, topo_mask))
++ continue;
++
++ for_each_cpu_wrap(i, &chk, cpu) {
++ int nr_migrated;
++ struct rq *src_rq;
++
++ src_rq = cpu_rq(i);
++ if (!do_raw_spin_trylock(&src_rq->lock))
++ continue;
++ spin_acquire(&src_rq->lock.dep_map,
++ SINGLE_DEPTH_NESTING, 1, _RET_IP_);
++
++ if ((nr_migrated = migrate_pending_tasks(src_rq, rq, cpu))) {
++ src_rq->nr_running -= nr_migrated;
++ if (src_rq->nr_running < 2)
++ cpumask_clear_cpu(i, &sched_rq_pending_mask);
++
++ spin_release(&src_rq->lock.dep_map, _RET_IP_);
++ do_raw_spin_unlock(&src_rq->lock);
++
++ rq->nr_running += nr_migrated;
++ if (rq->nr_running > 1)
++ cpumask_set_cpu(cpu, &sched_rq_pending_mask);
++
++ update_sched_preempt_mask(rq);
++ cpufreq_update_util(rq, 0);
++
++ return 1;
++ }
++
++ spin_release(&src_rq->lock.dep_map, _RET_IP_);
++ do_raw_spin_unlock(&src_rq->lock);
++ }
++ } while (++topo_mask < end_mask);
++
++ return 0;
++}
++#endif
++
++static inline void time_slice_expired(struct task_struct *p, struct rq *rq)
++{
++ p->time_slice = sysctl_sched_base_slice;
++
++ sched_task_renew(p, rq);
++
++ if (SCHED_FIFO != p->policy && task_on_rq_queued(p))
++ requeue_task(p, rq);
++}
++
++/*
++ * Timeslices below RESCHED_NS are considered as good as expired as there's no
++ * point rescheduling when there's so little time left.
++ */
++static inline void check_curr(struct task_struct *p, struct rq *rq)
++{
++ if (unlikely(rq->idle == p))
++ return;
++
++ update_curr(rq, p);
++
++ if (p->time_slice < RESCHED_NS)
++ time_slice_expired(p, rq);
++}
++
++static inline struct task_struct *
++choose_next_task(struct rq *rq, int cpu)
++{
++ struct task_struct *next = sched_rq_first_task(rq);
++
++ if (next == rq->idle) {
++#ifdef CONFIG_SMP
++ if (!take_other_rq_tasks(rq, cpu)) {
++#endif
++
++#ifdef CONFIG_SCHED_SMT
++ if (static_key_count(&sched_smt_present.key) > 1 &&
++ cpumask_test_cpu(cpu, sched_sg_idle_mask) &&
++ rq->online)
++ __queue_balance_callback(rq, &per_cpu(sg_balance_head, cpu));
++#endif
++ schedstat_inc(rq->sched_goidle);
++ /*printk(KERN_INFO "sched: choose_next_task(%d) idle %px\n", cpu, next);*/
++ return next;
++#ifdef CONFIG_SMP
++ }
++ next = sched_rq_first_task(rq);
++#endif
++ }
++#ifdef CONFIG_HIGH_RES_TIMERS
++ hrtick_start(rq, next->time_slice);
++#endif
++ /*printk(KERN_INFO "sched: choose_next_task(%d) next %px\n", cpu, next);*/
++ return next;
++}
++
++/*
++ * Constants for the sched_mode argument of __schedule().
++ *
++ * The mode argument allows RT enabled kernels to differentiate a
++ * preemption from blocking on an 'sleeping' spin/rwlock. Note that
++ * SM_MASK_PREEMPT for !RT has all bits set, which allows the compiler to
++ * optimize the AND operation out and just check for zero.
++ */
++#define SM_NONE 0x0
++#define SM_PREEMPT 0x1
++#define SM_RTLOCK_WAIT 0x2
++
++#ifndef CONFIG_PREEMPT_RT
++# define SM_MASK_PREEMPT (~0U)
++#else
++# define SM_MASK_PREEMPT SM_PREEMPT
++#endif
++
++/*
++ * schedule() is the main scheduler function.
++ *
++ * The main means of driving the scheduler and thus entering this function are:
++ *
++ * 1. Explicit blocking: mutex, semaphore, waitqueue, etc.
++ *
++ * 2. TIF_NEED_RESCHED flag is checked on interrupt and userspace return
++ * paths. For example, see arch/x86/entry_64.S.
++ *
++ * To drive preemption between tasks, the scheduler sets the flag in timer
++ * interrupt handler sched_tick().
++ *
++ * 3. Wakeups don't really cause entry into schedule(). They add a
++ * task to the run-queue and that's it.
++ *
++ * Now, if the new task added to the run-queue preempts the current
++ * task, then the wakeup sets TIF_NEED_RESCHED and schedule() gets
++ * called on the nearest possible occasion:
++ *
++ * - If the kernel is preemptible (CONFIG_PREEMPTION=y):
++ *
++ * - in syscall or exception context, at the next outmost
++ * preempt_enable(). (this might be as soon as the wake_up()'s
++ * spin_unlock()!)
++ *
++ * - in IRQ context, return from interrupt-handler to
++ * preemptible context
++ *
++ * - If the kernel is not preemptible (CONFIG_PREEMPTION is not set)
++ * then at the next:
++ *
++ * - cond_resched() call
++ * - explicit schedule() call
++ * - return from syscall or exception to user-space
++ * - return from interrupt-handler to user-space
++ *
++ * WARNING: must be called with preemption disabled!
++ */
++static void __sched notrace __schedule(unsigned int sched_mode)
++{
++ struct task_struct *prev, *next;
++ unsigned long *switch_count;
++ unsigned long prev_state;
++ struct rq *rq;
++ int cpu;
++
++ cpu = smp_processor_id();
++ rq = cpu_rq(cpu);
++ prev = rq->curr;
++
++ schedule_debug(prev, !!sched_mode);
++
++ /* by passing sched_feat(HRTICK) checking which Alt schedule FW doesn't support */
++ hrtick_clear(rq);
++
++ local_irq_disable();
++ rcu_note_context_switch(!!sched_mode);
++
++ /*
++ * Make sure that signal_pending_state()->signal_pending() below
++ * can't be reordered with __set_current_state(TASK_INTERRUPTIBLE)
++ * done by the caller to avoid the race with signal_wake_up():
++ *
++ * __set_current_state(@state) signal_wake_up()
++ * schedule() set_tsk_thread_flag(p, TIF_SIGPENDING)
++ * wake_up_state(p, state)
++ * LOCK rq->lock LOCK p->pi_state
++ * smp_mb__after_spinlock() smp_mb__after_spinlock()
++ * if (signal_pending_state()) if (p->state & @state)
++ *
++ * Also, the membarrier system call requires a full memory barrier
++ * after coming from user-space, before storing to rq->curr; this
++ * barrier matches a full barrier in the proximity of the membarrier
++ * system call exit.
++ */
++ raw_spin_lock(&rq->lock);
++ smp_mb__after_spinlock();
++
++ update_rq_clock(rq);
++
++ switch_count = &prev->nivcsw;
++ /*
++ * We must load prev->state once (task_struct::state is volatile), such
++ * that we form a control dependency vs deactivate_task() below.
++ */
++ prev_state = READ_ONCE(prev->__state);
++ if (!(sched_mode & SM_MASK_PREEMPT) && prev_state) {
++ if (signal_pending_state(prev_state, prev)) {
++ WRITE_ONCE(prev->__state, TASK_RUNNING);
++ } else {
++ prev->sched_contributes_to_load =
++ (prev_state & TASK_UNINTERRUPTIBLE) &&
++ !(prev_state & TASK_NOLOAD) &&
++ !(prev_state & TASK_FROZEN);
++
++ if (prev->sched_contributes_to_load)
++ rq->nr_uninterruptible++;
++
++ /*
++ * __schedule() ttwu()
++ * prev_state = prev->state; if (p->on_rq && ...)
++ * if (prev_state) goto out;
++ * p->on_rq = 0; smp_acquire__after_ctrl_dep();
++ * p->state = TASK_WAKING
++ *
++ * Where __schedule() and ttwu() have matching control dependencies.
++ *
++ * After this, schedule() must not care about p->state any more.
++ */
++ sched_task_deactivate(prev, rq);
++ deactivate_task(prev, rq);
++
++ if (prev->in_iowait) {
++ atomic_inc(&rq->nr_iowait);
++ delayacct_blkio_start();
++ }
++ }
++ switch_count = &prev->nvcsw;
++ }
++
++ check_curr(prev, rq);
++
++ next = choose_next_task(rq, cpu);
++ clear_tsk_need_resched(prev);
++ clear_preempt_need_resched();
++#ifdef CONFIG_SCHED_DEBUG
++ rq->last_seen_need_resched_ns = 0;
++#endif
++
++ if (likely(prev != next)) {
++ next->last_ran = rq->clock_task;
++
++ /*printk(KERN_INFO "sched: %px -> %px\n", prev, next);*/
++ rq->nr_switches++;
++ /*
++ * RCU users of rcu_dereference(rq->curr) may not see
++ * changes to task_struct made by pick_next_task().
++ */
++ RCU_INIT_POINTER(rq->curr, next);
++ /*
++ * The membarrier system call requires each architecture
++ * to have a full memory barrier after updating
++ * rq->curr, before returning to user-space.
++ *
++ * Here are the schemes providing that barrier on the
++ * various architectures:
++ * - mm ? switch_mm() : mmdrop() for x86, s390, sparc, PowerPC,
++ * RISC-V. switch_mm() relies on membarrier_arch_switch_mm()
++ * on PowerPC and on RISC-V.
++ * - finish_lock_switch() for weakly-ordered
++ * architectures where spin_unlock is a full barrier,
++ * - switch_to() for arm64 (weakly-ordered, spin_unlock
++ * is a RELEASE barrier),
++ *
++ * The barrier matches a full barrier in the proximity of
++ * the membarrier system call entry.
++ *
++ * On RISC-V, this barrier pairing is also needed for the
++ * SYNC_CORE command when switching between processes, cf.
++ * the inline comments in membarrier_arch_switch_mm().
++ */
++ ++*switch_count;
++
++ trace_sched_switch(sched_mode & SM_MASK_PREEMPT, prev, next, prev_state);
++
++ /* Also unlocks the rq: */
++ rq = context_switch(rq, prev, next);
++
++ cpu = cpu_of(rq);
++ } else {
++ __balance_callbacks(rq);
++ raw_spin_unlock_irq(&rq->lock);
++ }
++}
++
++void __noreturn do_task_dead(void)
++{
++ /* Causes final put_task_struct in finish_task_switch(): */
++ set_special_state(TASK_DEAD);
++
++ /* Tell freezer to ignore us: */
++ current->flags |= PF_NOFREEZE;
++
++ __schedule(SM_NONE);
++ BUG();
++
++ /* Avoid "noreturn function does return" - but don't continue if BUG() is a NOP: */
++ for (;;)
++ cpu_relax();
++}
++
++static inline void sched_submit_work(struct task_struct *tsk)
++{
++ static DEFINE_WAIT_OVERRIDE_MAP(sched_map, LD_WAIT_CONFIG);
++ unsigned int task_flags;
++
++ /*
++ * Establish LD_WAIT_CONFIG context to ensure none of the code called
++ * will use a blocking primitive -- which would lead to recursion.
++ */
++ lock_map_acquire_try(&sched_map);
++
++ task_flags = tsk->flags;
++ /*
++ * If a worker goes to sleep, notify and ask workqueue whether it
++ * wants to wake up a task to maintain concurrency.
++ */
++ if (task_flags & PF_WQ_WORKER)
++ wq_worker_sleeping(tsk);
++ else if (task_flags & PF_IO_WORKER)
++ io_wq_worker_sleeping(tsk);
++
++ /*
++ * spinlock and rwlock must not flush block requests. This will
++ * deadlock if the callback attempts to acquire a lock which is
++ * already acquired.
++ */
++ SCHED_WARN_ON(current->__state & TASK_RTLOCK_WAIT);
++
++ /*
++ * If we are going to sleep and we have plugged IO queued,
++ * make sure to submit it to avoid deadlocks.
++ */
++ blk_flush_plug(tsk->plug, true);
++
++ lock_map_release(&sched_map);
++}
++
++static void sched_update_worker(struct task_struct *tsk)
++{
++ if (tsk->flags & (PF_WQ_WORKER | PF_IO_WORKER | PF_BLOCK_TS)) {
++ if (tsk->flags & PF_BLOCK_TS)
++ blk_plug_invalidate_ts(tsk);
++ if (tsk->flags & PF_WQ_WORKER)
++ wq_worker_running(tsk);
++ else if (tsk->flags & PF_IO_WORKER)
++ io_wq_worker_running(tsk);
++ }
++}
++
++static __always_inline void __schedule_loop(unsigned int sched_mode)
++{
++ do {
++ preempt_disable();
++ __schedule(sched_mode);
++ sched_preempt_enable_no_resched();
++ } while (need_resched());
++}
++
++asmlinkage __visible void __sched schedule(void)
++{
++ struct task_struct *tsk = current;
++
++#ifdef CONFIG_RT_MUTEXES
++ lockdep_assert(!tsk->sched_rt_mutex);
++#endif
++
++ if (!task_is_running(tsk))
++ sched_submit_work(tsk);
++ __schedule_loop(SM_NONE);
++ sched_update_worker(tsk);
++}
++EXPORT_SYMBOL(schedule);
++
++/*
++ * synchronize_rcu_tasks() makes sure that no task is stuck in preempted
++ * state (have scheduled out non-voluntarily) by making sure that all
++ * tasks have either left the run queue or have gone into user space.
++ * As idle tasks do not do either, they must not ever be preempted
++ * (schedule out non-voluntarily).
++ *
++ * schedule_idle() is similar to schedule_preempt_disable() except that it
++ * never enables preemption because it does not call sched_submit_work().
++ */
++void __sched schedule_idle(void)
++{
++ /*
++ * As this skips calling sched_submit_work(), which the idle task does
++ * regardless because that function is a nop when the task is in a
++ * TASK_RUNNING state, make sure this isn't used someplace that the
++ * current task can be in any other state. Note, idle is always in the
++ * TASK_RUNNING state.
++ */
++ WARN_ON_ONCE(current->__state);
++ do {
++ __schedule(SM_NONE);
++ } while (need_resched());
++}
++
++#if defined(CONFIG_CONTEXT_TRACKING_USER) && !defined(CONFIG_HAVE_CONTEXT_TRACKING_USER_OFFSTACK)
++asmlinkage __visible void __sched schedule_user(void)
++{
++ /*
++ * If we come here after a random call to set_need_resched(),
++ * or we have been woken up remotely but the IPI has not yet arrived,
++ * we haven't yet exited the RCU idle mode. Do it here manually until
++ * we find a better solution.
++ *
++ * NB: There are buggy callers of this function. Ideally we
++ * should warn if prev_state != CONTEXT_USER, but that will trigger
++ * too frequently to make sense yet.
++ */
++ enum ctx_state prev_state = exception_enter();
++ schedule();
++ exception_exit(prev_state);
++}
++#endif
++
++/**
++ * schedule_preempt_disabled - called with preemption disabled
++ *
++ * Returns with preemption disabled. Note: preempt_count must be 1
++ */
++void __sched schedule_preempt_disabled(void)
++{
++ sched_preempt_enable_no_resched();
++ schedule();
++ preempt_disable();
++}
++
++#ifdef CONFIG_PREEMPT_RT
++void __sched notrace schedule_rtlock(void)
++{
++ __schedule_loop(SM_RTLOCK_WAIT);
++}
++NOKPROBE_SYMBOL(schedule_rtlock);
++#endif
++
++static void __sched notrace preempt_schedule_common(void)
++{
++ do {
++ /*
++ * Because the function tracer can trace preempt_count_sub()
++ * and it also uses preempt_enable/disable_notrace(), if
++ * NEED_RESCHED is set, the preempt_enable_notrace() called
++ * by the function tracer will call this function again and
++ * cause infinite recursion.
++ *
++ * Preemption must be disabled here before the function
++ * tracer can trace. Break up preempt_disable() into two
++ * calls. One to disable preemption without fear of being
++ * traced. The other to still record the preemption latency,
++ * which can also be traced by the function tracer.
++ */
++ preempt_disable_notrace();
++ preempt_latency_start(1);
++ __schedule(SM_PREEMPT);
++ preempt_latency_stop(1);
++ preempt_enable_no_resched_notrace();
++
++ /*
++ * Check again in case we missed a preemption opportunity
++ * between schedule and now.
++ */
++ } while (need_resched());
++}
++
++#ifdef CONFIG_PREEMPTION
++/*
++ * This is the entry point to schedule() from in-kernel preemption
++ * off of preempt_enable.
++ */
++asmlinkage __visible void __sched notrace preempt_schedule(void)
++{
++ /*
++ * If there is a non-zero preempt_count or interrupts are disabled,
++ * we do not want to preempt the current task. Just return..
++ */
++ if (likely(!preemptible()))
++ return;
++
++ preempt_schedule_common();
++}
++NOKPROBE_SYMBOL(preempt_schedule);
++EXPORT_SYMBOL(preempt_schedule);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#ifndef preempt_schedule_dynamic_enabled
++#define preempt_schedule_dynamic_enabled preempt_schedule
++#define preempt_schedule_dynamic_disabled NULL
++#endif
++DEFINE_STATIC_CALL(preempt_schedule, preempt_schedule_dynamic_enabled);
++EXPORT_STATIC_CALL_TRAMP(preempt_schedule);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule);
++void __sched notrace dynamic_preempt_schedule(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule))
++ return;
++ preempt_schedule();
++}
++NOKPROBE_SYMBOL(dynamic_preempt_schedule);
++EXPORT_SYMBOL(dynamic_preempt_schedule);
++#endif
++#endif
++
++/**
++ * preempt_schedule_notrace - preempt_schedule called by tracing
++ *
++ * The tracing infrastructure uses preempt_enable_notrace to prevent
++ * recursion and tracing preempt enabling caused by the tracing
++ * infrastructure itself. But as tracing can happen in areas coming
++ * from userspace or just about to enter userspace, a preempt enable
++ * can occur before user_exit() is called. This will cause the scheduler
++ * to be called when the system is still in usermode.
++ *
++ * To prevent this, the preempt_enable_notrace will use this function
++ * instead of preempt_schedule() to exit user context if needed before
++ * calling the scheduler.
++ */
++asmlinkage __visible void __sched notrace preempt_schedule_notrace(void)
++{
++ enum ctx_state prev_ctx;
++
++ if (likely(!preemptible()))
++ return;
++
++ do {
++ /*
++ * Because the function tracer can trace preempt_count_sub()
++ * and it also uses preempt_enable/disable_notrace(), if
++ * NEED_RESCHED is set, the preempt_enable_notrace() called
++ * by the function tracer will call this function again and
++ * cause infinite recursion.
++ *
++ * Preemption must be disabled here before the function
++ * tracer can trace. Break up preempt_disable() into two
++ * calls. One to disable preemption without fear of being
++ * traced. The other to still record the preemption latency,
++ * which can also be traced by the function tracer.
++ */
++ preempt_disable_notrace();
++ preempt_latency_start(1);
++ /*
++ * Needs preempt disabled in case user_exit() is traced
++ * and the tracer calls preempt_enable_notrace() causing
++ * an infinite recursion.
++ */
++ prev_ctx = exception_enter();
++ __schedule(SM_PREEMPT);
++ exception_exit(prev_ctx);
++
++ preempt_latency_stop(1);
++ preempt_enable_no_resched_notrace();
++ } while (need_resched());
++}
++EXPORT_SYMBOL_GPL(preempt_schedule_notrace);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#ifndef preempt_schedule_notrace_dynamic_enabled
++#define preempt_schedule_notrace_dynamic_enabled preempt_schedule_notrace
++#define preempt_schedule_notrace_dynamic_disabled NULL
++#endif
++DEFINE_STATIC_CALL(preempt_schedule_notrace, preempt_schedule_notrace_dynamic_enabled);
++EXPORT_STATIC_CALL_TRAMP(preempt_schedule_notrace);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_TRUE(sk_dynamic_preempt_schedule_notrace);
++void __sched notrace dynamic_preempt_schedule_notrace(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_preempt_schedule_notrace))
++ return;
++ preempt_schedule_notrace();
++}
++NOKPROBE_SYMBOL(dynamic_preempt_schedule_notrace);
++EXPORT_SYMBOL(dynamic_preempt_schedule_notrace);
++#endif
++#endif
++
++#endif /* CONFIG_PREEMPTION */
++
++/*
++ * This is the entry point to schedule() from kernel preemption
++ * off of irq context.
++ * Note, that this is called and return with irqs disabled. This will
++ * protect us against recursive calling from irq.
++ */
++asmlinkage __visible void __sched preempt_schedule_irq(void)
++{
++ enum ctx_state prev_state;
++
++ /* Catch callers which need to be fixed */
++ BUG_ON(preempt_count() || !irqs_disabled());
++
++ prev_state = exception_enter();
++
++ do {
++ preempt_disable();
++ local_irq_enable();
++ __schedule(SM_PREEMPT);
++ local_irq_disable();
++ sched_preempt_enable_no_resched();
++ } while (need_resched());
++
++ exception_exit(prev_state);
++}
++
++int default_wake_function(wait_queue_entry_t *curr, unsigned mode, int wake_flags,
++ void *key)
++{
++ WARN_ON_ONCE(IS_ENABLED(CONFIG_SCHED_DEBUG) && wake_flags & ~(WF_SYNC|WF_CURRENT_CPU));
++ return try_to_wake_up(curr->private, mode, wake_flags);
++}
++EXPORT_SYMBOL(default_wake_function);
++
++static inline void check_task_changed(struct task_struct *p, struct rq *rq)
++{
++ /* Trigger resched if task sched_prio has been modified. */
++ if (task_on_rq_queued(p)) {
++ update_rq_clock(rq);
++ requeue_task(p, rq);
++ wakeup_preempt(rq);
++ }
++}
++
++static void __setscheduler_prio(struct task_struct *p, int prio)
++{
++ p->prio = prio;
++}
++
++#ifdef CONFIG_RT_MUTEXES
++
++/*
++ * Would be more useful with typeof()/auto_type but they don't mix with
++ * bit-fields. Since it's a local thing, use int. Keep the generic sounding
++ * name such that if someone were to implement this function we get to compare
++ * notes.
++ */
++#define fetch_and_set(x, v) ({ int _x = (x); (x) = (v); _x; })
++
++void rt_mutex_pre_schedule(void)
++{
++ lockdep_assert(!fetch_and_set(current->sched_rt_mutex, 1));
++ sched_submit_work(current);
++}
++
++void rt_mutex_schedule(void)
++{
++ lockdep_assert(current->sched_rt_mutex);
++ __schedule_loop(SM_NONE);
++}
++
++void rt_mutex_post_schedule(void)
++{
++ sched_update_worker(current);
++ lockdep_assert(fetch_and_set(current->sched_rt_mutex, 0));
++}
++
++static inline int __rt_effective_prio(struct task_struct *pi_task, int prio)
++{
++ if (pi_task)
++ prio = min(prio, pi_task->prio);
++
++ return prio;
++}
++
++static inline int rt_effective_prio(struct task_struct *p, int prio)
++{
++ struct task_struct *pi_task = rt_mutex_get_top_task(p);
++
++ return __rt_effective_prio(pi_task, prio);
++}
++
++/*
++ * rt_mutex_setprio - set the current priority of a task
++ * @p: task to boost
++ * @pi_task: donor task
++ *
++ * This function changes the 'effective' priority of a task. It does
++ * not touch ->normal_prio like __setscheduler().
++ *
++ * Used by the rt_mutex code to implement priority inheritance
++ * logic. Call site only calls if the priority of the task changed.
++ */
++void rt_mutex_setprio(struct task_struct *p, struct task_struct *pi_task)
++{
++ int prio;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ /* XXX used to be waiter->prio, not waiter->task->prio */
++ prio = __rt_effective_prio(pi_task, p->normal_prio);
++
++ /*
++ * If nothing changed; bail early.
++ */
++ if (p->pi_top_task == pi_task && prio == p->prio)
++ return;
++
++ rq = __task_access_lock(p, &lock);
++ /*
++ * Set under pi_lock && rq->lock, such that the value can be used under
++ * either lock.
++ *
++ * Note that there is loads of tricky to make this pointer cache work
++ * right. rt_mutex_slowunlock()+rt_mutex_postunlock() work together to
++ * ensure a task is de-boosted (pi_task is set to NULL) before the
++ * task is allowed to run again (and can exit). This ensures the pointer
++ * points to a blocked task -- which guarantees the task is present.
++ */
++ p->pi_top_task = pi_task;
++
++ /*
++ * For FIFO/RR we only need to set prio, if that matches we're done.
++ */
++ if (prio == p->prio)
++ goto out_unlock;
++
++ /*
++ * Idle task boosting is a nono in general. There is one
++ * exception, when PREEMPT_RT and NOHZ is active:
++ *
++ * The idle task calls get_next_timer_interrupt() and holds
++ * the timer wheel base->lock on the CPU and another CPU wants
++ * to access the timer (probably to cancel it). We can safely
++ * ignore the boosting request, as the idle CPU runs this code
++ * with interrupts disabled and will complete the lock
++ * protected section without being interrupted. So there is no
++ * real need to boost.
++ */
++ if (unlikely(p == rq->idle)) {
++ WARN_ON(p != rq->curr);
++ WARN_ON(p->pi_blocked_on);
++ goto out_unlock;
++ }
++
++ trace_sched_pi_setprio(p, pi_task);
++
++ __setscheduler_prio(p, prio);
++
++ check_task_changed(p, rq);
++out_unlock:
++ /* Avoid rq from going away on us: */
++ preempt_disable();
++
++ if (task_on_rq_queued(p))
++ __balance_callbacks(rq);
++ __task_access_unlock(p, lock);
++
++ preempt_enable();
++}
++#else
++static inline int rt_effective_prio(struct task_struct *p, int prio)
++{
++ return prio;
++}
++#endif
++
++void set_user_nice(struct task_struct *p, long nice)
++{
++ unsigned long flags;
++ struct rq *rq;
++ raw_spinlock_t *lock;
++
++ if (task_nice(p) == nice || nice < MIN_NICE || nice > MAX_NICE)
++ return;
++ /*
++ * We have to be careful, if called from sys_setpriority(),
++ * the task might be in the middle of scheduling on another CPU.
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++ rq = __task_access_lock(p, &lock);
++
++ p->static_prio = NICE_TO_PRIO(nice);
++ /*
++ * The RT priorities are set via sched_setscheduler(), but we still
++ * allow the 'normal' nice value to be set - but as expected
++ * it won't have any effect on scheduling until the task is
++ * not SCHED_NORMAL/SCHED_BATCH:
++ */
++ if (task_has_rt_policy(p))
++ goto out_unlock;
++
++ p->prio = effective_prio(p);
++
++ check_task_changed(p, rq);
++out_unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++}
++EXPORT_SYMBOL(set_user_nice);
++
++/*
++ * is_nice_reduction - check if nice value is an actual reduction
++ *
++ * Similar to can_nice() but does not perform a capability check.
++ *
++ * @p: task
++ * @nice: nice value
++ */
++static bool is_nice_reduction(const struct task_struct *p, const int nice)
++{
++ /* Convert nice value [19,-20] to rlimit style value [1,40]: */
++ int nice_rlim = nice_to_rlimit(nice);
++
++ return (nice_rlim <= task_rlimit(p, RLIMIT_NICE));
++}
++
++/*
++ * can_nice - check if a task can reduce its nice value
++ * @p: task
++ * @nice: nice value
++ */
++int can_nice(const struct task_struct *p, const int nice)
++{
++ return is_nice_reduction(p, nice) || capable(CAP_SYS_NICE);
++}
++
++#ifdef __ARCH_WANT_SYS_NICE
++
++/*
++ * sys_nice - change the priority of the current process.
++ * @increment: priority increment
++ *
++ * sys_setpriority is a more generic, but much slower function that
++ * does similar things.
++ */
++SYSCALL_DEFINE1(nice, int, increment)
++{
++ long nice, retval;
++
++ /*
++ * Setpriority might change our priority at the same moment.
++ * We don't have to worry. Conceptually one call occurs first
++ * and we have a single winner.
++ */
++
++ increment = clamp(increment, -NICE_WIDTH, NICE_WIDTH);
++ nice = task_nice(current) + increment;
++
++ nice = clamp_val(nice, MIN_NICE, MAX_NICE);
++ if (increment < 0 && !can_nice(current, nice))
++ return -EPERM;
++
++ retval = security_task_setnice(current, nice);
++ if (retval)
++ return retval;
++
++ set_user_nice(current, nice);
++ return 0;
++}
++
++#endif
++
++/**
++ * task_prio - return the priority value of a given task.
++ * @p: the task in question.
++ *
++ * Return: The priority value as seen by users in /proc.
++ *
++ * sched policy return value kernel prio user prio/nice
++ *
++ * (BMQ)normal, batch, idle[0 ... 53] [100 ... 139] 0/[-20 ... 19]/[-7 ... 7]
++ * (PDS)normal, batch, idle[0 ... 39] 100 0/[-20 ... 19]
++ * fifo, rr [-1 ... -100] [99 ... 0] [0 ... 99]
++ */
++int task_prio(const struct task_struct *p)
++{
++ return (p->prio < MAX_RT_PRIO) ? p->prio - MAX_RT_PRIO :
++ task_sched_prio_normal(p, task_rq(p));
++}
++
++/**
++ * idle_cpu - is a given CPU idle currently?
++ * @cpu: the processor in question.
++ *
++ * Return: 1 if the CPU is currently idle. 0 otherwise.
++ */
++int idle_cpu(int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ if (rq->curr != rq->idle)
++ return 0;
++
++ if (rq->nr_running)
++ return 0;
++
++#ifdef CONFIG_SMP
++ if (rq->ttwu_pending)
++ return 0;
++#endif
++
++ return 1;
++}
++
++/**
++ * idle_task - return the idle task for a given CPU.
++ * @cpu: the processor in question.
++ *
++ * Return: The idle task for the cpu @cpu.
++ */
++struct task_struct *idle_task(int cpu)
++{
++ return cpu_rq(cpu)->idle;
++}
++
++/**
++ * find_process_by_pid - find a process with a matching PID value.
++ * @pid: the pid in question.
++ *
++ * The task of @pid, if found. %NULL otherwise.
++ */
++static inline struct task_struct *find_process_by_pid(pid_t pid)
++{
++ return pid ? find_task_by_vpid(pid) : current;
++}
++
++static struct task_struct *find_get_task(pid_t pid)
++{
++ struct task_struct *p;
++ guard(rcu)();
++
++ p = find_process_by_pid(pid);
++ if (likely(p))
++ get_task_struct(p);
++
++ return p;
++}
++
++DEFINE_CLASS(find_get_task, struct task_struct *, if (_T) put_task_struct(_T),
++ find_get_task(pid), pid_t pid)
++
++/*
++ * sched_setparam() passes in -1 for its policy, to let the functions
++ * it calls know not to change it.
++ */
++#define SETPARAM_POLICY -1
++
++static void __setscheduler_params(struct task_struct *p,
++ const struct sched_attr *attr)
++{
++ int policy = attr->sched_policy;
++
++ if (policy == SETPARAM_POLICY)
++ policy = p->policy;
++
++ p->policy = policy;
++
++ /*
++ * allow normal nice value to be set, but will not have any
++ * effect on scheduling until the task not SCHED_NORMAL/
++ * SCHED_BATCH
++ */
++ p->static_prio = NICE_TO_PRIO(attr->sched_nice);
++
++ /*
++ * __sched_setscheduler() ensures attr->sched_priority == 0 when
++ * !rt_policy. Always setting this ensures that things like
++ * getparam()/getattr() don't report silly values for !rt tasks.
++ */
++ p->rt_priority = attr->sched_priority;
++ p->normal_prio = normal_prio(p);
++}
++
++/*
++ * check the target process has a UID that matches the current process's
++ */
++static bool check_same_owner(struct task_struct *p)
++{
++ const struct cred *cred = current_cred(), *pcred;
++ guard(rcu)();
++
++ pcred = __task_cred(p);
++ return (uid_eq(cred->euid, pcred->euid) ||
++ uid_eq(cred->euid, pcred->uid));
++}
++
++/*
++ * Allow unprivileged RT tasks to decrease priority.
++ * Only issue a capable test if needed and only once to avoid an audit
++ * event on permitted non-privileged operations:
++ */
++static int user_check_sched_setscheduler(struct task_struct *p,
++ const struct sched_attr *attr,
++ int policy, int reset_on_fork)
++{
++ if (rt_policy(policy)) {
++ unsigned long rlim_rtprio = task_rlimit(p, RLIMIT_RTPRIO);
++
++ /* Can't set/change the rt policy: */
++ if (policy != p->policy && !rlim_rtprio)
++ goto req_priv;
++
++ /* Can't increase priority: */
++ if (attr->sched_priority > p->rt_priority &&
++ attr->sched_priority > rlim_rtprio)
++ goto req_priv;
++ }
++
++ /* Can't change other user's priorities: */
++ if (!check_same_owner(p))
++ goto req_priv;
++
++ /* Normal users shall not reset the sched_reset_on_fork flag: */
++ if (p->sched_reset_on_fork && !reset_on_fork)
++ goto req_priv;
++
++ return 0;
++
++req_priv:
++ if (!capable(CAP_SYS_NICE))
++ return -EPERM;
++
++ return 0;
++}
++
++static int __sched_setscheduler(struct task_struct *p,
++ const struct sched_attr *attr,
++ bool user, bool pi)
++{
++ const struct sched_attr dl_squash_attr = {
++ .size = sizeof(struct sched_attr),
++ .sched_policy = SCHED_FIFO,
++ .sched_nice = 0,
++ .sched_priority = 99,
++ };
++ int oldpolicy = -1, policy = attr->sched_policy;
++ int retval, newprio;
++ struct balance_callback *head;
++ unsigned long flags;
++ struct rq *rq;
++ int reset_on_fork;
++ raw_spinlock_t *lock;
++
++ /* The pi code expects interrupts enabled */
++ BUG_ON(pi && in_interrupt());
++
++ /*
++ * Alt schedule FW supports SCHED_DEADLINE by squash it as prio 0 SCHED_FIFO
++ */
++ if (unlikely(SCHED_DEADLINE == policy)) {
++ attr = &dl_squash_attr;
++ policy = attr->sched_policy;
++ }
++recheck:
++ /* Double check policy once rq lock held */
++ if (policy < 0) {
++ reset_on_fork = p->sched_reset_on_fork;
++ policy = oldpolicy = p->policy;
++ } else {
++ reset_on_fork = !!(attr->sched_flags & SCHED_RESET_ON_FORK);
++
++ if (policy > SCHED_IDLE)
++ return -EINVAL;
++ }
++
++ if (attr->sched_flags & ~(SCHED_FLAG_ALL))
++ return -EINVAL;
++
++ /*
++ * Valid priorities for SCHED_FIFO and SCHED_RR are
++ * 1..MAX_RT_PRIO-1, valid priority for SCHED_NORMAL and
++ * SCHED_BATCH and SCHED_IDLE is 0.
++ */
++ if (attr->sched_priority < 0 ||
++ (p->mm && attr->sched_priority > MAX_RT_PRIO - 1) ||
++ (!p->mm && attr->sched_priority > MAX_RT_PRIO - 1))
++ return -EINVAL;
++ if ((SCHED_RR == policy || SCHED_FIFO == policy) !=
++ (attr->sched_priority != 0))
++ return -EINVAL;
++
++ if (user) {
++ retval = user_check_sched_setscheduler(p, attr, policy, reset_on_fork);
++ if (retval)
++ return retval;
++
++ retval = security_task_setscheduler(p);
++ if (retval)
++ return retval;
++ }
++
++ /*
++ * Make sure no PI-waiters arrive (or leave) while we are
++ * changing the priority of the task:
++ */
++ raw_spin_lock_irqsave(&p->pi_lock, flags);
++
++ /*
++ * To be able to change p->policy safely, task_access_lock()
++ * must be called.
++ * IF use task_access_lock() here:
++ * For the task p which is not running, reading rq->stop is
++ * racy but acceptable as ->stop doesn't change much.
++ * An enhancemnet can be made to read rq->stop saftly.
++ */
++ rq = __task_access_lock(p, &lock);
++
++ /*
++ * Changing the policy of the stop threads its a very bad idea
++ */
++ if (p == rq->stop) {
++ retval = -EINVAL;
++ goto unlock;
++ }
++
++ /*
++ * If not changing anything there's no need to proceed further:
++ */
++ if (unlikely(policy == p->policy)) {
++ if (rt_policy(policy) && attr->sched_priority != p->rt_priority)
++ goto change;
++ if (!rt_policy(policy) &&
++ NICE_TO_PRIO(attr->sched_nice) != p->static_prio)
++ goto change;
++
++ p->sched_reset_on_fork = reset_on_fork;
++ retval = 0;
++ goto unlock;
++ }
++change:
++
++ /* Re-check policy now with rq lock held */
++ if (unlikely(oldpolicy != -1 && oldpolicy != p->policy)) {
++ policy = oldpolicy = -1;
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ goto recheck;
++ }
++
++ p->sched_reset_on_fork = reset_on_fork;
++
++ newprio = __normal_prio(policy, attr->sched_priority, NICE_TO_PRIO(attr->sched_nice));
++ if (pi) {
++ /*
++ * Take priority boosted tasks into account. If the new
++ * effective priority is unchanged, we just store the new
++ * normal parameters and do not touch the scheduler class and
++ * the runqueue. This will be done when the task deboost
++ * itself.
++ */
++ newprio = rt_effective_prio(p, newprio);
++ }
++
++ if (!(attr->sched_flags & SCHED_FLAG_KEEP_PARAMS)) {
++ __setscheduler_params(p, attr);
++ __setscheduler_prio(p, newprio);
++ }
++
++ check_task_changed(p, rq);
++
++ /* Avoid rq from going away on us: */
++ preempt_disable();
++ head = splice_balance_callbacks(rq);
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++
++ if (pi)
++ rt_mutex_adjust_pi(p);
++
++ /* Run balance callbacks after we've adjusted the PI chain: */
++ balance_callbacks(rq, head);
++ preempt_enable();
++
++ return 0;
++
++unlock:
++ __task_access_unlock(p, lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, flags);
++ return retval;
++}
++
++static int _sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param, bool check)
++{
++ struct sched_attr attr = {
++ .sched_policy = policy,
++ .sched_priority = param->sched_priority,
++ .sched_nice = PRIO_TO_NICE(p->static_prio),
++ };
++
++ /* Fixup the legacy SCHED_RESET_ON_FORK hack. */
++ if ((policy != SETPARAM_POLICY) && (policy & SCHED_RESET_ON_FORK)) {
++ attr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
++ policy &= ~SCHED_RESET_ON_FORK;
++ attr.sched_policy = policy;
++ }
++
++ return __sched_setscheduler(p, &attr, check, true);
++}
++
++/**
++ * sched_setscheduler - change the scheduling policy and/or RT priority of a thread.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * Use sched_set_fifo(), read its comment.
++ *
++ * Return: 0 on success. An error code otherwise.
++ *
++ * NOTE that the task may be already dead.
++ */
++int sched_setscheduler(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return _sched_setscheduler(p, policy, param, true);
++}
++
++int sched_setattr(struct task_struct *p, const struct sched_attr *attr)
++{
++ return __sched_setscheduler(p, attr, true, true);
++}
++
++int sched_setattr_nocheck(struct task_struct *p, const struct sched_attr *attr)
++{
++ return __sched_setscheduler(p, attr, false, true);
++}
++EXPORT_SYMBOL_GPL(sched_setattr_nocheck);
++
++/**
++ * sched_setscheduler_nocheck - change the scheduling policy and/or RT priority of a thread from kernelspace.
++ * @p: the task in question.
++ * @policy: new policy.
++ * @param: structure containing the new RT priority.
++ *
++ * Just like sched_setscheduler, only don't bother checking if the
++ * current context has permission. For example, this is needed in
++ * stop_machine(): we create temporary high priority worker threads,
++ * but our caller might not have that capability.
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++int sched_setscheduler_nocheck(struct task_struct *p, int policy,
++ const struct sched_param *param)
++{
++ return _sched_setscheduler(p, policy, param, false);
++}
++
++/*
++ * SCHED_FIFO is a broken scheduler model; that is, it is fundamentally
++ * incapable of resource management, which is the one thing an OS really should
++ * be doing.
++ *
++ * This is of course the reason it is limited to privileged users only.
++ *
++ * Worse still; it is fundamentally impossible to compose static priority
++ * workloads. You cannot take two correctly working static prio workloads
++ * and smash them together and still expect them to work.
++ *
++ * For this reason 'all' FIFO tasks the kernel creates are basically at:
++ *
++ * MAX_RT_PRIO / 2
++ *
++ * The administrator _MUST_ configure the system, the kernel simply doesn't
++ * know enough information to make a sensible choice.
++ */
++void sched_set_fifo(struct task_struct *p)
++{
++ struct sched_param sp = { .sched_priority = MAX_RT_PRIO / 2 };
++ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_fifo);
++
++/*
++ * For when you don't much care about FIFO, but want to be above SCHED_NORMAL.
++ */
++void sched_set_fifo_low(struct task_struct *p)
++{
++ struct sched_param sp = { .sched_priority = 1 };
++ WARN_ON_ONCE(sched_setscheduler_nocheck(p, SCHED_FIFO, &sp) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_fifo_low);
++
++void sched_set_normal(struct task_struct *p, int nice)
++{
++ struct sched_attr attr = {
++ .sched_policy = SCHED_NORMAL,
++ .sched_nice = nice,
++ };
++ WARN_ON_ONCE(sched_setattr_nocheck(p, &attr) != 0);
++}
++EXPORT_SYMBOL_GPL(sched_set_normal);
++
++static int
++do_sched_setscheduler(pid_t pid, int policy, struct sched_param __user *param)
++{
++ struct sched_param lparam;
++
++ if (!param || pid < 0)
++ return -EINVAL;
++ if (copy_from_user(&lparam, param, sizeof(struct sched_param)))
++ return -EFAULT;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ return sched_setscheduler(p, policy, &lparam);
++}
++
++/*
++ * Mimics kernel/events/core.c perf_copy_attr().
++ */
++static int sched_copy_attr(struct sched_attr __user *uattr, struct sched_attr *attr)
++{
++ u32 size;
++ int ret;
++
++ /* Zero the full structure, so that a short copy will be nice: */
++ memset(attr, 0, sizeof(*attr));
++
++ ret = get_user(size, &uattr->size);
++ if (ret)
++ return ret;
++
++ /* ABI compatibility quirk: */
++ if (!size)
++ size = SCHED_ATTR_SIZE_VER0;
++
++ if (size < SCHED_ATTR_SIZE_VER0 || size > PAGE_SIZE)
++ goto err_size;
++
++ ret = copy_struct_from_user(attr, sizeof(*attr), uattr, size);
++ if (ret) {
++ if (ret == -E2BIG)
++ goto err_size;
++ return ret;
++ }
++
++ /*
++ * XXX: Do we want to be lenient like existing syscalls; or do we want
++ * to be strict and return an error on out-of-bounds values?
++ */
++ attr->sched_nice = clamp(attr->sched_nice, -20, 19);
++
++ /* sched/core.c uses zero here but we already know ret is zero */
++ return 0;
++
++err_size:
++ put_user(sizeof(*attr), &uattr->size);
++ return -E2BIG;
++}
++
++/**
++ * sys_sched_setscheduler - set/change the scheduler policy and RT priority
++ * @pid: the pid in question.
++ * @policy: new policy.
++ *
++ * Return: 0 on success. An error code otherwise.
++ * @param: structure containing the new RT priority.
++ */
++SYSCALL_DEFINE3(sched_setscheduler, pid_t, pid, int, policy, struct sched_param __user *, param)
++{
++ if (policy < 0)
++ return -EINVAL;
++
++ return do_sched_setscheduler(pid, policy, param);
++}
++
++/**
++ * sys_sched_setparam - set/change the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the new RT priority.
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++SYSCALL_DEFINE2(sched_setparam, pid_t, pid, struct sched_param __user *, param)
++{
++ return do_sched_setscheduler(pid, SETPARAM_POLICY, param);
++}
++
++static void get_params(struct task_struct *p, struct sched_attr *attr)
++{
++ if (task_has_rt_policy(p))
++ attr->sched_priority = p->rt_priority;
++ else
++ attr->sched_nice = task_nice(p);
++}
++
++/**
++ * sys_sched_setattr - same as above, but with extended sched_attr
++ * @pid: the pid in question.
++ * @uattr: structure containing the extended parameters.
++ */
++SYSCALL_DEFINE3(sched_setattr, pid_t, pid, struct sched_attr __user *, uattr,
++ unsigned int, flags)
++{
++ struct sched_attr attr;
++ int retval;
++
++ if (!uattr || pid < 0 || flags)
++ return -EINVAL;
++
++ retval = sched_copy_attr(uattr, &attr);
++ if (retval)
++ return retval;
++
++ if ((int)attr.sched_policy < 0)
++ return -EINVAL;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ if (attr.sched_flags & SCHED_FLAG_KEEP_PARAMS)
++ get_params(p, &attr);
++
++ return sched_setattr(p, &attr);
++}
++
++/**
++ * sys_sched_getscheduler - get the policy (scheduling class) of a thread
++ * @pid: the pid in question.
++ *
++ * Return: On success, the policy of the thread. Otherwise, a negative error
++ * code.
++ */
++SYSCALL_DEFINE1(sched_getscheduler, pid_t, pid)
++{
++ struct task_struct *p;
++ int retval = -EINVAL;
++
++ if (pid < 0)
++ return -ESRCH;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (!retval)
++ retval = p->policy;
++
++ return retval;
++}
++
++/**
++ * sys_sched_getscheduler - get the RT priority of a thread
++ * @pid: the pid in question.
++ * @param: structure containing the RT priority.
++ *
++ * Return: On success, 0 and the RT priority is in @param. Otherwise, an error
++ * code.
++ */
++SYSCALL_DEFINE2(sched_getparam, pid_t, pid, struct sched_param __user *, param)
++{
++ struct sched_param lp = { .sched_priority = 0 };
++ struct task_struct *p;
++
++ if (!param || pid < 0)
++ return -EINVAL;
++
++ scoped_guard (rcu) {
++ int retval;
++
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -EINVAL;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ if (task_has_rt_policy(p))
++ lp.sched_priority = p->rt_priority;
++ }
++
++ /*
++ * This one might sleep, we cannot do it with a spinlock held ...
++ */
++ return copy_to_user(param, &lp, sizeof(*param)) ? -EFAULT : 0;
++}
++
++/*
++ * Copy the kernel size attribute structure (which might be larger
++ * than what user-space knows about) to user-space.
++ *
++ * Note that all cases are valid: user-space buffer can be larger or
++ * smaller than the kernel-space buffer. The usual case is that both
++ * have the same size.
++ */
++static int
++sched_attr_copy_to_user(struct sched_attr __user *uattr,
++ struct sched_attr *kattr,
++ unsigned int usize)
++{
++ unsigned int ksize = sizeof(*kattr);
++
++ if (!access_ok(uattr, usize))
++ return -EFAULT;
++
++ /*
++ * sched_getattr() ABI forwards and backwards compatibility:
++ *
++ * If usize == ksize then we just copy everything to user-space and all is good.
++ *
++ * If usize < ksize then we only copy as much as user-space has space for,
++ * this keeps ABI compatibility as well. We skip the rest.
++ *
++ * If usize > ksize then user-space is using a newer version of the ABI,
++ * which part the kernel doesn't know about. Just ignore it - tooling can
++ * detect the kernel's knowledge of attributes from the attr->size value
++ * which is set to ksize in this case.
++ */
++ kattr->size = min(usize, ksize);
++
++ if (copy_to_user(uattr, kattr, kattr->size))
++ return -EFAULT;
++
++ return 0;
++}
++
++/**
++ * sys_sched_getattr - similar to sched_getparam, but with sched_attr
++ * @pid: the pid in question.
++ * @uattr: structure containing the extended parameters.
++ * @usize: sizeof(attr) for fwd/bwd comp.
++ * @flags: for future extension.
++ */
++SYSCALL_DEFINE4(sched_getattr, pid_t, pid, struct sched_attr __user *, uattr,
++ unsigned int, usize, unsigned int, flags)
++{
++ struct sched_attr kattr = { };
++ struct task_struct *p;
++ int retval;
++
++ if (!uattr || pid < 0 || usize > PAGE_SIZE ||
++ usize < SCHED_ATTR_SIZE_VER0 || flags)
++ return -EINVAL;
++
++ scoped_guard (rcu) {
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ kattr.sched_policy = p->policy;
++ if (p->sched_reset_on_fork)
++ kattr.sched_flags |= SCHED_FLAG_RESET_ON_FORK;
++ get_params(p, &kattr);
++ kattr.sched_flags &= SCHED_FLAG_ALL;
++
++#ifdef CONFIG_UCLAMP_TASK
++ kattr.sched_util_min = p->uclamp_req[UCLAMP_MIN].value;
++ kattr.sched_util_max = p->uclamp_req[UCLAMP_MAX].value;
++#endif
++ }
++
++ return sched_attr_copy_to_user(uattr, &kattr, usize);
++}
++
++#ifdef CONFIG_SMP
++int dl_task_check_affinity(struct task_struct *p, const struct cpumask *mask)
++{
++ return 0;
++}
++#endif
++
++static int
++__sched_setaffinity(struct task_struct *p, struct affinity_context *ctx)
++{
++ int retval;
++ cpumask_var_t cpus_allowed, new_mask;
++
++ if (!alloc_cpumask_var(&cpus_allowed, GFP_KERNEL))
++ return -ENOMEM;
++
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL)) {
++ retval = -ENOMEM;
++ goto out_free_cpus_allowed;
++ }
++
++ cpuset_cpus_allowed(p, cpus_allowed);
++ cpumask_and(new_mask, ctx->new_mask, cpus_allowed);
++
++ ctx->new_mask = new_mask;
++ ctx->flags |= SCA_CHECK;
++
++ retval = __set_cpus_allowed_ptr(p, ctx);
++ if (retval)
++ goto out_free_new_mask;
++
++ cpuset_cpus_allowed(p, cpus_allowed);
++ if (!cpumask_subset(new_mask, cpus_allowed)) {
++ /*
++ * We must have raced with a concurrent cpuset
++ * update. Just reset the cpus_allowed to the
++ * cpuset's cpus_allowed
++ */
++ cpumask_copy(new_mask, cpus_allowed);
++
++ /*
++ * If SCA_USER is set, a 2nd call to __set_cpus_allowed_ptr()
++ * will restore the previous user_cpus_ptr value.
++ *
++ * In the unlikely event a previous user_cpus_ptr exists,
++ * we need to further restrict the mask to what is allowed
++ * by that old user_cpus_ptr.
++ */
++ if (unlikely((ctx->flags & SCA_USER) && ctx->user_mask)) {
++ bool empty = !cpumask_and(new_mask, new_mask,
++ ctx->user_mask);
++
++ if (WARN_ON_ONCE(empty))
++ cpumask_copy(new_mask, cpus_allowed);
++ }
++ __set_cpus_allowed_ptr(p, ctx);
++ retval = -EINVAL;
++ }
++
++out_free_new_mask:
++ free_cpumask_var(new_mask);
++out_free_cpus_allowed:
++ free_cpumask_var(cpus_allowed);
++ return retval;
++}
++
++long sched_setaffinity(pid_t pid, const struct cpumask *in_mask)
++{
++ struct affinity_context ac;
++ struct cpumask *user_mask;
++ int retval;
++
++ CLASS(find_get_task, p)(pid);
++ if (!p)
++ return -ESRCH;
++
++ if (p->flags & PF_NO_SETAFFINITY)
++ return -EINVAL;
++
++ if (!check_same_owner(p)) {
++ guard(rcu)();
++ if (!ns_capable(__task_cred(p)->user_ns, CAP_SYS_NICE))
++ return -EPERM;
++ }
++
++ retval = security_task_setscheduler(p);
++ if (retval)
++ return retval;
++
++ /*
++ * With non-SMP configs, user_cpus_ptr/user_mask isn't used and
++ * alloc_user_cpus_ptr() returns NULL.
++ */
++ user_mask = alloc_user_cpus_ptr(NUMA_NO_NODE);
++ if (user_mask) {
++ cpumask_copy(user_mask, in_mask);
++ } else if (IS_ENABLED(CONFIG_SMP)) {
++ return -ENOMEM;
++ }
++
++ ac = (struct affinity_context){
++ .new_mask = in_mask,
++ .user_mask = user_mask,
++ .flags = SCA_USER,
++ };
++
++ retval = __sched_setaffinity(p, &ac);
++ kfree(ac.user_mask);
++
++ return retval;
++}
++
++static int get_user_cpu_mask(unsigned long __user *user_mask_ptr, unsigned len,
++ struct cpumask *new_mask)
++{
++ if (len < cpumask_size())
++ cpumask_clear(new_mask);
++ else if (len > cpumask_size())
++ len = cpumask_size();
++
++ return copy_from_user(new_mask, user_mask_ptr, len) ? -EFAULT : 0;
++}
++
++/**
++ * sys_sched_setaffinity - set the CPU affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to the new CPU mask
++ *
++ * Return: 0 on success. An error code otherwise.
++ */
++SYSCALL_DEFINE3(sched_setaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ cpumask_var_t new_mask;
++ int retval;
++
++ if (!alloc_cpumask_var(&new_mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ retval = get_user_cpu_mask(user_mask_ptr, len, new_mask);
++ if (retval == 0)
++ retval = sched_setaffinity(pid, new_mask);
++ free_cpumask_var(new_mask);
++ return retval;
++}
++
++long sched_getaffinity(pid_t pid, cpumask_t *mask)
++{
++ struct task_struct *p;
++ int retval;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -ESRCH;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ guard(raw_spinlock_irqsave)(&p->pi_lock);
++ cpumask_and(mask, &p->cpus_mask, cpu_active_mask);
++
++ return retval;
++}
++
++/**
++ * sys_sched_getaffinity - get the CPU affinity of a process
++ * @pid: pid of the process
++ * @len: length in bytes of the bitmask pointed to by user_mask_ptr
++ * @user_mask_ptr: user-space pointer to hold the current CPU mask
++ *
++ * Return: size of CPU mask copied to user_mask_ptr on success. An
++ * error code otherwise.
++ */
++SYSCALL_DEFINE3(sched_getaffinity, pid_t, pid, unsigned int, len,
++ unsigned long __user *, user_mask_ptr)
++{
++ int ret;
++ cpumask_var_t mask;
++
++ if ((len * BITS_PER_BYTE) < nr_cpu_ids)
++ return -EINVAL;
++ if (len & (sizeof(unsigned long)-1))
++ return -EINVAL;
++
++ if (!zalloc_cpumask_var(&mask, GFP_KERNEL))
++ return -ENOMEM;
++
++ ret = sched_getaffinity(pid, mask);
++ if (ret == 0) {
++ unsigned int retlen = min(len, cpumask_size());
++
++ if (copy_to_user(user_mask_ptr, cpumask_bits(mask), retlen))
++ ret = -EFAULT;
++ else
++ ret = retlen;
++ }
++ free_cpumask_var(mask);
++
++ return ret;
++}
++
++static void do_sched_yield(void)
++{
++ struct rq *rq;
++ struct rq_flags rf;
++ struct task_struct *p;
++
++ if (!sched_yield_type)
++ return;
++
++ rq = this_rq_lock_irq(&rf);
++
++ schedstat_inc(rq->yld_count);
++
++ p = current;
++ if (rt_task(p)) {
++ if (task_on_rq_queued(p))
++ requeue_task(p, rq);
++ } else if (rq->nr_running > 1) {
++ do_sched_yield_type_1(p, rq);
++ if (task_on_rq_queued(p))
++ requeue_task(p, rq);
++ }
++
++ preempt_disable();
++ raw_spin_unlock_irq(&rq->lock);
++ sched_preempt_enable_no_resched();
++
++ schedule();
++}
++
++/**
++ * sys_sched_yield - yield the current processor to other threads.
++ *
++ * This function yields the current CPU to other tasks. If there are no
++ * other threads running on this CPU then this function will return.
++ *
++ * Return: 0.
++ */
++SYSCALL_DEFINE0(sched_yield)
++{
++ do_sched_yield();
++ return 0;
++}
++
++#if !defined(CONFIG_PREEMPTION) || defined(CONFIG_PREEMPT_DYNAMIC)
++int __sched __cond_resched(void)
++{
++ if (should_resched(0)) {
++ preempt_schedule_common();
++ return 1;
++ }
++ /*
++ * In preemptible kernels, ->rcu_read_lock_nesting tells the tick
++ * whether the current CPU is in an RCU read-side critical section,
++ * so the tick can report quiescent states even for CPUs looping
++ * in kernel context. In contrast, in non-preemptible kernels,
++ * RCU readers leave no in-memory hints, which means that CPU-bound
++ * processes executing in kernel context might never report an
++ * RCU quiescent state. Therefore, the following code causes
++ * cond_resched() to report a quiescent state, but only when RCU
++ * is in urgent need of one.
++ */
++#ifndef CONFIG_PREEMPT_RCU
++ rcu_all_qs();
++#endif
++ return 0;
++}
++EXPORT_SYMBOL(__cond_resched);
++#endif
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#define cond_resched_dynamic_enabled __cond_resched
++#define cond_resched_dynamic_disabled ((void *)&__static_call_return0)
++DEFINE_STATIC_CALL_RET0(cond_resched, __cond_resched);
++EXPORT_STATIC_CALL_TRAMP(cond_resched);
++
++#define might_resched_dynamic_enabled __cond_resched
++#define might_resched_dynamic_disabled ((void *)&__static_call_return0)
++DEFINE_STATIC_CALL_RET0(might_resched, __cond_resched);
++EXPORT_STATIC_CALL_TRAMP(might_resched);
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++static DEFINE_STATIC_KEY_FALSE(sk_dynamic_cond_resched);
++int __sched dynamic_cond_resched(void)
++{
++ klp_sched_try_switch();
++ if (!static_branch_unlikely(&sk_dynamic_cond_resched))
++ return 0;
++ return __cond_resched();
++}
++EXPORT_SYMBOL(dynamic_cond_resched);
++
++static DEFINE_STATIC_KEY_FALSE(sk_dynamic_might_resched);
++int __sched dynamic_might_resched(void)
++{
++ if (!static_branch_unlikely(&sk_dynamic_might_resched))
++ return 0;
++ return __cond_resched();
++}
++EXPORT_SYMBOL(dynamic_might_resched);
++#endif
++#endif
++
++/*
++ * __cond_resched_lock() - if a reschedule is pending, drop the given lock,
++ * call schedule, and on return reacquire the lock.
++ *
++ * This works OK both with and without CONFIG_PREEMPTION. We do strange low-level
++ * operations here to prevent schedule() from being called twice (once via
++ * spin_unlock(), once by hand).
++ */
++int __cond_resched_lock(spinlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held(lock);
++
++ if (spin_needbreak(lock) || resched) {
++ spin_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ spin_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_lock);
++
++int __cond_resched_rwlock_read(rwlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held_read(lock);
++
++ if (rwlock_needbreak(lock) || resched) {
++ read_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ read_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_rwlock_read);
++
++int __cond_resched_rwlock_write(rwlock_t *lock)
++{
++ int resched = should_resched(PREEMPT_LOCK_OFFSET);
++ int ret = 0;
++
++ lockdep_assert_held_write(lock);
++
++ if (rwlock_needbreak(lock) || resched) {
++ write_unlock(lock);
++ if (!_cond_resched())
++ cpu_relax();
++ ret = 1;
++ write_lock(lock);
++ }
++ return ret;
++}
++EXPORT_SYMBOL(__cond_resched_rwlock_write);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++
++#ifdef CONFIG_GENERIC_ENTRY
++#include <linux/entry-common.h>
++#endif
++
++/*
++ * SC:cond_resched
++ * SC:might_resched
++ * SC:preempt_schedule
++ * SC:preempt_schedule_notrace
++ * SC:irqentry_exit_cond_resched
++ *
++ *
++ * NONE:
++ * cond_resched <- __cond_resched
++ * might_resched <- RET0
++ * preempt_schedule <- NOP
++ * preempt_schedule_notrace <- NOP
++ * irqentry_exit_cond_resched <- NOP
++ *
++ * VOLUNTARY:
++ * cond_resched <- __cond_resched
++ * might_resched <- __cond_resched
++ * preempt_schedule <- NOP
++ * preempt_schedule_notrace <- NOP
++ * irqentry_exit_cond_resched <- NOP
++ *
++ * FULL:
++ * cond_resched <- RET0
++ * might_resched <- RET0
++ * preempt_schedule <- preempt_schedule
++ * preempt_schedule_notrace <- preempt_schedule_notrace
++ * irqentry_exit_cond_resched <- irqentry_exit_cond_resched
++ */
++
++enum {
++ preempt_dynamic_undefined = -1,
++ preempt_dynamic_none,
++ preempt_dynamic_voluntary,
++ preempt_dynamic_full,
++};
++
++int preempt_dynamic_mode = preempt_dynamic_undefined;
++
++int sched_dynamic_mode(const char *str)
++{
++ if (!strcmp(str, "none"))
++ return preempt_dynamic_none;
++
++ if (!strcmp(str, "voluntary"))
++ return preempt_dynamic_voluntary;
++
++ if (!strcmp(str, "full"))
++ return preempt_dynamic_full;
++
++ return -EINVAL;
++}
++
++#if defined(CONFIG_HAVE_PREEMPT_DYNAMIC_CALL)
++#define preempt_dynamic_enable(f) static_call_update(f, f##_dynamic_enabled)
++#define preempt_dynamic_disable(f) static_call_update(f, f##_dynamic_disabled)
++#elif defined(CONFIG_HAVE_PREEMPT_DYNAMIC_KEY)
++#define preempt_dynamic_enable(f) static_key_enable(&sk_dynamic_##f.key)
++#define preempt_dynamic_disable(f) static_key_disable(&sk_dynamic_##f.key)
++#else
++#error "Unsupported PREEMPT_DYNAMIC mechanism"
++#endif
++
++static DEFINE_MUTEX(sched_dynamic_mutex);
++static bool klp_override;
++
++static void __sched_dynamic_update(int mode)
++{
++ /*
++ * Avoid {NONE,VOLUNTARY} -> FULL transitions from ever ending up in
++ * the ZERO state, which is invalid.
++ */
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(might_resched);
++ preempt_dynamic_enable(preempt_schedule);
++ preempt_dynamic_enable(preempt_schedule_notrace);
++ preempt_dynamic_enable(irqentry_exit_cond_resched);
++
++ switch (mode) {
++ case preempt_dynamic_none:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_disable(might_resched);
++ preempt_dynamic_disable(preempt_schedule);
++ preempt_dynamic_disable(preempt_schedule_notrace);
++ preempt_dynamic_disable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: none\n");
++ break;
++
++ case preempt_dynamic_voluntary:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_enable(might_resched);
++ preempt_dynamic_disable(preempt_schedule);
++ preempt_dynamic_disable(preempt_schedule_notrace);
++ preempt_dynamic_disable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: voluntary\n");
++ break;
++
++ case preempt_dynamic_full:
++ if (!klp_override)
++ preempt_dynamic_enable(cond_resched);
++ preempt_dynamic_disable(might_resched);
++ preempt_dynamic_enable(preempt_schedule);
++ preempt_dynamic_enable(preempt_schedule_notrace);
++ preempt_dynamic_enable(irqentry_exit_cond_resched);
++ if (mode != preempt_dynamic_mode)
++ pr_info("Dynamic Preempt: full\n");
++ break;
++ }
++
++ preempt_dynamic_mode = mode;
++}
++
++void sched_dynamic_update(int mode)
++{
++ mutex_lock(&sched_dynamic_mutex);
++ __sched_dynamic_update(mode);
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++#ifdef CONFIG_HAVE_PREEMPT_DYNAMIC_CALL
++
++static int klp_cond_resched(void)
++{
++ __klp_sched_try_switch();
++ return __cond_resched();
++}
++
++void sched_dynamic_klp_enable(void)
++{
++ mutex_lock(&sched_dynamic_mutex);
++
++ klp_override = true;
++ static_call_update(cond_resched, klp_cond_resched);
++
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++void sched_dynamic_klp_disable(void)
++{
++ mutex_lock(&sched_dynamic_mutex);
++
++ klp_override = false;
++ __sched_dynamic_update(preempt_dynamic_mode);
++
++ mutex_unlock(&sched_dynamic_mutex);
++}
++
++#endif /* CONFIG_HAVE_PREEMPT_DYNAMIC_CALL */
++
++
++static int __init setup_preempt_mode(char *str)
++{
++ int mode = sched_dynamic_mode(str);
++ if (mode < 0) {
++ pr_warn("Dynamic Preempt: unsupported mode: %s\n", str);
++ return 0;
++ }
++
++ sched_dynamic_update(mode);
++ return 1;
++}
++__setup("preempt=", setup_preempt_mode);
++
++static void __init preempt_dynamic_init(void)
++{
++ if (preempt_dynamic_mode == preempt_dynamic_undefined) {
++ if (IS_ENABLED(CONFIG_PREEMPT_NONE)) {
++ sched_dynamic_update(preempt_dynamic_none);
++ } else if (IS_ENABLED(CONFIG_PREEMPT_VOLUNTARY)) {
++ sched_dynamic_update(preempt_dynamic_voluntary);
++ } else {
++ /* Default static call setting, nothing to do */
++ WARN_ON_ONCE(!IS_ENABLED(CONFIG_PREEMPT));
++ preempt_dynamic_mode = preempt_dynamic_full;
++ pr_info("Dynamic Preempt: full\n");
++ }
++ }
++}
++
++#define PREEMPT_MODEL_ACCESSOR(mode) \
++ bool preempt_model_##mode(void) \
++ { \
++ WARN_ON_ONCE(preempt_dynamic_mode == preempt_dynamic_undefined); \
++ return preempt_dynamic_mode == preempt_dynamic_##mode; \
++ } \
++ EXPORT_SYMBOL_GPL(preempt_model_##mode)
++
++PREEMPT_MODEL_ACCESSOR(none);
++PREEMPT_MODEL_ACCESSOR(voluntary);
++PREEMPT_MODEL_ACCESSOR(full);
++
++#else /* !CONFIG_PREEMPT_DYNAMIC */
++
++static inline void preempt_dynamic_init(void) { }
++
++#endif /* #ifdef CONFIG_PREEMPT_DYNAMIC */
++
++/**
++ * yield - yield the current processor to other threads.
++ *
++ * Do not ever use this function, there's a 99% chance you're doing it wrong.
++ *
++ * The scheduler is at all times free to pick the calling task as the most
++ * eligible task to run, if removing the yield() call from your code breaks
++ * it, it's already broken.
++ *
++ * Typical broken usage is:
++ *
++ * while (!event)
++ * yield();
++ *
++ * where one assumes that yield() will let 'the other' process run that will
++ * make event true. If the current task is a SCHED_FIFO task that will never
++ * happen. Never use yield() as a progress guarantee!!
++ *
++ * If you want to use yield() to wait for something, use wait_event().
++ * If you want to use yield() to be 'nice' for others, use cond_resched().
++ * If you still want to use yield(), do not!
++ */
++void __sched yield(void)
++{
++ set_current_state(TASK_RUNNING);
++ do_sched_yield();
++}
++EXPORT_SYMBOL(yield);
++
++/**
++ * yield_to - yield the current processor to another thread in
++ * your thread group, or accelerate that thread toward the
++ * processor it's on.
++ * @p: target task
++ * @preempt: whether task preemption is allowed or not
++ *
++ * It's the caller's job to ensure that the target task struct
++ * can't go away on us before we can do any checks.
++ *
++ * In Alt schedule FW, yield_to is not supported.
++ *
++ * Return:
++ * true (>0) if we indeed boosted the target task.
++ * false (0) if we failed to boost the target.
++ * -ESRCH if there's no task to yield to.
++ */
++int __sched yield_to(struct task_struct *p, bool preempt)
++{
++ return 0;
++}
++EXPORT_SYMBOL_GPL(yield_to);
++
++int io_schedule_prepare(void)
++{
++ int old_iowait = current->in_iowait;
++
++ current->in_iowait = 1;
++ blk_flush_plug(current->plug, true);
++ return old_iowait;
++}
++
++void io_schedule_finish(int token)
++{
++ current->in_iowait = token;
++}
++
++/*
++ * This task is about to go to sleep on IO. Increment rq->nr_iowait so
++ * that process accounting knows that this is a task in IO wait state.
++ *
++ * But don't do that if it is a deliberate, throttling IO wait (this task
++ * has set its backing_dev_info: the queue against which it should throttle)
++ */
++
++long __sched io_schedule_timeout(long timeout)
++{
++ int token;
++ long ret;
++
++ token = io_schedule_prepare();
++ ret = schedule_timeout(timeout);
++ io_schedule_finish(token);
++
++ return ret;
++}
++EXPORT_SYMBOL(io_schedule_timeout);
++
++void __sched io_schedule(void)
++{
++ int token;
++
++ token = io_schedule_prepare();
++ schedule();
++ io_schedule_finish(token);
++}
++EXPORT_SYMBOL(io_schedule);
++
++/**
++ * sys_sched_get_priority_max - return maximum RT priority.
++ * @policy: scheduling class.
++ *
++ * Return: On success, this syscall returns the maximum
++ * rt_priority that can be used by a given scheduling class.
++ * On failure, a negative error code is returned.
++ */
++SYSCALL_DEFINE1(sched_get_priority_max, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = MAX_RT_PRIO - 1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_IDLE:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++/**
++ * sys_sched_get_priority_min - return minimum RT priority.
++ * @policy: scheduling class.
++ *
++ * Return: On success, this syscall returns the minimum
++ * rt_priority that can be used by a given scheduling class.
++ * On failure, a negative error code is returned.
++ */
++SYSCALL_DEFINE1(sched_get_priority_min, int, policy)
++{
++ int ret = -EINVAL;
++
++ switch (policy) {
++ case SCHED_FIFO:
++ case SCHED_RR:
++ ret = 1;
++ break;
++ case SCHED_NORMAL:
++ case SCHED_BATCH:
++ case SCHED_IDLE:
++ ret = 0;
++ break;
++ }
++ return ret;
++}
++
++static int sched_rr_get_interval(pid_t pid, struct timespec64 *t)
++{
++ struct task_struct *p;
++ int retval;
++
++ alt_sched_debug();
++
++ if (pid < 0)
++ return -EINVAL;
++
++ guard(rcu)();
++ p = find_process_by_pid(pid);
++ if (!p)
++ return -EINVAL;
++
++ retval = security_task_getscheduler(p);
++ if (retval)
++ return retval;
++
++ *t = ns_to_timespec64(sysctl_sched_base_slice);
++ return 0;
++}
++
++/**
++ * sys_sched_rr_get_interval - return the default timeslice of a process.
++ * @pid: pid of the process.
++ * @interval: userspace pointer to the timeslice value.
++ *
++ *
++ * Return: On success, 0 and the timeslice is in @interval. Otherwise,
++ * an error code.
++ */
++SYSCALL_DEFINE2(sched_rr_get_interval, pid_t, pid,
++ struct __kernel_timespec __user *, interval)
++{
++ struct timespec64 t;
++ int retval = sched_rr_get_interval(pid, &t);
++
++ if (retval == 0)
++ retval = put_timespec64(&t, interval);
++
++ return retval;
++}
++
++#ifdef CONFIG_COMPAT_32BIT_TIME
++SYSCALL_DEFINE2(sched_rr_get_interval_time32, pid_t, pid,
++ struct old_timespec32 __user *, interval)
++{
++ struct timespec64 t;
++ int retval = sched_rr_get_interval(pid, &t);
++
++ if (retval == 0)
++ retval = put_old_timespec32(&t, interval);
++ return retval;
++}
++#endif
++
++void sched_show_task(struct task_struct *p)
++{
++ unsigned long free = 0;
++ int ppid;
++
++ if (!try_get_task_stack(p))
++ return;
++
++ pr_info("task:%-15.15s state:%c", p->comm, task_state_to_char(p));
++
++ if (task_is_running(p))
++ pr_cont(" running task ");
++#ifdef CONFIG_DEBUG_STACK_USAGE
++ free = stack_not_used(p);
++#endif
++ ppid = 0;
++ rcu_read_lock();
++ if (pid_alive(p))
++ ppid = task_pid_nr(rcu_dereference(p->real_parent));
++ rcu_read_unlock();
++ pr_cont(" stack:%-5lu pid:%-5d tgid:%-5d ppid:%-6d flags:0x%08lx\n",
++ free, task_pid_nr(p), task_tgid_nr(p),
++ ppid, read_task_thread_flags(p));
++
++ print_worker_info(KERN_INFO, p);
++ print_stop_info(KERN_INFO, p);
++ show_stack(p, NULL, KERN_INFO);
++ put_task_stack(p);
++}
++EXPORT_SYMBOL_GPL(sched_show_task);
++
++static inline bool
++state_filter_match(unsigned long state_filter, struct task_struct *p)
++{
++ unsigned int state = READ_ONCE(p->__state);
++
++ /* no filter, everything matches */
++ if (!state_filter)
++ return true;
++
++ /* filter, but doesn't match */
++ if (!(state & state_filter))
++ return false;
++
++ /*
++ * When looking for TASK_UNINTERRUPTIBLE skip TASK_IDLE (allows
++ * TASK_KILLABLE).
++ */
++ if (state_filter == TASK_UNINTERRUPTIBLE && (state & TASK_NOLOAD))
++ return false;
++
++ return true;
++}
++
++
++void show_state_filter(unsigned int state_filter)
++{
++ struct task_struct *g, *p;
++
++ rcu_read_lock();
++ for_each_process_thread(g, p) {
++ /*
++ * reset the NMI-timeout, listing all files on a slow
++ * console might take a lot of time:
++ * Also, reset softlockup watchdogs on all CPUs, because
++ * another CPU might be blocked waiting for us to process
++ * an IPI.
++ */
++ touch_nmi_watchdog();
++ touch_all_softlockup_watchdogs();
++ if (state_filter_match(state_filter, p))
++ sched_show_task(p);
++ }
++
++#ifdef CONFIG_SCHED_DEBUG
++ /* TODO: Alt schedule FW should support this
++ if (!state_filter)
++ sysrq_sched_debug_show();
++ */
++#endif
++ rcu_read_unlock();
++ /*
++ * Only show locks if all tasks are dumped:
++ */
++ if (!state_filter)
++ debug_show_all_locks();
++}
++
++void dump_cpu_task(int cpu)
++{
++ if (cpu == smp_processor_id() && in_hardirq()) {
++ struct pt_regs *regs;
++
++ regs = get_irq_regs();
++ if (regs) {
++ show_regs(regs);
++ return;
++ }
++ }
++
++ if (trigger_single_cpu_backtrace(cpu))
++ return;
++
++ pr_info("Task dump for CPU %d:\n", cpu);
++ sched_show_task(cpu_curr(cpu));
++}
++
++/**
++ * init_idle - set up an idle thread for a given CPU
++ * @idle: task in question
++ * @cpu: CPU the idle task belongs to
++ *
++ * NOTE: this function does not set the idle thread's NEED_RESCHED
++ * flag, to make booting more robust.
++ */
++void __init init_idle(struct task_struct *idle, int cpu)
++{
++#ifdef CONFIG_SMP
++ struct affinity_context ac = (struct affinity_context) {
++ .new_mask = cpumask_of(cpu),
++ .flags = 0,
++ };
++#endif
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ __sched_fork(0, idle);
++
++ raw_spin_lock_irqsave(&idle->pi_lock, flags);
++ raw_spin_lock(&rq->lock);
++
++ idle->last_ran = rq->clock_task;
++ idle->__state = TASK_RUNNING;
++ /*
++ * PF_KTHREAD should already be set at this point; regardless, make it
++ * look like a proper per-CPU kthread.
++ */
++ idle->flags |= PF_KTHREAD | PF_NO_SETAFFINITY;
++ kthread_set_per_cpu(idle, cpu);
++
++ sched_queue_init_idle(&rq->queue, idle);
++
++#ifdef CONFIG_SMP
++ /*
++ * It's possible that init_idle() gets called multiple times on a task,
++ * in that case do_set_cpus_allowed() will not do the right thing.
++ *
++ * And since this is boot we can forgo the serialisation.
++ */
++ set_cpus_allowed_common(idle, &ac);
++#endif
++
++ /* Silence PROVE_RCU */
++ rcu_read_lock();
++ __set_task_cpu(idle, cpu);
++ rcu_read_unlock();
++
++ rq->idle = idle;
++ rcu_assign_pointer(rq->curr, idle);
++ idle->on_cpu = 1;
++
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&idle->pi_lock, flags);
++
++ /* Set the preempt count _outside_ the spinlocks! */
++ init_idle_preempt_count(idle, cpu);
++
++ ftrace_graph_init_idle_task(idle, cpu);
++ vtime_init_idle(idle, cpu);
++#ifdef CONFIG_SMP
++ sprintf(idle->comm, "%s/%d", INIT_TASK_COMM, cpu);
++#endif
++}
++
++#ifdef CONFIG_SMP
++
++int cpuset_cpumask_can_shrink(const struct cpumask __maybe_unused *cur,
++ const struct cpumask __maybe_unused *trial)
++{
++ return 1;
++}
++
++int task_can_attach(struct task_struct *p)
++{
++ int ret = 0;
++
++ /*
++ * Kthreads which disallow setaffinity shouldn't be moved
++ * to a new cpuset; we don't want to change their CPU
++ * affinity and isolating such threads by their set of
++ * allowed nodes is unnecessary. Thus, cpusets are not
++ * applicable for such threads. This prevents checking for
++ * success of set_cpus_allowed_ptr() on all attached tasks
++ * before cpus_mask may be changed.
++ */
++ if (p->flags & PF_NO_SETAFFINITY)
++ ret = -EINVAL;
++
++ return ret;
++}
++
++bool sched_smp_initialized __read_mostly;
++
++#ifdef CONFIG_HOTPLUG_CPU
++/*
++ * Ensures that the idle task is using init_mm right before its CPU goes
++ * offline.
++ */
++void idle_task_exit(void)
++{
++ struct mm_struct *mm = current->active_mm;
++
++ BUG_ON(current != this_rq()->idle);
++
++ if (mm != &init_mm) {
++ switch_mm(mm, &init_mm, current);
++ finish_arch_post_lock_switch();
++ }
++
++ /* finish_cpu(), as ran on the BP, will clean up the active_mm state */
++}
++
++static int __balance_push_cpu_stop(void *arg)
++{
++ struct task_struct *p = arg;
++ struct rq *rq = this_rq();
++ struct rq_flags rf;
++ int cpu;
++
++ raw_spin_lock_irq(&p->pi_lock);
++ rq_lock(rq, &rf);
++
++ update_rq_clock(rq);
++
++ if (task_rq(p) == rq && task_on_rq_queued(p)) {
++ cpu = select_fallback_rq(rq->cpu, p);
++ rq = __migrate_task(rq, p, cpu);
++ }
++
++ rq_unlock(rq, &rf);
++ raw_spin_unlock_irq(&p->pi_lock);
++
++ put_task_struct(p);
++
++ return 0;
++}
++
++static DEFINE_PER_CPU(struct cpu_stop_work, push_work);
++
++/*
++ * This is enabled below SCHED_AP_ACTIVE; when !cpu_active(), but only
++ * effective when the hotplug motion is down.
++ */
++static void balance_push(struct rq *rq)
++{
++ struct task_struct *push_task = rq->curr;
++
++ lockdep_assert_held(&rq->lock);
++
++ /*
++ * Ensure the thing is persistent until balance_push_set(.on = false);
++ */
++ rq->balance_callback = &balance_push_callback;
++
++ /*
++ * Only active while going offline and when invoked on the outgoing
++ * CPU.
++ */
++ if (!cpu_dying(rq->cpu) || rq != this_rq())
++ return;
++
++ /*
++ * Both the cpu-hotplug and stop task are in this case and are
++ * required to complete the hotplug process.
++ */
++ if (kthread_is_per_cpu(push_task) ||
++ is_migration_disabled(push_task)) {
++
++ /*
++ * If this is the idle task on the outgoing CPU try to wake
++ * up the hotplug control thread which might wait for the
++ * last task to vanish. The rcuwait_active() check is
++ * accurate here because the waiter is pinned on this CPU
++ * and can't obviously be running in parallel.
++ *
++ * On RT kernels this also has to check whether there are
++ * pinned and scheduled out tasks on the runqueue. They
++ * need to leave the migrate disabled section first.
++ */
++ if (!rq->nr_running && !rq_has_pinned_tasks(rq) &&
++ rcuwait_active(&rq->hotplug_wait)) {
++ raw_spin_unlock(&rq->lock);
++ rcuwait_wake_up(&rq->hotplug_wait);
++ raw_spin_lock(&rq->lock);
++ }
++ return;
++ }
++
++ get_task_struct(push_task);
++ /*
++ * Temporarily drop rq->lock such that we can wake-up the stop task.
++ * Both preemption and IRQs are still disabled.
++ */
++ preempt_disable();
++ raw_spin_unlock(&rq->lock);
++ stop_one_cpu_nowait(rq->cpu, __balance_push_cpu_stop, push_task,
++ this_cpu_ptr(&push_work));
++ preempt_enable();
++ /*
++ * At this point need_resched() is true and we'll take the loop in
++ * schedule(). The next pick is obviously going to be the stop task
++ * which kthread_is_per_cpu() and will push this task away.
++ */
++ raw_spin_lock(&rq->lock);
++}
++
++static void balance_push_set(int cpu, bool on)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct rq_flags rf;
++
++ rq_lock_irqsave(rq, &rf);
++ if (on) {
++ WARN_ON_ONCE(rq->balance_callback);
++ rq->balance_callback = &balance_push_callback;
++ } else if (rq->balance_callback == &balance_push_callback) {
++ rq->balance_callback = NULL;
++ }
++ rq_unlock_irqrestore(rq, &rf);
++}
++
++/*
++ * Invoked from a CPUs hotplug control thread after the CPU has been marked
++ * inactive. All tasks which are not per CPU kernel threads are either
++ * pushed off this CPU now via balance_push() or placed on a different CPU
++ * during wakeup. Wait until the CPU is quiescent.
++ */
++static void balance_hotplug_wait(void)
++{
++ struct rq *rq = this_rq();
++
++ rcuwait_wait_event(&rq->hotplug_wait,
++ rq->nr_running == 1 && !rq_has_pinned_tasks(rq),
++ TASK_UNINTERRUPTIBLE);
++}
++
++#else
++
++static void balance_push(struct rq *rq)
++{
++}
++
++static void balance_push_set(int cpu, bool on)
++{
++}
++
++static inline void balance_hotplug_wait(void)
++{
++}
++#endif /* CONFIG_HOTPLUG_CPU */
++
++static void set_rq_offline(struct rq *rq)
++{
++ if (rq->online) {
++ update_rq_clock(rq);
++ rq->online = false;
++ }
++}
++
++static void set_rq_online(struct rq *rq)
++{
++ if (!rq->online)
++ rq->online = true;
++}
++
++/*
++ * used to mark begin/end of suspend/resume:
++ */
++static int num_cpus_frozen;
++
++/*
++ * Update cpusets according to cpu_active mask. If cpusets are
++ * disabled, cpuset_update_active_cpus() becomes a simple wrapper
++ * around partition_sched_domains().
++ *
++ * If we come here as part of a suspend/resume, don't touch cpusets because we
++ * want to restore it back to its original state upon resume anyway.
++ */
++static void cpuset_cpu_active(void)
++{
++ if (cpuhp_tasks_frozen) {
++ /*
++ * num_cpus_frozen tracks how many CPUs are involved in suspend
++ * resume sequence. As long as this is not the last online
++ * operation in the resume sequence, just build a single sched
++ * domain, ignoring cpusets.
++ */
++ partition_sched_domains(1, NULL, NULL);
++ if (--num_cpus_frozen)
++ return;
++ /*
++ * This is the last CPU online operation. So fall through and
++ * restore the original sched domains by considering the
++ * cpuset configurations.
++ */
++ cpuset_force_rebuild();
++ }
++
++ cpuset_update_active_cpus();
++}
++
++static int cpuset_cpu_inactive(unsigned int cpu)
++{
++ if (!cpuhp_tasks_frozen) {
++ cpuset_update_active_cpus();
++ } else {
++ num_cpus_frozen++;
++ partition_sched_domains(1, NULL, NULL);
++ }
++ return 0;
++}
++
++int sched_cpu_activate(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ /*
++ * Clear the balance_push callback and prepare to schedule
++ * regular tasks.
++ */
++ balance_push_set(cpu, false);
++
++#ifdef CONFIG_SCHED_SMT
++ /*
++ * When going up, increment the number of cores with SMT present.
++ */
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2)
++ static_branch_inc_cpuslocked(&sched_smt_present);
++#endif
++ set_cpu_active(cpu, true);
++
++ if (sched_smp_initialized)
++ cpuset_cpu_active();
++
++ /*
++ * Put the rq online, if not already. This happens:
++ *
++ * 1) In the early boot process, because we build the real domains
++ * after all cpus have been brought up.
++ *
++ * 2) At runtime, if cpuset_cpu_active() fails to rebuild the
++ * domains.
++ */
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ set_rq_online(rq);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ return 0;
++}
++
++int sched_cpu_deactivate(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++ int ret;
++
++ set_cpu_active(cpu, false);
++
++ /*
++ * From this point forward, this CPU will refuse to run any task that
++ * is not: migrate_disable() or KTHREAD_IS_PER_CPU, and will actively
++ * push those tasks away until this gets cleared, see
++ * sched_cpu_dying().
++ */
++ balance_push_set(cpu, true);
++
++ /*
++ * We've cleared cpu_active_mask, wait for all preempt-disabled and RCU
++ * users of this state to go away such that all new such users will
++ * observe it.
++ *
++ * Specifically, we rely on ttwu to no longer target this CPU, see
++ * ttwu_queue_cond() and is_cpu_allowed().
++ *
++ * Do sync before park smpboot threads to take care the rcu boost case.
++ */
++ synchronize_rcu();
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ set_rq_offline(rq);
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++#ifdef CONFIG_SCHED_SMT
++ /*
++ * When going down, decrement the number of cores with SMT present.
++ */
++ if (cpumask_weight(cpu_smt_mask(cpu)) == 2) {
++ static_branch_dec_cpuslocked(&sched_smt_present);
++ if (!static_branch_likely(&sched_smt_present))
++ cpumask_clear(sched_sg_idle_mask);
++ }
++#endif
++
++ if (!sched_smp_initialized)
++ return 0;
++
++ ret = cpuset_cpu_inactive(cpu);
++ if (ret) {
++ balance_push_set(cpu, false);
++ set_cpu_active(cpu, true);
++ return ret;
++ }
++
++ return 0;
++}
++
++static void sched_rq_cpu_starting(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++
++ rq->calc_load_update = calc_load_update;
++}
++
++int sched_cpu_starting(unsigned int cpu)
++{
++ sched_rq_cpu_starting(cpu);
++ sched_tick_start(cpu);
++ return 0;
++}
++
++#ifdef CONFIG_HOTPLUG_CPU
++
++/*
++ * Invoked immediately before the stopper thread is invoked to bring the
++ * CPU down completely. At this point all per CPU kthreads except the
++ * hotplug thread (current) and the stopper thread (inactive) have been
++ * either parked or have been unbound from the outgoing CPU. Ensure that
++ * any of those which might be on the way out are gone.
++ *
++ * If after this point a bound task is being woken on this CPU then the
++ * responsible hotplug callback has failed to do it's job.
++ * sched_cpu_dying() will catch it with the appropriate fireworks.
++ */
++int sched_cpu_wait_empty(unsigned int cpu)
++{
++ balance_hotplug_wait();
++ return 0;
++}
++
++/*
++ * Since this CPU is going 'away' for a while, fold any nr_active delta we
++ * might have. Called from the CPU stopper task after ensuring that the
++ * stopper is the last running task on the CPU, so nr_active count is
++ * stable. We need to take the teardown thread which is calling this into
++ * account, so we hand in adjust = 1 to the load calculation.
++ *
++ * Also see the comment "Global load-average calculations".
++ */
++static void calc_load_migrate(struct rq *rq)
++{
++ long delta = calc_load_fold_active(rq, 1);
++
++ if (delta)
++ atomic_long_add(delta, &calc_load_tasks);
++}
++
++static void dump_rq_tasks(struct rq *rq, const char *loglvl)
++{
++ struct task_struct *g, *p;
++ int cpu = cpu_of(rq);
++
++ lockdep_assert_held(&rq->lock);
++
++ printk("%sCPU%d enqueued tasks (%u total):\n", loglvl, cpu, rq->nr_running);
++ for_each_process_thread(g, p) {
++ if (task_cpu(p) != cpu)
++ continue;
++
++ if (!task_on_rq_queued(p))
++ continue;
++
++ printk("%s\tpid: %d, name: %s\n", loglvl, p->pid, p->comm);
++ }
++}
++
++int sched_cpu_dying(unsigned int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ unsigned long flags;
++
++ /* Handle pending wakeups and then migrate everything off */
++ sched_tick_stop(cpu);
++
++ raw_spin_lock_irqsave(&rq->lock, flags);
++ if (rq->nr_running != 1 || rq_has_pinned_tasks(rq)) {
++ WARN(true, "Dying CPU not properly vacated!");
++ dump_rq_tasks(rq, KERN_WARNING);
++ }
++ raw_spin_unlock_irqrestore(&rq->lock, flags);
++
++ calc_load_migrate(rq);
++ hrtick_clear(rq);
++ return 0;
++}
++#endif
++
++#ifdef CONFIG_SMP
++static void sched_init_topology_cpumask_early(void)
++{
++ int cpu;
++ cpumask_t *tmp;
++
++ for_each_possible_cpu(cpu) {
++ /* init topo masks */
++ tmp = per_cpu(sched_cpu_topo_masks, cpu);
++
++ cpumask_copy(tmp, cpu_possible_mask);
++ per_cpu(sched_cpu_llc_mask, cpu) = tmp;
++ per_cpu(sched_cpu_topo_end_mask, cpu) = ++tmp;
++ }
++}
++
++#define TOPOLOGY_CPUMASK(name, mask, last)\
++ if (cpumask_and(topo, topo, mask)) { \
++ cpumask_copy(topo, mask); \
++ printk(KERN_INFO "sched: cpu#%02d topo: 0x%08lx - "#name, \
++ cpu, (topo++)->bits[0]); \
++ } \
++ if (!last) \
++ bitmap_complement(cpumask_bits(topo), cpumask_bits(mask), \
++ nr_cpumask_bits);
++
++static void sched_init_topology_cpumask(void)
++{
++ int cpu;
++ cpumask_t *topo;
++
++ for_each_online_cpu(cpu) {
++ /* take chance to reset time slice for idle tasks */
++ cpu_rq(cpu)->idle->time_slice = sysctl_sched_base_slice;
++
++ topo = per_cpu(sched_cpu_topo_masks, cpu);
++
++ bitmap_complement(cpumask_bits(topo), cpumask_bits(cpumask_of(cpu)),
++ nr_cpumask_bits);
++#ifdef CONFIG_SCHED_SMT
++ TOPOLOGY_CPUMASK(smt, topology_sibling_cpumask(cpu), false);
++#endif
++ TOPOLOGY_CPUMASK(cluster, topology_cluster_cpumask(cpu), false);
++
++ per_cpu(sd_llc_id, cpu) = cpumask_first(cpu_coregroup_mask(cpu));
++ per_cpu(sched_cpu_llc_mask, cpu) = topo;
++ TOPOLOGY_CPUMASK(coregroup, cpu_coregroup_mask(cpu), false);
++
++ TOPOLOGY_CPUMASK(core, topology_core_cpumask(cpu), false);
++
++ TOPOLOGY_CPUMASK(others, cpu_online_mask, true);
++
++ per_cpu(sched_cpu_topo_end_mask, cpu) = topo;
++ printk(KERN_INFO "sched: cpu#%02d llc_id = %d, llc_mask idx = %d\n",
++ cpu, per_cpu(sd_llc_id, cpu),
++ (int) (per_cpu(sched_cpu_llc_mask, cpu) -
++ per_cpu(sched_cpu_topo_masks, cpu)));
++ }
++}
++#endif
++
++void __init sched_init_smp(void)
++{
++ /* Move init over to a non-isolated CPU */
++ if (set_cpus_allowed_ptr(current, housekeeping_cpumask(HK_TYPE_DOMAIN)) < 0)
++ BUG();
++ current->flags &= ~PF_NO_SETAFFINITY;
++
++ sched_init_topology_cpumask();
++
++ sched_smp_initialized = true;
++}
++
++static int __init migration_init(void)
++{
++ sched_cpu_starting(smp_processor_id());
++ return 0;
++}
++early_initcall(migration_init);
++
++#else
++void __init sched_init_smp(void)
++{
++ cpu_rq(0)->idle->time_slice = sysctl_sched_base_slice;
++}
++#endif /* CONFIG_SMP */
++
++int in_sched_functions(unsigned long addr)
++{
++ return in_lock_functions(addr) ||
++ (addr >= (unsigned long)__sched_text_start
++ && addr < (unsigned long)__sched_text_end);
++}
++
++#ifdef CONFIG_CGROUP_SCHED
++/*
++ * Default task group.
++ * Every task in system belongs to this group at bootup.
++ */
++struct task_group root_task_group;
++LIST_HEAD(task_groups);
++
++/* Cacheline aligned slab cache for task_group */
++static struct kmem_cache *task_group_cache __ro_after_init;
++#endif /* CONFIG_CGROUP_SCHED */
++
++void __init sched_init(void)
++{
++ int i;
++ struct rq *rq;
++#ifdef CONFIG_SCHED_SMT
++ struct balance_arg balance_arg = {.cpumask = sched_sg_idle_mask, .active = 0};
++#endif
++
++ printk(KERN_INFO "sched/alt: "ALT_SCHED_NAME" CPU Scheduler "ALT_SCHED_VERSION\
++ " by Alfred Chen.\n");
++
++ wait_bit_init();
++
++#ifdef CONFIG_SMP
++ for (i = 0; i < SCHED_QUEUE_BITS; i++)
++ cpumask_copy(sched_preempt_mask + i, cpu_present_mask);
++#endif
++
++#ifdef CONFIG_CGROUP_SCHED
++ task_group_cache = KMEM_CACHE(task_group, 0);
++
++ list_add(&root_task_group.list, &task_groups);
++ INIT_LIST_HEAD(&root_task_group.children);
++ INIT_LIST_HEAD(&root_task_group.siblings);
++#endif /* CONFIG_CGROUP_SCHED */
++ for_each_possible_cpu(i) {
++ rq = cpu_rq(i);
++
++ sched_queue_init(&rq->queue);
++ rq->prio = IDLE_TASK_SCHED_PRIO;
++#ifdef CONFIG_SCHED_PDS
++ rq->prio_idx = rq->prio;
++#endif
++
++ raw_spin_lock_init(&rq->lock);
++ rq->nr_running = rq->nr_uninterruptible = 0;
++ rq->calc_load_active = 0;
++ rq->calc_load_update = jiffies + LOAD_FREQ;
++#ifdef CONFIG_SMP
++ rq->online = false;
++ rq->cpu = i;
++
++#ifdef CONFIG_SCHED_SMT
++ rq->sg_balance_arg = balance_arg;
++#endif
++
++#ifdef CONFIG_NO_HZ_COMMON
++ INIT_CSD(&rq->nohz_csd, nohz_csd_func, rq);
++#endif
++ rq->balance_callback = &balance_push_callback;
++#ifdef CONFIG_HOTPLUG_CPU
++ rcuwait_init(&rq->hotplug_wait);
++#endif
++#endif /* CONFIG_SMP */
++ rq->nr_switches = 0;
++
++ hrtick_rq_init(rq);
++ atomic_set(&rq->nr_iowait, 0);
++
++ zalloc_cpumask_var_node(&rq->scratch_mask, GFP_KERNEL, cpu_to_node(i));
++ }
++#ifdef CONFIG_SMP
++ /* Set rq->online for cpu 0 */
++ cpu_rq(0)->online = true;
++#endif
++ /*
++ * The boot idle thread does lazy MMU switching as well:
++ */
++ mmgrab(&init_mm);
++ enter_lazy_tlb(&init_mm, current);
++
++ /*
++ * The idle task doesn't need the kthread struct to function, but it
++ * is dressed up as a per-CPU kthread and thus needs to play the part
++ * if we want to avoid special-casing it in code that deals with per-CPU
++ * kthreads.
++ */
++ WARN_ON(!set_kthread_struct(current));
++
++ /*
++ * Make us the idle thread. Technically, schedule() should not be
++ * called from this thread, however somewhere below it might be,
++ * but because we are the idle thread, we just pick up running again
++ * when this runqueue becomes "idle".
++ */
++ init_idle(current, smp_processor_id());
++
++ calc_load_update = jiffies + LOAD_FREQ;
++
++#ifdef CONFIG_SMP
++ idle_thread_set_boot_cpu();
++ balance_push_set(smp_processor_id(), false);
++
++ sched_init_topology_cpumask_early();
++#endif /* SMP */
++
++ preempt_dynamic_init();
++}
++
++#ifdef CONFIG_DEBUG_ATOMIC_SLEEP
++
++void __might_sleep(const char *file, int line)
++{
++ unsigned int state = get_current_state();
++ /*
++ * Blocking primitives will set (and therefore destroy) current->state,
++ * since we will exit with TASK_RUNNING make sure we enter with it,
++ * otherwise we will destroy state.
++ */
++ WARN_ONCE(state != TASK_RUNNING && current->task_state_change,
++ "do not call blocking ops when !TASK_RUNNING; "
++ "state=%x set at [<%p>] %pS\n", state,
++ (void *)current->task_state_change,
++ (void *)current->task_state_change);
++
++ __might_resched(file, line, 0);
++}
++EXPORT_SYMBOL(__might_sleep);
++
++static void print_preempt_disable_ip(int preempt_offset, unsigned long ip)
++{
++ if (!IS_ENABLED(CONFIG_DEBUG_PREEMPT))
++ return;
++
++ if (preempt_count() == preempt_offset)
++ return;
++
++ pr_err("Preemption disabled at:");
++ print_ip_sym(KERN_ERR, ip);
++}
++
++static inline bool resched_offsets_ok(unsigned int offsets)
++{
++ unsigned int nested = preempt_count();
++
++ nested += rcu_preempt_depth() << MIGHT_RESCHED_RCU_SHIFT;
++
++ return nested == offsets;
++}
++
++void __might_resched(const char *file, int line, unsigned int offsets)
++{
++ /* Ratelimiting timestamp: */
++ static unsigned long prev_jiffy;
++
++ unsigned long preempt_disable_ip;
++
++ /* WARN_ON_ONCE() by default, no rate limit required: */
++ rcu_sleep_check();
++
++ if ((resched_offsets_ok(offsets) && !irqs_disabled() &&
++ !is_idle_task(current) && !current->non_block_count) ||
++ system_state == SYSTEM_BOOTING || system_state > SYSTEM_RUNNING ||
++ oops_in_progress)
++ return;
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ /* Save this before calling printk(), since that will clobber it: */
++ preempt_disable_ip = get_preempt_disable_ip(current);
++
++ pr_err("BUG: sleeping function called from invalid context at %s:%d\n",
++ file, line);
++ pr_err("in_atomic(): %d, irqs_disabled(): %d, non_block: %d, pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(), current->non_block_count,
++ current->pid, current->comm);
++ pr_err("preempt_count: %x, expected: %x\n", preempt_count(),
++ offsets & MIGHT_RESCHED_PREEMPT_MASK);
++
++ if (IS_ENABLED(CONFIG_PREEMPT_RCU)) {
++ pr_err("RCU nest depth: %d, expected: %u\n",
++ rcu_preempt_depth(), offsets >> MIGHT_RESCHED_RCU_SHIFT);
++ }
++
++ if (task_stack_end_corrupted(current))
++ pr_emerg("Thread overran stack, or stack corrupted\n");
++
++ debug_show_held_locks(current);
++ if (irqs_disabled())
++ print_irqtrace_events(current);
++
++ print_preempt_disable_ip(offsets & MIGHT_RESCHED_PREEMPT_MASK,
++ preempt_disable_ip);
++
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL(__might_resched);
++
++void __cant_sleep(const char *file, int line, int preempt_offset)
++{
++ static unsigned long prev_jiffy;
++
++ if (irqs_disabled())
++ return;
++
++ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
++ return;
++
++ if (preempt_count() > preempt_offset)
++ return;
++
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ printk(KERN_ERR "BUG: assuming atomic context at %s:%d\n", file, line);
++ printk(KERN_ERR "in_atomic(): %d, irqs_disabled(): %d, pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(),
++ current->pid, current->comm);
++
++ debug_show_held_locks(current);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL_GPL(__cant_sleep);
++
++#ifdef CONFIG_SMP
++void __cant_migrate(const char *file, int line)
++{
++ static unsigned long prev_jiffy;
++
++ if (irqs_disabled())
++ return;
++
++ if (is_migration_disabled(current))
++ return;
++
++ if (!IS_ENABLED(CONFIG_PREEMPT_COUNT))
++ return;
++
++ if (preempt_count() > 0)
++ return;
++
++ if (current->migration_flags & MDF_FORCE_ENABLED)
++ return;
++
++ if (time_before(jiffies, prev_jiffy + HZ) && prev_jiffy)
++ return;
++ prev_jiffy = jiffies;
++
++ pr_err("BUG: assuming non migratable context at %s:%d\n", file, line);
++ pr_err("in_atomic(): %d, irqs_disabled(): %d, migration_disabled() %u pid: %d, name: %s\n",
++ in_atomic(), irqs_disabled(), is_migration_disabled(current),
++ current->pid, current->comm);
++
++ debug_show_held_locks(current);
++ dump_stack();
++ add_taint(TAINT_WARN, LOCKDEP_STILL_OK);
++}
++EXPORT_SYMBOL_GPL(__cant_migrate);
++#endif
++#endif
++
++#ifdef CONFIG_MAGIC_SYSRQ
++void normalize_rt_tasks(void)
++{
++ struct task_struct *g, *p;
++ struct sched_attr attr = {
++ .sched_policy = SCHED_NORMAL,
++ };
++
++ read_lock(&tasklist_lock);
++ for_each_process_thread(g, p) {
++ /*
++ * Only normalize user tasks:
++ */
++ if (p->flags & PF_KTHREAD)
++ continue;
++
++ schedstat_set(p->stats.wait_start, 0);
++ schedstat_set(p->stats.sleep_start, 0);
++ schedstat_set(p->stats.block_start, 0);
++
++ if (!rt_task(p)) {
++ /*
++ * Renice negative nice level userspace
++ * tasks back to 0:
++ */
++ if (task_nice(p) < 0)
++ set_user_nice(p, 0);
++ continue;
++ }
++
++ __sched_setscheduler(p, &attr, false, false);
++ }
++ read_unlock(&tasklist_lock);
++}
++#endif /* CONFIG_MAGIC_SYSRQ */
++
++#if defined(CONFIG_KGDB_KDB)
++/*
++ * These functions are only useful for kdb.
++ *
++ * They can only be called when the whole system has been
++ * stopped - every CPU needs to be quiescent, and no scheduling
++ * activity can take place. Using them for anything else would
++ * be a serious bug, and as a result, they aren't even visible
++ * under any other configuration.
++ */
++
++/**
++ * curr_task - return the current task for a given CPU.
++ * @cpu: the processor in question.
++ *
++ * ONLY VALID WHEN THE WHOLE SYSTEM IS STOPPED!
++ *
++ * Return: The current task for @cpu.
++ */
++struct task_struct *curr_task(int cpu)
++{
++ return cpu_curr(cpu);
++}
++
++#endif /* defined(CONFIG_KGDB_KDB) */
++
++#ifdef CONFIG_CGROUP_SCHED
++static void sched_free_group(struct task_group *tg)
++{
++ kmem_cache_free(task_group_cache, tg);
++}
++
++static void sched_free_group_rcu(struct rcu_head *rhp)
++{
++ sched_free_group(container_of(rhp, struct task_group, rcu));
++}
++
++static void sched_unregister_group(struct task_group *tg)
++{
++ /*
++ * We have to wait for yet another RCU grace period to expire, as
++ * print_cfs_stats() might run concurrently.
++ */
++ call_rcu(&tg->rcu, sched_free_group_rcu);
++}
++
++/* allocate runqueue etc for a new task group */
++struct task_group *sched_create_group(struct task_group *parent)
++{
++ struct task_group *tg;
++
++ tg = kmem_cache_alloc(task_group_cache, GFP_KERNEL | __GFP_ZERO);
++ if (!tg)
++ return ERR_PTR(-ENOMEM);
++
++ return tg;
++}
++
++void sched_online_group(struct task_group *tg, struct task_group *parent)
++{
++}
++
++/* rcu callback to free various structures associated with a task group */
++static void sched_unregister_group_rcu(struct rcu_head *rhp)
++{
++ /* Now it should be safe to free those cfs_rqs: */
++ sched_unregister_group(container_of(rhp, struct task_group, rcu));
++}
++
++void sched_destroy_group(struct task_group *tg)
++{
++ /* Wait for possible concurrent references to cfs_rqs complete: */
++ call_rcu(&tg->rcu, sched_unregister_group_rcu);
++}
++
++void sched_release_group(struct task_group *tg)
++{
++}
++
++static inline struct task_group *css_tg(struct cgroup_subsys_state *css)
++{
++ return css ? container_of(css, struct task_group, css) : NULL;
++}
++
++static struct cgroup_subsys_state *
++cpu_cgroup_css_alloc(struct cgroup_subsys_state *parent_css)
++{
++ struct task_group *parent = css_tg(parent_css);
++ struct task_group *tg;
++
++ if (!parent) {
++ /* This is early initialization for the top cgroup */
++ return &root_task_group.css;
++ }
++
++ tg = sched_create_group(parent);
++ if (IS_ERR(tg))
++ return ERR_PTR(-ENOMEM);
++ return &tg->css;
++}
++
++/* Expose task group only after completing cgroup initialization */
++static int cpu_cgroup_css_online(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++ struct task_group *parent = css_tg(css->parent);
++
++ if (parent)
++ sched_online_group(tg, parent);
++ return 0;
++}
++
++static void cpu_cgroup_css_released(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++
++ sched_release_group(tg);
++}
++
++static void cpu_cgroup_css_free(struct cgroup_subsys_state *css)
++{
++ struct task_group *tg = css_tg(css);
++
++ /*
++ * Relies on the RCU grace period between css_released() and this.
++ */
++ sched_unregister_group(tg);
++}
++
++#ifdef CONFIG_RT_GROUP_SCHED
++static int cpu_cgroup_can_attach(struct cgroup_taskset *tset)
++{
++ return 0;
++}
++#endif
++
++static void cpu_cgroup_attach(struct cgroup_taskset *tset)
++{
++}
++
++#ifdef CONFIG_FAIR_GROUP_SCHED
++static DEFINE_MUTEX(shares_mutex);
++
++static int sched_group_set_shares(struct task_group *tg, unsigned long shares)
++{
++ /*
++ * We can't change the weight of the root cgroup.
++ */
++ if (&root_task_group == tg)
++ return -EINVAL;
++
++ shares = clamp(shares, scale_load(MIN_SHARES), scale_load(MAX_SHARES));
++
++ mutex_lock(&shares_mutex);
++ if (tg->shares == shares)
++ goto done;
++
++ tg->shares = shares;
++done:
++ mutex_unlock(&shares_mutex);
++ return 0;
++}
++
++static int cpu_shares_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 shareval)
++{
++ if (shareval > scale_load_down(ULONG_MAX))
++ shareval = MAX_SHARES;
++ return sched_group_set_shares(css_tg(css), scale_load(shareval));
++}
++
++static u64 cpu_shares_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ struct task_group *tg = css_tg(css);
++
++ return (u64) scale_load_down(tg->shares);
++}
++#endif
++
++static s64 cpu_cfs_quota_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_quota_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, s64 cfs_quota_us)
++{
++ return 0;
++}
++
++static u64 cpu_cfs_period_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_period_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 cfs_period_us)
++{
++ return 0;
++}
++
++static u64 cpu_cfs_burst_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_cfs_burst_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 cfs_burst_us)
++{
++ return 0;
++}
++
++static int cpu_cfs_stat_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_cfs_local_stat_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_rt_runtime_write(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 val)
++{
++ return 0;
++}
++
++static s64 cpu_rt_runtime_read(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_rt_period_write_uint(struct cgroup_subsys_state *css,
++ struct cftype *cftype, u64 rt_period_us)
++{
++ return 0;
++}
++
++static u64 cpu_rt_period_read_uint(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_uclamp_min_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static int cpu_uclamp_max_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static ssize_t cpu_uclamp_min_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes,
++ loff_t off)
++{
++ return nbytes;
++}
++
++static ssize_t cpu_uclamp_max_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes,
++ loff_t off)
++{
++ return nbytes;
++}
++
++static struct cftype cpu_legacy_files[] = {
++#ifdef CONFIG_FAIR_GROUP_SCHED
++ {
++ .name = "shares",
++ .read_u64 = cpu_shares_read_u64,
++ .write_u64 = cpu_shares_write_u64,
++ },
++#endif
++ {
++ .name = "cfs_quota_us",
++ .read_s64 = cpu_cfs_quota_read_s64,
++ .write_s64 = cpu_cfs_quota_write_s64,
++ },
++ {
++ .name = "cfs_period_us",
++ .read_u64 = cpu_cfs_period_read_u64,
++ .write_u64 = cpu_cfs_period_write_u64,
++ },
++ {
++ .name = "cfs_burst_us",
++ .read_u64 = cpu_cfs_burst_read_u64,
++ .write_u64 = cpu_cfs_burst_write_u64,
++ },
++ {
++ .name = "stat",
++ .seq_show = cpu_cfs_stat_show,
++ },
++ {
++ .name = "stat.local",
++ .seq_show = cpu_cfs_local_stat_show,
++ },
++ {
++ .name = "rt_runtime_us",
++ .read_s64 = cpu_rt_runtime_read,
++ .write_s64 = cpu_rt_runtime_write,
++ },
++ {
++ .name = "rt_period_us",
++ .read_u64 = cpu_rt_period_read_uint,
++ .write_u64 = cpu_rt_period_write_uint,
++ },
++ {
++ .name = "uclamp.min",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_min_show,
++ .write = cpu_uclamp_min_write,
++ },
++ {
++ .name = "uclamp.max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_max_show,
++ .write = cpu_uclamp_max_write,
++ },
++ { } /* Terminate */
++};
++
++static u64 cpu_weight_read_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_weight_write_u64(struct cgroup_subsys_state *css,
++ struct cftype *cft, u64 weight)
++{
++ return 0;
++}
++
++static s64 cpu_weight_nice_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_weight_nice_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 nice)
++{
++ return 0;
++}
++
++static s64 cpu_idle_read_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft)
++{
++ return 0;
++}
++
++static int cpu_idle_write_s64(struct cgroup_subsys_state *css,
++ struct cftype *cft, s64 idle)
++{
++ return 0;
++}
++
++static int cpu_max_show(struct seq_file *sf, void *v)
++{
++ return 0;
++}
++
++static ssize_t cpu_max_write(struct kernfs_open_file *of,
++ char *buf, size_t nbytes, loff_t off)
++{
++ return nbytes;
++}
++
++static struct cftype cpu_files[] = {
++ {
++ .name = "weight",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_u64 = cpu_weight_read_u64,
++ .write_u64 = cpu_weight_write_u64,
++ },
++ {
++ .name = "weight.nice",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_s64 = cpu_weight_nice_read_s64,
++ .write_s64 = cpu_weight_nice_write_s64,
++ },
++ {
++ .name = "idle",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_s64 = cpu_idle_read_s64,
++ .write_s64 = cpu_idle_write_s64,
++ },
++ {
++ .name = "max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_max_show,
++ .write = cpu_max_write,
++ },
++ {
++ .name = "max.burst",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .read_u64 = cpu_cfs_burst_read_u64,
++ .write_u64 = cpu_cfs_burst_write_u64,
++ },
++ {
++ .name = "uclamp.min",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_min_show,
++ .write = cpu_uclamp_min_write,
++ },
++ {
++ .name = "uclamp.max",
++ .flags = CFTYPE_NOT_ON_ROOT,
++ .seq_show = cpu_uclamp_max_show,
++ .write = cpu_uclamp_max_write,
++ },
++ { } /* terminate */
++};
++
++static int cpu_extra_stat_show(struct seq_file *sf,
++ struct cgroup_subsys_state *css)
++{
++ return 0;
++}
++
++static int cpu_local_stat_show(struct seq_file *sf,
++ struct cgroup_subsys_state *css)
++{
++ return 0;
++}
++
++struct cgroup_subsys cpu_cgrp_subsys = {
++ .css_alloc = cpu_cgroup_css_alloc,
++ .css_online = cpu_cgroup_css_online,
++ .css_released = cpu_cgroup_css_released,
++ .css_free = cpu_cgroup_css_free,
++ .css_extra_stat_show = cpu_extra_stat_show,
++ .css_local_stat_show = cpu_local_stat_show,
++#ifdef CONFIG_RT_GROUP_SCHED
++ .can_attach = cpu_cgroup_can_attach,
++#endif
++ .attach = cpu_cgroup_attach,
++ .legacy_cftypes = cpu_legacy_files,
++ .dfl_cftypes = cpu_files,
++ .early_init = true,
++ .threaded = true,
++};
++#endif /* CONFIG_CGROUP_SCHED */
++
++#undef CREATE_TRACE_POINTS
++
++#ifdef CONFIG_SCHED_MM_CID
++
++#
++/*
++ * @cid_lock: Guarantee forward-progress of cid allocation.
++ *
++ * Concurrency ID allocation within a bitmap is mostly lock-free. The cid_lock
++ * is only used when contention is detected by the lock-free allocation so
++ * forward progress can be guaranteed.
++ */
++DEFINE_RAW_SPINLOCK(cid_lock);
++
++/*
++ * @use_cid_lock: Select cid allocation behavior: lock-free vs spinlock.
++ *
++ * When @use_cid_lock is 0, the cid allocation is lock-free. When contention is
++ * detected, it is set to 1 to ensure that all newly coming allocations are
++ * serialized by @cid_lock until the allocation which detected contention
++ * completes and sets @use_cid_lock back to 0. This guarantees forward progress
++ * of a cid allocation.
++ */
++int use_cid_lock;
++
++/*
++ * mm_cid remote-clear implements a lock-free algorithm to clear per-mm/cpu cid
++ * concurrently with respect to the execution of the source runqueue context
++ * switch.
++ *
++ * There is one basic properties we want to guarantee here:
++ *
++ * (1) Remote-clear should _never_ mark a per-cpu cid UNSET when it is actively
++ * used by a task. That would lead to concurrent allocation of the cid and
++ * userspace corruption.
++ *
++ * Provide this guarantee by introducing a Dekker memory ordering to guarantee
++ * that a pair of loads observe at least one of a pair of stores, which can be
++ * shown as:
++ *
++ * X = Y = 0
++ *
++ * w[X]=1 w[Y]=1
++ * MB MB
++ * r[Y]=y r[X]=x
++ *
++ * Which guarantees that x==0 && y==0 is impossible. But rather than using
++ * values 0 and 1, this algorithm cares about specific state transitions of the
++ * runqueue current task (as updated by the scheduler context switch), and the
++ * per-mm/cpu cid value.
++ *
++ * Let's introduce task (Y) which has task->mm == mm and task (N) which has
++ * task->mm != mm for the rest of the discussion. There are two scheduler state
++ * transitions on context switch we care about:
++ *
++ * (TSA) Store to rq->curr with transition from (N) to (Y)
++ *
++ * (TSB) Store to rq->curr with transition from (Y) to (N)
++ *
++ * On the remote-clear side, there is one transition we care about:
++ *
++ * (TMA) cmpxchg to *pcpu_cid to set the LAZY flag
++ *
++ * There is also a transition to UNSET state which can be performed from all
++ * sides (scheduler, remote-clear). It is always performed with a cmpxchg which
++ * guarantees that only a single thread will succeed:
++ *
++ * (TMB) cmpxchg to *pcpu_cid to mark UNSET
++ *
++ * Just to be clear, what we do _not_ want to happen is a transition to UNSET
++ * when a thread is actively using the cid (property (1)).
++ *
++ * Let's looks at the relevant combinations of TSA/TSB, and TMA transitions.
++ *
++ * Scenario A) (TSA)+(TMA) (from next task perspective)
++ *
++ * CPU0 CPU1
++ *
++ * Context switch CS-1 Remote-clear
++ * - store to rq->curr: (N)->(Y) (TSA) - cmpxchg to *pcpu_id to LAZY (TMA)
++ * (implied barrier after cmpxchg)
++ * - switch_mm_cid()
++ * - memory barrier (see switch_mm_cid()
++ * comment explaining how this barrier
++ * is combined with other scheduler
++ * barriers)
++ * - mm_cid_get (next)
++ * - READ_ONCE(*pcpu_cid) - rcu_dereference(src_rq->curr)
++ *
++ * This Dekker ensures that either task (Y) is observed by the
++ * rcu_dereference() or the LAZY flag is observed by READ_ONCE(), or both are
++ * observed.
++ *
++ * If task (Y) store is observed by rcu_dereference(), it means that there is
++ * still an active task on the cpu. Remote-clear will therefore not transition
++ * to UNSET, which fulfills property (1).
++ *
++ * If task (Y) is not observed, but the lazy flag is observed by READ_ONCE(),
++ * it will move its state to UNSET, which clears the percpu cid perhaps
++ * uselessly (which is not an issue for correctness). Because task (Y) is not
++ * observed, CPU1 can move ahead to set the state to UNSET. Because moving
++ * state to UNSET is done with a cmpxchg expecting that the old state has the
++ * LAZY flag set, only one thread will successfully UNSET.
++ *
++ * If both states (LAZY flag and task (Y)) are observed, the thread on CPU0
++ * will observe the LAZY flag and transition to UNSET (perhaps uselessly), and
++ * CPU1 will observe task (Y) and do nothing more, which is fine.
++ *
++ * What we are effectively preventing with this Dekker is a scenario where
++ * neither LAZY flag nor store (Y) are observed, which would fail property (1)
++ * because this would UNSET a cid which is actively used.
++ */
++
++void sched_mm_cid_migrate_from(struct task_struct *t)
++{
++ t->migrate_from_cpu = task_cpu(t);
++}
++
++static
++int __sched_mm_cid_migrate_from_fetch_cid(struct rq *src_rq,
++ struct task_struct *t,
++ struct mm_cid *src_pcpu_cid)
++{
++ struct mm_struct *mm = t->mm;
++ struct task_struct *src_task;
++ int src_cid, last_mm_cid;
++
++ if (!mm)
++ return -1;
++
++ last_mm_cid = t->last_mm_cid;
++ /*
++ * If the migrated task has no last cid, or if the current
++ * task on src rq uses the cid, it means the source cid does not need
++ * to be moved to the destination cpu.
++ */
++ if (last_mm_cid == -1)
++ return -1;
++ src_cid = READ_ONCE(src_pcpu_cid->cid);
++ if (!mm_cid_is_valid(src_cid) || last_mm_cid != src_cid)
++ return -1;
++
++ /*
++ * If we observe an active task using the mm on this rq, it means we
++ * are not the last task to be migrated from this cpu for this mm, so
++ * there is no need to move src_cid to the destination cpu.
++ */
++ rcu_read_lock();
++ src_task = rcu_dereference(src_rq->curr);
++ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
++ rcu_read_unlock();
++ t->last_mm_cid = -1;
++ return -1;
++ }
++ rcu_read_unlock();
++
++ return src_cid;
++}
++
++static
++int __sched_mm_cid_migrate_from_try_steal_cid(struct rq *src_rq,
++ struct task_struct *t,
++ struct mm_cid *src_pcpu_cid,
++ int src_cid)
++{
++ struct task_struct *src_task;
++ struct mm_struct *mm = t->mm;
++ int lazy_cid;
++
++ if (src_cid == -1)
++ return -1;
++
++ /*
++ * Attempt to clear the source cpu cid to move it to the destination
++ * cpu.
++ */
++ lazy_cid = mm_cid_set_lazy_put(src_cid);
++ if (!try_cmpxchg(&src_pcpu_cid->cid, &src_cid, lazy_cid))
++ return -1;
++
++ /*
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm matches the scheduler barrier in context_switch()
++ * between store to rq->curr and load of prev and next task's
++ * per-mm/cpu cid.
++ *
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm_cid_active matches the barrier in
++ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
++ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
++ * load of per-mm/cpu cid.
++ */
++
++ /*
++ * If we observe an active task using the mm on this rq after setting
++ * the lazy-put flag, this task will be responsible for transitioning
++ * from lazy-put flag set to MM_CID_UNSET.
++ */
++ scoped_guard (rcu) {
++ src_task = rcu_dereference(src_rq->curr);
++ if (READ_ONCE(src_task->mm_cid_active) && src_task->mm == mm) {
++ rcu_read_unlock();
++ /*
++ * We observed an active task for this mm, there is therefore
++ * no point in moving this cid to the destination cpu.
++ */
++ t->last_mm_cid = -1;
++ return -1;
++ }
++ }
++
++ /*
++ * The src_cid is unused, so it can be unset.
++ */
++ if (!try_cmpxchg(&src_pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
++ return -1;
++ return src_cid;
++}
++
++/*
++ * Migration to dst cpu. Called with dst_rq lock held.
++ * Interrupts are disabled, which keeps the window of cid ownership without the
++ * source rq lock held small.
++ */
++void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu)
++{
++ struct mm_cid *src_pcpu_cid, *dst_pcpu_cid;
++ struct mm_struct *mm = t->mm;
++ int src_cid, dst_cid;
++ struct rq *src_rq;
++
++ lockdep_assert_rq_held(dst_rq);
++
++ if (!mm)
++ return;
++ if (src_cpu == -1) {
++ t->last_mm_cid = -1;
++ return;
++ }
++ /*
++ * Move the src cid if the dst cid is unset. This keeps id
++ * allocation closest to 0 in cases where few threads migrate around
++ * many cpus.
++ *
++ * If destination cid is already set, we may have to just clear
++ * the src cid to ensure compactness in frequent migrations
++ * scenarios.
++ *
++ * It is not useful to clear the src cid when the number of threads is
++ * greater or equal to the number of allowed cpus, because user-space
++ * can expect that the number of allowed cids can reach the number of
++ * allowed cpus.
++ */
++ dst_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(dst_rq));
++ dst_cid = READ_ONCE(dst_pcpu_cid->cid);
++ if (!mm_cid_is_unset(dst_cid) &&
++ atomic_read(&mm->mm_users) >= t->nr_cpus_allowed)
++ return;
++ src_pcpu_cid = per_cpu_ptr(mm->pcpu_cid, src_cpu);
++ src_rq = cpu_rq(src_cpu);
++ src_cid = __sched_mm_cid_migrate_from_fetch_cid(src_rq, t, src_pcpu_cid);
++ if (src_cid == -1)
++ return;
++ src_cid = __sched_mm_cid_migrate_from_try_steal_cid(src_rq, t, src_pcpu_cid,
++ src_cid);
++ if (src_cid == -1)
++ return;
++ if (!mm_cid_is_unset(dst_cid)) {
++ __mm_cid_put(mm, src_cid);
++ return;
++ }
++ /* Move src_cid to dst cpu. */
++ mm_cid_snapshot_time(dst_rq, mm);
++ WRITE_ONCE(dst_pcpu_cid->cid, src_cid);
++}
++
++static void sched_mm_cid_remote_clear(struct mm_struct *mm, struct mm_cid *pcpu_cid,
++ int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct task_struct *t;
++ int cid, lazy_cid;
++
++ cid = READ_ONCE(pcpu_cid->cid);
++ if (!mm_cid_is_valid(cid))
++ return;
++
++ /*
++ * Clear the cpu cid if it is set to keep cid allocation compact. If
++ * there happens to be other tasks left on the source cpu using this
++ * mm, the next task using this mm will reallocate its cid on context
++ * switch.
++ */
++ lazy_cid = mm_cid_set_lazy_put(cid);
++ if (!try_cmpxchg(&pcpu_cid->cid, &cid, lazy_cid))
++ return;
++
++ /*
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm matches the scheduler barrier in context_switch()
++ * between store to rq->curr and load of prev and next task's
++ * per-mm/cpu cid.
++ *
++ * The implicit barrier after cmpxchg per-mm/cpu cid before loading
++ * rq->curr->mm_cid_active matches the barrier in
++ * sched_mm_cid_exit_signals(), sched_mm_cid_before_execve(), and
++ * sched_mm_cid_after_execve() between store to t->mm_cid_active and
++ * load of per-mm/cpu cid.
++ */
++
++ /*
++ * If we observe an active task using the mm on this rq after setting
++ * the lazy-put flag, that task will be responsible for transitioning
++ * from lazy-put flag set to MM_CID_UNSET.
++ */
++ scoped_guard (rcu) {
++ t = rcu_dereference(rq->curr);
++ if (READ_ONCE(t->mm_cid_active) && t->mm == mm)
++ return;
++ }
++
++ /*
++ * The cid is unused, so it can be unset.
++ * Disable interrupts to keep the window of cid ownership without rq
++ * lock small.
++ */
++ scoped_guard (irqsave) {
++ if (try_cmpxchg(&pcpu_cid->cid, &lazy_cid, MM_CID_UNSET))
++ __mm_cid_put(mm, cid);
++ }
++}
++
++static void sched_mm_cid_remote_clear_old(struct mm_struct *mm, int cpu)
++{
++ struct rq *rq = cpu_rq(cpu);
++ struct mm_cid *pcpu_cid;
++ struct task_struct *curr;
++ u64 rq_clock;
++
++ /*
++ * rq->clock load is racy on 32-bit but one spurious clear once in a
++ * while is irrelevant.
++ */
++ rq_clock = READ_ONCE(rq->clock);
++ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
++
++ /*
++ * In order to take care of infrequently scheduled tasks, bump the time
++ * snapshot associated with this cid if an active task using the mm is
++ * observed on this rq.
++ */
++ scoped_guard (rcu) {
++ curr = rcu_dereference(rq->curr);
++ if (READ_ONCE(curr->mm_cid_active) && curr->mm == mm) {
++ WRITE_ONCE(pcpu_cid->time, rq_clock);
++ return;
++ }
++ }
++
++ if (rq_clock < pcpu_cid->time + SCHED_MM_CID_PERIOD_NS)
++ return;
++ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
++}
++
++static void sched_mm_cid_remote_clear_weight(struct mm_struct *mm, int cpu,
++ int weight)
++{
++ struct mm_cid *pcpu_cid;
++ int cid;
++
++ pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu);
++ cid = READ_ONCE(pcpu_cid->cid);
++ if (!mm_cid_is_valid(cid) || cid < weight)
++ return;
++ sched_mm_cid_remote_clear(mm, pcpu_cid, cpu);
++}
++
++static void task_mm_cid_work(struct callback_head *work)
++{
++ unsigned long now = jiffies, old_scan, next_scan;
++ struct task_struct *t = current;
++ struct cpumask *cidmask;
++ struct mm_struct *mm;
++ int weight, cpu;
++
++ SCHED_WARN_ON(t != container_of(work, struct task_struct, cid_work));
++
++ work->next = work; /* Prevent double-add */
++ if (t->flags & PF_EXITING)
++ return;
++ mm = t->mm;
++ if (!mm)
++ return;
++ old_scan = READ_ONCE(mm->mm_cid_next_scan);
++ next_scan = now + msecs_to_jiffies(MM_CID_SCAN_DELAY);
++ if (!old_scan) {
++ unsigned long res;
++
++ res = cmpxchg(&mm->mm_cid_next_scan, old_scan, next_scan);
++ if (res != old_scan)
++ old_scan = res;
++ else
++ old_scan = next_scan;
++ }
++ if (time_before(now, old_scan))
++ return;
++ if (!try_cmpxchg(&mm->mm_cid_next_scan, &old_scan, next_scan))
++ return;
++ cidmask = mm_cidmask(mm);
++ /* Clear cids that were not recently used. */
++ for_each_possible_cpu(cpu)
++ sched_mm_cid_remote_clear_old(mm, cpu);
++ weight = cpumask_weight(cidmask);
++ /*
++ * Clear cids that are greater or equal to the cidmask weight to
++ * recompact it.
++ */
++ for_each_possible_cpu(cpu)
++ sched_mm_cid_remote_clear_weight(mm, cpu, weight);
++}
++
++void init_sched_mm_cid(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ int mm_users = 0;
++
++ if (mm) {
++ mm_users = atomic_read(&mm->mm_users);
++ if (mm_users == 1)
++ mm->mm_cid_next_scan = jiffies + msecs_to_jiffies(MM_CID_SCAN_DELAY);
++ }
++ t->cid_work.next = &t->cid_work; /* Protect against double add */
++ init_task_work(&t->cid_work, task_mm_cid_work);
++}
++
++void task_tick_mm_cid(struct rq *rq, struct task_struct *curr)
++{
++ struct callback_head *work = &curr->cid_work;
++ unsigned long now = jiffies;
++
++ if (!curr->mm || (curr->flags & (PF_EXITING | PF_KTHREAD)) ||
++ work->next != work)
++ return;
++ if (time_before(now, READ_ONCE(curr->mm->mm_cid_next_scan)))
++ return;
++ task_work_add(curr, work, TWA_RESUME);
++}
++
++void sched_mm_cid_exit_signals(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ guard(rq_lock_irqsave)(rq);
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 0);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ mm_cid_put(mm);
++ t->last_mm_cid = t->mm_cid = -1;
++}
++
++void sched_mm_cid_before_execve(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ guard(rq_lock_irqsave)(rq);
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 0);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ mm_cid_put(mm);
++ t->last_mm_cid = t->mm_cid = -1;
++}
++
++void sched_mm_cid_after_execve(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct rq *rq;
++
++ if (!mm)
++ return;
++
++ preempt_disable();
++ rq = this_rq();
++ scoped_guard (rq_lock_irqsave, rq) {
++ preempt_enable_no_resched(); /* holding spinlock */
++ WRITE_ONCE(t->mm_cid_active, 1);
++ /*
++ * Store t->mm_cid_active before loading per-mm/cpu cid.
++ * Matches barrier in sched_mm_cid_remote_clear_old().
++ */
++ smp_mb();
++ t->last_mm_cid = t->mm_cid = mm_cid_get(rq, mm);
++ }
++ rseq_set_notify_resume(t);
++}
++
++void sched_mm_cid_fork(struct task_struct *t)
++{
++ WARN_ON_ONCE(!t->mm || t->mm_cid != -1);
++ t->mm_cid_active = 1;
++}
++#endif
+diff --new-file -rup linux-6.10/kernel/sched/alt_debug.c linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_debug.c
+--- linux-6.10/kernel/sched/alt_debug.c 1970-01-01 01:00:00.000000000 +0100
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_debug.c 2024-07-15 16:47:37.000000000 +0200
+@@ -0,0 +1,32 @@
++/*
++ * kernel/sched/alt_debug.c
++ *
++ * Print the alt scheduler debugging details
++ *
++ * Author: Alfred Chen
++ * Date : 2020
++ */
++#include "sched.h"
++#include "linux/sched/debug.h"
++
++/*
++ * This allows printing both to /proc/sched_debug and
++ * to the console
++ */
++#define SEQ_printf(m, x...) \
++ do { \
++ if (m) \
++ seq_printf(m, x); \
++ else \
++ pr_cont(x); \
++ } while (0)
++
++void proc_sched_show_task(struct task_struct *p, struct pid_namespace *ns,
++ struct seq_file *m)
++{
++ SEQ_printf(m, "%s (%d, #threads: %d)\n", p->comm, task_pid_nr_ns(p, ns),
++ get_nr_threads(p));
++}
++
++void proc_sched_set_task(struct task_struct *p)
++{}
+diff --new-file -rup linux-6.10/kernel/sched/alt_sched.h linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_sched.h
+--- linux-6.10/kernel/sched/alt_sched.h 1970-01-01 01:00:00.000000000 +0100
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/alt_sched.h 2024-07-15 16:47:37.000000000 +0200
+@@ -0,0 +1,976 @@
++#ifndef ALT_SCHED_H
++#define ALT_SCHED_H
++
++#include <linux/context_tracking.h>
++#include <linux/profile.h>
++#include <linux/stop_machine.h>
++#include <linux/syscalls.h>
++#include <linux/tick.h>
++
++#include <trace/events/power.h>
++#include <trace/events/sched.h>
++
++#include "../workqueue_internal.h"
++
++#include "cpupri.h"
++
++#ifdef CONFIG_CGROUP_SCHED
++/* task group related information */
++struct task_group {
++ struct cgroup_subsys_state css;
++
++ struct rcu_head rcu;
++ struct list_head list;
++
++ struct task_group *parent;
++ struct list_head siblings;
++ struct list_head children;
++#ifdef CONFIG_FAIR_GROUP_SCHED
++ unsigned long shares;
++#endif
++};
++
++extern struct task_group *sched_create_group(struct task_group *parent);
++extern void sched_online_group(struct task_group *tg,
++ struct task_group *parent);
++extern void sched_destroy_group(struct task_group *tg);
++extern void sched_release_group(struct task_group *tg);
++#endif /* CONFIG_CGROUP_SCHED */
++
++#define MIN_SCHED_NORMAL_PRIO (32)
++/*
++ * levels: RT(0-24), reserved(25-31), NORMAL(32-63), cpu idle task(64)
++ *
++ * -- BMQ --
++ * NORMAL: (lower boost range 12, NICE_WIDTH 40, higher boost range 12) / 2
++ * -- PDS --
++ * NORMAL: SCHED_EDGE_DELTA + ((NICE_WIDTH 40) / 2)
++ */
++#define SCHED_LEVELS (64 + 1)
++
++#define IDLE_TASK_SCHED_PRIO (SCHED_LEVELS - 1)
++
++#ifdef CONFIG_SCHED_DEBUG
++# define SCHED_WARN_ON(x) WARN_ONCE(x, #x)
++extern void resched_latency_warn(int cpu, u64 latency);
++#else
++# define SCHED_WARN_ON(x) ({ (void)(x), 0; })
++static inline void resched_latency_warn(int cpu, u64 latency) {}
++#endif
++
++/*
++ * Increase resolution of nice-level calculations for 64-bit architectures.
++ * The extra resolution improves shares distribution and load balancing of
++ * low-weight task groups (eg. nice +19 on an autogroup), deeper taskgroup
++ * hierarchies, especially on larger systems. This is not a user-visible change
++ * and does not change the user-interface for setting shares/weights.
++ *
++ * We increase resolution only if we have enough bits to allow this increased
++ * resolution (i.e. 64-bit). The costs for increasing resolution when 32-bit
++ * are pretty high and the returns do not justify the increased costs.
++ *
++ * Really only required when CONFIG_FAIR_GROUP_SCHED=y is also set, but to
++ * increase coverage and consistency always enable it on 64-bit platforms.
++ */
++#ifdef CONFIG_64BIT
++# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT + SCHED_FIXEDPOINT_SHIFT)
++# define scale_load(w) ((w) << SCHED_FIXEDPOINT_SHIFT)
++# define scale_load_down(w) \
++({ \
++ unsigned long __w = (w); \
++ if (__w) \
++ __w = max(2UL, __w >> SCHED_FIXEDPOINT_SHIFT); \
++ __w; \
++})
++#else
++# define NICE_0_LOAD_SHIFT (SCHED_FIXEDPOINT_SHIFT)
++# define scale_load(w) (w)
++# define scale_load_down(w) (w)
++#endif
++
++#ifdef CONFIG_FAIR_GROUP_SCHED
++#define ROOT_TASK_GROUP_LOAD NICE_0_LOAD
++
++/*
++ * A weight of 0 or 1 can cause arithmetics problems.
++ * A weight of a cfs_rq is the sum of weights of which entities
++ * are queued on this cfs_rq, so a weight of a entity should not be
++ * too large, so as the shares value of a task group.
++ * (The default weight is 1024 - so there's no practical
++ * limitation from this.)
++ */
++#define MIN_SHARES (1UL << 1)
++#define MAX_SHARES (1UL << 18)
++#endif
++
++/*
++ * Tunables that become constants when CONFIG_SCHED_DEBUG is off:
++ */
++#ifdef CONFIG_SCHED_DEBUG
++# define const_debug __read_mostly
++#else
++# define const_debug const
++#endif
++
++/* task_struct::on_rq states: */
++#define TASK_ON_RQ_QUEUED 1
++#define TASK_ON_RQ_MIGRATING 2
++
++static inline int task_on_rq_queued(struct task_struct *p)
++{
++ return p->on_rq == TASK_ON_RQ_QUEUED;
++}
++
++static inline int task_on_rq_migrating(struct task_struct *p)
++{
++ return READ_ONCE(p->on_rq) == TASK_ON_RQ_MIGRATING;
++}
++
++/* Wake flags. The first three directly map to some SD flag value */
++#define WF_EXEC 0x02 /* Wakeup after exec; maps to SD_BALANCE_EXEC */
++#define WF_FORK 0x04 /* Wakeup after fork; maps to SD_BALANCE_FORK */
++#define WF_TTWU 0x08 /* Wakeup; maps to SD_BALANCE_WAKE */
++
++#define WF_SYNC 0x10 /* Waker goes to sleep after wakeup */
++#define WF_MIGRATED 0x20 /* Internal use, task got migrated */
++#define WF_CURRENT_CPU 0x40 /* Prefer to move the wakee to the current CPU. */
++
++#ifdef CONFIG_SMP
++static_assert(WF_EXEC == SD_BALANCE_EXEC);
++static_assert(WF_FORK == SD_BALANCE_FORK);
++static_assert(WF_TTWU == SD_BALANCE_WAKE);
++#endif
++
++#define SCHED_QUEUE_BITS (SCHED_LEVELS - 1)
++
++struct sched_queue {
++ DECLARE_BITMAP(bitmap, SCHED_QUEUE_BITS);
++ struct list_head heads[SCHED_LEVELS];
++};
++
++struct rq;
++struct cpuidle_state;
++
++struct balance_callback {
++ struct balance_callback *next;
++ void (*func)(struct rq *rq);
++};
++
++struct balance_arg {
++ struct task_struct *task;
++ int active;
++ cpumask_t *cpumask;
++};
++
++/*
++ * This is the main, per-CPU runqueue data structure.
++ * This data should only be modified by the local cpu.
++ */
++struct rq {
++ /* runqueue lock: */
++ raw_spinlock_t lock;
++
++ struct task_struct __rcu *curr;
++ struct task_struct *idle;
++ struct task_struct *stop;
++ struct mm_struct *prev_mm;
++
++ struct sched_queue queue ____cacheline_aligned;
++
++ int prio;
++#ifdef CONFIG_SCHED_PDS
++ int prio_idx;
++ u64 time_edge;
++#endif
++
++ /* switch count */
++ u64 nr_switches;
++
++ atomic_t nr_iowait;
++
++#ifdef CONFIG_SCHED_DEBUG
++ u64 last_seen_need_resched_ns;
++ int ticks_without_resched;
++#endif
++
++#ifdef CONFIG_MEMBARRIER
++ int membarrier_state;
++#endif
++
++#ifdef CONFIG_SMP
++ int cpu; /* cpu of this runqueue */
++ bool online;
++
++ unsigned int ttwu_pending;
++ unsigned char nohz_idle_balance;
++ unsigned char idle_balance;
++
++#ifdef CONFIG_HAVE_SCHED_AVG_IRQ
++ struct sched_avg avg_irq;
++#endif
++
++#ifdef CONFIG_SCHED_SMT
++ struct balance_arg sg_balance_arg ____cacheline_aligned;
++#endif
++ struct cpu_stop_work active_balance_work;
++
++ struct balance_callback *balance_callback;
++#ifdef CONFIG_HOTPLUG_CPU
++ struct rcuwait hotplug_wait;
++#endif
++ unsigned int nr_pinned;
++
++#endif /* CONFIG_SMP */
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++ u64 prev_irq_time;
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++#ifdef CONFIG_PARAVIRT
++ u64 prev_steal_time;
++#endif /* CONFIG_PARAVIRT */
++#ifdef CONFIG_PARAVIRT_TIME_ACCOUNTING
++ u64 prev_steal_time_rq;
++#endif /* CONFIG_PARAVIRT_TIME_ACCOUNTING */
++
++ /* For genenal cpu load util */
++ s32 load_history;
++ u64 load_block;
++ u64 load_stamp;
++
++ /* calc_load related fields */
++ unsigned long calc_load_update;
++ long calc_load_active;
++
++ /* Ensure that all clocks are in the same cache line */
++ u64 clock ____cacheline_aligned;
++ u64 clock_task;
++
++ unsigned int nr_running;
++ unsigned long nr_uninterruptible;
++
++#ifdef CONFIG_SCHED_HRTICK
++#ifdef CONFIG_SMP
++ call_single_data_t hrtick_csd;
++#endif
++ struct hrtimer hrtick_timer;
++ ktime_t hrtick_time;
++#endif
++
++#ifdef CONFIG_SCHEDSTATS
++
++ /* latency stats */
++ struct sched_info rq_sched_info;
++ unsigned long long rq_cpu_time;
++ /* could above be rq->cfs_rq.exec_clock + rq->rt_rq.rt_runtime ? */
++
++ /* sys_sched_yield() stats */
++ unsigned int yld_count;
++
++ /* schedule() stats */
++ unsigned int sched_switch;
++ unsigned int sched_count;
++ unsigned int sched_goidle;
++
++ /* try_to_wake_up() stats */
++ unsigned int ttwu_count;
++ unsigned int ttwu_local;
++#endif /* CONFIG_SCHEDSTATS */
++
++#ifdef CONFIG_CPU_IDLE
++ /* Must be inspected within a rcu lock section */
++ struct cpuidle_state *idle_state;
++#endif
++
++#ifdef CONFIG_NO_HZ_COMMON
++#ifdef CONFIG_SMP
++ call_single_data_t nohz_csd;
++#endif
++ atomic_t nohz_flags;
++#endif /* CONFIG_NO_HZ_COMMON */
++
++ /* Scratch cpumask to be temporarily used under rq_lock */
++ cpumask_var_t scratch_mask;
++};
++
++extern unsigned int sysctl_sched_base_slice;
++
++extern unsigned long rq_load_util(struct rq *rq, unsigned long max);
++
++extern unsigned long calc_load_update;
++extern atomic_long_t calc_load_tasks;
++
++extern void calc_global_load_tick(struct rq *this_rq);
++extern long calc_load_fold_active(struct rq *this_rq, long adjust);
++
++DECLARE_PER_CPU_SHARED_ALIGNED(struct rq, runqueues);
++#define cpu_rq(cpu) (&per_cpu(runqueues, (cpu)))
++#define this_rq() this_cpu_ptr(&runqueues)
++#define task_rq(p) cpu_rq(task_cpu(p))
++#define cpu_curr(cpu) (cpu_rq(cpu)->curr)
++#define raw_rq() raw_cpu_ptr(&runqueues)
++
++#ifdef CONFIG_SMP
++#if defined(CONFIG_SCHED_DEBUG) && defined(CONFIG_SYSCTL)
++void register_sched_domain_sysctl(void);
++void unregister_sched_domain_sysctl(void);
++#else
++static inline void register_sched_domain_sysctl(void)
++{
++}
++static inline void unregister_sched_domain_sysctl(void)
++{
++}
++#endif
++
++extern bool sched_smp_initialized;
++
++enum {
++#ifdef CONFIG_SCHED_SMT
++ SMT_LEVEL_SPACE_HOLDER,
++#endif
++ COREGROUP_LEVEL_SPACE_HOLDER,
++ CORE_LEVEL_SPACE_HOLDER,
++ OTHER_LEVEL_SPACE_HOLDER,
++ NR_CPU_AFFINITY_LEVELS
++};
++
++DECLARE_PER_CPU_ALIGNED(cpumask_t [NR_CPU_AFFINITY_LEVELS], sched_cpu_topo_masks);
++
++static inline int
++__best_mask_cpu(const cpumask_t *cpumask, const cpumask_t *mask)
++{
++ int cpu;
++
++ while ((cpu = cpumask_any_and(cpumask, mask)) >= nr_cpu_ids)
++ mask++;
++
++ return cpu;
++}
++
++static inline int best_mask_cpu(int cpu, const cpumask_t *mask)
++{
++ return __best_mask_cpu(mask, per_cpu(sched_cpu_topo_masks, cpu));
++}
++
++#endif
++
++#ifndef arch_scale_freq_tick
++static __always_inline
++void arch_scale_freq_tick(void)
++{
++}
++#endif
++
++#ifndef arch_scale_freq_capacity
++static __always_inline
++unsigned long arch_scale_freq_capacity(int cpu)
++{
++ return SCHED_CAPACITY_SCALE;
++}
++#endif
++
++static inline u64 __rq_clock_broken(struct rq *rq)
++{
++ return READ_ONCE(rq->clock);
++}
++
++static inline u64 rq_clock(struct rq *rq)
++{
++ /*
++ * Relax lockdep_assert_held() checking as in VRQ, call to
++ * sched_info_xxxx() may not held rq->lock
++ * lockdep_assert_held(&rq->lock);
++ */
++ return rq->clock;
++}
++
++static inline u64 rq_clock_task(struct rq *rq)
++{
++ /*
++ * Relax lockdep_assert_held() checking as in VRQ, call to
++ * sched_info_xxxx() may not held rq->lock
++ * lockdep_assert_held(&rq->lock);
++ */
++ return rq->clock_task;
++}
++
++/*
++ * {de,en}queue flags:
++ *
++ * DEQUEUE_SLEEP - task is no longer runnable
++ * ENQUEUE_WAKEUP - task just became runnable
++ *
++ */
++
++#define DEQUEUE_SLEEP 0x01
++
++#define ENQUEUE_WAKEUP 0x01
++
++
++/*
++ * Below are scheduler API which using in other kernel code
++ * It use the dummy rq_flags
++ * ToDo : BMQ need to support these APIs for compatibility with mainline
++ * scheduler code.
++ */
++struct rq_flags {
++ unsigned long flags;
++};
++
++struct rq *__task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(rq->lock);
++
++struct rq *task_rq_lock(struct task_struct *p, struct rq_flags *rf)
++ __acquires(p->pi_lock)
++ __acquires(rq->lock);
++
++static inline void __task_rq_unlock(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock(&rq->lock);
++}
++
++static inline void
++task_rq_unlock(struct rq *rq, struct task_struct *p, struct rq_flags *rf)
++ __releases(rq->lock)
++ __releases(p->pi_lock)
++{
++ raw_spin_unlock(&rq->lock);
++ raw_spin_unlock_irqrestore(&p->pi_lock, rf->flags);
++}
++
++static inline void
++rq_lock(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock(&rq->lock);
++}
++
++static inline void
++rq_unlock(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock(&rq->lock);
++}
++
++static inline void
++rq_lock_irq(struct rq *rq, struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ raw_spin_lock_irq(&rq->lock);
++}
++
++static inline void
++rq_unlock_irq(struct rq *rq, struct rq_flags *rf)
++ __releases(rq->lock)
++{
++ raw_spin_unlock_irq(&rq->lock);
++}
++
++static inline struct rq *
++this_rq_lock_irq(struct rq_flags *rf)
++ __acquires(rq->lock)
++{
++ struct rq *rq;
++
++ local_irq_disable();
++ rq = this_rq();
++ raw_spin_lock(&rq->lock);
++
++ return rq;
++}
++
++static inline raw_spinlock_t *__rq_lockp(struct rq *rq)
++{
++ return &rq->lock;
++}
++
++static inline raw_spinlock_t *rq_lockp(struct rq *rq)
++{
++ return __rq_lockp(rq);
++}
++
++static inline void lockdep_assert_rq_held(struct rq *rq)
++{
++ lockdep_assert_held(__rq_lockp(rq));
++}
++
++extern void raw_spin_rq_lock_nested(struct rq *rq, int subclass);
++extern void raw_spin_rq_unlock(struct rq *rq);
++
++static inline void raw_spin_rq_lock(struct rq *rq)
++{
++ raw_spin_rq_lock_nested(rq, 0);
++}
++
++static inline void raw_spin_rq_lock_irq(struct rq *rq)
++{
++ local_irq_disable();
++ raw_spin_rq_lock(rq);
++}
++
++static inline void raw_spin_rq_unlock_irq(struct rq *rq)
++{
++ raw_spin_rq_unlock(rq);
++ local_irq_enable();
++}
++
++static inline int task_current(struct rq *rq, struct task_struct *p)
++{
++ return rq->curr == p;
++}
++
++static inline bool task_on_cpu(struct task_struct *p)
++{
++ return p->on_cpu;
++}
++
++extern int task_running_nice(struct task_struct *p);
++
++extern struct static_key_false sched_schedstats;
++
++#ifdef CONFIG_CPU_IDLE
++static inline void idle_set_state(struct rq *rq,
++ struct cpuidle_state *idle_state)
++{
++ rq->idle_state = idle_state;
++}
++
++static inline struct cpuidle_state *idle_get_state(struct rq *rq)
++{
++ WARN_ON(!rcu_read_lock_held());
++ return rq->idle_state;
++}
++#else
++static inline void idle_set_state(struct rq *rq,
++ struct cpuidle_state *idle_state)
++{
++}
++
++static inline struct cpuidle_state *idle_get_state(struct rq *rq)
++{
++ return NULL;
++}
++#endif
++
++static inline int cpu_of(const struct rq *rq)
++{
++#ifdef CONFIG_SMP
++ return rq->cpu;
++#else
++ return 0;
++#endif
++}
++
++extern void resched_cpu(int cpu);
++
++#include "stats.h"
++
++#ifdef CONFIG_NO_HZ_COMMON
++#define NOHZ_BALANCE_KICK_BIT 0
++#define NOHZ_STATS_KICK_BIT 1
++
++#define NOHZ_BALANCE_KICK BIT(NOHZ_BALANCE_KICK_BIT)
++#define NOHZ_STATS_KICK BIT(NOHZ_STATS_KICK_BIT)
++
++#define NOHZ_KICK_MASK (NOHZ_BALANCE_KICK | NOHZ_STATS_KICK)
++
++#define nohz_flags(cpu) (&cpu_rq(cpu)->nohz_flags)
++
++/* TODO: needed?
++extern void nohz_balance_exit_idle(struct rq *rq);
++#else
++static inline void nohz_balance_exit_idle(struct rq *rq) { }
++*/
++#endif
++
++#ifdef CONFIG_IRQ_TIME_ACCOUNTING
++struct irqtime {
++ u64 total;
++ u64 tick_delta;
++ u64 irq_start_time;
++ struct u64_stats_sync sync;
++};
++
++DECLARE_PER_CPU(struct irqtime, cpu_irqtime);
++
++/*
++ * Returns the irqtime minus the softirq time computed by ksoftirqd.
++ * Otherwise ksoftirqd's sum_exec_runtime is substracted its own runtime
++ * and never move forward.
++ */
++static inline u64 irq_time_read(int cpu)
++{
++ struct irqtime *irqtime = &per_cpu(cpu_irqtime, cpu);
++ unsigned int seq;
++ u64 total;
++
++ do {
++ seq = __u64_stats_fetch_begin(&irqtime->sync);
++ total = irqtime->total;
++ } while (__u64_stats_fetch_retry(&irqtime->sync, seq));
++
++ return total;
++}
++#endif /* CONFIG_IRQ_TIME_ACCOUNTING */
++
++#ifdef CONFIG_CPU_FREQ
++DECLARE_PER_CPU(struct update_util_data __rcu *, cpufreq_update_util_data);
++#endif /* CONFIG_CPU_FREQ */
++
++#ifdef CONFIG_NO_HZ_FULL
++extern int __init sched_tick_offload_init(void);
++#else
++static inline int sched_tick_offload_init(void) { return 0; }
++#endif
++
++#ifdef arch_scale_freq_capacity
++#ifndef arch_scale_freq_invariant
++#define arch_scale_freq_invariant() (true)
++#endif
++#else /* arch_scale_freq_capacity */
++#define arch_scale_freq_invariant() (false)
++#endif
++
++#ifdef CONFIG_SMP
++unsigned long sugov_effective_cpu_perf(int cpu, unsigned long actual,
++ unsigned long min,
++ unsigned long max);
++#endif /* CONFIG_SMP */
++
++extern void schedule_idle(void);
++
++#define cap_scale(v, s) ((v)*(s) >> SCHED_CAPACITY_SHIFT)
++
++/*
++ * !! For sched_setattr_nocheck() (kernel) only !!
++ *
++ * This is actually gross. :(
++ *
++ * It is used to make schedutil kworker(s) higher priority than SCHED_DEADLINE
++ * tasks, but still be able to sleep. We need this on platforms that cannot
++ * atomically change clock frequency. Remove once fast switching will be
++ * available on such platforms.
++ *
++ * SUGOV stands for SchedUtil GOVernor.
++ */
++#define SCHED_FLAG_SUGOV 0x10000000
++
++#ifdef CONFIG_MEMBARRIER
++/*
++ * The scheduler provides memory barriers required by membarrier between:
++ * - prior user-space memory accesses and store to rq->membarrier_state,
++ * - store to rq->membarrier_state and following user-space memory accesses.
++ * In the same way it provides those guarantees around store to rq->curr.
++ */
++static inline void membarrier_switch_mm(struct rq *rq,
++ struct mm_struct *prev_mm,
++ struct mm_struct *next_mm)
++{
++ int membarrier_state;
++
++ if (prev_mm == next_mm)
++ return;
++
++ membarrier_state = atomic_read(&next_mm->membarrier_state);
++ if (READ_ONCE(rq->membarrier_state) == membarrier_state)
++ return;
++
++ WRITE_ONCE(rq->membarrier_state, membarrier_state);
++}
++#else
++static inline void membarrier_switch_mm(struct rq *rq,
++ struct mm_struct *prev_mm,
++ struct mm_struct *next_mm)
++{
++}
++#endif
++
++#ifdef CONFIG_NUMA
++extern int sched_numa_find_closest(const struct cpumask *cpus, int cpu);
++#else
++static inline int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
++{
++ return nr_cpu_ids;
++}
++#endif
++
++extern void swake_up_all_locked(struct swait_queue_head *q);
++extern void __prepare_to_swait(struct swait_queue_head *q, struct swait_queue *wait);
++
++extern int try_to_wake_up(struct task_struct *tsk, unsigned int state, int wake_flags);
++
++#ifdef CONFIG_PREEMPT_DYNAMIC
++extern int preempt_dynamic_mode;
++extern int sched_dynamic_mode(const char *str);
++extern void sched_dynamic_update(int mode);
++#endif
++
++static inline void nohz_run_idle_balance(int cpu) { }
++
++static inline
++unsigned long uclamp_rq_util_with(struct rq *rq, unsigned long util,
++ struct task_struct *p)
++{
++ return util;
++}
++
++static inline bool uclamp_rq_is_capped(struct rq *rq) { return false; }
++
++#ifdef CONFIG_SCHED_MM_CID
++
++#define SCHED_MM_CID_PERIOD_NS (100ULL * 1000000) /* 100ms */
++#define MM_CID_SCAN_DELAY 100 /* 100ms */
++
++extern raw_spinlock_t cid_lock;
++extern int use_cid_lock;
++
++extern void sched_mm_cid_migrate_from(struct task_struct *t);
++extern void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu);
++extern void task_tick_mm_cid(struct rq *rq, struct task_struct *curr);
++extern void init_sched_mm_cid(struct task_struct *t);
++
++static inline void __mm_cid_put(struct mm_struct *mm, int cid)
++{
++ if (cid < 0)
++ return;
++ cpumask_clear_cpu(cid, mm_cidmask(mm));
++}
++
++/*
++ * The per-mm/cpu cid can have the MM_CID_LAZY_PUT flag set or transition to
++ * the MM_CID_UNSET state without holding the rq lock, but the rq lock needs to
++ * be held to transition to other states.
++ *
++ * State transitions synchronized with cmpxchg or try_cmpxchg need to be
++ * consistent across cpus, which prevents use of this_cpu_cmpxchg.
++ */
++static inline void mm_cid_put_lazy(struct task_struct *t)
++{
++ struct mm_struct *mm = t->mm;
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ int cid;
++
++ lockdep_assert_irqs_disabled();
++ cid = __this_cpu_read(pcpu_cid->cid);
++ if (!mm_cid_is_lazy_put(cid) ||
++ !try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
++ return;
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++}
++
++static inline int mm_cid_pcpu_unset(struct mm_struct *mm)
++{
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ int cid, res;
++
++ lockdep_assert_irqs_disabled();
++ cid = __this_cpu_read(pcpu_cid->cid);
++ for (;;) {
++ if (mm_cid_is_unset(cid))
++ return MM_CID_UNSET;
++ /*
++ * Attempt transition from valid or lazy-put to unset.
++ */
++ res = cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, cid, MM_CID_UNSET);
++ if (res == cid)
++ break;
++ cid = res;
++ }
++ return cid;
++}
++
++static inline void mm_cid_put(struct mm_struct *mm)
++{
++ int cid;
++
++ lockdep_assert_irqs_disabled();
++ cid = mm_cid_pcpu_unset(mm);
++ if (cid == MM_CID_UNSET)
++ return;
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++}
++
++static inline int __mm_cid_try_get(struct mm_struct *mm)
++{
++ struct cpumask *cpumask;
++ int cid;
++
++ cpumask = mm_cidmask(mm);
++ /*
++ * Retry finding first zero bit if the mask is temporarily
++ * filled. This only happens during concurrent remote-clear
++ * which owns a cid without holding a rq lock.
++ */
++ for (;;) {
++ cid = cpumask_first_zero(cpumask);
++ if (cid < nr_cpu_ids)
++ break;
++ cpu_relax();
++ }
++ if (cpumask_test_and_set_cpu(cid, cpumask))
++ return -1;
++ return cid;
++}
++
++/*
++ * Save a snapshot of the current runqueue time of this cpu
++ * with the per-cpu cid value, allowing to estimate how recently it was used.
++ */
++static inline void mm_cid_snapshot_time(struct rq *rq, struct mm_struct *mm)
++{
++ struct mm_cid *pcpu_cid = per_cpu_ptr(mm->pcpu_cid, cpu_of(rq));
++
++ lockdep_assert_rq_held(rq);
++ WRITE_ONCE(pcpu_cid->time, rq->clock);
++}
++
++static inline int __mm_cid_get(struct rq *rq, struct mm_struct *mm)
++{
++ int cid;
++
++ /*
++ * All allocations (even those using the cid_lock) are lock-free. If
++ * use_cid_lock is set, hold the cid_lock to perform cid allocation to
++ * guarantee forward progress.
++ */
++ if (!READ_ONCE(use_cid_lock)) {
++ cid = __mm_cid_try_get(mm);
++ if (cid >= 0)
++ goto end;
++ raw_spin_lock(&cid_lock);
++ } else {
++ raw_spin_lock(&cid_lock);
++ cid = __mm_cid_try_get(mm);
++ if (cid >= 0)
++ goto unlock;
++ }
++
++ /*
++ * cid concurrently allocated. Retry while forcing following
++ * allocations to use the cid_lock to ensure forward progress.
++ */
++ WRITE_ONCE(use_cid_lock, 1);
++ /*
++ * Set use_cid_lock before allocation. Only care about program order
++ * because this is only required for forward progress.
++ */
++ barrier();
++ /*
++ * Retry until it succeeds. It is guaranteed to eventually succeed once
++ * all newcoming allocations observe the use_cid_lock flag set.
++ */
++ do {
++ cid = __mm_cid_try_get(mm);
++ cpu_relax();
++ } while (cid < 0);
++ /*
++ * Allocate before clearing use_cid_lock. Only care about
++ * program order because this is for forward progress.
++ */
++ barrier();
++ WRITE_ONCE(use_cid_lock, 0);
++unlock:
++ raw_spin_unlock(&cid_lock);
++end:
++ mm_cid_snapshot_time(rq, mm);
++ return cid;
++}
++
++static inline int mm_cid_get(struct rq *rq, struct mm_struct *mm)
++{
++ struct mm_cid __percpu *pcpu_cid = mm->pcpu_cid;
++ struct cpumask *cpumask;
++ int cid;
++
++ lockdep_assert_rq_held(rq);
++ cpumask = mm_cidmask(mm);
++ cid = __this_cpu_read(pcpu_cid->cid);
++ if (mm_cid_is_valid(cid)) {
++ mm_cid_snapshot_time(rq, mm);
++ return cid;
++ }
++ if (mm_cid_is_lazy_put(cid)) {
++ if (try_cmpxchg(&this_cpu_ptr(pcpu_cid)->cid, &cid, MM_CID_UNSET))
++ __mm_cid_put(mm, mm_cid_clear_lazy_put(cid));
++ }
++ cid = __mm_cid_get(rq, mm);
++ __this_cpu_write(pcpu_cid->cid, cid);
++ return cid;
++}
++
++static inline void switch_mm_cid(struct rq *rq,
++ struct task_struct *prev,
++ struct task_struct *next)
++{
++ /*
++ * Provide a memory barrier between rq->curr store and load of
++ * {prev,next}->mm->pcpu_cid[cpu] on rq->curr->mm transition.
++ *
++ * Should be adapted if context_switch() is modified.
++ */
++ if (!next->mm) { // to kernel
++ /*
++ * user -> kernel transition does not guarantee a barrier, but
++ * we can use the fact that it performs an atomic operation in
++ * mmgrab().
++ */
++ if (prev->mm) // from user
++ smp_mb__after_mmgrab();
++ /*
++ * kernel -> kernel transition does not change rq->curr->mm
++ * state. It stays NULL.
++ */
++ } else { // to user
++ /*
++ * kernel -> user transition does not provide a barrier
++ * between rq->curr store and load of {prev,next}->mm->pcpu_cid[cpu].
++ * Provide it here.
++ */
++ if (!prev->mm) // from kernel
++ smp_mb();
++ /*
++ * user -> user transition guarantees a memory barrier through
++ * switch_mm() when current->mm changes. If current->mm is
++ * unchanged, no barrier is needed.
++ */
++ }
++ if (prev->mm_cid_active) {
++ mm_cid_snapshot_time(rq, prev->mm);
++ mm_cid_put_lazy(prev);
++ prev->mm_cid = -1;
++ }
++ if (next->mm_cid_active)
++ next->last_mm_cid = next->mm_cid = mm_cid_get(rq, next->mm);
++}
++
++#else
++static inline void switch_mm_cid(struct rq *rq, struct task_struct *prev, struct task_struct *next) { }
++static inline void sched_mm_cid_migrate_from(struct task_struct *t) { }
++static inline void sched_mm_cid_migrate_to(struct rq *dst_rq, struct task_struct *t, int src_cpu) { }
++static inline void task_tick_mm_cid(struct rq *rq, struct task_struct *curr) { }
++static inline void init_sched_mm_cid(struct task_struct *t) { }
++#endif
++
++#ifdef CONFIG_SMP
++extern struct balance_callback balance_push_callback;
++
++static inline void
++__queue_balance_callback(struct rq *rq,
++ struct balance_callback *head)
++{
++ lockdep_assert_rq_held(rq);
++
++ /*
++ * Don't (re)queue an already queued item; nor queue anything when
++ * balance_push() is active, see the comment with
++ * balance_push_callback.
++ */
++ if (unlikely(head->next || rq->balance_callback == &balance_push_callback))
++ return;
++
++ head->next = rq->balance_callback;
++ rq->balance_callback = head;
++}
++#endif /* CONFIG_SMP */
++
++#endif /* ALT_SCHED_H */
+diff --new-file -rup linux-6.10/kernel/sched/bmq.h linux-prjc-linux-6.10.y-prjc/kernel/sched/bmq.h
+--- linux-6.10/kernel/sched/bmq.h 1970-01-01 01:00:00.000000000 +0100
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/bmq.h 2024-07-15 16:47:37.000000000 +0200
+@@ -0,0 +1,98 @@
++#define ALT_SCHED_NAME "BMQ"
++
++/*
++ * BMQ only routines
++ */
++static inline void boost_task(struct task_struct *p, int n)
++{
++ int limit;
++
++ switch (p->policy) {
++ case SCHED_NORMAL:
++ limit = -MAX_PRIORITY_ADJ;
++ break;
++ case SCHED_BATCH:
++ limit = 0;
++ break;
++ default:
++ return;
++ }
++
++ p->boost_prio = max(limit, p->boost_prio - n);
++}
++
++static inline void deboost_task(struct task_struct *p)
++{
++ if (p->boost_prio < MAX_PRIORITY_ADJ)
++ p->boost_prio++;
++}
++
++/*
++ * Common interfaces
++ */
++static inline void sched_timeslice_imp(const int timeslice_ms) {}
++
++/* This API is used in task_prio(), return value readed by human users */
++static inline int
++task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
++{
++ return p->prio + p->boost_prio - MIN_NORMAL_PRIO;
++}
++
++static inline int task_sched_prio(const struct task_struct *p)
++{
++ return (p->prio < MIN_NORMAL_PRIO)? (p->prio >> 2) :
++ MIN_SCHED_NORMAL_PRIO + (p->prio + p->boost_prio - MIN_NORMAL_PRIO) / 2;
++}
++
++#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
++ prio = task_sched_prio(p); \
++ idx = prio;
++
++static inline int sched_prio2idx(int prio, struct rq *rq)
++{
++ return prio;
++}
++
++static inline int sched_idx2prio(int idx, struct rq *rq)
++{
++ return idx;
++}
++
++static inline int sched_rq_prio_idx(struct rq *rq)
++{
++ return rq->prio;
++}
++
++inline int task_running_nice(struct task_struct *p)
++{
++ return (p->prio + p->boost_prio > DEFAULT_PRIO);
++}
++
++static inline void sched_update_rq_clock(struct rq *rq) {}
++
++static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
++{
++ deboost_task(p);
++}
++
++static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq) {}
++static void sched_task_fork(struct task_struct *p, struct rq *rq) {}
++
++static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
++{
++ p->boost_prio = MAX_PRIORITY_ADJ;
++}
++
++static inline void sched_task_ttwu(struct task_struct *p)
++{
++ s64 delta = this_rq()->clock_task > p->last_ran;
++
++ if (likely(delta > 0))
++ boost_task(p, delta >> 22);
++}
++
++static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq)
++{
++ boost_task(p, 1);
++}
+diff --new-file -rup linux-6.10/kernel/sched/build_policy.c linux-prjc-linux-6.10.y-prjc/kernel/sched/build_policy.c
+--- linux-6.10/kernel/sched/build_policy.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/build_policy.c 2024-07-15 16:47:37.000000000 +0200
+@@ -42,13 +42,19 @@
+
+ #include "idle.c"
+
++#ifndef CONFIG_SCHED_ALT
+ #include "rt.c"
++#endif
+
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ # include "cpudeadline.c"
++#endif
+ # include "pelt.c"
+ #endif
+
+ #include "cputime.c"
+-#include "deadline.c"
+
++#ifndef CONFIG_SCHED_ALT
++#include "deadline.c"
++#endif
+diff --new-file -rup linux-6.10/kernel/sched/build_utility.c linux-prjc-linux-6.10.y-prjc/kernel/sched/build_utility.c
+--- linux-6.10/kernel/sched/build_utility.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/build_utility.c 2024-07-15 16:47:37.000000000 +0200
+@@ -84,7 +84,9 @@
+
+ #ifdef CONFIG_SMP
+ # include "cpupri.c"
++#ifndef CONFIG_SCHED_ALT
+ # include "stop_task.c"
++#endif
+ # include "topology.c"
+ #endif
+
+diff --new-file -rup linux-6.10/kernel/sched/cpufreq_schedutil.c linux-prjc-linux-6.10.y-prjc/kernel/sched/cpufreq_schedutil.c
+--- linux-6.10/kernel/sched/cpufreq_schedutil.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/cpufreq_schedutil.c 2024-07-15 16:47:37.000000000 +0200
+@@ -197,12 +197,17 @@ unsigned long sugov_effective_cpu_perf(i
+
+ static void sugov_get_util(struct sugov_cpu *sg_cpu, unsigned long boost)
+ {
++#ifndef CONFIG_SCHED_ALT
+ unsigned long min, max, util = cpu_util_cfs_boost(sg_cpu->cpu);
+
+ util = effective_cpu_util(sg_cpu->cpu, util, &min, &max);
+ util = max(util, boost);
+ sg_cpu->bw_min = min;
+ sg_cpu->util = sugov_effective_cpu_perf(sg_cpu->cpu, util, min, max);
++#else /* CONFIG_SCHED_ALT */
++ sg_cpu->bw_min = 0;
++ sg_cpu->util = rq_load_util(cpu_rq(sg_cpu->cpu), arch_scale_cpu_capacity(sg_cpu->cpu));
++#endif /* CONFIG_SCHED_ALT */
+ }
+
+ /**
+@@ -343,8 +348,10 @@ static inline bool sugov_cpu_is_busy(str
+ */
+ static inline void ignore_dl_rate_limit(struct sugov_cpu *sg_cpu)
+ {
++#ifndef CONFIG_SCHED_ALT
+ if (cpu_bw_dl(cpu_rq(sg_cpu->cpu)) > sg_cpu->bw_min)
+ sg_cpu->sg_policy->limits_changed = true;
++#endif
+ }
+
+ static inline bool sugov_update_single_common(struct sugov_cpu *sg_cpu,
+@@ -676,6 +683,7 @@ static int sugov_kthread_create(struct s
+ }
+
+ ret = sched_setattr_nocheck(thread, &attr);
++
+ if (ret) {
+ kthread_stop(thread);
+ pr_warn("%s: failed to set SCHED_DEADLINE\n", __func__);
+diff --new-file -rup linux-6.10/kernel/sched/cputime.c linux-prjc-linux-6.10.y-prjc/kernel/sched/cputime.c
+--- linux-6.10/kernel/sched/cputime.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/cputime.c 2024-07-15 16:47:37.000000000 +0200
+@@ -126,7 +126,7 @@ void account_user_time(struct task_struc
+ p->utime += cputime;
+ account_group_user_time(p, cputime);
+
+- index = (task_nice(p) > 0) ? CPUTIME_NICE : CPUTIME_USER;
++ index = task_running_nice(p) ? CPUTIME_NICE : CPUTIME_USER;
+
+ /* Add user time to cpustat. */
+ task_group_account_field(p, index, cputime);
+@@ -150,7 +150,7 @@ void account_guest_time(struct task_stru
+ p->gtime += cputime;
+
+ /* Add guest time to cpustat. */
+- if (task_nice(p) > 0) {
++ if (task_running_nice(p)) {
+ task_group_account_field(p, CPUTIME_NICE, cputime);
+ cpustat[CPUTIME_GUEST_NICE] += cputime;
+ } else {
+@@ -288,7 +288,7 @@ static inline u64 account_other_time(u64
+ #ifdef CONFIG_64BIT
+ static inline u64 read_sum_exec_runtime(struct task_struct *t)
+ {
+- return t->se.sum_exec_runtime;
++ return tsk_seruntime(t);
+ }
+ #else
+ static u64 read_sum_exec_runtime(struct task_struct *t)
+@@ -298,7 +298,7 @@ static u64 read_sum_exec_runtime(struct
+ struct rq *rq;
+
+ rq = task_rq_lock(t, &rf);
+- ns = t->se.sum_exec_runtime;
++ ns = tsk_seruntime(t);
+ task_rq_unlock(rq, t, &rf);
+
+ return ns;
+@@ -617,7 +617,7 @@ out:
+ void task_cputime_adjusted(struct task_struct *p, u64 *ut, u64 *st)
+ {
+ struct task_cputime cputime = {
+- .sum_exec_runtime = p->se.sum_exec_runtime,
++ .sum_exec_runtime = tsk_seruntime(p),
+ };
+
+ if (task_cputime(p, &cputime.utime, &cputime.stime))
+diff --new-file -rup linux-6.10/kernel/sched/debug.c linux-prjc-linux-6.10.y-prjc/kernel/sched/debug.c
+--- linux-6.10/kernel/sched/debug.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/debug.c 2024-07-15 16:47:37.000000000 +0200
+@@ -7,6 +7,7 @@
+ * Copyright(C) 2007, Red Hat, Inc., Ingo Molnar
+ */
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * This allows printing both to /sys/kernel/debug/sched/debug and
+ * to the console
+@@ -215,6 +216,7 @@ static const struct file_operations sche
+ };
+
+ #endif /* SMP */
++#endif /* !CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_PREEMPT_DYNAMIC
+
+@@ -278,6 +280,7 @@ static const struct file_operations sche
+
+ #endif /* CONFIG_PREEMPT_DYNAMIC */
+
++#ifndef CONFIG_SCHED_ALT
+ __read_mostly bool sched_debug_verbose;
+
+ #ifdef CONFIG_SMP
+@@ -332,6 +335,7 @@ static const struct file_operations sche
+ .llseek = seq_lseek,
+ .release = seq_release,
+ };
++#endif /* !CONFIG_SCHED_ALT */
+
+ static struct dentry *debugfs_sched;
+
+@@ -341,14 +345,17 @@ static __init int sched_init_debug(void)
+
+ debugfs_sched = debugfs_create_dir("sched", NULL);
+
++#ifndef CONFIG_SCHED_ALT
+ debugfs_create_file("features", 0644, debugfs_sched, NULL, &sched_feat_fops);
+ debugfs_create_file_unsafe("verbose", 0644, debugfs_sched, &sched_debug_verbose, &sched_verbose_fops);
++#endif /* !CONFIG_SCHED_ALT */
+ #ifdef CONFIG_PREEMPT_DYNAMIC
+ debugfs_create_file("preempt", 0644, debugfs_sched, NULL, &sched_dynamic_fops);
+ #endif
+
+ debugfs_create_u32("base_slice_ns", 0644, debugfs_sched, &sysctl_sched_base_slice);
+
++#ifndef CONFIG_SCHED_ALT
+ debugfs_create_u32("latency_warn_ms", 0644, debugfs_sched, &sysctl_resched_latency_warn_ms);
+ debugfs_create_u32("latency_warn_once", 0644, debugfs_sched, &sysctl_resched_latency_warn_once);
+
+@@ -373,11 +380,13 @@ static __init int sched_init_debug(void)
+ #endif
+
+ debugfs_create_file("debug", 0444, debugfs_sched, NULL, &sched_debug_fops);
++#endif /* !CONFIG_SCHED_ALT */
+
+ return 0;
+ }
+ late_initcall(sched_init_debug);
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_SMP
+
+ static cpumask_var_t sd_sysctl_cpus;
+@@ -1111,6 +1120,7 @@ void proc_sched_set_task(struct task_str
+ memset(&p->stats, 0, sizeof(p->stats));
+ #endif
+ }
++#endif /* !CONFIG_SCHED_ALT */
+
+ void resched_latency_warn(int cpu, u64 latency)
+ {
+diff --new-file -rup linux-6.10/kernel/sched/idle.c linux-prjc-linux-6.10.y-prjc/kernel/sched/idle.c
+--- linux-6.10/kernel/sched/idle.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/idle.c 2024-07-15 16:47:37.000000000 +0200
+@@ -430,6 +430,7 @@ void cpu_startup_entry(enum cpuhp_state
+ do_idle();
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * idle-task scheduling class.
+ */
+@@ -551,3 +552,4 @@ DEFINE_SCHED_CLASS(idle) = {
+ .switched_to = switched_to_idle,
+ .update_curr = update_curr_idle,
+ };
++#endif
+diff --new-file -rup linux-6.10/kernel/sched/pds.h linux-prjc-linux-6.10.y-prjc/kernel/sched/pds.h
+--- linux-6.10/kernel/sched/pds.h 1970-01-01 01:00:00.000000000 +0100
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/pds.h 2024-07-15 16:47:37.000000000 +0200
+@@ -0,0 +1,134 @@
++#define ALT_SCHED_NAME "PDS"
++
++static const u64 RT_MASK = ((1ULL << MIN_SCHED_NORMAL_PRIO) - 1);
++
++#define SCHED_NORMAL_PRIO_NUM (32)
++#define SCHED_EDGE_DELTA (SCHED_NORMAL_PRIO_NUM - NICE_WIDTH / 2)
++
++/* PDS assume SCHED_NORMAL_PRIO_NUM is power of 2 */
++#define SCHED_NORMAL_PRIO_MOD(x) ((x) & (SCHED_NORMAL_PRIO_NUM - 1))
++
++/* default time slice 4ms -> shift 22, 2 time slice slots -> shift 23 */
++static __read_mostly int sched_timeslice_shift = 23;
++
++/*
++ * Common interfaces
++ */
++static inline int
++task_sched_prio_normal(const struct task_struct *p, const struct rq *rq)
++{
++ u64 sched_dl = max(p->deadline, rq->time_edge);
++
++#ifdef ALT_SCHED_DEBUG
++ if (WARN_ONCE(sched_dl - rq->time_edge > NORMAL_PRIO_NUM - 1,
++ "pds: task_sched_prio_normal() delta %lld\n", sched_dl - rq->time_edge))
++ return SCHED_NORMAL_PRIO_NUM - 1;
++#endif
++
++ return sched_dl - rq->time_edge;
++}
++
++static inline int task_sched_prio(const struct task_struct *p)
++{
++ return (p->prio < MIN_NORMAL_PRIO) ? (p->prio >> 2) :
++ MIN_SCHED_NORMAL_PRIO + task_sched_prio_normal(p, task_rq(p));
++}
++
++#define TASK_SCHED_PRIO_IDX(p, rq, idx, prio) \
++ if (p->prio < MIN_NORMAL_PRIO) { \
++ prio = p->prio >> 2; \
++ idx = prio; \
++ } else { \
++ u64 sched_dl = max(p->deadline, rq->time_edge); \
++ prio = MIN_SCHED_NORMAL_PRIO + sched_dl - rq->time_edge; \
++ idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_dl); \
++ }
++
++static inline int sched_prio2idx(int sched_prio, struct rq *rq)
++{
++ return (IDLE_TASK_SCHED_PRIO == sched_prio || sched_prio < MIN_SCHED_NORMAL_PRIO) ?
++ sched_prio :
++ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_prio + rq->time_edge);
++}
++
++static inline int sched_idx2prio(int sched_idx, struct rq *rq)
++{
++ return (sched_idx < MIN_SCHED_NORMAL_PRIO) ?
++ sched_idx :
++ MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(sched_idx - rq->time_edge);
++}
++
++static inline int sched_rq_prio_idx(struct rq *rq)
++{
++ return rq->prio_idx;
++}
++
++int task_running_nice(struct task_struct *p)
++{
++ return (p->prio > DEFAULT_PRIO);
++}
++
++static inline void sched_update_rq_clock(struct rq *rq)
++{
++ struct list_head head;
++ u64 old = rq->time_edge;
++ u64 now = rq->clock >> sched_timeslice_shift;
++ u64 prio, delta;
++ DECLARE_BITMAP(normal, SCHED_QUEUE_BITS);
++
++ if (now == old)
++ return;
++
++ rq->time_edge = now;
++ delta = min_t(u64, SCHED_NORMAL_PRIO_NUM, now - old);
++ INIT_LIST_HEAD(&head);
++
++ prio = MIN_SCHED_NORMAL_PRIO;
++ for_each_set_bit_from(prio, rq->queue.bitmap, MIN_SCHED_NORMAL_PRIO + delta)
++ list_splice_tail_init(rq->queue.heads + MIN_SCHED_NORMAL_PRIO +
++ SCHED_NORMAL_PRIO_MOD(prio + old), &head);
++
++ bitmap_shift_right(normal, rq->queue.bitmap, delta, SCHED_QUEUE_BITS);
++ if (!list_empty(&head)) {
++ u64 idx = MIN_SCHED_NORMAL_PRIO + SCHED_NORMAL_PRIO_MOD(now);
++
++ __list_splice(&head, rq->queue.heads + idx, rq->queue.heads[idx].next);
++ set_bit(MIN_SCHED_NORMAL_PRIO, normal);
++ }
++ bitmap_replace(rq->queue.bitmap, normal, rq->queue.bitmap,
++ (const unsigned long *)&RT_MASK, SCHED_QUEUE_BITS);
++
++ if (rq->prio < MIN_SCHED_NORMAL_PRIO || IDLE_TASK_SCHED_PRIO == rq->prio)
++ return;
++
++ rq->prio = max_t(u64, MIN_SCHED_NORMAL_PRIO, rq->prio - delta);
++ rq->prio_idx = sched_prio2idx(rq->prio, rq);
++}
++
++static inline void sched_task_renew(struct task_struct *p, const struct rq *rq)
++{
++ if (p->prio >= MIN_NORMAL_PRIO)
++ p->deadline = rq->time_edge + SCHED_EDGE_DELTA +
++ (p->static_prio - (MAX_PRIO - NICE_WIDTH)) / 2;
++}
++
++static inline void sched_task_sanity_check(struct task_struct *p, struct rq *rq)
++{
++ u64 max_dl = rq->time_edge + SCHED_EDGE_DELTA + NICE_WIDTH / 2 - 1;
++ if (unlikely(p->deadline > max_dl))
++ p->deadline = max_dl;
++}
++
++static void sched_task_fork(struct task_struct *p, struct rq *rq)
++{
++ sched_task_renew(p, rq);
++}
++
++static inline void do_sched_yield_type_1(struct task_struct *p, struct rq *rq)
++{
++ p->time_slice = sysctl_sched_base_slice;
++ sched_task_renew(p, rq);
++}
++
++static inline void sched_task_ttwu(struct task_struct *p) {}
++static inline void sched_task_deactivate(struct task_struct *p, struct rq *rq) {}
+diff --new-file -rup linux-6.10/kernel/sched/pelt.c linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.c
+--- linux-6.10/kernel/sched/pelt.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.c 2024-07-15 16:47:37.000000000 +0200
+@@ -266,6 +266,7 @@ ___update_load_avg(struct sched_avg *sa,
+ WRITE_ONCE(sa->util_avg, sa->util_sum / divider);
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ /*
+ * sched_entity:
+ *
+@@ -383,8 +384,9 @@ int update_dl_rq_load_avg(u64 now, struc
+
+ return 0;
+ }
++#endif
+
+-#ifdef CONFIG_SCHED_HW_PRESSURE
++#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
+ /*
+ * hardware:
+ *
+diff --new-file -rup linux-6.10/kernel/sched/pelt.h linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.h
+--- linux-6.10/kernel/sched/pelt.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/pelt.h 2024-07-15 16:47:37.000000000 +0200
+@@ -1,13 +1,15 @@
+ #ifdef CONFIG_SMP
+ #include "sched-pelt.h"
+
++#ifndef CONFIG_SCHED_ALT
+ int __update_load_avg_blocked_se(u64 now, struct sched_entity *se);
+ int __update_load_avg_se(u64 now, struct cfs_rq *cfs_rq, struct sched_entity *se);
+ int __update_load_avg_cfs_rq(u64 now, struct cfs_rq *cfs_rq);
+ int update_rt_rq_load_avg(u64 now, struct rq *rq, int running);
+ int update_dl_rq_load_avg(u64 now, struct rq *rq, int running);
++#endif
+
+-#ifdef CONFIG_SCHED_HW_PRESSURE
++#if defined(CONFIG_SCHED_HW_PRESSURE) && !defined(CONFIG_SCHED_ALT)
+ int update_hw_load_avg(u64 now, struct rq *rq, u64 capacity);
+
+ static inline u64 hw_load_avg(struct rq *rq)
+@@ -44,6 +46,7 @@ static inline u32 get_pelt_divider(struc
+ return PELT_MIN_DIVIDER + avg->period_contrib;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ static inline void cfs_se_util_change(struct sched_avg *avg)
+ {
+ unsigned int enqueued;
+@@ -180,9 +183,11 @@ static inline u64 cfs_rq_clock_pelt(stru
+ return rq_clock_pelt(rq_of(cfs_rq));
+ }
+ #endif
++#endif /* CONFIG_SCHED_ALT */
+
+ #else
+
++#ifndef CONFIG_SCHED_ALT
+ static inline int
+ update_cfs_rq_load_avg(u64 now, struct cfs_rq *cfs_rq)
+ {
+@@ -200,6 +205,7 @@ update_dl_rq_load_avg(u64 now, struct rq
+ {
+ return 0;
+ }
++#endif
+
+ static inline int
+ update_hw_load_avg(u64 now, struct rq *rq, u64 capacity)
+diff --new-file -rup linux-6.10/kernel/sched/sched.h linux-prjc-linux-6.10.y-prjc/kernel/sched/sched.h
+--- linux-6.10/kernel/sched/sched.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/sched.h 2024-07-15 16:47:37.000000000 +0200
+@@ -5,6 +5,10 @@
+ #ifndef _KERNEL_SCHED_SCHED_H
+ #define _KERNEL_SCHED_SCHED_H
+
++#ifdef CONFIG_SCHED_ALT
++#include "alt_sched.h"
++#else
++
+ #include <linux/sched/affinity.h>
+ #include <linux/sched/autogroup.h>
+ #include <linux/sched/cpufreq.h>
+@@ -3481,4 +3485,9 @@ static inline void init_sched_mm_cid(str
+ extern u64 avg_vruntime(struct cfs_rq *cfs_rq);
+ extern int entity_eligible(struct cfs_rq *cfs_rq, struct sched_entity *se);
+
++static inline int task_running_nice(struct task_struct *p)
++{
++ return (task_nice(p) > 0);
++}
++#endif /* !CONFIG_SCHED_ALT */
+ #endif /* _KERNEL_SCHED_SCHED_H */
+diff --new-file -rup linux-6.10/kernel/sched/stats.c linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.c
+--- linux-6.10/kernel/sched/stats.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.c 2024-07-15 16:47:37.000000000 +0200
+@@ -125,9 +125,11 @@ static int show_schedstat(struct seq_fil
+ } else {
+ struct rq *rq;
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ struct sched_domain *sd;
+ int dcount = 0;
+ #endif
++#endif
+ cpu = (unsigned long)(v - 2);
+ rq = cpu_rq(cpu);
+
+@@ -143,6 +145,7 @@ static int show_schedstat(struct seq_fil
+ seq_printf(seq, "\n");
+
+ #ifdef CONFIG_SMP
++#ifndef CONFIG_SCHED_ALT
+ /* domain-specific stats */
+ rcu_read_lock();
+ for_each_domain(cpu, sd) {
+@@ -171,6 +174,7 @@ static int show_schedstat(struct seq_fil
+ }
+ rcu_read_unlock();
+ #endif
++#endif
+ }
+ return 0;
+ }
+diff --new-file -rup linux-6.10/kernel/sched/stats.h linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.h
+--- linux-6.10/kernel/sched/stats.h 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/stats.h 2024-07-15 16:47:37.000000000 +0200
+@@ -89,6 +89,7 @@ static inline void rq_sched_info_depart
+
+ #endif /* CONFIG_SCHEDSTATS */
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_FAIR_GROUP_SCHED
+ struct sched_entity_stats {
+ struct sched_entity se;
+@@ -105,6 +106,7 @@ __schedstats_from_se(struct sched_entity
+ #endif
+ return &task_of(se)->stats;
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ #ifdef CONFIG_PSI
+ void psi_task_change(struct task_struct *task, int clear, int set);
+diff --new-file -rup linux-6.10/kernel/sched/topology.c linux-prjc-linux-6.10.y-prjc/kernel/sched/topology.c
+--- linux-6.10/kernel/sched/topology.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sched/topology.c 2024-07-15 16:47:37.000000000 +0200
+@@ -3,6 +3,7 @@
+ * Scheduler topology setup/handling methods
+ */
+
++#ifndef CONFIG_SCHED_ALT
+ #include <linux/bsearch.h>
+
+ DEFINE_MUTEX(sched_domains_mutex);
+@@ -1451,8 +1452,10 @@ static void asym_cpu_capacity_scan(void)
+ */
+
+ static int default_relax_domain_level = -1;
++#endif /* CONFIG_SCHED_ALT */
+ int sched_domain_level_max;
+
++#ifndef CONFIG_SCHED_ALT
+ static int __init setup_relax_domain_level(char *str)
+ {
+ if (kstrtoint(str, 0, &default_relax_domain_level))
+@@ -1687,6 +1690,7 @@ sd_init(struct sched_domain_topology_lev
+
+ return sd;
+ }
++#endif /* CONFIG_SCHED_ALT */
+
+ /*
+ * Topology list, bottom-up.
+@@ -1723,6 +1727,7 @@ void __init set_sched_topology(struct sc
+ sched_domain_topology_saved = NULL;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_NUMA
+
+ static const struct cpumask *sd_numa_mask(int cpu)
+@@ -2789,3 +2794,28 @@ void partition_sched_domains(int ndoms_n
+ partition_sched_domains_locked(ndoms_new, doms_new, dattr_new);
+ mutex_unlock(&sched_domains_mutex);
+ }
++#else /* CONFIG_SCHED_ALT */
++DEFINE_STATIC_KEY_FALSE(sched_asym_cpucapacity);
++
++void partition_sched_domains(int ndoms_new, cpumask_var_t doms_new[],
++ struct sched_domain_attr *dattr_new)
++{}
++
++#ifdef CONFIG_NUMA
++int sched_numa_find_closest(const struct cpumask *cpus, int cpu)
++{
++ return best_mask_cpu(cpu, cpus);
++}
++
++int sched_numa_find_nth_cpu(const struct cpumask *cpus, int cpu, int node)
++{
++ return cpumask_nth(cpu, cpus);
++}
++
++const struct cpumask *sched_numa_hop_mask(unsigned int node, unsigned int hops)
++{
++ return ERR_PTR(-EOPNOTSUPP);
++}
++EXPORT_SYMBOL_GPL(sched_numa_hop_mask);
++#endif /* CONFIG_NUMA */
++#endif
+diff --new-file -rup linux-6.10/kernel/sysctl.c linux-prjc-linux-6.10.y-prjc/kernel/sysctl.c
+--- linux-6.10/kernel/sysctl.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/sysctl.c 2024-07-15 16:47:37.000000000 +0200
+@@ -92,6 +92,10 @@ EXPORT_SYMBOL_GPL(sysctl_long_vals);
+
+ /* Constants used for minimum and maximum */
+
++#ifdef CONFIG_SCHED_ALT
++extern int sched_yield_type;
++#endif
++
+ #ifdef CONFIG_PERF_EVENTS
+ static const int six_hundred_forty_kb = 640 * 1024;
+ #endif
+@@ -1912,6 +1916,17 @@ static struct ctl_table kern_table[] = {
+ .proc_handler = proc_dointvec,
+ },
+ #endif
++#ifdef CONFIG_SCHED_ALT
++ {
++ .procname = "yield_type",
++ .data = &sched_yield_type,
++ .maxlen = sizeof (int),
++ .mode = 0644,
++ .proc_handler = &proc_dointvec_minmax,
++ .extra1 = SYSCTL_ZERO,
++ .extra2 = SYSCTL_TWO,
++ },
++#endif
+ #if defined(CONFIG_S390) && defined(CONFIG_SMP)
+ {
+ .procname = "spin_retry",
+diff --new-file -rup linux-6.10/kernel/time/hrtimer.c linux-prjc-linux-6.10.y-prjc/kernel/time/hrtimer.c
+--- linux-6.10/kernel/time/hrtimer.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/time/hrtimer.c 2024-07-15 16:47:37.000000000 +0200
+@@ -2074,8 +2074,10 @@ long hrtimer_nanosleep(ktime_t rqtp, con
+ int ret = 0;
+ u64 slack;
+
++#ifndef CONFIG_SCHED_ALT
+ slack = current->timer_slack_ns;
+- if (rt_task(current))
++ if (dl_task(current) || rt_task(current))
++#endif
+ slack = 0;
+
+ hrtimer_init_sleeper_on_stack(&t, clockid, mode);
+diff --new-file -rup linux-6.10/kernel/time/posix-cpu-timers.c linux-prjc-linux-6.10.y-prjc/kernel/time/posix-cpu-timers.c
+--- linux-6.10/kernel/time/posix-cpu-timers.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/time/posix-cpu-timers.c 2024-07-15 16:47:37.000000000 +0200
+@@ -223,7 +223,7 @@ static void task_sample_cputime(struct t
+ u64 stime, utime;
+
+ task_cputime(p, &utime, &stime);
+- store_samples(samples, stime, utime, p->se.sum_exec_runtime);
++ store_samples(samples, stime, utime, tsk_seruntime(p));
+ }
+
+ static void proc_sample_cputime_atomic(struct task_cputime_atomic *at,
+@@ -867,6 +867,7 @@ static void collect_posix_cputimers(stru
+ }
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ static inline void check_dl_overrun(struct task_struct *tsk)
+ {
+ if (tsk->dl.dl_overrun) {
+@@ -874,6 +875,7 @@ static inline void check_dl_overrun(stru
+ send_signal_locked(SIGXCPU, SEND_SIG_PRIV, tsk, PIDTYPE_TGID);
+ }
+ }
++#endif
+
+ static bool check_rlimit(u64 time, u64 limit, int signo, bool rt, bool hard)
+ {
+@@ -901,8 +903,10 @@ static void check_thread_timers(struct t
+ u64 samples[CPUCLOCK_MAX];
+ unsigned long soft;
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(tsk))
+ check_dl_overrun(tsk);
++#endif
+
+ if (expiry_cache_is_inactive(pct))
+ return;
+@@ -916,7 +920,7 @@ static void check_thread_timers(struct t
+ soft = task_rlimit(tsk, RLIMIT_RTTIME);
+ if (soft != RLIM_INFINITY) {
+ /* Task RT timeout is accounted in jiffies. RTTIME is usec */
+- unsigned long rttime = tsk->rt.timeout * (USEC_PER_SEC / HZ);
++ unsigned long rttime = tsk_rttimeout(tsk) * (USEC_PER_SEC / HZ);
+ unsigned long hard = task_rlimit_max(tsk, RLIMIT_RTTIME);
+
+ /* At the hard limit, send SIGKILL. No further action. */
+@@ -1152,8 +1156,10 @@ static inline bool fastpath_timer_check(
+ return true;
+ }
+
++#ifndef CONFIG_SCHED_ALT
+ if (dl_task(tsk) && tsk->dl.dl_overrun)
+ return true;
++#endif
+
+ return false;
+ }
+diff --new-file -rup linux-6.10/kernel/trace/trace_selftest.c linux-prjc-linux-6.10.y-prjc/kernel/trace/trace_selftest.c
+--- linux-6.10/kernel/trace/trace_selftest.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/trace/trace_selftest.c 2024-07-15 16:47:37.000000000 +0200
+@@ -1155,10 +1155,15 @@ static int trace_wakeup_test_thread(void
+ {
+ /* Make this a -deadline thread */
+ static const struct sched_attr attr = {
++#ifdef CONFIG_SCHED_ALT
++ /* No deadline on BMQ/PDS, use RR */
++ .sched_policy = SCHED_RR,
++#else
+ .sched_policy = SCHED_DEADLINE,
+ .sched_runtime = 100000ULL,
+ .sched_deadline = 10000000ULL,
+ .sched_period = 10000000ULL
++#endif
+ };
+ struct wakeup_test_data *x = data;
+
+diff --new-file -rup linux-6.10/kernel/workqueue.c linux-prjc-linux-6.10.y-prjc/kernel/workqueue.c
+--- linux-6.10/kernel/workqueue.c 2024-07-15 00:43:32.000000000 +0200
++++ linux-prjc-linux-6.10.y-prjc/kernel/workqueue.c 2024-07-15 16:47:37.000000000 +0200
+@@ -1248,6 +1248,7 @@ static bool kick_pool(struct worker_pool
+
+ p = worker->task;
+
++#ifndef CONFIG_SCHED_ALT
+ #ifdef CONFIG_SMP
+ /*
+ * Idle @worker is about to execute @work and waking up provides an
+@@ -1277,6 +1278,8 @@ static bool kick_pool(struct worker_pool
+ }
+ }
+ #endif
++#endif /* !CONFIG_SCHED_ALT */
++
+ wake_up_process(p);
+ return true;
+ }
+@@ -1405,7 +1408,11 @@ void wq_worker_running(struct task_struc
+ * CPU intensive auto-detection cares about how long a work item hogged
+ * CPU without sleeping. Reset the starting timestamp on wakeup.
+ */
++#ifdef CONFIG_SCHED_ALT
++ worker->current_at = worker->task->sched_time;
++#else
+ worker->current_at = worker->task->se.sum_exec_runtime;
++#endif
+
+ WRITE_ONCE(worker->sleeping, 0);
+ }
+@@ -1490,7 +1497,11 @@ void wq_worker_tick(struct task_struct *
+ * We probably want to make this prettier in the future.
+ */
+ if ((worker->flags & WORKER_NOT_RUNNING) || READ_ONCE(worker->sleeping) ||
++#ifdef CONFIG_SCHED_ALT
++ worker->task->sched_time - worker->current_at <
++#else
+ worker->task->se.sum_exec_runtime - worker->current_at <
++#endif
+ wq_cpu_intensive_thresh_us * NSEC_PER_USEC)
+ return;
+
+@@ -3176,7 +3187,11 @@ __acquires(&pool->lock)
+ worker->current_func = work->func;
+ worker->current_pwq = pwq;
+ if (worker->task)
++#ifdef CONFIG_SCHED_ALT
++ worker->current_at = worker->task->sched_time;
++#else
+ worker->current_at = worker->task->se.sum_exec_runtime;
++#endif
+ work_data = *work_data_bits(work);
+ worker->current_color = get_work_color(work_data);
+
diff --git a/5021_BMQ-and-PDS-gentoo-defaults.patch b/5021_BMQ-and-PDS-gentoo-defaults.patch
new file mode 100644
index 00000000..6dc48eec
--- /dev/null
+++ b/5021_BMQ-and-PDS-gentoo-defaults.patch
@@ -0,0 +1,13 @@
+--- a/init/Kconfig 2023-02-13 08:16:09.534315265 -0500
++++ b/init/Kconfig 2023-02-13 08:17:24.130237204 -0500
+@@ -867,8 +867,9 @@ config UCLAMP_BUCKETS_COUNT
+ If in doubt, use the default value.
+
+ menuconfig SCHED_ALT
++ depends on X86_64
+ bool "Alternative CPU Schedulers"
+- default y
++ default n
+ help
+ This feature enable alternative CPU scheduler"
+
^ permalink raw reply related [flat|nested] 37+ messages in thread
end of thread, other threads:[~2024-10-04 15:22 UTC | newest]
Thread overview: 37+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2024-08-15 13:19 [gentoo-commits] proj/linux-patches:6.10 commit in: / Mike Pagano
-- strict thread matches above, loose matches on Subject: below --
2024-10-04 15:22 Mike Pagano
2024-09-30 16:11 Mike Pagano
2024-09-30 16:03 Mike Pagano
2024-09-24 18:52 Mike Pagano
2024-09-18 18:01 Mike Pagano
2024-09-12 13:08 Mike Pagano
2024-09-12 12:30 Mike Pagano
2024-09-08 11:05 Mike Pagano
2024-09-07 18:10 Mike Pagano
2024-09-07 14:26 Mike Pagano
2024-09-07 14:23 Mike Pagano
2024-09-07 14:23 Mike Pagano
2024-09-05 13:58 Mike Pagano
2024-09-04 14:06 Mike Pagano
2024-09-04 13:51 Mike Pagano
2024-09-04 13:50 Mike Pagano
2024-09-04 13:50 Mike Pagano
2024-08-29 16:48 Mike Pagano
2024-08-19 10:23 Mike Pagano
2024-08-15 14:05 Mike Pagano
2024-08-14 15:18 Mike Pagano
2024-08-14 14:49 Mike Pagano
2024-08-14 14:08 Mike Pagano
2024-08-14 14:08 Mike Pagano
2024-08-11 13:27 Mike Pagano
2024-08-09 18:13 Mike Pagano
2024-08-03 15:55 Mike Pagano
2024-08-03 15:16 Mike Pagano
2024-07-27 22:16 Mike Pagano
2024-07-27 22:04 Mike Pagano
2024-07-27 13:45 Mike Pagano
2024-07-24 16:59 Mike Pagano
2024-07-24 16:44 Mike Pagano
2024-07-24 16:43 Mike Pagano
2024-07-19 22:35 Mike Pagano
2024-07-15 22:24 Mike Pagano
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox